test(agent): controlled fixture KB + one-command fast loop for tool-calling iterations

The phase-72 iteration loop cleared the database, git-cloned the homelab repo, re-imported 38-51 documents and re-embedded per run — many minutes per iteration against a different KB every time (owner directive 2026-09-04: stop importing the homelab repo on every test run). Replace it with:

- tests/fixtures/agent_kb/: 8 hand-written markdown docs (sources 'deployments'/'homelab') whose specifics (rack7, 10.77.42.0/24, VLAN 130, rbm-8842, 17 2 * * *, obsidian-bor:2026.7.14, 18765, 18443, ...) no model can guess; read targets carry non-topical filenames so their questions do not lexically seed them (the read must actually happen)
- tests/fixtures/test_kb.dump.sql: data-only snapshot (TRUNCATE + INSERTs incl. embeddings, self-contained git_sources rows, static KB overview) — verified by round-trip checksum at build time
- scripts/load_test_kb.py: one-off rebuild (real pipeline + embeddings, ~2s) that also prints the per-question retrieval report (all 10 battery questions must be grounded)
- scripts/restore_test_kb.py: sub-second one-transaction restore (no git clone, no re-embedding)
- scripts/agent_realmodel_check.py: the gate gains --restore / --mode fixture (curated 10-question battery with one unambiguously correct tool behavior per question) / --turns N (12s micro-loop) / --concurrency / per-turn + total wall timing, and a second accuracy metric (contract accuracy: well-formed calls targeting resolvable entities) alongside the phase-72 locked executed ratio — the re-read of a seeded doc is a copy-invariant model behavior (5 variants, 0/15 flipped) that the dedupe refusal counts as a failure
- TOOL_CALLING_TESTING.md: the human-readable methodology (fast loop, design rules, metrics, copy levers + tried-and-reverted table, current standing, open design question)

Measured: restore 0.03s; micro-loop ~12s; full loop ~43-55s; concurrency 2/3 gives no gain (endpoint serializes).
This commit is contained in:
2026-09-04 13:10:15 -04:00
parent 575d6c88d0
commit 7909bdb8da
13 changed files with 2090 additions and 0 deletions
+178
View File
@@ -0,0 +1,178 @@
"""One-shot restore of the controlled tool-calling test KB (the fast loop).
The fixture KB (``tests/fixtures/agent_kb/`` — two sources, eight
hand-written markdown documents) is built once by
:mod:`scripts.load_test_kb`, which embeds the documents and snapshots the
resulting database state into ``tests/fixtures/test_kb.dump.sql`` — a
data-only SQL script (``TRUNCATE`` + one multi-row ``INSERT`` per app
table, generated in-process — the same file runs in psql or psycopg). This
script restores that
snapshot in **one transaction** through the app's own database URL
(``BOR_DATABASE_URL``): no git clone of the homelab repo, no re-embedding,
no ``lite``-model calls — the whole known state (documents, chunks +
embeddings, the source registry rows, the KB overview, the sources
version) lands in a fraction of a second, which is what makes a
tool-calling iteration loop fast (see ``TOOL_CALLING_TESTING.md``):
uv run python -m scripts.restore_test_kb
# restore_test_kb: ok in 0.41s (8 docs, 2 sources, 16 chunks)
The gate runs the same restore inline:
``uv run python -m scripts.agent_realmodel_check --restore``.
The dump is data-only on purpose: the schema stays owned by alembic, and
the generated ``chunks.tsv`` tsvector column (``GENERATED ALWAYS AS …
STORED``) is recomputed by Postgres, so the restore is safe against schema
drift limited to additive columns. Restoring into a database whose schema
lacks an app table fails loudly with an actionable line (exit 2).
Exit codes: **0** restored, **2** precondition failure (DB unreachable,
dump missing, schema not applied).
"""
from __future__ import annotations
import argparse
import sys
import time
from dataclasses import dataclass
from pathlib import Path
import psycopg
from dotenv import load_dotenv
from sqlalchemy import text
from app.db import SessionLocal, db_available
#: The app tables the dump covers, TRUNCATE order (one statement —
#: Postgres resolves the inter-table FKs within it). ``chunks`` and
#: ``documents`` are listed first for readability; the order is
#: irrelevant inside a single TRUNCATE.
APP_TABLES: tuple[str, ...] = (
"chunks",
"documents",
"git_sources",
"kb_overview",
"sources_meta",
"steering_notes",
"query_log",
"saved_chats",
"doc_drafts",
)
#: Repo-relative default dump location (the load script writes it there).
DEFAULT_DUMP = Path("tests/fixtures/test_kb.dump.sql")
@dataclass(frozen=True)
class RestoreResult:
"""What :func:`restore_dump` did — one line of the summary output."""
seconds: float
docs: int
sources: tuple[str, ...]
chunks: int
dump_bytes: int
def _connect():
"""A raw psycopg connection on the app's DB URL (psycopg3 speaks the
SQLAlchemy URL's driver scheme — ``postgresql+psycopg`` maps to
``postgresql`` for psycopg)."""
from app.config import get_settings
url = get_settings().database_url
if url.startswith("postgresql+psycopg://"):
url = "postgresql://" + url.split("://", 1)[1]
return psycopg.connect(url)
def restore_dump(dump: Path) -> RestoreResult:
"""Restore *dump* (the data-only SQL script) into the app database.
One transaction (TRUNCATE + INSERTs + nothing else — a failed restore
rolls back and leaves the previous KB intact). Returns the measured
result; raises :class:`RuntimeError` with an actionable line on
failure (missing table = schema not applied).
"""
if not dump.is_file():
raise RuntimeError(
f"dump not found: {dump} — build it first: "
"`uv run python -m scripts.load_test_kb`"
)
script = dump.read_text(encoding="utf-8")
started = time.monotonic()
conn = _connect()
try:
with conn.transaction():
# A plain multi-statement SQL script (TRUNCATE + INSERTs — no
# parameters) runs on psycopg's simple-protocol execute; the
# installed stubs type the query parameter as Template-only
# (and ``sql.SQL`` wants a LiteralString), hence the ignore.
conn.execute(script) # pyright: ignore[reportArgumentType, reportCallIssue]
except Exception as e:
message = str(e)
if "relation" in message and "does not exist" in message:
raise RuntimeError(
"schema not applied — the dump needs the alembic-managed "
f"tables; run `uv run alembic upgrade head` first ({e})"
) from None
raise RuntimeError(f"restore failed: {e}") from None
seconds = time.monotonic() - started
with SessionLocal() as db:
docs = db.execute(text("select count(*) from documents")).scalar_one()
sources = tuple(
row[0]
for row in db.execute(
text("select distinct source from documents order by source")
)
)
chunks = db.execute(text("select count(*) from chunks")).scalar_one()
return RestoreResult(
seconds=seconds,
docs=docs,
sources=sources,
chunks=chunks,
dump_bytes=dump.stat().st_size,
)
def main(argv: list[str] | None = None) -> int:
# CLI-only: pick up .env without side effects on import (the house
# probe pattern, cf. scripts/llm_probe.py).
load_dotenv()
parser = argparse.ArgumentParser(
description=(
"Restore the controlled tool-calling test KB from the fixture "
"dump (one transaction, no git clone, no re-embedding). Exit "
"0 on success, 2 on precondition failure."
)
)
parser.add_argument(
"--dump",
type=Path,
default=DEFAULT_DUMP,
help=f"the data-only SQL dump to restore (default: {DEFAULT_DUMP})",
)
args = parser.parse_args(argv)
if not db_available():
print(
"restore_test_kb: precondition failed — database unreachable; "
"start Postgres with `podman compose up -d db`"
)
return 2
try:
result = restore_dump(args.dump)
except RuntimeError as e:
print(f"restore_test_kb: {e}")
return 2
print(
f"restore_test_kb: ok in {result.seconds:.2f}s "
f"({result.docs} docs, {len(result.sources)} sources, "
f"{result.chunks} chunks, dump {result.dump_bytes // 1024} KB)"
)
return 0
if __name__ == "__main__":
sys.exit(main())