mirror of
https://github.com/headroomlabs-ai/headroom.git
synced 2026-08-27 14:17:10 -04:00
c29b4ba84f
## Description Extracts the output-savings stratification, holdout assignment, conversation key, and transform-label helpers into a pure policy module while preserving the existing `headroom.proxy.output_savings` public imports. This keeps the estimator/ledger adapter focused on statistics and persistence. Closes # ## Type of Change - [ ] 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 - [x] Code refactoring (no functional changes) ## Changes Made - Added `headroom.proxy.output_savings_policy` for pure savings policy helpers. - Re-exported the moved helpers from `headroom.proxy.output_savings` to keep callers stable. - Added direct tests for the extracted policy boundary. - Kept the LiteLLM callback compatibility shim required for repo-wide type checking on fresh branches. ## Testing - [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_output_savings_policy.py tests/test_output_savings.py tests/test_litellm_callback.py tests/test_compress_api.py::TestLiteLLMCallback -q 54 passed in 6.42s python -m ruff check . All checks passed! python -m ruff format --check . 1095 files already formatted python -m mypy headroom --ignore-missing-imports Success: no issues found in 409 source files gitleaks protect --staged --no-banner --redact no leaks found ``` ## Real Behavior Proof - Environment: Windows, Python 3.13.13, local worktree based on `headroomlabs/main`. - Exact command / steps: ran the focused pytest set, Ruff lint/format checks, mypy over `headroom`, and staged gitleaks scan. - Observed result: all local checks passed; staged secret scan found no leaks. - Not tested: full CI matrix and deployment flows; those are covered by GitHub Actions. ## 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 ## Screenshots (if applicable) N/A ## Additional Notes Documentation and changelog updates are not applicable for this internal refactor. GitHub reported existing Dependabot alerts on the default branch during push; this PR does not change dependencies, and the staged secret scan is clean.
60 lines
1.7 KiB
Python
60 lines
1.7 KiB
Python
"""Tests for pure output savings policy helpers."""
|
|
|
|
from __future__ import annotations
|
|
|
|
from headroom.proxy.output_savings_policy import (
|
|
assign_arm,
|
|
conversation_key_from_body,
|
|
input_bucket,
|
|
model_family,
|
|
parse_stratum_label,
|
|
stratum_key,
|
|
stratum_label,
|
|
)
|
|
|
|
|
|
def test_stratum_key_is_most_to_least_specific() -> None:
|
|
key = stratum_key(
|
|
turn_kind="new_user_ask",
|
|
input_tokens=5000,
|
|
model="claude-opus-4-8",
|
|
has_tools=True,
|
|
)
|
|
|
|
assert key == "opus|new_user_ask|s|tools"
|
|
|
|
|
|
def test_input_bucket_and_model_family_are_coarse() -> None:
|
|
assert [input_bucket(v) for v in (0, 2_000, 8_000, 32_000, 200_000)] == [
|
|
"xs",
|
|
"s",
|
|
"m",
|
|
"l",
|
|
"xl",
|
|
]
|
|
assert model_family("claude-sonnet-4-6") == "sonnet"
|
|
assert model_family("unknown-model") == "other"
|
|
|
|
|
|
def test_assign_arm_is_stable_and_respects_extreme_holdouts() -> None:
|
|
assert assign_arm("conv-123", 0.0) == "treatment"
|
|
assert assign_arm("conv-123", 1.0) == "control"
|
|
assert assign_arm("conv-123", 0.5) == assign_arm("conv-123", 0.5)
|
|
|
|
|
|
def test_conversation_key_uses_response_create_payload() -> None:
|
|
http_body = {"model": "gpt-5", "input": "build a cache"}
|
|
ws_body = {
|
|
"type": "response.create",
|
|
"response": {"model": "gpt-5", "input": "build a cache"},
|
|
}
|
|
|
|
assert conversation_key_from_body(http_body) == conversation_key_from_body(ws_body)
|
|
|
|
|
|
def test_stratum_label_round_trips_arm_and_key() -> None:
|
|
key = "opus|code|m|tools"
|
|
|
|
assert parse_stratum_label(stratum_label("treatment", key)) == ("treatment", key)
|
|
assert parse_stratum_label(stratum_label("control", key)) == ("control", key)
|
|
assert parse_stratum_label("unrelated") is None
|