andre/crewAI
1
0
Fork 0
mirror of https://github.com/crewAIInc/crewAI.git synced 2026-04-25 12:22:38 +00:00
Code Issues Actions 5 Packages Projects Releases Wiki Activity

feat: enhance agent planning with structured todo management

Browse Source 
This commit introduces a new planning system within the AgentExecutor class, allowing for the creation of structured todo items from planning steps. The TodoList and TodoItem models have been added to facilitate tracking of plan execution. The reasoning plan now includes a list of steps, improving the clarity and organization of agent tasks. Additionally, tests have been added to validate the new planning functionality and ensure proper integration with existing workflows.
This commit is contained in:
lorenzejay
2026-02-03 13:24:55 -08:00
parent ab6ce4b7aa
commit bd95cffd41
9 changed files with 4796 additions and 21 deletions
Download Patch File Download Diff File Expand all files Collapse all files

28
lib/crewai/src/crewai/experimental/agent_executor.py
View File

@@ -61,6 +61,7 @@ from crewai.utilities.agent_utils import (
)
from crewai.utilities.constants import TRAINING_DATA_FILE
from crewai.utilities.i18n import I18N, get_i18n
from crewai.utilities.planning_types import PlanStep, TodoItem, TodoList
from crewai.utilities.printer import Printer
from crewai.utilities.string_utils import sanitize_tool_name
from crewai.utilities.tool_utils import execute_tool_and_check_finality
@@ -98,6 +99,9 @@ class AgentReActState(BaseModel):
plan_ready: bool = Field(
default=False, description="Whether agent is ready to execute"
)
todos: TodoList = Field(
default_factory=TodoList, description="Todo list for tracking plan execution"
)
class AgentExecutor(Flow[AgentReActState], CrewAgentExecutorMixin):
@@ -330,7 +334,7 @@ class AgentExecutor(Flow[AgentReActState], CrewAgentExecutorMixin):
This is the entry point for the agent execution flow. If planning is
enabled on the agent, it generates a plan before execution begins.
The plan is stored in state but not executed on yet (Phase 2).
The plan is stored in state and todos are created from the steps.
"""
if not getattr(self.agent, "planning_enabled", False):
return
@@ -354,6 +358,9 @@ class AgentExecutor(Flow[AgentReActState], CrewAgentExecutorMixin):
self.state.plan = output.plan.plan
self.state.plan_ready = output.plan.ready
if self.state.plan_ready and output.plan.steps:
self._create_todos_from_plan(output.plan.steps)
# Backward compatibility: append plan to task description
# This can be removed in Phase 2 when plan execution is implemented
if self.task and self.state.plan:
@@ -363,6 +370,25 @@ class AgentExecutor(Flow[AgentReActState], CrewAgentExecutorMixin):
if hasattr(self.agent, "_logger"):
self.agent._logger.log("error", f"Error during planning: {e!s}")
def _create_todos_from_plan(self, steps: list[PlanStep]) -> None:
"""Convert plan steps into trackable todo items.
Args:
steps: List of PlanStep objects from the reasoning handler.
"""
todos: list[TodoItem] = []
for step in steps:
todo = TodoItem(
step_number=step.step_number,
description=step.description,
tool_to_use=step.tool_to_use,
depends_on=step.depends_on,
status="pending",
)
todos.append(todo)
self.state.todos = TodoList(items=todos)
@listen(generate_plan)
def initialize_reasoning(self) -> Literal["initialized"]:
"""Initialize the reasoning flow and emit agent start logs."""

103
lib/crewai/src/crewai/utilities/planning_types.py Normal file
View File

@@ -0,0 +1,103 @@
"""Types for agent planning and todo tracking."""
from __future__ import annotations
from typing import Literal
from uuid import uuid4
from pydantic import BaseModel, Field
# Todo status type
TodoStatus = Literal["pending", "running", "completed"]
class PlanStep(BaseModel):
"""A single step in the reasoning plan."""
step_number: int = Field(description="Step number (1-based)")
description: str = Field(description="What to do in this step")
tool_to_use: str | None = Field(
default=None, description="Tool to use for this step, if any"
)
depends_on: list[int] = Field(
default_factory=list, description="Step numbers this step depends on"
)
class TodoItem(BaseModel):
"""A single todo item representing a step in the execution plan."""
id: str = Field(default_factory=lambda: str(uuid4()))
step_number: int = Field(description="Order of this step in the plan (1-based)")
description: str = Field(description="What needs to be done")
tool_to_use: str | None = Field(
default=None, description="Tool to use for this step, if any"
)
status: TodoStatus = Field(default="pending", description="Current status")
depends_on: list[int] = Field(
default_factory=list, description="Step numbers this depends on"
)
result: str | None = Field(
default=None, description="Result after completion, if any"
)
class TodoList(BaseModel):
"""Collection of todos for tracking plan execution."""
items: list[TodoItem] = Field(default_factory=list)
@property
def current_todo(self) -> TodoItem | None:
"""Get the currently running todo item."""
for item in self.items:
if item.status == "running":
return item
return None
@property
def next_pending(self) -> TodoItem | None:
"""Get the next pending todo item."""
for item in self.items:
if item.status == "pending":
return item
return None
@property
def is_complete(self) -> bool:
"""Check if all todos are completed."""
return len(self.items) > 0 and all(
item.status == "completed" for item in self.items
)
@property
def pending_count(self) -> int:
"""Count of pending todos."""
return sum(1 for item in self.items if item.status == "pending")
@property
def completed_count(self) -> int:
"""Count of completed todos."""
return sum(1 for item in self.items if item.status == "completed")
def get_by_step_number(self, step_number: int) -> TodoItem | None:
"""Get a todo by its step number."""
for item in self.items:
if item.step_number == step_number:
return item
return None
def mark_running(self, step_number: int) -> None:
"""Mark a todo as running by step number."""
item = self.get_by_step_number(step_number)
if item:
item.status = "running"
def mark_completed(self, step_number: int, result: str | None = None) -> None:
"""Mark a todo as completed by step number."""
item = self.get_by_step_number(step_number)
if item:
item.status = "completed"
if result:
item.result = result

109
lib/crewai/src/crewai/utilities/reasoning_handler.py
View File

@@ -16,6 +16,7 @@ from crewai.events.types.reasoning_events import (
)
from crewai.llm import LLM
from crewai.utilities.llm_utils import create_llm
from crewai.utilities.planning_types import PlanStep
from crewai.utilities.string_utils import sanitize_tool_name
@@ -29,6 +30,9 @@ class ReasoningPlan(BaseModel):
"""Model representing a reasoning plan for a task."""
plan: str = Field(description="The detailed reasoning plan for the task.")
steps: list[PlanStep] = Field(
default_factory=list, description="Structured steps to execute"
)
ready: bool = Field(description="Whether the agent is ready to execute the task.")
@@ -47,20 +51,53 @@ FUNCTION_SCHEMA: Final[dict[str, Any]] = {
"type": "function",
"function": {
"name": "create_reasoning_plan",
"description": "Create or refine a reasoning plan for a task",
"description": "Create or refine a reasoning plan for a task with structured steps",
"parameters": {
"type": "object",
"properties": {
"plan": {
"type": "string",
"description": "The detailed reasoning plan for the task.",
"description": "A brief summary of the overall plan.",
},
"steps": {
"type": "array",
"description": "List of discrete steps to execute the plan",
"items": {
"type": "object",
"properties": {
"step_number": {
"type": "integer",
"description": "Step number (1-based)",
},
"description": {
"type": "string",
"description": "What to do in this step",
},
"tool_to_use": {
"type": ["string", "null"],
"description": "Tool to use for this step, or null if no tool needed",
},
"depends_on": {
"type": "array",
"items": {"type": "integer"},
"description": "Step numbers this step depends on (empty array if none)",
},
},
"required": [
"step_number",
"description",
"tool_to_use",
"depends_on",
],
"additionalProperties": False,
},
},
"ready": {
"type": "boolean",
"description": "Whether the agent is ready to execute the task.",
},
},
"required": ["plan", "ready"],
"required": ["plan", "steps", "ready"],
"additionalProperties": False,
},
},
@@ -214,40 +251,46 @@ class AgentReasoning:
Returns:
The output of the agent planning process.
"""
plan, ready = self._create_initial_plan()
plan, ready = self._refine_plan_if_needed(plan, ready)
plan, steps, ready = self._create_initial_plan()
plan, steps, ready = self._refine_plan_if_needed(plan, steps, ready)
reasoning_plan = ReasoningPlan(plan=plan, ready=ready)
reasoning_plan = ReasoningPlan(plan=plan, steps=steps, ready=ready)
return AgentReasoningOutput(plan=reasoning_plan)
def _create_initial_plan(self) -> tuple[str, bool]:
def _create_initial_plan(self) -> tuple[str, list[PlanStep], bool]:
"""Creates the initial plan for the task.
Returns:
The initial plan and whether the agent is ready to execute the task.
A tuple of the plan summary, list of steps, and whether the agent is ready.
"""
planning_prompt = self._create_planning_prompt()
if self.llm.supports_function_calling():
plan, ready = self._call_with_function(planning_prompt, "create_plan")
return plan, ready
plan, steps, ready = self._call_with_function(
planning_prompt, "create_plan"
)
return plan, steps, ready
response = self._call_llm_with_prompt(
prompt=planning_prompt,
plan_type="create_plan",
)
return self._parse_planning_response(str(response))
plan, ready = self._parse_planning_response(str(response))
return plan, [], ready # No structured steps from text parsing
def _refine_plan_if_needed(self, plan: str, ready: bool) -> tuple[str, bool]:
def _refine_plan_if_needed(
self, plan: str, steps: list[PlanStep], ready: bool
) -> tuple[str, list[PlanStep], bool]:
"""Refines the plan if the agent is not ready to execute the task.
Args:
plan: The current plan.
steps: The current list of steps.
ready: Whether the agent is ready to execute the task.
Returns:
The refined plan and whether the agent is ready to execute the task.
The refined plan, steps, and whether the agent is ready to execute.
"""
attempt = 1
max_attempts = self.config.max_attempts
@@ -271,13 +314,16 @@ class AgentReasoning:
refine_prompt = self._create_refine_prompt(plan)
if self.llm.supports_function_calling():
plan, ready = self._call_with_function(refine_prompt, "refine_plan")
plan, steps, ready = self._call_with_function(
refine_prompt, "refine_plan"
)
else:
response = self._call_llm_with_prompt(
prompt=refine_prompt,
plan_type="refine_plan",
)
plan, ready = self._parse_planning_response(str(response))
steps = [] # No structured steps from text parsing
attempt += 1
@@ -288,11 +334,11 @@ class AgentReasoning:
)
break
return plan, ready
return plan, steps, ready
def _call_with_function(
self, prompt: str, plan_type: Literal["create_plan", "refine_plan"]
) -> tuple[str, bool]:
) -> tuple[str, list[PlanStep], bool]:
"""Calls the LLM with function calling to get a plan.
Args:
@@ -300,7 +346,7 @@ class AgentReasoning:
plan_type: The type of plan being created.
Returns:
A tuple containing the plan and whether the agent is ready.
A tuple containing the plan summary, list of steps, and whether the agent is ready.
"""
self.logger.debug(f"Using function calling for {plan_type} planning")
@@ -308,9 +354,13 @@ class AgentReasoning:
system_prompt = self._get_system_prompt()
# Prepare a simple callable that just returns the tool arguments as JSON
def _create_reasoning_plan(plan: str, ready: bool = True) -> str:
def _create_reasoning_plan(
plan: str,
steps: list[dict[str, Any]] | None = None,
ready: bool = True,
) -> str:
"""Return the planning result in JSON string form."""
return json.dumps({"plan": plan, "ready": ready})
return json.dumps({"plan": plan, "steps": steps or [], "ready": ready})
response = self.llm.call(
[
@@ -326,13 +376,30 @@ class AgentReasoning:
try:
result = json.loads(response)
if "plan" in result and "ready" in result:
return result["plan"], result["ready"]
# Parse steps from the response
steps: list[PlanStep] = []
raw_steps = result.get("steps", [])
for step_data in raw_steps:
try:
step = PlanStep(
step_number=step_data.get("step_number", 0),
description=step_data.get("description", ""),
tool_to_use=step_data.get("tool_to_use"),
depends_on=step_data.get("depends_on", []),
)
steps.append(step)
except Exception as step_error:
self.logger.warning(
f"Failed to parse step: {step_data}, error: {step_error}"
)
return result["plan"], steps, result["ready"]
except (json.JSONDecodeError, KeyError):
pass
response_str = str(response)
return (
response_str,
[],
"READY: I am ready to execute the task." in response_str,
)
@@ -356,12 +423,14 @@ class AgentReasoning:
fallback_str = str(fallback_response)
return (
fallback_str,
[],
"READY: I am ready to execute the task." in fallback_str,
)
except Exception as inner_e:
self.logger.error(f"Error during fallback text parsing: {inner_e!s}")
return (
"Failed to generate a plan due to an error.",
[],
True,
) # Default to ready to avoid getting stuck

1621
lib/crewai/tests/cassettes/utilities/TestAnthropicStructuredPlanning.test_anthropic_research_workflow_generates_steps.yaml Normal file
View File

File diff suppressed because it is too large Load Diff

548
lib/crewai/tests/cassettes/utilities/TestAzureStructuredPlanning.test_azure_research_workflow_generates_steps.yaml Normal file
View File

@@ -0,0 +1,548 @@
interactions:
- request:
body: '{"messages": [{"role": "system", "content": "You are a strategic planning
assistant. Create minimal, effective execution plans. Prefer fewer steps over
more."}, {"role": "user", "content": "Create a focused execution plan for the
following task:\n\n## Task\nResearch the current state of the AI agent market:\n1.
Search for recent information about AI agents and their market trends\n2. Read
detailed content from a relevant industry source\n3. Generate a brief report
summarizing the key findings\n\nUse the available tools for each step.\n\n##
Expected Output\nComplete the task successfully\n\n## Available Tools\nweb_search,
read_website, generate_report\n\n## Instructions\nCreate ONLY the essential
steps needed to complete this task. Use the MINIMUM number of steps required
- do NOT pad your plan with unnecessary steps. Most tasks need only 2-5 steps.\n\nFor
each step:\n- State the specific action to take\n- Specify which tool to use
(if any)\n- Note dependencies on previous steps if this step requires their
output\n- If a step involves multiple items (e.g., research 3 competitors),
note this explicitly\n\nDo NOT include:\n- Setup or preparation steps that are
obvious\n- Verification steps unless critical\n- Documentation or cleanup steps
unless explicitly required\n- Generic steps like \"review results\" or \"finalize
output\"\n\nAfter your plan, state:\n- \"READY: I am ready to execute the task.\"
if the plan is complete\n- \"NOT READY: I need to refine my plan because [reason].\"
if you need more thinking"}], "stream": false, "stop": ["\nObservation:"], "tool_choice":
"auto", "tools": [{"function": {"name": "create_reasoning_plan", "description":
"Create or refine a reasoning plan for a task with structured steps", "parameters":
{"type": "object", "properties": {"plan": {"type": "string", "description":
"A brief summary of the overall plan."}, "steps": {"type": "array", "description":
"List of discrete steps to execute the plan", "items": {"type": "object", "properties":
{"step_number": {"type": "integer", "description": "Step number (1-based)"},
"description": {"type": "string", "description": "What to do in this step"},
"tool_to_use": {"type": ["string", "null"], "description": "Tool to use for
this step, or null if no tool needed"}, "depends_on": {"type": "array", "items":
{"type": "integer"}, "description": "Step numbers this step depends on (empty
array if none)"}}, "required": ["step_number", "description", "tool_to_use",
"depends_on"], "additionalProperties": false}}, "ready": {"type": "boolean",
"description": "Whether the agent is ready to execute the task."}}, "required":
["plan", "steps", "ready"], "additionalProperties": false}}, "type": "function"}]}'
headers:
Accept:
- application/json
Connection:
- keep-alive
Content-Length:
- '2711'
Content-Type:
- application/json
User-Agent:
- X-USER-AGENT-XXX
accept-encoding:
- ACCEPT-ENCODING-XXX
api-key:
- X-API-KEY-XXX
authorization:
- AUTHORIZATION-XXX
x-ms-client-request-id:
- X-MS-CLIENT-REQUEST-ID-XXX
method: POST
uri: https://fake-azure-endpoint.openai.azure.com/openai/deployments/gpt-4o/chat/completions?api-version=2024-12-01-preview
response:
body:
string: '{"choices":[{"content_filter_results":{},"finish_reason":"tool_calls","index":0,"logprobs":null,"message":{"annotations":[],"content":null,"refusal":null,"role":"assistant","tool_calls":[{"function":{"arguments":"{\"plan\":\"Research
the current state of the AI agent market and summarize the key findings.\",\"steps\":[{\"step_number\":1,\"description\":\"Search
for recent information about AI agents and their market trends using web_search.\",\"tool_to_use\":\"web_search\",\"depends_on\":[]},{\"step_number\":2,\"description\":\"Read
detailed content from a relevant industry source using read_website, gathering
insights on trends and competitive analysis.\",\"tool_to_use\":\"read_website\",\"depends_on\":[1]},{\"step_number\":3,\"description\":\"Using
the knowledge from steps 1 and 2, generate a brief report summarizing the
AI agent market findings.\",\"tool_to_use\":\"generate_report\",\"depends_on\":[1,2]}],\"ready\":true}","name":"create_reasoning_plan"},"id":"call_TPmou69xLfxPqApRnPwI6zYV","type":"function"}]}}],"created":1770145131,"id":"chatcmpl-D5Ftr1QP6lTPXIemws2EtuKaWeSxt","model":"gpt-4o-2024-11-20","object":"chat.completion","prompt_filter_results":[{"prompt_index":0,"content_filter_results":{"hate":{"filtered":false,"severity":"safe"},"jailbreak":{"detected":false,"filtered":false},"self_harm":{"filtered":false,"severity":"safe"},"sexual":{"filtered":false,"severity":"safe"},"violence":{"filtered":false,"severity":"safe"}}}],"system_fingerprint":"fp_b54fe76834","usage":{"completion_tokens":157,"completion_tokens_details":{"accepted_prediction_tokens":0,"audio_tokens":0,"reasoning_tokens":0,"rejected_prediction_tokens":0},"prompt_tokens":480,"prompt_tokens_details":{"audio_tokens":0,"cached_tokens":0},"total_tokens":637}}
'
headers:
Content-Length:
- '1762'
Content-Type:
- application/json
Date:
- Tue, 03 Feb 2026 18:58:54 GMT
Strict-Transport-Security:
- STS-XXX
apim-request-id:
- APIM-REQUEST-ID-XXX
azureml-model-session:
- AZUREML-MODEL-SESSION-XXX
x-accel-buffering:
- 'no'
x-content-type-options:
- X-CONTENT-TYPE-XXX
x-ms-client-request-id:
- X-MS-CLIENT-REQUEST-ID-XXX
x-ms-deployment-name:
- gpt-4o
x-ms-rai-invoked:
- 'true'
x-ms-region:
- X-MS-REGION-XXX
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-request-id:
- X-REQUEST-ID-XXX
status:
code: 200
message: OK
- request:
body: '{"messages": [{"role": "system", "content": "You are Research Analyst.
An experienced analyst skilled at gathering information and synthesizing findings
into actionable insights.\nYour personal goal is: Conduct thorough research
and produce insightful reports"}, {"role": "user", "content": "\nCurrent Task:
Research the current state of the AI agent market:\n1. Search for recent information
about AI agents and their market trends\n2. Read detailed content from a relevant
industry source\n3. Generate a brief report summarizing the key findings\n\nUse
the available tools for each step."}], "stream": false, "stop": ["\nObservation:"],
"tool_choice": "auto", "tools": [{"function": {"name": "web_search", "description":
"Search the web for information on a given topic.\n\nArgs:\n query: The search
query to look up.\n\nReturns:\n Search results as a string.", "parameters":
{"properties": {"query": {"title": "Query", "type": "string"}}, "required":
["query"], "type": "object", "additionalProperties": false}}, "type": "function"},
{"function": {"name": "read_website", "description": "Read and extract content
from a website URL.\n\nArgs:\n url: The URL of the website to read.\n\nReturns:\n The
extracted content from the website.", "parameters": {"properties": {"url": {"title":
"Url", "type": "string"}}, "required": ["url"], "type": "object", "additionalProperties":
false}}, "type": "function"}, {"function": {"name": "generate_report", "description":
"Generate a structured report based on research findings.\n\nArgs:\n title:
The title of the report.\n findings: The research findings to include.\n\nReturns:\n A
formatted report string.", "parameters": {"properties": {"title": {"title":
"Title", "type": "string"}, "findings": {"title": "Findings", "type": "string"}},
"required": ["title", "findings"], "type": "object", "additionalProperties":
false}}, "type": "function"}]}'
headers:
Accept:
- application/json
Connection:
- keep-alive
Content-Length:
- '1912'
Content-Type:
- application/json
User-Agent:
- X-USER-AGENT-XXX
accept-encoding:
- ACCEPT-ENCODING-XXX
api-key:
- X-API-KEY-XXX
authorization:
- AUTHORIZATION-XXX
x-ms-client-request-id:
- X-MS-CLIENT-REQUEST-ID-XXX
method: POST
uri: https://fake-azure-endpoint.openai.azure.com/openai/deployments/gpt-4o/chat/completions?api-version=2024-12-01-preview
response:
body:
string: '{"choices":[{"content_filter_results":{},"finish_reason":"tool_calls","index":0,"logprobs":null,"message":{"annotations":[],"content":null,"refusal":null,"role":"assistant","tool_calls":[{"function":{"arguments":"{\"query\":\"current
state of AI agent market 2023\"}","name":"web_search"},"id":"call_6RDgkQSr8S7luEHqqOaI734w","type":"function"}]}}],"created":1770145136,"id":"chatcmpl-D5FtwVvV3KE10L2JIOd7n8Ph1Iu3Q","model":"gpt-4o-2024-11-20","object":"chat.completion","prompt_filter_results":[{"prompt_index":0,"content_filter_results":{"hate":{"filtered":false,"severity":"safe"},"jailbreak":{"detected":false,"filtered":false},"self_harm":{"filtered":false,"severity":"safe"},"sexual":{"filtered":false,"severity":"safe"},"violence":{"filtered":false,"severity":"safe"}}}],"system_fingerprint":"fp_b54fe76834","usage":{"completion_tokens":23,"completion_tokens_details":{"accepted_prediction_tokens":0,"audio_tokens":0,"reasoning_tokens":0,"rejected_prediction_tokens":0},"prompt_tokens":267,"prompt_tokens_details":{"audio_tokens":0,"cached_tokens":0},"total_tokens":290}}
'
headers:
Content-Length:
- '1079'
Content-Type:
- application/json
Date:
- Tue, 03 Feb 2026 18:58:55 GMT
Strict-Transport-Security:
- STS-XXX
apim-request-id:
- APIM-REQUEST-ID-XXX
azureml-model-session:
- AZUREML-MODEL-SESSION-XXX
x-accel-buffering:
- 'no'
x-content-type-options:
- X-CONTENT-TYPE-XXX
x-ms-client-request-id:
- X-MS-CLIENT-REQUEST-ID-XXX
x-ms-deployment-name:
- gpt-4o
x-ms-rai-invoked:
- 'true'
x-ms-region:
- X-MS-REGION-XXX
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-request-id:
- X-REQUEST-ID-XXX
status:
code: 200
message: OK
- request:
body: '{"messages": [{"role": "system", "content": "You are Research Analyst.
An experienced analyst skilled at gathering information and synthesizing findings
into actionable insights.\nYour personal goal is: Conduct thorough research
and produce insightful reports"}, {"role": "user", "content": "\nCurrent Task:
Research the current state of the AI agent market:\n1. Search for recent information
about AI agents and their market trends\n2. Read detailed content from a relevant
industry source\n3. Generate a brief report summarizing the key findings\n\nUse
the available tools for each step."}, {"role": "assistant", "content": "", "tool_calls":
[{"id": "call_6RDgkQSr8S7luEHqqOaI734w", "type": "function", "function": {"name":
"web_search", "arguments": "{\"query\":\"current state of AI agent market 2023\"}"}}]},
{"role": "tool", "tool_call_id": "call_6RDgkQSr8S7luEHqqOaI734w", "content":
"Search results for ''current state of AI agent market 2023'': Found 3 relevant
articles about the topic including market analysis, competitor data, and industry
trends."}], "stream": false, "stop": ["\nObservation:"], "tool_choice": "auto",
"tools": [{"function": {"name": "web_search", "description": "Search the web
for information on a given topic.\n\nArgs:\n query: The search query to look
up.\n\nReturns:\n Search results as a string.", "parameters": {"properties":
{"query": {"title": "Query", "type": "string"}}, "required": ["query"], "type":
"object", "additionalProperties": false}}, "type": "function"}, {"function":
{"name": "read_website", "description": "Read and extract content from a website
URL.\n\nArgs:\n url: The URL of the website to read.\n\nReturns:\n The
extracted content from the website.", "parameters": {"properties": {"url": {"title":
"Url", "type": "string"}}, "required": ["url"], "type": "object", "additionalProperties":
false}}, "type": "function"}, {"function": {"name": "generate_report", "description":
"Generate a structured report based on research findings.\n\nArgs:\n title:
The title of the report.\n findings: The research findings to include.\n\nReturns:\n A
formatted report string.", "parameters": {"properties": {"title": {"title":
"Title", "type": "string"}, "findings": {"title": "Findings", "type": "string"}},
"required": ["title", "findings"], "type": "object", "additionalProperties":
false}}, "type": "function"}]}'
headers:
Accept:
- application/json
Connection:
- keep-alive
Content-Length:
- '2381'
Content-Type:
- application/json
User-Agent:
- X-USER-AGENT-XXX
accept-encoding:
- ACCEPT-ENCODING-XXX
api-key:
- X-API-KEY-XXX
authorization:
- AUTHORIZATION-XXX
x-ms-client-request-id:
- X-MS-CLIENT-REQUEST-ID-XXX
method: POST
uri: https://fake-azure-endpoint.openai.azure.com/openai/deployments/gpt-4o/chat/completions?api-version=2024-12-01-preview
response:
body:
string: '{"choices":[{"content_filter_results":{},"finish_reason":"tool_calls","index":0,"logprobs":null,"message":{"annotations":[],"content":null,"refusal":null,"role":"assistant","tool_calls":[{"function":{"arguments":"{\"url\":
\"https://example.com/article1\"}","name":"read_website"},"id":"call_ie6tNHSbW9TWIqoXD9CN3MNZ","type":"function"},{"function":{"arguments":"{\"url\":
\"https://example.com/article2\"}","name":"read_website"},"id":"call_qxn4V4mMMpOnYSAwVuwarFkB","type":"function"},{"function":{"arguments":"{\"url\":
\"https://example.com/article3\"}","name":"read_website"},"id":"call_7ElzUIHHJvuciFWj6eIF5RhF","type":"function"}]}}],"created":1770145137,"id":"chatcmpl-D5Ftxnr2VyEYZd6zSpTJavdxSoE18","model":"gpt-4o-2024-11-20","object":"chat.completion","prompt_filter_results":[{"prompt_index":0,"content_filter_results":{"hate":{"filtered":false,"severity":"safe"},"jailbreak":{"detected":false,"filtered":false},"self_harm":{"filtered":false,"severity":"safe"},"sexual":{"filtered":false,"severity":"safe"},"violence":{"filtered":false,"severity":"safe"}}}],"system_fingerprint":"fp_b54fe76834","usage":{"completion_tokens":77,"completion_tokens_details":{"accepted_prediction_tokens":0,"audio_tokens":0,"reasoning_tokens":0,"rejected_prediction_tokens":0},"prompt_tokens":330,"prompt_tokens_details":{"audio_tokens":0,"cached_tokens":0},"total_tokens":407}}
'
headers:
Content-Length:
- '1371'
Content-Type:
- application/json
Date:
- Tue, 03 Feb 2026 18:58:57 GMT
Strict-Transport-Security:
- STS-XXX
apim-request-id:
- APIM-REQUEST-ID-XXX
azureml-model-session:
- AZUREML-MODEL-SESSION-XXX
x-accel-buffering:
- 'no'
x-content-type-options:
- X-CONTENT-TYPE-XXX
x-ms-client-request-id:
- X-MS-CLIENT-REQUEST-ID-XXX
x-ms-deployment-name:
- gpt-4o
x-ms-rai-invoked:
- 'true'
x-ms-region:
- X-MS-REGION-XXX
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-request-id:
- X-REQUEST-ID-XXX
status:
code: 200
message: OK
- request:
body: '{"messages": [{"role": "system", "content": "You are Research Analyst.
An experienced analyst skilled at gathering information and synthesizing findings
into actionable insights.\nYour personal goal is: Conduct thorough research
and produce insightful reports"}, {"role": "user", "content": "\nCurrent Task:
Research the current state of the AI agent market:\n1. Search for recent information
about AI agents and their market trends\n2. Read detailed content from a relevant
industry source\n3. Generate a brief report summarizing the key findings\n\nUse
the available tools for each step."}, {"role": "assistant", "content": "", "tool_calls":
[{"id": "call_6RDgkQSr8S7luEHqqOaI734w", "type": "function", "function": {"name":
"web_search", "arguments": "{\"query\":\"current state of AI agent market 2023\"}"}}]},
{"role": "tool", "tool_call_id": "call_6RDgkQSr8S7luEHqqOaI734w", "content":
"Search results for ''current state of AI agent market 2023'': Found 3 relevant
articles about the topic including market analysis, competitor data, and industry
trends."}, {"role": "assistant", "content": "", "tool_calls": [{"id": "call_ie6tNHSbW9TWIqoXD9CN3MNZ",
"type": "function", "function": {"name": "read_website", "arguments": "{\"url\":
\"https://example.com/article1\"}"}}, {"id": "call_qxn4V4mMMpOnYSAwVuwarFkB",
"type": "function", "function": {"name": "read_website", "arguments": "{\"url\":
\"https://example.com/article2\"}"}}, {"id": "call_7ElzUIHHJvuciFWj6eIF5RhF",
"type": "function", "function": {"name": "read_website", "arguments": "{\"url\":
\"https://example.com/article3\"}"}}]}, {"role": "tool", "tool_call_id": "call_ie6tNHSbW9TWIqoXD9CN3MNZ",
"content": "Content from https://example.com/article1: This article discusses
key insights about the topic including market size ($50B), growth rate (15%
YoY), and major players in the industry."}, {"role": "tool", "tool_call_id":
"call_qxn4V4mMMpOnYSAwVuwarFkB", "content": "Content from https://example.com/article2:
This article discusses key insights about the topic including market size ($50B),
growth rate (15% YoY), and major players in the industry."}, {"role": "tool",
"tool_call_id": "call_7ElzUIHHJvuciFWj6eIF5RhF", "content": "Content from https://example.com/article3:
This article discusses key insights about the topic including market size ($50B),
growth rate (15% YoY), and major players in the industry."}], "stream": false,
"stop": ["\nObservation:"], "tool_choice": "auto", "tools": [{"function": {"name":
"web_search", "description": "Search the web for information on a given topic.\n\nArgs:\n query:
The search query to look up.\n\nReturns:\n Search results as a string.",
"parameters": {"properties": {"query": {"title": "Query", "type": "string"}},
"required": ["query"], "type": "object", "additionalProperties": false}}, "type":
"function"}, {"function": {"name": "read_website", "description": "Read and
extract content from a website URL.\n\nArgs:\n url: The URL of the website
to read.\n\nReturns:\n The extracted content from the website.", "parameters":
{"properties": {"url": {"title": "Url", "type": "string"}}, "required": ["url"],
"type": "object", "additionalProperties": false}}, "type": "function"}, {"function":
{"name": "generate_report", "description": "Generate a structured report based
on research findings.\n\nArgs:\n title: The title of the report.\n findings:
The research findings to include.\n\nReturns:\n A formatted report string.",
"parameters": {"properties": {"title": {"title": "Title", "type": "string"},
"findings": {"title": "Findings", "type": "string"}}, "required": ["title",
"findings"], "type": "object", "additionalProperties": false}}, "type": "function"}]}'
headers:
Accept:
- application/json
Connection:
- keep-alive
Content-Length:
- '3704'
Content-Type:
- application/json
User-Agent:
- X-USER-AGENT-XXX
accept-encoding:
- ACCEPT-ENCODING-XXX
api-key:
- X-API-KEY-XXX
authorization:
- AUTHORIZATION-XXX
x-ms-client-request-id:
- X-MS-CLIENT-REQUEST-ID-XXX
method: POST
uri: https://fake-azure-endpoint.openai.azure.com/openai/deployments/gpt-4o/chat/completions?api-version=2024-12-01-preview
response:
body:
string: '{"choices":[{"content_filter_results":{},"finish_reason":"tool_calls","index":0,"logprobs":null,"message":{"annotations":[],"content":null,"refusal":null,"role":"assistant","tool_calls":[{"function":{"arguments":"{\"title\":\"Current
State of the AI Agent Market\",\"findings\":\"The AI agent market in 2023
is valued at $50 billion, with a growth rate of 15% YoY. Major players in
the market have been identified as contributing to the expansion of industry
capabilities. Trends point to increasing adoption across industries such as
healthcare and finance, where automation and intelligence are becoming central
to operations. Emerging competitive forces are influencing pricing and technological
advancements in AI agents. Existing and new entrants focus on innovation to
differentiate their offerings and capture market share.\"}","name":"generate_report"},"id":"call_7eE0bJbpvO6YYQNs87iTifQ3","type":"function"}]}}],"created":1770145138,"id":"chatcmpl-D5Ftys4PE1B1dkTuv6EPOQyqk0xuv","model":"gpt-4o-2024-11-20","object":"chat.completion","prompt_filter_results":[{"prompt_index":0,"content_filter_results":{"hate":{"filtered":false,"severity":"safe"},"jailbreak":{"detected":false,"filtered":false},"self_harm":{"filtered":false,"severity":"safe"},"sexual":{"filtered":false,"severity":"safe"},"violence":{"filtered":false,"severity":"safe"}}}],"system_fingerprint":"fp_b54fe76834","usage":{"completion_tokens":120,"completion_tokens_details":{"accepted_prediction_tokens":0,"audio_tokens":0,"reasoning_tokens":0,"rejected_prediction_tokens":0},"prompt_tokens":537,"prompt_tokens_details":{"audio_tokens":0,"cached_tokens":0},"total_tokens":657}}
'
headers:
Content-Length:
- '1652'
Content-Type:
- application/json
Date:
- Tue, 03 Feb 2026 18:58:59 GMT
Strict-Transport-Security:
- STS-XXX
apim-request-id:
- APIM-REQUEST-ID-XXX
azureml-model-session:
- AZUREML-MODEL-SESSION-XXX
x-accel-buffering:
- 'no'
x-content-type-options:
- X-CONTENT-TYPE-XXX
x-ms-client-request-id:
- X-MS-CLIENT-REQUEST-ID-XXX
x-ms-deployment-name:
- gpt-4o
x-ms-rai-invoked:
- 'true'
x-ms-region:
- X-MS-REGION-XXX
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-request-id:
- X-REQUEST-ID-XXX
status:
code: 200
message: OK
- request:
body: '{"messages": [{"role": "system", "content": "You are Research Analyst.
An experienced analyst skilled at gathering information and synthesizing findings
into actionable insights.\nYour personal goal is: Conduct thorough research
and produce insightful reports"}, {"role": "user", "content": "\nCurrent Task:
Research the current state of the AI agent market:\n1. Search for recent information
about AI agents and their market trends\n2. Read detailed content from a relevant
industry source\n3. Generate a brief report summarizing the key findings\n\nUse
the available tools for each step."}, {"role": "assistant", "content": "", "tool_calls":
[{"id": "call_6RDgkQSr8S7luEHqqOaI734w", "type": "function", "function": {"name":
"web_search", "arguments": "{\"query\":\"current state of AI agent market 2023\"}"}}]},
{"role": "tool", "tool_call_id": "call_6RDgkQSr8S7luEHqqOaI734w", "content":
"Search results for ''current state of AI agent market 2023'': Found 3 relevant
articles about the topic including market analysis, competitor data, and industry
trends."}, {"role": "assistant", "content": "", "tool_calls": [{"id": "call_ie6tNHSbW9TWIqoXD9CN3MNZ",
"type": "function", "function": {"name": "read_website", "arguments": "{\"url\":
\"https://example.com/article1\"}"}}, {"id": "call_qxn4V4mMMpOnYSAwVuwarFkB",
"type": "function", "function": {"name": "read_website", "arguments": "{\"url\":
\"https://example.com/article2\"}"}}, {"id": "call_7ElzUIHHJvuciFWj6eIF5RhF",
"type": "function", "function": {"name": "read_website", "arguments": "{\"url\":
\"https://example.com/article3\"}"}}]}, {"role": "tool", "tool_call_id": "call_ie6tNHSbW9TWIqoXD9CN3MNZ",
"content": "Content from https://example.com/article1: This article discusses
key insights about the topic including market size ($50B), growth rate (15%
YoY), and major players in the industry."}, {"role": "tool", "tool_call_id":
"call_qxn4V4mMMpOnYSAwVuwarFkB", "content": "Content from https://example.com/article2:
This article discusses key insights about the topic including market size ($50B),
growth rate (15% YoY), and major players in the industry."}, {"role": "tool",
"tool_call_id": "call_7ElzUIHHJvuciFWj6eIF5RhF", "content": "Content from https://example.com/article3:
This article discusses key insights about the topic including market size ($50B),
growth rate (15% YoY), and major players in the industry."}, {"role": "assistant",
"content": "", "tool_calls": [{"id": "call_7eE0bJbpvO6YYQNs87iTifQ3", "type":
"function", "function": {"name": "generate_report", "arguments": "{\"title\":\"Current
State of the AI Agent Market\",\"findings\":\"The AI agent market in 2023 is
valued at $50 billion, with a growth rate of 15% YoY. Major players in the market
have been identified as contributing to the expansion of industry capabilities.
Trends point to increasing adoption across industries such as healthcare and
finance, where automation and intelligence are becoming central to operations.
Emerging competitive forces are influencing pricing and technological advancements
in AI agents. Existing and new entrants focus on innovation to differentiate
their offerings and capture market share.\"}"}}]}, {"role": "tool", "tool_call_id":
"call_7eE0bJbpvO6YYQNs87iTifQ3", "content": "# Current State of the AI Agent
Market\n\n## Executive Summary\nThe AI agent market in 2023 is valued at $50
billion, with a growth rate of 15% YoY. Major players in the market have been
identified as contributing to the expansion of industry capabilities. Trends
point to increasing adoption across industries such as healthcare and finance,
where automation and intelligence are becoming central to operations. Emerging
competitive forces are influencing pricing and technological advancements in
AI agents. Existing and new entrants focus on innovation to differentiate their
offerings and capture market share.\n\n## Conclusion\nBased on the analysis,
the market shows strong growth potential."}], "stream": false, "stop": ["\nObservation:"],
"tool_choice": "auto", "tools": [{"function": {"name": "web_search", "description":
"Search the web for information on a given topic.\n\nArgs:\n query: The search
query to look up.\n\nReturns:\n Search results as a string.", "parameters":
{"properties": {"query": {"title": "Query", "type": "string"}}, "required":
["query"], "type": "object", "additionalProperties": false}}, "type": "function"},
{"function": {"name": "read_website", "description": "Read and extract content
from a website URL.\n\nArgs:\n url: The URL of the website to read.\n\nReturns:\n The
extracted content from the website.", "parameters": {"properties": {"url": {"title":
"Url", "type": "string"}}, "required": ["url"], "type": "object", "additionalProperties":
false}}, "type": "function"}, {"function": {"name": "generate_report", "description":
"Generate a structured report based on research findings.\n\nArgs:\n title:
The title of the report.\n findings: The research findings to include.\n\nReturns:\n A
formatted report string.", "parameters": {"properties": {"title": {"title":
"Title", "type": "string"}, "findings": {"title": "Findings", "type": "string"}},
"required": ["title", "findings"], "type": "object", "additionalProperties":
false}}, "type": "function"}]}'
headers:
Accept:
- application/json
Connection:
- keep-alive
Content-Length:
- '5276'
Content-Type:
- application/json
User-Agent:
- X-USER-AGENT-XXX
accept-encoding:
- ACCEPT-ENCODING-XXX
api-key:
- X-API-KEY-XXX
authorization:
- AUTHORIZATION-XXX
x-ms-client-request-id:
- X-MS-CLIENT-REQUEST-ID-XXX
method: POST
uri: https://fake-azure-endpoint.openai.azure.com/openai/deployments/gpt-4o/chat/completions?api-version=2024-12-01-preview
response:
body:
string: '{"choices":[{"content_filter_results":{"hate":{"filtered":false,"severity":"safe"},"protected_material_code":{"detected":false,"filtered":false},"protected_material_text":{"detected":false,"filtered":false},"self_harm":{"filtered":false,"severity":"safe"},"sexual":{"filtered":false,"severity":"safe"},"violence":{"filtered":false,"severity":"safe"}},"finish_reason":"stop","index":0,"logprobs":null,"message":{"annotations":[],"content":"The
report detailing the current state of the AI agent market has been generated
successfully. It highlights the market''s $50 billion valuation in 2023, with
a consistent annual growth rate of 15%. Key findings identify the role of
major players, impactful trends like sector adoption (healthcare and finance),
and the competitive dynamic driving innovation and technological advancements.","refusal":null,"role":"assistant"}}],"created":1770145141,"id":"chatcmpl-D5Fu18JFkDPGsKf10eiS2e2uI04MU","model":"gpt-4o-2024-11-20","object":"chat.completion","prompt_filter_results":[{"prompt_index":0,"content_filter_results":{"hate":{"filtered":false,"severity":"safe"},"jailbreak":{"detected":false,"filtered":false},"self_harm":{"filtered":false,"severity":"safe"},"sexual":{"filtered":false,"severity":"safe"},"violence":{"filtered":false,"severity":"safe"}}}],"system_fingerprint":"fp_b54fe76834","usage":{"completion_tokens":72,"completion_tokens_details":{"accepted_prediction_tokens":0,"audio_tokens":0,"reasoning_tokens":0,"rejected_prediction_tokens":0},"prompt_tokens":787,"prompt_tokens_details":{"audio_tokens":0,"cached_tokens":0},"total_tokens":859}}
'
headers:
Content-Length:
- '1597'
Content-Type:
- application/json
Date:
- Tue, 03 Feb 2026 18:59:01 GMT
Strict-Transport-Security:
- STS-XXX
apim-request-id:
- APIM-REQUEST-ID-XXX
azureml-model-session:
- AZUREML-MODEL-SESSION-XXX
x-accel-buffering:
- 'no'
x-content-type-options:
- X-CONTENT-TYPE-XXX
x-ms-client-request-id:
- X-MS-CLIENT-REQUEST-ID-XXX
x-ms-deployment-name:
- gpt-4o
x-ms-rai-invoked:
- 'true'
x-ms-region:
- X-MS-REGION-XXX
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-request-id:
- X-REQUEST-ID-XXX
status:
code: 200
message: OK
version: 1

613
lib/crewai/tests/cassettes/utilities/TestGeminiStructuredPlanning.test_gemini_research_workflow_generates_steps.yaml Normal file
View File

@@ -0,0 +1,613 @@
interactions:
- request:
body: '{"contents": [{"parts": [{"text": "Create a focused execution plan for
the following task:\n\n## Task\nResearch the current state of the AI agent market:\n1.
Search for recent information about AI agents and their market trends\n2. Read
detailed content from a relevant industry source\n3. Generate a brief report
summarizing the key findings\n\nUse the available tools for each step.\n\n##
Expected Output\nComplete the task successfully\n\n## Available Tools\nweb_search,
read_website, generate_report\n\n## Instructions\nCreate ONLY the essential
steps needed to complete this task. Use the MINIMUM number of steps required
- do NOT pad your plan with unnecessary steps. Most tasks need only 2-5 steps.\n\nFor
each step:\n- State the specific action to take\n- Specify which tool to use
(if any)\n- Note dependencies on previous steps if this step requires their
output\n- If a step involves multiple items (e.g., research 3 competitors),
note this explicitly\n\nDo NOT include:\n- Setup or preparation steps that are
obvious\n- Verification steps unless critical\n- Documentation or cleanup steps
unless explicitly required\n- Generic steps like \"review results\" or \"finalize
output\"\n\nAfter your plan, state:\n- \"READY: I am ready to execute the task.\"
if the plan is complete\n- \"NOT READY: I need to refine my plan because [reason].\"
if you need more thinking"}], "role": "user"}], "systemInstruction": {"parts":
[{"text": "You are a strategic planning assistant. Create minimal, effective
execution plans. Prefer fewer steps over more."}], "role": "user"}, "tools":
[{"functionDeclarations": [{"description": "Create or refine a reasoning plan
for a task with structured steps", "name": "create_reasoning_plan", "parameters_json_schema":
{"type": "object", "properties": {"plan": {"type": "string", "description":
"A brief summary of the overall plan."}, "steps": {"type": "array", "description":
"List of discrete steps to execute the plan", "items": {"type": "object", "properties":
{"step_number": {"type": "integer", "description": "Step number (1-based)"},
"description": {"type": "string", "description": "What to do in this step"},
"tool_to_use": {"type": ["string", "null"], "description": "Tool to use for
this step, or null if no tool needed"}, "depends_on": {"type": "array", "items":
{"type": "integer"}, "description": "Step numbers this step depends on (empty
array if none)"}}, "required": ["step_number", "description", "tool_to_use",
"depends_on"], "additionalProperties": false}}, "ready": {"type": "boolean",
"description": "Whether the agent is ready to execute the task."}}, "required":
["plan", "steps", "ready"], "additionalProperties": false}}]}], "generationConfig":
{"stopSequences": ["\nObservation:"]}}'
headers:
User-Agent:
- X-USER-AGENT-XXX
accept:
- '*/*'
accept-encoding:
- ACCEPT-ENCODING-XXX
connection:
- keep-alive
content-length:
- '2747'
content-type:
- application/json
host:
- generativelanguage.googleapis.com
x-goog-api-client:
- google-genai-sdk/1.49.0 gl-python/3.13.3
x-goog-api-key:
- X-GOOG-API-KEY-XXX
method: POST
uri: https://generativelanguage.googleapis.com/v1beta/models/gemini-2.5-flash:generateContent
response:
body:
string: "{\n \"candidates\": [\n {\n \"content\": {\n \"parts\":
[\n {\n \"functionCall\": {\n \"name\": \"create_reasoning_plan\",\n
\ \"args\": {\n \"steps\": [\n {\n
\ \"step_number\": 1,\n \"tool_to_use\":
\"web_search\",\n \"depends_on\": [],\n \"description\":
\"Search for recent information on AI agent market trends.\"\n },\n
\ {\n \"description\": \"Read detailed
content from a relevant industry source found in the search results.\",\n
\ \"depends_on\": [\n 1\n ],\n
\ \"step_number\": 2,\n \"tool_to_use\":
\"read_website\"\n },\n {\n \"depends_on\":
[\n 2\n ],\n \"step_number\":
3,\n \"tool_to_use\": \"generate_report\",\n \"description\":
\"Generate a brief report summarizing the key findings from the researched
content.\"\n }\n ],\n \"plan\":
\"Research the current state of the AI agent market and generate a summary
report.\",\n \"ready\": true\n }\n },\n
\ \"thoughtSignature\": \"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\"\n
\ }\n ],\n \"role\": \"model\"\n },\n \"finishReason\":
\"STOP\",\n \"index\": 0,\n \"finishMessage\": \"Model generated
function call(s).\"\n }\n ],\n \"usageMetadata\": {\n \"promptTokenCount\":
529,\n \"candidatesTokenCount\": 169,\n \"totalTokenCount\": 955,\n
\ \"promptTokensDetails\": [\n {\n \"modality\": \"TEXT\",\n
\ \"tokenCount\": 529\n }\n ],\n \"thoughtsTokenCount\":
257\n },\n \"modelVersion\": \"gemini-2.5-flash\",\n \"responseId\": \"h0WCacqWA6WM_PUPl-niyQ0\"\n}\n"
headers:
Alt-Svc:
- h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
Content-Type:
- application/json; charset=UTF-8
Date:
- Tue, 03 Feb 2026 18:59:19 GMT
Server:
- scaffolding on HTTPServer2
Server-Timing:
- gfet4t7; dur=2345
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: Research the current
state of the AI agent market:\n1. Search for recent information about AI agents
and their market trends\n2. Read detailed content from a relevant industry source\n3.
Generate a brief report summarizing the key findings\n\nUse the available tools
for each step."}], "role": "user"}], "systemInstruction": {"parts": [{"text":
"You are Research Analyst. An experienced analyst skilled at gathering information
and synthesizing findings into actionable insights.\nYour personal goal is:
Conduct thorough research and produce insightful reports"}], "role": "user"},
"tools": [{"functionDeclarations": [{"description": "Search the web for information
on a given topic.\n\nArgs:\n query: The search query to look up.\n\nReturns:\n Search
results as a string.", "name": "web_search", "parameters_json_schema": {"properties":
{"query": {"title": "Query", "type": "string"}}, "required": ["query"], "type":
"object", "additionalProperties": false}}, {"description": "Read and extract
content from a website URL.\n\nArgs:\n url: The URL of the website to read.\n\nReturns:\n The
extracted content from the website.", "name": "read_website", "parameters_json_schema":
{"properties": {"url": {"title": "Url", "type": "string"}}, "required": ["url"],
"type": "object", "additionalProperties": false}}, {"description": "Generate
a structured report based on research findings.\n\nArgs:\n title: The title
of the report.\n findings: The research findings to include.\n\nReturns:\n A
formatted report string.", "name": "generate_report", "parameters_json_schema":
{"properties": {"title": {"title": "Title", "type": "string"}, "findings": {"title":
"Findings", "type": "string"}}, "required": ["title", "findings"], "type": "object",
"additionalProperties": false}}]}], "generationConfig": {"stopSequences": ["\nObservation:"]}}'
headers:
User-Agent:
- X-USER-AGENT-XXX
accept:
- '*/*'
accept-encoding:
- ACCEPT-ENCODING-XXX
connection:
- keep-alive
content-length:
- '1904'
content-type:
- application/json
host:
- generativelanguage.googleapis.com
x-goog-api-client:
- google-genai-sdk/1.49.0 gl-python/3.13.3
x-goog-api-key:
- X-GOOG-API-KEY-XXX
method: POST
uri: https://generativelanguage.googleapis.com/v1beta/models/gemini-2.5-flash:generateContent
response:
body:
string: "{\n \"candidates\": [\n {\n \"content\": {\n \"parts\":
[\n {\n \"functionCall\": {\n \"name\": \"web_search\",\n
\ \"args\": {\n \"query\": \"AI agent market trends
2023-2024\"\n }\n },\n \"thoughtSignature\":
\"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\"\n
\ }\n ],\n \"role\": \"model\"\n },\n \"finishReason\":
\"STOP\",\n \"index\": 0,\n \"finishMessage\": \"Model generated
function call(s).\"\n }\n ],\n \"usageMetadata\": {\n \"promptTokenCount\":
319,\n \"candidatesTokenCount\": 28,\n \"totalTokenCount\": 461,\n \"promptTokensDetails\":
[\n {\n \"modality\": \"TEXT\",\n \"tokenCount\": 319\n
\ }\n ],\n \"thoughtsTokenCount\": 114\n },\n \"modelVersion\":
\"gemini-2.5-flash\",\n \"responseId\": \"iEWCaYyJENDn_uMP4q3N8QE\"\n}\n"
headers:
Alt-Svc:
- h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
Content-Type:
- application/json; charset=UTF-8
Date:
- Tue, 03 Feb 2026 18:59:20 GMT
Server:
- scaffolding on HTTPServer2
Server-Timing:
- gfet4t7; dur=1193
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: Research the current
state of the AI agent market:\n1. Search for recent information about AI agents
and their market trends\n2. Read detailed content from a relevant industry source\n3.
Generate a brief report summarizing the key findings\n\nUse the available tools
for each step."}], "role": "user"}, {"parts": [{"functionCall": {"args": {"query":
"AI agent market trends 2023-2024"}, "name": "web_search"}, "thoughtSignature":
"CoYEAXLI2nzmyDix3_QA-tMOiUwpDVoA5-RJoRW7kw3okJaVYCa5Usx7eBn4xowP7oXNynS4NfawCYqboufBXjHinq13UTcYg0Y74qIrza4KuctliGmf8G7S4QoS0Y3gqCHQKsxTdShQOg8wirnr8Rdu1eyrrhWE0XKk0HPA0Ssj7zUVoJBqHPqwyvkFyXkMtpcmtq9qXmZYfMFuSKRQnYLVLllL_BpOIL3w7MuofpviO85bvYk9gX0vsDjYWS6EdVEfC9k2BWGjhHaILXT9A1iwNPdDAg33SOC-BlPrGox0ghCr5qEKnBMZhUszqaUCykczFCq-xMIA3xDGNbTjicWb53sL_PXBYLsNty1giW3nKFe8-8eRpUsHUx7oQ82m4AUxKqk99mZjaLp8bHk-rERjFZErcw_pe_3190K0WGHH5ecB4amJCzZtVrQJ1oAZhb7_P1VZ57xmt1z_c1pQgjuvnV-cWE9blh5o6mNNFbFuzJDIO2k8qrFeeDwlCF8OOrxo8F-z1evg4yjZ1-9TLCVFTmZ0S0PI54FS5afb0RdPol2_ISNw7H_dtnO4z6LhT2NmlYqYZr8qfVoUD21rmI08NFs-f_6JW5-7eSQbax76SW-6A2IqqPPyF66MCpqtEzC-hpzVsCBcIQyRQWsdm-RNAs50gmqF6W3CcTPryWkeS7w9ORqxdiU="}],
"role": "model"}, {"parts": [{"functionResponse": {"name": "web_search", "response":
{"result": "Search results for ''AI agent market trends 2023-2024'': Found 3
relevant articles about the topic including market analysis, competitor data,
and industry trends."}}}], "role": "user"}], "systemInstruction": {"parts":
[{"text": "You are Research Analyst. An experienced analyst skilled at gathering
information and synthesizing findings into actionable insights.\nYour personal
goal is: Conduct thorough research and produce insightful reports"}], "role":
"user"}, "tools": [{"functionDeclarations": [{"description": "Search the web
for information on a given topic.\n\nArgs:\n query: The search query to look
up.\n\nReturns:\n Search results as a string.", "name": "web_search", "parameters_json_schema":
{"properties": {"query": {"title": "Query", "type": "string"}}, "required":
["query"], "type": "object", "additionalProperties": false}}, {"description":
"Read and extract content from a website URL.\n\nArgs:\n url: The URL of
the website to read.\n\nReturns:\n The extracted content from the website.",
"name": "read_website", "parameters_json_schema": {"properties": {"url": {"title":
"Url", "type": "string"}}, "required": ["url"], "type": "object", "additionalProperties":
false}}, {"description": "Generate a structured report based on research findings.\n\nArgs:\n title:
The title of the report.\n findings: The research findings to include.\n\nReturns:\n A
formatted report string.", "name": "generate_report", "parameters_json_schema":
{"properties": {"title": {"title": "Title", "type": "string"}, "findings": {"title":
"Findings", "type": "string"}}, "required": ["title", "findings"], "type": "object",
"additionalProperties": false}}]}], "generationConfig": {"stopSequences": ["\nObservation:"]}}'
headers:
User-Agent:
- X-USER-AGENT-XXX
accept:
- '*/*'
accept-encoding:
- ACCEPT-ENCODING-XXX
connection:
- keep-alive
content-length:
- '3015'
content-type:
- application/json
host:
- generativelanguage.googleapis.com
x-goog-api-client:
- google-genai-sdk/1.49.0 gl-python/3.13.3
x-goog-api-key:
- X-GOOG-API-KEY-XXX
method: POST
uri: https://generativelanguage.googleapis.com/v1beta/models/gemini-2.5-flash:generateContent
response:
body:
string: "{\n \"candidates\": [\n {\n \"content\": {\n \"parts\":
[\n {\n \"functionCall\": {\n \"name\": \"web_search\",\n
\ \"args\": {\n \"query\": \"latest reports AI
agent market analysis\"\n }\n },\n \"thoughtSignature\":
\"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\"\n
\ }\n ],\n \"role\": \"model\"\n },\n \"finishReason\":
\"STOP\",\n \"index\": 0,\n \"finishMessage\": \"Model generated
function call(s).\"\n }\n ],\n \"usageMetadata\": {\n \"promptTokenCount\":
400,\n \"candidatesTokenCount\": 20,\n \"totalTokenCount\": 589,\n \"promptTokensDetails\":
[\n {\n \"modality\": \"TEXT\",\n \"tokenCount\": 400\n
\ }\n ],\n \"thoughtsTokenCount\": 169\n },\n \"modelVersion\":
\"gemini-2.5-flash\",\n \"responseId\": \"ikWCacqBG8ve_uMPj4KFyAY\"\n}\n"
headers:
Alt-Svc:
- h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
Content-Type:
- application/json; charset=UTF-8
Date:
- Tue, 03 Feb 2026 18:59:22 GMT
Server:
- scaffolding on HTTPServer2
Server-Timing:
- gfet4t7; dur=2125
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: Research the current
state of the AI agent market:\n1. Search for recent information about AI agents
and their market trends\n2. Read detailed content from a relevant industry source\n3.
Generate a brief report summarizing the key findings\n\nUse the available tools
for each step."}], "role": "user"}, {"parts": [{"functionCall": {"args": {"query":
"AI agent market trends 2023-2024"}, "name": "web_search"}, "thoughtSignature":
"CoYEAXLI2nzmyDix3_QA-tMOiUwpDVoA5-RJoRW7kw3okJaVYCa5Usx7eBn4xowP7oXNynS4NfawCYqboufBXjHinq13UTcYg0Y74qIrza4KuctliGmf8G7S4QoS0Y3gqCHQKsxTdShQOg8wirnr8Rdu1eyrrhWE0XKk0HPA0Ssj7zUVoJBqHPqwyvkFyXkMtpcmtq9qXmZYfMFuSKRQnYLVLllL_BpOIL3w7MuofpviO85bvYk9gX0vsDjYWS6EdVEfC9k2BWGjhHaILXT9A1iwNPdDAg33SOC-BlPrGox0ghCr5qEKnBMZhUszqaUCykczFCq-xMIA3xDGNbTjicWb53sL_PXBYLsNty1giW3nKFe8-8eRpUsHUx7oQ82m4AUxKqk99mZjaLp8bHk-rERjFZErcw_pe_3190K0WGHH5ecB4amJCzZtVrQJ1oAZhb7_P1VZ57xmt1z_c1pQgjuvnV-cWE9blh5o6mNNFbFuzJDIO2k8qrFeeDwlCF8OOrxo8F-z1evg4yjZ1-9TLCVFTmZ0S0PI54FS5afb0RdPol2_ISNw7H_dtnO4z6LhT2NmlYqYZr8qfVoUD21rmI08NFs-f_6JW5-7eSQbax76SW-6A2IqqPPyF66MCpqtEzC-hpzVsCBcIQyRQWsdm-RNAs50gmqF6W3CcTPryWkeS7w9ORqxdiU="}],
"role": "model"}, {"parts": [{"functionResponse": {"name": "web_search", "response":
{"result": "Search results for ''AI agent market trends 2023-2024'': Found 3
relevant articles about the topic including market analysis, competitor data,
and industry trends."}}}], "role": "user"}, {"parts": [{"functionCall": {"args":
{"query": "latest reports AI agent market analysis"}, "name": "web_search"},
"thoughtSignature": "CpwGAXLI2nybmVGffIN1k-T5M2HmQNlvybZRPoo_ysgNARa-9nrPdRoBZ9RC-Dee9KSk1o7O-IU9l0sWCTirQYcroEhXon-JIQUVTed_L0s__sBOR-hJnZWoaG5ucsfJQvovAQba2Wb7uViEkdySvHfRApF0atewbC-TCKZrxDAQ6Naby8nwUTauJPKlgsBsZVnlViRfIbF7pom1zvXD-d5htjMiuJr1nOuSH0EGQWC4TUiuJD23hgockzhmIpbU_bStn8PFIQNsySEzl6H5sZdlD4auwCMCD2Q-Ur05w1uLv7n8GoSZn5dkdXLR5R7dZ-kkX-xP4w841Ih2gc6rBKT5tSedN01AuJsK65NSfOXZBwakxs58WZXDQXnIQe4d2QThAX3nPdUmhvVI6sHX-ZdtQZIrhE7hRf9j_T_wvvrUao5VDv-mxXd9bcPEV2BzSXkvkAB1SbJ-5wN7Qb2j31lkiUu5uRnZOiVxL5iCS-8Z_jEl4NjpGithbcPoNpFIDOeiE_f8kf7tQJDX-YNquPbYZRJHvIfLalVQndVGNlZVN2jXT3Wwo8So3vmzIDFVjV-pj7tSRNK8hTITm6bfHS-XUZqJdm7eHCzhonyJ7_tl7LbsstPXoZU3ZN50tNpXYOK-NzgzU7iwd9SaHVXgzQRdujWgHuBmSiSd9qNHvdaNwgARVTnMj3VYpehgIuaYMzQmgM99TdC_zmzcqHa5VZSnHKHqMIVc9gjRvVwz4DUm6VLLnKnVYFClM6gofmUI6s9fThiR5EdfimaDTlRlzh6Df33jAbRA9rUTDH6uE-DjiopCvXuHjmQqK9Smyxt2vTao9H7AYIRN7yWmdVoaG0tUSL2XQ31wIW3cEyhz7ihQwFYKJnOkQ3_CiU6KV-4ldk9UY_vKWSgItVTTE6G8Di0iviiCAkmL59Uj7vnIp80-U9rDIK7WhxpAWlrDA6cGQT2LGAXQ2liXtLa31nXyfvCezhtSS8jSVm4SHaiU-INvYtpq2Q7nXPTFbjjZooyC5FePGqAH1T-sRYbR02jaa572_NuwFgBCObTfqO8G5A=="}],
"role": "model"}, {"parts": [{"functionResponse": {"name": "web_search", "response":
{"result": "Search results for ''latest reports AI agent market analysis'':
Found 3 relevant articles about the topic including market analysis, competitor
data, and industry trends."}}}], "role": "user"}], "systemInstruction": {"parts":
[{"text": "You are Research Analyst. An experienced analyst skilled at gathering
information and synthesizing findings into actionable insights.\nYour personal
goal is: Conduct thorough research and produce insightful reports"}], "role":
"user"}, "tools": [{"functionDeclarations": [{"description": "Search the web
for information on a given topic.\n\nArgs:\n query: The search query to look
up.\n\nReturns:\n Search results as a string.", "name": "web_search", "parameters_json_schema":
{"properties": {"query": {"title": "Query", "type": "string"}}, "required":
["query"], "type": "object", "additionalProperties": false}}, {"description":
"Read and extract content from a website URL.\n\nArgs:\n url: The URL of
the website to read.\n\nReturns:\n The extracted content from the website.",
"name": "read_website", "parameters_json_schema": {"properties": {"url": {"title":
"Url", "type": "string"}}, "required": ["url"], "type": "object", "additionalProperties":
false}}, {"description": "Generate a structured report based on research findings.\n\nArgs:\n title:
The title of the report.\n findings: The research findings to include.\n\nReturns:\n A
formatted report string.", "name": "generate_report", "parameters_json_schema":
{"properties": {"title": {"title": "Title", "type": "string"}, "findings": {"title":
"Findings", "type": "string"}}, "required": ["title", "findings"], "type": "object",
"additionalProperties": false}}]}], "generationConfig": {"stopSequences": ["\nObservation:"]}}'
headers:
User-Agent:
- X-USER-AGENT-XXX
accept:
- '*/*'
accept-encoding:
- ACCEPT-ENCODING-XXX
connection:
- keep-alive
content-length:
- '4512'
content-type:
- application/json
host:
- generativelanguage.googleapis.com
x-goog-api-client:
- google-genai-sdk/1.49.0 gl-python/3.13.3
x-goog-api-key:
- X-GOOG-API-KEY-XXX
method: POST
uri: https://generativelanguage.googleapis.com/v1beta/models/gemini-2.5-flash:generateContent
response:
body:
string: "{\n \"candidates\": [\n {\n \"content\": {\n \"parts\":
[\n {\n \"functionCall\": {\n \"name\": \"read_website\",\n
\ \"args\": {\n \"url\": \"https://www.example.com/ai-agent-market-report\"\n
\ }\n },\n \"thoughtSignature\": \"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\"\n
\ }\n ],\n \"role\": \"model\"\n },\n \"finishReason\":
\"STOP\",\n \"index\": 0,\n \"finishMessage\": \"Model generated
function call(s).\"\n }\n ],\n \"usageMetadata\": {\n \"promptTokenCount\":
465,\n \"candidatesTokenCount\": 29,\n \"totalTokenCount\": 916,\n \"promptTokensDetails\":
[\n {\n \"modality\": \"TEXT\",\n \"tokenCount\": 465\n
\ }\n ],\n \"thoughtsTokenCount\": 422\n },\n \"modelVersion\":
\"gemini-2.5-flash\",\n \"responseId\": \"jUWCadDOIdi8_uMPxuOu4Ak\"\n}\n"
headers:
Alt-Svc:
- h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
Content-Type:
- application/json; charset=UTF-8
Date:
- Tue, 03 Feb 2026 18:59:25 GMT
Server:
- scaffolding on HTTPServer2
Server-Timing:
- gfet4t7; dur=3079
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: Research the current
state of the AI agent market:\n1. Search for recent information about AI agents
and their market trends\n2. Read detailed content from a relevant industry source\n3.
Generate a brief report summarizing the key findings\n\nUse the available tools
for each step."}], "role": "user"}, {"parts": [{"functionCall": {"args": {"query":
"AI agent market trends 2023-2024"}, "name": "web_search"}, "thoughtSignature":
"CoYEAXLI2nzmyDix3_QA-tMOiUwpDVoA5-RJoRW7kw3okJaVYCa5Usx7eBn4xowP7oXNynS4NfawCYqboufBXjHinq13UTcYg0Y74qIrza4KuctliGmf8G7S4QoS0Y3gqCHQKsxTdShQOg8wirnr8Rdu1eyrrhWE0XKk0HPA0Ssj7zUVoJBqHPqwyvkFyXkMtpcmtq9qXmZYfMFuSKRQnYLVLllL_BpOIL3w7MuofpviO85bvYk9gX0vsDjYWS6EdVEfC9k2BWGjhHaILXT9A1iwNPdDAg33SOC-BlPrGox0ghCr5qEKnBMZhUszqaUCykczFCq-xMIA3xDGNbTjicWb53sL_PXBYLsNty1giW3nKFe8-8eRpUsHUx7oQ82m4AUxKqk99mZjaLp8bHk-rERjFZErcw_pe_3190K0WGHH5ecB4amJCzZtVrQJ1oAZhb7_P1VZ57xmt1z_c1pQgjuvnV-cWE9blh5o6mNNFbFuzJDIO2k8qrFeeDwlCF8OOrxo8F-z1evg4yjZ1-9TLCVFTmZ0S0PI54FS5afb0RdPol2_ISNw7H_dtnO4z6LhT2NmlYqYZr8qfVoUD21rmI08NFs-f_6JW5-7eSQbax76SW-6A2IqqPPyF66MCpqtEzC-hpzVsCBcIQyRQWsdm-RNAs50gmqF6W3CcTPryWkeS7w9ORqxdiU="}],
"role": "model"}, {"parts": [{"functionResponse": {"name": "web_search", "response":
{"result": "Search results for ''AI agent market trends 2023-2024'': Found 3
relevant articles about the topic including market analysis, competitor data,
and industry trends."}}}], "role": "user"}, {"parts": [{"functionCall": {"args":
{"query": "latest reports AI agent market analysis"}, "name": "web_search"},
"thoughtSignature": "CpwGAXLI2nybmVGffIN1k-T5M2HmQNlvybZRPoo_ysgNARa-9nrPdRoBZ9RC-Dee9KSk1o7O-IU9l0sWCTirQYcroEhXon-JIQUVTed_L0s__sBOR-hJnZWoaG5ucsfJQvovAQba2Wb7uViEkdySvHfRApF0atewbC-TCKZrxDAQ6Naby8nwUTauJPKlgsBsZVnlViRfIbF7pom1zvXD-d5htjMiuJr1nOuSH0EGQWC4TUiuJD23hgockzhmIpbU_bStn8PFIQNsySEzl6H5sZdlD4auwCMCD2Q-Ur05w1uLv7n8GoSZn5dkdXLR5R7dZ-kkX-xP4w841Ih2gc6rBKT5tSedN01AuJsK65NSfOXZBwakxs58WZXDQXnIQe4d2QThAX3nPdUmhvVI6sHX-ZdtQZIrhE7hRf9j_T_wvvrUao5VDv-mxXd9bcPEV2BzSXkvkAB1SbJ-5wN7Qb2j31lkiUu5uRnZOiVxL5iCS-8Z_jEl4NjpGithbcPoNpFIDOeiE_f8kf7tQJDX-YNquPbYZRJHvIfLalVQndVGNlZVN2jXT3Wwo8So3vmzIDFVjV-pj7tSRNK8hTITm6bfHS-XUZqJdm7eHCzhonyJ7_tl7LbsstPXoZU3ZN50tNpXYOK-NzgzU7iwd9SaHVXgzQRdujWgHuBmSiSd9qNHvdaNwgARVTnMj3VYpehgIuaYMzQmgM99TdC_zmzcqHa5VZSnHKHqMIVc9gjRvVwz4DUm6VLLnKnVYFClM6gofmUI6s9fThiR5EdfimaDTlRlzh6Df33jAbRA9rUTDH6uE-DjiopCvXuHjmQqK9Smyxt2vTao9H7AYIRN7yWmdVoaG0tUSL2XQ31wIW3cEyhz7ihQwFYKJnOkQ3_CiU6KV-4ldk9UY_vKWSgItVTTE6G8Di0iviiCAkmL59Uj7vnIp80-U9rDIK7WhxpAWlrDA6cGQT2LGAXQ2liXtLa31nXyfvCezhtSS8jSVm4SHaiU-INvYtpq2Q7nXPTFbjjZooyC5FePGqAH1T-sRYbR02jaa572_NuwFgBCObTfqO8G5A=="}],
"role": "model"}, {"parts": [{"functionResponse": {"name": "web_search", "response":
{"result": "Search results for ''latest reports AI agent market analysis'':
Found 3 relevant articles about the topic including market analysis, competitor
data, and industry trends."}}}], "role": "user"}, {"parts": [{"functionCall":
{"args": {"url": "https://www.example.com/ai-agent-market-report"}, "name":
"read_website"}, "thoughtSignature": "CooPAXLI2nzYy6ki8YJo4RDDzryK6qtkbIEWXCh0ZjpoRX2fgNghUrxXZUwrsrbrwEpccdvWCDpb5ZkwYMNuzMi4yRUsjfcebfd2VCwQgvWnWmitj3taAcLCUDIJX5pGt0L2O8V6ehWmrANQHGw6Qc_QVx5dMlSFeFKHtfc1M95CJz2BxZd3lnuKLCEu7LCCiqIDdd1o1y_EcGsl7OHai6WyQJg49Cvcww__Z-kfSVoAPGNedTYPIf4ImttMyofV8-yczI0IGjhFzE0Qk1Pvo84O9NyOufpPELeKY8l1yfZgSZEL0sUA6weqf1P_xzNKt6h96Rh1KpAx5iTGFtqOWJrJ8OP-ZdGJ-rA-xZQuTRtKbW_e60rC5kPgJnkhWCp1p7HTLgTGwpzzxztqL0ggURaWw8GJw8S41BcM5mFEA-a7ivMWPMLdMk6h5gr_Y8JTnLSRZFoZYHkY9bTcAFPc9gapyFlKkQDciYet_MHe2zfE7ycx0e8c0W7ISoYPHpXW_WxNekMiNdfx1eg_mEX_Y0Vjc70p-HtbnEGaBoZWJSo-cJtZdA4sNJaIuEnnVTtAdAtnoxJUOyr2jrKDAsSjHmVoeLARZO2_DuJKsEVNHzsNPMw4SrBq1DkG52Aof7KcskOfW2OyoZEUnIf23IRabKflUG_7dHGqYfLtkWRApWZYBy2eQILwsmXJ4xx27S7_02Jl0D8rX3vOQhjS7lTjrXvy8wU3biUFvbnqJuLj3ACLn7Hn1axe4dB7zIpYC1di63DDs1fQp79d2VaGRC-tVMKiQu_-yC6nCM4j8JSnpBNgvyhq3ilAr_iDHD6GkbxdBBChFbZl0KY-WkrcZpPp2g2m_beiQuzF-cM6RuaqF2W0TEjVT-OZ1ivObreXFVFWa9T5qFsTjV3E_SFlmrXdx6Kf8d0i9QeEwbzBIvvX3VNUdW1DJ95WylaUXFtljk_cqylri2j2WTPMTSV9fcM_a8UWoayUAuLzq8zgxd2Wvrm8uvGcaewAQT-yK-u5FsLFoKxaMkoakb2_1tjWfhn-MrbIoYOBIebUapUhADUJgGDTG7byEEQlbwNaa8rOZ5ZpdBrDXjtj1tsz6cqaEiCbtZWqei0myuMa0J6Z3FHoceSUgOACD_bHWSkzdW7LdKBKLxB25fKfD1hCLscE1skZ7nAEZWmrUzKz9yCiqAPfatQhHqnr3EchEB_dxbNXxCCT6IFxemhb9AsaQWjcTrlQJiuz8t4VMmu1slgEcrhweZ_PpxI_E74qvV9ljcFLcziW0BZaqepJMeBe2cLfVVki5R5kudQVuAcCEdkrwBDWAwZlO9aWTmiZ9-ggfl3F_63JzZXSM_NDc_2rJ1k65e-O-vyTzkrUwnSPnh4RPK6jeIul4SSLPgyZBwp0qHyTl4As8jpMe9Rbt0NRli6Z5eAr_IYdbicKo_pzqiupdxvu4u-jKt-F4KojU9avgWFAB01isHHO5Z1vzVJ6XDilWeah5DvHc1lkcPCXtbBGvykfFqJIBhthnFi0f_S4HV-IlOKwvKbfmL5GplD7H-DjUA5UdHjw8HoJa6uQxhbERy5dZlYqxN918aL147Afq4LuPoWUJULEsYULwUuA6HspemIKUltHacOAxZgP4OLVkB3zwssj8E6rMtU1puupHiL7J66fFaR3co71gzzlvl8R2Xi3xEQdpigxxCUAsZWMrSrITRBnKPKGF1CrFEhU6FP6bQAQ6UuhAdqLoJihwVnMTyY9fGUriwCkrQu5gK7ZQlnXyluV0J_5xWh4sOaPmwmeiUXMBPN0iGb7z24lyHaI3QXz3kGlJBnIFhseJTJo3ed66Z_LAf8I_hFC6s_sIioEmRgd4tm3Q1U05ETKrptnzo8Ac4AOTdJtbQv0uDQSkoefUbebu7x6L9Dns04VSvDPKLwlFQd81sl9DYmi9SPDxKT7S6gfG6WjJ9z35eNSR01QW1QIgAAhMU8UX4o7QQaXnUZxfZeYRMXlzu_xb4KSREvc_FeLJ-IvnPFgzryAgLi_Sipl__Eul0sjrREPYJE1GxBOIoURGa-Bsmc3yy8aWArxv_HGpbLzwjmH8TaMvB3P_4tkvT-5IjJlpe0UrR1ssqasUtwfH9yWv5-4i-EdJrJ_SJ4Hl1Vlj9zi9lEFr33Zs96kn8ZOkBHp0m7Sxr5xP-krSxQkROIpu0d02kIqQ3nob-kGbnAf0zkmH6pS3H4mG2Zksu8KcGvghx7XTl3qBOJ-ZY4vlev2cSMBfMmnbUHKvMlz4YsmTGR1JPntDguA8UJJ1UZCex4E_W3KcHwd4qvzqgMZNjdarIvGjlmnKmoL1RV7EqUsBkpk-jauY0SqoWsIIf4b6O9Y3fQRRJURLeIfGCTmlxl-df-4yjqUhxUXTaQsX2KlEJ3tZK-ZI9FdKMzqPip2oMFwf2XfLIyIuRA0NU5fDRIxqPUzYv6RQ-zhXXB1QscsAtyf1t-LsaVw__1Vfj6V3Ups4pNyiwMAZg1z9DaIHht--VfgCdqT4RLcaGI8eEDrjkOc9G_iLkLBCfOB7EZkcXT20Lc1Silxa--dZsaYp5Tni8dz6f5YWg=="}],
"role": "model"}, {"parts": [{"functionResponse": {"name": "read_website", "response":
{"result": "Content from https://www.example.com/ai-agent-market-report: This
article discusses key insights about the topic including market size ($50B),
growth rate (15% YoY), and major players in the industry."}}}], "role": "user"}],
"systemInstruction": {"parts": [{"text": "You are Research Analyst. An experienced
analyst skilled at gathering information and synthesizing findings into actionable
insights.\nYour personal goal is: Conduct thorough research and produce insightful
reports"}], "role": "user"}, "tools": [{"functionDeclarations": [{"description":
"Search the web for information on a given topic.\n\nArgs:\n query: The search
query to look up.\n\nReturns:\n Search results as a string.", "name": "web_search",
"parameters_json_schema": {"properties": {"query": {"title": "Query", "type":
"string"}}, "required": ["query"], "type": "object", "additionalProperties":
false}}, {"description": "Read and extract content from a website URL.\n\nArgs:\n url:
The URL of the website to read.\n\nReturns:\n The extracted content from
the website.", "name": "read_website", "parameters_json_schema": {"properties":
{"url": {"title": "Url", "type": "string"}}, "required": ["url"], "type": "object",
"additionalProperties": false}}, {"description": "Generate a structured report
based on research findings.\n\nArgs:\n title: The title of the report.\n findings:
The research findings to include.\n\nReturns:\n A formatted report string.",
"name": "generate_report", "parameters_json_schema": {"properties": {"title":
{"title": "Title", "type": "string"}, "findings": {"title": "Findings", "type":
"string"}}, "required": ["title", "findings"], "type": "object", "additionalProperties":
false}}]}], "generationConfig": {"stopSequences": ["\nObservation:"]}}'
headers:
User-Agent:
- X-USER-AGENT-XXX
accept:
- '*/*'
accept-encoding:
- ACCEPT-ENCODING-XXX
connection:
- keep-alive
content-length:
- '7562'
content-type:
- application/json
host:
- generativelanguage.googleapis.com
x-goog-api-client:
- google-genai-sdk/1.49.0 gl-python/3.13.3
x-goog-api-key:
- X-GOOG-API-KEY-XXX
method: POST
uri: https://generativelanguage.googleapis.com/v1beta/models/gemini-2.5-flash:generateContent
response:
body:
string: "{\n \"candidates\": [\n {\n \"content\": {\n \"parts\":
[\n {\n \"functionCall\": {\n \"name\": \"generate_report\",\n
\ \"args\": {\n \"findings\": \"The AI agent market
is currently valued at $50 billion and is experiencing a strong growth rate
of 15% year-over-year. Key players in the industry are contributing to this
expansion, driven by increasing adoption across various sectors.\",\n \"title\":
\"Current State of the AI Agent Market\"\n }\n },\n
\ \"thoughtSignature\": \"CuACAXLI2nzhub94iTgphfrBnaQV13Wv0+kRJj+l9jEDfxsyNg9eGnhxRfj4cued3Mgvv1CR9vkpfDV/V9x57TVWLNwPsVvsTgZKI0pwmV355sUCRKqAyfRBwDWhn0UAl9+sYNFCKUJCp8G5QBGfrar1lYLltX/z83d4O13Wn5Ugvxco9o4CdxnnPJOWkTPETRgXA/1HSdEiwGNqt0A3lKYkGRXQx+XyK54lDwmOBg+Yx4ZVgUxANXLK1z91NF/6cpmSVgoE2sL0VrIHISYs4XdUCj1fL3R7DpnZdrrZhmqnTjEgkeR1C3BR5GJeSUmg+kmqjPSPnP0NYiZo9H9SGL/ewGz3wg+GKcILAa4nD7/tfdqIMbAff8PJemwJE4ONT5zAmJ69/NFj0i1X01v04E8f2NdHewPSsKO5mptk5qzWxoW3G3uUhXccxk62EydTsESf6WRwolsmphaGgVE9AwuhzQ==\"\n
\ }\n ],\n \"role\": \"model\"\n },\n \"finishReason\":
\"STOP\",\n \"index\": 0,\n \"finishMessage\": \"Model generated
function call(s).\"\n }\n ],\n \"usageMetadata\": {\n \"promptTokenCount\":
557,\n \"candidatesTokenCount\": 73,\n \"totalTokenCount\": 700,\n \"cachedContentTokenCount\":
330,\n \"promptTokensDetails\": [\n {\n \"modality\": \"TEXT\",\n
\ \"tokenCount\": 557\n }\n ],\n \"cacheTokensDetails\":
[\n {\n \"modality\": \"TEXT\",\n \"tokenCount\": 330\n
\ }\n ],\n \"thoughtsTokenCount\": 70\n },\n \"modelVersion\":
\"gemini-2.5-flash\",\n \"responseId\": \"jkWCacGZMLrv_uMPibCHmQU\"\n}\n"
headers:
Alt-Svc:
- h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
Content-Type:
- application/json; charset=UTF-8
Date:
- Tue, 03 Feb 2026 18:59:26 GMT
Server:
- scaffolding on HTTPServer2
Server-Timing:
- gfet4t7; dur=1224
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: Research the current
state of the AI agent market:\n1. Search for recent information about AI agents
and their market trends\n2. Read detailed content from a relevant industry source\n3.
Generate a brief report summarizing the key findings\n\nUse the available tools
for each step."}], "role": "user"}, {"parts": [{"functionCall": {"args": {"query":
"AI agent market trends 2023-2024"}, "name": "web_search"}, "thoughtSignature":
"CoYEAXLI2nzmyDix3_QA-tMOiUwpDVoA5-RJoRW7kw3okJaVYCa5Usx7eBn4xowP7oXNynS4NfawCYqboufBXjHinq13UTcYg0Y74qIrza4KuctliGmf8G7S4QoS0Y3gqCHQKsxTdShQOg8wirnr8Rdu1eyrrhWE0XKk0HPA0Ssj7zUVoJBqHPqwyvkFyXkMtpcmtq9qXmZYfMFuSKRQnYLVLllL_BpOIL3w7MuofpviO85bvYk9gX0vsDjYWS6EdVEfC9k2BWGjhHaILXT9A1iwNPdDAg33SOC-BlPrGox0ghCr5qEKnBMZhUszqaUCykczFCq-xMIA3xDGNbTjicWb53sL_PXBYLsNty1giW3nKFe8-8eRpUsHUx7oQ82m4AUxKqk99mZjaLp8bHk-rERjFZErcw_pe_3190K0WGHH5ecB4amJCzZtVrQJ1oAZhb7_P1VZ57xmt1z_c1pQgjuvnV-cWE9blh5o6mNNFbFuzJDIO2k8qrFeeDwlCF8OOrxo8F-z1evg4yjZ1-9TLCVFTmZ0S0PI54FS5afb0RdPol2_ISNw7H_dtnO4z6LhT2NmlYqYZr8qfVoUD21rmI08NFs-f_6JW5-7eSQbax76SW-6A2IqqPPyF66MCpqtEzC-hpzVsCBcIQyRQWsdm-RNAs50gmqF6W3CcTPryWkeS7w9ORqxdiU="}],
"role": "model"}, {"parts": [{"functionResponse": {"name": "web_search", "response":
{"result": "Search results for ''AI agent market trends 2023-2024'': Found 3
relevant articles about the topic including market analysis, competitor data,
and industry trends."}}}], "role": "user"}, {"parts": [{"functionCall": {"args":
{"query": "latest reports AI agent market analysis"}, "name": "web_search"},
"thoughtSignature": "CpwGAXLI2nybmVGffIN1k-T5M2HmQNlvybZRPoo_ysgNARa-9nrPdRoBZ9RC-Dee9KSk1o7O-IU9l0sWCTirQYcroEhXon-JIQUVTed_L0s__sBOR-hJnZWoaG5ucsfJQvovAQba2Wb7uViEkdySvHfRApF0atewbC-TCKZrxDAQ6Naby8nwUTauJPKlgsBsZVnlViRfIbF7pom1zvXD-d5htjMiuJr1nOuSH0EGQWC4TUiuJD23hgockzhmIpbU_bStn8PFIQNsySEzl6H5sZdlD4auwCMCD2Q-Ur05w1uLv7n8GoSZn5dkdXLR5R7dZ-kkX-xP4w841Ih2gc6rBKT5tSedN01AuJsK65NSfOXZBwakxs58WZXDQXnIQe4d2QThAX3nPdUmhvVI6sHX-ZdtQZIrhE7hRf9j_T_wvvrUao5VDv-mxXd9bcPEV2BzSXkvkAB1SbJ-5wN7Qb2j31lkiUu5uRnZOiVxL5iCS-8Z_jEl4NjpGithbcPoNpFIDOeiE_f8kf7tQJDX-YNquPbYZRJHvIfLalVQndVGNlZVN2jXT3Wwo8So3vmzIDFVjV-pj7tSRNK8hTITm6bfHS-XUZqJdm7eHCzhonyJ7_tl7LbsstPXoZU3ZN50tNpXYOK-NzgzU7iwd9SaHVXgzQRdujWgHuBmSiSd9qNHvdaNwgARVTnMj3VYpehgIuaYMzQmgM99TdC_zmzcqHa5VZSnHKHqMIVc9gjRvVwz4DUm6VLLnKnVYFClM6gofmUI6s9fThiR5EdfimaDTlRlzh6Df33jAbRA9rUTDH6uE-DjiopCvXuHjmQqK9Smyxt2vTao9H7AYIRN7yWmdVoaG0tUSL2XQ31wIW3cEyhz7ihQwFYKJnOkQ3_CiU6KV-4ldk9UY_vKWSgItVTTE6G8Di0iviiCAkmL59Uj7vnIp80-U9rDIK7WhxpAWlrDA6cGQT2LGAXQ2liXtLa31nXyfvCezhtSS8jSVm4SHaiU-INvYtpq2Q7nXPTFbjjZooyC5FePGqAH1T-sRYbR02jaa572_NuwFgBCObTfqO8G5A=="}],
"role": "model"}, {"parts": [{"functionResponse": {"name": "web_search", "response":
{"result": "Search results for ''latest reports AI agent market analysis'':
Found 3 relevant articles about the topic including market analysis, competitor
data, and industry trends."}}}], "role": "user"}, {"parts": [{"functionCall":
{"args": {"url": "https://www.example.com/ai-agent-market-report"}, "name":
"read_website"}, "thoughtSignature": "CooPAXLI2nzYy6ki8YJo4RDDzryK6qtkbIEWXCh0ZjpoRX2fgNghUrxXZUwrsrbrwEpccdvWCDpb5ZkwYMNuzMi4yRUsjfcebfd2VCwQgvWnWmitj3taAcLCUDIJX5pGt0L2O8V6ehWmrANQHGw6Qc_QVx5dMlSFeFKHtfc1M95CJz2BxZd3lnuKLCEu7LCCiqIDdd1o1y_EcGsl7OHai6WyQJg49Cvcww__Z-kfSVoAPGNedTYPIf4ImttMyofV8-yczI0IGjhFzE0Qk1Pvo84O9NyOufpPELeKY8l1yfZgSZEL0sUA6weqf1P_xzNKt6h96Rh1KpAx5iTGFtqOWJrJ8OP-ZdGJ-rA-xZQuTRtKbW_e60rC5kPgJnkhWCp1p7HTLgTGwpzzxztqL0ggURaWw8GJw8S41BcM5mFEA-a7ivMWPMLdMk6h5gr_Y8JTnLSRZFoZYHkY9bTcAFPc9gapyFlKkQDciYet_MHe2zfE7ycx0e8c0W7ISoYPHpXW_WxNekMiNdfx1eg_mEX_Y0Vjc70p-HtbnEGaBoZWJSo-cJtZdA4sNJaIuEnnVTtAdAtnoxJUOyr2jrKDAsSjHmVoeLARZO2_DuJKsEVNHzsNPMw4SrBq1DkG52Aof7KcskOfW2OyoZEUnIf23IRabKflUG_7dHGqYfLtkWRApWZYBy2eQILwsmXJ4xx27S7_02Jl0D8rX3vOQhjS7lTjrXvy8wU3biUFvbnqJuLj3ACLn7Hn1axe4dB7zIpYC1di63DDs1fQp79d2VaGRC-tVMKiQu_-yC6nCM4j8JSnpBNgvyhq3ilAr_iDHD6GkbxdBBChFbZl0KY-WkrcZpPp2g2m_beiQuzF-cM6RuaqF2W0TEjVT-OZ1ivObreXFVFWa9T5qFsTjV3E_SFlmrXdx6Kf8d0i9QeEwbzBIvvX3VNUdW1DJ95WylaUXFtljk_cqylri2j2WTPMTSV9fcM_a8UWoayUAuLzq8zgxd2Wvrm8uvGcaewAQT-yK-u5FsLFoKxaMkoakb2_1tjWfhn-MrbIoYOBIebUapUhADUJgGDTG7byEEQlbwNaa8rOZ5ZpdBrDXjtj1tsz6cqaEiCbtZWqei0myuMa0J6Z3FHoceSUgOACD_bHWSkzdW7LdKBKLxB25fKfD1hCLscE1skZ7nAEZWmrUzKz9yCiqAPfatQhHqnr3EchEB_dxbNXxCCT6IFxemhb9AsaQWjcTrlQJiuz8t4VMmu1slgEcrhweZ_PpxI_E74qvV9ljcFLcziW0BZaqepJMeBe2cLfVVki5R5kudQVuAcCEdkrwBDWAwZlO9aWTmiZ9-ggfl3F_63JzZXSM_NDc_2rJ1k65e-O-vyTzkrUwnSPnh4RPK6jeIul4SSLPgyZBwp0qHyTl4As8jpMe9Rbt0NRli6Z5eAr_IYdbicKo_pzqiupdxvu4u-jKt-F4KojU9avgWFAB01isHHO5Z1vzVJ6XDilWeah5DvHc1lkcPCXtbBGvykfFqJIBhthnFi0f_S4HV-IlOKwvKbfmL5GplD7H-DjUA5UdHjw8HoJa6uQxhbERy5dZlYqxN918aL147Afq4LuPoWUJULEsYULwUuA6HspemIKUltHacOAxZgP4OLVkB3zwssj8E6rMtU1puupHiL7J66fFaR3co71gzzlvl8R2Xi3xEQdpigxxCUAsZWMrSrITRBnKPKGF1CrFEhU6FP6bQAQ6UuhAdqLoJihwVnMTyY9fGUriwCkrQu5gK7ZQlnXyluV0J_5xWh4sOaPmwmeiUXMBPN0iGb7z24lyHaI3QXz3kGlJBnIFhseJTJo3ed66Z_LAf8I_hFC6s_sIioEmRgd4tm3Q1U05ETKrptnzo8Ac4AOTdJtbQv0uDQSkoefUbebu7x6L9Dns04VSvDPKLwlFQd81sl9DYmi9SPDxKT7S6gfG6WjJ9z35eNSR01QW1QIgAAhMU8UX4o7QQaXnUZxfZeYRMXlzu_xb4KSREvc_FeLJ-IvnPFgzryAgLi_Sipl__Eul0sjrREPYJE1GxBOIoURGa-Bsmc3yy8aWArxv_HGpbLzwjmH8TaMvB3P_4tkvT-5IjJlpe0UrR1ssqasUtwfH9yWv5-4i-EdJrJ_SJ4Hl1Vlj9zi9lEFr33Zs96kn8ZOkBHp0m7Sxr5xP-krSxQkROIpu0d02kIqQ3nob-kGbnAf0zkmH6pS3H4mG2Zksu8KcGvghx7XTl3qBOJ-ZY4vlev2cSMBfMmnbUHKvMlz4YsmTGR1JPntDguA8UJJ1UZCex4E_W3KcHwd4qvzqgMZNjdarIvGjlmnKmoL1RV7EqUsBkpk-jauY0SqoWsIIf4b6O9Y3fQRRJURLeIfGCTmlxl-df-4yjqUhxUXTaQsX2KlEJ3tZK-ZI9FdKMzqPip2oMFwf2XfLIyIuRA0NU5fDRIxqPUzYv6RQ-zhXXB1QscsAtyf1t-LsaVw__1Vfj6V3Ups4pNyiwMAZg1z9DaIHht--VfgCdqT4RLcaGI8eEDrjkOc9G_iLkLBCfOB7EZkcXT20Lc1Silxa--dZsaYp5Tni8dz6f5YWg=="}],
"role": "model"}, {"parts": [{"functionResponse": {"name": "read_website", "response":
{"result": "Content from https://www.example.com/ai-agent-market-report: This
article discusses key insights about the topic including market size ($50B),
growth rate (15% YoY), and major players in the industry."}}}], "role": "user"},
{"parts": [{"functionCall": {"args": {"findings": "The AI agent market is currently
valued at $50 billion and is experiencing a strong growth rate of 15% year-over-year.
Key players in the industry are contributing to this expansion, driven by increasing
adoption across various sectors.", "title": "Current State of the AI Agent Market"},
"name": "generate_report"}, "thoughtSignature": "CuACAXLI2nzhub94iTgphfrBnaQV13Wv0-kRJj-l9jEDfxsyNg9eGnhxRfj4cued3Mgvv1CR9vkpfDV_V9x57TVWLNwPsVvsTgZKI0pwmV355sUCRKqAyfRBwDWhn0UAl9-sYNFCKUJCp8G5QBGfrar1lYLltX_z83d4O13Wn5Ugvxco9o4CdxnnPJOWkTPETRgXA_1HSdEiwGNqt0A3lKYkGRXQx-XyK54lDwmOBg-Yx4ZVgUxANXLK1z91NF_6cpmSVgoE2sL0VrIHISYs4XdUCj1fL3R7DpnZdrrZhmqnTjEgkeR1C3BR5GJeSUmg-kmqjPSPnP0NYiZo9H9SGL_ewGz3wg-GKcILAa4nD7_tfdqIMbAff8PJemwJE4ONT5zAmJ69_NFj0i1X01v04E8f2NdHewPSsKO5mptk5qzWxoW3G3uUhXccxk62EydTsESf6WRwolsmphaGgVE9AwuhzQ=="}],
"role": "model"}, {"parts": [{"functionResponse": {"name": "generate_report",
"response": {"result": "# Current State of the AI Agent Market\n\n## Executive
Summary\nThe AI agent market is currently valued at $50 billion and is experiencing
a strong growth rate of 15% year-over-year. Key players in the industry are
contributing to this expansion, driven by increasing adoption across various
sectors.\n\n## Conclusion\nBased on the analysis, the market shows strong growth
potential."}}}], "role": "user"}], "systemInstruction": {"parts": [{"text":
"You are Research Analyst. An experienced analyst skilled at gathering information
and synthesizing findings into actionable insights.\nYour personal goal is:
Conduct thorough research and produce insightful reports"}], "role": "user"},
"tools": [{"functionDeclarations": [{"description": "Search the web for information
on a given topic.\n\nArgs:\n query: The search query to look up.\n\nReturns:\n Search
results as a string.", "name": "web_search", "parameters_json_schema": {"properties":
{"query": {"title": "Query", "type": "string"}}, "required": ["query"], "type":
"object", "additionalProperties": false}}, {"description": "Read and extract
content from a website URL.\n\nArgs:\n url: The URL of the website to read.\n\nReturns:\n The
extracted content from the website.", "name": "read_website", "parameters_json_schema":
{"properties": {"url": {"title": "Url", "type": "string"}}, "required": ["url"],
"type": "object", "additionalProperties": false}}, {"description": "Generate
a structured report based on research findings.\n\nArgs:\n title: The title
of the report.\n findings: The research findings to include.\n\nReturns:\n A
formatted report string.", "name": "generate_report", "parameters_json_schema":
{"properties": {"title": {"title": "Title", "type": "string"}, "findings": {"title":
"Findings", "type": "string"}}, "required": ["title", "findings"], "type": "object",
"additionalProperties": false}}]}], "generationConfig": {"stopSequences": ["\nObservation:"]}}'
headers:
User-Agent:
- X-USER-AGENT-XXX
accept:
- '*/*'
accept-encoding:
- ACCEPT-ENCODING-XXX
connection:
- keep-alive
content-length:
- '8941'
content-type:
- application/json
host:
- generativelanguage.googleapis.com
x-goog-api-client:
- google-genai-sdk/1.49.0 gl-python/3.13.3
x-goog-api-key:
- X-GOOG-API-KEY-XXX
method: POST
uri: https://generativelanguage.googleapis.com/v1beta/models/gemini-2.5-flash:generateContent
response:
body:
string: "{\n \"candidates\": [\n {\n \"content\": {\n \"parts\":
[\n {\n \"text\": \"The research on the current state
of the AI agent market has been completed. A report has been generated with
the following key findings:\\n\\n**Current State of the AI Agent Market**\\n\\n**Executive
Summary**\\nThe AI agent market is currently valued at $50 billion and is
experiencing a strong growth rate of 15% year-over-year. Key players in the
industry are contributing to this expansion, driven by increasing adoption
across various sectors.\\n\\n**Conclusion**\\nBased on the analysis, the market
shows strong growth potential.\",\n \"thoughtSignature\": \"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\"\n
\ }\n ],\n \"role\": \"model\"\n },\n \"finishReason\":
\"STOP\",\n \"index\": 0\n }\n ],\n \"usageMetadata\": {\n \"promptTokenCount\":
727,\n \"candidatesTokenCount\": 108,\n \"totalTokenCount\": 910,\n
\ \"cachedContentTokenCount\": 375,\n \"promptTokensDetails\": [\n {\n
\ \"modality\": \"TEXT\",\n \"tokenCount\": 727\n }\n ],\n
\ \"cacheTokensDetails\": [\n {\n \"modality\": \"TEXT\",\n
\ \"tokenCount\": 375\n }\n ],\n \"thoughtsTokenCount\":
75\n },\n \"modelVersion\": \"gemini-2.5-flash\",\n \"responseId\": \"kUWCabvgOafg_uMP06Ga0QI\"\n}\n"
headers:
Alt-Svc:
- h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
Content-Type:
- application/json; charset=UTF-8
Date:
- Tue, 03 Feb 2026 18:59:30 GMT
Server:
- scaffolding on HTTPServer2
Server-Timing:
- gfet4t7; dur=3125
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

708
lib/crewai/tests/cassettes/utilities/TestOpenAIStructuredPlanning.test_openai_research_workflow_generates_steps.yaml Normal file
View File

@@ -0,0 +1,708 @@
interactions:
- request:
body: '{"messages":[{"role":"system","content":"You are a strategic planning assistant.
Create minimal, effective execution plans. Prefer fewer steps over more."},{"role":"user","content":"Create
a focused execution plan for the following task:\n\n## Task\nResearch the current
state of the AI agent market:\n1. Search for recent information about AI agents
and their market trends\n2. Read detailed content from a relevant industry source\n3.
Generate a brief report summarizing the key findings\n\nUse the available tools
for each step.\n\n## Expected Output\nComplete the task successfully\n\n## Available
Tools\nweb_search, read_website, generate_report\n\n## Instructions\nCreate
ONLY the essential steps needed to complete this task. Use the MINIMUM number
of steps required - do NOT pad your plan with unnecessary steps. Most tasks
need only 2-5 steps.\n\nFor each step:\n- State the specific action to take\n-
Specify which tool to use (if any)\n- Note dependencies on previous steps if
this step requires their output\n- If a step involves multiple items (e.g.,
research 3 competitors), note this explicitly\n\nDo NOT include:\n- Setup or
preparation steps that are obvious\n- Verification steps unless critical\n-
Documentation or cleanup steps unless explicitly required\n- Generic steps like
\"review results\" or \"finalize output\"\n\nAfter your plan, state:\n- \"READY:
I am ready to execute the task.\" if the plan is complete\n- \"NOT READY: I
need to refine my plan because [reason].\" if you need more thinking"}],"model":"gpt-4o","tool_choice":"auto","tools":[{"type":"function","function":{"name":"create_reasoning_plan","description":"Create
or refine a reasoning plan for a task with structured steps","strict":true,"parameters":{"type":"object","properties":{"plan":{"type":"string","description":"A
brief summary of the overall plan."},"steps":{"type":"array","description":"List
of discrete steps to execute the plan","items":{"type":"object","properties":{"step_number":{"type":"integer","description":"Step
number (1-based)"},"description":{"type":"string","description":"What to do
in this step"},"tool_to_use":{"type":["string","null"],"description":"Tool to
use for this step, or null if no tool needed"},"depends_on":{"type":"array","items":{"type":"integer"},"description":"Step
numbers this step depends on (empty array if none)"}},"required":["step_number","description","tool_to_use","depends_on"],"additionalProperties":false}},"ready":{"type":"boolean","description":"Whether
the agent is ready to execute the task."}},"required":["plan","steps","ready"],"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:
- '2619'
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-D5Fu3HzCCoZJXtY9WqBmBv4QA4PS8\",\n \"object\":
\"chat.completion\",\n \"created\": 1770145143,\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_bVEiQHpiVX9FEfuWVwTe8XGj\",\n \"type\":
\"function\",\n \"function\": {\n \"name\": \"create_reasoning_plan\",\n
\ \"arguments\": \"{\\\"plan\\\":\\\"Research the current state
of the AI agent market by gathering recent market trend data, reading in-depth
content from a reliable industry source, and generating a concise report.\\\",\\\"steps\\\":[{\\\"step_number\\\":1,\\\"description\\\":\\\"Search
for recent information about AI agents and their market trends.\\\",\\\"tool_to_use\\\":\\\"web_search\\\",\\\"depends_on\\\":[]},{\\\"step_number\\\":2,\\\"description\\\":\\\"Read
detailed content from a relevant industry source found during the search.\\\",\\\"tool_to_use\\\":\\\"read_website\\\",\\\"depends_on\\\":[1]},{\\\"step_number\\\":3,\\\"description\\\":\\\"Generate
a brief report summarizing the key findings from the gathered information.\\\",\\\"tool_to_use\\\":\\\"generate_report\\\",\\\"depends_on\\\":[1,2]}],\\\"ready\\\":true}\"\n
\ }\n }\n ],\n \"refusal\": null,\n \"annotations\":
[]\n },\n \"logprobs\": null,\n \"finish_reason\": \"tool_calls\"\n
\ }\n ],\n \"usage\": {\n \"prompt_tokens\": 480,\n \"completion_tokens\":
153,\n \"total_tokens\": 633,\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_fa7f5b168b\"\n}\n"
headers:
CF-RAY:
- CF-RAY-XXX
Connection:
- keep-alive
Content-Type:
- application/json
Date:
- Tue, 03 Feb 2026 18:59:05 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
openai-organization:
- OPENAI-ORG-XXX
openai-processing-ms:
- '2629'
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 Research Analyst. An experienced
analyst skilled at gathering information and synthesizing findings into actionable
insights.\nYour personal goal is: Conduct thorough research and produce insightful
reports"},{"role":"user","content":"\nCurrent Task: Research the current state
of the AI agent market:\n1. Search for recent information about AI agents and
their market trends\n2. Read detailed content from a relevant industry source\n3.
Generate a brief report summarizing the key findings\n\nUse the available tools
for each step."}],"model":"gpt-4o","tool_choice":"auto","tools":[{"type":"function","function":{"name":"web_search","description":"Search
the web for information on a given topic.\n\nArgs:\n query: The search query
to look up.\n\nReturns:\n Search results as a string.","strict":true,"parameters":{"properties":{"query":{"title":"Query","type":"string"}},"required":["query"],"type":"object","additionalProperties":false}}},{"type":"function","function":{"name":"read_website","description":"Read
and extract content from a website URL.\n\nArgs:\n url: The URL of the website
to read.\n\nReturns:\n The extracted content from the website.","strict":true,"parameters":{"properties":{"url":{"title":"Url","type":"string"}},"required":["url"],"type":"object","additionalProperties":false}}},{"type":"function","function":{"name":"generate_report","description":"Generate
a structured report based on research findings.\n\nArgs:\n title: The title
of the report.\n findings: The research findings to include.\n\nReturns:\n A
formatted report string.","strict":true,"parameters":{"properties":{"title":{"title":"Title","type":"string"},"findings":{"title":"Findings","type":"string"}},"required":["title","findings"],"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:
- '1849'
content-type:
- application/json
cookie:
- COOKIE-XXX
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-D5Fu6H5Oz7CA6xtmPwoBDIAr59nyJ\",\n \"object\":
\"chat.completion\",\n \"created\": 1770145146,\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_QlnPEA94TbaFA83eRDhOHXRY\",\n \"type\":
\"function\",\n \"function\": {\n \"name\": \"web_search\",\n
\ \"arguments\": \"{\\\"query\\\":\\\"current state of AI agent
market 2023\\\"}\"\n }\n }\n ],\n \"refusal\":
null,\n \"annotations\": []\n },\n \"logprobs\": null,\n
\ \"finish_reason\": \"tool_calls\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
267,\n \"completion_tokens\": 22,\n \"total_tokens\": 289,\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_fa7f5b168b\"\n}\n"
headers:
CF-RAY:
- CF-RAY-XXX
Connection:
- keep-alive
Content-Type:
- application/json
Date:
- Tue, 03 Feb 2026 18:59:07 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:
- '752'
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 Research Analyst. An experienced
analyst skilled at gathering information and synthesizing findings into actionable
insights.\nYour personal goal is: Conduct thorough research and produce insightful
reports"},{"role":"user","content":"\nCurrent Task: Research the current state
of the AI agent market:\n1. Search for recent information about AI agents and
their market trends\n2. Read detailed content from a relevant industry source\n3.
Generate a brief report summarizing the key findings\n\nUse the available tools
for each step."},{"role":"assistant","content":null,"tool_calls":[{"id":"call_QlnPEA94TbaFA83eRDhOHXRY","type":"function","function":{"name":"web_search","arguments":"{\"query\":\"current
state of AI agent market 2023\"}"}}]},{"role":"tool","tool_call_id":"call_QlnPEA94TbaFA83eRDhOHXRY","name":"web_search","content":"Search
results for ''current state of AI agent market 2023'': Found 3 relevant articles
about the topic including market analysis, competitor data, and industry trends."}],"model":"gpt-4o","tool_choice":"auto","tools":[{"type":"function","function":{"name":"web_search","description":"Search
the web for information on a given topic.\n\nArgs:\n query: The search query
to look up.\n\nReturns:\n Search results as a string.","strict":true,"parameters":{"properties":{"query":{"title":"Query","type":"string"}},"required":["query"],"type":"object","additionalProperties":false}}},{"type":"function","function":{"name":"read_website","description":"Read
and extract content from a website URL.\n\nArgs:\n url: The URL of the website
to read.\n\nReturns:\n The extracted content from the website.","strict":true,"parameters":{"properties":{"url":{"title":"Url","type":"string"}},"required":["url"],"type":"object","additionalProperties":false}}},{"type":"function","function":{"name":"generate_report","description":"Generate
a structured report based on research findings.\n\nArgs:\n title: The title
of the report.\n findings: The research findings to include.\n\nReturns:\n A
formatted report string.","strict":true,"parameters":{"properties":{"title":{"title":"Title","type":"string"},"findings":{"title":"Findings","type":"string"}},"required":["title","findings"],"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:
- '2320'
content-type:
- application/json
cookie:
- COOKIE-XXX
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-D5Fu7QFl2h9pGJ0uhX6g4Fi4MMzMX\",\n \"object\":
\"chat.completion\",\n \"created\": 1770145147,\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_sOaxpAdq5dvpRhUJMAct2oNP\",\n \"type\":
\"function\",\n \"function\": {\n \"name\": \"read_website\",\n
\ \"arguments\": \"{\\\"url\\\": \\\"https://www.example.com/ai-agent-market-analysis-2023\\\"}\"\n
\ }\n },\n {\n \"id\": \"call_1GRSbggp4SYHg5WqAUQx5Dce\",\n
\ \"type\": \"function\",\n \"function\": {\n \"name\":
\"read_website\",\n \"arguments\": \"{\\\"url\\\": \\\"https://www.example.com/ai-agent-competitor-data-2023\\\"}\"\n
\ }\n },\n {\n \"id\": \"call_43s9ebATowN3hA5piPjL2z5N\",\n
\ \"type\": \"function\",\n \"function\": {\n \"name\":
\"read_website\",\n \"arguments\": \"{\\\"url\\\": \\\"https://www.example.com/ai-agent-industry-trends-2023\\\"}\"\n
\ }\n }\n ],\n \"refusal\": null,\n \"annotations\":
[]\n },\n \"logprobs\": null,\n \"finish_reason\": \"tool_calls\"\n
\ }\n ],\n \"usage\": {\n \"prompt_tokens\": 330,\n \"completion_tokens\":
101,\n \"total_tokens\": 431,\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_fa7f5b168b\"\n}\n"
headers:
CF-RAY:
- CF-RAY-XXX
Connection:
- keep-alive
Content-Type:
- application/json
Date:
- Tue, 03 Feb 2026 18:59:09 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:
- '1885'
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 Research Analyst. An experienced
analyst skilled at gathering information and synthesizing findings into actionable
insights.\nYour personal goal is: Conduct thorough research and produce insightful
reports"},{"role":"user","content":"\nCurrent Task: Research the current state
of the AI agent market:\n1. Search for recent information about AI agents and
their market trends\n2. Read detailed content from a relevant industry source\n3.
Generate a brief report summarizing the key findings\n\nUse the available tools
for each step."},{"role":"assistant","content":null,"tool_calls":[{"id":"call_QlnPEA94TbaFA83eRDhOHXRY","type":"function","function":{"name":"web_search","arguments":"{\"query\":\"current
state of AI agent market 2023\"}"}}]},{"role":"tool","tool_call_id":"call_QlnPEA94TbaFA83eRDhOHXRY","name":"web_search","content":"Search
results for ''current state of AI agent market 2023'': Found 3 relevant articles
about the topic including market analysis, competitor data, and industry trends."},{"role":"assistant","content":null,"tool_calls":[{"id":"call_sOaxpAdq5dvpRhUJMAct2oNP","type":"function","function":{"name":"read_website","arguments":"{\"url\":
\"https://www.example.com/ai-agent-market-analysis-2023\"}"}},{"id":"call_1GRSbggp4SYHg5WqAUQx5Dce","type":"function","function":{"name":"read_website","arguments":"{\"url\":
\"https://www.example.com/ai-agent-competitor-data-2023\"}"}},{"id":"call_43s9ebATowN3hA5piPjL2z5N","type":"function","function":{"name":"read_website","arguments":"{\"url\":
\"https://www.example.com/ai-agent-industry-trends-2023\"}"}}]},{"role":"tool","tool_call_id":"call_sOaxpAdq5dvpRhUJMAct2oNP","name":"read_website","content":"Content
from https://www.example.com/ai-agent-market-analysis-2023: This article discusses
key insights about the topic including market size ($50B), growth rate (15%
YoY), and major players in the industry."},{"role":"tool","tool_call_id":"call_1GRSbggp4SYHg5WqAUQx5Dce","name":"read_website","content":"Content
from https://www.example.com/ai-agent-competitor-data-2023: This article discusses
key insights about the topic including market size ($50B), growth rate (15%
YoY), and major players in the industry."},{"role":"tool","tool_call_id":"call_43s9ebATowN3hA5piPjL2z5N","name":"read_website","content":"Content
from https://www.example.com/ai-agent-industry-trends-2023: This article discusses
key insights about the topic including market size ($50B), growth rate (15%
YoY), and major players in the industry."}],"model":"gpt-4o","tool_choice":"auto","tools":[{"type":"function","function":{"name":"web_search","description":"Search
the web for information on a given topic.\n\nArgs:\n query: The search query
to look up.\n\nReturns:\n Search results as a string.","strict":true,"parameters":{"properties":{"query":{"title":"Query","type":"string"}},"required":["query"],"type":"object","additionalProperties":false}}},{"type":"function","function":{"name":"read_website","description":"Read
and extract content from a website URL.\n\nArgs:\n url: The URL of the website
to read.\n\nReturns:\n The extracted content from the website.","strict":true,"parameters":{"properties":{"url":{"title":"Url","type":"string"}},"required":["url"],"type":"object","additionalProperties":false}}},{"type":"function","function":{"name":"generate_report","description":"Generate
a structured report based on research findings.\n\nArgs:\n title: The title
of the report.\n findings: The research findings to include.\n\nReturns:\n A
formatted report string.","strict":true,"parameters":{"properties":{"title":{"title":"Title","type":"string"},"findings":{"title":"Findings","type":"string"}},"required":["title","findings"],"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:
- '3811'
content-type:
- application/json
cookie:
- COOKIE-XXX
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-D5Fu95gX9R1zxpiJUa1wSOzIGA9CL\",\n \"object\":
\"chat.completion\",\n \"created\": 1770145149,\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_QjEKbvT6OnKkCOTvwTu0TmAK\",\n \"type\":
\"function\",\n \"function\": {\n \"name\": \"generate_report\",\n
\ \"arguments\": \"{\\\"title\\\":\\\"Current State of the AI
Agent Market 2023\\\",\\\"findings\\\":\\\"1. Market Size: The AI agent market
is currently valued at $50 billion.\\\\n2. Growth Rate: The industry is experiencing
a growth rate of 15% year-over-year.\\\\n3. Major Players: Significant companies
in this space include tech giants and specialized AI startups.\\\\n4. Market
Trends: The demand for AI agents is being driven by improvements in machine
learning algorithms and increasing adoption in customer service and automation
processes.\\\\n5. Competitive Landscape: The market is competitive with ongoing
innovation and investment in developing more advanced AI capabilities.\\\\n6.
Future Prospects: Continued growth is expected as businesses further integrate
AI agents into their operations for efficiency gains and customer engagement.\\\"}\"\n
\ }\n }\n ],\n \"refusal\": null,\n \"annotations\":
[]\n },\n \"logprobs\": null,\n \"finish_reason\": \"tool_calls\"\n
\ }\n ],\n \"usage\": {\n \"prompt_tokens\": 587,\n \"completion_tokens\":
163,\n \"total_tokens\": 750,\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_fa7f5b168b\"\n}\n"
headers:
CF-RAY:
- CF-RAY-XXX
Connection:
- keep-alive
Content-Type:
- application/json
Date:
- Tue, 03 Feb 2026 18:59:12 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:
- '3444'
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 Research Analyst. An experienced
analyst skilled at gathering information and synthesizing findings into actionable
insights.\nYour personal goal is: Conduct thorough research and produce insightful
reports"},{"role":"user","content":"\nCurrent Task: Research the current state
of the AI agent market:\n1. Search for recent information about AI agents and
their market trends\n2. Read detailed content from a relevant industry source\n3.
Generate a brief report summarizing the key findings\n\nUse the available tools
for each step."},{"role":"assistant","content":null,"tool_calls":[{"id":"call_QlnPEA94TbaFA83eRDhOHXRY","type":"function","function":{"name":"web_search","arguments":"{\"query\":\"current
state of AI agent market 2023\"}"}}]},{"role":"tool","tool_call_id":"call_QlnPEA94TbaFA83eRDhOHXRY","name":"web_search","content":"Search
results for ''current state of AI agent market 2023'': Found 3 relevant articles
about the topic including market analysis, competitor data, and industry trends."},{"role":"assistant","content":null,"tool_calls":[{"id":"call_sOaxpAdq5dvpRhUJMAct2oNP","type":"function","function":{"name":"read_website","arguments":"{\"url\":
\"https://www.example.com/ai-agent-market-analysis-2023\"}"}},{"id":"call_1GRSbggp4SYHg5WqAUQx5Dce","type":"function","function":{"name":"read_website","arguments":"{\"url\":
\"https://www.example.com/ai-agent-competitor-data-2023\"}"}},{"id":"call_43s9ebATowN3hA5piPjL2z5N","type":"function","function":{"name":"read_website","arguments":"{\"url\":
\"https://www.example.com/ai-agent-industry-trends-2023\"}"}}]},{"role":"tool","tool_call_id":"call_sOaxpAdq5dvpRhUJMAct2oNP","name":"read_website","content":"Content
from https://www.example.com/ai-agent-market-analysis-2023: This article discusses
key insights about the topic including market size ($50B), growth rate (15%
YoY), and major players in the industry."},{"role":"tool","tool_call_id":"call_1GRSbggp4SYHg5WqAUQx5Dce","name":"read_website","content":"Content
from https://www.example.com/ai-agent-competitor-data-2023: This article discusses
key insights about the topic including market size ($50B), growth rate (15%
YoY), and major players in the industry."},{"role":"tool","tool_call_id":"call_43s9ebATowN3hA5piPjL2z5N","name":"read_website","content":"Content
from https://www.example.com/ai-agent-industry-trends-2023: This article discusses
key insights about the topic including market size ($50B), growth rate (15%
YoY), and major players in the industry."},{"role":"assistant","content":null,"tool_calls":[{"id":"call_QjEKbvT6OnKkCOTvwTu0TmAK","type":"function","function":{"name":"generate_report","arguments":"{\"title\":\"Current
State of the AI Agent Market 2023\",\"findings\":\"1. Market Size: The AI agent
market is currently valued at $50 billion.\\n2. Growth Rate: The industry is
experiencing a growth rate of 15% year-over-year.\\n3. Major Players: Significant
companies in this space include tech giants and specialized AI startups.\\n4.
Market Trends: The demand for AI agents is being driven by improvements in machine
learning algorithms and increasing adoption in customer service and automation
processes.\\n5. Competitive Landscape: The market is competitive with ongoing
innovation and investment in developing more advanced AI capabilities.\\n6.
Future Prospects: Continued growth is expected as businesses further integrate
AI agents into their operations for efficiency gains and customer engagement.\"}"}}]},{"role":"tool","tool_call_id":"call_QjEKbvT6OnKkCOTvwTu0TmAK","name":"generate_report","content":"#
Current State of the AI Agent Market 2023\n\n## Executive Summary\n1. Market
Size: The AI agent market is currently valued at $50 billion.\n2. Growth Rate:
The industry is experiencing a growth rate of 15% year-over-year.\n3. Major
Players: Significant companies in this space include tech giants and specialized
AI startups.\n4. Market Trends: The demand for AI agents is being driven by
improvements in machine learning algorithms and increasing adoption in customer
service and automation processes.\n5. Competitive Landscape: The market is competitive
with ongoing innovation and investment in developing more advanced AI capabilities.\n6.
Future Prospects: Continued growth is expected as businesses further integrate
AI agents into their operations for efficiency gains and customer engagement.\n\n##
Conclusion\nBased on the analysis, the market shows strong growth potential."}],"model":"gpt-4o","tool_choice":"auto","tools":[{"type":"function","function":{"name":"web_search","description":"Search
the web for information on a given topic.\n\nArgs:\n query: The search query
to look up.\n\nReturns:\n Search results as a string.","strict":true,"parameters":{"properties":{"query":{"title":"Query","type":"string"}},"required":["query"],"type":"object","additionalProperties":false}}},{"type":"function","function":{"name":"read_website","description":"Read
and extract content from a website URL.\n\nArgs:\n url: The URL of the website
to read.\n\nReturns:\n The extracted content from the website.","strict":true,"parameters":{"properties":{"url":{"title":"Url","type":"string"}},"required":["url"],"type":"object","additionalProperties":false}}},{"type":"function","function":{"name":"generate_report","description":"Generate
a structured report based on research findings.\n\nArgs:\n title: The title
of the report.\n findings: The research findings to include.\n\nReturns:\n A
formatted report string.","strict":true,"parameters":{"properties":{"title":{"title":"Title","type":"string"},"findings":{"title":"Findings","type":"string"}},"required":["title","findings"],"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:
- '5771'
content-type:
- application/json
cookie:
- COOKIE-XXX
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-D5FuCTJhAII96iBV05ECT71cV6QmJ\",\n \"object\":
\"chat.completion\",\n \"created\": 1770145152,\n \"model\": \"gpt-4o-2024-08-06\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"The research on the current state of
the AI agent market indicates a robust and rapidly growing industry. Here\u2019s
a summary of the findings:\\n\\n1. **Market Size**: The AI agent market is
currently valued at $50 billion.\\n2. **Growth Rate**: It is experiencing
a significant growth rate of 15% year-over-year.\\n3. **Major Players**: The
market is dominated by tech giants and specialized AI startups.\\n4. **Market
Trends**: The increasing adoption of machine learning algorithms and the integration
of AI in customer service and automation are key drivers.\\n5. **Competitive
Landscape**: There is substantial competition and continuous innovation in
AI capabilities.\\n6. **Future Prospects**: The sector is expected to keep
growing as businesses increasingly use AI agents for efficiency and improved
customer engagement.\\n\\nThis analysis highlights significant opportunities
in the AI agent sector, underlining its importance in future technological
advancements.\",\n \"refusal\": null,\n \"annotations\": []\n
\ },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n
\ ],\n \"usage\": {\n \"prompt_tokens\": 920,\n \"completion_tokens\":
182,\n \"total_tokens\": 1102,\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_fa7f5b168b\"\n}\n"
headers:
CF-RAY:
- CF-RAY-XXX
Connection:
- keep-alive
Content-Type:
- application/json
Date:
- Tue, 03 Feb 2026 18:59:16 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:
- '3456'
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
version: 1

389
lib/crewai/tests/utilities/test_planning_types.py Normal file
View File

@@ -0,0 +1,389 @@
"""Tests for planning types (PlanStep, TodoItem, TodoList)."""
import pytest
from uuid import UUID
from crewai.utilities.planning_types import (
PlanStep,
TodoItem,
TodoList,
TodoStatus,
)
class TestPlanStep:
"""Tests for the PlanStep model."""
def test_plan_step_with_required_fields(self):
"""Test PlanStep creation with only required fields."""
step = PlanStep(
step_number=1,
description="Research the topic",
)
assert step.step_number == 1
assert step.description == "Research the topic"
assert step.tool_to_use is None
assert step.depends_on == []
def test_plan_step_with_all_fields(self):
"""Test PlanStep creation with all fields."""
step = PlanStep(
step_number=2,
description="Search for information",
tool_to_use="search_tool",
depends_on=[1],
)
assert step.step_number == 2
assert step.description == "Search for information"
assert step.tool_to_use == "search_tool"
assert step.depends_on == [1]
def test_plan_step_with_multiple_dependencies(self):
"""Test PlanStep with multiple dependencies."""
step = PlanStep(
step_number=4,
description="Synthesize results",
depends_on=[1, 2, 3],
)
assert step.depends_on == [1, 2, 3]
def test_plan_step_requires_step_number(self):
"""Test that step_number is required."""
with pytest.raises(ValueError):
PlanStep(description="Missing step number")
def test_plan_step_requires_description(self):
"""Test that description is required."""
with pytest.raises(ValueError):
PlanStep(step_number=1)
def test_plan_step_serialization(self):
"""Test PlanStep can be serialized to dict."""
step = PlanStep(
step_number=1,
description="Test step",
tool_to_use="test_tool",
depends_on=[],
)
data = step.model_dump()
assert data["step_number"] == 1
assert data["description"] == "Test step"
assert data["tool_to_use"] == "test_tool"
assert data["depends_on"] == []
class TestTodoItem:
"""Tests for the TodoItem model."""
def test_todo_item_with_required_fields(self):
"""Test TodoItem creation with only required fields."""
todo = TodoItem(
step_number=1,
description="First task",
)
assert todo.step_number == 1
assert todo.description == "First task"
assert todo.status == "pending"
assert todo.tool_to_use is None
assert todo.depends_on == []
assert todo.result is None
# ID should be auto-generated
assert todo.id is not None
# Verify it's a valid UUID
UUID(todo.id)
def test_todo_item_with_all_fields(self):
"""Test TodoItem creation with all fields."""
todo = TodoItem(
id="custom-id-123",
step_number=2,
description="Second task",
tool_to_use="search_tool",
status="running",
depends_on=[1],
result="Task completed",
)
assert todo.id == "custom-id-123"
assert todo.step_number == 2
assert todo.description == "Second task"
assert todo.tool_to_use == "search_tool"
assert todo.status == "running"
assert todo.depends_on == [1]
assert todo.result == "Task completed"
def test_todo_item_status_values(self):
"""Test all valid status values."""
for status in ["pending", "running", "completed"]:
todo = TodoItem(
step_number=1,
description="Test",
status=status,
)
assert todo.status == status
def test_todo_item_auto_generates_unique_ids(self):
"""Test that each TodoItem gets a unique auto-generated ID."""
todo1 = TodoItem(step_number=1, description="Task 1")
todo2 = TodoItem(step_number=2, description="Task 2")
assert todo1.id != todo2.id
def test_todo_item_serialization(self):
"""Test TodoItem can be serialized to dict."""
todo = TodoItem(
step_number=1,
description="Test task",
status="pending",
)
data = todo.model_dump()
assert "id" in data
assert data["step_number"] == 1
assert data["description"] == "Test task"
assert data["status"] == "pending"
class TestTodoList:
"""Tests for the TodoList model."""
@pytest.fixture
def empty_todo_list(self):
"""Create an empty TodoList."""
return TodoList()
@pytest.fixture
def sample_todo_list(self):
"""Create a TodoList with sample items."""
return TodoList(
items=[
TodoItem(step_number=1, description="Step 1", status="completed"),
TodoItem(step_number=2, description="Step 2", status="running"),
TodoItem(step_number=3, description="Step 3", status="pending"),
TodoItem(step_number=4, description="Step 4", status="pending"),
]
)
def test_empty_todo_list(self, empty_todo_list):
"""Test empty TodoList properties."""
assert empty_todo_list.items == []
assert empty_todo_list.current_todo is None
assert empty_todo_list.next_pending is None
assert empty_todo_list.is_complete is False
assert empty_todo_list.pending_count == 0
assert empty_todo_list.completed_count == 0
def test_current_todo_property(self, sample_todo_list):
"""Test current_todo returns the running item."""
current = sample_todo_list.current_todo
assert current is not None
assert current.step_number == 2
assert current.status == "running"
def test_current_todo_returns_none_when_no_running(self):
"""Test current_todo returns None when no running items."""
todo_list = TodoList(
items=[
TodoItem(step_number=1, description="Step 1", status="completed"),
TodoItem(step_number=2, description="Step 2", status="pending"),
]
)
assert todo_list.current_todo is None
def test_next_pending_property(self, sample_todo_list):
"""Test next_pending returns the first pending item."""
next_item = sample_todo_list.next_pending
assert next_item is not None
assert next_item.step_number == 3
assert next_item.status == "pending"
def test_next_pending_returns_none_when_no_pending(self):
"""Test next_pending returns None when no pending items."""
todo_list = TodoList(
items=[
TodoItem(step_number=1, description="Step 1", status="completed"),
TodoItem(step_number=2, description="Step 2", status="completed"),
]
)
assert todo_list.next_pending is None
def test_is_complete_property_when_complete(self):
"""Test is_complete returns True when all items completed."""
todo_list = TodoList(
items=[
TodoItem(step_number=1, description="Step 1", status="completed"),
TodoItem(step_number=2, description="Step 2", status="completed"),
]
)
assert todo_list.is_complete is True
def test_is_complete_property_when_not_complete(self, sample_todo_list):
"""Test is_complete returns False when items are pending."""
assert sample_todo_list.is_complete is False
def test_is_complete_false_for_empty_list(self, empty_todo_list):
"""Test is_complete returns False for empty list."""
assert empty_todo_list.is_complete is False
def test_pending_count(self, sample_todo_list):
"""Test pending_count returns correct count."""
assert sample_todo_list.pending_count == 2
def test_completed_count(self, sample_todo_list):
"""Test completed_count returns correct count."""
assert sample_todo_list.completed_count == 1
def test_get_by_step_number(self, sample_todo_list):
"""Test get_by_step_number returns correct item."""
item = sample_todo_list.get_by_step_number(3)
assert item is not None
assert item.step_number == 3
assert item.description == "Step 3"
def test_get_by_step_number_returns_none_for_missing(self, sample_todo_list):
"""Test get_by_step_number returns None for non-existent step."""
item = sample_todo_list.get_by_step_number(99)
assert item is None
def test_mark_running(self, sample_todo_list):
"""Test mark_running changes status correctly."""
sample_todo_list.mark_running(3)
item = sample_todo_list.get_by_step_number(3)
assert item.status == "running"
def test_mark_running_does_nothing_for_missing(self, sample_todo_list):
"""Test mark_running handles missing step gracefully."""
# Should not raise an error
sample_todo_list.mark_running(99)
def test_mark_completed(self, sample_todo_list):
"""Test mark_completed changes status correctly."""
sample_todo_list.mark_completed(3)
item = sample_todo_list.get_by_step_number(3)
assert item.status == "completed"
assert item.result is None
def test_mark_completed_with_result(self, sample_todo_list):
"""Test mark_completed with result."""
sample_todo_list.mark_completed(3, result="Task output")
item = sample_todo_list.get_by_step_number(3)
assert item.status == "completed"
assert item.result == "Task output"
def test_mark_completed_does_nothing_for_missing(self, sample_todo_list):
"""Test mark_completed handles missing step gracefully."""
# Should not raise an error
sample_todo_list.mark_completed(99, result="Some result")
def test_todo_list_workflow(self):
"""Test a complete workflow through TodoList."""
# Create a todo list with 3 items
todo_list = TodoList(
items=[
TodoItem(
step_number=1,
description="Research",
tool_to_use="search_tool",
),
TodoItem(
step_number=2,
description="Analyze",
depends_on=[1],
),
TodoItem(
step_number=3,
description="Report",
depends_on=[1, 2],
),
]
)
# Initial state
assert todo_list.pending_count == 3
assert todo_list.completed_count == 0
assert todo_list.is_complete is False
# Start first task
todo_list.mark_running(1)
assert todo_list.current_todo.step_number == 1
assert todo_list.next_pending.step_number == 2
# Complete first task
todo_list.mark_completed(1, result="Research done")
assert todo_list.current_todo is None
assert todo_list.completed_count == 1
# Start and complete second task
todo_list.mark_running(2)
todo_list.mark_completed(2, result="Analysis complete")
assert todo_list.completed_count == 2
# Start and complete third task
todo_list.mark_running(3)
todo_list.mark_completed(3, result="Report generated")
# Final state
assert todo_list.is_complete is True
assert todo_list.pending_count == 0
assert todo_list.completed_count == 3
assert todo_list.current_todo is None
assert todo_list.next_pending is None
class TestTodoFromPlanStep:
"""Tests for converting PlanStep to TodoItem."""
def test_convert_plan_step_to_todo_item(self):
"""Test converting a PlanStep to TodoItem."""
step = PlanStep(
step_number=1,
description="Search for information",
tool_to_use="search_tool",
depends_on=[],
)
todo = TodoItem(
step_number=step.step_number,
description=step.description,
tool_to_use=step.tool_to_use,
depends_on=step.depends_on,
status="pending",
)
assert todo.step_number == step.step_number
assert todo.description == step.description
assert todo.tool_to_use == step.tool_to_use
assert todo.depends_on == step.depends_on
assert todo.status == "pending"
def test_convert_multiple_plan_steps_to_todo_list(self):
"""Test converting multiple PlanSteps to a TodoList."""
steps = [
PlanStep(step_number=1, description="Step 1", tool_to_use="tool1"),
PlanStep(step_number=2, description="Step 2", depends_on=[1]),
PlanStep(step_number=3, description="Step 3", depends_on=[1, 2]),
]
todos = []
for step in steps:
todo = TodoItem(
step_number=step.step_number,
description=step.description,
tool_to_use=step.tool_to_use,
depends_on=step.depends_on,
status="pending",
)
todos.append(todo)
todo_list = TodoList(items=todos)
assert len(todo_list.items) == 3
assert todo_list.pending_count == 3
assert todo_list.items[0].tool_to_use == "tool1"
assert todo_list.items[1].depends_on == [1]
assert todo_list.items[2].depends_on == [1, 2]

698
lib/crewai/tests/utilities/test_structured_planning.py Normal file
View File

@@ -0,0 +1,698 @@
"""Tests for structured planning with steps and todo generation.
These tests verify that the planning system correctly generates structured
PlanStep objects and converts them to TodoItems across different LLM providers.
"""
import json
import os
from unittest.mock import MagicMock, Mock, patch
import pytest
from crewai import Agent, PlanningConfig, Task
from crewai.llm import LLM
from crewai.utilities.planning_types import PlanStep, TodoItem, TodoList
from crewai.utilities.reasoning_handler import (
FUNCTION_SCHEMA,
AgentReasoning,
ReasoningPlan,
)
class TestFunctionSchema:
"""Tests for the FUNCTION_SCHEMA used in structured planning."""
def test_schema_has_required_structure(self):
"""Test that FUNCTION_SCHEMA has the correct structure."""
assert FUNCTION_SCHEMA["type"] == "function"
assert "function" in FUNCTION_SCHEMA
assert FUNCTION_SCHEMA["function"]["name"] == "create_reasoning_plan"
def test_schema_parameters_structure(self):
"""Test that parameters have correct structure."""
params = FUNCTION_SCHEMA["function"]["parameters"]
assert params["type"] == "object"
assert "properties" in params
assert "required" in params
def test_schema_has_plan_property(self):
"""Test that schema includes plan property."""
props = FUNCTION_SCHEMA["function"]["parameters"]["properties"]
assert "plan" in props
assert props["plan"]["type"] == "string"
def test_schema_has_steps_property(self):
"""Test that schema includes steps array property."""
props = FUNCTION_SCHEMA["function"]["parameters"]["properties"]
assert "steps" in props
assert props["steps"]["type"] == "array"
def test_schema_steps_items_structure(self):
"""Test that steps items have correct structure."""
items = FUNCTION_SCHEMA["function"]["parameters"]["properties"]["steps"]["items"]
assert items["type"] == "object"
assert "properties" in items
assert "required" in items
assert "additionalProperties" in items
assert items["additionalProperties"] is False
def test_schema_step_properties(self):
"""Test that step items have all required properties."""
step_props = FUNCTION_SCHEMA["function"]["parameters"]["properties"]["steps"]["items"]["properties"]
assert "step_number" in step_props
assert step_props["step_number"]["type"] == "integer"
assert "description" in step_props
assert step_props["description"]["type"] == "string"
assert "tool_to_use" in step_props
# tool_to_use should be nullable
assert step_props["tool_to_use"]["type"] == ["string", "null"]
assert "depends_on" in step_props
assert step_props["depends_on"]["type"] == "array"
def test_schema_step_required_fields(self):
"""Test that step required fields are correct."""
required = FUNCTION_SCHEMA["function"]["parameters"]["properties"]["steps"]["items"]["required"]
assert "step_number" in required
assert "description" in required
assert "tool_to_use" in required
assert "depends_on" in required
def test_schema_has_ready_property(self):
"""Test that schema includes ready property."""
props = FUNCTION_SCHEMA["function"]["parameters"]["properties"]
assert "ready" in props
assert props["ready"]["type"] == "boolean"
def test_schema_top_level_required(self):
"""Test that top-level required fields are correct."""
required = FUNCTION_SCHEMA["function"]["parameters"]["required"]
assert "plan" in required
assert "steps" in required
assert "ready" in required
def test_schema_top_level_additional_properties(self):
"""Test that additionalProperties is False at top level."""
params = FUNCTION_SCHEMA["function"]["parameters"]
assert params["additionalProperties"] is False
class TestReasoningPlan:
"""Tests for the ReasoningPlan model with structured steps."""
def test_reasoning_plan_with_empty_steps(self):
"""Test ReasoningPlan can be created with empty steps."""
plan = ReasoningPlan(
plan="Simple plan",
steps=[],
ready=True,
)
assert plan.plan == "Simple plan"
assert plan.steps == []
assert plan.ready is True
def test_reasoning_plan_with_steps(self):
"""Test ReasoningPlan with structured steps."""
steps = [
PlanStep(step_number=1, description="First step", tool_to_use="tool1"),
PlanStep(step_number=2, description="Second step", depends_on=[1]),
]
plan = ReasoningPlan(
plan="Multi-step plan",
steps=steps,
ready=True,
)
assert plan.plan == "Multi-step plan"
assert len(plan.steps) == 2
assert plan.steps[0].step_number == 1
assert plan.steps[1].depends_on == [1]
class TestAgentReasoningWithMockedLLM:
"""Tests for AgentReasoning with mocked LLM responses."""
@pytest.fixture
def mock_agent(self):
"""Create a mock agent for testing."""
agent = MagicMock()
agent.role = "Test Agent"
agent.goal = "Test goal"
agent.backstory = "Test backstory"
agent.verbose = False
agent.planning_config = PlanningConfig()
agent.i18n = MagicMock()
agent.i18n.retrieve.return_value = "Test prompt: {description}"
# Mock the llm attribute
agent.llm = MagicMock()
agent.llm.supports_function_calling.return_value = True
return agent
def test_parse_steps_from_function_response(self, mock_agent):
"""Test that steps are correctly parsed from LLM function response."""
# Mock the LLM response with structured steps
mock_response = json.dumps({
"plan": "Research and analyze",
"steps": [
{
"step_number": 1,
"description": "Search for information",
"tool_to_use": "search_tool",
"depends_on": [],
},
{
"step_number": 2,
"description": "Analyze results",
"tool_to_use": None,
"depends_on": [1],
},
],
"ready": True,
})
mock_agent.llm.call.return_value = mock_response
handler = AgentReasoning(
agent=mock_agent,
task=None,
description="Test task",
expected_output="Test output",
)
# Call the function parsing method
plan, steps, ready = handler._call_with_function(
prompt="Test prompt",
plan_type="create_plan",
)
assert plan == "Research and analyze"
assert len(steps) == 2
assert steps[0].step_number == 1
assert steps[0].tool_to_use == "search_tool"
assert steps[1].depends_on == [1]
assert ready is True
def test_parse_steps_handles_missing_optional_fields(self, mock_agent):
"""Test that missing optional fields are handled correctly."""
mock_response = json.dumps({
"plan": "Simple plan",
"steps": [
{
"step_number": 1,
"description": "Do something",
"tool_to_use": None,
"depends_on": [],
},
],
"ready": True,
})
mock_agent.llm.call.return_value = mock_response
handler = AgentReasoning(
agent=mock_agent,
task=None,
description="Test task",
expected_output="Test output",
)
plan, steps, ready = handler._call_with_function(
prompt="Test prompt",
plan_type="create_plan",
)
assert len(steps) == 1
assert steps[0].tool_to_use is None
assert steps[0].depends_on == []
def test_parse_steps_with_missing_fields_uses_defaults(self, mock_agent):
"""Test that steps with missing fields get default values."""
mock_response = json.dumps({
"plan": "Plan with step missing fields",
"steps": [
{"step_number": 1, "description": "Valid step", "tool_to_use": None, "depends_on": []},
{"step_number": 2}, # Missing description, tool_to_use, depends_on
{"step_number": 3, "description": "Another valid", "tool_to_use": None, "depends_on": []},
],
"ready": True,
})
mock_agent.llm.call.return_value = mock_response
handler = AgentReasoning(
agent=mock_agent,
task=None,
description="Test task",
expected_output="Test output",
)
plan, steps, ready = handler._call_with_function(
prompt="Test prompt",
plan_type="create_plan",
)
# All 3 steps should be parsed, with defaults for missing fields
assert len(steps) == 3
assert steps[0].step_number == 1
assert steps[0].description == "Valid step"
assert steps[1].step_number == 2
assert steps[1].description == "" # Default value
assert steps[2].step_number == 3
class TestTodoCreationFromPlan:
"""Tests for converting plan steps to todo items."""
def test_create_todos_from_plan_steps(self):
"""Test creating TodoList from PlanSteps."""
steps = [
PlanStep(
step_number=1,
description="Research competitors",
tool_to_use="search_tool",
depends_on=[],
),
PlanStep(
step_number=2,
description="Analyze data",
tool_to_use=None,
depends_on=[1],
),
PlanStep(
step_number=3,
description="Generate report",
tool_to_use="write_tool",
depends_on=[1, 2],
),
]
# Convert steps to todos (mirroring agent_executor._create_todos_from_plan)
todos = []
for step in steps:
todo = TodoItem(
step_number=step.step_number,
description=step.description,
tool_to_use=step.tool_to_use,
depends_on=step.depends_on,
status="pending",
)
todos.append(todo)
todo_list = TodoList(items=todos)
assert len(todo_list.items) == 3
assert todo_list.pending_count == 3
assert todo_list.completed_count == 0
# Verify todo properties match step properties
assert todo_list.items[0].description == "Research competitors"
assert todo_list.items[0].tool_to_use == "search_tool"
assert todo_list.items[1].depends_on == [1]
assert todo_list.items[2].depends_on == [1, 2]
# =============================================================================
# Provider-Specific Integration Tests (VCR recorded)
# =============================================================================
# Common test tools used across provider tests
def create_research_tools():
"""Create research tools for testing structured planning."""
from crewai.tools import tool
@tool
def web_search(query: str) -> str:
"""Search the web for information on a given topic.
Args:
query: The search query to look up.
Returns:
Search results as a string.
"""
# Simulated search results for testing
return f"Search results for '{query}': Found 3 relevant articles about the topic including market analysis, competitor data, and industry trends."
@tool
def read_website(url: str) -> str:
"""Read and extract content from a website URL.
Args:
url: The URL of the website to read.
Returns:
The extracted content from the website.
"""
# Simulated website content for testing
return f"Content from {url}: This article discusses key insights about the topic including market size ($50B), growth rate (15% YoY), and major players in the industry."
@tool
def generate_report(title: str, findings: str) -> str:
"""Generate a structured report based on research findings.
Args:
title: The title of the report.
findings: The research findings to include.
Returns:
A formatted report string.
"""
return f"# {title}\n\n## Executive Summary\n{findings}\n\n## Conclusion\nBased on the analysis, the market shows strong growth potential."
return web_search, read_website, generate_report
RESEARCH_TASK = """Research the current state of the AI agent market:
1. Search for recent information about AI agents and their market trends
2. Read detailed content from a relevant industry source
3. Generate a brief report summarizing the key findings
Use the available tools for each step."""
class TestOpenAIStructuredPlanning:
"""Integration tests for OpenAI structured planning with research workflow."""
@pytest.mark.vcr()
def test_openai_research_workflow_generates_steps(self):
"""Test that OpenAI generates structured plan steps for a research task."""
web_search, read_website, generate_report = create_research_tools()
llm = LLM(model="gpt-4o")
agent = Agent(
role="Research Analyst",
goal="Conduct thorough research and produce insightful reports",
backstory="An experienced analyst skilled at gathering information and synthesizing findings into actionable insights.",
llm=llm,
tools=[web_search, read_website, generate_report],
planning_config=PlanningConfig(max_attempts=1),
verbose=False,
)
result = agent.kickoff(RESEARCH_TASK)
# Verify result exists
assert result is not None
assert result.raw is not None
# The result should contain some report-like content
assert len(str(result.raw)) > 50
class TestAnthropicStructuredPlanning:
"""Integration tests for Anthropic structured planning with research workflow."""
@pytest.fixture(autouse=True)
def mock_anthropic_api_key(self):
"""Mock API key if not set."""
if "ANTHROPIC_API_KEY" not in os.environ:
with patch.dict(os.environ, {"ANTHROPIC_API_KEY": "test-key"}):
yield
else:
yield
@pytest.mark.vcr()
def test_anthropic_research_workflow_generates_steps(self):
"""Test that Anthropic generates structured plan steps for a research task."""
web_search, read_website, generate_report = create_research_tools()
llm = LLM(model="anthropic/claude-sonnet-4-20250514")
agent = Agent(
role="Research Analyst",
goal="Conduct thorough research and produce insightful reports",
backstory="An experienced analyst skilled at gathering information and synthesizing findings into actionable insights.",
llm=llm,
tools=[web_search, read_website, generate_report],
planning_config=PlanningConfig(max_attempts=1),
verbose=False,
)
result = agent.kickoff(RESEARCH_TASK)
# Verify result exists
assert result is not None
assert result.raw is not None
# The result should contain some report-like content
assert len(str(result.raw)) > 50
class TestGeminiStructuredPlanning:
"""Integration tests for Google Gemini structured planning with research workflow."""
@pytest.fixture(autouse=True)
def mock_google_api_key(self):
"""Mock API key if not set."""
if "GOOGLE_API_KEY" not in os.environ and "GEMINI_API_KEY" not in os.environ:
with patch.dict(os.environ, {"GOOGLE_API_KEY": "test-key"}):
yield
else:
yield
@pytest.mark.vcr()
def test_gemini_research_workflow_generates_steps(self):
"""Test that Gemini generates structured plan steps for a research task."""
web_search, read_website, generate_report = create_research_tools()
llm = LLM(model="gemini/gemini-2.5-flash")
agent = Agent(
role="Research Analyst",
goal="Conduct thorough research and produce insightful reports",
backstory="An experienced analyst skilled at gathering information and synthesizing findings into actionable insights.",
llm=llm,
tools=[web_search, read_website, generate_report],
planning_config=PlanningConfig(max_attempts=1),
verbose=False,
)
result = agent.kickoff(RESEARCH_TASK)
# Verify result exists
assert result is not None
assert result.raw is not None
# The result should contain some report-like content
assert len(str(result.raw)) > 50
class TestAzureStructuredPlanning:
"""Integration tests for Azure OpenAI structured planning with research workflow."""
@pytest.fixture(autouse=True)
def mock_azure_credentials(self):
"""Mock Azure credentials for tests."""
if "AZURE_API_KEY" not in os.environ:
with patch.dict(os.environ, {
"AZURE_API_KEY": "test-key",
"AZURE_ENDPOINT": "https://test.openai.azure.com"
}):
yield
else:
yield
@pytest.mark.vcr()
def test_azure_research_workflow_generates_steps(self):
"""Test that Azure OpenAI generates structured plan steps for a research task."""
web_search, read_website, generate_report = create_research_tools()
llm = LLM(model="azure/gpt-4o")
agent = Agent(
role="Research Analyst",
goal="Conduct thorough research and produce insightful reports",
backstory="An experienced analyst skilled at gathering information and synthesizing findings into actionable insights.",
llm=llm,
tools=[web_search, read_website, generate_report],
planning_config=PlanningConfig(max_attempts=1),
verbose=False,
)
result = agent.kickoff(RESEARCH_TASK)
# Verify result exists
assert result is not None
assert result.raw is not None
# The result should contain some report-like content
assert len(str(result.raw)) > 50
# =============================================================================
# Unit Tests with Mocked LLM Providers
# =============================================================================
class TestStructuredPlanningWithMockedProviders:
"""Unit tests with mocked LLM providers for faster execution."""
def _create_mock_plan_response(self, steps_data):
"""Helper to create mock plan response."""
return json.dumps({
"plan": "Test plan",
"steps": steps_data,
"ready": True,
})
def test_openai_mock_structured_response(self):
"""Test parsing OpenAI structured response."""
steps_data = [
{"step_number": 1, "description": "Search", "tool_to_use": "search", "depends_on": []},
{"step_number": 2, "description": "Analyze", "tool_to_use": None, "depends_on": [1]},
]
response = self._create_mock_plan_response(steps_data)
parsed = json.loads(response)
assert len(parsed["steps"]) == 2
assert parsed["steps"][0]["tool_to_use"] == "search"
assert parsed["steps"][1]["depends_on"] == [1]
def test_anthropic_mock_structured_response(self):
"""Test parsing Anthropic structured response (same format)."""
steps_data = [
{"step_number": 1, "description": "Research", "tool_to_use": "web_search", "depends_on": []},
{"step_number": 2, "description": "Summarize", "tool_to_use": None, "depends_on": [1]},
{"step_number": 3, "description": "Report", "tool_to_use": "write_file", "depends_on": [1, 2]},
]
response = self._create_mock_plan_response(steps_data)
parsed = json.loads(response)
assert len(parsed["steps"]) == 3
assert parsed["steps"][2]["depends_on"] == [1, 2]
def test_gemini_mock_structured_response(self):
"""Test parsing Gemini structured response (same format)."""
steps_data = [
{"step_number": 1, "description": "Gather data", "tool_to_use": "data_tool", "depends_on": []},
{"step_number": 2, "description": "Process", "tool_to_use": None, "depends_on": [1]},
]
response = self._create_mock_plan_response(steps_data)
parsed = json.loads(response)
assert len(parsed["steps"]) == 2
assert parsed["ready"] is True
def test_azure_mock_structured_response(self):
"""Test parsing Azure OpenAI structured response (same format as OpenAI)."""
steps_data = [
{"step_number": 1, "description": "Initialize", "tool_to_use": None, "depends_on": []},
{"step_number": 2, "description": "Execute", "tool_to_use": "executor", "depends_on": [1]},
{"step_number": 3, "description": "Finalize", "tool_to_use": None, "depends_on": [1, 2]},
]
response = self._create_mock_plan_response(steps_data)
parsed = json.loads(response)
assert len(parsed["steps"]) == 3
assert parsed["steps"][0]["tool_to_use"] is None
class TestTodoListIntegration:
"""Integration tests for TodoList with plan execution simulation."""
def test_full_plan_execution_workflow(self):
"""Test complete workflow from plan to todos to execution."""
# Simulate plan steps from LLM
plan_steps = [
PlanStep(
step_number=1,
description="Research the topic",
tool_to_use="search_tool",
depends_on=[],
),
PlanStep(
step_number=2,
description="Compile findings",
tool_to_use=None,
depends_on=[1],
),
PlanStep(
step_number=3,
description="Generate summary",
tool_to_use="summarize_tool",
depends_on=[1, 2],
),
]
# Convert to todos (like agent_executor._create_todos_from_plan)
todos = [
TodoItem(
step_number=step.step_number,
description=step.description,
tool_to_use=step.tool_to_use,
depends_on=step.depends_on,
status="pending",
)
for step in plan_steps
]
todo_list = TodoList(items=todos)
# Verify initial state
assert todo_list.pending_count == 3
assert todo_list.is_complete is False
# Simulate execution
for i in range(1, 4):
todo_list.mark_running(i)
assert todo_list.current_todo.step_number == i
todo_list.mark_completed(i, result=f"Step {i} completed")
# Verify final state
assert todo_list.is_complete is True
assert todo_list.completed_count == 3
assert all(item.result is not None for item in todo_list.items)
def test_dependency_aware_execution(self):
"""Test that dependencies are respected in execution order."""
steps = [
PlanStep(step_number=1, description="Base step", depends_on=[]),
PlanStep(step_number=2, description="Depends on 1", depends_on=[1]),
PlanStep(step_number=3, description="Depends on 1", depends_on=[1]),
PlanStep(step_number=4, description="Depends on 2 and 3", depends_on=[2, 3]),
]
todos = [
TodoItem(
step_number=s.step_number,
description=s.description,
depends_on=s.depends_on,
)
for s in steps
]
todo_list = TodoList(items=todos)
# Helper to check if dependencies are satisfied
def can_execute(todo: TodoItem) -> bool:
for dep in todo.depends_on:
dep_todo = todo_list.get_by_step_number(dep)
if dep_todo and dep_todo.status != "completed":
return False
return True
# Step 1 has no dependencies
assert can_execute(todo_list.items[0]) is True
# Steps 2 and 3 depend on 1 (not yet done)
assert can_execute(todo_list.items[1]) is False
assert can_execute(todo_list.items[2]) is False
# Complete step 1
todo_list.mark_completed(1)
# Now steps 2 and 3 can execute
assert can_execute(todo_list.items[1]) is True
assert can_execute(todo_list.items[2]) is True
# Step 4 still can't (depends on 2 and 3)
assert can_execute(todo_list.items[3]) is False
# Complete steps 2 and 3
todo_list.mark_completed(2)
todo_list.mark_completed(3)
# Now step 4 can execute
assert can_execute(todo_list.items[3]) is True