headroom/tests/test_audit_codex.py

Ignoring revisions in .git-blame-ignore-revs. Click here to bypass and see the normal blame view.

136 lines
4.7 KiB
Python
Raw Normal View History

feat: compression extraction — Rust knob exposure, CCR hardening, traffic audits (#818) ## Description A data-driven push for better compression savings without accuracy loss, in four parts: expose and tune the Rust compressor knobs, harden the CCR retrieval store, add traffic-audit tooling that sizes opportunities from real transcripts, and introduce **read maturation** — a new, live-validated mechanism that compresses Read outputs *before* they ever enter the provider prefix cache. ## Type of Change - [x] Bug fix (non-breaking change that fixes an issue) - [x] New feature (non-breaking change that adds functionality) - [ ] Breaking change (fix or feature that would cause existing functionality to change) - [ ] Documentation update - [x] Performance improvement - [ ] Code refactoring (no functional changes) ## Changes Made ### 1. Rust compressor extraction - Expose `lossless_min_savings_ratio` end-to-end and lower the default 0.30 → 0.15 (lockstep across Rust, PyO3, and both Python config classes) so the lossless Table/CSV compaction path wins more often. - Expose the `CompactConfig` heuristics (core-field fraction, heterogeneity ratio, flatten cap, bucket bounds) through PyO3 + Python. - `SearchCompressor` grouped-by-file output (`rg --heading` style — path once per file instead of per match). Library default off; the proxy enables it in token mode. - Complete `factor_out_constants`: constant fields now emit once in a `_constant_fields` sentinel with slim rows (defensive per-item value match; default off). - `ContentRouter` accepts a SmartCrusher config override and the search-grouping knob. ### 2. CCR store hardening - Session-scale TTL: 300s → 1800s (CCRConfig, CompressionEntry, CompressionStore, Rust `DEFAULT_TTL` — lockstep). - **SQLite is the default CCR backend** (`~/.headroom/ccr_store.db`, WAL): survives proxy restarts and is shared across workers. `HEADROOM_CCR_BACKEND=memory` opts out. - Multi-worker safety: `busy_timeout`, and corruption detection narrowed so transient `SQLITE_BUSY` errors can never trigger database deletion. - Data-at-rest hygiene: `chmod 600` on db + sidecars, expired rows swept at open. - Retrieval-miss messages are actionable (re-read the file / re-run the command). ### 3. Traffic audit tooling (measure before tuning) - `headroom audit-reads`: sizes Read opportunities from local Claude Code transcripts (read share, stale %, line-number overhead, context residency, cache-death windows). - `--simulate-maturation`: Mechanism B risk sizing (re-read rates, never-touched-again share, quiesce coverage, at-risk edits). - `--codex`: shell-read classifier for Codex transcripts (rtk-wrapper aware, workdir resolution). - Findings that shaped this PR (81 sessions): Reads are 67% of tool bytes; median Read lingers 118 turns (~13x lifetime cost); a prototyped repeat-Read dedup measured 0.1% and was **removed** rather than shipped as dead code. ### 4. Read maturation (Mechanism B) — experimental, default OFF - Activity-based: a fresh large Read is held **out** of the provider cache (trailing breakpoint relocated before it), stays verbatim while its file is active, and matures into a CCR-backed marker once the file is quiet for `quiesce_turns` (default 5; `max_hold_turns` bounds busy files). - Only the final compressed form ever enters the cache — **no cached byte is ever mutated**; matured markers replay byte-identically. - Wired into the Anthropic handler behind `--read-maturation` / `HEADROOM_READ_MATURATION=1`; session state rides on the prefix tracker; advisory (can never fail a request). - Live-validated against the Anthropic API: held content excluded from cache_creation; after maturation the prior cached prefix still served — the no-bust invariant holds end-to-end. ### 5. Rebase / CI fixups (this update) - Rebased onto latest `main` (was 28 commits behind): picks up `ci: pass CODECOV_TOKEN to coverage uploads (#968)`, which is what was turning the 4 test shards red — the tests themselves passed (1528) but the post-test codecov upload exited non-zero on a protected branch. - Resolved the duplicate `lossless_min_savings_ratio` that two independent main/branch additions left in `SmartCrusherConfig` and the Rust-config kwarg (import-time `SyntaxError` + mypy `no-redef`). - Aligned CCR tests with the new defaults (SQLite backend, 1800s TTL) across `test_ccr`, `test_adapter_hooks`, `test_compression_store`, `test_proxy_ccr`, and the lossy row-drop bridge test. ## Testing <!-- Check what you actually ran, then paste the real command output below. --> - [x] Unit tests pass (`pytest`) - [x] Linting passes (`ruff check .`) - [x] Type checking passes (`mypy headroom`) - [x] New tests added for new functionality - [ ] Manual testing performed ### Test Output ```text $ python -m pytest tests/test_proxy_ccr.py tests/test_ccr.py tests/test_compression_store.py tests/test_adapter_hooks.py tests/test_ccr_row_drop_store_bridge.py -q 170 passed, 4 warnings in 42.49s $ python -m pytest tests/test_audit_reads.py tests/test_audit_codex.py tests/test_read_maturation.py tests/test_transforms_content_router.py tests/test_smart_crusher_toin_attachment.py -q 83 passed $ mypy headroom/ Success: no issues found in 365 source files $ python -m compileall headroom/ -q COMPILE-OK # CI (run 27488990477, pre-rebase head): all 4 shards ran to completion — # "1528 passed, 120 skipped, 4922 deselected" # The red shards were the codecov upload step, not test failures; fixed by # the #968 rebase above. ``` ## Real Behavior Proof - Environment: macOS (darwin), Python 3.12 venv; branch `feat/compression-extraction` rebased onto `origin/main` (head 7cb0f43b); GitHub Actions CI run 27488990477 for the test shards - Exact command / steps: rebased onto latest main (clean, 13 commits replayed, 0 conflicts); ran the pytest suites and mypy above locally; inspected CI shard logs to confirm the failure was the codecov upload, not the test phase - Observed result: 253 targeted tests pass locally; mypy clean on 365 files; CI test phase reports `1528 passed, 120 skipped`; the only red step (codecov `upload-coverage` → "Token required because branch is protected") is resolved by the rebased-in #968 CODECOV_TOKEN fix - Not tested: the read-maturation live-API no-bust validation (`tests/test_live/`) was not re-run in this rebase pass (requires provider keys); it was validated when the feature first landed, and no maturation code changed in the rebase — only CCR-default test assertions and the duplicate-field resolution ## Review Readiness - [x] I have performed a self-review - [x] This PR is ready for human review ## Checklist - [x] My code follows the project's style guidelines - [x] I have performed a self-review of my code - [x] I have commented my code, particularly in hard-to-understand areas - [ ] I have made corresponding changes to the documentation - [x] My changes generate no new warnings - [x] I have added tests that prove my fix is effective or that my feature works - [x] New and existing unit tests pass locally with my changes - [ ] I have updated the CHANGELOG.md if applicable ## Additional Notes CHANGELOG is generated by release-please from the conventional commits, so the CHANGELOG box is intentionally left unchecked. "Manual testing performed" is unchecked deliberately — see `Real Behavior Proof` → `Not tested` for the exact boundary (the live-API maturation validation was not re-run in this rebase pass). ### Follow-ups (tracked, not in this PR) - Mechanism B provider extensions: OpenAI-family wiring (no breakpoint hold — bounded near-tail bust) and the Codex runtime read-detector (the audit classifier is the prototype). - Pilot enablement playbook: run `audit-reads --simulate-maturation` on target traffic → pick `quiesce_turns` → enable via env → watch cache hit rate + `read_maturation:N` transform tags.
2026-06-16 20:21:13 -07:00
"""Tests for the Codex read-pattern audit (headroom.audit.codex)."""
from __future__ import annotations
import json
import pytest
from headroom.audit.codex import audit_codex, classify_command, render_codex_text, strip_wrappers
class TestClassifier:
def test_strip_wrappers(self):
assert strip_wrappers("rtk cat foo.py") == "cat foo.py"
assert strip_wrappers("rtk proxy sed -n '1,20p' foo.py") == "sed -n '1,20p' foo.py"
assert strip_wrappers("git status") == "git status"
@pytest.mark.parametrize(
("cmd", "category", "partial"),
[
("cat src/foo.py", "read", False),
("sed -n '1,200p' src/foo.py", "read", True),
("rtk read src/foo.py --lines 10-50", "read", True),
("head -50 src/foo.py", "read", True),
("nl headroom/config.py", "read", False),
("rg -n 'def apply' headroom/", "search", False),
("rtk grep -n pattern .", "search", False),
("git diff HEAD~1", "git", False),
("apply_patch <<'EOF'\n*** Begin Patch\nEOF", "edit", False),
("pytest tests/ -x -q", "build/test", False),
("echo hello", "other", False),
],
)
def test_categories(self, cmd, category, partial):
cat, _path, is_partial = classify_command(cmd)
assert cat == category
if category == "read":
assert is_partial == partial
def test_path_extraction_and_workdir(self):
_, path, _ = classify_command("cat src/foo.py", workdir="/repo")
assert path == "/repo/src/foo.py"
_, path, _ = classify_command("cat /abs/foo.py", workdir="/repo")
assert path == "/abs/foo.py"
def test_sed_range_not_mistaken_for_path(self):
_, path, _ = classify_command("sed -n '5,30p' headroom/config.py")
assert path == "headroom/config.py"
def test_compound_command_with_read(self):
cat, path, _ = classify_command("cat foo.py | grep def", workdir="/r")
assert cat == "read"
assert path == "/r/foo.py"
def _call(call_id: str, cmd: str, workdir: str = "/repo") -> str:
return json.dumps(
{
"payload": {
"type": "function_call",
"name": "exec_command",
"call_id": call_id,
"arguments": json.dumps({"cmd": cmd, "workdir": workdir}),
}
}
)
def _output(call_id: str, text: str) -> str:
return json.dumps(
{"payload": {"type": "function_call_output", "call_id": call_id, "output": text}}
)
@pytest.fixture
def codex_dir(tmp_path):
content = "line\n" * 600 # 3000B — over the maturation floor
lines = [
_call("c1", "cat src/foo.py"),
_output("c1", content),
_call("c2", "sed -n '1,100p' src/foo.py"), # partial re-read, same path
_output("c2", content[:500]),
_call("c3", "rg -n 'def ' src/"),
_output("c3", "src/foo.py:1:def x():"),
_call("c4", "rtk read src/bar.py --lines 1-50"),
_output("c4", "bar content " * 10),
]
sessions = tmp_path / "sessions" / "2026" / "06"
sessions.mkdir(parents=True)
(sessions / "rollout-1.jsonl").write_text("\n".join(lines))
return tmp_path / "sessions"
class TestAuditCodex:
def test_metrics(self, codex_dir):
r = audit_codex(codex_dir)
assert r.sessions == 1
assert r.exec_calls == 4
assert r.read_calls == 3 # c1, c2, c4
assert r.reads_partial == 2 # c2 (sed range), c4 (--lines)
assert r.rereads_same_path == 1 # c2 re-reads foo.py
assert r.distinct_files_read == 2
assert r.reads_over_floor == 1 # c1 (3000B)
assert r.calls_by_category["search"] == 1
assert r.bytes_by_category["read"] > r.bytes_by_category["search"]
def test_render_runs(self, codex_dir):
out = render_codex_text(audit_codex(codex_dir))
assert "codex read-pattern audit" in out
assert "partial slices" in out
def test_empty_dir(self, tmp_path):
assert audit_codex(tmp_path).sessions == 0
class TestCli:
def test_cli_codex_mode(self, codex_dir):
from click.testing import CliRunner
from headroom.cli.main import main
runner = CliRunner()
res = runner.invoke(main, ["audit-reads", "--codex", "--path", str(codex_dir)])
assert res.exit_code == 0, res.output
assert "codex read-pattern audit" in res.output
res = runner.invoke(
main, ["audit-reads", "--codex", "--path", str(codex_dir), "--format", "json"]
)
assert res.exit_code == 0
assert json.loads(res.output)["read_calls"] == 3
if __name__ == "__main__":
pytest.main([__file__, "-v"])