feat(rag): lite-generated KB overview in the system prompt — stored single row, regenerated on import, <knowledge_base> section in HIGH+LOW prompts

This commit is contained in:
2026-08-25 20:22:51 -04:00
parent 572a4190a6
commit 0654b304e1
23 changed files with 2276 additions and 34 deletions
@@ -0,0 +1,222 @@
"""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``.
"""
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.models import KbOverview
from app.rag.llm import LLMError
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 _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"))
db.commit()
yield
db.execute(text("TRUNCATE chunks, documents, kb_overview"))
db.commit()
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
assert out.rstrip().endswith("overview=updated")
# Exactly one lite call — the overview itself (markdown files never
# get a summary, so nothing else may touch ``chat``).
assert len(llm.chat_calls) == 1
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"]
# 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")
assert len(llm.chat_calls) == 1
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")
assert len(llm.chat_calls) == 1 # no new lite call
row = _row(db)
assert row is not None and row.content == "Summary of MyDocs"
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")
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
assert out.rstrip().endswith("overview=failed")
assert len(bad.chat_calls) == 1 # the (failed) attempt was made
row = _row(db)
assert row is not None
assert row.content == previous_content # previous row untouched
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")
assert len(llm.chat_calls) == 1
# An incomplete walk must not rewrite the outline (mirrors the
# --prune-with---limit guard).
(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")
assert len(llm.chat_calls) == 1 # --limit never burns a lite call
row = _row(db)
assert row is not None and row.content == "Summary of MyDocs"
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")
assert llm.chat_calls == [] # no KB → no outline, no wasted model call
assert _row(db) is None # nothing created