feat(mcp): Phase 5 — write-time near-duplicate gate (update-over-create)
CI & Build / Python lint (push) Successful in 3s
CI & Build / TypeScript typecheck (push) Successful in 35s
CI & Build / Python tests (push) Failing after 42s
CI & Build / Build & push image (push) Has been skipped

#755 Phase 5. create_note / create_task now BLOCK a near-duplicate instead of
silently inserting: they return {"duplicate": true, "existing_id", message}
pointing at the record to UPDATE. Fights store bloat and stale competing copies
that semantic search (RAG) would otherwise resurface for reconciliation. A
force=true override creates anyway for genuinely-distinct records.

- services/dedup.py: find_duplicate_note — two signals, scoped to owner + same
  project + same kind: (1) normalized-title exact match (cheap, always); (2)
  semantic cosine ≥ 0.90 but ONLY when body ≥ 200 chars (short/title-only
  embeddings false-positive — the pre-pivot lesson). Project-less (orphan)
  records compare only to other orphans on BOTH signals (orphan_only on the
  semantic call) — they're not matched across every project.
- Gate wired into the MCP create_note/create_task tools (the LLM write path)
  with force override; _INSTRUCTIONS documents the duplicate response + force.
- Opt-in by design: the service helper is only called from the interactive
  create tools. Internal/programmatic creates (recurrence spawn, imports) go
  straight through services.create_note and are NOT gated — a recurring task
  spawning its next same-titled instance must not be blocked.
- Scope v1: MCP tools only. REST/web (human CRUD, needs a UI affordance) and
  create_rule (not a RAG surface; _INSTRUCTIONS already steer it) are follow-ups.
- tests: dedup service (title/semantic/body-gate/type-filter) + tool gate
  (blocks, force bypasses) for notes and tasks.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This commit is contained in:
2026-06-14 13:21:35 -04:00
parent 33f9a0a4d4
commit 322cbc3b5e
7 changed files with 301 additions and 1 deletions
+26
View File
@@ -25,6 +25,32 @@ def _fake_note(**overrides) -> MagicMock:
return note
@pytest.mark.asyncio
async def test_create_note_blocked_by_duplicate_gate():
from scribe.services.dedup import DuplicateMatch
dup = DuplicateMatch(id=88, title="Embeddings notes", similarity=0.94, reason="semantic")
create_mock = AsyncMock()
with patch("scribe.mcp.tools.notes.dedup_svc.find_duplicate_note",
AsyncMock(return_value=dup)), \
patch("scribe.mcp.tools.notes.notes_svc.create_note", create_mock):
out = await create_note(title="embeddings", body="notes about embeddings")
assert out["duplicate"] is True
assert out["existing_id"] == 88
assert out["match"] == "semantic"
create_mock.assert_not_called()
@pytest.mark.asyncio
async def test_create_note_force_bypasses_duplicate_gate():
find_mock = AsyncMock()
with patch("scribe.mcp.tools.notes.dedup_svc.find_duplicate_note", find_mock), \
patch("scribe.mcp.tools.notes.notes_svc.create_note",
AsyncMock(return_value=_fake_note(id=3))):
out = await create_note(title="dup", force=True)
assert out["id"] == 3
find_mock.assert_not_called()
@pytest.mark.asyncio
async def test_list_notes_repackages_tuple_into_dict():
rows = [_fake_note(id=1), _fake_note(id=2)]