**Phase 118 final verification pass — complete.** All criteria verified; 4 pre-existing defects found and fixed.
- **Verified:** summary-seed wiring (`select_suggested` top-5 no-floor → summary blocks, no full text in HIGH prompt), all-doc markdown summaries + NULL backfill (`summary_backfilled`, no `sources_meta` bump), `read` adds full text with `read_docs`-only dedupe, `done.sources` = suggested+read / durable record = suggested+related+read + `suggested=N` log line (seen live in E2E), byte-locked PERSONA/LOW/TOOLS_SECTION, battery gate PASS recorded in `TOOL_CALLING_TESTING.md` §10 (turbo 2026-09-16: 1/2/4 GREEN, cond-3 reported 9/10 per A7, contract 21/21, caps 0).
- **Defects fixed (all pre-existing, none phase-118):** ① `ChatMessage` schema missing the phase-113 `related` key → `extra="forbid"` 422'd every done-time auto-save of grounded turns with a related tier, leaving `message_count=1` (root cause of `test_share_chat` 3F; browser-level instrumentation proved the PUT 422) — added the field + unit/integration pins; ② `test_theme_semantic_completion` pins stale vs phase-117 debox (border/chip removed) — re-targeted to assert border/chip *absence*; ③ `test_header_consistency` `<26`px pin red on 26.125px native date-input line — bound relaxed to `<34` (wrap-detection intent kept); ④ `test_navbar_refresh` bor.chat.v1 key set updated for `related`.
- **Test/lint/coverage:** `uv run pytest --cov=app --cov-report=term-missing` → **2506 passed, app/ 99%** (>90%); `uv run ruff check . && uv run pyright` → clean, 0 errors.
- **E2E:** new story suite in isolation → **2 passed**; full 103-suite matrix sweep (each isolated) → **all 103 green** after the fixes; `test_share_chat` 4 passed, `test_theme_semantic_completion` 8 passed, `test_header_consistency` 3 passed, `test_navbar_refresh` 7 passed.
- **Deviations:** none from LOCKED decisions. Note: orphaned diagnostic uvicorn processes briefly made E2E sessions exercise stale code — killed and re-verified; a sweep-regenerated tracked screenshot was restored. No commits made (harness commits).
- **Completion criteria:** all 7 ✅ (commit/phase-move is the harness's step).
- **Next pending phase:** none — `todo/` holds only this phase's overview pending the harness move.
300 lines
12 KiB
Python
300 lines
12 KiB
Python
"""Integration test: phase 102 — extensionless files named in
|
|
``BOR_IMPORT_EXTENSIONS`` import end to end.
|
|
|
|
The owner's defect: ``Dockerfile`` / ``Containerfile`` never synced even
|
|
with ``dockerfile`` / ``containerfile`` in the env, because the importer
|
|
matched on the dotted suffix only (``Path("Dockerfile").suffix`` is
|
|
``""``). Phase 102's rule (D1/D2): a suffix-less file is in scope iff its
|
|
lowercased FULL filename equals a token of the set — exact name,
|
|
case-insensitive — and the ``formats`` counter keys it by the matched
|
|
token, never ``unknown``.
|
|
|
|
Proven here against the story-dedicated fixture directory
|
|
``tests/fixtures/extensionless_kb/`` (the shared ``extension_kb``
|
|
fixture of phase 56 stays pinned by its own suite):
|
|
|
|
* positive — ``md,dockerfile,containerfile`` walks ``Dockerfile``,
|
|
``Containerfile`` and ``notes.md`` (the ``Makefile`` negative control
|
|
stays out): rows + embedded chunks + the deterministic mock
|
|
``SUMMARY_MODE`` digest for EVERY doc (phase 118, A2: markdown
|
|
included — the phase-30 ``lite`` path), ``formats == {"dockerfile": 1,
|
|
"containerfile": 1, "md": 1}`` with NO ``unknown`` key;
|
|
* case — an on-disk ``DOCKERFILE`` imports under the ``dockerfile``
|
|
token, its row keeps the on-disk case;
|
|
* negative — ``md`` alone: only the control note imports;
|
|
* prune — a token removed from the env drops its extensionless rows on
|
|
the next ``prune=True`` run (D4 — the A9 junk precedent).
|
|
|
|
The LLM is the deterministic mock server (``tests/e2e/mock_llm.py``) on
|
|
a scratch port — the integration analogue of the e2e ``mock_llm``
|
|
fixture (the phase-56 integration pattern). Runs against the local
|
|
compose Postgres (the ``db`` fixture from ``tests/conftest.py``); only
|
|
the distinctive ``extensionless_kb`` / ``casekb`` source rows are
|
|
created and deleted, so the rest of the shared KB is untouched.
|
|
|
|
Runs (DB must be up: ``podman compose up -d db``):
|
|
|
|
uv run pytest tests/integration/test_import_extensionless.py -v
|
|
"""
|
|
from __future__ import annotations
|
|
|
|
import asyncio
|
|
import os
|
|
import socket
|
|
import subprocess
|
|
import sys
|
|
import time
|
|
from collections.abc import Iterator
|
|
from pathlib import Path
|
|
from typing import Any
|
|
|
|
import httpx
|
|
import pytest
|
|
from sqlalchemy import select
|
|
from sqlalchemy.orm import Session
|
|
|
|
from app.config import Settings
|
|
from app.models import Document
|
|
from app.rag.importer import import_sources
|
|
from app.rag.llm import LLMClient
|
|
|
|
REPO = Path(__file__).resolve().parents[2]
|
|
FIXTURES = REPO / "tests" / "fixtures" / "extensionless_kb"
|
|
SOURCE = FIXTURES.name # "extensionless_kb" — distinctive, never asserted by count
|
|
DOCKER_REL = "Dockerfile"
|
|
CONTAINER_REL = "Containerfile"
|
|
NOTES_REL = "notes.md"
|
|
DOCKER_SENTINEL = "DOCKERFILE-PROBE-SENTINEL-7a3e"
|
|
CONTAINER_SENTINEL = "CONTAINERFILE-PROBE-SENTINEL-4b1c"
|
|
#: The mock's SUMMARY_MODE tokenizes the document (``[a-z0-9]+``) — the
|
|
#: hyphenated sentinels land in the digest in their tokenized forms.
|
|
DOCKER_SENTINEL_TOKENS = "dockerfile probe sentinel 7a3e"
|
|
CONTAINER_SENTINEL_TOKENS = "containerfile probe sentinel 4b1c"
|
|
|
|
|
|
def _wait_http(url: str, timeout: float = 30.0) -> 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(0.2)
|
|
raise RuntimeError(f"mock LLM at {url} did not come up: {last_err}")
|
|
|
|
|
|
@pytest.fixture(scope="module")
|
|
def mock_llm_port() -> Iterator[int]:
|
|
"""The deterministic mock LLM (``tests/e2e/mock_llm.py``) on a free
|
|
scratch port — same server as the e2e ``mock_llm`` fixture, but
|
|
private to this file (integration tests otherwise run network-free)."""
|
|
sock = socket.socket()
|
|
sock.bind(("127.0.0.1", 0))
|
|
port = sock.getsockname()[1]
|
|
sock.close()
|
|
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(port), "--log-level", "warning"],
|
|
cwd=REPO,
|
|
env=env,
|
|
)
|
|
try:
|
|
_wait_http(f"http://127.0.0.1:{port}/v1/models")
|
|
yield port
|
|
finally:
|
|
proc.terminate()
|
|
try:
|
|
proc.wait(timeout=10)
|
|
except subprocess.TimeoutExpired:
|
|
proc.kill()
|
|
|
|
|
|
def _settings(mock_port: int, extensions: str) -> Settings:
|
|
kwargs: dict[str, Any] = {
|
|
"_env_file": None,
|
|
"llm_base_url": f"http://127.0.0.1:{mock_port}/v1",
|
|
"import_extensions": extensions,
|
|
}
|
|
return Settings(**kwargs) # pyright: ignore[reportCallIssue]
|
|
|
|
|
|
def _cleanup_source(db: Session, source: str) -> None:
|
|
for doc in db.scalars(select(Document).where(Document.source == source)).all():
|
|
db.delete(doc)
|
|
db.commit()
|
|
|
|
|
|
def test_name_token_files_import_end_to_end(mock_llm_port: int, db: Session) -> None:
|
|
"""``md,dockerfile,containerfile`` over the fixture imports the two
|
|
name-token build files + the markdown control: rows, embedded
|
|
chunks, the mock ``SUMMARY_MODE`` digest for each build file, and
|
|
the ``formats`` counter keyed by the matched token — never
|
|
``unknown``. The ``Makefile`` (no token) stays out."""
|
|
settings = _settings(mock_llm_port, "md,dockerfile,containerfile")
|
|
assert settings.import_extension_set == {".md", ".dockerfile", ".containerfile"}
|
|
summary = asyncio.run(import_sources([FIXTURES], LLMClient(settings), session=db))
|
|
try:
|
|
# Exactly the three in-scope files walk — the Makefile negative
|
|
# control and nothing else.
|
|
assert (
|
|
summary.files, summary.added, summary.unchanged, summary.updated, summary.errors
|
|
) == (3, 3, 0, 0, 0)
|
|
# D2: extensionless files count under their matched token.
|
|
assert summary.formats == {"dockerfile": 1, "containerfile": 1, "md": 1}
|
|
assert "unknown" not in summary.formats
|
|
# Phase 118 (A2): EVERY doc gets a lite summary — both build
|
|
# files AND the markdown control.
|
|
assert (summary.summaries, summary.summary_errors) == (3, 0)
|
|
|
|
for rel, sentinel, tokens in (
|
|
(DOCKER_REL, DOCKER_SENTINEL, DOCKER_SENTINEL_TOKENS),
|
|
(CONTAINER_REL, CONTAINER_SENTINEL, CONTAINER_SENTINEL_TOKENS),
|
|
):
|
|
doc = db.scalar(
|
|
select(Document).where(Document.source == SOURCE, Document.path == rel)
|
|
)
|
|
assert doc is not None, f"{rel} was not imported by name token"
|
|
# Suffix-less: the title is the file stem — the whole name.
|
|
assert doc.title == rel
|
|
# Plain-text chunking: the content (incl. the sentinel) is
|
|
# chunked and every content chunk is embedded at the 768-dim
|
|
# contract.
|
|
content = [c for c in doc.chunks if not c.is_summary]
|
|
assert content, f"{rel} has no content chunks"
|
|
assert all(
|
|
c.embedding is not None and len(c.embedding) == 768 for c in content
|
|
)
|
|
assert any(sentinel in c.content for c in content)
|
|
# Mock SUMMARY_MODE digest: byte-stable, the tokenized
|
|
# sentinel inside it, plus the code-appended pointer line.
|
|
assert doc.summary is not None
|
|
assert doc.summary.startswith("This document covers")
|
|
assert tokens in doc.summary
|
|
assert f"Source: {SOURCE}/{rel}" in doc.summary
|
|
schunks = [c for c in doc.chunks if c.is_summary]
|
|
assert len(schunks) == 1 and schunks[0].position == -1
|
|
assert schunks[0].embedding is not None
|
|
|
|
# The markdown control doc imported too — AND got the mock
|
|
# ``SUMMARY_MODE`` digest (phase 118, A2: markdown summarized).
|
|
note = db.scalar(
|
|
select(Document).where(Document.source == SOURCE, Document.path == NOTES_REL)
|
|
)
|
|
assert note is not None
|
|
assert note.summary is not None
|
|
assert note.summary.startswith("This document covers extensionless fixture notes")
|
|
assert f"Source: {SOURCE}/{NOTES_REL}" in note.summary
|
|
note_schunks = [c for c in note.chunks if c.is_summary]
|
|
assert len(note_schunks) == 1 and note_schunks[0].position == -1
|
|
assert note_schunks[0].embedding is not None
|
|
assert [c for c in note.chunks if not c.is_summary]
|
|
|
|
# The negative control: no token names Makefile exactly — never
|
|
# walked.
|
|
assert (
|
|
db.scalar(
|
|
select(Document).where(Document.source == SOURCE, Document.path == "Makefile")
|
|
)
|
|
is None
|
|
)
|
|
finally:
|
|
_cleanup_source(db, SOURCE)
|
|
|
|
|
|
def test_uppercase_extensionless_name_imports(
|
|
mock_llm_port: int, db: Session, tmp_path: Path
|
|
) -> None:
|
|
"""Case-insensitive exact name (D1): an on-disk ``DOCKERFILE``
|
|
imports under the ``dockerfile`` token, and its row keeps the
|
|
on-disk case in both ``path`` and ``title``."""
|
|
root = tmp_path / "casekb"
|
|
root.mkdir()
|
|
(root / "DOCKERFILE").write_text("FROM alpine\nRUN apk add --no-cache curl\n")
|
|
settings = _settings(mock_llm_port, "md,dockerfile")
|
|
summary = asyncio.run(import_sources([root], LLMClient(settings), session=db))
|
|
try:
|
|
assert (summary.files, summary.added, summary.errors) == (1, 1, 0)
|
|
assert summary.formats == {"dockerfile": 1}
|
|
doc = db.scalar(
|
|
select(Document).where(Document.source == "casekb", Document.path == "DOCKERFILE")
|
|
)
|
|
assert doc is not None, "DOCKERFILE did not import under the dockerfile token"
|
|
assert doc.title == "DOCKERFILE"
|
|
assert [c for c in doc.chunks if not c.is_summary]
|
|
# Non-markdown → the phase-30 lite path ran.
|
|
assert summary.summaries == 1
|
|
assert doc.summary is not None
|
|
assert doc.summary.startswith("This document covers")
|
|
finally:
|
|
_cleanup_source(db, "casekb")
|
|
|
|
|
|
def test_without_tokens_the_extensionless_files_stay_out(
|
|
mock_llm_port: int, db: Session
|
|
) -> None:
|
|
"""``md`` alone: the control note imports; ``Dockerfile`` /
|
|
``Containerfile`` (their names are not tokens in this scope) and the
|
|
``Makefile`` are all out of scope — no value of the scope walks
|
|
them."""
|
|
settings = _settings(mock_llm_port, "md")
|
|
assert settings.import_extension_set == {".md"}
|
|
summary = asyncio.run(import_sources([FIXTURES], LLMClient(settings), session=db))
|
|
try:
|
|
assert (
|
|
summary.files, summary.added, summary.unchanged, summary.updated, summary.errors
|
|
) == (1, 1, 0, 0, 0)
|
|
assert summary.formats == {"md": 1}
|
|
# Phase 118 (A2): the md-only run still summarizes the note.
|
|
assert summary.summaries == 1
|
|
for rel in (DOCKER_REL, CONTAINER_REL, "Makefile"):
|
|
assert (
|
|
db.scalar(
|
|
select(Document).where(Document.source == SOURCE, Document.path == rel)
|
|
)
|
|
is None
|
|
), f"{rel} was imported although its name is not a token in `md`"
|
|
assert (
|
|
db.scalar(
|
|
select(Document).where(Document.source == SOURCE, Document.path == NOTES_REL)
|
|
)
|
|
is not None
|
|
)
|
|
finally:
|
|
_cleanup_source(db, SOURCE)
|
|
|
|
|
|
def test_prune_removes_extensionless_rows_when_the_token_is_removed(
|
|
mock_llm_port: int, db: Session
|
|
) -> None:
|
|
"""D4: a file that stops matching — the token leaves the env —
|
|
leaves ``seen`` and is deleted by the next ``prune=True`` run (the
|
|
A9 junk precedent); the in-scope ``notes.md`` row survives."""
|
|
with_tokens = _settings(mock_llm_port, "md,dockerfile,containerfile")
|
|
asyncio.run(import_sources([FIXTURES], LLMClient(with_tokens), session=db))
|
|
try:
|
|
md_only = _settings(mock_llm_port, "md")
|
|
summary = asyncio.run(
|
|
import_sources([FIXTURES], LLMClient(md_only), session=db, prune=True)
|
|
)
|
|
assert summary.pruned == 2, "the two extensionless rows must be pruned"
|
|
assert summary.unchanged == 1, "notes.md must survive the prune"
|
|
for rel in (DOCKER_REL, CONTAINER_REL):
|
|
assert (
|
|
db.scalar(
|
|
select(Document).where(Document.source == SOURCE, Document.path == rel)
|
|
)
|
|
is None
|
|
), f"{rel} survived although its token left the env"
|
|
assert (
|
|
db.scalar(
|
|
select(Document).where(Document.source == SOURCE, Document.path == NOTES_REL)
|
|
)
|
|
is not None
|
|
)
|
|
finally:
|
|
_cleanup_source(db, SOURCE)
|