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`.
202 lines
8.7 KiB
Python
202 lines
8.7 KiB
Python
"""Phase 113 E2E (Playwright): the source-chip quality contract (TODO L5 +
|
||
L2c) — the usefulness bar + the de-emphasized related-docs row, as VISIBLE
|
||
chip counts.
|
||
|
||
Run in isolation (DB must be up: ``podman compose up -d db``):
|
||
|
||
uv run pytest tests/e2e/test_source_chip_quality.py -v --no-cov
|
||
|
||
Acceptance (TODO L144–146): "for a single-document question, the turn
|
||
shows one citation chip"; a weak 2nd doc renders only in the
|
||
de-emphasized related row (``.related-doc`` links, NEVER ``.source-chip``);
|
||
a deflected turn shows zero citation chips (its weak hits, if any, live in
|
||
the related row).
|
||
|
||
The fixture KB's tier shapes are deterministic under the E2E mock's
|
||
bag-of-words embeddings + the mock-calibrated bar (conftest:
|
||
``BOR_SOURCE_USEFULNESS_FLOOR=0.15``, half the 0.30 threshold — like the
|
||
lexical floor):
|
||
|
||
* **single-source question** — "What SSH aliases do I have?":
|
||
``ssh_aliases.txt`` is the ONLY doc whose best-chunk cosine clears the
|
||
bar (0.352 ≥ 0.15; grounded at 0.352 ≥ 0.30) → the done frame carries
|
||
exactly ONE cited ref; the two below-bar docs (gitlab-compose.yaml
|
||
0.025, uptime_probe.py 0.113) ride the related tier. This IS the
|
||
strong+weak two-tier shape on the wire (the four OBSERVED live shapes
|
||
are unit-pinned at plan level in
|
||
``tests/unit/test_source_chip_quality.py`` — the fixture KB reproduces
|
||
the same shape live, so no docstring caveat is needed).
|
||
* **deflected question** — "How do I bake sourdough bread?": best cosine
|
||
0.109 < 0.30 and zero FTS hits → honest deflection; nothing clears the
|
||
bar → zero cited refs; the weak hits (new-service.md 0.109,
|
||
ssh_aliases.txt 0.050) ride the related row.
|
||
"""
|
||
from __future__ import annotations
|
||
|
||
import asyncio
|
||
from pathlib import Path
|
||
from threading import Thread
|
||
from typing import Any
|
||
|
||
from playwright.sync_api import Page, expect
|
||
from sqlalchemy import select, text
|
||
|
||
from app.config import Settings, get_settings
|
||
from app.db import SessionLocal
|
||
from app.models import QueryLog
|
||
from app.rag.importer import ImportSummary, import_sources
|
||
from app.rag.llm import LLMClient
|
||
from e2e.auth_helpers import login
|
||
|
||
REPO = Path(__file__).resolve().parents[2]
|
||
FIXTURES = REPO / "tests" / "fixtures" / "docs"
|
||
SINGLE_SOURCE_QUESTION = "What SSH aliases do I have?"
|
||
OFF_TOPIC = "How do I bake sourdough bread?"
|
||
MOCK_ANSWER_MARKER = "Deterministic mock answer for E2E"
|
||
|
||
|
||
async def _import_fixtures(mock_port: int) -> ImportSummary:
|
||
kwargs: dict[str, Any] = {"_env_file": None, "llm_base_url": f"http://127.0.0.1:{mock_port}/v1"}
|
||
settings = Settings(**kwargs) # pyright: ignore[reportCallIssue]
|
||
return await import_sources([FIXTURES], LLMClient(settings))
|
||
|
||
|
||
def _run_in_thread(coro: Any) -> Any:
|
||
"""Run a coroutine on a worker thread (Playwright owns the test loop)."""
|
||
box: dict[str, Any] = {}
|
||
|
||
def runner() -> None:
|
||
try:
|
||
box["value"] = asyncio.run(coro)
|
||
except BaseException as e: # noqa: BLE001 — re-raised on the test thread
|
||
box["error"] = e
|
||
|
||
t = Thread(target=runner)
|
||
t.start()
|
||
t.join()
|
||
if "error" in box:
|
||
raise box["error"]
|
||
return box["value"]
|
||
|
||
|
||
def _reset_db(mock_port: int, seed: bool = True) -> ImportSummary | None:
|
||
"""Truncate the KB (and query log), then optionally re-import fixtures."""
|
||
with SessionLocal() as db:
|
||
db.execute(text("TRUNCATE chunks, documents, query_log"))
|
||
db.commit()
|
||
if not seed:
|
||
return None
|
||
return _run_in_thread(_import_fixtures(mock_port))
|
||
|
||
|
||
def _ask(page: Page, message: str) -> None:
|
||
page.fill("#message-input", message)
|
||
page.click("#send-btn")
|
||
|
||
|
||
def test_single_source_question_shows_exactly_one_citation_chip(
|
||
page: Page, app_url: str, mock_llm: int, db_ready: None
|
||
) -> None:
|
||
"""The acceptance pin: a single-document question → the done bubble
|
||
carries EXACTLY ONE ``.source-chip`` (the bar-clearing doc) and the
|
||
below-bar docs render only in the de-emphasized ``.related-docs`` row
|
||
(``.related-doc`` links — never ``.source-chip``), labeled
|
||
"Nearby docs, in case:". The durable record keeps the FULL retrieval
|
||
(LOCKED A3)."""
|
||
_reset_db(mock_llm)
|
||
page.set_default_timeout(30_000)
|
||
login(page, app_url, next="/") # phase 79: chat is require_user-gated
|
||
|
||
_ask(page, SINGLE_SOURCE_QUESTION)
|
||
expect(page.locator(".msg.user .bubble")).to_contain_text(SINGLE_SOURCE_QUESTION)
|
||
|
||
bubble = page.locator(".msg.brain .bubble").first
|
||
bubble.wait_for(state="visible", timeout=30_000)
|
||
expect(bubble).to_contain_text(MOCK_ANSWER_MARKER, timeout=30_000)
|
||
# Grounded: no deflected bubble at all.
|
||
expect(page.locator(".msg.brain.is-deflected")).to_have_count(0)
|
||
|
||
# EXACTLY ONE citation chip — the bar-clearing doc (the 2nd chip of
|
||
# the pre-phase turn demoted to the row; the acceptance criterion).
|
||
chip = page.locator(".msg.brain .source-chip")
|
||
expect(chip).to_have_count(1, timeout=30_000)
|
||
expect(chip.first).to_contain_text("ssh_aliases.txt")
|
||
|
||
# The below-bar docs ride the related row: a labeled, de-emphasized
|
||
# list — one .related-doc link per doc (rank order, capped at
|
||
# related_max_docs = 2), never a .source-chip.
|
||
row = page.locator(".msg.brain .related-docs")
|
||
expect(row).to_have_count(1)
|
||
expect(row.first).to_have_attribute("aria-label", "Nearby docs, in case")
|
||
expect(row.first.locator(".related-docs-label")).to_have_text("Nearby docs, in case:")
|
||
links = page.locator(".msg.brain .related-docs .related-doc")
|
||
expect(links).to_have_count(2, timeout=30_000)
|
||
expect(links.nth(0)).to_contain_text("gitlab-compose.yaml")
|
||
expect(links.nth(1)).to_contain_text("uptime_probe.py")
|
||
expect(page.locator(".msg.brain .related-docs .source-chip")).to_have_count(0)
|
||
# The related links keep the chip's /document.html href + identity.
|
||
expect(links.first).to_have_attribute(
|
||
"title", "docs/homelab/container_gitlab/gitlab-compose.yaml"
|
||
)
|
||
|
||
# Durable record: not deflected; the FULL retrieval (cited + related)
|
||
# is logged — query_log records retrieval, not citations (LOCKED A3).
|
||
with SessionLocal() as db:
|
||
row_log = db.scalars(select(QueryLog)).one()
|
||
assert row_log.question == SINGLE_SOURCE_QUESTION
|
||
assert row_log.deflected is False
|
||
for path in (
|
||
"homelab/ssh/ssh_aliases.txt",
|
||
"homelab/container_gitlab/gitlab-compose.yaml",
|
||
"homelab/scripts/uptime_probe.py",
|
||
):
|
||
assert path in row_log.sources
|
||
|
||
|
||
def test_deflected_question_shows_zero_citation_chips(
|
||
page: Page, app_url: str, mock_llm: int, db_ready: None
|
||
) -> None:
|
||
"""The acceptance pin: a deflected turn (known-out-of-KB) → ZERO
|
||
``.source-chip`` elements under the bubble; the weak hits live in the
|
||
related row only — its links are ``.related-doc``, never
|
||
``.source-chip`` (L2c: "at minimum: never render them as answer
|
||
citations"). The "Maybe try" chips and the durable record are
|
||
unchanged."""
|
||
_reset_db(mock_llm)
|
||
page.set_default_timeout(30_000)
|
||
login(page, app_url, next="/") # phase 79: chat is require_user-gated
|
||
|
||
_ask(page, OFF_TOPIC)
|
||
bubble = page.locator(".msg.brain.is-deflected .bubble").first
|
||
bubble.wait_for(state="visible", timeout=30_000)
|
||
expect(page.locator(".msg.brain.is-deflected")).to_have_count(1)
|
||
|
||
# Wait for the done frame to have fully rendered (the related row and
|
||
# the suggestion chips append in it), THEN pin the absence of chips —
|
||
# a mid-stream reading would be a false zero.
|
||
chips = page.locator(".msg.brain.is-deflected .maybe-try .suggestion-chip")
|
||
expect(chips.first).to_be_visible(timeout=30_000)
|
||
assert chips.count() >= 2, "deflection must offer 2-3 alternative chips"
|
||
|
||
row = page.locator(".msg.brain .related-docs")
|
||
expect(row).to_have_count(1, timeout=30_000)
|
||
links = page.locator(".msg.brain .related-docs .related-doc")
|
||
expect(links).to_have_count(2) # the weak hits, rank order, capped at 2
|
||
expect(links.nth(0)).to_contain_text("new-service.md")
|
||
expect(links.nth(1)).to_contain_text("ssh_aliases.txt")
|
||
|
||
# ZERO citation chips under the bubble — the weak hits are scored
|
||
# docs, not citations (the phase-112/113 contract on the wire).
|
||
expect(page.locator(".msg.brain .source-chip")).to_have_count(0)
|
||
expect(page.locator(".msg.brain .related-docs .source-chip")).to_have_count(0)
|
||
|
||
# Durable record: deflected, weak top score — the retrieval stays
|
||
# logged for threshold tuning (LOCKED A3: observability unchanged).
|
||
with SessionLocal() as db:
|
||
row_log = db.scalars(select(QueryLog)).one()
|
||
assert row_log.question == OFF_TOPIC
|
||
assert row_log.deflected is True
|
||
assert 0.0 < row_log.top_score < get_settings().relevance_threshold
|
||
assert row_log.fts_hits == 0
|
||
assert row_log.sources # the weak-hit paths, for threshold tuning
|