Support adaptive thinking for Anthropic-compatible aliases

closes #4790

packages/coding-agent/docs/custom-provider.md

@@ -230,6 +230,8 @@ 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.
+
 > Migration note: Mistral moved from `openai-completions` to `mistral-conversations`.
 > Use `mistral-conversations` for native Mistral models.
 > If you intentionally route Mistral-compatible/custom endpoints through `openai-completions`, set `compat` flags explicitly as needed.
@@ -702,8 +704,9 @@ interface ProviderModelConfig {
   /** Custom headers for this specific model. */
   headers?: Record<string, string>;
 
-  /** OpenAI compatibility settings for openai-completions API. */
+  /** Compatibility settings for the selected API. */
   compat?: {
+    // openai-completions
     supportsStore?: boolean;
     supportsDeveloperRole?: boolean;
     supportsReasoningEffort?: boolean;
@@ -715,6 +718,13 @@ interface ProviderModelConfig {
     requiresReasoningContentOnAssistantMessages?: boolean;
     thinkingFormat?: "openai" | "openrouter" | "deepseek" | "together" | "zai" | "qwen" | "qwen-chat-template";
     cacheControlFormat?: "anthropic";
+
+    // anthropic-messages
+    supportsEagerToolInputStreaming?: boolean;
+    supportsLongCacheRetention?: boolean;
+    sendSessionAffinityHeaders?: boolean;
+    supportsCacheControlOnTools?: boolean;
+    forceAdaptiveThinking?: boolean;
   };
 }
 ```

packages/coding-agent/docs/models.md

@@ -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