Files
ducoterra 97d663d16d
Build and Push Containers / build-and-push-app (push) Successful in 2m2s
Build and Push Containers / build-and-push-db (push) Successful in 15s
phase: 113_source_chip_quality
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`.
2026-09-15 03:11:05 -04:00

189 lines
7.6 KiB
Python
Raw Permalink Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
"""Playwright E2E fixtures (shared by every story's test file).
Each user story in ``.agents/user_stories/`` gets its own isolated E2E test
file; this conftest provides the shared environment:
* ``mock_llm`` — deterministic OpenAI-compatible server (see mock_llm.py).
Set ``E2E_REAL_LLM=1`` to point at the real aipi endpoint
instead (requires an imported knowledge base).
* ``app_server`` — the real FastAPI app under test (uvicorn subprocess).
* ``browser``/``page`` — headless Chromium pointed at the app.
Prerequisite for story tests that touch the database:
podman compose up -d db
"""
from __future__ import annotations
import json
import os
import subprocess
import sys
import time
from collections.abc import Iterator
from pathlib import Path
import httpx
import pytest
from playwright.sync_api import Browser, Page, sync_playwright
from app.config import Settings as _Settings
REPO = Path(__file__).resolve().parents[2]
APP_PORT = int(os.environ.get("E2E_APP_PORT", "8123"))
MOCK_PORT = int(os.environ.get("E2E_MOCK_PORT", "8901"))
APP_URL = f"http://127.0.0.1:{APP_PORT}"
USE_REAL_LLM = os.environ.get("E2E_REAL_LLM") == "1"
# Phase 16: the app under test boots with single-admin auth configured
# (fail-loud otherwise). Known E2E values — the shared form-login helper
# (tests/e2e/auth_helpers.py) uses ADMIN_PASSWORD; the secret is fixed so
# session cookies stay valid across a session-scoped app restart.
ADMIN_PASSWORD = "e2e-admin-password"
SESSION_SECRET = "e2e-session-secret-0123456789abcdef0123456789abcdef"
def _wait_http(url: str, timeout: float = 40.0) -> None:
deadline = time.monotonic() + timeout
last_err = "unknown"
while time.monotonic() < deadline:
try:
httpx.get(url, timeout=2.0)
return
except Exception as e: # noqa: BLE001 — retry until deadline
last_err = str(e)
time.sleep(0.5)
raise RuntimeError(f"server at {url} did not come up: {last_err}")
@pytest.fixture(scope="session")
def mock_llm() -> Iterator[int]:
"""Deterministic OpenAI-compatible LLM (chat + embeddings)."""
if USE_REAL_LLM:
yield 0
return
env = dict(os.environ)
env.pop("DEBUGPY", None)
proc = subprocess.Popen(
[sys.executable, "-m", "uvicorn", "tests.e2e.mock_llm:app",
"--host", "127.0.0.1", "--port", str(MOCK_PORT), "--log-level", "warning"],
cwd=REPO,
env=env,
)
try:
_wait_http(f"http://127.0.0.1:{MOCK_PORT}/v1/models")
yield MOCK_PORT
finally:
proc.terminate()
try:
proc.wait(timeout=10)
except subprocess.TimeoutExpired:
proc.kill()
@pytest.fixture(scope="session")
def app_server(mock_llm: int) -> Iterator[str]:
"""The real app under test."""
env = dict(os.environ)
env.pop("DEBUGPY", None)
env["BOR_ENVIRONMENT"] = "e2e"
env["BOR_STATIC_DIR"] = str(REPO / "frontend")
env["BOR_LLM_BASE_URL"] = (
"https://aipi.reeseapps.com/v1"
if USE_REAL_LLM
else f"http://127.0.0.1:{mock_llm}/v1"
)
# The E2E mock's token-overlap embeddings have their own score
# distribution (phase 09) — the app under test gets the mock-calibrated
# threshold so every story suite keeps its deterministic gate behavior.
# The production default stays 0.62 (re-tuned against the real
# `embed` model's 0.41–0.84 cosine range, PLAN A8).
env["BOR_RELEVANCE_THRESHOLD"] = "0.30"
# Phase 112 (defect fix): the code-default lexical_support_floor (0.35)
# violates the startup validator against the mock-calibrated threshold
# (0.30) and the app under test refused to boot — pin the
# mock-calibrated value (tests/conftest.py pattern). It also pins the
# gate quadrant end-to-end: "Who composed Rhapsody in Blue?" (top
# ~0.124 with FTS hits) deflects while the corroborated-lexical
# kafkabridge question (top ~0.239) grounds.
env["BOR_LEXICAL_SUPPORT_FLOOR"] = "0.15"
# Phase 113: the source usefulness bar (citation slot), mock-calibrated
# (half the threshold, like the lexical floor): a doc earns a citation
# chip only when its best-chunk cosine clears it (e.g. the kafkabridge
# doc at ~0.20 clears; the rhapsody weak hits at ~0.12 or below do not
# and demote to the related tier). The production default stays 0.35
# (app/config.py, LOCKED A2).
env["BOR_SOURCE_USEFULNESS_FLOOR"] = "0.15"
# Phase 67 (LLM retry): the e2e pins the retry MECHANISM with instant
# waits (BOR_LLM_RETRY_DELAY=0 — the 5 s default is unit-pinned via
# tests/unit/test_config.py). BOR_LLM_RETRIES is forced to the code
# default (derived from the class field, never drifts from
# app/config.py) so the exhaustion test relies on the REAL budget and
# an operator's local (gitignored) .env cannot leak a different one
# into the app under test (the phase-61 leak-guard pattern).
env["BOR_LLM_RETRY_DELAY"] = "0"
env["BOR_LLM_RETRIES"] = str(_Settings.model_fields["llm_retries"].default)
env.setdefault("BOR_DATABASE_URL", "postgresql+psycopg://reese:reese@localhost:5432/brain_of_reese")
# Phase 16: admin auth must be set or create_app() refuses to boot.
env["BOR_ADMIN_PASSWORD"] = ADMIN_PASSWORD
env["BOR_SESSION_SECRET"] = SESSION_SECRET
# Phase 61 (defect fix): force the code DEFAULTS so an operator's local
# (gitignored) ``.env`` — loaded by pydantic-settings from ``cwd=REPO``
# — cannot leak corpus-specific chips / a docs repo into the app under
# test: process env ranks above the ``.env`` file. The suggestions
# default is derived from the class field (never drifts from
# ``app/config.py``); docs-push stays inert (empty repo).
env["BOR_DOCS_REPO"] = ""
env["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 (gitignored) ``.env`` may
# legitimately carry ``BOR_INPUT_PLACEHOLDER`` /
# ``BOR_FOOTER_TEXT``, and the byte-identical default contract
# must see the code defaults (derived from the class fields, never
# drifts from ``app/config.py``). (Phase 91, task 03: the retired
# CSS-file theme env var no longer exists — nothing to pin.)
env["BOR_INPUT_PLACEHOLDER"] = _Settings.model_fields["input_placeholder"].default
env["BOR_FOOTER_TEXT"] = _Settings.model_fields["footer_text"].default
proc = subprocess.Popen(
[sys.executable, "-m", "uvicorn", "app.main:app",
"--host", "127.0.0.1", "--port", str(APP_PORT), "--log-level", "warning"],
cwd=REPO,
env=env,
)
try:
_wait_http(f"{APP_URL}/api/health")
yield APP_URL
finally:
proc.terminate()
try:
proc.wait(timeout=10)
except subprocess.TimeoutExpired:
proc.kill()
@pytest.fixture(scope="session")
def app_url(app_server: str) -> str:
return app_server
@pytest.fixture()
def db_ready(app_url: str) -> None:
"""Skip a test with clear instructions when Postgres is not running."""
body = httpx.get(f"{app_url}/api/health", timeout=5).json()
if body["db"] != "up":
pytest.skip("Postgres not reachable — run `podman compose up -d db` first")
@pytest.fixture(scope="session")
def browser() -> Iterator[Browser]:
with sync_playwright() as p:
yield p.chromium.launch(headless=True)
@pytest.fixture()
def page(browser: Browser) -> Iterator[Page]:
pg = browser.new_page(viewport={"width": 1280, "height": 800})
yield pg
pg.close()