@rouvanpm/rouva 0.2.12 → 0.2.13

package/README.md

@@ -245,7 +245,7 @@ Every turn is logged as a usage snapshot in the Rouva dashboard under the shared
 | `messages` | `ChatMessage[]` | ✓ | Conversation seed — usually a single user message |
 | `tools` | `object[]` | ✓ | Tool definitions (OpenAI or Anthropic format) |
 | `tool_handlers` | `Record<string, string>` | ✓ | Tool name → handler URL mapping |
-| `model` | `RouvaModel` | recommended | Model to use — required for Anthropic tools |
+| `model` | `RouvaModel` | ✓ | Model to use — required for all `/run` requests |
 | `provider` | `RouvaProvider` | | Force a specific provider |
 | `max_turns` | `number` | | Max loop iterations (default: 10) |
 | `max_tokens` | `number` | | Max tokens per turn (default: 4096) |

package/dist/index.d.mts

@@ -45,7 +45,7 @@ interface ContentBlockMessage {
  * valid when `tools` is set on the request.
  */
 type ChatMessage = Message | AssistantToolCallMessage | ToolResultMessage | ContentBlockMessage;
-type RouvaProvider = 'anthropic' | 'openai' | 'gemini' | 'deepseek' | 'mistral' | 'moonshot' | 'xai' | 'zai' | (string & {});
+type RouvaProvider = 'anthropic' | 'openai' | 'gemini' | 'deepseek' | 'mistral' | 'moonshot' | 'xai' | 'zai' | 'alibaba' | (string & {});
 /**
  * Supported models across all providers.
  * Omit `model` entirely to let Rouva route to the cheapest capable model automatically.
@@ -56,7 +56,7 @@ type RouvaProvider = 'anthropic' | 'openai' | 'gemini' | 'deepseek' | 'mistral'
  * as-is. Until the gateway's registry knows their pricing, such requests are
  * logged with token counts but zero cost.
  */
-type RouvaModel = 'claude-opus-4-6' | 'claude-opus-4-7' | 'claude-opus-4-8' | 'claude-sonnet-4-6' | 'claude-sonnet-5' | 'claude-haiku-4-5-20251001' | 'claude-fable-5' | 'gpt-5-nano' | 'gpt-5-mini' | 'gpt-5.4-mini' | 'gpt-5' | 'gpt-5.6' | 'gpt-4.1-nano' | 'gpt-4.1-mini' | 'gpt-4.1' | 'gpt-4o' | 'gpt-4o-mini' | 'gemini-3.7-flash' | 'gemini-3.6-flash' | 'gemini-2.5-flash' | 'gemini-2.5-pro' | 'deepseek-v4-flash' | 'deepseek-v4-flash-think' | 'deepseek-v4-pro' | 'mistral-small-latest' | 'mistral-large-latest' | 'kimi-k2.6' | 'kimi-k3' | 'grok-4.6' | 'grok-4.5' | 'grok-4.3' | 'grok-4.20-0309-reasoning' | 'glm-4.7-flash' | 'glm-5.2' | (string & {});
+type RouvaModel = 'claude-opus-4-6' | 'claude-opus-4-7' | 'claude-opus-4-8' | 'claude-sonnet-4-6' | 'claude-sonnet-5' | 'claude-haiku-4-5-20251001' | 'claude-fable-5' | 'gpt-5-nano' | 'gpt-5-mini' | 'gpt-5.4-mini' | 'gpt-5' | 'gpt-5.6' | 'gpt-4.1-nano' | 'gpt-4.1-mini' | 'gpt-4.1' | 'gpt-4o' | 'gpt-4o-mini' | 'gemini-3.7-flash' | 'gemini-3.6-flash' | 'gemini-2.5-flash' | 'gemini-2.5-pro' | 'deepseek-v4-flash' | 'deepseek-v4-flash-think' | 'deepseek-v4-pro' | 'mistral-small-latest' | 'mistral-large-latest' | 'kimi-k2.6' | 'kimi-k3' | 'grok-4.6' | 'grok-4.5' | 'grok-4.3' | 'grok-4.20-0309-reasoning' | 'glm-4.7-flash' | 'glm-5.2' | 'qwen-turbo' | 'qwen-plus' | 'qwen-max' | 'qwen3-30b-a3b' | 'qwen3-32b' | 'qwen3-235b-a22b' | (string & {});
 /** Anthropic-style text block — the array form of the `system` param */
 interface SystemTextBlock {
     type: 'text';
@@ -176,6 +176,12 @@ interface RunParams {
      * `{ type: "function", function: { name, description, parameters } }` and
      * Anthropic-style `{ name, description, input_schema }` objects.
      * At least one tool is required.
+     *
+     * The gateway's canonical translation layer normalizes tool schemas to the
+     * correct wire format for the selected provider on every turn — you do not
+     * need to convert between formats. Same-provider turns replay schemas
+     * verbatim, preserving vendor-specific fields like `strict` (OpenAI) or
+     * `cache_control` (Anthropic) exactly as supplied.
      */
     tools: Array<Record<string, unknown>>;
     /**
@@ -189,9 +195,12 @@ interface RunParams {
      */
     tool_handlers: Record<string, string>;
     /**
-     * Target model. Must be specified for tool calls — the gateway never
-     * re-routes tool requests across providers since tool schemas are
-     * provider-specific.
+     * Target model. Intelligent Routing selects a provider and model once before
+     * the loop begins — the session stays on that provider for all turns. When
+     * the session history is fully translatable, routing may cross the
+     * Anthropic ↔ OpenAI-compatible boundary; the canonical layer handles tool
+     * schema translation automatically. Omit to let Rouva select the cheapest
+     * capable model automatically.
      */
     model?: RouvaModel;
     /**

package/dist/index.d.ts

@@ -45,7 +45,7 @@ interface ContentBlockMessage {
  * valid when `tools` is set on the request.
  */
 type ChatMessage = Message | AssistantToolCallMessage | ToolResultMessage | ContentBlockMessage;
-type RouvaProvider = 'anthropic' | 'openai' | 'gemini' | 'deepseek' | 'mistral' | 'moonshot' | 'xai' | 'zai' | (string & {});
+type RouvaProvider = 'anthropic' | 'openai' | 'gemini' | 'deepseek' | 'mistral' | 'moonshot' | 'xai' | 'zai' | 'alibaba' | (string & {});
 /**
  * Supported models across all providers.
  * Omit `model` entirely to let Rouva route to the cheapest capable model automatically.
@@ -56,7 +56,7 @@ type RouvaProvider = 'anthropic' | 'openai' | 'gemini' | 'deepseek' | 'mistral'
  * as-is. Until the gateway's registry knows their pricing, such requests are
  * logged with token counts but zero cost.
  */
-type RouvaModel = 'claude-opus-4-6' | 'claude-opus-4-7' | 'claude-opus-4-8' | 'claude-sonnet-4-6' | 'claude-sonnet-5' | 'claude-haiku-4-5-20251001' | 'claude-fable-5' | 'gpt-5-nano' | 'gpt-5-mini' | 'gpt-5.4-mini' | 'gpt-5' | 'gpt-5.6' | 'gpt-4.1-nano' | 'gpt-4.1-mini' | 'gpt-4.1' | 'gpt-4o' | 'gpt-4o-mini' | 'gemini-3.7-flash' | 'gemini-3.6-flash' | 'gemini-2.5-flash' | 'gemini-2.5-pro' | 'deepseek-v4-flash' | 'deepseek-v4-flash-think' | 'deepseek-v4-pro' | 'mistral-small-latest' | 'mistral-large-latest' | 'kimi-k2.6' | 'kimi-k3' | 'grok-4.6' | 'grok-4.5' | 'grok-4.3' | 'grok-4.20-0309-reasoning' | 'glm-4.7-flash' | 'glm-5.2' | (string & {});
+type RouvaModel = 'claude-opus-4-6' | 'claude-opus-4-7' | 'claude-opus-4-8' | 'claude-sonnet-4-6' | 'claude-sonnet-5' | 'claude-haiku-4-5-20251001' | 'claude-fable-5' | 'gpt-5-nano' | 'gpt-5-mini' | 'gpt-5.4-mini' | 'gpt-5' | 'gpt-5.6' | 'gpt-4.1-nano' | 'gpt-4.1-mini' | 'gpt-4.1' | 'gpt-4o' | 'gpt-4o-mini' | 'gemini-3.7-flash' | 'gemini-3.6-flash' | 'gemini-2.5-flash' | 'gemini-2.5-pro' | 'deepseek-v4-flash' | 'deepseek-v4-flash-think' | 'deepseek-v4-pro' | 'mistral-small-latest' | 'mistral-large-latest' | 'kimi-k2.6' | 'kimi-k3' | 'grok-4.6' | 'grok-4.5' | 'grok-4.3' | 'grok-4.20-0309-reasoning' | 'glm-4.7-flash' | 'glm-5.2' | 'qwen-turbo' | 'qwen-plus' | 'qwen-max' | 'qwen3-30b-a3b' | 'qwen3-32b' | 'qwen3-235b-a22b' | (string & {});
 /** Anthropic-style text block — the array form of the `system` param */
 interface SystemTextBlock {
     type: 'text';
@@ -176,6 +176,12 @@ interface RunParams {
      * `{ type: "function", function: { name, description, parameters } }` and
      * Anthropic-style `{ name, description, input_schema }` objects.
      * At least one tool is required.
+     *
+     * The gateway's canonical translation layer normalizes tool schemas to the
+     * correct wire format for the selected provider on every turn — you do not
+     * need to convert between formats. Same-provider turns replay schemas
+     * verbatim, preserving vendor-specific fields like `strict` (OpenAI) or
+     * `cache_control` (Anthropic) exactly as supplied.
      */
     tools: Array<Record<string, unknown>>;
     /**
@@ -189,9 +195,12 @@ interface RunParams {
      */
     tool_handlers: Record<string, string>;
     /**
-     * Target model. Must be specified for tool calls — the gateway never
-     * re-routes tool requests across providers since tool schemas are
-     * provider-specific.
+     * Target model. Intelligent Routing selects a provider and model once before
+     * the loop begins — the session stays on that provider for all turns. When
+     * the session history is fully translatable, routing may cross the
+     * Anthropic ↔ OpenAI-compatible boundary; the canonical layer handles tool
+     * schema translation automatically. Omit to let Rouva select the cheapest
+     * capable model automatically.
      */
     model?: RouvaModel;
     /**

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@rouvanpm/rouva",
-  "version": "0.2.12",
+  "version": "0.2.13",
   "description": "Official Node.js SDK for Rouva — managed AI gateway with intelligent routing and spend tracking",
   "main": "dist/index.js",
   "module": "dist/index.mjs",