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

Support adaptive thinking for Anthropic-compatible aliases

Browse Source 
closes #4790
This commit is contained in:
Mario Zechner
2026-05-22 18:30:04 +02:00
parent 7002c68f8b
commit d801d88a11
11 changed files with 239 additions and 33 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
packages/coding-agent/docs/models.md
View File

@@ -315,10 +315,12 @@ Behavior notes:
## Anthropic Messages Compatibility
For providers or proxies using `api: "anthropic-messages"`, use `compat.supportsEagerToolInputStreaming` to control Anthropic fine-grained tool streaming compatibility.
For providers or proxies using `api: "anthropic-messages"`, use `compat` to control Anthropic-specific request compatibility.
By default pi sends per-tool `eager_input_streaming: true`. If a proxy or Anthropic-compatible backend rejects that field, set `supportsEagerToolInputStreaming` to `false`. Pi will omit `tools[].eager_input_streaming` and send the legacy `fine-grained-tool-streaming-2025-05-14` beta header for tool-enabled requests instead.
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`.
```json
{
"providers": {
@@ -328,7 +330,8 @@ By default pi sends per-tool `eager_input_streaming: true`. If a proxy or Anthro
"apiKey": "ANTHROPIC_PROXY_KEY",
"compat": {
"supportsEagerToolInputStreaming": false,
"supportsLongCacheRetention": true
"supportsLongCacheRetention": true,
"forceAdaptiveThinking": true
},
"models": [
{
@@ -346,6 +349,9 @@ By default pi sends per-tool `eager_input_streaming: true`. If a proxy or Anthro
|-------|-------------|
| `supportsEagerToolInputStreaming` | Whether the provider accepts per-tool `eager_input_streaming`. Default: `true`. Set to `false` to omit that field and use the legacy fine-grained tool streaming beta header on tool-enabled requests. |
| `supportsLongCacheRetention` | Whether the provider accepts Anthropic long cache retention (`cache_control.ttl: "1h"`) when cache retention is `long`. Default: `true`. |
| `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`. |
## OpenAI Compatibility