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

Fix Anthropic empty thinking signature replay

Browse Source 
closes #4464
This commit is contained in:
Mario Zechner
2026-05-28 12:02:54 +02:00
parent 3e9f717445
commit 458a7bc27c
10 changed files with 252 additions and 18 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
packages/coding-agent/docs/custom-provider.md
View File

@@ -232,7 +232,7 @@ models: [{
Use `openrouter` for OpenRouter-style `reasoning: { effort }` controls. Use `together` for Together-style `reasoning: { enabled }` controls; with `supportsReasoningEffort`, it also sends `reasoning_effort`. Use `qwen-chat-template` instead for local Qwen-compatible servers that read `chat_template_kwargs.enable_thinking`.
Use `cacheControlFormat: "anthropic"` for OpenAI-compatible providers that expose Anthropic-style prompt caching via `cache_control` on the system prompt, last tool definition, and last user/assistant text content.
For Anthropic-compatible providers using `api: "anthropic-messages"`, set `compat.forceAdaptiveThinking: true` on models or providers whose upstream model requires adaptive thinking (`thinking.type: "adaptive"` plus `output_config.effort`). Built-in adaptive Claude models set this automatically.
For Anthropic-compatible providers using `api: "anthropic-messages"`, set `compat.forceAdaptiveThinking: true` on models or providers whose upstream model requires adaptive thinking (`thinking.type: "adaptive"` plus `output_config.effort`). Built-in adaptive Claude models set this automatically. Set `compat.allowEmptySignature: true` only for providers that emit empty thinking signatures and expect `signature: ""` on replay.
> Migration note: Mistral moved from `openai-completions` to `mistral-conversations`.
> Use `mistral-conversations` for native Mistral models.
@@ -727,6 +727,7 @@ interface ProviderModelConfig {
sendSessionAffinityHeaders?: boolean;
supportsCacheControlOnTools?: boolean;
forceAdaptiveThinking?: boolean;
allowEmptySignature?: boolean;
};
}
```

6
packages/coding-agent/docs/models.md
View File

@@ -330,6 +330,8 @@ By default pi sends per-tool `eager_input_streaming: true`. If a proxy or Anthro
Some Anthropic models require adaptive thinking (`thinking.type: "adaptive"` plus `output_config.effort`) instead of the legacy budget-based thinking payload. Built-in models set this automatically. For custom providers or aliases that route to those models, set `forceAdaptiveThinking` to `true`.
Some Anthropic-compatible providers emit thinking blocks with empty signatures and still expect them on replay. Set `allowEmptySignature` to `true` only for those providers; real Anthropic rejects empty thinking signatures.
```json
{
"providers": {
@@ -340,7 +342,8 @@ Some Anthropic models require adaptive thinking (`thinking.type: "adaptive"` plu
"compat": {
"supportsEagerToolInputStreaming": false,
"supportsLongCacheRetention": true,
"forceAdaptiveThinking": true
"forceAdaptiveThinking": true,
"allowEmptySignature": true
},
"models": [
{
@@ -361,6 +364,7 @@ Some Anthropic models require adaptive thinking (`thinking.type: "adaptive"` plu
| `sendSessionAffinityHeaders` | Whether to send `x-session-affinity` from the session id when caching is enabled. Default: auto-detected for known providers. |
| `supportsCacheControlOnTools` | Whether the provider accepts Anthropic-style `cache_control` markers on tool definitions. Default: `true`. |
| `forceAdaptiveThinking` | Whether to send adaptive thinking (`thinking.type: "adaptive"` plus `output_config.effort`) for this model. Built-in adaptive models set this automatically. Default: `false`. |
| `allowEmptySignature` | Whether to replay empty thinking signatures as `signature: ""` instead of converting thinking to text. Default: `false`. |
## OpenAI Compatibility