mirror of
https://github.com/headroomlabs-ai/headroom.git
synced 2026-08-27 14:17:10 -04:00
22dad133e2
Root cause: CompressionCache.compute_frozen_count() stopped at the first tool_result not in its cache, capping frozen_message_count at 2. Tool results excluded by content_router (Read/Glob) or skipped (ratio too high) never entered the cache, so every subsequent message was eligible for recompression — causing 192 cache busts per session. Four fixes: 1. Add _stable_hashes set to CompressionCache so excluded/skipped tool_results don't block the frozen count walk 2. Fix _estimate_message_tokens to count tool_result content and tool_use input fields (were counted as 0 tokens in Anthropic format) 3. Fix streaming handler to include assistant response and original_messages in prefix tracker updates (parity with non-streaming) 4. TTL-aware batch recompression: defer first-time compressions within the 5-min cache TTL window, batching them at the boundary to trade many small busts for one |
||
|---|---|---|
| .. | ||
| __init__.py | ||
| test_anthropic.py | ||
| test_backends.py | ||
| test_base.py | ||
| test_client_integration.py | ||
| test_dynamic_detector.py | ||
| test_google.py | ||
| test_openai.py | ||
| test_prefix_tracker.py | ||
| test_registry.py | ||
| test_semantic.py | ||