lmin/zmo-cli
1
0
Fork 0
Code Issues Pull Requests Actions 6 Packages Projects Releases Wiki Activity

chore: generate

Browse Source
This commit is contained in:
opencode-agent[bot]
2026-05-11 02:11:07 +00:00
parent 942630eb4a
commit 02cb7e7b71
7 changed files with 14 additions and 46 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
packages/llm/README.md
View File

@@ -82,12 +82,12 @@ LLM.request({
### Provider behavior table
| Protocol | `cache: "auto"` |
|---|---|
| Anthropic Messages | emits up to 3 `cache_control` markers (4-breakpoint cap enforced) |
| Bedrock Converse | emits up to 3 `cachePoint` blocks (4-breakpoint cap enforced) |
| OpenAI Chat / Responses | no-op (implicit caching above 1024 tokens) |
| Gemini | no-op (implicit caching on 2.5+; explicit `CachedContent` is out-of-band) |
| Protocol | `cache: "auto"` |
| ----------------------- | ------------------------------------------------------------------------- |
| Anthropic Messages | emits up to 3 `cache_control` markers (4-breakpoint cap enforced) |
| Bedrock Converse | emits up to 3 `cachePoint` blocks (4-breakpoint cap enforced) |
| OpenAI Chat / Responses | no-op (implicit caching above 1024 tokens) |
| Gemini | no-op (implicit caching on 2.5+; explicit `CachedContent` is out-of-band) |
Normalized cache usage is read back into `response.usage.cacheReadInputTokens` and `cacheWriteInputTokens` across every provider.