mirror of
https://github.com/kuhyx/testsAndMisc.git
synced 2026-11-10 18:07:06 +01:00
Krzysztof kuhy Rudnicki
9cb4c81322
Some checks are pending
dependency freshness / dependencies on newest stable (push) Waiting to run
md-naming / markdown naming convention (push) Waiting to run
Pre-commit checks / pre-commit (${{ matrix.group }}) (mypy, mypy) (push) Waiting to run
Pre-commit checks / pre-commit (${{ matrix.group }}) (pylint, pylint) (push) Waiting to run
Pre-commit checks / pre-commit (${{ matrix.group }}) (rest, ) (push) Waiting to run
Pre-commit checks / pre-commit (${{ matrix.group }}) (shellcheck, shellcheck) (push) Waiting to run
Python tests / test (push) Waiting to run
repo-contract / repo contract (push) Waiting to run
Shell tests / shell-tests (push) Waiting to run
Shell tests / lib-tests (push) Waiting to run
Shell tests / arch-tests (push) Waiting to run
Links sessions to todo notes (note_claim.sh, todo-images prompts, fuzzy first prompt >= 0.5, handoff chains), dates completions from the status HLC in the first Firebase dump, and adds usd_per_note, note_linked_usd_share, notes_done(_linked) to the snapshot, a WEEKLY section and notes.json. token_dashboard stores the build-class A/B (agent-ab-build.jsonl) as meta ab_build. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01WzxdWWMeapxnDcgk7HSw67
70 lines
2.5 KiB
Python
70 lines
2.5 KiB
Python
"""The build-class A/B (agent-ab-build.jsonl) is summarised on its own."""
|
|
|
|
from __future__ import annotations
|
|
|
|
import json
|
|
from typing import TYPE_CHECKING
|
|
|
|
from python_pkg.token_dashboard import ab, ingest, schema
|
|
from python_pkg.token_dashboard.tests.conftest import assistant, prompt, result, use
|
|
from python_pkg.token_dashboard.tests.conftest import write as write_jsonl
|
|
|
|
if TYPE_CHECKING:
|
|
from pathlib import Path
|
|
|
|
|
|
def _store(tmp_path: Path) -> Path:
|
|
root = tmp_path / "projects"
|
|
write_jsonl(
|
|
root / "p" / "s1.jsonl",
|
|
[
|
|
prompt("go", 0),
|
|
assistant("m1", 1, blocks=[use("t1", "Agent", description="Build x")]),
|
|
result("t1", 50, "done", toolUseResult={"agentId": "abc"}),
|
|
assistant("m2", 60, blocks=[use("t2", "Agent", description="Review y")]),
|
|
result("t2", 70, "done", toolUseResult={"agentId": "def"}),
|
|
],
|
|
)
|
|
db = tmp_path / "t.sqlite"
|
|
ingest.run(root, db, tmp_path / "report", 30.0)
|
|
return db
|
|
|
|
|
|
def _log(path: Path, rows: list[dict[str, str]]) -> Path:
|
|
path.write_text("\n".join(json.dumps(r) for r in rows), encoding="utf-8")
|
|
return path
|
|
|
|
|
|
def test_build_log_lands_in_its_own_meta_row(tmp_path: Path) -> None:
|
|
conn = schema.connect(_store(tmp_path))
|
|
judgment = _log(
|
|
tmp_path / "agent-ab.jsonl",
|
|
[{"tool_use_id": "t2", "arm": "opus", "class": "review"}],
|
|
)
|
|
build = _log(
|
|
tmp_path / "agent-ab-build.jsonl",
|
|
[{"tool_use_id": "t1", "arm": "sonnet", "class": "build"}],
|
|
)
|
|
ab.rebuild(conn, judgment, build)
|
|
stored = {
|
|
k: json.loads(v)
|
|
for k, v in conn.execute("SELECT key, value FROM meta WHERE key LIKE 'ab%'")
|
|
}
|
|
rows = conn.execute("SELECT tool_use_id FROM ab_rows").fetchall()
|
|
conn.close()
|
|
assert stored["ab"]["arms"]["opus"]["n"] == 1
|
|
assert stored["ab"]["arms"]["sonnet"]["n"] == 0
|
|
assert stored["ab_build"]["arms"]["sonnet"]["n"] == 1
|
|
assert stored["ab_build"]["arms"]["opus"]["n"] == 0
|
|
assert stored["ab_build"]["banner"]["text"].startswith("A/B build agents")
|
|
assert stored["ab"]["banner"]["text"].startswith("A/B judgment agents")
|
|
assert rows == [("t2",)]
|
|
|
|
|
|
def test_missing_build_log_stores_an_empty_summary(tmp_path: Path) -> None:
|
|
conn = schema.connect(_store(tmp_path))
|
|
ab.rebuild(conn, tmp_path / "none.jsonl", tmp_path / "none-build.jsonl")
|
|
raw = conn.execute("SELECT value FROM meta WHERE key = 'ab_build'").fetchone()
|
|
conn.close()
|
|
assert json.loads(raw[0])["arms"]["sonnet"]["n"] == 0
|