thanhnv
e0ab653a61
Complete the Project Context MCP MVP with the second read-only tool, search_project_knowledge, so an agent can go from an issue's requirement to the project documents that explain it, with citable evidence. Retrieval reuses what Cowork already owns instead of adding a vector DB, an embedding pipeline, or a new RAG framework: - core/projects.py already defines a project's knowledge as the files at its workspace root, so that folder is the entire corpus. Isolation is structural, not a filter applied after the fact. - core/doc_extract.py already extracts docx/pptx/xlsx/pdf/text, so the provider inherits format support and duplicates none of it. Security properties: - Read-only. The workspace root resolves from the identity, never from the request; project_id only verifies scope and is never routing authority. Symlinks escaping the workspace are dropped. - Policy runs before provider resolution; target and access resolution are separate seams so a pilot local root can become an on-behalf-of served backend without changing the tool or the provider. - Bounded output per detail mode with cursor pagination; no unlimited mode. Backend failures map to safe errors that leak no internals. score is honest term coverage, not a fabricated similarity; the upgrade path is documented on _score_chunk. Adds tests/test_project_context_knowledge.py (40 tests) and tests/test_project_context_e2e.py, which proves the two tools compose: issue -> requirement -> related knowledge -> evidence.
Cowork Local
Cowork Local is the internal AI cowork desktop platform owned by the Cowork Team. It provides the Cowork runtime, workspace and agent experiences, MCP/connectors, security controls, and model routing foundation.
The Cowork Team owns this product and its stable branch. The FSG AI Core Team contributes selected reusable capabilities through branches and Pull Requests; it is not the owner or final merger of this repository.
Quick start
The imported application is a Python/PySide6 package. Run it from the directory that contains cowork_local:
python -m cowork_local
The source snapshot does not include a complete runtime dependency manifest. Use the Cowork Team's supported runtime environment until that packaging contract is documented. The reliable automated test surface currently checked by CI is:
python -m pip install -r cowork_local/requirements-test.txt
python -m pytest cowork_local/tests -q
When already inside this repository, run python -m pytest tests -q.
Configuration and runtime data live under ~/.cowork_local/. Provider keys and local unlock codes must be supplied through environment variables or an approved secret manager; see .env.example.
Contributing
Start with START_CONTRIBUTING.md, then read CONTRIBUTING.md. Core AI task execution remains in fsg-ai-core-assets; source changes are reviewed as Pull Requests in this repository.
Security concerns should follow SECURITY.md. Ownership and completion rules are documented under docs/governance/.