mirror of
https://github.com/headroomlabs-ai/headroom.git
synced 2026-08-27 14:17:10 -04:00
## Description Hardens persistent install startup and proxy compression behavior for issue #1843. Repeated `headroom install start` / scheduled ensure calls no longer spawn duplicate runtimes by default, and `/v1/compress` now fails open on compression timeout instead of returning a 503. The PR also adds a machine-readable platform feature matrix and app-level stabilization tests for health, compression functionality, timeout behavior, and matrix evidence. Refs #1843 ## Type of Change - [x] Bug fix (non-breaking change that fixes an issue) - [ ] New feature (non-breaking change that adds functionality) - [ ] Breaking change (fix or feature that would cause existing functionality to change) - [x] Documentation update - [x] Performance improvement - [ ] Code refactoring (no functional changes) ## Changes Made - Wrapped direct persistent deployment starts with the existing profile-local runtime start lock. - Made `headroom install start` idempotent when the deployment is already healthy. - Added wedged-runtime handling: if a PID is running but `/readyz` does not recover inside the grace window, stop it before starting again. - Kept `install agent ensure` inside the already-held lock while delegating to the shared start helper. - Changed `/v1/compress` timeout behavior from `503 compression_timeout` to fail-open `200` with original messages, `compression_skipped: true`, and `skip_reason: compression_timeout`. - Added `tests/test_platform_stabilization_functional.py` covering real FastAPI health/compression routes, successful compression metrics, timeout fail-open speed, and a real JSON tool payload that reduces tokens. - Added `docs/platform-feature-matrix.json` and `docs/platform-stabilization.md` for Linux/macOS/Windows hardening coverage and known gaps. - Strengthened matrix tests so cited local test/workflow paths must exist. ## Testing - [x] Unit tests pass (`pytest`) - [x] Linting passes (`ruff check .`) - [x] Type checking passes (`mypy headroom`) - [x] New tests added for new functionality - [x] Manual testing performed ### Test Output ```text # Clean source tree without copied Rust extension: functional module is skipped locally, as CI copies _core from the built wheel. > python -m pytest tests/test_install tests/test_cli/test_install_cli.py tests/test_platform_feature_matrix.py tests/test_platform_stabilization_functional.py -q collected 120 items / 1 skipped 119 passed, 2 skipped in 17.08s > python -m ruff check headroom/proxy/handlers/openai.py tests/test_platform_stabilization_functional.py tests/test_platform_feature_matrix.py All checks passed! # Local Windows compiled-core proof: > python -m maturin build --profile ci --out dist-local Built wheel for abi3 Python >= 3.10 to dist-local\headroom_ai-0.29.0-cp310-abi3-win_amd64.whl # Copied _core.pyd from the wheel into headroom/ for local route execution, then: > python -m pytest tests/test_platform_stabilization_functional.py -q collected 4 items 4 passed in 6.71s > python -m pytest tests/test_install tests/test_cli/test_install_cli.py tests/test_platform_feature_matrix.py -q collected 120 items 119 passed, 1 skipped in 17.16s Commit hooks: Sync plugin versions.....................................................Passed check for merge conflicts................................................Passed ruff.....................................................................Passed ruff-format..............................................................Passed mypy.....................................................................Passed ``` ## Real Behavior Proof - Environment: Windows 11, PowerShell, Python 3.13.13, worktree `C:\git\headroom-stabilization` on branch `jd/cross-platform-stabilization`. - Exact command / steps: built the Windows wheel with `maturin`, extracted `_core.pyd`, ran the new FastAPI route tests and install/matrix tests listed above, then removed generated artifacts before committing. - Observed result: direct start paths now no-op when healthy, skip spawning when the start lock is contended, and stop a wedged runtime before restart. `/v1/compress` now returns original messages quickly on timeout instead of a 503. The real JSON tool-payload smoke test returns `tokens_before > tokens_after`, `tokens_saved > 0`, `compression_ratio < 1.0`, and non-empty transforms through the public route. - Not tested: full native Windows persistent process e2e remains blocked by the upstream CRT/wheel issue already documented in workflows and in the matrix. No real OS service was installed locally; service manager behavior is covered by argument-level unit tests. ## 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 - [x] 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 ## Screenshots (if applicable) N/A ## Additional Notes CHANGELOG is not updated because this is an unreleased hardening/test/documentation pass. The platform matrix intentionally records partial/blocked Windows/macOS e2e gaps instead of claiming full coverage where the repo cannot currently run it.
70 lines
2.7 KiB
Python
70 lines
2.7 KiB
Python
from __future__ import annotations
|
|
|
|
import json
|
|
from pathlib import Path
|
|
|
|
MATRIX_PATH = Path("docs/platform-feature-matrix.json")
|
|
VALID_STATUSES = {"covered", "partial", "gap", "blocked"}
|
|
PLATFORMS = {"linux", "macos", "windows"}
|
|
|
|
|
|
def test_platform_feature_matrix_is_complete() -> None:
|
|
matrix = json.loads(MATRIX_PATH.read_text(encoding="utf-8"))
|
|
|
|
assert matrix["schema_version"] == 1
|
|
assert set(matrix["platforms"]) == PLATFORMS
|
|
assert set(matrix["status_values"]) == VALID_STATUSES
|
|
assert matrix["features"], "matrix must list hardening features"
|
|
|
|
feature_ids: set[str] = set()
|
|
for feature in matrix["features"]:
|
|
feature_id = feature["id"]
|
|
assert feature_id not in feature_ids, f"duplicate feature id: {feature_id}"
|
|
feature_ids.add(feature_id)
|
|
assert feature["name"]
|
|
assert feature["risk"] in {"install", "runtime", "performance", "cache", "proxy"}
|
|
assert set(feature["platforms"]) == PLATFORMS
|
|
|
|
for platform, coverage in feature["platforms"].items():
|
|
status = coverage["status"]
|
|
assert status in VALID_STATUSES, f"{feature_id}/{platform} has invalid status"
|
|
assert coverage["tests"], f"{feature_id}/{platform} must cite tests or workflows"
|
|
for test_ref in coverage["tests"]:
|
|
path = Path(test_ref.split("#", 1)[0])
|
|
assert path.exists(), f"{feature_id}/{platform} cites missing path {test_ref}"
|
|
if status in {"partial", "gap", "blocked"}:
|
|
assert coverage.get("gap"), f"{feature_id}/{platform} must explain {status}"
|
|
|
|
|
|
def test_platform_feature_matrix_covers_issue_1843_regression_areas() -> None:
|
|
matrix = json.loads(MATRIX_PATH.read_text(encoding="utf-8"))
|
|
feature_ids = {feature["id"] for feature in matrix["features"]}
|
|
|
|
assert {
|
|
"install_windows_service",
|
|
"single_instance_start",
|
|
"compression_fail_open",
|
|
"proxy_functional_smoke",
|
|
"ccr_persistence",
|
|
"toin_skip_recommendations",
|
|
} <= feature_ids
|
|
|
|
|
|
def test_platform_feature_matrix_sanity_tests_are_enumerated() -> None:
|
|
matrix = json.loads(MATRIX_PATH.read_text(encoding="utf-8"))
|
|
sanity_ids = {item["id"] for item in matrix["sanity_tests"]}
|
|
|
|
assert {
|
|
"cli_help",
|
|
"install_paths",
|
|
"runtime_selection",
|
|
"health_startup",
|
|
"compression_backpressure",
|
|
"proxy_route_smoke",
|
|
} <= sanity_ids
|
|
for item in matrix["sanity_tests"]:
|
|
assert item["description"]
|
|
assert item["tests"]
|
|
for test_ref in item["tests"]:
|
|
path = Path(test_ref.split("#", 1)[0])
|
|
assert path.exists(), f"{item['id']} cites missing path {test_ref}"
|