diff --git a/lib/crewai/src/crewai/agent/core.py b/lib/crewai/src/crewai/agent/core.py index 02b286093..22b5a24ca 100644 --- a/lib/crewai/src/crewai/agent/core.py +++ b/lib/crewai/src/crewai/agent/core.py @@ -864,7 +864,11 @@ class Agent(BaseAgent): respect_context_window=self.respect_context_window, request_within_rpm_limit=rpm_limit_fn, callbacks=[TokenCalcHandler(self._token_process)], - response_model=task.response_model if task else None, + response_model=( + task.response_model or task.output_pydantic or task.output_json + ) + if task + else None, ) def _update_executor_parameters( @@ -893,7 +897,11 @@ class Agent(BaseAgent): self.agent_executor.stop = stop_words self.agent_executor.tools_names = get_tool_names(tools) self.agent_executor.tools_description = render_text_description_and_args(tools) - self.agent_executor.response_model = task.response_model if task else None + self.agent_executor.response_model = ( + (task.response_model or task.output_pydantic or task.output_json) + if task + else None + ) self.agent_executor.tools_handler = self.tools_handler self.agent_executor.request_within_rpm_limit = rpm_limit_fn @@ -1712,7 +1720,8 @@ class Agent(BaseAgent): existing_names = {sanitize_tool_name(t.name) for t in raw_tools} raw_tools.extend( - mt for mt in create_memory_tools(agent_memory) + mt + for mt in create_memory_tools(agent_memory) if sanitize_tool_name(mt.name) not in existing_names ) @@ -1937,14 +1946,15 @@ class Agent(BaseAgent): if isinstance(messages, str): input_str = messages else: - input_str = "\n".join( - str(msg.get("content", "")) for msg in messages if msg.get("content") - ) or "User request" - raw = ( - f"Input: {input_str}\n" - f"Agent: {self.role}\n" - f"Result: {output_text}" - ) + input_str = ( + "\n".join( + str(msg.get("content", "")) + for msg in messages + if msg.get("content") + ) + or "User request" + ) + raw = f"Input: {input_str}\nAgent: {self.role}\nResult: {output_text}" extracted = agent_memory.extract_memories(raw) if extracted: agent_memory.remember_many(extracted) diff --git a/lib/crewai/src/crewai/lite_agent.py b/lib/crewai/src/crewai/lite_agent.py index 7a7097bf2..5b7725a3b 100644 --- a/lib/crewai/src/crewai/lite_agent.py +++ b/lib/crewai/src/crewai/lite_agent.py @@ -2,10 +2,10 @@ from __future__ import annotations import asyncio from collections.abc import Callable -import time from functools import wraps import inspect import json +import time from types import MethodType from typing import ( TYPE_CHECKING, @@ -49,15 +49,20 @@ from crewai.events.types.agent_events import ( LiteAgentExecutionErrorEvent, LiteAgentExecutionStartedEvent, ) +from crewai.events.types.logging_events import AgentLogsExecutionEvent from crewai.events.types.memory_events import ( MemoryRetrievalCompletedEvent, MemoryRetrievalFailedEvent, MemoryRetrievalStartedEvent, ) -from crewai.events.types.logging_events import AgentLogsExecutionEvent from crewai.flow.flow_trackable import FlowTrackable from crewai.hooks.llm_hooks import get_after_llm_call_hooks, get_before_llm_call_hooks -from crewai.hooks.types import AfterLLMCallHookType, BeforeLLMCallHookType +from crewai.hooks.types import ( + AfterLLMCallHookCallable, + AfterLLMCallHookType, + BeforeLLMCallHookCallable, + BeforeLLMCallHookType, +) from crewai.lite_agent_output import LiteAgentOutput from crewai.llm import LLM from crewai.llms.base_llm import BaseLLM @@ -270,11 +275,11 @@ class LiteAgent(FlowTrackable, BaseModel): _guardrail: GuardrailCallable | None = PrivateAttr(default=None) _guardrail_retry_count: int = PrivateAttr(default=0) _callbacks: list[TokenCalcHandler] = PrivateAttr(default_factory=list) - _before_llm_call_hooks: list[BeforeLLMCallHookType] = PrivateAttr( - default_factory=get_before_llm_call_hooks + _before_llm_call_hooks: list[BeforeLLMCallHookType | BeforeLLMCallHookCallable] = ( + PrivateAttr(default_factory=get_before_llm_call_hooks) ) - _after_llm_call_hooks: list[AfterLLMCallHookType] = PrivateAttr( - default_factory=get_after_llm_call_hooks + _after_llm_call_hooks: list[AfterLLMCallHookType | AfterLLMCallHookCallable] = ( + PrivateAttr(default_factory=get_after_llm_call_hooks) ) _memory: Any = PrivateAttr(default=None) @@ -440,12 +445,16 @@ class LiteAgent(FlowTrackable, BaseModel): return self.role @property - def before_llm_call_hooks(self) -> list[BeforeLLMCallHookType]: + def before_llm_call_hooks( + self, + ) -> list[BeforeLLMCallHookType | BeforeLLMCallHookCallable]: """Get the before_llm_call hooks for this agent.""" return self._before_llm_call_hooks @property - def after_llm_call_hooks(self) -> list[AfterLLMCallHookType]: + def after_llm_call_hooks( + self, + ) -> list[AfterLLMCallHookType | AfterLLMCallHookCallable]: """Get the after_llm_call hooks for this agent.""" return self._after_llm_call_hooks @@ -482,11 +491,12 @@ class LiteAgent(FlowTrackable, BaseModel): # Inject memory tools once if memory is configured (mirrors Agent._prepare_kickoff) if self._memory is not None: from crewai.tools.memory_tools import create_memory_tools - from crewai.utilities.agent_utils import sanitize_tool_name + from crewai.utilities.string_utils import sanitize_tool_name existing_names = {sanitize_tool_name(t.name) for t in self._parsed_tools} memory_tools = [ - mt for mt in create_memory_tools(self._memory) + mt + for mt in create_memory_tools(self._memory) if sanitize_tool_name(mt.name) not in existing_names ] if memory_tools: @@ -565,9 +575,10 @@ class LiteAgent(FlowTrackable, BaseModel): if memory_block: formatted = self.i18n.slice("memory").format(memory=memory_block) if self._messages and self._messages[0].get("role") == "system": - self._messages[0]["content"] = ( - self._messages[0].get("content", "") + "\n\n" + formatted - ) + existing_content = self._messages[0].get("content", "") + if not isinstance(existing_content, str): + existing_content = "" + self._messages[0]["content"] = existing_content + "\n\n" + formatted crewai_event_bus.emit( self, event=MemoryRetrievalCompletedEvent( @@ -593,11 +604,7 @@ class LiteAgent(FlowTrackable, BaseModel): return input_str = self._get_last_user_content() or "User request" try: - raw = ( - f"Input: {input_str}\n" - f"Agent: {self.role}\n" - f"Result: {output_text}" - ) + raw = f"Input: {input_str}\nAgent: {self.role}\nResult: {output_text}" extracted = self._memory.extract_memories(raw) if extracted: self._memory.remember_many(extracted, agent_role=self.role) @@ -622,13 +629,20 @@ class LiteAgent(FlowTrackable, BaseModel): ) # Execute the agent using invoke loop - agent_finish = self._invoke_loop() + active_response_format = response_format or self.response_format + agent_finish = self._invoke_loop(response_model=active_response_format) if self._memory is not None: - self._save_to_memory(agent_finish.output) + output_text = ( + agent_finish.output.model_dump_json() + if isinstance(agent_finish.output, BaseModel) + else agent_finish.output + ) + self._save_to_memory(output_text) formatted_result: BaseModel | None = None - active_response_format = response_format or self.response_format - if active_response_format: + if isinstance(agent_finish.output, BaseModel): + formatted_result = agent_finish.output + elif active_response_format: try: model_schema = generate_model_description(active_response_format) schema = json.dumps(model_schema, indent=2) @@ -660,8 +674,13 @@ class LiteAgent(FlowTrackable, BaseModel): usage_metrics = self._token_process.get_summary() # Create output + raw_output = ( + agent_finish.output.model_dump_json() + if isinstance(agent_finish.output, BaseModel) + else agent_finish.output + ) output = LiteAgentOutput( - raw=agent_finish.output, + raw=raw_output, pydantic=formatted_result, agent_role=self.role, usage_metrics=usage_metrics.model_dump() if usage_metrics else None, @@ -838,10 +857,15 @@ class LiteAgent(FlowTrackable, BaseModel): return formatted_messages - def _invoke_loop(self) -> AgentFinish: + def _invoke_loop( + self, response_model: type[BaseModel] | None = None + ) -> AgentFinish: """ Run the agent's thought process until it reaches a conclusion or max iterations. + Args: + response_model: Optional Pydantic model for native structured output. + Returns: AgentFinish: The final result of the agent execution. """ @@ -870,12 +894,19 @@ class LiteAgent(FlowTrackable, BaseModel): printer=self._printer, from_agent=self, executor_context=self, + response_model=response_model, verbose=self.verbose, ) except Exception as e: raise e + if isinstance(answer, BaseModel): + formatted_answer = AgentFinish( + thought="", output=answer, text=answer.model_dump_json() + ) + break + formatted_answer = process_llm_response( cast(str, answer), self.use_stop_words ) @@ -901,7 +932,7 @@ class LiteAgent(FlowTrackable, BaseModel): ) self._append_message(formatted_answer.text, role="assistant") - except OutputParserError as e: # noqa: PERF203 + except OutputParserError as e: if self.verbose: self._printer.print( content="Failed to parse LLM output. Retrying...", diff --git a/lib/crewai/src/crewai/llms/providers/gemini/completion.py b/lib/crewai/src/crewai/llms/providers/gemini/completion.py index 14603b7d2..bd634c8dc 100644 --- a/lib/crewai/src/crewai/llms/providers/gemini/completion.py +++ b/lib/crewai/src/crewai/llms/providers/gemini/completion.py @@ -894,7 +894,7 @@ class GeminiCompletion(BaseLLM): content = self._extract_text_from_response(response) effective_response_model = None if self.tools else response_model - if not effective_response_model: + if not response_model: content = self._apply_stop_words(content) return self._finalize_completion_response( diff --git a/lib/crewai/src/crewai/task.py b/lib/crewai/src/crewai/task.py index 775e3c94d..cfcb01799 100644 --- a/lib/crewai/src/crewai/task.py +++ b/lib/crewai/src/crewai/task.py @@ -586,16 +586,29 @@ class Task(BaseModel): self._post_agent_execution(agent) - if not self._guardrails and not self._guardrail: + if isinstance(result, BaseModel): + raw = result.model_dump_json() + if self.output_pydantic: + pydantic_output = result + json_output = None + elif self.output_json: + pydantic_output = None + json_output = result.model_dump() + else: + pydantic_output = None + json_output = None + elif not self._guardrails and not self._guardrail: + raw = result pydantic_output, json_output = self._export_output(result) else: + raw = result pydantic_output, json_output = None, None task_output = TaskOutput( name=self.name or self.description, description=self.description, expected_output=self.expected_output, - raw=result, + raw=raw, pydantic=pydantic_output, json_dict=json_output, agent=agent.role, @@ -687,16 +700,29 @@ class Task(BaseModel): self._post_agent_execution(agent) - if not self._guardrails and not self._guardrail: + if isinstance(result, BaseModel): + raw = result.model_dump_json() + if self.output_pydantic: + pydantic_output = result + json_output = None + elif self.output_json: + pydantic_output = None + json_output = result.model_dump() + else: + pydantic_output = None + json_output = None + elif not self._guardrails and not self._guardrail: + raw = result pydantic_output, json_output = self._export_output(result) else: + raw = result pydantic_output, json_output = None, None task_output = TaskOutput( name=self.name or self.description, description=self.description, expected_output=self.expected_output, - raw=result, + raw=raw, pydantic=pydantic_output, json_dict=json_output, agent=agent.role, diff --git a/lib/crewai/tests/cassettes/llms/google/test_gemini_crew_structured_output_with_tools.yaml b/lib/crewai/tests/cassettes/llms/google/test_gemini_crew_structured_output_with_tools.yaml new file mode 100644 index 000000000..78f9bbe4e --- /dev/null +++ b/lib/crewai/tests/cassettes/llms/google/test_gemini_crew_structured_output_with_tools.yaml @@ -0,0 +1,197 @@ +interactions: +- request: + body: '{"contents": [{"parts": [{"text": "\nCurrent Task: Calculate 15 + 27 using + your add_numbers tool. Report the result.\n\nThis is the expected criteria for + your final answer: A structured calculation result\nyou MUST return the actual + complete content as the final answer, not a summary.\nFormat your final answer + according to the following OpenAPI schema: {\n \"properties\": {\n \"operation\": + {\n \"description\": \"The mathematical operation performed\",\n \"title\": + \"Operation\",\n \"type\": \"string\"\n },\n \"result\": {\n \"description\": + \"The result of the calculation\",\n \"title\": \"Result\",\n \"type\": + \"integer\"\n },\n \"explanation\": {\n \"description\": \"Brief + explanation of the calculation\",\n \"title\": \"Explanation\",\n \"type\": + \"string\"\n }\n },\n \"required\": [\n \"operation\",\n \"result\",\n \"explanation\"\n ],\n \"title\": + \"CalculationResult\",\n \"type\": \"object\",\n \"additionalProperties\": + false\n}\n\nIMPORTANT: Preserve the original content exactly as-is. Do NOT rewrite, + paraphrase, or modify the meaning of the content. Only structure it to match + the schema format.\n\nDo not include the OpenAPI schema in the final output. + Ensure the final output does not include any code block markers like ```json + or ```python."}], "role": "user"}], "systemInstruction": {"parts": [{"text": + "You are Calculator. You are a calculator assistant that uses tools to compute + results.\nYour personal goal is: Perform calculations using available tools"}], + "role": "user"}, "tools": [{"functionDeclarations": [{"description": "Add two + numbers together and return the sum.", "name": "add_numbers", "parameters_json_schema": + {"properties": {"a": {"title": "A", "type": "integer"}, "b": {"title": "B", + "type": "integer"}}, "required": ["a", "b"], "type": "object", "additionalProperties": + false}}, {"description": "Use this tool to provide your final structured response. + Call this tool when you have gathered all necessary information and are ready + to provide the final answer in the required format.", "name": "structured_output", + "parameters_json_schema": {"properties": {"operation": {"description": "The + mathematical operation performed", "title": "Operation", "type": "string"}, + "result": {"description": "The result of the calculation", "title": "Result", + "type": "integer"}, "explanation": {"description": "Brief explanation of the + calculation", "title": "Explanation", "type": "string"}}, "required": ["operation", + "result", "explanation"], "title": "CalculationResult", "type": "object", "additionalProperties": + false, "propertyOrdering": ["operation", "result", "explanation"]}}]}], "generationConfig": + {"stopSequences": ["\nObservation:"]}}' + headers: + User-Agent: + - X-USER-AGENT-XXX + accept: + - '*/*' + accept-encoding: + - ACCEPT-ENCODING-XXX + connection: + - keep-alive + content-length: + - '2763' + content-type: + - application/json + host: + - generativelanguage.googleapis.com + x-goog-api-client: + - google-genai-sdk/1.49.0 gl-python/3.13.12 + x-goog-api-key: + - X-GOOG-API-KEY-XXX + method: POST + uri: https://generativelanguage.googleapis.com/v1beta/models/gemini-2.0-flash-001:generateContent + response: + body: + string: "{\n \"candidates\": [\n {\n \"content\": {\n \"parts\": + [\n {\n \"functionCall\": {\n \"name\": \"add_numbers\",\n + \ \"args\": {\n \"a\": 15,\n \"b\": + 27\n }\n }\n }\n ],\n \"role\": + \"model\"\n },\n \"finishReason\": \"STOP\",\n \"avgLogprobs\": + 4.3579145442760951e-06\n }\n ],\n \"usageMetadata\": {\n \"promptTokenCount\": + 377,\n \"candidatesTokenCount\": 7,\n \"totalTokenCount\": 384,\n \"promptTokensDetails\": + [\n {\n \"modality\": \"TEXT\",\n \"tokenCount\": 377\n + \ }\n ],\n \"candidatesTokensDetails\": [\n {\n \"modality\": + \"TEXT\",\n \"tokenCount\": 7\n }\n ]\n },\n \"modelVersion\": + \"gemini-2.0-flash-001\",\n \"responseId\": \"vVefaYDSOouXjMcPicLCsQY\"\n}\n" + headers: + Alt-Svc: + - h3=":443"; ma=2592000,h3-29=":443"; ma=2592000 + Content-Type: + - application/json; charset=UTF-8 + Date: + - Wed, 25 Feb 2026 20:12:46 GMT + Server: + - scaffolding on HTTPServer2 + Server-Timing: + - gfet4t7; dur=718 + Transfer-Encoding: + - chunked + Vary: + - Origin + - X-Origin + - Referer + X-Content-Type-Options: + - X-CONTENT-TYPE-XXX + X-Frame-Options: + - X-FRAME-OPTIONS-XXX + X-XSS-Protection: + - '0' + status: + code: 200 + message: OK +- request: + body: '{"contents": [{"parts": [{"text": "\nCurrent Task: Calculate 15 + 27 using + your add_numbers tool. Report the result.\n\nThis is the expected criteria for + your final answer: A structured calculation result\nyou MUST return the actual + complete content as the final answer, not a summary.\nFormat your final answer + according to the following OpenAPI schema: {\n \"properties\": {\n \"operation\": + {\n \"description\": \"The mathematical operation performed\",\n \"title\": + \"Operation\",\n \"type\": \"string\"\n },\n \"result\": {\n \"description\": + \"The result of the calculation\",\n \"title\": \"Result\",\n \"type\": + \"integer\"\n },\n \"explanation\": {\n \"description\": \"Brief + explanation of the calculation\",\n \"title\": \"Explanation\",\n \"type\": + \"string\"\n }\n },\n \"required\": [\n \"operation\",\n \"result\",\n \"explanation\"\n ],\n \"title\": + \"CalculationResult\",\n \"type\": \"object\",\n \"additionalProperties\": + false\n}\n\nIMPORTANT: Preserve the original content exactly as-is. Do NOT rewrite, + paraphrase, or modify the meaning of the content. Only structure it to match + the schema format.\n\nDo not include the OpenAPI schema in the final output. + Ensure the final output does not include any code block markers like ```json + or ```python."}], "role": "user"}, {"parts": [{"functionCall": {"args": {"a": + 15, "b": 27}, "name": "add_numbers"}}], "role": "model"}, {"parts": [{"functionResponse": + {"name": "add_numbers", "response": {"result": 42}}}], "role": "user"}, {"parts": + [{"text": "Analyze the tool result. If requirements are met, provide the Final + Answer. Otherwise, call the next tool. Deliver only the answer without meta-commentary."}], + "role": "user"}], "systemInstruction": {"parts": [{"text": "You are Calculator. + You are a calculator assistant that uses tools to compute results.\nYour personal + goal is: Perform calculations using available tools"}], "role": "user"}, "tools": + [{"functionDeclarations": [{"description": "Add two numbers together and return + the sum.", "name": "add_numbers", "parameters_json_schema": {"properties": {"a": + {"title": "A", "type": "integer"}, "b": {"title": "B", "type": "integer"}}, + "required": ["a", "b"], "type": "object", "additionalProperties": false}}, {"description": + "Use this tool to provide your final structured response. Call this tool when + you have gathered all necessary information and are ready to provide the final + answer in the required format.", "name": "structured_output", "parameters_json_schema": + {"properties": {"operation": {"description": "The mathematical operation performed", + "title": "Operation", "type": "string"}, "result": {"description": "The result + of the calculation", "title": "Result", "type": "integer"}, "explanation": {"description": + "Brief explanation of the calculation", "title": "Explanation", "type": "string"}}, + "required": ["operation", "result", "explanation"], "title": "CalculationResult", + "type": "object", "additionalProperties": false, "propertyOrdering": ["operation", + "result", "explanation"]}}]}], "generationConfig": {"stopSequences": ["\nObservation:"]}}' + headers: + User-Agent: + - X-USER-AGENT-XXX + accept: + - '*/*' + accept-encoding: + - ACCEPT-ENCODING-XXX + connection: + - keep-alive + content-length: + - '3166' + content-type: + - application/json + host: + - generativelanguage.googleapis.com + x-goog-api-client: + - google-genai-sdk/1.49.0 gl-python/3.13.12 + x-goog-api-key: + - X-GOOG-API-KEY-XXX + method: POST + uri: https://generativelanguage.googleapis.com/v1beta/models/gemini-2.0-flash-001:generateContent + response: + body: + string: "{\n \"candidates\": [\n {\n \"content\": {\n \"parts\": + [\n {\n \"functionCall\": {\n \"name\": \"structured_output\",\n + \ \"args\": {\n \"result\": 42,\n \"explanation\": + \"15 + 27 = 42\",\n \"operation\": \"addition\"\n }\n + \ }\n }\n ],\n \"role\": \"model\"\n },\n + \ \"finishReason\": \"STOP\",\n \"avgLogprobs\": -0.07498827245500353\n + \ }\n ],\n \"usageMetadata\": {\n \"promptTokenCount\": 421,\n \"candidatesTokenCount\": + 18,\n \"totalTokenCount\": 439,\n \"promptTokensDetails\": [\n {\n + \ \"modality\": \"TEXT\",\n \"tokenCount\": 421\n }\n ],\n + \ \"candidatesTokensDetails\": [\n {\n \"modality\": \"TEXT\",\n + \ \"tokenCount\": 18\n }\n ]\n },\n \"modelVersion\": \"gemini-2.0-flash-001\",\n + \ \"responseId\": \"vlefac7bJb6TjMcPzYWh0Ag\"\n}\n" + headers: + Alt-Svc: + - h3=":443"; ma=2592000,h3-29=":443"; ma=2592000 + Content-Type: + - application/json; charset=UTF-8 + Date: + - Wed, 25 Feb 2026 20:12:47 GMT + Server: + - scaffolding on HTTPServer2 + Server-Timing: + - gfet4t7; dur=774 + Transfer-Encoding: + - chunked + Vary: + - Origin + - X-Origin + - Referer + X-Content-Type-Options: + - X-CONTENT-TYPE-XXX + X-Frame-Options: + - X-FRAME-OPTIONS-XXX + X-XSS-Protection: + - '0' + status: + code: 200 + message: OK +version: 1 diff --git a/lib/crewai/tests/cassettes/test_crew_testing_function.yaml b/lib/crewai/tests/cassettes/test_crew_testing_function.yaml index 5aff851cb..74ff9f0b9 100644 --- a/lib/crewai/tests/cassettes/test_crew_testing_function.yaml +++ b/lib/crewai/tests/cassettes/test_crew_testing_function.yaml @@ -1,735 +1,768 @@ interactions: - request: - body: '{"trace_id": "b2bfe230-4539-4522-a372-ab58b85f4ce1", "execution_type": "crew", "user_identifier": null, "execution_context": {"crew_fingerprint": null, "crew_name": "crew", "flow_name": null, "crewai_version": "1.0.0", "privacy_level": "standard"}, "execution_metadata": {"expected_duration_estimate": 300, "agent_count": 0, "task_count": 0, "flow_method_count": 0, "execution_started_at": "2025-10-21T14:21:07.172904+00:00"}, "ephemeral_trace_id": "b2bfe230-4539-4522-a372-ab58b85f4ce1"}' + body: '{"messages":[{"role":"system","content":"You are Researcher. You''re an + expert researcher, specialized in technology, software engineering, AI and startups. + You work as a freelancer and is now working on doing research and analysis for + a new customer.\nYour personal goal is: Make the best research and analysis + on content about AI and AI agents"},{"role":"user","content":"\nCurrent Task: + Come up with a list of 5 interesting ideas to explore for an article, then write + one amazing paragraph highlight for each idea that showcases how good an article + about this topic could be. Return the list of ideas with their paragraph and + your notes.\n\nThis is the expected criteria for your final answer: 5 bullet + points with a paragraph for each idea.\nyou MUST return the actual complete + content as the final answer, not a summary.\n\nProvide your complete response:"}],"model":"gpt-4.1-mini"}' headers: - Accept: - - '*/*' - Accept-Encoding: - - gzip, deflate, zstd - Connection: - - keep-alive - Content-Length: - - '488' - Content-Type: - - application/json User-Agent: - - CrewAI-CLI/1.0.0 - X-Crewai-Version: - - 1.0.0 - method: POST - uri: https://app.crewai.com/crewai_plus/api/v1/tracing/ephemeral/batches - response: - body: - string: '{"id":"9da97d5c-cb85-4950-8c08-3a33f4e87265","ephemeral_trace_id":"b2bfe230-4539-4522-a372-ab58b85f4ce1","execution_type":"crew","crew_name":"crew","flow_name":null,"status":"running","duration_ms":null,"crewai_version":"1.0.0","total_events":0,"execution_context":{"crew_fingerprint":null,"crew_name":"crew","flow_name":null,"crewai_version":"1.0.0","privacy_level":"standard"},"created_at":"2025-10-21T14:21:09.013Z","updated_at":"2025-10-21T14:21:09.013Z","access_code":"TRACE-4feb6c2ae8","user_identifier":null}' - headers: - Connection: - - keep-alive - Content-Length: - - '515' - Content-Type: - - application/json; charset=utf-8 - Date: - - Tue, 21 Oct 2025 14:21:09 GMT - cache-control: - - no-store - content-security-policy: - - 'default-src ''self'' *.app.crewai.com app.crewai.com; script-src ''self'' ''unsafe-inline'' *.app.crewai.com app.crewai.com https://cdn.jsdelivr.net/npm/apexcharts https://www.gstatic.com https://run.pstmn.io https://apis.google.com https://apis.google.com/js/api.js https://accounts.google.com https://accounts.google.com/gsi/client https://cdnjs.cloudflare.com/ajax/libs/normalize/8.0.1/normalize.min.css.map https://*.google.com https://docs.google.com https://slides.google.com https://js.hs-scripts.com https://js.sentry-cdn.com https://browser.sentry-cdn.com https://www.googletagmanager.com https://js-na1.hs-scripts.com https://js.hubspot.com http://js-na1.hs-scripts.com https://bat.bing.com https://cdn.amplitude.com https://cdn.segment.com https://d1d3n03t5zntha.cloudfront.net/ https://descriptusercontent.com https://edge.fullstory.com https://googleads.g.doubleclick.net https://js.hs-analytics.net https://js.hs-banner.com https://js.hsadspixel.net https://js.hscollectedforms.net - https://js.usemessages.com https://snap.licdn.com https://static.cloudflareinsights.com https://static.reo.dev https://www.google-analytics.com https://share.descript.com/; style-src ''self'' ''unsafe-inline'' *.app.crewai.com app.crewai.com https://cdn.jsdelivr.net/npm/apexcharts; img-src ''self'' data: *.app.crewai.com app.crewai.com https://zeus.tools.crewai.com https://dashboard.tools.crewai.com https://cdn.jsdelivr.net https://forms.hsforms.com https://track.hubspot.com https://px.ads.linkedin.com https://px4.ads.linkedin.com https://www.google.com https://www.google.com.br; font-src ''self'' data: *.app.crewai.com app.crewai.com; connect-src ''self'' *.app.crewai.com app.crewai.com https://zeus.tools.crewai.com https://connect.useparagon.com/ https://zeus.useparagon.com/* https://*.useparagon.com/* https://run.pstmn.io https://connect.tools.crewai.com/ https://*.sentry.io https://www.google-analytics.com https://edge.fullstory.com https://rs.fullstory.com https://api.hubspot.com - https://forms.hscollectedforms.net https://api.hubapi.com https://px.ads.linkedin.com https://px4.ads.linkedin.com https://google.com/pagead/form-data/16713662509 https://google.com/ccm/form-data/16713662509 https://www.google.com/ccm/collect https://worker-actionkit.tools.crewai.com https://api.reo.dev; frame-src ''self'' *.app.crewai.com app.crewai.com https://connect.useparagon.com/ https://zeus.tools.crewai.com https://zeus.useparagon.com/* https://connect.tools.crewai.com/ https://docs.google.com https://drive.google.com https://slides.google.com https://accounts.google.com https://*.google.com https://app.hubspot.com/ https://td.doubleclick.net https://www.googletagmanager.com/ https://www.youtube.com https://share.descript.com' - etag: - - W/"df138e6daf98e0258258ca1415a9037a" - expires: - - '0' - permissions-policy: - - camera=(), microphone=(self), geolocation=() - pragma: - - no-cache - referrer-policy: - - strict-origin-when-cross-origin - strict-transport-security: - - max-age=63072000; includeSubDomains - vary: - - Accept - x-content-type-options: - - nosniff - x-frame-options: - - SAMEORIGIN - x-permitted-cross-domain-policies: - - none - x-request-id: - - fc4913e1-332f-4747-a028-d42998def4f6 - x-runtime: - - '0.557821' - x-xss-protection: - - 1; mode=block - status: - code: 201 - message: Created -- request: - body: '{"messages": [{"role": "system", "content": "You are Researcher. You''re an expert researcher, specialized in technology, software engineering, AI and startups. You work as a freelancer and is now working on doing research and analysis for a new customer.\nYour personal goal is: Make the best research and analysis on content about AI and AI agents\nTo give my best complete final answer to the task respond using the exact following format:\n\nThought: I now can give a great answer\nFinal Answer: Your final answer must be the great and the most complete as possible, it must be outcome described.\n\nI MUST use these formats, my job depends on it!"}, {"role": "user", "content": "\nCurrent Task: Come up with a list of 5 interesting ideas to explore for an article, then write one amazing paragraph highlight for each idea that showcases how good an article about this topic could be. Return the list of ideas with their paragraph and your notes.\n\nThis is the expected criteria for your - final answer: 5 bullet points with a paragraph for each idea.\nyou MUST return the actual complete content as the final answer, not a summary.\n\nYou MUST follow these instructions: \n - Incorporate specific examples and case studies in initial outputs for clearer illustration of concepts.\n - Engage more with current events or trends to enhance relevance, especially in fields like remote work and decision-making.\n - Invite perspectives from experts and stakeholders to add depth to discussions on ethical implications and collaboration in creativity.\n - Use more precise language when discussing topics, ensuring clarity and accessibility for readers.\n - Encourage exploration of user experiences and testimonials to provide more relatable content, especially in education and mental health contexts.\n\nBegin! This is VERY important to you, use the tools available and give your best Final Answer, your job depends on it!\n\nThought:"}], "model": "gpt-4o-mini", "stream": false}' - headers: + - X-USER-AGENT-XXX accept: - application/json accept-encoding: - - gzip, deflate, zstd + - ACCEPT-ENCODING-XXX + authorization: + - AUTHORIZATION-XXX connection: - keep-alive content-length: - - '1979' + - '886' content-type: - application/json host: - api.openai.com - user-agent: - - OpenAI/Python 1.109.1 x-stainless-arch: - - arm64 + - X-STAINLESS-ARCH-XXX x-stainless-async: - 'false' x-stainless-lang: - python x-stainless-os: - - MacOS + - X-STAINLESS-OS-XXX x-stainless-package-version: - - 1.109.1 + - 1.83.0 x-stainless-read-timeout: - - '600' + - X-STAINLESS-READ-TIMEOUT-XXX x-stainless-retry-count: - '0' x-stainless-runtime: - CPython x-stainless-runtime-version: - - 3.12.9 + - 3.13.12 method: POST uri: https://api.openai.com/v1/chat/completions response: body: - string: "{\n \"id\": \"chatcmpl-CT7WWADiu3QnBcF0XrM0OdYDRxh6o\",\n \"object\": \"chat.completion\",\n \"created\": 1761056468,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"I now can give a great answer. \\nFinal Answer:\\n\\n- **The Rise of AI Agents in Remote Work** \\nAs remote work continues to crystallize in the corporate environment, AI agents are transforming how teams collaborate and operate. An article could delve into case studies from companies like GitLab and Buffer that have successfully integrated AI tools to facilitate communication, project tracking, and workload distribution among distributed teams. By interviewing team leaders and employees, we can uncover how AI agents are not merely assisting but actively enhancing productivity and reducing the cognitive load on human workers. This exploration would not only highlight the practical applications\ - \ of AI in remote settings but also provoke critical discussions about the evolving nature of work, employee satisfaction, and balance between AI support and human effort.\\n\\n- **AI as a Creative Collaborator** \\nThe boundaries of human creativity are being challenged as AI becomes a key player in the creative process. An example can be drawn from collaborative tools like OpenAI's DALL-E or Adobe's Sensei, which are enabling artists, writers, and designers to push their creative limits. The article could feature testimonials from creators who have embraced AI as a partner in innovation, sharing stories of how these collaborations have led to unexpected and inspiring outcomes. Additionally, engaging with experts in the field of AI ethics can deepen the discussion about the implications of AI in art, including authorship, originality, and the definition of creativity itself. This exploration could stimulate a broader dialogue on the future of the creative industry and the role\ - \ of AI within it.\\n\\n- **Personalized Learning through AI** \\nIn the realm of education, AI is reshaping how personalized learning experiences are crafted for students. For instance, platforms like DreamBox and Knewton use AI algorithms to tailor lessons based on individual learning styles and paces. An article addressing this topic could synthesize insights gathered from educators who have implemented AI in their classrooms, sharing success stories and challenges faced when adjusting teaching methodologies. By highlighting real user experiences, the discussion could extend to the ethical implications of data privacy, algorithmic bias, and equity in education, thereby painting a comprehensive picture of how AI is both a tool of progress and a subject for scrutiny.\\n\\n- **The Ethical Implications of AI in Decision Making** \\nAs organizations increasingly rely on AI for decision-making—be it through predictive analytics in finance or recruiting algorithms in HR—the ethical\ - \ implications of these technologies come into sharp focus. This article could pull in case studies such as Amazon's recruitment tool that inadvertently favored male candidates, thereby unveiling the hidden biases entrenched in AI systems. By interviewing ethicists, data scientists, and business leaders, the narrative could explore how companies are navigating these ethical waters, balancing efficiency and fairness, and ensuring that AI serves as an equitable decision-making assistant rather than a perpetuator of injustice. \\n\\n- **AI in Mental Health: A New Frontier** \\nThe integration of AI in mental health care presents a myriad of possibilities, from chatbots like Woebot providing cognitive behavioral therapy (CBT) to AI tools that analyze speech for emotional cues. An inspiring article could chronicle the journeys of users who have benefited from AI-driven mental health services, juxtaposed with expert opinions from psychologists discussing the potential and limitations\ - \ of AI in this sensitive field. Through this exploration, readers would gain a nuanced understanding of how AI is shaping therapeutic practices, the importance of human empathy in mental health support, and the ethical concerns that arise from relying on technology for emotional well-being.\\n\\nNotes: Each idea provides a rich ground for exploration, allowing for real-world applications and ethical considerations regarding AI. The proposed articles have the potential to engage a wide readership by blending current trends, expert insights, and relatable experiences—making them both informative and meaningful.\",\n \"refusal\": null,\n \"annotations\": []\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 354,\n \"completion_tokens\": 744,\n \"total_tokens\": 1098,\n \"prompt_tokens_details\": {\n \"cached_tokens\": 0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\"\ - : {\n \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\": 0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\": \"default\",\n \"system_fingerprint\": \"fp_560af6e559\"\n}\n" + string: "{\n \"id\": \"chatcmpl-DDFzCiMzYEJMnv9oV3KbMUwH6TGRO\",\n \"object\": + \"chat.completion\",\n \"created\": 1772052086,\n \"model\": \"gpt-4.1-mini-2025-04-14\",\n + \ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": + \"assistant\",\n \"content\": \"- **The Rise of Autonomous AI Agents: + Redefining Productivity and Creativity** \\n This article would dive into + how autonomous AI agents\u2014intelligent software systems capable of independently + performing complex tasks\u2014are transforming industries by augmenting human + productivity and creativity. It would explore real-world use cases from automated + content generation and customer support bots to AI-driven design and research + assistants, illustrating how these agents reduce repetitive workload and open + new avenues for innovation. The article could also analyze challenges such + as ethical considerations, decision-making transparency, and integration with + existing workflows, offering readers a comprehensive view of how autonomous + AI agents are reshaping the future of work.\\n\\n- **Bridging Human-AI Collaboration: + Designing AI Agents for Intuitive Interaction** \\n This piece would investigate + the critical design principles behind successful human-AI collaboration, focusing + on building AI agents that communicate and interact naturally with users. + From natural language processing nuances to adaptive learning from user behavior, + the article would examine how these technological advancements create seamless + partnerships between humans and machines. Highlighting case studies in healthcare, + finance, and creative industries, it would demonstrate the importance of trust, + interpretability, and empathy in AI agent interfaces, emphasizing how better-designed + interactions can dramatically improve adoption and effectiveness.\\n\\n- **The + Ethical Frontier: Navigating Bias and Accountability in AI Agents** \\n Exploring + the ethical implications of deploying AI agents at scale, this article would + address pressing issues like algorithmic bias, privacy concerns, and accountability + in autonomous decision-making. It would analyze how biases embedded in training + data can propagate through AI agents, impacting critical outcomes in hiring, + lending, and law enforcement. The article would also discuss emerging regulatory + frameworks, best practices for auditing AI agents, and the role of interdisciplinary + ethics teams in ensuring these technologies are fair, transparent, and responsible, + helping readers grasp the societal responsibilities accompanying AI advancement.\\n\\n- + **AI Agents in Startups: Driving Innovation and Competitive Advantage** \\n + \ Focused on the startup ecosystem, this article would explore how emerging + companies leverage AI agents to disrupt markets and scale rapidly with limited + resources. It would profile startups using AI agents for customer acquisition, + personalized marketing, operational automation, and product development, illustrating + how these tools enable lean teams to achieve much more. The narrative would + consider investment trends, challenges faced by startups incorporating AI + agents, and strategies for balancing innovation with reliability, providing + entrepreneurs and investors with valuable insights into harnessing AI agents + for meaningful growth.\\n\\n- **From Data to Decision: How AI Agents Transform + Business Intelligence** \\n This article would delve into the role of AI + agents as intelligent intermediaries in business intelligence (BI) systems, + automating data analysis and delivering actionable insights in real-time. + It would explain how AI agents can parse vast datasets, identify trends, generate + forecasts, and even suggest strategic decisions without constant human oversight. + Highlighting innovations like conversational BI interfaces and predictive + analytics agents, the article would underscore how businesses of all sizes + can democratize data-driven decision-making, driving agility and competitive + advantage in increasingly complex markets.\",\n \"refusal\": null,\n + \ \"annotations\": []\n },\n \"logprobs\": null,\n \"finish_reason\": + \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 164,\n \"completion_tokens\": + 597,\n \"total_tokens\": 761,\n \"prompt_tokens_details\": {\n \"cached_tokens\": + 0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\": + {\n \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\": + 0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\": + \"default\",\n \"system_fingerprint\": \"fp_417e90869b\"\n}\n" headers: CF-RAY: - - 9921664f4da41b58-EWR + - CF-RAY-XXX Connection: - keep-alive Content-Type: - application/json Date: - - Tue, 21 Oct 2025 14:21:25 GMT + - Wed, 25 Feb 2026 20:41:39 GMT Server: - cloudflare - Set-Cookie: - - __cf_bm=p.q22A4.LnQmooo01V_89ZAEGXj_S4fJNkPlbLadtaE-1761056485-1.0.1.1-txy4D4FrtqHpILOE_iiFcBXCTM8d2UsSGzKJeB0qgd3TosZJx3.EmL1CgIJqbJS31Qd5mnCHOqUjx6UFOgOxfBO1NpIe4inEmYUS9xJf33M; path=/; expires=Tue, 21-Oct-25 14:51:25 GMT; domain=.api.openai.com; HttpOnly; Secure; SameSite=None - - _cfuvid=Vix88TUp4dnmVridKpA6LWYGOsSdcnEg942n1s6NoNg-1761056485340-0.0.1.1-604800000; path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None Strict-Transport-Security: - - max-age=31536000; includeSubDomains; preload + - STS-XXX Transfer-Encoding: - chunked X-Content-Type-Options: - - nosniff + - X-CONTENT-TYPE-XXX access-control-expose-headers: - - X-Request-ID + - ACCESS-CONTROL-XXX alt-svc: - h3=":443"; ma=86400 cf-cache-status: - DYNAMIC openai-organization: - - crewai-iuxna1 + - OPENAI-ORG-XXX openai-processing-ms: - - '16416' + - '13437' openai-project: - - proj_fL4UBWR1CMpAAdgzaSKqsVvA + - OPENAI-PROJECT-XXX openai-version: - '2020-10-01' - x-envoy-upstream-service-time: - - '16584' + set-cookie: + - SET-COOKIE-XXX x-openai-proxy-wasm: - v0.1 x-ratelimit-limit-requests: - - '10000' + - X-RATELIMIT-LIMIT-REQUESTS-XXX x-ratelimit-limit-tokens: - - '200000' + - X-RATELIMIT-LIMIT-TOKENS-XXX x-ratelimit-remaining-requests: - - '9999' + - X-RATELIMIT-REMAINING-REQUESTS-XXX x-ratelimit-remaining-tokens: - - '199538' + - X-RATELIMIT-REMAINING-TOKENS-XXX x-ratelimit-reset-requests: - - 8.64s + - X-RATELIMIT-RESET-REQUESTS-XXX x-ratelimit-reset-tokens: - - 138ms + - X-RATELIMIT-RESET-TOKENS-XXX x-request-id: - - req_711a382be0544fa291fe95d0f1e51072 + - X-REQUEST-ID-XXX status: code: 200 message: OK - request: - body: '{"messages": [{"role": "system", "content": "You are Task Execution Evaluator. Evaluator agent for crew evaluation with precise capabilities to evaluate the performance of the agents in the crew based on the tasks they have performed\nYour personal goal is: Your goal is to evaluate the performance of the agents in the crew based on the tasks they have performed using score from 1 to 10 evaluating on completion, quality, and overall performance.\nTo give my best complete final answer to the task respond using the exact following format:\n\nThought: I now can give a great answer\nFinal Answer: Your final answer must be the great and the most complete as possible, it must be outcome described.\n\nI MUST use these formats, my job depends on it!"}, {"role": "user", "content": "\nCurrent Task: Based on the task description and the expected output, compare and evaluate the performance of the agents in the crew based on the Task Output they have performed using score from 1 to 10 evaluating - on completion, quality, and overall performance.task_description: Come up with a list of 5 interesting ideas to explore for an article, then write one amazing paragraph highlight for each idea that showcases how good an article about this topic could be. Return the list of ideas with their paragraph and your notes. task_expected_output: 5 bullet points with a paragraph for each idea. agent: Researcher agent_goal: Make the best research and analysis on content about AI and AI agents Task Output: - **The Rise of AI Agents in Remote Work** \nAs remote work continues to crystallize in the corporate environment, AI agents are transforming how teams collaborate and operate. An article could delve into case studies from companies like GitLab and Buffer that have successfully integrated AI tools to facilitate communication, project tracking, and workload distribution among distributed teams. By interviewing team leaders and employees, we can uncover how AI agents are not merely assisting - but actively enhancing productivity and reducing the cognitive load on human workers. This exploration would not only highlight the practical applications of AI in remote settings but also provoke critical discussions about the evolving nature of work, employee satisfaction, and balance between AI support and human effort.\n\n- **AI as a Creative Collaborator** \nThe boundaries of human creativity are being challenged as AI becomes a key player in the creative process. An example can be drawn from collaborative tools like OpenAI''s DALL-E or Adobe''s Sensei, which are enabling artists, writers, and designers to push their creative limits. The article could feature testimonials from creators who have embraced AI as a partner in innovation, sharing stories of how these collaborations have led to unexpected and inspiring outcomes. Additionally, engaging with experts in the field of AI ethics can deepen the discussion about the implications of AI in art, including authorship, originality, - and the definition of creativity itself. This exploration could stimulate a broader dialogue on the future of the creative industry and the role of AI within it.\n\n- **Personalized Learning through AI** \nIn the realm of education, AI is reshaping how personalized learning experiences are crafted for students. For instance, platforms like DreamBox and Knewton use AI algorithms to tailor lessons based on individual learning styles and paces. An article addressing this topic could synthesize insights gathered from educators who have implemented AI in their classrooms, sharing success stories and challenges faced when adjusting teaching methodologies. By highlighting real user experiences, the discussion could extend to the ethical implications of data privacy, algorithmic bias, and equity in education, thereby painting a comprehensive picture of how AI is both a tool of progress and a subject for scrutiny.\n\n- **The Ethical Implications of AI in Decision Making** \nAs organizations - increasingly rely on AI for decision-making\u2014be it through predictive analytics in finance or recruiting algorithms in HR\u2014the ethical implications of these technologies come into sharp focus. This article could pull in case studies such as Amazon''s recruitment tool that inadvertently favored male candidates, thereby unveiling the hidden biases entrenched in AI systems. By interviewing ethicists, data scientists, and business leaders, the narrative could explore how companies are navigating these ethical waters, balancing efficiency and fairness, and ensuring that AI serves as an equitable decision-making assistant rather than a perpetuator of injustice. \n\n- **AI in Mental Health: A New Frontier** \nThe integration of AI in mental health care presents a myriad of possibilities, from chatbots like Woebot providing cognitive behavioral therapy (CBT) to AI tools that analyze speech for emotional cues. An inspiring article could chronicle the journeys of users who have benefited - from AI-driven mental health services, juxtaposed with expert opinions from psychologists discussing the potential and limitations of AI in this sensitive field. Through this exploration, readers would gain a nuanced understanding of how AI is shaping therapeutic practices, the importance of human empathy in mental health support, and the ethical concerns that arise from relying on technology for emotional well-being.\n\nNotes: Each idea provides a rich ground for exploration, allowing for real-world applications and ethical considerations regarding AI. The proposed articles have the potential to engage a wide readership by blending current trends, expert insights, and relatable experiences\u2014making them both informative and meaningful.\n\nThis is the expected criteria for your final answer: Evaluation Score from 1 to 10 based on the performance of the agents on the tasks\nyou MUST return the actual complete content as the final answer, not a summary.\nEnsure your final answer contains - only the content in the following format: {\n \"quality\": float\n}\n\nEnsure the final output does not include any code block markers like ```json or ```python.\n\nBegin! This is VERY important to you, use the tools available and give your best Final Answer, your job depends on it!\n\nThought:"}], "model": "gpt-4o-mini", "stream": false}' + body: "{\"messages\":[{\"role\":\"system\",\"content\":\"You are Task Execution + Evaluator. Evaluator agent for crew evaluation with precise capabilities to + evaluate the performance of the agents in the crew based on the tasks they have + performed\\nYour personal goal is: Your goal is to evaluate the performance + of the agents in the crew based on the tasks they have performed using score + from 1 to 10 evaluating on completion, quality, and overall performance.\"},{\"role\":\"user\",\"content\":\"\\nCurrent + Task: Based on the task description and the expected output, compare and evaluate + the performance of the agents in the crew based on the Task Output they have + performed using score from 1 to 10 evaluating on completion, quality, and overall + performance.task_description: Come up with a list of 5 interesting ideas to + explore for an article, then write one amazing paragraph highlight for each + idea that showcases how good an article about this topic could be. Return the + list of ideas with their paragraph and your notes. task_expected_output: 5 bullet + points with a paragraph for each idea. agent: Researcher agent_goal: Make the + best research and analysis on content about AI and AI agents Task Output: - + **The Rise of Autonomous AI Agents: Redefining Productivity and Creativity** + \ \\n This article would dive into how autonomous AI agents\u2014intelligent + software systems capable of independently performing complex tasks\u2014are + transforming industries by augmenting human productivity and creativity. It + would explore real-world use cases from automated content generation and customer + support bots to AI-driven design and research assistants, illustrating how these + agents reduce repetitive workload and open new avenues for innovation. The article + could also analyze challenges such as ethical considerations, decision-making + transparency, and integration with existing workflows, offering readers a comprehensive + view of how autonomous AI agents are reshaping the future of work.\\n\\n- **Bridging + Human-AI Collaboration: Designing AI Agents for Intuitive Interaction** \\n + \ This piece would investigate the critical design principles behind successful + human-AI collaboration, focusing on building AI agents that communicate and + interact naturally with users. From natural language processing nuances to adaptive + learning from user behavior, the article would examine how these technological + advancements create seamless partnerships between humans and machines. Highlighting + case studies in healthcare, finance, and creative industries, it would demonstrate + the importance of trust, interpretability, and empathy in AI agent interfaces, + emphasizing how better-designed interactions can dramatically improve adoption + and effectiveness.\\n\\n- **The Ethical Frontier: Navigating Bias and Accountability + in AI Agents** \\n Exploring the ethical implications of deploying AI agents + at scale, this article would address pressing issues like algorithmic bias, + privacy concerns, and accountability in autonomous decision-making. It would + analyze how biases embedded in training data can propagate through AI agents, + impacting critical outcomes in hiring, lending, and law enforcement. The article + would also discuss emerging regulatory frameworks, best practices for auditing + AI agents, and the role of interdisciplinary ethics teams in ensuring these + technologies are fair, transparent, and responsible, helping readers grasp the + societal responsibilities accompanying AI advancement.\\n\\n- **AI Agents in + Startups: Driving Innovation and Competitive Advantage** \\n Focused on the + startup ecosystem, this article would explore how emerging companies leverage + AI agents to disrupt markets and scale rapidly with limited resources. It would + profile startups using AI agents for customer acquisition, personalized marketing, + operational automation, and product development, illustrating how these tools + enable lean teams to achieve much more. The narrative would consider investment + trends, challenges faced by startups incorporating AI agents, and strategies + for balancing innovation with reliability, providing entrepreneurs and investors + with valuable insights into harnessing AI agents for meaningful growth.\\n\\n- + **From Data to Decision: How AI Agents Transform Business Intelligence** \\n + \ This article would delve into the role of AI agents as intelligent intermediaries + in business intelligence (BI) systems, automating data analysis and delivering + actionable insights in real-time. It would explain how AI agents can parse vast + datasets, identify trends, generate forecasts, and even suggest strategic decisions + without constant human oversight. Highlighting innovations like conversational + BI interfaces and predictive analytics agents, the article would underscore + how businesses of all sizes can democratize data-driven decision-making, driving + agility and competitive advantage in increasingly complex markets.\\n\\nThis + is the expected criteria for your final answer: Evaluation Score from 1 to 10 + based on the performance of the agents on the tasks\\nyou MUST return the actual + complete content as the final answer, not a summary.\\nFormat your final answer + according to the following OpenAPI schema: {\\n \\\"properties\\\": {\\n \\\"quality\\\": + {\\n \\\"description\\\": \\\"A score from 1 to 10 evaluating on completion, + quality, and overall performance from the task_description and task_expected_output + to the actual Task Output.\\\",\\n \\\"title\\\": \\\"Quality\\\",\\n \\\"type\\\": + \\\"number\\\"\\n }\\n },\\n \\\"required\\\": [\\n \\\"quality\\\"\\n + \ ],\\n \\\"title\\\": \\\"TaskEvaluationPydanticOutput\\\",\\n \\\"type\\\": + \\\"object\\\",\\n \\\"additionalProperties\\\": false\\n}\\n\\nIMPORTANT: + Preserve the original content exactly as-is. Do NOT rewrite, paraphrase, or + modify the meaning of the content. Only structure it to match the schema format.\\n\\nDo + not include the OpenAPI schema in the final output. Ensure the final output + does not include any code block markers like ```json or ```python.\\n\\nProvide + your complete response:\"}],\"model\":\"gpt-4o-mini\",\"response_format\":{\"type\":\"json_schema\",\"json_schema\":{\"schema\":{\"properties\":{\"quality\":{\"description\":\"A + score from 1 to 10 evaluating on completion, quality, and overall performance + from the task_description and task_expected_output to the actual Task Output.\",\"title\":\"Quality\",\"type\":\"number\"}},\"required\":[\"quality\"],\"title\":\"TaskEvaluationPydanticOutput\",\"type\":\"object\",\"additionalProperties\":false},\"name\":\"TaskEvaluationPydanticOutput\",\"strict\":true}},\"stream\":false}" headers: + User-Agent: + - X-USER-AGENT-XXX accept: - application/json accept-encoding: - - gzip, deflate, zstd + - ACCEPT-ENCODING-XXX + authorization: + - AUTHORIZATION-XXX connection: - keep-alive content-length: - - '6338' + - '6502' content-type: - application/json host: - api.openai.com - user-agent: - - OpenAI/Python 1.109.1 x-stainless-arch: - - arm64 + - X-STAINLESS-ARCH-XXX x-stainless-async: - 'false' + x-stainless-helper-method: + - beta.chat.completions.parse x-stainless-lang: - python x-stainless-os: - - MacOS + - X-STAINLESS-OS-XXX x-stainless-package-version: - - 1.109.1 + - 1.83.0 x-stainless-read-timeout: - - '600' + - X-STAINLESS-READ-TIMEOUT-XXX x-stainless-retry-count: - '0' x-stainless-runtime: - CPython x-stainless-runtime-version: - - 3.12.9 + - 3.13.12 method: POST uri: https://api.openai.com/v1/chat/completions response: body: - string: "{\n \"id\": \"chatcmpl-CT7WnkkrcKAvciaNC1JI6BT3L6Xm5\",\n \"object\": \"chat.completion\",\n \"created\": 1761056485,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"I now can give a great answer \\nFinal Answer: {\\n \\\"quality\\\": 9.5\\n}\",\n \"refusal\": null,\n \"annotations\": []\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 1134,\n \"completion_tokens\": 22,\n \"total_tokens\": 1156,\n \"prompt_tokens_details\": {\n \"cached_tokens\": 0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\": {\n \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\": 0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\": \"default\",\n \"system_fingerprint\": \"fp_560af6e559\"\ - \n}\n" + string: "{\n \"id\": \"chatcmpl-DDFzQTBe214rOuf82URXmgkuNj5u4\",\n \"object\": + \"chat.completion\",\n \"created\": 1772052100,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n + \ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": + \"assistant\",\n \"content\": \"{\\\"quality\\\":9}\",\n \"refusal\": + null,\n \"annotations\": []\n },\n \"logprobs\": null,\n + \ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": + 1134,\n \"completion_tokens\": 5,\n \"total_tokens\": 1139,\n \"prompt_tokens_details\": + {\n \"cached_tokens\": 0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\": + {\n \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\": + 0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\": + \"default\",\n \"system_fingerprint\": \"fp_bd4be55b21\"\n}\n" headers: CF-RAY: - - 992166b9cb8e42c0-EWR + - CF-RAY-XXX Connection: - keep-alive Content-Type: - application/json Date: - - Tue, 21 Oct 2025 14:21:26 GMT + - Wed, 25 Feb 2026 20:41:40 GMT Server: - cloudflare - Set-Cookie: - - __cf_bm=ujzGLIjq87ZWlYFBH3FycG8cIYtaTjon9XdbV63J84s-1761056486-1.0.1.1-V9wZVN8TxLIQ..Cd6VD53rSKVM8GssieHpzu53MMLsuoM7jVI8nAKNTbZeCqJxyHPutyhj_BwPvR56_gb0Nx90S6pVs3gQC2vj8VmCPbh1Y; path=/; expires=Tue, 21-Oct-25 14:51:26 GMT; domain=.api.openai.com; HttpOnly; Secure; SameSite=None - - _cfuvid=GIa.4ZxD52A2dXSZxoW1Mckm_eGjntP2i_mB4sczwEI-1761056486732-0.0.1.1-604800000; path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None Strict-Transport-Security: - - max-age=31536000; includeSubDomains; preload + - STS-XXX Transfer-Encoding: - chunked X-Content-Type-Options: - - nosniff + - X-CONTENT-TYPE-XXX access-control-expose-headers: - - X-Request-ID + - ACCESS-CONTROL-XXX alt-svc: - h3=":443"; ma=86400 cf-cache-status: - DYNAMIC openai-organization: - - crewai-iuxna1 + - OPENAI-ORG-XXX openai-processing-ms: - - '787' + - '241' openai-project: - - proj_fL4UBWR1CMpAAdgzaSKqsVvA + - OPENAI-PROJECT-XXX openai-version: - '2020-10-01' - x-envoy-upstream-service-time: - - '955' + set-cookie: + - SET-COOKIE-XXX x-openai-proxy-wasm: - v0.1 x-ratelimit-limit-requests: - - '10000' + - X-RATELIMIT-LIMIT-REQUESTS-XXX x-ratelimit-limit-tokens: - - '200000' + - X-RATELIMIT-LIMIT-TOKENS-XXX x-ratelimit-remaining-requests: - - '9999' + - X-RATELIMIT-REMAINING-REQUESTS-XXX x-ratelimit-remaining-tokens: - - '198454' + - X-RATELIMIT-REMAINING-TOKENS-XXX x-ratelimit-reset-requests: - - 8.64s + - X-RATELIMIT-RESET-REQUESTS-XXX x-ratelimit-reset-tokens: - - 463ms + - X-RATELIMIT-RESET-TOKENS-XXX x-request-id: - - req_1911f5f9d34e499ca97c99ee3f40d04b + - X-REQUEST-ID-XXX status: code: 200 message: OK - request: - body: '{"events": [{"event_id": "660f299b-0769-482e-b169-fcd0cb2ce48b", "timestamp": "2025-10-21T14:21:07.171393+00:00", "type": "crew_kickoff_started", "event_data": {"timestamp": "2025-10-21T14:21:07.171393+00:00", "type": "crew_kickoff_started", "source_fingerprint": null, "source_type": null, "fingerprint_metadata": null, "task_id": null, "task_name": null, "agent_id": null, "agent_role": null, "crew_name": "crew", "crew": null, "inputs": {"topic": "AI"}}}, {"event_id": "9c615452-4b34-4f35-8768-a15b69e01205", "timestamp": "2025-10-21T14:21:07.173802+00:00", "type": "task_started", "event_data": {"task_description": "Come up with a list of 5 interesting ideas to explore for an article, then write one amazing paragraph highlight for each idea that showcases how good an article about this topic could be. Return the list of ideas with their paragraph and your notes.", "expected_output": "5 bullet points with a paragraph for each idea.", "task_name": "Come up with a list of 5 interesting - ideas to explore for an article, then write one amazing paragraph highlight for each idea that showcases how good an article about this topic could be. Return the list of ideas with their paragraph and your notes.", "context": "", "agent_role": "Researcher", "task_id": "b6c0fa7b-c537-48d9-9456-914fd6dbc421"}}, {"event_id": "fec0b51d-50c2-4e7a-b73e-016d0fb260fc", "timestamp": "2025-10-21T14:21:07.174578+00:00", "type": "agent_execution_started", "event_data": {"agent_role": "Researcher", "agent_goal": "Make the best research and analysis on content about AI and AI agents", "agent_backstory": "You''re an expert researcher, specialized in technology, software engineering, AI and startups. You work as a freelancer and is now working on doing research and analysis for a new customer."}}, {"event_id": "ac858ea6-3ba3-46cb-93e8-3244029faac4", "timestamp": "2025-10-21T14:21:07.174743+00:00", "type": "llm_call_started", "event_data": {"timestamp": "2025-10-21T14:21:07.174743+00:00", "type": - "llm_call_started", "source_fingerprint": null, "source_type": null, "fingerprint_metadata": null, "task_id": "b6c0fa7b-c537-48d9-9456-914fd6dbc421", "task_name": "Come up with a list of 5 interesting ideas to explore for an article, then write one amazing paragraph highlight for each idea that showcases how good an article about this topic could be. Return the list of ideas with their paragraph and your notes.", "agent_id": "d2d12d9f-88f6-4955-bf69-f5f9868961c3", "agent_role": "Researcher", "from_task": null, "from_agent": null, "model": "gpt-4o-mini", "messages": [{"role": "system", "content": "You are Researcher. You''re an expert researcher, specialized in technology, software engineering, AI and startups. You work as a freelancer and is now working on doing research and analysis for a new customer.\nYour personal goal is: Make the best research and analysis on content about AI and AI agents\nTo give my best complete final answer to the task respond using the exact following format:\n\nThought: - I now can give a great answer\nFinal Answer: Your final answer must be the great and the most complete as possible, it must be outcome described.\n\nI MUST use these formats, my job depends on it!"}, {"role": "user", "content": "\nCurrent Task: Come up with a list of 5 interesting ideas to explore for an article, then write one amazing paragraph highlight for each idea that showcases how good an article about this topic could be. Return the list of ideas with their paragraph and your notes.\n\nThis is the expected criteria for your final answer: 5 bullet points with a paragraph for each idea.\nyou MUST return the actual complete content as the final answer, not a summary.\n\nYou MUST follow these instructions: \n - Incorporate specific examples and case studies in initial outputs for clearer illustration of concepts.\n - Engage more with current events or trends to enhance relevance, especially in fields like remote work and decision-making.\n - Invite perspectives from experts and - stakeholders to add depth to discussions on ethical implications and collaboration in creativity.\n - Use more precise language when discussing topics, ensuring clarity and accessibility for readers.\n - Encourage exploration of user experiences and testimonials to provide more relatable content, especially in education and mental health contexts.\n\nBegin! This is VERY important to you, use the tools available and give your best Final Answer, your job depends on it!\n\nThought:"}], "tools": null, "callbacks": [""], "available_functions": null}}, {"event_id": "0ff635a9-0d57-4d4d-991a-71e2fc6e6b86", "timestamp": "2025-10-21T14:21:25.185353+00:00", "type": "llm_call_completed", "event_data": {"timestamp": "2025-10-21T14:21:25.185353+00:00", "type": "llm_call_completed", "source_fingerprint": null, "source_type": null, "fingerprint_metadata": null, "task_id": "b6c0fa7b-c537-48d9-9456-914fd6dbc421", "task_name": - "Come up with a list of 5 interesting ideas to explore for an article, then write one amazing paragraph highlight for each idea that showcases how good an article about this topic could be. Return the list of ideas with their paragraph and your notes.", "agent_id": "d2d12d9f-88f6-4955-bf69-f5f9868961c3", "agent_role": "Researcher", "from_task": null, "from_agent": null, "messages": [{"role": "system", "content": "You are Researcher. You''re an expert researcher, specialized in technology, software engineering, AI and startups. You work as a freelancer and is now working on doing research and analysis for a new customer.\nYour personal goal is: Make the best research and analysis on content about AI and AI agents\nTo give my best complete final answer to the task respond using the exact following format:\n\nThought: I now can give a great answer\nFinal Answer: Your final answer must be the great and the most complete as possible, it must be outcome described.\n\nI MUST use these formats, - my job depends on it!"}, {"role": "user", "content": "\nCurrent Task: Come up with a list of 5 interesting ideas to explore for an article, then write one amazing paragraph highlight for each idea that showcases how good an article about this topic could be. Return the list of ideas with their paragraph and your notes.\n\nThis is the expected criteria for your final answer: 5 bullet points with a paragraph for each idea.\nyou MUST return the actual complete content as the final answer, not a summary.\n\nYou MUST follow these instructions: \n - Incorporate specific examples and case studies in initial outputs for clearer illustration of concepts.\n - Engage more with current events or trends to enhance relevance, especially in fields like remote work and decision-making.\n - Invite perspectives from experts and stakeholders to add depth to discussions on ethical implications and collaboration in creativity.\n - Use more precise language when discussing topics, ensuring clarity and accessibility - for readers.\n - Encourage exploration of user experiences and testimonials to provide more relatable content, especially in education and mental health contexts.\n\nBegin! This is VERY important to you, use the tools available and give your best Final Answer, your job depends on it!\n\nThought:"}], "response": "I now can give a great answer. \nFinal Answer:\n\n- **The Rise of AI Agents in Remote Work** \nAs remote work continues to crystallize in the corporate environment, AI agents are transforming how teams collaborate and operate. An article could delve into case studies from companies like GitLab and Buffer that have successfully integrated AI tools to facilitate communication, project tracking, and workload distribution among distributed teams. By interviewing team leaders and employees, we can uncover how AI agents are not merely assisting but actively enhancing productivity and reducing the cognitive load on human workers. This exploration would not only highlight the practical - applications of AI in remote settings but also provoke critical discussions about the evolving nature of work, employee satisfaction, and balance between AI support and human effort.\n\n- **AI as a Creative Collaborator** \nThe boundaries of human creativity are being challenged as AI becomes a key player in the creative process. An example can be drawn from collaborative tools like OpenAI''s DALL-E or Adobe''s Sensei, which are enabling artists, writers, and designers to push their creative limits. The article could feature testimonials from creators who have embraced AI as a partner in innovation, sharing stories of how these collaborations have led to unexpected and inspiring outcomes. Additionally, engaging with experts in the field of AI ethics can deepen the discussion about the implications of AI in art, including authorship, originality, and the definition of creativity itself. This exploration could stimulate a broader dialogue on the future of the creative industry and the - role of AI within it.\n\n- **Personalized Learning through AI** \nIn the realm of education, AI is reshaping how personalized learning experiences are crafted for students. For instance, platforms like DreamBox and Knewton use AI algorithms to tailor lessons based on individual learning styles and paces. An article addressing this topic could synthesize insights gathered from educators who have implemented AI in their classrooms, sharing success stories and challenges faced when adjusting teaching methodologies. By highlighting real user experiences, the discussion could extend to the ethical implications of data privacy, algorithmic bias, and equity in education, thereby painting a comprehensive picture of how AI is both a tool of progress and a subject for scrutiny.\n\n- **The Ethical Implications of AI in Decision Making** \nAs organizations increasingly rely on AI for decision-making\u2014be it through predictive analytics in finance or recruiting algorithms in HR\u2014the ethical - implications of these technologies come into sharp focus. This article could pull in case studies such as Amazon''s recruitment tool that inadvertently favored male candidates, thereby unveiling the hidden biases entrenched in AI systems. By interviewing ethicists, data scientists, and business leaders, the narrative could explore how companies are navigating these ethical waters, balancing efficiency and fairness, and ensuring that AI serves as an equitable decision-making assistant rather than a perpetuator of injustice. \n\n- **AI in Mental Health: A New Frontier** \nThe integration of AI in mental health care presents a myriad of possibilities, from chatbots like Woebot providing cognitive behavioral therapy (CBT) to AI tools that analyze speech for emotional cues. An inspiring article could chronicle the journeys of users who have benefited from AI-driven mental health services, juxtaposed with expert opinions from psychologists discussing the potential and limitations of AI - in this sensitive field. Through this exploration, readers would gain a nuanced understanding of how AI is shaping therapeutic practices, the importance of human empathy in mental health support, and the ethical concerns that arise from relying on technology for emotional well-being.\n\nNotes: Each idea provides a rich ground for exploration, allowing for real-world applications and ethical considerations regarding AI. The proposed articles have the potential to engage a wide readership by blending current trends, expert insights, and relatable experiences\u2014making them both informative and meaningful.", "call_type": "", "model": "gpt-4o-mini"}}, {"event_id": "4b0cdd26-0257-4e1e-95b5-f174793088f4", "timestamp": "2025-10-21T14:21:25.185503+00:00", "type": "agent_execution_completed", "event_data": {"agent_role": "Researcher", "agent_goal": "Make the best research and analysis on content about AI and AI agents", "agent_backstory": "You''re an expert - researcher, specialized in technology, software engineering, AI and startups. You work as a freelancer and is now working on doing research and analysis for a new customer."}}, {"event_id": "cf861e0b-7e38-4162-8c7f-64135c9b59f4", "timestamp": "2025-10-21T14:21:25.186875+00:00", "type": "task_started", "event_data": {"task_description": "Based on the task description and the expected output, compare and evaluate the performance of the agents in the crew based on the Task Output they have performed using score from 1 to 10 evaluating on completion, quality, and overall performance.task_description: Come up with a list of 5 interesting ideas to explore for an article, then write one amazing paragraph highlight for each idea that showcases how good an article about this topic could be. Return the list of ideas with their paragraph and your notes. task_expected_output: 5 bullet points with a paragraph for each idea. agent: Researcher agent_goal: Make the best research and analysis on content - about AI and AI agents Task Output: - **The Rise of AI Agents in Remote Work** \nAs remote work continues to crystallize in the corporate environment, AI agents are transforming how teams collaborate and operate. An article could delve into case studies from companies like GitLab and Buffer that have successfully integrated AI tools to facilitate communication, project tracking, and workload distribution among distributed teams. By interviewing team leaders and employees, we can uncover how AI agents are not merely assisting but actively enhancing productivity and reducing the cognitive load on human workers. This exploration would not only highlight the practical applications of AI in remote settings but also provoke critical discussions about the evolving nature of work, employee satisfaction, and balance between AI support and human effort.\n\n- **AI as a Creative Collaborator** \nThe boundaries of human creativity are being challenged as AI becomes a key player in the creative - process. An example can be drawn from collaborative tools like OpenAI''s DALL-E or Adobe''s Sensei, which are enabling artists, writers, and designers to push their creative limits. The article could feature testimonials from creators who have embraced AI as a partner in innovation, sharing stories of how these collaborations have led to unexpected and inspiring outcomes. Additionally, engaging with experts in the field of AI ethics can deepen the discussion about the implications of AI in art, including authorship, originality, and the definition of creativity itself. This exploration could stimulate a broader dialogue on the future of the creative industry and the role of AI within it.\n\n- **Personalized Learning through AI** \nIn the realm of education, AI is reshaping how personalized learning experiences are crafted for students. For instance, platforms like DreamBox and Knewton use AI algorithms to tailor lessons based on individual learning styles and paces. An article addressing - this topic could synthesize insights gathered from educators who have implemented AI in their classrooms, sharing success stories and challenges faced when adjusting teaching methodologies. By highlighting real user experiences, the discussion could extend to the ethical implications of data privacy, algorithmic bias, and equity in education, thereby painting a comprehensive picture of how AI is both a tool of progress and a subject for scrutiny.\n\n- **The Ethical Implications of AI in Decision Making** \nAs organizations increasingly rely on AI for decision-making\u2014be it through predictive analytics in finance or recruiting algorithms in HR\u2014the ethical implications of these technologies come into sharp focus. This article could pull in case studies such as Amazon''s recruitment tool that inadvertently favored male candidates, thereby unveiling the hidden biases entrenched in AI systems. By interviewing ethicists, data scientists, and business leaders, the narrative could - explore how companies are navigating these ethical waters, balancing efficiency and fairness, and ensuring that AI serves as an equitable decision-making assistant rather than a perpetuator of injustice. \n\n- **AI in Mental Health: A New Frontier** \nThe integration of AI in mental health care presents a myriad of possibilities, from chatbots like Woebot providing cognitive behavioral therapy (CBT) to AI tools that analyze speech for emotional cues. An inspiring article could chronicle the journeys of users who have benefited from AI-driven mental health services, juxtaposed with expert opinions from psychologists discussing the potential and limitations of AI in this sensitive field. Through this exploration, readers would gain a nuanced understanding of how AI is shaping therapeutic practices, the importance of human empathy in mental health support, and the ethical concerns that arise from relying on technology for emotional well-being.\n\nNotes: Each idea provides a rich ground - for exploration, allowing for real-world applications and ethical considerations regarding AI. The proposed articles have the potential to engage a wide readership by blending current trends, expert insights, and relatable experiences\u2014making them both informative and meaningful.", "expected_output": "Evaluation Score from 1 to 10 based on the performance of the agents on the tasks", "task_name": "Based on the task description and the expected output, compare and evaluate the performance of the agents in the crew based on the Task Output they have performed using score from 1 to 10 evaluating on completion, quality, and overall performance.task_description: Come up with a list of 5 interesting ideas to explore for an article, then write one amazing paragraph highlight for each idea that showcases how good an article about this topic could be. Return the list of ideas with their paragraph and your notes. task_expected_output: 5 bullet points with a paragraph for each idea. agent: - Researcher agent_goal: Make the best research and analysis on content about AI and AI agents Task Output: - **The Rise of AI Agents in Remote Work** \nAs remote work continues to crystallize in the corporate environment, AI agents are transforming how teams collaborate and operate. An article could delve into case studies from companies like GitLab and Buffer that have successfully integrated AI tools to facilitate communication, project tracking, and workload distribution among distributed teams. By interviewing team leaders and employees, we can uncover how AI agents are not merely assisting but actively enhancing productivity and reducing the cognitive load on human workers. This exploration would not only highlight the practical applications of AI in remote settings but also provoke critical discussions about the evolving nature of work, employee satisfaction, and balance between AI support and human effort.\n\n- **AI as a Creative Collaborator** \nThe boundaries of human creativity - are being challenged as AI becomes a key player in the creative process. An example can be drawn from collaborative tools like OpenAI''s DALL-E or Adobe''s Sensei, which are enabling artists, writers, and designers to push their creative limits. The article could feature testimonials from creators who have embraced AI as a partner in innovation, sharing stories of how these collaborations have led to unexpected and inspiring outcomes. Additionally, engaging with experts in the field of AI ethics can deepen the discussion about the implications of AI in art, including authorship, originality, and the definition of creativity itself. This exploration could stimulate a broader dialogue on the future of the creative industry and the role of AI within it.\n\n- **Personalized Learning through AI** \nIn the realm of education, AI is reshaping how personalized learning experiences are crafted for students. For instance, platforms like DreamBox and Knewton use AI algorithms to tailor lessons - based on individual learning styles and paces. An article addressing this topic could synthesize insights gathered from educators who have implemented AI in their classrooms, sharing success stories and challenges faced when adjusting teaching methodologies. By highlighting real user experiences, the discussion could extend to the ethical implications of data privacy, algorithmic bias, and equity in education, thereby painting a comprehensive picture of how AI is both a tool of progress and a subject for scrutiny.\n\n- **The Ethical Implications of AI in Decision Making** \nAs organizations increasingly rely on AI for decision-making\u2014be it through predictive analytics in finance or recruiting algorithms in HR\u2014the ethical implications of these technologies come into sharp focus. This article could pull in case studies such as Amazon''s recruitment tool that inadvertently favored male candidates, thereby unveiling the hidden biases entrenched in AI systems. By interviewing - ethicists, data scientists, and business leaders, the narrative could explore how companies are navigating these ethical waters, balancing efficiency and fairness, and ensuring that AI serves as an equitable decision-making assistant rather than a perpetuator of injustice. \n\n- **AI in Mental Health: A New Frontier** \nThe integration of AI in mental health care presents a myriad of possibilities, from chatbots like Woebot providing cognitive behavioral therapy (CBT) to AI tools that analyze speech for emotional cues. An inspiring article could chronicle the journeys of users who have benefited from AI-driven mental health services, juxtaposed with expert opinions from psychologists discussing the potential and limitations of AI in this sensitive field. Through this exploration, readers would gain a nuanced understanding of how AI is shaping therapeutic practices, the importance of human empathy in mental health support, and the ethical concerns that arise from relying on technology - for emotional well-being.\n\nNotes: Each idea provides a rich ground for exploration, allowing for real-world applications and ethical considerations regarding AI. The proposed articles have the potential to engage a wide readership by blending current trends, expert insights, and relatable experiences\u2014making them both informative and meaningful.", "context": null, "agent_role": "Task Execution Evaluator", "task_id": "73f03e42-b56a-4e3b-8015-2377ba04393b"}}, {"event_id": "2f874052-6753-4641-97a8-ae358ff85ac8", "timestamp": "2025-10-21T14:21:25.187449+00:00", "type": "agent_execution_started", "event_data": {"agent_role": "Task Execution Evaluator", "agent_goal": "Your goal is to evaluate the performance of the agents in the crew based on the tasks they have performed using score from 1 to 10 evaluating on completion, quality, and overall performance.", "agent_backstory": "Evaluator agent for crew evaluation with precise capabilities to evaluate the performance of the agents in - the crew based on the tasks they have performed"}}, {"event_id": "b60f05bd-529b-4041-bb8b-fd6a84e9c163", "timestamp": "2025-10-21T14:21:25.187556+00:00", "type": "llm_call_started", "event_data": {"timestamp": "2025-10-21T14:21:25.187556+00:00", "type": "llm_call_started", "source_fingerprint": null, "source_type": null, "fingerprint_metadata": null, "task_id": "73f03e42-b56a-4e3b-8015-2377ba04393b", "task_name": "Based on the task description and the expected output, compare and evaluate the performance of the agents in the crew based on the Task Output they have performed using score from 1 to 10 evaluating on completion, quality, and overall performance.task_description: Come up with a list of 5 interesting ideas to explore for an article, then write one amazing paragraph highlight for each idea that showcases how good an article about this topic could be. Return the list of ideas with their paragraph and your notes. task_expected_output: 5 bullet points with a paragraph for each - idea. agent: Researcher agent_goal: Make the best research and analysis on content about AI and AI agents Task Output: - **The Rise of AI Agents in Remote Work** \nAs remote work continues to crystallize in the corporate environment, AI agents are transforming how teams collaborate and operate. An article could delve into case studies from companies like GitLab and Buffer that have successfully integrated AI tools to facilitate communication, project tracking, and workload distribution among distributed teams. By interviewing team leaders and employees, we can uncover how AI agents are not merely assisting but actively enhancing productivity and reducing the cognitive load on human workers. This exploration would not only highlight the practical applications of AI in remote settings but also provoke critical discussions about the evolving nature of work, employee satisfaction, and balance between AI support and human effort.\n\n- **AI as a Creative Collaborator** \nThe boundaries - of human creativity are being challenged as AI becomes a key player in the creative process. An example can be drawn from collaborative tools like OpenAI''s DALL-E or Adobe''s Sensei, which are enabling artists, writers, and designers to push their creative limits. The article could feature testimonials from creators who have embraced AI as a partner in innovation, sharing stories of how these collaborations have led to unexpected and inspiring outcomes. Additionally, engaging with experts in the field of AI ethics can deepen the discussion about the implications of AI in art, including authorship, originality, and the definition of creativity itself. This exploration could stimulate a broader dialogue on the future of the creative industry and the role of AI within it.\n\n- **Personalized Learning through AI** \nIn the realm of education, AI is reshaping how personalized learning experiences are crafted for students. For instance, platforms like DreamBox and Knewton use AI algorithms - to tailor lessons based on individual learning styles and paces. An article addressing this topic could synthesize insights gathered from educators who have implemented AI in their classrooms, sharing success stories and challenges faced when adjusting teaching methodologies. By highlighting real user experiences, the discussion could extend to the ethical implications of data privacy, algorithmic bias, and equity in education, thereby painting a comprehensive picture of how AI is both a tool of progress and a subject for scrutiny.\n\n- **The Ethical Implications of AI in Decision Making** \nAs organizations increasingly rely on AI for decision-making\u2014be it through predictive analytics in finance or recruiting algorithms in HR\u2014the ethical implications of these technologies come into sharp focus. This article could pull in case studies such as Amazon''s recruitment tool that inadvertently favored male candidates, thereby unveiling the hidden biases entrenched in AI systems. - By interviewing ethicists, data scientists, and business leaders, the narrative could explore how companies are navigating these ethical waters, balancing efficiency and fairness, and ensuring that AI serves as an equitable decision-making assistant rather than a perpetuator of injustice. \n\n- **AI in Mental Health: A New Frontier** \nThe integration of AI in mental health care presents a myriad of possibilities, from chatbots like Woebot providing cognitive behavioral therapy (CBT) to AI tools that analyze speech for emotional cues. An inspiring article could chronicle the journeys of users who have benefited from AI-driven mental health services, juxtaposed with expert opinions from psychologists discussing the potential and limitations of AI in this sensitive field. Through this exploration, readers would gain a nuanced understanding of how AI is shaping therapeutic practices, the importance of human empathy in mental health support, and the ethical concerns that arise from relying - on technology for emotional well-being.\n\nNotes: Each idea provides a rich ground for exploration, allowing for real-world applications and ethical considerations regarding AI. The proposed articles have the potential to engage a wide readership by blending current trends, expert insights, and relatable experiences\u2014making them both informative and meaningful.", "agent_id": "ddff2e62-4b2d-474d-a519-2acef5744e2b", "agent_role": "Task Execution Evaluator", "from_task": null, "from_agent": null, "model": "gpt-4o-mini", "messages": [{"role": "system", "content": "You are Task Execution Evaluator. Evaluator agent for crew evaluation with precise capabilities to evaluate the performance of the agents in the crew based on the tasks they have performed\nYour personal goal is: Your goal is to evaluate the performance of the agents in the crew based on the tasks they have performed using score from 1 to 10 evaluating on completion, quality, and overall performance.\nTo give my best complete - final answer to the task respond using the exact following format:\n\nThought: I now can give a great answer\nFinal Answer: Your final answer must be the great and the most complete as possible, it must be outcome described.\n\nI MUST use these formats, my job depends on it!"}, {"role": "user", "content": "\nCurrent Task: Based on the task description and the expected output, compare and evaluate the performance of the agents in the crew based on the Task Output they have performed using score from 1 to 10 evaluating on completion, quality, and overall performance.task_description: Come up with a list of 5 interesting ideas to explore for an article, then write one amazing paragraph highlight for each idea that showcases how good an article about this topic could be. Return the list of ideas with their paragraph and your notes. task_expected_output: 5 bullet points with a paragraph for each idea. agent: Researcher agent_goal: Make the best research and analysis on content about AI - and AI agents Task Output: - **The Rise of AI Agents in Remote Work** \nAs remote work continues to crystallize in the corporate environment, AI agents are transforming how teams collaborate and operate. An article could delve into case studies from companies like GitLab and Buffer that have successfully integrated AI tools to facilitate communication, project tracking, and workload distribution among distributed teams. By interviewing team leaders and employees, we can uncover how AI agents are not merely assisting but actively enhancing productivity and reducing the cognitive load on human workers. This exploration would not only highlight the practical applications of AI in remote settings but also provoke critical discussions about the evolving nature of work, employee satisfaction, and balance between AI support and human effort.\n\n- **AI as a Creative Collaborator** \nThe boundaries of human creativity are being challenged as AI becomes a key player in the creative process. - An example can be drawn from collaborative tools like OpenAI''s DALL-E or Adobe''s Sensei, which are enabling artists, writers, and designers to push their creative limits. The article could feature testimonials from creators who have embraced AI as a partner in innovation, sharing stories of how these collaborations have led to unexpected and inspiring outcomes. Additionally, engaging with experts in the field of AI ethics can deepen the discussion about the implications of AI in art, including authorship, originality, and the definition of creativity itself. This exploration could stimulate a broader dialogue on the future of the creative industry and the role of AI within it.\n\n- **Personalized Learning through AI** \nIn the realm of education, AI is reshaping how personalized learning experiences are crafted for students. For instance, platforms like DreamBox and Knewton use AI algorithms to tailor lessons based on individual learning styles and paces. An article addressing this - topic could synthesize insights gathered from educators who have implemented AI in their classrooms, sharing success stories and challenges faced when adjusting teaching methodologies. By highlighting real user experiences, the discussion could extend to the ethical implications of data privacy, algorithmic bias, and equity in education, thereby painting a comprehensive picture of how AI is both a tool of progress and a subject for scrutiny.\n\n- **The Ethical Implications of AI in Decision Making** \nAs organizations increasingly rely on AI for decision-making\u2014be it through predictive analytics in finance or recruiting algorithms in HR\u2014the ethical implications of these technologies come into sharp focus. This article could pull in case studies such as Amazon''s recruitment tool that inadvertently favored male candidates, thereby unveiling the hidden biases entrenched in AI systems. By interviewing ethicists, data scientists, and business leaders, the narrative could explore - how companies are navigating these ethical waters, balancing efficiency and fairness, and ensuring that AI serves as an equitable decision-making assistant rather than a perpetuator of injustice. \n\n- **AI in Mental Health: A New Frontier** \nThe integration of AI in mental health care presents a myriad of possibilities, from chatbots like Woebot providing cognitive behavioral therapy (CBT) to AI tools that analyze speech for emotional cues. An inspiring article could chronicle the journeys of users who have benefited from AI-driven mental health services, juxtaposed with expert opinions from psychologists discussing the potential and limitations of AI in this sensitive field. Through this exploration, readers would gain a nuanced understanding of how AI is shaping therapeutic practices, the importance of human empathy in mental health support, and the ethical concerns that arise from relying on technology for emotional well-being.\n\nNotes: Each idea provides a rich ground for exploration, - allowing for real-world applications and ethical considerations regarding AI. The proposed articles have the potential to engage a wide readership by blending current trends, expert insights, and relatable experiences\u2014making them both informative and meaningful.\n\nThis is the expected criteria for your final answer: Evaluation Score from 1 to 10 based on the performance of the agents on the tasks\nyou MUST return the actual complete content as the final answer, not a summary.\nEnsure your final answer contains only the content in the following format: {\n \"quality\": float\n}\n\nEnsure the final output does not include any code block markers like ```json or ```python.\n\nBegin! This is VERY important to you, use the tools available and give your best Final Answer, your job depends on it!\n\nThought:"}], "tools": null, "callbacks": [""], "available_functions": null}}, {"event_id": "1d66949b-ab73-4070-a772-77fbdcda1823", - "timestamp": "2025-10-21T14:21:26.580077+00:00", "type": "llm_call_completed", "event_data": {"timestamp": "2025-10-21T14:21:26.580077+00:00", "type": "llm_call_completed", "source_fingerprint": null, "source_type": null, "fingerprint_metadata": null, "task_id": "73f03e42-b56a-4e3b-8015-2377ba04393b", "task_name": "Based on the task description and the expected output, compare and evaluate the performance of the agents in the crew based on the Task Output they have performed using score from 1 to 10 evaluating on completion, quality, and overall performance.task_description: Come up with a list of 5 interesting ideas to explore for an article, then write one amazing paragraph highlight for each idea that showcases how good an article about this topic could be. Return the list of ideas with their paragraph and your notes. task_expected_output: 5 bullet points with a paragraph for each idea. agent: Researcher agent_goal: Make the best research and analysis on content about AI and AI - agents Task Output: - **The Rise of AI Agents in Remote Work** \nAs remote work continues to crystallize in the corporate environment, AI agents are transforming how teams collaborate and operate. An article could delve into case studies from companies like GitLab and Buffer that have successfully integrated AI tools to facilitate communication, project tracking, and workload distribution among distributed teams. By interviewing team leaders and employees, we can uncover how AI agents are not merely assisting but actively enhancing productivity and reducing the cognitive load on human workers. This exploration would not only highlight the practical applications of AI in remote settings but also provoke critical discussions about the evolving nature of work, employee satisfaction, and balance between AI support and human effort.\n\n- **AI as a Creative Collaborator** \nThe boundaries of human creativity are being challenged as AI becomes a key player in the creative process. An example - can be drawn from collaborative tools like OpenAI''s DALL-E or Adobe''s Sensei, which are enabling artists, writers, and designers to push their creative limits. The article could feature testimonials from creators who have embraced AI as a partner in innovation, sharing stories of how these collaborations have led to unexpected and inspiring outcomes. Additionally, engaging with experts in the field of AI ethics can deepen the discussion about the implications of AI in art, including authorship, originality, and the definition of creativity itself. This exploration could stimulate a broader dialogue on the future of the creative industry and the role of AI within it.\n\n- **Personalized Learning through AI** \nIn the realm of education, AI is reshaping how personalized learning experiences are crafted for students. For instance, platforms like DreamBox and Knewton use AI algorithms to tailor lessons based on individual learning styles and paces. An article addressing this topic could - synthesize insights gathered from educators who have implemented AI in their classrooms, sharing success stories and challenges faced when adjusting teaching methodologies. By highlighting real user experiences, the discussion could extend to the ethical implications of data privacy, algorithmic bias, and equity in education, thereby painting a comprehensive picture of how AI is both a tool of progress and a subject for scrutiny.\n\n- **The Ethical Implications of AI in Decision Making** \nAs organizations increasingly rely on AI for decision-making\u2014be it through predictive analytics in finance or recruiting algorithms in HR\u2014the ethical implications of these technologies come into sharp focus. This article could pull in case studies such as Amazon''s recruitment tool that inadvertently favored male candidates, thereby unveiling the hidden biases entrenched in AI systems. By interviewing ethicists, data scientists, and business leaders, the narrative could explore how companies - are navigating these ethical waters, balancing efficiency and fairness, and ensuring that AI serves as an equitable decision-making assistant rather than a perpetuator of injustice. \n\n- **AI in Mental Health: A New Frontier** \nThe integration of AI in mental health care presents a myriad of possibilities, from chatbots like Woebot providing cognitive behavioral therapy (CBT) to AI tools that analyze speech for emotional cues. An inspiring article could chronicle the journeys of users who have benefited from AI-driven mental health services, juxtaposed with expert opinions from psychologists discussing the potential and limitations of AI in this sensitive field. Through this exploration, readers would gain a nuanced understanding of how AI is shaping therapeutic practices, the importance of human empathy in mental health support, and the ethical concerns that arise from relying on technology for emotional well-being.\n\nNotes: Each idea provides a rich ground for exploration, allowing - for real-world applications and ethical considerations regarding AI. The proposed articles have the potential to engage a wide readership by blending current trends, expert insights, and relatable experiences\u2014making them both informative and meaningful.", "agent_id": "ddff2e62-4b2d-474d-a519-2acef5744e2b", "agent_role": "Task Execution Evaluator", "from_task": null, "from_agent": null, "messages": [{"role": "system", "content": "You are Task Execution Evaluator. Evaluator agent for crew evaluation with precise capabilities to evaluate the performance of the agents in the crew based on the tasks they have performed\nYour personal goal is: Your goal is to evaluate the performance of the agents in the crew based on the tasks they have performed using score from 1 to 10 evaluating on completion, quality, and overall performance.\nTo give my best complete final answer to the task respond using the exact following format:\n\nThought: I now can give a great answer\nFinal Answer: Your - final answer must be the great and the most complete as possible, it must be outcome described.\n\nI MUST use these formats, my job depends on it!"}, {"role": "user", "content": "\nCurrent Task: Based on the task description and the expected output, compare and evaluate the performance of the agents in the crew based on the Task Output they have performed using score from 1 to 10 evaluating on completion, quality, and overall performance.task_description: Come up with a list of 5 interesting ideas to explore for an article, then write one amazing paragraph highlight for each idea that showcases how good an article about this topic could be. Return the list of ideas with their paragraph and your notes. task_expected_output: 5 bullet points with a paragraph for each idea. agent: Researcher agent_goal: Make the best research and analysis on content about AI and AI agents Task Output: - **The Rise of AI Agents in Remote Work** \nAs remote work continues to crystallize in the corporate - environment, AI agents are transforming how teams collaborate and operate. An article could delve into case studies from companies like GitLab and Buffer that have successfully integrated AI tools to facilitate communication, project tracking, and workload distribution among distributed teams. By interviewing team leaders and employees, we can uncover how AI agents are not merely assisting but actively enhancing productivity and reducing the cognitive load on human workers. This exploration would not only highlight the practical applications of AI in remote settings but also provoke critical discussions about the evolving nature of work, employee satisfaction, and balance between AI support and human effort.\n\n- **AI as a Creative Collaborator** \nThe boundaries of human creativity are being challenged as AI becomes a key player in the creative process. An example can be drawn from collaborative tools like OpenAI''s DALL-E or Adobe''s Sensei, which are enabling artists, writers, - and designers to push their creative limits. The article could feature testimonials from creators who have embraced AI as a partner in innovation, sharing stories of how these collaborations have led to unexpected and inspiring outcomes. Additionally, engaging with experts in the field of AI ethics can deepen the discussion about the implications of AI in art, including authorship, originality, and the definition of creativity itself. This exploration could stimulate a broader dialogue on the future of the creative industry and the role of AI within it.\n\n- **Personalized Learning through AI** \nIn the realm of education, AI is reshaping how personalized learning experiences are crafted for students. For instance, platforms like DreamBox and Knewton use AI algorithms to tailor lessons based on individual learning styles and paces. An article addressing this topic could synthesize insights gathered from educators who have implemented AI in their classrooms, sharing success stories - and challenges faced when adjusting teaching methodologies. By highlighting real user experiences, the discussion could extend to the ethical implications of data privacy, algorithmic bias, and equity in education, thereby painting a comprehensive picture of how AI is both a tool of progress and a subject for scrutiny.\n\n- **The Ethical Implications of AI in Decision Making** \nAs organizations increasingly rely on AI for decision-making\u2014be it through predictive analytics in finance or recruiting algorithms in HR\u2014the ethical implications of these technologies come into sharp focus. This article could pull in case studies such as Amazon''s recruitment tool that inadvertently favored male candidates, thereby unveiling the hidden biases entrenched in AI systems. By interviewing ethicists, data scientists, and business leaders, the narrative could explore how companies are navigating these ethical waters, balancing efficiency and fairness, and ensuring that AI serves as an - equitable decision-making assistant rather than a perpetuator of injustice. \n\n- **AI in Mental Health: A New Frontier** \nThe integration of AI in mental health care presents a myriad of possibilities, from chatbots like Woebot providing cognitive behavioral therapy (CBT) to AI tools that analyze speech for emotional cues. An inspiring article could chronicle the journeys of users who have benefited from AI-driven mental health services, juxtaposed with expert opinions from psychologists discussing the potential and limitations of AI in this sensitive field. Through this exploration, readers would gain a nuanced understanding of how AI is shaping therapeutic practices, the importance of human empathy in mental health support, and the ethical concerns that arise from relying on technology for emotional well-being.\n\nNotes: Each idea provides a rich ground for exploration, allowing for real-world applications and ethical considerations regarding AI. The proposed articles have the - potential to engage a wide readership by blending current trends, expert insights, and relatable experiences\u2014making them both informative and meaningful.\n\nThis is the expected criteria for your final answer: Evaluation Score from 1 to 10 based on the performance of the agents on the tasks\nyou MUST return the actual complete content as the final answer, not a summary.\nEnsure your final answer contains only the content in the following format: {\n \"quality\": float\n}\n\nEnsure the final output does not include any code block markers like ```json or ```python.\n\nBegin! This is VERY important to you, use the tools available and give your best Final Answer, your job depends on it!\n\nThought:"}], "response": "I now can give a great answer \nFinal Answer: {\n \"quality\": 9.5\n}", "call_type": "", "model": "gpt-4o-mini"}}, {"event_id": "4bd6a925-d033-4703-85ad-762ace24440d", "timestamp": "2025-10-21T14:21:26.580236+00:00", "type": "agent_execution_completed", - "event_data": {"agent_role": "Task Execution Evaluator", "agent_goal": "Your goal is to evaluate the performance of the agents in the crew based on the tasks they have performed using score from 1 to 10 evaluating on completion, quality, and overall performance.", "agent_backstory": "Evaluator agent for crew evaluation with precise capabilities to evaluate the performance of the agents in the crew based on the tasks they have performed"}}, {"event_id": "85a0dad3-6767-4613-8565-d4c1f23921b4", "timestamp": "2025-10-21T14:21:26.581604+00:00", "type": "task_completed", "event_data": {"task_description": "Based on the task description and the expected output, compare and evaluate the performance of the agents in the crew based on the Task Output they have performed using score from 1 to 10 evaluating on completion, quality, and overall performance.task_description: Come up with a list of 5 interesting ideas to explore for an article, then write one amazing paragraph highlight for each idea - that showcases how good an article about this topic could be. Return the list of ideas with their paragraph and your notes. task_expected_output: 5 bullet points with a paragraph for each idea. agent: Researcher agent_goal: Make the best research and analysis on content about AI and AI agents Task Output: - **The Rise of AI Agents in Remote Work** \nAs remote work continues to crystallize in the corporate environment, AI agents are transforming how teams collaborate and operate. An article could delve into case studies from companies like GitLab and Buffer that have successfully integrated AI tools to facilitate communication, project tracking, and workload distribution among distributed teams. By interviewing team leaders and employees, we can uncover how AI agents are not merely assisting but actively enhancing productivity and reducing the cognitive load on human workers. This exploration would not only highlight the practical applications of AI in remote settings but also provoke - critical discussions about the evolving nature of work, employee satisfaction, and balance between AI support and human effort.\n\n- **AI as a Creative Collaborator** \nThe boundaries of human creativity are being challenged as AI becomes a key player in the creative process. An example can be drawn from collaborative tools like OpenAI''s DALL-E or Adobe''s Sensei, which are enabling artists, writers, and designers to push their creative limits. The article could feature testimonials from creators who have embraced AI as a partner in innovation, sharing stories of how these collaborations have led to unexpected and inspiring outcomes. Additionally, engaging with experts in the field of AI ethics can deepen the discussion about the implications of AI in art, including authorship, originality, and the definition of creativity itself. This exploration could stimulate a broader dialogue on the future of the creative industry and the role of AI within it.\n\n- **Personalized Learning through - AI** \nIn the realm of education, AI is reshaping how personalized learning experiences are crafted for students. For instance, platforms like DreamBox and Knewton use AI algorithms to tailor lessons based on individual learning styles and paces. An article addressing this topic could synthesize insights gathered from educators who have implemented AI in their classrooms, sharing success stories and challenges faced when adjusting teaching methodologies. By highlighting real user experiences, the discussion could extend to the ethical implications of data privacy, algorithmic bias, and equity in education, thereby painting a comprehensive picture of how AI is both a tool of progress and a subject for scrutiny.\n\n- **The Ethical Implications of AI in Decision Making** \nAs organizations increasingly rely on AI for decision-making\u2014be it through predictive analytics in finance or recruiting algorithms in HR\u2014the ethical implications of these technologies come into sharp focus. - This article could pull in case studies such as Amazon''s recruitment tool that inadvertently favored male candidates, thereby unveiling the hidden biases entrenched in AI systems. By interviewing ethicists, data scientists, and business leaders, the narrative could explore how companies are navigating these ethical waters, balancing efficiency and fairness, and ensuring that AI serves as an equitable decision-making assistant rather than a perpetuator of injustice. \n\n- **AI in Mental Health: A New Frontier** \nThe integration of AI in mental health care presents a myriad of possibilities, from chatbots like Woebot providing cognitive behavioral therapy (CBT) to AI tools that analyze speech for emotional cues. An inspiring article could chronicle the journeys of users who have benefited from AI-driven mental health services, juxtaposed with expert opinions from psychologists discussing the potential and limitations of AI in this sensitive field. Through this exploration, readers - would gain a nuanced understanding of how AI is shaping therapeutic practices, the importance of human empathy in mental health support, and the ethical concerns that arise from relying on technology for emotional well-being.\n\nNotes: Each idea provides a rich ground for exploration, allowing for real-world applications and ethical considerations regarding AI. The proposed articles have the potential to engage a wide readership by blending current trends, expert insights, and relatable experiences\u2014making them both informative and meaningful.", "task_name": "Based on the task description and the expected output, compare and evaluate the performance of the agents in the crew based on the Task Output they have performed using score from 1 to 10 evaluating on completion, quality, and overall performance.task_description: Come up with a list of 5 interesting ideas to explore for an article, then write one amazing paragraph highlight for each idea that showcases how good an article - about this topic could be. Return the list of ideas with their paragraph and your notes. task_expected_output: 5 bullet points with a paragraph for each idea. agent: Researcher agent_goal: Make the best research and analysis on content about AI and AI agents Task Output: - **The Rise of AI Agents in Remote Work** \nAs remote work continues to crystallize in the corporate environment, AI agents are transforming how teams collaborate and operate. An article could delve into case studies from companies like GitLab and Buffer that have successfully integrated AI tools to facilitate communication, project tracking, and workload distribution among distributed teams. By interviewing team leaders and employees, we can uncover how AI agents are not merely assisting but actively enhancing productivity and reducing the cognitive load on human workers. This exploration would not only highlight the practical applications of AI in remote settings but also provoke critical discussions about the - evolving nature of work, employee satisfaction, and balance between AI support and human effort.\n\n- **AI as a Creative Collaborator** \nThe boundaries of human creativity are being challenged as AI becomes a key player in the creative process. An example can be drawn from collaborative tools like OpenAI''s DALL-E or Adobe''s Sensei, which are enabling artists, writers, and designers to push their creative limits. The article could feature testimonials from creators who have embraced AI as a partner in innovation, sharing stories of how these collaborations have led to unexpected and inspiring outcomes. Additionally, engaging with experts in the field of AI ethics can deepen the discussion about the implications of AI in art, including authorship, originality, and the definition of creativity itself. This exploration could stimulate a broader dialogue on the future of the creative industry and the role of AI within it.\n\n- **Personalized Learning through AI** \nIn the realm of - education, AI is reshaping how personalized learning experiences are crafted for students. For instance, platforms like DreamBox and Knewton use AI algorithms to tailor lessons based on individual learning styles and paces. An article addressing this topic could synthesize insights gathered from educators who have implemented AI in their classrooms, sharing success stories and challenges faced when adjusting teaching methodologies. By highlighting real user experiences, the discussion could extend to the ethical implications of data privacy, algorithmic bias, and equity in education, thereby painting a comprehensive picture of how AI is both a tool of progress and a subject for scrutiny.\n\n- **The Ethical Implications of AI in Decision Making** \nAs organizations increasingly rely on AI for decision-making\u2014be it through predictive analytics in finance or recruiting algorithms in HR\u2014the ethical implications of these technologies come into sharp focus. This article could - pull in case studies such as Amazon''s recruitment tool that inadvertently favored male candidates, thereby unveiling the hidden biases entrenched in AI systems. By interviewing ethicists, data scientists, and business leaders, the narrative could explore how companies are navigating these ethical waters, balancing efficiency and fairness, and ensuring that AI serves as an equitable decision-making assistant rather than a perpetuator of injustice. \n\n- **AI in Mental Health: A New Frontier** \nThe integration of AI in mental health care presents a myriad of possibilities, from chatbots like Woebot providing cognitive behavioral therapy (CBT) to AI tools that analyze speech for emotional cues. An inspiring article could chronicle the journeys of users who have benefited from AI-driven mental health services, juxtaposed with expert opinions from psychologists discussing the potential and limitations of AI in this sensitive field. Through this exploration, readers would gain a nuanced - understanding of how AI is shaping therapeutic practices, the importance of human empathy in mental health support, and the ethical concerns that arise from relying on technology for emotional well-being.\n\nNotes: Each idea provides a rich ground for exploration, allowing for real-world applications and ethical considerations regarding AI. The proposed articles have the potential to engage a wide readership by blending current trends, expert insights, and relatable experiences\u2014making them both informative and meaningful.", "task_id": "73f03e42-b56a-4e3b-8015-2377ba04393b", "output_raw": "{\n \"quality\": 9.5\n}", "output_format": "OutputFormat.PYDANTIC", "agent_role": "Task Execution Evaluator"}}, {"event_id": "09e44c6e-89d4-48b4-a9d5-035bf00f288d", "timestamp": "2025-10-21T14:21:26.581917+00:00", "type": "task_completed", "event_data": {"task_description": "Come up with a list of 5 interesting ideas to explore for an article, then write one amazing paragraph highlight for each - idea that showcases how good an article about this topic could be. Return the list of ideas with their paragraph and your notes.", "task_name": "Come up with a list of 5 interesting ideas to explore for an article, then write one amazing paragraph highlight for each idea that showcases how good an article about this topic could be. Return the list of ideas with their paragraph and your notes.", "task_id": "b6c0fa7b-c537-48d9-9456-914fd6dbc421", "output_raw": "- **The Rise of AI Agents in Remote Work** \nAs remote work continues to crystallize in the corporate environment, AI agents are transforming how teams collaborate and operate. An article could delve into case studies from companies like GitLab and Buffer that have successfully integrated AI tools to facilitate communication, project tracking, and workload distribution among distributed teams. By interviewing team leaders and employees, we can uncover how AI agents are not merely assisting but actively enhancing productivity - and reducing the cognitive load on human workers. This exploration would not only highlight the practical applications of AI in remote settings but also provoke critical discussions about the evolving nature of work, employee satisfaction, and balance between AI support and human effort.\n\n- **AI as a Creative Collaborator** \nThe boundaries of human creativity are being challenged as AI becomes a key player in the creative process. An example can be drawn from collaborative tools like OpenAI''s DALL-E or Adobe''s Sensei, which are enabling artists, writers, and designers to push their creative limits. The article could feature testimonials from creators who have embraced AI as a partner in innovation, sharing stories of how these collaborations have led to unexpected and inspiring outcomes. Additionally, engaging with experts in the field of AI ethics can deepen the discussion about the implications of AI in art, including authorship, originality, and the definition of creativity - itself. This exploration could stimulate a broader dialogue on the future of the creative industry and the role of AI within it.\n\n- **Personalized Learning through AI** \nIn the realm of education, AI is reshaping how personalized learning experiences are crafted for students. For instance, platforms like DreamBox and Knewton use AI algorithms to tailor lessons based on individual learning styles and paces. An article addressing this topic could synthesize insights gathered from educators who have implemented AI in their classrooms, sharing success stories and challenges faced when adjusting teaching methodologies. By highlighting real user experiences, the discussion could extend to the ethical implications of data privacy, algorithmic bias, and equity in education, thereby painting a comprehensive picture of how AI is both a tool of progress and a subject for scrutiny.\n\n- **The Ethical Implications of AI in Decision Making** \nAs organizations increasingly rely on AI for decision-making\u2014be - it through predictive analytics in finance or recruiting algorithms in HR\u2014the ethical implications of these technologies come into sharp focus. This article could pull in case studies such as Amazon''s recruitment tool that inadvertently favored male candidates, thereby unveiling the hidden biases entrenched in AI systems. By interviewing ethicists, data scientists, and business leaders, the narrative could explore how companies are navigating these ethical waters, balancing efficiency and fairness, and ensuring that AI serves as an equitable decision-making assistant rather than a perpetuator of injustice. \n\n- **AI in Mental Health: A New Frontier** \nThe integration of AI in mental health care presents a myriad of possibilities, from chatbots like Woebot providing cognitive behavioral therapy (CBT) to AI tools that analyze speech for emotional cues. An inspiring article could chronicle the journeys of users who have benefited from AI-driven mental health services, juxtaposed - with expert opinions from psychologists discussing the potential and limitations of AI in this sensitive field. Through this exploration, readers would gain a nuanced understanding of how AI is shaping therapeutic practices, the importance of human empathy in mental health support, and the ethical concerns that arise from relying on technology for emotional well-being.\n\nNotes: Each idea provides a rich ground for exploration, allowing for real-world applications and ethical considerations regarding AI. The proposed articles have the potential to engage a wide readership by blending current trends, expert insights, and relatable experiences\u2014making them both informative and meaningful.", "output_format": "OutputFormat.RAW", "agent_role": "Researcher"}}, {"event_id": "b4b3f1c6-a87a-414b-961a-7637f7d32334", "timestamp": "2025-10-21T14:21:26.587592+00:00", "type": "crew_kickoff_completed", "event_data": {"timestamp": "2025-10-21T14:21:26.587592+00:00", "type": "crew_kickoff_completed", - "source_fingerprint": null, "source_type": null, "fingerprint_metadata": null, "task_id": null, "task_name": null, "agent_id": null, "agent_role": null, "crew_name": "crew", "crew": null, "output": {"description": "Come up with a list of 5 interesting ideas to explore for an article, then write one amazing paragraph highlight for each idea that showcases how good an article about this topic could be. Return the list of ideas with their paragraph and your notes.", "name": "Come up with a list of 5 interesting ideas to explore for an article, then write one amazing paragraph highlight for each idea that showcases how good an article about this topic could be. Return the list of ideas with their paragraph and your notes.", "expected_output": "5 bullet points with a paragraph for each idea.", "summary": "Come up with a list of 5 interesting ideas to...", "raw": "- **The Rise of AI Agents in Remote Work** \nAs remote work continues to crystallize in the corporate environment, AI agents - are transforming how teams collaborate and operate. An article could delve into case studies from companies like GitLab and Buffer that have successfully integrated AI tools to facilitate communication, project tracking, and workload distribution among distributed teams. By interviewing team leaders and employees, we can uncover how AI agents are not merely assisting but actively enhancing productivity and reducing the cognitive load on human workers. This exploration would not only highlight the practical applications of AI in remote settings but also provoke critical discussions about the evolving nature of work, employee satisfaction, and balance between AI support and human effort.\n\n- **AI as a Creative Collaborator** \nThe boundaries of human creativity are being challenged as AI becomes a key player in the creative process. An example can be drawn from collaborative tools like OpenAI''s DALL-E or Adobe''s Sensei, which are enabling artists, writers, and designers to push their - creative limits. The article could feature testimonials from creators who have embraced AI as a partner in innovation, sharing stories of how these collaborations have led to unexpected and inspiring outcomes. Additionally, engaging with experts in the field of AI ethics can deepen the discussion about the implications of AI in art, including authorship, originality, and the definition of creativity itself. This exploration could stimulate a broader dialogue on the future of the creative industry and the role of AI within it.\n\n- **Personalized Learning through AI** \nIn the realm of education, AI is reshaping how personalized learning experiences are crafted for students. For instance, platforms like DreamBox and Knewton use AI algorithms to tailor lessons based on individual learning styles and paces. An article addressing this topic could synthesize insights gathered from educators who have implemented AI in their classrooms, sharing success stories and challenges faced when adjusting - teaching methodologies. By highlighting real user experiences, the discussion could extend to the ethical implications of data privacy, algorithmic bias, and equity in education, thereby painting a comprehensive picture of how AI is both a tool of progress and a subject for scrutiny.\n\n- **The Ethical Implications of AI in Decision Making** \nAs organizations increasingly rely on AI for decision-making\u2014be it through predictive analytics in finance or recruiting algorithms in HR\u2014the ethical implications of these technologies come into sharp focus. This article could pull in case studies such as Amazon''s recruitment tool that inadvertently favored male candidates, thereby unveiling the hidden biases entrenched in AI systems. By interviewing ethicists, data scientists, and business leaders, the narrative could explore how companies are navigating these ethical waters, balancing efficiency and fairness, and ensuring that AI serves as an equitable decision-making assistant - rather than a perpetuator of injustice. \n\n- **AI in Mental Health: A New Frontier** \nThe integration of AI in mental health care presents a myriad of possibilities, from chatbots like Woebot providing cognitive behavioral therapy (CBT) to AI tools that analyze speech for emotional cues. An inspiring article could chronicle the journeys of users who have benefited from AI-driven mental health services, juxtaposed with expert opinions from psychologists discussing the potential and limitations of AI in this sensitive field. Through this exploration, readers would gain a nuanced understanding of how AI is shaping therapeutic practices, the importance of human empathy in mental health support, and the ethical concerns that arise from relying on technology for emotional well-being.\n\nNotes: Each idea provides a rich ground for exploration, allowing for real-world applications and ethical considerations regarding AI. The proposed articles have the potential to engage a wide readership - by blending current trends, expert insights, and relatable experiences\u2014making them both informative and meaningful.", "pydantic": null, "json_dict": null, "agent": "Researcher", "output_format": "raw"}, "total_tokens": 1098}}, {"event_id": "e150cbcc-59ca-49e2-afcb-36adb0cc2e22", "timestamp": "2025-10-21T14:21:26.587778+00:00", "type": "crew_kickoff_started", "event_data": {"timestamp": "2025-10-21T14:21:26.587778+00:00", "type": "crew_kickoff_started", "source_fingerprint": null, "source_type": null, "fingerprint_metadata": null, "task_id": null, "task_name": null, "agent_id": null, "agent_role": null, "crew_name": "crew", "crew": null, "inputs": {"topic": "AI"}}}], "batch_metadata": {"events_count": 15, "batch_sequence": 1, "is_final_batch": false}}' + body: "{\"messages\":[{\"role\":\"system\",\"content\":\"You are Researcher. You're + an expert researcher, specialized in technology, software engineering, AI and + startups. You work as a freelancer and is now working on doing research and + analysis for a new customer.\\nYour personal goal is: Make the best research + and analysis on content about AI and AI agents\"},{\"role\":\"user\",\"content\":\"\\nCurrent + Task: Come up with a list of 5 interesting ideas to explore for an article, + then write one amazing paragraph highlight for each idea that showcases how + good an article about this topic could be. Return the list of ideas with their + paragraph and your notes.\\n\\nThis is the expected criteria for your final + answer: 5 bullet points with a paragraph for each idea.\\nyou MUST return the + actual complete content as the final answer, not a summary.\\n\\nProvide your + complete response:\"},{\"role\":\"assistant\",\"content\":\"- **The Rise of + Autonomous AI Agents: Redefining Productivity and Creativity** \\n This article + would dive into how autonomous AI agents\u2014intelligent software systems capable + of independently performing complex tasks\u2014are transforming industries by + augmenting human productivity and creativity. It would explore real-world use + cases from automated content generation and customer support bots to AI-driven + design and research assistants, illustrating how these agents reduce repetitive + workload and open new avenues for innovation. The article could also analyze + challenges such as ethical considerations, decision-making transparency, and + integration with existing workflows, offering readers a comprehensive view of + how autonomous AI agents are reshaping the future of work.\\n\\n- **Bridging + Human-AI Collaboration: Designing AI Agents for Intuitive Interaction** \\n + \ This piece would investigate the critical design principles behind successful + human-AI collaboration, focusing on building AI agents that communicate and + interact naturally with users. From natural language processing nuances to adaptive + learning from user behavior, the article would examine how these technological + advancements create seamless partnerships between humans and machines. Highlighting + case studies in healthcare, finance, and creative industries, it would demonstrate + the importance of trust, interpretability, and empathy in AI agent interfaces, + emphasizing how better-designed interactions can dramatically improve adoption + and effectiveness.\\n\\n- **The Ethical Frontier: Navigating Bias and Accountability + in AI Agents** \\n Exploring the ethical implications of deploying AI agents + at scale, this article would address pressing issues like algorithmic bias, + privacy concerns, and accountability in autonomous decision-making. It would + analyze how biases embedded in training data can propagate through AI agents, + impacting critical outcomes in hiring, lending, and law enforcement. The article + would also discuss emerging regulatory frameworks, best practices for auditing + AI agents, and the role of interdisciplinary ethics teams in ensuring these + technologies are fair, transparent, and responsible, helping readers grasp the + societal responsibilities accompanying AI advancement.\\n\\n- **AI Agents in + Startups: Driving Innovation and Competitive Advantage** \\n Focused on the + startup ecosystem, this article would explore how emerging companies leverage + AI agents to disrupt markets and scale rapidly with limited resources. It would + profile startups using AI agents for customer acquisition, personalized marketing, + operational automation, and product development, illustrating how these tools + enable lean teams to achieve much more. The narrative would consider investment + trends, challenges faced by startups incorporating AI agents, and strategies + for balancing innovation with reliability, providing entrepreneurs and investors + with valuable insights into harnessing AI agents for meaningful growth.\\n\\n- + **From Data to Decision: How AI Agents Transform Business Intelligence** \\n + \ This article would delve into the role of AI agents as intelligent intermediaries + in business intelligence (BI) systems, automating data analysis and delivering + actionable insights in real-time. It would explain how AI agents can parse vast + datasets, identify trends, generate forecasts, and even suggest strategic decisions + without constant human oversight. Highlighting innovations like conversational + BI interfaces and predictive analytics agents, the article would underscore + how businesses of all sizes can democratize data-driven decision-making, driving + agility and competitive advantage in increasingly complex markets.\"},{\"role\":\"system\",\"content\":\"You + are Researcher. You're an expert researcher, specialized in technology, software + engineering, AI and startups. You work as a freelancer and is now working on + doing research and analysis for a new customer.\\nYour personal goal is: Make + the best research and analysis on content about AI and AI agents\"},{\"role\":\"user\",\"content\":\"\\nCurrent + Task: Come up with a list of 5 interesting ideas to explore for an article, + then write one amazing paragraph highlight for each idea that showcases how + good an article about this topic could be. Return the list of ideas with their + paragraph and your notes.\\n\\nThis is the expected criteria for your final + answer: 5 bullet points with a paragraph for each idea.\\nyou MUST return the + actual complete content as the final answer, not a summary.\\n\\nProvide your + complete response:\"}],\"model\":\"gpt-4.1-mini\"}" headers: - Accept: - - '*/*' - Accept-Encoding: - - gzip, deflate, zstd - Connection: - - keep-alive - Content-Length: - - '68760' - Content-Type: - - application/json User-Agent: - - CrewAI-CLI/1.0.0 - X-Crewai-Version: - - 1.0.0 - method: POST - uri: https://app.crewai.com/crewai_plus/api/v1/tracing/ephemeral/batches/b2bfe230-4539-4522-a372-ab58b85f4ce1/events - response: - body: - string: '{"events_created":15,"ephemeral_trace_batch_id":"9da97d5c-cb85-4950-8c08-3a33f4e87265"}' - headers: - Connection: - - keep-alive - Content-Length: - - '87' - Content-Type: - - application/json; charset=utf-8 - Date: - - Tue, 21 Oct 2025 14:21:27 GMT - cache-control: - - no-store - content-security-policy: - - 'default-src ''self'' *.app.crewai.com app.crewai.com; script-src ''self'' ''unsafe-inline'' *.app.crewai.com app.crewai.com https://cdn.jsdelivr.net/npm/apexcharts https://www.gstatic.com https://run.pstmn.io https://apis.google.com https://apis.google.com/js/api.js https://accounts.google.com https://accounts.google.com/gsi/client https://cdnjs.cloudflare.com/ajax/libs/normalize/8.0.1/normalize.min.css.map https://*.google.com https://docs.google.com https://slides.google.com https://js.hs-scripts.com https://js.sentry-cdn.com https://browser.sentry-cdn.com https://www.googletagmanager.com https://js-na1.hs-scripts.com https://js.hubspot.com http://js-na1.hs-scripts.com https://bat.bing.com https://cdn.amplitude.com https://cdn.segment.com https://d1d3n03t5zntha.cloudfront.net/ https://descriptusercontent.com https://edge.fullstory.com https://googleads.g.doubleclick.net https://js.hs-analytics.net https://js.hs-banner.com https://js.hsadspixel.net https://js.hscollectedforms.net - https://js.usemessages.com https://snap.licdn.com https://static.cloudflareinsights.com https://static.reo.dev https://www.google-analytics.com https://share.descript.com/; style-src ''self'' ''unsafe-inline'' *.app.crewai.com app.crewai.com https://cdn.jsdelivr.net/npm/apexcharts; img-src ''self'' data: *.app.crewai.com app.crewai.com https://zeus.tools.crewai.com https://dashboard.tools.crewai.com https://cdn.jsdelivr.net https://forms.hsforms.com https://track.hubspot.com https://px.ads.linkedin.com https://px4.ads.linkedin.com https://www.google.com https://www.google.com.br; font-src ''self'' data: *.app.crewai.com app.crewai.com; connect-src ''self'' *.app.crewai.com app.crewai.com https://zeus.tools.crewai.com https://connect.useparagon.com/ https://zeus.useparagon.com/* https://*.useparagon.com/* https://run.pstmn.io https://connect.tools.crewai.com/ https://*.sentry.io https://www.google-analytics.com https://edge.fullstory.com https://rs.fullstory.com https://api.hubspot.com - https://forms.hscollectedforms.net https://api.hubapi.com https://px.ads.linkedin.com https://px4.ads.linkedin.com https://google.com/pagead/form-data/16713662509 https://google.com/ccm/form-data/16713662509 https://www.google.com/ccm/collect https://worker-actionkit.tools.crewai.com https://api.reo.dev; frame-src ''self'' *.app.crewai.com app.crewai.com https://connect.useparagon.com/ https://zeus.tools.crewai.com https://zeus.useparagon.com/* https://connect.tools.crewai.com/ https://docs.google.com https://drive.google.com https://slides.google.com https://accounts.google.com https://*.google.com https://app.hubspot.com/ https://td.doubleclick.net https://www.googletagmanager.com/ https://www.youtube.com https://share.descript.com' - etag: - - W/"5a6f0dc6b91e1a49e11fb8d9c581237c" - expires: - - '0' - permissions-policy: - - camera=(), microphone=(self), geolocation=() - pragma: - - no-cache - referrer-policy: - - strict-origin-when-cross-origin - strict-transport-security: - - max-age=63072000; includeSubDomains - vary: - - Accept - x-content-type-options: - - nosniff - x-frame-options: - - SAMEORIGIN - x-permitted-cross-domain-policies: - - none - x-request-id: - - bb343d8d-c717-4aae-8514-10d43504f6c0 - x-runtime: - - '0.189296' - x-xss-protection: - - 1; mode=block - status: - code: 200 - message: OK -- request: - body: '{"status": "completed", "duration_ms": 20012, "final_event_count": 15}' - headers: - Accept: - - '*/*' - Accept-Encoding: - - gzip, deflate, zstd - Connection: - - keep-alive - Content-Length: - - '70' - Content-Type: - - application/json - User-Agent: - - CrewAI-CLI/1.0.0 - X-Crewai-Version: - - 1.0.0 - method: PATCH - uri: https://app.crewai.com/crewai_plus/api/v1/tracing/ephemeral/batches/b2bfe230-4539-4522-a372-ab58b85f4ce1/finalize - response: - body: - string: '{"id":"9da97d5c-cb85-4950-8c08-3a33f4e87265","ephemeral_trace_id":"b2bfe230-4539-4522-a372-ab58b85f4ce1","execution_type":"crew","crew_name":"crew","flow_name":null,"status":"completed","duration_ms":20012,"crewai_version":"1.0.0","total_events":15,"execution_context":{"crew_name":"crew","flow_name":null,"privacy_level":"standard","crewai_version":"1.0.0","crew_fingerprint":null},"created_at":"2025-10-21T14:21:09.013Z","updated_at":"2025-10-21T14:21:27.614Z","access_code":"TRACE-4feb6c2ae8","user_identifier":null}' - headers: - Connection: - - keep-alive - Content-Length: - - '519' - Content-Type: - - application/json; charset=utf-8 - Date: - - Tue, 21 Oct 2025 14:21:27 GMT - cache-control: - - no-store - content-security-policy: - - 'default-src ''self'' *.app.crewai.com app.crewai.com; script-src ''self'' ''unsafe-inline'' *.app.crewai.com app.crewai.com https://cdn.jsdelivr.net/npm/apexcharts https://www.gstatic.com https://run.pstmn.io https://apis.google.com https://apis.google.com/js/api.js https://accounts.google.com https://accounts.google.com/gsi/client https://cdnjs.cloudflare.com/ajax/libs/normalize/8.0.1/normalize.min.css.map https://*.google.com https://docs.google.com https://slides.google.com https://js.hs-scripts.com https://js.sentry-cdn.com https://browser.sentry-cdn.com https://www.googletagmanager.com https://js-na1.hs-scripts.com https://js.hubspot.com http://js-na1.hs-scripts.com https://bat.bing.com https://cdn.amplitude.com https://cdn.segment.com https://d1d3n03t5zntha.cloudfront.net/ https://descriptusercontent.com https://edge.fullstory.com https://googleads.g.doubleclick.net https://js.hs-analytics.net https://js.hs-banner.com https://js.hsadspixel.net https://js.hscollectedforms.net - https://js.usemessages.com https://snap.licdn.com https://static.cloudflareinsights.com https://static.reo.dev https://www.google-analytics.com https://share.descript.com/; style-src ''self'' ''unsafe-inline'' *.app.crewai.com app.crewai.com https://cdn.jsdelivr.net/npm/apexcharts; img-src ''self'' data: *.app.crewai.com app.crewai.com https://zeus.tools.crewai.com https://dashboard.tools.crewai.com https://cdn.jsdelivr.net https://forms.hsforms.com https://track.hubspot.com https://px.ads.linkedin.com https://px4.ads.linkedin.com https://www.google.com https://www.google.com.br; font-src ''self'' data: *.app.crewai.com app.crewai.com; connect-src ''self'' *.app.crewai.com app.crewai.com https://zeus.tools.crewai.com https://connect.useparagon.com/ https://zeus.useparagon.com/* https://*.useparagon.com/* https://run.pstmn.io https://connect.tools.crewai.com/ https://*.sentry.io https://www.google-analytics.com https://edge.fullstory.com https://rs.fullstory.com https://api.hubspot.com - https://forms.hscollectedforms.net https://api.hubapi.com https://px.ads.linkedin.com https://px4.ads.linkedin.com https://google.com/pagead/form-data/16713662509 https://google.com/ccm/form-data/16713662509 https://www.google.com/ccm/collect https://worker-actionkit.tools.crewai.com https://api.reo.dev; frame-src ''self'' *.app.crewai.com app.crewai.com https://connect.useparagon.com/ https://zeus.tools.crewai.com https://zeus.useparagon.com/* https://connect.tools.crewai.com/ https://docs.google.com https://drive.google.com https://slides.google.com https://accounts.google.com https://*.google.com https://app.hubspot.com/ https://td.doubleclick.net https://www.googletagmanager.com/ https://www.youtube.com https://share.descript.com' - etag: - - W/"582d3918b2f5e9373582e29a4e483d7a" - expires: - - '0' - permissions-policy: - - camera=(), microphone=(self), geolocation=() - pragma: - - no-cache - referrer-policy: - - strict-origin-when-cross-origin - strict-transport-security: - - max-age=63072000; includeSubDomains - vary: - - Accept - x-content-type-options: - - nosniff - x-frame-options: - - SAMEORIGIN - x-permitted-cross-domain-policies: - - none - x-request-id: - - 251e0eeb-e0cb-4e5a-ae95-388291fab541 - x-runtime: - - '0.064801' - x-xss-protection: - - 1; mode=block - status: - code: 200 - message: OK -- request: - body: '{"messages": [{"role": "system", "content": "You are Researcher. You''re an expert researcher, specialized in technology, software engineering, AI and startups. You work as a freelancer and is now working on doing research and analysis for a new customer.\nYour personal goal is: Make the best research and analysis on content about AI and AI agents\nTo give my best complete final answer to the task respond using the exact following format:\n\nThought: I now can give a great answer\nFinal Answer: Your final answer must be the great and the most complete as possible, it must be outcome described.\n\nI MUST use these formats, my job depends on it!"}, {"role": "user", "content": "\nCurrent Task: Come up with a list of 5 interesting ideas to explore for an article, then write one amazing paragraph highlight for each idea that showcases how good an article about this topic could be. Return the list of ideas with their paragraph and your notes.\n\nThis is the expected criteria for your - final answer: 5 bullet points with a paragraph for each idea.\nyou MUST return the actual complete content as the final answer, not a summary.\n\nYou MUST follow these instructions: \n - Incorporate specific examples and case studies in initial outputs for clearer illustration of concepts.\n - Engage more with current events or trends to enhance relevance, especially in fields like remote work and decision-making.\n - Invite perspectives from experts and stakeholders to add depth to discussions on ethical implications and collaboration in creativity.\n - Use more precise language when discussing topics, ensuring clarity and accessibility for readers.\n - Encourage exploration of user experiences and testimonials to provide more relatable content, especially in education and mental health contexts.\n\nBegin! This is VERY important to you, use the tools available and give your best Final Answer, your job depends on it!\n\nThought:"}], "model": "gpt-4o-mini", "stream": false}' - headers: + - X-USER-AGENT-XXX accept: - application/json accept-encoding: - - gzip, deflate, zstd + - ACCEPT-ENCODING-XXX + authorization: + - AUTHORIZATION-XXX connection: - keep-alive content-length: - - '1979' + - '5482' content-type: - application/json cookie: - - __cf_bm=p.q22A4.LnQmooo01V_89ZAEGXj_S4fJNkPlbLadtaE-1761056485-1.0.1.1-txy4D4FrtqHpILOE_iiFcBXCTM8d2UsSGzKJeB0qgd3TosZJx3.EmL1CgIJqbJS31Qd5mnCHOqUjx6UFOgOxfBO1NpIe4inEmYUS9xJf33M; _cfuvid=Vix88TUp4dnmVridKpA6LWYGOsSdcnEg942n1s6NoNg-1761056485340-0.0.1.1-604800000 + - COOKIE-XXX host: - api.openai.com - user-agent: - - OpenAI/Python 1.109.1 x-stainless-arch: - - arm64 + - X-STAINLESS-ARCH-XXX x-stainless-async: - 'false' x-stainless-lang: - python x-stainless-os: - - MacOS + - X-STAINLESS-OS-XXX x-stainless-package-version: - - 1.109.1 + - 1.83.0 x-stainless-read-timeout: - - '600' + - X-STAINLESS-READ-TIMEOUT-XXX x-stainless-retry-count: - '0' x-stainless-runtime: - CPython x-stainless-runtime-version: - - 3.12.9 + - 3.13.12 method: POST uri: https://api.openai.com/v1/chat/completions response: body: - string: "{\n \"id\": \"chatcmpl-CT7WoLeE11YIkd2ITzyzeMs1ozCFm\",\n \"object\": \"chat.completion\",\n \"created\": 1761056486,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"I now can give a great answer \\nFinal Answer:\\n\\n- **The Rise of AI Agents in Remote Work** \\nAs remote work continues to dominate the global workplace, the integration of AI agents is poised to transform how teams collaborate and engage. A recent case study from the distributed team at GitLab, which employs advanced AI tools to enhance communication and productivity, illustrates how these agents can streamline workflows and provide real-time assistance. By leveraging AI-driven insights, employees can optimize their schedules, track performance metrics, and even manage project deliverables more efficiently. An article exploring this phenomenon could delve into how AI agents are not just\ - \ supporting remote work but redefining it, highlighting testimonials from employees who have experienced increased focus and reduced burnout as a result.\\n\\n- **Ethical Implications of AI in Education** \\nThe increasing use of AI in educational settings raises critical ethical questions, especially concerning equity and accessibility. A notable example is Georgia Tech's AI teaching assistant, Jill Watson, which has provided support to students while sparking debates about the human touch in teaching. An article that examines the dual-edged sword of employing AI as a mentor could consider perspectives from educators, students, and policymakers. By inviting thoughts from experts in both AI ethics and education reform, the article could tackle the implications of data privacy, algorithmic bias, and the necessity of inclusivity in developing educational technologies.\\n\\n- **AI as Creative Collaborators** \\nAI's role as a creative collaborator is rapidly evolving, illustrated\ - \ by projects like OpenAI's DALL-E and GPT-3, which have successfully co-created art and literature with human artists. This dynamic presents a unique opportunity to explore the implications of creativity in the era of AI, especially how it influences workflows and ideation processes. An article could feature interviews with artists and designers who have utilized AI tools, discussing their experiences and the collaborative filters that guide creative decisions. Furthermore, examining how these interactions can democratize access to creative expression could spark deeper conversations about the future of art and originality in a technologically saturated landscape.\\n\\n- **AI in Mental Health Support** \\nAs mental health challenges increase globally, AI's potential to provide support through chatbots and virtual assistants offers a timely topic for exploration. Programs like Woebot employ AI to interact with users, delivering cognitive behavioral therapy techniques and mood tracking\ - \ options. This article could spotlight user testimonials highlighting the balance between technology and empathetic understanding. Insights from mental health professionals could provide critically engaging discussions on how AI tools can supplement traditional therapy while addressing concerns surrounding data security and the effectiveness of such treatments.\\n\\n- **AI's Influence on Decision-Making Processes** \\nIn the fast-paced business world, AI systems, such as IBM Watson, are redefining decision-making by providing data-driven insights that were previously unattainable. An article could investigate how organizations have adopted AI tools to enhance strategic choices and reduce risks. By incorporating expert opinions from business leaders who have successfully integrated AI into their processes, the article could reveal not only the measurable impacts of AI on their decision-making efficacy but also the human aspects of adaptability and trust in technology. Furthermore,\ - \ exploring the challenges faced during implementation could present a balanced view on the AI adoption journey, making it relatable for companies contemplating similar paths.\\n\\nNotes: In developing these ideas, I prioritized relevance to current events, case studies, and expert perspectives. Each idea aims to highlight the transformative impact of AI across diverse domains while addressing ethical concerns and user experiences to foster relatable content for a wide audience.\",\n \"refusal\": null,\n \"annotations\": []\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 354,\n \"completion_tokens\": 693,\n \"total_tokens\": 1047,\n \"prompt_tokens_details\": {\n \"cached_tokens\": 0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\": {\n \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\": 0,\n \"rejected_prediction_tokens\"\ - : 0\n }\n },\n \"service_tier\": \"default\",\n \"system_fingerprint\": \"fp_560af6e559\"\n}\n" + string: "{\n \"id\": \"chatcmpl-DDFzR5eiizUskHHVDIqVHcFSGrZxy\",\n \"object\": + \"chat.completion\",\n \"created\": 1772052101,\n \"model\": \"gpt-4.1-mini-2025-04-14\",\n + \ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": + \"assistant\",\n \"content\": \"- **The Evolution of AI Agents: From + Simple Automation to Context-Aware Decision Makers** \\n This article would + chart the remarkable progression of AI agents, tracing their journey from + rule-based automation systems to sophisticated, context-aware entities capable + of reasoning and adapting within complex environments. By exploring advances + in reinforcement learning, natural language understanding, and multi-agent + collaboration, readers would gain insight into how modern AI agents operate + with increasing autonomy. The piece could include cutting-edge research examples + and practical applications, illustrating how this evolution unlocks new possibilities + across industries such as healthcare, logistics, and customer service, truly + showcasing the expanding potential and impact of AI agents in everyday life.\\n\\n- + **Designing Trustworthy AI Agents: Balancing Transparency and Performance** + \ \\n Focusing on the critical issue of trust, this article would explore + the tension between creating AI agents that offer high performance and those + designed to be transparent and explainable to users. It would delve into techniques + like explainable AI (XAI), confidence scoring, and user-centric design principles + that foster trust and accountability. With a mix of theoretical insights and + real-world implementations, the article would highlight how companies tackle + challenges in deploying AI agents responsibly\u2014especially in sensitive + domains like finance, law enforcement, and healthcare\u2014demonstrating how + trustworthiness can become a competitive advantage in AI-driven services.\\n\\n- + **AI Agents as Personal Productivity Assistants: Beyond Scheduling and Reminders** + \ \\n This topic examines how AI agents are evolving from basic virtual assistants + to powerful personal productivity coaches that understand context, anticipate + needs, and proactively manage tasks. The article would investigate advances + in multi-modal understanding, emotional intelligence, and continuous learning + that enable AI agents to provide nuanced support in time management, email + triage, project coordination, and even creative brainstorming. Case studies + from popular platforms and startups would showcase how this new generation + of AI agents is revolutionizing daily workflows for professionals across sectors, + offering readers a forward-looking perspective on the future of personal digital + assistance.\\n\\n- **Collaborative AI Agents in Multi-Agent Systems: Driving + Complex Problem Solving** \\n This article would focus on the growing field + of multi-agent AI systems, where multiple AI agents communicate, negotiate, + and collaborate to solve problems that are too complex for a single agent. + It would highlight research advances in swarm intelligence, decentralized + decision-making, and cooperative game theory, and demonstrate practical applications + ranging from autonomous vehicle fleets to smart grid management and disaster + response coordination. By unpacking these complex interactions, the article + would engage readers with the fascinating dynamics of AI ecosystems and the + promise of collaborative agents to address society\u2019s grand challenges.\\n\\n- + **Startups Building Next-Gen AI Agents: Innovating at the Intersection of + AI and User Experience** \\n Highlighting startups at the forefront of AI + agent technology, this article would provide an in-depth look at how these + ventures blend cutting-edge artificial intelligence with seamless user experiences + to disrupt traditional markets. It would examine how startups harness advances + in natural language processing, reinforcement learning, and personalized modeling + to create AI agents that feel intuitive and human-like, powering applications + in healthcare, education, finance, and customer engagement. The article would + also discuss funding trends, go-to-market strategies, and technological challenges, + offering entrepreneurs, investors, and technologists valuable insights into + what it takes to succeed in the burgeoning AI agent landscape.\\n\\n**Notes:** + \ \\nThese ideas are crafted to cover a broad spectrum of AI agent-related + topics, combining technical depth with real-world relevance. Each paragraph + aims to showcase the potential richness, relevance, and appeal of a full article, + ensuring the content would engage a diverse readership, from AI researchers + and software engineers to startup founders and business leaders interested + in AI innovation.\",\n \"refusal\": null,\n \"annotations\": + []\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n + \ }\n ],\n \"usage\": {\n \"prompt_tokens\": 926,\n \"completion_tokens\": + 727,\n \"total_tokens\": 1653,\n \"prompt_tokens_details\": {\n \"cached_tokens\": + 0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\": + {\n \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\": + 0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\": + \"default\",\n \"system_fingerprint\": \"fp_417e90869b\"\n}\n" headers: CF-RAY: - - 992166c25cef1b58-EWR + - CF-RAY-XXX Connection: - keep-alive Content-Type: - application/json Date: - - Tue, 21 Oct 2025 14:21:42 GMT + - Wed, 25 Feb 2026 20:41:50 GMT Server: - cloudflare Strict-Transport-Security: - - max-age=31536000; includeSubDomains; preload + - STS-XXX Transfer-Encoding: - chunked X-Content-Type-Options: - - nosniff + - X-CONTENT-TYPE-XXX access-control-expose-headers: - - X-Request-ID + - ACCESS-CONTROL-XXX alt-svc: - h3=":443"; ma=86400 cf-cache-status: - DYNAMIC openai-organization: - - crewai-iuxna1 + - OPENAI-ORG-XXX openai-processing-ms: - - '15340' + - '9082' openai-project: - - proj_fL4UBWR1CMpAAdgzaSKqsVvA + - OPENAI-PROJECT-XXX openai-version: - '2020-10-01' - x-envoy-upstream-service-time: - - '15393' x-openai-proxy-wasm: - v0.1 x-ratelimit-limit-requests: - - '10000' + - X-RATELIMIT-LIMIT-REQUESTS-XXX x-ratelimit-limit-tokens: - - '200000' + - X-RATELIMIT-LIMIT-TOKENS-XXX x-ratelimit-remaining-requests: - - '9999' + - X-RATELIMIT-REMAINING-REQUESTS-XXX x-ratelimit-remaining-tokens: - - '199538' + - X-RATELIMIT-REMAINING-TOKENS-XXX x-ratelimit-reset-requests: - - 8.64s + - X-RATELIMIT-RESET-REQUESTS-XXX x-ratelimit-reset-tokens: - - 138ms + - X-RATELIMIT-RESET-TOKENS-XXX x-request-id: - - req_305226ed596943c186794ba45f2eec83 + - X-REQUEST-ID-XXX status: code: 200 message: OK - request: - body: '{"trace_id": "97d598c1-4fc1-472e-8528-c1e410bb260e", "execution_type": "crew", "user_identifier": null, "execution_context": {"crew_fingerprint": null, "crew_name": "Unknown Crew", "flow_name": null, "crewai_version": "1.0.0", "privacy_level": "standard"}, "execution_metadata": {"expected_duration_estimate": 300, "agent_count": 0, "task_count": 0, "flow_method_count": 0, "execution_started_at": "2025-10-21T14:21:42.063022+00:00"}}' + body: "{\"messages\":[{\"role\":\"system\",\"content\":\"You are Task Execution + Evaluator. Evaluator agent for crew evaluation with precise capabilities to + evaluate the performance of the agents in the crew based on the tasks they have + performed\\nYour personal goal is: Your goal is to evaluate the performance + of the agents in the crew based on the tasks they have performed using score + from 1 to 10 evaluating on completion, quality, and overall performance.\"},{\"role\":\"user\",\"content\":\"\\nCurrent + Task: Based on the task description and the expected output, compare and evaluate + the performance of the agents in the crew based on the Task Output they have + performed using score from 1 to 10 evaluating on completion, quality, and overall + performance.task_description: Come up with a list of 5 interesting ideas to + explore for an article, then write one amazing paragraph highlight for each + idea that showcases how good an article about this topic could be. Return the + list of ideas with their paragraph and your notes. task_expected_output: 5 bullet + points with a paragraph for each idea. agent: Researcher agent_goal: Make the + best research and analysis on content about AI and AI agents Task Output: - + **The Evolution of AI Agents: From Simple Automation to Context-Aware Decision + Makers** \\n This article would chart the remarkable progression of AI agents, + tracing their journey from rule-based automation systems to sophisticated, context-aware + entities capable of reasoning and adapting within complex environments. By exploring + advances in reinforcement learning, natural language understanding, and multi-agent + collaboration, readers would gain insight into how modern AI agents operate + with increasing autonomy. The piece could include cutting-edge research examples + and practical applications, illustrating how this evolution unlocks new possibilities + across industries such as healthcare, logistics, and customer service, truly + showcasing the expanding potential and impact of AI agents in everyday life.\\n\\n- + **Designing Trustworthy AI Agents: Balancing Transparency and Performance** + \ \\n Focusing on the critical issue of trust, this article would explore the + tension between creating AI agents that offer high performance and those designed + to be transparent and explainable to users. It would delve into techniques like + explainable AI (XAI), confidence scoring, and user-centric design principles + that foster trust and accountability. With a mix of theoretical insights and + real-world implementations, the article would highlight how companies tackle + challenges in deploying AI agents responsibly\u2014especially in sensitive domains + like finance, law enforcement, and healthcare\u2014demonstrating how trustworthiness + can become a competitive advantage in AI-driven services.\\n\\n- **AI Agents + as Personal Productivity Assistants: Beyond Scheduling and Reminders** \\n + \ This topic examines how AI agents are evolving from basic virtual assistants + to powerful personal productivity coaches that understand context, anticipate + needs, and proactively manage tasks. The article would investigate advances + in multi-modal understanding, emotional intelligence, and continuous learning + that enable AI agents to provide nuanced support in time management, email triage, + project coordination, and even creative brainstorming. Case studies from popular + platforms and startups would showcase how this new generation of AI agents is + revolutionizing daily workflows for professionals across sectors, offering readers + a forward-looking perspective on the future of personal digital assistance.\\n\\n- + **Collaborative AI Agents in Multi-Agent Systems: Driving Complex Problem Solving** + \ \\n This article would focus on the growing field of multi-agent AI systems, + where multiple AI agents communicate, negotiate, and collaborate to solve problems + that are too complex for a single agent. It would highlight research advances + in swarm intelligence, decentralized decision-making, and cooperative game theory, + and demonstrate practical applications ranging from autonomous vehicle fleets + to smart grid management and disaster response coordination. By unpacking these + complex interactions, the article would engage readers with the fascinating + dynamics of AI ecosystems and the promise of collaborative agents to address + society\u2019s grand challenges.\\n\\n- **Startups Building Next-Gen AI Agents: + Innovating at the Intersection of AI and User Experience** \\n Highlighting + startups at the forefront of AI agent technology, this article would provide + an in-depth look at how these ventures blend cutting-edge artificial intelligence + with seamless user experiences to disrupt traditional markets. It would examine + how startups harness advances in natural language processing, reinforcement + learning, and personalized modeling to create AI agents that feel intuitive + and human-like, powering applications in healthcare, education, finance, and + customer engagement. The article would also discuss funding trends, go-to-market + strategies, and technological challenges, offering entrepreneurs, investors, + and technologists valuable insights into what it takes to succeed in the burgeoning + AI agent landscape.\\n\\n**Notes:** \\nThese ideas are crafted to cover a broad + spectrum of AI agent-related topics, combining technical depth with real-world + relevance. Each paragraph aims to showcase the potential richness, relevance, + and appeal of a full article, ensuring the content would engage a diverse readership, + from AI researchers and software engineers to startup founders and business + leaders interested in AI innovation.\\n\\nThis is the expected criteria for + your final answer: Evaluation Score from 1 to 10 based on the performance of + the agents on the tasks\\nyou MUST return the actual complete content as the + final answer, not a summary.\\nFormat your final answer according to the following + OpenAPI schema: {\\n \\\"properties\\\": {\\n \\\"quality\\\": {\\n \\\"description\\\": + \\\"A score from 1 to 10 evaluating on completion, quality, and overall performance + from the task_description and task_expected_output to the actual Task Output.\\\",\\n + \ \\\"title\\\": \\\"Quality\\\",\\n \\\"type\\\": \\\"number\\\"\\n + \ }\\n },\\n \\\"required\\\": [\\n \\\"quality\\\"\\n ],\\n \\\"title\\\": + \\\"TaskEvaluationPydanticOutput\\\",\\n \\\"type\\\": \\\"object\\\",\\n \\\"additionalProperties\\\": + false\\n}\\n\\nIMPORTANT: Preserve the original content exactly as-is. Do NOT + rewrite, paraphrase, or modify the meaning of the content. Only structure it + to match the schema format.\\n\\nDo not include the OpenAPI schema in the final + output. Ensure the final output does not include any code block markers like + ```json or ```python.\\n\\nProvide your complete response:\"}],\"model\":\"gpt-4o-mini\",\"response_format\":{\"type\":\"json_schema\",\"json_schema\":{\"schema\":{\"properties\":{\"quality\":{\"description\":\"A + score from 1 to 10 evaluating on completion, quality, and overall performance + from the task_description and task_expected_output to the actual Task Output.\",\"title\":\"Quality\",\"type\":\"number\"}},\"required\":[\"quality\"],\"title\":\"TaskEvaluationPydanticOutput\",\"type\":\"object\",\"additionalProperties\":false},\"name\":\"TaskEvaluationPydanticOutput\",\"strict\":true}},\"stream\":false}" headers: - Accept: - - '*/*' - Accept-Encoding: - - gzip, deflate, zstd - Connection: - - keep-alive - Content-Length: - - '434' - Content-Type: - - application/json User-Agent: - - CrewAI-CLI/1.0.0 - X-Crewai-Version: - - 1.0.0 - method: POST - uri: https://app.crewai.com/crewai_plus/api/v1/tracing/batches - response: - body: - string: '{"error":"bad_credentials","message":"Bad credentials"}' - headers: - Connection: - - keep-alive - Content-Length: - - '55' - Content-Type: - - application/json; charset=utf-8 - Date: - - Tue, 21 Oct 2025 14:21:42 GMT - cache-control: - - no-store - content-security-policy: - - 'default-src ''self'' *.app.crewai.com app.crewai.com; script-src ''self'' ''unsafe-inline'' *.app.crewai.com app.crewai.com https://cdn.jsdelivr.net/npm/apexcharts https://www.gstatic.com https://run.pstmn.io https://apis.google.com https://apis.google.com/js/api.js https://accounts.google.com https://accounts.google.com/gsi/client https://cdnjs.cloudflare.com/ajax/libs/normalize/8.0.1/normalize.min.css.map https://*.google.com https://docs.google.com https://slides.google.com https://js.hs-scripts.com https://js.sentry-cdn.com https://browser.sentry-cdn.com https://www.googletagmanager.com https://js-na1.hs-scripts.com https://js.hubspot.com http://js-na1.hs-scripts.com https://bat.bing.com https://cdn.amplitude.com https://cdn.segment.com https://d1d3n03t5zntha.cloudfront.net/ https://descriptusercontent.com https://edge.fullstory.com https://googleads.g.doubleclick.net https://js.hs-analytics.net https://js.hs-banner.com https://js.hsadspixel.net https://js.hscollectedforms.net - https://js.usemessages.com https://snap.licdn.com https://static.cloudflareinsights.com https://static.reo.dev https://www.google-analytics.com https://share.descript.com/; style-src ''self'' ''unsafe-inline'' *.app.crewai.com app.crewai.com https://cdn.jsdelivr.net/npm/apexcharts; img-src ''self'' data: *.app.crewai.com app.crewai.com https://zeus.tools.crewai.com https://dashboard.tools.crewai.com https://cdn.jsdelivr.net https://forms.hsforms.com https://track.hubspot.com https://px.ads.linkedin.com https://px4.ads.linkedin.com https://www.google.com https://www.google.com.br; font-src ''self'' data: *.app.crewai.com app.crewai.com; connect-src ''self'' *.app.crewai.com app.crewai.com https://zeus.tools.crewai.com https://connect.useparagon.com/ https://zeus.useparagon.com/* https://*.useparagon.com/* https://run.pstmn.io https://connect.tools.crewai.com/ https://*.sentry.io https://www.google-analytics.com https://edge.fullstory.com https://rs.fullstory.com https://api.hubspot.com - https://forms.hscollectedforms.net https://api.hubapi.com https://px.ads.linkedin.com https://px4.ads.linkedin.com https://google.com/pagead/form-data/16713662509 https://google.com/ccm/form-data/16713662509 https://www.google.com/ccm/collect https://worker-actionkit.tools.crewai.com https://api.reo.dev; frame-src ''self'' *.app.crewai.com app.crewai.com https://connect.useparagon.com/ https://zeus.tools.crewai.com https://zeus.useparagon.com/* https://connect.tools.crewai.com/ https://docs.google.com https://drive.google.com https://slides.google.com https://accounts.google.com https://*.google.com https://app.hubspot.com/ https://td.doubleclick.net https://www.googletagmanager.com/ https://www.youtube.com https://share.descript.com' - expires: - - '0' - permissions-policy: - - camera=(), microphone=(self), geolocation=() - pragma: - - no-cache - referrer-policy: - - strict-origin-when-cross-origin - strict-transport-security: - - max-age=63072000; includeSubDomains - vary: - - Accept - x-content-type-options: - - nosniff - x-frame-options: - - SAMEORIGIN - x-permitted-cross-domain-policies: - - none - x-request-id: - - af7d2664-96a5-47fa-aa2b-5fef9fb2889c - x-runtime: - - '0.324159' - x-xss-protection: - - 1; mode=block - status: - code: 401 - message: Unauthorized -- request: - body: '{"messages": [{"role": "system", "content": "You are Task Execution Evaluator. Evaluator agent for crew evaluation with precise capabilities to evaluate the performance of the agents in the crew based on the tasks they have performed\nYour personal goal is: Your goal is to evaluate the performance of the agents in the crew based on the tasks they have performed using score from 1 to 10 evaluating on completion, quality, and overall performance.\nTo give my best complete final answer to the task respond using the exact following format:\n\nThought: I now can give a great answer\nFinal Answer: Your final answer must be the great and the most complete as possible, it must be outcome described.\n\nI MUST use these formats, my job depends on it!"}, {"role": "user", "content": "\nCurrent Task: Based on the task description and the expected output, compare and evaluate the performance of the agents in the crew based on the Task Output they have performed using score from 1 to 10 evaluating - on completion, quality, and overall performance.task_description: Come up with a list of 5 interesting ideas to explore for an article, then write one amazing paragraph highlight for each idea that showcases how good an article about this topic could be. Return the list of ideas with their paragraph and your notes. task_expected_output: 5 bullet points with a paragraph for each idea. agent: Researcher agent_goal: Make the best research and analysis on content about AI and AI agents Task Output: - **The Rise of AI Agents in Remote Work** \nAs remote work continues to dominate the global workplace, the integration of AI agents is poised to transform how teams collaborate and engage. A recent case study from the distributed team at GitLab, which employs advanced AI tools to enhance communication and productivity, illustrates how these agents can streamline workflows and provide real-time assistance. By leveraging AI-driven insights, employees can optimize their schedules, track performance - metrics, and even manage project deliverables more efficiently. An article exploring this phenomenon could delve into how AI agents are not just supporting remote work but redefining it, highlighting testimonials from employees who have experienced increased focus and reduced burnout as a result.\n\n- **Ethical Implications of AI in Education** \nThe increasing use of AI in educational settings raises critical ethical questions, especially concerning equity and accessibility. A notable example is Georgia Tech''s AI teaching assistant, Jill Watson, which has provided support to students while sparking debates about the human touch in teaching. An article that examines the dual-edged sword of employing AI as a mentor could consider perspectives from educators, students, and policymakers. By inviting thoughts from experts in both AI ethics and education reform, the article could tackle the implications of data privacy, algorithmic bias, and the necessity of inclusivity in developing - educational technologies.\n\n- **AI as Creative Collaborators** \nAI''s role as a creative collaborator is rapidly evolving, illustrated by projects like OpenAI''s DALL-E and GPT-3, which have successfully co-created art and literature with human artists. This dynamic presents a unique opportunity to explore the implications of creativity in the era of AI, especially how it influences workflows and ideation processes. An article could feature interviews with artists and designers who have utilized AI tools, discussing their experiences and the collaborative filters that guide creative decisions. Furthermore, examining how these interactions can democratize access to creative expression could spark deeper conversations about the future of art and originality in a technologically saturated landscape.\n\n- **AI in Mental Health Support** \nAs mental health challenges increase globally, AI''s potential to provide support through chatbots and virtual assistants offers a timely topic for - exploration. Programs like Woebot employ AI to interact with users, delivering cognitive behavioral therapy techniques and mood tracking options. This article could spotlight user testimonials highlighting the balance between technology and empathetic understanding. Insights from mental health professionals could provide critically engaging discussions on how AI tools can supplement traditional therapy while addressing concerns surrounding data security and the effectiveness of such treatments.\n\n- **AI''s Influence on Decision-Making Processes** \nIn the fast-paced business world, AI systems, such as IBM Watson, are redefining decision-making by providing data-driven insights that were previously unattainable. An article could investigate how organizations have adopted AI tools to enhance strategic choices and reduce risks. By incorporating expert opinions from business leaders who have successfully integrated AI into their processes, the article could reveal not only the measurable - impacts of AI on their decision-making efficacy but also the human aspects of adaptability and trust in technology. Furthermore, exploring the challenges faced during implementation could present a balanced view on the AI adoption journey, making it relatable for companies contemplating similar paths.\n\nNotes: In developing these ideas, I prioritized relevance to current events, case studies, and expert perspectives. Each idea aims to highlight the transformative impact of AI across diverse domains while addressing ethical concerns and user experiences to foster relatable content for a wide audience.\n\nThis is the expected criteria for your final answer: Evaluation Score from 1 to 10 based on the performance of the agents on the tasks\nyou MUST return the actual complete content as the final answer, not a summary.\nEnsure your final answer contains only the content in the following format: {\n \"quality\": float\n}\n\nEnsure the final output does not include any code block markers - like ```json or ```python.\n\nBegin! This is VERY important to you, use the tools available and give your best Final Answer, your job depends on it!\n\nThought:"}], "model": "gpt-4o-mini", "stream": false}' - headers: + - X-USER-AGENT-XXX accept: - application/json accept-encoding: - - gzip, deflate, zstd + - ACCEPT-ENCODING-XXX + authorization: + - AUTHORIZATION-XXX connection: - keep-alive content-length: - - '6196' + - '7196' content-type: - application/json cookie: - - __cf_bm=ujzGLIjq87ZWlYFBH3FycG8cIYtaTjon9XdbV63J84s-1761056486-1.0.1.1-V9wZVN8TxLIQ..Cd6VD53rSKVM8GssieHpzu53MMLsuoM7jVI8nAKNTbZeCqJxyHPutyhj_BwPvR56_gb0Nx90S6pVs3gQC2vj8VmCPbh1Y; _cfuvid=GIa.4ZxD52A2dXSZxoW1Mckm_eGjntP2i_mB4sczwEI-1761056486732-0.0.1.1-604800000 + - COOKIE-XXX host: - api.openai.com - user-agent: - - OpenAI/Python 1.109.1 x-stainless-arch: - - arm64 + - X-STAINLESS-ARCH-XXX x-stainless-async: - 'false' + x-stainless-helper-method: + - beta.chat.completions.parse x-stainless-lang: - python x-stainless-os: - - MacOS + - X-STAINLESS-OS-XXX x-stainless-package-version: - - 1.109.1 + - 1.83.0 x-stainless-read-timeout: - - '600' + - X-STAINLESS-READ-TIMEOUT-XXX x-stainless-retry-count: - '0' x-stainless-runtime: - CPython x-stainless-runtime-version: - - 3.12.9 + - 3.13.12 method: POST uri: https://api.openai.com/v1/chat/completions response: body: - string: "{\n \"id\": \"chatcmpl-CT7X4zWdSfYW2eTqKKF8ou174Mwp0\",\n \"object\": \"chat.completion\",\n \"created\": 1761056502,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"I now can give a great answer \\nFinal Answer: {\\n \\\"quality\\\": 9.0\\n}\",\n \"refusal\": null,\n \"annotations\": []\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 1084,\n \"completion_tokens\": 22,\n \"total_tokens\": 1106,\n \"prompt_tokens_details\": {\n \"cached_tokens\": 0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\": {\n \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\": 0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\": \"default\",\n \"system_fingerprint\": \"fp_560af6e559\"\ - \n}\n" + string: "{\n \"id\": \"chatcmpl-DDFzaYq2i96GKjZisy507Xk2rVvjn\",\n \"object\": + \"chat.completion\",\n \"created\": 1772052110,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n + \ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": + \"assistant\",\n \"content\": \"{\\\"quality\\\":9}\",\n \"refusal\": + null,\n \"annotations\": []\n },\n \"logprobs\": null,\n + \ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": + 1264,\n \"completion_tokens\": 5,\n \"total_tokens\": 1269,\n \"prompt_tokens_details\": + {\n \"cached_tokens\": 0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\": + {\n \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\": + 0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\": + \"default\",\n \"system_fingerprint\": \"fp_bd4be55b21\"\n}\n" headers: CF-RAY: - - 99216723793e6180-EWR + - CF-RAY-XXX Connection: - keep-alive Content-Type: - application/json Date: - - Tue, 21 Oct 2025 14:21:43 GMT + - Wed, 25 Feb 2026 20:41:51 GMT Server: - cloudflare Strict-Transport-Security: - - max-age=31536000; includeSubDomains; preload + - STS-XXX Transfer-Encoding: - chunked X-Content-Type-Options: - - nosniff + - X-CONTENT-TYPE-XXX access-control-expose-headers: - - X-Request-ID + - ACCESS-CONTROL-XXX alt-svc: - h3=":443"; ma=86400 cf-cache-status: - DYNAMIC openai-organization: - - crewai-iuxna1 + - OPENAI-ORG-XXX openai-processing-ms: - - '792' + - '391' openai-project: - - proj_fL4UBWR1CMpAAdgzaSKqsVvA + - OPENAI-PROJECT-XXX openai-version: - '2020-10-01' - x-envoy-upstream-service-time: - - '942' x-openai-proxy-wasm: - v0.1 x-ratelimit-limit-requests: - - '10000' + - X-RATELIMIT-LIMIT-REQUESTS-XXX x-ratelimit-limit-tokens: - - '200000' + - X-RATELIMIT-LIMIT-TOKENS-XXX x-ratelimit-remaining-requests: - - '9998' + - X-RATELIMIT-REMAINING-REQUESTS-XXX x-ratelimit-remaining-tokens: - - '198488' + - X-RATELIMIT-REMAINING-TOKENS-XXX x-ratelimit-reset-requests: - - 9.341s + - X-RATELIMIT-RESET-REQUESTS-XXX x-ratelimit-reset-tokens: - - 453ms + - X-RATELIMIT-RESET-TOKENS-XXX x-request-id: - - req_b521ced37dbf49beb8d19fcf36980e3c + - X-REQUEST-ID-XXX status: code: 200 message: OK diff --git a/lib/crewai/tests/cassettes/test_custom_converter_cls.yaml b/lib/crewai/tests/cassettes/test_custom_converter_cls.yaml index 541d5e7b5..ddb9f56df 100644 --- a/lib/crewai/tests/cassettes/test_custom_converter_cls.yaml +++ b/lib/crewai/tests/cassettes/test_custom_converter_cls.yaml @@ -1,97 +1,120 @@ interactions: - request: - body: '{"messages":[{"role":"system","content":"You are Scorer. You''re an expert scorer, specialized in scoring titles.\nYour personal goal is: Score the title\nTo give my best complete final answer to the task respond using the exact following format:\n\nThought: I now can give a great answer\nFinal Answer: Your final answer must be the great and the most complete as possible, it must be outcome described.\n\nI MUST use these formats, my job depends on it!"},{"role":"user","content":"\nCurrent Task: Give me an integer score between 1-5 for the following title: ''The impact of AI in the future of work''\n\nThis is the expected criteria for your final answer: The score of the title.\nyou MUST return the actual complete content as the final answer, not a summary.\nEnsure your final answer strictly adheres to the following OpenAPI schema: {\n \"properties\": {\n \"score\": {\n \"title\": \"Score\",\n \"type\": \"integer\"\n }\n },\n \"required\": [\n \"score\"\n ],\n \"title\": - \"ScoreOutput\",\n \"type\": \"object\",\n \"additionalProperties\": false\n}\n\nDo not include the OpenAPI schema in the final output. Ensure the final output does not include any code block markers like ```json or ```python.\n\nBegin! This is VERY important to you, use the tools available and give your best Final Answer, your job depends on it!\n\nThought:"}],"model":"gpt-4.1-mini"}' + body: '{"messages":[{"role":"system","content":"You are Scorer. You''re an expert + scorer, specialized in scoring titles.\nYour personal goal is: Score the title"},{"role":"user","content":"\nCurrent + Task: Give me an integer score between 1-5 for the following title: ''The impact + of AI in the future of work''\n\nThis is the expected criteria for your final + answer: The score of the title.\nyou MUST return the actual complete content + as the final answer, not a summary.\nFormat your final answer according to the + following OpenAPI schema: {\n \"properties\": {\n \"score\": {\n \"title\": + \"Score\",\n \"type\": \"integer\"\n }\n },\n \"required\": [\n \"score\"\n ],\n \"title\": + \"ScoreOutput\",\n \"type\": \"object\",\n \"additionalProperties\": false\n}\n\nIMPORTANT: + Preserve the original content exactly as-is. Do NOT rewrite, paraphrase, or + modify the meaning of the content. Only structure it to match the schema format.\n\nDo + not include the OpenAPI schema in the final output. Ensure the final output + does not include any code block markers like ```json or ```python.\n\nProvide + your complete response:"}],"model":"gpt-4.1-mini","response_format":{"type":"json_schema","json_schema":{"schema":{"properties":{"score":{"title":"Score","type":"integer"}},"required":["score"],"title":"ScoreOutput","type":"object","additionalProperties":false},"name":"ScoreOutput","strict":true}},"stream":false}' headers: + User-Agent: + - X-USER-AGENT-XXX accept: - application/json accept-encoding: - - gzip, deflate, zstd + - ACCEPT-ENCODING-XXX + authorization: + - AUTHORIZATION-XXX connection: - keep-alive content-length: - - '1394' + - '1421' content-type: - application/json host: - api.openai.com - user-agent: - - OpenAI/Python 1.109.1 x-stainless-arch: - - arm64 + - X-STAINLESS-ARCH-XXX x-stainless-async: - 'false' + x-stainless-helper-method: + - beta.chat.completions.parse x-stainless-lang: - python x-stainless-os: - - MacOS + - X-STAINLESS-OS-XXX x-stainless-package-version: - - 1.109.1 + - 1.83.0 x-stainless-read-timeout: - - '600' + - X-STAINLESS-READ-TIMEOUT-XXX x-stainless-retry-count: - '0' x-stainless-runtime: - CPython x-stainless-runtime-version: - - 3.12.9 + - 3.13.12 method: POST uri: https://api.openai.com/v1/chat/completions response: body: - string: "{\n \"id\": \"chatcmpl-CYg0OJQX3eMkY3pcrZz7iSh2HHTPF\",\n \"object\": \"chat.completion\",\n \"created\": 1762380656,\n \"model\": \"gpt-4.1-mini-2025-04-14\",\n \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"Thought: I now can give a great answer\\nFinal Answer: {\\\"score\\\":4}\",\n \"refusal\": null,\n \"annotations\": []\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 294,\n \"completion_tokens\": 18,\n \"total_tokens\": 312,\n \"prompt_tokens_details\": {\n \"cached_tokens\": 0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\": {\n \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\": 0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\": \"default\",\n \"system_fingerprint\": \"fp_4c2851f862\"\n}\n" + string: "{\n \"id\": \"chatcmpl-DDDzfvCsU0fZWdxFwjGh6dmaEheAW\",\n \"object\": + \"chat.completion\",\n \"created\": 1772044427,\n \"model\": \"gpt-4.1-mini-2025-04-14\",\n + \ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": + \"assistant\",\n \"content\": \"{\\\"score\\\":4}\",\n \"refusal\": + null,\n \"annotations\": []\n },\n \"logprobs\": null,\n + \ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": + 276,\n \"completion_tokens\": 5,\n \"total_tokens\": 281,\n \"prompt_tokens_details\": + {\n \"cached_tokens\": 0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\": + {\n \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\": + 0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\": + \"default\",\n \"system_fingerprint\": \"fp_a391f2cee0\"\n}\n" headers: CF-RAY: - - REDACTED-RAY + - CF-RAY-XXX Connection: - keep-alive Content-Type: - application/json Date: - - Wed, 05 Nov 2025 22:10:56 GMT + - Wed, 25 Feb 2026 18:33:48 GMT Server: - cloudflare - Set-Cookie: - - __cf_bm=REDACTED; path=/; expires=Wed, 05-Nov-25 22:40:56 GMT; domain=.api.openai.com; HttpOnly; Secure; SameSite=None - - _cfuvid=REDACTED; path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None Strict-Transport-Security: - - max-age=31536000; includeSubDomains; preload + - STS-XXX Transfer-Encoding: - chunked X-Content-Type-Options: - - nosniff + - X-CONTENT-TYPE-XXX access-control-expose-headers: - - X-Request-ID + - ACCESS-CONTROL-XXX alt-svc: - h3=":443"; ma=86400 cf-cache-status: - DYNAMIC openai-organization: - - user-hortuttj2f3qtmxyik2zxf4q + - OPENAI-ORG-XXX openai-processing-ms: - - '770' + - '552' openai-project: - - proj_fL4UBWR1CMpAAdgzaSKqsVvA + - OPENAI-PROJECT-XXX openai-version: - '2020-10-01' - x-envoy-upstream-service-time: - - '796' + set-cookie: + - SET-COOKIE-XXX x-openai-proxy-wasm: - v0.1 x-ratelimit-limit-requests: - - '500' + - X-RATELIMIT-LIMIT-REQUESTS-XXX x-ratelimit-limit-tokens: - - '200000' + - X-RATELIMIT-LIMIT-TOKENS-XXX x-ratelimit-remaining-requests: - - '499' + - X-RATELIMIT-REMAINING-REQUESTS-XXX x-ratelimit-remaining-tokens: - - '199687' + - X-RATELIMIT-REMAINING-TOKENS-XXX x-ratelimit-reset-requests: - - 120ms + - X-RATELIMIT-RESET-REQUESTS-XXX x-ratelimit-reset-tokens: - - 93ms + - X-RATELIMIT-RESET-TOKENS-XXX x-request-id: - - req_REDACTED + - X-REQUEST-ID-XXX status: code: 200 message: OK diff --git a/lib/crewai/tests/cassettes/test_guardrail_emits_events.yaml b/lib/crewai/tests/cassettes/test_guardrail_emits_events.yaml index 530c495a0..5f2e3d9de 100644 --- a/lib/crewai/tests/cassettes/test_guardrail_emits_events.yaml +++ b/lib/crewai/tests/cassettes/test_guardrail_emits_events.yaml @@ -1,684 +1,684 @@ interactions: - request: - body: '{"messages":[{"role":"system","content":"You are Test Agent. Test Backstory\nYour personal goal is: Test Goal\nTo give my best complete final answer to the task respond using the exact following format:\n\nThought: I now can give a great answer\nFinal Answer: Your final answer must be the great and the most complete as possible, it must be outcome described.\n\nI MUST use these formats, my job depends on it!"},{"role":"user","content":"\nCurrent Task: Gather information about available books on the First World War\n\nThis is the expected criteria for your final answer: A list of available books on the First World War\nyou MUST return the actual complete content as the final answer, not a summary.\n\nBegin! This is VERY important to you, use the tools available and give your best Final Answer, your job depends on it!\n\nThought:"}],"model":"gpt-4.1-mini"}' + body: '{"messages":[{"role":"system","content":"You are Test Agent. Test Backstory\nYour + personal goal is: Test Goal"},{"role":"user","content":"\nCurrent Task: Gather + information about available books on the First World War\n\nThis is the expected + criteria for your final answer: A list of available books on the First World + War\nyou MUST return the actual complete content as the final answer, not a + summary.\n\nProvide your complete response:"}],"model":"gpt-4.1-mini"}' headers: + User-Agent: + - X-USER-AGENT-XXX accept: - application/json accept-encoding: - - gzip, deflate, zstd + - ACCEPT-ENCODING-XXX + authorization: + - AUTHORIZATION-XXX connection: - keep-alive content-length: - - '866' + - '465' content-type: - application/json host: - api.openai.com - user-agent: - - OpenAI/Python 1.109.1 x-stainless-arch: - - arm64 + - X-STAINLESS-ARCH-XXX x-stainless-async: - 'false' x-stainless-lang: - python x-stainless-os: - - MacOS + - X-STAINLESS-OS-XXX x-stainless-package-version: - - 1.109.1 + - 1.83.0 x-stainless-read-timeout: - - '600' + - X-STAINLESS-READ-TIMEOUT-XXX x-stainless-retry-count: - '0' x-stainless-runtime: - CPython x-stainless-runtime-version: - - 3.12.9 + - 3.13.12 method: POST uri: https://api.openai.com/v1/chat/completions response: body: - string: "{\n \"id\": \"chatcmpl-CYgCMDtJgyyp33WkN0RtsJ9aI3zOA\",\n \"object\": \"chat.completion\",\n \"created\": 1762381398,\n \"model\": \"gpt-4.1-mini-2025-04-14\",\n \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"Thought: I now can give a great answer\\nFinal Answer: \\n\\nList of available books on the First World War:\\n\\n1. \\\"The Guns of August\\\" by Barbara W. Tuchman \\n - A detailed narrative of the first month of World War I, focusing on the political and military events that set the stage for the conflict.\\n\\n2. \\\"The First World War\\\" by John Keegan \\n - A comprehensive analysis of the causes, battles, and consequences of WWI by one of the foremost military historians.\\n\\n3. \\\"A World Undone: The Story of the Great War, 1914 to 1918\\\" by G.J. Meyer \\n - An accessible and detailed account covering the entire war, including social and political impacts.\\n\\n4. \\\ - \"The Sleepwalkers: How Europe Went to War in 1914\\\" by Christopher Clark \\n - Explores the complex political landscape and decisions that led to the outbreak of the war.\\n\\n5. \\\"The Pity of War: Explaining World War I\\\" by Niall Ferguson \\n - Offers a controversial interpretation of the war’s causes and outcomes.\\n\\n6. \\\"World War I: A Very Short Introduction\\\" by Michael Howard \\n - A brief but thorough overview of WWI, including its military and political aspects.\\n\\n7. \\\"Goodbye to All That\\\" by Robert Graves \\n - A personal memoir of a British officer’s experiences during the war, highlighting the human side.\\n\\n8. \\\"Storm of Steel\\\" by Ernst Jünger \\n - A German soldier’s firsthand account of combat on the Western Front.\\n\\n9. \\\"The War That Ended Peace: The Road to 1914\\\" by Margaret MacMillan \\n - Focuses on the lead-up to WWI and the political tensions that culminated in the conflict.\\n\\n10. \\\"The First World War:\ - \ An Illustrated History\\\" by Hew Strachan \\n - Combines detailed research with rich illustrations to provide a comprehensive history of the war.\\n\\nThese books provide a range of perspectives, from military history and political analysis to personal memoirs and social impact, offering comprehensive information about the First World War.\",\n \"refusal\": null,\n \"annotations\": []\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 170,\n \"completion_tokens\": 433,\n \"total_tokens\": 603,\n \"prompt_tokens_details\": {\n \"cached_tokens\": 0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\": {\n \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\": 0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\": \"default\",\n \"system_fingerprint\": \"fp_4c2851f862\"\n}\n" + string: "{\n \"id\": \"chatcmpl-DDGADaYtAf39e4orQQyF7DAeZbQLX\",\n \"object\": + \"chat.completion\",\n \"created\": 1772052769,\n \"model\": \"gpt-4.1-mini-2025-04-14\",\n + \ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": + \"assistant\",\n \"content\": \"Here is a list of available books on + the First World War:\\n\\n1. \\\"The Guns of August\\\" by Barbara W. Tuchman\\n2. + \\\"A World Undone: The Story of the Great War, 1914 to 1918\\\" by G.J. Meyer\\n3. + \\\"The First World War\\\" by John Keegan\\n4. \\\"The Sleepwalkers: How + Europe Went to War in 1914\\\" by Christopher Clark\\n5. \\\"To End All Wars: + A Story of Loyalty and Rebellion, 1914-1918\\\" by Adam Hochschild\\n6. \\\"The + Pity of War\\\" by Niall Ferguson\\n7. \\\"Catastrophe 1914: Europe Goes to + War\\\" by Max Hastings\\n8. \\\"World War I: The Definitive Visual History\\\" + by R.G. Grant\\n9. \\\"The War That Ended Peace: The Road to 1914\\\" by Margaret + MacMillan\\n10. \\\"Paris 1919: Six Months That Changed the World\\\" by Margaret + MacMillan\\n\\nThese books cover various aspects of the First World War, including + its causes, key battles, political consequences, and personal experiences.\",\n + \ \"refusal\": null,\n \"annotations\": []\n },\n \"logprobs\": + null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": + 84,\n \"completion_tokens\": 240,\n \"total_tokens\": 324,\n \"prompt_tokens_details\": + {\n \"cached_tokens\": 0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\": + {\n \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\": + 0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\": + \"default\",\n \"system_fingerprint\": \"fp_a391f2cee0\"\n}\n" headers: CF-RAY: - - REDACTED-RAY + - CF-RAY-XXX Connection: - keep-alive Content-Type: - application/json Date: - - Wed, 05 Nov 2025 22:23:24 GMT + - Wed, 25 Feb 2026 20:52:52 GMT Server: - cloudflare - Set-Cookie: - - __cf_bm=REDACTED; path=/; expires=Wed, 05-Nov-25 22:53:24 GMT; domain=.api.openai.com; HttpOnly; Secure; SameSite=None - - _cfuvid=REDACTED; path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None Strict-Transport-Security: - - max-age=31536000; includeSubDomains; preload + - STS-XXX Transfer-Encoding: - chunked X-Content-Type-Options: - - nosniff + - X-CONTENT-TYPE-XXX access-control-expose-headers: - - X-Request-ID + - ACCESS-CONTROL-XXX alt-svc: - h3=":443"; ma=86400 cf-cache-status: - DYNAMIC openai-organization: - - user-hortuttj2f3qtmxyik2zxf4q + - OPENAI-ORG-XXX openai-processing-ms: - - '5778' + - '3002' openai-project: - - proj_fL4UBWR1CMpAAdgzaSKqsVvA + - OPENAI-PROJECT-XXX openai-version: - '2020-10-01' - x-envoy-upstream-service-time: - - '5803' + set-cookie: + - SET-COOKIE-XXX x-openai-proxy-wasm: - v0.1 x-ratelimit-limit-requests: - - '500' + - X-RATELIMIT-LIMIT-REQUESTS-XXX x-ratelimit-limit-tokens: - - '200000' + - X-RATELIMIT-LIMIT-TOKENS-XXX x-ratelimit-remaining-requests: - - '499' + - X-RATELIMIT-REMAINING-REQUESTS-XXX x-ratelimit-remaining-tokens: - - '199808' + - X-RATELIMIT-REMAINING-TOKENS-XXX x-ratelimit-reset-requests: - - 120ms + - X-RATELIMIT-RESET-REQUESTS-XXX x-ratelimit-reset-tokens: - - 57ms + - X-RATELIMIT-RESET-TOKENS-XXX x-request-id: - - req_REDACTED + - X-REQUEST-ID-XXX status: code: 200 message: OK - request: - body: '{"messages":[{"role":"system","content":"You are Guardrail Agent. You are a expert at validating the output of a task. By providing effective feedback if the output is not valid.\nYour personal goal is: Validate the output of the task\n\nTo give my best complete final answer to the task respond using the exact following format:\n\nThought: I now can give a great answer\nFinal Answer: Your final answer must be the great and the most complete as possible, it must be outcome described.\n\nI MUST use these formats, my job depends on it!Ensure your final answer strictly adheres to the following OpenAPI schema: {\n \"type\": \"json_schema\",\n \"json_schema\": {\n \"name\": \"LLMGuardrailResult\",\n \"strict\": true,\n \"schema\": {\n \"properties\": {\n \"valid\": {\n \"description\": \"Whether the task output complies with the guardrail\",\n \"title\": \"Valid\",\n \"type\": \"boolean\"\n },\n \"feedback\": {\n \"anyOf\": - [\n {\n \"type\": \"string\"\n },\n {\n \"type\": \"null\"\n }\n ],\n \"default\": null,\n \"description\": \"A feedback about the task output if it is not valid\",\n \"title\": \"Feedback\"\n }\n },\n \"required\": [\n \"valid\",\n \"feedback\"\n ],\n \"title\": \"LLMGuardrailResult\",\n \"type\": \"object\",\n \"additionalProperties\": false\n }\n }\n}\n\nDo not include the OpenAPI schema in the final output. Ensure the final output does not include any code block markers like ```json or ```python."},{"role":"user","content":"\n Ensure the following task result complies with the given guardrail.\n\n Task result:\n List of available books on the First World War:\n\n1. \"The Guns of August\" by Barbara W. Tuchman \n - A detailed narrative of the first month of World War I, focusing on the political and - military events that set the stage for the conflict.\n\n2. \"The First World War\" by John Keegan \n - A comprehensive analysis of the causes, battles, and consequences of WWI by one of the foremost military historians.\n\n3. \"A World Undone: The Story of the Great War, 1914 to 1918\" by G.J. Meyer \n - An accessible and detailed account covering the entire war, including social and political impacts.\n\n4. \"The Sleepwalkers: How Europe Went to War in 1914\" by Christopher Clark \n - Explores the complex political landscape and decisions that led to the outbreak of the war.\n\n5. \"The Pity of War: Explaining World War I\" by Niall Ferguson \n - Offers a controversial interpretation of the war’s causes and outcomes.\n\n6. \"World War I: A Very Short Introduction\" by Michael Howard \n - A brief but thorough overview of WWI, including its military and political aspects.\n\n7. \"Goodbye to All That\" by Robert Graves \n - A personal memoir of a British officer’s experiences - during the war, highlighting the human side.\n\n8. \"Storm of Steel\" by Ernst Jünger \n - A German soldier’s firsthand account of combat on the Western Front.\n\n9. \"The War That Ended Peace: The Road to 1914\" by Margaret MacMillan \n - Focuses on the lead-up to WWI and the political tensions that culminated in the conflict.\n\n10. \"The First World War: An Illustrated History\" by Hew Strachan \n - Combines detailed research with rich illustrations to provide a comprehensive history of the war.\n\nThese books provide a range of perspectives, from military history and political analysis to personal memoirs and social impact, offering comprehensive information about the First World War.\n\n Guardrail:\n Ensure the authors are from Italy\n\n Your task:\n - Confirm if the Task result complies with the guardrail.\n - If not, provide clear feedback explaining what is wrong (e.g., by how much it violates the rule, or what specific part fails).\n - - Focus only on identifying issues — do not propose corrections.\n - If the Task result complies with the guardrail, saying that is valid\n "}],"model":"gpt-4.1-mini"}' + body: "{\"messages\":[{\"role\":\"system\",\"content\":\"You are Guardrail Agent. + You are a expert at validating the output of a task. By providing effective + feedback if the output is not valid.\\nYour personal goal is: Validate the output + of the task\"},{\"role\":\"user\",\"content\":\"\\nCurrent Task: \\n Ensure + the following task result complies with the given guardrail.\\n\\n Task + result:\\n Here is a list of available books on the First World War:\\n\\n1. + \\\"The Guns of August\\\" by Barbara W. Tuchman\\n2. \\\"A World Undone: The + Story of the Great War, 1914 to 1918\\\" by G.J. Meyer\\n3. \\\"The First World + War\\\" by John Keegan\\n4. \\\"The Sleepwalkers: How Europe Went to War in + 1914\\\" by Christopher Clark\\n5. \\\"To End All Wars: A Story of Loyalty and + Rebellion, 1914-1918\\\" by Adam Hochschild\\n6. \\\"The Pity of War\\\" by + Niall Ferguson\\n7. \\\"Catastrophe 1914: Europe Goes to War\\\" by Max Hastings\\n8. + \\\"World War I: The Definitive Visual History\\\" by R.G. Grant\\n9. \\\"The + War That Ended Peace: The Road to 1914\\\" by Margaret MacMillan\\n10. \\\"Paris + 1919: Six Months That Changed the World\\\" by Margaret MacMillan\\n\\nThese + books cover various aspects of the First World War, including its causes, key + battles, political consequences, and personal experiences.\\n\\n Guardrail:\\n + \ Ensure the authors are from Italy\\n\\n Your task:\\n - + Confirm if the Task result complies with the guardrail.\\n - If not, + provide clear feedback explaining what is wrong (e.g., by how much it violates + the rule, or what specific part fails).\\n - Focus only on identifying + issues \u2014 do not propose corrections.\\n - If the Task result complies + with the guardrail, saying that is valid\\n \\n\\nProvide your complete + response:\"}],\"model\":\"gpt-4.1-mini\",\"response_format\":{\"type\":\"json_schema\",\"json_schema\":{\"schema\":{\"properties\":{\"valid\":{\"description\":\"Whether + the task output complies with the guardrail\",\"title\":\"Valid\",\"type\":\"boolean\"},\"feedback\":{\"anyOf\":[{\"type\":\"string\"},{\"type\":\"null\"}],\"description\":\"A + feedback about the task output if it is not valid\",\"title\":\"Feedback\"}},\"required\":[\"valid\",\"feedback\"],\"title\":\"LLMGuardrailResult\",\"type\":\"object\",\"additionalProperties\":false},\"name\":\"LLMGuardrailResult\",\"strict\":true}},\"stream\":false}" headers: + User-Agent: + - X-USER-AGENT-XXX accept: - application/json accept-encoding: - - gzip, deflate, zstd + - ACCEPT-ENCODING-XXX + authorization: + - AUTHORIZATION-XXX connection: - keep-alive content-length: - - '4210' + - '2271' content-type: - application/json cookie: - - __cf_bm=REDACTED; _cfuvid=REDACTED + - COOKIE-XXX host: - api.openai.com - user-agent: - - OpenAI/Python 1.109.1 x-stainless-arch: - - arm64 - x-stainless-async: - - 'false' - x-stainless-lang: - - python - x-stainless-os: - - MacOS - x-stainless-package-version: - - 1.109.1 - x-stainless-read-timeout: - - '600' - x-stainless-retry-count: - - '0' - x-stainless-runtime: - - CPython - x-stainless-runtime-version: - - 3.12.9 - method: POST - uri: https://api.openai.com/v1/chat/completions - response: - body: - string: "{\n \"id\": \"chatcmpl-CYgCSORvqXRvHk9WrMZInBh6xp6DI\",\n \"object\": \"chat.completion\",\n \"created\": 1762381404,\n \"model\": \"gpt-4.1-mini-2025-04-14\",\n \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"{\\n \\\"valid\\\": false,\\n \\\"feedback\\\": \\\"None of the listed authors are from Italy; all authors mentioned are from various other countries such as the United States, United Kingdom, Germany, and Canada. This does not comply with the guardrail which requires authors to be from Italy.\\\"\\n}\",\n \"refusal\": null,\n \"annotations\": []\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 878,\n \"completion_tokens\": 60,\n \"total_tokens\": 938,\n \"prompt_tokens_details\": {\n \"cached_tokens\": 0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\": {\n \ - \ \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\": 0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\": \"default\",\n \"system_fingerprint\": \"fp_4c2851f862\"\n}\n" - headers: - CF-RAY: - - REDACTED-RAY - Connection: - - keep-alive - Content-Type: - - application/json - Date: - - Wed, 05 Nov 2025 22:23:25 GMT - Server: - - cloudflare - Strict-Transport-Security: - - max-age=31536000; includeSubDomains; preload - Transfer-Encoding: - - chunked - X-Content-Type-Options: - - nosniff - access-control-expose-headers: - - X-Request-ID - alt-svc: - - h3=":443"; ma=86400 - cf-cache-status: - - DYNAMIC - openai-organization: - - user-hortuttj2f3qtmxyik2zxf4q - openai-processing-ms: - - '920' - openai-project: - - proj_fL4UBWR1CMpAAdgzaSKqsVvA - openai-version: - - '2020-10-01' - x-envoy-upstream-service-time: - - '931' - x-openai-proxy-wasm: - - v0.1 - x-ratelimit-limit-requests: - - '500' - x-ratelimit-limit-tokens: - - '200000' - x-ratelimit-remaining-requests: - - '499' - x-ratelimit-remaining-tokens: - - '199013' - x-ratelimit-reset-requests: - - 120ms - x-ratelimit-reset-tokens: - - 296ms - x-request-id: - - req_REDACTED - status: - code: 200 - message: OK -- request: - body: '{"messages":[{"role":"system","content":"Ensure your final answer strictly adheres to the following OpenAPI schema: {\n \"type\": \"json_schema\",\n \"json_schema\": {\n \"name\": \"LLMGuardrailResult\",\n \"strict\": true,\n \"schema\": {\n \"properties\": {\n \"valid\": {\n \"description\": \"Whether the task output complies with the guardrail\",\n \"title\": \"Valid\",\n \"type\": \"boolean\"\n },\n \"feedback\": {\n \"anyOf\": [\n {\n \"type\": \"string\"\n },\n {\n \"type\": \"null\"\n }\n ],\n \"default\": null,\n \"description\": \"A feedback about the task output if it is not valid\",\n \"title\": \"Feedback\"\n }\n },\n \"required\": [\n \"valid\",\n \"feedback\"\n ],\n \"title\": \"LLMGuardrailResult\",\n \"type\": \"object\",\n \"additionalProperties\": - false\n }\n }\n}\n\nDo not include the OpenAPI schema in the final output. Ensure the final output does not include any code block markers like ```json or ```python."},{"role":"user","content":"{\n \"valid\": false,\n \"feedback\": \"None of the listed authors are from Italy; all authors mentioned are from various other countries such as the United States, United Kingdom, Germany, and Canada. This does not comply with the guardrail which requires authors to be from Italy.\"\n}"}],"model":"gpt-4.1-mini","response_format":{"type":"json_schema","json_schema":{"schema":{"properties":{"valid":{"description":"Whether the task output complies with the guardrail","title":"Valid","type":"boolean"},"feedback":{"anyOf":[{"type":"string"},{"type":"null"}],"description":"A feedback about the task output if it is not valid","title":"Feedback"}},"required":["valid","feedback"],"title":"LLMGuardrailResult","type":"object","additionalProperties":false},"name":"LLMGuardrailResult","strict":true}},"stream":false}' - headers: - accept: - - application/json - accept-encoding: - - gzip, deflate, zstd - connection: - - keep-alive - content-length: - - '2020' - content-type: - - application/json - cookie: - - __cf_bm=REDACTED; _cfuvid=REDACTED - host: - - api.openai.com - user-agent: - - OpenAI/Python 1.109.1 - x-stainless-arch: - - arm64 + - X-STAINLESS-ARCH-XXX x-stainless-async: - 'false' x-stainless-helper-method: - - chat.completions.parse + - beta.chat.completions.parse x-stainless-lang: - python x-stainless-os: - - MacOS + - X-STAINLESS-OS-XXX x-stainless-package-version: - - 1.109.1 + - 1.83.0 x-stainless-read-timeout: - - '600' + - X-STAINLESS-READ-TIMEOUT-XXX x-stainless-retry-count: - '0' x-stainless-runtime: - CPython x-stainless-runtime-version: - - 3.12.9 + - 3.13.12 method: POST uri: https://api.openai.com/v1/chat/completions response: body: - string: "{\n \"id\": \"chatcmpl-CYgCTfEoC2Q5aZFEAXbsW4zQq0Ihu\",\n \"object\": \"chat.completion\",\n \"created\": 1762381405,\n \"model\": \"gpt-4.1-mini-2025-04-14\",\n \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"{\\\"valid\\\":false,\\\"feedback\\\":\\\"The output indicates that none of the authors mentioned are from Italy, while the guardrail requires authors to be from Italy. Therefore, the output does not comply with the guardrail.\\\"}\",\n \"refusal\": null,\n \"annotations\": []\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 397,\n \"completion_tokens\": 44,\n \"total_tokens\": 441,\n \"prompt_tokens_details\": {\n \"cached_tokens\": 0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\": {\n \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\"\ - : 0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\": \"default\",\n \"system_fingerprint\": \"fp_4c2851f862\"\n}\n" + string: "{\n \"id\": \"chatcmpl-DDGAImuBOpJTAf2UGXPUCFcRcYXua\",\n \"object\": + \"chat.completion\",\n \"created\": 1772052774,\n \"model\": \"gpt-4.1-mini-2025-04-14\",\n + \ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": + \"assistant\",\n \"content\": \"{\\\"valid\\\":false,\\\"feedback\\\":\\\"None + of the authors listed are from Italy. The guardrail requires that the authors + be from Italy, but all the authors mentioned, such as Barbara W. Tuchman, + G.J. Meyer, John Keegan, Christopher Clark, Adam Hochschild, Niall Ferguson, + Max Hastings, R.G. Grant, and Margaret MacMillan, are not Italian. Therefore, + the task result does not comply with the guardrail.\\\"}\",\n \"refusal\": + null,\n \"annotations\": []\n },\n \"logprobs\": null,\n + \ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": + 500,\n \"completion_tokens\": 93,\n \"total_tokens\": 593,\n \"prompt_tokens_details\": + {\n \"cached_tokens\": 0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\": + {\n \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\": + 0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\": + \"default\",\n \"system_fingerprint\": \"fp_d96d8e3578\"\n}\n" headers: CF-RAY: - - REDACTED-RAY + - CF-RAY-XXX Connection: - keep-alive Content-Type: - application/json Date: - - Wed, 05 Nov 2025 22:23:26 GMT + - Wed, 25 Feb 2026 20:52:56 GMT Server: - cloudflare Strict-Transport-Security: - - max-age=31536000; includeSubDomains; preload + - STS-XXX Transfer-Encoding: - chunked X-Content-Type-Options: - - nosniff + - X-CONTENT-TYPE-XXX access-control-expose-headers: - - X-Request-ID + - ACCESS-CONTROL-XXX alt-svc: - h3=":443"; ma=86400 cf-cache-status: - DYNAMIC openai-organization: - - user-hortuttj2f3qtmxyik2zxf4q + - OPENAI-ORG-XXX openai-processing-ms: - - '1214' + - '1401' openai-project: - - proj_fL4UBWR1CMpAAdgzaSKqsVvA + - OPENAI-PROJECT-XXX openai-version: - '2020-10-01' - x-envoy-upstream-service-time: - - '1251' x-openai-proxy-wasm: - v0.1 x-ratelimit-limit-requests: - - '500' + - X-RATELIMIT-LIMIT-REQUESTS-XXX x-ratelimit-limit-tokens: - - '200000' + - X-RATELIMIT-LIMIT-TOKENS-XXX x-ratelimit-remaining-requests: - - '499' + - X-RATELIMIT-REMAINING-REQUESTS-XXX x-ratelimit-remaining-tokens: - - '199670' + - X-RATELIMIT-REMAINING-TOKENS-XXX x-ratelimit-reset-requests: - - 120ms + - X-RATELIMIT-RESET-REQUESTS-XXX x-ratelimit-reset-tokens: - - 99ms + - X-RATELIMIT-RESET-TOKENS-XXX x-request-id: - - req_REDACTED + - X-REQUEST-ID-XXX status: code: 200 message: OK - request: - body: '{"messages":[{"role":"system","content":"You are Test Agent. Test Backstory\nYour personal goal is: Test Goal\nTo give my best complete final answer to the task respond using the exact following format:\n\nThought: I now can give a great answer\nFinal Answer: Your final answer must be the great and the most complete as possible, it must be outcome described.\n\nI MUST use these formats, my job depends on it!"},{"role":"user","content":"\nCurrent Task: Gather information about available books on the First World War\n\nThis is the expected criteria for your final answer: A list of available books on the First World War\nyou MUST return the actual complete content as the final answer, not a summary.\n\nThis is the context you''re working with:\n### Previous attempt failed validation: The output indicates that none of the authors mentioned are from Italy, while the guardrail requires authors to be from Italy. Therefore, the output does not comply with the guardrail.\n\n\n### Previous - result:\nList of available books on the First World War:\n\n1. \"The Guns of August\" by Barbara W. Tuchman \n - A detailed narrative of the first month of World War I, focusing on the political and military events that set the stage for the conflict.\n\n2. \"The First World War\" by John Keegan \n - A comprehensive analysis of the causes, battles, and consequences of WWI by one of the foremost military historians.\n\n3. \"A World Undone: The Story of the Great War, 1914 to 1918\" by G.J. Meyer \n - An accessible and detailed account covering the entire war, including social and political impacts.\n\n4. \"The Sleepwalkers: How Europe Went to War in 1914\" by Christopher Clark \n - Explores the complex political landscape and decisions that led to the outbreak of the war.\n\n5. \"The Pity of War: Explaining World War I\" by Niall Ferguson \n - Offers a controversial interpretation of the war’s causes and outcomes.\n\n6. \"World War I: A Very Short Introduction\" by Michael - Howard \n - A brief but thorough overview of WWI, including its military and political aspects.\n\n7. \"Goodbye to All That\" by Robert Graves \n - A personal memoir of a British officer’s experiences during the war, highlighting the human side.\n\n8. \"Storm of Steel\" by Ernst Jünger \n - A German soldier’s firsthand account of combat on the Western Front.\n\n9. \"The War That Ended Peace: The Road to 1914\" by Margaret MacMillan \n - Focuses on the lead-up to WWI and the political tensions that culminated in the conflict.\n\n10. \"The First World War: An Illustrated History\" by Hew Strachan \n - Combines detailed research with rich illustrations to provide a comprehensive history of the war.\n\nThese books provide a range of perspectives, from military history and political analysis to personal memoirs and social impact, offering comprehensive information about the First World War.\n\n\nTry again, making sure to address the validation error.\n\nBegin! This is VERY - important to you, use the tools available and give your best Final Answer, your job depends on it!\n\nThought:"}],"model":"gpt-4.1-mini"}' + body: '{"messages":[{"role":"system","content":"You are Test Agent. Test Backstory\nYour + personal goal is: Test Goal"},{"role":"user","content":"\nCurrent Task: Gather + information about available books on the First World War\n\nThis is the expected + criteria for your final answer: A list of available books on the First World + War\nyou MUST return the actual complete content as the final answer, not a + summary.\n\nProvide your complete response:"},{"role":"assistant","content":"Here + is a list of available books on the First World War:\n\n1. \"The Guns of August\" + by Barbara W. Tuchman\n2. \"A World Undone: The Story of the Great War, 1914 + to 1918\" by G.J. Meyer\n3. \"The First World War\" by John Keegan\n4. \"The + Sleepwalkers: How Europe Went to War in 1914\" by Christopher Clark\n5. \"To + End All Wars: A Story of Loyalty and Rebellion, 1914-1918\" by Adam Hochschild\n6. + \"The Pity of War\" by Niall Ferguson\n7. \"Catastrophe 1914: Europe Goes to + War\" by Max Hastings\n8. \"World War I: The Definitive Visual History\" by + R.G. Grant\n9. \"The War That Ended Peace: The Road to 1914\" by Margaret MacMillan\n10. + \"Paris 1919: Six Months That Changed the World\" by Margaret MacMillan\n\nThese + books cover various aspects of the First World War, including its causes, key + battles, political consequences, and personal experiences."},{"role":"system","content":"You + are Test Agent. Test Backstory\nYour personal goal is: Test Goal"},{"role":"user","content":"\nCurrent + Task: Gather information about available books on the First World War\n\nThis + is the expected criteria for your final answer: A list of available books on + the First World War\nyou MUST return the actual complete content as the final + answer, not a summary.\n\nThis is the context you''re working with:\n### Previous + attempt failed validation: None of the authors listed are from Italy. The guardrail + requires that the authors be from Italy, but all the authors mentioned, such + as Barbara W. Tuchman, G.J. Meyer, John Keegan, Christopher Clark, Adam Hochschild, + Niall Ferguson, Max Hastings, R.G. Grant, and Margaret MacMillan, are not Italian. + Therefore, the task result does not comply with the guardrail.\n\n\n### Previous + result:\nHere is a list of available books on the First World War:\n\n1. \"The + Guns of August\" by Barbara W. Tuchman\n2. \"A World Undone: The Story of the + Great War, 1914 to 1918\" by G.J. Meyer\n3. \"The First World War\" by John + Keegan\n4. \"The Sleepwalkers: How Europe Went to War in 1914\" by Christopher + Clark\n5. \"To End All Wars: A Story of Loyalty and Rebellion, 1914-1918\" by + Adam Hochschild\n6. \"The Pity of War\" by Niall Ferguson\n7. \"Catastrophe + 1914: Europe Goes to War\" by Max Hastings\n8. \"World War I: The Definitive + Visual History\" by R.G. Grant\n9. \"The War That Ended Peace: The Road to 1914\" + by Margaret MacMillan\n10. \"Paris 1919: Six Months That Changed the World\" + by Margaret MacMillan\n\nThese books cover various aspects of the First World + War, including its causes, key battles, political consequences, and personal + experiences.\n\n\nTry again, making sure to address the validation error.\n\nProvide + your complete response:"}],"model":"gpt-4.1-mini"}' headers: + User-Agent: + - X-USER-AGENT-XXX accept: - application/json accept-encoding: - - gzip, deflate, zstd + - ACCEPT-ENCODING-XXX + authorization: + - AUTHORIZATION-XXX connection: - keep-alive content-length: - - '3139' + - '3185' content-type: - application/json cookie: - - __cf_bm=REDACTED; _cfuvid=REDACTED + - COOKIE-XXX host: - api.openai.com - user-agent: - - OpenAI/Python 1.109.1 x-stainless-arch: - - arm64 + - X-STAINLESS-ARCH-XXX x-stainless-async: - 'false' x-stainless-lang: - python x-stainless-os: - - MacOS + - X-STAINLESS-OS-XXX x-stainless-package-version: - - 1.109.1 + - 1.83.0 x-stainless-read-timeout: - - '600' + - X-STAINLESS-READ-TIMEOUT-XXX x-stainless-retry-count: - '0' x-stainless-runtime: - CPython x-stainless-runtime-version: - - 3.12.9 + - 3.13.12 method: POST uri: https://api.openai.com/v1/chat/completions response: body: - string: "{\n \"id\": \"chatcmpl-CYgCUFGx7P3dG6mkKENsAdMSjbDP2\",\n \"object\": \"chat.completion\",\n \"created\": 1762381406,\n \"model\": \"gpt-4.1-mini-2025-04-14\",\n \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"Thought: I now can give a great answer\\nFinal Answer: List of available books on the First World War by Italian authors or published in Italy:\\n\\n1. \\\"La Grande Guerra\\\" by Alessandro Barbero \\n - A comprehensive history of the First World War with a focus on Italy’s involvement and the impact on Italian society and politics.\\n\\n2. \\\"La guerra bianca: Come gli Italiani hanno combattuto la Prima guerra mondiale\\\" by Alessandro Barbero \\n - Explores the harsh conditions of mountain warfare endured by Italian soldiers, with vivid descriptions of battles and daily life on the Alpine front.\\n\\n3. \\\"La Prima Guerra Mondiale\\\" by Paolo Mieli \\n - Provides a broad overview\ - \ of the war, including Italy's role and the broader European context, combining historical facts with cultural insights.\\n\\n4. \\\"1915-1918: La guerra italiana sul fronte interno\\\" by Giovanni De Luna \\n - Focuses on the social and political effects of the war within Italy, examining public opinion, propaganda, and the home front.\\n\\n5. \\\"Il Giorno della Vittoria: 4 Novembre 1918\\\" by Paolo Gaspari \\n - Detailed analysis of Italy’s final victories and the aftermath of the war, including the political and social changes that followed.\\n\\n6. \\\"La Guerra prima della Grande Guerra\\\" by Alessandro Barbero \\n - Discusses the international tensions preceding the First World War with an Italian perspective on diplomatic and military developments.\\n\\n7. \\\"La guerra dimenticata: Il fronte orientale, 1915-1917\\\" by Luca Micheletti \\n - Covers Italy’s campaigns on the Eastern Front, less frequently discussed in general histories of the war, providing new\ - \ insights into Italy’s military efforts.\\n\\n8. \\\"Tornare a casa. Grande Guerra 1914-1918\\\" by Marco Balzano \\n - A novelized account based on testimonies and letters from Italian soldiers, blending historical documentation with personal narrative.\\n\\n9. \\\"I cento giorni: La battaglia finale della Grande Guerra\\\" by Giuseppe Cultrera \\n - Concentrates on the decisive Italian military operations in the war’s final phase, highlighting strategy and key personalities.\\n\\n10. \\\"La Grande Guerra sul Carso\\\" by Mario Isnenghi \\n - Focuses specifically on the Carso front, a crucial and brutal theater of war for Italian forces, combining military history with human stories.\\n\\nThese titles emphasize the Italian experience of the First World War, authored by prominent Italian historians and writers, thus fulfilling the requirement for Italian authorship and perspective.\",\n \"refusal\": null,\n \"annotations\": []\n },\n \"logprobs\"\ - : null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 654,\n \"completion_tokens\": 516,\n \"total_tokens\": 1170,\n \"prompt_tokens_details\": {\n \"cached_tokens\": 0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\": {\n \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\": 0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\": \"default\",\n \"system_fingerprint\": \"fp_4c2851f862\"\n}\n" + string: "{\n \"id\": \"chatcmpl-DDGAKo0MLHbMnvDBrDJ43r7OO4uh8\",\n \"object\": + \"chat.completion\",\n \"created\": 1772052776,\n \"model\": \"gpt-4.1-mini-2025-04-14\",\n + \ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": + \"assistant\",\n \"content\": \"Here is a list of available books on + the First World War by Italian authors:\\n\\n1. \\\"La Grande Guerra\\\" by + Alessandro Barbero \\n2. \\\"Il grande nulla: La prima guerra mondiale\\\" + by Emilio Gentile \\n3. \\\"La guerra italiana 1915-1918\\\" by Paolo Piccione + \ \\n4. \\\"La prima guerra mondiale\\\" by Andrea di Robilant \\n5. \\\"1914-1918: + La guerra e la memoria\\\" edited by Paolo G. Minuto \\n\\nThese books provide + various perspectives on the First World War from Italian historians and authors.\",\n + \ \"refusal\": null,\n \"annotations\": []\n },\n \"logprobs\": + null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": + 763,\n \"completion_tokens\": 117,\n \"total_tokens\": 880,\n \"prompt_tokens_details\": + {\n \"cached_tokens\": 0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\": + {\n \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\": + 0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\": + \"default\",\n \"system_fingerprint\": \"fp_a391f2cee0\"\n}\n" headers: CF-RAY: - - REDACTED-RAY + - CF-RAY-XXX Connection: - keep-alive Content-Type: - application/json Date: - - Wed, 05 Nov 2025 22:23:34 GMT + - Wed, 25 Feb 2026 20:52:58 GMT Server: - cloudflare Strict-Transport-Security: - - max-age=31536000; includeSubDomains; preload + - STS-XXX Transfer-Encoding: - chunked X-Content-Type-Options: - - nosniff + - X-CONTENT-TYPE-XXX access-control-expose-headers: - - X-Request-ID + - ACCESS-CONTROL-XXX alt-svc: - h3=":443"; ma=86400 cf-cache-status: - DYNAMIC openai-organization: - - user-hortuttj2f3qtmxyik2zxf4q + - OPENAI-ORG-XXX openai-processing-ms: - - '7917' + - '1725' openai-project: - - proj_fL4UBWR1CMpAAdgzaSKqsVvA + - OPENAI-PROJECT-XXX openai-version: - '2020-10-01' - x-envoy-upstream-service-time: - - '7943' x-openai-proxy-wasm: - v0.1 x-ratelimit-limit-requests: - - '500' + - X-RATELIMIT-LIMIT-REQUESTS-XXX x-ratelimit-limit-tokens: - - '200000' + - X-RATELIMIT-LIMIT-TOKENS-XXX x-ratelimit-remaining-requests: - - '499' + - X-RATELIMIT-REMAINING-REQUESTS-XXX x-ratelimit-remaining-tokens: - - '199255' + - X-RATELIMIT-REMAINING-TOKENS-XXX x-ratelimit-reset-requests: - - 120ms + - X-RATELIMIT-RESET-REQUESTS-XXX x-ratelimit-reset-tokens: - - 223ms + - X-RATELIMIT-RESET-TOKENS-XXX x-request-id: - - req_REDACTED + - X-REQUEST-ID-XXX status: code: 200 message: OK - request: - body: '{"messages":[{"role":"system","content":"You are Guardrail Agent. You are a expert at validating the output of a task. By providing effective feedback if the output is not valid.\nYour personal goal is: Validate the output of the task\n\nTo give my best complete final answer to the task respond using the exact following format:\n\nThought: I now can give a great answer\nFinal Answer: Your final answer must be the great and the most complete as possible, it must be outcome described.\n\nI MUST use these formats, my job depends on it!Ensure your final answer strictly adheres to the following OpenAPI schema: {\n \"type\": \"json_schema\",\n \"json_schema\": {\n \"name\": \"LLMGuardrailResult\",\n \"strict\": true,\n \"schema\": {\n \"properties\": {\n \"valid\": {\n \"description\": \"Whether the task output complies with the guardrail\",\n \"title\": \"Valid\",\n \"type\": \"boolean\"\n },\n \"feedback\": {\n \"anyOf\": - [\n {\n \"type\": \"string\"\n },\n {\n \"type\": \"null\"\n }\n ],\n \"default\": null,\n \"description\": \"A feedback about the task output if it is not valid\",\n \"title\": \"Feedback\"\n }\n },\n \"required\": [\n \"valid\",\n \"feedback\"\n ],\n \"title\": \"LLMGuardrailResult\",\n \"type\": \"object\",\n \"additionalProperties\": false\n }\n }\n}\n\nDo not include the OpenAPI schema in the final output. Ensure the final output does not include any code block markers like ```json or ```python."},{"role":"user","content":"\n Ensure the following task result complies with the given guardrail.\n\n Task result:\n List of available books on the First World War by Italian authors or published in Italy:\n\n1. \"La Grande Guerra\" by Alessandro Barbero \n - A comprehensive history of the First World War - with a focus on Italy’s involvement and the impact on Italian society and politics.\n\n2. \"La guerra bianca: Come gli Italiani hanno combattuto la Prima guerra mondiale\" by Alessandro Barbero \n - Explores the harsh conditions of mountain warfare endured by Italian soldiers, with vivid descriptions of battles and daily life on the Alpine front.\n\n3. \"La Prima Guerra Mondiale\" by Paolo Mieli \n - Provides a broad overview of the war, including Italy''s role and the broader European context, combining historical facts with cultural insights.\n\n4. \"1915-1918: La guerra italiana sul fronte interno\" by Giovanni De Luna \n - Focuses on the social and political effects of the war within Italy, examining public opinion, propaganda, and the home front.\n\n5. \"Il Giorno della Vittoria: 4 Novembre 1918\" by Paolo Gaspari \n - Detailed analysis of Italy’s final victories and the aftermath of the war, including the political and social changes that followed.\n\n6. \"La Guerra - prima della Grande Guerra\" by Alessandro Barbero \n - Discusses the international tensions preceding the First World War with an Italian perspective on diplomatic and military developments.\n\n7. \"La guerra dimenticata: Il fronte orientale, 1915-1917\" by Luca Micheletti \n - Covers Italy’s campaigns on the Eastern Front, less frequently discussed in general histories of the war, providing new insights into Italy’s military efforts.\n\n8. \"Tornare a casa. Grande Guerra 1914-1918\" by Marco Balzano \n - A novelized account based on testimonies and letters from Italian soldiers, blending historical documentation with personal narrative.\n\n9. \"I cento giorni: La battaglia finale della Grande Guerra\" by Giuseppe Cultrera \n - Concentrates on the decisive Italian military operations in the war’s final phase, highlighting strategy and key personalities.\n\n10. \"La Grande Guerra sul Carso\" by Mario Isnenghi \n - Focuses specifically on the Carso front, a crucial and - brutal theater of war for Italian forces, combining military history with human stories.\n\nThese titles emphasize the Italian experience of the First World War, authored by prominent Italian historians and writers, thus fulfilling the requirement for Italian authorship and perspective.\n\n Guardrail:\n Ensure the authors are from Italy\n\n Your task:\n - Confirm if the Task result complies with the guardrail.\n - If not, provide clear feedback explaining what is wrong (e.g., by how much it violates the rule, or what specific part fails).\n - Focus only on identifying issues — do not propose corrections.\n - If the Task result complies with the guardrail, saying that is valid\n "}],"model":"gpt-4.1-mini"}' + body: "{\"messages\":[{\"role\":\"system\",\"content\":\"You are Guardrail Agent. + You are a expert at validating the output of a task. By providing effective + feedback if the output is not valid.\\nYour personal goal is: Validate the output + of the task\"},{\"role\":\"user\",\"content\":\"\\nCurrent Task: \\n Ensure + the following task result complies with the given guardrail.\\n\\n Task + result:\\n Here is a list of available books on the First World War by + Italian authors:\\n\\n1. \\\"La Grande Guerra\\\" by Alessandro Barbero \\n2. + \\\"Il grande nulla: La prima guerra mondiale\\\" by Emilio Gentile \\n3. \\\"La + guerra italiana 1915-1918\\\" by Paolo Piccione \\n4. \\\"La prima guerra mondiale\\\" + by Andrea di Robilant \\n5. \\\"1914-1918: La guerra e la memoria\\\" edited + by Paolo G. Minuto \\n\\nThese books provide various perspectives on the First + World War from Italian historians and authors.\\n\\n Guardrail:\\n Ensure + the authors are from Italy\\n\\n Your task:\\n - Confirm if the + Task result complies with the guardrail.\\n - If not, provide clear feedback + explaining what is wrong (e.g., by how much it violates the rule, or what specific + part fails).\\n - Focus only on identifying issues \u2014 do not propose + corrections.\\n - If the Task result complies with the guardrail, saying + that is valid\\n \\n\\nProvide your complete response:\"}],\"model\":\"gpt-4.1-mini\",\"response_format\":{\"type\":\"json_schema\",\"json_schema\":{\"schema\":{\"properties\":{\"valid\":{\"description\":\"Whether + the task output complies with the guardrail\",\"title\":\"Valid\",\"type\":\"boolean\"},\"feedback\":{\"anyOf\":[{\"type\":\"string\"},{\"type\":\"null\"}],\"description\":\"A + feedback about the task output if it is not valid\",\"title\":\"Feedback\"}},\"required\":[\"valid\",\"feedback\"],\"title\":\"LLMGuardrailResult\",\"type\":\"object\",\"additionalProperties\":false},\"name\":\"LLMGuardrailResult\",\"strict\":true}},\"stream\":false}" headers: + User-Agent: + - X-USER-AGENT-XXX accept: - application/json accept-encoding: - - gzip, deflate, zstd + - ACCEPT-ENCODING-XXX + authorization: + - AUTHORIZATION-XXX connection: - keep-alive content-length: - - '4782' + - '1896' content-type: - application/json cookie: - - __cf_bm=REDACTED; _cfuvid=REDACTED + - COOKIE-XXX host: - api.openai.com - user-agent: - - OpenAI/Python 1.109.1 x-stainless-arch: - - arm64 + - X-STAINLESS-ARCH-XXX x-stainless-async: - 'false' + x-stainless-helper-method: + - beta.chat.completions.parse x-stainless-lang: - python x-stainless-os: - - MacOS + - X-STAINLESS-OS-XXX x-stainless-package-version: - - 1.109.1 + - 1.83.0 x-stainless-read-timeout: - - '600' + - X-STAINLESS-READ-TIMEOUT-XXX x-stainless-retry-count: - '0' x-stainless-runtime: - CPython x-stainless-runtime-version: - - 3.12.9 + - 3.13.12 method: POST uri: https://api.openai.com/v1/chat/completions response: body: - string: "{\n \"id\": \"chatcmpl-CYgCc8ZK4YyFBqgK1P1mOpdaCPfC7\",\n \"object\": \"chat.completion\",\n \"created\": 1762381414,\n \"model\": \"gpt-4.1-mini-2025-04-14\",\n \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"{\\n \\\"valid\\\": true,\\n \\\"feedback\\\": null\\n}\",\n \"refusal\": null,\n \"annotations\": []\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 962,\n \"completion_tokens\": 14,\n \"total_tokens\": 976,\n \"prompt_tokens_details\": {\n \"cached_tokens\": 0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\": {\n \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\": 0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\": \"default\",\n \"system_fingerprint\": \"fp_4c2851f862\"\n}\n" + string: "{\n \"id\": \"chatcmpl-DDGAMhqLQH0xSQdFBe8xOEyjBIa59\",\n \"object\": + \"chat.completion\",\n \"created\": 1772052778,\n \"model\": \"gpt-4.1-mini-2025-04-14\",\n + \ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": + \"assistant\",\n \"content\": \"{\\\"valid\\\":true,\\\"feedback\\\":null}\",\n + \ \"refusal\": null,\n \"annotations\": []\n },\n \"logprobs\": + null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": + 377,\n \"completion_tokens\": 9,\n \"total_tokens\": 386,\n \"prompt_tokens_details\": + {\n \"cached_tokens\": 0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\": + {\n \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\": + 0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\": + \"default\",\n \"system_fingerprint\": \"fp_d96d8e3578\"\n}\n" headers: CF-RAY: - - REDACTED-RAY + - CF-RAY-XXX Connection: - keep-alive Content-Type: - application/json Date: - - Wed, 05 Nov 2025 22:23:35 GMT + - Wed, 25 Feb 2026 20:52:58 GMT Server: - cloudflare Strict-Transport-Security: - - max-age=31536000; includeSubDomains; preload + - STS-XXX Transfer-Encoding: - chunked X-Content-Type-Options: - - nosniff + - X-CONTENT-TYPE-XXX access-control-expose-headers: - - X-Request-ID + - ACCESS-CONTROL-XXX alt-svc: - h3=":443"; ma=86400 cf-cache-status: - DYNAMIC openai-organization: - - user-hortuttj2f3qtmxyik2zxf4q + - OPENAI-ORG-XXX openai-processing-ms: - - '395' - openai-project: - - proj_fL4UBWR1CMpAAdgzaSKqsVvA - openai-version: - - '2020-10-01' - x-envoy-upstream-service-time: - '420' - x-openai-proxy-wasm: - - v0.1 - x-ratelimit-limit-requests: - - '500' - x-ratelimit-limit-tokens: - - '200000' - x-ratelimit-remaining-requests: - - '499' - x-ratelimit-remaining-tokens: - - '198710' - x-ratelimit-reset-requests: - - 120ms - x-ratelimit-reset-tokens: - - 386ms - x-request-id: - - req_REDACTED - status: - code: 200 - message: OK -- request: - body: '{"messages":[{"role":"system","content":"Ensure your final answer strictly adheres to the following OpenAPI schema: {\n \"type\": \"json_schema\",\n \"json_schema\": {\n \"name\": \"LLMGuardrailResult\",\n \"strict\": true,\n \"schema\": {\n \"properties\": {\n \"valid\": {\n \"description\": \"Whether the task output complies with the guardrail\",\n \"title\": \"Valid\",\n \"type\": \"boolean\"\n },\n \"feedback\": {\n \"anyOf\": [\n {\n \"type\": \"string\"\n },\n {\n \"type\": \"null\"\n }\n ],\n \"default\": null,\n \"description\": \"A feedback about the task output if it is not valid\",\n \"title\": \"Feedback\"\n }\n },\n \"required\": [\n \"valid\",\n \"feedback\"\n ],\n \"title\": \"LLMGuardrailResult\",\n \"type\": \"object\",\n \"additionalProperties\": - false\n }\n }\n}\n\nDo not include the OpenAPI schema in the final output. Ensure the final output does not include any code block markers like ```json or ```python."},{"role":"user","content":"{\n \"valid\": true,\n \"feedback\": null\n}"}],"model":"gpt-4.1-mini","response_format":{"type":"json_schema","json_schema":{"schema":{"properties":{"valid":{"description":"Whether the task output complies with the guardrail","title":"Valid","type":"boolean"},"feedback":{"anyOf":[{"type":"string"},{"type":"null"}],"description":"A feedback about the task output if it is not valid","title":"Feedback"}},"required":["valid","feedback"],"title":"LLMGuardrailResult","type":"object","additionalProperties":false},"name":"LLMGuardrailResult","strict":true}},"stream":false}' - headers: - accept: - - application/json - accept-encoding: - - gzip, deflate, zstd - connection: - - keep-alive - content-length: - - '1777' - content-type: - - application/json - cookie: - - __cf_bm=REDACTED; _cfuvid=REDACTED - host: - - api.openai.com - user-agent: - - OpenAI/Python 1.109.1 - x-stainless-arch: - - arm64 - x-stainless-async: - - 'false' - x-stainless-helper-method: - - chat.completions.parse - x-stainless-lang: - - python - x-stainless-os: - - MacOS - x-stainless-package-version: - - 1.109.1 - x-stainless-read-timeout: - - '600' - x-stainless-retry-count: - - '0' - x-stainless-runtime: - - CPython - x-stainless-runtime-version: - - 3.12.9 - method: POST - uri: https://api.openai.com/v1/chat/completions - response: - body: - string: "{\n \"id\": \"chatcmpl-CYgCdfjTW26WehWv9HjK3NHOT5e4l\",\n \"object\": \"chat.completion\",\n \"created\": 1762381415,\n \"model\": \"gpt-4.1-mini-2025-04-14\",\n \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"{\\\"valid\\\":true,\\\"feedback\\\":null}\",\n \"refusal\": null,\n \"annotations\": []\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 351,\n \"completion_tokens\": 9,\n \"total_tokens\": 360,\n \"prompt_tokens_details\": {\n \"cached_tokens\": 0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\": {\n \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\": 0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\": \"default\",\n \"system_fingerprint\": \"fp_4c2851f862\"\n}\n" - headers: - CF-RAY: - - REDACTED-RAY - Connection: - - keep-alive - Content-Type: - - application/json - Date: - - Wed, 05 Nov 2025 22:23:35 GMT - Server: - - cloudflare - Strict-Transport-Security: - - max-age=31536000; includeSubDomains; preload - Transfer-Encoding: - - chunked - X-Content-Type-Options: - - nosniff - access-control-expose-headers: - - X-Request-ID - alt-svc: - - h3=":443"; ma=86400 - cf-cache-status: - - DYNAMIC - openai-organization: - - user-hortuttj2f3qtmxyik2zxf4q - openai-processing-ms: - - '424' openai-project: - - proj_fL4UBWR1CMpAAdgzaSKqsVvA + - OPENAI-PROJECT-XXX openai-version: - '2020-10-01' - x-envoy-upstream-service-time: - - '450' x-openai-proxy-wasm: - v0.1 x-ratelimit-limit-requests: - - '500' + - X-RATELIMIT-LIMIT-REQUESTS-XXX x-ratelimit-limit-tokens: - - '200000' + - X-RATELIMIT-LIMIT-TOKENS-XXX x-ratelimit-remaining-requests: - - '499' + - X-RATELIMIT-REMAINING-REQUESTS-XXX x-ratelimit-remaining-tokens: - - '199730' + - X-RATELIMIT-REMAINING-TOKENS-XXX x-ratelimit-reset-requests: - - 120ms + - X-RATELIMIT-RESET-REQUESTS-XXX x-ratelimit-reset-tokens: - - 81ms + - X-RATELIMIT-RESET-TOKENS-XXX x-request-id: - - req_REDACTED + - X-REQUEST-ID-XXX status: code: 200 message: OK - request: - body: '{"messages":[{"role":"system","content":"You are Test Agent. Test Backstory\nYour personal goal is: Test Goal\nTo give my best complete final answer to the task respond using the exact following format:\n\nThought: I now can give a great answer\nFinal Answer: Your final answer must be the great and the most complete as possible, it must be outcome described.\n\nI MUST use these formats, my job depends on it!"},{"role":"user","content":"\nCurrent Task: Test task\n\nThis is the expected criteria for your final answer: Output\nyou MUST return the actual complete content as the final answer, not a summary.\n\nBegin! This is VERY important to you, use the tools available and give your best Final Answer, your job depends on it!\n\nThought:"}],"model":"gpt-4.1-mini"}' + body: '{"messages":[{"role":"system","content":"You are Test Agent. Test Backstory\nYour + personal goal is: Test Goal"},{"role":"user","content":"\nCurrent Task: Gather + information about available books on the First World War\n\nThis is the expected + criteria for your final answer: A list of available books on the First World + War\nyou MUST return the actual complete content as the final answer, not a + summary.\n\nProvide your complete response:"},{"role":"assistant","content":"Here + is a list of available books on the First World War:\n\n1. \"The Guns of August\" + by Barbara W. Tuchman\n2. \"A World Undone: The Story of the Great War, 1914 + to 1918\" by G.J. Meyer\n3. \"The First World War\" by John Keegan\n4. \"The + Sleepwalkers: How Europe Went to War in 1914\" by Christopher Clark\n5. \"To + End All Wars: A Story of Loyalty and Rebellion, 1914-1918\" by Adam Hochschild\n6. + \"The Pity of War\" by Niall Ferguson\n7. \"Catastrophe 1914: Europe Goes to + War\" by Max Hastings\n8. \"World War I: The Definitive Visual History\" by + R.G. Grant\n9. \"The War That Ended Peace: The Road to 1914\" by Margaret MacMillan\n10. + \"Paris 1919: Six Months That Changed the World\" by Margaret MacMillan\n\nThese + books cover various aspects of the First World War, including its causes, key + battles, political consequences, and personal experiences."},{"role":"system","content":"You + are Test Agent. Test Backstory\nYour personal goal is: Test Goal"},{"role":"user","content":"\nCurrent + Task: Gather information about available books on the First World War\n\nThis + is the expected criteria for your final answer: A list of available books on + the First World War\nyou MUST return the actual complete content as the final + answer, not a summary.\n\nThis is the context you''re working with:\n### Previous + attempt failed validation: None of the authors listed are from Italy. The guardrail + requires that the authors be from Italy, but all the authors mentioned, such + as Barbara W. Tuchman, G.J. Meyer, John Keegan, Christopher Clark, Adam Hochschild, + Niall Ferguson, Max Hastings, R.G. Grant, and Margaret MacMillan, are not Italian. + Therefore, the task result does not comply with the guardrail.\n\n\n### Previous + result:\nHere is a list of available books on the First World War:\n\n1. \"The + Guns of August\" by Barbara W. Tuchman\n2. \"A World Undone: The Story of the + Great War, 1914 to 1918\" by G.J. Meyer\n3. \"The First World War\" by John + Keegan\n4. \"The Sleepwalkers: How Europe Went to War in 1914\" by Christopher + Clark\n5. \"To End All Wars: A Story of Loyalty and Rebellion, 1914-1918\" by + Adam Hochschild\n6. \"The Pity of War\" by Niall Ferguson\n7. \"Catastrophe + 1914: Europe Goes to War\" by Max Hastings\n8. \"World War I: The Definitive + Visual History\" by R.G. Grant\n9. \"The War That Ended Peace: The Road to 1914\" + by Margaret MacMillan\n10. \"Paris 1919: Six Months That Changed the World\" + by Margaret MacMillan\n\nThese books cover various aspects of the First World + War, including its causes, key battles, political consequences, and personal + experiences.\n\n\nTry again, making sure to address the validation error.\n\nProvide + your complete response:"},{"role":"assistant","content":"Here is a list of available + books on the First World War by Italian authors:\n\n1. \"La Grande Guerra\" + by Alessandro Barbero \n2. \"Il grande nulla: La prima guerra mondiale\" by + Emilio Gentile \n3. \"La guerra italiana 1915-1918\" by Paolo Piccione \n4. + \"La prima guerra mondiale\" by Andrea di Robilant \n5. \"1914-1918: La guerra + e la memoria\" edited by Paolo G. Minuto \n\nThese books provide various perspectives + on the First World War from Italian historians and authors."},{"role":"system","content":"You + are Test Agent. Test Backstory\nYour personal goal is: Test Goal"},{"role":"user","content":"\nCurrent + Task: Test task\n\nThis is the expected criteria for your final answer: Output\nyou + MUST return the actual complete content as the final answer, not a summary.\n\nProvide + your complete response:"}],"model":"gpt-4.1-mini"}' headers: + User-Agent: + - X-USER-AGENT-XXX accept: - application/json accept-encoding: - - gzip, deflate, zstd + - ACCEPT-ENCODING-XXX + authorization: + - AUTHORIZATION-XXX connection: - keep-alive content-length: - - '770' + - '4036' content-type: - application/json cookie: - - __cf_bm=REDACTED; _cfuvid=REDACTED + - COOKIE-XXX host: - api.openai.com - user-agent: - - OpenAI/Python 1.109.1 x-stainless-arch: - - arm64 + - X-STAINLESS-ARCH-XXX x-stainless-async: - 'false' x-stainless-lang: - python x-stainless-os: - - MacOS + - X-STAINLESS-OS-XXX x-stainless-package-version: - - 1.109.1 + - 1.83.0 x-stainless-read-timeout: - - '600' + - X-STAINLESS-READ-TIMEOUT-XXX x-stainless-retry-count: - '0' x-stainless-runtime: - CPython x-stainless-runtime-version: - - 3.12.9 + - 3.13.12 method: POST uri: https://api.openai.com/v1/chat/completions response: body: - string: "{\n \"id\": \"chatcmpl-CYgCdUkawcuGKhJQYVfLlwbbDwljX\",\n \"object\": \"chat.completion\",\n \"created\": 1762381415,\n \"model\": \"gpt-4.1-mini-2025-04-14\",\n \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"Thought: I now can give a great answer\\nFinal Answer: Output\",\n \"refusal\": null,\n \"annotations\": []\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 153,\n \"completion_tokens\": 14,\n \"total_tokens\": 167,\n \"prompt_tokens_details\": {\n \"cached_tokens\": 0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\": {\n \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\": 0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\": \"default\",\n \"system_fingerprint\": \"fp_4c2851f862\"\n}\n" + string: "{\n \"id\": \"chatcmpl-DDGAMOb5FXfsZwEhCqnUP11VAcuqF\",\n \"object\": + \"chat.completion\",\n \"created\": 1772052778,\n \"model\": \"gpt-4.1-mini-2025-04-14\",\n + \ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": + \"assistant\",\n \"content\": \"Output\",\n \"refusal\": null,\n + \ \"annotations\": []\n },\n \"logprobs\": null,\n \"finish_reason\": + \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 948,\n \"completion_tokens\": + 1,\n \"total_tokens\": 949,\n \"prompt_tokens_details\": {\n \"cached_tokens\": + 0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\": + {\n \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\": + 0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\": + \"default\",\n \"system_fingerprint\": \"fp_a391f2cee0\"\n}\n" headers: CF-RAY: - - REDACTED-RAY + - CF-RAY-XXX Connection: - keep-alive Content-Type: - application/json Date: - - Wed, 05 Nov 2025 22:23:36 GMT + - Wed, 25 Feb 2026 20:52:59 GMT Server: - cloudflare Strict-Transport-Security: - - max-age=31536000; includeSubDomains; preload + - STS-XXX Transfer-Encoding: - chunked X-Content-Type-Options: - - nosniff + - X-CONTENT-TYPE-XXX access-control-expose-headers: - - X-Request-ID + - ACCESS-CONTROL-XXX alt-svc: - h3=":443"; ma=86400 cf-cache-status: - DYNAMIC openai-organization: - - user-hortuttj2f3qtmxyik2zxf4q + - OPENAI-ORG-XXX openai-processing-ms: - - '441' + - '347' openai-project: - - proj_fL4UBWR1CMpAAdgzaSKqsVvA + - OPENAI-PROJECT-XXX openai-version: - '2020-10-01' - x-envoy-upstream-service-time: - - '462' x-openai-proxy-wasm: - v0.1 x-ratelimit-limit-requests: - - '500' + - X-RATELIMIT-LIMIT-REQUESTS-XXX x-ratelimit-limit-tokens: - - '200000' + - X-RATELIMIT-LIMIT-TOKENS-XXX x-ratelimit-remaining-requests: - - '499' + - X-RATELIMIT-REMAINING-REQUESTS-XXX x-ratelimit-remaining-tokens: - - '199832' + - X-RATELIMIT-REMAINING-TOKENS-XXX x-ratelimit-reset-requests: - - 120ms + - X-RATELIMIT-RESET-REQUESTS-XXX x-ratelimit-reset-tokens: - - 50ms + - X-RATELIMIT-RESET-TOKENS-XXX x-request-id: - - req_REDACTED + - X-REQUEST-ID-XXX status: code: 200 message: OK diff --git a/lib/crewai/tests/cassettes/test_guardrail_when_an_error_occurs.yaml b/lib/crewai/tests/cassettes/test_guardrail_when_an_error_occurs.yaml index 1ac34dfe5..af0bc5aaf 100644 --- a/lib/crewai/tests/cassettes/test_guardrail_when_an_error_occurs.yaml +++ b/lib/crewai/tests/cassettes/test_guardrail_when_an_error_occurs.yaml @@ -1,189 +1,121 @@ interactions: - request: - body: '{"messages": [{"role": "system", "content": "You are Test Agent. Test Backstory\nYour personal goal is: Test Goal\nTo give my best complete final answer to the task respond using the exact following format:\n\nThought: I now can give a great answer\nFinal Answer: Your final answer must be the great and the most complete as possible, it must be outcome described.\n\nI MUST use these formats, my job depends on it!"}, {"role": "user", "content": "\nCurrent Task: Gather information about available books on the First World War\n\nThis is the expected criteria for your final answer: A list of available books on the First World War\nyou MUST return the actual complete content as the final answer, not a summary.\n\nBegin! This is VERY important to you, use the tools available and give your best Final Answer, your job depends on it!\n\nThought:"}], "model": "gpt-4o-mini", "stop": ["\nObservation:"]}' + body: '{"messages":[{"role":"system","content":"You are Test Agent. Test Backstory\nYour + personal goal is: Test Goal"},{"role":"user","content":"\nCurrent Task: Gather + information about available books on the First World War\n\nThis is the expected + criteria for your final answer: A list of available books on the First World + War\nyou MUST return the actual complete content as the final answer, not a + summary.\n\nProvide your complete response:"}],"model":"gpt-4.1-mini"}' headers: + User-Agent: + - X-USER-AGENT-XXX accept: - application/json accept-encoding: - - gzip, deflate + - ACCEPT-ENCODING-XXX + authorization: + - AUTHORIZATION-XXX connection: - keep-alive content-length: - - '903' + - '465' content-type: - application/json host: - api.openai.com - user-agent: - - OpenAI/Python 1.68.2 x-stainless-arch: - - arm64 + - X-STAINLESS-ARCH-XXX x-stainless-async: - 'false' x-stainless-lang: - python x-stainless-os: - - MacOS + - X-STAINLESS-OS-XXX x-stainless-package-version: - - 1.68.2 - x-stainless-raw-response: - - 'true' + - 1.83.0 x-stainless-read-timeout: - - '600.0' + - X-STAINLESS-READ-TIMEOUT-XXX x-stainless-retry-count: - '0' x-stainless-runtime: - CPython x-stainless-runtime-version: - - 3.12.9 + - 3.13.12 method: POST uri: https://api.openai.com/v1/chat/completions response: body: - string: "{\n \"id\": \"chatcmpl-BReRV6HdeL9wUgmKwfAZfVjuGdpAo\",\n \"object\": \"chat.completion\",\n \"created\": 1745930017,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"I now can give a great answer \\nFinal Answer: Here is a comprehensive list of available books on the First World War:\\n\\n1. **\\\"The Sleepwalkers: How Europe Went to War in 1914\\\" by Christopher Clark** \\n This book delves into the complex factors that led to the outbreak of the war, offering insights into the political and social dynamics of early 20th century Europe.\\n\\n2. **\\\"A World Undone: The Story of the Great War, 1914 to 1918\\\" by G.J. Meyer** \\n Meyer's expansive narrative covers the entire war with a focus on both military strategies and the human experiences endured by soldiers and civilians alike.\\n\\n3. **\\\"All Quiet on the Western Front\\\" by Erich Maria\ - \ Remarque** \\n A poignant novel that captures the resilience and trauma experienced by German soldiers during World War I, based on the author's own experiences.\\n\\n4. **\\\"The First World War\\\" by John Keegan** \\n Keegan provides a detailed military history of the war, featuring insights on battles, strategies, and the overall impact on global affairs.\\n\\n5. **\\\"Goodbye to All That\\\" by Robert Graves** \\n This autobiography recounts the author's experiences as a soldier during the war, offering a personal and critical perspective on the conflicts and the post-war era.\\n\\n6. **\\\"Catastrophe 1914: Europe Goes to War\\\" by Max Hastings** \\n Hastings chronicles the events leading up to World War I and the early battles, detailing the war's initial impact on European societies.\\n\\n7. **\\\"The War That Ended Peace: The Road to 1914\\\" by Margaret MacMillan** \\n MacMillan explores the political and historical factors that contributed to the outbreak\ - \ of war, emphasizing the decisions made by leaders across Europe.\\n\\n8. **\\\"The First World War: A Complete History\\\" by Martin Gilbert** \\n This complete history takes readers through the entirety of the war, from its causes to its aftermath, using a wide range of sources.\\n\\n9. **\\\"1914: The Year the World Ended\\\" by Paul Ham** \\n Ham focuses on the pivotal year of 1914 and the early war's devastation, analyzing its long-lasting effects on the world.\\n\\n10. **\\\"War Horse\\\" by Michael Morpurgo** \\n This children's novel tells the story of a horse and his experiences during the war, highlighting the bond between animals and humans amidst the chaos.\\n\\nEach of these books offers unique perspectives and rich details about the First World War, making them valuable resources for anyone interested in this pivotal period in history.\",\n \"refusal\": null,\n \"annotations\": []\n },\n \"logprobs\": null,\n \"finish_reason\"\ - : \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 170,\n \"completion_tokens\": 534,\n \"total_tokens\": 704,\n \"prompt_tokens_details\": {\n \"cached_tokens\": 0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\": {\n \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\": 0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\": \"default\",\n \"system_fingerprint\": \"fp_dbaca60df0\"\n}\n" + string: "{\n \"id\": \"chatcmpl-DDGA6ArRnT0S8ME2I1R4x9Mo4JyGJ\",\n \"object\": + \"chat.completion\",\n \"created\": 1772052762,\n \"model\": \"gpt-4.1-mini-2025-04-14\",\n + \ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": + \"assistant\",\n \"content\": \"Here is a list of available books on + the First World War:\\n\\n1. \\\"The Guns of August\\\" by Barbara W. Tuchman\\n2. + \\\"A World Undone: The Story of the Great War, 1914 to 1918\\\" by G.J. Meyer\\n3. + \\\"The First World War\\\" by John Keegan\\n4. \\\"The Sleepwalkers: How + Europe Went to War in 1914\\\" by Christopher Clark\\n5. \\\"To End All Wars: + A Story of Loyalty and Rebellion, 1914-1918\\\" by Adam Hochschild\\n6. \\\"World + War I: The Definitive Visual History\\\" by R.G. Grant\\n7. \\\"Catastrophe + 1914: Europe Goes to War\\\" by Max Hastings\\n8. \\\"The Great War and Modern + Memory\\\" by Paul Fussell\\n9. \\\"Paris 1919: Six Months That Changed the + World\\\" by Margaret MacMillan\\n10. \\\"The Pity of War: Explaining World + War I\\\" by Niall Ferguson\\n\\nIf you need further details on any of these + titles, feel free to ask.\",\n \"refusal\": null,\n \"annotations\": + []\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n + \ }\n ],\n \"usage\": {\n \"prompt_tokens\": 84,\n \"completion_tokens\": + 230,\n \"total_tokens\": 314,\n \"prompt_tokens_details\": {\n \"cached_tokens\": + 0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\": + {\n \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\": + 0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\": + \"default\",\n \"system_fingerprint\": \"fp_a391f2cee0\"\n}\n" headers: CF-RAY: - - 937ed42dee2e621f-GRU + - CF-RAY-XXX Connection: - keep-alive Content-Type: - application/json Date: - - Tue, 29 Apr 2025 12:33:48 GMT + - Wed, 25 Feb 2026 20:52:46 GMT Server: - cloudflare - Set-Cookie: - - __cf_bm=mLRCnpdB3n_6medIZWHnUu8MNRGZsD6riaRhN47PK74-1745930028-1.0.1.1-M2lDM1_V9hNCK0MZrBnFalF3lndC3JkS8zhDOGww_LmOrgdpU9fZLpNZUmyinCQOnlCjDjDYJUECM82ffT1anqBiO1NoDeNp91EPKiK7s.8; path=/; expires=Tue, 29-Apr-25 13:03:48 GMT; domain=.api.openai.com; HttpOnly; Secure; SameSite=None - - _cfuvid=eTrj_ZhCx2XuylS5vYROwUlPrJBwOyrbS2Ki.msl45E-1745930028010-0.0.1.1-604800000; path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None + Strict-Transport-Security: + - STS-XXX Transfer-Encoding: - chunked X-Content-Type-Options: - - nosniff + - X-CONTENT-TYPE-XXX access-control-expose-headers: - - X-Request-ID + - ACCESS-CONTROL-XXX alt-svc: - h3=":443"; ma=86400 cf-cache-status: - DYNAMIC openai-organization: - - crewai-iuxna1 + - OPENAI-ORG-XXX openai-processing-ms: - - '10856' + - '3250' + openai-project: + - OPENAI-PROJECT-XXX openai-version: - '2020-10-01' - strict-transport-security: - - max-age=31536000; includeSubDomains; preload + set-cookie: + - SET-COOKIE-XXX + x-openai-proxy-wasm: + - v0.1 x-ratelimit-limit-requests: - - '30000' + - X-RATELIMIT-LIMIT-REQUESTS-XXX x-ratelimit-limit-tokens: - - '150000000' + - X-RATELIMIT-LIMIT-TOKENS-XXX x-ratelimit-remaining-requests: - - '29999' + - X-RATELIMIT-REMAINING-REQUESTS-XXX x-ratelimit-remaining-tokens: - - '149999807' + - X-RATELIMIT-REMAINING-TOKENS-XXX x-ratelimit-reset-requests: - - 2ms + - X-RATELIMIT-RESET-REQUESTS-XXX x-ratelimit-reset-tokens: - - 0s + - X-RATELIMIT-RESET-TOKENS-XXX x-request-id: - - req_bc2d62d8325b2bdd3e98544a66389132 - status: - code: 200 - message: OK -- request: - body: '{"messages": [{"role": "system", "content": "You are Guardrail Agent. You are a expert at validating the output of a task. By providing effective feedback if the output is not valid.\nYour personal goal is: Validate the output of the task\n\nTo give my best complete final answer to the task respond using the exact following format:\n\nThought: I now can give a great answer\nFinal Answer: Your final answer must be the great and the most complete as possible, it must be outcome described.\n\nI MUST use these formats, my job depends on it!\nIMPORTANT: Your final answer MUST contain all the information requested in the following format: {\n \"valid\": bool,\n \"feedback\": str | None\n}\n\nIMPORTANT: Ensure the final output does not include any code block markers like ```json or ```python."}, {"role": "user", "content": "\n Ensure the following task result complies with the given guardrail.\n\n Task result:\n Here is a comprehensive list of available books on - the First World War:\n\n1. **\"The Sleepwalkers: How Europe Went to War in 1914\" by Christopher Clark** \n This book delves into the complex factors that led to the outbreak of the war, offering insights into the political and social dynamics of early 20th century Europe.\n\n2. **\"A World Undone: The Story of the Great War, 1914 to 1918\" by G.J. Meyer** \n Meyer''s expansive narrative covers the entire war with a focus on both military strategies and the human experiences endured by soldiers and civilians alike.\n\n3. **\"All Quiet on the Western Front\" by Erich Maria Remarque** \n A poignant novel that captures the resilience and trauma experienced by German soldiers during World War I, based on the author''s own experiences.\n\n4. **\"The First World War\" by John Keegan** \n Keegan provides a detailed military history of the war, featuring insights on battles, strategies, and the overall impact on global affairs.\n\n5. **\"Goodbye to All That\" by Robert Graves** \n This - autobiography recounts the author''s experiences as a soldier during the war, offering a personal and critical perspective on the conflicts and the post-war era.\n\n6. **\"Catastrophe 1914: Europe Goes to War\" by Max Hastings** \n Hastings chronicles the events leading up to World War I and the early battles, detailing the war''s initial impact on European societies.\n\n7. **\"The War That Ended Peace: The Road to 1914\" by Margaret MacMillan** \n MacMillan explores the political and historical factors that contributed to the outbreak of war, emphasizing the decisions made by leaders across Europe.\n\n8. **\"The First World War: A Complete History\" by Martin Gilbert** \n This complete history takes readers through the entirety of the war, from its causes to its aftermath, using a wide range of sources.\n\n9. **\"1914: The Year the World Ended\" by Paul Ham** \n Ham focuses on the pivotal year of 1914 and the early war''s devastation, analyzing its long-lasting effects - on the world.\n\n10. **\"War Horse\" by Michael Morpurgo** \n This children''s novel tells the story of a horse and his experiences during the war, highlighting the bond between animals and humans amidst the chaos.\n\nEach of these books offers unique perspectives and rich details about the First World War, making them valuable resources for anyone interested in this pivotal period in history.\n\n Guardrail:\n Ensure the authors are from Italy\n \n Your task:\n - Confirm if the Task result complies with the guardrail.\n - If not, provide clear feedback explaining what is wrong (e.g., by how much it violates the rule, or what specific part fails).\n - Focus only on identifying issues \u2014 do not propose corrections.\n - If the Task result complies with the guardrail, saying that is valid\n "}], "model": "gpt-4o-mini", "stop": ["\nObservation:"]}' - headers: - accept: - - application/json - accept-encoding: - - gzip, deflate - connection: - - keep-alive - content-length: - - '3917' - content-type: - - application/json - cookie: - - __cf_bm=mLRCnpdB3n_6medIZWHnUu8MNRGZsD6riaRhN47PK74-1745930028-1.0.1.1-M2lDM1_V9hNCK0MZrBnFalF3lndC3JkS8zhDOGww_LmOrgdpU9fZLpNZUmyinCQOnlCjDjDYJUECM82ffT1anqBiO1NoDeNp91EPKiK7s.8; _cfuvid=eTrj_ZhCx2XuylS5vYROwUlPrJBwOyrbS2Ki.msl45E-1745930028010-0.0.1.1-604800000 - host: - - api.openai.com - user-agent: - - OpenAI/Python 1.68.2 - x-stainless-arch: - - arm64 - x-stainless-async: - - 'false' - x-stainless-lang: - - python - x-stainless-os: - - MacOS - x-stainless-package-version: - - 1.68.2 - x-stainless-raw-response: - - 'true' - x-stainless-read-timeout: - - '600.0' - x-stainless-retry-count: - - '0' - x-stainless-runtime: - - CPython - x-stainless-runtime-version: - - 3.12.9 - method: POST - uri: https://api.openai.com/v1/chat/completions - response: - body: - string: "{\n \"id\": \"chatcmpl-BReTBRCAvSDG5VMdtF9ZjByy7lqSJ\",\n \"object\": \"chat.completion\",\n \"created\": 1745930121,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"Thought: I now can give a great answer \\nFinal Answer: {\\n \\\"valid\\\": false,\\n \\\"feedback\\\": \\\"None of the authors listed in the task result are from Italy. All the authors mentioned are from other countries, such as Germany, the UK, and the US.\\\"\\n}\",\n \"refusal\": null,\n \"annotations\": []\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 797,\n \"completion_tokens\": 60,\n \"total_tokens\": 857,\n \"prompt_tokens_details\": {\n \"cached_tokens\": 0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\": {\n \"reasoning_tokens\": 0,\n \"\ - audio_tokens\": 0,\n \"accepted_prediction_tokens\": 0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\": \"default\",\n \"system_fingerprint\": \"fp_0392822090\"\n}\n" - headers: - CF-RAY: - - 937ed6bd68faa435-GRU - Connection: - - keep-alive - Content-Type: - - application/json - Date: - - Tue, 29 Apr 2025 12:35:23 GMT - Server: - - cloudflare - Transfer-Encoding: - - chunked - X-Content-Type-Options: - - nosniff - access-control-expose-headers: - - X-Request-ID - alt-svc: - - h3=":443"; ma=86400 - cf-cache-status: - - DYNAMIC - openai-organization: - - crewai-iuxna1 - openai-processing-ms: - - '1138' - openai-version: - - '2020-10-01' - strict-transport-security: - - max-age=31536000; includeSubDomains; preload - x-ratelimit-limit-requests: - - '30000' - x-ratelimit-limit-tokens: - - '150000000' - x-ratelimit-remaining-requests: - - '29999' - x-ratelimit-remaining-tokens: - - '149999072' - x-ratelimit-reset-requests: - - 2ms - x-ratelimit-reset-tokens: - - 0s - x-request-id: - - req_2ba1be014a5974ba354aff564e26516a + - X-REQUEST-ID-XXX status: code: 200 message: OK diff --git a/lib/crewai/tests/cassettes/test_json_property_without_output_json.yaml b/lib/crewai/tests/cassettes/test_json_property_without_output_json.yaml index df5205161..f7089e7d2 100644 --- a/lib/crewai/tests/cassettes/test_json_property_without_output_json.yaml +++ b/lib/crewai/tests/cassettes/test_json_property_without_output_json.yaml @@ -1,11 +1,14 @@ interactions: - request: - body: '{"trace_id": "4ced1ade-0d34-4d28-a47d-61011b1f3582", "execution_type": "crew", "user_identifier": null, "execution_context": {"crew_fingerprint": null, "crew_name": "crew", "flow_name": null, "crewai_version": "1.2.1", "privacy_level": "standard"}, "execution_metadata": {"expected_duration_estimate": 300, "agent_count": 0, "task_count": 0, "flow_method_count": 0, "execution_started_at": "2025-10-31T07:25:08.937105+00:00"}, "ephemeral_trace_id": "4ced1ade-0d34-4d28-a47d-61011b1f3582"}' + body: '{"trace_id": "4ced1ade-0d34-4d28-a47d-61011b1f3582", "execution_type": + "crew", "user_identifier": null, "execution_context": {"crew_fingerprint": null, + "crew_name": "crew", "flow_name": null, "crewai_version": "1.2.1", "privacy_level": + "standard"}, "execution_metadata": {"expected_duration_estimate": 300, "agent_count": + 0, "task_count": 0, "flow_method_count": 0, "execution_started_at": "2025-10-31T07:25:08.937105+00:00"}, + "ephemeral_trace_id": "4ced1ade-0d34-4d28-a47d-61011b1f3582"}' headers: Accept: - '*/*' - Accept-Encoding: - - gzip, deflate, zstd Connection: - keep-alive Content-Length: @@ -13,11 +16,13 @@ interactions: Content-Type: - application/json User-Agent: - - CrewAI-CLI/1.2.1 + - X-USER-AGENT-XXX X-Crewai-Organization-Id: - 73c2b193-f579-422c-84c7-76a39a1da77f X-Crewai-Version: - 1.2.1 + accept-encoding: + - ACCEPT-ENCODING-XXX method: POST uri: https://app.crewai.com/crewai_plus/api/v1/tracing/ephemeral/batches response: @@ -35,46 +40,60 @@ interactions: cache-control: - no-store content-security-policy: - - 'default-src ''self'' *.app.crewai.com app.crewai.com; script-src ''self'' ''unsafe-inline'' *.app.crewai.com app.crewai.com https://cdn.jsdelivr.net/npm/apexcharts https://www.gstatic.com https://run.pstmn.io https://apis.google.com https://apis.google.com/js/api.js https://accounts.google.com https://accounts.google.com/gsi/client https://cdnjs.cloudflare.com/ajax/libs/normalize/8.0.1/normalize.min.css.map https://*.google.com https://docs.google.com https://slides.google.com https://js.hs-scripts.com https://js.sentry-cdn.com https://browser.sentry-cdn.com https://www.googletagmanager.com https://js-na1.hs-scripts.com https://js.hubspot.com http://js-na1.hs-scripts.com https://bat.bing.com https://cdn.amplitude.com https://cdn.segment.com https://d1d3n03t5zntha.cloudfront.net/ https://descriptusercontent.com https://edge.fullstory.com https://googleads.g.doubleclick.net https://js.hs-analytics.net https://js.hs-banner.com https://js.hsadspixel.net https://js.hscollectedforms.net - https://js.usemessages.com https://snap.licdn.com https://static.cloudflareinsights.com https://static.reo.dev https://www.google-analytics.com https://share.descript.com/; style-src ''self'' ''unsafe-inline'' *.app.crewai.com app.crewai.com https://cdn.jsdelivr.net/npm/apexcharts; img-src ''self'' data: *.app.crewai.com app.crewai.com https://zeus.tools.crewai.com https://dashboard.tools.crewai.com https://cdn.jsdelivr.net https://forms.hsforms.com https://track.hubspot.com https://px.ads.linkedin.com https://px4.ads.linkedin.com https://www.google.com https://www.google.com.br; font-src ''self'' data: *.app.crewai.com app.crewai.com; connect-src ''self'' *.app.crewai.com app.crewai.com https://zeus.tools.crewai.com https://connect.useparagon.com/ https://zeus.useparagon.com/* https://*.useparagon.com/* https://run.pstmn.io https://connect.tools.crewai.com/ https://*.sentry.io https://www.google-analytics.com https://edge.fullstory.com https://rs.fullstory.com https://api.hubspot.com - https://forms.hscollectedforms.net https://api.hubapi.com https://px.ads.linkedin.com https://px4.ads.linkedin.com https://google.com/pagead/form-data/16713662509 https://google.com/ccm/form-data/16713662509 https://www.google.com/ccm/collect https://worker-actionkit.tools.crewai.com https://api.reo.dev; frame-src ''self'' *.app.crewai.com app.crewai.com https://connect.useparagon.com/ https://zeus.tools.crewai.com https://zeus.useparagon.com/* https://connect.tools.crewai.com/ https://docs.google.com https://drive.google.com https://slides.google.com https://accounts.google.com https://*.google.com https://app.hubspot.com/ https://td.doubleclick.net https://www.googletagmanager.com/ https://www.youtube.com https://share.descript.com' + - CSP-FILTERED etag: - - W/"684f9dff2cfefa325ac69ea38dba2309" + - ETAG-XXX expires: - '0' permissions-policy: - - camera=(), microphone=(self), geolocation=() + - PERMISSIONS-POLICY-XXX pragma: - no-cache referrer-policy: - - strict-origin-when-cross-origin + - REFERRER-POLICY-XXX strict-transport-security: - - max-age=63072000; includeSubDomains + - STS-XXX vary: - Accept x-content-type-options: - - nosniff + - X-CONTENT-TYPE-XXX x-frame-options: - - SAMEORIGIN + - X-FRAME-OPTIONS-XXX x-permitted-cross-domain-policies: - - none + - X-PERMITTED-XXX x-request-id: - - 630cda16-c991-4ed0-b534-16c03eb2ffca + - X-REQUEST-ID-XXX x-runtime: - - '0.072382' + - X-RUNTIME-XXX x-xss-protection: - - 1; mode=block + - X-XSS-PROTECTION-XXX status: code: 201 message: Created - request: - body: '{"messages":[{"role":"system","content":"You are Scorer. You''re an expert scorer, specialized in scoring titles.\nYour personal goal is: Score the title\nTo give my best complete final answer to the task respond using the exact following format:\n\nThought: I now can give a great answer\nFinal Answer: Your final answer must be the great and the most complete as possible, it must be outcome described.\n\nI MUST use these formats, my job depends on it!"},{"role":"user","content":"\nCurrent Task: Give me an integer score between 1-5 for the following title: ''The impact of AI in the future of work''\n\nThis is the expected criteria for your final answer: The score of the title.\nyou MUST return the actual complete content as the final answer, not a summary.\nEnsure your final answer contains only the content in the following format: {\n \"properties\": {\n \"score\": {\n \"title\": \"Score\",\n \"type\": \"integer\"\n }\n },\n \"required\": [\n \"score\"\n ],\n \"title\": - \"ScoreOutput\",\n \"type\": \"object\",\n \"additionalProperties\": false\n}\n\nEnsure the final output does not include any code block markers like ```json or ```python.\n\nBegin! This is VERY important to you, use the tools available and give your best Final Answer, your job depends on it!\n\nThought:"}],"model":"gpt-4.1-mini"}' + body: '{"messages":[{"role":"system","content":"You are Scorer. You''re an expert + scorer, specialized in scoring titles.\nYour personal goal is: Score the title\nTo + give my best complete final answer to the task respond using the exact following + format:\n\nThought: I now can give a great answer\nFinal Answer: Your final + answer must be the great and the most complete as possible, it must be outcome + described.\n\nI MUST use these formats, my job depends on it!"},{"role":"user","content":"\nCurrent + Task: Give me an integer score between 1-5 for the following title: ''The impact + of AI in the future of work''\n\nThis is the expected criteria for your final + answer: The score of the title.\nyou MUST return the actual complete content + as the final answer, not a summary.\nEnsure your final answer contains only + the content in the following format: {\n \"properties\": {\n \"score\": + {\n \"title\": \"Score\",\n \"type\": \"integer\"\n }\n },\n \"required\": + [\n \"score\"\n ],\n \"title\": \"ScoreOutput\",\n \"type\": \"object\",\n \"additionalProperties\": + false\n}\n\nEnsure the final output does not include any code block markers + like ```json or ```python.\n\nBegin! This is VERY important to you, use the + tools available and give your best Final Answer, your job depends on it!\n\nThought:"}],"model":"gpt-4.1-mini"}' headers: + User-Agent: + - X-USER-AGENT-XXX accept: - application/json accept-encoding: - - gzip, deflate, zstd + - ACCEPT-ENCODING-XXX connection: - keep-alive content-length: @@ -83,20 +102,18 @@ interactions: - application/json host: - api.openai.com - user-agent: - - OpenAI/Python 1.109.1 x-stainless-arch: - - arm64 + - X-STAINLESS-ARCH-XXX x-stainless-async: - 'false' x-stainless-lang: - python x-stainless-os: - - MacOS + - X-STAINLESS-OS-XXX x-stainless-package-version: - 1.109.1 x-stainless-read-timeout: - - '600' + - X-STAINLESS-READ-TIMEOUT-XXX x-stainless-retry-count: - '0' x-stainless-runtime: @@ -107,10 +124,21 @@ interactions: uri: https://api.openai.com/v1/chat/completions response: body: - string: "{\n \"id\": \"chatcmpl-CWdnRkRPYTVe5JfVO7aC1cdVfqIdd\",\n \"object\": \"chat.completion\",\n \"created\": 1761895509,\n \"model\": \"gpt-4.1-mini-2025-04-14\",\n \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"Thought: I now can give a great answer\\n{\\n \\\"score\\\": 4\\n}\",\n \"refusal\": null,\n \"annotations\": []\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 281,\n \"completion_tokens\": 19,\n \"total_tokens\": 300,\n \"prompt_tokens_details\": {\n \"cached_tokens\": 0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\": {\n \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\": 0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\": \"default\",\n \"system_fingerprint\": \"fp_4c2851f862\"\n}\n" + string: "{\n \"id\": \"chatcmpl-CWdnRkRPYTVe5JfVO7aC1cdVfqIdd\",\n \"object\": + \"chat.completion\",\n \"created\": 1761895509,\n \"model\": \"gpt-4.1-mini-2025-04-14\",\n + \ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": + \"assistant\",\n \"content\": \"Thought: I now can give a great answer\\n{\\n + \ \\\"score\\\": 4\\n}\",\n \"refusal\": null,\n \"annotations\": + []\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n + \ }\n ],\n \"usage\": {\n \"prompt_tokens\": 281,\n \"completion_tokens\": + 19,\n \"total_tokens\": 300,\n \"prompt_tokens_details\": {\n \"cached_tokens\": + 0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\": + {\n \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\": + 0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\": + \"default\",\n \"system_fingerprint\": \"fp_4c2851f862\"\n}\n" headers: CF-RAY: - - 99716ab4788dea35-FCO + - CF-RAY-XXX Connection: - keep-alive Content-Type: @@ -120,26 +148,25 @@ interactions: Server: - cloudflare Set-Cookie: - - __cf_bm=S.q8_0ONHDHBHNOJdMZHwJDue9lKhWQHpKuP2lsspx4-1761895510-1.0.1.1-QUDxMm9SVfRT2R188bLcvxUd6SXIBmZgnz3D35UF95nNg8zX5Gzdg2OmU.uo29rqaGatjupcLPNMyhfOqeoyhNQ28Zz1ESSQLq0y70x3IvM; path=/; expires=Fri, 31-Oct-25 07:55:10 GMT; domain=.api.openai.com; HttpOnly; Secure; SameSite=None - - _cfuvid=TvP4GePeQO8E5c_xWNGzJb84f940MFRG_lZ_0hWAc5M-1761895510432-0.0.1.1-604800000; path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None + - SET-COOKIE-XXX Strict-Transport-Security: - - max-age=31536000; includeSubDomains; preload + - STS-XXX Transfer-Encoding: - chunked X-Content-Type-Options: - - nosniff + - X-CONTENT-TYPE-XXX access-control-expose-headers: - - X-Request-ID + - ACCESS-CONTROL-XXX alt-svc: - h3=":443"; ma=86400 cf-cache-status: - DYNAMIC openai-organization: - - crewai-iuxna1 + - OPENAI-ORG-XXX openai-processing-ms: - '569' openai-project: - - proj_xitITlrFeen7zjNSzML82h9x + - OPENAI-PROJECT-XXX openai-version: - '2020-10-01' x-envoy-upstream-service-time: @@ -149,40 +176,119 @@ interactions: x-ratelimit-limit-project-tokens: - '150000000' x-ratelimit-limit-requests: - - '30000' + - X-RATELIMIT-LIMIT-REQUESTS-XXX x-ratelimit-limit-tokens: - - '150000000' + - X-RATELIMIT-LIMIT-TOKENS-XXX x-ratelimit-remaining-project-tokens: - '149999700' x-ratelimit-remaining-requests: - - '29999' + - X-RATELIMIT-REMAINING-REQUESTS-XXX x-ratelimit-remaining-tokens: - - '149999700' + - X-RATELIMIT-REMAINING-TOKENS-XXX x-ratelimit-reset-project-tokens: - 0s x-ratelimit-reset-requests: - - 2ms + - X-RATELIMIT-RESET-REQUESTS-XXX x-ratelimit-reset-tokens: - - 0s + - X-RATELIMIT-RESET-TOKENS-XXX x-request-id: - - req_393e029e99d54ab0b4e7c69c5cba099f + - X-REQUEST-ID-XXX status: code: 200 message: OK - request: - body: '{"events": [{"event_id": "ea607d3f-c9ff-4aa8-babb-a84eb6d16663", "timestamp": "2025-10-31T07:25:08.935640+00:00", "type": "crew_kickoff_started", "event_data": {"timestamp": "2025-10-31T07:25:08.935640+00:00", "type": "crew_kickoff_started", "source_fingerprint": null, "source_type": null, "fingerprint_metadata": null, "task_id": null, "task_name": null, "agent_id": null, "agent_role": null, "crew_name": "crew", "crew": null, "inputs": null}}, {"event_id": "8e792d78-fe9c-4601-a7b4-7b105fa8fb40", "timestamp": "2025-10-31T07:25:08.937816+00:00", "type": "task_started", "event_data": {"task_description": "Give me an integer score between 1-5 for the following title: ''The impact of AI in the future of work''", "expected_output": "The score of the title.", "task_name": "Give me an integer score between 1-5 for the following title: ''The impact of AI in the future of work''", "context": "", "agent_role": "Scorer", "task_id": "677cf2dd-96a9-4eac-9140-0ecaba9609f7"}}, {"event_id": "a2fcdfee-a395-4dc8-99b8-ba3d8d843a70", - "timestamp": "2025-10-31T07:25:08.938816+00:00", "type": "agent_execution_started", "event_data": {"agent_role": "Scorer", "agent_goal": "Score the title", "agent_backstory": "You''re an expert scorer, specialized in scoring titles."}}, {"event_id": "b0ba7582-6ea0-4b66-a64a-0a1e38d57502", "timestamp": "2025-10-31T07:25:08.938996+00:00", "type": "llm_call_started", "event_data": {"timestamp": "2025-10-31T07:25:08.938996+00:00", "type": "llm_call_started", "source_fingerprint": null, "source_type": null, "fingerprint_metadata": null, "task_id": "677cf2dd-96a9-4eac-9140-0ecaba9609f7", "task_name": "Give me an integer score between 1-5 for the following title: ''The impact of AI in the future of work''", "agent_id": "8d6e3481-36fa-4fca-9665-977e6d76a969", "agent_role": "Scorer", "from_task": null, "from_agent": null, "model": "gpt-4.1-mini", "messages": [{"role": "system", "content": "You are Scorer. You''re an expert scorer, specialized in scoring titles.\nYour personal goal is: Score - the title\nTo give my best complete final answer to the task respond using the exact following format:\n\nThought: I now can give a great answer\nFinal Answer: Your final answer must be the great and the most complete as possible, it must be outcome described.\n\nI MUST use these formats, my job depends on it!"}, {"role": "user", "content": "\nCurrent Task: Give me an integer score between 1-5 for the following title: ''The impact of AI in the future of work''\n\nThis is the expected criteria for your final answer: The score of the title.\nyou MUST return the actual complete content as the final answer, not a summary.\nEnsure your final answer contains only the content in the following format: {\n \"properties\": {\n \"score\": {\n \"title\": \"Score\",\n \"type\": \"integer\"\n }\n },\n \"required\": [\n \"score\"\n ],\n \"title\": \"ScoreOutput\",\n \"type\": \"object\",\n \"additionalProperties\": false\n}\n\nEnsure the final output does not include any - code block markers like ```json or ```python.\n\nBegin! This is VERY important to you, use the tools available and give your best Final Answer, your job depends on it!\n\nThought:"}], "tools": null, "callbacks": [""], "available_functions": null}}, {"event_id": "ab6b168b-d954-494f-ae58-d9ef7a1941dc", "timestamp": "2025-10-31T07:25:10.466669+00:00", "type": "llm_call_completed", "event_data": {"timestamp": "2025-10-31T07:25:10.466669+00:00", "type": "llm_call_completed", "source_fingerprint": null, "source_type": null, "fingerprint_metadata": null, "task_id": "677cf2dd-96a9-4eac-9140-0ecaba9609f7", "task_name": "Give me an integer score between 1-5 for the following title: ''The impact of AI in the future of work''", "agent_id": "8d6e3481-36fa-4fca-9665-977e6d76a969", "agent_role": "Scorer", "from_task": null, "from_agent": null, "messages": [{"role": "system", "content": "You are Scorer. You''re an expert - scorer, specialized in scoring titles.\nYour personal goal is: Score the title\nTo give my best complete final answer to the task respond using the exact following format:\n\nThought: I now can give a great answer\nFinal Answer: Your final answer must be the great and the most complete as possible, it must be outcome described.\n\nI MUST use these formats, my job depends on it!"}, {"role": "user", "content": "\nCurrent Task: Give me an integer score between 1-5 for the following title: ''The impact of AI in the future of work''\n\nThis is the expected criteria for your final answer: The score of the title.\nyou MUST return the actual complete content as the final answer, not a summary.\nEnsure your final answer contains only the content in the following format: {\n \"properties\": {\n \"score\": {\n \"title\": \"Score\",\n \"type\": \"integer\"\n }\n },\n \"required\": [\n \"score\"\n ],\n \"title\": \"ScoreOutput\",\n \"type\": \"object\",\n \"additionalProperties\": - false\n}\n\nEnsure the final output does not include any code block markers like ```json or ```python.\n\nBegin! This is VERY important to you, use the tools available and give your best Final Answer, your job depends on it!\n\nThought:"}], "response": "Thought: I now can give a great answer\n{\n \"score\": 4\n}", "call_type": "", "model": "gpt-4.1-mini"}}, {"event_id": "0b8a17b6-e7d2-464d-a969-56dd705a40ef", "timestamp": "2025-10-31T07:25:10.466933+00:00", "type": "agent_execution_completed", "event_data": {"agent_role": "Scorer", "agent_goal": "Score the title", "agent_backstory": "You''re an expert scorer, specialized in scoring titles."}}, {"event_id": "b835b8e7-992b-4364-9ff8-25c81203ef77", "timestamp": "2025-10-31T07:25:10.467175+00:00", "type": "task_completed", "event_data": {"task_description": "Give me an integer score between 1-5 for the following title: ''The impact of AI in the future of work''", "task_name": "Give me an integer score - between 1-5 for the following title: ''The impact of AI in the future of work''", "task_id": "677cf2dd-96a9-4eac-9140-0ecaba9609f7", "output_raw": "Thought: I now can give a great answer\n{\n \"score\": 4\n}", "output_format": "OutputFormat.PYDANTIC", "agent_role": "Scorer"}}, {"event_id": "a9973b74-9ca6-46c3-b219-0b11ffa9e210", "timestamp": "2025-10-31T07:25:10.469421+00:00", "type": "crew_kickoff_completed", "event_data": {"timestamp": "2025-10-31T07:25:10.469421+00:00", "type": "crew_kickoff_completed", "source_fingerprint": null, "source_type": null, "fingerprint_metadata": null, "task_id": null, "task_name": null, "agent_id": null, "agent_role": null, "crew_name": "crew", "crew": null, "output": {"description": "Give me an integer score between 1-5 for the following title: ''The impact of AI in the future of work''", "name": "Give me an integer score between 1-5 for the following title: ''The impact of AI in the future of work''", "expected_output": "The score of the title.", - "summary": "Give me an integer score between 1-5 for the following...", "raw": "Thought: I now can give a great answer\n{\n \"score\": 4\n}", "pydantic": {}, "json_dict": null, "agent": "Scorer", "output_format": "pydantic"}, "total_tokens": 300}}], "batch_metadata": {"events_count": 8, "batch_sequence": 1, "is_final_batch": false}}' + body: '{"events": [{"event_id": "ea607d3f-c9ff-4aa8-babb-a84eb6d16663", "timestamp": + "2025-10-31T07:25:08.935640+00:00", "type": "crew_kickoff_started", "event_data": + {"timestamp": "2025-10-31T07:25:08.935640+00:00", "type": "crew_kickoff_started", + "source_fingerprint": null, "source_type": null, "fingerprint_metadata": null, + "task_id": null, "task_name": null, "agent_id": null, "agent_role": null, "crew_name": + "crew", "crew": null, "inputs": null}}, {"event_id": "8e792d78-fe9c-4601-a7b4-7b105fa8fb40", + "timestamp": "2025-10-31T07:25:08.937816+00:00", "type": "task_started", "event_data": + {"task_description": "Give me an integer score between 1-5 for the following + title: ''The impact of AI in the future of work''", "expected_output": "The + score of the title.", "task_name": "Give me an integer score between 1-5 for + the following title: ''The impact of AI in the future of work''", "context": + "", "agent_role": "Scorer", "task_id": "677cf2dd-96a9-4eac-9140-0ecaba9609f7"}}, + {"event_id": "a2fcdfee-a395-4dc8-99b8-ba3d8d843a70", "timestamp": "2025-10-31T07:25:08.938816+00:00", + "type": "agent_execution_started", "event_data": {"agent_role": "Scorer", "agent_goal": + "Score the title", "agent_backstory": "You''re an expert scorer, specialized + in scoring titles."}}, {"event_id": "b0ba7582-6ea0-4b66-a64a-0a1e38d57502", + "timestamp": "2025-10-31T07:25:08.938996+00:00", "type": "llm_call_started", + "event_data": {"timestamp": "2025-10-31T07:25:08.938996+00:00", "type": "llm_call_started", + "source_fingerprint": null, "source_type": null, "fingerprint_metadata": null, + "task_id": "677cf2dd-96a9-4eac-9140-0ecaba9609f7", "task_name": "Give me an + integer score between 1-5 for the following title: ''The impact of AI in the + future of work''", "agent_id": "8d6e3481-36fa-4fca-9665-977e6d76a969", "agent_role": + "Scorer", "from_task": null, "from_agent": null, "model": "gpt-4.1-mini", "messages": + [{"role": "system", "content": "You are Scorer. You''re an expert scorer, specialized + in scoring titles.\nYour personal goal is: Score the title\nTo give my best + complete final answer to the task respond using the exact following format:\n\nThought: + I now can give a great answer\nFinal Answer: Your final answer must be the great + and the most complete as possible, it must be outcome described.\n\nI MUST use + these formats, my job depends on it!"}, {"role": "user", "content": "\nCurrent + Task: Give me an integer score between 1-5 for the following title: ''The impact + of AI in the future of work''\n\nThis is the expected criteria for your final + answer: The score of the title.\nyou MUST return the actual complete content + as the final answer, not a summary.\nEnsure your final answer contains only + the content in the following format: {\n \"properties\": {\n \"score\": + {\n \"title\": \"Score\",\n \"type\": \"integer\"\n }\n },\n \"required\": + [\n \"score\"\n ],\n \"title\": \"ScoreOutput\",\n \"type\": \"object\",\n \"additionalProperties\": + false\n}\n\nEnsure the final output does not include any code block markers + like ```json or ```python.\n\nBegin! This is VERY important to you, use the + tools available and give your best Final Answer, your job depends on it!\n\nThought:"}], + "tools": null, "callbacks": [""], "available_functions": null}}, {"event_id": "ab6b168b-d954-494f-ae58-d9ef7a1941dc", + "timestamp": "2025-10-31T07:25:10.466669+00:00", "type": "llm_call_completed", + "event_data": {"timestamp": "2025-10-31T07:25:10.466669+00:00", "type": "llm_call_completed", + "source_fingerprint": null, "source_type": null, "fingerprint_metadata": null, + "task_id": "677cf2dd-96a9-4eac-9140-0ecaba9609f7", "task_name": "Give me an + integer score between 1-5 for the following title: ''The impact of AI in the + future of work''", "agent_id": "8d6e3481-36fa-4fca-9665-977e6d76a969", "agent_role": + "Scorer", "from_task": null, "from_agent": null, "messages": [{"role": "system", + "content": "You are Scorer. You''re an expert scorer, specialized in scoring + titles.\nYour personal goal is: Score the title\nTo give my best complete final + answer to the task respond using the exact following format:\n\nThought: I now + can give a great answer\nFinal Answer: Your final answer must be the great and + the most complete as possible, it must be outcome described.\n\nI MUST use these + formats, my job depends on it!"}, {"role": "user", "content": "\nCurrent Task: + Give me an integer score between 1-5 for the following title: ''The impact of + AI in the future of work''\n\nThis is the expected criteria for your final answer: + The score of the title.\nyou MUST return the actual complete content as the + final answer, not a summary.\nEnsure your final answer contains only the content + in the following format: {\n \"properties\": {\n \"score\": {\n \"title\": + \"Score\",\n \"type\": \"integer\"\n }\n },\n \"required\": [\n \"score\"\n ],\n \"title\": + \"ScoreOutput\",\n \"type\": \"object\",\n \"additionalProperties\": false\n}\n\nEnsure + the final output does not include any code block markers like ```json or ```python.\n\nBegin! + This is VERY important to you, use the tools available and give your best Final + Answer, your job depends on it!\n\nThought:"}], "response": "Thought: I now + can give a great answer\n{\n \"score\": 4\n}", "call_type": "", "model": "gpt-4.1-mini"}}, {"event_id": "0b8a17b6-e7d2-464d-a969-56dd705a40ef", + "timestamp": "2025-10-31T07:25:10.466933+00:00", "type": "agent_execution_completed", + "event_data": {"agent_role": "Scorer", "agent_goal": "Score the title", "agent_backstory": + "You''re an expert scorer, specialized in scoring titles."}}, {"event_id": "b835b8e7-992b-4364-9ff8-25c81203ef77", + "timestamp": "2025-10-31T07:25:10.467175+00:00", "type": "task_completed", "event_data": + {"task_description": "Give me an integer score between 1-5 for the following + title: ''The impact of AI in the future of work''", "task_name": "Give me an + integer score between 1-5 for the following title: ''The impact of AI in the + future of work''", "task_id": "677cf2dd-96a9-4eac-9140-0ecaba9609f7", "output_raw": + "Thought: I now can give a great answer\n{\n \"score\": 4\n}", "output_format": + "OutputFormat.PYDANTIC", "agent_role": "Scorer"}}, {"event_id": "a9973b74-9ca6-46c3-b219-0b11ffa9e210", + "timestamp": "2025-10-31T07:25:10.469421+00:00", "type": "crew_kickoff_completed", + "event_data": {"timestamp": "2025-10-31T07:25:10.469421+00:00", "type": "crew_kickoff_completed", + "source_fingerprint": null, "source_type": null, "fingerprint_metadata": null, + "task_id": null, "task_name": null, "agent_id": null, "agent_role": null, "crew_name": + "crew", "crew": null, "output": {"description": "Give me an integer score between + 1-5 for the following title: ''The impact of AI in the future of work''", "name": + "Give me an integer score between 1-5 for the following title: ''The impact + of AI in the future of work''", "expected_output": "The score of the title.", + "summary": "Give me an integer score between 1-5 for the following...", "raw": + "Thought: I now can give a great answer\n{\n \"score\": 4\n}", "pydantic": + {}, "json_dict": null, "agent": "Scorer", "output_format": "pydantic"}, "total_tokens": + 300}}], "batch_metadata": {"events_count": 8, "batch_sequence": 1, "is_final_batch": + false}}' headers: Accept: - '*/*' - Accept-Encoding: - - gzip, deflate, zstd Connection: - keep-alive Content-Length: @@ -190,11 +296,13 @@ interactions: Content-Type: - application/json User-Agent: - - CrewAI-CLI/1.2.1 + - X-USER-AGENT-XXX X-Crewai-Organization-Id: - 73c2b193-f579-422c-84c7-76a39a1da77f X-Crewai-Version: - 1.2.1 + accept-encoding: + - ACCEPT-ENCODING-XXX method: POST uri: https://app.crewai.com/crewai_plus/api/v1/tracing/ephemeral/batches/4ced1ade-0d34-4d28-a47d-61011b1f3582/events response: @@ -212,35 +320,33 @@ interactions: cache-control: - no-store content-security-policy: - - 'default-src ''self'' *.app.crewai.com app.crewai.com; script-src ''self'' ''unsafe-inline'' *.app.crewai.com app.crewai.com https://cdn.jsdelivr.net/npm/apexcharts https://www.gstatic.com https://run.pstmn.io https://apis.google.com https://apis.google.com/js/api.js https://accounts.google.com https://accounts.google.com/gsi/client https://cdnjs.cloudflare.com/ajax/libs/normalize/8.0.1/normalize.min.css.map https://*.google.com https://docs.google.com https://slides.google.com https://js.hs-scripts.com https://js.sentry-cdn.com https://browser.sentry-cdn.com https://www.googletagmanager.com https://js-na1.hs-scripts.com https://js.hubspot.com http://js-na1.hs-scripts.com https://bat.bing.com https://cdn.amplitude.com https://cdn.segment.com https://d1d3n03t5zntha.cloudfront.net/ https://descriptusercontent.com https://edge.fullstory.com https://googleads.g.doubleclick.net https://js.hs-analytics.net https://js.hs-banner.com https://js.hsadspixel.net https://js.hscollectedforms.net - https://js.usemessages.com https://snap.licdn.com https://static.cloudflareinsights.com https://static.reo.dev https://www.google-analytics.com https://share.descript.com/; style-src ''self'' ''unsafe-inline'' *.app.crewai.com app.crewai.com https://cdn.jsdelivr.net/npm/apexcharts; img-src ''self'' data: *.app.crewai.com app.crewai.com https://zeus.tools.crewai.com https://dashboard.tools.crewai.com https://cdn.jsdelivr.net https://forms.hsforms.com https://track.hubspot.com https://px.ads.linkedin.com https://px4.ads.linkedin.com https://www.google.com https://www.google.com.br; font-src ''self'' data: *.app.crewai.com app.crewai.com; connect-src ''self'' *.app.crewai.com app.crewai.com https://zeus.tools.crewai.com https://connect.useparagon.com/ https://zeus.useparagon.com/* https://*.useparagon.com/* https://run.pstmn.io https://connect.tools.crewai.com/ https://*.sentry.io https://www.google-analytics.com https://edge.fullstory.com https://rs.fullstory.com https://api.hubspot.com - https://forms.hscollectedforms.net https://api.hubapi.com https://px.ads.linkedin.com https://px4.ads.linkedin.com https://google.com/pagead/form-data/16713662509 https://google.com/ccm/form-data/16713662509 https://www.google.com/ccm/collect https://worker-actionkit.tools.crewai.com https://api.reo.dev; frame-src ''self'' *.app.crewai.com app.crewai.com https://connect.useparagon.com/ https://zeus.tools.crewai.com https://zeus.useparagon.com/* https://connect.tools.crewai.com/ https://docs.google.com https://drive.google.com https://slides.google.com https://accounts.google.com https://*.google.com https://app.hubspot.com/ https://td.doubleclick.net https://www.googletagmanager.com/ https://www.youtube.com https://share.descript.com' + - CSP-FILTERED etag: - - W/"be223998b84365d3a863f942c880adfb" + - ETAG-XXX expires: - '0' permissions-policy: - - camera=(), microphone=(self), geolocation=() + - PERMISSIONS-POLICY-XXX pragma: - no-cache referrer-policy: - - strict-origin-when-cross-origin + - REFERRER-POLICY-XXX strict-transport-security: - - max-age=63072000; includeSubDomains + - STS-XXX vary: - Accept x-content-type-options: - - nosniff + - X-CONTENT-TYPE-XXX x-frame-options: - - SAMEORIGIN + - X-FRAME-OPTIONS-XXX x-permitted-cross-domain-policies: - - none + - X-PERMITTED-XXX x-request-id: - - 9c19d6df-9190-4764-afed-f3444939d2e4 + - X-REQUEST-ID-XXX x-runtime: - - '0.123911' + - X-RUNTIME-XXX x-xss-protection: - - 1; mode=block + - X-XSS-PROTECTION-XXX status: code: 200 message: OK @@ -249,8 +355,6 @@ interactions: headers: Accept: - '*/*' - Accept-Encoding: - - gzip, deflate, zstd Connection: - keep-alive Content-Length: @@ -258,11 +362,13 @@ interactions: Content-Type: - application/json User-Agent: - - CrewAI-CLI/1.2.1 + - X-USER-AGENT-XXX X-Crewai-Organization-Id: - 73c2b193-f579-422c-84c7-76a39a1da77f X-Crewai-Version: - 1.2.1 + accept-encoding: + - ACCEPT-ENCODING-XXX method: PATCH uri: https://app.crewai.com/crewai_plus/api/v1/tracing/ephemeral/batches/4ced1ade-0d34-4d28-a47d-61011b1f3582/finalize response: @@ -280,35 +386,167 @@ interactions: cache-control: - no-store content-security-policy: - - 'default-src ''self'' *.app.crewai.com app.crewai.com; script-src ''self'' ''unsafe-inline'' *.app.crewai.com app.crewai.com https://cdn.jsdelivr.net/npm/apexcharts https://www.gstatic.com https://run.pstmn.io https://apis.google.com https://apis.google.com/js/api.js https://accounts.google.com https://accounts.google.com/gsi/client https://cdnjs.cloudflare.com/ajax/libs/normalize/8.0.1/normalize.min.css.map https://*.google.com https://docs.google.com https://slides.google.com https://js.hs-scripts.com https://js.sentry-cdn.com https://browser.sentry-cdn.com https://www.googletagmanager.com https://js-na1.hs-scripts.com https://js.hubspot.com http://js-na1.hs-scripts.com https://bat.bing.com https://cdn.amplitude.com https://cdn.segment.com https://d1d3n03t5zntha.cloudfront.net/ https://descriptusercontent.com https://edge.fullstory.com https://googleads.g.doubleclick.net https://js.hs-analytics.net https://js.hs-banner.com https://js.hsadspixel.net https://js.hscollectedforms.net - https://js.usemessages.com https://snap.licdn.com https://static.cloudflareinsights.com https://static.reo.dev https://www.google-analytics.com https://share.descript.com/; style-src ''self'' ''unsafe-inline'' *.app.crewai.com app.crewai.com https://cdn.jsdelivr.net/npm/apexcharts; img-src ''self'' data: *.app.crewai.com app.crewai.com https://zeus.tools.crewai.com https://dashboard.tools.crewai.com https://cdn.jsdelivr.net https://forms.hsforms.com https://track.hubspot.com https://px.ads.linkedin.com https://px4.ads.linkedin.com https://www.google.com https://www.google.com.br; font-src ''self'' data: *.app.crewai.com app.crewai.com; connect-src ''self'' *.app.crewai.com app.crewai.com https://zeus.tools.crewai.com https://connect.useparagon.com/ https://zeus.useparagon.com/* https://*.useparagon.com/* https://run.pstmn.io https://connect.tools.crewai.com/ https://*.sentry.io https://www.google-analytics.com https://edge.fullstory.com https://rs.fullstory.com https://api.hubspot.com - https://forms.hscollectedforms.net https://api.hubapi.com https://px.ads.linkedin.com https://px4.ads.linkedin.com https://google.com/pagead/form-data/16713662509 https://google.com/ccm/form-data/16713662509 https://www.google.com/ccm/collect https://worker-actionkit.tools.crewai.com https://api.reo.dev; frame-src ''self'' *.app.crewai.com app.crewai.com https://connect.useparagon.com/ https://zeus.tools.crewai.com https://zeus.useparagon.com/* https://connect.tools.crewai.com/ https://docs.google.com https://drive.google.com https://slides.google.com https://accounts.google.com https://*.google.com https://app.hubspot.com/ https://td.doubleclick.net https://www.googletagmanager.com/ https://www.youtube.com https://share.descript.com' + - CSP-FILTERED etag: - - W/"bff97e21bd1971750dcfdb102fba9dcd" + - ETAG-XXX expires: - '0' permissions-policy: - - camera=(), microphone=(self), geolocation=() + - PERMISSIONS-POLICY-XXX pragma: - no-cache referrer-policy: - - strict-origin-when-cross-origin + - REFERRER-POLICY-XXX strict-transport-security: - - max-age=63072000; includeSubDomains + - STS-XXX vary: - Accept x-content-type-options: - - nosniff + - X-CONTENT-TYPE-XXX x-frame-options: - - SAMEORIGIN + - X-FRAME-OPTIONS-XXX x-permitted-cross-domain-policies: - - none + - X-PERMITTED-XXX x-request-id: - - 2b6cd38d-78fa-4676-94ff-80e3bcf48a03 + - X-REQUEST-ID-XXX x-runtime: - - '0.064858' + - X-RUNTIME-XXX x-xss-protection: - - 1; mode=block + - X-XSS-PROTECTION-XXX + status: + code: 200 + message: OK +- request: + body: '{"messages":[{"role":"system","content":"You are Scorer. You''re an expert + scorer, specialized in scoring titles.\nYour personal goal is: Score the title"},{"role":"user","content":"\nCurrent + Task: Give me an integer score between 1-5 for the following title: ''The impact + of AI in the future of work''\n\nThis is the expected criteria for your final + answer: The score of the title.\nyou MUST return the actual complete content + as the final answer, not a summary.\nFormat your final answer according to the + following OpenAPI schema: {\n \"properties\": {\n \"score\": {\n \"title\": + \"Score\",\n \"type\": \"integer\"\n }\n },\n \"required\": [\n \"score\"\n ],\n \"title\": + \"ScoreOutput\",\n \"type\": \"object\",\n \"additionalProperties\": false\n}\n\nIMPORTANT: + Preserve the original content exactly as-is. Do NOT rewrite, paraphrase, or + modify the meaning of the content. Only structure it to match the schema format.\n\nDo + not include the OpenAPI schema in the final output. Ensure the final output + does not include any code block markers like ```json or ```python.\n\nProvide + your complete response:"},{"role":"system","content":"You are Scorer. You''re + an expert scorer, specialized in scoring titles.\nYour personal goal is: Score + the title"},{"role":"user","content":"\nCurrent Task: Give me an integer score + between 1-5 for the following title: ''The impact of AI in the future of work''\n\nThis + is the expected criteria for your final answer: The score of the title.\nyou + MUST return the actual complete content as the final answer, not a summary.\nFormat + your final answer according to the following OpenAPI schema: {\n \"properties\": + {\n \"score\": {\n \"title\": \"Score\",\n \"type\": \"integer\"\n }\n },\n \"required\": + [\n \"score\"\n ],\n \"title\": \"ScoreOutput\",\n \"type\": \"object\",\n \"additionalProperties\": + false\n}\n\nIMPORTANT: Preserve the original content exactly as-is. Do NOT rewrite, + paraphrase, or modify the meaning of the content. Only structure it to match + the schema format.\n\nDo not include the OpenAPI schema in the final output. + Ensure the final output does not include any code block markers like ```json + or ```python.\n\nProvide your complete response:"}],"model":"gpt-4.1-mini","response_format":{"type":"json_schema","json_schema":{"schema":{"properties":{"score":{"title":"Score","type":"integer"}},"required":["score"],"title":"ScoreOutput","type":"object","additionalProperties":false},"name":"ScoreOutput","strict":true}},"stream":false}' + headers: + User-Agent: + - X-USER-AGENT-XXX + accept: + - application/json + accept-encoding: + - ACCEPT-ENCODING-XXX + authorization: + - AUTHORIZATION-XXX + connection: + - keep-alive + content-length: + - '2541' + content-type: + - application/json + cookie: + - COOKIE-XXX + host: + - api.openai.com + x-stainless-arch: + - X-STAINLESS-ARCH-XXX + x-stainless-async: + - 'false' + x-stainless-helper-method: + - beta.chat.completions.parse + x-stainless-lang: + - python + x-stainless-os: + - X-STAINLESS-OS-XXX + x-stainless-package-version: + - 1.83.0 + x-stainless-read-timeout: + - X-STAINLESS-READ-TIMEOUT-XXX + x-stainless-retry-count: + - '0' + x-stainless-runtime: + - CPython + x-stainless-runtime-version: + - 3.13.12 + method: POST + uri: https://api.openai.com/v1/chat/completions + response: + body: + string: "{\n \"id\": \"chatcmpl-DDE0D15NvBLDvn8Wy68ZscARhqMaX\",\n \"object\": + \"chat.completion\",\n \"created\": 1772044461,\n \"model\": \"gpt-4.1-mini-2025-04-14\",\n + \ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": + \"assistant\",\n \"content\": \"{\\\"score\\\":4}\",\n \"refusal\": + null,\n \"annotations\": []\n },\n \"logprobs\": null,\n + \ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": + 513,\n \"completion_tokens\": 5,\n \"total_tokens\": 518,\n \"prompt_tokens_details\": + {\n \"cached_tokens\": 0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\": + {\n \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\": + 0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\": + \"default\",\n \"system_fingerprint\": \"fp_a391f2cee0\"\n}\n" + headers: + CF-RAY: + - CF-RAY-XXX + Connection: + - keep-alive + Content-Type: + - application/json + Date: + - Wed, 25 Feb 2026 18:34:21 GMT + Server: + - cloudflare + Strict-Transport-Security: + - STS-XXX + Transfer-Encoding: + - chunked + X-Content-Type-Options: + - X-CONTENT-TYPE-XXX + access-control-expose-headers: + - ACCESS-CONTROL-XXX + alt-svc: + - h3=":443"; ma=86400 + cf-cache-status: + - DYNAMIC + openai-organization: + - OPENAI-ORG-XXX + openai-processing-ms: + - '477' + openai-project: + - OPENAI-PROJECT-XXX + openai-version: + - '2020-10-01' + set-cookie: + - SET-COOKIE-XXX + x-openai-proxy-wasm: + - v0.1 + x-ratelimit-limit-requests: + - X-RATELIMIT-LIMIT-REQUESTS-XXX + x-ratelimit-limit-tokens: + - X-RATELIMIT-LIMIT-TOKENS-XXX + x-ratelimit-remaining-requests: + - X-RATELIMIT-REMAINING-REQUESTS-XXX + x-ratelimit-remaining-tokens: + - X-RATELIMIT-REMAINING-TOKENS-XXX + x-ratelimit-reset-requests: + - X-RATELIMIT-RESET-REQUESTS-XXX + x-ratelimit-reset-tokens: + - X-RATELIMIT-RESET-TOKENS-XXX + x-request-id: + - X-REQUEST-ID-XXX status: code: 200 message: OK diff --git a/lib/crewai/tests/cassettes/test_output_json_dict_hierarchical.yaml b/lib/crewai/tests/cassettes/test_output_json_dict_hierarchical.yaml index 59fc8a1e9..472fc68e7 100644 --- a/lib/crewai/tests/cassettes/test_output_json_dict_hierarchical.yaml +++ b/lib/crewai/tests/cassettes/test_output_json_dict_hierarchical.yaml @@ -426,4 +426,121 @@ interactions: status: code: 200 message: OK +- request: + body: '{"messages":[{"role":"user","content":"Thought: I now can give a great + answer\nFinal Answer: I would assign a score of 4 to the title \"The impact + of AI in the future of work.\" The title is very relevant and timely, as artificial + intelligence is a major transformative force affecting the labor market and + employment trends. It is clear and concise, effectively highlighting the focus + on AI''s influence on the future of work. However, while it is engaging and + implies substantial potential impact, it could be slightly more specific or + dynamic to reach an excellent level. Overall, it meets very good standards for + potential impact, engagement, relevance, and clarity."}],"model":"gpt-4o","tool_choice":{"type":"function","function":{"name":"ScoreOutput"}},"tools":[{"type":"function","function":{"name":"ScoreOutput","description":"Correctly + extracted `ScoreOutput` with all the required parameters with correct types","parameters":{"properties":{"score":{"title":"Score","type":"integer"}},"required":["score"],"type":"object"}}}]}' + headers: + User-Agent: + - X-USER-AGENT-XXX + accept: + - application/json + accept-encoding: + - ACCEPT-ENCODING-XXX + authorization: + - AUTHORIZATION-XXX + connection: + - keep-alive + content-length: + - '1034' + content-type: + - application/json + host: + - api.openai.com + x-stainless-arch: + - X-STAINLESS-ARCH-XXX + x-stainless-async: + - 'false' + x-stainless-lang: + - python + x-stainless-os: + - X-STAINLESS-OS-XXX + x-stainless-package-version: + - 1.83.0 + x-stainless-read-timeout: + - X-STAINLESS-READ-TIMEOUT-XXX + x-stainless-retry-count: + - '0' + x-stainless-runtime: + - CPython + x-stainless-runtime-version: + - 3.13.12 + method: POST + uri: https://api.openai.com/v1/chat/completions + response: + body: + string: "{\n \"id\": \"chatcmpl-DDE0G4tjiC8Je3BD8xhWMey7kZF66\",\n \"object\": + \"chat.completion\",\n \"created\": 1772044464,\n \"model\": \"gpt-4o-2024-08-06\",\n + \ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": + \"assistant\",\n \"content\": null,\n \"tool_calls\": [\n {\n + \ \"id\": \"call_x95I7UxdCvFccZ87imExKzu9\",\n \"type\": + \"function\",\n \"function\": {\n \"name\": \"ScoreOutput\",\n + \ \"arguments\": \"{\\\"score\\\":4}\"\n }\n }\n + \ ],\n \"refusal\": null,\n \"annotations\": []\n },\n + \ \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n ],\n + \ \"usage\": {\n \"prompt_tokens\": 188,\n \"completion_tokens\": 5,\n + \ \"total_tokens\": 193,\n \"prompt_tokens_details\": {\n \"cached_tokens\": + 0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\": + {\n \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\": + 0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\": + \"default\",\n \"system_fingerprint\": \"fp_64dfa806c7\"\n}\n" + headers: + CF-RAY: + - CF-RAY-XXX + Connection: + - keep-alive + Content-Type: + - application/json + Date: + - Wed, 25 Feb 2026 18:34:24 GMT + Server: + - cloudflare + Strict-Transport-Security: + - STS-XXX + Transfer-Encoding: + - chunked + X-Content-Type-Options: + - X-CONTENT-TYPE-XXX + access-control-expose-headers: + - ACCESS-CONTROL-XXX + alt-svc: + - h3=":443"; ma=86400 + cf-cache-status: + - DYNAMIC + openai-organization: + - OPENAI-ORG-XXX + openai-processing-ms: + - '385' + openai-project: + - OPENAI-PROJECT-XXX + openai-version: + - '2020-10-01' + set-cookie: + - SET-COOKIE-XXX + x-openai-proxy-wasm: + - v0.1 + x-ratelimit-limit-requests: + - X-RATELIMIT-LIMIT-REQUESTS-XXX + x-ratelimit-limit-tokens: + - X-RATELIMIT-LIMIT-TOKENS-XXX + x-ratelimit-remaining-requests: + - X-RATELIMIT-REMAINING-REQUESTS-XXX + x-ratelimit-remaining-tokens: + - X-RATELIMIT-REMAINING-TOKENS-XXX + x-ratelimit-reset-requests: + - X-RATELIMIT-RESET-REQUESTS-XXX + x-ratelimit-reset-tokens: + - X-RATELIMIT-RESET-TOKENS-XXX + x-request-id: + - X-REQUEST-ID-XXX + status: + code: 200 + message: OK version: 1 diff --git a/lib/crewai/tests/cassettes/test_output_json_dict_sequential.yaml b/lib/crewai/tests/cassettes/test_output_json_dict_sequential.yaml index 47a55673a..875005ced 100644 --- a/lib/crewai/tests/cassettes/test_output_json_dict_sequential.yaml +++ b/lib/crewai/tests/cassettes/test_output_json_dict_sequential.yaml @@ -1,98 +1,120 @@ interactions: - request: - body: '{"messages":[{"role":"system","content":"You are Scorer. You''re an expert scorer, specialized in scoring titles.\nYour personal goal is: Score the title\nTo give my best complete final answer to the task respond using the exact following format:\n\nThought: I now can give a great answer\nFinal Answer: Your final answer must be the great and the most complete as possible, it must be outcome described.\n\nI MUST use these formats, my job depends on it!"},{"role":"user","content":"\nCurrent Task: Give me an integer score between 1-5 for the following title: ''The impact of AI in the future of work''\n\nThis is the expected criteria for your final answer: The score of the title.\nyou MUST return the actual complete content as the final answer, not a summary.\nEnsure your final answer strictly adheres to the following OpenAPI schema: {\n \"properties\": {\n \"score\": {\n \"title\": \"Score\",\n \"type\": \"integer\"\n }\n },\n \"required\": [\n \"score\"\n ],\n \"title\": - \"ScoreOutput\",\n \"type\": \"object\",\n \"additionalProperties\": false\n}\n\nDo not include the OpenAPI schema in the final output. Ensure the final output does not include any code block markers like ```json or ```python.\n\nBegin! This is VERY important to you, use the tools available and give your best Final Answer, your job depends on it!\n\nThought:"}],"model":"gpt-4.1-mini"}' + body: '{"messages":[{"role":"system","content":"You are Scorer. You''re an expert + scorer, specialized in scoring titles.\nYour personal goal is: Score the title"},{"role":"user","content":"\nCurrent + Task: Give me an integer score between 1-5 for the following title: ''The impact + of AI in the future of work''\n\nThis is the expected criteria for your final + answer: The score of the title.\nyou MUST return the actual complete content + as the final answer, not a summary.\nFormat your final answer according to the + following OpenAPI schema: {\n \"properties\": {\n \"score\": {\n \"title\": + \"Score\",\n \"type\": \"integer\"\n }\n },\n \"required\": [\n \"score\"\n ],\n \"title\": + \"ScoreOutput\",\n \"type\": \"object\",\n \"additionalProperties\": false\n}\n\nIMPORTANT: + Preserve the original content exactly as-is. Do NOT rewrite, paraphrase, or + modify the meaning of the content. Only structure it to match the schema format.\n\nDo + not include the OpenAPI schema in the final output. Ensure the final output + does not include any code block markers like ```json or ```python.\n\nProvide + your complete response:"}],"model":"gpt-4.1-mini","response_format":{"type":"json_schema","json_schema":{"schema":{"properties":{"score":{"title":"Score","type":"integer"}},"required":["score"],"title":"ScoreOutput","type":"object","additionalProperties":false},"name":"ScoreOutput","strict":true}},"stream":false}' headers: + User-Agent: + - X-USER-AGENT-XXX accept: - application/json accept-encoding: - - gzip, deflate, zstd + - ACCEPT-ENCODING-XXX + authorization: + - AUTHORIZATION-XXX connection: - keep-alive content-length: - - '1394' + - '1421' content-type: - application/json host: - api.openai.com - user-agent: - - OpenAI/Python 1.109.1 x-stainless-arch: - - arm64 + - X-STAINLESS-ARCH-XXX x-stainless-async: - 'false' + x-stainless-helper-method: + - beta.chat.completions.parse x-stainless-lang: - python x-stainless-os: - - MacOS + - X-STAINLESS-OS-XXX x-stainless-package-version: - - 1.109.1 + - 1.83.0 x-stainless-read-timeout: - - '600' + - X-STAINLESS-READ-TIMEOUT-XXX x-stainless-retry-count: - '0' x-stainless-runtime: - CPython x-stainless-runtime-version: - - 3.12.9 + - 3.13.12 method: POST uri: https://api.openai.com/v1/chat/completions response: body: - string: "{\n \"id\": \"chatcmpl-CYg0UpOvDuMqlqYkt9WW8lQSkyatz\",\n \"object\": \"chat.completion\",\n \"created\": 1762380662,\n \"model\": \"gpt-4.1-mini-2025-04-14\",\n \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"Thought: I now can give a great answer\\nFinal Answer: {\\n \\\"score\\\": 4\\n}\",\n \"refusal\": null,\n \"annotations\": []\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 294,\n \"completion_tokens\": 22,\n \"total_tokens\": 316,\n \"prompt_tokens_details\": {\n \"cached_tokens\": 0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\": {\n \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\": 0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\": \"default\",\n \"system_fingerprint\": \"fp_4c2851f862\"\ - \n}\n" + string: "{\n \"id\": \"chatcmpl-DDE5QUOVeJDiOh6TuObUjh32f7Q0g\",\n \"object\": + \"chat.completion\",\n \"created\": 1772044784,\n \"model\": \"gpt-4.1-mini-2025-04-14\",\n + \ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": + \"assistant\",\n \"content\": \"{\\\"score\\\":4}\",\n \"refusal\": + null,\n \"annotations\": []\n },\n \"logprobs\": null,\n + \ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": + 276,\n \"completion_tokens\": 5,\n \"total_tokens\": 281,\n \"prompt_tokens_details\": + {\n \"cached_tokens\": 0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\": + {\n \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\": + 0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\": + \"default\",\n \"system_fingerprint\": \"fp_a391f2cee0\"\n}\n" headers: CF-RAY: - - REDACTED-RAY + - CF-RAY-XXX Connection: - keep-alive Content-Type: - application/json Date: - - Wed, 05 Nov 2025 22:11:02 GMT + - Wed, 25 Feb 2026 18:39:44 GMT Server: - cloudflare - Set-Cookie: - - __cf_bm=REDACTED; path=/; expires=Wed, 05-Nov-25 22:41:02 GMT; domain=.api.openai.com; HttpOnly; Secure; SameSite=None - - _cfuvid=REDACTED; path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None Strict-Transport-Security: - - max-age=31536000; includeSubDomains; preload + - STS-XXX Transfer-Encoding: - chunked X-Content-Type-Options: - - nosniff + - X-CONTENT-TYPE-XXX access-control-expose-headers: - - X-Request-ID + - ACCESS-CONTROL-XXX alt-svc: - h3=":443"; ma=86400 cf-cache-status: - DYNAMIC openai-organization: - - user-hortuttj2f3qtmxyik2zxf4q + - OPENAI-ORG-XXX openai-processing-ms: - - '864' + - '303' openai-project: - - proj_fL4UBWR1CMpAAdgzaSKqsVvA + - OPENAI-PROJECT-XXX openai-version: - '2020-10-01' - x-envoy-upstream-service-time: - - '3087' + set-cookie: + - SET-COOKIE-XXX x-openai-proxy-wasm: - v0.1 x-ratelimit-limit-requests: - - '500' + - X-RATELIMIT-LIMIT-REQUESTS-XXX x-ratelimit-limit-tokens: - - '200000' + - X-RATELIMIT-LIMIT-TOKENS-XXX x-ratelimit-remaining-requests: - - '499' + - X-RATELIMIT-REMAINING-REQUESTS-XXX x-ratelimit-remaining-tokens: - - '199687' + - X-RATELIMIT-REMAINING-TOKENS-XXX x-ratelimit-reset-requests: - - 120ms + - X-RATELIMIT-RESET-REQUESTS-XXX x-ratelimit-reset-tokens: - - 93ms + - X-RATELIMIT-RESET-TOKENS-XXX x-request-id: - - req_REDACTED + - X-REQUEST-ID-XXX status: code: 200 message: OK diff --git a/lib/crewai/tests/cassettes/test_output_json_hierarchical.yaml b/lib/crewai/tests/cassettes/test_output_json_hierarchical.yaml index 3596e3334..eff290b18 100644 --- a/lib/crewai/tests/cassettes/test_output_json_hierarchical.yaml +++ b/lib/crewai/tests/cassettes/test_output_json_hierarchical.yaml @@ -427,4 +427,122 @@ interactions: status: code: 200 message: OK +- request: + body: '{"messages":[{"role":"user","content":"Thought: The title \"The impact + of AI in the future of work\" is highly relevant given the widespread and ongoing + discussions about AI''s role in transforming workplaces globally. It is clear + and concise, directly indicating the subject and scope, which helps the reader + understand what to expect. In terms of engagement, it has strong potential to + attract interest from professionals, researchers, and the general public curious + about how AI will shape jobs and employment trends. Although it is somewhat + broad and could be more specific to a particular aspect of work or type of AI, + it remains focused enough to be effective as a general overview title.\n\nFinal + Answer: 4"}],"model":"gpt-4o","tool_choice":{"type":"function","function":{"name":"ScoreOutput"}},"tools":[{"type":"function","function":{"name":"ScoreOutput","description":"Correctly + extracted `ScoreOutput` with all the required parameters with correct types","parameters":{"properties":{"score":{"title":"Score","type":"integer"}},"required":["score"],"type":"object"}}}]}' + headers: + User-Agent: + - X-USER-AGENT-XXX + accept: + - application/json + accept-encoding: + - ACCEPT-ENCODING-XXX + authorization: + - AUTHORIZATION-XXX + connection: + - keep-alive + content-length: + - '1077' + content-type: + - application/json + host: + - api.openai.com + x-stainless-arch: + - X-STAINLESS-ARCH-XXX + x-stainless-async: + - 'false' + x-stainless-lang: + - python + x-stainless-os: + - X-STAINLESS-OS-XXX + x-stainless-package-version: + - 1.83.0 + x-stainless-read-timeout: + - X-STAINLESS-READ-TIMEOUT-XXX + x-stainless-retry-count: + - '0' + x-stainless-runtime: + - CPython + x-stainless-runtime-version: + - 3.13.12 + method: POST + uri: https://api.openai.com/v1/chat/completions + response: + body: + string: "{\n \"id\": \"chatcmpl-DDE0FPRrXCbAAssWcvT9wUojN8yPa\",\n \"object\": + \"chat.completion\",\n \"created\": 1772044463,\n \"model\": \"gpt-4o-2024-08-06\",\n + \ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": + \"assistant\",\n \"content\": null,\n \"tool_calls\": [\n {\n + \ \"id\": \"call_237IZJqLGcX4N5MZYEd6Wz2n\",\n \"type\": + \"function\",\n \"function\": {\n \"name\": \"ScoreOutput\",\n + \ \"arguments\": \"{\\\"score\\\":4}\"\n }\n }\n + \ ],\n \"refusal\": null,\n \"annotations\": []\n },\n + \ \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n ],\n + \ \"usage\": {\n \"prompt_tokens\": 191,\n \"completion_tokens\": 5,\n + \ \"total_tokens\": 196,\n \"prompt_tokens_details\": {\n \"cached_tokens\": + 0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\": + {\n \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\": + 0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\": + \"default\",\n \"system_fingerprint\": \"fp_64dfa806c7\"\n}\n" + headers: + CF-RAY: + - CF-RAY-XXX + Connection: + - keep-alive + Content-Type: + - application/json + Date: + - Wed, 25 Feb 2026 18:34:23 GMT + Server: + - cloudflare + Strict-Transport-Security: + - STS-XXX + Transfer-Encoding: + - chunked + X-Content-Type-Options: + - X-CONTENT-TYPE-XXX + access-control-expose-headers: + - ACCESS-CONTROL-XXX + alt-svc: + - h3=":443"; ma=86400 + cf-cache-status: + - DYNAMIC + openai-organization: + - OPENAI-ORG-XXX + openai-processing-ms: + - '365' + openai-project: + - OPENAI-PROJECT-XXX + openai-version: + - '2020-10-01' + set-cookie: + - SET-COOKIE-XXX + x-openai-proxy-wasm: + - v0.1 + x-ratelimit-limit-requests: + - X-RATELIMIT-LIMIT-REQUESTS-XXX + x-ratelimit-limit-tokens: + - X-RATELIMIT-LIMIT-TOKENS-XXX + x-ratelimit-remaining-requests: + - X-RATELIMIT-REMAINING-REQUESTS-XXX + x-ratelimit-remaining-tokens: + - X-RATELIMIT-REMAINING-TOKENS-XXX + x-ratelimit-reset-requests: + - X-RATELIMIT-RESET-REQUESTS-XXX + x-ratelimit-reset-tokens: + - X-RATELIMIT-RESET-TOKENS-XXX + x-request-id: + - X-REQUEST-ID-XXX + status: + code: 200 + message: OK version: 1 diff --git a/lib/crewai/tests/cassettes/test_output_json_sequential.yaml b/lib/crewai/tests/cassettes/test_output_json_sequential.yaml index 34d52b658..397f46fea 100644 --- a/lib/crewai/tests/cassettes/test_output_json_sequential.yaml +++ b/lib/crewai/tests/cassettes/test_output_json_sequential.yaml @@ -1,12 +1,29 @@ interactions: - request: - body: '{"messages":[{"role":"system","content":"You are Scorer. You''re an expert scorer, specialized in scoring titles.\nYour personal goal is: Score the title\nTo give my best complete final answer to the task respond using the exact following format:\n\nThought: I now can give a great answer\nFinal Answer: Your final answer must be the great and the most complete as possible, it must be outcome described.\n\nI MUST use these formats, my job depends on it!"},{"role":"user","content":"\nCurrent Task: Give me an integer score between 1-5 for the following title: ''The impact of AI in the future of work''\n\nThis is the expected criteria for your final answer: The score of the title.\nyou MUST return the actual complete content as the final answer, not a summary.\nEnsure your final answer strictly adheres to the following OpenAPI schema: {\n \"properties\": {\n \"score\": {\n \"title\": \"Score\",\n \"type\": \"integer\"\n }\n },\n \"required\": [\n \"score\"\n ],\n \"title\": - \"ScoreOutput\",\n \"type\": \"object\",\n \"additionalProperties\": false\n}\n\nDo not include the OpenAPI schema in the final output. Ensure the final output does not include any code block markers like ```json or ```python.\n\nBegin! This is VERY important to you, use the tools available and give your best Final Answer, your job depends on it!\n\nThought:"}],"model":"gpt-4.1-mini"}' + body: '{"messages":[{"role":"system","content":"You are Scorer. You''re an expert + scorer, specialized in scoring titles.\nYour personal goal is: Score the title\nTo + give my best complete final answer to the task respond using the exact following + format:\n\nThought: I now can give a great answer\nFinal Answer: Your final + answer must be the great and the most complete as possible, it must be outcome + described.\n\nI MUST use these formats, my job depends on it!"},{"role":"user","content":"\nCurrent + Task: Give me an integer score between 1-5 for the following title: ''The impact + of AI in the future of work''\n\nThis is the expected criteria for your final + answer: The score of the title.\nyou MUST return the actual complete content + as the final answer, not a summary.\nEnsure your final answer strictly adheres + to the following OpenAPI schema: {\n \"properties\": {\n \"score\": {\n \"title\": + \"Score\",\n \"type\": \"integer\"\n }\n },\n \"required\": [\n \"score\"\n ],\n \"title\": + \"ScoreOutput\",\n \"type\": \"object\",\n \"additionalProperties\": false\n}\n\nDo + not include the OpenAPI schema in the final output. Ensure the final output + does not include any code block markers like ```json or ```python.\n\nBegin! + This is VERY important to you, use the tools available and give your best Final + Answer, your job depends on it!\n\nThought:"}],"model":"gpt-4.1-mini"}' headers: + User-Agent: + - X-USER-AGENT-XXX accept: - application/json accept-encoding: - - gzip, deflate, zstd + - ACCEPT-ENCODING-XXX connection: - keep-alive content-length: @@ -15,20 +32,18 @@ interactions: - application/json host: - api.openai.com - user-agent: - - OpenAI/Python 1.109.1 x-stainless-arch: - - arm64 + - X-STAINLESS-ARCH-XXX x-stainless-async: - 'false' x-stainless-lang: - python x-stainless-os: - - MacOS + - X-STAINLESS-OS-XXX x-stainless-package-version: - 1.109.1 x-stainless-read-timeout: - - '600' + - X-STAINLESS-READ-TIMEOUT-XXX x-stainless-retry-count: - '0' x-stainless-runtime: @@ -39,11 +54,21 @@ interactions: uri: https://api.openai.com/v1/chat/completions response: body: - string: "{\n \"id\": \"chatcmpl-CYg0P4wugCaRcXw9kmLG3BAMBmkA0\",\n \"object\": \"chat.completion\",\n \"created\": 1762380657,\n \"model\": \"gpt-4.1-mini-2025-04-14\",\n \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"Thought: I now can give a great answer\\nFinal Answer: {\\n \\\"score\\\": 4\\n}\",\n \"refusal\": null,\n \"annotations\": []\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 294,\n \"completion_tokens\": 22,\n \"total_tokens\": 316,\n \"prompt_tokens_details\": {\n \"cached_tokens\": 0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\": {\n \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\": 0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\": \"default\",\n \"system_fingerprint\": \"fp_4c2851f862\"\ - \n}\n" + string: "{\n \"id\": \"chatcmpl-CYg0P4wugCaRcXw9kmLG3BAMBmkA0\",\n \"object\": + \"chat.completion\",\n \"created\": 1762380657,\n \"model\": \"gpt-4.1-mini-2025-04-14\",\n + \ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": + \"assistant\",\n \"content\": \"Thought: I now can give a great answer\\nFinal + Answer: {\\n \\\"score\\\": 4\\n}\",\n \"refusal\": null,\n \"annotations\": + []\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n + \ }\n ],\n \"usage\": {\n \"prompt_tokens\": 294,\n \"completion_tokens\": + 22,\n \"total_tokens\": 316,\n \"prompt_tokens_details\": {\n \"cached_tokens\": + 0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\": + {\n \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\": + 0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\": + \"default\",\n \"system_fingerprint\": \"fp_4c2851f862\"\n}\n" headers: CF-RAY: - - REDACTED-RAY + - CF-RAY-XXX Connection: - keep-alive Content-Type: @@ -53,26 +78,25 @@ interactions: Server: - cloudflare Set-Cookie: - - __cf_bm=REDACTED; path=/; expires=Wed, 05-Nov-25 22:40:57 GMT; domain=.api.openai.com; HttpOnly; Secure; SameSite=None - - _cfuvid=REDACTED; path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None + - SET-COOKIE-XXX Strict-Transport-Security: - - max-age=31536000; includeSubDomains; preload + - STS-XXX Transfer-Encoding: - chunked X-Content-Type-Options: - - nosniff + - X-CONTENT-TYPE-XXX access-control-expose-headers: - - X-Request-ID + - ACCESS-CONTROL-XXX alt-svc: - h3=":443"; ma=86400 cf-cache-status: - DYNAMIC openai-organization: - - user-hortuttj2f3qtmxyik2zxf4q + - OPENAI-ORG-XXX openai-processing-ms: - '537' openai-project: - - proj_fL4UBWR1CMpAAdgzaSKqsVvA + - OPENAI-PROJECT-XXX openai-version: - '2020-10-01' x-envoy-upstream-service-time: @@ -80,19 +104,153 @@ interactions: x-openai-proxy-wasm: - v0.1 x-ratelimit-limit-requests: - - '500' + - X-RATELIMIT-LIMIT-REQUESTS-XXX x-ratelimit-limit-tokens: - - '200000' + - X-RATELIMIT-LIMIT-TOKENS-XXX x-ratelimit-remaining-requests: - - '499' + - X-RATELIMIT-REMAINING-REQUESTS-XXX x-ratelimit-remaining-tokens: - - '199687' + - X-RATELIMIT-REMAINING-TOKENS-XXX x-ratelimit-reset-requests: - - 120ms + - X-RATELIMIT-RESET-REQUESTS-XXX x-ratelimit-reset-tokens: - - 93ms + - X-RATELIMIT-RESET-TOKENS-XXX x-request-id: - - req_REDACTED + - X-REQUEST-ID-XXX + status: + code: 200 + message: OK +- request: + body: '{"messages":[{"role":"system","content":"You are Scorer. You''re an expert + scorer, specialized in scoring titles.\nYour personal goal is: Score the title"},{"role":"user","content":"\nCurrent + Task: Give me an integer score between 1-5 for the following title: ''The impact + of AI in the future of work''\n\nThis is the expected criteria for your final + answer: The score of the title.\nyou MUST return the actual complete content + as the final answer, not a summary.\nFormat your final answer according to the + following OpenAPI schema: {\n \"properties\": {\n \"score\": {\n \"title\": + \"Score\",\n \"type\": \"integer\"\n }\n },\n \"required\": [\n \"score\"\n ],\n \"title\": + \"ScoreOutput\",\n \"type\": \"object\",\n \"additionalProperties\": false\n}\n\nIMPORTANT: + Preserve the original content exactly as-is. Do NOT rewrite, paraphrase, or + modify the meaning of the content. Only structure it to match the schema format.\n\nDo + not include the OpenAPI schema in the final output. Ensure the final output + does not include any code block markers like ```json or ```python.\n\nProvide + your complete response:"},{"role":"system","content":"You are Scorer. You''re + an expert scorer, specialized in scoring titles.\nYour personal goal is: Score + the title"},{"role":"user","content":"\nCurrent Task: Give me an integer score + between 1-5 for the following title: ''The impact of AI in the future of work''\n\nThis + is the expected criteria for your final answer: The score of the title.\nyou + MUST return the actual complete content as the final answer, not a summary.\nFormat + your final answer according to the following OpenAPI schema: {\n \"properties\": + {\n \"score\": {\n \"title\": \"Score\",\n \"type\": \"integer\"\n }\n },\n \"required\": + [\n \"score\"\n ],\n \"title\": \"ScoreOutput\",\n \"type\": \"object\",\n \"additionalProperties\": + false\n}\n\nIMPORTANT: Preserve the original content exactly as-is. Do NOT rewrite, + paraphrase, or modify the meaning of the content. Only structure it to match + the schema format.\n\nDo not include the OpenAPI schema in the final output. + Ensure the final output does not include any code block markers like ```json + or ```python.\n\nProvide your complete response:"}],"model":"gpt-4.1-mini","response_format":{"type":"json_schema","json_schema":{"schema":{"properties":{"score":{"title":"Score","type":"integer"}},"required":["score"],"title":"ScoreOutput","type":"object","additionalProperties":false},"name":"ScoreOutput","strict":true}},"stream":false}' + headers: + User-Agent: + - X-USER-AGENT-XXX + accept: + - application/json + accept-encoding: + - ACCEPT-ENCODING-XXX + authorization: + - AUTHORIZATION-XXX + connection: + - keep-alive + content-length: + - '2541' + content-type: + - application/json + cookie: + - COOKIE-XXX + host: + - api.openai.com + x-stainless-arch: + - X-STAINLESS-ARCH-XXX + x-stainless-async: + - 'false' + x-stainless-helper-method: + - beta.chat.completions.parse + x-stainless-lang: + - python + x-stainless-os: + - X-STAINLESS-OS-XXX + x-stainless-package-version: + - 1.83.0 + x-stainless-read-timeout: + - X-STAINLESS-READ-TIMEOUT-XXX + x-stainless-retry-count: + - '0' + x-stainless-runtime: + - CPython + x-stainless-runtime-version: + - 3.13.12 + method: POST + uri: https://api.openai.com/v1/chat/completions + response: + body: + string: "{\n \"id\": \"chatcmpl-DDDzz40VXTe9AsmG5ZSlL0IufvYKz\",\n \"object\": + \"chat.completion\",\n \"created\": 1772044447,\n \"model\": \"gpt-4.1-mini-2025-04-14\",\n + \ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": + \"assistant\",\n \"content\": \"{\\\"score\\\":4}\",\n \"refusal\": + null,\n \"annotations\": []\n },\n \"logprobs\": null,\n + \ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": + 513,\n \"completion_tokens\": 5,\n \"total_tokens\": 518,\n \"prompt_tokens_details\": + {\n \"cached_tokens\": 0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\": + {\n \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\": + 0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\": + \"default\",\n \"system_fingerprint\": \"fp_a391f2cee0\"\n}\n" + headers: + CF-RAY: + - CF-RAY-XXX + Connection: + - keep-alive + Content-Type: + - application/json + Date: + - Wed, 25 Feb 2026 18:34:07 GMT + Server: + - cloudflare + Strict-Transport-Security: + - STS-XXX + Transfer-Encoding: + - chunked + X-Content-Type-Options: + - X-CONTENT-TYPE-XXX + access-control-expose-headers: + - ACCESS-CONTROL-XXX + alt-svc: + - h3=":443"; ma=86400 + cf-cache-status: + - DYNAMIC + openai-organization: + - OPENAI-ORG-XXX + openai-processing-ms: + - '426' + openai-project: + - OPENAI-PROJECT-XXX + openai-version: + - '2020-10-01' + set-cookie: + - SET-COOKIE-XXX + x-openai-proxy-wasm: + - v0.1 + x-ratelimit-limit-requests: + - X-RATELIMIT-LIMIT-REQUESTS-XXX + x-ratelimit-limit-tokens: + - X-RATELIMIT-LIMIT-TOKENS-XXX + x-ratelimit-remaining-requests: + - X-RATELIMIT-REMAINING-REQUESTS-XXX + x-ratelimit-remaining-tokens: + - X-RATELIMIT-REMAINING-TOKENS-XXX + x-ratelimit-reset-requests: + - X-RATELIMIT-RESET-REQUESTS-XXX + x-ratelimit-reset-tokens: + - X-RATELIMIT-RESET-TOKENS-XXX + x-request-id: + - X-REQUEST-ID-XXX status: code: 200 message: OK diff --git a/lib/crewai/tests/cassettes/test_output_json_to_another_task.yaml b/lib/crewai/tests/cassettes/test_output_json_to_another_task.yaml index 575e9f85f..dac267822 100644 --- a/lib/crewai/tests/cassettes/test_output_json_to_another_task.yaml +++ b/lib/crewai/tests/cassettes/test_output_json_to_another_task.yaml @@ -1,194 +1,254 @@ interactions: - request: - body: '{"messages":[{"role":"system","content":"You are Scorer. You''re an expert scorer, specialized in scoring titles.\nYour personal goal is: Score the title\nTo give my best complete final answer to the task respond using the exact following format:\n\nThought: I now can give a great answer\nFinal Answer: Your final answer must be the great and the most complete as possible, it must be outcome described.\n\nI MUST use these formats, my job depends on it!"},{"role":"user","content":"\nCurrent Task: Give me an integer score between 1-5 for the following title: ''The impact of AI in the future of work''\n\nThis is the expected criteria for your final answer: The score of the title.\nyou MUST return the actual complete content as the final answer, not a summary.\nEnsure your final answer strictly adheres to the following OpenAPI schema: {\n \"properties\": {\n \"score\": {\n \"title\": \"Score\",\n \"type\": \"integer\"\n }\n },\n \"required\": [\n \"score\"\n ],\n \"title\": - \"ScoreOutput\",\n \"type\": \"object\",\n \"additionalProperties\": false\n}\n\nDo not include the OpenAPI schema in the final output. Ensure the final output does not include any code block markers like ```json or ```python.\n\nBegin! This is VERY important to you, use the tools available and give your best Final Answer, your job depends on it!\n\nThought:"}],"model":"gpt-4.1-mini"}' + body: '{"messages":[{"role":"system","content":"You are Scorer. You''re an expert + scorer, specialized in scoring titles.\nYour personal goal is: Score the title"},{"role":"user","content":"\nCurrent + Task: Give me an integer score between 1-5 for the following title: ''The impact + of AI in the future of work''\n\nThis is the expected criteria for your final + answer: The score of the title.\nyou MUST return the actual complete content + as the final answer, not a summary.\nFormat your final answer according to the + following OpenAPI schema: {\n \"properties\": {\n \"score\": {\n \"title\": + \"Score\",\n \"type\": \"integer\"\n }\n },\n \"required\": [\n \"score\"\n ],\n \"title\": + \"ScoreOutput\",\n \"type\": \"object\",\n \"additionalProperties\": false\n}\n\nIMPORTANT: + Preserve the original content exactly as-is. Do NOT rewrite, paraphrase, or + modify the meaning of the content. Only structure it to match the schema format.\n\nDo + not include the OpenAPI schema in the final output. Ensure the final output + does not include any code block markers like ```json or ```python.\n\nProvide + your complete response:"}],"model":"gpt-4.1-mini","response_format":{"type":"json_schema","json_schema":{"schema":{"properties":{"score":{"title":"Score","type":"integer"}},"required":["score"],"title":"ScoreOutput","type":"object","additionalProperties":false},"name":"ScoreOutput","strict":true}},"stream":false}' headers: + User-Agent: + - X-USER-AGENT-XXX accept: - application/json accept-encoding: - - gzip, deflate, zstd + - ACCEPT-ENCODING-XXX + authorization: + - AUTHORIZATION-XXX connection: - keep-alive content-length: - - '1394' + - '1421' content-type: - application/json host: - api.openai.com - user-agent: - - OpenAI/Python 1.109.1 x-stainless-arch: - - arm64 + - X-STAINLESS-ARCH-XXX x-stainless-async: - 'false' + x-stainless-helper-method: + - beta.chat.completions.parse x-stainless-lang: - python x-stainless-os: - - MacOS + - X-STAINLESS-OS-XXX x-stainless-package-version: - - 1.109.1 + - 1.83.0 x-stainless-read-timeout: - - '600' + - X-STAINLESS-READ-TIMEOUT-XXX x-stainless-retry-count: - '0' x-stainless-runtime: - CPython x-stainless-runtime-version: - - 3.12.9 + - 3.13.12 method: POST uri: https://api.openai.com/v1/chat/completions response: body: - string: "{\n \"id\": \"chatcmpl-CYg0M3aPReBrUikkn7QiHFyZG8ETn\",\n \"object\": \"chat.completion\",\n \"created\": 1762380654,\n \"model\": \"gpt-4.1-mini-2025-04-14\",\n \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"Thought: I now can give a great answer\\nFinal Answer: {\\n \\\"score\\\": 4\\n}\",\n \"refusal\": null,\n \"annotations\": []\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 294,\n \"completion_tokens\": 22,\n \"total_tokens\": 316,\n \"prompt_tokens_details\": {\n \"cached_tokens\": 0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\": {\n \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\": 0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\": \"default\",\n \"system_fingerprint\": \"fp_4c2851f862\"\ - \n}\n" + string: "{\n \"id\": \"chatcmpl-DDE5OBoRr3j1NGXkef0waj9TCBmLb\",\n \"object\": + \"chat.completion\",\n \"created\": 1772044782,\n \"model\": \"gpt-4.1-mini-2025-04-14\",\n + \ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": + \"assistant\",\n \"content\": \"{\\\"score\\\":4}\",\n \"refusal\": + null,\n \"annotations\": []\n },\n \"logprobs\": null,\n + \ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": + 276,\n \"completion_tokens\": 5,\n \"total_tokens\": 281,\n \"prompt_tokens_details\": + {\n \"cached_tokens\": 0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\": + {\n \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\": + 0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\": + \"default\",\n \"system_fingerprint\": \"fp_a391f2cee0\"\n}\n" headers: CF-RAY: - - REDACTED-RAY + - CF-RAY-XXX Connection: - keep-alive Content-Type: - application/json Date: - - Wed, 05 Nov 2025 22:10:54 GMT + - Wed, 25 Feb 2026 18:39:42 GMT Server: - cloudflare - Set-Cookie: - - __cf_bm=REDACTED; path=/; expires=Wed, 05-Nov-25 22:40:54 GMT; domain=.api.openai.com; HttpOnly; Secure; SameSite=None - - _cfuvid=REDACTED; path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None Strict-Transport-Security: - - max-age=31536000; includeSubDomains; preload + - STS-XXX Transfer-Encoding: - chunked X-Content-Type-Options: - - nosniff + - X-CONTENT-TYPE-XXX access-control-expose-headers: - - X-Request-ID + - ACCESS-CONTROL-XXX alt-svc: - h3=":443"; ma=86400 cf-cache-status: - DYNAMIC openai-organization: - - user-hortuttj2f3qtmxyik2zxf4q + - OPENAI-ORG-XXX openai-processing-ms: - - '730' + - '435' openai-project: - - proj_fL4UBWR1CMpAAdgzaSKqsVvA + - OPENAI-PROJECT-XXX openai-version: - '2020-10-01' - x-envoy-upstream-service-time: - - '754' + set-cookie: + - SET-COOKIE-XXX x-openai-proxy-wasm: - v0.1 x-ratelimit-limit-requests: - - '500' + - X-RATELIMIT-LIMIT-REQUESTS-XXX x-ratelimit-limit-tokens: - - '200000' + - X-RATELIMIT-LIMIT-TOKENS-XXX x-ratelimit-remaining-requests: - - '499' + - X-RATELIMIT-REMAINING-REQUESTS-XXX x-ratelimit-remaining-tokens: - - '199687' + - X-RATELIMIT-REMAINING-TOKENS-XXX x-ratelimit-reset-requests: - - 120ms + - X-RATELIMIT-RESET-REQUESTS-XXX x-ratelimit-reset-tokens: - - 93ms + - X-RATELIMIT-RESET-TOKENS-XXX x-request-id: - - req_REDACTED + - X-REQUEST-ID-XXX status: code: 200 message: OK - request: - body: '{"messages":[{"role":"system","content":"You are Scorer. You''re an expert scorer, specialized in scoring titles.\nYour personal goal is: Score the title\nTo give my best complete final answer to the task respond using the exact following format:\n\nThought: I now can give a great answer\nFinal Answer: Your final answer must be the great and the most complete as possible, it must be outcome described.\n\nI MUST use these formats, my job depends on it!"},{"role":"user","content":"\nCurrent Task: Given the score the title ''The impact of AI in the future of work'' got, give me an integer score between 1-5 for the following title: ''Return of the Jedi''\n\nThis is the expected criteria for your final answer: The score of the title.\nyou MUST return the actual complete content as the final answer, not a summary.\nEnsure your final answer strictly adheres to the following OpenAPI schema: {\n \"properties\": {\n \"score\": {\n \"title\": \"Score\",\n \"type\": \"integer\"\n }\n },\n \"required\": - [\n \"score\"\n ],\n \"title\": \"ScoreOutput\",\n \"type\": \"object\",\n \"additionalProperties\": false\n}\n\nDo not include the OpenAPI schema in the final output. Ensure the final output does not include any code block markers like ```json or ```python.\n\nThis is the context you''re working with:\n{\n \"score\": 4\n}\n\nBegin! This is VERY important to you, use the tools available and give your best Final Answer, your job depends on it!\n\nThought:"}],"model":"gpt-4.1-mini"}' + body: '{"messages":[{"role":"system","content":"You are Scorer. You''re an expert + scorer, specialized in scoring titles.\nYour personal goal is: Score the title"},{"role":"user","content":"\nCurrent + Task: Give me an integer score between 1-5 for the following title: ''The impact + of AI in the future of work''\n\nThis is the expected criteria for your final + answer: The score of the title.\nyou MUST return the actual complete content + as the final answer, not a summary.\nFormat your final answer according to the + following OpenAPI schema: {\n \"properties\": {\n \"score\": {\n \"title\": + \"Score\",\n \"type\": \"integer\"\n }\n },\n \"required\": [\n \"score\"\n ],\n \"title\": + \"ScoreOutput\",\n \"type\": \"object\",\n \"additionalProperties\": false\n}\n\nIMPORTANT: + Preserve the original content exactly as-is. Do NOT rewrite, paraphrase, or + modify the meaning of the content. Only structure it to match the schema format.\n\nDo + not include the OpenAPI schema in the final output. Ensure the final output + does not include any code block markers like ```json or ```python.\n\nProvide + your complete response:"},{"role":"assistant","content":"{\"score\":4}"},{"role":"system","content":"You + are Scorer. You''re an expert scorer, specialized in scoring titles.\nYour personal + goal is: Score the title"},{"role":"user","content":"\nCurrent Task: Given the + score the title ''The impact of AI in the future of work'' got, give me an integer + score between 1-5 for the following title: ''Return of the Jedi''\n\nThis is + the expected criteria for your final answer: The score of the title.\nyou MUST + return the actual complete content as the final answer, not a summary.\nFormat + your final answer according to the following OpenAPI schema: {\n \"properties\": + {\n \"score\": {\n \"title\": \"Score\",\n \"type\": \"integer\"\n }\n },\n \"required\": + [\n \"score\"\n ],\n \"title\": \"ScoreOutput\",\n \"type\": \"object\",\n \"additionalProperties\": + false\n}\n\nIMPORTANT: Preserve the original content exactly as-is. Do NOT rewrite, + paraphrase, or modify the meaning of the content. Only structure it to match + the schema format.\n\nDo not include the OpenAPI schema in the final output. + Ensure the final output does not include any code block markers like ```json + or ```python.\n\nThis is the context you''re working with:\n{\"score\":4}\n\nProvide + your complete response:"}],"model":"gpt-4.1-mini","response_format":{"type":"json_schema","json_schema":{"schema":{"properties":{"score":{"title":"Score","type":"integer"}},"required":["score"],"title":"ScoreOutput","type":"object","additionalProperties":false},"name":"ScoreOutput","strict":true}},"stream":false}' headers: + User-Agent: + - X-USER-AGENT-XXX accept: - application/json accept-encoding: - - gzip, deflate, zstd + - ACCEPT-ENCODING-XXX + authorization: + - AUTHORIZATION-XXX connection: - keep-alive content-length: - - '1512' + - '2699' content-type: - application/json cookie: - - __cf_bm=REDACTED; _cfuvid=REDACTED + - COOKIE-XXX host: - api.openai.com - user-agent: - - OpenAI/Python 1.109.1 x-stainless-arch: - - arm64 + - X-STAINLESS-ARCH-XXX x-stainless-async: - 'false' + x-stainless-helper-method: + - beta.chat.completions.parse x-stainless-lang: - python x-stainless-os: - - MacOS + - X-STAINLESS-OS-XXX x-stainless-package-version: - - 1.109.1 + - 1.83.0 x-stainless-read-timeout: - - '600' + - X-STAINLESS-READ-TIMEOUT-XXX x-stainless-retry-count: - '0' x-stainless-runtime: - CPython x-stainless-runtime-version: - - 3.12.9 + - 3.13.12 method: POST uri: https://api.openai.com/v1/chat/completions response: body: - string: "{\n \"id\": \"chatcmpl-CYg0MEYp1MebCu2eCMBqCwXtNYTbD\",\n \"object\": \"chat.completion\",\n \"created\": 1762380654,\n \"model\": \"gpt-4.1-mini-2025-04-14\",\n \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"Thought: I now can give a great answer\\nFinal Answer: {\\n \\\"score\\\": 3\\n}\",\n \"refusal\": null,\n \"annotations\": []\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 324,\n \"completion_tokens\": 22,\n \"total_tokens\": 346,\n \"prompt_tokens_details\": {\n \"cached_tokens\": 0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\": {\n \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\": 0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\": \"default\",\n \"system_fingerprint\": \"fp_4c2851f862\"\ - \n}\n" + string: "{\n \"id\": \"chatcmpl-DDE5OEawexwaazoOAgn4QD9W8roe6\",\n \"object\": + \"chat.completion\",\n \"created\": 1772044782,\n \"model\": \"gpt-4.1-mini-2025-04-14\",\n + \ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": + \"assistant\",\n \"content\": \"{\\\"score\\\":3}\",\n \"refusal\": + null,\n \"annotations\": []\n },\n \"logprobs\": null,\n + \ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": + 552,\n \"completion_tokens\": 5,\n \"total_tokens\": 557,\n \"prompt_tokens_details\": + {\n \"cached_tokens\": 0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\": + {\n \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\": + 0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\": + \"default\",\n \"system_fingerprint\": \"fp_a391f2cee0\"\n}\n" headers: CF-RAY: - - REDACTED-RAY + - CF-RAY-XXX Connection: - keep-alive Content-Type: - application/json Date: - - Wed, 05 Nov 2025 22:10:55 GMT + - Wed, 25 Feb 2026 18:39:43 GMT Server: - cloudflare Strict-Transport-Security: - - max-age=31536000; includeSubDomains; preload + - STS-XXX Transfer-Encoding: - chunked X-Content-Type-Options: - - nosniff + - X-CONTENT-TYPE-XXX access-control-expose-headers: - - X-Request-ID + - ACCESS-CONTROL-XXX alt-svc: - h3=":443"; ma=86400 cf-cache-status: - DYNAMIC openai-organization: - - user-hortuttj2f3qtmxyik2zxf4q + - OPENAI-ORG-XXX openai-processing-ms: - - '983' + - '309' openai-project: - - proj_fL4UBWR1CMpAAdgzaSKqsVvA + - OPENAI-PROJECT-XXX openai-version: - '2020-10-01' - x-envoy-upstream-service-time: - - '1002' x-openai-proxy-wasm: - v0.1 x-ratelimit-limit-requests: - - '500' + - X-RATELIMIT-LIMIT-REQUESTS-XXX x-ratelimit-limit-tokens: - - '200000' + - X-RATELIMIT-LIMIT-TOKENS-XXX x-ratelimit-remaining-requests: - - '499' + - X-RATELIMIT-REMAINING-REQUESTS-XXX x-ratelimit-remaining-tokens: - - '199659' + - X-RATELIMIT-REMAINING-TOKENS-XXX x-ratelimit-reset-requests: - - 120ms + - X-RATELIMIT-RESET-REQUESTS-XXX x-ratelimit-reset-tokens: - - 102ms + - X-RATELIMIT-RESET-TOKENS-XXX x-request-id: - - req_REDACTED + - X-REQUEST-ID-XXX status: code: 200 message: OK diff --git a/lib/crewai/tests/cassettes/test_output_pydantic_hierarchical.yaml b/lib/crewai/tests/cassettes/test_output_pydantic_hierarchical.yaml index f48000904..7ee93fe76 100644 --- a/lib/crewai/tests/cassettes/test_output_pydantic_hierarchical.yaml +++ b/lib/crewai/tests/cassettes/test_output_pydantic_hierarchical.yaml @@ -10,28 +10,29 @@ interactions: Task: Give me an integer score between 1-5 for the following title: ''The impact of AI in the future of work''\n\nThis is the expected criteria for your final answer: The score of the title.\nyou MUST return the actual complete content - as the final answer, not a summary.\nEnsure your final answer strictly adheres - to the following OpenAPI schema: {\n \"properties\": {\n \"score\": {\n \"title\": + as the final answer, not a summary.\nFormat your final answer according to the + following OpenAPI schema: {\n \"properties\": {\n \"score\": {\n \"title\": \"Score\",\n \"type\": \"integer\"\n }\n },\n \"required\": [\n \"score\"\n ],\n \"title\": - \"ScoreOutput\",\n \"type\": \"object\",\n \"additionalProperties\": false\n}\n\nDo + \"ScoreOutput\",\n \"type\": \"object\",\n \"additionalProperties\": false\n}\n\nIMPORTANT: + Preserve the original content exactly as-is. Do NOT rewrite, paraphrase, or + modify the meaning of the content. Only structure it to match the schema format.\n\nDo not include the OpenAPI schema in the final output. Ensure the final output - does not include any code block markers like ```json or ```python.\n\nThis is - VERY important to you, your job depends on it!"}],"model":"gpt-4o","tool_choice":"auto","tools":[{"type":"function","function":{"name":"Delegate_work_to_coworker","description":"Delegate + does not include any code block markers like ```json or ```python."}],"model":"gpt-4o","response_format":{"type":"json_schema","json_schema":{"schema":{"properties":{"score":{"title":"Score","type":"integer"}},"required":["score"],"title":"ScoreOutput","type":"object","additionalProperties":false},"name":"ScoreOutput","strict":true}},"stream":false,"tool_choice":"auto","tools":[{"type":"function","function":{"name":"delegate_work_to_coworker","description":"Delegate a specific task to one of the following coworkers: Scorer\nThe input to this tool should be the coworker, the task you want them to do, and ALL necessary context to execute the task, they know nothing about the task, so share absolutely - everything you know, don''t reference things but instead explain them.","parameters":{"properties":{"task":{"description":"The + everything you know, don''t reference things but instead explain them.","strict":true,"parameters":{"properties":{"task":{"description":"The task to delegate","title":"Task","type":"string"},"context":{"description":"The context for the task","title":"Context","type":"string"},"coworker":{"description":"The - role/name of the coworker to delegate to","title":"Coworker","type":"string"}},"required":["task","context","coworker"],"type":"object"}}},{"type":"function","function":{"name":"Ask_question_to_coworker","description":"Ask + role/name of the coworker to delegate to","title":"Coworker","type":"string"}},"required":["task","context","coworker"],"type":"object","additionalProperties":false}}},{"type":"function","function":{"name":"ask_question_to_coworker","description":"Ask a specific question to one of the following coworkers: Scorer\nThe input to this tool should be the coworker, the question you have for them, and ALL necessary context to ask the question properly, they know nothing about the question, so share absolutely everything you know, don''t reference things but instead - explain them.","parameters":{"properties":{"question":{"description":"The question - to ask","title":"Question","type":"string"},"context":{"description":"The context - for the question","title":"Context","type":"string"},"coworker":{"description":"The - role/name of the coworker to ask","title":"Coworker","type":"string"}},"required":["question","context","coworker"],"type":"object"}}}]}' + explain them.","strict":true,"parameters":{"properties":{"question":{"description":"The + question to ask","title":"Question","type":"string"},"context":{"description":"The + context for the question","title":"Context","type":"string"},"coworker":{"description":"The + role/name of the coworker to ask","title":"Coworker","type":"string"}},"required":["question","context","coworker"],"type":"object","additionalProperties":false}}}]}' headers: User-Agent: - X-USER-AGENT-XXX @@ -44,7 +45,7 @@ interactions: connection: - keep-alive content-length: - - '2959' + - '3415' content-type: - application/json host: @@ -53,6 +54,8 @@ interactions: - X-STAINLESS-ARCH-XXX x-stainless-async: - 'false' + x-stainless-helper-method: + - beta.chat.completions.parse x-stainless-lang: - python x-stainless-os: @@ -66,31 +69,33 @@ interactions: x-stainless-runtime: - CPython x-stainless-runtime-version: - - 3.13.3 + - 3.13.12 method: POST uri: https://api.openai.com/v1/chat/completions response: body: - string: "{\n \"id\": \"chatcmpl-D0u1dSPVqe5art2HXWibsPOp3SOti\",\n \"object\": - \"chat.completion\",\n \"created\": 1769107733,\n \"model\": \"gpt-4o-2024-08-06\",\n + string: "{\n \"id\": \"chatcmpl-DDG9wKD6IRmnAwBS1tw4NMVccsPnZ\",\n \"object\": + \"chat.completion\",\n \"created\": 1772052752,\n \"model\": \"gpt-4o-2024-08-06\",\n \ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": null,\n \"tool_calls\": [\n {\n - \ \"id\": \"call_AEHe6pv1NqguBRA5q9CHVSn3\",\n \"type\": - \"function\",\n \"function\": {\n \"name\": \"Delegate_work_to_coworker\",\n - \ \"arguments\": \"{\\\"task\\\":\\\"Provide an integer score - between 1-5 for the title 'The impact of AI in the future of work'. The score - should reflect how engaging, relevant, and thought-provoking the title is.\\\",\\\"context\\\":\\\"You - need to evaluate how well the title 'The impact of AI in the future of work' - meets the criteria of being engaging, relevant, and thought-provoking in the - context of emerging technologies and their implications on future work environments.\\\",\\\"coworker\\\":\\\"Scorer\\\"}\"\n - \ }\n }\n ],\n \"refusal\": null,\n \"annotations\": - []\n },\n \"logprobs\": null,\n \"finish_reason\": \"tool_calls\"\n - \ }\n ],\n \"usage\": {\n \"prompt_tokens\": 562,\n \"completion_tokens\": - 111,\n \"total_tokens\": 673,\n \"prompt_tokens_details\": {\n \"cached_tokens\": + \ \"id\": \"call_VzfUuCi89kzEC9gJgiMCz5B2\",\n \"type\": + \"function\",\n \"function\": {\n \"name\": \"delegate_work_to_coworker\",\n + \ \"arguments\": \"{\\\"task\\\":\\\"Evaluate the title 'The impact + of AI in the future of work' and give an integer score between 1-5 based on + how compelling or effective the title is.\\\",\\\"context\\\":\\\"You are + asked to evaluate a title 'The impact of AI in the future of work' and provide + an integer score between 1-5. The criteria for evaluation include how informative, + engaging, relevant, and clear the title is. Additionally, consider how the + title may attract the intended audience's interest and its potential impact + on readers.\\\",\\\"coworker\\\":\\\"Scorer\\\"}\"\n }\n }\n + \ ],\n \"refusal\": null,\n \"annotations\": []\n },\n + \ \"logprobs\": null,\n \"finish_reason\": \"tool_calls\"\n }\n + \ ],\n \"usage\": {\n \"prompt_tokens\": 613,\n \"completion_tokens\": + 127,\n \"total_tokens\": 740,\n \"prompt_tokens_details\": {\n \"cached_tokens\": 0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\": {\n \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\": 0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\": - \"default\",\n \"system_fingerprint\": \"fp_deacdd5f6f\"\n}\n" + \"default\",\n \"system_fingerprint\": \"fp_64dfa806c7\"\n}\n" headers: CF-RAY: - CF-RAY-XXX @@ -99,11 +104,9 @@ interactions: Content-Type: - application/json Date: - - Thu, 22 Jan 2026 18:48:56 GMT + - Wed, 25 Feb 2026 20:52:34 GMT Server: - cloudflare - Set-Cookie: - - SET-COOKIE-XXX Strict-Transport-Security: - STS-XXX Transfer-Encoding: @@ -119,146 +122,13 @@ interactions: openai-organization: - OPENAI-ORG-XXX openai-processing-ms: - - '3849' + - '2259' openai-project: - OPENAI-PROJECT-XXX openai-version: - '2020-10-01' - x-envoy-upstream-service-time: - - '3973' - x-openai-proxy-wasm: - - v0.1 - x-ratelimit-limit-requests: - - X-RATELIMIT-LIMIT-REQUESTS-XXX - x-ratelimit-limit-tokens: - - X-RATELIMIT-LIMIT-TOKENS-XXX - x-ratelimit-remaining-requests: - - X-RATELIMIT-REMAINING-REQUESTS-XXX - x-ratelimit-remaining-tokens: - - X-RATELIMIT-REMAINING-TOKENS-XXX - x-ratelimit-reset-requests: - - X-RATELIMIT-RESET-REQUESTS-XXX - x-ratelimit-reset-tokens: - - X-RATELIMIT-RESET-TOKENS-XXX - x-request-id: - - X-REQUEST-ID-XXX - status: - code: 200 - message: OK -- request: - body: '{"messages":[{"role":"system","content":"You are Scorer. You''re an expert - scorer, specialized in scoring titles.\nYour personal goal is: Score the title\nTo - give my best complete final answer to the task respond using the exact following - format:\n\nThought: I now can give a great answer\nFinal Answer: Your final - answer must be the great and the most complete as possible, it must be outcome - described.\n\nI MUST use these formats, my job depends on it!"},{"role":"user","content":"\nCurrent - Task: Provide an integer score between 1-5 for the title ''The impact of AI - in the future of work''. The score should reflect how engaging, relevant, and - thought-provoking the title is.\n\nThis is the expected criteria for your final - answer: Your best answer to your coworker asking you this, accounting for the - context shared.\nyou MUST return the actual complete content as the final answer, - not a summary.\n\nThis is the context you''re working with:\nYou need to evaluate - how well the title ''The impact of AI in the future of work'' meets the criteria - of being engaging, relevant, and thought-provoking in the context of emerging - technologies and their implications on future work environments.\n\nBegin! This - is VERY important to you, use the tools available and give your best Final Answer, - your job depends on it!\n\nThought:"}],"model":"gpt-4.1-mini"}' - headers: - User-Agent: - - X-USER-AGENT-XXX - accept: - - application/json - accept-encoding: - - ACCEPT-ENCODING-XXX - authorization: - - AUTHORIZATION-XXX - connection: - - keep-alive - content-length: - - '1348' - content-type: - - application/json - host: - - api.openai.com - x-stainless-arch: - - X-STAINLESS-ARCH-XXX - x-stainless-async: - - 'false' - x-stainless-lang: - - python - x-stainless-os: - - X-STAINLESS-OS-XXX - x-stainless-package-version: - - 1.83.0 - x-stainless-read-timeout: - - X-STAINLESS-READ-TIMEOUT-XXX - x-stainless-retry-count: - - '0' - x-stainless-runtime: - - CPython - x-stainless-runtime-version: - - 3.13.3 - method: POST - uri: https://api.openai.com/v1/chat/completions - response: - body: - string: "{\n \"id\": \"chatcmpl-D0u1hKGQrrJVYOcW1tAlQMgAjcaDX\",\n \"object\": - \"chat.completion\",\n \"created\": 1769107737,\n \"model\": \"gpt-4.1-mini-2025-04-14\",\n - \ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": - \"assistant\",\n \"content\": \"Thought: I now can give a great answer\\nFinal - Answer: The title 'The impact of AI in the future of work' is highly relevant - given the current and growing significance of artificial intelligence in transforming - work environments across industries. It is engaging because AI's influence - on future employment is a topic of widespread interest and concern, prompting - readers to explore its implications. Furthermore, it is thought-provoking - as it invites consideration of both the opportunities and challenges AI presents - for the workforce, including changes in job roles, skills, and economic structures. - However, the title could be more captivating or specific to heighten curiosity - and emphasize particular aspects of AI's impact. Overall, it effectively meets - the criteria but could be slightly enhanced for maximum engagement. Considering - all factors, I would score it a 4 out of 5.\",\n \"refusal\": null,\n - \ \"annotations\": []\n },\n \"logprobs\": null,\n \"finish_reason\": - \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 264,\n \"completion_tokens\": - 160,\n \"total_tokens\": 424,\n \"prompt_tokens_details\": {\n \"cached_tokens\": - 0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\": - {\n \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\": - 0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\": - \"default\",\n \"system_fingerprint\": \"fp_376a7ccef1\"\n}\n" - headers: - CF-RAY: - - CF-RAY-XXX - Connection: - - keep-alive - Content-Type: - - application/json - Date: - - Thu, 22 Jan 2026 18:49:00 GMT - Server: - - cloudflare - Set-Cookie: + set-cookie: - SET-COOKIE-XXX - Strict-Transport-Security: - - STS-XXX - Transfer-Encoding: - - chunked - X-Content-Type-Options: - - X-CONTENT-TYPE-XXX - access-control-expose-headers: - - ACCESS-CONTROL-XXX - alt-svc: - - h3=":443"; ma=86400 - cf-cache-status: - - DYNAMIC - openai-organization: - - OPENAI-ORG-XXX - openai-processing-ms: - - '3273' - openai-project: - - OPENAI-PROJECT-XXX - openai-version: - - '2020-10-01' - x-envoy-upstream-service-time: - - '3299' x-openai-proxy-wasm: - v0.1 x-ratelimit-limit-requests: @@ -289,47 +159,29 @@ interactions: Task: Give me an integer score between 1-5 for the following title: ''The impact of AI in the future of work''\n\nThis is the expected criteria for your final answer: The score of the title.\nyou MUST return the actual complete content - as the final answer, not a summary.\nEnsure your final answer strictly adheres - to the following OpenAPI schema: {\n \"properties\": {\n \"score\": {\n \"title\": + as the final answer, not a summary.\nFormat your final answer according to the + following OpenAPI schema: {\n \"properties\": {\n \"score\": {\n \"title\": \"Score\",\n \"type\": \"integer\"\n }\n },\n \"required\": [\n \"score\"\n ],\n \"title\": - \"ScoreOutput\",\n \"type\": \"object\",\n \"additionalProperties\": false\n}\n\nDo + \"ScoreOutput\",\n \"type\": \"object\",\n \"additionalProperties\": false\n}\n\nIMPORTANT: + Preserve the original content exactly as-is. Do NOT rewrite, paraphrase, or + modify the meaning of the content. Only structure it to match the schema format.\n\nDo not include the OpenAPI schema in the final output. Ensure the final output - does not include any code block markers like ```json or ```python.\n\nThis is - VERY important to you, your job depends on it!"},{"role":"assistant","content":null,"tool_calls":[{"id":"call_AEHe6pv1NqguBRA5q9CHVSn3","type":"function","function":{"name":"Delegate_work_to_coworker","arguments":"{\"task\":\"Provide - an integer score between 1-5 for the title ''The impact of AI in the future - of work''. The score should reflect how engaging, relevant, and thought-provoking - the title is.\",\"context\":\"You need to evaluate how well the title ''The - impact of AI in the future of work'' meets the criteria of being engaging, relevant, - and thought-provoking in the context of emerging technologies and their implications - on future work environments.\",\"coworker\":\"Scorer\"}"}}]},{"role":"tool","tool_call_id":"call_AEHe6pv1NqguBRA5q9CHVSn3","content":"The - title ''The impact of AI in the future of work'' is highly relevant given the - current and growing significance of artificial intelligence in transforming - work environments across industries. It is engaging because AI''s influence - on future employment is a topic of widespread interest and concern, prompting - readers to explore its implications. Furthermore, it is thought-provoking as - it invites consideration of both the opportunities and challenges AI presents - for the workforce, including changes in job roles, skills, and economic structures. - However, the title could be more captivating or specific to heighten curiosity - and emphasize particular aspects of AI''s impact. Overall, it effectively meets - the criteria but could be slightly enhanced for maximum engagement. Considering - all factors, I would score it a 4 out of 5."},{"role":"user","content":"Analyze - the tool result. If requirements are met, provide the Final Answer. Otherwise, - call the next tool. Deliver only the answer without meta-commentary."}],"model":"gpt-4o","tool_choice":"auto","tools":[{"type":"function","function":{"name":"Delegate_work_to_coworker","description":"Delegate + does not include any code block markers like ```json or ```python."}],"model":"gpt-4o","tool_choice":"auto","tools":[{"type":"function","function":{"name":"delegate_work_to_coworker","description":"Delegate a specific task to one of the following coworkers: Scorer\nThe input to this tool should be the coworker, the task you want them to do, and ALL necessary context to execute the task, they know nothing about the task, so share absolutely - everything you know, don''t reference things but instead explain them.","parameters":{"properties":{"task":{"description":"The + everything you know, don''t reference things but instead explain them.","strict":true,"parameters":{"properties":{"task":{"description":"The task to delegate","title":"Task","type":"string"},"context":{"description":"The context for the task","title":"Context","type":"string"},"coworker":{"description":"The - role/name of the coworker to delegate to","title":"Coworker","type":"string"}},"required":["task","context","coworker"],"type":"object"}}},{"type":"function","function":{"name":"Ask_question_to_coworker","description":"Ask + role/name of the coworker to delegate to","title":"Coworker","type":"string"}},"required":["task","context","coworker"],"type":"object","additionalProperties":false}}},{"type":"function","function":{"name":"ask_question_to_coworker","description":"Ask a specific question to one of the following coworkers: Scorer\nThe input to this tool should be the coworker, the question you have for them, and ALL necessary context to ask the question properly, they know nothing about the question, so share absolutely everything you know, don''t reference things but instead - explain them.","parameters":{"properties":{"question":{"description":"The question - to ask","title":"Question","type":"string"},"context":{"description":"The context - for the question","title":"Context","type":"string"},"coworker":{"description":"The - role/name of the coworker to ask","title":"Coworker","type":"string"}},"required":["question","context","coworker"],"type":"object"}}}]}' + explain them.","strict":true,"parameters":{"properties":{"question":{"description":"The + question to ask","title":"Question","type":"string"},"context":{"description":"The + context for the question","title":"Context","type":"string"},"coworker":{"description":"The + role/name of the coworker to ask","title":"Coworker","type":"string"}},"required":["question","context","coworker"],"type":"object","additionalProperties":false}}}]}' headers: User-Agent: - X-USER-AGENT-XXX @@ -342,7 +194,7 @@ interactions: connection: - keep-alive content-length: - - '4694' + - '3151' content-type: - application/json cookie: @@ -366,22 +218,31 @@ interactions: x-stainless-runtime: - CPython x-stainless-runtime-version: - - 3.13.3 + - 3.13.12 method: POST uri: https://api.openai.com/v1/chat/completions response: body: - string: "{\n \"id\": \"chatcmpl-D0u1kZrAEdxxk1GHhh8iEvvddrv5C\",\n \"object\": - \"chat.completion\",\n \"created\": 1769107740,\n \"model\": \"gpt-4o-2024-08-06\",\n + string: "{\n \"id\": \"chatcmpl-DDG9zJ5ZtuBIJLBxuTBqV4pYyaAf3\",\n \"object\": + \"chat.completion\",\n \"created\": 1772052755,\n \"model\": \"gpt-4o-2024-08-06\",\n \ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": - \"assistant\",\n \"content\": \"{\\\"score\\\":4}\",\n \"refusal\": - null,\n \"annotations\": []\n },\n \"logprobs\": null,\n - \ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": - 868,\n \"completion_tokens\": 6,\n \"total_tokens\": 874,\n \"prompt_tokens_details\": - {\n \"cached_tokens\": 0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\": + \"assistant\",\n \"content\": null,\n \"tool_calls\": [\n {\n + \ \"id\": \"call_IdyahKEb4Ez9fWTlL0SWNU97\",\n \"type\": + \"function\",\n \"function\": {\n \"name\": \"ask_question_to_coworker\",\n + \ \"arguments\": \"{\\\"question\\\":\\\"What score would you + give between 1-5 to the following title: 'The impact of AI in the future of + work' and why?\\\",\\\"context\\\":\\\"Your task is to evaluate the title + based on its ability to intrigue, its clarity, and relevance. You need to + provide an integer score between 1 and 5 for this title, considering these + aspects.\\\",\\\"coworker\\\":\\\"Scorer\\\"}\"\n }\n }\n + \ ],\n \"refusal\": null,\n \"annotations\": []\n },\n + \ \"logprobs\": null,\n \"finish_reason\": \"tool_calls\"\n }\n + \ ],\n \"usage\": {\n \"prompt_tokens\": 581,\n \"completion_tokens\": + 97,\n \"total_tokens\": 678,\n \"prompt_tokens_details\": {\n \"cached_tokens\": + 0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\": {\n \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\": 0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\": - \"default\",\n \"system_fingerprint\": \"fp_deacdd5f6f\"\n}\n" + \"default\",\n \"system_fingerprint\": \"fp_18e61aa3bc\"\n}\n" headers: CF-RAY: - CF-RAY-XXX @@ -390,7 +251,7 @@ interactions: Content-Type: - application/json Date: - - Thu, 22 Jan 2026 18:49:00 GMT + - Wed, 25 Feb 2026 20:52:36 GMT Server: - cloudflare Strict-Transport-Security: @@ -408,13 +269,299 @@ interactions: openai-organization: - OPENAI-ORG-XXX openai-processing-ms: - - '480' + - '1686' + openai-project: + - OPENAI-PROJECT-XXX + openai-version: + - '2020-10-01' + x-openai-proxy-wasm: + - v0.1 + x-ratelimit-limit-requests: + - X-RATELIMIT-LIMIT-REQUESTS-XXX + x-ratelimit-limit-tokens: + - X-RATELIMIT-LIMIT-TOKENS-XXX + x-ratelimit-remaining-requests: + - X-RATELIMIT-REMAINING-REQUESTS-XXX + x-ratelimit-remaining-tokens: + - X-RATELIMIT-REMAINING-TOKENS-XXX + x-ratelimit-reset-requests: + - X-RATELIMIT-RESET-REQUESTS-XXX + x-ratelimit-reset-tokens: + - X-RATELIMIT-RESET-TOKENS-XXX + x-request-id: + - X-REQUEST-ID-XXX + status: + code: 200 + message: OK +- request: + body: '{"messages":[{"role":"system","content":"You are Scorer. You''re an expert + scorer, specialized in scoring titles.\nYour personal goal is: Score the title"},{"role":"user","content":"\nCurrent + Task: What score would you give between 1-5 to the following title: ''The impact + of AI in the future of work'' and why?\n\nThis is the expected criteria for + your final answer: Your best answer to your coworker asking you this, accounting + for the context shared.\nyou MUST return the actual complete content as the + final answer, not a summary.\n\nThis is the context you''re working with:\nYour + task is to evaluate the title based on its ability to intrigue, its clarity, + and relevance. You need to provide an integer score between 1 and 5 for this + title, considering these aspects.\n\nProvide your complete response:"}],"model":"gpt-4.1-mini"}' + headers: + User-Agent: + - X-USER-AGENT-XXX + accept: + - application/json + accept-encoding: + - ACCEPT-ENCODING-XXX + authorization: + - AUTHORIZATION-XXX + connection: + - keep-alive + content-length: + - '831' + content-type: + - application/json + host: + - api.openai.com + x-stainless-arch: + - X-STAINLESS-ARCH-XXX + x-stainless-async: + - 'false' + x-stainless-lang: + - python + x-stainless-os: + - X-STAINLESS-OS-XXX + x-stainless-package-version: + - 1.83.0 + x-stainless-read-timeout: + - X-STAINLESS-READ-TIMEOUT-XXX + x-stainless-retry-count: + - '0' + x-stainless-runtime: + - CPython + x-stainless-runtime-version: + - 3.13.12 + method: POST + uri: https://api.openai.com/v1/chat/completions + response: + body: + string: "{\n \"id\": \"chatcmpl-DDGA1eLxVsUvh5Ptopxsrctx3s8fF\",\n \"object\": + \"chat.completion\",\n \"created\": 1772052757,\n \"model\": \"gpt-4.1-mini-2025-04-14\",\n + \ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": + \"assistant\",\n \"content\": \"I would give the title \\\"The impact + of AI in the future of work\\\" a score of 4 out of 5.\\n\\nHere's why:\\n\\n- + **Clarity:** The title is clear and straightforward; it immediately tells + the reader that the focus is on how AI will influence the work landscape going + forward. There is no ambiguity about the subject matter.\\n\\n- **Relevance:** + The topic is highly relevant in today's context, as AI technologies are rapidly + transforming industries and workplace dynamics. This makes the title timely + and likely to attract interest from professionals, academics, and anyone curious + about technological impacts on employment.\\n\\n- **Intrigue:** While the + title is clear and relevant, it lacks a bit of punch or uniqueness that might + make it stand out more. It's somewhat generic\u2014many articles use similar + phrasing. Adding an element that hints at specific insights or a fresh perspective + could increase intrigue.\\n\\nOverall, the title effectively conveys the subject + and relevance but could be slightly improved with more compelling language + to boost interest.\",\n \"refusal\": null,\n \"annotations\": + []\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n + \ }\n ],\n \"usage\": {\n \"prompt_tokens\": 164,\n \"completion_tokens\": + 198,\n \"total_tokens\": 362,\n \"prompt_tokens_details\": {\n \"cached_tokens\": + 0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\": + {\n \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\": + 0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\": + \"default\",\n \"system_fingerprint\": \"fp_a391f2cee0\"\n}\n" + headers: + CF-RAY: + - CF-RAY-XXX + Connection: + - keep-alive + Content-Type: + - application/json + Date: + - Wed, 25 Feb 2026 20:52:41 GMT + Server: + - cloudflare + Strict-Transport-Security: + - STS-XXX + Transfer-Encoding: + - chunked + X-Content-Type-Options: + - X-CONTENT-TYPE-XXX + access-control-expose-headers: + - ACCESS-CONTROL-XXX + alt-svc: + - h3=":443"; ma=86400 + cf-cache-status: + - DYNAMIC + openai-organization: + - OPENAI-ORG-XXX + openai-processing-ms: + - '4344' + openai-project: + - OPENAI-PROJECT-XXX + openai-version: + - '2020-10-01' + set-cookie: + - SET-COOKIE-XXX + x-openai-proxy-wasm: + - v0.1 + x-ratelimit-limit-requests: + - X-RATELIMIT-LIMIT-REQUESTS-XXX + x-ratelimit-limit-tokens: + - X-RATELIMIT-LIMIT-TOKENS-XXX + x-ratelimit-remaining-requests: + - X-RATELIMIT-REMAINING-REQUESTS-XXX + x-ratelimit-remaining-tokens: + - X-RATELIMIT-REMAINING-TOKENS-XXX + x-ratelimit-reset-requests: + - X-RATELIMIT-RESET-REQUESTS-XXX + x-ratelimit-reset-tokens: + - X-RATELIMIT-RESET-TOKENS-XXX + x-request-id: + - X-REQUEST-ID-XXX + status: + code: 200 + message: OK +- request: + body: "{\"messages\":[{\"role\":\"system\",\"content\":\"You are Crew Manager. + You are a seasoned manager with a knack for getting the best out of your team.\\nYou + are also known for your ability to delegate work to the right people, and to + ask the right questions to get the best out of your team.\\nEven though you + don't perform tasks by yourself, you have a lot of experience in the field, + which allows you to properly evaluate the work of your team members.\\nYour + personal goal is: Manage the team to complete the task in the best way possible.\"},{\"role\":\"user\",\"content\":\"\\nCurrent + Task: Give me an integer score between 1-5 for the following title: 'The impact + of AI in the future of work'\\n\\nThis is the expected criteria for your final + answer: The score of the title.\\nyou MUST return the actual complete content + as the final answer, not a summary.\\nFormat your final answer according to + the following OpenAPI schema: {\\n \\\"properties\\\": {\\n \\\"score\\\": + {\\n \\\"title\\\": \\\"Score\\\",\\n \\\"type\\\": \\\"integer\\\"\\n + \ }\\n },\\n \\\"required\\\": [\\n \\\"score\\\"\\n ],\\n \\\"title\\\": + \\\"ScoreOutput\\\",\\n \\\"type\\\": \\\"object\\\",\\n \\\"additionalProperties\\\": + false\\n}\\n\\nIMPORTANT: Preserve the original content exactly as-is. Do NOT + rewrite, paraphrase, or modify the meaning of the content. Only structure it + to match the schema format.\\n\\nDo not include the OpenAPI schema in the final + output. Ensure the final output does not include any code block markers like + ```json or ```python.\"},{\"role\":\"assistant\",\"content\":null,\"tool_calls\":[{\"id\":\"call_IdyahKEb4Ez9fWTlL0SWNU97\",\"type\":\"function\",\"function\":{\"name\":\"ask_question_to_coworker\",\"arguments\":\"{\\\"question\\\":\\\"What + score would you give between 1-5 to the following title: 'The impact of AI in + the future of work' and why?\\\",\\\"context\\\":\\\"Your task is to evaluate + the title based on its ability to intrigue, its clarity, and relevance. You + need to provide an integer score between 1 and 5 for this title, considering + these aspects.\\\",\\\"coworker\\\":\\\"Scorer\\\"}\"}}]},{\"role\":\"tool\",\"tool_call_id\":\"call_IdyahKEb4Ez9fWTlL0SWNU97\",\"name\":\"ask_question_to_coworker\",\"content\":\"I + would give the title \\\"The impact of AI in the future of work\\\" a score + of 4 out of 5.\\n\\nHere's why:\\n\\n- **Clarity:** The title is clear and straightforward; + it immediately tells the reader that the focus is on how AI will influence the + work landscape going forward. There is no ambiguity about the subject matter.\\n\\n- + **Relevance:** The topic is highly relevant in today's context, as AI technologies + are rapidly transforming industries and workplace dynamics. This makes the title + timely and likely to attract interest from professionals, academics, and anyone + curious about technological impacts on employment.\\n\\n- **Intrigue:** While + the title is clear and relevant, it lacks a bit of punch or uniqueness that + might make it stand out more. It's somewhat generic\u2014many articles use similar + phrasing. Adding an element that hints at specific insights or a fresh perspective + could increase intrigue.\\n\\nOverall, the title effectively conveys the subject + and relevance but could be slightly improved with more compelling language to + boost interest.\"},{\"role\":\"user\",\"content\":\"Analyze the tool result. + If requirements are met, provide the Final Answer. Otherwise, call the next + tool. Deliver only the answer without meta-commentary.\"}],\"model\":\"gpt-4o\",\"response_format\":{\"type\":\"json_schema\",\"json_schema\":{\"schema\":{\"properties\":{\"score\":{\"title\":\"Score\",\"type\":\"integer\"}},\"required\":[\"score\"],\"title\":\"ScoreOutput\",\"type\":\"object\",\"additionalProperties\":false},\"name\":\"ScoreOutput\",\"strict\":true}},\"stream\":false,\"tool_choice\":\"auto\",\"tools\":[{\"type\":\"function\",\"function\":{\"name\":\"delegate_work_to_coworker\",\"description\":\"Delegate + a specific task to one of the following coworkers: Scorer\\nThe input to this + tool should be the coworker, the task you want them to do, and ALL necessary + context to execute the task, they know nothing about the task, so share absolutely + everything you know, don't reference things but instead explain them.\",\"strict\":true,\"parameters\":{\"properties\":{\"task\":{\"description\":\"The + task to delegate\",\"title\":\"Task\",\"type\":\"string\"},\"context\":{\"description\":\"The + context for the task\",\"title\":\"Context\",\"type\":\"string\"},\"coworker\":{\"description\":\"The + role/name of the coworker to delegate to\",\"title\":\"Coworker\",\"type\":\"string\"}},\"required\":[\"task\",\"context\",\"coworker\"],\"type\":\"object\",\"additionalProperties\":false}}},{\"type\":\"function\",\"function\":{\"name\":\"ask_question_to_coworker\",\"description\":\"Ask + a specific question to one of the following coworkers: Scorer\\nThe input to + this tool should be the coworker, the question you have for them, and ALL necessary + context to ask the question properly, they know nothing about the question, + so share absolutely everything you know, don't reference things but instead + explain them.\",\"strict\":true,\"parameters\":{\"properties\":{\"question\":{\"description\":\"The + question to ask\",\"title\":\"Question\",\"type\":\"string\"},\"context\":{\"description\":\"The + context for the question\",\"title\":\"Context\",\"type\":\"string\"},\"coworker\":{\"description\":\"The + role/name of the coworker to ask\",\"title\":\"Coworker\",\"type\":\"string\"}},\"required\":[\"question\",\"context\",\"coworker\"],\"type\":\"object\",\"additionalProperties\":false}}}]}" + headers: + User-Agent: + - X-USER-AGENT-XXX + accept: + - application/json + accept-encoding: + - ACCEPT-ENCODING-XXX + authorization: + - AUTHORIZATION-XXX + connection: + - keep-alive + content-length: + - '5297' + content-type: + - application/json + cookie: + - COOKIE-XXX + host: + - api.openai.com + x-stainless-arch: + - X-STAINLESS-ARCH-XXX + x-stainless-async: + - 'false' + x-stainless-helper-method: + - beta.chat.completions.parse + x-stainless-lang: + - python + x-stainless-os: + - X-STAINLESS-OS-XXX + x-stainless-package-version: + - 1.83.0 + x-stainless-read-timeout: + - X-STAINLESS-READ-TIMEOUT-XXX + x-stainless-retry-count: + - '0' + x-stainless-runtime: + - CPython + x-stainless-runtime-version: + - 3.13.12 + method: POST + uri: https://api.openai.com/v1/chat/completions + response: + body: + string: "{\n \"id\": \"chatcmpl-DDGA5qDbleuzKoN7uVs5MFOC6X5DG\",\n \"object\": + \"chat.completion\",\n \"created\": 1772052761,\n \"model\": \"gpt-4o-2024-08-06\",\n + \ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": + \"assistant\",\n \"content\": \"{\\\"score\\\":4}\",\n \"refusal\": + null,\n \"annotations\": []\n },\n \"logprobs\": null,\n + \ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": + 956,\n \"completion_tokens\": 10,\n \"total_tokens\": 966,\n \"prompt_tokens_details\": + {\n \"cached_tokens\": 0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\": + {\n \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\": + 0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\": + \"default\",\n \"system_fingerprint\": \"fp_64dfa806c7\"\n}\n" + headers: + CF-RAY: + - CF-RAY-XXX + Connection: + - keep-alive + Content-Type: + - application/json + Date: + - Wed, 25 Feb 2026 20:52:42 GMT + Server: + - cloudflare + Strict-Transport-Security: + - STS-XXX + Transfer-Encoding: + - chunked + X-Content-Type-Options: + - X-CONTENT-TYPE-XXX + access-control-expose-headers: + - ACCESS-CONTROL-XXX + alt-svc: + - h3=":443"; ma=86400 + cf-cache-status: + - DYNAMIC + openai-organization: + - OPENAI-ORG-XXX + openai-processing-ms: + - '508' openai-project: - OPENAI-PROJECT-XXX openai-version: - '2020-10-01' - x-envoy-upstream-service-time: - - '503' x-openai-proxy-wasm: - v0.1 x-ratelimit-limit-requests: diff --git a/lib/crewai/tests/cassettes/test_output_pydantic_sequential.yaml b/lib/crewai/tests/cassettes/test_output_pydantic_sequential.yaml index c8e210ed2..c1a86e1f0 100644 --- a/lib/crewai/tests/cassettes/test_output_pydantic_sequential.yaml +++ b/lib/crewai/tests/cassettes/test_output_pydantic_sequential.yaml @@ -1,98 +1,120 @@ interactions: - request: - body: '{"messages":[{"role":"system","content":"You are Scorer. You''re an expert scorer, specialized in scoring titles.\nYour personal goal is: Score the title\nTo give my best complete final answer to the task respond using the exact following format:\n\nThought: I now can give a great answer\nFinal Answer: Your final answer must be the great and the most complete as possible, it must be outcome described.\n\nI MUST use these formats, my job depends on it!"},{"role":"user","content":"\nCurrent Task: Give me an integer score between 1-5 for the following title: ''The impact of AI in the future of work''\n\nThis is the expected criteria for your final answer: The score of the title.\nyou MUST return the actual complete content as the final answer, not a summary.\nEnsure your final answer strictly adheres to the following OpenAPI schema: {\n \"properties\": {\n \"score\": {\n \"title\": \"Score\",\n \"type\": \"integer\"\n }\n },\n \"required\": [\n \"score\"\n ],\n \"title\": - \"ScoreOutput\",\n \"type\": \"object\",\n \"additionalProperties\": false\n}\n\nDo not include the OpenAPI schema in the final output. Ensure the final output does not include any code block markers like ```json or ```python.\n\nBegin! This is VERY important to you, use the tools available and give your best Final Answer, your job depends on it!\n\nThought:"}],"model":"gpt-4.1-mini"}' + body: '{"messages":[{"role":"system","content":"You are Scorer. You''re an expert + scorer, specialized in scoring titles.\nYour personal goal is: Score the title"},{"role":"user","content":"\nCurrent + Task: Give me an integer score between 1-5 for the following title: ''The impact + of AI in the future of work''\n\nThis is the expected criteria for your final + answer: The score of the title.\nyou MUST return the actual complete content + as the final answer, not a summary.\nFormat your final answer according to the + following OpenAPI schema: {\n \"properties\": {\n \"score\": {\n \"title\": + \"Score\",\n \"type\": \"integer\"\n }\n },\n \"required\": [\n \"score\"\n ],\n \"title\": + \"ScoreOutput\",\n \"type\": \"object\",\n \"additionalProperties\": false\n}\n\nIMPORTANT: + Preserve the original content exactly as-is. Do NOT rewrite, paraphrase, or + modify the meaning of the content. Only structure it to match the schema format.\n\nDo + not include the OpenAPI schema in the final output. Ensure the final output + does not include any code block markers like ```json or ```python.\n\nProvide + your complete response:"}],"model":"gpt-4.1-mini","response_format":{"type":"json_schema","json_schema":{"schema":{"properties":{"score":{"title":"Score","type":"integer"}},"required":["score"],"title":"ScoreOutput","type":"object","additionalProperties":false},"name":"ScoreOutput","strict":true}},"stream":false}' headers: + User-Agent: + - X-USER-AGENT-XXX accept: - application/json accept-encoding: - - gzip, deflate, zstd + - ACCEPT-ENCODING-XXX + authorization: + - AUTHORIZATION-XXX connection: - keep-alive content-length: - - '1394' + - '1421' content-type: - application/json host: - api.openai.com - user-agent: - - OpenAI/Python 1.109.1 x-stainless-arch: - - arm64 + - X-STAINLESS-ARCH-XXX x-stainless-async: - 'false' + x-stainless-helper-method: + - beta.chat.completions.parse x-stainless-lang: - python x-stainless-os: - - MacOS + - X-STAINLESS-OS-XXX x-stainless-package-version: - - 1.109.1 + - 1.83.0 x-stainless-read-timeout: - - '600' + - X-STAINLESS-READ-TIMEOUT-XXX x-stainless-retry-count: - '0' x-stainless-runtime: - CPython x-stainless-runtime-version: - - 3.12.9 + - 3.13.12 method: POST uri: https://api.openai.com/v1/chat/completions response: body: - string: "{\n \"id\": \"chatcmpl-CYg0ICsr8nVjoOoVFpnOLUh71LgfJ\",\n \"object\": \"chat.completion\",\n \"created\": 1762380650,\n \"model\": \"gpt-4.1-mini-2025-04-14\",\n \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"Thought: I now can give a great answer\\nFinal Answer: {\\n \\\"score\\\": 4\\n}\",\n \"refusal\": null,\n \"annotations\": []\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 294,\n \"completion_tokens\": 22,\n \"total_tokens\": 316,\n \"prompt_tokens_details\": {\n \"cached_tokens\": 0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\": {\n \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\": 0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\": \"default\",\n \"system_fingerprint\": \"fp_4c2851f862\"\ - \n}\n" + string: "{\n \"id\": \"chatcmpl-DDDxMk9AEzSz8xZnza3XoSeijSI5R\",\n \"object\": + \"chat.completion\",\n \"created\": 1772044284,\n \"model\": \"gpt-4.1-mini-2025-04-14\",\n + \ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": + \"assistant\",\n \"content\": \"{\\\"score\\\":4}\",\n \"refusal\": + null,\n \"annotations\": []\n },\n \"logprobs\": null,\n + \ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": + 276,\n \"completion_tokens\": 5,\n \"total_tokens\": 281,\n \"prompt_tokens_details\": + {\n \"cached_tokens\": 0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\": + {\n \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\": + 0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\": + \"default\",\n \"system_fingerprint\": \"fp_a391f2cee0\"\n}\n" headers: CF-RAY: - - REDACTED-RAY + - CF-RAY-XXX Connection: - keep-alive Content-Type: - application/json Date: - - Wed, 05 Nov 2025 22:10:50 GMT + - Wed, 25 Feb 2026 18:31:25 GMT Server: - cloudflare - Set-Cookie: - - __cf_bm=REDACTED; path=/; expires=Wed, 05-Nov-25 22:40:50 GMT; domain=.api.openai.com; HttpOnly; Secure; SameSite=None - - _cfuvid=REDACTED; path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None Strict-Transport-Security: - - max-age=31536000; includeSubDomains; preload + - STS-XXX Transfer-Encoding: - chunked X-Content-Type-Options: - - nosniff + - X-CONTENT-TYPE-XXX access-control-expose-headers: - - X-Request-ID + - ACCESS-CONTROL-XXX alt-svc: - h3=":443"; ma=86400 cf-cache-status: - DYNAMIC openai-organization: - - user-hortuttj2f3qtmxyik2zxf4q + - OPENAI-ORG-XXX openai-processing-ms: - - '482' + - '385' openai-project: - - proj_fL4UBWR1CMpAAdgzaSKqsVvA + - OPENAI-PROJECT-XXX openai-version: - '2020-10-01' - x-envoy-upstream-service-time: - - '495' + set-cookie: + - SET-COOKIE-XXX x-openai-proxy-wasm: - v0.1 x-ratelimit-limit-requests: - - '500' + - X-RATELIMIT-LIMIT-REQUESTS-XXX x-ratelimit-limit-tokens: - - '200000' + - X-RATELIMIT-LIMIT-TOKENS-XXX x-ratelimit-remaining-requests: - - '499' + - X-RATELIMIT-REMAINING-REQUESTS-XXX x-ratelimit-remaining-tokens: - - '199687' + - X-RATELIMIT-REMAINING-TOKENS-XXX x-ratelimit-reset-requests: - - 120ms + - X-RATELIMIT-RESET-REQUESTS-XXX x-ratelimit-reset-tokens: - - 93ms + - X-RATELIMIT-RESET-TOKENS-XXX x-request-id: - - req_REDACTED + - X-REQUEST-ID-XXX status: code: 200 message: OK diff --git a/lib/crewai/tests/cassettes/test_output_pydantic_to_another_task.yaml b/lib/crewai/tests/cassettes/test_output_pydantic_to_another_task.yaml index 5eec1ed00..4fd91fc44 100644 --- a/lib/crewai/tests/cassettes/test_output_pydantic_to_another_task.yaml +++ b/lib/crewai/tests/cassettes/test_output_pydantic_to_another_task.yaml @@ -1,192 +1,254 @@ interactions: - request: - body: '{"messages":[{"role":"system","content":"You are Scorer. You''re an expert scorer, specialized in scoring titles.\nYour personal goal is: Score the title\nTo give my best complete final answer to the task respond using the exact following format:\n\nThought: I now can give a great answer\nFinal Answer: Your final answer must be the great and the most complete as possible, it must be outcome described.\n\nI MUST use these formats, my job depends on it!"},{"role":"user","content":"\nCurrent Task: Give me an integer score between 1-5 for the following title: ''The impact of AI in the future of work''\n\nThis is the expected criteria for your final answer: The score of the title.\nyou MUST return the actual complete content as the final answer, not a summary.\nEnsure your final answer strictly adheres to the following OpenAPI schema: {\n \"properties\": {\n \"score\": {\n \"title\": \"Score\",\n \"type\": \"integer\"\n }\n },\n \"required\": [\n \"score\"\n ],\n \"title\": - \"ScoreOutput\",\n \"type\": \"object\",\n \"additionalProperties\": false\n}\n\nDo not include the OpenAPI schema in the final output. Ensure the final output does not include any code block markers like ```json or ```python.\n\nBegin! This is VERY important to you, use the tools available and give your best Final Answer, your job depends on it!\n\nThought:"}],"model":"gpt-4o"}' + body: '{"messages":[{"role":"system","content":"You are Scorer. You''re an expert + scorer, specialized in scoring titles.\nYour personal goal is: Score the title"},{"role":"user","content":"\nCurrent + Task: Give me an integer score between 1-5 for the following title: ''The impact + of AI in the future of work''\n\nThis is the expected criteria for your final + answer: The score of the title.\nyou MUST return the actual complete content + as the final answer, not a summary.\nFormat your final answer according to the + following OpenAPI schema: {\n \"properties\": {\n \"score\": {\n \"title\": + \"Score\",\n \"type\": \"integer\"\n }\n },\n \"required\": [\n \"score\"\n ],\n \"title\": + \"ScoreOutput\",\n \"type\": \"object\",\n \"additionalProperties\": false\n}\n\nIMPORTANT: + Preserve the original content exactly as-is. Do NOT rewrite, paraphrase, or + modify the meaning of the content. Only structure it to match the schema format.\n\nDo + not include the OpenAPI schema in the final output. Ensure the final output + does not include any code block markers like ```json or ```python.\n\nProvide + your complete response:"}],"model":"gpt-4o","response_format":{"type":"json_schema","json_schema":{"schema":{"properties":{"score":{"title":"Score","type":"integer"}},"required":["score"],"title":"ScoreOutput","type":"object","additionalProperties":false},"name":"ScoreOutput","strict":true}},"stream":false}' headers: + User-Agent: + - X-USER-AGENT-XXX accept: - application/json accept-encoding: - - gzip, deflate, zstd + - ACCEPT-ENCODING-XXX + authorization: + - AUTHORIZATION-XXX connection: - keep-alive content-length: - - '1388' + - '1415' content-type: - application/json host: - api.openai.com - user-agent: - - OpenAI/Python 1.109.1 x-stainless-arch: - - arm64 + - X-STAINLESS-ARCH-XXX x-stainless-async: - 'false' + x-stainless-helper-method: + - beta.chat.completions.parse x-stainless-lang: - python x-stainless-os: - - MacOS + - X-STAINLESS-OS-XXX x-stainless-package-version: - - 1.109.1 + - 1.83.0 x-stainless-read-timeout: - - '600' + - X-STAINLESS-READ-TIMEOUT-XXX x-stainless-retry-count: - '0' x-stainless-runtime: - CPython x-stainless-runtime-version: - - 3.12.9 + - 3.13.12 method: POST uri: https://api.openai.com/v1/chat/completions response: body: - string: "{\n \"id\": \"chatcmpl-CYg0Jd7eOJXIC6Yc1xB0F6Ve3KK1M\",\n \"object\": \"chat.completion\",\n \"created\": 1762380651,\n \"model\": \"gpt-4o-2024-08-06\",\n \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"I now can give a great answer\\nFinal Answer: {\\\"score\\\": 4}\",\n \"refusal\": null,\n \"annotations\": []\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 294,\n \"completion_tokens\": 17,\n \"total_tokens\": 311,\n \"prompt_tokens_details\": {\n \"cached_tokens\": 0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\": {\n \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\": 0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\": \"default\",\n \"system_fingerprint\": \"fp_65564d8ba5\"\n}\n" + string: "{\n \"id\": \"chatcmpl-DDDxNULmWtIUe1SAGHcArDXYSifV8\",\n \"object\": + \"chat.completion\",\n \"created\": 1772044285,\n \"model\": \"gpt-4o-2024-08-06\",\n + \ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": + \"assistant\",\n \"content\": \"{\\\"score\\\":4}\",\n \"refusal\": + null,\n \"annotations\": []\n },\n \"logprobs\": null,\n + \ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": + 276,\n \"completion_tokens\": 5,\n \"total_tokens\": 281,\n \"prompt_tokens_details\": + {\n \"cached_tokens\": 0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\": + {\n \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\": + 0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\": + \"default\",\n \"system_fingerprint\": \"fp_9e0d253e63\"\n}\n" headers: CF-RAY: - - REDACTED-RAY + - CF-RAY-XXX Connection: - keep-alive Content-Type: - application/json Date: - - Wed, 05 Nov 2025 22:10:52 GMT + - Wed, 25 Feb 2026 18:31:26 GMT Server: - cloudflare - Set-Cookie: - - __cf_bm=REDACTED; path=/; expires=Wed, 05-Nov-25 22:40:52 GMT; domain=.api.openai.com; HttpOnly; Secure; SameSite=None - - _cfuvid=REDACTED; path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None Strict-Transport-Security: - - max-age=31536000; includeSubDomains; preload + - STS-XXX Transfer-Encoding: - chunked X-Content-Type-Options: - - nosniff + - X-CONTENT-TYPE-XXX access-control-expose-headers: - - X-Request-ID + - ACCESS-CONTROL-XXX alt-svc: - h3=":443"; ma=86400 cf-cache-status: - DYNAMIC openai-organization: - - user-hortuttj2f3qtmxyik2zxf4q + - OPENAI-ORG-XXX openai-processing-ms: - - '1337' + - '364' openai-project: - - proj_fL4UBWR1CMpAAdgzaSKqsVvA + - OPENAI-PROJECT-XXX openai-version: - '2020-10-01' - x-envoy-upstream-service-time: - - '1487' + set-cookie: + - SET-COOKIE-XXX x-openai-proxy-wasm: - v0.1 x-ratelimit-limit-requests: - - '500' + - X-RATELIMIT-LIMIT-REQUESTS-XXX x-ratelimit-limit-tokens: - - '30000' + - X-RATELIMIT-LIMIT-TOKENS-XXX x-ratelimit-remaining-requests: - - '499' + - X-RATELIMIT-REMAINING-REQUESTS-XXX x-ratelimit-remaining-tokens: - - '29687' + - X-RATELIMIT-REMAINING-TOKENS-XXX x-ratelimit-reset-requests: - - 120ms + - X-RATELIMIT-RESET-REQUESTS-XXX x-ratelimit-reset-tokens: - - 626ms + - X-RATELIMIT-RESET-TOKENS-XXX x-request-id: - - req_REDACTED + - X-REQUEST-ID-XXX status: code: 200 message: OK - request: - body: '{"messages":[{"role":"system","content":"You are Scorer. You''re an expert scorer, specialized in scoring titles.\nYour personal goal is: Score the title\nTo give my best complete final answer to the task respond using the exact following format:\n\nThought: I now can give a great answer\nFinal Answer: Your final answer must be the great and the most complete as possible, it must be outcome described.\n\nI MUST use these formats, my job depends on it!"},{"role":"user","content":"\nCurrent Task: Given the score the title ''The impact of AI in the future of work'' got, give me an integer score between 1-5 for the following title: ''Return of the Jedi'', you MUST give it a score, use your best judgment\n\nThis is the expected criteria for your final answer: The score of the title.\nyou MUST return the actual complete content as the final answer, not a summary.\nEnsure your final answer strictly adheres to the following OpenAPI schema: {\n \"properties\": {\n \"score\": {\n \"title\": - \"Score\",\n \"type\": \"integer\"\n }\n },\n \"required\": [\n \"score\"\n ],\n \"title\": \"ScoreOutput\",\n \"type\": \"object\",\n \"additionalProperties\": false\n}\n\nDo not include the OpenAPI schema in the final output. Ensure the final output does not include any code block markers like ```json or ```python.\n\nThis is the context you''re working with:\n{\"score\": 4}\n\nBegin! This is VERY important to you, use the tools available and give your best Final Answer, your job depends on it!\n\nThought:"}],"model":"gpt-4o"}' + body: '{"messages":[{"role":"system","content":"You are Scorer. You''re an expert + scorer, specialized in scoring titles.\nYour personal goal is: Score the title"},{"role":"user","content":"\nCurrent + Task: Give me an integer score between 1-5 for the following title: ''The impact + of AI in the future of work''\n\nThis is the expected criteria for your final + answer: The score of the title.\nyou MUST return the actual complete content + as the final answer, not a summary.\nFormat your final answer according to the + following OpenAPI schema: {\n \"properties\": {\n \"score\": {\n \"title\": + \"Score\",\n \"type\": \"integer\"\n }\n },\n \"required\": [\n \"score\"\n ],\n \"title\": + \"ScoreOutput\",\n \"type\": \"object\",\n \"additionalProperties\": false\n}\n\nIMPORTANT: + Preserve the original content exactly as-is. Do NOT rewrite, paraphrase, or + modify the meaning of the content. Only structure it to match the schema format.\n\nDo + not include the OpenAPI schema in the final output. Ensure the final output + does not include any code block markers like ```json or ```python.\n\nProvide + your complete response:"},{"role":"assistant","content":"{\"score\":4}"},{"role":"system","content":"You + are Scorer. You''re an expert scorer, specialized in scoring titles.\nYour personal + goal is: Score the title"},{"role":"user","content":"\nCurrent Task: Given the + score the title ''The impact of AI in the future of work'' got, give me an integer + score between 1-5 for the following title: ''Return of the Jedi'', you MUST + give it a score, use your best judgment\n\nThis is the expected criteria for + your final answer: The score of the title.\nyou MUST return the actual complete + content as the final answer, not a summary.\nFormat your final answer according + to the following OpenAPI schema: {\n \"properties\": {\n \"score\": {\n \"title\": + \"Score\",\n \"type\": \"integer\"\n }\n },\n \"required\": [\n \"score\"\n ],\n \"title\": + \"ScoreOutput\",\n \"type\": \"object\",\n \"additionalProperties\": false\n}\n\nIMPORTANT: + Preserve the original content exactly as-is. Do NOT rewrite, paraphrase, or + modify the meaning of the content. Only structure it to match the schema format.\n\nDo + not include the OpenAPI schema in the final output. Ensure the final output + does not include any code block markers like ```json or ```python.\n\nThis is + the context you''re working with:\n{\"score\":4}\n\nProvide your complete response:"}],"model":"gpt-4o","response_format":{"type":"json_schema","json_schema":{"schema":{"properties":{"score":{"title":"Score","type":"integer"}},"required":["score"],"title":"ScoreOutput","type":"object","additionalProperties":false},"name":"ScoreOutput","strict":true}},"stream":false}' headers: + User-Agent: + - X-USER-AGENT-XXX accept: - application/json accept-encoding: - - gzip, deflate, zstd + - ACCEPT-ENCODING-XXX + authorization: + - AUTHORIZATION-XXX connection: - keep-alive content-length: - - '1550' + - '2743' content-type: - application/json cookie: - - __cf_bm=REDACTED; _cfuvid=REDACTED + - COOKIE-XXX host: - api.openai.com - user-agent: - - OpenAI/Python 1.109.1 x-stainless-arch: - - arm64 + - X-STAINLESS-ARCH-XXX x-stainless-async: - 'false' + x-stainless-helper-method: + - beta.chat.completions.parse x-stainless-lang: - python x-stainless-os: - - MacOS + - X-STAINLESS-OS-XXX x-stainless-package-version: - - 1.109.1 + - 1.83.0 x-stainless-read-timeout: - - '600' + - X-STAINLESS-READ-TIMEOUT-XXX x-stainless-retry-count: - '0' x-stainless-runtime: - CPython x-stainless-runtime-version: - - 3.12.9 + - 3.13.12 method: POST uri: https://api.openai.com/v1/chat/completions response: body: - string: "{\n \"id\": \"chatcmpl-CYg0KidOU2tphhqhW69ygSBSubHBQ\",\n \"object\": \"chat.completion\",\n \"created\": 1762380652,\n \"model\": \"gpt-4o-2024-08-06\",\n \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"I now can give a great answer\\nFinal Answer: {\\\"score\\\": 5}\",\n \"refusal\": null,\n \"annotations\": []\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 333,\n \"completion_tokens\": 17,\n \"total_tokens\": 350,\n \"prompt_tokens_details\": {\n \"cached_tokens\": 0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\": {\n \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\": 0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\": \"default\",\n \"system_fingerprint\": \"fp_a788c5aef0\"\n}\n" + string: "{\n \"id\": \"chatcmpl-DDDxOIf7hV4pRmOxmlsA7bO8L2z5w\",\n \"object\": + \"chat.completion\",\n \"created\": 1772044286,\n \"model\": \"gpt-4o-2024-08-06\",\n + \ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": + \"assistant\",\n \"content\": \"{\\\"score\\\":5}\",\n \"refusal\": + null,\n \"annotations\": []\n },\n \"logprobs\": null,\n + \ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": + 564,\n \"completion_tokens\": 5,\n \"total_tokens\": 569,\n \"prompt_tokens_details\": + {\n \"cached_tokens\": 0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\": + {\n \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\": + 0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\": + \"default\",\n \"system_fingerprint\": \"fp_9e0d253e63\"\n}\n" headers: CF-RAY: - - REDACTED-RAY + - CF-RAY-XXX Connection: - keep-alive Content-Type: - application/json Date: - - Wed, 05 Nov 2025 22:10:53 GMT + - Wed, 25 Feb 2026 18:31:27 GMT Server: - cloudflare Strict-Transport-Security: - - max-age=31536000; includeSubDomains; preload + - STS-XXX Transfer-Encoding: - chunked X-Content-Type-Options: - - nosniff + - X-CONTENT-TYPE-XXX access-control-expose-headers: - - X-Request-ID + - ACCESS-CONTROL-XXX alt-svc: - h3=":443"; ma=86400 cf-cache-status: - DYNAMIC openai-organization: - - user-hortuttj2f3qtmxyik2zxf4q + - OPENAI-ORG-XXX openai-processing-ms: - - '1009' + - '393' openai-project: - - proj_fL4UBWR1CMpAAdgzaSKqsVvA + - OPENAI-PROJECT-XXX openai-version: - '2020-10-01' - x-envoy-upstream-service-time: - - '1106' x-openai-proxy-wasm: - v0.1 x-ratelimit-limit-requests: - - '500' + - X-RATELIMIT-LIMIT-REQUESTS-XXX x-ratelimit-limit-tokens: - - '30000' + - X-RATELIMIT-LIMIT-TOKENS-XXX x-ratelimit-remaining-requests: - - '499' + - X-RATELIMIT-REMAINING-REQUESTS-XXX x-ratelimit-remaining-tokens: - - '29647' + - X-RATELIMIT-REMAINING-TOKENS-XXX x-ratelimit-reset-requests: - - 120ms + - X-RATELIMIT-RESET-REQUESTS-XXX x-ratelimit-reset-tokens: - - 706ms + - X-RATELIMIT-RESET-TOKENS-XXX x-request-id: - - req_REDACTED + - X-REQUEST-ID-XXX status: code: 200 message: OK diff --git a/lib/crewai/tests/cassettes/test_save_task_json_output.yaml b/lib/crewai/tests/cassettes/test_save_task_json_output.yaml index 2692841e2..d7449fa08 100644 --- a/lib/crewai/tests/cassettes/test_save_task_json_output.yaml +++ b/lib/crewai/tests/cassettes/test_save_task_json_output.yaml @@ -1,11 +1,14 @@ interactions: - request: - body: '{"trace_id": "00000000-0000-0000-0000-000000000000", "execution_type": "crew", "user_identifier": null, "execution_context": {"crew_fingerprint": null, "crew_name": "crew", "flow_name": null, "crewai_version": "1.3.0", "privacy_level": "standard"}, "execution_metadata": {"expected_duration_estimate": 300, "agent_count": 0, "task_count": 0, "flow_method_count": 0, "execution_started_at": "2025-11-05T22:10:38.307164+00:00"}, "ephemeral_trace_id": "00000000-0000-0000-0000-000000000000"}' + body: '{"trace_id": "00000000-0000-0000-0000-000000000000", "execution_type": + "crew", "user_identifier": null, "execution_context": {"crew_fingerprint": null, + "crew_name": "crew", "flow_name": null, "crewai_version": "1.3.0", "privacy_level": + "standard"}, "execution_metadata": {"expected_duration_estimate": 300, "agent_count": + 0, "task_count": 0, "flow_method_count": 0, "execution_started_at": "2025-11-05T22:10:38.307164+00:00"}, + "ephemeral_trace_id": "00000000-0000-0000-0000-000000000000"}' headers: Accept: - '*/*' - Accept-Encoding: - - gzip, deflate, zstd Connection: - keep-alive Content-Length: @@ -13,14 +16,18 @@ interactions: Content-Type: - application/json User-Agent: - - CrewAI-CLI/1.3.0 + - X-USER-AGENT-XXX X-Crewai-Version: - 1.3.0 + accept-encoding: + - ACCEPT-ENCODING-XXX method: POST uri: https://app.crewai.com/crewai_plus/api/v1/tracing/ephemeral/batches response: body: - string: '{"id": "00000000-0000-0000-0000-000000000000","ephemeral_trace_id": "00000000-0000-0000-0000-000000000000","execution_type":"crew","crew_name":"crew","flow_name":null,"status":"running","duration_ms":null,"crewai_version":"1.3.0","total_events":0,"execution_context":{"crew_fingerprint":null,"crew_name":"crew","flow_name":null,"crewai_version":"1.3.0","privacy_level":"standard"},"created_at":"2025-11-05T22:10:38.904Z","updated_at":"2025-11-05T22:10:38.904Z","access_code": "TRACE-0000000000","user_identifier":null}' + string: '{"id": "00000000-0000-0000-0000-000000000000","ephemeral_trace_id": + "00000000-0000-0000-0000-000000000000","execution_type":"crew","crew_name":"crew","flow_name":null,"status":"running","duration_ms":null,"crewai_version":"1.3.0","total_events":0,"execution_context":{"crew_fingerprint":null,"crew_name":"crew","flow_name":null,"crewai_version":"1.3.0","privacy_level":"standard"},"created_at":"2025-11-05T22:10:38.904Z","updated_at":"2025-11-05T22:10:38.904Z","access_code": + "TRACE-0000000000","user_identifier":null}' headers: Connection: - keep-alive @@ -33,46 +40,61 @@ interactions: cache-control: - no-store content-security-policy: - - 'default-src ''self'' *.app.crewai.com app.crewai.com; script-src ''self'' ''unsafe-inline'' *.app.crewai.com app.crewai.com https://cdn.jsdelivr.net/npm/apexcharts https://www.gstatic.com https://run.pstmn.io https://apis.google.com https://apis.google.com/js/api.js https://accounts.google.com https://accounts.google.com/gsi/client https://cdnjs.cloudflare.com/ajax/libs/normalize/8.0.1/normalize.min.css.map https://*.google.com https://docs.google.com https://slides.google.com https://js.hs-scripts.com https://js.sentry-cdn.com https://browser.sentry-cdn.com https://www.googletagmanager.com https://js-na1.hs-scripts.com https://js.hubspot.com http://js-na1.hs-scripts.com https://bat.bing.com https://cdn.amplitude.com https://cdn.segment.com https://d1d3n03t5zntha.cloudfront.net/ https://descriptusercontent.com https://edge.fullstory.com https://googleads.g.doubleclick.net https://js.hs-analytics.net https://js.hs-banner.com https://js.hsadspixel.net https://js.hscollectedforms.net - https://js.usemessages.com https://snap.licdn.com https://static.cloudflareinsights.com https://static.reo.dev https://www.google-analytics.com https://share.descript.com/; style-src ''self'' ''unsafe-inline'' *.app.crewai.com app.crewai.com https://cdn.jsdelivr.net/npm/apexcharts; img-src ''self'' data: *.app.crewai.com app.crewai.com https://zeus.tools.crewai.com https://dashboard.tools.crewai.com https://cdn.jsdelivr.net https://forms.hsforms.com https://track.hubspot.com https://px.ads.linkedin.com https://px4.ads.linkedin.com https://www.google.com https://www.google.com.br; font-src ''self'' data: *.app.crewai.com app.crewai.com; connect-src ''self'' *.app.crewai.com app.crewai.com https://zeus.tools.crewai.com https://connect.useparagon.com/ https://zeus.useparagon.com/* https://*.useparagon.com/* https://run.pstmn.io https://connect.tools.crewai.com/ https://*.sentry.io https://www.google-analytics.com https://edge.fullstory.com https://rs.fullstory.com https://api.hubspot.com - https://forms.hscollectedforms.net https://api.hubapi.com https://px.ads.linkedin.com https://px4.ads.linkedin.com https://google.com/pagead/form-data/16713662509 https://google.com/ccm/form-data/16713662509 https://www.google.com/ccm/collect https://worker-actionkit.tools.crewai.com https://api.reo.dev; frame-src ''self'' *.app.crewai.com app.crewai.com https://connect.useparagon.com/ https://zeus.tools.crewai.com https://zeus.useparagon.com/* https://connect.tools.crewai.com/ https://docs.google.com https://drive.google.com https://slides.google.com https://accounts.google.com https://*.google.com https://app.hubspot.com/ https://td.doubleclick.net https://www.googletagmanager.com/ https://www.youtube.com https://share.descript.com' + - CSP-FILTERED etag: - - W/"06db9ad73130a1da388846e83fc98135" + - ETAG-XXX expires: - '0' permissions-policy: - - camera=(), microphone=(self), geolocation=() + - PERMISSIONS-POLICY-XXX pragma: - no-cache referrer-policy: - - strict-origin-when-cross-origin + - REFERRER-POLICY-XXX strict-transport-security: - - max-age=63072000; includeSubDomains + - STS-XXX vary: - Accept x-content-type-options: - - nosniff + - X-CONTENT-TYPE-XXX x-frame-options: - - SAMEORIGIN + - X-FRAME-OPTIONS-XXX x-permitted-cross-domain-policies: - - none + - X-PERMITTED-XXX x-request-id: - - 34f34729-198e-482e-8c87-163a997bc3f4 + - X-REQUEST-ID-XXX x-runtime: - - '0.239932' + - X-RUNTIME-XXX x-xss-protection: - - 1; mode=block + - X-XSS-PROTECTION-XXX status: code: 201 message: Created - request: - body: '{"messages":[{"role":"system","content":"You are Scorer. You''re an expert scorer, specialized in scoring titles.\nYour personal goal is: Score the title\nTo give my best complete final answer to the task respond using the exact following format:\n\nThought: I now can give a great answer\nFinal Answer: Your final answer must be the great and the most complete as possible, it must be outcome described.\n\nI MUST use these formats, my job depends on it!"},{"role":"user","content":"\nCurrent Task: Give me an integer score between 1-5 for the following title: ''The impact of AI in the future of work''\n\nThis is the expected criteria for your final answer: The score of the title.\nyou MUST return the actual complete content as the final answer, not a summary.\nEnsure your final answer strictly adheres to the following OpenAPI schema: {\n \"properties\": {\n \"score\": {\n \"title\": \"Score\",\n \"type\": \"integer\"\n }\n },\n \"required\": [\n \"score\"\n ],\n \"title\": - \"ScoreOutput\",\n \"type\": \"object\",\n \"additionalProperties\": false\n}\n\nDo not include the OpenAPI schema in the final output. Ensure the final output does not include any code block markers like ```json or ```python.\n\nBegin! This is VERY important to you, use the tools available and give your best Final Answer, your job depends on it!\n\nThought:"}],"model":"gpt-4.1-mini"}' + body: '{"messages":[{"role":"system","content":"You are Scorer. You''re an expert + scorer, specialized in scoring titles.\nYour personal goal is: Score the title\nTo + give my best complete final answer to the task respond using the exact following + format:\n\nThought: I now can give a great answer\nFinal Answer: Your final + answer must be the great and the most complete as possible, it must be outcome + described.\n\nI MUST use these formats, my job depends on it!"},{"role":"user","content":"\nCurrent + Task: Give me an integer score between 1-5 for the following title: ''The impact + of AI in the future of work''\n\nThis is the expected criteria for your final + answer: The score of the title.\nyou MUST return the actual complete content + as the final answer, not a summary.\nEnsure your final answer strictly adheres + to the following OpenAPI schema: {\n \"properties\": {\n \"score\": {\n \"title\": + \"Score\",\n \"type\": \"integer\"\n }\n },\n \"required\": [\n \"score\"\n ],\n \"title\": + \"ScoreOutput\",\n \"type\": \"object\",\n \"additionalProperties\": false\n}\n\nDo + not include the OpenAPI schema in the final output. Ensure the final output + does not include any code block markers like ```json or ```python.\n\nBegin! + This is VERY important to you, use the tools available and give your best Final + Answer, your job depends on it!\n\nThought:"}],"model":"gpt-4.1-mini"}' headers: + User-Agent: + - X-USER-AGENT-XXX accept: - application/json accept-encoding: - - gzip, deflate, zstd + - ACCEPT-ENCODING-XXX connection: - keep-alive content-length: @@ -81,20 +103,18 @@ interactions: - application/json host: - api.openai.com - user-agent: - - OpenAI/Python 1.109.1 x-stainless-arch: - - arm64 + - X-STAINLESS-ARCH-XXX x-stainless-async: - 'false' x-stainless-lang: - python x-stainless-os: - - MacOS + - X-STAINLESS-OS-XXX x-stainless-package-version: - 1.109.1 x-stainless-read-timeout: - - '600' + - X-STAINLESS-READ-TIMEOUT-XXX x-stainless-retry-count: - '0' x-stainless-runtime: @@ -105,11 +125,21 @@ interactions: uri: https://api.openai.com/v1/chat/completions response: body: - string: "{\n \"id\": \"chatcmpl-CYg0656gofDPbkHnqVBtb4a5cX4I0\",\n \"object\": \"chat.completion\",\n \"created\": 1762380638,\n \"model\": \"gpt-4.1-mini-2025-04-14\",\n \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"Thought: I now can give a great answer\\nFinal Answer: {\\n \\\"score\\\": 4\\n}\",\n \"refusal\": null,\n \"annotations\": []\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 294,\n \"completion_tokens\": 22,\n \"total_tokens\": 316,\n \"prompt_tokens_details\": {\n \"cached_tokens\": 0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\": {\n \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\": 0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\": \"default\",\n \"system_fingerprint\": \"fp_4c2851f862\"\ - \n}\n" + string: "{\n \"id\": \"chatcmpl-CYg0656gofDPbkHnqVBtb4a5cX4I0\",\n \"object\": + \"chat.completion\",\n \"created\": 1762380638,\n \"model\": \"gpt-4.1-mini-2025-04-14\",\n + \ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": + \"assistant\",\n \"content\": \"Thought: I now can give a great answer\\nFinal + Answer: {\\n \\\"score\\\": 4\\n}\",\n \"refusal\": null,\n \"annotations\": + []\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n + \ }\n ],\n \"usage\": {\n \"prompt_tokens\": 294,\n \"completion_tokens\": + 22,\n \"total_tokens\": 316,\n \"prompt_tokens_details\": {\n \"cached_tokens\": + 0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\": + {\n \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\": + 0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\": + \"default\",\n \"system_fingerprint\": \"fp_4c2851f862\"\n}\n" headers: CF-RAY: - - REDACTED-RAY + - CF-RAY-XXX Connection: - keep-alive Content-Type: @@ -119,26 +149,25 @@ interactions: Server: - cloudflare Set-Cookie: - - __cf_bm=REDACTED; path=/; expires=Wed, 05-Nov-25 22:40:39 GMT; domain=.api.openai.com; HttpOnly; Secure; SameSite=None - - _cfuvid=REDACTED; path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None + - SET-COOKIE-XXX Strict-Transport-Security: - - max-age=31536000; includeSubDomains; preload + - STS-XXX Transfer-Encoding: - chunked X-Content-Type-Options: - - nosniff + - X-CONTENT-TYPE-XXX access-control-expose-headers: - - X-Request-ID + - ACCESS-CONTROL-XXX alt-svc: - h3=":443"; ma=86400 cf-cache-status: - DYNAMIC openai-organization: - - user-hortuttj2f3qtmxyik2zxf4q + - OPENAI-ORG-XXX openai-processing-ms: - '491' openai-project: - - proj_fL4UBWR1CMpAAdgzaSKqsVvA + - OPENAI-PROJECT-XXX openai-version: - '2020-10-01' x-envoy-upstream-service-time: @@ -146,19 +175,153 @@ interactions: x-openai-proxy-wasm: - v0.1 x-ratelimit-limit-requests: - - '500' + - X-RATELIMIT-LIMIT-REQUESTS-XXX x-ratelimit-limit-tokens: - - '200000' + - X-RATELIMIT-LIMIT-TOKENS-XXX x-ratelimit-remaining-requests: - - '499' + - X-RATELIMIT-REMAINING-REQUESTS-XXX x-ratelimit-remaining-tokens: - - '199687' + - X-RATELIMIT-REMAINING-TOKENS-XXX x-ratelimit-reset-requests: - - 120ms + - X-RATELIMIT-RESET-REQUESTS-XXX x-ratelimit-reset-tokens: - - 93ms + - X-RATELIMIT-RESET-TOKENS-XXX x-request-id: - - req_REDACTED + - X-REQUEST-ID-XXX + status: + code: 200 + message: OK +- request: + body: '{"messages":[{"role":"system","content":"You are Scorer. You''re an expert + scorer, specialized in scoring titles.\nYour personal goal is: Score the title"},{"role":"user","content":"\nCurrent + Task: Give me an integer score between 1-5 for the following title: ''The impact + of AI in the future of work''\n\nThis is the expected criteria for your final + answer: The score of the title.\nyou MUST return the actual complete content + as the final answer, not a summary.\nFormat your final answer according to the + following OpenAPI schema: {\n \"properties\": {\n \"score\": {\n \"title\": + \"Score\",\n \"type\": \"integer\"\n }\n },\n \"required\": [\n \"score\"\n ],\n \"title\": + \"ScoreOutput\",\n \"type\": \"object\",\n \"additionalProperties\": false\n}\n\nIMPORTANT: + Preserve the original content exactly as-is. Do NOT rewrite, paraphrase, or + modify the meaning of the content. Only structure it to match the schema format.\n\nDo + not include the OpenAPI schema in the final output. Ensure the final output + does not include any code block markers like ```json or ```python.\n\nProvide + your complete response:"},{"role":"system","content":"You are Scorer. You''re + an expert scorer, specialized in scoring titles.\nYour personal goal is: Score + the title"},{"role":"user","content":"\nCurrent Task: Give me an integer score + between 1-5 for the following title: ''The impact of AI in the future of work''\n\nThis + is the expected criteria for your final answer: The score of the title.\nyou + MUST return the actual complete content as the final answer, not a summary.\nFormat + your final answer according to the following OpenAPI schema: {\n \"properties\": + {\n \"score\": {\n \"title\": \"Score\",\n \"type\": \"integer\"\n }\n },\n \"required\": + [\n \"score\"\n ],\n \"title\": \"ScoreOutput\",\n \"type\": \"object\",\n \"additionalProperties\": + false\n}\n\nIMPORTANT: Preserve the original content exactly as-is. Do NOT rewrite, + paraphrase, or modify the meaning of the content. Only structure it to match + the schema format.\n\nDo not include the OpenAPI schema in the final output. + Ensure the final output does not include any code block markers like ```json + or ```python.\n\nProvide your complete response:"}],"model":"gpt-4.1-mini","response_format":{"type":"json_schema","json_schema":{"schema":{"properties":{"score":{"title":"Score","type":"integer"}},"required":["score"],"title":"ScoreOutput","type":"object","additionalProperties":false},"name":"ScoreOutput","strict":true}},"stream":false}' + headers: + User-Agent: + - X-USER-AGENT-XXX + accept: + - application/json + accept-encoding: + - ACCEPT-ENCODING-XXX + authorization: + - AUTHORIZATION-XXX + connection: + - keep-alive + content-length: + - '2541' + content-type: + - application/json + cookie: + - COOKIE-XXX + host: + - api.openai.com + x-stainless-arch: + - X-STAINLESS-ARCH-XXX + x-stainless-async: + - 'false' + x-stainless-helper-method: + - beta.chat.completions.parse + x-stainless-lang: + - python + x-stainless-os: + - X-STAINLESS-OS-XXX + x-stainless-package-version: + - 1.83.0 + x-stainless-read-timeout: + - X-STAINLESS-READ-TIMEOUT-XXX + x-stainless-retry-count: + - '0' + x-stainless-runtime: + - CPython + x-stainless-runtime-version: + - 3.13.12 + method: POST + uri: https://api.openai.com/v1/chat/completions + response: + body: + string: "{\n \"id\": \"chatcmpl-DDDzycCKiyLb7UfPI2tKGyQAw8LGi\",\n \"object\": + \"chat.completion\",\n \"created\": 1772044446,\n \"model\": \"gpt-4.1-mini-2025-04-14\",\n + \ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": + \"assistant\",\n \"content\": \"{\\\"score\\\":4}\",\n \"refusal\": + null,\n \"annotations\": []\n },\n \"logprobs\": null,\n + \ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": + 513,\n \"completion_tokens\": 5,\n \"total_tokens\": 518,\n \"prompt_tokens_details\": + {\n \"cached_tokens\": 0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\": + {\n \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\": + 0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\": + \"default\",\n \"system_fingerprint\": \"fp_a391f2cee0\"\n}\n" + headers: + CF-RAY: + - CF-RAY-XXX + Connection: + - keep-alive + Content-Type: + - application/json + Date: + - Wed, 25 Feb 2026 18:34:07 GMT + Server: + - cloudflare + Strict-Transport-Security: + - STS-XXX + Transfer-Encoding: + - chunked + X-Content-Type-Options: + - X-CONTENT-TYPE-XXX + access-control-expose-headers: + - ACCESS-CONTROL-XXX + alt-svc: + - h3=":443"; ma=86400 + cf-cache-status: + - DYNAMIC + openai-organization: + - OPENAI-ORG-XXX + openai-processing-ms: + - '497' + openai-project: + - OPENAI-PROJECT-XXX + openai-version: + - '2020-10-01' + set-cookie: + - SET-COOKIE-XXX + x-openai-proxy-wasm: + - v0.1 + x-ratelimit-limit-requests: + - X-RATELIMIT-LIMIT-REQUESTS-XXX + x-ratelimit-limit-tokens: + - X-RATELIMIT-LIMIT-TOKENS-XXX + x-ratelimit-remaining-requests: + - X-RATELIMIT-REMAINING-REQUESTS-XXX + x-ratelimit-remaining-tokens: + - X-RATELIMIT-REMAINING-TOKENS-XXX + x-ratelimit-reset-requests: + - X-RATELIMIT-RESET-REQUESTS-XXX + x-ratelimit-reset-tokens: + - X-RATELIMIT-RESET-TOKENS-XXX + x-request-id: + - X-REQUEST-ID-XXX status: code: 200 message: OK diff --git a/lib/crewai/tests/cassettes/test_save_task_output.yaml b/lib/crewai/tests/cassettes/test_save_task_output.yaml index ddd2caa05..ddf434235 100644 --- a/lib/crewai/tests/cassettes/test_save_task_output.yaml +++ b/lib/crewai/tests/cassettes/test_save_task_output.yaml @@ -1,106 +1,110 @@ interactions: - request: - body: '{"messages": [{"role": "system", "content": "You are Scorer. You''re an - expert scorer, specialized in scoring titles.\nYour personal goal is: Score - the title\nTo give my best complete final answer to the task use the exact following - format:\n\nThought: I now can give a great answer\nFinal Answer: Your final - answer must be the great and the most complete as possible, it must be outcome - described.\n\nI MUST use these formats, my job depends on it!"}, {"role": "user", - "content": "\nCurrent Task: Give me an integer score between 1-5 for the following - title: ''The impact of AI in the future of work''\n\nThis is the expect criteria - for your final answer: The score of the title.\nyou MUST return the actual complete - content as the final answer, not a summary.\n\nBegin! This is VERY important - to you, use the tools available and give your best Final Answer, your job depends - on it!\n\nThought:"}], "model": "gpt-4o"}' + body: '{"messages":[{"role":"system","content":"You are Scorer. You''re an expert + scorer, specialized in scoring titles.\nYour personal goal is: Score the title"},{"role":"user","content":"\nCurrent + Task: Give me an integer score between 1-5 for the following title: ''The impact + of AI in the future of work''\n\nThis is the expected criteria for your final + answer: The score of the title.\nyou MUST return the actual complete content + as the final answer, not a summary.\n\nProvide your complete response:"}],"model":"gpt-4.1-mini"}' headers: + User-Agent: + - X-USER-AGENT-XXX accept: - application/json accept-encoding: - - gzip, deflate + - ACCEPT-ENCODING-XXX + authorization: + - AUTHORIZATION-XXX connection: - keep-alive content-length: - - '915' + - '522' content-type: - application/json - cookie: - - __cf_bm=9.8sBYBkvBR8R1K_bVF7xgU..80XKlEIg3N2OBbTSCU-1727214102-1.0.1.1-.qiTLXbPamYUMSuyNsOEB9jhGu.jOifujOrx9E2JZvStbIZ9RTIiE44xKKNfLPxQkOi6qAT3h6htK8lPDGV_5g; - _cfuvid=lbRdAddVWV6W3f5Dm9SaOPWDUOxqtZBSPr_fTW26nEA-1727213194587-0.0.1.1-604800000 host: - api.openai.com - user-agent: - - OpenAI/Python 1.47.0 x-stainless-arch: - - arm64 + - X-STAINLESS-ARCH-XXX x-stainless-async: - 'false' x-stainless-lang: - python x-stainless-os: - - MacOS + - X-STAINLESS-OS-XXX x-stainless-package-version: - - 1.47.0 - x-stainless-raw-response: - - 'true' + - 1.83.0 + x-stainless-read-timeout: + - X-STAINLESS-READ-TIMEOUT-XXX + x-stainless-retry-count: + - '0' x-stainless-runtime: - CPython x-stainless-runtime-version: - - 3.11.7 + - 3.13.12 method: POST uri: https://api.openai.com/v1/chat/completions response: body: - string: "{\n \"id\": \"chatcmpl-AB7gKOb785BSjHMwGUL7QpXJHDfmJ\",\n \"object\"\ - : \"chat.completion\",\n \"created\": 1727214500,\n \"model\": \"gpt-4o-2024-05-13\"\ - ,\n \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \ - \ \"role\": \"assistant\",\n \"content\": \"Thought: I now can\ - \ give a great answer\\nFinal Answer: 4\",\n \"refusal\": null\n \ - \ },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n \ - \ }\n ],\n \"usage\": {\n \"prompt_tokens\": 186,\n \"completion_tokens\"\ - : 15,\n \"total_tokens\": 201,\n \"completion_tokens_details\": {\n\ - \ \"reasoning_tokens\": 0\n }\n },\n \"system_fingerprint\": \"\ - fp_52a7f40b0b\"\n}\n" + string: "{\n \"id\": \"chatcmpl-DDG9vqGZskrNpGfY0XnTHvzJGDu5u\",\n \"object\": + \"chat.completion\",\n \"created\": 1772052751,\n \"model\": \"gpt-4.1-mini-2025-04-14\",\n + \ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": + \"assistant\",\n \"content\": \"4\",\n \"refusal\": null,\n + \ \"annotations\": []\n },\n \"logprobs\": null,\n \"finish_reason\": + \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 101,\n \"completion_tokens\": + 1,\n \"total_tokens\": 102,\n \"prompt_tokens_details\": {\n \"cached_tokens\": + 0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\": + {\n \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\": + 0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\": + \"default\",\n \"system_fingerprint\": \"fp_a391f2cee0\"\n}\n" headers: - CF-Cache-Status: - - DYNAMIC CF-RAY: - - 8c85fa63ed091cf3-GRU + - CF-RAY-XXX Connection: - keep-alive Content-Type: - application/json Date: - - Tue, 24 Sep 2024 21:48:21 GMT + - Wed, 25 Feb 2026 20:52:32 GMT Server: - cloudflare + Strict-Transport-Security: + - STS-XXX Transfer-Encoding: - chunked X-Content-Type-Options: - - nosniff + - X-CONTENT-TYPE-XXX access-control-expose-headers: - - X-Request-ID + - ACCESS-CONTROL-XXX + alt-svc: + - h3=":443"; ma=86400 + cf-cache-status: + - DYNAMIC openai-organization: - - crewai-iuxna1 + - OPENAI-ORG-XXX openai-processing-ms: - - '199' + - '276' + openai-project: + - OPENAI-PROJECT-XXX openai-version: - '2020-10-01' - strict-transport-security: - - max-age=31536000; includeSubDomains; preload + set-cookie: + - SET-COOKIE-XXX + x-openai-proxy-wasm: + - v0.1 x-ratelimit-limit-requests: - - '10000' + - X-RATELIMIT-LIMIT-REQUESTS-XXX x-ratelimit-limit-tokens: - - '30000000' + - X-RATELIMIT-LIMIT-TOKENS-XXX x-ratelimit-remaining-requests: - - '9999' + - X-RATELIMIT-REMAINING-REQUESTS-XXX x-ratelimit-remaining-tokens: - - '29999781' + - X-RATELIMIT-REMAINING-TOKENS-XXX x-ratelimit-reset-requests: - - 6ms + - X-RATELIMIT-RESET-REQUESTS-XXX x-ratelimit-reset-tokens: - - 0s + - X-RATELIMIT-RESET-TOKENS-XXX x-request-id: - - req_93411fed8e9bb5607df0dbc5d178f2cb + - X-REQUEST-ID-XXX status: code: 200 message: OK diff --git a/lib/crewai/tests/cassettes/test_save_task_pydantic_output.yaml b/lib/crewai/tests/cassettes/test_save_task_pydantic_output.yaml index f854903fa..6959ae12f 100644 --- a/lib/crewai/tests/cassettes/test_save_task_pydantic_output.yaml +++ b/lib/crewai/tests/cassettes/test_save_task_pydantic_output.yaml @@ -1,12 +1,29 @@ interactions: - request: - body: '{"messages":[{"role":"system","content":"You are Scorer. You''re an expert scorer, specialized in scoring titles.\nYour personal goal is: Score the title\nTo give my best complete final answer to the task respond using the exact following format:\n\nThought: I now can give a great answer\nFinal Answer: Your final answer must be the great and the most complete as possible, it must be outcome described.\n\nI MUST use these formats, my job depends on it!"},{"role":"user","content":"\nCurrent Task: Give me an integer score between 1-5 for the following title: ''The impact of AI in the future of work''\n\nThis is the expected criteria for your final answer: The score of the title.\nyou MUST return the actual complete content as the final answer, not a summary.\nEnsure your final answer strictly adheres to the following OpenAPI schema: {\n \"properties\": {\n \"score\": {\n \"title\": \"Score\",\n \"type\": \"integer\"\n }\n },\n \"required\": [\n \"score\"\n ],\n \"title\": - \"ScoreOutput\",\n \"type\": \"object\",\n \"additionalProperties\": false\n}\n\nDo not include the OpenAPI schema in the final output. Ensure the final output does not include any code block markers like ```json or ```python.\n\nBegin! This is VERY important to you, use the tools available and give your best Final Answer, your job depends on it!\n\nThought:"}],"model":"gpt-4.1-mini"}' + body: '{"messages":[{"role":"system","content":"You are Scorer. You''re an expert + scorer, specialized in scoring titles.\nYour personal goal is: Score the title\nTo + give my best complete final answer to the task respond using the exact following + format:\n\nThought: I now can give a great answer\nFinal Answer: Your final + answer must be the great and the most complete as possible, it must be outcome + described.\n\nI MUST use these formats, my job depends on it!"},{"role":"user","content":"\nCurrent + Task: Give me an integer score between 1-5 for the following title: ''The impact + of AI in the future of work''\n\nThis is the expected criteria for your final + answer: The score of the title.\nyou MUST return the actual complete content + as the final answer, not a summary.\nEnsure your final answer strictly adheres + to the following OpenAPI schema: {\n \"properties\": {\n \"score\": {\n \"title\": + \"Score\",\n \"type\": \"integer\"\n }\n },\n \"required\": [\n \"score\"\n ],\n \"title\": + \"ScoreOutput\",\n \"type\": \"object\",\n \"additionalProperties\": false\n}\n\nDo + not include the OpenAPI schema in the final output. Ensure the final output + does not include any code block markers like ```json or ```python.\n\nBegin! + This is VERY important to you, use the tools available and give your best Final + Answer, your job depends on it!\n\nThought:"}],"model":"gpt-4.1-mini"}' headers: + User-Agent: + - X-USER-AGENT-XXX accept: - application/json accept-encoding: - - gzip, deflate, zstd + - ACCEPT-ENCODING-XXX connection: - keep-alive content-length: @@ -15,20 +32,18 @@ interactions: - application/json host: - api.openai.com - user-agent: - - OpenAI/Python 1.109.1 x-stainless-arch: - - arm64 + - X-STAINLESS-ARCH-XXX x-stainless-async: - 'false' x-stainless-lang: - python x-stainless-os: - - MacOS + - X-STAINLESS-OS-XXX x-stainless-package-version: - 1.109.1 x-stainless-read-timeout: - - '600' + - X-STAINLESS-READ-TIMEOUT-XXX x-stainless-retry-count: - '0' x-stainless-runtime: @@ -39,11 +54,25 @@ interactions: uri: https://api.openai.com/v1/chat/completions response: body: - string: "{\n \"id\": \"chatcmpl-CYg0PI2q4kRtIkqoIwCl9TVmZiD0o\",\n \"object\": \"chat.completion\",\n \"created\": 1762380657,\n \"model\": \"gpt-4.1-mini-2025-04-14\",\n \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"Thought: The title \\\"The impact of AI in the future of work\\\" is clear, relevant, and concise. It accurately reflects a significant and current topic that is likely to attract interest. However, it could be more specific about the type of impact or scope to make it more compelling. Overall, it is a strong and effective title.\\n\\nFinal Answer: {\\n \\\"score\\\": 4\\n}\",\n \"refusal\": null,\n \"annotations\": []\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 294,\n \"completion_tokens\": 80,\n \"total_tokens\": 374,\n \"prompt_tokens_details\": {\n \"cached_tokens\": 0,\n \ - \ \"audio_tokens\": 0\n },\n \"completion_tokens_details\": {\n \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\": 0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\": \"default\",\n \"system_fingerprint\": \"fp_4c2851f862\"\n}\n" + string: "{\n \"id\": \"chatcmpl-CYg0PI2q4kRtIkqoIwCl9TVmZiD0o\",\n \"object\": + \"chat.completion\",\n \"created\": 1762380657,\n \"model\": \"gpt-4.1-mini-2025-04-14\",\n + \ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": + \"assistant\",\n \"content\": \"Thought: The title \\\"The impact of + AI in the future of work\\\" is clear, relevant, and concise. It accurately + reflects a significant and current topic that is likely to attract interest. + However, it could be more specific about the type of impact or scope to make + it more compelling. Overall, it is a strong and effective title.\\n\\nFinal + Answer: {\\n \\\"score\\\": 4\\n}\",\n \"refusal\": null,\n \"annotations\": + []\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n + \ }\n ],\n \"usage\": {\n \"prompt_tokens\": 294,\n \"completion_tokens\": + 80,\n \"total_tokens\": 374,\n \"prompt_tokens_details\": {\n \"cached_tokens\": + 0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\": + {\n \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\": + 0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\": + \"default\",\n \"system_fingerprint\": \"fp_4c2851f862\"\n}\n" headers: CF-RAY: - - REDACTED-RAY + - CF-RAY-XXX Connection: - keep-alive Content-Type: @@ -53,26 +82,25 @@ interactions: Server: - cloudflare Set-Cookie: - - __cf_bm=REDACTED; path=/; expires=Wed, 05-Nov-25 22:40:59 GMT; domain=.api.openai.com; HttpOnly; Secure; SameSite=None - - _cfuvid=REDACTED; path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None + - SET-COOKIE-XXX Strict-Transport-Security: - - max-age=31536000; includeSubDomains; preload + - STS-XXX Transfer-Encoding: - chunked X-Content-Type-Options: - - nosniff + - X-CONTENT-TYPE-XXX access-control-expose-headers: - - X-Request-ID + - ACCESS-CONTROL-XXX alt-svc: - h3=":443"; ma=86400 cf-cache-status: - DYNAMIC openai-organization: - - user-hortuttj2f3qtmxyik2zxf4q + - OPENAI-ORG-XXX openai-processing-ms: - '1476' openai-project: - - proj_fL4UBWR1CMpAAdgzaSKqsVvA + - OPENAI-PROJECT-XXX openai-version: - '2020-10-01' x-envoy-upstream-service-time: @@ -80,29 +108,32 @@ interactions: x-openai-proxy-wasm: - v0.1 x-ratelimit-limit-requests: - - '500' + - X-RATELIMIT-LIMIT-REQUESTS-XXX x-ratelimit-limit-tokens: - - '200000' + - X-RATELIMIT-LIMIT-TOKENS-XXX x-ratelimit-remaining-requests: - - '499' + - X-RATELIMIT-REMAINING-REQUESTS-XXX x-ratelimit-remaining-tokens: - - '199687' + - X-RATELIMIT-REMAINING-TOKENS-XXX x-ratelimit-reset-requests: - - 120ms + - X-RATELIMIT-RESET-REQUESTS-XXX x-ratelimit-reset-tokens: - - 93ms + - X-RATELIMIT-RESET-TOKENS-XXX x-request-id: - - req_REDACTED + - X-REQUEST-ID-XXX status: code: 200 message: OK - request: - body: '{"trace_id": "c682f49d-bb6b-49d9-84b7-06e1881d37cd", "execution_type": "crew", "user_identifier": null, "execution_context": {"crew_fingerprint": null, "crew_name": "crew", "flow_name": null, "crewai_version": "1.4.1", "privacy_level": "standard"}, "execution_metadata": {"expected_duration_estimate": 300, "agent_count": 0, "task_count": 0, "flow_method_count": 0, "execution_started_at": "2025-11-15T21:20:09.431751+00:00"}, "ephemeral_trace_id": "c682f49d-bb6b-49d9-84b7-06e1881d37cd"}' + body: '{"trace_id": "c682f49d-bb6b-49d9-84b7-06e1881d37cd", "execution_type": + "crew", "user_identifier": null, "execution_context": {"crew_fingerprint": null, + "crew_name": "crew", "flow_name": null, "crewai_version": "1.4.1", "privacy_level": + "standard"}, "execution_metadata": {"expected_duration_estimate": 300, "agent_count": + 0, "task_count": 0, "flow_method_count": 0, "execution_started_at": "2025-11-15T21:20:09.431751+00:00"}, + "ephemeral_trace_id": "c682f49d-bb6b-49d9-84b7-06e1881d37cd"}' headers: Accept: - '*/*' - Accept-Encoding: - - gzip, deflate Connection: - keep-alive Content-Length: @@ -110,11 +141,13 @@ interactions: Content-Type: - application/json User-Agent: - - CrewAI-CLI/1.4.1 + - X-USER-AGENT-XXX X-Crewai-Organization-Id: - 73c2b193-f579-422c-84c7-76a39a1da77f X-Crewai-Version: - 1.4.1 + accept-encoding: + - ACCEPT-ENCODING-XXX method: POST uri: https://app.crewai.com/crewai_plus/api/v1/tracing/ephemeral/batches response: @@ -132,36 +165,168 @@ interactions: cache-control: - no-store content-security-policy: - - 'default-src ''self'' *.app.crewai.com app.crewai.com; script-src ''self'' ''unsafe-inline'' *.app.crewai.com app.crewai.com https://cdn.jsdelivr.net/npm/apexcharts https://www.gstatic.com https://run.pstmn.io https://apis.google.com https://apis.google.com/js/api.js https://accounts.google.com https://accounts.google.com/gsi/client https://cdnjs.cloudflare.com/ajax/libs/normalize/8.0.1/normalize.min.css.map https://*.google.com https://docs.google.com https://slides.google.com https://js.hs-scripts.com https://js.sentry-cdn.com https://browser.sentry-cdn.com https://www.googletagmanager.com https://js-na1.hs-scripts.com https://js.hubspot.com http://js-na1.hs-scripts.com https://bat.bing.com https://cdn.amplitude.com https://cdn.segment.com https://d1d3n03t5zntha.cloudfront.net/ https://descriptusercontent.com https://edge.fullstory.com https://googleads.g.doubleclick.net https://js.hs-analytics.net https://js.hs-banner.com https://js.hsadspixel.net https://js.hscollectedforms.net - https://js.usemessages.com https://snap.licdn.com https://static.cloudflareinsights.com https://static.reo.dev https://www.google-analytics.com https://share.descript.com/; style-src ''self'' ''unsafe-inline'' *.app.crewai.com app.crewai.com https://cdn.jsdelivr.net/npm/apexcharts; img-src ''self'' data: *.app.crewai.com app.crewai.com https://zeus.tools.crewai.com https://dashboard.tools.crewai.com https://cdn.jsdelivr.net https://forms.hsforms.com https://track.hubspot.com https://px.ads.linkedin.com https://px4.ads.linkedin.com https://www.google.com https://www.google.com.br; font-src ''self'' data: *.app.crewai.com app.crewai.com; connect-src ''self'' *.app.crewai.com app.crewai.com https://zeus.tools.crewai.com https://connect.useparagon.com/ https://zeus.useparagon.com/* https://*.useparagon.com/* https://run.pstmn.io https://connect.tools.crewai.com/ https://*.sentry.io https://www.google-analytics.com https://edge.fullstory.com https://rs.fullstory.com https://api.hubspot.com - https://forms.hscollectedforms.net https://api.hubapi.com https://px.ads.linkedin.com https://px4.ads.linkedin.com https://google.com/pagead/form-data/16713662509 https://google.com/ccm/form-data/16713662509 https://www.google.com/ccm/collect https://worker-actionkit.tools.crewai.com https://api.reo.dev; frame-src ''self'' *.app.crewai.com app.crewai.com https://connect.useparagon.com/ https://zeus.tools.crewai.com https://zeus.useparagon.com/* https://connect.tools.crewai.com/ https://docs.google.com https://drive.google.com https://slides.google.com https://accounts.google.com https://*.google.com https://app.hubspot.com/ https://td.doubleclick.net https://www.googletagmanager.com/ https://www.youtube.com https://share.descript.com' + - CSP-FILTERED etag: - - W/"e8d1e903c8c6ec2f765163c0c03bed79" + - ETAG-XXX expires: - '0' permissions-policy: - - camera=(), microphone=(self), geolocation=() + - PERMISSIONS-POLICY-XXX pragma: - no-cache referrer-policy: - - strict-origin-when-cross-origin + - REFERRER-POLICY-XXX strict-transport-security: - - max-age=63072000; includeSubDomains + - STS-XXX vary: - Accept x-content-type-options: - - nosniff + - X-CONTENT-TYPE-XXX x-frame-options: - - SAMEORIGIN + - X-FRAME-OPTIONS-XXX x-permitted-cross-domain-policies: - - none + - X-PERMITTED-XXX x-request-id: - - 5ea5f513-c359-4a92-a84a-08ad44d9857b + - X-REQUEST-ID-XXX x-runtime: - - '0.044665' + - X-RUNTIME-XXX x-xss-protection: - - 1; mode=block + - X-XSS-PROTECTION-XXX status: code: 201 message: Created +- request: + body: '{"messages":[{"role":"system","content":"You are Scorer. You''re an expert + scorer, specialized in scoring titles.\nYour personal goal is: Score the title"},{"role":"user","content":"\nCurrent + Task: Give me an integer score between 1-5 for the following title: ''The impact + of AI in the future of work''\n\nThis is the expected criteria for your final + answer: The score of the title.\nyou MUST return the actual complete content + as the final answer, not a summary.\nFormat your final answer according to the + following OpenAPI schema: {\n \"properties\": {\n \"score\": {\n \"title\": + \"Score\",\n \"type\": \"integer\"\n }\n },\n \"required\": [\n \"score\"\n ],\n \"title\": + \"ScoreOutput\",\n \"type\": \"object\",\n \"additionalProperties\": false\n}\n\nIMPORTANT: + Preserve the original content exactly as-is. Do NOT rewrite, paraphrase, or + modify the meaning of the content. Only structure it to match the schema format.\n\nDo + not include the OpenAPI schema in the final output. Ensure the final output + does not include any code block markers like ```json or ```python.\n\nProvide + your complete response:"},{"role":"system","content":"You are Scorer. You''re + an expert scorer, specialized in scoring titles.\nYour personal goal is: Score + the title"},{"role":"user","content":"\nCurrent Task: Give me an integer score + between 1-5 for the following title: ''The impact of AI in the future of work''\n\nThis + is the expected criteria for your final answer: The score of the title.\nyou + MUST return the actual complete content as the final answer, not a summary.\nFormat + your final answer according to the following OpenAPI schema: {\n \"properties\": + {\n \"score\": {\n \"title\": \"Score\",\n \"type\": \"integer\"\n }\n },\n \"required\": + [\n \"score\"\n ],\n \"title\": \"ScoreOutput\",\n \"type\": \"object\",\n \"additionalProperties\": + false\n}\n\nIMPORTANT: Preserve the original content exactly as-is. Do NOT rewrite, + paraphrase, or modify the meaning of the content. Only structure it to match + the schema format.\n\nDo not include the OpenAPI schema in the final output. + Ensure the final output does not include any code block markers like ```json + or ```python.\n\nProvide your complete response:"}],"model":"gpt-4.1-mini","response_format":{"type":"json_schema","json_schema":{"schema":{"properties":{"score":{"title":"Score","type":"integer"}},"required":["score"],"title":"ScoreOutput","type":"object","additionalProperties":false},"name":"ScoreOutput","strict":true}},"stream":false}' + headers: + User-Agent: + - X-USER-AGENT-XXX + accept: + - application/json + accept-encoding: + - ACCEPT-ENCODING-XXX + authorization: + - AUTHORIZATION-XXX + connection: + - keep-alive + content-length: + - '2541' + content-type: + - application/json + cookie: + - COOKIE-XXX + host: + - api.openai.com + x-stainless-arch: + - X-STAINLESS-ARCH-XXX + x-stainless-async: + - 'false' + x-stainless-helper-method: + - beta.chat.completions.parse + x-stainless-lang: + - python + x-stainless-os: + - X-STAINLESS-OS-XXX + x-stainless-package-version: + - 1.83.0 + x-stainless-read-timeout: + - X-STAINLESS-READ-TIMEOUT-XXX + x-stainless-retry-count: + - '0' + x-stainless-runtime: + - CPython + x-stainless-runtime-version: + - 3.13.12 + method: POST + uri: https://api.openai.com/v1/chat/completions + response: + body: + string: "{\n \"id\": \"chatcmpl-DDE0GSLDtGruDzwtl2bwlAXUmvmHG\",\n \"object\": + \"chat.completion\",\n \"created\": 1772044464,\n \"model\": \"gpt-4.1-mini-2025-04-14\",\n + \ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": + \"assistant\",\n \"content\": \"{\\\"score\\\":4}\",\n \"refusal\": + null,\n \"annotations\": []\n },\n \"logprobs\": null,\n + \ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": + 513,\n \"completion_tokens\": 5,\n \"total_tokens\": 518,\n \"prompt_tokens_details\": + {\n \"cached_tokens\": 0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\": + {\n \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\": + 0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\": + \"default\",\n \"system_fingerprint\": \"fp_a391f2cee0\"\n}\n" + headers: + CF-RAY: + - CF-RAY-XXX + Connection: + - keep-alive + Content-Type: + - application/json + Date: + - Wed, 25 Feb 2026 18:34:25 GMT + Server: + - cloudflare + Strict-Transport-Security: + - STS-XXX + Transfer-Encoding: + - chunked + X-Content-Type-Options: + - X-CONTENT-TYPE-XXX + access-control-expose-headers: + - ACCESS-CONTROL-XXX + alt-svc: + - h3=":443"; ma=86400 + cf-cache-status: + - DYNAMIC + openai-organization: + - OPENAI-ORG-XXX + openai-processing-ms: + - '530' + openai-project: + - OPENAI-PROJECT-XXX + openai-version: + - '2020-10-01' + set-cookie: + - SET-COOKIE-XXX + x-openai-proxy-wasm: + - v0.1 + x-ratelimit-limit-requests: + - X-RATELIMIT-LIMIT-REQUESTS-XXX + x-ratelimit-limit-tokens: + - X-RATELIMIT-LIMIT-TOKENS-XXX + x-ratelimit-remaining-requests: + - X-RATELIMIT-REMAINING-REQUESTS-XXX + x-ratelimit-remaining-tokens: + - X-RATELIMIT-REMAINING-TOKENS-XXX + x-ratelimit-reset-requests: + - X-RATELIMIT-RESET-REQUESTS-XXX + x-ratelimit-reset-tokens: + - X-RATELIMIT-RESET-TOKENS-XXX + x-request-id: + - X-REQUEST-ID-XXX + status: + code: 200 + message: OK version: 1 diff --git a/lib/crewai/tests/cassettes/test_task_guardrail_process_output.yaml b/lib/crewai/tests/cassettes/test_task_guardrail_process_output.yaml index 26e54a516..d9454ccd2 100644 --- a/lib/crewai/tests/cassettes/test_task_guardrail_process_output.yaml +++ b/lib/crewai/tests/cassettes/test_task_guardrail_process_output.yaml @@ -3,11 +3,7 @@ interactions: body: "{\"messages\":[{\"role\":\"system\",\"content\":\"You are Guardrail Agent. You are a expert at validating the output of a task. By providing effective feedback if the output is not valid.\\nYour personal goal is: Validate the output - of the task\\nTo give my best complete final answer to the task respond using - the exact following format:\\n\\nThought: I now can give a great answer\\nFinal - Answer: Your final answer must be the great and the most complete as possible, - it must be outcome described.\\n\\nI MUST use these formats, my job depends - on it!\"},{\"role\":\"user\",\"content\":\"\\nCurrent Task: \\n Ensure + of the task\"},{\"role\":\"user\",\"content\":\"\\nCurrent Task: \\n Ensure the following task result complies with the given guardrail.\\n\\n Task result:\\n \\n Lorem Ipsum is simply dummy text of the printing and typesetting industry. Lorem Ipsum has been the industry's standard dummy @@ -17,8 +13,9 @@ interactions: what is wrong (e.g., by how much it violates the rule, or what specific part fails).\\n - Focus only on identifying issues \u2014 do not propose corrections.\\n \ - If the Task result complies with the guardrail, saying that is valid\\n - \ \\n\\nBegin! This is VERY important to you, use the tools available - and give your best Final Answer, your job depends on it!\\n\\nThought:\"}],\"model\":\"gpt-4o\"}" + \ \\n\\nProvide your complete response:\"}],\"model\":\"gpt-4o\",\"response_format\":{\"type\":\"json_schema\",\"json_schema\":{\"schema\":{\"properties\":{\"valid\":{\"description\":\"Whether + the task output complies with the guardrail\",\"title\":\"Valid\",\"type\":\"boolean\"},\"feedback\":{\"anyOf\":[{\"type\":\"string\"},{\"type\":\"null\"}],\"description\":\"A + feedback about the task output if it is not valid\",\"title\":\"Feedback\"}},\"required\":[\"valid\",\"feedback\"],\"title\":\"LLMGuardrailResult\",\"type\":\"object\",\"additionalProperties\":false},\"name\":\"LLMGuardrailResult\",\"strict\":true}},\"stream\":false}" headers: User-Agent: - X-USER-AGENT-XXX @@ -31,7 +28,7 @@ interactions: connection: - keep-alive content-length: - - '1467' + - '1567' content-type: - application/json host: @@ -40,142 +37,6 @@ interactions: - X-STAINLESS-ARCH-XXX x-stainless-async: - 'false' - x-stainless-lang: - - python - x-stainless-os: - - X-STAINLESS-OS-XXX - x-stainless-package-version: - - 1.83.0 - x-stainless-read-timeout: - - X-STAINLESS-READ-TIMEOUT-XXX - x-stainless-retry-count: - - '0' - x-stainless-runtime: - - CPython - x-stainless-runtime-version: - - 3.13.3 - method: POST - uri: https://api.openai.com/v1/chat/completions - response: - body: - string: "{\n \"id\": \"chatcmpl-Cy7yHRYTZi8yzRbcODnKr92keLKCb\",\n \"object\": - \"chat.completion\",\n \"created\": 1768446357,\n \"model\": \"gpt-4o-2024-08-06\",\n - \ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": - \"assistant\",\n \"content\": \"The task result provided has more than - 10 words. I will count the words to verify this.\\n\\nThe task result is the - following text:\\n\\\"Lorem Ipsum is simply dummy text of the printing and - typesetting industry. Lorem Ipsum has been the industry's standard dummy text - ever\\\"\\n\\nCounting the words:\\n\\n1. Lorem \\n2. Ipsum \\n3. is \\n4. - simply \\n5. dummy \\n6. text \\n7. of \\n8. the \\n9. printing \\n10. and - \\n11. typesetting \\n12. industry. \\n13. Lorem \\n14. Ipsum \\n15. has \\n16. - been \\n17. the \\n18. industry's \\n19. standard \\n20. dummy \\n21. text - \\n22. ever\\n\\nThe total word count is 22.\\n\\nThought: I now can give - a great answer\\nFinal Answer: The task result does not comply with the guardrail. - It contains 22 words, which exceeds the limit of 10 words.\",\n \"refusal\": - null,\n \"annotations\": []\n },\n \"logprobs\": null,\n - \ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": - 285,\n \"completion_tokens\": 195,\n \"total_tokens\": 480,\n \"prompt_tokens_details\": - {\n \"cached_tokens\": 0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\": - {\n \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\": - 0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\": - \"default\",\n \"system_fingerprint\": \"fp_deacdd5f6f\"\n}\n" - headers: - CF-RAY: - - CF-RAY-XXX - Connection: - - keep-alive - Content-Type: - - application/json - Date: - - Thu, 15 Jan 2026 03:05:59 GMT - Server: - - cloudflare - Set-Cookie: - - SET-COOKIE-XXX - Strict-Transport-Security: - - STS-XXX - Transfer-Encoding: - - chunked - X-Content-Type-Options: - - X-CONTENT-TYPE-XXX - access-control-expose-headers: - - ACCESS-CONTROL-XXX - alt-svc: - - h3=":443"; ma=86400 - cf-cache-status: - - DYNAMIC - content-length: - - '1557' - openai-organization: - - OPENAI-ORG-XXX - openai-processing-ms: - - '2130' - openai-project: - - OPENAI-PROJECT-XXX - openai-version: - - '2020-10-01' - x-envoy-upstream-service-time: - - '2147' - x-openai-proxy-wasm: - - v0.1 - x-ratelimit-limit-requests: - - X-RATELIMIT-LIMIT-REQUESTS-XXX - x-ratelimit-limit-tokens: - - X-RATELIMIT-LIMIT-TOKENS-XXX - x-ratelimit-remaining-requests: - - X-RATELIMIT-REMAINING-REQUESTS-XXX - x-ratelimit-remaining-tokens: - - X-RATELIMIT-REMAINING-TOKENS-XXX - x-ratelimit-reset-requests: - - X-RATELIMIT-RESET-REQUESTS-XXX - x-ratelimit-reset-tokens: - - X-RATELIMIT-RESET-TOKENS-XXX - x-request-id: - - X-REQUEST-ID-XXX - status: - code: 200 - message: OK -- request: - body: '{"messages":[{"role":"system","content":"Ensure your final answer strictly - adheres to the following OpenAPI schema: {\n \"type\": \"json_schema\",\n \"json_schema\": - {\n \"name\": \"LLMGuardrailResult\",\n \"strict\": true,\n \"schema\": - {\n \"properties\": {\n \"valid\": {\n \"description\": - \"Whether the task output complies with the guardrail\",\n \"title\": - \"Valid\",\n \"type\": \"boolean\"\n },\n \"feedback\": - {\n \"anyOf\": [\n {\n \"type\": \"string\"\n },\n {\n \"type\": - \"null\"\n }\n ],\n \"default\": null,\n \"description\": - \"A feedback about the task output if it is not valid\",\n \"title\": - \"Feedback\"\n }\n },\n \"required\": [\n \"valid\",\n \"feedback\"\n ],\n \"title\": - \"LLMGuardrailResult\",\n \"type\": \"object\",\n \"additionalProperties\": - false\n }\n }\n}\n\nDo not include the OpenAPI schema in the final output. - Ensure the final output does not include any code block markers like ```json - or ```python."},{"role":"user","content":"The task result does not comply with - the guardrail. It contains 22 words, which exceeds the limit of 10 words."}],"model":"gpt-4o","response_format":{"type":"json_schema","json_schema":{"schema":{"properties":{"valid":{"description":"Whether - the task output complies with the guardrail","title":"Valid","type":"boolean"},"feedback":{"anyOf":[{"type":"string"},{"type":"null"}],"description":"A - feedback about the task output if it is not valid","title":"Feedback"}},"required":["valid","feedback"],"title":"LLMGuardrailResult","type":"object","additionalProperties":false},"name":"LLMGuardrailResult","strict":true}},"stream":false}' - headers: - User-Agent: - - X-USER-AGENT-XXX - accept: - - application/json - accept-encoding: - - ACCEPT-ENCODING-XXX - authorization: - - AUTHORIZATION-XXX - connection: - - keep-alive - content-length: - - '1835' - content-type: - - application/json - cookie: - - COOKIE-XXX - host: - - api.openai.com - x-stainless-arch: - - X-STAINLESS-ARCH-XXX - x-stainless-async: - - 'false' x-stainless-helper-method: - beta.chat.completions.parse x-stainless-lang: @@ -191,23 +52,24 @@ interactions: x-stainless-runtime: - CPython x-stainless-runtime-version: - - 3.13.3 + - 3.13.12 method: POST uri: https://api.openai.com/v1/chat/completions response: body: - string: "{\n \"id\": \"chatcmpl-Cy7yJiPCk4fXuogyT5e8XeGRLCSf8\",\n \"object\": - \"chat.completion\",\n \"created\": 1768446359,\n \"model\": \"gpt-4o-2024-08-06\",\n + string: "{\n \"id\": \"chatcmpl-DDGANa7LCEtvfCZsEly4mNksTjCX3\",\n \"object\": + \"chat.completion\",\n \"created\": 1772052779,\n \"model\": \"gpt-4o-2024-08-06\",\n \ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"{\\\"valid\\\":false,\\\"feedback\\\":\\\"The - task output exceeds the word limit of 10 words by containing 22 words.\\\"}\",\n - \ \"refusal\": null,\n \"annotations\": []\n },\n \"logprobs\": - null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": - 363,\n \"completion_tokens\": 25,\n \"total_tokens\": 388,\n \"prompt_tokens_details\": - {\n \"cached_tokens\": 0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\": + task result contains more than 10 words. Specifically, it has 20 words, which + exceeds the guardrail limit by 10 words.\\\"}\",\n \"refusal\": null,\n + \ \"annotations\": []\n },\n \"logprobs\": null,\n \"finish_reason\": + \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 290,\n \"completion_tokens\": + 37,\n \"total_tokens\": 327,\n \"prompt_tokens_details\": {\n \"cached_tokens\": + 0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\": {\n \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\": 0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\": - \"default\",\n \"system_fingerprint\": \"fp_a0e9480a2f\"\n}\n" + \"default\",\n \"system_fingerprint\": \"fp_64dfa806c7\"\n}\n" headers: CF-RAY: - CF-RAY-XXX @@ -216,7 +78,7 @@ interactions: Content-Type: - application/json Date: - - Thu, 15 Jan 2026 03:05:59 GMT + - Wed, 25 Feb 2026 20:53:00 GMT Server: - cloudflare Strict-Transport-Security: @@ -231,18 +93,16 @@ interactions: - h3=":443"; ma=86400 cf-cache-status: - DYNAMIC - content-length: - - '913' openai-organization: - OPENAI-ORG-XXX openai-processing-ms: - - '488' + - '1108' openai-project: - OPENAI-PROJECT-XXX openai-version: - '2020-10-01' - x-envoy-upstream-service-time: - - '507' + set-cookie: + - SET-COOKIE-XXX x-openai-proxy-wasm: - v0.1 x-ratelimit-limit-requests: @@ -266,11 +126,7 @@ interactions: body: "{\"messages\":[{\"role\":\"system\",\"content\":\"You are Guardrail Agent. You are a expert at validating the output of a task. By providing effective feedback if the output is not valid.\\nYour personal goal is: Validate the output - of the task\\nTo give my best complete final answer to the task respond using - the exact following format:\\n\\nThought: I now can give a great answer\\nFinal - Answer: Your final answer must be the great and the most complete as possible, - it must be outcome described.\\n\\nI MUST use these formats, my job depends - on it!\"},{\"role\":\"user\",\"content\":\"\\nCurrent Task: \\n Ensure + of the task\"},{\"role\":\"user\",\"content\":\"\\nCurrent Task: \\n Ensure the following task result complies with the given guardrail.\\n\\n Task result:\\n \\n Lorem Ipsum is simply dummy text of the printing and typesetting industry. Lorem Ipsum has been the industry's standard dummy @@ -280,8 +136,9 @@ interactions: explaining what is wrong (e.g., by how much it violates the rule, or what specific part fails).\\n - Focus only on identifying issues \u2014 do not propose corrections.\\n - If the Task result complies with the guardrail, saying - that is valid\\n \\n\\nBegin! This is VERY important to you, use the - tools available and give your best Final Answer, your job depends on it!\\n\\nThought:\"}],\"model\":\"gpt-4o\"}" + that is valid\\n \\n\\nProvide your complete response:\"}],\"model\":\"gpt-4o\",\"response_format\":{\"type\":\"json_schema\",\"json_schema\":{\"schema\":{\"properties\":{\"valid\":{\"description\":\"Whether + the task output complies with the guardrail\",\"title\":\"Valid\",\"type\":\"boolean\"},\"feedback\":{\"anyOf\":[{\"type\":\"string\"},{\"type\":\"null\"}],\"description\":\"A + feedback about the task output if it is not valid\",\"title\":\"Feedback\"}},\"required\":[\"valid\",\"feedback\"],\"title\":\"LLMGuardrailResult\",\"type\":\"object\",\"additionalProperties\":false},\"name\":\"LLMGuardrailResult\",\"strict\":true}},\"stream\":false}" headers: User-Agent: - X-USER-AGENT-XXX @@ -294,7 +151,7 @@ interactions: connection: - keep-alive content-length: - - '1468' + - '1568' content-type: - application/json host: @@ -303,144 +160,6 @@ interactions: - X-STAINLESS-ARCH-XXX x-stainless-async: - 'false' - x-stainless-lang: - - python - x-stainless-os: - - X-STAINLESS-OS-XXX - x-stainless-package-version: - - 1.83.0 - x-stainless-read-timeout: - - X-STAINLESS-READ-TIMEOUT-XXX - x-stainless-retry-count: - - '0' - x-stainless-runtime: - - CPython - x-stainless-runtime-version: - - 3.13.3 - method: POST - uri: https://api.openai.com/v1/chat/completions - response: - body: - string: "{\n \"id\": \"chatcmpl-Cy7yKa0rmi2YoTLpyXt9hjeLt2rTI\",\n \"object\": - \"chat.completion\",\n \"created\": 1768446360,\n \"model\": \"gpt-4o-2024-08-06\",\n - \ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": - \"assistant\",\n \"content\": \"First, I'll count the number of words - in the Task result to ensure it complies with the guardrail. \\n\\nThe Task - result is: \\\"Lorem Ipsum is simply dummy text of the printing and typesetting - industry. Lorem Ipsum has been the industry's standard dummy text ever.\\\"\\n\\nBy - counting the words: \\n1. Lorem\\n2. Ipsum\\n3. is\\n4. simply\\n5. dummy\\n6. - text\\n7. of\\n8. the\\n9. printing\\n10. and\\n11. typesetting\\n12. industry\\n13. - Lorem\\n14. Ipsum\\n15. has\\n16. been\\n17. the\\n18. industry's\\n19. standard\\n20. - dummy\\n21. text\\n22. ever\\n\\nThere are 22 words total in the Task result.\\n\\nI - need to verify if the count of 22 words is less than the guardrail limit of - 500 words.\\n\\nThought: I now can give a great answer\\nFinal Answer: The - Task result complies with the guardrail as it contains 22 words, which is - less than the 500-word limit. Therefore, the output is valid.\",\n \"refusal\": - null,\n \"annotations\": []\n },\n \"logprobs\": null,\n - \ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": - 285,\n \"completion_tokens\": 227,\n \"total_tokens\": 512,\n \"prompt_tokens_details\": - {\n \"cached_tokens\": 0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\": - {\n \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\": - 0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\": - \"default\",\n \"system_fingerprint\": \"fp_deacdd5f6f\"\n}\n" - headers: - CF-RAY: - - CF-RAY-XXX - Connection: - - keep-alive - Content-Type: - - application/json - Date: - - Thu, 15 Jan 2026 03:06:02 GMT - Server: - - cloudflare - Set-Cookie: - - SET-COOKIE-XXX - Strict-Transport-Security: - - STS-XXX - Transfer-Encoding: - - chunked - X-Content-Type-Options: - - X-CONTENT-TYPE-XXX - access-control-expose-headers: - - ACCESS-CONTROL-XXX - alt-svc: - - h3=":443"; ma=86400 - cf-cache-status: - - DYNAMIC - content-length: - - '1668' - openai-organization: - - OPENAI-ORG-XXX - openai-processing-ms: - - '2502' - openai-project: - - OPENAI-PROJECT-XXX - openai-version: - - '2020-10-01' - x-envoy-upstream-service-time: - - '2522' - x-openai-proxy-wasm: - - v0.1 - x-ratelimit-limit-requests: - - X-RATELIMIT-LIMIT-REQUESTS-XXX - x-ratelimit-limit-tokens: - - X-RATELIMIT-LIMIT-TOKENS-XXX - x-ratelimit-remaining-requests: - - X-RATELIMIT-REMAINING-REQUESTS-XXX - x-ratelimit-remaining-tokens: - - X-RATELIMIT-REMAINING-TOKENS-XXX - x-ratelimit-reset-requests: - - X-RATELIMIT-RESET-REQUESTS-XXX - x-ratelimit-reset-tokens: - - X-RATELIMIT-RESET-TOKENS-XXX - x-request-id: - - X-REQUEST-ID-XXX - status: - code: 200 - message: OK -- request: - body: '{"messages":[{"role":"system","content":"Ensure your final answer strictly - adheres to the following OpenAPI schema: {\n \"type\": \"json_schema\",\n \"json_schema\": - {\n \"name\": \"LLMGuardrailResult\",\n \"strict\": true,\n \"schema\": - {\n \"properties\": {\n \"valid\": {\n \"description\": - \"Whether the task output complies with the guardrail\",\n \"title\": - \"Valid\",\n \"type\": \"boolean\"\n },\n \"feedback\": - {\n \"anyOf\": [\n {\n \"type\": \"string\"\n },\n {\n \"type\": - \"null\"\n }\n ],\n \"default\": null,\n \"description\": - \"A feedback about the task output if it is not valid\",\n \"title\": - \"Feedback\"\n }\n },\n \"required\": [\n \"valid\",\n \"feedback\"\n ],\n \"title\": - \"LLMGuardrailResult\",\n \"type\": \"object\",\n \"additionalProperties\": - false\n }\n }\n}\n\nDo not include the OpenAPI schema in the final output. - Ensure the final output does not include any code block markers like ```json - or ```python."},{"role":"user","content":"The Task result complies with the - guardrail as it contains 22 words, which is less than the 500-word limit. Therefore, - the output is valid."}],"model":"gpt-4o","response_format":{"type":"json_schema","json_schema":{"schema":{"properties":{"valid":{"description":"Whether - the task output complies with the guardrail","title":"Valid","type":"boolean"},"feedback":{"anyOf":[{"type":"string"},{"type":"null"}],"description":"A - feedback about the task output if it is not valid","title":"Feedback"}},"required":["valid","feedback"],"title":"LLMGuardrailResult","type":"object","additionalProperties":false},"name":"LLMGuardrailResult","strict":true}},"stream":false}' - headers: - User-Agent: - - X-USER-AGENT-XXX - accept: - - application/json - accept-encoding: - - ACCEPT-ENCODING-XXX - authorization: - - AUTHORIZATION-XXX - connection: - - keep-alive - content-length: - - '1864' - content-type: - - application/json - cookie: - - COOKIE-XXX - host: - - api.openai.com - x-stainless-arch: - - X-STAINLESS-ARCH-XXX - x-stainless-async: - - 'false' x-stainless-helper-method: - beta.chat.completions.parse x-stainless-lang: @@ -456,22 +175,22 @@ interactions: x-stainless-runtime: - CPython x-stainless-runtime-version: - - 3.13.3 + - 3.13.12 method: POST uri: https://api.openai.com/v1/chat/completions response: body: - string: "{\n \"id\": \"chatcmpl-Cy7yMAjNYSCz2foZPEcSVCuapzF8y\",\n \"object\": - \"chat.completion\",\n \"created\": 1768446362,\n \"model\": \"gpt-4o-2024-08-06\",\n + string: "{\n \"id\": \"chatcmpl-DDGAO7HbV6K3Iy0lQA058TOzTDoVa\",\n \"object\": + \"chat.completion\",\n \"created\": 1772052780,\n \"model\": \"gpt-4o-2024-08-06\",\n \ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"{\\\"valid\\\":true,\\\"feedback\\\":null}\",\n \ \"refusal\": null,\n \"annotations\": []\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": - 369,\n \"completion_tokens\": 9,\n \"total_tokens\": 378,\n \"prompt_tokens_details\": + 290,\n \"completion_tokens\": 9,\n \"total_tokens\": 299,\n \"prompt_tokens_details\": {\n \"cached_tokens\": 0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\": {\n \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\": 0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\": - \"default\",\n \"system_fingerprint\": \"fp_a0e9480a2f\"\n}\n" + \"default\",\n \"system_fingerprint\": \"fp_1d6b4c17c3\"\n}\n" headers: CF-RAY: - CF-RAY-XXX @@ -480,7 +199,7 @@ interactions: Content-Type: - application/json Date: - - Thu, 15 Jan 2026 03:06:03 GMT + - Wed, 25 Feb 2026 20:53:01 GMT Server: - cloudflare Strict-Transport-Security: @@ -495,18 +214,16 @@ interactions: - h3=":443"; ma=86400 cf-cache-status: - DYNAMIC - content-length: - - '837' openai-organization: - OPENAI-ORG-XXX openai-processing-ms: - - '413' + - '386' openai-project: - OPENAI-PROJECT-XXX openai-version: - '2020-10-01' - x-envoy-upstream-service-time: - - '650' + set-cookie: + - SET-COOKIE-XXX x-openai-proxy-wasm: - v0.1 x-ratelimit-limit-requests: diff --git a/lib/crewai/tests/cassettes/utilities/test_crew_emits_test_kickoff_type_event.yaml b/lib/crewai/tests/cassettes/utilities/test_crew_emits_test_kickoff_type_event.yaml index 89b172a9e..c103d8b5b 100644 --- a/lib/crewai/tests/cassettes/utilities/test_crew_emits_test_kickoff_type_event.yaml +++ b/lib/crewai/tests/cassettes/utilities/test_crew_emits_test_kickoff_type_event.yaml @@ -1,266 +1,240 @@ interactions: - request: - body: null - headers: {} - method: GET - uri: https://pypi.org/pypi/agentops/json + body: '{"messages":[{"role":"system","content":"You are base_agent. You are a + helpful assistant that just says hi\nYour personal goal is: Just say hi"},{"role":"user","content":"\nCurrent + Task: Just say hi\n\nThis is the expected criteria for your final answer: hi\nyou + MUST return the actual complete content as the final answer, not a summary.\n\nProvide + your complete response:"}],"model":"gpt-4o-mini"}' + headers: + User-Agent: + - X-USER-AGENT-XXX + accept: + - application/json + accept-encoding: + - ACCEPT-ENCODING-XXX + authorization: + - AUTHORIZATION-XXX + connection: + - keep-alive + content-length: + - '399' + content-type: + - application/json + host: + - api.openai.com + x-stainless-arch: + - X-STAINLESS-ARCH-XXX + x-stainless-async: + - 'false' + x-stainless-lang: + - python + x-stainless-os: + - X-STAINLESS-OS-XXX + x-stainless-package-version: + - 1.83.0 + x-stainless-read-timeout: + - X-STAINLESS-READ-TIMEOUT-XXX + x-stainless-retry-count: + - '0' + x-stainless-runtime: + - CPython + x-stainless-runtime-version: + - 3.13.12 + method: POST + uri: https://api.openai.com/v1/chat/completions response: body: - string: '{"info":{"author":null,"author_email":"Alex Reibman , Shawn Qiu , Braelyn Boynton , Howard Gil , Constantin Teodorescu , Pratyush Shukla , Travis Dent , Dwij Patel ","bugtrack_url":null,"classifiers":["License :: OSI Approved :: MIT License","Operating System :: OS Independent","Programming Language :: Python :: 3","Programming Language :: Python :: 3.10","Programming Language :: Python :: 3.11","Programming Language :: Python :: 3.12","Programming Language :: Python :: 3.13","Programming Language :: Python :: 3.9"],"description":"","description_content_type":null,"docs_url":null,"download_url":null,"downloads":{"last_day":-1,"last_month":-1,"last_week":-1},"dynamic":null,"home_page":null,"keywords":null,"license":null,"license_expression":null,"license_files":["LICENSE"],"maintainer":null,"maintainer_email":null,"name":"agentops","package_url":"https://pypi.org/project/agentops/","platform":null,"project_url":"https://pypi.org/project/agentops/","project_urls":{"Homepage":"https://github.com/AgentOps-AI/agentops","Issues":"https://github.com/AgentOps-AI/agentops/issues"},"provides_extra":null,"release_url":"https://pypi.org/project/agentops/0.4.12/","requires_dist":["httpx<0.29.0,>=0.24.0","opentelemetry-api==1.29.0; - python_version < \"3.10\"","opentelemetry-api>1.29.0; python_version >= \"3.10\"","opentelemetry-exporter-otlp-proto-http==1.29.0; python_version < \"3.10\"","opentelemetry-exporter-otlp-proto-http>1.29.0; python_version >= \"3.10\"","opentelemetry-instrumentation==0.50b0; python_version < \"3.10\"","opentelemetry-instrumentation>=0.50b0; python_version >= \"3.10\"","opentelemetry-sdk==1.29.0; python_version < \"3.10\"","opentelemetry-sdk>1.29.0; python_version >= \"3.10\"","opentelemetry-semantic-conventions==0.50b0; python_version < \"3.10\"","opentelemetry-semantic-conventions>=0.50b0; python_version >= \"3.10\"","ordered-set<5.0.0,>=4.0.0","packaging<25.0,>=21.0","psutil<6.1.0,>=5.9.8","pyyaml<7.0,>=5.3","requests<3.0.0,>=2.0.0","termcolor<2.5.0,>=2.3.0","wrapt<2.0.0,>=1.0.0"],"requires_python":"<3.14,>=3.9","summary":"Observability and DevTool Platform for AI Agents","version":"0.4.12","yanked":false,"yanked_reason":null},"last_serial":29075100,"releases":{"0.0.1":[{"comment_text":"","digests":{"blake2b_256":"9b4641d084346e88671acc02e3a0049d3e0925fe99edd88c8b82700dc3c04d01","md5":"2b491f3b3dd01edd4ee37c361087bb46","sha256":"f2cb9d59a0413e7977a44a23dbd6a9d89cda5309b63ed08f5c346c7488acf645"},"downloads":-1,"filename":"agentops-0.0.1-py3-none-any.whl","has_sig":false,"md5_digest":"2b491f3b3dd01edd4ee37c361087bb46","packagetype":"bdist_wheel","python_version":"py3","requires_python":">=3.7","size":10328,"upload_time":"2023-08-21T18:33:47","upload_time_iso_8601":"2023-08-21T18:33:47.827866Z","url":"https://files.pythonhosted.org/packages/9b/46/41d084346e88671acc02e3a0049d3e0925fe99edd88c8b82700dc3c04d01/agentops-0.0.1-py3-none-any.whl","yanked":false,"yanked_reason":null},{"comment_text":"","digests":{"blake2b_256":"b280bf609d98778499bd42df723100a8e910d9b9827cbd00b804cf0b13bb3c87","md5":"ff218fc16d45cf72f73d50ee9a0afe82","sha256":"5c3d4311b9dde0c71cb475ec99d2963a71604c78d468b333f55e81364f4fe79e"},"downloads":-1,"filename":"agentops-0.0.1.tar.gz","has_sig":false,"md5_digest":"ff218fc16d45cf72f73d50ee9a0afe82","packagetype":"sdist","python_version":"source","requires_python":">=3.7","size":11452,"upload_time":"2023-08-21T18:33:49","upload_time_iso_8601":"2023-08-21T18:33:49.613830Z","url":"https://files.pythonhosted.org/packages/b2/80/bf609d98778499bd42df723100a8e910d9b9827cbd00b804cf0b13bb3c87/agentops-0.0.1.tar.gz","yanked":false,"yanked_reason":null}],"0.0.10":[{"comment_text":"","digests":{"blake2b_256":"92933862af53105332cb524db237138d3284b5d6abcc7df5fd4406e382372d94","md5":"8bdea319b5579775eb88efac72e70cd6","sha256":"e8a333567458c1df35538d626bc596f3ba7b8fa2aac5015bc378f3f7f8850669"},"downloads":-1,"filename":"agentops-0.0.10-py3-none-any.whl","has_sig":false,"md5_digest":"8bdea319b5579775eb88efac72e70cd6","packagetype":"bdist_wheel","python_version":"py3","requires_python":">=3.7","size":14752,"upload_time":"2023-12-16T01:40:40","upload_time_iso_8601":"2023-12-16T01:40:40.867657Z","url":"https://files.pythonhosted.org/packages/92/93/3862af53105332cb524db237138d3284b5d6abcc7df5fd4406e382372d94/agentops-0.0.10-py3-none-any.whl","yanked":false,"yanked_reason":null},{"comment_text":"","digests":{"blake2b_256":"c63136b1f2e508b67f92ddb5f51f2acf5abdf2bf4b32d5b355d8018b368dc854","md5":"87bdcd4d7469d22ce922234d4f0b2b98","sha256":"5fbc567bece7b218fc35ce70d208e88e89bb399a9dbf84ab7ad59a2aa559648c"},"downloads":-1,"filename":"agentops-0.0.10.tar.gz","has_sig":false,"md5_digest":"87bdcd4d7469d22ce922234d4f0b2b98","packagetype":"sdist","python_version":"source","requires_python":">=3.7","size":15099,"upload_time":"2023-12-16T01:40:42","upload_time_iso_8601":"2023-12-16T01:40:42.281826Z","url":"https://files.pythonhosted.org/packages/c6/31/36b1f2e508b67f92ddb5f51f2acf5abdf2bf4b32d5b355d8018b368dc854/agentops-0.0.10.tar.gz","yanked":false,"yanked_reason":null}],"0.0.11":[{"comment_text":"","digests":{"blake2b_256":"7125ed114f918332cda824092f620b1002fd76ab6b538dd83711b31c93907139","md5":"83ba7e621f01412144aa38306fc1e04c","sha256":"cb80823e065d17dc26bdc8fe951ea7e04b23677ef2b4da939669c6fe1b2502bf"},"downloads":-1,"filename":"agentops-0.0.11-py3-none-any.whl","has_sig":false,"md5_digest":"83ba7e621f01412144aa38306fc1e04c","packagetype":"bdist_wheel","python_version":"py3","requires_python":">=3.7","size":16627,"upload_time":"2023-12-21T19:50:28","upload_time_iso_8601":"2023-12-21T19:50:28.595886Z","url":"https://files.pythonhosted.org/packages/71/25/ed114f918332cda824092f620b1002fd76ab6b538dd83711b31c93907139/agentops-0.0.11-py3-none-any.whl","yanked":false,"yanked_reason":null},{"comment_text":"","digests":{"blake2b_256":"9e037750b04398cda2548bbf3d84ce554c4009592095c060c4904e773f3a43da","md5":"5bbb120cc9a5f5ff6fb5dd45691ba279","sha256":"cbf0f39768d47e32be448a3ff3ded665fce64ff8a90c0e10692fd7a3ab4790ee"},"downloads":-1,"filename":"agentops-0.0.11.tar.gz","has_sig":false,"md5_digest":"5bbb120cc9a5f5ff6fb5dd45691ba279","packagetype":"sdist","python_version":"source","requires_python":">=3.7","size":16794,"upload_time":"2023-12-21T19:50:29","upload_time_iso_8601":"2023-12-21T19:50:29.881561Z","url":"https://files.pythonhosted.org/packages/9e/03/7750b04398cda2548bbf3d84ce554c4009592095c060c4904e773f3a43da/agentops-0.0.11.tar.gz","yanked":false,"yanked_reason":null}],"0.0.12":[{"comment_text":"","digests":{"blake2b_256":"adf5cc3e93b2328532ea80b8b36450b8b48a8199ebbe1f75ebb490e57a926b88","md5":"694ba49ca8841532039bdf8dc0250b85","sha256":"9a2c773efbe3353f60d1b86da12333951dad288ba54839615a53b57e5965bea8"},"downloads":-1,"filename":"agentops-0.0.12-py3-none-any.whl","has_sig":false,"md5_digest":"694ba49ca8841532039bdf8dc0250b85","packagetype":"bdist_wheel","python_version":"py3","requires_python":">=3.7","size":18602,"upload_time":"2024-01-03T03:47:07","upload_time_iso_8601":"2024-01-03T03:47:07.184203Z","url":"https://files.pythonhosted.org/packages/ad/f5/cc3e93b2328532ea80b8b36450b8b48a8199ebbe1f75ebb490e57a926b88/agentops-0.0.12-py3-none-any.whl","yanked":false,"yanked_reason":null},{"comment_text":"","digests":{"blake2b_256":"7eb0633ecd30c74a0613c7330ececf0303286622ce429f08ce0daa9ee8cc4ecf","md5":"025daef9622472882a1fa58b6c1fddb5","sha256":"fbb4c38711a7dff3ab08004591451b5a5c33bea5e496fa71fac668c7284513d2"},"downloads":-1,"filename":"agentops-0.0.12.tar.gz","has_sig":false,"md5_digest":"025daef9622472882a1fa58b6c1fddb5","packagetype":"sdist","python_version":"source","requires_python":">=3.7","size":19826,"upload_time":"2024-01-03T03:47:08","upload_time_iso_8601":"2024-01-03T03:47:08.942790Z","url":"https://files.pythonhosted.org/packages/7e/b0/633ecd30c74a0613c7330ececf0303286622ce429f08ce0daa9ee8cc4ecf/agentops-0.0.12.tar.gz","yanked":false,"yanked_reason":null}],"0.0.13":[{"comment_text":"","digests":{"blake2b_256":"3a0f9c1500adb4191531374db4d7920c51aba92c5472d13d172108e881c36948","md5":"f0a3b78c15af3ab467778f94fb50bf4a","sha256":"3379a231f37a375bda421114a5626643263e84ce951503d0bdff8411149946e0"},"downloads":-1,"filename":"agentops-0.0.13-py3-none-any.whl","has_sig":false,"md5_digest":"f0a3b78c15af3ab467778f94fb50bf4a","packagetype":"bdist_wheel","python_version":"py3","requires_python":">=3.7","size":18709,"upload_time":"2024-01-07T08:57:57","upload_time_iso_8601":"2024-01-07T08:57:57.456769Z","url":"https://files.pythonhosted.org/packages/3a/0f/9c1500adb4191531374db4d7920c51aba92c5472d13d172108e881c36948/agentops-0.0.13-py3-none-any.whl","yanked":false,"yanked_reason":null},{"comment_text":"","digests":{"blake2b_256":"cbf9a3824bd30d7107aaca8d409165c0a3574a879efd7ca0fea755e903623b61","md5":"0ebceb6aad82c0622adcd4c2633fc677","sha256":"5e6adf68c2a533496648ea3fabb6e791f39ce810d18dbc1354d118b195fd8556"},"downloads":-1,"filename":"agentops-0.0.13.tar.gz","has_sig":false,"md5_digest":"0ebceb6aad82c0622adcd4c2633fc677","packagetype":"sdist","python_version":"source","requires_python":">=3.7","size":19933,"upload_time":"2024-01-07T08:57:59","upload_time_iso_8601":"2024-01-07T08:57:59.146933Z","url":"https://files.pythonhosted.org/packages/cb/f9/a3824bd30d7107aaca8d409165c0a3574a879efd7ca0fea755e903623b61/agentops-0.0.13.tar.gz","yanked":false,"yanked_reason":null}],"0.0.14":[{"comment_text":"","digests":{"blake2b_256":"252b1d8ee3b4ab02215eb1a52865a9f2c209d6d4cbf4a3444fb7faf23b02ca66","md5":"a8ba77b0ec0d25072b2e0535a135cc40","sha256":"d5bb4661642daf8fc63a257ef0f04ccc5c79a73e73d57ea04190e74d9a3e6df9"},"downloads":-1,"filename":"agentops-0.0.14-py3-none-any.whl","has_sig":false,"md5_digest":"a8ba77b0ec0d25072b2e0535a135cc40","packagetype":"bdist_wheel","python_version":"py3","requires_python":">=3.7","size":18710,"upload_time":"2024-01-08T21:52:28","upload_time_iso_8601":"2024-01-08T21:52:28.340899Z","url":"https://files.pythonhosted.org/packages/25/2b/1d8ee3b4ab02215eb1a52865a9f2c209d6d4cbf4a3444fb7faf23b02ca66/agentops-0.0.14-py3-none-any.whl","yanked":false,"yanked_reason":null},{"comment_text":"","digests":{"blake2b_256":"bf3a1fdf85563c47c2fc6571a1406aecb772f644d53a2adabf4981012971587a","md5":"1ecf7177ab57738c6663384de20887e5","sha256":"c54cee1c9ed1b5b7829fd80d5d01278b1efb50e977e5a890627f4688d0f2afb2"},"downloads":-1,"filename":"agentops-0.0.14.tar.gz","has_sig":false,"md5_digest":"1ecf7177ab57738c6663384de20887e5","packagetype":"sdist","python_version":"source","requires_python":">=3.7","size":19932,"upload_time":"2024-01-08T21:52:29","upload_time_iso_8601":"2024-01-08T21:52:29.988596Z","url":"https://files.pythonhosted.org/packages/bf/3a/1fdf85563c47c2fc6571a1406aecb772f644d53a2adabf4981012971587a/agentops-0.0.14.tar.gz","yanked":false,"yanked_reason":null}],"0.0.15":[{"comment_text":"","digests":{"blake2b_256":"0c5374cbe5c78db9faa7c939d1a91eff111c4d3f13f4d8d18920ddd48f89f335","md5":"c4528a66151e76c7b1abdcac3c3eaf52","sha256":"aa8034dc9a0e9e56014a06fac521fc2a63a968d34f73e4d4c9bef4b0e87f8241"},"downloads":-1,"filename":"agentops-0.0.15-py3-none-any.whl","has_sig":false,"md5_digest":"c4528a66151e76c7b1abdcac3c3eaf52","packagetype":"bdist_wheel","python_version":"py3","requires_python":">=3.7","size":18734,"upload_time":"2024-01-23T08:43:24","upload_time_iso_8601":"2024-01-23T08:43:24.651479Z","url":"https://files.pythonhosted.org/packages/0c/53/74cbe5c78db9faa7c939d1a91eff111c4d3f13f4d8d18920ddd48f89f335/agentops-0.0.15-py3-none-any.whl","yanked":false,"yanked_reason":null},{"comment_text":"","digests":{"blake2b_256":"da56c7d8189f4accc182be6729bc44a8006d981173e721ff4751ab784bbadfb3","md5":"cd27bff6c943c6fcbed33ed8280ab5ea","sha256":"71b0e048d2f1b86744105509436cbb6fa51e6b418a50a8253849dc6cdeda6cca"},"downloads":-1,"filename":"agentops-0.0.15.tar.gz","has_sig":false,"md5_digest":"cd27bff6c943c6fcbed33ed8280ab5ea","packagetype":"sdist","python_version":"source","requires_python":">=3.7","size":19985,"upload_time":"2024-01-23T08:43:26","upload_time_iso_8601":"2024-01-23T08:43:26.316265Z","url":"https://files.pythonhosted.org/packages/da/56/c7d8189f4accc182be6729bc44a8006d981173e721ff4751ab784bbadfb3/agentops-0.0.15.tar.gz","yanked":false,"yanked_reason":null}],"0.0.16":[{"comment_text":"","digests":{"blake2b_256":"b694d78d43f49688829cab72b7326db1d9e3f436f71eed113f26d402fefa6856","md5":"657c2cad11b3c8b97469524bff19b916","sha256":"e9633dcbc419a47db8de13bd0dc4f5d55f0a50ef3434ffe8e1f8a3468561bd60"},"downloads":-1,"filename":"agentops-0.0.16-py3-none-any.whl","has_sig":false,"md5_digest":"657c2cad11b3c8b97469524bff19b916","packagetype":"bdist_wheel","python_version":"py3","requires_python":">=3.7","size":18736,"upload_time":"2024-01-23T09:03:05","upload_time_iso_8601":"2024-01-23T09:03:05.799496Z","url":"https://files.pythonhosted.org/packages/b6/94/d78d43f49688829cab72b7326db1d9e3f436f71eed113f26d402fefa6856/agentops-0.0.16-py3-none-any.whl","yanked":false,"yanked_reason":null},{"comment_text":"","digests":{"blake2b_256":"ec353005c98c1e2642d61510a9977c2118d3baa72f50e3c45ef6a341bfd9a3b0","md5":"2f9b28dd0953fdd2da606e19b9131006","sha256":"469588d72734fc6e90c66cf9658613baf2a0b94c933a23cab16820435576c61f"},"downloads":-1,"filename":"agentops-0.0.16.tar.gz","has_sig":false,"md5_digest":"2f9b28dd0953fdd2da606e19b9131006","packagetype":"sdist","python_version":"source","requires_python":">=3.7","size":19986,"upload_time":"2024-01-23T09:03:07","upload_time_iso_8601":"2024-01-23T09:03:07.645949Z","url":"https://files.pythonhosted.org/packages/ec/35/3005c98c1e2642d61510a9977c2118d3baa72f50e3c45ef6a341bfd9a3b0/agentops-0.0.16.tar.gz","yanked":false,"yanked_reason":null}],"0.0.17":[{"comment_text":"","digests":{"blake2b_256":"f3b2eff27fc5373097fc4f4d3d90f4d0fad1c3be7b923a6213750fe1cb022e6e","md5":"20325afd9b9d9633b120b63967d4ae85","sha256":"1a7c8d8fc8821e2e7eedbbe2683e076bfaca3434401b0d1ca6b830bf3230e61e"},"downloads":-1,"filename":"agentops-0.0.17-py3-none-any.whl","has_sig":false,"md5_digest":"20325afd9b9d9633b120b63967d4ae85","packagetype":"bdist_wheel","python_version":"py3","requires_python":">=3.7","size":18827,"upload_time":"2024-01-23T17:12:19","upload_time_iso_8601":"2024-01-23T17:12:19.300806Z","url":"https://files.pythonhosted.org/packages/f3/b2/eff27fc5373097fc4f4d3d90f4d0fad1c3be7b923a6213750fe1cb022e6e/agentops-0.0.17-py3-none-any.whl","yanked":false,"yanked_reason":null},{"comment_text":"","digests":{"blake2b_256":"ac2a2cb7548cce5b009bee9e6f9b46b26df1cca777830231e2d1603b83740053","md5":"4ac65e38fa45946f1d382ce290b904e9","sha256":"cc1e7f796a84c66a29b271d8f0faa4999c152c80195911b817502da002a3ae02"},"downloads":-1,"filename":"agentops-0.0.17.tar.gz","has_sig":false,"md5_digest":"4ac65e38fa45946f1d382ce290b904e9","packagetype":"sdist","python_version":"source","requires_python":">=3.7","size":20063,"upload_time":"2024-01-23T17:12:20","upload_time_iso_8601":"2024-01-23T17:12:20.558647Z","url":"https://files.pythonhosted.org/packages/ac/2a/2cb7548cce5b009bee9e6f9b46b26df1cca777830231e2d1603b83740053/agentops-0.0.17.tar.gz","yanked":false,"yanked_reason":null}],"0.0.18":[{"comment_text":"","digests":{"blake2b_256":"321102c865df2245ab8cfaeb48a72ef7011a7bbbe1553a43791d68295ff7c20d","md5":"ad10ec2bf28bf434d3d2f11500f5a396","sha256":"df241f6a62368aa645d1599bb6885688fba0d49dcc26f97f7f65ab29a6af1a2a"},"downloads":-1,"filename":"agentops-0.0.18-py3-none-any.whl","has_sig":false,"md5_digest":"ad10ec2bf28bf434d3d2f11500f5a396","packagetype":"bdist_wheel","python_version":"py3","requires_python":">=3.7","size":18860,"upload_time":"2024-01-24T04:39:06","upload_time_iso_8601":"2024-01-24T04:39:06.952175Z","url":"https://files.pythonhosted.org/packages/32/11/02c865df2245ab8cfaeb48a72ef7011a7bbbe1553a43791d68295ff7c20d/agentops-0.0.18-py3-none-any.whl","yanked":false,"yanked_reason":null},{"comment_text":"","digests":{"blake2b_256":"7831bd4249dcf9a0cdcad5451ca62aa83187295bb9c16fd1b3034999bff7ceaf","md5":"76dc30c0a2e68f09c0411c23dd5e3a36","sha256":"47e071424247dbbb1b9aaf07ff60a7e376ae01666478d0305d62a9068d61c1c1"},"downloads":-1,"filename":"agentops-0.0.18.tar.gz","has_sig":false,"md5_digest":"76dc30c0a2e68f09c0411c23dd5e3a36","packagetype":"sdist","python_version":"source","requires_python":">=3.7","size":20094,"upload_time":"2024-01-24T04:39:09","upload_time_iso_8601":"2024-01-24T04:39:09.795862Z","url":"https://files.pythonhosted.org/packages/78/31/bd4249dcf9a0cdcad5451ca62aa83187295bb9c16fd1b3034999bff7ceaf/agentops-0.0.18.tar.gz","yanked":false,"yanked_reason":null}],"0.0.19":[{"comment_text":"","digests":{"blake2b_256":"9d48292d743b748eddc01b51747e1dac4b62dea0eb5f240877bae821c0049572","md5":"a26178cdf9d5fc5b466a30e5990c16a1","sha256":"0e663e26aad41bf0288d250685e88130430dd087d03ffc69aa7f43e587921b59"},"downloads":-1,"filename":"agentops-0.0.19-py3-none-any.whl","has_sig":false,"md5_digest":"a26178cdf9d5fc5b466a30e5990c16a1","packagetype":"bdist_wheel","python_version":"py3","requires_python":">=3.7","size":18380,"upload_time":"2024-01-24T07:58:38","upload_time_iso_8601":"2024-01-24T07:58:38.440021Z","url":"https://files.pythonhosted.org/packages/9d/48/292d743b748eddc01b51747e1dac4b62dea0eb5f240877bae821c0049572/agentops-0.0.19-py3-none-any.whl","yanked":false,"yanked_reason":null},{"comment_text":"","digests":{"blake2b_256":"dfe6f3b3fc53b050ec70de947e27227d0ea1e7a75037d082fc5f4d914178d12f","md5":"c62a69951acd19121b059215cf0ddb8b","sha256":"3d46faabf2dad44bd4705279569c76240ab5c71f03f511ba9d363dfd033d453e"},"downloads":-1,"filename":"agentops-0.0.19.tar.gz","has_sig":false,"md5_digest":"c62a69951acd19121b059215cf0ddb8b","packagetype":"sdist","python_version":"source","requires_python":">=3.7","size":19728,"upload_time":"2024-01-24T07:58:41","upload_time_iso_8601":"2024-01-24T07:58:41.352463Z","url":"https://files.pythonhosted.org/packages/df/e6/f3b3fc53b050ec70de947e27227d0ea1e7a75037d082fc5f4d914178d12f/agentops-0.0.19.tar.gz","yanked":false,"yanked_reason":null}],"0.0.2":[{"comment_text":"","digests":{"blake2b_256":"e593e3863d3c61a75e43a347d423f754bc57559989773af6a9c7bc696ff1d6b4","md5":"8ff77b84c32a4e846ce50c6844664b49","sha256":"3bea2bdd8a26c190675aaf2775d97bc2e3c52d7da05c04ae8ec46fed959e0c6e"},"downloads":-1,"filename":"agentops-0.0.2-py3-none-any.whl","has_sig":false,"md5_digest":"8ff77b84c32a4e846ce50c6844664b49","packagetype":"bdist_wheel","python_version":"py3","requires_python":">=3.7","size":10452,"upload_time":"2023-08-28T23:14:23","upload_time_iso_8601":"2023-08-28T23:14:23.488523Z","url":"https://files.pythonhosted.org/packages/e5/93/e3863d3c61a75e43a347d423f754bc57559989773af6a9c7bc696ff1d6b4/agentops-0.0.2-py3-none-any.whl","yanked":false,"yanked_reason":null},{"comment_text":"","digests":{"blake2b_256":"82dbea7088c3ba71d9882a8d09d896d8529100f3103d1fe58ff4b890f9d616f1","md5":"02c4fed5ca014de524e5c1dfe3ec2dd2","sha256":"dc183d28965a9514cb33d916b29b3159189f5be64c4a7d943be0cad1a00379f9"},"downloads":-1,"filename":"agentops-0.0.2.tar.gz","has_sig":false,"md5_digest":"02c4fed5ca014de524e5c1dfe3ec2dd2","packagetype":"sdist","python_version":"source","requires_python":">=3.7","size":11510,"upload_time":"2023-08-28T23:14:24","upload_time_iso_8601":"2023-08-28T23:14:24.882664Z","url":"https://files.pythonhosted.org/packages/82/db/ea7088c3ba71d9882a8d09d896d8529100f3103d1fe58ff4b890f9d616f1/agentops-0.0.2.tar.gz","yanked":false,"yanked_reason":null}],"0.0.20":[{"comment_text":"","digests":{"blake2b_256":"ad68d8cc6d631618e04ec6988d0c3f4462a74b0b5849719b8373c2470cf9d533","md5":"09b2866043abc3e5cb5dfc17b80068cb","sha256":"ba20fc48902434858f28e3c4a7febe56d275a28bd33378868e7fcde2f53f2430"},"downloads":-1,"filename":"agentops-0.0.20-py3-none-any.whl","has_sig":false,"md5_digest":"09b2866043abc3e5cb5dfc17b80068cb","packagetype":"bdist_wheel","python_version":"py3","requires_python":">=3.7","size":18367,"upload_time":"2024-01-25T07:12:48","upload_time_iso_8601":"2024-01-25T07:12:48.514177Z","url":"https://files.pythonhosted.org/packages/ad/68/d8cc6d631618e04ec6988d0c3f4462a74b0b5849719b8373c2470cf9d533/agentops-0.0.20-py3-none-any.whl","yanked":false,"yanked_reason":null},{"comment_text":"","digests":{"blake2b_256":"0ba37435a8ce7125c7d75b931a373a188acf1c9e793be28db1b5c5e5a57d7a10","md5":"fb700178ad44a4697b696ecbd28d115c","sha256":"d50623b03b410c8c88718c29ea271304681e1305b5c05ba824edb92d18aab4f8"},"downloads":-1,"filename":"agentops-0.0.20.tar.gz","has_sig":false,"md5_digest":"fb700178ad44a4697b696ecbd28d115c","packagetype":"sdist","python_version":"source","requires_python":">=3.7","size":19707,"upload_time":"2024-01-25T07:12:49","upload_time_iso_8601":"2024-01-25T07:12:49.915462Z","url":"https://files.pythonhosted.org/packages/0b/a3/7435a8ce7125c7d75b931a373a188acf1c9e793be28db1b5c5e5a57d7a10/agentops-0.0.20.tar.gz","yanked":false,"yanked_reason":null}],"0.0.21":[{"comment_text":"","digests":{"blake2b_256":"9182ceb8c12e05c0e56ea6c5ba7395c57764ffc5a8134fd045b247793873c172","md5":"ce428cf01a0c1066d3f1f3c8ca6b4f9b","sha256":"fdefe50d945ad669b33c90bf526f9af0e7dc4792b4443aeb907b0a36de2be186"},"downloads":-1,"filename":"agentops-0.0.21-py3-none-any.whl","has_sig":false,"md5_digest":"ce428cf01a0c1066d3f1f3c8ca6b4f9b","packagetype":"bdist_wheel","python_version":"py3","requires_python":">=3.7","size":18483,"upload_time":"2024-02-22T03:07:14","upload_time_iso_8601":"2024-02-22T03:07:14.032143Z","url":"https://files.pythonhosted.org/packages/91/82/ceb8c12e05c0e56ea6c5ba7395c57764ffc5a8134fd045b247793873c172/agentops-0.0.21-py3-none-any.whl","yanked":false,"yanked_reason":null},{"comment_text":"","digests":{"blake2b_256":"acbb361e3d7ed85fc4207ffbbe44ddfa7ee3b8f96b76c3712d4153d63ebb45e2","md5":"360f00d330fa37ad10f687906e31e219","sha256":"ec10f8e64c553a1c400f1d5c792c3daef383cd718747cabb8e5abc9ef685f25d"},"downloads":-1,"filename":"agentops-0.0.21.tar.gz","has_sig":false,"md5_digest":"360f00d330fa37ad10f687906e31e219","packagetype":"sdist","python_version":"source","requires_python":">=3.7","size":19787,"upload_time":"2024-02-22T03:07:15","upload_time_iso_8601":"2024-02-22T03:07:15.546312Z","url":"https://files.pythonhosted.org/packages/ac/bb/361e3d7ed85fc4207ffbbe44ddfa7ee3b8f96b76c3712d4153d63ebb45e2/agentops-0.0.21.tar.gz","yanked":false,"yanked_reason":null}],"0.0.22":[{"comment_text":"","digests":{"blake2b_256":"b9da29a808d5bd3045f80b5652737e94695056b4a7cf7830ed7de037b1fe941c","md5":"d9e04a68f0b143432b9e34341e4f0a17","sha256":"fbcd962ff08a2e216637341c36c558be74368fbfda0b2408e55388e4c96474ca"},"downloads":-1,"filename":"agentops-0.0.22-py3-none-any.whl","has_sig":false,"md5_digest":"d9e04a68f0b143432b9e34341e4f0a17","packagetype":"bdist_wheel","python_version":"py3","requires_python":">=3.7","size":18485,"upload_time":"2024-02-29T21:16:00","upload_time_iso_8601":"2024-02-29T21:16:00.124986Z","url":"https://files.pythonhosted.org/packages/b9/da/29a808d5bd3045f80b5652737e94695056b4a7cf7830ed7de037b1fe941c/agentops-0.0.22-py3-none-any.whl","yanked":false,"yanked_reason":null},{"comment_text":"","digests":{"blake2b_256":"4d842d1c5d80c69e6c9b8f3fd925c2f2fd084ad6eb29d93fdeadbdeca79e5eda","md5":"8f3b286fd01c2c43f7f7b1e4aebe3594","sha256":"397544ce90474fee59f1e8561c92f4923e9034842be593f1ac41437c5fca5841"},"downloads":-1,"filename":"agentops-0.0.22.tar.gz","has_sig":false,"md5_digest":"8f3b286fd01c2c43f7f7b1e4aebe3594","packagetype":"sdist","python_version":"source","requires_python":">=3.7","size":19784,"upload_time":"2024-02-29T21:16:01","upload_time_iso_8601":"2024-02-29T21:16:01.909583Z","url":"https://files.pythonhosted.org/packages/4d/84/2d1c5d80c69e6c9b8f3fd925c2f2fd084ad6eb29d93fdeadbdeca79e5eda/agentops-0.0.22.tar.gz","yanked":false,"yanked_reason":null}],"0.0.3":[{"comment_text":"","digests":{"blake2b_256":"324eda261865c2042eeb5da9827a350760e435896855d5480b8f3136212c3f65","md5":"07a9f9f479a14e65b82054a145514e8d","sha256":"35351701e3caab900243771bda19d6613bdcb84cc9ef2e1adde431a775c09af8"},"downloads":-1,"filename":"agentops-0.0.3-py3-none-any.whl","has_sig":false,"md5_digest":"07a9f9f479a14e65b82054a145514e8d","packagetype":"bdist_wheel","python_version":"py3","requires_python":">=3.7","size":11872,"upload_time":"2023-09-13T23:03:34","upload_time_iso_8601":"2023-09-13T23:03:34.300564Z","url":"https://files.pythonhosted.org/packages/32/4e/da261865c2042eeb5da9827a350760e435896855d5480b8f3136212c3f65/agentops-0.0.3-py3-none-any.whl","yanked":false,"yanked_reason":null},{"comment_text":"","digests":{"blake2b_256":"643485e455d4f411b56bef2a99c40e32f35f456c93deda0a3915231f1da92e56","md5":"c637ee3cfa358b65ed14cfc20d5f803f","sha256":"45a57492e4072f3f27b5e851f6e501b54c796f6ace5f65ecf70e51dbe18ca1a8"},"downloads":-1,"filename":"agentops-0.0.3.tar.gz","has_sig":false,"md5_digest":"c637ee3cfa358b65ed14cfc20d5f803f","packagetype":"sdist","python_version":"source","requires_python":">=3.7","size":12455,"upload_time":"2023-09-13T23:03:35","upload_time_iso_8601":"2023-09-13T23:03:35.513682Z","url":"https://files.pythonhosted.org/packages/64/34/85e455d4f411b56bef2a99c40e32f35f456c93deda0a3915231f1da92e56/agentops-0.0.3.tar.gz","yanked":false,"yanked_reason":null}],"0.0.4":[{"comment_text":"","digests":{"blake2b_256":"20cc12cf2391854ed588eaf6cdc87f60048f84e8dc7d15792850b7e90a0406b8","md5":"7a3c11004517e22dc7cde83cf6d8d5e8","sha256":"5a5cdcbe6e32c59237521182b83768e650b4519416b42f4e13929a115a0f20ee"},"downloads":-1,"filename":"agentops-0.0.4-py3-none-any.whl","has_sig":false,"md5_digest":"7a3c11004517e22dc7cde83cf6d8d5e8","packagetype":"bdist_wheel","python_version":"py3","requires_python":">=3.7","size":13520,"upload_time":"2023-09-22T09:23:52","upload_time_iso_8601":"2023-09-22T09:23:52.896099Z","url":"https://files.pythonhosted.org/packages/20/cc/12cf2391854ed588eaf6cdc87f60048f84e8dc7d15792850b7e90a0406b8/agentops-0.0.4-py3-none-any.whl","yanked":false,"yanked_reason":null},{"comment_text":"","digests":{"blake2b_256":"98d2d9f9932d17711dd5d98af674c868686bdbdd9aaae9b8d69e9eecfd4c68f4","md5":"712d3bc3b28703963f8f398845b1d17a","sha256":"97743c6420bc5ba2655ac690041d5f5732fb950130cf61ab25ef6d44be6ecfb2"},"downloads":-1,"filename":"agentops-0.0.4.tar.gz","has_sig":false,"md5_digest":"712d3bc3b28703963f8f398845b1d17a","packagetype":"sdist","python_version":"source","requires_python":">=3.7","size":14050,"upload_time":"2023-09-22T09:23:54","upload_time_iso_8601":"2023-09-22T09:23:54.315467Z","url":"https://files.pythonhosted.org/packages/98/d2/d9f9932d17711dd5d98af674c868686bdbdd9aaae9b8d69e9eecfd4c68f4/agentops-0.0.4.tar.gz","yanked":false,"yanked_reason":null}],"0.0.5":[{"comment_text":"","digests":{"blake2b_256":"e900cd903074a01932ded9a05dac7849a16c5850ed20c027b954b1eccfba54c1","md5":"1bd4fd6cca14dac4947ecc6c4e3fe0a1","sha256":"e39e1051ba8c58f222f3495196eb939ccc53f04bd279372ae01e694973dd25d6"},"downloads":-1,"filename":"agentops-0.0.5-py3-none-any.whl","has_sig":false,"md5_digest":"1bd4fd6cca14dac4947ecc6c4e3fe0a1","packagetype":"bdist_wheel","python_version":"py3","requires_python":">=3.7","size":14107,"upload_time":"2023-10-07T00:22:48","upload_time_iso_8601":"2023-10-07T00:22:48.714074Z","url":"https://files.pythonhosted.org/packages/e9/00/cd903074a01932ded9a05dac7849a16c5850ed20c027b954b1eccfba54c1/agentops-0.0.5-py3-none-any.whl","yanked":false,"yanked_reason":null},{"comment_text":"","digests":{"blake2b_256":"08d5c29068ce4df9c85865b45e1cdb7be1df06e54fce087fad18ec390a7aea54","md5":"4d8fc5553e3199fe24d6118337884a2b","sha256":"8f3662e600ba57e9a102c6bf86a6a1e16c0e53e1f38a84fa1b9c01cc07ca4990"},"downloads":-1,"filename":"agentops-0.0.5.tar.gz","has_sig":false,"md5_digest":"4d8fc5553e3199fe24d6118337884a2b","packagetype":"sdist","python_version":"source","requires_python":">=3.7","size":14724,"upload_time":"2023-10-07T00:22:50","upload_time_iso_8601":"2023-10-07T00:22:50.304226Z","url":"https://files.pythonhosted.org/packages/08/d5/c29068ce4df9c85865b45e1cdb7be1df06e54fce087fad18ec390a7aea54/agentops-0.0.5.tar.gz","yanked":false,"yanked_reason":null}],"0.0.6":[{"comment_text":"","digests":{"blake2b_256":"2f5b5f3bd8a5b2d96b6417fd4a3fc72ed484e3a4ffacac49035f17bb8df1dd5b","md5":"b7e701ff7953ecca01ceec3a6b9374b2","sha256":"05dea1d06f8f8d06a8f460d18d302febe91f4dad2e3fc0088d05b7017765f3b6"},"downloads":-1,"filename":"agentops-0.0.6-py3-none-any.whl","has_sig":false,"md5_digest":"b7e701ff7953ecca01ceec3a6b9374b2","packagetype":"bdist_wheel","python_version":"py3","requires_python":">=3.7","size":14236,"upload_time":"2023-10-27T06:56:14","upload_time_iso_8601":"2023-10-27T06:56:14.029277Z","url":"https://files.pythonhosted.org/packages/2f/5b/5f3bd8a5b2d96b6417fd4a3fc72ed484e3a4ffacac49035f17bb8df1dd5b/agentops-0.0.6-py3-none-any.whl","yanked":false,"yanked_reason":null},{"comment_text":"","digests":{"blake2b_256":"4af43743bf40518545c8906687038e5717b1bd33db7ba300a084ec4f6c9c59e0","md5":"0a78dcafcbc6292cf0823181cdc226a7","sha256":"0057cb5d6dc0dd2c444f3371faef40c844a1510700b31824a4fccf5302713361"},"downloads":-1,"filename":"agentops-0.0.6.tar.gz","has_sig":false,"md5_digest":"0a78dcafcbc6292cf0823181cdc226a7","packagetype":"sdist","python_version":"source","requires_python":">=3.7","size":14785,"upload_time":"2023-10-27T06:56:15","upload_time_iso_8601":"2023-10-27T06:56:15.069192Z","url":"https://files.pythonhosted.org/packages/4a/f4/3743bf40518545c8906687038e5717b1bd33db7ba300a084ec4f6c9c59e0/agentops-0.0.6.tar.gz","yanked":false,"yanked_reason":null}],"0.0.7":[{"comment_text":"","digests":{"blake2b_256":"3cb1d15c39bbc95f66c64d01cca304f9b4b0c3503509ad92ef29f926c9163599","md5":"f494f6c256899103a80666be68d136ad","sha256":"6984429ca1a9013fd4386105516cb36a46dd7078f7ac81e0a4701f1700bd25b5"},"downloads":-1,"filename":"agentops-0.0.7-py3-none-any.whl","has_sig":false,"md5_digest":"f494f6c256899103a80666be68d136ad","packagetype":"bdist_wheel","python_version":"py3","requires_python":">=3.7","size":14370,"upload_time":"2023-11-02T06:37:36","upload_time_iso_8601":"2023-11-02T06:37:36.480189Z","url":"https://files.pythonhosted.org/packages/3c/b1/d15c39bbc95f66c64d01cca304f9b4b0c3503509ad92ef29f926c9163599/agentops-0.0.7-py3-none-any.whl","yanked":false,"yanked_reason":null},{"comment_text":"","digests":{"blake2b_256":"ba709ae02fc635cab51b237dcc3657ec69aac61ee67ea5f903cfae07de19abc8","md5":"b163eaaf9cbafbbd19ec3f91b2b56969","sha256":"a6f36d94a82d8e481b406f040790cefd4d939f07108737c696327d97c0ccdaf4"},"downloads":-1,"filename":"agentops-0.0.7.tar.gz","has_sig":false,"md5_digest":"b163eaaf9cbafbbd19ec3f91b2b56969","packagetype":"sdist","python_version":"source","requires_python":">=3.7","size":14895,"upload_time":"2023-11-02T06:37:37","upload_time_iso_8601":"2023-11-02T06:37:37.698159Z","url":"https://files.pythonhosted.org/packages/ba/70/9ae02fc635cab51b237dcc3657ec69aac61ee67ea5f903cfae07de19abc8/agentops-0.0.7.tar.gz","yanked":false,"yanked_reason":null}],"0.0.8":[{"comment_text":"","digests":{"blake2b_256":"8147fa3ee8807ad961aa50a773b6567e3a624000936d3cc1a578af72d83e02e7","md5":"20cffb5534b4545fa1e8b24a6a24b1da","sha256":"5d50b2ab18a203dbb4555a2cd482dae8df5bf2aa3e771a9758ee28b540330da3"},"downloads":-1,"filename":"agentops-0.0.8-py3-none-any.whl","has_sig":false,"md5_digest":"20cffb5534b4545fa1e8b24a6a24b1da","packagetype":"bdist_wheel","python_version":"py3","requires_python":">=3.7","size":14391,"upload_time":"2023-11-23T06:17:56","upload_time_iso_8601":"2023-11-23T06:17:56.154712Z","url":"https://files.pythonhosted.org/packages/81/47/fa3ee8807ad961aa50a773b6567e3a624000936d3cc1a578af72d83e02e7/agentops-0.0.8-py3-none-any.whl","yanked":false,"yanked_reason":null},{"comment_text":"","digests":{"blake2b_256":"707473dc640a3fecfbe84ab7da230f7c862f72f231514a2a488b43a896146ed6","md5":"bba7e74b58849f15d50f4e1270cbd23f","sha256":"3a625d2acc922d99563ce71c5032b0b3b0db57d1c6fade319cf1bb636608eca0"},"downloads":-1,"filename":"agentops-0.0.8.tar.gz","has_sig":false,"md5_digest":"bba7e74b58849f15d50f4e1270cbd23f","packagetype":"sdist","python_version":"source","requires_python":">=3.7","size":14775,"upload_time":"2023-11-23T06:17:58","upload_time_iso_8601":"2023-11-23T06:17:58.768877Z","url":"https://files.pythonhosted.org/packages/70/74/73dc640a3fecfbe84ab7da230f7c862f72f231514a2a488b43a896146ed6/agentops-0.0.8.tar.gz","yanked":false,"yanked_reason":null}],"0.1.0":[{"comment_text":"","digests":{"blake2b_256":"c2a41dc8456edc9bccc0c560967cfdce23a4d7ab8162946be288b54391d80f7c","md5":"5fb09f82b7eeb270c6644dcd3656953f","sha256":"b480fd51fbffc76ae13bb885c2adb1236a7d3b0095b4dafb4a992f6e25647433"},"downloads":-1,"filename":"agentops-0.1.0-py3-none-any.whl","has_sig":false,"md5_digest":"5fb09f82b7eeb270c6644dcd3656953f","packagetype":"bdist_wheel","python_version":"py3","requires_python":">=3.7","size":25045,"upload_time":"2024-04-03T02:01:56","upload_time_iso_8601":"2024-04-03T02:01:56.936873Z","url":"https://files.pythonhosted.org/packages/c2/a4/1dc8456edc9bccc0c560967cfdce23a4d7ab8162946be288b54391d80f7c/agentops-0.1.0-py3-none-any.whl","yanked":false,"yanked_reason":null},{"comment_text":"","digests":{"blake2b_256":"a81756443f28de774cb7c863a2856e1b07658a9a772ba86dfb1cfbb19bc08fe3","md5":"b93c602c1d1da5d8f7a2dcdaa70f8e21","sha256":"22d3dc87dedf93b3b78a0dfdef8c685b2f3bff9fbab32016360e298a24d311dc"},"downloads":-1,"filename":"agentops-0.1.0.tar.gz","has_sig":false,"md5_digest":"b93c602c1d1da5d8f7a2dcdaa70f8e21","packagetype":"sdist","python_version":"source","requires_python":">=3.7","size":24685,"upload_time":"2024-04-03T02:01:58","upload_time_iso_8601":"2024-04-03T02:01:58.623055Z","url":"https://files.pythonhosted.org/packages/a8/17/56443f28de774cb7c863a2856e1b07658a9a772ba86dfb1cfbb19bc08fe3/agentops-0.1.0.tar.gz","yanked":false,"yanked_reason":null}],"0.1.0b1":[{"comment_text":"","digests":{"blake2b_256":"c03a329c59f001f50701e9e541775c79304a5ce4ffe34d717b1d2af555362e9e","md5":"7c7e84b3b4448580bf5a7e9c08012477","sha256":"825ab57ac5f7840f5a7f8ac195f4af75ec07a9c0972b17d1a57a595420d06208"},"downloads":-1,"filename":"agentops-0.1.0b1-py3-none-any.whl","has_sig":false,"md5_digest":"7c7e84b3b4448580bf5a7e9c08012477","packagetype":"bdist_wheel","python_version":"py3","requires_python":">=3.7","size":23258,"upload_time":"2024-03-18T18:51:08","upload_time_iso_8601":"2024-03-18T18:51:08.693772Z","url":"https://files.pythonhosted.org/packages/c0/3a/329c59f001f50701e9e541775c79304a5ce4ffe34d717b1d2af555362e9e/agentops-0.1.0b1-py3-none-any.whl","yanked":false,"yanked_reason":null},{"comment_text":"","digests":{"blake2b_256":"026ee44f1d5a49924867475f7d101abe40170c0674b4b395f28ce88552c1ba71","md5":"9cf6699fe45f13f1893c8992405e7261","sha256":"f5ce4b34999fe4b21a4ce3643980253d30f8ea9c55f01d96cd35631355fc7ac3"},"downloads":-1,"filename":"agentops-0.1.0b1.tar.gz","has_sig":false,"md5_digest":"9cf6699fe45f13f1893c8992405e7261","packagetype":"sdist","python_version":"source","requires_python":">=3.7","size":23842,"upload_time":"2024-03-18T18:51:10","upload_time_iso_8601":"2024-03-18T18:51:10.250127Z","url":"https://files.pythonhosted.org/packages/02/6e/e44f1d5a49924867475f7d101abe40170c0674b4b395f28ce88552c1ba71/agentops-0.1.0b1.tar.gz","yanked":false,"yanked_reason":null}],"0.1.0b2":[{"comment_text":"","digests":{"blake2b_256":"6a25e9282f81c3f2615ef6543a0b5ca49dd14b03f311fc5a108ad1aff4f0b720","md5":"1d3e736ef44c0ad8829c50f036ac807b","sha256":"485362b9a68d2327da250f0681b30a9296f0b41e058672b023ae2a8ed924b4d3"},"downloads":-1,"filename":"agentops-0.1.0b2-py3-none-any.whl","has_sig":false,"md5_digest":"1d3e736ef44c0ad8829c50f036ac807b","packagetype":"bdist_wheel","python_version":"py3","requires_python":">=3.7","size":23477,"upload_time":"2024-03-21T23:31:20","upload_time_iso_8601":"2024-03-21T23:31:20.022797Z","url":"https://files.pythonhosted.org/packages/6a/25/e9282f81c3f2615ef6543a0b5ca49dd14b03f311fc5a108ad1aff4f0b720/agentops-0.1.0b2-py3-none-any.whl","yanked":false,"yanked_reason":null},{"comment_text":"","digests":{"blake2b_256":"3165f702684da6e01f8df74a4291be2914c382ec4cb6f8ed2c3dc6d5a9f177ff","md5":"0d51a6f6bf7cb0d3651574404c9c703c","sha256":"cf9a8b54cc4f76592b6380729c03ec7adfe2256e6b200876d7595e50015f5d62"},"downloads":-1,"filename":"agentops-0.1.0b2.tar.gz","has_sig":false,"md5_digest":"0d51a6f6bf7cb0d3651574404c9c703c","packagetype":"sdist","python_version":"source","requires_python":">=3.7","size":23659,"upload_time":"2024-03-21T23:31:21","upload_time_iso_8601":"2024-03-21T23:31:21.330837Z","url":"https://files.pythonhosted.org/packages/31/65/f702684da6e01f8df74a4291be2914c382ec4cb6f8ed2c3dc6d5a9f177ff/agentops-0.1.0b2.tar.gz","yanked":false,"yanked_reason":null}],"0.1.0b3":[{"comment_text":"","digests":{"blake2b_256":"2e64bfe82911b8981ce57f86154915d53b45fffa83ccb9cd6cf4cc71af3f796b","md5":"470bc56525c114dddd908628dcb4f267","sha256":"45b5aaa9f38989cfbfcc4f64e3041050df6d417177874316839225085e60d18d"},"downloads":-1,"filename":"agentops-0.1.0b3-py3-none-any.whl","has_sig":false,"md5_digest":"470bc56525c114dddd908628dcb4f267","packagetype":"bdist_wheel","python_version":"py3","requires_python":">=3.7","size":23522,"upload_time":"2024-03-25T19:34:58","upload_time_iso_8601":"2024-03-25T19:34:58.102867Z","url":"https://files.pythonhosted.org/packages/2e/64/bfe82911b8981ce57f86154915d53b45fffa83ccb9cd6cf4cc71af3f796b/agentops-0.1.0b3-py3-none-any.whl","yanked":false,"yanked_reason":null},{"comment_text":"","digests":{"blake2b_256":"0858e4b718e30a6bbe27d32b7128398cb3884f83f89b4121e36cbb7f979466ca","md5":"8ddb13824d3636d841739479e02a12e6","sha256":"9020daab306fe8c7ed0a98a9edcad9772eb1df0eacce7f936a5ed6bf0f7d2af1"},"downloads":-1,"filename":"agentops-0.1.0b3.tar.gz","has_sig":false,"md5_digest":"8ddb13824d3636d841739479e02a12e6","packagetype":"sdist","python_version":"source","requires_python":">=3.7","size":23641,"upload_time":"2024-03-25T19:35:01","upload_time_iso_8601":"2024-03-25T19:35:01.119334Z","url":"https://files.pythonhosted.org/packages/08/58/e4b718e30a6bbe27d32b7128398cb3884f83f89b4121e36cbb7f979466ca/agentops-0.1.0b3.tar.gz","yanked":false,"yanked_reason":null}],"0.1.0b4":[{"comment_text":"","digests":{"blake2b_256":"67f860440d18b674b06c5a9f4f334bf1f1656dca9f6763d5dd3a2be9e5d2c256","md5":"b11f47108926fb46964bbf28675c3e35","sha256":"93a1f241c3fd7880c3d29ab64baa0661d9ba84e2071092aecb3e4fc574037900"},"downloads":-1,"filename":"agentops-0.1.0b4-py3-none-any.whl","has_sig":false,"md5_digest":"b11f47108926fb46964bbf28675c3e35","packagetype":"bdist_wheel","python_version":"py3","requires_python":">=3.7","size":23512,"upload_time":"2024-03-26T01:14:54","upload_time_iso_8601":"2024-03-26T01:14:54.986869Z","url":"https://files.pythonhosted.org/packages/67/f8/60440d18b674b06c5a9f4f334bf1f1656dca9f6763d5dd3a2be9e5d2c256/agentops-0.1.0b4-py3-none-any.whl","yanked":false,"yanked_reason":null},{"comment_text":"","digests":{"blake2b_256":"10feabb836b04b7eae44383f5616ed1c4c6e9aee9beecc3df4617f69f7e3adc5","md5":"fa4512f74baf9909544ebab021862740","sha256":"4716b4e2a627d7a3846ddee3d334c8f5e8a1a2d231ec5286379c0f22920a2a9d"},"downloads":-1,"filename":"agentops-0.1.0b4.tar.gz","has_sig":false,"md5_digest":"fa4512f74baf9909544ebab021862740","packagetype":"sdist","python_version":"source","requires_python":">=3.7","size":23668,"upload_time":"2024-03-26T01:14:56","upload_time_iso_8601":"2024-03-26T01:14:56.921017Z","url":"https://files.pythonhosted.org/packages/10/fe/abb836b04b7eae44383f5616ed1c4c6e9aee9beecc3df4617f69f7e3adc5/agentops-0.1.0b4.tar.gz","yanked":false,"yanked_reason":null}],"0.1.0b5":[{"comment_text":"","digests":{"blake2b_256":"3ac591c14d08000def551f70ccc1da9ab8b37f57561d24cf7fdf6cd3547610ee","md5":"52a2212b79870ee48f0dbdad852dbb90","sha256":"ed050e51137baa4f46769c77595e1cbe212bb86243f27a29b50218782a0d8242"},"downloads":-1,"filename":"agentops-0.1.0b5-py3-none-any.whl","has_sig":false,"md5_digest":"52a2212b79870ee48f0dbdad852dbb90","packagetype":"bdist_wheel","python_version":"py3","requires_python":">=3.7","size":24597,"upload_time":"2024-04-02T00:56:17","upload_time_iso_8601":"2024-04-02T00:56:17.570921Z","url":"https://files.pythonhosted.org/packages/3a/c5/91c14d08000def551f70ccc1da9ab8b37f57561d24cf7fdf6cd3547610ee/agentops-0.1.0b5-py3-none-any.whl","yanked":false,"yanked_reason":null},{"comment_text":"","digests":{"blake2b_256":"84d6f0bbe5883b86e749f2f02896d94054ebd84b4d66524e4b7004263ae21a6f","md5":"89c6aa7864f45c17f42a38bb6fae904b","sha256":"6ebe6a94f0898fd47521755b6c8083c5f6c0c8bb30d43441200b9ef67998ed01"},"downloads":-1,"filename":"agentops-0.1.0b5.tar.gz","has_sig":false,"md5_digest":"89c6aa7864f45c17f42a38bb6fae904b","packagetype":"sdist","python_version":"source","requires_python":">=3.7","size":24624,"upload_time":"2024-04-02T00:56:18","upload_time_iso_8601":"2024-04-02T00:56:18.703411Z","url":"https://files.pythonhosted.org/packages/84/d6/f0bbe5883b86e749f2f02896d94054ebd84b4d66524e4b7004263ae21a6f/agentops-0.1.0b5.tar.gz","yanked":false,"yanked_reason":null}],"0.1.0b7":[{"comment_text":"","digests":{"blake2b_256":"3cc4ebdb56f0ff88ad20ddba765093aa6c1fc655a8f2bbafbcb2057f998d814f","md5":"d117591df22735d1dedbdc034c93bff6","sha256":"0d4fdb036836dddcce770cffcb2d564b0011a3307224d9a4675fc9bf80ffa5d2"},"downloads":-1,"filename":"agentops-0.1.0b7-py3-none-any.whl","has_sig":false,"md5_digest":"d117591df22735d1dedbdc034c93bff6","packagetype":"bdist_wheel","python_version":"py3","requires_python":">=3.7","size":24592,"upload_time":"2024-04-02T03:20:11","upload_time_iso_8601":"2024-04-02T03:20:11.132539Z","url":"https://files.pythonhosted.org/packages/3c/c4/ebdb56f0ff88ad20ddba765093aa6c1fc655a8f2bbafbcb2057f998d814f/agentops-0.1.0b7-py3-none-any.whl","yanked":false,"yanked_reason":null},{"comment_text":"","digests":{"blake2b_256":"cbf0c32014a8ee12df4596ec4d90428e73e0cc5277d1b9bd2b53f815a7f0ea1f","md5":"20364eb7d493e6f9b46666f36be8fb2f","sha256":"938b29cd894ff38c7b1dee02f6422458702ccf8f3b69b69bc0e4220e42a33629"},"downloads":-1,"filename":"agentops-0.1.0b7.tar.gz","has_sig":false,"md5_digest":"20364eb7d493e6f9b46666f36be8fb2f","packagetype":"sdist","python_version":"source","requires_python":">=3.7","size":24611,"upload_time":"2024-04-02T03:20:12","upload_time_iso_8601":"2024-04-02T03:20:12.490524Z","url":"https://files.pythonhosted.org/packages/cb/f0/c32014a8ee12df4596ec4d90428e73e0cc5277d1b9bd2b53f815a7f0ea1f/agentops-0.1.0b7.tar.gz","yanked":false,"yanked_reason":null}],"0.1.1":[{"comment_text":"","digests":{"blake2b_256":"ba13ff18b4ff72805bcbe7437aa445cde854a44b4b358564ed2b044678e270b9","md5":"d4f77de8dd58468c6c307e735c1cfaa9","sha256":"8afc0b7871d17f8cbe9996cab5ca10a8a3ed33a3406e1ddc257fadc214daa79a"},"downloads":-1,"filename":"agentops-0.1.1-py3-none-any.whl","has_sig":false,"md5_digest":"d4f77de8dd58468c6c307e735c1cfaa9","packagetype":"bdist_wheel","python_version":"py3","requires_python":">=3.7","size":25189,"upload_time":"2024-04-05T22:41:01","upload_time_iso_8601":"2024-04-05T22:41:01.867983Z","url":"https://files.pythonhosted.org/packages/ba/13/ff18b4ff72805bcbe7437aa445cde854a44b4b358564ed2b044678e270b9/agentops-0.1.1-py3-none-any.whl","yanked":false,"yanked_reason":null},{"comment_text":"","digests":{"blake2b_256":"1dec1d2af6e33dd097feaf1e41a4d34c66d4e4e59ce35c5efac85c18614b9d4b","md5":"f072d8700d4e22fc25eae8bb29a54d1f","sha256":"001582703d5e6ffe67a51f9d67a303b5344e4ef8ca315f24aa43e0dd3d19f53b"},"downloads":-1,"filename":"agentops-0.1.1.tar.gz","has_sig":false,"md5_digest":"f072d8700d4e22fc25eae8bb29a54d1f","packagetype":"sdist","python_version":"source","requires_python":">=3.7","size":24831,"upload_time":"2024-04-05T22:41:03","upload_time_iso_8601":"2024-04-05T22:41:03.677234Z","url":"https://files.pythonhosted.org/packages/1d/ec/1d2af6e33dd097feaf1e41a4d34c66d4e4e59ce35c5efac85c18614b9d4b/agentops-0.1.1.tar.gz","yanked":false,"yanked_reason":null}],"0.1.10":[{"comment_text":"","digests":{"blake2b_256":"cdf9a295ed62701dd4e56d5b57e45e0425db2bcea992c687534c9a2dd1e001f1","md5":"8d82b9cb794b4b4a1e91ddece5447bcf","sha256":"8b80800d4fa5a7a6c85c79f2bf39a50fb446ab8b209519bd51f44dee3b38517e"},"downloads":-1,"filename":"agentops-0.1.10-py3-none-any.whl","has_sig":false,"md5_digest":"8d82b9cb794b4b4a1e91ddece5447bcf","packagetype":"bdist_wheel","python_version":"py3","requires_python":">=3.7","size":29769,"upload_time":"2024-05-10T20:13:39","upload_time_iso_8601":"2024-05-10T20:13:39.477237Z","url":"https://files.pythonhosted.org/packages/cd/f9/a295ed62701dd4e56d5b57e45e0425db2bcea992c687534c9a2dd1e001f1/agentops-0.1.10-py3-none-any.whl","yanked":false,"yanked_reason":null},{"comment_text":"","digests":{"blake2b_256":"f3788e027be4aa50f677a46bba1e0132f021e90d299c6eae093181a91679e378","md5":"4dd3d1fd8c08efb1a08ae212ed9211d7","sha256":"73fbd36cd5f3052d22e64dbea1fa9d70fb02658a901a600101801daa73f359f9"},"downloads":-1,"filename":"agentops-0.1.10.tar.gz","has_sig":false,"md5_digest":"4dd3d1fd8c08efb1a08ae212ed9211d7","packagetype":"sdist","python_version":"source","requires_python":">=3.7","size":30268,"upload_time":"2024-05-10T20:14:25","upload_time_iso_8601":"2024-05-10T20:14:25.258530Z","url":"https://files.pythonhosted.org/packages/f3/78/8e027be4aa50f677a46bba1e0132f021e90d299c6eae093181a91679e378/agentops-0.1.10.tar.gz","yanked":false,"yanked_reason":null}],"0.1.11":[{"comment_text":"","digests":{"blake2b_256":"1ebfaaa31babe3bf687312592f99fe900e3808058658577bd1367b7df0332a08","md5":"73c0b028248665a7927688fb8baa7680","sha256":"e9411981a5d0b1190b93e3e1124db3ac6f17015c65a84b92a793f34d79b694c9"},"downloads":-1,"filename":"agentops-0.1.11-py3-none-any.whl","has_sig":false,"md5_digest":"73c0b028248665a7927688fb8baa7680","packagetype":"bdist_wheel","python_version":"py3","requires_python":">=3.7","size":30952,"upload_time":"2024-05-17T00:32:49","upload_time_iso_8601":"2024-05-17T00:32:49.202597Z","url":"https://files.pythonhosted.org/packages/1e/bf/aaa31babe3bf687312592f99fe900e3808058658577bd1367b7df0332a08/agentops-0.1.11-py3-none-any.whl","yanked":false,"yanked_reason":null},{"comment_text":"","digests":{"blake2b_256":"6ee43f71a7d1d63595058cd6945e7b9e2de1b06ace04176a6723b7bfb37bf880","md5":"36092e907e4f15a6bafd6788383df112","sha256":"4a365ee56303b5b80d9de21fc13ccb7a3fe44544a6c165327bbfd9213bfe0191"},"downloads":-1,"filename":"agentops-0.1.11.tar.gz","has_sig":false,"md5_digest":"36092e907e4f15a6bafd6788383df112","packagetype":"sdist","python_version":"source","requires_python":">=3.7","size":31256,"upload_time":"2024-05-17T00:32:50","upload_time_iso_8601":"2024-05-17T00:32:50.919974Z","url":"https://files.pythonhosted.org/packages/6e/e4/3f71a7d1d63595058cd6945e7b9e2de1b06ace04176a6723b7bfb37bf880/agentops-0.1.11.tar.gz","yanked":false,"yanked_reason":null}],"0.1.12":[{"comment_text":"","digests":{"blake2b_256":"67f5227dffbebeffd3b404db0dd71805f00814e458c0d081faf7a4e70c7e984f","md5":"2591924de6f2e5580e4733b0e8336e2c","sha256":"b4b47c990638b74810cc1c38624ada162094b46e3fdd63883642a16bc5258386"},"downloads":-1,"filename":"agentops-0.1.12-py3-none-any.whl","has_sig":false,"md5_digest":"2591924de6f2e5580e4733b0e8336e2c","packagetype":"bdist_wheel","python_version":"py3","requires_python":">=3.7","size":35605,"upload_time":"2024-05-24T20:11:52","upload_time_iso_8601":"2024-05-24T20:11:52.863109Z","url":"https://files.pythonhosted.org/packages/67/f5/227dffbebeffd3b404db0dd71805f00814e458c0d081faf7a4e70c7e984f/agentops-0.1.12-py3-none-any.whl","yanked":false,"yanked_reason":null},{"comment_text":"","digests":{"blake2b_256":"9f9ae6dc42ad8d40ad47c6116629b2cbda443d314327ab4d33e1044cb75ba88b","md5":"4c2e76e7b6d4799ef4b464dee29e7255","sha256":"c4f762482fb240fc3503907f52498f2d8d9e4f80236ee4a12bf039317a85fcd7"},"downloads":-1,"filename":"agentops-0.1.12.tar.gz","has_sig":false,"md5_digest":"4c2e76e7b6d4799ef4b464dee29e7255","packagetype":"sdist","python_version":"source","requires_python":">=3.7","size":35103,"upload_time":"2024-05-24T20:11:54","upload_time_iso_8601":"2024-05-24T20:11:54.846567Z","url":"https://files.pythonhosted.org/packages/9f/9a/e6dc42ad8d40ad47c6116629b2cbda443d314327ab4d33e1044cb75ba88b/agentops-0.1.12.tar.gz","yanked":false,"yanked_reason":null}],"0.1.2":[{"comment_text":"","digests":{"blake2b_256":"e709193dfe68c2d23de2c60dd0af2af336cbf81d3a3f0c175705783b4c1da580","md5":"588d9877b9767546606d3d6d76d247fc","sha256":"ec79e56889eadd2bab04dfe2f6a899a1b90dc347a66cc80488297368386105b4"},"downloads":-1,"filename":"agentops-0.1.2-py3-none-any.whl","has_sig":false,"md5_digest":"588d9877b9767546606d3d6d76d247fc","packagetype":"bdist_wheel","python_version":"py3","requires_python":">=3.7","size":25359,"upload_time":"2024-04-09T23:00:51","upload_time_iso_8601":"2024-04-09T23:00:51.897995Z","url":"https://files.pythonhosted.org/packages/e7/09/193dfe68c2d23de2c60dd0af2af336cbf81d3a3f0c175705783b4c1da580/agentops-0.1.2-py3-none-any.whl","yanked":false,"yanked_reason":null},{"comment_text":"","digests":{"blake2b_256":"8acc872aba374093481bb40ed6b7531b1500b00138baf6bfb9ca7c20fb889d58","md5":"80f8f7c56b1e1a6ff4c48877fe12dd12","sha256":"d213e1037d2d319743889c2bdbc10dc068b0591e2c6c156f69019302490336d5"},"downloads":-1,"filename":"agentops-0.1.2.tar.gz","has_sig":false,"md5_digest":"80f8f7c56b1e1a6ff4c48877fe12dd12","packagetype":"sdist","python_version":"source","requires_python":">=3.7","size":24968,"upload_time":"2024-04-09T23:00:53","upload_time_iso_8601":"2024-04-09T23:00:53.227389Z","url":"https://files.pythonhosted.org/packages/8a/cc/872aba374093481bb40ed6b7531b1500b00138baf6bfb9ca7c20fb889d58/agentops-0.1.2.tar.gz","yanked":false,"yanked_reason":null}],"0.1.3":[{"comment_text":"","digests":{"blake2b_256":"9701aad65170506dcf29606e9e619d2c0caaee565e5e8b14a791c3e0e86c6356","md5":"4dc967275c884e2a5a1de8df448ae1c6","sha256":"f1ca0f2c5156d826381e9ebd634555215c67e1cb344683abddb382e594f483e4"},"downloads":-1,"filename":"agentops-0.1.3-py3-none-any.whl","has_sig":false,"md5_digest":"4dc967275c884e2a5a1de8df448ae1c6","packagetype":"bdist_wheel","python_version":"py3","requires_python":">=3.7","size":25393,"upload_time":"2024-04-09T23:24:20","upload_time_iso_8601":"2024-04-09T23:24:20.821465Z","url":"https://files.pythonhosted.org/packages/97/01/aad65170506dcf29606e9e619d2c0caaee565e5e8b14a791c3e0e86c6356/agentops-0.1.3-py3-none-any.whl","yanked":false,"yanked_reason":null},{"comment_text":"","digests":{"blake2b_256":"5e22afde273bcf52cfc6581fba804b44eeebea6ff2ae774f0e5917fa1dd3ee09","md5":"624c9b63dbe56c8b1dd535e1b20ada81","sha256":"dd65e80ec70accfac0692171199b6ecfa37a7d109a3c25f2191c0934b5004114"},"downloads":-1,"filename":"agentops-0.1.3.tar.gz","has_sig":false,"md5_digest":"624c9b63dbe56c8b1dd535e1b20ada81","packagetype":"sdist","python_version":"source","requires_python":">=3.7","size":24994,"upload_time":"2024-04-09T23:24:22","upload_time_iso_8601":"2024-04-09T23:24:22.610198Z","url":"https://files.pythonhosted.org/packages/5e/22/afde273bcf52cfc6581fba804b44eeebea6ff2ae774f0e5917fa1dd3ee09/agentops-0.1.3.tar.gz","yanked":false,"yanked_reason":null}],"0.1.4":[{"comment_text":"","digests":{"blake2b_256":"50313e20afb169e707941cc3342cecb88060aa8746e95d72a202fd90ac4096b6","md5":"3f64b736522ea40c35db6d2a609fc54f","sha256":"476a5e795a6cc87858a0885be61b1e05eed21e4c6ab47f20348c48717c2ac454"},"downloads":-1,"filename":"agentops-0.1.4-py3-none-any.whl","has_sig":false,"md5_digest":"3f64b736522ea40c35db6d2a609fc54f","packagetype":"bdist_wheel","python_version":"py3","requires_python":">=3.7","size":25558,"upload_time":"2024-04-11T19:26:01","upload_time_iso_8601":"2024-04-11T19:26:01.162829Z","url":"https://files.pythonhosted.org/packages/50/31/3e20afb169e707941cc3342cecb88060aa8746e95d72a202fd90ac4096b6/agentops-0.1.4-py3-none-any.whl","yanked":false,"yanked_reason":null},{"comment_text":"","digests":{"blake2b_256":"e0688b1a21f72b85c9bdd56da4223c991bdfb5d0c2accd9ddd326616bf952795","md5":"6f4601047f3e2080b4f7363ff84f15f3","sha256":"d55e64953f84654d44557b496a3b3744a20449b854af84fa83a15be75b362b3d"},"downloads":-1,"filename":"agentops-0.1.4.tar.gz","has_sig":false,"md5_digest":"6f4601047f3e2080b4f7363ff84f15f3","packagetype":"sdist","python_version":"source","requires_python":">=3.7","size":25390,"upload_time":"2024-04-11T19:26:02","upload_time_iso_8601":"2024-04-11T19:26:02.991657Z","url":"https://files.pythonhosted.org/packages/e0/68/8b1a21f72b85c9bdd56da4223c991bdfb5d0c2accd9ddd326616bf952795/agentops-0.1.4.tar.gz","yanked":false,"yanked_reason":null}],"0.1.5":[{"comment_text":"","digests":{"blake2b_256":"641c742793fa77c803e5667830ccd34b8d313d11f361a105fe92ce68d871cc5f","md5":"964421a604c67c07b5c72b70ceee6ce8","sha256":"bc65dd4cd85d1ffcba195f2490b5a4380d0b565dd0f4a71ecc64ed96a7fe1eee"},"downloads":-1,"filename":"agentops-0.1.5-py3-none-any.whl","has_sig":false,"md5_digest":"964421a604c67c07b5c72b70ceee6ce8","packagetype":"bdist_wheel","python_version":"py3","requires_python":">=3.7","size":25793,"upload_time":"2024-04-20T01:56:23","upload_time_iso_8601":"2024-04-20T01:56:23.089343Z","url":"https://files.pythonhosted.org/packages/64/1c/742793fa77c803e5667830ccd34b8d313d11f361a105fe92ce68d871cc5f/agentops-0.1.5-py3-none-any.whl","yanked":false,"yanked_reason":null},{"comment_text":"","digests":{"blake2b_256":"62beabcb235daf34d4740961c4ad295b8dfb8a053ac6a1e341394e36f722ea89","md5":"3ff7fa3135bc5c4254aaa99e3cc00dc8","sha256":"17f0a573362d9c4770846874a4091662304d6889e21ca6a7dd747be48b9c8597"},"downloads":-1,"filename":"agentops-0.1.5.tar.gz","has_sig":false,"md5_digest":"3ff7fa3135bc5c4254aaa99e3cc00dc8","packagetype":"sdist","python_version":"source","requires_python":">=3.7","size":25664,"upload_time":"2024-04-20T01:56:24","upload_time_iso_8601":"2024-04-20T01:56:24.303013Z","url":"https://files.pythonhosted.org/packages/62/be/abcb235daf34d4740961c4ad295b8dfb8a053ac6a1e341394e36f722ea89/agentops-0.1.5.tar.gz","yanked":false,"yanked_reason":null}],"0.1.6":[{"comment_text":"","digests":{"blake2b_256":"430b9f3fcfc2f9778dbbfc1fd68b223e9a91938505ef987e17b93a631bb6b2e4","md5":"28ce2e6aa7a4598fa1e764d9762fd030","sha256":"9dff841ef71f5fad2d897012a00f50011a706970e0e5eaae9d7b0540a637b128"},"downloads":-1,"filename":"agentops-0.1.6-py3-none-any.whl","has_sig":false,"md5_digest":"28ce2e6aa7a4598fa1e764d9762fd030","packagetype":"bdist_wheel","python_version":"py3","requires_python":">=3.7","size":26154,"upload_time":"2024-04-20T03:48:58","upload_time_iso_8601":"2024-04-20T03:48:58.494391Z","url":"https://files.pythonhosted.org/packages/43/0b/9f3fcfc2f9778dbbfc1fd68b223e9a91938505ef987e17b93a631bb6b2e4/agentops-0.1.6-py3-none-any.whl","yanked":false,"yanked_reason":null},{"comment_text":"","digests":{"blake2b_256":"a6c2b437246ce28bad9c2bbad9a9371f7008f76a979fb19699588212f653daf9","md5":"fc81fd641ad630a17191d4a9cf77193b","sha256":"48ddb49fc01eb83ce151d3f08ae670b3d603c454aa35b4ea145f2dc15e081b36"},"downloads":-1,"filename":"agentops-0.1.6.tar.gz","has_sig":false,"md5_digest":"fc81fd641ad630a17191d4a9cf77193b","packagetype":"sdist","python_version":"source","requires_python":">=3.7","size":25792,"upload_time":"2024-04-20T03:48:59","upload_time_iso_8601":"2024-04-20T03:48:59.957150Z","url":"https://files.pythonhosted.org/packages/a6/c2/b437246ce28bad9c2bbad9a9371f7008f76a979fb19699588212f653daf9/agentops-0.1.6.tar.gz","yanked":false,"yanked_reason":null}],"0.1.7":[{"comment_text":"","digests":{"blake2b_256":"1ca529570477f62973c6b835e09dc5bbda7498c1a26ba7a428cdb08a71ae86ca","md5":"a1962d1bb72c6fd00e67e83fe56a3692","sha256":"ce7a9e89dcf17507ee6db85017bef8f87fc4e8a23745f3f73e1fbda5489fb6f9"},"downloads":-1,"filename":"agentops-0.1.7-py3-none-any.whl","has_sig":false,"md5_digest":"a1962d1bb72c6fd00e67e83fe56a3692","packagetype":"bdist_wheel","python_version":"py3","requires_python":">=3.10","size":27891,"upload_time":"2024-05-03T19:21:38","upload_time_iso_8601":"2024-05-03T19:21:38.018602Z","url":"https://files.pythonhosted.org/packages/1c/a5/29570477f62973c6b835e09dc5bbda7498c1a26ba7a428cdb08a71ae86ca/agentops-0.1.7-py3-none-any.whl","yanked":true,"yanked_reason":"Introduced - breaking bug"},{"comment_text":"","digests":{"blake2b_256":"b2447ce75e71fcc9605a609b41adc52d517eba4356d15f7ca77d46f683ca07f1","md5":"9a9bb22af4b30c454d46b9a01e8701a0","sha256":"70d22e9a71ea13af6e6ad9c1cffe63c98f9dbccf91bda199825609379b2babaf"},"downloads":-1,"filename":"agentops-0.1.7.tar.gz","has_sig":false,"md5_digest":"9a9bb22af4b30c454d46b9a01e8701a0","packagetype":"sdist","python_version":"source","requires_python":">=3.10","size":28122,"upload_time":"2024-05-03T19:21:39","upload_time_iso_8601":"2024-05-03T19:21:39.415523Z","url":"https://files.pythonhosted.org/packages/b2/44/7ce75e71fcc9605a609b41adc52d517eba4356d15f7ca77d46f683ca07f1/agentops-0.1.7.tar.gz","yanked":true,"yanked_reason":"Introduced breaking bug"}],"0.1.8":[{"comment_text":"","digests":{"blake2b_256":"38c63d0d19eeae4c3c9e3ff5957b10c3c16a4a9fd2be6673fbfc965f8bb4fd08","md5":"e12d3d92f51f5b2fed11a01742e5b5b5","sha256":"d49d113028a891d50900bb4fae253218cc49519f7fe39f9ea15f8f2b29d6d7ef"},"downloads":-1,"filename":"agentops-0.1.8-py3-none-any.whl","has_sig":false,"md5_digest":"e12d3d92f51f5b2fed11a01742e5b5b5","packagetype":"bdist_wheel","python_version":"py3","requires_python":">=3.10","size":27977,"upload_time":"2024-05-04T03:01:53","upload_time_iso_8601":"2024-05-04T03:01:53.905081Z","url":"https://files.pythonhosted.org/packages/38/c6/3d0d19eeae4c3c9e3ff5957b10c3c16a4a9fd2be6673fbfc965f8bb4fd08/agentops-0.1.8-py3-none-any.whl","yanked":false,"yanked_reason":null},{"comment_text":"","digests":{"blake2b_256":"9269e51fa1714f169f692e4fad0a42ebeb77c7a27c48f62b751c869ad6441c69","md5":"07dbdb45f9ec086b1bc314d6a8264423","sha256":"5762137a84e2309e1b6ca9a0fd72c8b72c90f6f73ba49549980722221960cac8"},"downloads":-1,"filename":"agentops-0.1.8.tar.gz","has_sig":false,"md5_digest":"07dbdb45f9ec086b1bc314d6a8264423","packagetype":"sdist","python_version":"source","requires_python":">=3.10","size":28189,"upload_time":"2024-05-04T03:01:55","upload_time_iso_8601":"2024-05-04T03:01:55.328668Z","url":"https://files.pythonhosted.org/packages/92/69/e51fa1714f169f692e4fad0a42ebeb77c7a27c48f62b751c869ad6441c69/agentops-0.1.8.tar.gz","yanked":false,"yanked_reason":null}],"0.1.9":[{"comment_text":"","digests":{"blake2b_256":"eb5a920e71729bd1f06b002ee146b38b0d1862357a1f484628e6b20a7d3dcca1","md5":"6ae4929d91c4bb8025edc86b5322630c","sha256":"af7983ba4929b04a34714dd97d7e82c11384ebbe9d7d8bc7b673e1263c4c79a1"},"downloads":-1,"filename":"agentops-0.1.9-py3-none-any.whl","has_sig":false,"md5_digest":"6ae4929d91c4bb8025edc86b5322630c","packagetype":"bdist_wheel","python_version":"py3","requires_python":">=3.7","size":28458,"upload_time":"2024-05-07T07:07:30","upload_time_iso_8601":"2024-05-07T07:07:30.798380Z","url":"https://files.pythonhosted.org/packages/eb/5a/920e71729bd1f06b002ee146b38b0d1862357a1f484628e6b20a7d3dcca1/agentops-0.1.9-py3-none-any.whl","yanked":false,"yanked_reason":null},{"comment_text":"","digests":{"blake2b_256":"df2b8fc76d629d8a83b0796612a27b966426550114c930eee5d730654fcd9fe9","md5":"43090632f87cd398ed77b57daa8c28d6","sha256":"7f428bfda2db57a994029b1c9f72b63ca7660616635c9c671b2b729d112a833e"},"downloads":-1,"filename":"agentops-0.1.9.tar.gz","has_sig":false,"md5_digest":"43090632f87cd398ed77b57daa8c28d6","packagetype":"sdist","python_version":"source","requires_python":">=3.7","size":28596,"upload_time":"2024-05-07T07:07:35","upload_time_iso_8601":"2024-05-07T07:07:35.242350Z","url":"https://files.pythonhosted.org/packages/df/2b/8fc76d629d8a83b0796612a27b966426550114c930eee5d730654fcd9fe9/agentops-0.1.9.tar.gz","yanked":false,"yanked_reason":null}],"0.2.0":[{"comment_text":"","digests":{"blake2b_256":"483560ec38a81a7e9588d32730ed4f581621169216f968771d5f611388f68a9b","md5":"bdda5480977cccd55628e117e8c8da04","sha256":"bee84bf046c9b4346c5f0f50e2087a992e8d2eae80b3fe9f01c456b49c299bcc"},"downloads":-1,"filename":"agentops-0.2.0-py3-none-any.whl","has_sig":false,"md5_digest":"bdda5480977cccd55628e117e8c8da04","packagetype":"bdist_wheel","python_version":"py3","requires_python":">=3.7","size":35921,"upload_time":"2024-05-28T22:04:14","upload_time_iso_8601":"2024-05-28T22:04:14.813154Z","url":"https://files.pythonhosted.org/packages/48/35/60ec38a81a7e9588d32730ed4f581621169216f968771d5f611388f68a9b/agentops-0.2.0-py3-none-any.whl","yanked":false,"yanked_reason":null},{"comment_text":"","digests":{"blake2b_256":"8d7591c79141d31da4e56d6c6a00737b50dcc2f1ce8a711c1293d2a1d70478fc","md5":"71e3c3b9fe0286c9b58d81ba1c12a42d","sha256":"ca340136abff6a3727729c3eda87f0768e5ba2b672ce03320cb52ad138b05598"},"downloads":-1,"filename":"agentops-0.2.0.tar.gz","has_sig":false,"md5_digest":"71e3c3b9fe0286c9b58d81ba1c12a42d","packagetype":"sdist","python_version":"source","requires_python":">=3.7","size":35498,"upload_time":"2024-05-28T22:04:16","upload_time_iso_8601":"2024-05-28T22:04:16.598374Z","url":"https://files.pythonhosted.org/packages/8d/75/91c79141d31da4e56d6c6a00737b50dcc2f1ce8a711c1293d2a1d70478fc/agentops-0.2.0.tar.gz","yanked":false,"yanked_reason":null}],"0.2.1":[{"comment_text":"","digests":{"blake2b_256":"fa3b84032b7dca3d7315b329db6681bbfe0872c2a46d62ca992a05f2d6a078e1","md5":"ce3fc46711fa8225a3d6a9566f95f875","sha256":"7dde95db92c8306c0a17e193bfb5ee20e71e16630ccc629db685e148b3aca3f6"},"downloads":-1,"filename":"agentops-0.2.1-py3-none-any.whl","has_sig":false,"md5_digest":"ce3fc46711fa8225a3d6a9566f95f875","packagetype":"bdist_wheel","python_version":"py3","requires_python":">=3.7","size":36375,"upload_time":"2024-06-03T18:40:02","upload_time_iso_8601":"2024-06-03T18:40:02.820700Z","url":"https://files.pythonhosted.org/packages/fa/3b/84032b7dca3d7315b329db6681bbfe0872c2a46d62ca992a05f2d6a078e1/agentops-0.2.1-py3-none-any.whl","yanked":false,"yanked_reason":null},{"comment_text":"","digests":{"blake2b_256":"d6286ad330da5736588a54575fde95502006da58c3e9f4f15933f5876c1e1482","md5":"faa972c26a3e59fb6ca04f253165da22","sha256":"9f18a36a79c04e9c06f6e96aefe75f0fb1d08e562873315d6cb945488306e515"},"downloads":-1,"filename":"agentops-0.2.1.tar.gz","has_sig":false,"md5_digest":"faa972c26a3e59fb6ca04f253165da22","packagetype":"sdist","python_version":"source","requires_python":">=3.7","size":35784,"upload_time":"2024-06-03T18:40:05","upload_time_iso_8601":"2024-06-03T18:40:05.431174Z","url":"https://files.pythonhosted.org/packages/d6/28/6ad330da5736588a54575fde95502006da58c3e9f4f15933f5876c1e1482/agentops-0.2.1.tar.gz","yanked":false,"yanked_reason":null}],"0.2.2":[{"comment_text":"","digests":{"blake2b_256":"fbe73a57dd30e354b7bcc5a86908fc92aa16378035c69eb225ce254387940b5d","md5":"c24e4656bb6de14ffb9d810fe7872829","sha256":"57aab8a5d76a0dd7b1f0b14e90e778c42444eeaf5c48f2f387719735d7d840ee"},"downloads":-1,"filename":"agentops-0.2.2-py3-none-any.whl","has_sig":false,"md5_digest":"c24e4656bb6de14ffb9d810fe7872829","packagetype":"bdist_wheel","python_version":"py3","requires_python":">=3.7","size":36588,"upload_time":"2024-06-05T19:30:29","upload_time_iso_8601":"2024-06-05T19:30:29.208415Z","url":"https://files.pythonhosted.org/packages/fb/e7/3a57dd30e354b7bcc5a86908fc92aa16378035c69eb225ce254387940b5d/agentops-0.2.2-py3-none-any.whl","yanked":false,"yanked_reason":null},{"comment_text":"","digests":{"blake2b_256":"89c51cbd038b9d2898b7f1b05943c338aa4aa9654d7e7763d8fa8d73a25fbfb6","md5":"401bfce001638cc26d7975f6534b5bab","sha256":"d4135c96ad7ec39c81015b3e33dfa977d2d846a685aba0d1922d2d6e3dca7fff"},"downloads":-1,"filename":"agentops-0.2.2.tar.gz","has_sig":false,"md5_digest":"401bfce001638cc26d7975f6534b5bab","packagetype":"sdist","python_version":"source","requires_python":">=3.7","size":36012,"upload_time":"2024-06-05T19:30:31","upload_time_iso_8601":"2024-06-05T19:30:31.173781Z","url":"https://files.pythonhosted.org/packages/89/c5/1cbd038b9d2898b7f1b05943c338aa4aa9654d7e7763d8fa8d73a25fbfb6/agentops-0.2.2.tar.gz","yanked":false,"yanked_reason":null}],"0.2.3":[{"comment_text":"","digests":{"blake2b_256":"b66fb36e2bb7158f45b6c496ce3cec50ef861e130cfa3ec8c62e709d63fa9e94","md5":"b3f6a8d97cc0129a9e4730b7810509c6","sha256":"a1829a21301223c26464cbc9da5bfba2f3750e21238912ee1d2f3097c358859a"},"downloads":-1,"filename":"agentops-0.2.3-py3-none-any.whl","has_sig":false,"md5_digest":"b3f6a8d97cc0129a9e4730b7810509c6","packagetype":"bdist_wheel","python_version":"py3","requires_python":">=3.7","size":36986,"upload_time":"2024-06-13T19:56:33","upload_time_iso_8601":"2024-06-13T19:56:33.675807Z","url":"https://files.pythonhosted.org/packages/b6/6f/b36e2bb7158f45b6c496ce3cec50ef861e130cfa3ec8c62e709d63fa9e94/agentops-0.2.3-py3-none-any.whl","yanked":false,"yanked_reason":null},{"comment_text":"","digests":{"blake2b_256":"f4d34aed81a4ec4251131b94fb8ed4edf0823922bfda66ba0e4c43d9452111d2","md5":"466abe04d466a950d4bcebbe9c3ccc27","sha256":"b502b83bb4954386a28c4304028ba8cd2b45303f7e1f84720477b521267a3b4e"},"downloads":-1,"filename":"agentops-0.2.3.tar.gz","has_sig":false,"md5_digest":"466abe04d466a950d4bcebbe9c3ccc27","packagetype":"sdist","python_version":"source","requires_python":">=3.7","size":37024,"upload_time":"2024-06-13T19:56:35","upload_time_iso_8601":"2024-06-13T19:56:35.481794Z","url":"https://files.pythonhosted.org/packages/f4/d3/4aed81a4ec4251131b94fb8ed4edf0823922bfda66ba0e4c43d9452111d2/agentops-0.2.3.tar.gz","yanked":false,"yanked_reason":null}],"0.2.4":[{"comment_text":"","digests":{"blake2b_256":"a4d4e91fb66bc2eb7effb53f7d9481da04e60809d10240306452a8307aca7985","md5":"f1ba1befb6bd854d5fd6f670937dcb55","sha256":"96162c28cc0391011c04e654273e5a96ec4dcf015e27a7ac12a1ea4077d38950"},"downloads":-1,"filename":"agentops-0.2.4-py3-none-any.whl","has_sig":false,"md5_digest":"f1ba1befb6bd854d5fd6f670937dcb55","packagetype":"bdist_wheel","python_version":"py3","requires_python":">=3.7","size":37518,"upload_time":"2024-06-24T19:31:58","upload_time_iso_8601":"2024-06-24T19:31:58.838680Z","url":"https://files.pythonhosted.org/packages/a4/d4/e91fb66bc2eb7effb53f7d9481da04e60809d10240306452a8307aca7985/agentops-0.2.4-py3-none-any.whl","yanked":true,"yanked_reason":"Potential - breaking change"},{"comment_text":"","digests":{"blake2b_256":"8e4b920629e08c956cdc74a31ab466d005eb13d86c2d58fa2d2bd261cf36c37b","md5":"527c82f21f01f13b879a1fca90ddb209","sha256":"d263de21eb40e15eb17adc31821fc0dee4ff4ca4501a9feb7ed376d473063208"},"downloads":-1,"filename":"agentops-0.2.4.tar.gz","has_sig":false,"md5_digest":"527c82f21f01f13b879a1fca90ddb209","packagetype":"sdist","python_version":"source","requires_python":">=3.7","size":37656,"upload_time":"2024-06-24T19:32:01","upload_time_iso_8601":"2024-06-24T19:32:01.155014Z","url":"https://files.pythonhosted.org/packages/8e/4b/920629e08c956cdc74a31ab466d005eb13d86c2d58fa2d2bd261cf36c37b/agentops-0.2.4.tar.gz","yanked":true,"yanked_reason":"Potential breaking change"}],"0.2.5":[{"comment_text":"","digests":{"blake2b_256":"47c73ab9d7d971b664a9bdff6e6464afb6c1de8eb0f845d8de93eb036d5dcc60","md5":"bed576cc1591da4783777920fb223761","sha256":"ff87b82d1efaf50b10624e00c6e9334f4c16ffe08ec7f9889b4417c231c31471"},"downloads":-1,"filename":"agentops-0.2.5-py3-none-any.whl","has_sig":false,"md5_digest":"bed576cc1591da4783777920fb223761","packagetype":"bdist_wheel","python_version":"py3","requires_python":">=3.7","size":37529,"upload_time":"2024-06-26T22:57:15","upload_time_iso_8601":"2024-06-26T22:57:15.646328Z","url":"https://files.pythonhosted.org/packages/47/c7/3ab9d7d971b664a9bdff6e6464afb6c1de8eb0f845d8de93eb036d5dcc60/agentops-0.2.5-py3-none-any.whl","yanked":false,"yanked_reason":null},{"comment_text":"","digests":{"blake2b_256":"31c48f2af30ae75dbdb4697506f80f76ce786f79014deb8c6679fa62962fdd6f","md5":"42def99798edfaf201fa6f62846e77c5","sha256":"6bad7aca37af6174307769550a53ec00824049a57e97b8868a9a213b2272adb4"},"downloads":-1,"filename":"agentops-0.2.5.tar.gz","has_sig":false,"md5_digest":"42def99798edfaf201fa6f62846e77c5","packagetype":"sdist","python_version":"source","requires_python":">=3.7","size":37703,"upload_time":"2024-06-26T22:57:17","upload_time_iso_8601":"2024-06-26T22:57:17.337904Z","url":"https://files.pythonhosted.org/packages/31/c4/8f2af30ae75dbdb4697506f80f76ce786f79014deb8c6679fa62962fdd6f/agentops-0.2.5.tar.gz","yanked":false,"yanked_reason":null}],"0.2.6":[{"comment_text":"","digests":{"blake2b_256":"5af2f90538b00d887c04a5570e8a3af4aef27a600a67c058a0ee6befafd60748","md5":"8ef3ed13ed582346b71648ca9df30f7c","sha256":"59e88000a9f108931fd68056f22def7a7f4b3015906de5791e777c23ba7dee52"},"downloads":-1,"filename":"agentops-0.2.6-py3-none-any.whl","has_sig":false,"md5_digest":"8ef3ed13ed582346b71648ca9df30f7c","packagetype":"bdist_wheel","python_version":"py3","requires_python":">=3.7","size":37534,"upload_time":"2024-06-28T21:41:56","upload_time_iso_8601":"2024-06-28T21:41:56.933334Z","url":"https://files.pythonhosted.org/packages/5a/f2/f90538b00d887c04a5570e8a3af4aef27a600a67c058a0ee6befafd60748/agentops-0.2.6-py3-none-any.whl","yanked":false,"yanked_reason":null},{"comment_text":"","digests":{"blake2b_256":"bcf412c388dccc301ad54a501843ba5b5dd359575dcef9ac24c18a619a32214d","md5":"89a6b04f12801682b53ee0133593ce74","sha256":"7906a08c9154355484deb173b82631f9acddec3775b2d5e8ca946abdee27183b"},"downloads":-1,"filename":"agentops-0.2.6.tar.gz","has_sig":false,"md5_digest":"89a6b04f12801682b53ee0133593ce74","packagetype":"sdist","python_version":"source","requires_python":">=3.7","size":37874,"upload_time":"2024-06-28T21:41:59","upload_time_iso_8601":"2024-06-28T21:41:59.143953Z","url":"https://files.pythonhosted.org/packages/bc/f4/12c388dccc301ad54a501843ba5b5dd359575dcef9ac24c18a619a32214d/agentops-0.2.6.tar.gz","yanked":false,"yanked_reason":null}],"0.3.0":[{"comment_text":"","digests":{"blake2b_256":"b8e996f12ac457f46c370c6f70f344e975d534f2c92853703ee29802f0127024","md5":"d9c6995a843b49ac7eb6f500fa1f3c2a","sha256":"22aeb3355e66b32a2b2a9f676048b81979b2488feddb088f9266034b3ed50539"},"downloads":-1,"filename":"agentops-0.3.0-py3-none-any.whl","has_sig":false,"md5_digest":"d9c6995a843b49ac7eb6f500fa1f3c2a","packagetype":"bdist_wheel","python_version":"py3","requires_python":">=3.7","size":39430,"upload_time":"2024-07-17T18:38:24","upload_time_iso_8601":"2024-07-17T18:38:24.763919Z","url":"https://files.pythonhosted.org/packages/b8/e9/96f12ac457f46c370c6f70f344e975d534f2c92853703ee29802f0127024/agentops-0.3.0-py3-none-any.whl","yanked":false,"yanked_reason":null},{"comment_text":"","digests":{"blake2b_256":"7e2d6fda9613562c0394d7ef3dd8f0cb9fc4ebaa8d413862fce33940c73564d6","md5":"8fa67ca01ca726e3bfcd66898313f33f","sha256":"6c0c08a57410fa5e826a7bafa1deeba9f7b3524709427d9e1abbd0964caaf76b"},"downloads":-1,"filename":"agentops-0.3.0.tar.gz","has_sig":false,"md5_digest":"8fa67ca01ca726e3bfcd66898313f33f","packagetype":"sdist","python_version":"source","requires_python":">=3.7","size":41734,"upload_time":"2024-07-17T18:38:26","upload_time_iso_8601":"2024-07-17T18:38:26.447237Z","url":"https://files.pythonhosted.org/packages/7e/2d/6fda9613562c0394d7ef3dd8f0cb9fc4ebaa8d413862fce33940c73564d6/agentops-0.3.0.tar.gz","yanked":false,"yanked_reason":null}],"0.3.10":[{"comment_text":"","digests":{"blake2b_256":"eb5e3ac36b33d3e95747d64effd509f66a9b3b76b47216b16f492e27d8d90b0c","md5":"6fade0b81fc65b2c79a869b5f240590b","sha256":"b304d366691281e08c1f02307aabdd551ae4f68b0de82bbbb4cf6f651af2dd16"},"downloads":-1,"filename":"agentops-0.3.10-py3-none-any.whl","has_sig":false,"md5_digest":"6fade0b81fc65b2c79a869b5f240590b","packagetype":"bdist_wheel","python_version":"py3","requires_python":">=3.7","size":41201,"upload_time":"2024-08-19T20:51:49","upload_time_iso_8601":"2024-08-19T20:51:49.487947Z","url":"https://files.pythonhosted.org/packages/eb/5e/3ac36b33d3e95747d64effd509f66a9b3b76b47216b16f492e27d8d90b0c/agentops-0.3.10-py3-none-any.whl","yanked":false,"yanked_reason":null},{"comment_text":"","digests":{"blake2b_256":"8367ca0cb01df6b529f0127d23ec661e92c95ff68faf544439d86ec2331f3a52","md5":"639da9c2a3381cb3f62812bfe48a5e57","sha256":"40f895019f29bc5a6c023110cbec32870e5edb3e3926f8100974db8d3e299e2a"},"downloads":-1,"filename":"agentops-0.3.10.tar.gz","has_sig":false,"md5_digest":"639da9c2a3381cb3f62812bfe48a5e57","packagetype":"sdist","python_version":"source","requires_python":">=3.7","size":45332,"upload_time":"2024-08-19T20:51:50","upload_time_iso_8601":"2024-08-19T20:51:50.714217Z","url":"https://files.pythonhosted.org/packages/83/67/ca0cb01df6b529f0127d23ec661e92c95ff68faf544439d86ec2331f3a52/agentops-0.3.10.tar.gz","yanked":false,"yanked_reason":null}],"0.3.11":[{"comment_text":"","digests":{"blake2b_256":"0b078e6a74f084463def9d79d2c84d79475adc0229bbfb2e57401b0616ba6d6a","md5":"e760d867d9431d1bc13798024237ab99","sha256":"75fe10b8fc86c7f5c2633139ac1c06959611f22434fc1aaa8688c3c223fde8b5"},"downloads":-1,"filename":"agentops-0.3.11-py3-none-any.whl","has_sig":false,"md5_digest":"e760d867d9431d1bc13798024237ab99","packagetype":"bdist_wheel","python_version":"py3","requires_python":">=3.7","size":50252,"upload_time":"2024-09-17T21:57:23","upload_time_iso_8601":"2024-09-17T21:57:23.085964Z","url":"https://files.pythonhosted.org/packages/0b/07/8e6a74f084463def9d79d2c84d79475adc0229bbfb2e57401b0616ba6d6a/agentops-0.3.11-py3-none-any.whl","yanked":false,"yanked_reason":null},{"comment_text":"","digests":{"blake2b_256":"3746057c552ea7ded5c954bdcbaf8a7dca07b6109633e040bf33de5f97a1289b","md5":"3b661fb76d343ec3bdef5b70fc9e5cc3","sha256":"38a2ffeeac1d722cb72c32d70e1c840424902b57934c647ef10de15478fe8f27"},"downloads":-1,"filename":"agentops-0.3.11.tar.gz","has_sig":false,"md5_digest":"3b661fb76d343ec3bdef5b70fc9e5cc3","packagetype":"sdist","python_version":"source","requires_python":">=3.7","size":48018,"upload_time":"2024-09-17T21:57:24","upload_time_iso_8601":"2024-09-17T21:57:24.699442Z","url":"https://files.pythonhosted.org/packages/37/46/057c552ea7ded5c954bdcbaf8a7dca07b6109633e040bf33de5f97a1289b/agentops-0.3.11.tar.gz","yanked":false,"yanked_reason":null}],"0.3.12":[{"comment_text":"","digests":{"blake2b_256":"ac0a9004d7a8c2865ed804ddd6968095ef100ac554bc51ada7a2f3c0b4e9142b","md5":"be18cdad4333c6013d9584b84b4c7875","sha256":"4767def30de5dd97397728efcb50398a4f6d6823c1b534846f0a9b0cb85a6d45"},"downloads":-1,"filename":"agentops-0.3.12-py3-none-any.whl","has_sig":false,"md5_digest":"be18cdad4333c6013d9584b84b4c7875","packagetype":"bdist_wheel","python_version":"py3","requires_python":">=3.7","size":50794,"upload_time":"2024-09-23T19:30:49","upload_time_iso_8601":"2024-09-23T19:30:49.050650Z","url":"https://files.pythonhosted.org/packages/ac/0a/9004d7a8c2865ed804ddd6968095ef100ac554bc51ada7a2f3c0b4e9142b/agentops-0.3.12-py3-none-any.whl","yanked":false,"yanked_reason":null},{"comment_text":"","digests":{"blake2b_256":"2c6d4f640d9fadd22f8cd7cb9857eed1f56d422f11b130ba226b947454eb0f0b","md5":"91aa981d4199ac73b4d7407547667e2f","sha256":"11ce3048656b5d146d02a4890dd50c8d2801ca5ad5caccab17d573cd8eea6e83"},"downloads":-1,"filename":"agentops-0.3.12.tar.gz","has_sig":false,"md5_digest":"91aa981d4199ac73b4d7407547667e2f","packagetype":"sdist","python_version":"source","requires_python":">=3.7","size":48525,"upload_time":"2024-09-23T19:30:50","upload_time_iso_8601":"2024-09-23T19:30:50.568151Z","url":"https://files.pythonhosted.org/packages/2c/6d/4f640d9fadd22f8cd7cb9857eed1f56d422f11b130ba226b947454eb0f0b/agentops-0.3.12.tar.gz","yanked":false,"yanked_reason":null}],"0.3.13":[{"comment_text":"","digests":{"blake2b_256":"68efa3b8adc0de2e7daa1e6e2734af9a0e37c90e3346b8a804e3fdc322c82b6c","md5":"948e9278dfc02e1a6ba2ec563296779a","sha256":"81bfdfedd990fbc3064ee42a67422ddbee07b6cd96c5fca7e124eb8c1e0cebdc"},"downloads":-1,"filename":"agentops-0.3.13-py3-none-any.whl","has_sig":false,"md5_digest":"948e9278dfc02e1a6ba2ec563296779a","packagetype":"bdist_wheel","python_version":"py3","requires_python":">=3.7","size":50813,"upload_time":"2024-10-02T18:32:59","upload_time_iso_8601":"2024-10-02T18:32:59.208892Z","url":"https://files.pythonhosted.org/packages/68/ef/a3b8adc0de2e7daa1e6e2734af9a0e37c90e3346b8a804e3fdc322c82b6c/agentops-0.3.13-py3-none-any.whl","yanked":false,"yanked_reason":null},{"comment_text":"","digests":{"blake2b_256":"3511fb06b4cee96285a5f745809d0f4efddef70d2a82112a633ed53834d6fc64","md5":"27a923eaceb4ae35abe2cf1aed1b8241","sha256":"319b7325fb79004ce996191aa21f0982489be22cc1acc2f3f6d02cdff1db2429"},"downloads":-1,"filename":"agentops-0.3.13.tar.gz","has_sig":false,"md5_digest":"27a923eaceb4ae35abe2cf1aed1b8241","packagetype":"sdist","python_version":"source","requires_python":">=3.7","size":48559,"upload_time":"2024-10-02T18:33:00","upload_time_iso_8601":"2024-10-02T18:33:00.614409Z","url":"https://files.pythonhosted.org/packages/35/11/fb06b4cee96285a5f745809d0f4efddef70d2a82112a633ed53834d6fc64/agentops-0.3.13.tar.gz","yanked":false,"yanked_reason":null}],"0.3.14":[{"comment_text":"","digests":{"blake2b_256":"1c2775ab5bf99341a6a02775e3858f54a18cbcda0f35b5c6c0f114a829d62b8e","md5":"ad2d676d293c4baa1f9afecc61654e50","sha256":"f4a2fcf1a7caf1d5383bfb66d8a9d567f3cb88fc7495cfd81ade167b0c06a4ea"},"downloads":-1,"filename":"agentops-0.3.14-py3-none-any.whl","has_sig":false,"md5_digest":"ad2d676d293c4baa1f9afecc61654e50","packagetype":"bdist_wheel","python_version":"py3","requires_python":">=3.7","size":50825,"upload_time":"2024-10-14T23:53:48","upload_time_iso_8601":"2024-10-14T23:53:48.464714Z","url":"https://files.pythonhosted.org/packages/1c/27/75ab5bf99341a6a02775e3858f54a18cbcda0f35b5c6c0f114a829d62b8e/agentops-0.3.14-py3-none-any.whl","yanked":false,"yanked_reason":null},{"comment_text":"","digests":{"blake2b_256":"46cb183fdaf40ae97ac1806ba91f6f23d55dc0a1a5cdf0881a5c834c8ca7175a","md5":"b90053253770c8e1c385b18e7172d58f","sha256":"fcb515e5743d73efee851b687692bed74797dc88e29a8327b2bbfb21d73a7447"},"downloads":-1,"filename":"agentops-0.3.14.tar.gz","has_sig":false,"md5_digest":"b90053253770c8e1c385b18e7172d58f","packagetype":"sdist","python_version":"source","requires_python":">=3.7","size":48548,"upload_time":"2024-10-14T23:53:50","upload_time_iso_8601":"2024-10-14T23:53:50.306080Z","url":"https://files.pythonhosted.org/packages/46/cb/183fdaf40ae97ac1806ba91f6f23d55dc0a1a5cdf0881a5c834c8ca7175a/agentops-0.3.14.tar.gz","yanked":false,"yanked_reason":null}],"0.3.15":[{"comment_text":"","digests":{"blake2b_256":"eadebed95f173bd304abe219b2b0a6f4e1f8e38b6733b19f2444a30fe2e731e1","md5":"7a46ccd127ffcd52eff26edaf5721bd9","sha256":"d5617108bbd9871a4250415f4e536ba33c2a6a2d2bec9342046303fb9e839f9d"},"downloads":-1,"filename":"agentops-0.3.15-py3-none-any.whl","has_sig":false,"md5_digest":"7a46ccd127ffcd52eff26edaf5721bd9","packagetype":"bdist_wheel","python_version":"py3","requires_python":">=3.7","size":55349,"upload_time":"2024-11-09T01:18:40","upload_time_iso_8601":"2024-11-09T01:18:40.622134Z","url":"https://files.pythonhosted.org/packages/ea/de/bed95f173bd304abe219b2b0a6f4e1f8e38b6733b19f2444a30fe2e731e1/agentops-0.3.15-py3-none-any.whl","yanked":false,"yanked_reason":null},{"comment_text":"","digests":{"blake2b_256":"33a40ef511dc3f23bba2d345b464223b1e7acc3c2a29230a93abb8fbcb6faebf","md5":"7af7abcf01e8d3ef64ac287e9300528f","sha256":"4358f85929d55929002cae589323d36b68fc4d12d0ea5010a80bfc4c7addc0ec"},"downloads":-1,"filename":"agentops-0.3.15.tar.gz","has_sig":false,"md5_digest":"7af7abcf01e8d3ef64ac287e9300528f","packagetype":"sdist","python_version":"source","requires_python":">=3.7","size":51296,"upload_time":"2024-11-09T01:18:42","upload_time_iso_8601":"2024-11-09T01:18:42.358185Z","url":"https://files.pythonhosted.org/packages/33/a4/0ef511dc3f23bba2d345b464223b1e7acc3c2a29230a93abb8fbcb6faebf/agentops-0.3.15.tar.gz","yanked":false,"yanked_reason":null}],"0.3.15rc1":[{"comment_text":"","digests":{"blake2b_256":"0978ac2f89ccb7b3a31742f5b70434953faff168da6cab67c0836f432919c762","md5":"7f805adf76594ac4bc169b1a111817f4","sha256":"86069387a265bc6c5fa00ffbb3f8a131254a51ee3a9b8b35af4aca823dee76f1"},"downloads":-1,"filename":"agentops-0.3.15rc1-py3-none-any.whl","has_sig":false,"md5_digest":"7f805adf76594ac4bc169b1a111817f4","packagetype":"bdist_wheel","python_version":"py3","requires_python":">=3.7","size":50798,"upload_time":"2024-10-31T04:36:11","upload_time_iso_8601":"2024-10-31T04:36:11.059082Z","url":"https://files.pythonhosted.org/packages/09/78/ac2f89ccb7b3a31742f5b70434953faff168da6cab67c0836f432919c762/agentops-0.3.15rc1-py3-none-any.whl","yanked":false,"yanked_reason":null},{"comment_text":"","digests":{"blake2b_256":"4317d6950ad32c33317509ea05a64d01ab661515165ffbd4e120148826b69ffb","md5":"5f131294c10c9b60b33ec93edc106f4f","sha256":"897ab94ae4fca8f1711216f9317dbf6f14e5d018c866086ef0b8831dc125e4ad"},"downloads":-1,"filename":"agentops-0.3.15rc1.tar.gz","has_sig":false,"md5_digest":"5f131294c10c9b60b33ec93edc106f4f","packagetype":"sdist","python_version":"source","requires_python":">=3.7","size":48739,"upload_time":"2024-10-31T04:36:12","upload_time_iso_8601":"2024-10-31T04:36:12.630857Z","url":"https://files.pythonhosted.org/packages/43/17/d6950ad32c33317509ea05a64d01ab661515165ffbd4e120148826b69ffb/agentops-0.3.15rc1.tar.gz","yanked":false,"yanked_reason":null}],"0.3.16":[{"comment_text":"","digests":{"blake2b_256":"b876e1c933480ec9ad093a841321e5c9f7f16a0af59f339ba2c840851b1af01d","md5":"d57593bb32704fae1163656f03355a71","sha256":"7763e65efe053fa81cea2a2e16f015c7603365280972e0c0709eec32c3c8569e"},"downloads":-1,"filename":"agentops-0.3.16-py3-none-any.whl","has_sig":false,"md5_digest":"d57593bb32704fae1163656f03355a71","packagetype":"bdist_wheel","python_version":"py3","requires_python":">=3.7","size":55351,"upload_time":"2024-11-09T18:44:21","upload_time_iso_8601":"2024-11-09T18:44:21.626158Z","url":"https://files.pythonhosted.org/packages/b8/76/e1c933480ec9ad093a841321e5c9f7f16a0af59f339ba2c840851b1af01d/agentops-0.3.16-py3-none-any.whl","yanked":false,"yanked_reason":null},{"comment_text":"","digests":{"blake2b_256":"aa748e77e654b37a5e0c977eca4f7e92740c1e24be39c827815e7bd8da429003","md5":"23078e1dc78ef459a667feeb904345c1","sha256":"564163eb048939d64e848c7e6caf25d6c0aee31200623ef97efe492f090f8939"},"downloads":-1,"filename":"agentops-0.3.16.tar.gz","has_sig":false,"md5_digest":"23078e1dc78ef459a667feeb904345c1","packagetype":"sdist","python_version":"source","requires_python":">=3.7","size":51308,"upload_time":"2024-11-09T18:44:23","upload_time_iso_8601":"2024-11-09T18:44:23.037514Z","url":"https://files.pythonhosted.org/packages/aa/74/8e77e654b37a5e0c977eca4f7e92740c1e24be39c827815e7bd8da429003/agentops-0.3.16.tar.gz","yanked":false,"yanked_reason":null}],"0.3.17":[{"comment_text":"","digests":{"blake2b_256":"6c3038a659671eec20fcae759bd69655ec45b08c4e875627b33e3b05bd46f299","md5":"93bbe3bd4ee492e7e73780c07897b017","sha256":"0d24dd082270a76c98ad0391101d5b5c3d01e389c5032389ecd551285e4b0662"},"downloads":-1,"filename":"agentops-0.3.17-py3-none-any.whl","has_sig":false,"md5_digest":"93bbe3bd4ee492e7e73780c07897b017","packagetype":"bdist_wheel","python_version":"py3","requires_python":">=3.7","size":55503,"upload_time":"2024-11-10T02:39:28","upload_time_iso_8601":"2024-11-10T02:39:28.884052Z","url":"https://files.pythonhosted.org/packages/6c/30/38a659671eec20fcae759bd69655ec45b08c4e875627b33e3b05bd46f299/agentops-0.3.17-py3-none-any.whl","yanked":false,"yanked_reason":null},{"comment_text":"","digests":{"blake2b_256":"2131d9a3747df04b7915ee1cffaa4a5636f8ed0e1385e5236b0da085ccce936a","md5":"49e8cf186203cadaa39301c4ce5fda42","sha256":"a893cc7c37eda720ab59e8facaa2774cc23d125648aa00539ae485ff592e8b77"},"downloads":-1,"filename":"agentops-0.3.17.tar.gz","has_sig":false,"md5_digest":"49e8cf186203cadaa39301c4ce5fda42","packagetype":"sdist","python_version":"source","requires_python":">=3.7","size":51469,"upload_time":"2024-11-10T02:39:30","upload_time_iso_8601":"2024-11-10T02:39:30.636907Z","url":"https://files.pythonhosted.org/packages/21/31/d9a3747df04b7915ee1cffaa4a5636f8ed0e1385e5236b0da085ccce936a/agentops-0.3.17.tar.gz","yanked":false,"yanked_reason":null}],"0.3.18":[{"comment_text":"","digests":{"blake2b_256":"978dbd4cad95dad722dc2d3e4179feab1058ef846828c0e15e51e8bfaea373ee","md5":"d9afc3636cb969c286738ce02ed12196","sha256":"8b48d8a1662f276653430fd541c77fa4f9a15a43e881b518ff88ea56925afcf7"},"downloads":-1,"filename":"agentops-0.3.18-py3-none-any.whl","has_sig":false,"md5_digest":"d9afc3636cb969c286738ce02ed12196","packagetype":"bdist_wheel","python_version":"py3","requires_python":">=3.7","size":58032,"upload_time":"2024-11-19T19:06:19","upload_time_iso_8601":"2024-11-19T19:06:19.068511Z","url":"https://files.pythonhosted.org/packages/97/8d/bd4cad95dad722dc2d3e4179feab1058ef846828c0e15e51e8bfaea373ee/agentops-0.3.18-py3-none-any.whl","yanked":false,"yanked_reason":null},{"comment_text":"","digests":{"blake2b_256":"c55246bb2f29b9e5f2e1d8b124296b7794934a9048de635d9e7d6a95e791ad7b","md5":"02a4fc081499360aac58485a94a6ca33","sha256":"4d509754df7be52579597cc9f53939c5218131a0379463e0ff6f6f40cde9fcc4"},"downloads":-1,"filename":"agentops-0.3.18.tar.gz","has_sig":false,"md5_digest":"02a4fc081499360aac58485a94a6ca33","packagetype":"sdist","python_version":"source","requires_python":">=3.7","size":55394,"upload_time":"2024-11-19T19:06:21","upload_time_iso_8601":"2024-11-19T19:06:21.306448Z","url":"https://files.pythonhosted.org/packages/c5/52/46bb2f29b9e5f2e1d8b124296b7794934a9048de635d9e7d6a95e791ad7b/agentops-0.3.18.tar.gz","yanked":false,"yanked_reason":null}],"0.3.19":[{"comment_text":"","digests":{"blake2b_256":"fc1e48616d2db40717d560a561e13521009655d447388f944f12f2b3811e6d7d","md5":"a9e23f1d31821585017e97633b058233","sha256":"1888a47dd3d9b92c5f246cdeeab333def5acbd26833d3148c63e8793457405b3"},"downloads":-1,"filename":"agentops-0.3.19-py3-none-any.whl","has_sig":false,"md5_digest":"a9e23f1d31821585017e97633b058233","packagetype":"bdist_wheel","python_version":"py3","requires_python":">=3.7","size":38648,"upload_time":"2024-12-04T00:54:00","upload_time_iso_8601":"2024-12-04T00:54:00.173948Z","url":"https://files.pythonhosted.org/packages/fc/1e/48616d2db40717d560a561e13521009655d447388f944f12f2b3811e6d7d/agentops-0.3.19-py3-none-any.whl","yanked":true,"yanked_reason":"Broken - dependency, please install 0.3.18"},{"comment_text":"","digests":{"blake2b_256":"b319bb0e9895cb6da29f764f8d7b95b10ac8fde400bc17028f9bd486e9574dbe","md5":"f6424c41464d438007e9628748a0bea6","sha256":"ca0d4ba35ae699169ae20f74f72ca6a5780a8768ba2a2c32589fc5292ed81674"},"downloads":-1,"filename":"agentops-0.3.19.tar.gz","has_sig":false,"md5_digest":"f6424c41464d438007e9628748a0bea6","packagetype":"sdist","python_version":"source","requires_python":">=3.7","size":48360,"upload_time":"2024-12-04T00:54:01","upload_time_iso_8601":"2024-12-04T00:54:01.418776Z","url":"https://files.pythonhosted.org/packages/b3/19/bb0e9895cb6da29f764f8d7b95b10ac8fde400bc17028f9bd486e9574dbe/agentops-0.3.19.tar.gz","yanked":true,"yanked_reason":"Broken dependency, please install 0.3.18"}],"0.3.2":[{"comment_text":"","digests":{"blake2b_256":"9d2c23b745a61d48df788b8020e5ea37e94f9da59b322a17accafe18d8cb4006","md5":"62d576d9518a627fe4232709c0721eff","sha256":"b35988e04378624204572bb3d7a454094f879ea573f05b57d4e75ab0bfbb82af"},"downloads":-1,"filename":"agentops-0.3.2-py3-none-any.whl","has_sig":false,"md5_digest":"62d576d9518a627fe4232709c0721eff","packagetype":"bdist_wheel","python_version":"py3","requires_python":">=3.7","size":39527,"upload_time":"2024-07-21T03:09:56","upload_time_iso_8601":"2024-07-21T03:09:56.844372Z","url":"https://files.pythonhosted.org/packages/9d/2c/23b745a61d48df788b8020e5ea37e94f9da59b322a17accafe18d8cb4006/agentops-0.3.2-py3-none-any.whl","yanked":false,"yanked_reason":null},{"comment_text":"","digests":{"blake2b_256":"d2a1cc21406646c065e83435fe30fa205b99b2204d8074eca31926a5f8ef4381","md5":"30b247bcae25b181485a89213518241c","sha256":"55559ac4a43634831dfa8937c2597c28e332809dc7c6bb3bc3c8b233442e224c"},"downloads":-1,"filename":"agentops-0.3.2.tar.gz","has_sig":false,"md5_digest":"30b247bcae25b181485a89213518241c","packagetype":"sdist","python_version":"source","requires_python":">=3.7","size":41894,"upload_time":"2024-07-21T03:09:58","upload_time_iso_8601":"2024-07-21T03:09:58.409826Z","url":"https://files.pythonhosted.org/packages/d2/a1/cc21406646c065e83435fe30fa205b99b2204d8074eca31926a5f8ef4381/agentops-0.3.2.tar.gz","yanked":false,"yanked_reason":null}],"0.3.20":[{"comment_text":"","digests":{"blake2b_256":"a854ae9147a490dd9bd03ab7bfc5af47f40ff675840a9aa143896b385a8f8d3a","md5":"a13af8737ddff8a0c7c0f05cee70085f","sha256":"b5396e11b0bfef46b85604e8e36ab17668057711edd56f1edb0a067b8676fdcc"},"downloads":-1,"filename":"agentops-0.3.20-py3-none-any.whl","has_sig":false,"md5_digest":"a13af8737ddff8a0c7c0f05cee70085f","packagetype":"bdist_wheel","python_version":"py3","requires_python":">=3.7","size":38674,"upload_time":"2024-12-07T00:06:31","upload_time_iso_8601":"2024-12-07T00:06:31.901162Z","url":"https://files.pythonhosted.org/packages/a8/54/ae9147a490dd9bd03ab7bfc5af47f40ff675840a9aa143896b385a8f8d3a/agentops-0.3.20-py3-none-any.whl","yanked":true,"yanked_reason":"Wrong - release"},{"comment_text":"","digests":{"blake2b_256":"c1eb19d04c801854ba75e235eb87c51a6a9c5b1a89e8579cb745c83f8bf84e08","md5":"11754497191d8340eda7a831720d9b74","sha256":"c71406294804a82795310a4afc492064a8884b1ba47e12607230975bc1291ce3"},"downloads":-1,"filename":"agentops-0.3.20.tar.gz","has_sig":false,"md5_digest":"11754497191d8340eda7a831720d9b74","packagetype":"sdist","python_version":"source","requires_python":">=3.7","size":48332,"upload_time":"2024-12-07T00:06:33","upload_time_iso_8601":"2024-12-07T00:06:33.568362Z","url":"https://files.pythonhosted.org/packages/c1/eb/19d04c801854ba75e235eb87c51a6a9c5b1a89e8579cb745c83f8bf84e08/agentops-0.3.20.tar.gz","yanked":true,"yanked_reason":"Wrong release"}],"0.3.20rc1":[{"comment_text":"","digests":{"blake2b_256":"073de7eba58e2a60c0136eee2760b20f99607001d372de26505feee891e0976b","md5":"73c6ac515ee9d555e27a7ba7e26e3a46","sha256":"079ea8138938e27a3e1319a235a6f4cf98c0d6846731d854aa83b8422d570bda"},"downloads":-1,"filename":"agentops-0.3.20rc1-py3-none-any.whl","has_sig":false,"md5_digest":"73c6ac515ee9d555e27a7ba7e26e3a46","packagetype":"bdist_wheel","python_version":"py3","requires_python":">=3.7","size":38718,"upload_time":"2024-12-07T00:10:18","upload_time_iso_8601":"2024-12-07T00:10:18.796963Z","url":"https://files.pythonhosted.org/packages/07/3d/e7eba58e2a60c0136eee2760b20f99607001d372de26505feee891e0976b/agentops-0.3.20rc1-py3-none-any.whl","yanked":false,"yanked_reason":null},{"comment_text":"","digests":{"blake2b_256":"02ff111d618c21aad946caedb666030f1f374a0d558228b9061ea2b46acb6bcd","md5":"17062e985b931dc85b4855922d7842ce","sha256":"ef48447e07a3eded246b2f7e10bba74422a34563ffdc667ac16b2d3383475a3f"},"downloads":-1,"filename":"agentops-0.3.20rc1.tar.gz","has_sig":false,"md5_digest":"17062e985b931dc85b4855922d7842ce","packagetype":"sdist","python_version":"source","requires_python":">=3.7","size":48329,"upload_time":"2024-12-07T00:10:20","upload_time_iso_8601":"2024-12-07T00:10:20.510407Z","url":"https://files.pythonhosted.org/packages/02/ff/111d618c21aad946caedb666030f1f374a0d558228b9061ea2b46acb6bcd/agentops-0.3.20rc1.tar.gz","yanked":false,"yanked_reason":null}],"0.3.20rc10":[{"comment_text":"","digests":{"blake2b_256":"a7274706d8d9c8f4abecc1dda2b9b02cd02ffe895220bd39f58322a46ccc7254","md5":"2c66a93c691c6b8cac2f2dc8fab9efae","sha256":"3c10d77f2fe88b61d97ad007820c1ba968c62f692986ea2b2cbfd8b22ec9e5bc"},"downloads":-1,"filename":"agentops-0.3.20rc10-py3-none-any.whl","has_sig":false,"md5_digest":"2c66a93c691c6b8cac2f2dc8fab9efae","packagetype":"bdist_wheel","python_version":"py3","requires_python":">=3.7","size":57423,"upload_time":"2024-12-10T03:41:04","upload_time_iso_8601":"2024-12-10T03:41:04.579814Z","url":"https://files.pythonhosted.org/packages/a7/27/4706d8d9c8f4abecc1dda2b9b02cd02ffe895220bd39f58322a46ccc7254/agentops-0.3.20rc10-py3-none-any.whl","yanked":false,"yanked_reason":null},{"comment_text":"","digests":{"blake2b_256":"efe9e304f465945f57e4c6d35cd35fff53dc2a2e36b9b32793fa57017467b0c2","md5":"9882d32866b94d925ba36ac376c30bea","sha256":"f0c72c20e7fe41054c22c6257420314863549dd91428a892ac9b47b81cdfcc8c"},"downloads":-1,"filename":"agentops-0.3.20rc10.tar.gz","has_sig":false,"md5_digest":"9882d32866b94d925ba36ac376c30bea","packagetype":"sdist","python_version":"source","requires_python":">=3.7","size":57564,"upload_time":"2024-12-10T03:41:06","upload_time_iso_8601":"2024-12-10T03:41:06.899043Z","url":"https://files.pythonhosted.org/packages/ef/e9/e304f465945f57e4c6d35cd35fff53dc2a2e36b9b32793fa57017467b0c2/agentops-0.3.20rc10.tar.gz","yanked":false,"yanked_reason":null}],"0.3.20rc11":[{"comment_text":"","digests":{"blake2b_256":"8dbf598ec2532b713a228f4041c9b2c10358cd43e6aecf6128d0988a0b5f103e","md5":"d9ab67a850aefcb5bf9467b48f74675d","sha256":"3e5d4c19de6c58ae684693f47a2f03db35eaf4cd6d8aafc1e804a134462c2b55"},"downloads":-1,"filename":"agentops-0.3.20rc11-py3-none-any.whl","has_sig":false,"md5_digest":"d9ab67a850aefcb5bf9467b48f74675d","packagetype":"bdist_wheel","python_version":"py3","requires_python":">=3.7","size":60280,"upload_time":"2024-12-10T22:45:05","upload_time_iso_8601":"2024-12-10T22:45:05.280119Z","url":"https://files.pythonhosted.org/packages/8d/bf/598ec2532b713a228f4041c9b2c10358cd43e6aecf6128d0988a0b5f103e/agentops-0.3.20rc11-py3-none-any.whl","yanked":false,"yanked_reason":null},{"comment_text":"","digests":{"blake2b_256":"210642e51fff6a4537fb811a15bc22d00343145285c6246dc069433d61436e1b","md5":"ca5279f4cb6ad82e06ef542a2d08d06e","sha256":"9211489c6a01bc9cda4061826f8b80d0989cfcd7fbabe1dd2ed5a5cb76b3d6f0"},"downloads":-1,"filename":"agentops-0.3.20rc11.tar.gz","has_sig":false,"md5_digest":"ca5279f4cb6ad82e06ef542a2d08d06e","packagetype":"sdist","python_version":"source","requires_python":">=3.7","size":59718,"upload_time":"2024-12-10T22:45:09","upload_time_iso_8601":"2024-12-10T22:45:09.616947Z","url":"https://files.pythonhosted.org/packages/21/06/42e51fff6a4537fb811a15bc22d00343145285c6246dc069433d61436e1b/agentops-0.3.20rc11.tar.gz","yanked":false,"yanked_reason":null}],"0.3.20rc12":[{"comment_text":"","digests":{"blake2b_256":"dc281db6f49f10ac849683de1d7f5b5ef492be2a996325302167b8388f375d51","md5":"8b2611d2510f0d4fac7ab824d7658ff7","sha256":"9237652d28db89315c49c0705829b291c17280e07d41272f909e2609acec650b"},"downloads":-1,"filename":"agentops-0.3.20rc12-py3-none-any.whl","has_sig":false,"md5_digest":"8b2611d2510f0d4fac7ab824d7658ff7","packagetype":"bdist_wheel","python_version":"py3","requires_python":">=3.7","size":60282,"upload_time":"2024-12-10T23:10:54","upload_time_iso_8601":"2024-12-10T23:10:54.516317Z","url":"https://files.pythonhosted.org/packages/dc/28/1db6f49f10ac849683de1d7f5b5ef492be2a996325302167b8388f375d51/agentops-0.3.20rc12-py3-none-any.whl","yanked":false,"yanked_reason":null},{"comment_text":"","digests":{"blake2b_256":"10c073cb9a55592f55bb44c9206f50f41d7b7a8a8d6fd67d42f40c8f9f184b0e","md5":"02b3a68f3491564af2e29f0f216eea1e","sha256":"d4d3a73ac34b2a00edb6e6b5b220cbb031bb76ff58d85e2096b536be24aee4fe"},"downloads":-1,"filename":"agentops-0.3.20rc12.tar.gz","has_sig":false,"md5_digest":"02b3a68f3491564af2e29f0f216eea1e","packagetype":"sdist","python_version":"source","requires_python":">=3.7","size":59731,"upload_time":"2024-12-10T23:10:56","upload_time_iso_8601":"2024-12-10T23:10:56.822803Z","url":"https://files.pythonhosted.org/packages/10/c0/73cb9a55592f55bb44c9206f50f41d7b7a8a8d6fd67d42f40c8f9f184b0e/agentops-0.3.20rc12.tar.gz","yanked":false,"yanked_reason":null}],"0.3.20rc13":[{"comment_text":"","digests":{"blake2b_256":"4ed48a97563074235f266281167c70ab90833c195e2b704087e414509ae3ec32","md5":"c86fe22044483f94bc044a3bf7b054b7","sha256":"2fbb3b55701d9aea64f622e7e29aa417772e897e2414f74ed3954d99009d224f"},"downloads":-1,"filename":"agentops-0.3.20rc13-py3-none-any.whl","has_sig":false,"md5_digest":"c86fe22044483f94bc044a3bf7b054b7","packagetype":"bdist_wheel","python_version":"py3","requires_python":">=3.7","size":64724,"upload_time":"2024-12-10T23:27:50","upload_time_iso_8601":"2024-12-10T23:27:50.895316Z","url":"https://files.pythonhosted.org/packages/4e/d4/8a97563074235f266281167c70ab90833c195e2b704087e414509ae3ec32/agentops-0.3.20rc13-py3-none-any.whl","yanked":false,"yanked_reason":null},{"comment_text":"","digests":{"blake2b_256":"767e59c6f34e9a067d9152021de7e3146e5c0f69f36434dcb3026ff03f382489","md5":"152a70647d5ff28fe851e4cc406d8fb4","sha256":"b7a6d1d7f603bbb2605cc747762ae866bdee53941c4c76087c9f0f0a5efad03b"},"downloads":-1,"filename":"agentops-0.3.20rc13.tar.gz","has_sig":false,"md5_digest":"152a70647d5ff28fe851e4cc406d8fb4","packagetype":"sdist","python_version":"source","requires_python":">=3.7","size":63242,"upload_time":"2024-12-10T23:27:53","upload_time_iso_8601":"2024-12-10T23:27:53.657606Z","url":"https://files.pythonhosted.org/packages/76/7e/59c6f34e9a067d9152021de7e3146e5c0f69f36434dcb3026ff03f382489/agentops-0.3.20rc13.tar.gz","yanked":false,"yanked_reason":null}],"0.3.20rc2":[{"comment_text":"","digests":{"blake2b_256":"cebbbca58531e21f4c1c92cbe6ba15d0f308ff8f3b27083cd0ce6358c7d1d117","md5":"5a9fcd99e0b6e3b24e721b22c3ee5907","sha256":"ada95d42e82abef16c1e83443dc42d02bb470ee48b1fa8f2d58a20703511a7be"},"downloads":-1,"filename":"agentops-0.3.20rc2-py3-none-any.whl","has_sig":false,"md5_digest":"5a9fcd99e0b6e3b24e721b22c3ee5907","packagetype":"bdist_wheel","python_version":"py3","requires_python":">=3.7","size":38716,"upload_time":"2024-12-07T00:20:01","upload_time_iso_8601":"2024-12-07T00:20:01.561074Z","url":"https://files.pythonhosted.org/packages/ce/bb/bca58531e21f4c1c92cbe6ba15d0f308ff8f3b27083cd0ce6358c7d1d117/agentops-0.3.20rc2-py3-none-any.whl","yanked":false,"yanked_reason":null},{"comment_text":"","digests":{"blake2b_256":"124aec14492566949b7383ae321cb40c1edc18940712b277c08d32392566f7a8","md5":"ff8db0075584474e35784b080fb9b6b1","sha256":"60462b82390e78fd21312c5db45f0f48dfcc9c9ab354e6bf232db557ccf57c13"},"downloads":-1,"filename":"agentops-0.3.20rc2.tar.gz","has_sig":false,"md5_digest":"ff8db0075584474e35784b080fb9b6b1","packagetype":"sdist","python_version":"source","requires_python":">=3.7","size":48341,"upload_time":"2024-12-07T00:20:02","upload_time_iso_8601":"2024-12-07T00:20:02.519240Z","url":"https://files.pythonhosted.org/packages/12/4a/ec14492566949b7383ae321cb40c1edc18940712b277c08d32392566f7a8/agentops-0.3.20rc2.tar.gz","yanked":false,"yanked_reason":null}],"0.3.20rc4":[{"comment_text":"","digests":{"blake2b_256":"a1551125b2b3823fcb3f3afa3c6b9621541799ac329622ee21038babbfbedf39","md5":"a82f1b73347d3a2fe33f31cec01ca376","sha256":"72253950b46a11b5b1163b13bbb9d5b769e6cdb7b102acf46efac8cf02f7eaac"},"downloads":-1,"filename":"agentops-0.3.20rc4-py3-none-any.whl","has_sig":false,"md5_digest":"a82f1b73347d3a2fe33f31cec01ca376","packagetype":"bdist_wheel","python_version":"py3","requires_python":">=3.7","size":38719,"upload_time":"2024-12-07T00:53:45","upload_time_iso_8601":"2024-12-07T00:53:45.212239Z","url":"https://files.pythonhosted.org/packages/a1/55/1125b2b3823fcb3f3afa3c6b9621541799ac329622ee21038babbfbedf39/agentops-0.3.20rc4-py3-none-any.whl","yanked":false,"yanked_reason":null},{"comment_text":"","digests":{"blake2b_256":"a180420ef26926052b12d1c2010360b4037f6765321055ce7e09c6bfaeac3480","md5":"1a314ff81d87a774e5e1cf338151a353","sha256":"4218fcfa42644dd86ee50ac7806d08783e4629db30b127bc8011c9c3523eeb5c"},"downloads":-1,"filename":"agentops-0.3.20rc4.tar.gz","has_sig":false,"md5_digest":"1a314ff81d87a774e5e1cf338151a353","packagetype":"sdist","python_version":"source","requires_python":">=3.7","size":48332,"upload_time":"2024-12-07T00:53:47","upload_time_iso_8601":"2024-12-07T00:53:47.581677Z","url":"https://files.pythonhosted.org/packages/a1/80/420ef26926052b12d1c2010360b4037f6765321055ce7e09c6bfaeac3480/agentops-0.3.20rc4.tar.gz","yanked":false,"yanked_reason":null}],"0.3.20rc5":[{"comment_text":"","digests":{"blake2b_256":"7747e61c5387124f53a3095261427888ab88e192828e3bb8be92660bf4e008d0","md5":"fd7343ddf99f077d1a159b87d84ed79c","sha256":"97df38116ec7fe337fc04b800e423aa8b5e69681565c02dc4af3e9c60764827e"},"downloads":-1,"filename":"agentops-0.3.20rc5-py3-none-any.whl","has_sig":false,"md5_digest":"fd7343ddf99f077d1a159b87d84ed79c","packagetype":"bdist_wheel","python_version":"py3","requires_python":">=3.7","size":44545,"upload_time":"2024-12-07T01:38:17","upload_time_iso_8601":"2024-12-07T01:38:17.177125Z","url":"https://files.pythonhosted.org/packages/77/47/e61c5387124f53a3095261427888ab88e192828e3bb8be92660bf4e008d0/agentops-0.3.20rc5-py3-none-any.whl","yanked":false,"yanked_reason":null},{"comment_text":"","digests":{"blake2b_256":"145fa0bf5ee5b56dacf63b9712ac62169c585c6222efe043cc77f3148f709965","md5":"20a32d514b5d51851dbcbdfb2c189491","sha256":"48111083dab1fc30f0545e0812c4aab00fc9e9d48de42de95d254699396992a8"},"downloads":-1,"filename":"agentops-0.3.20rc5.tar.gz","has_sig":false,"md5_digest":"20a32d514b5d51851dbcbdfb2c189491","packagetype":"sdist","python_version":"source","requires_python":">=3.7","size":53243,"upload_time":"2024-12-07T01:38:18","upload_time_iso_8601":"2024-12-07T01:38:18.772880Z","url":"https://files.pythonhosted.org/packages/14/5f/a0bf5ee5b56dacf63b9712ac62169c585c6222efe043cc77f3148f709965/agentops-0.3.20rc5.tar.gz","yanked":false,"yanked_reason":null}],"0.3.20rc6":[{"comment_text":"","digests":{"blake2b_256":"85f3a5ae3d8d47aa5160a5c805551d75077cad61bff9626abe44079d29d1c299","md5":"30f87c628c530e82e27b8bc2d2a46d8a","sha256":"d03f16832b3a5670d9c3273b95c9d9def772c203b2cd4ac52ae0e7f6d3b1b9e4"},"downloads":-1,"filename":"agentops-0.3.20rc6-py3-none-any.whl","has_sig":false,"md5_digest":"30f87c628c530e82e27b8bc2d2a46d8a","packagetype":"bdist_wheel","python_version":"py3","requires_python":">=3.7","size":61844,"upload_time":"2024-12-07T01:49:11","upload_time_iso_8601":"2024-12-07T01:49:11.801219Z","url":"https://files.pythonhosted.org/packages/85/f3/a5ae3d8d47aa5160a5c805551d75077cad61bff9626abe44079d29d1c299/agentops-0.3.20rc6-py3-none-any.whl","yanked":false,"yanked_reason":null},{"comment_text":"","digests":{"blake2b_256":"060e24f42ed1de3d892355f3ba90f0b7f659855fafd18851e59aa7174fa30615","md5":"384c60ee11b827b8bad31cef20a35a17","sha256":"45aa4797269214d41858537d95050964f330651da5c7412b2895e714a81f30f5"},"downloads":-1,"filename":"agentops-0.3.20rc6.tar.gz","has_sig":false,"md5_digest":"384c60ee11b827b8bad31cef20a35a17","packagetype":"sdist","python_version":"source","requires_python":">=3.7","size":61004,"upload_time":"2024-12-07T01:49:13","upload_time_iso_8601":"2024-12-07T01:49:13.917920Z","url":"https://files.pythonhosted.org/packages/06/0e/24f42ed1de3d892355f3ba90f0b7f659855fafd18851e59aa7174fa30615/agentops-0.3.20rc6.tar.gz","yanked":false,"yanked_reason":null}],"0.3.20rc7":[{"comment_text":"","digests":{"blake2b_256":"d502edf7ba8aff1a994176da4c95688c9ba0428ac3bd9a0db2392fe5009162a9","md5":"9b43c5e2df12abac01ffc5262e991825","sha256":"95972115c5c753ceee477834de902afaf0664107048e44eee2c65e74e05656a2"},"downloads":-1,"filename":"agentops-0.3.20rc7-py3-none-any.whl","has_sig":false,"md5_digest":"9b43c5e2df12abac01ffc5262e991825","packagetype":"bdist_wheel","python_version":"py3","requires_python":">=3.7","size":40117,"upload_time":"2024-12-07T02:12:48","upload_time_iso_8601":"2024-12-07T02:12:48.512036Z","url":"https://files.pythonhosted.org/packages/d5/02/edf7ba8aff1a994176da4c95688c9ba0428ac3bd9a0db2392fe5009162a9/agentops-0.3.20rc7-py3-none-any.whl","yanked":false,"yanked_reason":null},{"comment_text":"","digests":{"blake2b_256":"5d7029d8d02fcf6db627c6b20ceab974c455e23a25fc0e991c0a8d0eaebda523","md5":"9de760856bed3f7adbd1d0ab7ba0a63a","sha256":"7c793b7b199a61ca61366ddb8fd94986fac262ef6514918c3baaa08184b86669"},"downloads":-1,"filename":"agentops-0.3.20rc7.tar.gz","has_sig":false,"md5_digest":"9de760856bed3f7adbd1d0ab7ba0a63a","packagetype":"sdist","python_version":"source","requires_python":">=3.7","size":49661,"upload_time":"2024-12-07T02:12:50","upload_time_iso_8601":"2024-12-07T02:12:50.120388Z","url":"https://files.pythonhosted.org/packages/5d/70/29d8d02fcf6db627c6b20ceab974c455e23a25fc0e991c0a8d0eaebda523/agentops-0.3.20rc7.tar.gz","yanked":false,"yanked_reason":null}],"0.3.20rc8":[{"comment_text":"","digests":{"blake2b_256":"6d0f66418c0b20f40fe11de50f29481abdb266ff641ac6166eab9eac3d7364d2","md5":"52a2cea48e48d1818169c07507a6c7a9","sha256":"8cf2e9fe6400a4fb4367a039cacc5d76339a8fd2749a44243389547e928e545c"},"downloads":-1,"filename":"agentops-0.3.20rc8-py3-none-any.whl","has_sig":false,"md5_digest":"52a2cea48e48d1818169c07507a6c7a9","packagetype":"bdist_wheel","python_version":"py3","requires_python":">=3.7","size":57414,"upload_time":"2024-12-07T02:17:51","upload_time_iso_8601":"2024-12-07T02:17:51.404804Z","url":"https://files.pythonhosted.org/packages/6d/0f/66418c0b20f40fe11de50f29481abdb266ff641ac6166eab9eac3d7364d2/agentops-0.3.20rc8-py3-none-any.whl","yanked":false,"yanked_reason":null},{"comment_text":"","digests":{"blake2b_256":"4d18250b066f23ccbb22f2bba8df101361abd5724ddcef59a4d63d4539c7cd82","md5":"f7887176e88d4434e38e237850363b80","sha256":"a06e7939dd4d59c9880ded1b129fd4548b34be5530a46cf043326740bdfeca56"},"downloads":-1,"filename":"agentops-0.3.20rc8.tar.gz","has_sig":false,"md5_digest":"f7887176e88d4434e38e237850363b80","packagetype":"sdist","python_version":"source","requires_python":">=3.7","size":57521,"upload_time":"2024-12-07T02:17:53","upload_time_iso_8601":"2024-12-07T02:17:53.055737Z","url":"https://files.pythonhosted.org/packages/4d/18/250b066f23ccbb22f2bba8df101361abd5724ddcef59a4d63d4539c7cd82/agentops-0.3.20rc8.tar.gz","yanked":false,"yanked_reason":null}],"0.3.21":[{"comment_text":"","digests":{"blake2b_256":"c4cb3b6cc5a08d11d9e56501f980222da0fa41814b7d6948a7f6354f31739af6","md5":"c7592f9e7993dbe307fbffd7e4da1e51","sha256":"4f98beecdce4c7cbee80ec26658a9657ba307a1fb2910b589f85325d3259b75b"},"downloads":-1,"filename":"agentops-0.3.21-py3-none-any.whl","has_sig":false,"md5_digest":"c7592f9e7993dbe307fbffd7e4da1e51","packagetype":"bdist_wheel","python_version":"py3","requires_python":">=3.7","size":64701,"upload_time":"2024-12-11T12:24:00","upload_time_iso_8601":"2024-12-11T12:24:00.934724Z","url":"https://files.pythonhosted.org/packages/c4/cb/3b6cc5a08d11d9e56501f980222da0fa41814b7d6948a7f6354f31739af6/agentops-0.3.21-py3-none-any.whl","yanked":false,"yanked_reason":null},{"comment_text":"","digests":{"blake2b_256":"83f6bfd27fa4b948c353eaff579dafdf4eb54833f5c526e00c6f2faee4b467a8","md5":"83d7666511cccf3b0d4354cebd99b110","sha256":"d8e8d1f6d154554dba64ec5b139905bf76c68f21575af9fa2ca1697277fe36f2"},"downloads":-1,"filename":"agentops-0.3.21.tar.gz","has_sig":false,"md5_digest":"83d7666511cccf3b0d4354cebd99b110","packagetype":"sdist","python_version":"source","requires_python":">=3.7","size":63185,"upload_time":"2024-12-11T12:24:02","upload_time_iso_8601":"2024-12-11T12:24:02.068404Z","url":"https://files.pythonhosted.org/packages/83/f6/bfd27fa4b948c353eaff579dafdf4eb54833f5c526e00c6f2faee4b467a8/agentops-0.3.21.tar.gz","yanked":false,"yanked_reason":null}],"0.3.22":[{"comment_text":"","digests":{"blake2b_256":"11e721b42168ecfd0a9fff9dea51201646b6e62c4f52c8cd9c2a6400125d7234","md5":"26061ab467e358b63251f9547275bbbd","sha256":"992f4f31d80e8b0b2098abf58ae2707c60538e4b66e5aec8cf49fb269d5a2adc"},"downloads":-1,"filename":"agentops-0.3.22-py3-none-any.whl","has_sig":false,"md5_digest":"26061ab467e358b63251f9547275bbbd","packagetype":"bdist_wheel","python_version":"py3","requires_python":"<3.14,>=3.9","size":39539,"upload_time":"2025-01-11T03:21:39","upload_time_iso_8601":"2025-01-11T03:21:39.093169Z","url":"https://files.pythonhosted.org/packages/11/e7/21b42168ecfd0a9fff9dea51201646b6e62c4f52c8cd9c2a6400125d7234/agentops-0.3.22-py3-none-any.whl","yanked":true,"yanked_reason":"Broken - dependency"},{"comment_text":"","digests":{"blake2b_256":"e067e61aa4c2e329da10b5e95d325091e599d8a00a28843a54bdcefa7a2eef8d","md5":"bcf45b6c4c56884ed2409f835571af62","sha256":"705d772b6994f8bab0cd163b24602009353f7906c72d9db008af11683f6e9341"},"downloads":-1,"filename":"agentops-0.3.22.tar.gz","has_sig":false,"md5_digest":"bcf45b6c4c56884ed2409f835571af62","packagetype":"sdist","python_version":"source","requires_python":"<3.14,>=3.9","size":52845,"upload_time":"2025-01-11T03:21:41","upload_time_iso_8601":"2025-01-11T03:21:41.762282Z","url":"https://files.pythonhosted.org/packages/e0/67/e61aa4c2e329da10b5e95d325091e599d8a00a28843a54bdcefa7a2eef8d/agentops-0.3.22.tar.gz","yanked":true,"yanked_reason":"Broken dependency"}],"0.3.23":[{"comment_text":null,"digests":{"blake2b_256":"e67de1434765cf0a3d62372b74f47919aa17c0b01909823f7d3ee705edf821a9","md5":"1f0f02509b8ba713db72e57a072f01a6","sha256":"ecfff77d8f9006361ef2a2e8593271e97eb54b7b504abfb8abd6504006baca56"},"downloads":-1,"filename":"agentops-0.3.23-py3-none-any.whl","has_sig":false,"md5_digest":"1f0f02509b8ba713db72e57a072f01a6","packagetype":"bdist_wheel","python_version":"py3","requires_python":"<3.14,>=3.9","size":70098,"upload_time":"2025-01-12T02:11:56","upload_time_iso_8601":"2025-01-12T02:11:56.319763Z","url":"https://files.pythonhosted.org/packages/e6/7d/e1434765cf0a3d62372b74f47919aa17c0b01909823f7d3ee705edf821a9/agentops-0.3.23-py3-none-any.whl","yanked":false,"yanked_reason":null},{"comment_text":null,"digests":{"blake2b_256":"5c7fa4fd91f8fd819e1ecfdc608d1c7ade83de0f9dddd868e2c2c139a2fdae25","md5":"b7922399f81fb26517eb69fc7fef97c9","sha256":"4e4de49caeaf567b8746082f84a8cdd65afe2c698720f6f40251bbc4fdffe4c9"},"downloads":-1,"filename":"agentops-0.3.23.tar.gz","has_sig":false,"md5_digest":"b7922399f81fb26517eb69fc7fef97c9","packagetype":"sdist","python_version":"source","requires_python":"<3.14,>=3.9","size":64225,"upload_time":"2025-01-12T02:11:59","upload_time_iso_8601":"2025-01-12T02:11:59.360077Z","url":"https://files.pythonhosted.org/packages/5c/7f/a4fd91f8fd819e1ecfdc608d1c7ade83de0f9dddd868e2c2c139a2fdae25/agentops-0.3.23.tar.gz","yanked":false,"yanked_reason":null}],"0.3.24":[{"comment_text":null,"digests":{"blake2b_256":"254ea7d131802bac2ece5302ebf78dcef1ba1ba2f8b3a51fbe44c7f52bae6a53","md5":"39c39d8a7f1285add0fec21830a89a4a","sha256":"c5dfc8098b0dd49ddd819aa55280d07f8bfbf2f8fa088fc51ff5849b65062b10"},"downloads":-1,"filename":"agentops-0.3.24-py3-none-any.whl","has_sig":false,"md5_digest":"39c39d8a7f1285add0fec21830a89a4a","packagetype":"bdist_wheel","python_version":"py3","requires_python":"<3.14,>=3.9","size":71957,"upload_time":"2025-01-18T19:08:02","upload_time_iso_8601":"2025-01-18T19:08:02.053316Z","url":"https://files.pythonhosted.org/packages/25/4e/a7d131802bac2ece5302ebf78dcef1ba1ba2f8b3a51fbe44c7f52bae6a53/agentops-0.3.24-py3-none-any.whl","yanked":false,"yanked_reason":null},{"comment_text":null,"digests":{"blake2b_256":"71fee96e22c4bf762f34cd5ba435880470dad4576ab357ee61742fe053752322","md5":"3e1b7e0a31197936e099a7509128f794","sha256":"c97a3af959b728bcfbfb1ac2494cef82d8804defc9dac858648b39a9ecdcd2e4"},"downloads":-1,"filename":"agentops-0.3.24.tar.gz","has_sig":false,"md5_digest":"3e1b7e0a31197936e099a7509128f794","packagetype":"sdist","python_version":"source","requires_python":"<3.14,>=3.9","size":233974,"upload_time":"2025-01-18T19:08:04","upload_time_iso_8601":"2025-01-18T19:08:04.121618Z","url":"https://files.pythonhosted.org/packages/71/fe/e96e22c4bf762f34cd5ba435880470dad4576ab357ee61742fe053752322/agentops-0.3.24.tar.gz","yanked":false,"yanked_reason":null}],"0.3.25":[{"comment_text":null,"digests":{"blake2b_256":"e6e39cff4ed65c5deac34f427ed60cd7af3604ec7ed8a999c351f6411e190d3b","md5":"328dedc417be02fc28f8a4c7ed7b52e9","sha256":"4faebf73a62aa0bcac8578428277ca5b9af5e828f49f2cb03a9695b8426e6b9d"},"downloads":-1,"filename":"agentops-0.3.25-py3-none-any.whl","has_sig":false,"md5_digest":"328dedc417be02fc28f8a4c7ed7b52e9","packagetype":"bdist_wheel","python_version":"py3","requires_python":"<3.14,>=3.9","size":71971,"upload_time":"2025-01-22T10:43:16","upload_time_iso_8601":"2025-01-22T10:43:16.070593Z","url":"https://files.pythonhosted.org/packages/e6/e3/9cff4ed65c5deac34f427ed60cd7af3604ec7ed8a999c351f6411e190d3b/agentops-0.3.25-py3-none-any.whl","yanked":false,"yanked_reason":null},{"comment_text":null,"digests":{"blake2b_256":"2fdfeb00eaabebb51feae0724a5928f25df4d71d1c8392204f4f849351fd748c","md5":"a40bc7037baf6dbba92d63331f561a28","sha256":"868d855b6531d1fa2d1047db2cb03ddb1121062fd51c44b564dc626f15cc1e40"},"downloads":-1,"filename":"agentops-0.3.25.tar.gz","has_sig":false,"md5_digest":"a40bc7037baf6dbba92d63331f561a28","packagetype":"sdist","python_version":"source","requires_python":"<3.14,>=3.9","size":234024,"upload_time":"2025-01-22T10:43:17","upload_time_iso_8601":"2025-01-22T10:43:17.986230Z","url":"https://files.pythonhosted.org/packages/2f/df/eb00eaabebb51feae0724a5928f25df4d71d1c8392204f4f849351fd748c/agentops-0.3.25.tar.gz","yanked":false,"yanked_reason":null}],"0.3.26":[{"comment_text":null,"digests":{"blake2b_256":"f521671c458951850bd3a445aa09eafd2793aae1104fa68351a5c3976cdf762b","md5":"c3f8fa92ff5a94a37516e774c7f58b9a","sha256":"20948f52e3ffb4ba1d52301c3a82e59490182c4dad22774ad831dce0181eb5c2"},"downloads":-1,"filename":"agentops-0.3.26-py3-none-any.whl","has_sig":false,"md5_digest":"c3f8fa92ff5a94a37516e774c7f58b9a","packagetype":"bdist_wheel","python_version":"py3","requires_python":"<3.14,>=3.9","size":72090,"upload_time":"2025-01-24T23:44:06","upload_time_iso_8601":"2025-01-24T23:44:06.828461Z","url":"https://files.pythonhosted.org/packages/f5/21/671c458951850bd3a445aa09eafd2793aae1104fa68351a5c3976cdf762b/agentops-0.3.26-py3-none-any.whl","yanked":false,"yanked_reason":null},{"comment_text":null,"digests":{"blake2b_256":"76a1b03c6348a77798e750bde4eec03b4af620d71b9e4b64ff7dcf0860025a2d","md5":"ba4d0f2411ec72828677b38a395465cc","sha256":"bc824bf8727332f59bf803cf84440d13e9e398406222ab29f45909ac1e39f815"},"downloads":-1,"filename":"agentops-0.3.26.tar.gz","has_sig":false,"md5_digest":"ba4d0f2411ec72828677b38a395465cc","packagetype":"sdist","python_version":"source","requires_python":"<3.14,>=3.9","size":234235,"upload_time":"2025-01-24T23:44:08","upload_time_iso_8601":"2025-01-24T23:44:08.541961Z","url":"https://files.pythonhosted.org/packages/76/a1/b03c6348a77798e750bde4eec03b4af620d71b9e4b64ff7dcf0860025a2d/agentops-0.3.26.tar.gz","yanked":false,"yanked_reason":null}],"0.3.4":[{"comment_text":"","digests":{"blake2b_256":"52f32bd714234ec345153c0fcbc9e4896c306c347f3fb66a3aa6d6fc109a7243","md5":"c7a975a86900f7dbe6861a21fdd3c2d8","sha256":"126f7aed4ba43c1399b5488d67a03d10cb4c531e619c650776f826ca00c1aa24"},"downloads":-1,"filename":"agentops-0.3.4-py3-none-any.whl","has_sig":false,"md5_digest":"c7a975a86900f7dbe6861a21fdd3c2d8","packagetype":"bdist_wheel","python_version":"py3","requires_python":">=3.7","size":39915,"upload_time":"2024-07-24T23:15:03","upload_time_iso_8601":"2024-07-24T23:15:03.892439Z","url":"https://files.pythonhosted.org/packages/52/f3/2bd714234ec345153c0fcbc9e4896c306c347f3fb66a3aa6d6fc109a7243/agentops-0.3.4-py3-none-any.whl","yanked":false,"yanked_reason":null},{"comment_text":"","digests":{"blake2b_256":"d28b88a2c9c2df655de806adbb5deebb12c64d19d6aa3cfa759da642953525e0","md5":"f48a2ab7fcaf9cf11a25805ac5300e26","sha256":"a92c9cb7c511197f0ecb8cb5aca15d35022c15a3d2fd2aaaa34cd7e5dc59393f"},"downloads":-1,"filename":"agentops-0.3.4.tar.gz","has_sig":false,"md5_digest":"f48a2ab7fcaf9cf11a25805ac5300e26","packagetype":"sdist","python_version":"source","requires_python":">=3.7","size":42063,"upload_time":"2024-07-24T23:15:05","upload_time_iso_8601":"2024-07-24T23:15:05.586475Z","url":"https://files.pythonhosted.org/packages/d2/8b/88a2c9c2df655de806adbb5deebb12c64d19d6aa3cfa759da642953525e0/agentops-0.3.4.tar.gz","yanked":false,"yanked_reason":null}],"0.3.5":[{"comment_text":"","digests":{"blake2b_256":"f253f9672c6aa3c79b6a5b64321e93d2316f126add867ceb2e3e95ea8b4bf1b0","md5":"bd45dc8100fd3974dff11014d12424ff","sha256":"687cb938ecf9d1bf7650afc910e2b2e1b8b6d9e969215aeb49e57f1555a2a756"},"downloads":-1,"filename":"agentops-0.3.5-py3-none-any.whl","has_sig":false,"md5_digest":"bd45dc8100fd3974dff11014d12424ff","packagetype":"bdist_wheel","python_version":"py3","requires_python":">=3.7","size":39177,"upload_time":"2024-08-01T19:32:19","upload_time_iso_8601":"2024-08-01T19:32:19.765946Z","url":"https://files.pythonhosted.org/packages/f2/53/f9672c6aa3c79b6a5b64321e93d2316f126add867ceb2e3e95ea8b4bf1b0/agentops-0.3.5-py3-none-any.whl","yanked":true,"yanked_reason":"Introduces - FileNotFoundError impacting OpenAI and LiteLLM integrations"},{"comment_text":"","digests":{"blake2b_256":"235508ce5915f1ceb86ea6f7a6e8c8dc025b34981408a1b638316b5140fad525","md5":"53ef2f5230de09260f4ead09633dde62","sha256":"ae98540355ce9b892a630e61a7224a9175657cad1b7e799269238748ca7bc0ea"},"downloads":-1,"filename":"agentops-0.3.5.tar.gz","has_sig":false,"md5_digest":"53ef2f5230de09260f4ead09633dde62","packagetype":"sdist","python_version":"source","requires_python":">=3.7","size":42699,"upload_time":"2024-08-01T19:32:21","upload_time_iso_8601":"2024-08-01T19:32:21.259555Z","url":"https://files.pythonhosted.org/packages/23/55/08ce5915f1ceb86ea6f7a6e8c8dc025b34981408a1b638316b5140fad525/agentops-0.3.5.tar.gz","yanked":true,"yanked_reason":"Introduces FileNotFoundError impacting OpenAI and LiteLLM integrations"}],"0.3.6":[{"comment_text":"","digests":{"blake2b_256":"be89412afc864df3715d377cff9fe15deadaccdc0902b0a242f742f286e6d84b","md5":"149922f5cd986a8641b6e88c991af0cc","sha256":"413f812eb015fb31175a507784afe08123adfa9e227870e315899b059f42b443"},"downloads":-1,"filename":"agentops-0.3.6-py3-none-any.whl","has_sig":false,"md5_digest":"149922f5cd986a8641b6e88c991af0cc","packagetype":"bdist_wheel","python_version":"py3","requires_python":">=3.7","size":39431,"upload_time":"2024-08-02T06:48:19","upload_time_iso_8601":"2024-08-02T06:48:19.594149Z","url":"https://files.pythonhosted.org/packages/be/89/412afc864df3715d377cff9fe15deadaccdc0902b0a242f742f286e6d84b/agentops-0.3.6-py3-none-any.whl","yanked":false,"yanked_reason":null},{"comment_text":"","digests":{"blake2b_256":"c3bf85f1439c3951ef69c81dbd7ef6df8a11df957e8d1180d835d71c11fa5131","md5":"b68d3124e365867f891bec4fb211a398","sha256":"0941f2486f3a561712ba6f77d560b49e2df55be141f243da0f9dc97ed43e6968"},"downloads":-1,"filename":"agentops-0.3.6.tar.gz","has_sig":false,"md5_digest":"b68d3124e365867f891bec4fb211a398","packagetype":"sdist","python_version":"source","requires_python":">=3.7","size":42933,"upload_time":"2024-08-02T06:48:21","upload_time_iso_8601":"2024-08-02T06:48:21.508300Z","url":"https://files.pythonhosted.org/packages/c3/bf/85f1439c3951ef69c81dbd7ef6df8a11df957e8d1180d835d71c11fa5131/agentops-0.3.6.tar.gz","yanked":false,"yanked_reason":null}],"0.3.7":[{"comment_text":"","digests":{"blake2b_256":"a34d05ba61e4fbd976dabe736d74fb2bb14d064ca758f05f084c0dadb6ac5cb1","md5":"551df1e89278270e0f5522d41f5c28ae","sha256":"7eeec5bef41e9ba397b3d880bcec8cd0818209ab31665c85e8b97615011a23d9"},"downloads":-1,"filename":"agentops-0.3.7-py3-none-any.whl","has_sig":false,"md5_digest":"551df1e89278270e0f5522d41f5c28ae","packagetype":"bdist_wheel","python_version":"py3","requires_python":">=3.7","size":39816,"upload_time":"2024-08-08T23:21:45","upload_time_iso_8601":"2024-08-08T23:21:45.035395Z","url":"https://files.pythonhosted.org/packages/a3/4d/05ba61e4fbd976dabe736d74fb2bb14d064ca758f05f084c0dadb6ac5cb1/agentops-0.3.7-py3-none-any.whl","yanked":false,"yanked_reason":null},{"comment_text":"","digests":{"blake2b_256":"9f31034c3e062287f4fe9f57f2448e9508617a26bbb8a16b11c77cda9b28e1c0","md5":"1c48a797903a25988bae9b72559307ec","sha256":"048ee3caa5edf01b98c994e4e3ff90c09d83f820a43a70f07db96032c3386750"},"downloads":-1,"filename":"agentops-0.3.7.tar.gz","has_sig":false,"md5_digest":"1c48a797903a25988bae9b72559307ec","packagetype":"sdist","python_version":"source","requires_python":">=3.7","size":43495,"upload_time":"2024-08-08T23:21:46","upload_time_iso_8601":"2024-08-08T23:21:46.798531Z","url":"https://files.pythonhosted.org/packages/9f/31/034c3e062287f4fe9f57f2448e9508617a26bbb8a16b11c77cda9b28e1c0/agentops-0.3.7.tar.gz","yanked":false,"yanked_reason":null}],"0.3.9":[{"comment_text":"","digests":{"blake2b_256":"660ce931f892e0cedd40d861c3deff4134e1af1d226d6dc9762b32514d6dbc9f","md5":"82792de7bccabed058a24d3bd47443db","sha256":"582c9ddb30a9bb951b4d3ee2fd0428ba77d4a4367950b9cc6043f45b10bf12d8"},"downloads":-1,"filename":"agentops-0.3.9-py3-none-any.whl","has_sig":false,"md5_digest":"82792de7bccabed058a24d3bd47443db","packagetype":"bdist_wheel","python_version":"py3","requires_python":">=3.7","size":40235,"upload_time":"2024-08-15T21:21:33","upload_time_iso_8601":"2024-08-15T21:21:33.468748Z","url":"https://files.pythonhosted.org/packages/66/0c/e931f892e0cedd40d861c3deff4134e1af1d226d6dc9762b32514d6dbc9f/agentops-0.3.9-py3-none-any.whl","yanked":false,"yanked_reason":null},{"comment_text":"","digests":{"blake2b_256":"e17b68cef3aaf44d423046b7779e9325e4feef5257e6d784a55c9dadf84bd61a","md5":"470f3b2663b71eb2f1597903bf8922e7","sha256":"7c999edbc64196924acdb06da09ec664a09d9fec8e73ba4e0f89e5f3dafc79e5"},"downloads":-1,"filename":"agentops-0.3.9.tar.gz","has_sig":false,"md5_digest":"470f3b2663b71eb2f1597903bf8922e7","packagetype":"sdist","python_version":"source","requires_python":">=3.7","size":43796,"upload_time":"2024-08-15T21:21:34","upload_time_iso_8601":"2024-08-15T21:21:34.591272Z","url":"https://files.pythonhosted.org/packages/e1/7b/68cef3aaf44d423046b7779e9325e4feef5257e6d784a55c9dadf84bd61a/agentops-0.3.9.tar.gz","yanked":false,"yanked_reason":null}],"0.4.0":[{"comment_text":null,"digests":{"blake2b_256":"060e66184fab1fc3bdd955ac20ea7bdef78f5b9aecc4080ea3e054c2a2436991","md5":"250de44e3599992c75625cef67682ecd","sha256":"b4821b8ec69c05a4d13b34eaad4762bb06a4f14e1241d57c16fdd28de5c8c929"},"downloads":-1,"filename":"agentops-0.4.0-py3-none-any.whl","has_sig":false,"md5_digest":"250de44e3599992c75625cef67682ecd","packagetype":"bdist_wheel","python_version":"py3","requires_python":"<3.14,>=3.9","size":171419,"upload_time":"2025-03-13T11:24:15","upload_time_iso_8601":"2025-03-13T11:24:15.042606Z","url":"https://files.pythonhosted.org/packages/06/0e/66184fab1fc3bdd955ac20ea7bdef78f5b9aecc4080ea3e054c2a2436991/agentops-0.4.0-py3-none-any.whl","yanked":true,"yanked_reason":"broken - dependencies"},{"comment_text":null,"digests":{"blake2b_256":"ff7f8a57d060489c780db3e15c4d9ff8c670e5db583549c74dd2d32ae6ec10c0","md5":"ea0932849a7311750c6ac0e567c90182","sha256":"45f5367cecd8a0b648055b6ec76e8a6a2801425e80dede8f86b39e9c6cfe1d98"},"downloads":-1,"filename":"agentops-0.4.0.tar.gz","has_sig":false,"md5_digest":"ea0932849a7311750c6ac0e567c90182","packagetype":"sdist","python_version":"source","requires_python":"<3.14,>=3.9","size":248757,"upload_time":"2025-03-13T11:24:16","upload_time_iso_8601":"2025-03-13T11:24:16.866033Z","url":"https://files.pythonhosted.org/packages/ff/7f/8a57d060489c780db3e15c4d9ff8c670e5db583549c74dd2d32ae6ec10c0/agentops-0.4.0.tar.gz","yanked":true,"yanked_reason":"broken dependencies"}],"0.4.1":[{"comment_text":null,"digests":{"blake2b_256":"736e7ab03c56260ec59bfaeeb08efb76f55ec6153861ad2a9cf20b38b222e4e7","md5":"3fcebe0141ca19b2fbcb53e918003ce9","sha256":"69c944e22628bc0f52c534007d2453da2a1988a7fd1f993720c4a15b0f70465a"},"downloads":-1,"filename":"agentops-0.4.1-py3-none-any.whl","has_sig":false,"md5_digest":"3fcebe0141ca19b2fbcb53e918003ce9","packagetype":"bdist_wheel","python_version":"py3","requires_python":"<3.14,>=3.9","size":171402,"upload_time":"2025-03-13T16:29:26","upload_time_iso_8601":"2025-03-13T16:29:26.477091Z","url":"https://files.pythonhosted.org/packages/73/6e/7ab03c56260ec59bfaeeb08efb76f55ec6153861ad2a9cf20b38b222e4e7/agentops-0.4.1-py3-none-any.whl","yanked":true,"yanked_reason":"Broken - dependencies"},{"comment_text":null,"digests":{"blake2b_256":"ca303217cd3480ad099ffa92848ccbc8672e5232c22918c95a4b99e49c0ef31e","md5":"ec421fa88b575b827fc0d3fd02f45515","sha256":"fec044f0346dca6aba17e458e669ac1f52f1b618a4a15b43342615096c5e7d56"},"downloads":-1,"filename":"agentops-0.4.1.tar.gz","has_sig":false,"md5_digest":"ec421fa88b575b827fc0d3fd02f45515","packagetype":"sdist","python_version":"source","requires_python":"<3.14,>=3.9","size":248747,"upload_time":"2025-03-13T16:29:27","upload_time_iso_8601":"2025-03-13T16:29:27.905694Z","url":"https://files.pythonhosted.org/packages/ca/30/3217cd3480ad099ffa92848ccbc8672e5232c22918c95a4b99e49c0ef31e/agentops-0.4.1.tar.gz","yanked":true,"yanked_reason":"Broken dependencies"}],"0.4.10":[{"comment_text":null,"digests":{"blake2b_256":"301e0fe4fb617a5a69a8692b571d726f03e713a37d94d6a43c595a08fc33cff3","md5":"5ac7ec12e80bae6946dc10e46ef768f7","sha256":"917ad7ad51af0ca00cace2a3ae1d1d36e0d65dc813e030fcd377ff98535002bd"},"downloads":-1,"filename":"agentops-0.4.10-py3-none-any.whl","has_sig":false,"md5_digest":"5ac7ec12e80bae6946dc10e46ef768f7","packagetype":"bdist_wheel","python_version":"py3","requires_python":"<3.14,>=3.9","size":198777,"upload_time":"2025-05-08T20:37:29","upload_time_iso_8601":"2025-05-08T20:37:29.322288Z","url":"https://files.pythonhosted.org/packages/30/1e/0fe4fb617a5a69a8692b571d726f03e713a37d94d6a43c595a08fc33cff3/agentops-0.4.10-py3-none-any.whl","yanked":false,"yanked_reason":null},{"comment_text":null,"digests":{"blake2b_256":"a0ef0a56be3981bd464ad5a22fa3a859421f4b5560cbbb082f3ef9aca9cdb1a7","md5":"1954d07bfa38ba5c5ce0e516b7dbfdc9","sha256":"b66a48b4ec50c9cb34abc6ff1df873f0dcddbbb528d8a8c0527cb97b24c91b36"},"downloads":-1,"filename":"agentops-0.4.10.tar.gz","has_sig":false,"md5_digest":"1954d07bfa38ba5c5ce0e516b7dbfdc9","packagetype":"sdist","python_version":"source","requires_python":"<3.14,>=3.9","size":284727,"upload_time":"2025-05-08T20:37:30","upload_time_iso_8601":"2025-05-08T20:37:30.744217Z","url":"https://files.pythonhosted.org/packages/a0/ef/0a56be3981bd464ad5a22fa3a859421f4b5560cbbb082f3ef9aca9cdb1a7/agentops-0.4.10.tar.gz","yanked":false,"yanked_reason":null}],"0.4.11":[{"comment_text":null,"digests":{"blake2b_256":"35cde66dea05d2d8070f886e8f4ce86905cf1cce2f89622e041f26e39f717c9e","md5":"20424d54ba76517d586d4bcc92dda3bf","sha256":"b08c84fd69f36fcd5d6f2b14d16ff88b977a9a417d92448c9709f3c7990d6438"},"downloads":-1,"filename":"agentops-0.4.11-py3-none-any.whl","has_sig":false,"md5_digest":"20424d54ba76517d586d4bcc92dda3bf","packagetype":"bdist_wheel","python_version":"py3","requires_python":"<3.14,>=3.9","size":198789,"upload_time":"2025-05-12T20:38:29","upload_time_iso_8601":"2025-05-12T20:38:29.202046Z","url":"https://files.pythonhosted.org/packages/35/cd/e66dea05d2d8070f886e8f4ce86905cf1cce2f89622e041f26e39f717c9e/agentops-0.4.11-py3-none-any.whl","yanked":false,"yanked_reason":null},{"comment_text":null,"digests":{"blake2b_256":"349df76fc1760cb21788967db3dd22ff2e6521c42b8ecee152e6ac4278e7cade","md5":"b7affd8b15834e4f9cb63066d7d160d1","sha256":"6eb80ee4a0653f9bdc9fc7641bf60cb7546cd34ff1c04dfbc4fca77dbb07edda"},"downloads":-1,"filename":"agentops-0.4.11.tar.gz","has_sig":false,"md5_digest":"b7affd8b15834e4f9cb63066d7d160d1","packagetype":"sdist","python_version":"source","requires_python":"<3.14,>=3.9","size":284735,"upload_time":"2025-05-12T20:38:30","upload_time_iso_8601":"2025-05-12T20:38:30.393540Z","url":"https://files.pythonhosted.org/packages/34/9d/f76fc1760cb21788967db3dd22ff2e6521c42b8ecee152e6ac4278e7cade/agentops-0.4.11.tar.gz","yanked":false,"yanked_reason":null}],"0.4.12":[{"comment_text":null,"digests":{"blake2b_256":"eb86772ed94e4e55433e8014933dab08aa6dfbcd8072f7fd74ffcad335ba0e73","md5":"831a3d54bccce09cc6c2a352776d02e6","sha256":"7c2685ae9c9de1a1071f6a29d395444191744d5ee58e33c020a69e2388dc2f7c"},"downloads":-1,"filename":"agentops-0.4.12-py3-none-any.whl","has_sig":false,"md5_digest":"831a3d54bccce09cc6c2a352776d02e6","packagetype":"bdist_wheel","python_version":"py3","requires_python":"<3.14,>=3.9","size":198319,"upload_time":"2025-05-15T19:59:27","upload_time_iso_8601":"2025-05-15T19:59:27.609093Z","url":"https://files.pythonhosted.org/packages/eb/86/772ed94e4e55433e8014933dab08aa6dfbcd8072f7fd74ffcad335ba0e73/agentops-0.4.12-py3-none-any.whl","yanked":false,"yanked_reason":null},{"comment_text":null,"digests":{"blake2b_256":"0cf664cea8e916a305d2dc2f3f3840a1d4cae40e1927892e1fcc11f83ec7ebee","md5":"7e97e0612a6e8544b37a2fa2e1633166","sha256":"530f15d428a4c78db918fa766366c8f11105c4d1d3b1a56de027747d805a573f"},"downloads":-1,"filename":"agentops-0.4.12.tar.gz","has_sig":false,"md5_digest":"7e97e0612a6e8544b37a2fa2e1633166","packagetype":"sdist","python_version":"source","requires_python":"<3.14,>=3.9","size":284309,"upload_time":"2025-05-15T19:59:28","upload_time_iso_8601":"2025-05-15T19:59:28.955745Z","url":"https://files.pythonhosted.org/packages/0c/f6/64cea8e916a305d2dc2f3f3840a1d4cae40e1927892e1fcc11f83ec7ebee/agentops-0.4.12.tar.gz","yanked":false,"yanked_reason":null}],"0.4.2":[{"comment_text":null,"digests":{"blake2b_256":"b13fcb38831e86502e3a30460a27e72a254df39cc2f223d1952e063e2d0b1f70","md5":"c958500ff1e2b600064e980d526f3ad8","sha256":"4c376e3a95d1c65a864e8a5ab6f4bdb62f76abf2271b3c9a1cda2a0ad33b2b1a"},"downloads":-1,"filename":"agentops-0.4.2-py3-none-any.whl","has_sig":false,"md5_digest":"c958500ff1e2b600064e980d526f3ad8","packagetype":"bdist_wheel","python_version":"py3","requires_python":"<3.14,>=3.9","size":171420,"upload_time":"2025-03-13T16:56:31","upload_time_iso_8601":"2025-03-13T16:56:31.589623Z","url":"https://files.pythonhosted.org/packages/b1/3f/cb38831e86502e3a30460a27e72a254df39cc2f223d1952e063e2d0b1f70/agentops-0.4.2-py3-none-any.whl","yanked":false,"yanked_reason":null},{"comment_text":null,"digests":{"blake2b_256":"4bd0f2c1951661617febfd14c3e98a58fbd805e48f453356e912dc8efc950490","md5":"7a125604d2bb3494714462442f0ac47c","sha256":"42cbc30a0eecee5db468d01dcbe398d57f080cbf8bb09aecc2ce40c5a21509a5"},"downloads":-1,"filename":"agentops-0.4.2.tar.gz","has_sig":false,"md5_digest":"7a125604d2bb3494714462442f0ac47c","packagetype":"sdist","python_version":"source","requires_python":"<3.14,>=3.9","size":248754,"upload_time":"2025-03-13T16:56:33","upload_time_iso_8601":"2025-03-13T16:56:33.062966Z","url":"https://files.pythonhosted.org/packages/4b/d0/f2c1951661617febfd14c3e98a58fbd805e48f453356e912dc8efc950490/agentops-0.4.2.tar.gz","yanked":false,"yanked_reason":null}],"0.4.3":[{"comment_text":null,"digests":{"blake2b_256":"398892f5a663cf616607e92a0499f5b636fe4e5ae8a6b7febc436077cd02ecd5","md5":"e739880fc1b0cf1e15a816277ca1e8d9","sha256":"c69cf884fc20cd3b44dd07bc9bca9ecec72e44fd2b12c50523670e3743fbbe6c"},"downloads":-1,"filename":"agentops-0.4.3-py3-none-any.whl","has_sig":false,"md5_digest":"e739880fc1b0cf1e15a816277ca1e8d9","packagetype":"bdist_wheel","python_version":"py3","requires_python":"<3.14,>=3.9","size":111111,"upload_time":"2025-03-14T17:35:53","upload_time_iso_8601":"2025-03-14T17:35:53.978325Z","url":"https://files.pythonhosted.org/packages/39/88/92f5a663cf616607e92a0499f5b636fe4e5ae8a6b7febc436077cd02ecd5/agentops-0.4.3-py3-none-any.whl","yanked":false,"yanked_reason":null},{"comment_text":null,"digests":{"blake2b_256":"c296f6f5268ffd68079185c6b21190a6ab5b35997678ce89af211d3c3683cc16","md5":"8df7f60a4346721caf9a4a74b0ba2e32","sha256":"48379801976e5e6c830ee40b247d7e7834fb79fb18d2cec926a8c06bdf767090"},"downloads":-1,"filename":"agentops-0.4.3.tar.gz","has_sig":false,"md5_digest":"8df7f60a4346721caf9a4a74b0ba2e32","packagetype":"sdist","python_version":"source","requires_python":"<3.14,>=3.9","size":209668,"upload_time":"2025-03-14T17:35:55","upload_time_iso_8601":"2025-03-14T17:35:55.387572Z","url":"https://files.pythonhosted.org/packages/c2/96/f6f5268ffd68079185c6b21190a6ab5b35997678ce89af211d3c3683cc16/agentops-0.4.3.tar.gz","yanked":false,"yanked_reason":null}],"0.4.4":[{"comment_text":null,"digests":{"blake2b_256":"e230799eb1a6b63e6f072611e4d6c5f7d70d969b1c2d14735100a5295eb794fd","md5":"76de08f25b0f1765ec9b3ce200f2273c","sha256":"a33f32e0d09e942b501a4066460b77bc1f6be960bdbd8dfed1cfc5950702f87c"},"downloads":-1,"filename":"agentops-0.4.4-py3-none-any.whl","has_sig":false,"md5_digest":"76de08f25b0f1765ec9b3ce200f2273c","packagetype":"bdist_wheel","python_version":"py3","requires_python":"<3.14,>=3.9","size":115456,"upload_time":"2025-03-17T21:08:16","upload_time_iso_8601":"2025-03-17T21:08:16.149499Z","url":"https://files.pythonhosted.org/packages/e2/30/799eb1a6b63e6f072611e4d6c5f7d70d969b1c2d14735100a5295eb794fd/agentops-0.4.4-py3-none-any.whl","yanked":false,"yanked_reason":null},{"comment_text":null,"digests":{"blake2b_256":"65e969c80c4c8fbf27826644c2bbcaf657bf9882a7974b115bff5021c683560d","md5":"2c34c20f9b785c60ea1cc6011b50684b","sha256":"509daf197bb27f8e5b1ac87e516487883178335c70328fd74897b1a5fadbf0bd"},"downloads":-1,"filename":"agentops-0.4.4.tar.gz","has_sig":false,"md5_digest":"2c34c20f9b785c60ea1cc6011b50684b","packagetype":"sdist","python_version":"source","requires_python":"<3.14,>=3.9","size":209971,"upload_time":"2025-03-17T21:08:17","upload_time_iso_8601":"2025-03-17T21:08:17.396763Z","url":"https://files.pythonhosted.org/packages/65/e9/69c80c4c8fbf27826644c2bbcaf657bf9882a7974b115bff5021c683560d/agentops-0.4.4.tar.gz","yanked":false,"yanked_reason":null}],"0.4.5":[{"comment_text":null,"digests":{"blake2b_256":"5cf1848e02d7233e3bfe74119e28a4fb7cf9dd3363eb215cf8bb8ca835317cc7","md5":"e70f8b49cbbbf5b6a56bbfc51938581c","sha256":"ec45a775dd5f494fe137620ce3e43aa06a6858495bed31c4b9019b343a34d092"},"downloads":-1,"filename":"agentops-0.4.5-py3-none-any.whl","has_sig":false,"md5_digest":"e70f8b49cbbbf5b6a56bbfc51938581c","packagetype":"bdist_wheel","python_version":"py3","requires_python":"<3.14,>=3.9","size":148034,"upload_time":"2025-03-25T00:05:57","upload_time_iso_8601":"2025-03-25T00:05:57.075368Z","url":"https://files.pythonhosted.org/packages/5c/f1/848e02d7233e3bfe74119e28a4fb7cf9dd3363eb215cf8bb8ca835317cc7/agentops-0.4.5-py3-none-any.whl","yanked":false,"yanked_reason":null},{"comment_text":null,"digests":{"blake2b_256":"cc2c243f2e01dae6cc2583bca8009c735bb08267c9f51f0e916154b91329e08f","md5":"16781e2f18e40444f869c38b3b27c70c","sha256":"d82d908072c8ffea1b90d63d651ccb73dec8597ef830e60b4311efb4f5593e8e"},"downloads":-1,"filename":"agentops-0.4.5.tar.gz","has_sig":false,"md5_digest":"16781e2f18e40444f869c38b3b27c70c","packagetype":"sdist","python_version":"source","requires_python":"<3.14,>=3.9","size":232839,"upload_time":"2025-03-25T00:05:58","upload_time_iso_8601":"2025-03-25T00:05:58.270348Z","url":"https://files.pythonhosted.org/packages/cc/2c/243f2e01dae6cc2583bca8009c735bb08267c9f51f0e916154b91329e08f/agentops-0.4.5.tar.gz","yanked":false,"yanked_reason":null}],"0.4.6":[{"comment_text":null,"digests":{"blake2b_256":"316124fa78f759c68e1484ed04ed6d0d60ad4b6b58d02570a65dc670975fd954","md5":"36d7d7e64cde9ed73d4ced26e9ee4fb0","sha256":"283929b8f7a1bc79693a6c982e012ccceac4645c6a35709603e7ff83332ec00d"},"downloads":-1,"filename":"agentops-0.4.6-py3-none-any.whl","has_sig":false,"md5_digest":"36d7d7e64cde9ed73d4ced26e9ee4fb0","packagetype":"bdist_wheel","python_version":"py3","requires_python":"<3.14,>=3.9","size":160863,"upload_time":"2025-04-07T22:18:58","upload_time_iso_8601":"2025-04-07T22:18:58.881418Z","url":"https://files.pythonhosted.org/packages/31/61/24fa78f759c68e1484ed04ed6d0d60ad4b6b58d02570a65dc670975fd954/agentops-0.4.6-py3-none-any.whl","yanked":false,"yanked_reason":null},{"comment_text":null,"digests":{"blake2b_256":"d0073869f9b99dbc45ac55bc0dbfd8cf6b22de850a716004135ec96a29c3d81e","md5":"1390e3bc3185a4e97492958c1c4e549c","sha256":"78179a0d2c02217445fb7315bb963496bb338c96bcc126bebfb45a5733fea23e"},"downloads":-1,"filename":"agentops-0.4.6.tar.gz","has_sig":false,"md5_digest":"1390e3bc3185a4e97492958c1c4e549c","packagetype":"sdist","python_version":"source","requires_python":"<3.14,>=3.9","size":254164,"upload_time":"2025-04-07T22:19:00","upload_time_iso_8601":"2025-04-07T22:19:00.589814Z","url":"https://files.pythonhosted.org/packages/d0/07/3869f9b99dbc45ac55bc0dbfd8cf6b22de850a716004135ec96a29c3d81e/agentops-0.4.6.tar.gz","yanked":false,"yanked_reason":null}],"0.4.7":[{"comment_text":null,"digests":{"blake2b_256":"a4be6d708281bd3a282879859231fb7d2ab1d0fec6ee421ec6b02d08a3726670","md5":"3bb2171ad2809a49c43935f1d249aa02","sha256":"b1c4acda70ef45a3c7deac01a695b922a14bb762826ba68fb2b8c3859f4e87da"},"downloads":-1,"filename":"agentops-0.4.7-py3-none-any.whl","has_sig":false,"md5_digest":"3bb2171ad2809a49c43935f1d249aa02","packagetype":"bdist_wheel","python_version":"py3","requires_python":"<3.14,>=3.9","size":182708,"upload_time":"2025-04-24T00:39:39","upload_time_iso_8601":"2025-04-24T00:39:39.403616Z","url":"https://files.pythonhosted.org/packages/a4/be/6d708281bd3a282879859231fb7d2ab1d0fec6ee421ec6b02d08a3726670/agentops-0.4.7-py3-none-any.whl","yanked":false,"yanked_reason":null},{"comment_text":null,"digests":{"blake2b_256":"20a5d142e98481d82912280e29b5b73dc5a5deea4d34c132045333b5201c1209","md5":"62c78776d059798f2e6a74bf1b03932f","sha256":"ad6dca62ff88d4c09eda34e3393c138880a5126682b53cf0c881a7dbb61dcc0d"},"downloads":-1,"filename":"agentops-0.4.7.tar.gz","has_sig":false,"md5_digest":"62c78776d059798f2e6a74bf1b03932f","packagetype":"sdist","python_version":"source","requires_python":"<3.14,>=3.9","size":272982,"upload_time":"2025-04-24T00:39:40","upload_time_iso_8601":"2025-04-24T00:39:40.931148Z","url":"https://files.pythonhosted.org/packages/20/a5/d142e98481d82912280e29b5b73dc5a5deea4d34c132045333b5201c1209/agentops-0.4.7.tar.gz","yanked":false,"yanked_reason":null}],"0.4.8":[{"comment_text":null,"digests":{"blake2b_256":"96d32cee2a94f2917be9c7575238dfff3088a51a6376168a2c7287da0e8b654c","md5":"a02a327b4620a909e831fbd6889bf25e","sha256":"86f439d47c0fdfcb3525859528300b19bb96c105875d0b5b3d205260aedc3f24"},"downloads":-1,"filename":"agentops-0.4.8-py3-none-any.whl","has_sig":false,"md5_digest":"a02a327b4620a909e831fbd6889bf25e","packagetype":"bdist_wheel","python_version":"py3","requires_python":"<3.14,>=3.9","size":182678,"upload_time":"2025-04-27T09:10:39","upload_time_iso_8601":"2025-04-27T09:10:39.925403Z","url":"https://files.pythonhosted.org/packages/96/d3/2cee2a94f2917be9c7575238dfff3088a51a6376168a2c7287da0e8b654c/agentops-0.4.8-py3-none-any.whl","yanked":false,"yanked_reason":null},{"comment_text":null,"digests":{"blake2b_256":"ba64732ebe57c77123058cbc03eec0795267fac65aa6032b8906b1dfe80ff837","md5":"f947ace32256ff3ee6b2a6c716ef3543","sha256":"c299ca067298f568ae2885e4d21951b0bdb7067692d930b57ff1f19bd447ae5a"},"downloads":-1,"filename":"agentops-0.4.8.tar.gz","has_sig":false,"md5_digest":"f947ace32256ff3ee6b2a6c716ef3543","packagetype":"sdist","python_version":"source","requires_python":"<3.14,>=3.9","size":272951,"upload_time":"2025-04-27T09:10:41","upload_time_iso_8601":"2025-04-27T09:10:41.806172Z","url":"https://files.pythonhosted.org/packages/ba/64/732ebe57c77123058cbc03eec0795267fac65aa6032b8906b1dfe80ff837/agentops-0.4.8.tar.gz","yanked":false,"yanked_reason":null}],"0.4.9":[{"comment_text":null,"digests":{"blake2b_256":"5814e40def8897f404273f69d6841793b3dbdcbb8f2948fb6bd9c50087239b37","md5":"f49c139fbf17affaa3e8165743971a50","sha256":"622b9ecdc1b5e91c5ac3aa92d2f756d083c4e0ba830d8e94c3785f7290587a97"},"downloads":-1,"filename":"agentops-0.4.9-py3-none-any.whl","has_sig":false,"md5_digest":"f49c139fbf17affaa3e8165743971a50","packagetype":"bdist_wheel","python_version":"py3","requires_python":"<3.14,>=3.9","size":198463,"upload_time":"2025-05-02T23:51:48","upload_time_iso_8601":"2025-05-02T23:51:48.502905Z","url":"https://files.pythonhosted.org/packages/58/14/e40def8897f404273f69d6841793b3dbdcbb8f2948fb6bd9c50087239b37/agentops-0.4.9-py3-none-any.whl","yanked":false,"yanked_reason":null},{"comment_text":null,"digests":{"blake2b_256":"32efa2af9802799b3d26c570b8dd18669e3577fb58fa093a3c9cfafbf179376c","md5":"5eb22fdc989748711f0252c3679388e9","sha256":"c69a0c912a75367850036c20368d4722462b5769eb86bdebabb0695f8be4c8bd"},"downloads":-1,"filename":"agentops-0.4.9.tar.gz","has_sig":false,"md5_digest":"5eb22fdc989748711f0252c3679388e9","packagetype":"sdist","python_version":"source","requires_python":"<3.14,>=3.9","size":284471,"upload_time":"2025-05-02T23:51:49","upload_time_iso_8601":"2025-05-02T23:51:49.781274Z","url":"https://files.pythonhosted.org/packages/32/ef/a2af9802799b3d26c570b8dd18669e3577fb58fa093a3c9cfafbf179376c/agentops-0.4.9.tar.gz","yanked":false,"yanked_reason":null}]},"urls":[{"comment_text":null,"digests":{"blake2b_256":"eb86772ed94e4e55433e8014933dab08aa6dfbcd8072f7fd74ffcad335ba0e73","md5":"831a3d54bccce09cc6c2a352776d02e6","sha256":"7c2685ae9c9de1a1071f6a29d395444191744d5ee58e33c020a69e2388dc2f7c"},"downloads":-1,"filename":"agentops-0.4.12-py3-none-any.whl","has_sig":false,"md5_digest":"831a3d54bccce09cc6c2a352776d02e6","packagetype":"bdist_wheel","python_version":"py3","requires_python":"<3.14,>=3.9","size":198319,"upload_time":"2025-05-15T19:59:27","upload_time_iso_8601":"2025-05-15T19:59:27.609093Z","url":"https://files.pythonhosted.org/packages/eb/86/772ed94e4e55433e8014933dab08aa6dfbcd8072f7fd74ffcad335ba0e73/agentops-0.4.12-py3-none-any.whl","yanked":false,"yanked_reason":null},{"comment_text":null,"digests":{"blake2b_256":"0cf664cea8e916a305d2dc2f3f3840a1d4cae40e1927892e1fcc11f83ec7ebee","md5":"7e97e0612a6e8544b37a2fa2e1633166","sha256":"530f15d428a4c78db918fa766366c8f11105c4d1d3b1a56de027747d805a573f"},"downloads":-1,"filename":"agentops-0.4.12.tar.gz","has_sig":false,"md5_digest":"7e97e0612a6e8544b37a2fa2e1633166","packagetype":"sdist","python_version":"source","requires_python":"<3.14,>=3.9","size":284309,"upload_time":"2025-05-15T19:59:28","upload_time_iso_8601":"2025-05-15T19:59:28.955745Z","url":"https://files.pythonhosted.org/packages/0c/f6/64cea8e916a305d2dc2f3f3840a1d4cae40e1927892e1fcc11f83ec7ebee/agentops-0.4.12.tar.gz","yanked":false,"yanked_reason":null}],"vulnerabilities":[]} - - ' + string: "{\n \"id\": \"chatcmpl-DDG3i8i7PX54gKKVTtyZoA9C4DBqM\",\n \"object\": + \"chat.completion\",\n \"created\": 1772052366,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n + \ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": + \"assistant\",\n \"content\": \"hi\",\n \"refusal\": null,\n + \ \"annotations\": []\n },\n \"logprobs\": null,\n \"finish_reason\": + \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 75,\n \"completion_tokens\": + 1,\n \"total_tokens\": 76,\n \"prompt_tokens_details\": {\n \"cached_tokens\": + 0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\": + {\n \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\": + 0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\": + \"default\",\n \"system_fingerprint\": \"fp_373a14eb6f\"\n}\n" headers: - Accept-Ranges: - - bytes + CF-RAY: + - CF-RAY-XXX Connection: - keep-alive - Content-Length: - - '141284' + Content-Type: + - application/json Date: - - Fri, 16 May 2025 22:11:18 GMT - Permissions-Policy: - - publickey-credentials-create=(self),publickey-credentials-get=(self),accelerometer=(),ambient-light-sensor=(),autoplay=(),battery=(),camera=(),display-capture=(),document-domain=(),encrypted-media=(),execution-while-not-rendered=(),execution-while-out-of-viewport=(),fullscreen=(),gamepad=(),geolocation=(),gyroscope=(),hid=(),identity-credentials-get=(),idle-detection=(),local-fonts=(),magnetometer=(),microphone=(),midi=(),otp-credentials=(),payment=(),picture-in-picture=(),screen-wake-lock=(),serial=(),speaker-selection=(),storage-access=(),usb=(),web-share=(),xr-spatial-tracking=() + - Wed, 25 Feb 2026 20:46:06 GMT + Server: + - cloudflare Strict-Transport-Security: - - max-age=31536000; includeSubDomains; preload - Vary: - - Accept-Encoding - X-Cache: - - MISS, HIT, HIT - X-Cache-Hits: - - 0, 14, 0 - X-Content-Type-Options: - - nosniff - X-Frame-Options: - - deny - X-Permitted-Cross-Domain-Policies: - - none - X-Served-By: - - cache-iad-kjyo7100048-IAD, cache-iad-kjyo7100044-IAD, cache-sjc10057-SJC - X-Timer: - - S1747433478.903585,VS0,VE171 - X-XSS-Protection: - - 1; mode=block - access-control-allow-headers: - - Content-Type, If-Match, If-Modified-Since, If-None-Match, If-Unmodified-Since - access-control-allow-methods: - - GET - access-control-allow-origin: - - '*' - access-control-expose-headers: - - X-PyPI-Last-Serial - access-control-max-age: - - '86400' - cache-control: - - max-age=900, public - content-security-policy: - - base-uri 'self'; connect-src 'self' https://api.github.com/repos/ https://api.github.com/search/issues https://gitlab.com/api/ https://analytics.python.org fastly-insights.com *.fastly-insights.com *.ethicalads.io https://api.pwnedpasswords.com https://cdn.jsdelivr.net/npm/mathjax@3.2.2/es5/sre/mathmaps/ https://2p66nmmycsj3.statuspage.io; default-src 'none'; font-src 'self' fonts.gstatic.com; form-action 'self' https://checkout.stripe.com; frame-ancestors 'none'; frame-src 'none'; img-src 'self' https://pypi-camo.freetls.fastly.net/ *.fastly-insights.com *.ethicalads.io ethicalads.blob.core.windows.net; script-src 'self' https://analytics.python.org *.fastly-insights.com *.ethicalads.io 'sha256-U3hKDidudIaxBDEzwGJApJgPEf2mWk6cfMWghrAa6i0=' https://cdn.jsdelivr.net/npm/mathjax@3.2.2/ 'sha256-1CldwzdEg2k1wTmf7s5RWVd7NMXI/7nxxjJM2C4DqII=' 'sha256-0POaN8stWYQxhzjKS+/eOfbbJ/u4YHO5ZagJvLpMypo='; style-src 'self' fonts.googleapis.com *.ethicalads.io 'sha256-2YHqZokjiizkHi1Zt+6ar0XJ0OeEy/egBnlm+MDMtrM=' - 'sha256-47DEQpj8HBSa+/TImW+5JCeuQeRkm5NMpJWZG3hSuFU=' 'sha256-JLEjeN9e5dGsz5475WyRaoA4eQOdNPxDIeUhclnJDCE=' 'sha256-mQyxHEuwZJqpxCw3SLmc4YOySNKXunyu2Oiz1r3/wAE=' 'sha256-OCf+kv5Asiwp++8PIevKBYSgnNLNUZvxAp4a7wMLuKA=' 'sha256-h5LOiLhk6wiJrGsG5ItM0KimwzWQH/yAcmoJDJL//bY='; worker-src *.fastly-insights.com - content-type: - - application/json - etag: - - '"f+xzB2HkOqSq5o8PEbR7zQ"' - referrer-policy: - - origin-when-cross-origin - x-pypi-last-serial: - - '29075100' - status: - code: 200 - message: OK -- request: - body: '{"messages": [{"role": "system", "content": "You are base_agent. You are a helpful assistant that just says hi\nYour personal goal is: Just say hi\nTo give my best complete final answer to the task respond using the exact following format:\n\nThought: I now can give a great answer\nFinal Answer: Your final answer must be the great and the most complete as possible, it must be outcome described.\n\nI MUST use these formats, my job depends on it!"}, {"role": "user", "content": "\nCurrent Task: Just say hi\n\nThis is the expected criteria for your final answer: hi\nyou MUST return the actual complete content as the final answer, not a summary.\n\nBegin! This is VERY important to you, use the tools available and give your best Final Answer, your job depends on it!\n\nThought:"}], "model": "gpt-4o-mini", "stop": ["\nObservation:"]}' - headers: - accept: - - application/json - accept-encoding: - - gzip, deflate - connection: - - keep-alive - content-length: - - '838' - content-type: - - application/json - cookie: - - _cfuvid=pgWR9g.y6i.3_EHHkfdBfvv5isYFU_joRq3kXvX2IE4-1740180069173-0.0.1.1-604800000 - host: - - api.openai.com - user-agent: - - OpenAI/Python 1.68.2 - x-stainless-arch: - - arm64 - x-stainless-async: - - 'false' - x-stainless-lang: - - python - x-stainless-os: - - MacOS - x-stainless-package-version: - - 1.68.2 - x-stainless-raw-response: - - 'true' - x-stainless-read-timeout: - - '600.0' - x-stainless-retry-count: - - '0' - x-stainless-runtime: - - CPython - x-stainless-runtime-version: - - 3.12.9 - method: POST - uri: https://api.openai.com/v1/chat/completions - response: - body: - string: "{\n \"id\": \"chatcmpl-BXxYsYY0bTPlXgle6qZOlhLQQqvVP\",\n \"object\": \"chat.completion\",\n \"created\": 1747433478,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"I now can give a great answer \\nFinal Answer: hi\",\n \"refusal\": null,\n \"annotations\": []\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 161,\n \"completion_tokens\": 12,\n \"total_tokens\": 173,\n \"prompt_tokens_details\": {\n \"cached_tokens\": 0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\": {\n \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\": 0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\": \"default\",\n \"system_fingerprint\": \"fp_dbaca60df0\"\n}\n" - headers: - CF-RAY: - - 940e35c4d9de174e-SJC - Connection: - - keep-alive - Content-Type: - - application/json - Date: - - Fri, 16 May 2025 22:11:18 GMT - Server: - - cloudflare - Set-Cookie: - - __cf_bm=7gYhEK1ZebbV2RqWIdRN.0Kv_XoKdpvnwX3SkGHCXnU-1747433478-1.0.1.1-2aU819p9q3cYgN_xx91359ew9UFwtVswCekjsQw7Qgz4X9r3RzR9e0CRqkfXgCACAMxJI7BJCmWvJ0bRuKaFrXbWRGphDbDW5xMKyMxQxbY; path=/; expires=Fri, 16-May-25 22:41:18 GMT; domain=.api.openai.com; HttpOnly; Secure; SameSite=None - - _cfuvid=SuZPImI5tNZ3RsqGDhWpp3lM9bZ.ClZzaHNPgVIvvHA-1747433478823-0.0.1.1-604800000; path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None + - STS-XXX Transfer-Encoding: - chunked X-Content-Type-Options: - - nosniff + - X-CONTENT-TYPE-XXX access-control-expose-headers: - - X-Request-ID + - ACCESS-CONTROL-XXX alt-svc: - h3=":443"; ma=86400 cf-cache-status: - DYNAMIC openai-organization: - - crewai-iuxna1 + - OPENAI-ORG-XXX openai-processing-ms: - - '405' + - '292' + openai-project: + - OPENAI-PROJECT-XXX openai-version: - '2020-10-01' - strict-transport-security: - - max-age=31536000; includeSubDomains; preload - x-envoy-upstream-service-time: - - '411' + set-cookie: + - SET-COOKIE-XXX + x-openai-proxy-wasm: + - v0.1 x-ratelimit-limit-requests: - - '30000' + - X-RATELIMIT-LIMIT-REQUESTS-XXX x-ratelimit-limit-tokens: - - '150000000' + - X-RATELIMIT-LIMIT-TOKENS-XXX x-ratelimit-remaining-requests: - - '29999' + - X-RATELIMIT-REMAINING-REQUESTS-XXX x-ratelimit-remaining-tokens: - - '149999824' + - X-RATELIMIT-REMAINING-TOKENS-XXX x-ratelimit-reset-requests: - - 2ms + - X-RATELIMIT-RESET-REQUESTS-XXX x-ratelimit-reset-tokens: - - 0s + - X-RATELIMIT-RESET-TOKENS-XXX x-request-id: - - req_8274f4da736f4f31854b3c8ad67d02fb + - X-REQUEST-ID-XXX status: code: 200 message: OK - request: - body: '{"messages": [{"role": "system", "content": "You are Task Execution Evaluator. Evaluator agent for crew evaluation with precise capabilities to evaluate the performance of the agents in the crew based on the tasks they have performed\nYour personal goal is: Your goal is to evaluate the performance of the agents in the crew based on the tasks they have performed using score from 1 to 10 evaluating on completion, quality, and overall performance.\nTo give my best complete final answer to the task respond using the exact following format:\n\nThought: I now can give a great answer\nFinal Answer: Your final answer must be the great and the most complete as possible, it must be outcome described.\n\nI MUST use these formats, my job depends on it!"}, {"role": "user", "content": "\nCurrent Task: Based on the task description and the expected output, compare and evaluate the performance of the agents in the crew based on the Task Output they have performed using score from 1 to 10 evaluating - on completion, quality, and overall performance.task_description: Just say hi task_expected_output: hi agent: base_agent agent_goal: Just say hi Task Output: hi\n\nThis is the expected criteria for your final answer: Evaluation Score from 1 to 10 based on the performance of the agents on the tasks\nyou MUST return the actual complete content as the final answer, not a summary.\nEnsure your final answer contains only the content in the following format: {\n \"quality\": float\n}\n\nEnsure the final output does not include any code block markers like ```json or ```python.\n\nBegin! This is VERY important to you, use the tools available and give your best Final Answer, your job depends on it!\n\nThought:"}], "model": "gpt-4o-mini", "stop": ["\nObservation:"]}' + body: '{"messages":[{"role":"system","content":"You are Task Execution Evaluator. + Evaluator agent for crew evaluation with precise capabilities to evaluate the + performance of the agents in the crew based on the tasks they have performed\nYour + personal goal is: Your goal is to evaluate the performance of the agents in + the crew based on the tasks they have performed using score from 1 to 10 evaluating + on completion, quality, and overall performance."},{"role":"user","content":"\nCurrent + Task: Based on the task description and the expected output, compare and evaluate + the performance of the agents in the crew based on the Task Output they have + performed using score from 1 to 10 evaluating on completion, quality, and overall + performance.task_description: Just say hi task_expected_output: hi agent: base_agent + agent_goal: Just say hi Task Output: hi\n\nThis is the expected criteria for + your final answer: Evaluation Score from 1 to 10 based on the performance of + the agents on the tasks\nyou MUST return the actual complete content as the + final answer, not a summary.\nFormat your final answer according to the following + OpenAPI schema: {\n \"properties\": {\n \"quality\": {\n \"description\": + \"A score from 1 to 10 evaluating on completion, quality, and overall performance + from the task_description and task_expected_output to the actual Task Output.\",\n \"title\": + \"Quality\",\n \"type\": \"number\"\n }\n },\n \"required\": [\n \"quality\"\n ],\n \"title\": + \"TaskEvaluationPydanticOutput\",\n \"type\": \"object\",\n \"additionalProperties\": + false\n}\n\nIMPORTANT: Preserve the original content exactly as-is. Do NOT rewrite, + paraphrase, or modify the meaning of the content. Only structure it to match + the schema format.\n\nDo not include the OpenAPI schema in the final output. + Ensure the final output does not include any code block markers like ```json + or ```python.\n\nProvide your complete response:"}],"model":"gpt-4o-mini","response_format":{"type":"json_schema","json_schema":{"schema":{"properties":{"quality":{"description":"A + score from 1 to 10 evaluating on completion, quality, and overall performance + from the task_description and task_expected_output to the actual Task Output.","title":"Quality","type":"number"}},"required":["quality"],"title":"TaskEvaluationPydanticOutput","type":"object","additionalProperties":false},"name":"TaskEvaluationPydanticOutput","strict":true}},"stream":false}' headers: + User-Agent: + - X-USER-AGENT-XXX accept: - application/json accept-encoding: - - gzip, deflate + - ACCEPT-ENCODING-XXX + authorization: + - AUTHORIZATION-XXX connection: - keep-alive content-length: - - '1765' + - '2449' content-type: - application/json - cookie: - - _cfuvid=SuZPImI5tNZ3RsqGDhWpp3lM9bZ.ClZzaHNPgVIvvHA-1747433478823-0.0.1.1-604800000; __cf_bm=7gYhEK1ZebbV2RqWIdRN.0Kv_XoKdpvnwX3SkGHCXnU-1747433478-1.0.1.1-2aU819p9q3cYgN_xx91359ew9UFwtVswCekjsQw7Qgz4X9r3RzR9e0CRqkfXgCACAMxJI7BJCmWvJ0bRuKaFrXbWRGphDbDW5xMKyMxQxbY host: - api.openai.com - user-agent: - - OpenAI/Python 1.68.2 x-stainless-arch: - - arm64 + - X-STAINLESS-ARCH-XXX x-stainless-async: - 'false' + x-stainless-helper-method: + - beta.chat.completions.parse x-stainless-lang: - python x-stainless-os: - - MacOS + - X-STAINLESS-OS-XXX x-stainless-package-version: - - 1.68.2 - x-stainless-raw-response: - - 'true' + - 1.83.0 x-stainless-read-timeout: - - '600.0' + - X-STAINLESS-READ-TIMEOUT-XXX x-stainless-retry-count: - '0' x-stainless-runtime: - CPython x-stainless-runtime-version: - - 3.12.9 + - 3.13.12 method: POST uri: https://api.openai.com/v1/chat/completions response: body: - string: "{\n \"id\": \"chatcmpl-BXxYtpQ3GBiYNJUfkAYDTQSCgL56c\",\n \"object\": \"chat.completion\",\n \"created\": 1747433479,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"I now can give a great answer \\nFinal Answer: {\\n \\\"quality\\\": 10.0\\n}\",\n \"refusal\": null,\n \"annotations\": []\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 338,\n \"completion_tokens\": 22,\n \"total_tokens\": 360,\n \"prompt_tokens_details\": {\n \"cached_tokens\": 0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\": {\n \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\": 0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\": \"default\",\n \"system_fingerprint\": \"fp_54eb4bd693\"\ - \n}\n" + string: "{\n \"id\": \"chatcmpl-DDG3kSHBFtT0Gw3lryKg9uTpbeNwD\",\n \"object\": + \"chat.completion\",\n \"created\": 1772052368,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n + \ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": + \"assistant\",\n \"content\": \"{\\\"quality\\\":10}\",\n \"refusal\": + null,\n \"annotations\": []\n },\n \"logprobs\": null,\n + \ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": + 473,\n \"completion_tokens\": 5,\n \"total_tokens\": 478,\n \"prompt_tokens_details\": + {\n \"cached_tokens\": 0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\": + {\n \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\": + 0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\": + \"default\",\n \"system_fingerprint\": \"fp_bd4be55b21\"\n}\n" headers: CF-RAY: - - 940e35cada1f174e-SJC + - CF-RAY-XXX Connection: - keep-alive Content-Type: - application/json Date: - - Fri, 16 May 2025 22:11:19 GMT + - Wed, 25 Feb 2026 20:46:08 GMT Server: - cloudflare + Strict-Transport-Security: + - STS-XXX Transfer-Encoding: - chunked X-Content-Type-Options: - - nosniff + - X-CONTENT-TYPE-XXX access-control-expose-headers: - - X-Request-ID + - ACCESS-CONTROL-XXX alt-svc: - h3=":443"; ma=86400 cf-cache-status: - DYNAMIC openai-organization: - - crewai-iuxna1 + - OPENAI-ORG-XXX openai-processing-ms: - - '696' + - '620' + openai-project: + - OPENAI-PROJECT-XXX openai-version: - '2020-10-01' - strict-transport-security: - - max-age=31536000; includeSubDomains; preload - x-envoy-upstream-service-time: - - '708' + set-cookie: + - SET-COOKIE-XXX + x-openai-proxy-wasm: + - v0.1 x-ratelimit-limit-requests: - - '30000' + - X-RATELIMIT-LIMIT-REQUESTS-XXX x-ratelimit-limit-tokens: - - '150000000' + - X-RATELIMIT-LIMIT-TOKENS-XXX x-ratelimit-remaining-requests: - - '29999' + - X-RATELIMIT-REMAINING-REQUESTS-XXX x-ratelimit-remaining-tokens: - - '149999594' + - X-RATELIMIT-REMAINING-TOKENS-XXX x-ratelimit-reset-requests: - - 2ms + - X-RATELIMIT-RESET-REQUESTS-XXX x-ratelimit-reset-tokens: - - 0s + - X-RATELIMIT-RESET-TOKENS-XXX x-request-id: - - req_1227f2635e62eb396693c8857c57b878 + - X-REQUEST-ID-XXX status: code: 200 message: OK diff --git a/lib/crewai/tests/llms/google/test_google.py b/lib/crewai/tests/llms/google/test_google.py index 3f86388d5..6f475ef49 100644 --- a/lib/crewai/tests/llms/google/test_google.py +++ b/lib/crewai/tests/llms/google/test_google.py @@ -957,6 +957,47 @@ def test_gemini_agent_kickoff_structured_output_with_tools(): +@pytest.mark.vcr() +def test_gemini_crew_structured_output_with_tools(): + """ + Test that a crew with Gemini can use both tools and output_pydantic on a task. + """ + from pydantic import BaseModel, Field + from crewai.tools import tool + + class CalculationResult(BaseModel): + operation: str = Field(description="The mathematical operation performed") + result: int = Field(description="The result of the calculation") + explanation: str = Field(description="Brief explanation of the calculation") + + @tool + def add_numbers(a: int, b: int) -> int: + """Add two numbers together and return the sum.""" + return a + b + + agent = Agent( + role="Calculator", + goal="Perform calculations using available tools", + backstory="You are a calculator assistant that uses tools to compute results.", + llm=LLM(model="google/gemini-2.0-flash-001"), + tools=[add_numbers], + ) + + task = Task( + description="Calculate 15 + 27 using your add_numbers tool. Report the result.", + expected_output="A structured calculation result", + output_pydantic=CalculationResult, + agent=agent, + ) + + crew = Crew(agents=[agent], tasks=[task]) + result = crew.kickoff() + + assert result.pydantic is not None, "Expected pydantic output but got None" + assert isinstance(result.pydantic, CalculationResult) + assert result.pydantic.result == 42, f"Expected 42 but got {result.pydantic.result}" + + def test_gemini_stop_words_not_applied_to_structured_output(): """ Test that stop words are NOT applied when response_model is provided. diff --git a/lib/crewai/tests/test_task.py b/lib/crewai/tests/test_task.py index 9a0010d89..21356c3b4 100644 --- a/lib/crewai/tests/test_task.py +++ b/lib/crewai/tests/test_task.py @@ -759,11 +759,11 @@ def test_custom_converter_cls(): crew = Crew(agents=[scorer], tasks=[task]) - with patch.object( - ScoreConverter, "to_pydantic", return_value=ScoreOutput(score=5) - ) as mock_to_pydantic: - crew.kickoff() - mock_to_pydantic.assert_called_once() + # With native structured output, the LLM returns a BaseModel directly, + # so the converter is bypassed. Verify the output is valid instead. + result = crew.kickoff() + assert isinstance(result.pydantic, ScoreOutput) + assert isinstance(result.pydantic.score, int) @pytest.mark.vcr()