mirror of
https://github.com/headroomlabs-ai/headroom.git
synced 2026-08-27 14:17:10 -04:00
d1c484b164
## Description Extracts the sticky memory tool session tracker from `headroom.proxy.helpers` into a focused state module. `helpers.SessionToolTracker` remains as an env-aware compatibility wrapper so existing injection and singleton call sites keep the same API. 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.tool_injection_tracker.SessionToolTracker` as the pure bounded LRU state holder. - Replaced the large in-helper tracker implementation with a small env-aware wrapper. - Added direct tracker tests for unknown sessions, ordered golden bytes, first-write wins, provider isolation, LRU eviction, and input validation. ## 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_tool_injection_tracker.py tests/test_memory_tool_session_sticky.py tests/test_corrupt_golden_bytes_recovery.py 44 passed in 0.54s python -m ruff check . All checks passed! python -m ruff format --check . 1069 files already formatted python -m mypy headroom --ignore-missing-imports Success: no issues found in 410 source files gitleaks protect --staged --no-banner --redact no leaks found ``` ## Real Behavior Proof - Environment: Windows, Python 3.13.13 - Exact command / steps: Ran direct tracker tests, sticky memory tool tests, corrupt golden byte recovery tests, full ruff, format check, mypy, and staged gitleaks scan. - Observed result: Existing sticky injection behavior and recovery behavior remain green while the tracker state domain is directly covered. - Not tested: Full repository pytest suite locally; CI covers the broader matrix. ## 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. The default-branch Dependabot alerts reported during push are pre-existing and unrelated to this PR.
72 lines
2.8 KiB
Python
72 lines
2.8 KiB
Python
from __future__ import annotations
|
|
|
|
import pytest
|
|
|
|
from headroom.proxy.tool_injection_tracker import SessionToolTracker
|
|
|
|
|
|
def test_tracker_reports_unknown_session_as_not_injected() -> None:
|
|
tracker = SessionToolTracker(max_sessions=10)
|
|
|
|
assert tracker.should_inject("anthropic", "s-1") is False
|
|
|
|
|
|
def test_tracker_records_and_returns_golden_bytes_in_order() -> None:
|
|
tracker = SessionToolTracker(max_sessions=10)
|
|
|
|
tracker.record_injection("anthropic", "s-1", "memory_save", b"save")
|
|
tracker.record_injection("anthropic", "s-1", "memory_search", b"search")
|
|
|
|
assert tracker.should_inject("anthropic", "s-1") is True
|
|
assert tracker.get_golden_definitions("anthropic", "s-1") == [
|
|
("memory_save", b"save"),
|
|
("memory_search", b"search"),
|
|
]
|
|
|
|
|
|
def test_tracker_first_write_wins_per_tool_name() -> None:
|
|
tracker = SessionToolTracker(max_sessions=10)
|
|
|
|
tracker.record_injection("anthropic", "s-1", "memory_save", b"original")
|
|
tracker.record_injection("anthropic", "s-1", "memory_save", b"drift")
|
|
|
|
assert tracker.get_golden_definitions("anthropic", "s-1") == [("memory_save", b"original")]
|
|
|
|
|
|
def test_tracker_keeps_provider_namespaces_independent() -> None:
|
|
tracker = SessionToolTracker(max_sessions=10)
|
|
|
|
tracker.record_injection("anthropic", "shared", "memory_save", b"anthropic")
|
|
tracker.record_injection("openai", "shared", "memory_save", b"openai")
|
|
|
|
assert tracker.get_golden_definitions("anthropic", "shared") == [("memory_save", b"anthropic")]
|
|
assert tracker.get_golden_definitions("openai", "shared") == [("memory_save", b"openai")]
|
|
|
|
|
|
def test_tracker_evicts_least_recently_used_session() -> None:
|
|
tracker = SessionToolTracker(max_sessions=2)
|
|
tracker.record_injection("anthropic", "s-1", "memory_save", b"a")
|
|
tracker.record_injection("anthropic", "s-2", "memory_save", b"b")
|
|
|
|
assert tracker.should_inject("anthropic", "s-1") is True
|
|
tracker.record_injection("anthropic", "s-3", "memory_save", b"c")
|
|
|
|
assert tracker.active_sessions == 2
|
|
assert tracker.should_inject("anthropic", "s-1") is True
|
|
assert tracker.should_inject("anthropic", "s-2") is False
|
|
assert tracker.should_inject("anthropic", "s-3") is True
|
|
|
|
|
|
def test_tracker_validates_constructor_and_record_inputs() -> None:
|
|
with pytest.raises(ValueError, match="max_sessions"):
|
|
SessionToolTracker(max_sessions=0)
|
|
|
|
tracker = SessionToolTracker(max_sessions=10)
|
|
with pytest.raises(ValueError, match="provider"):
|
|
tracker.should_inject("", "s-1")
|
|
with pytest.raises(ValueError, match="session_id"):
|
|
tracker.get_golden_definitions("anthropic", "")
|
|
with pytest.raises(ValueError, match="tool_name"):
|
|
tracker.record_injection("anthropic", "s-1", "", b"bytes")
|
|
with pytest.raises(ValueError, match="tool_definition_bytes"):
|
|
tracker.record_injection("anthropic", "s-1", "memory_save", b"")
|