mirror of
https://github.com/crewAIInc/crewAI.git
synced 2026-07-05 15:09:22 +00:00
feat: introduce PlanningConfig for enhanced agent planning capabilities (#4344)
* feat: introduce PlanningConfig for enhanced agent planning capabilities This update adds a new PlanningConfig class to manage agent planning configurations, allowing for customizable planning behavior before task execution. The existing reasoning parameter is deprecated in favor of this new configuration, ensuring backward compatibility while enhancing the planning process. Additionally, the Agent class has been updated to utilize this new configuration, and relevant utility functions have been adjusted accordingly. Tests have been added to validate the new planning functionality and ensure proper integration with existing agent workflows. * dropping redundancy * fix test * revert handle_reasoning here * refactor: update reasoning handling in Agent class This commit modifies the Agent class to conditionally call the handle_reasoning function based on the executor class being used. The legacy CrewAgentExecutor will continue to utilize handle_reasoning, while the new AgentExecutor will manage planning internally. Additionally, the PlanningConfig class has been referenced in the documentation to clarify its role in enabling or disabling planning. Tests have been updated to reflect these changes and ensure proper functionality. * improve planning prompts * matching * refactor: remove default enabled flag from PlanningConfig in Agent class * more cassettes * fix test * refactor: update planning prompt and remove deprecated methods in reasoning handler * improve planning prompt
This commit is contained in:
Lorenze Jay
@@ -4,6 +4,7 @@ import urllib.request
|
||||
import warnings
|
||||
|
||||
from crewai.agent.core import Agent
|
||||
from crewai.agent.planning_config import PlanningConfig
|
||||
from crewai.crew import Crew
|
||||
from crewai.crews.crew_output import CrewOutput
|
||||
from crewai.flow.flow import Flow
|
||||
@@ -80,6 +81,7 @@ __all__ = [
|
||||
"Flow",
|
||||
"Knowledge",
|
||||
"LLMGuardrail",
|
||||
"PlanningConfig",
|
||||
"Process",
|
||||
"Task",
|
||||
"TaskOutput",
|
||||
|
||||
@@ -24,6 +24,7 @@ from pydantic import (
|
||||
)
|
||||
from typing_extensions import Self
|
||||
|
||||
from crewai.agent.planning_config import PlanningConfig
|
||||
from crewai.agent.utils import (
|
||||
ahandle_knowledge_retrieval,
|
||||
apply_training_data,
|
||||
@@ -210,13 +211,23 @@ class Agent(BaseAgent):
|
||||
default="safe",
|
||||
description="Mode for code execution: 'safe' (using Docker) or 'unsafe' (direct execution).",
|
||||
)
|
||||
reasoning: bool = Field(
|
||||
planning_config: PlanningConfig | None = Field(
|
||||
default=None,
|
||||
description="Configuration for agent planning before task execution.",
|
||||
)
|
||||
planning: bool = Field(
|
||||
default=False,
|
||||
description="Whether the agent should reflect and create a plan before executing a task.",
|
||||
)
|
||||
reasoning: bool = Field(
|
||||
default=False,
|
||||
description="[DEPRECATED: Use planning_config instead] Whether the agent should reflect and create a plan before executing a task.",
|
||||
deprecated=True,
|
||||
)
|
||||
max_reasoning_attempts: int | None = Field(
|
||||
default=None,
|
||||
description="Maximum number of reasoning attempts before executing the task. If None, will try until ready.",
|
||||
description="[DEPRECATED: Use planning_config.max_attempts instead] Maximum number of reasoning attempts before executing the task. If None, will try until ready.",
|
||||
deprecated=True,
|
||||
)
|
||||
embedder: EmbedderConfig | None = Field(
|
||||
default=None,
|
||||
@@ -283,8 +294,26 @@ class Agent(BaseAgent):
|
||||
if self.allow_code_execution:
|
||||
self._validate_docker_installation()
|
||||
|
||||
# Handle backward compatibility: convert reasoning=True to planning_config
|
||||
if self.reasoning and self.planning_config is None:
|
||||
import warnings
|
||||
|
||||
warnings.warn(
|
||||
"The 'reasoning' parameter is deprecated. Use 'planning_config=PlanningConfig()' instead.",
|
||||
DeprecationWarning,
|
||||
stacklevel=2,
|
||||
)
|
||||
self.planning_config = PlanningConfig(
|
||||
max_attempts=self.max_reasoning_attempts,
|
||||
)
|
||||
|
||||
return self
|
||||
|
||||
@property
|
||||
def planning_enabled(self) -> bool:
|
||||
"""Check if planning is enabled for this agent."""
|
||||
return self.planning_config is not None or self.planning
|
||||
|
||||
def _setup_agent_executor(self) -> None:
|
||||
if not self.cache_handler:
|
||||
self.cache_handler = CacheHandler()
|
||||
@@ -360,7 +389,11 @@ class Agent(BaseAgent):
|
||||
ValueError: If the max execution time is not a positive integer.
|
||||
RuntimeError: If the agent execution fails for other reasons.
|
||||
"""
|
||||
handle_reasoning(self, task)
|
||||
# Only call handle_reasoning for legacy CrewAgentExecutor
|
||||
# For AgentExecutor, planning is handled in AgentExecutor.generate_plan()
|
||||
if self.executor_class is not AgentExecutor:
|
||||
handle_reasoning(self, task)
|
||||
|
||||
self._inject_date_to_task(task)
|
||||
|
||||
if self.tools_handler:
|
||||
@@ -595,7 +628,10 @@ class Agent(BaseAgent):
|
||||
ValueError: If the max execution time is not a positive integer.
|
||||
RuntimeError: If the agent execution fails for other reasons.
|
||||
"""
|
||||
handle_reasoning(self, task)
|
||||
if self.executor_class is not AgentExecutor:
|
||||
handle_reasoning(
|
||||
self, task
|
||||
) # we need this till CrewAgentExecutor migrates to AgentExecutor
|
||||
self._inject_date_to_task(task)
|
||||
|
||||
if self.tools_handler:
|
||||
|
||||
83
lib/crewai/src/crewai/agent/planning_config.py
Normal file
83
lib/crewai/src/crewai/agent/planning_config.py
Normal file
@@ -0,0 +1,83 @@
|
||||
from __future__ import annotations
|
||||
|
||||
from typing import Any
|
||||
|
||||
from pydantic import BaseModel, Field
|
||||
|
||||
|
||||
class PlanningConfig(BaseModel):
|
||||
"""Configuration for agent planning/reasoning before task execution.
|
||||
|
||||
This allows users to customize the planning behavior including prompts,
|
||||
iteration limits, and the LLM used for planning.
|
||||
|
||||
Note: To disable planning, don't pass a planning_config or set planning=False
|
||||
on the Agent. The presence of a PlanningConfig enables planning.
|
||||
|
||||
Attributes:
|
||||
max_attempts: Maximum number of planning refinement attempts.
|
||||
If None, will continue until the agent indicates readiness.
|
||||
max_steps: Maximum number of steps in the generated plan.
|
||||
system_prompt: Custom system prompt for planning. Uses default if None.
|
||||
plan_prompt: Custom prompt for creating the initial plan.
|
||||
refine_prompt: Custom prompt for refining the plan.
|
||||
llm: LLM to use for planning. Uses agent's LLM if None.
|
||||
|
||||
Example:
|
||||
```python
|
||||
from crewai import Agent
|
||||
from crewai.agent.planning_config import PlanningConfig
|
||||
|
||||
# Simple usage
|
||||
agent = Agent(
|
||||
role="Researcher",
|
||||
goal="Research topics",
|
||||
backstory="Expert researcher",
|
||||
planning_config=PlanningConfig(),
|
||||
)
|
||||
|
||||
# Customized planning
|
||||
agent = Agent(
|
||||
role="Researcher",
|
||||
goal="Research topics",
|
||||
backstory="Expert researcher",
|
||||
planning_config=PlanningConfig(
|
||||
max_attempts=3,
|
||||
max_steps=10,
|
||||
plan_prompt="Create a focused plan for: {description}",
|
||||
llm="gpt-4o-mini", # Use cheaper model for planning
|
||||
),
|
||||
)
|
||||
```
|
||||
"""
|
||||
|
||||
max_attempts: int | None = Field(
|
||||
default=None,
|
||||
description=(
|
||||
"Maximum number of planning refinement attempts. "
|
||||
"If None, will continue until the agent indicates readiness."
|
||||
),
|
||||
)
|
||||
max_steps: int = Field(
|
||||
default=20,
|
||||
description="Maximum number of steps in the generated plan.",
|
||||
ge=1,
|
||||
)
|
||||
system_prompt: str | None = Field(
|
||||
default=None,
|
||||
description="Custom system prompt for planning. Uses default if None.",
|
||||
)
|
||||
plan_prompt: str | None = Field(
|
||||
default=None,
|
||||
description="Custom prompt for creating the initial plan.",
|
||||
)
|
||||
refine_prompt: str | None = Field(
|
||||
default=None,
|
||||
description="Custom prompt for refining the plan.",
|
||||
)
|
||||
llm: str | Any | None = Field(
|
||||
default=None,
|
||||
description="LLM to use for planning. Uses agent's LLM if None.",
|
||||
)
|
||||
|
||||
model_config = {"arbitrary_types_allowed": True}
|
||||
@@ -28,13 +28,20 @@ if TYPE_CHECKING:
|
||||
|
||||
|
||||
def handle_reasoning(agent: Agent, task: Task) -> None:
|
||||
"""Handle the reasoning process for an agent before task execution.
|
||||
"""Handle the reasoning/planning process for an agent before task execution.
|
||||
|
||||
This function checks if planning is enabled for the agent and, if so,
|
||||
creates a plan that gets appended to the task description.
|
||||
|
||||
Note: This function is used by CrewAgentExecutor (legacy path).
|
||||
For AgentExecutor, planning is handled in AgentExecutor.generate_plan().
|
||||
|
||||
Args:
|
||||
agent: The agent performing the task.
|
||||
task: The task to execute.
|
||||
"""
|
||||
if not agent.reasoning:
|
||||
# Check if planning is enabled using the planning_enabled property
|
||||
if not getattr(agent, "planning_enabled", False):
|
||||
return
|
||||
|
||||
try:
|
||||
@@ -43,13 +50,13 @@ def handle_reasoning(agent: Agent, task: Task) -> None:
|
||||
AgentReasoningOutput,
|
||||
)
|
||||
|
||||
reasoning_handler = AgentReasoning(task=task, agent=agent)
|
||||
reasoning_output: AgentReasoningOutput = (
|
||||
reasoning_handler.handle_agent_reasoning()
|
||||
planning_handler = AgentReasoning(agent=agent, task=task)
|
||||
planning_output: AgentReasoningOutput = (
|
||||
planning_handler.handle_agent_reasoning()
|
||||
)
|
||||
task.description += f"\n\nReasoning Plan:\n{reasoning_output.plan.plan}"
|
||||
task.description += f"\n\nPlanning:\n{planning_output.plan.plan}"
|
||||
except Exception as e:
|
||||
agent._logger.log("error", f"Error during reasoning process: {e!s}")
|
||||
agent._logger.log("error", f"Error during planning: {e!s}")
|
||||
|
||||
|
||||
def build_task_prompt_with_schema(task: Task, task_prompt: str, i18n: I18N) -> str:
|
||||
|
||||
@@ -9,7 +9,7 @@ class ReasoningEvent(BaseEvent):
|
||||
type: str
|
||||
attempt: int = 1
|
||||
agent_role: str
|
||||
task_id: str
|
||||
task_id: str | None = None
|
||||
task_name: str | None = None
|
||||
from_task: Any | None = None
|
||||
agent_id: str | None = None
|
||||
|
||||
@@ -94,6 +94,10 @@ class AgentReActState(BaseModel):
|
||||
ask_for_human_input: bool = Field(default=False)
|
||||
use_native_tools: bool = Field(default=False)
|
||||
pending_tool_calls: list[Any] = Field(default_factory=list)
|
||||
plan: str | None = Field(default=None, description="Generated execution plan")
|
||||
plan_ready: bool = Field(
|
||||
default=False, description="Whether agent is ready to execute"
|
||||
)
|
||||
|
||||
|
||||
class AgentExecutor(Flow[AgentReActState], CrewAgentExecutorMixin):
|
||||
@@ -321,6 +325,45 @@ class AgentExecutor(Flow[AgentReActState], CrewAgentExecutorMixin):
|
||||
self._state.iterations = value
|
||||
|
||||
@start()
|
||||
def generate_plan(self) -> None:
|
||||
"""Generate execution plan if planning is enabled.
|
||||
|
||||
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).
|
||||
"""
|
||||
if not getattr(self.agent, "planning_enabled", False):
|
||||
return
|
||||
|
||||
try:
|
||||
from crewai.utilities.reasoning_handler import AgentReasoning
|
||||
|
||||
if self.task:
|
||||
planning_handler = AgentReasoning(agent=self.agent, task=self.task)
|
||||
else:
|
||||
# For kickoff() path - use input text directly, no Task needed
|
||||
input_text = getattr(self, "_kickoff_input", "")
|
||||
planning_handler = AgentReasoning(
|
||||
agent=self.agent,
|
||||
description=input_text or "Complete the requested task",
|
||||
expected_output="Complete the task successfully",
|
||||
)
|
||||
|
||||
output = planning_handler.handle_agent_reasoning()
|
||||
|
||||
self.state.plan = output.plan.plan
|
||||
self.state.plan_ready = output.plan.ready
|
||||
|
||||
# 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:
|
||||
self.task.description += f"\n\nPlanning:\n{self.state.plan}"
|
||||
|
||||
except Exception as e:
|
||||
if hasattr(self.agent, "_logger"):
|
||||
self.agent._logger.log("error", f"Error during planning: {e!s}")
|
||||
|
||||
@listen(generate_plan)
|
||||
def initialize_reasoning(self) -> Literal["initialized"]:
|
||||
"""Initialize the reasoning flow and emit agent start logs."""
|
||||
self._show_start_logs()
|
||||
@@ -991,6 +1034,10 @@ class AgentExecutor(Flow[AgentReActState], CrewAgentExecutorMixin):
|
||||
self.state.is_finished = False
|
||||
self.state.use_native_tools = False
|
||||
self.state.pending_tool_calls = []
|
||||
self.state.plan = None
|
||||
self.state.plan_ready = False
|
||||
|
||||
self._kickoff_input = inputs.get("input", "")
|
||||
|
||||
if "system" in self.prompt:
|
||||
prompt = cast("SystemPromptResult", self.prompt)
|
||||
@@ -1075,6 +1122,10 @@ class AgentExecutor(Flow[AgentReActState], CrewAgentExecutorMixin):
|
||||
self.state.is_finished = False
|
||||
self.state.use_native_tools = False
|
||||
self.state.pending_tool_calls = []
|
||||
self.state.plan = None
|
||||
self.state.plan_ready = False
|
||||
|
||||
self._kickoff_input = inputs.get("input", "")
|
||||
|
||||
if "system" in self.prompt:
|
||||
prompt = cast("SystemPromptResult", self.prompt)
|
||||
|
||||
@@ -58,9 +58,14 @@
|
||||
}
|
||||
},
|
||||
"reasoning": {
|
||||
"initial_plan": "You are {role}, a professional with the following background: {backstory}\n\nYour primary goal is: {goal}\n\nAs {role}, you are creating a strategic plan for a task that requires your expertise and unique perspective.",
|
||||
"refine_plan": "You are {role}, a professional with the following background: {backstory}\n\nYour primary goal is: {goal}\n\nAs {role}, you are refining a strategic plan for a task that requires your expertise and unique perspective.",
|
||||
"create_plan_prompt": "You are {role} with this background: {backstory}\n\nYour primary goal is: {goal}\n\nYou have been assigned the following task:\n{description}\n\nExpected output:\n{expected_output}\n\nAvailable tools: {tools}\n\nBefore executing this task, create a detailed plan that leverages your expertise as {role} and outlines:\n1. Your understanding of the task from your professional perspective\n2. The key steps you'll take to complete it, drawing on your background and skills\n3. How you'll approach any challenges that might arise, considering your expertise\n4. How you'll strategically use the available tools based on your experience, exactly what tools to use and how to use them\n5. The expected outcome and how it aligns with your goal\n\nAfter creating your plan, assess whether you feel ready to execute the task or if you could do better.\nConclude with one of these statements:\n- \"READY: I am ready to execute the task.\"\n- \"NOT READY: I need to refine my plan because [specific reason].\"",
|
||||
"refine_plan_prompt": "You are {role} with this background: {backstory}\n\nYour primary goal is: {goal}\n\nYou created the following plan for this task:\n{current_plan}\n\nHowever, you indicated that you're not ready to execute the task yet.\n\nPlease refine your plan further, drawing on your expertise as {role} to address any gaps or uncertainties. As you refine your plan, be specific about which available tools you will use, how you will use them, and why they are the best choices for each step. Clearly outline your tool usage strategy as part of your improved plan.\n\nAfter refining your plan, assess whether you feel ready to execute the task.\nConclude with one of these statements:\n- \"READY: I am ready to execute the task.\"\n- \"NOT READY: I need to refine my plan further because [specific reason].\""
|
||||
"initial_plan": "You are {role}. Create a focused execution plan using only the essential steps needed.",
|
||||
"refine_plan": "You are {role}. Refine your plan to address the specific gap while keeping it minimal.",
|
||||
"create_plan_prompt": "You are {role}.\n\nTask: {description}\n\nExpected output: {expected_output}\n\nAvailable tools: {tools}\n\nCreate a focused plan with ONLY the essential steps needed. Most tasks require just 2-5 steps. Do NOT pad with unnecessary steps like \"review\", \"verify\", \"document\", or \"finalize\" unless explicitly required.\n\nFor each step, specify the action and which tool to use (if any).\n\nConclude with:\n- \"READY: I am ready to execute the task.\"\n- \"NOT READY: I need to refine my plan because [specific reason].\"",
|
||||
"refine_plan_prompt": "Your plan:\n{current_plan}\n\nYou indicated you're not ready. Address the specific gap while keeping the plan minimal.\n\nConclude with READY or NOT READY."
|
||||
},
|
||||
"planning": {
|
||||
"system_prompt": "You are a strategic planning assistant. Create minimal, effective execution plans. Prefer fewer steps over more.",
|
||||
"create_plan_prompt": "Create a focused execution plan for the following task:\n\n## Task\n{description}\n\n## Expected Output\n{expected_output}\n\n## Available Tools\n{tools}\n\n## Planning Principles\nFocus on WHAT needs to be accomplished, not HOW. Group related actions into logical units. Fewer steps = better. Most tasks need 3-6 steps. Hard limit: {max_steps} steps.\n\n## Step Types (only these are valid):\n1. **Tool Step**: Uses a tool to gather information or take action\n2. **Output Step**: Synthesizes prior results into the final deliverable (usually the last step)\n\n## Rules:\n- Each step must either USE A TOOL or PRODUCE THE FINAL OUTPUT\n- Combine related tool calls: \"Research A, B, and C\" = ONE step, not three\n- Combine all synthesis into ONE final output step\n- NO standalone \"thinking\" steps (review, verify, confirm, refine, analyze) - these happen naturally between steps\n\nFor each step: State the action, specify the tool (if any), and note dependencies.\n\nAfter your plan, state READY or NOT READY.",
|
||||
"refine_plan_prompt": "Your previous plan:\n{current_plan}\n\nYou indicated you weren't ready. Refine your plan to address the specific gap.\n\nKeep the plan minimal - only add steps that directly address the issue.\n\nConclude with READY or NOT READY as before."
|
||||
}
|
||||
}
|
||||
|
||||
@@ -1,10 +1,13 @@
|
||||
"""Handles planning/reasoning for agents before task execution."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import json
|
||||
import logging
|
||||
from typing import Any, Final, Literal, cast
|
||||
from typing import TYPE_CHECKING, Any, Final, Literal, cast
|
||||
|
||||
from pydantic import BaseModel, Field
|
||||
|
||||
from crewai.agent import Agent
|
||||
from crewai.events.event_bus import crewai_event_bus
|
||||
from crewai.events.types.reasoning_events import (
|
||||
AgentReasoningCompletedEvent,
|
||||
@@ -12,10 +15,16 @@ from crewai.events.types.reasoning_events import (
|
||||
AgentReasoningStartedEvent,
|
||||
)
|
||||
from crewai.llm import LLM
|
||||
from crewai.task import Task
|
||||
from crewai.utilities.llm_utils import create_llm
|
||||
from crewai.utilities.string_utils import sanitize_tool_name
|
||||
|
||||
|
||||
if TYPE_CHECKING:
|
||||
from crewai.agent import Agent
|
||||
from crewai.agent.planning_config import PlanningConfig
|
||||
from crewai.task import Task
|
||||
|
||||
|
||||
class ReasoningPlan(BaseModel):
|
||||
"""Model representing a reasoning plan for a task."""
|
||||
|
||||
@@ -29,6 +38,11 @@ class AgentReasoningOutput(BaseModel):
|
||||
plan: ReasoningPlan = Field(description="The reasoning plan for the task.")
|
||||
|
||||
|
||||
# Aliases for backward compatibility
|
||||
PlanningPlan = ReasoningPlan
|
||||
AgentPlanningOutput = AgentReasoningOutput
|
||||
|
||||
|
||||
FUNCTION_SCHEMA: Final[dict[str, Any]] = {
|
||||
"type": "function",
|
||||
"function": {
|
||||
@@ -47,6 +61,7 @@ FUNCTION_SCHEMA: Final[dict[str, Any]] = {
|
||||
},
|
||||
},
|
||||
"required": ["plan", "ready"],
|
||||
"additionalProperties": False,
|
||||
},
|
||||
},
|
||||
}
|
||||
@@ -54,41 +69,101 @@ FUNCTION_SCHEMA: Final[dict[str, Any]] = {
|
||||
|
||||
class AgentReasoning:
|
||||
"""
|
||||
Handles the agent reasoning process, enabling an agent to reflect and create a plan
|
||||
before executing a task.
|
||||
Handles the agent planning/reasoning process, enabling an agent to reflect
|
||||
and create a plan before executing a task.
|
||||
|
||||
Attributes:
|
||||
task: The task for which the agent is reasoning.
|
||||
agent: The agent performing the reasoning.
|
||||
llm: The language model used for reasoning.
|
||||
task: The task for which the agent is planning (optional).
|
||||
agent: The agent performing the planning.
|
||||
config: The planning configuration.
|
||||
llm: The language model used for planning.
|
||||
logger: Logger for logging events and errors.
|
||||
description: Task description or input text for planning.
|
||||
expected_output: Expected output description.
|
||||
"""
|
||||
|
||||
def __init__(self, task: Task, agent: Agent) -> None:
|
||||
"""Initialize the AgentReasoning with a task and an agent.
|
||||
def __init__(
|
||||
self,
|
||||
agent: Agent,
|
||||
task: Task | None = None,
|
||||
*,
|
||||
description: str | None = None,
|
||||
expected_output: str | None = None,
|
||||
) -> None:
|
||||
"""Initialize the AgentReasoning with an agent and optional task.
|
||||
|
||||
Args:
|
||||
task: The task for which the agent is reasoning.
|
||||
agent: The agent performing the reasoning.
|
||||
agent: The agent performing the planning.
|
||||
task: The task for which the agent is planning (optional).
|
||||
description: Task description or input text (used if task is None).
|
||||
expected_output: Expected output (used if task is None).
|
||||
"""
|
||||
self.task = task
|
||||
self.agent = agent
|
||||
self.llm = cast(LLM, agent.llm)
|
||||
self.task = task
|
||||
# Use task attributes if available, otherwise use provided values
|
||||
self._description = description or (
|
||||
task.description if task else "Complete the requested task"
|
||||
)
|
||||
self._expected_output = expected_output or (
|
||||
task.expected_output if task else "Complete the task successfully"
|
||||
)
|
||||
self.config = self._get_planning_config()
|
||||
self.llm = self._resolve_llm()
|
||||
self.logger = logging.getLogger(__name__)
|
||||
|
||||
def handle_agent_reasoning(self) -> AgentReasoningOutput:
|
||||
"""Public method for the reasoning process that creates and refines a plan for the task until the agent is ready to execute it.
|
||||
@property
|
||||
def description(self) -> str:
|
||||
"""Get the task/input description."""
|
||||
return self._description
|
||||
|
||||
@property
|
||||
def expected_output(self) -> str:
|
||||
"""Get the expected output."""
|
||||
return self._expected_output
|
||||
|
||||
def _get_planning_config(self) -> PlanningConfig:
|
||||
"""Get the planning configuration from the agent.
|
||||
|
||||
Returns:
|
||||
AgentReasoningOutput: The output of the agent reasoning process.
|
||||
The planning configuration, using defaults if not set.
|
||||
"""
|
||||
# Emit a reasoning started event (attempt 1)
|
||||
from crewai.agent.planning_config import PlanningConfig
|
||||
|
||||
if self.agent.planning_config is not None:
|
||||
return self.agent.planning_config
|
||||
# Fallback for backward compatibility
|
||||
return PlanningConfig(
|
||||
max_attempts=getattr(self.agent, "max_reasoning_attempts", None),
|
||||
)
|
||||
|
||||
def _resolve_llm(self) -> LLM:
|
||||
"""Resolve which LLM to use for planning.
|
||||
|
||||
Returns:
|
||||
The LLM to use - either from config or the agent's LLM.
|
||||
"""
|
||||
if self.config.llm is not None:
|
||||
if isinstance(self.config.llm, LLM):
|
||||
return self.config.llm
|
||||
return create_llm(self.config.llm)
|
||||
return cast(LLM, self.agent.llm)
|
||||
|
||||
def handle_agent_reasoning(self) -> AgentReasoningOutput:
|
||||
"""Public method for the planning process that creates and refines a plan
|
||||
for the task until the agent is ready to execute it.
|
||||
|
||||
Returns:
|
||||
AgentReasoningOutput: The output of the agent planning process.
|
||||
"""
|
||||
task_id = str(self.task.id) if self.task else "kickoff"
|
||||
|
||||
# Emit a planning started event (attempt 1)
|
||||
try:
|
||||
crewai_event_bus.emit(
|
||||
self.agent,
|
||||
AgentReasoningStartedEvent(
|
||||
agent_role=self.agent.role,
|
||||
task_id=str(self.task.id),
|
||||
task_id=task_id,
|
||||
attempt=1,
|
||||
from_task=self.task,
|
||||
),
|
||||
@@ -98,13 +173,13 @@ class AgentReasoning:
|
||||
pass
|
||||
|
||||
try:
|
||||
output = self.__handle_agent_reasoning()
|
||||
output = self._execute_planning()
|
||||
|
||||
crewai_event_bus.emit(
|
||||
self.agent,
|
||||
AgentReasoningCompletedEvent(
|
||||
agent_role=self.agent.role,
|
||||
task_id=str(self.task.id),
|
||||
task_id=task_id,
|
||||
plan=output.plan.plan,
|
||||
ready=output.plan.ready,
|
||||
attempt=1,
|
||||
@@ -115,71 +190,68 @@ class AgentReasoning:
|
||||
|
||||
return output
|
||||
except Exception as e:
|
||||
# Emit reasoning failed event
|
||||
# Emit planning failed event
|
||||
try:
|
||||
crewai_event_bus.emit(
|
||||
self.agent,
|
||||
AgentReasoningFailedEvent(
|
||||
agent_role=self.agent.role,
|
||||
task_id=str(self.task.id),
|
||||
task_id=task_id,
|
||||
error=str(e),
|
||||
attempt=1,
|
||||
from_task=self.task,
|
||||
from_agent=self.agent,
|
||||
),
|
||||
)
|
||||
except Exception as e:
|
||||
logging.error(f"Error emitting reasoning failed event: {e}")
|
||||
except Exception as event_error:
|
||||
logging.error(f"Error emitting planning failed event: {event_error}")
|
||||
|
||||
raise
|
||||
|
||||
def __handle_agent_reasoning(self) -> AgentReasoningOutput:
|
||||
"""Private method that handles the agent reasoning process.
|
||||
def _execute_planning(self) -> AgentReasoningOutput:
|
||||
"""Execute the planning process.
|
||||
|
||||
Returns:
|
||||
The output of the agent reasoning process.
|
||||
The output of the agent planning process.
|
||||
"""
|
||||
plan, ready = self.__create_initial_plan()
|
||||
|
||||
plan, ready = self.__refine_plan_if_needed(plan, ready)
|
||||
plan, ready = self._create_initial_plan()
|
||||
plan, ready = self._refine_plan_if_needed(plan, ready)
|
||||
|
||||
reasoning_plan = ReasoningPlan(plan=plan, ready=ready)
|
||||
return AgentReasoningOutput(plan=reasoning_plan)
|
||||
|
||||
def __create_initial_plan(self) -> tuple[str, bool]:
|
||||
"""Creates the initial reasoning plan for the task.
|
||||
def _create_initial_plan(self) -> tuple[str, bool]:
|
||||
"""Creates the initial plan for the task.
|
||||
|
||||
Returns:
|
||||
The initial plan and whether the agent is ready to execute the task.
|
||||
"""
|
||||
reasoning_prompt = self.__create_reasoning_prompt()
|
||||
planning_prompt = self._create_planning_prompt()
|
||||
|
||||
if self.llm.supports_function_calling():
|
||||
plan, ready = self.__call_with_function(reasoning_prompt, "initial_plan")
|
||||
plan, ready = self._call_with_function(planning_prompt, "create_plan")
|
||||
return plan, ready
|
||||
response = _call_llm_with_reasoning_prompt(
|
||||
llm=self.llm,
|
||||
prompt=reasoning_prompt,
|
||||
task=self.task,
|
||||
reasoning_agent=self.agent,
|
||||
backstory=self.__get_agent_backstory(),
|
||||
plan_type="initial_plan",
|
||||
|
||||
response = self._call_llm_with_prompt(
|
||||
prompt=planning_prompt,
|
||||
plan_type="create_plan",
|
||||
)
|
||||
|
||||
return self.__parse_reasoning_response(str(response))
|
||||
return self._parse_planning_response(str(response))
|
||||
|
||||
def __refine_plan_if_needed(self, plan: str, ready: bool) -> tuple[str, bool]:
|
||||
"""Refines the reasoning plan if the agent is not ready to execute the task.
|
||||
def _refine_plan_if_needed(self, plan: str, ready: bool) -> tuple[str, bool]:
|
||||
"""Refines the plan if the agent is not ready to execute the task.
|
||||
|
||||
Args:
|
||||
plan: The current reasoning plan.
|
||||
plan: The current plan.
|
||||
ready: Whether the agent is ready to execute the task.
|
||||
|
||||
Returns:
|
||||
The refined plan and whether the agent is ready to execute the task.
|
||||
"""
|
||||
attempt = 1
|
||||
max_attempts = self.agent.max_reasoning_attempts
|
||||
max_attempts = self.config.max_attempts
|
||||
task_id = str(self.task.id) if self.task else "kickoff"
|
||||
|
||||
while not ready and (max_attempts is None or attempt < max_attempts):
|
||||
# Emit event for each refinement attempt
|
||||
@@ -188,7 +260,7 @@ class AgentReasoning:
|
||||
self.agent,
|
||||
AgentReasoningStartedEvent(
|
||||
agent_role=self.agent.role,
|
||||
task_id=str(self.task.id),
|
||||
task_id=task_id,
|
||||
attempt=attempt + 1,
|
||||
from_task=self.task,
|
||||
),
|
||||
@@ -196,53 +268,48 @@ class AgentReasoning:
|
||||
except Exception: # noqa: S110
|
||||
pass
|
||||
|
||||
refine_prompt = self.__create_refine_prompt(plan)
|
||||
refine_prompt = self._create_refine_prompt(plan)
|
||||
|
||||
if self.llm.supports_function_calling():
|
||||
plan, ready = self.__call_with_function(refine_prompt, "refine_plan")
|
||||
plan, ready = self._call_with_function(refine_prompt, "refine_plan")
|
||||
else:
|
||||
response = _call_llm_with_reasoning_prompt(
|
||||
llm=self.llm,
|
||||
response = self._call_llm_with_prompt(
|
||||
prompt=refine_prompt,
|
||||
task=self.task,
|
||||
reasoning_agent=self.agent,
|
||||
backstory=self.__get_agent_backstory(),
|
||||
plan_type="refine_plan",
|
||||
)
|
||||
plan, ready = self.__parse_reasoning_response(str(response))
|
||||
plan, ready = self._parse_planning_response(str(response))
|
||||
|
||||
attempt += 1
|
||||
|
||||
if max_attempts is not None and attempt >= max_attempts:
|
||||
self.logger.warning(
|
||||
f"Agent reasoning reached maximum attempts ({max_attempts}) without being ready. Proceeding with current plan."
|
||||
f"Agent planning reached maximum attempts ({max_attempts}) "
|
||||
"without being ready. Proceeding with current plan."
|
||||
)
|
||||
break
|
||||
|
||||
return plan, ready
|
||||
|
||||
def __call_with_function(self, prompt: str, prompt_type: str) -> tuple[str, bool]:
|
||||
"""Calls the LLM with function calling to get a reasoning plan.
|
||||
def _call_with_function(
|
||||
self, prompt: str, plan_type: Literal["create_plan", "refine_plan"]
|
||||
) -> tuple[str, bool]:
|
||||
"""Calls the LLM with function calling to get a plan.
|
||||
|
||||
Args:
|
||||
prompt: The prompt to send to the LLM.
|
||||
prompt_type: The type of prompt (initial_plan or refine_plan).
|
||||
plan_type: The type of plan being created.
|
||||
|
||||
Returns:
|
||||
A tuple containing the plan and whether the agent is ready.
|
||||
"""
|
||||
self.logger.debug(f"Using function calling for {prompt_type} reasoning")
|
||||
self.logger.debug(f"Using function calling for {plan_type} planning")
|
||||
|
||||
try:
|
||||
system_prompt = self.agent.i18n.retrieve("reasoning", prompt_type).format(
|
||||
role=self.agent.role,
|
||||
goal=self.agent.goal,
|
||||
backstory=self.__get_agent_backstory(),
|
||||
)
|
||||
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:
|
||||
"""Return the reasoning plan result in JSON string form."""
|
||||
"""Return the planning result in JSON string form."""
|
||||
return json.dumps({"plan": plan, "ready": ready})
|
||||
|
||||
response = self.llm.call(
|
||||
@@ -256,8 +323,6 @@ class AgentReasoning:
|
||||
from_agent=self.agent,
|
||||
)
|
||||
|
||||
self.logger.debug(f"Function calling response: {response[:100]}...")
|
||||
|
||||
try:
|
||||
result = json.loads(response)
|
||||
if "plan" in result and "ready" in result:
|
||||
@@ -277,13 +342,7 @@ class AgentReasoning:
|
||||
)
|
||||
|
||||
try:
|
||||
system_prompt = self.agent.i18n.retrieve(
|
||||
"reasoning", prompt_type
|
||||
).format(
|
||||
role=self.agent.role,
|
||||
goal=self.agent.goal,
|
||||
backstory=self.__get_agent_backstory(),
|
||||
)
|
||||
system_prompt = self._get_system_prompt()
|
||||
|
||||
fallback_response = self.llm.call(
|
||||
[
|
||||
@@ -306,69 +365,154 @@ class AgentReasoning:
|
||||
True,
|
||||
) # Default to ready to avoid getting stuck
|
||||
|
||||
def __get_agent_backstory(self) -> str:
|
||||
"""
|
||||
Safely gets the agent's backstory, providing a default if not available.
|
||||
def _call_llm_with_prompt(
|
||||
self,
|
||||
prompt: str,
|
||||
plan_type: Literal["create_plan", "refine_plan"],
|
||||
) -> str:
|
||||
"""Calls the LLM with the planning prompt.
|
||||
|
||||
Args:
|
||||
prompt: The prompt to send to the LLM.
|
||||
plan_type: The type of plan being created.
|
||||
|
||||
Returns:
|
||||
str: The agent's backstory or a default value.
|
||||
The LLM response.
|
||||
"""
|
||||
system_prompt = self._get_system_prompt()
|
||||
|
||||
response = self.llm.call(
|
||||
[
|
||||
{"role": "system", "content": system_prompt},
|
||||
{"role": "user", "content": prompt},
|
||||
],
|
||||
from_task=self.task,
|
||||
from_agent=self.agent,
|
||||
)
|
||||
return str(response)
|
||||
|
||||
def _get_system_prompt(self) -> str:
|
||||
"""Get the system prompt for planning.
|
||||
|
||||
Returns:
|
||||
The system prompt, either custom or from i18n.
|
||||
"""
|
||||
if self.config.system_prompt is not None:
|
||||
return self.config.system_prompt
|
||||
|
||||
# Try new "planning" section first, fall back to "reasoning" for compatibility
|
||||
try:
|
||||
return self.agent.i18n.retrieve("planning", "system_prompt")
|
||||
except (KeyError, AttributeError):
|
||||
# Fallback to reasoning section for backward compatibility
|
||||
return self.agent.i18n.retrieve("reasoning", "initial_plan").format(
|
||||
role=self.agent.role,
|
||||
goal=self.agent.goal,
|
||||
backstory=self._get_agent_backstory(),
|
||||
)
|
||||
|
||||
def _get_agent_backstory(self) -> str:
|
||||
"""Safely gets the agent's backstory, providing a default if not available.
|
||||
|
||||
Returns:
|
||||
The agent's backstory or a default value.
|
||||
"""
|
||||
return getattr(self.agent, "backstory", "No backstory provided")
|
||||
|
||||
def __create_reasoning_prompt(self) -> str:
|
||||
"""
|
||||
Creates a prompt for the agent to reason about the task.
|
||||
def _create_planning_prompt(self) -> str:
|
||||
"""Creates a prompt for the agent to plan the task.
|
||||
|
||||
Returns:
|
||||
str: The reasoning prompt.
|
||||
The planning prompt.
|
||||
"""
|
||||
available_tools = self.__format_available_tools()
|
||||
available_tools = self._format_available_tools()
|
||||
|
||||
return self.agent.i18n.retrieve("reasoning", "create_plan_prompt").format(
|
||||
role=self.agent.role,
|
||||
goal=self.agent.goal,
|
||||
backstory=self.__get_agent_backstory(),
|
||||
description=self.task.description,
|
||||
expected_output=self.task.expected_output,
|
||||
tools=available_tools,
|
||||
)
|
||||
# Use custom prompt if provided
|
||||
if self.config.plan_prompt is not None:
|
||||
return self.config.plan_prompt.format(
|
||||
role=self.agent.role,
|
||||
goal=self.agent.goal,
|
||||
backstory=self._get_agent_backstory(),
|
||||
description=self.description,
|
||||
expected_output=self.expected_output,
|
||||
tools=available_tools,
|
||||
max_steps=self.config.max_steps,
|
||||
)
|
||||
|
||||
def __format_available_tools(self) -> str:
|
||||
"""
|
||||
Formats the available tools for inclusion in the prompt.
|
||||
# Try new "planning" section first
|
||||
try:
|
||||
return self.agent.i18n.retrieve("planning", "create_plan_prompt").format(
|
||||
description=self.description,
|
||||
expected_output=self.expected_output,
|
||||
tools=available_tools,
|
||||
max_steps=self.config.max_steps,
|
||||
)
|
||||
except (KeyError, AttributeError):
|
||||
# Fallback to reasoning section for backward compatibility
|
||||
return self.agent.i18n.retrieve("reasoning", "create_plan_prompt").format(
|
||||
role=self.agent.role,
|
||||
goal=self.agent.goal,
|
||||
backstory=self._get_agent_backstory(),
|
||||
description=self.description,
|
||||
expected_output=self.expected_output,
|
||||
tools=available_tools,
|
||||
)
|
||||
|
||||
def _format_available_tools(self) -> str:
|
||||
"""Formats the available tools for inclusion in the prompt.
|
||||
|
||||
Returns:
|
||||
str: Comma-separated list of tool names.
|
||||
Comma-separated list of tool names.
|
||||
"""
|
||||
try:
|
||||
return ", ".join(
|
||||
[sanitize_tool_name(tool.name) for tool in (self.task.tools or [])]
|
||||
)
|
||||
# Try task tools first, then agent tools
|
||||
tools = []
|
||||
if self.task:
|
||||
tools = self.task.tools or []
|
||||
if not tools:
|
||||
tools = getattr(self.agent, "tools", []) or []
|
||||
if not tools:
|
||||
return "No tools available"
|
||||
return ", ".join([sanitize_tool_name(tool.name) for tool in tools])
|
||||
except (AttributeError, TypeError):
|
||||
return "No tools available"
|
||||
|
||||
def __create_refine_prompt(self, current_plan: str) -> str:
|
||||
"""
|
||||
Creates a prompt for the agent to refine its reasoning plan.
|
||||
def _create_refine_prompt(self, current_plan: str) -> str:
|
||||
"""Creates a prompt for the agent to refine its plan.
|
||||
|
||||
Args:
|
||||
current_plan: The current reasoning plan.
|
||||
current_plan: The current plan.
|
||||
|
||||
Returns:
|
||||
str: The refine prompt.
|
||||
The refine prompt.
|
||||
"""
|
||||
return self.agent.i18n.retrieve("reasoning", "refine_plan_prompt").format(
|
||||
role=self.agent.role,
|
||||
goal=self.agent.goal,
|
||||
backstory=self.__get_agent_backstory(),
|
||||
current_plan=current_plan,
|
||||
)
|
||||
# Use custom prompt if provided
|
||||
if self.config.refine_prompt is not None:
|
||||
return self.config.refine_prompt.format(
|
||||
role=self.agent.role,
|
||||
goal=self.agent.goal,
|
||||
backstory=self._get_agent_backstory(),
|
||||
current_plan=current_plan,
|
||||
max_steps=self.config.max_steps,
|
||||
)
|
||||
|
||||
# Try new "planning" section first
|
||||
try:
|
||||
return self.agent.i18n.retrieve("planning", "refine_plan_prompt").format(
|
||||
current_plan=current_plan,
|
||||
)
|
||||
except (KeyError, AttributeError):
|
||||
# Fallback to reasoning section for backward compatibility
|
||||
return self.agent.i18n.retrieve("reasoning", "refine_plan_prompt").format(
|
||||
role=self.agent.role,
|
||||
goal=self.agent.goal,
|
||||
backstory=self._get_agent_backstory(),
|
||||
current_plan=current_plan,
|
||||
)
|
||||
|
||||
@staticmethod
|
||||
def __parse_reasoning_response(response: str) -> tuple[str, bool]:
|
||||
"""
|
||||
Parses the reasoning response to extract the plan and whether
|
||||
the agent is ready to execute the task.
|
||||
def _parse_planning_response(response: str) -> tuple[str, bool]:
|
||||
"""Parses the planning response to extract the plan and readiness.
|
||||
|
||||
Args:
|
||||
response: The LLM response.
|
||||
@@ -380,25 +524,13 @@ class AgentReasoning:
|
||||
return "No plan was generated.", False
|
||||
|
||||
plan = response
|
||||
ready = False
|
||||
|
||||
if "READY: I am ready to execute the task." in response:
|
||||
ready = True
|
||||
ready = "READY: I am ready to execute the task." in response
|
||||
|
||||
return plan, ready
|
||||
|
||||
def _handle_agent_reasoning(self) -> AgentReasoningOutput:
|
||||
"""
|
||||
Deprecated method for backward compatibility.
|
||||
Use handle_agent_reasoning() instead.
|
||||
|
||||
Returns:
|
||||
AgentReasoningOutput: The output of the agent reasoning process.
|
||||
"""
|
||||
self.logger.warning(
|
||||
"The _handle_agent_reasoning method is deprecated. Use handle_agent_reasoning instead."
|
||||
)
|
||||
return self.handle_agent_reasoning()
|
||||
# Alias for backward compatibility
|
||||
AgentPlanning = AgentReasoning
|
||||
|
||||
|
||||
def _call_llm_with_reasoning_prompt(
|
||||
@@ -409,7 +541,9 @@ def _call_llm_with_reasoning_prompt(
|
||||
backstory: str,
|
||||
plan_type: Literal["initial_plan", "refine_plan"],
|
||||
) -> str:
|
||||
"""Calls the LLM with the reasoning prompt.
|
||||
"""Deprecated: Calls the LLM with the reasoning prompt.
|
||||
|
||||
This function is kept for backward compatibility.
|
||||
|
||||
Args:
|
||||
llm: The language model to use.
|
||||
@@ -417,7 +551,7 @@ def _call_llm_with_reasoning_prompt(
|
||||
task: The task for which the agent is reasoning.
|
||||
reasoning_agent: The agent performing the reasoning.
|
||||
backstory: The agent's backstory.
|
||||
plan_type: The type of plan being created ("initial_plan" or "refine_plan").
|
||||
plan_type: The type of plan being created.
|
||||
|
||||
Returns:
|
||||
The LLM response.
|
||||
|
||||
@@ -1454,7 +1454,7 @@ def test_agent_execute_task_with_tool():
|
||||
)
|
||||
|
||||
result = agent.execute_task(task)
|
||||
assert "you should always think about what to do" in result
|
||||
assert "test query" in result
|
||||
|
||||
|
||||
@pytest.mark.vcr()
|
||||
@@ -1473,9 +1473,9 @@ def test_agent_execute_task_with_custom_llm():
|
||||
)
|
||||
|
||||
result = agent.execute_task(task)
|
||||
assert "In circuits they thrive" in result
|
||||
assert "Artificial minds awake" in result
|
||||
assert "Future's coded drive" in result
|
||||
assert "Artificial minds" in result
|
||||
assert "Code and circuits" in result
|
||||
assert "Future undefined" in result
|
||||
|
||||
|
||||
@pytest.mark.vcr()
|
||||
|
||||
@@ -25,6 +25,18 @@ class TestAgentReActState:
|
||||
assert state.current_answer is None
|
||||
assert state.is_finished is False
|
||||
assert state.ask_for_human_input is False
|
||||
# Planning state fields
|
||||
assert state.plan is None
|
||||
assert state.plan_ready is False
|
||||
|
||||
def test_state_with_plan(self):
|
||||
"""Test AgentReActState initialization with planning fields."""
|
||||
state = AgentReActState(
|
||||
plan="Step 1: Do X\nStep 2: Do Y",
|
||||
plan_ready=True,
|
||||
)
|
||||
assert state.plan == "Step 1: Do X\nStep 2: Do Y"
|
||||
assert state.plan_ready is True
|
||||
|
||||
def test_state_with_values(self):
|
||||
"""Test AgentReActState initialization with values."""
|
||||
@@ -477,3 +489,249 @@ class TestFlowInvoke:
|
||||
|
||||
assert result == {"output": "Done"}
|
||||
assert len(executor.state.messages) >= 2
|
||||
|
||||
|
||||
class TestAgentExecutorPlanning:
|
||||
"""Test planning functionality in AgentExecutor with real agent kickoff."""
|
||||
|
||||
@pytest.mark.vcr()
|
||||
def test_agent_kickoff_with_planning_stores_plan_in_state(self):
|
||||
"""Test that Agent.kickoff() with planning enabled stores plan in executor state."""
|
||||
from crewai import Agent, PlanningConfig
|
||||
from crewai.llm import LLM
|
||||
|
||||
llm = LLM("gpt-4o-mini")
|
||||
|
||||
agent = Agent(
|
||||
role="Math Assistant",
|
||||
goal="Help solve simple math problems",
|
||||
backstory="A helpful assistant that solves math problems step by step",
|
||||
llm=llm,
|
||||
planning_config=PlanningConfig(max_attempts=1),
|
||||
verbose=False,
|
||||
)
|
||||
|
||||
# Execute kickoff with a simple task
|
||||
result = agent.kickoff("What is 2 + 2?")
|
||||
|
||||
# Verify result
|
||||
assert result is not None
|
||||
assert "4" in str(result)
|
||||
|
||||
@pytest.mark.vcr()
|
||||
def test_agent_kickoff_without_planning_skips_plan_generation(self):
|
||||
"""Test that Agent.kickoff() without planning skips planning phase."""
|
||||
from crewai import Agent
|
||||
from crewai.llm import LLM
|
||||
|
||||
llm = LLM("gpt-4o-mini")
|
||||
|
||||
agent = Agent(
|
||||
role="Math Assistant",
|
||||
goal="Help solve simple math problems",
|
||||
backstory="A helpful assistant",
|
||||
llm=llm,
|
||||
# No planning_config = no planning
|
||||
verbose=False,
|
||||
)
|
||||
|
||||
# Execute kickoff
|
||||
result = agent.kickoff("What is 3 + 3?")
|
||||
|
||||
# Verify we get a result
|
||||
assert result is not None
|
||||
assert "6" in str(result)
|
||||
|
||||
@pytest.mark.vcr()
|
||||
def test_planning_disabled_skips_planning(self):
|
||||
"""Test that planning=False skips planning."""
|
||||
from crewai import Agent
|
||||
from crewai.llm import LLM
|
||||
|
||||
llm = LLM("gpt-4o-mini")
|
||||
|
||||
agent = Agent(
|
||||
role="Math Assistant",
|
||||
goal="Help solve simple math problems",
|
||||
backstory="A helpful assistant",
|
||||
llm=llm,
|
||||
planning=False, # Explicitly disable planning
|
||||
verbose=False,
|
||||
)
|
||||
|
||||
result = agent.kickoff("What is 5 + 5?")
|
||||
|
||||
# Should still complete successfully
|
||||
assert result is not None
|
||||
assert "10" in str(result)
|
||||
|
||||
def test_backward_compat_reasoning_true_enables_planning(self):
|
||||
"""Test that reasoning=True (deprecated) still enables planning."""
|
||||
import warnings
|
||||
from crewai import Agent
|
||||
from crewai.llm import LLM
|
||||
|
||||
llm = LLM("gpt-4o-mini")
|
||||
|
||||
with warnings.catch_warnings(record=True):
|
||||
warnings.simplefilter("always")
|
||||
agent = Agent(
|
||||
role="Test Agent",
|
||||
goal="Complete tasks",
|
||||
backstory="A helpful agent",
|
||||
llm=llm,
|
||||
reasoning=True, # Deprecated but should still work
|
||||
verbose=False,
|
||||
)
|
||||
|
||||
# Should have planning_config created from reasoning=True
|
||||
assert agent.planning_config is not None
|
||||
assert agent.planning_enabled is True
|
||||
|
||||
@pytest.mark.vcr()
|
||||
def test_executor_state_contains_plan_after_planning(self):
|
||||
"""Test that executor state contains plan after planning phase."""
|
||||
from crewai import Agent, PlanningConfig
|
||||
from crewai.llm import LLM
|
||||
from crewai.experimental.agent_executor import AgentExecutor
|
||||
|
||||
llm = LLM("gpt-4o-mini")
|
||||
|
||||
agent = Agent(
|
||||
role="Math Assistant",
|
||||
goal="Help solve simple math problems",
|
||||
backstory="A helpful assistant that solves math problems step by step",
|
||||
llm=llm,
|
||||
planning_config=PlanningConfig(max_attempts=1),
|
||||
verbose=False,
|
||||
)
|
||||
|
||||
# Track executor for inspection
|
||||
executor_ref = [None]
|
||||
original_invoke = AgentExecutor.invoke
|
||||
|
||||
def capture_executor(self, inputs):
|
||||
executor_ref[0] = self
|
||||
return original_invoke(self, inputs)
|
||||
|
||||
with patch.object(AgentExecutor, "invoke", capture_executor):
|
||||
result = agent.kickoff("What is 7 + 7?")
|
||||
|
||||
# Verify result
|
||||
assert result is not None
|
||||
|
||||
# If we captured an executor, check its state
|
||||
if executor_ref[0] is not None:
|
||||
# After planning, state should have plan info
|
||||
assert hasattr(executor_ref[0].state, "plan")
|
||||
assert hasattr(executor_ref[0].state, "plan_ready")
|
||||
|
||||
@pytest.mark.vcr()
|
||||
def test_planning_creates_minimal_steps_for_multi_step_task(self):
|
||||
"""Test that planning creates only necessary steps for a multi-step task.
|
||||
|
||||
This task requires exactly 3 dependent steps:
|
||||
1. Identify the first 3 prime numbers (2, 3, 5)
|
||||
2. Sum them (2 + 3 + 5 = 10)
|
||||
3. Multiply by 2 (10 * 2 = 20)
|
||||
|
||||
The plan should reflect these dependencies without unnecessary padding.
|
||||
"""
|
||||
from crewai import Agent, PlanningConfig
|
||||
from crewai.llm import LLM
|
||||
from crewai.experimental.agent_executor import AgentExecutor
|
||||
|
||||
llm = LLM("gpt-4o-mini")
|
||||
|
||||
agent = Agent(
|
||||
role="Math Tutor",
|
||||
goal="Solve multi-step math problems accurately",
|
||||
backstory="An expert math tutor who breaks down problems step by step",
|
||||
llm=llm,
|
||||
planning_config=PlanningConfig(max_attempts=1, max_steps=10),
|
||||
verbose=False,
|
||||
)
|
||||
|
||||
# Track the plan that gets generated
|
||||
captured_plan = [None]
|
||||
original_invoke = AgentExecutor.invoke
|
||||
|
||||
def capture_plan(self, inputs):
|
||||
result = original_invoke(self, inputs)
|
||||
captured_plan[0] = self.state.plan
|
||||
return result
|
||||
|
||||
with patch.object(AgentExecutor, "invoke", capture_plan):
|
||||
result = agent.kickoff(
|
||||
"Calculate the sum of the first 3 prime numbers, then multiply that result by 2. "
|
||||
"Show your work for each step."
|
||||
)
|
||||
|
||||
# Verify result contains the correct answer (20)
|
||||
assert result is not None
|
||||
assert "20" in str(result)
|
||||
|
||||
# Verify a plan was generated
|
||||
assert captured_plan[0] is not None
|
||||
|
||||
# The plan should be concise - this task needs ~3 steps, not 10+
|
||||
plan_text = captured_plan[0]
|
||||
# Count steps by looking for numbered items or bullet points
|
||||
import re
|
||||
|
||||
step_pattern = r"^\s*\d+[\.\):]|\n\s*-\s+"
|
||||
steps = re.findall(step_pattern, plan_text, re.MULTILINE)
|
||||
# Plan should have roughly 3-5 steps, not fill up to max_steps
|
||||
assert len(steps) <= 6, f"Plan has too many steps ({len(steps)}): {plan_text}"
|
||||
|
||||
@pytest.mark.vcr()
|
||||
def test_planning_handles_sequential_dependency_task(self):
|
||||
"""Test planning for a task where step N depends on step N-1.
|
||||
|
||||
Task: Convert 100 Celsius to Fahrenheit, then round to nearest 10.
|
||||
Step 1: Apply formula (C * 9/5 + 32) = 212
|
||||
Step 2: Round 212 to nearest 10 = 210
|
||||
|
||||
This tests that the planner recognizes sequential dependencies.
|
||||
"""
|
||||
from crewai import Agent, PlanningConfig
|
||||
from crewai.llm import LLM
|
||||
from crewai.experimental.agent_executor import AgentExecutor
|
||||
|
||||
llm = LLM("gpt-4o-mini")
|
||||
|
||||
agent = Agent(
|
||||
role="Unit Converter",
|
||||
goal="Accurately convert between units and apply transformations",
|
||||
backstory="A precise unit conversion specialist",
|
||||
llm=llm,
|
||||
planning_config=PlanningConfig(max_attempts=1, max_steps=10),
|
||||
verbose=False,
|
||||
)
|
||||
|
||||
captured_plan = [None]
|
||||
original_invoke = AgentExecutor.invoke
|
||||
|
||||
def capture_plan(self, inputs):
|
||||
result = original_invoke(self, inputs)
|
||||
captured_plan[0] = self.state.plan
|
||||
return result
|
||||
|
||||
with patch.object(AgentExecutor, "invoke", capture_plan):
|
||||
result = agent.kickoff(
|
||||
"Convert 100 degrees Celsius to Fahrenheit, then round the result to the nearest 10."
|
||||
)
|
||||
|
||||
assert result is not None
|
||||
# 100C = 212F, rounded to nearest 10 = 210
|
||||
assert "210" in str(result) or "212" in str(result)
|
||||
|
||||
# Plan should exist and be minimal (2-3 steps for this task)
|
||||
assert captured_plan[0] is not None
|
||||
plan_text = captured_plan[0]
|
||||
|
||||
import re
|
||||
|
||||
step_pattern = r"^\s*\d+[\.\):]|\n\s*-\s+"
|
||||
steps = re.findall(step_pattern, plan_text, re.MULTILINE)
|
||||
assert len(steps) <= 5, f"Plan should be minimal ({len(steps)} steps): {plan_text}"
|
||||
|
||||
@@ -1,240 +1,345 @@
|
||||
"""Tests for reasoning in agents."""
|
||||
"""Tests for planning/reasoning in agents."""
|
||||
|
||||
import json
|
||||
import warnings
|
||||
|
||||
import pytest
|
||||
|
||||
from crewai import Agent, Task
|
||||
from crewai import Agent, PlanningConfig, Task
|
||||
from crewai.llm import LLM
|
||||
|
||||
|
||||
@pytest.fixture
|
||||
def mock_llm_responses():
|
||||
"""Fixture for mock LLM responses."""
|
||||
return {
|
||||
"ready": "I'll solve this simple math problem.\n\nREADY: I am ready to execute the task.\n\n",
|
||||
"not_ready": "I need to think about derivatives.\n\nNOT READY: I need to refine my plan because I'm not sure about the derivative rules.",
|
||||
"ready_after_refine": "I'll use the power rule for derivatives where d/dx(x^n) = n*x^(n-1).\n\nREADY: I am ready to execute the task.",
|
||||
"execution": "4",
|
||||
}
|
||||
# =============================================================================
|
||||
# Tests for PlanningConfig configuration (no LLM calls needed)
|
||||
# =============================================================================
|
||||
|
||||
|
||||
def test_agent_with_reasoning(mock_llm_responses):
|
||||
"""Test agent with reasoning."""
|
||||
llm = LLM("gpt-3.5-turbo")
|
||||
def test_planning_config_default_values():
|
||||
"""Test PlanningConfig default values."""
|
||||
config = PlanningConfig()
|
||||
|
||||
assert config.max_attempts is None
|
||||
assert config.max_steps == 20
|
||||
assert config.system_prompt is None
|
||||
assert config.plan_prompt is None
|
||||
assert config.refine_prompt is None
|
||||
assert config.llm is None
|
||||
|
||||
|
||||
def test_planning_config_custom_values():
|
||||
"""Test PlanningConfig with custom values."""
|
||||
config = PlanningConfig(
|
||||
max_attempts=5,
|
||||
max_steps=15,
|
||||
system_prompt="Custom system",
|
||||
plan_prompt="Custom plan: {description}",
|
||||
refine_prompt="Custom refine: {current_plan}",
|
||||
llm="gpt-4",
|
||||
)
|
||||
|
||||
assert config.max_attempts == 5
|
||||
assert config.max_steps == 15
|
||||
assert config.system_prompt == "Custom system"
|
||||
assert config.plan_prompt == "Custom plan: {description}"
|
||||
assert config.refine_prompt == "Custom refine: {current_plan}"
|
||||
assert config.llm == "gpt-4"
|
||||
|
||||
|
||||
def test_agent_with_planning_config_custom_prompts():
|
||||
"""Test agent with PlanningConfig using custom prompts."""
|
||||
llm = LLM("gpt-4o-mini")
|
||||
|
||||
custom_system_prompt = "You are a specialized planner."
|
||||
custom_plan_prompt = "Plan this task: {description}"
|
||||
|
||||
agent = Agent(
|
||||
role="Test Agent",
|
||||
goal="To test custom prompts",
|
||||
backstory="I am a test agent.",
|
||||
llm=llm,
|
||||
planning_config=PlanningConfig(
|
||||
system_prompt=custom_system_prompt,
|
||||
plan_prompt=custom_plan_prompt,
|
||||
max_steps=10,
|
||||
),
|
||||
verbose=False,
|
||||
)
|
||||
|
||||
# Just test that the agent is created properly
|
||||
assert agent.planning_config is not None
|
||||
assert agent.planning_config.system_prompt == custom_system_prompt
|
||||
assert agent.planning_config.plan_prompt == custom_plan_prompt
|
||||
assert agent.planning_config.max_steps == 10
|
||||
|
||||
|
||||
def test_agent_with_planning_config_disabled():
|
||||
"""Test agent with PlanningConfig disabled."""
|
||||
llm = LLM("gpt-4o-mini")
|
||||
|
||||
agent = Agent(
|
||||
role="Test Agent",
|
||||
goal="To test disabled planning",
|
||||
backstory="I am a test agent.",
|
||||
llm=llm,
|
||||
planning=False,
|
||||
verbose=False,
|
||||
)
|
||||
|
||||
# Planning should be disabled
|
||||
assert agent.planning_enabled is False
|
||||
|
||||
|
||||
def test_planning_enabled_property():
|
||||
"""Test the planning_enabled property on Agent."""
|
||||
llm = LLM("gpt-4o-mini")
|
||||
|
||||
# With planning_config enabled
|
||||
agent_with_planning = Agent(
|
||||
role="Test Agent",
|
||||
goal="Test",
|
||||
backstory="Test",
|
||||
llm=llm,
|
||||
planning=True,
|
||||
)
|
||||
assert agent_with_planning.planning_enabled is True
|
||||
|
||||
# With planning_config disabled
|
||||
agent_disabled = Agent(
|
||||
role="Test Agent",
|
||||
goal="Test",
|
||||
backstory="Test",
|
||||
llm=llm,
|
||||
planning=False,
|
||||
)
|
||||
assert agent_disabled.planning_enabled is False
|
||||
|
||||
# Without planning_config
|
||||
agent_no_planning = Agent(
|
||||
role="Test Agent",
|
||||
goal="Test",
|
||||
backstory="Test",
|
||||
llm=llm,
|
||||
)
|
||||
assert agent_no_planning.planning_enabled is False
|
||||
|
||||
|
||||
# =============================================================================
|
||||
# Tests for backward compatibility with reasoning=True (no LLM calls)
|
||||
# =============================================================================
|
||||
|
||||
|
||||
def test_agent_with_reasoning_backward_compat():
|
||||
"""Test agent with reasoning=True (backward compatibility)."""
|
||||
llm = LLM("gpt-4o-mini")
|
||||
|
||||
# This should emit a deprecation warning
|
||||
with warnings.catch_warnings(record=True):
|
||||
warnings.simplefilter("always")
|
||||
agent = Agent(
|
||||
role="Test Agent",
|
||||
goal="To test the reasoning feature",
|
||||
backstory="I am a test agent created to verify the reasoning feature works correctly.",
|
||||
llm=llm,
|
||||
reasoning=True,
|
||||
verbose=False,
|
||||
)
|
||||
|
||||
# Should have created a PlanningConfig internally
|
||||
assert agent.planning_config is not None
|
||||
assert agent.planning_enabled is True
|
||||
|
||||
|
||||
def test_agent_with_reasoning_and_max_attempts_backward_compat():
|
||||
"""Test agent with reasoning=True and max_reasoning_attempts (backward compatibility)."""
|
||||
llm = LLM("gpt-4o-mini")
|
||||
|
||||
agent = Agent(
|
||||
role="Test Agent",
|
||||
goal="To test the reasoning feature",
|
||||
backstory="I am a test agent created to verify the reasoning feature works correctly.",
|
||||
backstory="I am a test agent.",
|
||||
llm=llm,
|
||||
reasoning=True,
|
||||
verbose=True,
|
||||
max_reasoning_attempts=5,
|
||||
verbose=False,
|
||||
)
|
||||
|
||||
task = Task(
|
||||
description="Simple math task: What's 2+2?",
|
||||
expected_output="The answer should be a number.",
|
||||
agent=agent,
|
||||
)
|
||||
|
||||
agent.llm.call = lambda messages, *args, **kwargs: (
|
||||
mock_llm_responses["ready"]
|
||||
if any("create a detailed plan" in msg.get("content", "") for msg in messages)
|
||||
else mock_llm_responses["execution"]
|
||||
)
|
||||
|
||||
result = agent.execute_task(task)
|
||||
|
||||
assert result == mock_llm_responses["execution"]
|
||||
assert "Reasoning Plan:" in task.description
|
||||
# Should have created a PlanningConfig with max_attempts
|
||||
assert agent.planning_config is not None
|
||||
assert agent.planning_config.max_attempts == 5
|
||||
|
||||
|
||||
def test_agent_with_reasoning_not_ready_initially(mock_llm_responses):
|
||||
"""Test agent with reasoning that requires refinement."""
|
||||
llm = LLM("gpt-3.5-turbo")
|
||||
# =============================================================================
|
||||
# Tests for Agent.kickoff() with planning (uses AgentExecutor)
|
||||
# =============================================================================
|
||||
|
||||
|
||||
@pytest.mark.vcr()
|
||||
def test_agent_kickoff_with_planning():
|
||||
"""Test Agent.kickoff() with planning enabled generates a plan."""
|
||||
llm = LLM("gpt-4o-mini")
|
||||
|
||||
agent = Agent(
|
||||
role="Test Agent",
|
||||
goal="To test the reasoning feature",
|
||||
backstory="I am a test agent created to verify the reasoning feature works correctly.",
|
||||
role="Math Assistant",
|
||||
goal="Help solve math problems step by step",
|
||||
backstory="A helpful math tutor",
|
||||
llm=llm,
|
||||
reasoning=True,
|
||||
max_reasoning_attempts=2,
|
||||
verbose=True,
|
||||
planning_config=PlanningConfig(max_attempts=1),
|
||||
verbose=False,
|
||||
)
|
||||
|
||||
task = Task(
|
||||
description="Complex math task: What's the derivative of x²?",
|
||||
expected_output="The answer should be a mathematical expression.",
|
||||
agent=agent,
|
||||
)
|
||||
result = agent.kickoff("What is 15 + 27?")
|
||||
|
||||
call_count = [0]
|
||||
|
||||
def mock_llm_call(messages, *args, **kwargs):
|
||||
if any(
|
||||
"create a detailed plan" in msg.get("content", "") for msg in messages
|
||||
) or any("refine your plan" in msg.get("content", "") for msg in messages):
|
||||
call_count[0] += 1
|
||||
if call_count[0] == 1:
|
||||
return mock_llm_responses["not_ready"]
|
||||
return mock_llm_responses["ready_after_refine"]
|
||||
return "2x"
|
||||
|
||||
agent.llm.call = mock_llm_call
|
||||
|
||||
result = agent.execute_task(task)
|
||||
|
||||
assert result == "2x"
|
||||
assert call_count[0] == 2 # Should have made 2 reasoning calls
|
||||
assert "Reasoning Plan:" in task.description
|
||||
assert result is not None
|
||||
assert "42" in str(result)
|
||||
|
||||
|
||||
def test_agent_with_reasoning_max_attempts_reached():
|
||||
"""Test agent with reasoning that reaches max attempts without being ready."""
|
||||
llm = LLM("gpt-3.5-turbo")
|
||||
@pytest.mark.vcr()
|
||||
def test_agent_kickoff_without_planning():
|
||||
"""Test Agent.kickoff() without planning skips plan generation."""
|
||||
llm = LLM("gpt-4o-mini")
|
||||
|
||||
agent = Agent(
|
||||
role="Test Agent",
|
||||
goal="To test the reasoning feature",
|
||||
backstory="I am a test agent created to verify the reasoning feature works correctly.",
|
||||
role="Math Assistant",
|
||||
goal="Help solve math problems",
|
||||
backstory="A helpful assistant",
|
||||
llm=llm,
|
||||
reasoning=True,
|
||||
max_reasoning_attempts=2,
|
||||
verbose=True,
|
||||
# No planning_config = no planning
|
||||
verbose=False,
|
||||
)
|
||||
|
||||
task = Task(
|
||||
description="Complex math task: Solve the Riemann hypothesis.",
|
||||
expected_output="A proof or disproof of the hypothesis.",
|
||||
agent=agent,
|
||||
)
|
||||
result = agent.kickoff("What is 8 * 7?")
|
||||
|
||||
call_count = [0]
|
||||
|
||||
def mock_llm_call(messages, *args, **kwargs):
|
||||
if any(
|
||||
"create a detailed plan" in msg.get("content", "") for msg in messages
|
||||
) or any("refine your plan" in msg.get("content", "") for msg in messages):
|
||||
call_count[0] += 1
|
||||
return f"Attempt {call_count[0]}: I need more time to think.\n\nNOT READY: I need to refine my plan further."
|
||||
return "This is an unsolved problem in mathematics."
|
||||
|
||||
agent.llm.call = mock_llm_call
|
||||
|
||||
result = agent.execute_task(task)
|
||||
|
||||
assert result == "This is an unsolved problem in mathematics."
|
||||
assert (
|
||||
call_count[0] == 2
|
||||
) # Should have made exactly 2 reasoning calls (max_attempts)
|
||||
assert "Reasoning Plan:" in task.description
|
||||
assert result is not None
|
||||
assert "56" in str(result)
|
||||
|
||||
|
||||
def test_agent_reasoning_error_handling():
|
||||
"""Test error handling during the reasoning process."""
|
||||
llm = LLM("gpt-3.5-turbo")
|
||||
@pytest.mark.vcr()
|
||||
def test_agent_kickoff_with_planning_disabled():
|
||||
"""Test Agent.kickoff() with planning explicitly disabled via planning=False."""
|
||||
llm = LLM("gpt-4o-mini")
|
||||
|
||||
agent = Agent(
|
||||
role="Test Agent",
|
||||
goal="To test the reasoning feature",
|
||||
backstory="I am a test agent created to verify the reasoning feature works correctly.",
|
||||
role="Math Assistant",
|
||||
goal="Help solve math problems",
|
||||
backstory="A helpful assistant",
|
||||
llm=llm,
|
||||
reasoning=True,
|
||||
planning=False, # Explicitly disable planning
|
||||
verbose=False,
|
||||
)
|
||||
|
||||
task = Task(
|
||||
description="Task that will cause an error",
|
||||
expected_output="Output that will never be generated",
|
||||
agent=agent,
|
||||
)
|
||||
result = agent.kickoff("What is 100 / 4?")
|
||||
|
||||
call_count = [0]
|
||||
|
||||
def mock_llm_call_error(*args, **kwargs):
|
||||
call_count[0] += 1
|
||||
if call_count[0] <= 2: # First calls are for reasoning
|
||||
raise Exception("LLM error during reasoning")
|
||||
return "Fallback execution result" # Return a value for task execution
|
||||
|
||||
agent.llm.call = mock_llm_call_error
|
||||
|
||||
result = agent.execute_task(task)
|
||||
|
||||
assert result == "Fallback execution result"
|
||||
assert call_count[0] > 2 # Ensure we called the mock multiple times
|
||||
assert result is not None
|
||||
assert "25" in str(result)
|
||||
|
||||
|
||||
@pytest.mark.skip(reason="Test requires updates for native tool calling changes")
|
||||
def test_agent_with_function_calling():
|
||||
"""Test agent with reasoning using function calling."""
|
||||
llm = LLM("gpt-3.5-turbo")
|
||||
@pytest.mark.vcr()
|
||||
def test_agent_kickoff_multi_step_task_with_planning():
|
||||
"""Test Agent.kickoff() with a multi-step task that benefits from planning."""
|
||||
llm = LLM("gpt-4o-mini")
|
||||
|
||||
agent = Agent(
|
||||
role="Test Agent",
|
||||
goal="To test the reasoning feature",
|
||||
backstory="I am a test agent created to verify the reasoning feature works correctly.",
|
||||
role="Math Tutor",
|
||||
goal="Solve multi-step math problems",
|
||||
backstory="An expert tutor who explains step by step",
|
||||
llm=llm,
|
||||
reasoning=True,
|
||||
verbose=True,
|
||||
planning_config=PlanningConfig(max_attempts=1, max_steps=5),
|
||||
verbose=False,
|
||||
)
|
||||
|
||||
task = Task(
|
||||
description="Simple math task: What's 2+2?",
|
||||
expected_output="The answer should be a number.",
|
||||
agent=agent,
|
||||
# Task requires: find primes, sum them, then double
|
||||
result = agent.kickoff(
|
||||
"Find the first 3 prime numbers, add them together, then multiply by 2."
|
||||
)
|
||||
|
||||
agent.llm.supports_function_calling = lambda: True
|
||||
|
||||
def mock_function_call(messages, *args, **kwargs):
|
||||
if "tools" in kwargs:
|
||||
return json.dumps(
|
||||
{"plan": "I'll solve this simple math problem: 2+2=4.", "ready": True}
|
||||
)
|
||||
return "4"
|
||||
|
||||
agent.llm.call = mock_function_call
|
||||
|
||||
result = agent.execute_task(task)
|
||||
|
||||
assert result == "4"
|
||||
assert "Reasoning Plan:" in task.description
|
||||
assert "I'll solve this simple math problem: 2+2=4." in task.description
|
||||
assert result is not None
|
||||
# First 3 primes: 2, 3, 5 -> sum = 10 -> doubled = 20
|
||||
assert "20" in str(result)
|
||||
|
||||
|
||||
@pytest.mark.skip(reason="Test requires updates for native tool calling changes")
|
||||
def test_agent_with_function_calling_fallback():
|
||||
"""Test agent with reasoning using function calling that falls back to text parsing."""
|
||||
llm = LLM("gpt-3.5-turbo")
|
||||
# =============================================================================
|
||||
# Tests for Agent.execute_task() with planning (uses CrewAgentExecutor)
|
||||
# These test the legacy path via handle_reasoning()
|
||||
# =============================================================================
|
||||
|
||||
|
||||
@pytest.mark.vcr()
|
||||
def test_agent_execute_task_with_planning():
|
||||
"""Test Agent.execute_task() with planning via CrewAgentExecutor."""
|
||||
llm = LLM("gpt-4o-mini")
|
||||
|
||||
agent = Agent(
|
||||
role="Test Agent",
|
||||
goal="To test the reasoning feature",
|
||||
backstory="I am a test agent created to verify the reasoning feature works correctly.",
|
||||
role="Math Assistant",
|
||||
goal="Help solve math problems",
|
||||
backstory="A helpful math tutor",
|
||||
llm=llm,
|
||||
reasoning=True,
|
||||
verbose=True,
|
||||
planning_config=PlanningConfig(max_attempts=1),
|
||||
verbose=False,
|
||||
)
|
||||
|
||||
task = Task(
|
||||
description="Simple math task: What's 2+2?",
|
||||
expected_output="The answer should be a number.",
|
||||
description="What is 9 + 11?",
|
||||
expected_output="A number",
|
||||
agent=agent,
|
||||
)
|
||||
|
||||
agent.llm.supports_function_calling = lambda: True
|
||||
result = agent.execute_task(task)
|
||||
|
||||
def mock_function_call(messages, *args, **kwargs):
|
||||
if "tools" in kwargs:
|
||||
return "Invalid JSON that will trigger fallback. READY: I am ready to execute the task."
|
||||
return "4"
|
||||
assert result is not None
|
||||
assert "20" in str(result)
|
||||
# Planning should be appended to task description
|
||||
assert "Planning:" in task.description
|
||||
|
||||
agent.llm.call = mock_function_call
|
||||
|
||||
@pytest.mark.vcr()
|
||||
def test_agent_execute_task_without_planning():
|
||||
"""Test Agent.execute_task() without planning."""
|
||||
llm = LLM("gpt-4o-mini")
|
||||
|
||||
agent = Agent(
|
||||
role="Math Assistant",
|
||||
goal="Help solve math problems",
|
||||
backstory="A helpful assistant",
|
||||
llm=llm,
|
||||
verbose=False,
|
||||
)
|
||||
|
||||
task = Task(
|
||||
description="What is 12 * 3?",
|
||||
expected_output="A number",
|
||||
agent=agent,
|
||||
)
|
||||
|
||||
result = agent.execute_task(task)
|
||||
|
||||
assert result == "4"
|
||||
assert "Reasoning Plan:" in task.description
|
||||
assert "Invalid JSON that will trigger fallback" in task.description
|
||||
assert result is not None
|
||||
assert "36" in str(result)
|
||||
# No planning should be added
|
||||
assert "Planning:" not in task.description
|
||||
|
||||
|
||||
@pytest.mark.vcr()
|
||||
def test_agent_execute_task_with_planning_refine():
|
||||
"""Test Agent.execute_task() with planning that requires refinement."""
|
||||
llm = LLM("gpt-4o-mini")
|
||||
|
||||
agent = Agent(
|
||||
role="Math Tutor",
|
||||
goal="Solve complex math problems step by step",
|
||||
backstory="An expert tutor",
|
||||
llm=llm,
|
||||
planning_config=PlanningConfig(max_attempts=2),
|
||||
verbose=False,
|
||||
)
|
||||
|
||||
task = Task(
|
||||
description="Calculate the area of a circle with radius 5 (use pi = 3.14)",
|
||||
expected_output="The area as a number",
|
||||
agent=agent,
|
||||
)
|
||||
|
||||
result = agent.execute_task(task)
|
||||
|
||||
assert result is not None
|
||||
# Area = pi * r^2 = 3.14 * 25 = 78.5
|
||||
assert "78" in str(result) or "79" in str(result)
|
||||
assert "Planning:" in task.description
|
||||
|
||||
@@ -0,0 +1,234 @@
|
||||
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\nWhat is 2 + 2?\n\n##
|
||||
Expected Output\nComplete the task successfully\n\n## Available Tools\nNo tools
|
||||
available\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\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-mini","tool_choice":"auto","tools":[{"type":"function","function":{"name":"create_reasoning_plan","description":"Create
|
||||
or refine a reasoning plan for a task","strict":true,"parameters":{"type":"object","properties":{"plan":{"type":"string","description":"The
|
||||
detailed reasoning plan for the task."},"ready":{"type":"boolean","description":"Whether
|
||||
the agent is ready to execute the task."}},"required":["plan","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:
|
||||
- '1541'
|
||||
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-D4yTTAh68P65LybtqkwNI3p2HXcRv\",\n \"object\":
|
||||
\"chat.completion\",\n \"created\": 1770078147,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n
|
||||
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
|
||||
\"assistant\",\n \"content\": \"## Execution Plan\\n\\n1. **Action:**
|
||||
Perform the addition operation. \\n **Tool:** None (manually calculate).\\n\\n2.
|
||||
**Action:** State the result. \\n **Tool:** None (manually output).\\n\\nREADY:
|
||||
I am ready to execute the task.\",\n \"refusal\": null,\n \"annotations\":
|
||||
[]\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n
|
||||
\ }\n ],\n \"usage\": {\n \"prompt_tokens\": 281,\n \"completion_tokens\":
|
||||
56,\n \"total_tokens\": 337,\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_1590f93f9d\"\n}\n"
|
||||
headers:
|
||||
CF-RAY:
|
||||
- CF-RAY-XXX
|
||||
Connection:
|
||||
- keep-alive
|
||||
Content-Type:
|
||||
- application/json
|
||||
Date:
|
||||
- Tue, 03 Feb 2026 00:22:28 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:
|
||||
- '1165'
|
||||
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 Math Assistant. A helpful
|
||||
assistant that solves math problems step by step\nYour personal goal is: Help
|
||||
solve simple math problems"},{"role":"user","content":"\nCurrent Task: What
|
||||
is 2 + 2?\n\nProvide your complete response:"}],"model":"gpt-4o-mini"}'
|
||||
headers:
|
||||
User-Agent:
|
||||
- X-USER-AGENT-XXX
|
||||
accept:
|
||||
- application/json
|
||||
accept-encoding:
|
||||
- ACCEPT-ENCODING-XXX
|
||||
authorization:
|
||||
- AUTHORIZATION-XXX
|
||||
connection:
|
||||
- keep-alive
|
||||
content-length:
|
||||
- '299'
|
||||
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-D4yTVB9mdtq1YZrUVf1aSb6dVVQ8G\",\n \"object\":
|
||||
\"chat.completion\",\n \"created\": 1770078149,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n
|
||||
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
|
||||
\"assistant\",\n \"content\": \"To solve the problem of 2 + 2, we simply
|
||||
perform the addition:\\n\\n1. Start with the first number: 2\\n2. Add the
|
||||
second number: + 2\\n3. Combine the two: 2 + 2 = 4\\n\\nTherefore, the answer
|
||||
is 4.\",\n \"refusal\": null,\n \"annotations\": []\n },\n
|
||||
\ \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n ],\n
|
||||
\ \"usage\": {\n \"prompt_tokens\": 54,\n \"completion_tokens\": 62,\n
|
||||
\ \"total_tokens\": 116,\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_1590f93f9d\"\n}\n"
|
||||
headers:
|
||||
CF-RAY:
|
||||
- CF-RAY-XXX
|
||||
Connection:
|
||||
- keep-alive
|
||||
Content-Type:
|
||||
- application/json
|
||||
Date:
|
||||
- Tue, 03 Feb 2026 00:22:30 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:
|
||||
- '1300'
|
||||
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
|
||||
@@ -0,0 +1,108 @@
|
||||
interactions:
|
||||
- request:
|
||||
body: '{"messages":[{"role":"system","content":"You are Math Assistant. A helpful
|
||||
assistant\nYour personal goal is: Help solve simple math problems"},{"role":"user","content":"\nCurrent
|
||||
Task: What is 3 + 3?\n\nProvide your complete response:"}],"model":"gpt-4o-mini"}'
|
||||
headers:
|
||||
User-Agent:
|
||||
- X-USER-AGENT-XXX
|
||||
accept:
|
||||
- application/json
|
||||
accept-encoding:
|
||||
- ACCEPT-ENCODING-XXX
|
||||
authorization:
|
||||
- AUTHORIZATION-XXX
|
||||
connection:
|
||||
- keep-alive
|
||||
content-length:
|
||||
- '260'
|
||||
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-D4yTTFxQ75llVmJv0ee902FIjXE8p\",\n \"object\":
|
||||
\"chat.completion\",\n \"created\": 1770078147,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n
|
||||
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
|
||||
\"assistant\",\n \"content\": \"3 + 3 equals 6.\",\n \"refusal\":
|
||||
null,\n \"annotations\": []\n },\n \"logprobs\": null,\n
|
||||
\ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
|
||||
47,\n \"completion_tokens\": 8,\n \"total_tokens\": 55,\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_1590f93f9d\"\n}\n"
|
||||
headers:
|
||||
CF-RAY:
|
||||
- CF-RAY-XXX
|
||||
Connection:
|
||||
- keep-alive
|
||||
Content-Type:
|
||||
- application/json
|
||||
Date:
|
||||
- Tue, 03 Feb 2026 00:22:27 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:
|
||||
- '401'
|
||||
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
|
||||
@@ -0,0 +1,230 @@
|
||||
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\nWhat is 7 + 7?\n\n##
|
||||
Expected Output\nComplete the task successfully\n\n## Available Tools\nNo tools
|
||||
available\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\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-mini","tool_choice":"auto","tools":[{"type":"function","function":{"name":"create_reasoning_plan","description":"Create
|
||||
or refine a reasoning plan for a task","strict":true,"parameters":{"type":"object","properties":{"plan":{"type":"string","description":"The
|
||||
detailed reasoning plan for the task."},"ready":{"type":"boolean","description":"Whether
|
||||
the agent is ready to execute the task."}},"required":["plan","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:
|
||||
- '1541'
|
||||
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-D4yTdqlxwWowSdLncBERFrCgxTvVj\",\n \"object\":
|
||||
\"chat.completion\",\n \"created\": 1770078157,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n
|
||||
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
|
||||
\"assistant\",\n \"content\": \"## Execution Plan\\n\\n1. Calculate
|
||||
the sum of 7 and 7.\\n \\nREADY: I am ready to execute the task.\",\n \"refusal\":
|
||||
null,\n \"annotations\": []\n },\n \"logprobs\": null,\n
|
||||
\ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
|
||||
281,\n \"completion_tokens\": 28,\n \"total_tokens\": 309,\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_1590f93f9d\"\n}\n"
|
||||
headers:
|
||||
CF-RAY:
|
||||
- CF-RAY-XXX
|
||||
Connection:
|
||||
- keep-alive
|
||||
Content-Type:
|
||||
- application/json
|
||||
Date:
|
||||
- Tue, 03 Feb 2026 00:22:38 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:
|
||||
- '709'
|
||||
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 Math Assistant. A helpful
|
||||
assistant that solves math problems step by step\nYour personal goal is: Help
|
||||
solve simple math problems"},{"role":"user","content":"\nCurrent Task: What
|
||||
is 7 + 7?\n\nProvide your complete response:"}],"model":"gpt-4o-mini"}'
|
||||
headers:
|
||||
User-Agent:
|
||||
- X-USER-AGENT-XXX
|
||||
accept:
|
||||
- application/json
|
||||
accept-encoding:
|
||||
- ACCEPT-ENCODING-XXX
|
||||
authorization:
|
||||
- AUTHORIZATION-XXX
|
||||
connection:
|
||||
- keep-alive
|
||||
content-length:
|
||||
- '299'
|
||||
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-D4yTeB6Miecallw9SjSfLAXPjX2XD\",\n \"object\":
|
||||
\"chat.completion\",\n \"created\": 1770078158,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n
|
||||
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
|
||||
\"assistant\",\n \"content\": \"To find the sum of 7 and 7, you simply
|
||||
add the two numbers together:\\n\\n7 + 7 = 14\\n\\nSo, the answer is 14.\",\n
|
||||
\ \"refusal\": null,\n \"annotations\": []\n },\n \"logprobs\":
|
||||
null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
|
||||
54,\n \"completion_tokens\": 35,\n \"total_tokens\": 89,\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_1590f93f9d\"\n}\n"
|
||||
headers:
|
||||
CF-RAY:
|
||||
- CF-RAY-XXX
|
||||
Connection:
|
||||
- keep-alive
|
||||
Content-Type:
|
||||
- application/json
|
||||
Date:
|
||||
- Tue, 03 Feb 2026 00:22:38 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:
|
||||
- '733'
|
||||
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
|
||||
@@ -0,0 +1,108 @@
|
||||
interactions:
|
||||
- request:
|
||||
body: '{"messages":[{"role":"system","content":"You are Math Assistant. A helpful
|
||||
assistant\nYour personal goal is: Help solve simple math problems"},{"role":"user","content":"\nCurrent
|
||||
Task: What is 5 + 5?\n\nProvide your complete response:"}],"model":"gpt-4o-mini"}'
|
||||
headers:
|
||||
User-Agent:
|
||||
- X-USER-AGENT-XXX
|
||||
accept:
|
||||
- application/json
|
||||
accept-encoding:
|
||||
- ACCEPT-ENCODING-XXX
|
||||
authorization:
|
||||
- AUTHORIZATION-XXX
|
||||
connection:
|
||||
- keep-alive
|
||||
content-length:
|
||||
- '260'
|
||||
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-D4yTf8T2iADffpPCJBZhntLlaoaSy\",\n \"object\":
|
||||
\"chat.completion\",\n \"created\": 1770078159,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n
|
||||
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
|
||||
\"assistant\",\n \"content\": \"5 + 5 equals 10.\",\n \"refusal\":
|
||||
null,\n \"annotations\": []\n },\n \"logprobs\": null,\n
|
||||
\ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
|
||||
47,\n \"completion_tokens\": 8,\n \"total_tokens\": 55,\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_1590f93f9d\"\n}\n"
|
||||
headers:
|
||||
CF-RAY:
|
||||
- CF-RAY-XXX
|
||||
Connection:
|
||||
- keep-alive
|
||||
Content-Type:
|
||||
- application/json
|
||||
Date:
|
||||
- Tue, 03 Feb 2026 00:22:40 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:
|
||||
- '515'
|
||||
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
|
||||
@@ -0,0 +1,247 @@
|
||||
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\nCalculate the sum
|
||||
of the first 3 prime numbers, then multiply that result by 2. Show your work
|
||||
for each step.\n\n## Expected Output\nComplete the task successfully\n\n## Available
|
||||
Tools\nNo tools available\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\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-mini","tool_choice":"auto","tools":[{"type":"function","function":{"name":"create_reasoning_plan","description":"Create
|
||||
or refine a reasoning plan for a task","strict":true,"parameters":{"type":"object","properties":{"plan":{"type":"string","description":"The
|
||||
detailed reasoning plan for the task."},"ready":{"type":"boolean","description":"Whether
|
||||
the agent is ready to execute the task."}},"required":["plan","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:
|
||||
- '1636'
|
||||
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-D4yTWa7FxCHkHwHF25AYXXeJDBOuY\",\n \"object\":
|
||||
\"chat.completion\",\n \"created\": 1770078150,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n
|
||||
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
|
||||
\"assistant\",\n \"content\": \"## Execution Plan\\n\\n1. Identify
|
||||
the first 3 prime numbers: 2, 3, and 5.\\n2. Calculate the sum: \\\\(2 + 3
|
||||
+ 5 = 10\\\\).\\n3. Multiply the sum by 2: \\\\(10 \\\\times 2 = 20\\\\).\\n\\nREADY:
|
||||
I am ready to execute the task.\",\n \"refusal\": null,\n \"annotations\":
|
||||
[]\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n
|
||||
\ }\n ],\n \"usage\": {\n \"prompt_tokens\": 299,\n \"completion_tokens\":
|
||||
74,\n \"total_tokens\": 373,\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_1590f93f9d\"\n}\n"
|
||||
headers:
|
||||
CF-RAY:
|
||||
- CF-RAY-XXX
|
||||
Connection:
|
||||
- keep-alive
|
||||
Content-Type:
|
||||
- application/json
|
||||
Date:
|
||||
- Tue, 03 Feb 2026 00:22:32 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:
|
||||
- '1716'
|
||||
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 Math Tutor. An expert
|
||||
math tutor who breaks down problems step by step\nYour personal goal is: Solve
|
||||
multi-step math problems accurately"},{"role":"user","content":"\nCurrent Task:
|
||||
Calculate the sum of the first 3 prime numbers, then multiply that result by
|
||||
2. Show your work for each step.\n\nProvide your complete response:"}],"model":"gpt-4o-mini"}'
|
||||
headers:
|
||||
User-Agent:
|
||||
- X-USER-AGENT-XXX
|
||||
accept:
|
||||
- application/json
|
||||
accept-encoding:
|
||||
- ACCEPT-ENCODING-XXX
|
||||
authorization:
|
||||
- AUTHORIZATION-XXX
|
||||
connection:
|
||||
- keep-alive
|
||||
content-length:
|
||||
- '400'
|
||||
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-D4yTYJgCZf2oY7wiPMZmN4QEQhHb5\",\n \"object\":
|
||||
\"chat.completion\",\n \"created\": 1770078152,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n
|
||||
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
|
||||
\"assistant\",\n \"content\": \"To solve the problem, let's break it
|
||||
down into two main steps: \\n\\n1. Calculate the sum of the first 3 prime
|
||||
numbers.\\n2. Multiply the result of that sum by 2.\\n\\n### Step 1: Identify
|
||||
the first 3 prime numbers\\nPrime numbers are natural numbers greater than
|
||||
1 that have no positive divisors other than 1 and themselves. \\n\\nThe first
|
||||
three prime numbers are:\\n- 2\\n- 3\\n- 5\\n\\n### Step 2: Calculate the
|
||||
sum of the first 3 prime numbers\\nNow, we add these prime numbers together:\\n\\n\\\\[\\n2
|
||||
+ 3 + 5\\n\\\\]\\n\\nCalculating this step-by-step:\\n- First, add 2 and 3:\\n
|
||||
\ \\\\[\\n 2 + 3 = 5\\n \\\\]\\n \\n- Next, add this result to 5:\\n \\\\[\\n
|
||||
\ 5 + 5 = 10\\n \\\\]\\n\\nSo, the sum of the first 3 prime numbers is \\\\(10\\\\).\\n\\n###
|
||||
Step 3: Multiply the sum by 2\\nNext, we take the sum we calculated and multiply
|
||||
it by 2:\\n\\n\\\\[\\n10 \\\\times 2\\n\\\\]\\n\\nCalculating this:\\n\\\\[\\n10
|
||||
\\\\times 2 = 20\\n\\\\]\\n\\n### Final Answer\\nThus, the final result obtained
|
||||
after performing all the steps is:\\n\\n\\\\[\\n\\\\boxed{20}\\n\\\\]\",\n
|
||||
\ \"refusal\": null,\n \"annotations\": []\n },\n \"logprobs\":
|
||||
null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
|
||||
74,\n \"completion_tokens\": 288,\n \"total_tokens\": 362,\n \"prompt_tokens_details\":
|
||||
{\n \"cached_tokens\": 0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\":
|
||||
{\n \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\":
|
||||
0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\":
|
||||
\"default\",\n \"system_fingerprint\": \"fp_1590f93f9d\"\n}\n"
|
||||
headers:
|
||||
CF-RAY:
|
||||
- CF-RAY-XXX
|
||||
Connection:
|
||||
- keep-alive
|
||||
Content-Type:
|
||||
- application/json
|
||||
Date:
|
||||
- Tue, 03 Feb 2026 00:22:37 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:
|
||||
- '4751'
|
||||
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
|
||||
@@ -0,0 +1,108 @@
|
||||
interactions:
|
||||
- request:
|
||||
body: '{"messages":[{"role":"system","content":"You are Math Assistant. A helpful
|
||||
assistant\nYour personal goal is: Help solve simple math problems"},{"role":"user","content":"\nCurrent
|
||||
Task: What is 5 + 5?\n\nProvide your complete response:"}],"model":"gpt-4o-mini"}'
|
||||
headers:
|
||||
User-Agent:
|
||||
- X-USER-AGENT-XXX
|
||||
accept:
|
||||
- application/json
|
||||
accept-encoding:
|
||||
- ACCEPT-ENCODING-XXX
|
||||
authorization:
|
||||
- AUTHORIZATION-XXX
|
||||
connection:
|
||||
- keep-alive
|
||||
content-length:
|
||||
- '260'
|
||||
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-D4yXGD5IrieoUDSK5hDmJyA2gJtDc\",\n \"object\":
|
||||
\"chat.completion\",\n \"created\": 1770078382,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n
|
||||
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
|
||||
\"assistant\",\n \"content\": \"5 + 5 equals 10.\",\n \"refusal\":
|
||||
null,\n \"annotations\": []\n },\n \"logprobs\": null,\n
|
||||
\ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
|
||||
47,\n \"completion_tokens\": 8,\n \"total_tokens\": 55,\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_1590f93f9d\"\n}\n"
|
||||
headers:
|
||||
CF-RAY:
|
||||
- CF-RAY-XXX
|
||||
Connection:
|
||||
- keep-alive
|
||||
Content-Type:
|
||||
- application/json
|
||||
Date:
|
||||
- Tue, 03 Feb 2026 00:26:23 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:
|
||||
- '363'
|
||||
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
|
||||
@@ -0,0 +1,242 @@
|
||||
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\nConvert 100 degrees
|
||||
Celsius to Fahrenheit, then round the result to the nearest 10.\n\n## Expected
|
||||
Output\nComplete the task successfully\n\n## Available Tools\nNo tools available\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\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-mini","tool_choice":"auto","tools":[{"type":"function","function":{"name":"create_reasoning_plan","description":"Create
|
||||
or refine a reasoning plan for a task","strict":true,"parameters":{"type":"object","properties":{"plan":{"type":"string","description":"The
|
||||
detailed reasoning plan for the task."},"ready":{"type":"boolean","description":"Whether
|
||||
the agent is ready to execute the task."}},"required":["plan","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:
|
||||
- '1610'
|
||||
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-D4yTN8fHOefyzzhvdUOHjxdFDR2HW\",\n \"object\":
|
||||
\"chat.completion\",\n \"created\": 1770078141,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n
|
||||
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
|
||||
\"assistant\",\n \"content\": \"## Execution Plan\\n\\n1. Convert 100
|
||||
degrees Celsius to Fahrenheit using the formula: \\\\( F = C \\\\times \\\\frac{9}{5}
|
||||
+ 32 \\\\).\\n2. Round the Fahrenheit result to the nearest 10.\\n\\nREADY:
|
||||
I am ready to execute the task.\",\n \"refusal\": null,\n \"annotations\":
|
||||
[]\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n
|
||||
\ }\n ],\n \"usage\": {\n \"prompt_tokens\": 291,\n \"completion_tokens\":
|
||||
58,\n \"total_tokens\": 349,\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_1590f93f9d\"\n}\n"
|
||||
headers:
|
||||
CF-RAY:
|
||||
- CF-RAY-XXX
|
||||
Connection:
|
||||
- keep-alive
|
||||
Content-Type:
|
||||
- application/json
|
||||
Date:
|
||||
- Tue, 03 Feb 2026 00:22:22 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:
|
||||
- '1089'
|
||||
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 Unit Converter. A precise
|
||||
unit conversion specialist\nYour personal goal is: Accurately convert between
|
||||
units and apply transformations"},{"role":"user","content":"\nCurrent Task:
|
||||
Convert 100 degrees Celsius to Fahrenheit, then round the result to the nearest
|
||||
10.\n\nProvide your complete response:"}],"model":"gpt-4o-mini"}'
|
||||
headers:
|
||||
User-Agent:
|
||||
- X-USER-AGENT-XXX
|
||||
accept:
|
||||
- application/json
|
||||
accept-encoding:
|
||||
- ACCEPT-ENCODING-XXX
|
||||
authorization:
|
||||
- AUTHORIZATION-XXX
|
||||
connection:
|
||||
- keep-alive
|
||||
content-length:
|
||||
- '373'
|
||||
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-D4yTPQewXDyPdYHI4dHPH7YGHcRge\",\n \"object\":
|
||||
\"chat.completion\",\n \"created\": 1770078143,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n
|
||||
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
|
||||
\"assistant\",\n \"content\": \"To convert degrees Celsius to Fahrenheit,
|
||||
you can use the formula:\\n\\n\\\\[ F = \\\\left( C \\\\times \\\\frac{9}{5}
|
||||
\\\\right) + 32 \\\\]\\n\\nPlugging in 100 degrees Celsius:\\n\\n\\\\[ F =
|
||||
\\\\left( 100 \\\\times \\\\frac{9}{5} \\\\right) + 32 \\\\]\\n\\nCalculating
|
||||
that step-by-step:\\n\\n1. Multiply 100 by 9: \\n \\\\[ 100 \\\\times 9
|
||||
= 900 \\\\]\\n\\n2. Divide by 5:\\n \\\\[ 900 \\\\div 5 = 180 \\\\]\\n\\n3.
|
||||
Add 32:\\n \\\\[ 180 + 32 = 212 \\\\]\\n\\nSo, 100 degrees Celsius is equal
|
||||
to 212 degrees Fahrenheit.\\n\\nNow, rounding 212 to the nearest 10:\\n\\nThe
|
||||
nearest multiple of 10 to 212 is 210.\\n\\nTherefore, the final result is
|
||||
**210 degrees Fahrenheit**.\",\n \"refusal\": null,\n \"annotations\":
|
||||
[]\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n
|
||||
\ }\n ],\n \"usage\": {\n \"prompt_tokens\": 63,\n \"completion_tokens\":
|
||||
191,\n \"total_tokens\": 254,\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_1590f93f9d\"\n}\n"
|
||||
headers:
|
||||
CF-RAY:
|
||||
- CF-RAY-XXX
|
||||
Connection:
|
||||
- keep-alive
|
||||
Content-Type:
|
||||
- application/json
|
||||
Date:
|
||||
- Tue, 03 Feb 2026 00:22:26 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:
|
||||
- '3736'
|
||||
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
|
||||
@@ -1,6 +1,10 @@
|
||||
interactions:
|
||||
- request:
|
||||
body: '{"messages":[{"role":"system","content":"You are test role. test backstory\nYour personal goal is: test goal\nTo give my best complete final answer to the task respond using the exact following format:\n\nThought: I now can give a great answer\nFinal Answer: Your final answer must be the great and the most complete as possible, it must be outcome described.\n\nI MUST use these formats, my job depends on it!"},{"role":"user","content":"\nCurrent Task: Calculate 2 + 2\n\nThis is the expected criteria for your final answer: The result of the calculation\nyou MUST return the actual complete content as the final answer, not a summary.\n\nBegin! This is VERY important to you, use the tools available and give your best Final Answer, your job depends on it!\n\nThought:"}],"model":"gpt-4o-mini"}'
|
||||
body: '{"messages":[{"role":"system","content":"You are test role. test backstory\nYour
|
||||
personal goal is: test goal"},{"role":"user","content":"\nCurrent Task: Calculate
|
||||
2 + 2\n\nThis is the expected criteria for your final answer: The result of
|
||||
the calculation\nyou MUST return the actual complete content as the final answer,
|
||||
not a summary.\n\nProvide your complete response:"}],"model":"gpt-4o-mini"}'
|
||||
headers:
|
||||
User-Agent:
|
||||
- X-USER-AGENT-XXX
|
||||
@@ -13,7 +17,7 @@ interactions:
|
||||
connection:
|
||||
- keep-alive
|
||||
content-length:
|
||||
- '797'
|
||||
- '396'
|
||||
content-type:
|
||||
- application/json
|
||||
host:
|
||||
@@ -35,13 +39,23 @@ interactions:
|
||||
x-stainless-runtime:
|
||||
- CPython
|
||||
x-stainless-runtime-version:
|
||||
- 3.12.10
|
||||
- 3.13.3
|
||||
method: POST
|
||||
uri: https://api.openai.com/v1/chat/completions
|
||||
response:
|
||||
body:
|
||||
string: "{\n \"id\": \"chatcmpl-CjDsYJQa2tIYBbNloukSWecpsTvdK\",\n \"object\": \"chat.completion\",\n \"created\": 1764894146,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"I now can give a great answer \\nFinal Answer: The result of the calculation 2 + 2 is 4.\",\n \"refusal\": null,\n \"annotations\": []\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 161,\n \"completion_tokens\": 25,\n \"total_tokens\": 186,\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_11f3029f6b\"\
|
||||
\n}\n"
|
||||
string: "{\n \"id\": \"chatcmpl-D5DTjYe6n92Rjo4Ox6NiZpAAdBLF0\",\n \"object\":
|
||||
\"chat.completion\",\n \"created\": 1770135823,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n
|
||||
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
|
||||
\"assistant\",\n \"content\": \"The result of the calculation 2 + 2
|
||||
is 4.\",\n \"refusal\": null,\n \"annotations\": []\n },\n
|
||||
\ \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n ],\n
|
||||
\ \"usage\": {\n \"prompt_tokens\": 75,\n \"completion_tokens\": 14,\n
|
||||
\ \"total_tokens\": 89,\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_1590f93f9d\"\n}\n"
|
||||
headers:
|
||||
CF-RAY:
|
||||
- CF-RAY-XXX
|
||||
@@ -50,7 +64,7 @@ interactions:
|
||||
Content-Type:
|
||||
- application/json
|
||||
Date:
|
||||
- Fri, 05 Dec 2025 00:22:27 GMT
|
||||
- Tue, 03 Feb 2026 16:23:43 GMT
|
||||
Server:
|
||||
- cloudflare
|
||||
Set-Cookie:
|
||||
@@ -70,13 +84,11 @@ interactions:
|
||||
openai-organization:
|
||||
- OPENAI-ORG-XXX
|
||||
openai-processing-ms:
|
||||
- '516'
|
||||
- '636'
|
||||
openai-project:
|
||||
- OPENAI-PROJECT-XXX
|
||||
openai-version:
|
||||
- '2020-10-01'
|
||||
x-envoy-upstream-service-time:
|
||||
- '529'
|
||||
x-openai-proxy-wasm:
|
||||
- v0.1
|
||||
x-ratelimit-limit-requests:
|
||||
|
||||
@@ -1,6 +1,12 @@
|
||||
interactions:
|
||||
- request:
|
||||
body: '{"messages":[{"role":"system","content":"You are test role. test backstory\nYour personal goal is: test goal\nTo give my best complete final answer to the task respond using the exact following format:\n\nThought: I now can give a great answer\nFinal Answer: Your final answer must be the great and the most complete as possible, it must be outcome described.\n\nI MUST use these formats, my job depends on it!"},{"role":"user","content":"\nCurrent Task: Summarize the given context in one sentence\n\nThis is the expected criteria for your final answer: A one-sentence summary\nyou MUST return the actual complete content as the final answer, not a summary.\n\nThis is the context you''re working with:\nThe quick brown fox jumps over the lazy dog. This sentence contains every letter of the alphabet.\n\nBegin! This is VERY important to you, use the tools available and give your best Final Answer, your job depends on it!\n\nThought:"}],"model":"gpt-3.5-turbo"}'
|
||||
body: '{"messages":[{"role":"system","content":"You are test role. test backstory\nYour
|
||||
personal goal is: test goal"},{"role":"user","content":"\nCurrent Task: Summarize
|
||||
the given context in one sentence\n\nThis is the expected criteria for your
|
||||
final answer: A one-sentence summary\nyou MUST return the actual complete content
|
||||
as the final answer, not a summary.\n\nThis is the context you''re working with:\nThe
|
||||
quick brown fox jumps over the lazy dog. This sentence contains every letter
|
||||
of the alphabet.\n\nProvide your complete response:"}],"model":"gpt-3.5-turbo"}'
|
||||
headers:
|
||||
User-Agent:
|
||||
- X-USER-AGENT-XXX
|
||||
@@ -13,7 +19,7 @@ interactions:
|
||||
connection:
|
||||
- keep-alive
|
||||
content-length:
|
||||
- '963'
|
||||
- '562'
|
||||
content-type:
|
||||
- application/json
|
||||
host:
|
||||
@@ -35,13 +41,23 @@ interactions:
|
||||
x-stainless-runtime:
|
||||
- CPython
|
||||
x-stainless-runtime-version:
|
||||
- 3.12.10
|
||||
- 3.13.3
|
||||
method: POST
|
||||
uri: https://api.openai.com/v1/chat/completions
|
||||
response:
|
||||
body:
|
||||
string: "{\n \"id\": \"chatcmpl-CjDtsaX0LJ0dzZz02KwKeRGYgazv1\",\n \"object\": \"chat.completion\",\n \"created\": 1764894228,\n \"model\": \"gpt-3.5-turbo-0125\",\n \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"I now can give a great answer\\n\\nFinal Answer: The quick brown fox jumps over the lazy dog. This sentence contains every letter of the alphabet.\",\n \"refusal\": null,\n \"annotations\": []\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 191,\n \"completion_tokens\": 30,\n \"total_tokens\": 221,\n \"prompt_tokens_details\": {\n \"cached_tokens\": 0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\": {\n \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\": 0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\"\
|
||||
: \"default\",\n \"system_fingerprint\": null\n}\n"
|
||||
string: "{\n \"id\": \"chatcmpl-D5DTn6yIQ7HpIn5j5Bsbag1efzXPa\",\n \"object\":
|
||||
\"chat.completion\",\n \"created\": 1770135827,\n \"model\": \"gpt-3.5-turbo-0125\",\n
|
||||
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
|
||||
\"assistant\",\n \"content\": \"The quick brown fox jumps over the
|
||||
lazy dog. This sentence contains every letter of the alphabet.\",\n \"refusal\":
|
||||
null,\n \"annotations\": []\n },\n \"logprobs\": null,\n
|
||||
\ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
|
||||
105,\n \"completion_tokens\": 19,\n \"total_tokens\": 124,\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\": null\n}\n"
|
||||
headers:
|
||||
CF-RAY:
|
||||
- CF-RAY-XXX
|
||||
@@ -50,7 +66,7 @@ interactions:
|
||||
Content-Type:
|
||||
- application/json
|
||||
Date:
|
||||
- Fri, 05 Dec 2025 00:23:49 GMT
|
||||
- Tue, 03 Feb 2026 16:23:48 GMT
|
||||
Server:
|
||||
- cloudflare
|
||||
Set-Cookie:
|
||||
@@ -70,13 +86,11 @@ interactions:
|
||||
openai-organization:
|
||||
- OPENAI-ORG-XXX
|
||||
openai-processing-ms:
|
||||
- '506'
|
||||
- '606'
|
||||
openai-project:
|
||||
- OPENAI-PROJECT-XXX
|
||||
openai-version:
|
||||
- '2020-10-01'
|
||||
x-envoy-upstream-service-time:
|
||||
- '559'
|
||||
x-openai-proxy-wasm:
|
||||
- v0.1
|
||||
x-ratelimit-limit-requests:
|
||||
|
||||
@@ -1,6 +1,10 @@
|
||||
interactions:
|
||||
- request:
|
||||
body: '{"messages":[{"role":"system","content":"You are test role. test backstory\nYour personal goal is: test goal\nTo give my best complete final answer to the task respond using the exact following format:\n\nThought: I now can give a great answer\nFinal Answer: Your final answer must be the great and the most complete as possible, it must be outcome described.\n\nI MUST use these formats, my job depends on it!"},{"role":"user","content":"\nCurrent Task: Write a haiku about AI\n\nThis is the expected criteria for your final answer: A haiku (3 lines, 5-7-5 syllable pattern) about AI\nyou MUST return the actual complete content as the final answer, not a summary.\n\nBegin! This is VERY important to you, use the tools available and give your best Final Answer, your job depends on it!\n\nThought:"}],"model":"gpt-3.5-turbo","max_tokens":50,"temperature":0.7}'
|
||||
body: '{"messages":[{"role":"system","content":"You are test role. test backstory\nYour
|
||||
personal goal is: test goal"},{"role":"user","content":"\nCurrent Task: Write
|
||||
a haiku about AI\n\nThis is the expected criteria for your final answer: A haiku
|
||||
(3 lines, 5-7-5 syllable pattern) about AI\nyou MUST return the actual complete
|
||||
content as the final answer, not a summary.\n\nProvide your complete response:"}],"model":"gpt-3.5-turbo","max_tokens":50,"temperature":0.7}'
|
||||
headers:
|
||||
User-Agent:
|
||||
- X-USER-AGENT-XXX
|
||||
@@ -13,7 +17,7 @@ interactions:
|
||||
connection:
|
||||
- keep-alive
|
||||
content-length:
|
||||
- '861'
|
||||
- '460'
|
||||
content-type:
|
||||
- application/json
|
||||
host:
|
||||
@@ -35,13 +39,23 @@ interactions:
|
||||
x-stainless-runtime:
|
||||
- CPython
|
||||
x-stainless-runtime-version:
|
||||
- 3.12.10
|
||||
- 3.13.3
|
||||
method: POST
|
||||
uri: https://api.openai.com/v1/chat/completions
|
||||
response:
|
||||
body:
|
||||
string: "{\n \"id\": \"chatcmpl-CjDqr2BmEXQ08QzZKslTZJZ5vV9lo\",\n \"object\": \"chat.completion\",\n \"created\": 1764894041,\n \"model\": \"gpt-3.5-turbo-0125\",\n \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"I now can give a great answer\\n\\nFinal Answer: \\nIn circuits they thrive, \\nArtificial minds awake, \\nFuture's coded drive.\",\n \"refusal\": null,\n \"annotations\": []\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 174,\n \"completion_tokens\": 29,\n \"total_tokens\": 203,\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\": null\n}\n"
|
||||
string: "{\n \"id\": \"chatcmpl-D5DTgAqxaC8RmEvikXK0UDaxmVmf9\",\n \"object\":
|
||||
\"chat.completion\",\n \"created\": 1770135820,\n \"model\": \"gpt-3.5-turbo-0125\",\n
|
||||
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
|
||||
\"assistant\",\n \"content\": \"Artificial minds,\\nCode and circuits
|
||||
intertwine,\\nFuture undefined.\",\n \"refusal\": null,\n \"annotations\":
|
||||
[]\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n
|
||||
\ }\n ],\n \"usage\": {\n \"prompt_tokens\": 88,\n \"completion_tokens\":
|
||||
13,\n \"total_tokens\": 101,\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\": null\n}\n"
|
||||
headers:
|
||||
CF-RAY:
|
||||
- CF-RAY-XXX
|
||||
@@ -50,7 +64,7 @@ interactions:
|
||||
Content-Type:
|
||||
- application/json
|
||||
Date:
|
||||
- Fri, 05 Dec 2025 00:20:41 GMT
|
||||
- Tue, 03 Feb 2026 16:23:40 GMT
|
||||
Server:
|
||||
- cloudflare
|
||||
Set-Cookie:
|
||||
@@ -70,13 +84,11 @@ interactions:
|
||||
openai-organization:
|
||||
- OPENAI-ORG-XXX
|
||||
openai-processing-ms:
|
||||
- '434'
|
||||
- '277'
|
||||
openai-project:
|
||||
- OPENAI-PROJECT-XXX
|
||||
openai-version:
|
||||
- '2020-10-01'
|
||||
x-envoy-upstream-service-time:
|
||||
- '456'
|
||||
x-openai-proxy-wasm:
|
||||
- v0.1
|
||||
x-ratelimit-limit-requests:
|
||||
|
||||
@@ -0,0 +1,231 @@
|
||||
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\nWhat is 9 + 11?\n\n##
|
||||
Expected Output\nA number\n\n## Available Tools\nNo tools available\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\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-mini","tool_choice":"auto","tools":[{"type":"function","function":{"name":"create_reasoning_plan","description":"Create
|
||||
or refine a reasoning plan for a task","strict":true,"parameters":{"type":"object","properties":{"plan":{"type":"string","description":"The
|
||||
detailed reasoning plan for the task."},"ready":{"type":"boolean","description":"Whether
|
||||
the agent is ready to execute the task."}},"required":["plan","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:
|
||||
- '1520'
|
||||
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-D4yVACNTzZcghQRwt5kFYQ4HAvbgI\",\n \"object\":
|
||||
\"chat.completion\",\n \"created\": 1770078252,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n
|
||||
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
|
||||
\"assistant\",\n \"content\": \"## Execution Plan\\n1. Calculate the
|
||||
sum of 9 and 11.\\n \\nREADY: I am ready to execute the task.\",\n \"refusal\":
|
||||
null,\n \"annotations\": []\n },\n \"logprobs\": null,\n
|
||||
\ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
|
||||
279,\n \"completion_tokens\": 28,\n \"total_tokens\": 307,\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_1590f93f9d\"\n}\n"
|
||||
headers:
|
||||
CF-RAY:
|
||||
- CF-RAY-XXX
|
||||
Connection:
|
||||
- keep-alive
|
||||
Content-Type:
|
||||
- application/json
|
||||
Date:
|
||||
- Tue, 03 Feb 2026 00:24:13 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:
|
||||
- '951'
|
||||
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 Math Assistant. A helpful
|
||||
math tutor\nYour personal goal is: Help solve math problems"},{"role":"user","content":"\nCurrent
|
||||
Task: What is 9 + 11?\n\nPlanning:\n## Execution Plan\n1. Calculate the sum
|
||||
of 9 and 11.\n \nREADY: I am ready to execute the task.\n\nThis is the expected
|
||||
criteria for your final answer: A number\nyou MUST return the actual complete
|
||||
content as the final answer, not a summary.\n\nProvide your complete response:"}],"model":"gpt-4o-mini"}'
|
||||
headers:
|
||||
User-Agent:
|
||||
- X-USER-AGENT-XXX
|
||||
accept:
|
||||
- application/json
|
||||
accept-encoding:
|
||||
- ACCEPT-ENCODING-XXX
|
||||
authorization:
|
||||
- AUTHORIZATION-XXX
|
||||
connection:
|
||||
- keep-alive
|
||||
content-length:
|
||||
- '513'
|
||||
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-D4yVBdTCKSdfcJYlIOX9BbzrObgFI\",\n \"object\":
|
||||
\"chat.completion\",\n \"created\": 1770078253,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n
|
||||
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
|
||||
\"assistant\",\n \"content\": \"9 + 11 = 20\",\n \"refusal\":
|
||||
null,\n \"annotations\": []\n },\n \"logprobs\": null,\n
|
||||
\ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
|
||||
105,\n \"completion_tokens\": 7,\n \"total_tokens\": 112,\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_1590f93f9d\"\n}\n"
|
||||
headers:
|
||||
CF-RAY:
|
||||
- CF-RAY-XXX
|
||||
Connection:
|
||||
- keep-alive
|
||||
Content-Type:
|
||||
- application/json
|
||||
Date:
|
||||
- Tue, 03 Feb 2026 00:24:13 GMT
|
||||
Server:
|
||||
- cloudflare
|
||||
Strict-Transport-Security:
|
||||
- STS-XXX
|
||||
Transfer-Encoding:
|
||||
- chunked
|
||||
X-Content-Type-Options:
|
||||
- X-CONTENT-TYPE-XXX
|
||||
access-control-expose-headers:
|
||||
- ACCESS-CONTROL-XXX
|
||||
alt-svc:
|
||||
- h3=":443"; ma=86400
|
||||
cf-cache-status:
|
||||
- DYNAMIC
|
||||
openai-organization:
|
||||
- OPENAI-ORG-XXX
|
||||
openai-processing-ms:
|
||||
- '477'
|
||||
openai-project:
|
||||
- OPENAI-PROJECT-XXX
|
||||
openai-version:
|
||||
- '2020-10-01'
|
||||
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
|
||||
@@ -0,0 +1,243 @@
|
||||
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\nCalculate the area
|
||||
of a circle with radius 5 (use pi = 3.14)\n\n## Expected Output\nThe area as
|
||||
a number\n\n## Available Tools\nNo tools available\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\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-mini","tool_choice":"auto","tools":[{"type":"function","function":{"name":"create_reasoning_plan","description":"Create
|
||||
or refine a reasoning plan for a task","strict":true,"parameters":{"type":"object","properties":{"plan":{"type":"string","description":"The
|
||||
detailed reasoning plan for the task."},"ready":{"type":"boolean","description":"Whether
|
||||
the agent is ready to execute the task."}},"required":["plan","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:
|
||||
- '1577'
|
||||
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-D4yVCdA1csIzfoHSQvxkfrA4gDn4z\",\n \"object\":
|
||||
\"chat.completion\",\n \"created\": 1770078254,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n
|
||||
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
|
||||
\"assistant\",\n \"content\": \"## Execution Plan\\n1. Multiply the
|
||||
radius (5) by itself (5) to get the square of the radius.\\n2. Multiply the
|
||||
squared radius by pi (3.14) to calculate the area.\\n\\nREADY: I am ready
|
||||
to execute the task.\",\n \"refusal\": null,\n \"annotations\":
|
||||
[]\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n
|
||||
\ }\n ],\n \"usage\": {\n \"prompt_tokens\": 293,\n \"completion_tokens\":
|
||||
54,\n \"total_tokens\": 347,\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_1590f93f9d\"\n}\n"
|
||||
headers:
|
||||
CF-RAY:
|
||||
- CF-RAY-XXX
|
||||
Connection:
|
||||
- keep-alive
|
||||
Content-Type:
|
||||
- application/json
|
||||
Date:
|
||||
- Tue, 03 Feb 2026 00:24:15 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:
|
||||
- '845'
|
||||
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 Math Tutor. An expert
|
||||
tutor\nYour personal goal is: Solve complex math problems step by step"},{"role":"user","content":"\nCurrent
|
||||
Task: Calculate the area of a circle with radius 5 (use pi = 3.14)\n\nPlanning:\n##
|
||||
Execution Plan\n1. Multiply the radius (5) by itself (5) to get the square of
|
||||
the radius.\n2. Multiply the squared radius by pi (3.14) to calculate the area.\n\nREADY:
|
||||
I am ready to execute the task.\n\nThis is the expected criteria for your final
|
||||
answer: The area as a number\nyou MUST return the actual complete content as
|
||||
the final answer, not a summary.\n\nProvide your complete response:"}],"model":"gpt-4o-mini"}'
|
||||
headers:
|
||||
User-Agent:
|
||||
- X-USER-AGENT-XXX
|
||||
accept:
|
||||
- application/json
|
||||
accept-encoding:
|
||||
- ACCEPT-ENCODING-XXX
|
||||
authorization:
|
||||
- AUTHORIZATION-XXX
|
||||
connection:
|
||||
- keep-alive
|
||||
content-length:
|
||||
- '682'
|
||||
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-D4yVDh2U2xx3qeYHcDQvbetOmVCxb\",\n \"object\":
|
||||
\"chat.completion\",\n \"created\": 1770078255,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n
|
||||
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
|
||||
\"assistant\",\n \"content\": \"To calculate the area of a circle with
|
||||
a radius of 5, we will follow the steps outlined in the execution plan.\\n\\n1.
|
||||
**Square the radius**:\\n \\\\[\\n 5 \\\\times 5 = 25\\n \\\\]\\n\\n2.
|
||||
**Multiply the squared radius by pi (using \\\\(\\\\pi \\\\approx 3.14\\\\))**:\\n
|
||||
\ \\\\[\\n \\\\text{Area} = \\\\pi \\\\times (\\\\text{radius})^2 = 3.14
|
||||
\\\\times 25\\n \\\\]\\n\\n Now, let's perform the multiplication:\\n
|
||||
\ \\\\[\\n 3.14 \\\\times 25 = 78.5\\n \\\\]\\n\\nThus, the area of the
|
||||
circle is \\\\( \\\\boxed{78.5} \\\\).\",\n \"refusal\": null,\n \"annotations\":
|
||||
[]\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n
|
||||
\ }\n ],\n \"usage\": {\n \"prompt_tokens\": 147,\n \"completion_tokens\":
|
||||
155,\n \"total_tokens\": 302,\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_1590f93f9d\"\n}\n"
|
||||
headers:
|
||||
CF-RAY:
|
||||
- CF-RAY-XXX
|
||||
Connection:
|
||||
- keep-alive
|
||||
Content-Type:
|
||||
- application/json
|
||||
Date:
|
||||
- Tue, 03 Feb 2026 00:24:18 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:
|
||||
- '2228'
|
||||
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
|
||||
@@ -1,7 +1,11 @@
|
||||
interactions:
|
||||
- request:
|
||||
body: '{"messages":[{"role":"system","content":"You are test role. test backstory\nYour personal goal is: test goal\nYou ONLY have access to the following tools, and should NEVER make up tools that are not listed here:\n\nTool Name: dummy_tool\nTool Arguments: {''query'': {''description'': None, ''type'': ''str''}}\nTool Description: Useful for when you need to get a dummy result for a query.\n\nIMPORTANT: Use the following format in your response:\n\n```\nThought: you should always think about what to do\nAction: the action to take, only one name of [dummy_tool], just the name, exactly as it''s written.\nAction Input: the input to the action, just a simple JSON object, enclosed in curly braces, using \" to wrap keys and values.\nObservation: the result of the action\n```\n\nOnce all necessary information is gathered, return the following format:\n\n```\nThought: I now know the final answer\nFinal Answer: the final answer to the original input question\n```"},{"role":"user","content":"\nCurrent
|
||||
Task: Use the dummy tool to get a result for ''test query''\n\nThis is the expected criteria for your final answer: The result from the dummy tool\nyou MUST return the actual complete content as the final answer, not a summary.\n\nBegin! This is VERY important to you, use the tools available and give your best Final Answer, your job depends on it!\n\nThought:"}],"model":"gpt-3.5-turbo"}'
|
||||
body: '{"messages":[{"role":"system","content":"You are test role. test backstory\nYour
|
||||
personal goal is: test goal"},{"role":"user","content":"\nCurrent Task: Use
|
||||
the dummy tool to get a result for ''test query''\n\nThis is the expected criteria
|
||||
for your final answer: The result from the dummy tool\nyou MUST return the actual
|
||||
complete content as the final answer, not a summary."}],"model":"gpt-3.5-turbo","tool_choice":"auto","tools":[{"type":"function","function":{"name":"dummy_tool","description":"Useful
|
||||
for when you need to get a dummy result for a query.","strict":true,"parameters":{"properties":{"query":{"title":"Query","type":"string"}},"required":["query"],"type":"object","additionalProperties":false}}}]}'
|
||||
headers:
|
||||
User-Agent:
|
||||
- X-USER-AGENT-XXX
|
||||
@@ -14,7 +18,7 @@ interactions:
|
||||
connection:
|
||||
- keep-alive
|
||||
content-length:
|
||||
- '1381'
|
||||
- '712'
|
||||
content-type:
|
||||
- application/json
|
||||
host:
|
||||
@@ -36,12 +40,26 @@ interactions:
|
||||
x-stainless-runtime:
|
||||
- CPython
|
||||
x-stainless-runtime-version:
|
||||
- 3.12.10
|
||||
- 3.13.3
|
||||
method: POST
|
||||
uri: https://api.openai.com/v1/chat/completions
|
||||
response:
|
||||
body:
|
||||
string: "{\n \"id\": \"chatcmpl-CjDrE1Z8bFQjjxI2vDPPKgtOTm28p\",\n \"object\": \"chat.completion\",\n \"created\": 1764894064,\n \"model\": \"gpt-3.5-turbo-0125\",\n \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"you should always think about what to do\",\n \"refusal\": null,\n \"annotations\": []\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 289,\n \"completion_tokens\": 8,\n \"total_tokens\": 297,\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\": null\n}\n"
|
||||
string: "{\n \"id\": \"chatcmpl-D5DTlUmKYee1DaS5AqnaUCZ6B14xV\",\n \"object\":
|
||||
\"chat.completion\",\n \"created\": 1770135825,\n \"model\": \"gpt-3.5-turbo-0125\",\n
|
||||
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
|
||||
\"assistant\",\n \"content\": null,\n \"tool_calls\": [\n {\n
|
||||
\ \"id\": \"call_tBCgelchfQjXXJrrM15MxqGJ\",\n \"type\":
|
||||
\"function\",\n \"function\": {\n \"name\": \"dummy_tool\",\n
|
||||
\ \"arguments\": \"{\\\"query\\\":\\\"test query\\\"}\"\n }\n
|
||||
\ }\n ],\n \"refusal\": null,\n \"annotations\":
|
||||
[]\n },\n \"logprobs\": null,\n \"finish_reason\": \"tool_calls\"\n
|
||||
\ }\n ],\n \"usage\": {\n \"prompt_tokens\": 122,\n \"completion_tokens\":
|
||||
16,\n \"total_tokens\": 138,\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\": null\n}\n"
|
||||
headers:
|
||||
CF-RAY:
|
||||
- CF-RAY-XXX
|
||||
@@ -50,7 +68,7 @@ interactions:
|
||||
Content-Type:
|
||||
- application/json
|
||||
Date:
|
||||
- Fri, 05 Dec 2025 00:21:05 GMT
|
||||
- Tue, 03 Feb 2026 16:23:46 GMT
|
||||
Server:
|
||||
- cloudflare
|
||||
Set-Cookie:
|
||||
@@ -70,13 +88,124 @@ interactions:
|
||||
openai-organization:
|
||||
- OPENAI-ORG-XXX
|
||||
openai-processing-ms:
|
||||
- '379'
|
||||
- '694'
|
||||
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 test role. test backstory\nYour
|
||||
personal goal is: test goal"},{"role":"user","content":"\nCurrent Task: Use
|
||||
the dummy tool to get a result for ''test query''\n\nThis is the expected criteria
|
||||
for your final answer: The result from the dummy tool\nyou MUST return the actual
|
||||
complete content as the final answer, not a summary."},{"role":"assistant","content":null,"tool_calls":[{"id":"call_tBCgelchfQjXXJrrM15MxqGJ","type":"function","function":{"name":"dummy_tool","arguments":"{\"query\":\"test
|
||||
query\"}"}}]},{"role":"tool","tool_call_id":"call_tBCgelchfQjXXJrrM15MxqGJ","name":"dummy_tool","content":"Dummy
|
||||
result for: test query"},{"role":"user","content":"Analyze the tool result.
|
||||
If requirements are met, provide the Final Answer. Otherwise, call the next
|
||||
tool. Deliver only the answer without meta-commentary."}],"model":"gpt-3.5-turbo","tool_choice":"auto","tools":[{"type":"function","function":{"name":"dummy_tool","description":"Useful
|
||||
for when you need to get a dummy result for a query.","strict":true,"parameters":{"properties":{"query":{"title":"Query","type":"string"}},"required":["query"],"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:
|
||||
- '1202'
|
||||
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-D5DTmxZJI2Ee7fHNc9dYtQkD7sIY2\",\n \"object\":
|
||||
\"chat.completion\",\n \"created\": 1770135826,\n \"model\": \"gpt-3.5-turbo-0125\",\n
|
||||
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
|
||||
\"assistant\",\n \"content\": \"Dummy result for: test query\",\n \"refusal\":
|
||||
null,\n \"annotations\": []\n },\n \"logprobs\": null,\n
|
||||
\ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
|
||||
188,\n \"completion_tokens\": 7,\n \"total_tokens\": 195,\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\": null\n}\n"
|
||||
headers:
|
||||
CF-RAY:
|
||||
- CF-RAY-XXX
|
||||
Connection:
|
||||
- keep-alive
|
||||
Content-Type:
|
||||
- application/json
|
||||
Date:
|
||||
- Tue, 03 Feb 2026 16:23:47 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:
|
||||
- '416'
|
||||
openai-project:
|
||||
- OPENAI-PROJECT-XXX
|
||||
openai-version:
|
||||
- '2020-10-01'
|
||||
x-envoy-upstream-service-time:
|
||||
- '399'
|
||||
x-openai-proxy-wasm:
|
||||
- v0.1
|
||||
x-ratelimit-limit-requests:
|
||||
|
||||
@@ -0,0 +1,110 @@
|
||||
interactions:
|
||||
- request:
|
||||
body: '{"messages":[{"role":"system","content":"You are Math Assistant. A helpful
|
||||
assistant\nYour personal goal is: Help solve math problems"},{"role":"user","content":"\nCurrent
|
||||
Task: What is 12 * 3?\n\nThis is the expected criteria for your final answer:
|
||||
A number\nyou MUST return the actual complete content as the final answer, not
|
||||
a summary.\n\nProvide your complete response:"}],"model":"gpt-4o-mini"}'
|
||||
headers:
|
||||
User-Agent:
|
||||
- X-USER-AGENT-XXX
|
||||
accept:
|
||||
- application/json
|
||||
accept-encoding:
|
||||
- ACCEPT-ENCODING-XXX
|
||||
authorization:
|
||||
- AUTHORIZATION-XXX
|
||||
connection:
|
||||
- keep-alive
|
||||
content-length:
|
||||
- '400'
|
||||
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-D4yVCw0CGLFmcVvniplwCCt8avtRb\",\n \"object\":
|
||||
\"chat.completion\",\n \"created\": 1770078254,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n
|
||||
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
|
||||
\"assistant\",\n \"content\": \"12 * 3 = 36\",\n \"refusal\":
|
||||
null,\n \"annotations\": []\n },\n \"logprobs\": null,\n
|
||||
\ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
|
||||
75,\n \"completion_tokens\": 7,\n \"total_tokens\": 82,\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_1590f93f9d\"\n}\n"
|
||||
headers:
|
||||
CF-RAY:
|
||||
- CF-RAY-XXX
|
||||
Connection:
|
||||
- keep-alive
|
||||
Content-Type:
|
||||
- application/json
|
||||
Date:
|
||||
- Tue, 03 Feb 2026 00:24:14 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:
|
||||
- '331'
|
||||
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
|
||||
@@ -0,0 +1,243 @@
|
||||
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\nFind the first
|
||||
3 prime numbers, add them together, then multiply by 2.\n\n## Expected Output\nComplete
|
||||
the task successfully\n\n## Available Tools\nNo tools available\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\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-mini","tool_choice":"auto","tools":[{"type":"function","function":{"name":"create_reasoning_plan","description":"Create
|
||||
or refine a reasoning plan for a task","strict":true,"parameters":{"type":"object","properties":{"plan":{"type":"string","description":"The
|
||||
detailed reasoning plan for the task."},"ready":{"type":"boolean","description":"Whether
|
||||
the agent is ready to execute the task."}},"required":["plan","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:
|
||||
- '1597'
|
||||
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-D4yU0MD5GfSUjRW0R4cBmFJ6Hcjbi\",\n \"object\":
|
||||
\"chat.completion\",\n \"created\": 1770078180,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n
|
||||
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
|
||||
\"assistant\",\n \"content\": \"### Execution Plan\\n1. Identify the
|
||||
first 3 prime numbers: 2, 3, and 5.\\n2. Add the prime numbers together: 2
|
||||
+ 3 + 5 = 10.\\n3. Multiply the sum by 2: 10 * 2 = 20.\\n\\nREADY: I am ready
|
||||
to execute the task.\",\n \"refusal\": null,\n \"annotations\":
|
||||
[]\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n
|
||||
\ }\n ],\n \"usage\": {\n \"prompt_tokens\": 291,\n \"completion_tokens\":
|
||||
73,\n \"total_tokens\": 364,\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_1590f93f9d\"\n}\n"
|
||||
headers:
|
||||
CF-RAY:
|
||||
- CF-RAY-XXX
|
||||
Connection:
|
||||
- keep-alive
|
||||
Content-Type:
|
||||
- application/json
|
||||
Date:
|
||||
- Tue, 03 Feb 2026 00:23:02 GMT
|
||||
Server:
|
||||
- cloudflare
|
||||
Set-Cookie:
|
||||
- SET-COOKIE-XXX
|
||||
Strict-Transport-Security:
|
||||
- STS-XXX
|
||||
Transfer-Encoding:
|
||||
- chunked
|
||||
X-Content-Type-Options:
|
||||
- X-CONTENT-TYPE-XXX
|
||||
access-control-expose-headers:
|
||||
- ACCESS-CONTROL-XXX
|
||||
alt-svc:
|
||||
- h3=":443"; ma=86400
|
||||
cf-cache-status:
|
||||
- DYNAMIC
|
||||
openai-organization:
|
||||
- OPENAI-ORG-XXX
|
||||
openai-processing-ms:
|
||||
- '1253'
|
||||
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 Math Tutor. An expert
|
||||
tutor who explains step by step\nYour personal goal is: Solve multi-step math
|
||||
problems"},{"role":"user","content":"\nCurrent Task: Find the first 3 prime
|
||||
numbers, add them together, then multiply by 2.\n\nProvide your complete response:"}],"model":"gpt-4o-mini"}'
|
||||
headers:
|
||||
User-Agent:
|
||||
- X-USER-AGENT-XXX
|
||||
accept:
|
||||
- application/json
|
||||
accept-encoding:
|
||||
- ACCEPT-ENCODING-XXX
|
||||
authorization:
|
||||
- AUTHORIZATION-XXX
|
||||
connection:
|
||||
- keep-alive
|
||||
content-length:
|
||||
- '333'
|
||||
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-D4yU2qY6Xqpkz2D5yVAwagQzuPpen\",\n \"object\":
|
||||
\"chat.completion\",\n \"created\": 1770078182,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n
|
||||
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
|
||||
\"assistant\",\n \"content\": \"To solve the problem, let\u2019s go
|
||||
through each step methodically.\\n\\n1. **Identify the first three prime numbers**:\\n
|
||||
\ - **Prime numbers** are numbers greater than 1 that have no positive divisors
|
||||
other than 1 and themselves.\\n - The first three prime numbers are:\\n
|
||||
\ - 2\\n - 3\\n - 5\\n\\n2. **Add these prime numbers together**:\\n
|
||||
\ - We add them together:\\n \\\\[\\n 2 + 3 + 5\\n \\\\]\\n -
|
||||
Performing the addition step-by-step:\\n - First, add 2 and 3:\\n \\\\[\\n
|
||||
\ 2 + 3 = 5\\n \\\\]\\n - Then add 5 to this result:\\n \\\\[\\n
|
||||
\ 5 + 5 = 10\\n \\\\]\\n - So, the sum of the first three prime
|
||||
numbers is **10**.\\n\\n3. **Multiply the sum by 2**:\\n - Now we multiply
|
||||
the result by 2:\\n \\\\[\\n 10 \\\\times 2 = 20\\n \\\\]\\n \\nTherefore,
|
||||
the final answer is **20**.\",\n \"refusal\": null,\n \"annotations\":
|
||||
[]\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n
|
||||
\ }\n ],\n \"usage\": {\n \"prompt_tokens\": 62,\n \"completion_tokens\":
|
||||
236,\n \"total_tokens\": 298,\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_1590f93f9d\"\n}\n"
|
||||
headers:
|
||||
CF-RAY:
|
||||
- CF-RAY-XXX
|
||||
Connection:
|
||||
- keep-alive
|
||||
Content-Type:
|
||||
- application/json
|
||||
Date:
|
||||
- Tue, 03 Feb 2026 00:23:06 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:
|
||||
- '3846'
|
||||
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
|
||||
@@ -0,0 +1,238 @@
|
||||
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\nWhat is 15 + 27?\n\n##
|
||||
Expected Output\nComplete the task successfully\n\n## Available Tools\nNo tools
|
||||
available\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\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-mini","tool_choice":"auto","tools":[{"type":"function","function":{"name":"create_reasoning_plan","description":"Create
|
||||
or refine a reasoning plan for a task","strict":true,"parameters":{"type":"object","properties":{"plan":{"type":"string","description":"The
|
||||
detailed reasoning plan for the task."},"ready":{"type":"boolean","description":"Whether
|
||||
the agent is ready to execute the task."}},"required":["plan","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:
|
||||
- '1543'
|
||||
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-D4yTrm3GkzDX47DIcce9uA3iF8kFE\",\n \"object\":
|
||||
\"chat.completion\",\n \"created\": 1770078171,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n
|
||||
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
|
||||
\"assistant\",\n \"content\": \"## Execution Plan\\n\\n1. Calculate
|
||||
the sum of 15 and 27.\\n\\nREADY: I am ready to execute the task.\",\n \"refusal\":
|
||||
null,\n \"annotations\": []\n },\n \"logprobs\": null,\n
|
||||
\ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
|
||||
281,\n \"completion_tokens\": 27,\n \"total_tokens\": 308,\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_1590f93f9d\"\n}\n"
|
||||
headers:
|
||||
CF-RAY:
|
||||
- CF-RAY-XXX
|
||||
Connection:
|
||||
- keep-alive
|
||||
Content-Type:
|
||||
- application/json
|
||||
Date:
|
||||
- Tue, 03 Feb 2026 00:22:51 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:
|
||||
- '691'
|
||||
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 Math Assistant. A helpful
|
||||
math tutor\nYour personal goal is: Help solve math problems step by step"},{"role":"user","content":"\nCurrent
|
||||
Task: What is 15 + 27?\n\nProvide your complete response:"}],"model":"gpt-4o-mini"}'
|
||||
headers:
|
||||
User-Agent:
|
||||
- X-USER-AGENT-XXX
|
||||
accept:
|
||||
- application/json
|
||||
accept-encoding:
|
||||
- ACCEPT-ENCODING-XXX
|
||||
authorization:
|
||||
- AUTHORIZATION-XXX
|
||||
connection:
|
||||
- keep-alive
|
||||
content-length:
|
||||
- '269'
|
||||
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-D4yTrUOvExA9fTFDwYxvG4xEgRP6L\",\n \"object\":
|
||||
\"chat.completion\",\n \"created\": 1770078171,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n
|
||||
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
|
||||
\"assistant\",\n \"content\": \"To solve the problem \\\\( 15 + 27
|
||||
\\\\), we can follow these steps:\\n\\n1. **Align the numbers**: Write them
|
||||
one on top of the other, aligned by their rightmost digits:\\n\\n ```\\n
|
||||
\ 15\\n + 27\\n ```\\n\\n2. **Add the units place**: Start from the
|
||||
rightmost digits (units place):\\n - \\\\( 5 + 7 = 12 \\\\)\\n - Write
|
||||
down 2 and carry over 1.\\n\\n3. **Add the tens place**: Now, move to the
|
||||
next column (tens place):\\n - \\\\( 1 + 2 + 1 \\\\) (the 1 is from the
|
||||
carry) \\\\( = 4 \\\\)\\n\\n4. **Combine the results**: Now, combine the results
|
||||
from the tens and units places:\\n - The result in the tens place is 4 and
|
||||
in the units place is 2, giving us \\\\( 42 \\\\).\\n\\nTherefore, \\\\( 15
|
||||
+ 27 = 42 \\\\).\",\n \"refusal\": null,\n \"annotations\":
|
||||
[]\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n
|
||||
\ }\n ],\n \"usage\": {\n \"prompt_tokens\": 50,\n \"completion_tokens\":
|
||||
209,\n \"total_tokens\": 259,\n \"prompt_tokens_details\": {\n \"cached_tokens\":
|
||||
0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\":
|
||||
{\n \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\":
|
||||
0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\":
|
||||
\"default\",\n \"system_fingerprint\": \"fp_1590f93f9d\"\n}\n"
|
||||
headers:
|
||||
CF-RAY:
|
||||
- CF-RAY-XXX
|
||||
Connection:
|
||||
- keep-alive
|
||||
Content-Type:
|
||||
- application/json
|
||||
Date:
|
||||
- Tue, 03 Feb 2026 00:22:55 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:
|
||||
- '3263'
|
||||
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
|
||||
@@ -0,0 +1,110 @@
|
||||
interactions:
|
||||
- request:
|
||||
body: '{"messages":[{"role":"system","content":"You are Math Assistant. A helpful
|
||||
assistant\nYour personal goal is: Help solve math problems"},{"role":"user","content":"\nCurrent
|
||||
Task: What is 100 / 4?\n\nProvide your complete response:"}],"model":"gpt-4o-mini"}'
|
||||
headers:
|
||||
User-Agent:
|
||||
- X-USER-AGENT-XXX
|
||||
accept:
|
||||
- application/json
|
||||
accept-encoding:
|
||||
- ACCEPT-ENCODING-XXX
|
||||
authorization:
|
||||
- AUTHORIZATION-XXX
|
||||
connection:
|
||||
- keep-alive
|
||||
content-length:
|
||||
- '255'
|
||||
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-D4yU6mFapBLuCx4fJtYBup52dwwrs\",\n \"object\":
|
||||
\"chat.completion\",\n \"created\": 1770078186,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n
|
||||
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
|
||||
\"assistant\",\n \"content\": \"To solve the problem 100 divided by
|
||||
4, you can perform the division as follows:\\n\\n100 \xF7 4 = 25\\n\\nSo,
|
||||
the answer is 25.\",\n \"refusal\": null,\n \"annotations\":
|
||||
[]\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n
|
||||
\ }\n ],\n \"usage\": {\n \"prompt_tokens\": 46,\n \"completion_tokens\":
|
||||
36,\n \"total_tokens\": 82,\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_1590f93f9d\"\n}\n"
|
||||
headers:
|
||||
CF-RAY:
|
||||
- CF-RAY-XXX
|
||||
Connection:
|
||||
- keep-alive
|
||||
Content-Type:
|
||||
- application/json
|
||||
Date:
|
||||
- Tue, 03 Feb 2026 00:23:07 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:
|
||||
- '1098'
|
||||
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
|
||||
@@ -0,0 +1,108 @@
|
||||
interactions:
|
||||
- request:
|
||||
body: '{"messages":[{"role":"system","content":"You are Math Assistant. A helpful
|
||||
assistant\nYour personal goal is: Help solve math problems"},{"role":"user","content":"\nCurrent
|
||||
Task: What is 8 * 7?\n\nProvide your complete response:"}],"model":"gpt-4o-mini"}'
|
||||
headers:
|
||||
User-Agent:
|
||||
- X-USER-AGENT-XXX
|
||||
accept:
|
||||
- application/json
|
||||
accept-encoding:
|
||||
- ACCEPT-ENCODING-XXX
|
||||
authorization:
|
||||
- AUTHORIZATION-XXX
|
||||
connection:
|
||||
- keep-alive
|
||||
content-length:
|
||||
- '253'
|
||||
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-D4yTqLFhGtfq2CyS2aPPhiZL4GjtQ\",\n \"object\":
|
||||
\"chat.completion\",\n \"created\": 1770078170,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n
|
||||
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
|
||||
\"assistant\",\n \"content\": \"8 * 7 equals 56.\",\n \"refusal\":
|
||||
null,\n \"annotations\": []\n },\n \"logprobs\": null,\n
|
||||
\ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
|
||||
46,\n \"completion_tokens\": 8,\n \"total_tokens\": 54,\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_1590f93f9d\"\n}\n"
|
||||
headers:
|
||||
CF-RAY:
|
||||
- CF-RAY-XXX
|
||||
Connection:
|
||||
- keep-alive
|
||||
Content-Type:
|
||||
- application/json
|
||||
Date:
|
||||
- Tue, 03 Feb 2026 00:22:50 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:
|
||||
- '443'
|
||||
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
|
||||
Reference in New Issue
Block a user