mirror of
https://github.com/headroomlabs-ai/headroom.git
synced 2026-08-27 14:17:10 -04:00
## Description `/readyz` reports kompress as `"status": "unhealthy"` while the top-level payload simultaneously reports `"status": "healthy"` and `"ready": true`. This is a visible contradiction — kompress is intentionally excluded from the aggregate readiness gate, but it still receives the harshest label when it hasn't finished loading. This PR is a superset of #2829: it makes the same `degraded` status change **and** adds an `"optional": true` field to the component dict so API consumers can distinguish optional components from gating ones without parsing the `status` string. Fixes #2813. ## 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) - [ ] Documentation update - [ ] Performance improvement - [ ] Code refactoring (no functional changes) ## Changes Made - `headroom/proxy/server.py` — `_component_health()` accepts `optional: bool = False`; when `optional=True` and not-ready, status is `"degraded"` instead of `"unhealthy"`; `"optional": True` is added to the returned dict so callers can identify optional components without parsing the status string. Kompress call passes `optional=True`. - `tests/test_proxy_health.py` — All 11 kompress assertion dicts updated: `"status": "degraded"` for not-ready cases and `"optional": True` for all kompress cases (covering disabled/healthy/degraded states in the full parametrized matrix). ## Schema diff **Before** (kompress not yet loaded): ```json { "enabled": true, "ready": false, "status": "unhealthy", "backend": null } ``` **After**: ```json { "enabled": true, "ready": false, "status": "degraded", "optional": true, "backend": null } ``` The `"optional": true` field is additive — existing consumers that only check `status` are unaffected. The field gives consumers a stable machine-readable signal without requiring them to enumerate which component names are optional. ## Testing - [x] Unit tests pass (`pytest`) — CI only; `headroom._core` (compiled Rust extension) is not available locally, blocking direct `pytest tests/test_proxy_health.py` locally. All tests that don't import through `headroom.proxy.server → headroom.transforms → headroom._core` run locally. - [x] Linting passes (`ruff check .`) - [x] Type checking passes (`mypy headroom`) - [ ] New tests added for new functionality (existing tests updated to cover the new status value and the new `"optional"` field) - [ ] Manual testing performed ### Test Output ``` $ uv run ruff check headroom/proxy/server.py tests/test_proxy_health.py All checks passed! $ uv run mypy headroom/proxy/server.py Success: no issues found in 1 source file ``` Full test suite (`tests/test_proxy_health.py`) is verified by CI; local run blocked by missing `headroom._core` native extension. ## Real Behavior Proof - Environment: local dev checkout, Windows 11, Python 3.14.3 - Ruff + mypy pass locally on both changed files (see Test Output above) - `tests/test_proxy_health.py` test suite requires `headroom._core` (compiled Rust extension not available locally) — CI run covers this - Diff is a mechanical expansion of the same `optional` flag already approved in #2829's head, plus the additive `"optional": true` response field ## 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 - [ ] I have commented my code, particularly in hard-to-understand areas - [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 - [x] I did **not** edit `CHANGELOG.md` — it is generated by release-please from my Conventional Commit PR title --------- Signed-off-by: Radhakrishnan Pachyappan <radhakrishnan.p@op.tech> Co-authored-by: JD Davis <mxjerrett@gmail.com>
325 lines
9.3 KiB
Python
325 lines
9.3 KiB
Python
import pytest
|
|
from fastapi.testclient import TestClient
|
|
|
|
from headroom.proxy.models import ProxyConfig
|
|
from headroom.proxy.server import create_app
|
|
from headroom.transforms import kompress_compressor
|
|
|
|
|
|
class _ReadyCompressor:
|
|
def __init__(self, backend="onnx", ready=True, error=None):
|
|
self.backend = backend
|
|
self.ready = ready
|
|
self.error = error
|
|
self.calls = []
|
|
|
|
def is_ready(self):
|
|
self.calls.append("is_ready")
|
|
if self.error:
|
|
raise self.error
|
|
return self.ready
|
|
|
|
def ready_backend(self):
|
|
self.calls.append("ready_backend")
|
|
return self.backend
|
|
|
|
|
|
def _health_app(monkeypatch, compressor=None, *, disabled=False, **config_kwargs):
|
|
monkeypatch.setenv("HEADROOM_SKIP_UPSTREAM_CHECK", "1")
|
|
app = create_app(
|
|
ProxyConfig(
|
|
optimize=False,
|
|
cache_enabled=False,
|
|
rate_limit_enabled=False,
|
|
disable_kompress=disabled,
|
|
**config_kwargs,
|
|
)
|
|
)
|
|
app.state.ready = True
|
|
proxy = app.state.proxy
|
|
proxy.http_client = object()
|
|
router = proxy.anthropic_pipeline.transforms[-1]
|
|
if compressor is not None:
|
|
router._kompress = compressor
|
|
return app, proxy
|
|
|
|
|
|
def test_readyz_excludes_kompress_from_aggregate_readiness(monkeypatch):
|
|
monkeypatch.setenv("HEADROOM_SKIP_UPSTREAM_CHECK", "1")
|
|
|
|
app = create_app(
|
|
ProxyConfig(
|
|
optimize=False,
|
|
cache_enabled=False,
|
|
rate_limit_enabled=False,
|
|
)
|
|
)
|
|
app.state.ready = True
|
|
proxy = app.state.proxy
|
|
proxy.http_client = object()
|
|
proxy.warmup.kompress.mark_error("model not cached")
|
|
|
|
client = TestClient(app)
|
|
response = client.get("/readyz")
|
|
|
|
assert response.status_code == 200
|
|
payload = response.json()
|
|
assert payload["ready"] is True
|
|
assert payload["status"] == "healthy"
|
|
assert payload["checks"]["kompress"] == {
|
|
"enabled": True,
|
|
"ready": False,
|
|
"status": "degraded",
|
|
"optional": True,
|
|
"backend": None,
|
|
}
|
|
|
|
|
|
def test_readyz_promotes_deferred_kompress_after_runtime_load(monkeypatch):
|
|
compressor = _ReadyCompressor()
|
|
app, proxy = _health_app(monkeypatch, compressor)
|
|
proxy.warmup.kompress.info["source_status"] = "deferred"
|
|
|
|
payload = TestClient(app).get("/readyz").json()
|
|
|
|
assert payload["checks"]["kompress"] == {
|
|
"enabled": True,
|
|
"ready": True,
|
|
"status": "healthy",
|
|
"optional": True,
|
|
"backend": "onnx",
|
|
}
|
|
# The promotion must also clear the startup marker, otherwise the slot
|
|
# serializes as loaded-but-deferred in /debug/warmup.
|
|
assert proxy.warmup.kompress.info["source_status"] == "runtime"
|
|
|
|
|
|
@pytest.mark.parametrize("attached", [False, True])
|
|
def test_readyz_promotes_kompress_from_module_cache(monkeypatch, attached):
|
|
model = object()
|
|
monkeypatch.setattr(
|
|
kompress_compressor,
|
|
"_kompress_cache",
|
|
{kompress_compressor.HF_MODEL_ID: (model, object(), "onnx")},
|
|
)
|
|
compressor = _ReadyCompressor(ready=False) if attached else None
|
|
app, proxy = _health_app(monkeypatch, compressor)
|
|
proxy.warmup.kompress.info["source_status"] = "deferred"
|
|
|
|
payload = TestClient(app).get("/readyz").json()
|
|
|
|
assert payload["checks"]["kompress"] == {
|
|
"enabled": True,
|
|
"ready": True,
|
|
"status": "healthy",
|
|
"optional": True,
|
|
"backend": "onnx",
|
|
}
|
|
assert proxy.warmup.kompress.handle is model
|
|
if compressor is not None:
|
|
assert compressor.calls == ["is_ready"]
|
|
|
|
|
|
def test_readyz_promotes_remote_kompress_backend(monkeypatch):
|
|
compressor = _ReadyCompressor(backend="remote")
|
|
app, proxy = _health_app(monkeypatch)
|
|
router = proxy.anthropic_pipeline.transforms[-1]
|
|
router._kompress = None
|
|
router._kompress_remote = compressor
|
|
|
|
payload = TestClient(app).get("/readyz").json()
|
|
|
|
assert payload["checks"]["kompress"]["backend"] == "remote"
|
|
assert payload["checks"]["kompress"]["ready"] is True
|
|
|
|
|
|
def test_readyz_keeps_pending_kompress_unloaded(monkeypatch):
|
|
compressor = _ReadyCompressor(backend="onnx", ready=False)
|
|
app, proxy = _health_app(monkeypatch, compressor)
|
|
router = proxy.anthropic_pipeline.transforms[-1]
|
|
router._kompress = compressor
|
|
|
|
payload = TestClient(app).get("/readyz").json()
|
|
|
|
assert payload["checks"]["kompress"] == {
|
|
"enabled": True,
|
|
"ready": False,
|
|
"status": "degraded",
|
|
"optional": True,
|
|
"backend": None,
|
|
}
|
|
assert compressor.calls == ["is_ready"]
|
|
|
|
|
|
def test_readyz_never_starts_kompress_loading(monkeypatch):
|
|
compressor = _ReadyCompressor()
|
|
app, proxy = _health_app(monkeypatch, compressor)
|
|
router = proxy.anthropic_pipeline.transforms[-1]
|
|
router._kompress = compressor
|
|
|
|
TestClient(app).get("/readyz")
|
|
|
|
assert compressor.calls == ["is_ready", "ready_backend"]
|
|
|
|
|
|
def test_readyz_kompress_inspection_failure_fails_open(monkeypatch):
|
|
compressor = _ReadyCompressor(error=RuntimeError("inspection failed"))
|
|
app, proxy = _health_app(monkeypatch, compressor)
|
|
proxy.warmup.kompress.mark_loaded(handle=object(), backend="onnx")
|
|
|
|
payload = TestClient(app).get("/readyz").json()
|
|
|
|
assert payload["checks"]["kompress"]["ready"] is True
|
|
assert payload["checks"]["kompress"]["backend"] == "onnx"
|
|
|
|
|
|
def test_readyz_disabled_kompress_skips_inspection(monkeypatch):
|
|
compressor = _ReadyCompressor()
|
|
app, proxy = _health_app(monkeypatch, compressor, disabled=True)
|
|
router = proxy.anthropic_pipeline.transforms[-1]
|
|
router._kompress = compressor
|
|
|
|
payload = TestClient(app).get("/readyz").json()
|
|
|
|
assert payload["checks"]["kompress"] == {
|
|
"enabled": False,
|
|
"ready": True,
|
|
"status": "disabled",
|
|
"optional": True,
|
|
"backend": None,
|
|
}
|
|
assert compressor.calls == []
|
|
|
|
|
|
def test_readyz_per_provider_kompress_override_reenables_health(monkeypatch):
|
|
compressor = _ReadyCompressor()
|
|
app, proxy = _health_app(
|
|
monkeypatch,
|
|
disabled=True,
|
|
disable_kompress_anthropic=False,
|
|
)
|
|
router = proxy.anthropic_pipeline.transforms[-1]
|
|
router._kompress = compressor
|
|
|
|
payload = TestClient(app).get("/readyz").json()
|
|
|
|
assert payload["checks"]["kompress"] == {
|
|
"enabled": True,
|
|
"ready": True,
|
|
"status": "healthy",
|
|
"optional": True,
|
|
"backend": "onnx",
|
|
}
|
|
assert compressor.calls == ["is_ready", "ready_backend"]
|
|
|
|
|
|
def test_readyz_never_calls_lazy_kompress_getters(monkeypatch):
|
|
app, proxy = _health_app(monkeypatch)
|
|
router = proxy.anthropic_pipeline.transforms[-1]
|
|
|
|
def _boom():
|
|
raise AssertionError("health should not instantiate kompress")
|
|
|
|
router._get_kompress = _boom
|
|
router._get_remote_kompress = _boom
|
|
|
|
payload = TestClient(app).get("/readyz").json()
|
|
|
|
assert payload["checks"]["kompress"] == {
|
|
"enabled": True,
|
|
"ready": False,
|
|
"status": "degraded",
|
|
"optional": True,
|
|
"backend": None,
|
|
}
|
|
|
|
|
|
@pytest.mark.parametrize(
|
|
("slot_status", "compressor", "disabled", "expected"),
|
|
[
|
|
(
|
|
"null",
|
|
None,
|
|
False,
|
|
{
|
|
"enabled": True,
|
|
"ready": False,
|
|
"status": "degraded",
|
|
"optional": True,
|
|
"backend": None,
|
|
},
|
|
),
|
|
(
|
|
"null",
|
|
_ReadyCompressor(),
|
|
False,
|
|
{
|
|
"enabled": True,
|
|
"ready": True,
|
|
"status": "healthy",
|
|
"optional": True,
|
|
"backend": "onnx",
|
|
},
|
|
),
|
|
(
|
|
"null",
|
|
_ReadyCompressor(backend="remote"),
|
|
False,
|
|
{
|
|
"enabled": True,
|
|
"ready": True,
|
|
"status": "healthy",
|
|
"optional": True,
|
|
"backend": "remote",
|
|
},
|
|
),
|
|
(
|
|
"error",
|
|
_ReadyCompressor(),
|
|
False,
|
|
{
|
|
"enabled": True,
|
|
"ready": True,
|
|
"status": "healthy",
|
|
"optional": True,
|
|
"backend": "onnx",
|
|
},
|
|
),
|
|
(
|
|
"loaded",
|
|
_ReadyCompressor(),
|
|
False,
|
|
{
|
|
"enabled": True,
|
|
"ready": True,
|
|
"status": "healthy",
|
|
"optional": True,
|
|
"backend": "existing",
|
|
},
|
|
),
|
|
(
|
|
"null",
|
|
_ReadyCompressor(),
|
|
True,
|
|
{
|
|
"enabled": False,
|
|
"ready": True,
|
|
"status": "disabled",
|
|
"optional": True,
|
|
"backend": None,
|
|
},
|
|
),
|
|
],
|
|
)
|
|
def test_readyz_kompress_state_matrix(monkeypatch, slot_status, compressor, disabled, expected):
|
|
app, proxy = _health_app(monkeypatch, compressor, disabled=disabled)
|
|
if slot_status == "error":
|
|
proxy.warmup.kompress.mark_error("not cached")
|
|
elif slot_status == "loaded":
|
|
proxy.warmup.kompress.mark_loaded(handle=object(), backend=expected["backend"])
|
|
if compressor is not None and expected["backend"] == "existing":
|
|
compressor.backend = "new"
|
|
|
|
payload = TestClient(app).get("/readyz").json()["checks"]["kompress"]
|
|
|
|
assert payload == expected
|