mirror of https://github.com/langbot-app/LangBot.git synced 2026-08-09 12:40:59 +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

2.1 KiB

Raw Blame History

Dify AgentRunner

Use this reference when validating langbot/dify-agent through LangBot WebUI.

Prepare Dify

Use a Dify Service API key from the target Dify app. Do not print the key in reports.
For Dify Agent Chat apps, configure LangBot app-type as agent.
Dify Agent Chat Service API may reject direct blocking mode with Agent Chat App does not support blocking mode; use streaming for direct diagnostics.

LangBot Configuration

Open LANGBOT_FRONTEND_URL.
Navigate to Pipelines and open the target pipeline.
Open Configuration > AI.
Select runner Dify.
Configure:
- Base URL: usually https://api.dify.ai/v1
- App Type: Agent for Dify Agent Chat apps
- API Key: Dify Service API key
- Base Prompt: short neutral prompt unless the case needs a specific prompt
- Timeout: at least 60 when testing through proxies
Save before using Debug Chat.

Debug Chat Check

Send a prompt with a unique sentinel:

Reply exactly with LANGBOT_DIFY_<date_or_random> and nothing else.

Pass only when:

UI shows a Bot message containing the sentinel.
WebSocket history or DOM inspection confirms the sentinel is in an assistant/bot message, not only in the user message.
Backend logs show the request completed, for example HTTP Request: POST https://api.dify.ai/v1/chat-messages "HTTP/1.1 200 OK" and Conversation(0) Streaming completed.

Diagnostics

GET /api/v1/pipelines/{uuid} can confirm the saved runner id is plugin:langbot/dify-agent/default and runner config contains app-type, base-url, and api-key.
Direct Dify streaming API calls are useful only to distinguish invalid Dify credentials from LangBot runner issues.
If Debug Chat returns Agent runner execution failed, inspect backend logs before changing UI settings.

Known Failure Signatures

AttributeError: 'ActorContext' object has no attribute 'type': runner code is reading old actor fields; see troubleshooting agent-runner-actor-context-fields.
Multiple runner options display as 默认: component labels are ambiguous; see troubleshooting ambiguous-runner-default-label.

2.1 KiB Raw Blame History