Files
DocsGPT/docsgpt/agents/tools/think.py
T
Alex 574f96341e refactor: rename the application package to docsgpt
The backend import package is now docsgpt, the name it will carry on PyPI;
application was far too generic to install into anyone's site-packages.
git mv plus a mechanical rewrite of every import, dotted string and path
reference: 734 Python files, the compose files, Dockerfile, workflows, docs,
setup scripts, devcontainer, k8s manifests, vscode config, pytest and coverage
config, .gitignore. Behaviour is unchanged.

Kept for one release:
- A top-level application package whose meta-path finder resolves
  application.x.y to the already-imported docsgpt.x.y object, so old imports
  and entry points (celery -A application.app.celery,
  uvicorn application.asgi:asgi_app) keep working with a FutureWarning.
- Celery registers every application.* task name as an alias of its
  docsgpt.* task on start-up, so messages queued by the previous release still
  run. The redbeat key prefix moves to redbeat:docsgpt:v2: so schedule entries
  the previous release wrote are left unread instead of firing twice.

The backend image builds from the repository root (docker build -f
docsgpt/Dockerfile .) so it can ship the alias package; a root .dockerignore
allow-lists docsgpt/ and application/ and keeps caches, local data, .env
files, the sample index files and the Dockerfile out. Compose and the image
workflows point at the new context.
2026-09-07 10:20:43 +01:00

71 lines
2.0 KiB
Python

from docsgpt.agents.tools.base import Tool
THINK_TOOL_ID = "think"
THINK_TOOL_ENTRY = {
"name": "think",
"actions": [
{
"name": "reason",
"description": (
"Use this tool to think through your reasoning step by step "
"before deciding on your next action. Always reason before "
"searching or answering."
),
"active": True,
"parameters": {
"properties": {
"reasoning": {
"type": "string",
"description": "Your step-by-step reasoning and analysis",
"filled_by_llm": True,
"required": True,
}
}
},
}
],
}
class ThinkTool(Tool):
"""Pseudo-tool that captures chain-of-thought reasoning.
Returns a short acknowledgment so the LLM can continue.
The reasoning content is captured in tool_call data for transparency.
"""
internal = True
def __init__(self, config=None):
pass
def execute_action(self, action_name: str, **kwargs):
return "Continue."
def get_actions_metadata(self):
return [
{
"name": "reason",
"description": (
"Use this tool to think through a complex step — analyze "
"tool results, weigh options, or plan multi-step work — "
"before taking your next action."
),
"parameters": {
"properties": {
"reasoning": {
"type": "string",
"description": "Your step-by-step reasoning and analysis",
"filled_by_llm": True,
"required": True,
}
}
},
}
]
def get_config_requirements(self):
return {}