@earendil-works/pi-ai 0.79.8 → 0.79.9

package/README.md

@@ -967,7 +967,8 @@ interface OpenAICompletionsCompat {
   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)
   requiresReasoningContentOnAssistantMessages?: boolean; // Whether all replayed assistant messages must include empty reasoning_content when reasoning is enabled (default: auto-detected for DeepSeek)
-  thinkingFormat?: 'openai' | 'openrouter' | 'deepseek' | 'together' | 'zai' | 'qwen' | 'qwen-chat-template' | 'string-thinking' | 'ant-ling'; // Format for reasoning param: 'openai' uses reasoning_effort, 'openrouter' uses reasoning: { effort }, 'deepseek' uses thinking: { type } plus reasoning_effort when supported, 'together' uses reasoning: { enabled } plus reasoning_effort when supported, 'zai' uses enable_thinking, 'qwen' uses enable_thinking, 'qwen-chat-template' uses chat_template_kwargs.enable_thinking, 'string-thinking' uses top-level thinking, 'ant-ling' uses reasoning: { effort } only for mapped efforts (default: openai)
+  thinkingFormat?: 'openai' | 'openrouter' | 'deepseek' | 'together' | 'zai' | 'qwen' | 'chat-template' | 'qwen-chat-template' | 'string-thinking' | 'ant-ling'; // Format for reasoning param: 'openai' uses reasoning_effort, 'openrouter' uses reasoning: { effort }, 'deepseek' uses thinking: { type } plus reasoning_effort when supported, 'together' uses reasoning: { enabled } plus reasoning_effort when supported, 'zai' uses thinking: { type }, 'qwen' uses enable_thinking, 'chat-template' uses configurable chat_template_kwargs, 'qwen-chat-template' uses chat_template_kwargs.enable_thinking and preserve_thinking, 'string-thinking' uses top-level thinking, 'ant-ling' uses reasoning: { effort } only for mapped efforts (default: openai)
+  chatTemplateKwargs?: Record<string, string | number | boolean | null | { '$var': 'thinking.enabled' | 'thinking.effort'; omitWhenOff?: boolean }>; // chat_template_kwargs values; use $var for pi-controlled thinking values
   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

@@ -4187,16 +4187,21 @@ export declare const MODELS: {
         readonly "accounts/fireworks/models/glm-5p2": {
             id: string;
             name: string;
-            api: "anthropic-messages";
+            api: "openai-completions";
             provider: string;
             baseUrl: string;
             compat: {
-                sendSessionAffinityHeaders: true;
-                supportsEagerToolInputStreaming: false;
-                supportsCacheControlOnTools: false;
-                supportsLongCacheRetention: false;
+                supportsStore: false;
+                supportsDeveloperRole: false;
             };
             reasoning: true;
+            thinkingLevelMap: {
+                off: string;
+                minimal: null;
+                low: string;
+                medium: string;
+                xhigh: string;
+            };
             input: "text"[];
             cost: {
                 input: number;
@@ -5402,54 +5407,6 @@ export declare const MODELS: {
             contextWindow: number;
             maxTokens: number;
         };
-        readonly "gemma-4-E2B-it": {
-            id: string;
-            name: string;
-            api: "google-generative-ai";
-            provider: string;
-            baseUrl: string;
-            reasoning: true;
-            thinkingLevelMap: {
-                off: null;
-                minimal: string;
-                low: null;
-                medium: null;
-                high: string;
-            };
-            input: ("image" | "text")[];
-            cost: {
-                input: number;
-                output: number;
-                cacheRead: number;
-                cacheWrite: number;
-            };
-            contextWindow: number;
-            maxTokens: number;
-        };
-        readonly "gemma-4-E4B-it": {
-            id: string;
-            name: string;
-            api: "google-generative-ai";
-            provider: string;
-            baseUrl: string;
-            reasoning: true;
-            thinkingLevelMap: {
-                off: null;
-                minimal: string;
-                low: null;
-                medium: null;
-                high: string;
-            };
-            input: ("image" | "text")[];
-            cost: {
-                input: number;
-                output: number;
-                cacheRead: number;
-                cacheWrite: number;
-            };
-            contextWindow: number;
-            maxTokens: number;
-        };
     };
     readonly "google-vertex": {
         readonly "gemini-2.5-flash": {
@@ -14338,6 +14295,9 @@ export declare const MODELS: {
             provider: string;
             baseUrl: string;
             reasoning: true;
+            thinkingLevelMap: {
+                xhigh: string;
+            };
             input: "text"[];
             cost: {
                 input: number;