mirror of
https://github.com/rennf93/roboco.git
synced 2026-08-03 07:23:24 +02:00
Renn F
6422f77bb9
An adversarial audit of the piragi -> in-house swap surfaced nine confirmed issues; this fixes all of them. - Re-ingest now REPLACES a source's chunks instead of appending. Add VectorStore.delete_by_source and BaseIndexPlugin.replace_on_reingest (default True), called before add_chunks in both ingest paths. Without it every startup / periodic / manual reindex appended a fresh copy of each doc's chunks, growing the tables unbounded and crowding out distinct results. Conversations opt OUT (replace_on_reingest=False): their many messages share one source URI, so delete-by-source would wipe history. - index_* now honor the plugin IngestResult. The explicit record endpoints (error / standard / decision / review / learning) raise on failure instead of writing a green tracking row for content that never persisted; conversation / journal indexing stays best-effort but skips the tracking row when the embed fails. index_message / index_entry return IngestResult. - A deprecated index type (code) now returns 404 instead of a 500 leaked from _get_plugin's missing-plugin error: add OptimalService.is_index_registered and guard the stats / clear / refresh routes. The panel drops the dead 'Code' category, filter, badge, label, and mock data. - Panel: getContext reads 'results' (matches SearchResponse) instead of a non-existent 'context' field; the reindex toast no longer reports phantom '0 code files'; the stats 'Updated' label uses the max timestamp across indexes rather than indexes[0]; ProactiveContextItem matches the wire shape. - Drop the always-zero per-document chunk_count from the documents API. - Remove dead RAG settings (hybrid_search, cross_encoder) the engine never consumed, and correct stale piragi / BM25 references in code, README, and CLAUDE.md. Delete the unused duplicate roboco/kb embedder package the swap shipped. Adds tests for replace-on-reingest (incl. the conversations carve-out) and the deprecated-index 404.
24 lines
1.1 KiB
Python
24 lines
1.1 KiB
Python
"""
|
|
MCP Servers for RoboCo
|
|
|
|
These MCP servers bridge Claude Code agents to the RoboCo APIs,
|
|
providing tool interfaces with built-in enforcement and guidance.
|
|
|
|
Servers:
|
|
- Flow MCP Server (``flow_server``) intent verbs (lifecycle)
|
|
- Do MCP Server (``do_server``) content tools (commit, push,
|
|
PR, journal, notify, message)
|
|
- Git Read-Only MCP Server (``git_readonly``) status, log, diff, branches
|
|
- Optimal MCP Server (``optimal_server``) knowledge base and RAG
|
|
- Docs MCP Server (``docs_server``) documentation file management
|
|
|
|
Do NOT eagerly re-export server factories here. Each server is launched
|
|
as its own subprocess via ``python -m roboco.mcp.<name>``, and importing
|
|
the ``roboco.mcp`` package first forces every sibling module to load —
|
|
most notably ``optimal_server``, which pulls in the pgvector/ollama stack and adds
|
|
~6s to startup. Claude Code times out slow MCP servers during
|
|
init, which manifests as "roboco-flow/do tools never register". Keep
|
|
this file empty-of-imports; callers import the specific module they
|
|
need directly.
|
|
"""
|