Files
brain-of-reese/tests/integration/test_import_docs_overview.py
T
ducoterra d4943b4822
Build and Push Containers / build-and-push-app (push) Successful in 1m45s
Build and Push Containers / build-and-push-db (push) Successful in 25s
phase: 94_ls_tree_drilldown
All green. Verification complete.

**Phase 94 — `ls` drill-down tree: final verification pass (all 5 tasks were already complete; verified, nothing to fix)**

- Verified `ls` 3-level tree (`app/rag/agent.py`): `ls()` sources + summaries, `ls(source)`/`ls(source/folder)` drill-down, 50-line file cap + grep-pointer note, NOT-A-FOLDER teaching refusal
- Verified `folder_summaries` (migration 0017, model, `app/rag/folder_summaries.py` generator: `FOLDER_SUMMARY_MODE` marker, fail-soft per folder, ≥2-doc scope + prune) wired change-gated in both sync paths
- Verified 10-turn fixture battery verdict recorded in `TOOL_CALLING_TESTING.md` §9 (2026-09-11): turbo PASS 19/19 contract, 98.7 s (−12.5…−13.2 % vs baseline); lite PASS 18/18, 43.6 s (+7.7 %) — accuracy at/above baseline, gate met
- `uv run pytest --cov=app --cov-report=term-missing` → 1939 passed, 0 failed; TOTAL coverage **99 %** (folder_summaries.py 100 %)
- `uv run ruff check .` → clean; `uv run pyright` → 0 errors, 0 warnings
- E2E in isolation: `test_ls_tree_drilldown.py` 3 passed; `test_agent_document_tools` 4, `test_agent_unlimited_tools` 4, `test_harness_aligned_tools` 3, `test_search_tool` 3, `test_grep_regex_teaching` 2, `test_response_to_docs` 4 — all passed (read/grep contracts untouched)
- Dedicated folder-summary tests (fail-soft, prune, both sync paths, migration): 46 passed
- Completion criteria: all 6 met; working tree holds only phase-94 changes (commit left to harness per protocol)

**Next pending phase:** `95_read_truncation_cap`
2026-09-11 00:59:35 -04:00

339 lines
13 KiB
Python

"""Integration test: ``import_docs`` regenerates the KB overview (phase 31, task 04).
Drives ``scripts.import_docs.main()`` end to end against the local compose
Postgres with a deterministic fake LLM (no live aipi, no git — explicit
``--source`` dirs and fresh settings, the phase 28 test's mocking style),
covering the change-gated overview trigger:
- a KB-changing import → ``kb_overview`` row written, the ``lite`` ``chat``
called exactly once, summary line ends ``overview=updated``;
- an unchanged re-import → ``chat`` **not** called again, ``overview=skipped``;
- a ``lite`` failure → exit code still ``0`` (the import itself was fine),
``overview=failed``, the previous row untouched;
- a ``--limit`` debug run with changes → ``overview=skipped``;
- an empty source run with no row → no row created, ``overview=skipped``.
Phase 53 (task 02): the sources-version bump sits alongside the
overview gate — a KB-changing run bumps ``sources_meta`` exactly once
(``sources_version=<n>`` on the summary line), including a **prune-only**
run: the invalidation gate ``added + updated + pruned > 0`` is
deliberately broader than the overview's (a pruned doc can invalidate a
saved answer that cited it, while the outline stays). ``--limit`` runs
and unchanged re-runs never bump (``sources_version=skipped``), and a
failed ``lite`` never rolls the bump back. The counter is pinned to the
migration-0010 seed (0) around every test by
:func:`_reset_sources_version`.
Phase 94 (task 02, line-extension house rule): the summary line now
ends with the folder-summary stats —
``folder_summaries=<generated>/<failed>/<pruned>`` when the gate fired
(this fixture's 2-doc source holds exactly ONE qualifying subtree: the
source root) or ``folder_summaries=skipped`` otherwise — so the line
pinned here gains that token, and a KB-changing run burns exactly ONE
extra ``lite`` call (the source-root folder summary, markdown files
never get a document summary).
"""
from __future__ import annotations
import logging
from collections.abc import Iterator
from pathlib import Path
import pytest
from sqlalchemy import text
from sqlalchemy.orm import Session
from app.config import Settings
from app.db import SessionLocal, db_available
from app.models import KbOverview
from app.rag.llm import LLMError
from app.rag.sources_meta import current_sources_version
from scripts import import_docs
from tests.fakes import FakeEmbedder
class FailingChatEmbedder(FakeEmbedder):
"""A ``lite`` model that always fails (drives the fail-soft path)."""
async def chat(self, messages: list[dict[str, str]], model: str | None = None) -> str:
self.chat_calls.append(list(messages))
raise LLMError("simulated lite-model failure (test sentinel)")
def _row(db: Session) -> KbOverview | None:
"""The stored ``kb_overview`` row (freshly reloaded)."""
db.expire_all()
return db.get(KbOverview, 1)
def _version(db: Session) -> int:
"""The ``sources_meta`` generation (phase 53; freshly reloaded)."""
db.expire_all()
return current_sources_version(db)
def _run_main(
monkeypatch: pytest.MonkeyPatch,
llm: FakeEmbedder,
argv: list[str],
capsys: pytest.CaptureFixture[str],
) -> tuple[int, str]:
"""Run ``import_docs.main`` with fresh settings, a fake LLM, and a
fail-loud git mock (``--source`` always wins, so git must stay idle)."""
monkeypatch.setattr(
import_docs,
"get_settings",
lambda: Settings(_env_file=None), # pyright: ignore[reportCallIssue]
)
def _no_git(url: str, dest: Path | str) -> Path:
raise AssertionError("git sync must not run with explicit --source")
monkeypatch.setattr(import_docs, "clone_or_pull", _no_git)
monkeypatch.setattr(import_docs, "LLMClient", lambda: llm)
rc = import_docs.main(argv)
return rc, capsys.readouterr().out
@pytest.fixture()
def src(tmp_path: Path) -> Path:
"""A source dir with two markdown docs (md → no summary chat calls)."""
root = tmp_path / "MyDocs"
root.mkdir()
(root / "alpha.md").write_text("# Alpha\n\nFirst document.\n", encoding="utf-8")
(root / "beta.md").write_text("# Beta\n\nSecond document.\n", encoding="utf-8")
return root
@pytest.fixture(autouse=True)
def _clean_kb(db: Session) -> Iterator[None]:
db.execute(text("TRUNCATE chunks, documents, kb_overview, folder_summaries"))
db.commit()
yield
db.execute(text("TRUNCATE chunks, documents, kb_overview, folder_summaries"))
db.commit()
@pytest.fixture(autouse=True)
def _reset_sources_version() -> Iterator[None]:
"""Phase 53: the sources version counter is global mutable state —
pin it to the migration-0010 seed (0) around every test so the bump
assertions start from a known generation (own session: the CLI
bumps through its own short-lived ``SessionLocal``). Skips like the
``db`` fixture when Postgres is down."""
if not db_available():
pytest.skip("Postgres not reachable — run `podman compose up -d db` first")
session = SessionLocal()
try:
session.execute(text("UPDATE sources_meta SET version = 0 WHERE id = 1"))
session.commit()
yield
finally:
session.execute(text("UPDATE sources_meta SET version = 0 WHERE id = 1"))
session.commit()
session.close()
def test_changed_import_writes_overview_row(
db: Session,
src: Path,
monkeypatch: pytest.MonkeyPatch,
capsys: pytest.CaptureFixture[str],
) -> None:
llm = FakeEmbedder()
records: list[logging.LogRecord] = []
class _Sink(logging.Handler):
def emit(self, record: logging.LogRecord) -> None:
records.append(record)
overview_logger = logging.getLogger("app.rag.overview")
sink = _Sink()
overview_logger.addHandler(sink)
overview_logger.setLevel(logging.INFO)
try:
rc, out = _run_main(monkeypatch, llm, ["--source", str(src)], capsys)
finally:
overview_logger.removeHandler(sink)
assert rc == 0
assert "added=2" in out
# Phase 94: the line gains the folder-stats token — the 2-doc source
# holds one qualifying subtree (the source root): 1 generated.
assert out.rstrip().endswith(
"overview=updated sources_version=1 folder_summaries=1/0/0"
)
assert _version(db) == 1 # phase 53: a changed import bumps exactly once
# Exactly two lite calls — the overview + the source-root folder
# summary (markdown files never get a document summary, so nothing
# else may touch ``chat``).
assert len(llm.chat_calls) == 2
by_role = {m["role"]: m["content"] for m in llm.chat_calls[0]}
assert "KB_OVERVIEW_MODE" in by_role["system"]
# One line per doc: source — path — title (no summary for markdown).
assert "MyDocs — alpha.md — Alpha" in by_role["user"]
assert "MyDocs — beta.md — Beta" in by_role["user"]
by_role = {m["role"]: m["content"] for m in llm.chat_calls[1]}
assert "FOLDER_SUMMARY_MODE" in by_role["system"]
assert by_role["user"].splitlines()[0] == "Folder: MyDocs"
# The model's outline lands in the single row.
row = _row(db)
assert row is not None
assert row.content == "Summary of MyDocs"
assert row.updated_at is not None
# The phase's required log line (PLAN §9).
assert any("overview: regenerated docs=2 chars=" in r.getMessage() for r in records)
def test_unchanged_reimport_does_not_call_lite(
db: Session,
src: Path,
monkeypatch: pytest.MonkeyPatch,
capsys: pytest.CaptureFixture[str],
) -> None:
llm = FakeEmbedder()
rc, out = _run_main(monkeypatch, llm, ["--source", str(src)], capsys)
assert rc == 0
assert out.rstrip().endswith(
"overview=updated sources_version=1 folder_summaries=1/0/0"
)
assert len(llm.chat_calls) == 2 # overview + source-root folder summary
assert _row(db) is not None
# Same hashes → no KB change → no lite call, previous outline kept.
rc, out = _run_main(monkeypatch, llm, ["--source", str(src)], capsys)
assert rc == 0
assert "unchanged=2" in out
assert out.rstrip().endswith(
"overview=skipped sources_version=skipped folder_summaries=skipped"
)
assert len(llm.chat_calls) == 2 # no new lite call
row = _row(db)
assert row is not None and row.content == "Summary of MyDocs"
assert _version(db) == 1 # phase 53: an unchanged re-run never bumps
def test_lite_failure_is_fail_soft(
db: Session,
src: Path,
monkeypatch: pytest.MonkeyPatch,
capsys: pytest.CaptureFixture[str],
) -> None:
good = FakeEmbedder()
rc, out = _run_main(monkeypatch, good, ["--source", str(src)], capsys)
assert rc == 0
assert out.rstrip().endswith(
"overview=updated sources_version=1 folder_summaries=1/0/0"
)
previous = _row(db)
assert previous is not None
previous_content = previous.content
# A KB-changing run whose ``lite`` model fails: the import still
# succeeds (exit 0) and the previous outline stays untouched.
(src / "alpha.md").write_text("# Alpha\n\nChanged content.\n", encoding="utf-8")
bad = FailingChatEmbedder()
rc, out = _run_main(monkeypatch, bad, ["--source", str(src)], capsys)
assert rc == 0 # a failed outline must not fail the import
assert "updated=1" in out
# Phase 94: the folder batch fails too (per-folder fail-soft) — the
# failed attempt counts into the stats, the previous row stays.
assert out.rstrip().endswith(
"overview=failed sources_version=2 folder_summaries=0/1/0"
)
assert len(bad.chat_calls) == 2 # the (failed) attempts were made
row = _row(db)
assert row is not None
assert row.content == previous_content # previous row untouched
# Phase 53: the bump commits independently of the best-effort
# overview — a failed ``lite`` never rolls the version back.
assert _version(db) == 2
def test_limit_run_skips_overview(
db: Session,
src: Path,
monkeypatch: pytest.MonkeyPatch,
capsys: pytest.CaptureFixture[str],
) -> None:
llm = FakeEmbedder()
rc, out = _run_main(monkeypatch, llm, ["--source", str(src)], capsys)
assert rc == 0
assert out.rstrip().endswith(
"overview=updated sources_version=1 folder_summaries=1/0/0"
)
assert len(llm.chat_calls) == 2
# An incomplete walk must not rewrite the outline (mirrors the
# --prune-with---limit guard) — and must not advance the version.
(src / "alpha.md").write_text("# Alpha\n\nChanged content.\n", encoding="utf-8")
rc, out = _run_main(monkeypatch, llm, ["--source", str(src), "--limit", "1"], capsys)
assert rc == 0
assert "updated=1" in out
assert out.rstrip().endswith(
"overview=skipped sources_version=skipped folder_summaries=skipped"
)
assert len(llm.chat_calls) == 2 # --limit never burns a lite call
row = _row(db)
assert row is not None and row.content == "Summary of MyDocs"
assert _version(db) == 1 # phase 53: --limit debug runs never bump
def test_empty_source_without_row_creates_nothing(
db: Session,
tmp_path: Path,
monkeypatch: pytest.MonkeyPatch,
capsys: pytest.CaptureFixture[str],
) -> None:
empty = tmp_path / "EmptyDocs"
empty.mkdir()
llm = FakeEmbedder()
rc, out = _run_main(monkeypatch, llm, ["--source", str(empty)], capsys)
assert rc == 0
assert "files=0" in out
assert out.rstrip().endswith(
"overview=skipped sources_version=skipped folder_summaries=skipped"
)
assert llm.chat_calls == [] # no KB → no outline, no wasted model call
assert _row(db) is None # nothing created
assert _version(db) == 0 # nothing changed → nothing bumped
def test_prune_only_run_bumps_sources_version(
db: Session,
src: Path,
monkeypatch: pytest.MonkeyPatch,
capsys: pytest.CaptureFixture[str],
) -> None:
"""Phase 53 (task 02): the invalidation gate is deliberately broader
than the overview's — a prune-only run (added + updated == 0,
pruned > 0) advances the version (a pruned document can invalidate
a saved answer that cited it) while the outline stays.
"""
llm = FakeEmbedder()
rc, out = _run_main(monkeypatch, llm, ["--source", str(src)], capsys)
assert rc == 0
assert "added=2" in out
assert out.rstrip().endswith(
"overview=updated sources_version=1 folder_summaries=1/0/0"
)
assert _version(db) == 1
# Delete one file; a --prune run drops exactly it: no add/update,
# but pruned=1 → the version still bumps while the overview skips.
(src / "alpha.md").unlink()
rc, out = _run_main(monkeypatch, llm, ["--source", str(src), "--prune"], capsys)
assert rc == 0
assert "pruned=1" in out
# Phase 94: the folder gate is the overview's (added + updated > 0
# or empty table) — a prune-only re-walk with a populated table
# skips generation (the remaining 1-doc source stays summarized by
# its existing root row, which still describes it).
assert out.rstrip().endswith(
"overview=skipped sources_version=2 folder_summaries=skipped"
)
assert _version(db) == 2 # the prune-only change bumped exactly once
assert _row(db) is not None # the outline row is untouched