mirror of
https://github.com/openclaw/openclaw.git
synced 2026-05-28 05:16:17 +00:00
Carry over #82973 and fix #81281 by preserving explicit cacheRetention for OpenAI-compatible completions providers that opt into prompt-cache-key support. The change keeps explicit cacheRetention suppressed for OpenAI-compatible providers without compat.supportsPromptCacheKey, adds regression coverage for both paths, and updates prompt-caching docs for prompt_cache_key / prompt_cache_retention behavior. Fixes #81281. Supersedes #82973. Co-authored-by: lonexreb <reach2shubhankar@gmail.com>