@mariozechner/pi-ai 0.67.68 → 0.68.0

package/README.md

@@ -851,11 +851,13 @@ interface OpenAICompletionsCompat {
   supportsReasoningEffort?: boolean; // Whether provider supports `reasoning_effort` (default: true)
   supportsUsageInStreaming?: boolean; // Whether provider supports `stream_options: { include_usage: true }` (default: true)
   supportsStrictMode?: boolean;      // Whether provider supports `strict` in tool definitions (default: true)
+  sendSessionAffinityHeaders?: boolean; // Whether to send `session_id`, `x-client-request-id`, and `x-session-affinity` from `sessionId` when caching is enabled (default: false)
   maxTokensField?: 'max_completion_tokens' | 'max_tokens';  // Which field name to use (default: max_completion_tokens)
   requiresToolResultName?: boolean;  // Whether tool results require the `name` field (default: false)
   requiresAssistantAfterToolResult?: boolean; // Whether tool results must be followed by an assistant message (default: false)
   requiresThinkingAsText?: boolean;  // Whether thinking blocks must be converted to text (default: false)
-  thinkingFormat?: 'openai' | 'zai' | 'qwen'; // Format for reasoning param: 'openai' uses reasoning_effort, 'zai' uses thinking: { type: "enabled" }, 'qwen' uses enable_thinking: boolean (default: openai)
+  thinkingFormat?: 'openai' | 'zai' | 'qwen' | 'qwen-chat-template'; // Format for reasoning param: 'openai' uses reasoning_effort, 'zai' uses thinking: { type: "enabled" }, 'qwen' uses enable_thinking: boolean, 'qwen-chat-template' uses chat_template_kwargs.enable_thinking (default: openai)
+  cacheControlFormat?: 'anthropic';  // Anthropic-style cache_control on system prompt, last tool, and last user/assistant text content
   openRouterRouting?: OpenRouterRouting; // OpenRouter routing preferences (default: {})
   vercelGatewayRouting?: VercelGatewayRouting; // Vercel AI Gateway routing preferences (default: {})
 }

package/dist/models.generated.d.ts

@@ -6898,6 +6898,9 @@ export declare const MODELS: {
             api: "openai-completions";
             provider: string;
             baseUrl: string;
+            compat: {
+                cacheControlFormat: "anthropic";
+            };
             reasoning: true;
             input: ("image" | "text")[];
             cost: {
@@ -6915,6 +6918,9 @@ export declare const MODELS: {
             api: "openai-completions";
             provider: string;
             baseUrl: string;
+            compat: {
+                cacheControlFormat: "anthropic";
+            };
             reasoning: true;
             input: ("image" | "text")[];
             cost: {
@@ -6979,6 +6985,23 @@ export declare const MODELS: {
             contextWindow: number;
             maxTokens: number;
         };
+        readonly "kimi-k2.6": {
+            id: string;
+            name: string;
+            api: "openai-completions";
+            provider: string;
+            baseUrl: string;
+            reasoning: true;
+            input: ("image" | "text")[];
+            cost: {
+                input: number;
+                output: number;
+                cacheRead: number;
+                cacheWrite: number;
+            };
+            contextWindow: number;
+            maxTokens: number;
+        };
         readonly "mimo-v2-omni": {
             id: string;
             name: string;
@@ -7053,6 +7076,9 @@ export declare const MODELS: {
             api: "openai-completions";
             provider: string;
             baseUrl: string;
+            compat: {
+                cacheControlFormat: "anthropic";
+            };
             reasoning: true;
             input: ("image" | "text")[];
             cost: {
@@ -7070,6 +7096,9 @@ export declare const MODELS: {
             api: "openai-completions";
             provider: string;
             baseUrl: string;
+            compat: {
+                cacheControlFormat: "anthropic";
+            };
             reasoning: true;
             input: ("image" | "text")[];
             cost: {
@@ -8222,23 +8251,6 @@ export declare const MODELS: {
             contextWindow: number;
             maxTokens: number;
         };
-        readonly "meta-llama/llama-4-maverick": {
-            id: string;
-            name: string;
-            api: "openai-completions";
-            provider: string;
-            baseUrl: string;
-            reasoning: false;
-            input: ("image" | "text")[];
-            cost: {
-                input: number;
-                output: number;
-                cacheRead: number;
-                cacheWrite: number;
-            };
-            contextWindow: number;
-            maxTokens: number;
-        };
         readonly "meta-llama/llama-4-scout": {
             id: string;
             name: string;
@@ -8800,6 +8812,23 @@ export declare const MODELS: {
             contextWindow: number;
             maxTokens: number;
         };
+        readonly "moonshotai/kimi-k2.6": {
+            id: string;
+            name: string;
+            api: "openai-completions";
+            provider: string;
+            baseUrl: string;
+            reasoning: true;
+            input: ("image" | "text")[];
+            cost: {
+                input: number;
+                output: number;
+                cacheRead: number;
+                cacheWrite: number;
+            };
+            contextWindow: number;
+            maxTokens: number;
+        };
         readonly "nex-agi/deepseek-v3.1-nex-n1": {
             id: string;
             name: string;
@@ -9276,23 +9305,6 @@ export declare const MODELS: {
             contextWindow: number;
             maxTokens: number;
         };
-        readonly "openai/gpt-4o:extended": {
-            id: string;
-            name: string;
-            api: "openai-completions";
-            provider: string;
-            baseUrl: string;
-            reasoning: false;
-            input: ("image" | "text")[];
-            cost: {
-                input: number;
-                output: number;
-                cacheRead: number;
-                cacheWrite: number;
-            };
-            contextWindow: number;
-            maxTokens: number;
-        };
         readonly "openai/gpt-5": {
             id: string;
             name: string;
@@ -10183,7 +10195,7 @@ export declare const MODELS: {
             api: "openai-completions";
             provider: string;
             baseUrl: string;
-            reasoning: true;
+            reasoning: false;
             input: "text"[];
             cost: {
                 input: number;
@@ -12746,6 +12758,23 @@ export declare const MODELS: {
             contextWindow: number;
             maxTokens: number;
         };
+        readonly "moonshotai/kimi-k2.6": {
+            id: string;
+            name: string;
+            api: "anthropic-messages";
+            provider: string;
+            baseUrl: string;
+            reasoning: true;
+            input: ("image" | "text")[];
+            cost: {
+                input: number;
+                output: number;
+                cacheRead: number;
+                cacheWrite: number;
+            };
+            contextWindow: number;
+            maxTokens: number;
+        };
         readonly "nvidia/nemotron-nano-12b-v2-vl": {
             id: string;
             name: string;