Files
FabledScribe/tests/test_routes_snippets.py
T
bvandeusen 6db791965f
CI & Build / Python lint (push) Successful in 3s
CI & Build / TypeScript typecheck (push) Successful in 14s
CI & Build / integration (push) Successful in 36s
CI & Build / Python tests (push) Successful in 55s
CI & Build / Build & push image (push) Successful in 44s
feat(snippets): near-duplicate finder — surface the sets worth merging
#231's premise was unifying reusable things already scattered as one-offs.
The create gate PREVENTS a new duplicate and merge_snippets CURES one you
point it at, but nothing FOUND the duplicates already in the record —
someone had to notice them by hand, which is the exact failure the Drafter
exists to remove.

One indexed self-join over note_embeddings, not an N² Python scan:
pgvector's cosine distance is the same operator semantic search uses, so a
similarity floor is a distance ceiling and the work stays in Postgres.
`left.note_id < right.note_id` yields each unordered pair once and drops
the self-pair that would otherwise dominate the ranking.

Pairs are collapsed into merge SETS by connected components. Transitive on
purpose: A~B plus B~C puts all three together even when A and C don't
directly clear the bar, which is what merge actually does (it folds every
source into one survivor). The cost is that a chain of mild resemblances
can rope in a member that isn't really alike — so the UI presents a set as
a proposal, shows the members, and never merges without a confirm.

Two scope decisions worth naming:

- OWN snippets only. merge_snippets requires one owner across the set, so
  surfacing someone else's would propose a merge that cannot be performed.
  The report is bounded by what the operator can act on, not what they can
  see.

- Threshold defaults to 0.82, LOOSER than the write gate's 0.90, and is a
  setting rather than a constant (rule #25). The gate blocks a create and
  has to be unforgiving of noise; this only suggests a merge under review,
  so it must reach further or it would never surface the pairs the gate
  already let through — which are precisely the ones that accumulated.

Fixes a real bug in the merge flow while wiring the UI: selectedList
filtered the selection against the CURRENT PAGE, and doMerge derives its
source ids from that list. A corpus-wide suggested group with off-page
members would have rendered incomplete and silently merged only the
visible subset. A group under review is now the authority for that list.

Refs #2088

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01UaYUaouG9jjhATyuxCKrQs
2026-07-28 18:32:40 -04:00

110 lines
5.1 KiB
Python

"""Structural tests for the snippets blueprint — registration + handler/service
contracts. Full HTTP integration needs a live DB + auth the unit env lacks."""
import inspect
def test_snippets_blueprint_registered():
from scribe.routes.snippets import snippets_bp
assert snippets_bp.name == "snippets"
assert snippets_bp.url_prefix == "/api/snippets"
def test_snippets_blueprint_registered_in_app():
from scribe.app import create_app
app = create_app()
assert "snippets" in app.blueprints
def test_snippet_handlers_callable():
from scribe.routes import snippets as routes
for name in (
"list_snippets_route", "create_snippet_route", "get_snippet_route",
"update_snippet_route", "delete_snippet_route", "merge_snippet_route",
"verify_snippet_route", "duplicate_snippets_route",
):
assert callable(getattr(routes, name))
def test_service_functions_take_user_id():
"""Routes must call snippet services with user_id — verify the contract."""
from scribe.services import snippets as svc
for fn_name in (
"create_snippet", "list_snippets", "get_snippet", "update_snippet",
"delete_snippet", "merge_snippets", "record_verification",
):
fn = getattr(svc, fn_name)
assert callable(fn)
assert "user_id" in inspect.signature(fn).parameters
def test_agent_and_web_surfaces_stay_at_parity():
"""The MCP tools and the REST routes are two callers of one service; a
capability on one has to exist on the other (rule #33). This guard exists
because they drifted apart once: MCP had no delete or `locations`, and the
web side had no `system_ids` and no near-duplicate gate."""
from scribe.mcp.tools import snippets as tools
from scribe.routes import snippets as routes
# Every write verb the web surface offers, the agent surface offers too.
for verb in ("create", "get", "list", "update", "delete", "merge", "verify"):
assert callable(getattr(tools, f"{verb}_snippets", None) or
getattr(tools, f"{verb}_snippet", None)), f"MCP lacks {verb}"
# Multi-location records are reachable from both.
assert "locations" in inspect.signature(tools.create_snippet).parameters
assert "locations" in inspect.signature(tools.update_snippet).parameters
assert "locations" in inspect.getsource(routes.create_snippet_route)
assert "locations" in inspect.getsource(routes.update_snippet_route)
# System association and the duplicate gate reach both.
assert "system_ids" in inspect.signature(tools.create_snippet).parameters
for route in (routes.create_snippet_route, routes.update_snippet_route):
assert "system_ids" in inspect.getsource(route)
assert "find_duplicate_note" in inspect.getsource(routes.create_snippet_route)
# The drift check (#2086) reaches both: recording a verdict, and filtering
# the list by one. A verdict an agent records has to be visible to the human
# looking at the same corpus, or the two surfaces disagree about what's rotten.
assert "verification" in inspect.signature(tools.list_snippets).parameters
assert "verification" in inspect.getsource(routes.list_snippets_route)
# The near-duplicate report (#2088) reaches both. The web side can only hand
# a group to the merge flow if it can get the groups in the first place.
assert callable(getattr(tools, "find_duplicate_snippets", None))
assert callable(getattr(routes, "duplicate_snippets_route", None))
def test_project_scoping_reaches_every_caller():
"""A snippet search has to be narrowable to one project from both surfaces."""
from scribe.mcp.tools import snippets as tools
from scribe.routes import snippets as routes
from scribe.services import snippets as svc
assert "project_id" in inspect.signature(svc.list_snippets).parameters
assert "project_id" in inspect.signature(tools.list_snippets).parameters
assert "project_id" in inspect.getsource(routes.list_snippets_route)
def test_location_lookup_reaches_every_caller():
"""The reverse lookup — "what already lives here?" — has to be askable from
both surfaces, or an agent and a human get different answers about the same
file (rule #33)."""
from scribe.mcp.tools import snippets as tools
from scribe.routes import snippets as routes
from scribe.services import snippets as svc
for key in ("repo", "path", "symbol"):
assert key in inspect.signature(svc.list_snippets).parameters
assert key in inspect.signature(tools.list_snippets).parameters
assert f'request.args.get("{key}"' in inspect.getsource(routes)
def test_update_field_map_matches_service_kwargs():
"""Every field the PATCH route forwards must be a real update_snippet kwarg
(rule #33 interface-contract parity)."""
from scribe.routes import snippets as routes
from scribe.services import snippets as svc
params = inspect.signature(svc.update_snippet).parameters
for field in routes._STR_FIELDS:
assert field in params, f"update_snippet has no '{field}' kwarg"
assert "tags" in params
assert "project_id" in params