mirror of https://github.com/langbot-app/LangBot.git synced 2026-07-24 21:36:06 +00:00

Files

T

Junyan Chin e9dd584792 feat: MCP server + in-repo skills (agent-friendly platform) (#2269 )

* feat(api): support global API key from config.yaml (api.global_api_key)

Accept a config-defined global API key anywhere a web-UI key is accepted
(X-API-Key / Bearer), with no login session and no DB record. Useful for
automated deployments and AI agents (HTTP API + MCP). Defaults to empty
(disabled); does not require the lbk_ prefix.

- templates/config.yaml: add api.global_api_key with security notes
- service/apikey.py: verify_api_key checks global key first (constant-time)
- docs/API_KEY_AUTH.md: document the global key + security guidance
- tests: cover global-key match, prefix-free, fallback-to-db, disabled

* feat(mcp): expose LangBot management as an MCP server at /mcp

Add an MCP (Model Context Protocol) server so external AI agents can manage a
LangBot instance. Reuses the same API-key auth as the HTTP API (including the
config.yaml global API key).

- pkg/api/mcp/server.py: FastMCP server wrapping the service layer; 21 curated
  tools across system/bots/pipelines/models/knowledge/mcp-servers/skills
- pkg/api/mcp/mount.py: ASGI dispatcher fronting Quart; authenticates /mcp
  requests with an API key, runs the streamable-HTTP session manager lifespan
- controller/main.py: serve the wrapped ASGI app via hypercorn (was run_task)
- web: new 'MCP' tab in the API integration dialog showing endpoint, auth, and
  client config; i18n for 8 locales
- tests/manual/mcp_smoke.py: e2e check (401 unauth, list tools, call tools)

Tool surface is intentionally curated (not all ~25 route groups) to keep the
agent surface small, safe, and maintainable. Extend deliberately.

* feat(skills): add in-repo skills/ as the single source of truth

Migrate the agent skills + QA/e2e test harness from the (now archived)
langbot-app/langbot-skills repo into LangBot/skills/, and add four new skills.

Migrated:
- langbot-plugin-dev, langbot-testing (e2e), langbot-env-setup,
  langbot-skills-maintenance, langbot-eba-adapter-dev
- the bin/lbs CLI (src/, test/, scripts/, schemas/, qa-agent-docs/)

New:
- langbot-dev      core backend + web development
- langbot-deploy   Docker/K8s deployment + config.yaml + global API key
- langbot-mcp-ops  operating the LangBot MCP server (/mcp)
- langbot-space-ops operating the Space marketplace MCP server

- src/cli.ts repoRoot(): recognize the skills assets root (skills.index.json +
  bin/lbs) so the CLI works when nested inside the LangBot repo
- README.md: unified skill catalog; skills.index.json regenerated

Parity with source verified: bin/lbs validate + node test suite match the
source repo (only the uncommitted .lbpkg build-artifact fixture differs).

* docs(agents): document agent-facing surfaces + API/MCP/skills sync rule

* docs(readme): add 'Built for AI Agents' section across all locales

Highlight MCP server, in-repo skills (single source of truth), AGENTS.md
sync rule, and llms.txt. Cross-link LangBot Space MCP marketplace.

* style(mcp): fix ruff format + prettier lint in MCP server and API panel

* style(web): prettier format MCP i18n locale entries

* docs(skills): note MCP instance control in dev/testing skills

All development-guidance skills now point to the LangBot instance MCP
server (/mcp) and the Space marketplace MCP server, reusing API keys.

2026-06-20 15:14:47 +08:00

1.7 KiB

Raw Blame History

Pipeline Debug Chat

Goal

Verify that a pipeline can receive a private debug message and return a bot response through the configured frontend.

Path

Open LANGBOT_FRONTEND_URL from skills/.env or the active user-provided environment.
Navigate to Pipelines.
Open the target pipeline.
Select Debug Chat.

Send a short deterministic prompt, for example:

请只回复 OK，用于前端调试测试。

Success Criteria

The UI should show:

A User message containing the prompt.
A Bot message containing the expected response, for example OK.

When the prompt itself contains a sentinel token, do not treat document.body containing that token as success. Confirm the token appears in a Bot/assistant message, WebSocket history entry, or backend completion log.

For scripts/e2e/pipeline-debug-chat.mjs, inspect automation-result.json when a sentinel is present in the prompt. A pass should show the expected text in a new assistant message; the after_assistant_expected_count value must increase beyond before_assistant_expected_count. If only the user prompt contains the sentinel, the run is a failure even when the page body contains enough total occurrences.

The backend log should include:

Processing request from person_websocket...
Streaming completed

Failure Criteria

Treat the test as failed if:

Only the user message appears.
The page shows Agent runner temporarily unavailable.
Backend logs contain All models failed during streaming setup.
Backend logs contain Action invoke_llm_stream call timed out.
Backend logs contain Action list_plugins call timed out.

When failures match these signatures, read troubleshooting.md.

1.7 KiB Raw Blame History