ducoterra
97d663d16d
All gates green — no defects found; this pass was verification only. **Phase 113 final verification pass — report** - Verified (no code changes needed): `select_documents_tiered` cited/related tiering + `select_documents` wrapper, `TurnPlan.related_docs`, `ChatDoneEvent.related` (additive, old payloads parse), `appendRelated` UI row (`.related-doc`, never `.source-chip`), done-frame + restore-path wiring, two settings with validators, `.env.example` entries - `uv run pytest --cov=app --cov-report=term-missing` → 2422 passed, app/ coverage **99%** (>90% gate) - `uv run pytest tests/e2e/test_source_chip_quality.py -v --no-cov` (isolated) → 2 passed - Regression E2E `test_retrieval_quality.py` + `test_honest_deflection.py` + `test_chat_rag.py` + `test_sources_midstream_bug.py` → 17 passed - `uv run ruff check . && uv run pyright` → clean (0 errors); `bash .agents/validate.sh` → "validation OK" Completion criteria: 1. Single-doc question → exactly one `.source-chip` (E2E): ✅ passed 2. Weak 2nd doc only in de-emphasized related row, never `.source-chip` (unit + E2E): ✅ passed 3. Deflected turn → zero citation chips, weak hits in related row: ✅ passed 4. Full suite green, coverage >90%, isolated E2E green, lint/types clean: ✅ passed 5. `--no-gpg-sign` commit + phase dir move: left to harness per pass rules (task files already in `complete/`) No deviations. Next pending phase: `114_embed_question_length`.
108 lines
4.8 KiB
Python
108 lines
4.8 KiB
Python
"""Shared fixtures for unit + integration tests."""
|
||
from __future__ import annotations
|
||
|
||
import json
|
||
import os
|
||
from collections.abc import Iterator
|
||
|
||
import pytest
|
||
from fastapi.testclient import TestClient
|
||
from sqlalchemy.orm import Session
|
||
|
||
# In-process integration/E2E tests drive the app with *mock* embeddings
|
||
# (bag-of-words, cosine ~0.1–0.8), not the live aipi model — so the honesty
|
||
# gate is calibrated to the mock's distribution, mirroring tests/e2e/
|
||
# conftest.py. Must be set before ``app.main`` (below) caches settings.
|
||
# The production default stays 0.62 (app/config.py, A8 revised).
|
||
os.environ.setdefault("BOR_RELEVANCE_THRESHOLD", "0.30")
|
||
# A8 revised 2026-09-14: lexical_support_floor must be <= relevance_threshold.
|
||
os.environ.setdefault("BOR_LEXICAL_SUPPORT_FLOOR", "0.15")
|
||
# Phase 113: the source usefulness bar (citation slot) is calibrated to
|
||
# the mock's compressed distribution, like the threshold above — the
|
||
# weakest GROUNDED fixture cosine in the in-process suites (the
|
||
# kafkabridge question's static-dns.json, ~0.055) must stay citable so
|
||
# the pre-phase citation pins hold, while the bar is ON so endpoint
|
||
# tests exercise the tier (tests that pin bar-specific behavior set a
|
||
# higher floor explicitly, the BOR_LEXICAL_SUPPORT_FLOOR pattern).
|
||
# Production default stays 0.35 (app/config.py, LOCKED A2).
|
||
os.environ.setdefault("BOR_SOURCE_USEFULNESS_FLOOR", "0.02")
|
||
|
||
# Phase 16: single-admin auth is fail-loud — create_app() refuses to boot
|
||
# without both vars, and app.main (imported below) builds the app at
|
||
# import time. Set known test values first, same pattern as the threshold.
|
||
ADMIN_PASSWORD = "test-admin-password"
|
||
SESSION_SECRET = "test-session-secret-0123456789abcdef0123456789abcdef"
|
||
os.environ.setdefault("BOR_ADMIN_PASSWORD", ADMIN_PASSWORD)
|
||
os.environ.setdefault("BOR_SESSION_SECRET", SESSION_SECRET)
|
||
|
||
# Phase 61 (defect fix): the app under test must see the code DEFAULTS,
|
||
# not an operator's local (gitignored) ``.env`` — ``Settings`` loads
|
||
# ``env_file=".env"`` from the repo root, and a machine-specific corpus
|
||
# (e.g. ``BOR_SUGGESTIONS``, ``BOR_DOCS_REPO``) leaked into the tests
|
||
# broke the default-metadata pins. pydantic-settings ranks process env
|
||
# vars ABOVE the ``.env`` file, so force the defaults explicitly here,
|
||
# before ``app.main`` (below) caches settings. The suggestions default
|
||
# is derived from the class field so this can never drift from
|
||
# ``app/config.py``; docs-push stays inert (empty repo).
|
||
from app.config import Settings as _Settings # noqa: E402
|
||
|
||
os.environ["BOR_DOCS_REPO"] = ""
|
||
os.environ["BOR_SUGGESTIONS"] = json.dumps(_Settings.model_fields["suggestions"].default)
|
||
|
||
# Phase 62: the same leak class for the new UI customization settings —
|
||
# an operator's local ``.env`` may legitimately carry
|
||
# ``BOR_INPUT_PLACEHOLDER`` / ``BOR_FOOTER_TEXT``, and the
|
||
# default-metadata pins must see the code defaults (derived from
|
||
# the class fields, same pattern as the suggestions line above).
|
||
# (Phase 91, task 03: the retired CSS-file theme env var no longer
|
||
# exists — nothing to pin.)
|
||
os.environ["BOR_INPUT_PLACEHOLDER"] = _Settings.model_fields["input_placeholder"].default
|
||
os.environ["BOR_FOOTER_TEXT"] = _Settings.model_fields["footer_text"].default
|
||
|
||
# Phase 106 (task 07): the same leak class for the recency-boost
|
||
# settings — an operator's local ``.env`` may legitimately carry
|
||
# ``BOR_RECENCY_BOOST`` / ``BOR_RECENCY_HALF_LIFE_DAYS`` re-tuned live,
|
||
# and the fine-line integration battery pins the CODE DEFAULTS
|
||
# (derived from the class fields, same pattern as the lines above).
|
||
os.environ["BOR_RECENCY_BOOST"] = str(_Settings.model_fields["recency_boost"].default)
|
||
os.environ["BOR_RECENCY_HALF_LIFE_DAYS"] = str(
|
||
_Settings.model_fields["recency_half_life_days"].default
|
||
)
|
||
|
||
from app.db import SessionLocal, db_available # noqa: E402
|
||
from app.main import app as fastapi_app # noqa: E402
|
||
|
||
|
||
@pytest.fixture()
|
||
def client() -> TestClient:
|
||
return TestClient(fastapi_app)
|
||
|
||
|
||
@pytest.fixture()
|
||
def admin_client(client: TestClient) -> TestClient:
|
||
"""A client signed in as the single admin (phase 16).
|
||
|
||
TestClient keeps its cookie jar across requests, so one login covers
|
||
every subsequent request of the test. Use it for the admin-only
|
||
surface (``GET /api/docs``, ``/api/steering``).
|
||
"""
|
||
r = client.post("/api/login", json={"password": ADMIN_PASSWORD})
|
||
assert r.status_code == 204, f"admin login failed: {r.status_code} {r.text}"
|
||
return client
|
||
|
||
|
||
@pytest.fixture()
|
||
def db() -> Iterator[Session]:
|
||
"""Real Postgres session (``podman compose up -d db``).
|
||
|
||
Skips with clear instructions when the database is not running, so the
|
||
suite degrades gracefully on a machine without the stack started.
|
||
"""
|
||
if not db_available():
|
||
pytest.skip("Postgres not reachable — run `podman compose up -d db` first")
|
||
session = SessionLocal()
|
||
try:
|
||
yield session
|
||
finally:
|
||
session.close()
|