vultr/openclaw
1
0
Fork 0
mirror of https://github.com/openclaw/openclaw.git synced 2026-05-06 14:50:45 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix: forward completions prompt cache keys

Browse Source
This commit is contained in:
Peter Steinberger
2026-04-25 03:51:35 +01:00
parent 24fdfdba6e
commit 26f06afb90
4 changed files with 72 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
docs/reference/prompt-caching.md
View File

@@ -105,6 +105,7 @@ Per-agent heartbeat is supported at `agents.list[].heartbeat`.
- Prompt caching is automatic on supported recent models. OpenClaw does not need to inject block-level cache markers.
- OpenClaw uses `prompt_cache_key` to keep cache routing stable across turns and uses `prompt_cache_retention: "24h"` only when `cacheRetention: "long"` is selected on direct OpenAI hosts.
- OpenAI-compatible Completions providers receive `prompt_cache_key` only when their model config explicitly sets `compat.supportsPromptCacheKey: true`; `cacheRetention: "none"` still suppresses it.
- OpenAI responses expose cached prompt tokens via `usage.prompt_tokens_details.cached_tokens` (or `input_tokens_details.cached_tokens` on Responses API events). OpenClaw maps that to `cacheRead`.
- OpenAI does not expose a separate cache-write token counter, so `cacheWrite` stays `0` on OpenAI paths even when the provider is warming a cache.
- OpenAI returns useful tracing and rate-limit headers such as `x-request-id`, `openai-processing-ms`, and `x-ratelimit-*`, but cache-hit accounting should come from the usage payload, not from headers.