mirror of
https://github.com/headroomlabs-ai/headroom.git
synced 2026-08-27 14:17:10 -04:00
0ce2243dfb
Comprehensive PR-by-PR plan to realign Headroom around live-zone-only compression with prefix-cache safety as a non-negotiable invariant. Drafted from a 10-agent deep audit against the LLM-proxy compression guide. - 14 documents under REALIGNMENT/ - 72 ranked bugs (P0 cache-killers through P6 test-infra) - 40 feature PRs + 10 test-infra PRs across 9 phases - ~25K LOC retirement (ICM + scoring + relevance + rolling-window + summarizer + tool-crusher + LiteLLM-fake-Bedrock) - Preserves TOIN, CCR, Kompress-base per user direction - Auth-mode policy gates (PAYG / OAuth / subscription) - Phase 3 cache stabilization surface (tool-sort, schema-sort, cache_control auto-place, prompt_cache_key) - Native Bedrock SigV4 + Vertex ADC handlers - Test infrastructure: SHA-256 byte-faithful gate, SSE corner cases, property tests, real-traffic shadow |
||
|---|---|---|
| .. | ||
| 00-overview.md | ||
| 01-bug-list.md | ||
| 02-architecture.md | ||
| 03-phase-A-lockdown.md | ||
| 04-phase-B-live-zone.md | ||
| 05-phase-C-rust-proxy.md | ||
| 06-phase-D-bedrock-vertex.md | ||
| 07-phase-E-cache-stabilization.md | ||
| 08-phase-F-auth-mode.md | ||
| 09-phase-G-rtk-observability.md | ||
| 10-phase-H-python-retirement.md | ||
| 11-phase-I-test-infra.md | ||
| 12-decisions-needed.md | ||
| INDEX.md | ||