@yourgpt/llm-sdk 2.5.1-beta.6 → 2.6.0-beta.1

package/README.md

@@ -10,6 +10,83 @@ npm install @yourgpt/llm-sdk @anthropic-ai/sdk
 
 > For other providers (OpenAI, Google, xAI), see [Providers Documentation](https://copilot-sdk.yourgpt.ai/docs/providers).
 
+## OpenAI reasoning parameters
+
+The SDK normalizes token limits and sampling options for recognized OpenAI model
+families, including GPT-6. Reasoning stays enabled by default. An unsupported
+`temperature` is omitted with a warning; the SDK does not silently disable
+reasoning. Use `onWarning` in the OpenAI provider configuration to handle these
+warnings yourself.
+
+For a model that supports non-reasoning mode, select it explicitly when sampling
+control is required:
+
+```ts
+import { generateText } from "@yourgpt/llm-sdk";
+import { openai } from "@yourgpt/llm-sdk/openai";
+
+const result = await generateText({
+  model: openai("gpt-6-luna"),
+  prompt: "Classify this request.",
+  reasoningEffort: "none",
+  temperature: 0,
+});
+```
+
+`reasoningEffort` can also be set on `createOpenAI(...)` or `OpenAIAdapter` and
+overridden in a Runtime request's `config`. Unsupported `none`/`minimal` settings
+for recognized reasoning models fail before the provider request.
+
+On OpenAI's own endpoint, GPT-5.4+ and GPT-6 tool requests with reasoning use the
+existing Responses transport, in both Runtime and modern generation. Custom
+endpoints keep Chat routing. Servers with different parameter rules can set
+`parameterPolicy: "passthrough"` on the OpenAI provider. Responses requires an
+installed OpenAI client that exposes `responses.create`; older clients fail with
+an actionable error. This routing does not add the separate Decisions API.
+
+## Compatibility fallback
+
+Transient failures retain bounded retries and fallback. Compatibility errors such
+as an unsupported parameter stop by default. To advance to another model for a
+specific compatibility error without repeating the same invalid request, use
+`fallbackErrors` independently of `retryableErrors`:
+
+```ts
+import { createFallbackChain } from "@yourgpt/llm-sdk/fallback";
+import { createOpenAI } from "@yourgpt/llm-sdk/openai";
+
+const provider = createOpenAI();
+const adapter = createFallbackChain({
+  models: [
+    provider.languageModel("gpt-6-luna"),
+    provider.languageModel("gpt-4o"),
+  ],
+  retries: 2,
+  fallbackErrors(error) {
+    const e = error as { status?: number; code?: string; param?: string };
+    return (
+      e?.status === 400 &&
+      e.code === "unsupported_parameter" &&
+      e.param === "temperature"
+    );
+  },
+});
+```
+
+This is an additional fallback policy for otherwise non-retryable errors. It does
+not disable transient retries. Keep the predicate narrow; do not match every 400
+or use `retryableErrors: () => true` for compatibility failures. Cancellation and
+errors after stream output or tool events never retry or switch models. Provider
+status/code/parameter fields survive OpenAI streaming errors; raw error causes
+are retained only in-process and omitted from JSON/SSE output.
+
+Stream readers and final-result promises share one execution, including tool
+execution. Later readers replay retained stream parts; pass an abort signal to
+cancel generation. Cancellation during a tool stops subsequent tools and rejects
+the result rather than reporting a successful completion.
+`pnpm --filter @yourgpt/llm-sdk test` builds the package and
+runs offline provider/fallback regression tests without real API credentials.
+
 ## Quick Start
 
 ```ts

package/dist/adapters/index.d.mts

@@ -1,13 +1,15 @@
-import { L as LLMAdapter, C as ChatCompletionRequest, a as CompletionResult } from '../base-tNgbBaSo.mjs';
-export { A as AdapterFactory, l as AnthropicContentBlock, O as OpenAIContentBlock, j as attachmentToAnthropicDocument, i as attachmentToAnthropicImage, k as attachmentToOpenAIImage, f as formatMessages, c as formatMessagesForAnthropic, d as formatMessagesForOpenAI, b as formatTools, h as hasImageAttachments, g as hasMediaAttachments, m as messageToAnthropicContent, e as messageToOpenAIContent } from '../base-tNgbBaSo.mjs';
-import { W as WebSearchConfig, g as StreamEvent } from '../types-BkQCSiIt.mjs';
-import { d as OllamaModelOptions } from '../types-BSSiJW2o.mjs';
+import { L as LLMAdapter, C as ChatCompletionRequest, a as CompletionResult } from '../base-CkeT7u-O.mjs';
+export { A as AdapterFactory, l as AnthropicContentBlock, O as OpenAIContentBlock, j as attachmentToAnthropicDocument, i as attachmentToAnthropicImage, k as attachmentToOpenAIImage, f as formatMessages, c as formatMessagesForAnthropic, d as formatMessagesForOpenAI, b as formatTools, h as hasImageAttachments, g as hasMediaAttachments, m as messageToAnthropicContent, e as messageToOpenAIContent } from '../base-CkeT7u-O.mjs';
+import { a7 as OpenAIParameterOptions, W as WebSearchConfig, g as StreamEvent } from '../types-BW3csYo5.mjs';
+import { d as OllamaModelOptions } from '../types-NOswlhm9.mjs';
 import 'zod';
 
 /**
  * OpenAI adapter configuration
  */
-interface OpenAIAdapterConfig {
+interface OpenAIAdapterConfig extends OpenAIParameterOptions {
+    organization?: string;
+    headers?: Record<string, string>;
     apiKey: string;
     model?: string;
     baseUrl?: string;
@@ -32,11 +34,58 @@ declare class OpenAIAdapter implements LLMAdapter {
     constructor(config: OpenAIAdapterConfig);
     private static resolveProviderName;
     private getClient;
+    private parameterOptions;
+    private toolDefinitions;
     private shouldUseResponsesApi;
+    /**
+     * Convert one message's content to Responses content parts.
+     *
+     * The Responses API does not accept Chat Completions content blocks: input
+     * parts are `input_text` / `input_image` (with a bare `image_url` string)
+     * rather than `text` / `image_url: { url }`. Passing the Chat Completions
+     * shape through unchanged makes the API reject the request, so anything
+     * array-shaped has to be translated rather than forwarded.
+     */
+    private toResponsesContent;
     private buildResponsesInput;
+    /** Preserve Copilot screenshot attachments on every OpenAI transport. */
+    private formatRawMessages;
+    /**
+     * Build the web_search tool for the Responses API, or undefined when web
+     * search is off.
+     *
+     * The Chat Completions path uses `web_search_preview`; the Responses API
+     * names the same built-in `web_search`. Without this, enabling web search
+     * alongside a gpt-5.4+ function tool silently did nothing, because routing
+     * to /v1/responses skipped the Chat Completions tool assembly entirely.
+     */
+    private buildResponsesWebSearchTool;
+    /**
+     * Extract url_citation annotations from Responses output items.
+     *
+     * Annotations hang off the output_text content parts rather than arriving as
+     * their own stream events, so both the streaming and non-streaming paths read
+     * them from the same place.
+     */
+    private collectResponsesCitations;
     private buildResponsesTools;
     private parseResponsesResult;
+    private buildResponsesPayload;
     private completeWithResponses;
+    /**
+     * Stream from /v1/responses as real SSE.
+     *
+     * The Responses API emits semantic events rather than Chat Completions
+     * deltas, so the interesting ones are:
+     *   response.output_text.delta       — incremental assistant text
+     *   response.output_item.added       — a function_call item begins (name/id)
+     *   response.function_call_arguments.delta / .done — tool arguments
+     *   response.completed               — terminal, carries usage
+     *
+     * Tool calls are buffered and flushed as contiguous start→args→end triples
+     * because the runtime pairs action:args with the action:end that follows it.
+     */
+    private streamWithResponses;
     stream(request: ChatCompletionRequest): AsyncGenerator<StreamEvent>;
     complete(request: ChatCompletionRequest): Promise<CompletionResult>;
 }

package/dist/adapters/index.d.ts

@@ -1,13 +1,15 @@
-import { L as LLMAdapter, C as ChatCompletionRequest, a as CompletionResult } from '../base-C58Dsr9p.js';
-export { A as AdapterFactory, l as AnthropicContentBlock, O as OpenAIContentBlock, j as attachmentToAnthropicDocument, i as attachmentToAnthropicImage, k as attachmentToOpenAIImage, f as formatMessages, c as formatMessagesForAnthropic, d as formatMessagesForOpenAI, b as formatTools, h as hasImageAttachments, g as hasMediaAttachments, m as messageToAnthropicContent, e as messageToOpenAIContent } from '../base-C58Dsr9p.js';
-import { W as WebSearchConfig, g as StreamEvent } from '../types-BkQCSiIt.js';
-import { d as OllamaModelOptions } from '../types-BQ31QIsA.js';
+import { L as LLMAdapter, C as ChatCompletionRequest, a as CompletionResult } from '../base-BdTpUAWI.js';
+export { A as AdapterFactory, l as AnthropicContentBlock, O as OpenAIContentBlock, j as attachmentToAnthropicDocument, i as attachmentToAnthropicImage, k as attachmentToOpenAIImage, f as formatMessages, c as formatMessagesForAnthropic, d as formatMessagesForOpenAI, b as formatTools, h as hasImageAttachments, g as hasMediaAttachments, m as messageToAnthropicContent, e as messageToOpenAIContent } from '../base-BdTpUAWI.js';
+import { a7 as OpenAIParameterOptions, W as WebSearchConfig, g as StreamEvent } from '../types-BW3csYo5.js';
+import { d as OllamaModelOptions } from '../types-DA54bSmX.js';
 import 'zod';
 
 /**
  * OpenAI adapter configuration
  */
-interface OpenAIAdapterConfig {
+interface OpenAIAdapterConfig extends OpenAIParameterOptions {
+    organization?: string;
+    headers?: Record<string, string>;
     apiKey: string;
     model?: string;
     baseUrl?: string;
@@ -32,11 +34,58 @@ declare class OpenAIAdapter implements LLMAdapter {
     constructor(config: OpenAIAdapterConfig);
     private static resolveProviderName;
     private getClient;
+    private parameterOptions;
+    private toolDefinitions;
     private shouldUseResponsesApi;
+    /**
+     * Convert one message's content to Responses content parts.
+     *
+     * The Responses API does not accept Chat Completions content blocks: input
+     * parts are `input_text` / `input_image` (with a bare `image_url` string)
+     * rather than `text` / `image_url: { url }`. Passing the Chat Completions
+     * shape through unchanged makes the API reject the request, so anything
+     * array-shaped has to be translated rather than forwarded.
+     */
+    private toResponsesContent;
     private buildResponsesInput;
+    /** Preserve Copilot screenshot attachments on every OpenAI transport. */
+    private formatRawMessages;
+    /**
+     * Build the web_search tool for the Responses API, or undefined when web
+     * search is off.
+     *
+     * The Chat Completions path uses `web_search_preview`; the Responses API
+     * names the same built-in `web_search`. Without this, enabling web search
+     * alongside a gpt-5.4+ function tool silently did nothing, because routing
+     * to /v1/responses skipped the Chat Completions tool assembly entirely.
+     */
+    private buildResponsesWebSearchTool;
+    /**
+     * Extract url_citation annotations from Responses output items.
+     *
+     * Annotations hang off the output_text content parts rather than arriving as
+     * their own stream events, so both the streaming and non-streaming paths read
+     * them from the same place.
+     */
+    private collectResponsesCitations;
     private buildResponsesTools;
     private parseResponsesResult;
+    private buildResponsesPayload;
     private completeWithResponses;
+    /**
+     * Stream from /v1/responses as real SSE.
+     *
+     * The Responses API emits semantic events rather than Chat Completions
+     * deltas, so the interesting ones are:
+     *   response.output_text.delta       — incremental assistant text
+     *   response.output_item.added       — a function_call item begins (name/id)
+     *   response.function_call_arguments.delta / .done — tool arguments
+     *   response.completed               — terminal, carries usage
+     *
+     * Tool calls are buffered and flushed as contiguous start→args→end triples
+     * because the runtime pairs action:args with the action:end that follows it.
+     */
+    private streamWithResponses;
     stream(request: ChatCompletionRequest): AsyncGenerator<StreamEvent>;
     complete(request: ChatCompletionRequest): Promise<CompletionResult>;
 }