vultr/openclaw
1
0
Fork 0
mirror of https://github.com/openclaw/openclaw.git synced 2026-05-06 10:40:43 +00:00
Code Issues Packages Projects Releases Wiki Activity

test(openrouter): cover DeepSeek live cache hits

Browse Source
This commit is contained in:
Peter Steinberger
2026-04-25 06:47:34 +01:00
parent 2cd2732ab6
commit cfb551c709
2 changed files with 66 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
docs/reference/prompt-caching.md
View File

@@ -136,6 +136,11 @@ model refs, `contextPruning.mode: "cache-ttl"` is allowed because OpenRouter
handles provider-side prompt caching automatically. OpenClaw does not inject
Anthropic `cache_control` markers into those requests.
DeepSeek cache construction is best-effort and can take a few seconds. An
immediate follow-up may still show `cached_tokens: 0`; verify with a repeated
same-prefix request after a short delay and use `usage.prompt_tokens_details.cached_tokens`
as the cache-hit signal.
If you repoint the model at an arbitrary OpenAI-compatible proxy URL, OpenClaw
stops injecting those OpenRouter-specific Anthropic cache markers.