@rouvanpm/rouva 0.4.0 → 0.4.1

package/README.md

@@ -105,8 +105,10 @@ const res = await rouva.chat.completions.create({
 - **`metadata`** — up to 10 string key-value pairs (keys up to 64 characters, values up to 256, no null bytes) stored with the request's usage record; not sent to the provider.
 - **`seed`** — best-effort deterministic sampling. Only OpenAI honors it, so it requires an OpenAI `model` and pins the request to that exact model (no routing, no fallbacks).
 - **`response_format`** — JSON mode or a JSON schema; see [Structured output](#structured-output).
+- **`reasoning_effort`** — `'none'` … `'xhigh'`, or `'max'` for Claude. Which values a model takes depends on the model; routing only picks one that takes yours; a listed OpenAI or Claude model you name that doesn't gets a 400, and other providers' models get the value as sent. On gpt-6-luna / gpt-6-sol, `'none'` turns reasoning off. See [the docs](https://rouva.io/docs#reasoning-effort).
+- **`parallel_tool_calls`** — with `tools`: `false` allows at most one tool call per turn (Claude included).
 
-Unsupported OpenAI options (`logit_bias`, `logprobs`, `reasoning_effort`, `n > 1`, the legacy `functions`/`function_call` fields, …) are rejected by the gateway with an explicit 400 rather than silently ignored.
+Unsupported OpenAI options (`logit_bias`, `logprobs`, `n > 1`, the legacy `functions`/`function_call` fields, …) are rejected by the gateway with an explicit 400 rather than silently ignored.
 
 ## Unlisted models
 

package/dist/index.d.mts

@@ -143,6 +143,26 @@ interface ChatCompletionParams {
      * `rouva.run()` doesn't accept it. See https://rouva.io/docs#structured-output
      */
     response_format?: ResponseFormat | null;
+    /**
+     * How hard a reasoning model thinks (gateway support since 2026-10-21).
+     * OpenAI models take it as is; Claude gets it as `output_config.effort`.
+     * Values depend on the model: gpt-5 / -mini / -nano take minimal–high;
+     * gpt-5.4-mini, gpt-5.6-*, gpt-6-luna / -sol take none–xhigh; gpt-6.1-sol
+     * low–xhigh; Claude Sonnet / Opus 4.6 low, medium, high, max; newer Claude
+     * models also xhigh; GPT-4 models and Claude Haiku 4.5 don't take it. Routing
+     * only picks a model that takes the value; a listed OpenAI or Claude model you
+     * name that doesn't is a 400 (other providers' models get the value as sent). On gpt-6-luna / -sol, `'none'` turns reasoning off (temperature,
+     * top_p and tools then work) and any other value turns it on (tools and
+     * top_p are then a 400). `rouva.run()` doesn't accept it.
+     * See https://rouva.io/docs#reasoning-effort
+     */
+    reasoning_effort?: ReasoningEffort | null;
+    /**
+     * With `tools` only: `false` limits the model to at most one tool call per
+     * turn. Forwarded to OpenAI-format providers; for Claude the gateway sets
+     * `disable_parallel_tool_use` on `tool_choice`. `rouva.run()` doesn't accept it.
+     */
+    parallel_tool_calls?: boolean | null;
     /**
      * Stream the response. Client-side only — controls whether `create()`
      * returns a ReadableStream or a buffered ChatCompletion; never sent to
@@ -165,6 +185,8 @@ interface ChatCompletionParams {
      */
     tool_choice?: string | Record<string, unknown>;
 }
+/** `reasoning_effort` values the gateway accepts (which ones a model takes varies). */
+type ReasoningEffort = 'none' | 'minimal' | 'low' | 'medium' | 'high' | 'xhigh' | 'max';
 /** `response_format` values the gateway accepts. */
 type ResponseFormat = {
     type: 'text';
@@ -511,4 +533,4 @@ declare class RouvaError extends Error {
     constructor(kind: 'Gateway' | 'Run' | 'Request', status: number, headers: Headers, rawBody: string);
 }
 
-export { type AssistantToolCallMessage, type ChatCompletion, type ChatCompletionChoice, type ChatCompletionParams, type ChatCompletionUsage, type ChatMessage, type ContentBlockMessage, type FunctionToolCall, type Message, type RequestOptions, type ResponseFormat, type ResponseMessage, Rouva, RouvaError, type RouvaModel, type RouvaOptions, type RouvaProvider, type RouvaRequest, type RouvaRequestStatus, type RouvaResponseMeta, type RouvaRouteReason, type RouvaStream, type RunParams, type RunResult, type SystemTextBlock, type ToolResultMessage };
+export { type AssistantToolCallMessage, type ChatCompletion, type ChatCompletionChoice, type ChatCompletionParams, type ChatCompletionUsage, type ChatMessage, type ContentBlockMessage, type FunctionToolCall, type Message, type ReasoningEffort, type RequestOptions, type ResponseFormat, type ResponseMessage, Rouva, RouvaError, type RouvaModel, type RouvaOptions, type RouvaProvider, type RouvaRequest, type RouvaRequestStatus, type RouvaResponseMeta, type RouvaRouteReason, type RouvaStream, type RunParams, type RunResult, type SystemTextBlock, type ToolResultMessage };

package/dist/index.d.ts

@@ -143,6 +143,26 @@ interface ChatCompletionParams {
      * `rouva.run()` doesn't accept it. See https://rouva.io/docs#structured-output
      */
     response_format?: ResponseFormat | null;
+    /**
+     * How hard a reasoning model thinks (gateway support since 2026-10-21).
+     * OpenAI models take it as is; Claude gets it as `output_config.effort`.
+     * Values depend on the model: gpt-5 / -mini / -nano take minimal–high;
+     * gpt-5.4-mini, gpt-5.6-*, gpt-6-luna / -sol take none–xhigh; gpt-6.1-sol
+     * low–xhigh; Claude Sonnet / Opus 4.6 low, medium, high, max; newer Claude
+     * models also xhigh; GPT-4 models and Claude Haiku 4.5 don't take it. Routing
+     * only picks a model that takes the value; a listed OpenAI or Claude model you
+     * name that doesn't is a 400 (other providers' models get the value as sent). On gpt-6-luna / -sol, `'none'` turns reasoning off (temperature,
+     * top_p and tools then work) and any other value turns it on (tools and
+     * top_p are then a 400). `rouva.run()` doesn't accept it.
+     * See https://rouva.io/docs#reasoning-effort
+     */
+    reasoning_effort?: ReasoningEffort | null;
+    /**
+     * With `tools` only: `false` limits the model to at most one tool call per
+     * turn. Forwarded to OpenAI-format providers; for Claude the gateway sets
+     * `disable_parallel_tool_use` on `tool_choice`. `rouva.run()` doesn't accept it.
+     */
+    parallel_tool_calls?: boolean | null;
     /**
      * Stream the response. Client-side only — controls whether `create()`
      * returns a ReadableStream or a buffered ChatCompletion; never sent to
@@ -165,6 +185,8 @@ interface ChatCompletionParams {
      */
     tool_choice?: string | Record<string, unknown>;
 }
+/** `reasoning_effort` values the gateway accepts (which ones a model takes varies). */
+type ReasoningEffort = 'none' | 'minimal' | 'low' | 'medium' | 'high' | 'xhigh' | 'max';
 /** `response_format` values the gateway accepts. */
 type ResponseFormat = {
     type: 'text';
@@ -511,4 +533,4 @@ declare class RouvaError extends Error {
     constructor(kind: 'Gateway' | 'Run' | 'Request', status: number, headers: Headers, rawBody: string);
 }
 
-export { type AssistantToolCallMessage, type ChatCompletion, type ChatCompletionChoice, type ChatCompletionParams, type ChatCompletionUsage, type ChatMessage, type ContentBlockMessage, type FunctionToolCall, type Message, type RequestOptions, type ResponseFormat, type ResponseMessage, Rouva, RouvaError, type RouvaModel, type RouvaOptions, type RouvaProvider, type RouvaRequest, type RouvaRequestStatus, type RouvaResponseMeta, type RouvaRouteReason, type RouvaStream, type RunParams, type RunResult, type SystemTextBlock, type ToolResultMessage };
+export { type AssistantToolCallMessage, type ChatCompletion, type ChatCompletionChoice, type ChatCompletionParams, type ChatCompletionUsage, type ChatMessage, type ContentBlockMessage, type FunctionToolCall, type Message, type ReasoningEffort, type RequestOptions, type ResponseFormat, type ResponseMessage, Rouva, RouvaError, type RouvaModel, type RouvaOptions, type RouvaProvider, type RouvaRequest, type RouvaRequestStatus, type RouvaResponseMeta, type RouvaRouteReason, type RouvaStream, type RunParams, type RunResult, type SystemTextBlock, type ToolResultMessage };

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@rouvanpm/rouva",
-  "version": "0.4.0",
+  "version": "0.4.1",
   "description": "Official Node.js SDK for Rouva — managed AI gateway with intelligent routing and spend tracking",
   "main": "dist/index.js",
   "module": "dist/index.mjs",