"""search — semantic search across the user's notes and tasks. Mirrors the existing fable-mcp contract so Claude's prior usage pattern keeps working. Differences from fable-mcp: - calls services.embeddings.semantic_search_notes directly instead of HTTP - user_id comes from mcp.current_user_id() rather than a global API key """ from __future__ import annotations import time from scribe.mcp._context import current_user_id from scribe.services.access import owner_names_for from scribe.services.embeddings import DEFAULT_SIMILARITY_THRESHOLD, semantic_search_notes from scribe.services.retrieval_telemetry import record_retrieval async def search( q: str, content_type: str = "all", limit: int = 10, project_id: int = 0, ) -> dict: """Semantic search over the user's existing notes and tasks — Scribe's recall. Reach for this BEFORE answering a question about the user's work or starting a task: the user's second-brain almost always already holds related prior art. Check for an existing ticket before opening a new one (search with content_type='task'), and for prior notes/decisions before re-deriving them. Treating Scribe as the first place to look — not a place to only write — is the difference between it being a trustworthy record and a write-only log. Args: q: search query string. content_type: 'all' (default), 'note' (notes only), or 'task' (tasks only). limit: maximum number of results (1-50). project_id: Scope results to one project. PASS THE ACTIVE PROJECT'S ID whenever a project is in scope (the one you entered with enter_project) — otherwise this searches across ALL projects and bleeds unrelated work into the result set. 0 = search everything (use only when you genuinely want a cross-project sweep). Returns: {"results": [{"id", "title", "body", "is_task", "tags", "similarity"}], "total": int} A result marked `shared: true` with an `owner` belongs to another user — that person's suggestion, not the operator's own record or settled practice. Weigh it on its merits and say whose it is when you use it. """ uid = current_user_id() limit = max(1, min(limit, 50)) is_task = {"note": False, "task": True}.get(content_type) # None => any t0 = time.perf_counter() raw = await semantic_search_notes( uid, q, limit=limit, is_task=is_task, project_id=project_id or None, # An explicit search reaches everything the operator may read, including # records shared with them one-to-one. scope="read", ) record_retrieval( user_id=uid, source="mcp_search", query=q, threshold=DEFAULT_SIMILARITY_THRESHOLD, limit=limit, project_id=project_id or None, is_task=is_task, results=raw, duration_ms=(time.perf_counter() - t0) * 1000.0, ) owners = await owner_names_for( {int(note.user_id) for _s, note in raw if note.user_id != uid} ) return { "results": [ { "id": note.id, "title": note.title, "body": (note.body or "")[:240], "is_task": bool(note.is_task), "tags": list(note.tags or []), "similarity": float(score), **( {"shared": True, "owner": owners.get(int(note.user_id))} if note.user_id != uid else {} ), } for score, note in raw ], "total": len(raw), } def register(mcp) -> None: mcp.tool(name="search")(search)