Luis Pater baffbe2cc7 feat(executor): implement agent-scoped cache key isolation and enhance replay handling ...

- Introduced agent-specific cache key isolation to ensure distinct prompt caching across agents.
- Improved reasoning replay handling for Claude models, including cumulative tool turn restoration and validation.
- Enhanced HTTP and WebSocket session consistency during execution scope and cache replay synchronization.
- Added new unit tests and extended coverage for prompt caching, agent isolation, and replay cache functionality.

Closes: #4352

2026-07-18 02:18:09 +08:00

..

antigravity_reasoning_replay_cache.go

feat(antigravity): HOME reasoning replay for Gemini models

2026-06-18 19:50:28 +08:00

codex_reasoning_replay_cache_test.go

feat(executor): implement agent-scoped cache key isolation and enhance replay handling

2026-07-18 02:18:09 +08:00

codex_reasoning_replay_cache.go

feat(executor): implement agent-scoped cache key isolation and enhance replay handling

2026-07-18 02:18:09 +08:00

signature_cache_test.go

feat: enhance fault tolerance for kv-based caching and introduce additional tests

2026-06-14 21:11:35 +08:00

signature_cache.go

feat(xai): replay Grok reasoning for Claude messages (#3962)

2026-06-23 14:57:53 +08:00

xai_reasoning_replay_cache_test.go

fix(xai): preserve tool-call-only replay batches

2026-07-12 23:19:36 +08:00

xai_reasoning_replay_cache.go

fix(xai): preserve tool-call-only replay batches

2026-07-12 23:19:36 +08:00