vultr/openclaw
1
0
Fork 0
mirror of https://github.com/openclaw/openclaw.git synced 2026-05-06 10:30:44 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix(openrouter): allow DeepSeek cache-ttl eligibility

Browse Source
This commit is contained in:
Peter Steinberger
2026-04-25 06:38:11 +01:00
parent 29f7a2f441
commit d79b9e0af4
6 changed files with 19 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
docs/concepts/model-providers.md
View File

@@ -269,7 +269,7 @@ See [/providers/kilocode](/providers/kilocode) for setup details.
Quirks worth knowing:
- **OpenRouter** applies its app-attribution headers and Anthropic `cache_control` markers only on verified `openrouter.ai` routes. As a proxy-style OpenAI-compatible path, it skips native-OpenAI-only shaping (`serviceTier`, Responses `store`, prompt-cache hints, OpenAI reasoning-compat). Gemini-backed refs keep proxy-Gemini thought-signature sanitation only.
- **OpenRouter** applies its app-attribution headers and Anthropic `cache_control` markers only on verified `openrouter.ai` routes. DeepSeek, Moonshot, and ZAI refs are cache-TTL eligible for OpenRouter-managed prompt caching but do not receive Anthropic cache markers. As a proxy-style OpenAI-compatible path, it skips native-OpenAI-only shaping (`serviceTier`, Responses `store`, prompt-cache hints, OpenAI reasoning-compat). Gemini-backed refs keep proxy-Gemini thought-signature sanitation only.
- **Kilo Gateway** Gemini-backed refs follow the same proxy-Gemini sanitation path; `kilocode/kilo/auto` and other proxy-reasoning-unsupported refs skip proxy reasoning injection.
- **MiniMax** API-key onboarding writes explicit text-only M2.7 chat model definitions; image understanding stays on the plugin-owned `MiniMax-VL-01` media provider.
- **xAI** uses the xAI Responses path. `/fast` or `params.fastMode: true` rewrites `grok-3`, `grok-3-mini`, `grok-4`, and `grok-4-0709` to their `*-fast` variants. `tool_stream` defaults on; disable via `agents.defaults.models["xai/<model>"].params.tool_stream=false`.

7
docs/reference/prompt-caching.md
View File

@@ -123,7 +123,7 @@ Per-agent heartbeat is supported at `agents.list[].heartbeat`.
- Anthropic Claude model refs (`amazon-bedrock/*anthropic.claude*`) support explicit `cacheRetention` pass-through.
- Non-Anthropic Bedrock models are forced to `cacheRetention: "none"` at runtime.
### OpenRouter Anthropic models
### OpenRouter models
For `openrouter/anthropic/*` model refs, OpenClaw injects Anthropic
`cache_control` on system/developer prompt blocks to improve prompt-cache
@@ -131,6 +131,11 @@ reuse only when the request is still targeting a verified OpenRouter route
(`openrouter` on its default endpoint, or any provider/base URL that resolves
to `openrouter.ai`).
For `openrouter/deepseek/*`, `openrouter/moonshot*/*`, and `openrouter/zai/*`
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.
If you repoint the model at an arbitrary OpenAI-compatible proxy URL, OpenClaw
stops injecting those OpenRouter-specific Anthropic cache markers.