feat(search): retrieval telemetry — log every semantic retrieval

Add retrieval_logs (migration 0068) + services/retrieval_telemetry with a
fire-and-forget record_retrieval(), wired into the MCP search tool
(source=mcp_search) and the REST search route (source=rest_search). Captures
query, effective params, and the per-result score distribution so KB-injection
thresholds can be tuned from data rather than guessed.

Scribe: project 2, milestone 93, task 1032.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Xz4j1H7pjYSjKsEpgcNH5E

src/scribe/mcp/tools/search.py

@@ -7,8 +7,11 @@ working. Differences from fable-mcp:
 """
 from __future__ import annotations
 
+import time
+
 from scribe.mcp._context import current_user_id
-from scribe.services.embeddings import semantic_search_notes
+from scribe.services.embeddings import DEFAULT_SIMILARITY_THRESHOLD, semantic_search_notes
+from scribe.services.retrieval_telemetry import record_retrieval
 
 
 async def search(
@@ -43,10 +46,17 @@ async def search(
     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,
     )
+    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,
+    )
     return {
         "results": [
             {

src/scribe/models/__init__.py

@@ -26,6 +26,7 @@ from scribe.models.app_log import AppLog  # noqa: E402, F401
 from scribe.models.password_reset import PasswordResetToken  # noqa: E402, F401
 from scribe.models.invitation import InvitationToken  # noqa: E402, F401
 from scribe.models.embedding import NoteEmbedding  # noqa: E402, F401
+from scribe.models.retrieval_log import RetrievalLog  # noqa: E402, F401
 from scribe.models.project import Project  # noqa: E402, F401
 from scribe.models.event import Event  # noqa: E402, F401
 from scribe.models.milestone import Milestone  # noqa: E402, F401

src/scribe/models/retrieval_log.py

@@ -0,0 +1,70 @@
+from datetime import datetime, timezone
+
+from sqlalchemy import Boolean, DateTime, Float, Index, Integer, Text
+from sqlalchemy.dialects.postgresql import JSONB
+from sqlalchemy.orm import Mapped, mapped_column
+
+from scribe.models import Base
+
+
+class RetrievalLog(Base):
+    """One row per semantic-retrieval call, for KB-injection tuning.
+
+    Captures what a query asked for, what came back, and the score
+    distribution of the results — the empirical basis for tuning the
+    similarity threshold and top-k per surface. `result_ids` holds the ranked
+    hits (id + score + rank) so a later pass can correlate "what we surfaced"
+    against "what the agent then fetched/referenced".
+
+    Deliberately FK-free on user_id (mirrors AppLog): telemetry should outlive
+    the row it describes, and a deleted user shouldn't cascade away history.
+    """
+
+    __tablename__ = "retrieval_logs"
+
+    id: Mapped[int] = mapped_column(primary_key=True)
+    created_at: Mapped[datetime] = mapped_column(
+        DateTime(timezone=True), default=lambda: datetime.now(timezone.utc)
+    )
+    user_id: Mapped[int | None] = mapped_column(Integer, nullable=True)
+    # Retrieval surface: 'mcp_search' | 'rest_search' | 'auto_inject' | ...
+    source: Mapped[str] = mapped_column(Text, nullable=False)
+    query: Mapped[str | None] = mapped_column(Text, nullable=True)
+    # Effective parameters actually used for this call.
+    threshold: Mapped[float | None] = mapped_column(Float, nullable=True)
+    limit_n: Mapped[int | None] = mapped_column(Integer, nullable=True)
+    project_id: Mapped[int | None] = mapped_column(Integer, nullable=True)
+    # The content-type filter as passed to semantic_search_notes: True=tasks,
+    # False=notes, NULL=any.
+    is_task: Mapped[bool | None] = mapped_column(Boolean, nullable=True)
+    result_count: Mapped[int] = mapped_column(Integer, nullable=False, default=0)
+    top_score: Mapped[float | None] = mapped_column(Float, nullable=True)
+    min_score: Mapped[float | None] = mapped_column(Float, nullable=True)
+    # [{"id": int, "score": float, "rank": int}, ...], highest-first.
+    result_ids: Mapped[list] = mapped_column(JSONB, nullable=False, default=list)
+    duration_ms: Mapped[float | None] = mapped_column(Float, nullable=True)
+
+    __table_args__ = (
+        Index("ix_retrieval_logs_created_at", "created_at"),
+        Index("ix_retrieval_logs_user_id", "user_id"),
+        Index("ix_retrieval_logs_source", "source"),
+        Index("ix_retrieval_logs_source_created_at", "source", created_at.desc()),
+    )
+
+    def to_dict(self) -> dict:
+        return {
+            "id": self.id,
+            "created_at": self.created_at.isoformat() if self.created_at else None,
+            "user_id": self.user_id,
+            "source": self.source,
+            "query": self.query,
+            "threshold": self.threshold,
+            "limit_n": self.limit_n,
+            "project_id": self.project_id,
+            "is_task": self.is_task,
+            "result_count": self.result_count,
+            "top_score": self.top_score,
+            "min_score": self.min_score,
+            "result_ids": self.result_ids,
+            "duration_ms": self.duration_ms,
+        }

src/scribe/routes/search.py

@@ -1,7 +1,14 @@
+import time
+
 from quart import Blueprint, jsonify, request
 
 from scribe.auth import login_required, get_current_user_id
 from scribe.services.embeddings import semantic_search_notes
+from scribe.services.retrieval_telemetry import record_retrieval
+
+# This route searches with a looser floor than the MCP tool default — it powers
+# an interactive feed where loosely-related hits still have value.
+_REST_SEARCH_THRESHOLD = 0.3
 
 search_bp = Blueprint("search", __name__, url_prefix="/api/search")
 
@@ -27,8 +34,15 @@ async def search_route():
     limit = min(request.args.get("limit", 10, type=int), 50)
     is_task = _content_type_to_is_task(content_type)
 
+    t0 = time.perf_counter()
     results = await semantic_search_notes(
-        uid, q, limit=limit, is_task=is_task, threshold=0.3
+        uid, q, limit=limit, is_task=is_task, threshold=_REST_SEARCH_THRESHOLD
+    )
+    record_retrieval(
+        user_id=uid, source="rest_search", query=q,
+        threshold=_REST_SEARCH_THRESHOLD, limit=limit,
+        project_id=None, is_task=is_task, results=results,
+        duration_ms=(time.perf_counter() - t0) * 1000.0,
     )
     return jsonify({
         "results": [

src/scribe/services/retrieval_telemetry.py

@@ -0,0 +1,115 @@
+"""Retrieval telemetry — one RetrievalLog row per semantic-retrieval call.
+
+This is the empirical basis for KB-injection tuning: it records what each query
+asked for, the score distribution of what came back, and the effective params,
+so the similarity threshold and top-k can be tuned from data rather than guessed.
+
+Design notes:
+  - Fire-and-forget, mirroring upsert_note_embedding: `record_retrieval` extracts
+    the primitives it needs SYNCHRONOUSLY (while the caller's Note objects are
+    still valid) and schedules the DB insert as a background task, so logging
+    never adds latency to — or can break — the search response.
+  - Result objects are reduced to {id, score, rank} before scheduling; the
+    background writer touches only plain data, never a possibly-detached ORM row.
+  - Every failure path is swallowed: telemetry must never take down retrieval.
+"""
+from __future__ import annotations
+
+import asyncio
+import logging
+
+from scribe.models import async_session
+from scribe.models.note import Note
+from scribe.models.retrieval_log import RetrievalLog
+
+logger = logging.getLogger(__name__)
+
+
+def _build_payload(
+    *,
+    user_id: int | None,
+    source: str,
+    query: str | None,
+    threshold: float | None,
+    limit: int | None,
+    project_id: int | None,
+    is_task: bool | None,
+    results: list[tuple[float, Note]],
+    duration_ms: float | None,
+) -> dict:
+    """Reduce a retrieval call to a flat, JSON-safe RetrievalLog payload.
+
+    Pure and synchronous (no DB, no event loop) so it is unit-testable and safe
+    to run inline before scheduling the write. `results` is the
+    `(score, Note)` list from semantic_search_notes, already highest-first.
+    """
+    items = [
+        {"id": int(note.id), "score": round(float(score), 5), "rank": rank}
+        for rank, (score, note) in enumerate(results)
+    ]
+    scores = [it["score"] for it in items]
+    return {
+        "user_id": user_id,
+        "source": source,
+        "query": query,
+        "threshold": threshold,
+        "limit_n": limit,
+        "project_id": project_id,
+        "is_task": is_task,
+        "result_count": len(items),
+        "top_score": (scores[0] if scores else None),
+        "min_score": (scores[-1] if scores else None),
+        "result_ids": items,
+        "duration_ms": (round(duration_ms, 2) if duration_ms is not None else None),
+    }
+
+
+async def _insert_retrieval_log(payload: dict) -> None:
+    """Persist one RetrievalLog row. Best-effort: all errors are swallowed."""
+    try:
+        async with async_session() as session:
+            session.add(RetrievalLog(**payload))
+            await session.commit()
+    except Exception:
+        logger.debug("retrieval telemetry write skipped", exc_info=True)
+
+
+def record_retrieval(
+    *,
+    user_id: int | None,
+    source: str,
+    query: str | None,
+    threshold: float | None,
+    limit: int | None,
+    project_id: int | None,
+    is_task: bool | None,
+    results: list[tuple[float, Note]],
+    duration_ms: float | None = None,
+) -> None:
+    """Fire-and-forget: record one retrieval call.
+
+    Builds the payload inline (synchronously) then schedules the insert so the
+    caller returns immediately. Never raises — telemetry must not affect search.
+    """
+    try:
+        payload = _build_payload(
+            user_id=user_id,
+            source=source,
+            query=query,
+            threshold=threshold,
+            limit=limit,
+            project_id=project_id,
+            is_task=is_task,
+            results=results,
+            duration_ms=duration_ms,
+        )
+    except Exception:
+        logger.debug("retrieval telemetry payload build failed", exc_info=True)
+        return
+
+    try:
+        asyncio.get_running_loop().create_task(_insert_retrieval_log(payload))
+    except RuntimeError:
+        # No running loop (e.g. called from sync context outside the app) —
+        # skip rather than block. The app paths always run on the loop.
+        logger.debug("retrieval telemetry skipped — no running event loop")