mirror of
https://github.com/headroomlabs-ai/headroom.git
synced 2026-08-27 14:17:10 -04:00
## 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.
109 lines
3.3 KiB
Python
109 lines
3.3 KiB
Python
"""Live OpenAI API tests for the Codex (role="tool" message) path.
|
|
|
|
Same contract as the Anthropic live tests: the real API must accept our
|
|
transformed message shapes (lifecycle markers inside role="tool" results),
|
|
and the model must read them correctly.
|
|
|
|
Skipped without OPENAI_API_KEY. Costs: a few hundred gpt-4o-mini tokens/run.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import json
|
|
import os
|
|
|
|
import httpx
|
|
import pytest
|
|
|
|
pytestmark = pytest.mark.skipif(
|
|
not os.environ.get("OPENAI_API_KEY"),
|
|
reason="OPENAI_API_KEY not set",
|
|
)
|
|
|
|
MODEL = "gpt-4o-mini"
|
|
API_URL = "https://api.openai.com/v1/chat/completions"
|
|
|
|
FILE_CONTENT = (
|
|
' 1\tdef answer():\n 2\t """Returns the magic number."""\n 3\t return 42\n'
|
|
) + "".join(f" {i}\t# padding line {i}\n" for i in range(4, 40))
|
|
|
|
STALE_MARKER = (
|
|
"[Read content stale: /src/magic.py was modified after this read — "
|
|
"re-read the file for current content. "
|
|
"Retrieve original: hash=abc123def456abc123def456]"
|
|
)
|
|
|
|
READ_TOOL = {
|
|
"type": "function",
|
|
"function": {
|
|
"name": "Read",
|
|
"description": "Read a file",
|
|
"parameters": {
|
|
"type": "object",
|
|
"properties": {"file_path": {"type": "string"}},
|
|
"required": ["file_path"],
|
|
},
|
|
},
|
|
}
|
|
|
|
|
|
def call_openai(messages: list[dict]) -> str:
|
|
resp = httpx.post(
|
|
API_URL,
|
|
json={
|
|
"model": MODEL,
|
|
"max_tokens": 150,
|
|
"tools": [READ_TOOL],
|
|
"messages": messages,
|
|
},
|
|
headers={"Authorization": f"Bearer {os.environ['OPENAI_API_KEY']}"},
|
|
timeout=60,
|
|
)
|
|
assert resp.status_code == 200, f"{resp.status_code}: {resp.text[:500]}"
|
|
return resp.json()["choices"][0]["message"]["content"] or ""
|
|
|
|
|
|
def read_roundtrip(tc_id: str, content: str) -> list[dict]:
|
|
return [
|
|
{
|
|
"role": "assistant",
|
|
"content": None,
|
|
"tool_calls": [
|
|
{
|
|
"id": tc_id,
|
|
"type": "function",
|
|
"function": {
|
|
"name": "Read",
|
|
"arguments": json.dumps({"file_path": "/src/magic.py"}),
|
|
},
|
|
}
|
|
],
|
|
},
|
|
{"role": "tool", "tool_call_id": tc_id, "content": content},
|
|
]
|
|
|
|
|
|
class TestLifecycleMarkerLiveOpenAI:
|
|
def test_api_accepts_stale_marker_shape(self):
|
|
"""A stale-Read marker inside a role='tool' message must be a
|
|
valid body and must be read as 'this content is outdated'."""
|
|
messages = [{"role": "user", "content": "Read /src/magic.py"}]
|
|
messages += read_roundtrip("call_r1", FILE_CONTENT)
|
|
messages += [
|
|
{"role": "assistant", "content": "Read it. Anything else?"},
|
|
{"role": "user", "content": "Check it once more."},
|
|
]
|
|
messages += read_roundtrip("call_r2", STALE_MARKER)
|
|
messages.append(
|
|
{
|
|
"role": "user",
|
|
"content": "Is the latest read of /src/magic.py in this conversation "
|
|
"current or stale? One word.",
|
|
}
|
|
)
|
|
reply = call_openai(messages)
|
|
assert "stale" in reply.lower(), f"model misread the marker: {reply!r}"
|
|
|
|
|
|
if __name__ == "__main__":
|
|
pytest.main([__file__, "-v"])
|