shumengya/sproutclaw
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat: add model thinking level metadata

Browse Source 
closes #3208
This commit is contained in:
Mario Zechner
2026-05-02 01:20:01 +02:00
parent 73b7b2c564
commit 80f06d3636
28 changed files with 527 additions and 243 deletions
Download Patch File Download Diff File Expand all files Collapse all files

35
packages/coding-agent/docs/custom-provider.md
View File

@@ -201,28 +201,29 @@ The `api` field determines which streaming implementation is used:
| `google-vertex` | Google Vertex AI API |
| `bedrock-converse-stream` | Amazon Bedrock Converse API |
Most OpenAI-compatible providers work with `openai-completions`. Use `compat` for quirks:
Most OpenAI-compatible providers work with `openai-completions`. Use model-level `thinkingLevelMap` for model-specific thinking levels, and `compat` for provider quirks:
```typescript
models: [{
id: "custom-model",
// ...
reasoning: true,
thinkingLevelMap: { // map pi levels to provider values; null hides unsupported levels
minimal: null,
low: null,
medium: null,
high: "default",
xhigh: "max"
},
compat: {
supportsDeveloperRole: false, // use "system" instead of "developer"
supportsDeveloperRole: false, // use "system" instead of "developer"
supportsReasoningEffort: true,
reasoningEffortMap: { // map pi-ai levels to provider values
minimal: "default",
low: "default",
medium: "default",
high: "default",
xhigh: "default"
},
maxTokensField: "max_tokens", // instead of "max_completion_tokens"
requiresToolResultName: true, // tool results need name field
thinkingFormat: "qwen", // top-level enable_thinking: true
cacheControlFormat: "anthropic" // Anthropic-style cache_control markers
}
}]
maxTokensField: "max_tokens", // instead of "max_completion_tokens"
requiresToolResultName: true, // tool results need name field
thinkingFormat: "qwen", // top-level enable_thinking: true
cacheControlFormat: "anthropic" // Anthropic-style cache_control markers
}
}]
```
Use `qwen-chat-template` instead for local Qwen-compatible servers that read `chat_template_kwargs.enable_thinking`.
@@ -601,6 +602,9 @@ interface ProviderModelConfig {
/** Whether the model supports extended thinking. */
reasoning: boolean;
/** Maps pi thinking levels to provider/model-specific values; null marks a level unsupported. */
thinkingLevelMap?: Partial<Record<"off" | "minimal" | "low" | "medium" | "high" | "xhigh", string | null>>;
/** Supported input types. */
input: ("text" | "image")[];
@@ -626,7 +630,6 @@ interface ProviderModelConfig {
supportsStore?: boolean;
supportsDeveloperRole?: boolean;
supportsReasoningEffort?: boolean;
reasoningEffortMap?: Partial<Record<"minimal" | "low" | "medium" | "high" | "xhigh", string>>;
supportsUsageInStreaming?: boolean;
maxTokensField?: "max_completion_tokens" | "max_tokens";
requiresToolResultName?: boolean;