@dreb/ai 2.43.2 → 2.44.0

package/README.md

@@ -830,16 +830,27 @@ await streamAnthropic(claude, context, options);
 
 ## Cross-Provider Handoffs
 
-The library supports seamless handoffs between different LLM providers within the same conversation. This allows you to switch models mid-conversation while preserving context, including thinking blocks, tool calls, and tool results.
+The library can prepare one conversation for another model without changing the stored `Context`. User messages, visible assistant text, tool calls, and tool results remain available, while model-bound tool signatures and IDs are normalized for the destination. Provider-specific reasoning state is handled conservatively.
 
-### How It Works
+### Reasoning State Compatibility
 
-When messages from one provider are sent to a different provider, the library automatically transforms them for compatibility:
+- **Exact model:** signed, encrypted, and redacted reasoning state is replayed unchanged.
+- **Compatible model switch:** structured reasoning is preserved only when source and target share a provider, both use `openai-completions`, the destination accepts structured reasoning, and the source uses a recognized plain field: `reasoning_content`, `reasoning`, or `reasoning_text`.
+- **Other readable reasoning:** it is retained as labelled plaintext inside `<reformatted-pre-switch-reasoning>` markers, with incompatible protocol metadata stripped.
+- **Opaque state:** redacted or encrypted-only reasoning is omitted for incompatible targets.
 
-- **User and tool result messages** are passed through unchanged
-- **Assistant messages from the same provider/API** are preserved as-is
-- **Assistant messages from different providers** have their thinking blocks converted to text with `<thinking>` tags
-- **Tool calls and regular text** are preserved unchanged
+Compatibility depends on provider, API, and signature behavior. This includes custom models: two models at the same endpoint are not compatible merely because their IDs or URLs match; they must share the configured provider identity as well.
+
+The transformation applies only to the outbound request. It does not mutate `Context.messages`, so a later switch back to the original model can replay its original reasoning state unless that history has been compacted or pruned by the caller.
+
+### Examples
+
+| Source and target | Outbound reasoning state |
+|---|---|
+| The same model | Original signed, encrypted, or redacted state is replayed unchanged. |
+| Two models under the same custom provider, both using `openai-completions`, where the destination accepts the source's `reasoning_content`, `reasoning`, or `reasoning_text` field | Recognized plain structured reasoning is preserved. |
+| Different providers or APIs with readable reasoning | Reasoning is sent as labelled plaintext in `<reformatted-pre-switch-reasoning>` markers. |
+| An incompatible target with redacted or encrypted-only reasoning | Opaque reasoning state is omitted. |
 
 ### Example: Multi-Provider Conversation
 
@@ -858,32 +869,17 @@ const claudeResponse = await complete(claude, context, {
 });
 context.messages.push(claudeResponse);
 
-// Switch to GPT-5 - it will see Claude's thinking as <thinking> tagged text
+// Switch to GPT-5. Readable Claude reasoning is reformatted for this outbound request.
 const gpt5 = getModel('openai', 'gpt-5-mini');
 context.messages.push({ role: 'user', content: 'Is that calculation correct?' });
 const gptResponse = await complete(gpt5, context);
 context.messages.push(gptResponse);
 
-// Switch to Gemini
-const gemini = getModel('google', 'gemini-2.5-flash');
+// Switching back to Claude can use the original Claude state in context.
 context.messages.push({ role: 'user', content: 'What was the original question?' });
-const geminiResponse = await complete(gemini, context);
+const finalClaudeResponse = await complete(claude, context);
 ```
 
-### Provider Compatibility
-
-All providers can handle messages from other providers, including:
-- Text content
-- Tool calls and tool results (including images in tool results)
-- Thinking/reasoning blocks (transformed to tagged text for cross-provider compatibility)
-- Aborted messages with partial content
-
-This enables flexible workflows where you can:
-- Start with a fast model for initial responses
-- Switch to a more capable model for complex reasoning
-- Use specialized models for specific tasks
-- Maintain conversation continuity across provider outages
-
 ## Context Serialization
 
 The `Context` object can be easily serialized and deserialized using standard JSON methods, making it simple to persist conversations, implement chat history, or transfer contexts between services:

package/dist/models.generated.d.ts

@@ -3827,6 +3827,40 @@ export declare const MODELS: {
             contextWindow: number;
             maxTokens: number;
         };
+        readonly "gemini-3.5-flash-lite": {
+            id: string;
+            name: string;
+            api: "google-generative-ai";
+            provider: string;
+            baseUrl: string;
+            reasoning: true;
+            input: ("image" | "text")[];
+            cost: {
+                input: number;
+                output: number;
+                cacheRead: number;
+                cacheWrite: number;
+            };
+            contextWindow: number;
+            maxTokens: number;
+        };
+        readonly "gemini-3.6-flash": {
+            id: string;
+            name: string;
+            api: "google-generative-ai";
+            provider: string;
+            baseUrl: string;
+            reasoning: true;
+            input: ("image" | "text")[];
+            cost: {
+                input: number;
+                output: number;
+                cacheRead: number;
+                cacheWrite: number;
+            };
+            contextWindow: number;
+            maxTokens: number;
+        };
         readonly "gemini-flash-latest": {
             id: string;
             name: string;
@@ -4903,6 +4937,26 @@ export declare const MODELS: {
             contextWindow: number;
             maxTokens: number;
         };
+        readonly "XiaomiMiMo/MiMo-V2.5": {
+            id: string;
+            name: string;
+            api: "openai-completions";
+            provider: string;
+            baseUrl: string;
+            compat: {
+                supportsDeveloperRole: false;
+            };
+            reasoning: true;
+            input: "text"[];
+            cost: {
+                input: number;
+                output: number;
+                cacheRead: number;
+                cacheWrite: number;
+            };
+            contextWindow: number;
+            maxTokens: number;
+        };
         readonly "XiaomiMiMo/MiMo-V2.5-Pro": {
             id: string;
             name: string;
@@ -5482,7 +5536,7 @@ export declare const MODELS: {
             contextWindow: number;
             maxTokens: number;
         };
-        readonly k2p7: {
+        readonly k3: {
             id: string;
             name: string;
             api: "anthropic-messages";
@@ -5499,7 +5553,7 @@ export declare const MODELS: {
             contextWindow: number;
             maxTokens: number;
         };
-        readonly k3: {
+        readonly "kimi-for-coding": {
             id: string;
             name: string;
             api: "anthropic-messages";
@@ -7501,6 +7555,40 @@ export declare const MODELS: {
             contextWindow: number;
             maxTokens: number;
         };
+        readonly "gemini-3.5-flash-lite": {
+            id: string;
+            name: string;
+            api: "google-generative-ai";
+            provider: string;
+            baseUrl: string;
+            reasoning: true;
+            input: ("image" | "text")[];
+            cost: {
+                input: number;
+                output: number;
+                cacheRead: number;
+                cacheWrite: number;
+            };
+            contextWindow: number;
+            maxTokens: number;
+        };
+        readonly "gemini-3.6-flash": {
+            id: string;
+            name: string;
+            api: "google-generative-ai";
+            provider: string;
+            baseUrl: string;
+            reasoning: true;
+            input: ("image" | "text")[];
+            cost: {
+                input: number;
+                output: number;
+                cacheRead: number;
+                cacheWrite: number;
+            };
+            contextWindow: number;
+            maxTokens: number;
+        };
         readonly "glm-5": {
             id: string;
             name: string;
@@ -7878,7 +7966,7 @@ export declare const MODELS: {
         readonly "grok-4.5": {
             id: string;
             name: string;
-            api: "openai-completions";
+            api: "openai-responses";
             provider: string;
             baseUrl: string;
             reasoning: true;
@@ -7909,14 +7997,14 @@ export declare const MODELS: {
             contextWindow: number;
             maxTokens: number;
         };
-        readonly "hy3-free": {
+        readonly "kimi-k2.5": {
             id: string;
             name: string;
             api: "openai-completions";
             provider: string;
             baseUrl: string;
             reasoning: true;
-            input: "text"[];
+            input: ("image" | "text")[];
             cost: {
                 input: number;
                 output: number;
@@ -7926,7 +8014,7 @@ export declare const MODELS: {
             contextWindow: number;
             maxTokens: number;
         };
-        readonly "kimi-k2.5": {
+        readonly "kimi-k2.6": {
             id: string;
             name: string;
             api: "openai-completions";
@@ -7943,7 +8031,7 @@ export declare const MODELS: {
             contextWindow: number;
             maxTokens: number;
         };
-        readonly "kimi-k2.6": {
+        readonly "kimi-k2.7-code": {
             id: string;
             name: string;
             api: "openai-completions";
@@ -7960,14 +8048,14 @@ export declare const MODELS: {
             contextWindow: number;
             maxTokens: number;
         };
-        readonly "kimi-k2.7-code": {
+        readonly "laguna-s-2.1-free": {
             id: string;
             name: string;
             api: "openai-completions";
             provider: string;
             baseUrl: string;
             reasoning: true;
-            input: ("image" | "text")[];
+            input: "text"[];
             cost: {
                 input: number;
                 output: number;
@@ -8186,7 +8274,7 @@ export declare const MODELS: {
         readonly "grok-4.5": {
             id: string;
             name: string;
-            api: "openai-completions";
+            api: "openai-responses";
             provider: string;
             baseUrl: string;
             reasoning: true;
@@ -8200,6 +8288,23 @@ export declare const MODELS: {
             contextWindow: number;
             maxTokens: number;
         };
+        readonly hy3: {
+            id: string;
+            name: string;
+            api: "openai-completions";
+            provider: string;
+            baseUrl: string;
+            reasoning: true;
+            input: "text"[];
+            cost: {
+                input: number;
+                output: number;
+                cacheRead: number;
+                cacheWrite: number;
+            };
+            contextWindow: number;
+            maxTokens: number;
+        };
         readonly "kimi-k2.6": {
             id: string;
             name: string;
@@ -9324,6 +9429,40 @@ export declare const MODELS: {
             contextWindow: number;
             maxTokens: number;
         };
+        readonly "google/gemini-3.5-flash-lite": {
+            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 "google/gemini-3.6-flash": {
+            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 "google/gemma-3-12b-it": {
             id: string;
             name: string;
@@ -9562,13 +9701,13 @@ export declare const MODELS: {
             contextWindow: number;
             maxTokens: number;
         };
-        readonly "meta-llama/llama-3.1-70b-instruct": {
+        readonly "meituan/longcat-2.0": {
             id: string;
             name: string;
             api: "openai-completions";
             provider: string;
             baseUrl: string;
-            reasoning: false;
+            reasoning: true;
             input: "text"[];
             cost: {
                 input: number;
@@ -9579,7 +9718,7 @@ export declare const MODELS: {
             contextWindow: number;
             maxTokens: number;
         };
-        readonly "meta-llama/llama-3.1-8b-instruct": {
+        readonly "meta-llama/llama-3.1-70b-instruct": {
             id: string;
             name: string;
             api: "openai-completions";
@@ -9596,7 +9735,7 @@ export declare const MODELS: {
             contextWindow: number;
             maxTokens: number;
         };
-        readonly "meta-llama/llama-3.3-70b-instruct": {
+        readonly "meta-llama/llama-3.1-8b-instruct": {
             id: string;
             name: string;
             api: "openai-completions";
@@ -9613,7 +9752,7 @@ export declare const MODELS: {
             contextWindow: number;
             maxTokens: number;
         };
-        readonly "meta-llama/llama-3.3-70b-instruct:free": {
+        readonly "meta-llama/llama-3.3-70b-instruct": {
             id: string;
             name: string;
             api: "openai-completions";
@@ -11466,6 +11605,40 @@ export declare const MODELS: {
             contextWindow: number;
             maxTokens: number;
         };
+        readonly "poolside/laguna-s-2.1": {
+            id: string;
+            name: string;
+            api: "openai-completions";
+            provider: string;
+            baseUrl: string;
+            reasoning: true;
+            input: "text"[];
+            cost: {
+                input: number;
+                output: number;
+                cacheRead: number;
+                cacheWrite: number;
+            };
+            contextWindow: number;
+            maxTokens: number;
+        };
+        readonly "poolside/laguna-s-2.1:free": {
+            id: string;
+            name: string;
+            api: "openai-completions";
+            provider: string;
+            baseUrl: string;
+            reasoning: true;
+            input: "text"[];
+            cost: {
+                input: number;
+                output: number;
+                cacheRead: number;
+                cacheWrite: number;
+            };
+            contextWindow: number;
+            maxTokens: number;
+        };
         readonly "poolside/laguna-xs-2.1": {
             id: string;
             name: string;
@@ -11823,23 +11996,6 @@ export declare const MODELS: {
             contextWindow: number;
             maxTokens: number;
         };
-        readonly "qwen/qwen3-coder:free": {
-            id: string;
-            name: string;
-            api: "openai-completions";
-            provider: string;
-            baseUrl: string;
-            reasoning: false;
-            input: "text"[];
-            cost: {
-                input: number;
-                output: number;
-                cacheRead: number;
-                cacheWrite: number;
-            };
-            contextWindow: number;
-            maxTokens: number;
-        };
         readonly "qwen/qwen3-max": {
             id: string;
             name: string;
@@ -11891,23 +12047,6 @@ export declare const MODELS: {
             contextWindow: number;
             maxTokens: number;
         };
-        readonly "qwen/qwen3-next-80b-a3b-instruct:free": {
-            id: string;
-            name: string;
-            api: "openai-completions";
-            provider: string;
-            baseUrl: string;
-            reasoning: false;
-            input: "text"[];
-            cost: {
-                input: number;
-                output: number;
-                cacheRead: number;
-                cacheWrite: number;
-            };
-            contextWindow: number;
-            maxTokens: number;
-        };
         readonly "qwen/qwen3-next-80b-a3b-thinking": {
             id: string;
             name: string;
@@ -12435,23 +12574,6 @@ export declare const MODELS: {
             contextWindow: number;
             maxTokens: number;
         };
-        readonly "tencent/hy3:free": {
-            id: string;
-            name: string;
-            api: "openai-completions";
-            provider: string;
-            baseUrl: string;
-            reasoning: true;
-            input: "text"[];
-            cost: {
-                input: number;
-                output: number;
-                cacheRead: number;
-                cacheWrite: number;
-            };
-            contextWindow: number;
-            maxTokens: number;
-        };
         readonly "thedrummer/unslopnemo-12b": {
             id: string;
             name: string;
@@ -14086,6 +14208,40 @@ export declare const MODELS: {
             contextWindow: number;
             maxTokens: number;
         };
+        readonly "google/gemini-3.5-flash-lite": {
+            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 "google/gemini-3.6-flash": {
+            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 "google/gemma-4-26b-a4b-it": {
             id: string;
             name: string;
@@ -14154,6 +14310,23 @@ export declare const MODELS: {
             contextWindow: number;
             maxTokens: number;
         };
+        readonly "inclusionai/ling-3.0-flash-free": {
+            id: string;
+            name: string;
+            api: "anthropic-messages";
+            provider: string;
+            baseUrl: string;
+            reasoning: true;
+            input: "text"[];
+            cost: {
+                input: number;
+                output: number;
+                cacheRead: number;
+                cacheWrite: number;
+            };
+            contextWindow: number;
+            maxTokens: number;
+        };
         readonly "interfaze/interfaze-beta": {
             id: string;
             name: string;
@@ -15633,6 +15806,40 @@ export declare const MODELS: {
             contextWindow: number;
             maxTokens: number;
         };
+        readonly "poolside/laguna-s-2.1": {
+            id: string;
+            name: string;
+            api: "anthropic-messages";
+            provider: string;
+            baseUrl: string;
+            reasoning: true;
+            input: "text"[];
+            cost: {
+                input: number;
+                output: number;
+                cacheRead: number;
+                cacheWrite: number;
+            };
+            contextWindow: number;
+            maxTokens: number;
+        };
+        readonly "poolside/laguna-s-2.1-free": {
+            id: string;
+            name: string;
+            api: "anthropic-messages";
+            provider: string;
+            baseUrl: string;
+            reasoning: true;
+            input: "text"[];
+            cost: {
+                input: number;
+                output: number;
+                cacheRead: number;
+                cacheWrite: number;
+            };
+            contextWindow: number;
+            maxTokens: number;
+        };
         readonly "sakana/fugu-ultra": {
             id: string;
             name: string;
@@ -15684,6 +15891,23 @@ export declare const MODELS: {
             contextWindow: number;
             maxTokens: number;
         };
+        readonly "tencent/hy3": {
+            id: string;
+            name: string;
+            api: "anthropic-messages";
+            provider: string;
+            baseUrl: string;
+            reasoning: true;
+            input: "text"[];
+            cost: {
+                input: number;
+                output: number;
+                cacheRead: number;
+                cacheWrite: number;
+            };
+            contextWindow: number;
+            maxTokens: number;
+        };
         readonly "thinkingmachines/inkling": {
             id: string;
             name: string;