OldLigant/dsh-auto-review-model-router ↗★ 0
dsh-auto-review-model-router
Route DSH's experimental auto-review safety reviewer to a cheaper model: every review call is re-targeted to a configured provider/model while the agent's own route is untouched. 适合希望降低自动安全审查成本、将审查调用重定向到廉价模型的用户。
설치
$
npx -p @deepseek-ai/dsh dsh plugin --profile web add github:OldLigant/dsh-auto-review-model-routerConfiguration
| Field | Default | Meaning |
|---|---|---|
reviewModel | deepseek-official/deepseek-flash | ` |
| /` every review runs on. An empty string disables routing. | ||
systemPromptPatterns | the shipped REVIEW_POLICY opening | Substrings, or /regex/u literals, matched against a request's system prompt. Widen this only if a harness release rewrites that prompt. |
retryAttempts | 4 | Retries after the first attempt of one review call, so up to 5 attempts. 0 disables retrying. Maximum 10. |
retryDelayMs | 500 | Pause before each retry. |
wrapPrepareCall | true | Also route review requests issued through llm.prepareCall. |
dropReasoningEffort | true | Drop the source route's reasoning effort on the review request. |
dropMaxTokens | true | Drop the source route's output cap on the review request. |
logRetargets | true | Log each retargeted review. Retries log a warning regardless. |