mirror of
https://github.com/langbot-app/LangBot.git
synced 2026-07-25 05:46:13 +00:00
Junyan Chin
e9dd584792
* 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.
70 lines
3.5 KiB
YAML
70 lines
3.5 KiB
YAML
id: langrag-parser-golden-e2e
|
|
title: "LangRAG and GeneralParsers retrieve a structured golden document"
|
|
mode: agent-browser
|
|
area: knowledge
|
|
type: regression
|
|
priority: p1
|
|
risk: high
|
|
ci_eligible: false
|
|
tags:
|
|
- golden
|
|
- e2e
|
|
- langrag
|
|
- parser
|
|
- knowledge
|
|
skills:
|
|
- langbot-env-setup
|
|
- langbot-testing
|
|
env:
|
|
- LANGBOT_FRONTEND_URL
|
|
- LANGBOT_BACKEND_URL
|
|
- LANGBOT_REPO
|
|
- LANGBOT_WEB_REPO
|
|
- LANGBOT_RAG_PLUGIN_REPO
|
|
- LANGBOT_PARSER_PLUGIN_REPO
|
|
preconditions:
|
|
- "LANGBOT_REPO and plugin repo env values point to the worktrees intended for this golden parser/RAG run."
|
|
- "The active LangBot environment can build and install local LangRAG and GeneralParsers plugin packages."
|
|
- "A working embedding model is available before the Knowledge UI path starts."
|
|
steps:
|
|
- "Use LANGBOT_REPO as the active LangBot worktree and confirm it is the current master worktree for this run."
|
|
- "Start or verify the LangBot backend and frontend from LANGBOT_REPO and LANGBOT_WEB_REPO."
|
|
- "Build local plugin zips from LANGBOT_RAG_PLUGIN_REPO and LANGBOT_PARSER_PLUGIN_REPO using LANGBOT_REPO/.venv/bin/lbp build."
|
|
- "Open LANGBOT_FRONTEND_URL."
|
|
- "Navigate to Plugins and install or update the local LangRAG zip and GeneralParsers zip."
|
|
- "Wait until both plugins are initialized: langbot-team/LangRAG and langbot-team/GeneralParsers."
|
|
- "Navigate to Knowledge."
|
|
- "Create a knowledge base with engine LangRAG and a working embedding model, preferably chroma-all-MiniLM-L6-v2."
|
|
- "Keep index type Chunk for this golden case."
|
|
- "Upload skills/langbot-testing/fixtures/rag/parser-golden.html."
|
|
- "When the upload UI asks for a parser, select GeneralParsers for text/html."
|
|
- "Wait until the document row status is Completed."
|
|
- "Open Retrieve Test and query: What is the parser-rag golden sentinel and which parser/engine pair is documented? Return the exact sentinel and pair."
|
|
checks:
|
|
- "UI: Plugins shows langbot-team/LangRAG initialized."
|
|
- "UI: Plugins shows langbot-team/GeneralParsers initialized."
|
|
- "UI: The upload flow selects GeneralParsers for the HTML fixture, or the parser selector clearly defaults to GeneralParsers."
|
|
- "UI: The uploaded parser-golden.html document status becomes Completed."
|
|
- "UI: Retrieve Test result contains aurora-parser-rag-9137."
|
|
- "UI: Retrieve Test result contains GeneralParsers and LangRAG."
|
|
- "UI: Retrieve Test result preserves the table as Markdown, including '| Parser field | Golden value |'."
|
|
- "Console: No unexpected frontend errors appear during plugin install, KB creation, upload, or retrieve."
|
|
- "Logs: Backend/plugin logs show GeneralParsers parsed parser-golden.html and LangRAG used pre-parsed external parser content."
|
|
evidence_required:
|
|
- ui
|
|
- screenshot
|
|
- console
|
|
- backend_log
|
|
diagnostics:
|
|
- "If LangRAG is missing, check /api/v1/knowledge/engines for plugin id langbot-team/LangRAG."
|
|
- "If GeneralParsers is missing, check /api/v1/knowledge/parsers?mime_type=text/html for plugin id langbot-team/GeneralParsers."
|
|
- "If GeneralParsers local install fails on PyMuPDF, confirm the active LangBot master venv can import fitz and retry Upload Local."
|
|
- "If the document completes but table pipes are missing, inspect logs for LangRAG fallback to the internal FileParser instead of external parser content."
|
|
- "If embedding selection is empty, confirm the test embedding model exists under embedding_models, not llm_models."
|
|
troubleshooting:
|
|
- plugin-runtime-timeout
|
|
- plugin-dependency-install-offline
|
|
- marketplace-network-flaky
|
|
- dynamic-form-missing-config-id
|
|
- proxy-env-mismatch
|