Merge branch 'main' into brandon/eng-290-make-tool-inputs-actual-objects-and-not-strings

src/crewai/agent.py

@@ -86,7 +86,7 @@ class Agent(BaseAgent):
     llm: Union[str, InstanceOf[LLM], Any] = Field(
         description="Language model that will run the agent.", default=None
     )
-    function_calling_llm: Optional[Any] = Field(
+    function_calling_llm: Optional[Union[str, InstanceOf[LLM], Any]] = Field(
         description="Language model that will run the agent.", default=None
     )
     system_template: Optional[str] = Field(
@@ -142,7 +142,8 @@ class Agent(BaseAgent):
         self.agent_ops_agent_name = self.role
 
         self.llm = create_llm(self.llm)
-        self.function_calling_llm = create_llm(self.function_calling_llm)
+        if self.function_calling_llm and not isinstance(self.function_calling_llm, LLM):
+            self.function_calling_llm = create_llm(self.function_calling_llm)
 
         if not self.agent_executor:
             self._setup_agent_executor()

src/crewai/agents/crew_agent_executor.py

@@ -145,8 +145,6 @@ class CrewAgentExecutor(CrewAgentExecutorMixin):
                 if self._is_context_length_exceeded(e):
                     self._handle_context_length()
                     continue
-                else:
-                    raise e
 
         self._show_logs(formatted_answer)
         return formatted_answer
@@ -316,7 +314,7 @@ class CrewAgentExecutor(CrewAgentExecutorMixin):
             agent=self.agent,
             action=agent_action,
         )
-        tool_calling = tool_usage.parse(agent_action.text)
+        tool_calling = tool_usage.parse_tool_calling(agent_action.text)
 
         if isinstance(tool_calling, ToolUsageErrorException):
             tool_result = tool_calling.message

src/crewai/crew.py

@@ -47,6 +47,7 @@ from crewai.utilities.formatter import (
     aggregate_raw_outputs_from_task_outputs,
     aggregate_raw_outputs_from_tasks,
 )
+from crewai.utilities.llm_utils import create_llm
 from crewai.utilities.planning_handler import CrewPlanner
 from crewai.utilities.task_output_storage_handler import TaskOutputStorageHandler
 from crewai.utilities.training_handler import CrewTrainingHandler
@@ -149,7 +150,7 @@ class Crew(BaseModel):
     manager_agent: Optional[BaseAgent] = Field(
         description="Custom agent that will be used as manager.", default=None
     )
-    function_calling_llm: Optional[Any] = Field(
+    function_calling_llm: Optional[Union[str, InstanceOf[LLM], Any]] = Field(
         description="Language model that will run the agent.", default=None
     )
     config: Optional[Union[Json, Dict[str, Any]]] = Field(default=None)
@@ -245,15 +246,9 @@ class Crew(BaseModel):
         if self.output_log_file:
             self._file_handler = FileHandler(self.output_log_file)
         self._rpm_controller = RPMController(max_rpm=self.max_rpm, logger=self._logger)
-        if self.function_calling_llm:
-            if isinstance(self.function_calling_llm, str):
-                self.function_calling_llm = LLM(model=self.function_calling_llm)
-            elif not isinstance(self.function_calling_llm, LLM):
-                self.function_calling_llm = LLM(
-                    model=getattr(self.function_calling_llm, "model_name", None)
-                    or getattr(self.function_calling_llm, "deployment_name", None)
-                    or str(self.function_calling_llm)
-                )
+        if self.function_calling_llm and not isinstance(self.function_calling_llm, LLM):
+            self.function_calling_llm = create_llm(self.function_calling_llm)
+
         self._telemetry = Telemetry()
         self._telemetry.set_tracer()
         return self

src/crewai/tools/tool_usage.py

@@ -1,9 +1,13 @@
 import ast
 import datetime
+import json
+import re
 import time
 from difflib import SequenceMatcher
 from textwrap import dedent
-from typing import Any, List, Union
+from typing import Any, Dict, List, Union
+
+from json_repair import repair_json
 
 import crewai.utilities.events as events
 from crewai.agents.tools_handler import ToolsHandler
@@ -19,7 +23,15 @@ try:
     import agentops  # type: ignore
 except ImportError:
     agentops = None
-OPENAI_BIGGER_MODELS = ["gpt-4", "gpt-4o", "o1-preview", "o1-mini", "o1", "o3", "o3-mini"]
+OPENAI_BIGGER_MODELS = [
+    "gpt-4",
+    "gpt-4o",
+    "o1-preview",
+    "o1-mini",
+    "o1",
+    "o3",
+    "o3-mini",
+]
 
 
 class ToolUsageErrorException(Exception):
@@ -80,7 +92,7 @@ class ToolUsage:
             self._max_parsing_attempts = 2
             self._remember_format_after_usages = 4
 
-    def parse(self, tool_string: str):
+    def parse_tool_calling(self, tool_string: str):
         """Parse the tool string and return the tool calling."""
         return self._tool_calling(tool_string)
 
@@ -94,7 +106,6 @@ class ToolUsage:
             self.task.increment_tools_errors()
             return error
 
-        # BUG? The code below seems to be unreachable
         try:
             tool = self._select_tool(calling.tool_name)
         except Exception as e:
@@ -116,7 +127,7 @@ class ToolUsage:
                     self._printer.print(content=f"\n\n{error}\n", color="red")
                 return error
 
-        return f"{self._use(tool_string=tool_string, tool=tool, calling=calling)}"  # type: ignore # BUG?: "_use" of "ToolUsage" does not return a value (it only ever returns None)
+        return f"{self._use(tool_string=tool_string, tool=tool, calling=calling)}"
 
     def _use(
         self,
@@ -349,13 +360,13 @@ class ToolUsage:
         tool_name = self.action.tool
         tool = self._select_tool(tool_name)
         try:
-            tool_input = self._validate_tool_input(self.action.tool_input)
-            arguments = ast.literal_eval(tool_input)
+            arguments = self._validate_tool_input(self.action.tool_input)
+
         except Exception:
             if raise_error:
                 raise
             else:
-                return ToolUsageErrorException(  # type: ignore # Incompatible return value type (got "ToolUsageErrorException", expected "ToolCalling | InstructorToolCalling")
+                return ToolUsageErrorException(
                     f'{self._i18n.errors("tool_arguments_error")}'
                 )
 
@@ -363,14 +374,14 @@ class ToolUsage:
             if raise_error:
                 raise
             else:
-                return ToolUsageErrorException(  # type: ignore # Incompatible return value type (got "ToolUsageErrorException", expected "ToolCalling | InstructorToolCalling")
+                return ToolUsageErrorException(
                     f'{self._i18n.errors("tool_arguments_error")}'
                 )
 
         return ToolCalling(
             tool_name=tool.name,
             arguments=arguments,
-            log=tool_string,  # type: ignore
+            log=tool_string,
         )
 
     def _tool_calling(
@@ -396,57 +407,28 @@ class ToolUsage:
                 )
             return self._tool_calling(tool_string)
 
-    def _validate_tool_input(self, tool_input: str) -> str:
+    def _validate_tool_input(self, tool_input: str) -> Dict[str, Any]:
         try:
-            ast.literal_eval(tool_input)
-            return tool_input
-        except Exception:
-            # Clean and ensure the string is properly enclosed in braces
-            tool_input = tool_input.strip()
-            if not tool_input.startswith("{"):
-                tool_input = "{" + tool_input
-            if not tool_input.endswith("}"):
-                tool_input += "}"
+            # Replace Python literals with JSON equivalents
+            replacements = {
+                r"'": '"',
+                r"None": "null",
+                r"True": "true",
+                r"False": "false",
+            }
+            for pattern, replacement in replacements.items():
+                tool_input = re.sub(pattern, replacement, tool_input)
 
-            # Manually split the input into key-value pairs
-            entries = tool_input.strip("{} ").split(",")
-            formatted_entries = []
+            arguments = json.loads(tool_input)
+        except json.JSONDecodeError:
+            # Attempt to repair JSON string
+            repaired_input = repair_json(tool_input)
+            try:
+                arguments = json.loads(repaired_input)
+            except json.JSONDecodeError as e:
+                raise Exception(f"Invalid tool input JSON: {e}")
 
-            for entry in entries:
-                if ":" not in entry:
-                    continue  # Skip malformed entries
-                key, value = entry.split(":", 1)
-
-                # Remove extraneous white spaces and quotes, replace single quotes
-                key = key.strip().strip('"').replace("'", '"')
-                value = value.strip()
-
-                # Handle replacement of single quotes at the start and end of the value string
-                if value.startswith("'") and value.endswith("'"):
-                    value = value[1:-1]  # Remove single quotes
-                    value = (
-                        '"' + value.replace('"', '\\"') + '"'
-                    )  # Re-encapsulate with double quotes
-                elif value.isdigit():  # Check if value is a digit, hence integer
-                    value = value
-                elif value.lower() in [
-                    "true",
-                    "false",
-                ]:  # Check for boolean and null values
-                    value = value.lower().capitalize()
-                elif value.lower() == "null":
-                    value = "None"
-                else:
-                    # Assume the value is a string and needs quotes
-                    value = '"' + value.replace('"', '\\"') + '"'
-
-                # Rebuild the entry with proper quoting
-                formatted_entry = f'"{key}": {value}'
-                formatted_entries.append(formatted_entry)
-
-            # Reconstruct the JSON string
-            new_json_string = "{" + ", ".join(formatted_entries) + "}"
-            return new_json_string
+        return arguments
 
     def on_tool_error(self, tool: Any, tool_calling: ToolCalling, e: Exception) -> None:
         event_data = self._prepare_event_data(tool, tool_calling)

src/crewai/translations/en.json

@@ -9,11 +9,11 @@
     "task": "\nCurrent Task: {input}\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:",
     "memory": "\n\n# Useful context: \n{memory}",
     "role_playing": "You are {role}. {backstory}\nYour personal goal is: {goal}",
-    "tools": "\nYou ONLY have access to the following tools, and should NEVER make up tools that are not listed here:\n\n{tools}\n\nUse the following format:\n\nThought: you should always think about what to do\nAction: the action to take, only one name of [{tool_names}], just the name, exactly as it's written.\nAction Input: the input to the action, just a simple python dictionary, enclosed in curly braces, using \" to wrap keys and values.\nObservation: the result of the action\n\nOnce all necessary information is gathered:\n\nThought: I now know the final answer\nFinal Answer: the final answer to the original input question\n",
-    "no_tools": "\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!",
-    "format": "I MUST either use a tool (use one at time) OR give my best final answer not both at the same time. To Use the following format:\n\nThought: you should always think about what to do\nAction: the action to take, should be one of [{tool_names}]\nAction Input: the input to the action, dictionary enclosed in curly braces\nObservation: the result of the action\n... (this Thought/Action/Action Input/Result can repeat N times)\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\n",
-    "final_answer_format": "If you don't need to use any more tools, you must give your best complete final answer, make sure it satisfies the expected criteria, use the EXACT format below:\n\nThought: I now can give a great answer\nFinal Answer: my best complete final answer to the task.\n\n",
-    "format_without_tools": "\nSorry, I didn't use the right format. I MUST either use a tool (among the available ones), OR give my best final answer.\nI just remembered the expected format I must follow:\n\nQuestion: the input question you must answer\nThought: you should always think about what to do\nAction: the action to take, should be one of [{tool_names}]\nAction Input: the input to the action\nObservation: the result of the action\n... (this Thought/Action/Action Input/Result can repeat N times)\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\n",
+    "tools": "\nYou ONLY have access to the following tools, and should NEVER make up tools that are not listed here:\n\n{tools}\n\nIMPORTANT: Use the following format in your response:\n\n```\nThought: you should always think about what to do\nAction: the action to take, only one name of [{tool_names}], just the name, exactly as it's written.\nAction Input: the input to the action, just a simple JSON object, enclosed in curly braces, using \" to wrap keys and values.\nObservation: the result of the action\n```\n\nOnce all necessary information is gathered, return the following format:\n\n```\nThought: I now know the final answer\nFinal Answer: the final answer to the original input question\n```",
+    "no_tools": "\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!",
+    "format": "I MUST either use a tool (use one at time) OR give my best final answer not both at the same time. When responding, I must use the following format:\n\n```\nThought: you should always think about what to do\nAction: the action to take, should be one of [{tool_names}]\nAction Input: the input to the action, dictionary enclosed in curly braces\nObservation: the result of the action\n```\nThis Thought/Action/Action Input/Result can repeat N times. Once I know the final answer, I must return the following format:\n\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\n```",
+    "final_answer_format": "If you don't need to use any more tools, you must give your best complete final answer, make sure it satisfies the expected criteria, use the EXACT format below:\n\n```\nThought: I now can give a great answer\nFinal Answer: my best complete final answer to the task.\n\n```",
+    "format_without_tools": "\nSorry, I didn't use the right format. I MUST either use a tool (among the available ones), OR give my best final answer.\nHere is the expected format I must follow:\n\n```\nQuestion: the input question you must answer\nThought: you should always think about what to do\nAction: the action to take, should be one of [{tool_names}]\nAction Input: the input to the action\nObservation: the result of the action\n```\n This Thought/Action/Action Input/Result process can repeat N times. Once I know the final answer, I must return the following format:\n\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\n```",
     "task_with_context": "{task}\n\nThis is the context you're working with:\n{context}",
     "expected_output": "\nThis is the expect criteria for your final answer: {expected_output}\nyou MUST return the actual complete content as the final answer, not a summary.",
     "human_feedback": "You got human feedback on your work, re-evaluate it and give a new Final Answer when ready.\n {human_feedback}",

tests/cassettes/test_agent_tool_role_matching[ "Futel Official Infopoint" -True].yaml

@@ -0,0 +1,117 @@
+interactions:
+- request:
+    body: '{"messages": [{"role": "system", "content": "You are Futel Official Infopoint.
+      Futel Football Club info\nYour personal goal is: Answer questions about Futel\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 expect 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\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", "stop": ["\nObservation:"], "stream": false}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '939'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=cwWdOaPJjFMNJaLtJfa8Kjqavswg5bzVRFzBX4gneGw-1736458417-1.0.1.1-bvf2HshgcMtgn7GdxqwySFDAIacGccDFfEXniBFTTDmbGMCiIIwf6t2DiwWnBldmUHixwc5kDO9gYs08g.feBA;
+        _cfuvid=WMw7PSqkYqQOieguBRs0uNkwNU92A.ZKbgDbCAcV3EQ-1736458417825-0.0.1.1-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.52.1
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.52.1
+      x-stainless-raw-response:
+      - 'true'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.7
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-AnuRlxiTxduAVoXHHY58Fvfbll5IS\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1736458417,\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: This is a test task, and the context or question from the coworker is
+      not specified. Therefore, my best effort would be to affirm my readiness to
+      answer accurately and in detail any question about Futel Football Club based
+      on the context described. If provided with specific information or questions,
+      I will ensure to respond comprehensively as required by my job directives.\",\n
+      \       \"refusal\": null\n      },\n      \"logprobs\": null,\n      \"finish_reason\":
+      \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 177,\n    \"completion_tokens\":
+      82,\n    \"total_tokens\": 259,\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  \"system_fingerprint\":
+      \"fp_703d4ff298\"\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 8ff78bf7bd6cc002-ATL
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Thu, 09 Jan 2025 21:33:40 GMT
+      Server:
+      - cloudflare
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - nosniff
+      access-control-expose-headers:
+      - X-Request-ID
+      alt-svc:
+      - h3=":443"; ma=86400
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '2263'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      x-ratelimit-limit-requests:
+      - '10000'
+      x-ratelimit-limit-tokens:
+      - '30000000'
+      x-ratelimit-remaining-requests:
+      - '9999'
+      x-ratelimit-remaining-tokens:
+      - '29999786'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_7c1a31da73cd103e9f410f908e59187f
+    http_version: HTTP/1.1
+    status_code: 200
+version: 1

tests/cassettes/test_agent_tool_role_matching[ FUTEL\nOFFICIAL INFOPOINT -True].yaml

@@ -0,0 +1,119 @@
+interactions:
+- request:
+    body: '{"messages": [{"role": "system", "content": "You are Futel Official Infopoint.
+      Futel Football Club info\nYour personal goal is: Answer questions about Futel\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 expect 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\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", "stop": ["\nObservation:"], "stream": false}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '939'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=cwWdOaPJjFMNJaLtJfa8Kjqavswg5bzVRFzBX4gneGw-1736458417-1.0.1.1-bvf2HshgcMtgn7GdxqwySFDAIacGccDFfEXniBFTTDmbGMCiIIwf6t2DiwWnBldmUHixwc5kDO9gYs08g.feBA;
+        _cfuvid=WMw7PSqkYqQOieguBRs0uNkwNU92A.ZKbgDbCAcV3EQ-1736458417825-0.0.1.1-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.52.1
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.52.1
+      x-stainless-raw-response:
+      - 'true'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.7
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-AnuRrFJZGKw8cIEshvuW1PKwFZFKs\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1736458423,\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: Although you mentioned this being a \\\"Test task\\\" and haven't provided
+      a specific question regarding Futel Football Club, your request appears to involve
+      ensuring accuracy and detail in responses. For a proper answer about Futel,
+      I'd be ready to provide details about the club's history, management, players,
+      match schedules, and recent performance statistics. Remember to ask specific
+      questions to receive a targeted response. If this were a real context where
+      information was shared, I would respond precisely to what's been asked regarding
+      Futel Football Club.\",\n        \"refusal\": null\n      },\n      \"logprobs\":
+      null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+      177,\n    \"completion_tokens\": 113,\n    \"total_tokens\": 290,\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  \"system_fingerprint\":
+      \"fp_703d4ff298\"\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 8ff78c1d0ecdc002-ATL
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Thu, 09 Jan 2025 21:33:47 GMT
+      Server:
+      - cloudflare
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - nosniff
+      access-control-expose-headers:
+      - X-Request-ID
+      alt-svc:
+      - h3=":443"; ma=86400
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '3097'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      x-ratelimit-limit-requests:
+      - '10000'
+      x-ratelimit-limit-tokens:
+      - '30000000'
+      x-ratelimit-remaining-requests:
+      - '9999'
+      x-ratelimit-remaining-tokens:
+      - '29999786'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_179e1d56e2b17303e40480baffbc7b08
+    http_version: HTTP/1.1
+    status_code: 200
+version: 1

tests/cassettes/test_agent_tool_role_matching["Futel Official Infopoint"-True].yaml

@@ -0,0 +1,114 @@
+interactions:
+- request:
+    body: '{"messages": [{"role": "system", "content": "You are Futel Official Infopoint.
+      Futel Football Club info\nYour personal goal is: Answer questions about Futel\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 expect 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\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", "stop": ["\nObservation:"], "stream": false}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '939'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=cwWdOaPJjFMNJaLtJfa8Kjqavswg5bzVRFzBX4gneGw-1736458417-1.0.1.1-bvf2HshgcMtgn7GdxqwySFDAIacGccDFfEXniBFTTDmbGMCiIIwf6t2DiwWnBldmUHixwc5kDO9gYs08g.feBA;
+        _cfuvid=WMw7PSqkYqQOieguBRs0uNkwNU92A.ZKbgDbCAcV3EQ-1736458417825-0.0.1.1-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.52.1
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.52.1
+      x-stainless-raw-response:
+      - 'true'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.7
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-AnuRqgg7eiHnDi2DOqdk99fiqOboz\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1736458422,\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: Your best answer to your coworker asking you this, accounting for the
+      context shared. You MUST return the actual complete content as the final answer,
+      not a summary.\",\n        \"refusal\": null\n      },\n      \"logprobs\":
+      null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+      177,\n    \"completion_tokens\": 44,\n    \"total_tokens\": 221,\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  \"system_fingerprint\":
+      \"fp_703d4ff298\"\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 8ff78c164ad2c002-ATL
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Thu, 09 Jan 2025 21:33:43 GMT
+      Server:
+      - cloudflare
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - nosniff
+      access-control-expose-headers:
+      - X-Request-ID
+      alt-svc:
+      - h3=":443"; ma=86400
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '899'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      x-ratelimit-limit-requests:
+      - '10000'
+      x-ratelimit-limit-tokens:
+      - '30000000'
+      x-ratelimit-remaining-requests:
+      - '9999'
+      x-ratelimit-remaining-tokens:
+      - '29999786'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_9f5226208edb90a27987aaf7e0ca03d3
+    http_version: HTTP/1.1
+    status_code: 200
+version: 1

tests/cassettes/test_agent_tool_role_matching[Futel Official Infopoint-True].yaml

@@ -0,0 +1,119 @@
+interactions:
+- request:
+    body: '{"messages": [{"role": "system", "content": "You are Futel Official Infopoint.
+      Futel Football Club info\nYour personal goal is: Answer questions about Futel\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 expect 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\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", "stop": ["\nObservation:"], "stream": false}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '939'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.52.1
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.52.1
+      x-stainless-raw-response:
+      - 'true'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.7
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-AnuRjmwH5mrykLxQhFwTqqTiDtuTf\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1736458415,\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: As this is a test task, please note that Futel Football Club is fictional
+      and any specific details about it would not be available. However, if you have
+      specific questions or need information about a particular aspect of Futel or
+      any general football club inquiry, feel free to ask, and I'll do my best to
+      assist you with your query!\",\n        \"refusal\": null\n      },\n      \"logprobs\":
+      null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+      177,\n    \"completion_tokens\": 79,\n    \"total_tokens\": 256,\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  \"system_fingerprint\":
+      \"fp_703d4ff298\"\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 8ff78be5eebfc002-ATL
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Thu, 09 Jan 2025 21:33:37 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - __cf_bm=cwWdOaPJjFMNJaLtJfa8Kjqavswg5bzVRFzBX4gneGw-1736458417-1.0.1.1-bvf2HshgcMtgn7GdxqwySFDAIacGccDFfEXniBFTTDmbGMCiIIwf6t2DiwWnBldmUHixwc5kDO9gYs08g.feBA;
+        path=/; expires=Thu, 09-Jan-25 22:03:37 GMT; domain=.api.openai.com; HttpOnly;
+        Secure; SameSite=None
+      - _cfuvid=WMw7PSqkYqQOieguBRs0uNkwNU92A.ZKbgDbCAcV3EQ-1736458417825-0.0.1.1-604800000;
+        path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - nosniff
+      access-control-expose-headers:
+      - X-Request-ID
+      alt-svc:
+      - h3=":443"; ma=86400
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '2730'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      x-ratelimit-limit-requests:
+      - '10000'
+      x-ratelimit-limit-tokens:
+      - '30000000'
+      x-ratelimit-remaining-requests:
+      - '9999'
+      x-ratelimit-remaining-tokens:
+      - '29999786'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_014478ba748f860d10ac250ca0ba824a
+    http_version: HTTP/1.1
+    status_code: 200
+version: 1

tests/cassettes/test_agent_tool_role_matching[Futel Official Infopoint\n-True].yaml

@@ -0,0 +1,119 @@
+interactions:
+- request:
+    body: '{"messages": [{"role": "system", "content": "You are Futel Official Infopoint.
+      Futel Football Club info\nYour personal goal is: Answer questions about Futel\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 expect 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\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", "stop": ["\nObservation:"], "stream": false}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '939'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=cwWdOaPJjFMNJaLtJfa8Kjqavswg5bzVRFzBX4gneGw-1736458417-1.0.1.1-bvf2HshgcMtgn7GdxqwySFDAIacGccDFfEXniBFTTDmbGMCiIIwf6t2DiwWnBldmUHixwc5kDO9gYs08g.feBA;
+        _cfuvid=WMw7PSqkYqQOieguBRs0uNkwNU92A.ZKbgDbCAcV3EQ-1736458417825-0.0.1.1-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.52.1
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.52.1
+      x-stainless-raw-response:
+      - 'true'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.7
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-AnuRofLgmzWcDya5LILqYwIJYgFoq\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1736458420,\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: As an official Futel Football Club infopoint, my responsibility is to
+      provide detailed and accurate information about the club. This includes answering
+      questions regarding team statistics, player performances, upcoming fixtures,
+      ticketing and fan zone details, club history, and community initiatives. Our
+      focus is to ensure that fans and stakeholders have access to the latest and
+      most precise information about the club's on and off-pitch activities. If there's
+      anything specific you need to know, just let me know, and I'll be more than
+      happy to assist!\",\n        \"refusal\": null\n      },\n      \"logprobs\":
+      null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+      177,\n    \"completion_tokens\": 115,\n    \"total_tokens\": 292,\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  \"system_fingerprint\":
+      \"fp_703d4ff298\"\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 8ff78c066f37c002-ATL
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Thu, 09 Jan 2025 21:33:42 GMT
+      Server:
+      - cloudflare
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - nosniff
+      access-control-expose-headers:
+      - X-Request-ID
+      alt-svc:
+      - h3=":443"; ma=86400
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '2459'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      x-ratelimit-limit-requests:
+      - '10000'
+      x-ratelimit-limit-tokens:
+      - '30000000'
+      x-ratelimit-remaining-requests:
+      - '9999'
+      x-ratelimit-remaining-tokens:
+      - '29999786'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_a146dd27f040f39a576750970cca0f52
+    http_version: HTTP/1.1
+    status_code: 200
+version: 1

tests/crew_test.py

@@ -1464,39 +1464,35 @@ def test_dont_set_agents_step_callback_if_already_set():
 
 @pytest.mark.vcr(filter_headers=["authorization"])
 def test_crew_function_calling_llm():
-    from unittest.mock import patch
 
+    from crewai import LLM
     from crewai.tools import tool
 
-    llm = "gpt-4o"
+    llm = LLM(model="gpt-4o-mini")
 
     @tool
-    def learn_about_AI() -> str:
-        """Useful for when you need to learn about AI to write an paragraph about it."""
-        return "AI is a very broad field."
+    def look_up_greeting() -> str:
+        """Tool used to retrieve a greeting."""
+        return "Howdy!"
 
     agent1 = Agent(
-        role="test role",
-        goal="test goal",
-        backstory="test backstory",
-        tools=[learn_about_AI],
+        role="Greeter",
+        goal="Say hello.",
+        backstory="You are a friendly greeter.",
+        tools=[look_up_greeting],
         llm="gpt-4o-mini",
         function_calling_llm=llm,
     )
 
     essay = Task(
-        description="Write and then review an small paragraph on AI until it's AMAZING",
-        expected_output="The final paragraph.",
+        description="Look up the greeting and say it.",
+        expected_output="A greeting.",
         agent=agent1,
     )
-    tasks = [essay]
-    crew = Crew(agents=[agent1], tasks=tasks)
 
-    with patch.object(
-        instructor, "from_litellm", wraps=instructor.from_litellm
-    ) as mock_from_litellm:
-        crew.kickoff()
-        mock_from_litellm.assert_called()
+    crew = Crew(agents=[agent1], tasks=[essay])
+    result = crew.kickoff()
+    assert result.raw == "Howdy!"
 
 
 @pytest.mark.vcr(filter_headers=["authorization"])

tests/test_manager_llm_delegation.py

@@ -1,8 +1,6 @@
-from unittest.mock import MagicMock
-
 import pytest
 
-from crewai import Agent, Task
+from crewai import Agent
 from crewai.tools.agent_tools.base_agent_tools import BaseAgentTool
 
 
@@ -22,12 +20,9 @@ class InternalAgentTool(BaseAgentTool):
         ("Futel Official Infopoint\n", True),  # trailing newline
         ('"Futel Official Infopoint"', True),  # embedded quotes
         (" FUTEL\nOFFICIAL   INFOPOINT ", True),  # multiple whitespace and newline
-        ("futel official infopoint", True),  # lowercase
-        ("FUTEL OFFICIAL INFOPOINT", True),  # uppercase
-        ("Non Existent Agent", False),  # non-existent agent
-        (None, False),  # None agent name
     ],
 )
+@pytest.mark.vcr(filter_headers=["authorization"])
 def test_agent_tool_role_matching(role_name, should_match):
     """Test that agent tools can match roles regardless of case, whitespace, and special characters."""
     # Create test agent

tests/tools/test_tool_usage.py

@@ -121,3 +121,113 @@ def test_tool_usage_render():
         "Tool Name: Random Number Generator\nTool Arguments: {'min_value': {'description': 'The minimum value of the range (inclusive)', 'type': 'int'}, 'max_value': {'description': 'The maximum value of the range (inclusive)', 'type': 'int'}}\nTool Description: Generates a random number within a specified range"
         in rendered
     )
+
+
+def test_validate_tool_input_booleans_and_none():
+    # Create a ToolUsage instance with mocks
+    tool_usage = ToolUsage(
+        tools_handler=MagicMock(),
+        tools=[],
+        original_tools=[],
+        tools_description="",
+        tools_names="",
+        task=MagicMock(),
+        function_calling_llm=MagicMock(),
+        agent=MagicMock(),
+        action=MagicMock(),
+    )
+
+    # Input with booleans and None
+    tool_input = '{"key1": True, "key2": False, "key3": None}'
+    expected_arguments = {"key1": True, "key2": False, "key3": None}
+
+    arguments = tool_usage._validate_tool_input(tool_input)
+    assert arguments == expected_arguments
+
+
+def test_validate_tool_input_mixed_types():
+    # Create a ToolUsage instance with mocks
+    tool_usage = ToolUsage(
+        tools_handler=MagicMock(),
+        tools=[],
+        original_tools=[],
+        tools_description="",
+        tools_names="",
+        task=MagicMock(),
+        function_calling_llm=MagicMock(),
+        agent=MagicMock(),
+        action=MagicMock(),
+    )
+
+    # Input with mixed types
+    tool_input = '{"number": 123, "text": "Some text", "flag": True}'
+    expected_arguments = {"number": 123, "text": "Some text", "flag": True}
+
+    arguments = tool_usage._validate_tool_input(tool_input)
+    assert arguments == expected_arguments
+
+
+def test_validate_tool_input_single_quotes():
+    # Create a ToolUsage instance with mocks
+    tool_usage = ToolUsage(
+        tools_handler=MagicMock(),
+        tools=[],
+        original_tools=[],
+        tools_description="",
+        tools_names="",
+        task=MagicMock(),
+        function_calling_llm=MagicMock(),
+        agent=MagicMock(),
+        action=MagicMock(),
+    )
+
+    # Input with single quotes instead of double quotes
+    tool_input = "{'key': 'value', 'flag': True}"
+    expected_arguments = {"key": "value", "flag": True}
+
+    arguments = tool_usage._validate_tool_input(tool_input)
+    assert arguments == expected_arguments
+
+
+def test_validate_tool_input_invalid_json_repairable():
+    # Create a ToolUsage instance with mocks
+    tool_usage = ToolUsage(
+        tools_handler=MagicMock(),
+        tools=[],
+        original_tools=[],
+        tools_description="",
+        tools_names="",
+        task=MagicMock(),
+        function_calling_llm=MagicMock(),
+        agent=MagicMock(),
+        action=MagicMock(),
+    )
+
+    # Invalid JSON input that can be repaired
+    tool_input = '{"key": "value", "list": [1, 2, 3,]}'
+    expected_arguments = {"key": "value", "list": [1, 2, 3]}
+
+    arguments = tool_usage._validate_tool_input(tool_input)
+    assert arguments == expected_arguments
+
+
+def test_validate_tool_input_with_special_characters():
+    # Create a ToolUsage instance with mocks
+    tool_usage = ToolUsage(
+        tools_handler=MagicMock(),
+        tools=[],
+        original_tools=[],
+        tools_description="",
+        tools_names="",
+        task=MagicMock(),
+        function_calling_llm=MagicMock(),
+        agent=MagicMock(),
+        action=MagicMock(),
+    )
+
+    # Input with special characters
+    tool_input = '{"message": "Hello, world! \u263A", "valid": True}'
+    expected_arguments = {"message": "Hello, world! ☺", "valid": True}
+
+    arguments = tool_usage._validate_tool_input(tool_input)
+    assert arguments == expected_arguments