deer-flow/AGENTS.md
Ryker_Feng cf02646489
feat(scripts): add redacted community support bundle generator (#3886)
* feat(scripts): add redacted community support bundle generator

Add `make support-bundle` (scripts/support_bundle.py) to help users file
high-signal, privacy-safe GitHub issues for local setup/config/runtime
problems.

The command produces:
- `*-issue-summary.md` to paste into the issue body
- `*-issue-draft.md` scaffold for AI-assisted filing (REQUIRED placeholders,
  never invents repro/expected/summary facts)
- an optional evidence zip under `.deer-flow/support-bundles/` containing a
  stable `triage.json` plus redacted environment/config/extensions/git/doctor
  evidence

Privacy: secrets are redacted across config values, URL userinfo, query
strings, CLI flags, custom headers, bearer/sk- tokens, and home paths. The
bundle never includes `.env`, raw conversation messages, or user file
contents; optional `--thread-id` adds file manifests only. `thread_id` input
is validated against path traversal.

Wire it into the Makefile, AGENTS.md, README/README_zh, CONTRIBUTING, and the
bug-report issue template. Covered by backend/tests/test_support_bundle.py.

* fix(scripts): redact MCP env values by default in support bundle

Address PR #3886 review (willem-bd, P2): the key-name allowlist let literal
secrets under non-standard env keys (e.g. SUPABASE_SERVICE_ROLE_KEY,
R2_ACCESS_KEY, hardcoded AIza… keys) leak verbatim into the bundle that users
are told is safe to share publicly.

Mask all MCP `env` values by default, keeping only `$VAR`/`${VAR}` references
visible, and broaden SECRET_KEY_RE (access_key, pwd, private_key). Add tests
for non-keyword env secrets, broadened key names, and end-to-end zip redaction.
2026-07-01 22:30:55 +08:00

6.8 KiB

AGENTS.md

This file provides guidance to AI coding agents (Claude Code, Codex, and others) when working with code in this repository. It is the source of truth; the sibling CLAUDE.md imports it via @AGENTS.md.

It is the monorepo orientation layer: it maps the whole repo and points to the module guides that own the depth. For anything inside a module, read that module's guide rather than expecting full detail here:

  • backend/AGENTS.md — backend depth: harness/app split, agent & middleware chain, sandbox, MCP, skills, memory, IM channels, persistence/migrations, config system, test layout.
  • frontend/AGENTS.md — frontend depth: Next.js App Router layout, thread/streaming data flow, code style, commands.

What is DeerFlow

DeerFlow is a LangGraph-based AI super-agent system with a full-stack architecture. The backend runs a "super agent" with sandboxed execution, persistent memory, subagent delegation, and extensible tools (built-in, MCP, community), all per-thread isolated. The frontend is a Next.js chat UI. External IM platforms (Feishu, Slack, Telegram, Discord, DingTalk) bridge into the same agent through the Gateway.

Service Topology

A single make dev / Docker stack runs four cooperating services:

Service Port Role
Nginx 2026 Unified reverse-proxy entry point — open this in the browser
Gateway API 8001 FastAPI REST API + embedded LangGraph-compatible agent runtime
Frontend 3000 Next.js web interface
Provisioner 8002 Optional — only when sandbox is configured for provisioner/K8s mode

Nginx is the single public entry: it serves the frontend and proxies /api/langgraph/* to the Gateway's LangGraph runtime, rewriting it to Gateway's native /api/* routes; all other /api/* go straight to the Gateway REST routers. See backend/AGENTS.md for the runtime and router detail.

Repository Map

deer-flow/
├── Makefile                        # Root orchestration: drives the full stack (dev/start/stop, docker, setup)
├── config.example.yaml             # Template → copy to config.yaml (gitignored) at repo root
├── extensions_config.example.json  # Template → copy to extensions_config.json (gitignored): MCP servers + skills
├── backend/                        # Python backend — see backend/AGENTS.md
│   ├── Makefile                    # Per-module backend commands (dev, gateway, test, lint, migrate-rev)
│   ├── packages/harness/           # deerflow-harness package (import: deerflow.*) — agent framework
│   └── app/                        # FastAPI Gateway + IM channels (import: app.*)
├── frontend/                       # Next.js frontend (pnpm) — see frontend/AGENTS.md
├── docker/                         # docker-compose files, nginx config, provisioner
├── skills/                         # Agent skills: public/ (committed), custom/ (gitignored)
├── contracts/                      # Cross-component JSON contracts (e.g. subagent status)
├── scripts/                        # Root orchestration scripts invoked by the Makefile (check, configure, doctor, support_bundle, serve, docker, deploy, setup_wizard)
├── tests/                          # Root-level tests (currently tests/skills/ — public skill tests)
└── docs/                           # Cross-cutting docs, plans, and design notes

Runtime config lives at the repo root: copy config.example.yamlconfig.yaml (main app config) and extensions_config.example.jsonextensions_config.json (MCP servers + skills). Both real files are gitignored and may be edited at runtime via the Gateway API. Config schema and resolution order are documented in backend/AGENTS.md.

Commands: Root vs. Module

Root make targets drive the whole stack (run from the repo root):

make setup       # Interactive setup wizard (recommended for new users)
make doctor      # Check configuration and system requirements
make support-bundle  # Generate redacted troubleshooting summary, AI issue draft, and optional zip
make config      # Generate local config files from the examples
make check       # Check that required tools are installed
make install     # Install all dependencies (frontend + backend + pre-commit hooks)
make dev         # Start all services with hot-reload (Gateway + Frontend + Nginx)
make start       # Start all services in production mode (local, optimized)
make stop        # Stop all running services
make up / down   # Build/stop the production Docker stack (browser at localhost:2026)
make docker-start / docker-stop / docker-logs   # Docker development environment

Run make help for the full list.

Per-module commands drive a single module (run inside that module):

# Backend (see backend/AGENTS.md for the full set)
cd backend && make dev        # Gateway API with reload (port 8001)
cd backend && make test       # Backend test suite
cd backend && make lint       # ruff check
cd backend && make format     # ruff format

# Frontend (see frontend/AGENTS.md for the full set)
cd frontend && pnpm dev       # Dev server with Turbopack (port 3000)
cd frontend && pnpm check     # Lint + type check (run before committing)
cd frontend && pnpm test      # Unit tests

Rule of thumb: root make = the full application; backend/Makefile and frontend/ (pnpm) = per-module work.

Where to Go Next

Cross-Cutting Conventions

These apply repo-wide; module guides own the module-specific detail.

  • Documentation update policy — keep docs in sync with code: update README.md for user-facing changes and the relevant AGENTS.md for development/architecture changes in the same change set.
  • Test-driven development — features and bug fixes ship with tests. Backend tests live in backend/tests/ (TDD is mandatory there; see backend/AGENTS.md); frontend tests live in frontend/tests/.
  • Format before pushing — run make format (backend) / pnpm check (frontend). Backend CI enforces ruff format --check, so formatting must be clean before a push.