@cartanova/qgrid-ai-sdk 2.7.9 → 2.9.0

package/README.ko.md

@@ -12,8 +12,8 @@ AI SDK v6 custom `LanguageModelV3` provider for [qgrid](https://github.com/carta
 +import { qgrid } from "@cartanova/qgrid-ai-sdk";
 
  const { text } = await generateText({
--  model: openai("gpt-5.4-mini"),
-+  model: qgrid("openai/gpt-5.4-mini"),
+-  model: openai("gpt-5.6-luna"),
++  model: qgrid("openai/gpt-5.6-luna"),
    prompt: "서울 날씨 알려줘",
  });
 ```
@@ -43,7 +43,7 @@ import { generateText } from "ai";
 import { qgrid } from "@cartanova/qgrid-ai-sdk";
 
 const { text } = await generateText({
-  model: qgrid("openai/gpt-5.4-mini"),
+  model: qgrid("openai/gpt-5.6-luna"),
   prompt: "서울 날씨 알려줘",
 });
 ```
@@ -62,7 +62,7 @@ import { generateText } from "ai";
 import { qgrid } from "@cartanova/qgrid-ai-sdk";
 
 const { text } = await generateText({
-  model: qgrid("openai/gpt-5.4-mini"),
+  model: qgrid("openai/gpt-5.6-luna"),
   system: "당신은 학술 논문 요약가입니다.",
   prompt: paperText,
 });
@@ -77,7 +77,7 @@ import { qgrid } from "@cartanova/qgrid-ai-sdk";
 import { z } from "zod";
 
 const { output } = await generateText({
-  model: qgrid("openai/gpt-5.4"),
+  model: qgrid("openai/gpt-5.6-terra"),
   system: "논문 메타데이터를 추출해주세요.",
   prompt: paperText,
   output: Output.object({
@@ -104,7 +104,7 @@ import { streamText } from "ai";
 import { qgrid } from "@cartanova/qgrid-ai-sdk";
 
 const { textStream } = streamText({
-  model: qgrid("openai/gpt-5.4-mini"),
+  model: qgrid("openai/gpt-5.6-luna"),
   prompt: "TypeScript의 장점을 설명해줘",
 });
 
@@ -121,7 +121,7 @@ import { qgrid } from "@cartanova/qgrid-ai-sdk";
 import { z } from "zod";
 
 const { text } = await generateText({
-  model: qgrid("openai/gpt-5.4-mini"),
+  model: qgrid("openai/gpt-5.6-luna"),
   prompt: "서울 날씨 알려줘",
   tools: {
     getWeather: tool({
@@ -149,7 +149,7 @@ import { qgrid } from "@cartanova/qgrid-ai-sdk";
 import { z } from "zod";
 
 const { output } = await generateText({
-  model: qgrid("openai/gpt-5.4"),
+  model: qgrid("openai/gpt-5.6-terra"),
   prompt: "서울 날씨를 조회해서 예보를 반환해줘.",
   tools: {
     getWeather: tool({
@@ -187,7 +187,7 @@ import { generateText } from "ai";
 import { qgrid, type QgridProviderOptions } from "@cartanova/qgrid-ai-sdk";
 
 const { text } = await generateText({
-  model: qgrid("openai/gpt-5.4"),
+  model: qgrid("openai/gpt-5.6-terra"),
   prompt: "복잡한 문제를 분석해줘",
   providerOptions: {
     qgrid: {
@@ -201,6 +201,7 @@ const { text } = await generateText({
 
 | 옵션 | 값 | 적용 범위 | 설명 |
 |---|---|---|---|
+| `tokenName` | provider prefix를 포함한 토큰 이름 | 공통 | `anthropic/yds`처럼 활성 토큰 하나를 엄격히 지정. prefix는 model provider와 같아야 하며 빈 값·누락·inactive·quota 초과 시 다른 토큰으로 fallback하지 않음 |
 | `logger` | `boolean` | 공통 | qgrid request log 저장 여부. 기본값은 `true`. `false`로 설정해도 client tool 실행과 multi-step 연결은 계속 동작 |
 | `sessionKey` | `string` | OpenAI 전용 | 전체 history 재전송 시 불투명 prompt-cache affinity를 파생하는 멀티턴 대화 식별자 ([아래](#멀티턴-prompt-cache-sessionkey) 참조) |
 | `effort` | `"none"` \| `"minimal"` \| `"low"` \| `"medium"` \| `"high"` \| `"xhigh"` \| `"max"` | 공통 (지원 값은 모델별 상이, 예: `"max"`는 GPT-5.6+) | reasoning 모델의 추론 깊이. 기본값은 config의 `defaultEffort` (`"low"`) |
@@ -212,6 +213,18 @@ const { text } = await generateText({
 | `imageGenerationOptions` | `{ quality?, size? }` | OpenAI 전용 | 이미지 품질/크기 힌트. `quality: "low" \| "medium" \| "high"`, `size: "1024x1024" \| "1024x1536" \| "1536x1024"` (기본: `medium` / `1536x1024`) |
 | `fallbackModels` | `string[]` | 예약 | 향후 qgrid 서버 fallback routing용 예약 필드. 현재 동작하지 않으며 Claude Code의 Fable refusal fallback과 무관 |
 
+```typescript
+await generateText({
+  model: qgrid("anthropic/claude-fable-5"),
+  prompt,
+  providerOptions: {
+    qgrid: { tokenName: "anthropic/yds" } satisfies QgridProviderOptions,
+  },
+});
+```
+
+`tokenName`은 `streamText`에서도 같은 방식으로 동작합니다.
+
 AI SDK 최상위 `timeout`은 전체 클라이언트 제한시간이며 custom provider 실행 전에
 `AbortSignal`로 변환됩니다. 따라서 그 숫자 자체는 qgrid에 전달되지 않습니다. qgrid 서버의
 Claude Code 프로세스 제한시간을 바꾸려면 `providerOptions.qgrid.timeoutMs`를 사용하세요.
@@ -227,7 +240,7 @@ Anthropic `generateText` 요청에는 전역 설정을 바꾸지 않는 요청
 
 ```typescript
 const { text } = await generateText({
-  model: qgrid("openai/gpt-5.4-mini"),
+  model: qgrid("openai/gpt-5.6-luna"),
   prompt: nextTurnPrompt,
   providerOptions: { qgrid: { sessionKey: "game-session-123" } },
 });
@@ -242,7 +255,7 @@ OpenAI/codex 경로 전용, `generateText` 전용입니다. 해당 요청에만
 
 ```typescript
 const result = await generateText({
-  model: qgrid("openai/gpt-5.4"),
+  model: qgrid("openai/gpt-5.6-terra"),
   prompt: "우주를 나는 고래 일러스트",
   providerOptions: {
     qgrid: {
@@ -259,7 +272,7 @@ const image = result.files[0]; // mediaType: "image/png", base64
 
 ```typescript
 const result = await generateText({
-  model: qgrid("openai/gpt-5.4"),
+  model: qgrid("openai/gpt-5.6-terra"),
   messages: [
     {
       role: "user",
@@ -357,6 +370,7 @@ type QgridSupportedModel =
   | "openai/gpt-5.3-codex"
   | "openai/gpt-5.3-codex-spark"
   // Anthropic
+  | "anthropic/claude-fable-5-1"
   | "anthropic/claude-fable-5"
   | "anthropic/claude-haiku-4-5"
   | "anthropic/claude-sonnet-4"
@@ -373,6 +387,8 @@ type QgridSupportedModel =
   | "anthropic/claude-opus-5"
 ```
 
+`openai/gpt-5.4`, `openai/gpt-5.4-mini`, `openai/gpt-5.2`, `openai/gpt-5.3-codex`는 하위 호환을 위해 타입에 남아 있지만, qgrid가 사용하는 ChatGPT 구독 Codex 경로에서는 더 이상 제공되지 않습니다. `gpt-5.4`와 `gpt-5.4-mini`는 2026-08-31에 retire되었고(대체: `openai/gpt-5.6-terra`, `openai/gpt-5.6-luna`), `gpt-5.2`와 `gpt-5.3-codex`는 그보다 먼저 해당 경로에서 제거되었습니다. 이 id로 요청하면 백엔드에서 실패합니다.
+
 ### GPT-5.6 사양
 
 | 모델 | Context (qgrid OpenAI 경로) | 최대 출력 | 1M tokens당 input / cached input / output |
@@ -385,9 +401,11 @@ type QgridSupportedModel =
 
 `anthropic/claude-fable-5`는 1M context와 128K 최대 출력을 지원합니다. 1M tokens당 표준 단가는 input $10, cache read $1, 5분 cache write $12.50, 1시간 cache write $20, output $50입니다. qgrid는 Claude 응답의 5분/1시간 cache creation breakdown을 보존해 TTL별 단가를 각각 적용하며, breakdown이 없는 구버전 응답에서만 Claude Code가 subscription OAuth 경로에 자동 적용하는 1시간 TTL 단가로 fallback합니다. Fable은 adaptive thinking이 항상 켜져 있어야 하므로 qgrid는 이 모델의 adaptive thinking을 보존합니다.
 
+`anthropic/claude-fable-5-1`(2026-09-01 출시)은 Fable 5와 같은 1M context, 128K 최대 출력, 항상 켜진 adaptive thinking, input $10 / output $50 단가를 공유합니다. cache read만 Fable 5의 $1 대신 1M tokens당 $0.25(input의 0.025x)로 과금되며, cache write는 $12.50(5분)/$20(1시간)으로 같습니다. Fable 5.1의 API 수준 파괴적 변경(forced `tool_choice` 거부, 모델에 귀속된 thinking 블록)은 qgrid에 영향을 주지 않습니다. qgrid는 도구를 끈 Claude Code를 fresh 프로세스로 실행하고 히스토리를 텍스트로 평탄화해 전달하기 때문입니다.
+
 `anthropic/claude-opus-5`는 기본 1M context와 128K 최대 출력을 지원합니다. 1M tokens당 단가는 input $5, cache read $0.50, 5분 cache write $6.25, 1시간 cache write $10, output $25입니다. qgrid는 Opus 5의 기본 adaptive thinking 동작을 유지하고 `effort`로 추론 깊이를 조절합니다. 따라서 `xhigh` 또는 `max` effort에서 허용되지 않는 `thinking: disabled` 조합도 만들지 않습니다.
 
-Claude Code는 Fable의 safety refusal을 Opus 4.8로 자동 재시도할 수 있습니다. 이 경우 AI SDK 응답의 `response.modelId`와 `providerMetadata.qgrid.model`은 실제 serving 모델인 Opus를 가리킵니다. `providerMetadata.qgrid.requestedModel`은 Fable로 유지되고, `providerMetadata.qgrid.modelFallbacks`에 refusal fallback 이력이 담깁니다. 같은 metadata에서 `costSource`와 5분/1시간 cache-write 토큰 분해도 확인할 수 있습니다.
+Claude Code는 Fable의 safety refusal을 다른 Opus 모델로 자동 재시도할 수 있습니다. 현재 CLI는 refusal 카테고리에 따라 Opus 5 또는 Opus 4.8을 고릅니다. 이 경우 AI SDK 응답의 `response.modelId`와 `providerMetadata.qgrid.model`은 실제 serving 모델인 Opus를 가리킵니다. `providerMetadata.qgrid.requestedModel`은 Fable로 유지되고, `providerMetadata.qgrid.modelFallbacks`에 refusal fallback 이력이 담깁니다. 같은 metadata에서 `costSource`와 5분/1시간 cache-write 토큰 분해도 확인할 수 있습니다.
 
 `openai/gpt-5.3-codex-spark`는 아직 token 단가가 확정·공개되지 않은 research preview입니다. 따라서 qgrid는 generic fallback 추정치를 보고하며, 이를 공식 단가로 취급하지 않습니다.
 

package/README.md

@@ -12,8 +12,8 @@ AI SDK v6 custom `LanguageModelV3` provider for [qgrid](https://github.com/carta
 +import { qgrid } from "@cartanova/qgrid-ai-sdk";
 
  const { text } = await generateText({
--  model: openai("gpt-5.4-mini"),
-+  model: qgrid("openai/gpt-5.4-mini"),
+-  model: openai("gpt-5.6-luna"),
++  model: qgrid("openai/gpt-5.6-luna"),
    prompt: "What's the weather in Seoul?",
  });
 ```
@@ -43,7 +43,7 @@ import { generateText } from "ai";
 import { qgrid } from "@cartanova/qgrid-ai-sdk";
 
 const { text } = await generateText({
-  model: qgrid("openai/gpt-5.4-mini"),
+  model: qgrid("openai/gpt-5.6-luna"),
   prompt: "What's the weather in Seoul?",
 });
 ```
@@ -62,7 +62,7 @@ import { generateText } from "ai";
 import { qgrid } from "@cartanova/qgrid-ai-sdk";
 
 const { text } = await generateText({
-  model: qgrid("openai/gpt-5.4-mini"),
+  model: qgrid("openai/gpt-5.6-luna"),
   system: "You are an academic paper summarizer.",
   prompt: paperText,
 });
@@ -77,7 +77,7 @@ import { qgrid } from "@cartanova/qgrid-ai-sdk";
 import { z } from "zod";
 
 const { output } = await generateText({
-  model: qgrid("openai/gpt-5.4"),
+  model: qgrid("openai/gpt-5.6-terra"),
   system: "Extract the paper metadata.",
   prompt: paperText,
   output: Output.object({
@@ -112,7 +112,7 @@ import { streamText } from "ai";
 import { qgrid } from "@cartanova/qgrid-ai-sdk";
 
 const { textStream } = streamText({
-  model: qgrid("openai/gpt-5.4-mini"),
+  model: qgrid("openai/gpt-5.6-luna"),
   prompt: "Explain the benefits of TypeScript",
 });
 
@@ -129,7 +129,7 @@ import { qgrid } from "@cartanova/qgrid-ai-sdk";
 import { z } from "zod";
 
 const { text } = await generateText({
-  model: qgrid("openai/gpt-5.4-mini"),
+  model: qgrid("openai/gpt-5.6-luna"),
   prompt: "What's the weather in Seoul?",
   tools: {
     getWeather: tool({
@@ -157,7 +157,7 @@ import { qgrid } from "@cartanova/qgrid-ai-sdk";
 import { z } from "zod";
 
 const { output } = await generateText({
-  model: qgrid("openai/gpt-5.4"),
+  model: qgrid("openai/gpt-5.6-terra"),
   prompt: "Look up Seoul's weather and return a forecast.",
   tools: {
     getWeather: tool({
@@ -196,7 +196,7 @@ import { generateText } from "ai";
 import { qgrid, type QgridProviderOptions } from "@cartanova/qgrid-ai-sdk";
 
 const { text } = await generateText({
-  model: qgrid("openai/gpt-5.4"),
+  model: qgrid("openai/gpt-5.6-terra"),
   prompt: "Analyze this complex problem",
   providerOptions: {
     qgrid: {
@@ -210,6 +210,7 @@ const { text } = await generateText({
 
 | Option | Values | Applies to | Description |
 |---|---|---|---|
+| `tokenName` | provider-prefixed token name | both providers | Strictly targets one active token, such as `anthropic/yds`. The prefix must match the model provider; empty, missing, inactive, or over-threshold targets fail without fallback |
 | `logger` | `boolean` | both providers | qgrid request logging. Defaults to `true`; `false` disables request-log persistence for this generation without disabling client tools or multi-step continuation |
 | `sessionKey` | `string` | OpenAI only | Multi-turn conversation identifier used to derive opaque prompt-cache affinity while replaying full history (see [below](#multi-turn-prompt-cache-sessionkey)) |
 | `effort` | `"none"` \| `"minimal"` \| `"low"` \| `"medium"` \| `"high"` \| `"xhigh"` \| `"max"` | both providers (supported values are model-dependent, e.g. `"max"` is GPT-5.6+) | Reasoning depth. Defaults to the config's `defaultEffort` (`"low"`) |
@@ -221,6 +222,18 @@ const { text } = await generateText({
 | `imageGenerationOptions` | `{ quality?, size? }` | OpenAI only | Image quality/size hints. `quality: "low" \| "medium" \| "high"`, `size: "1024x1024" \| "1024x1536" \| "1536x1024"` (defaults: `medium` / `1536x1024`) |
 | `fallbackModels` | `string[]` | reserved | Reserved for future qgrid server-side fallback routing. Not functional yet and unrelated to Claude Code's Fable refusal fallback |
 
+```typescript
+await generateText({
+  model: qgrid("anthropic/claude-fable-5"),
+  prompt,
+  providerOptions: {
+    qgrid: { tokenName: "anthropic/yds" } satisfies QgridProviderOptions,
+  },
+});
+```
+
+`tokenName` works the same way with `streamText`.
+
 AI SDK's top-level `timeout` remains the overall client-side budget and is converted to an
 `AbortSignal` before the custom provider runs. It does not expose the numeric timeout to qgrid.
 Use `providerOptions.qgrid.timeoutMs` when the qgrid server's Claude Code process needs a different
@@ -236,7 +249,7 @@ For multi-turn conversations, pass a caller-side domain ID (game session ID, cha
 
 ```typescript
 const { text } = await generateText({
-  model: qgrid("openai/gpt-5.4-mini"),
+  model: qgrid("openai/gpt-5.6-luna"),
   prompt: nextTurnPrompt,
   providerOptions: { qgrid: { sessionKey: "game-session-123" } },
 });
@@ -251,7 +264,7 @@ OpenAI/codex route only, `generateText` only. Enables codex's built-in `image_ge
 
 ```typescript
 const result = await generateText({
-  model: qgrid("openai/gpt-5.4"),
+  model: qgrid("openai/gpt-5.6-terra"),
   prompt: "An illustration of a whale flying through space",
   providerOptions: {
     qgrid: {
@@ -268,7 +281,7 @@ Reference images can be passed through normal AI SDK multimodal message parts:
 
 ```typescript
 const result = await generateText({
-  model: qgrid("openai/gpt-5.4"),
+  model: qgrid("openai/gpt-5.6-terra"),
   messages: [
     {
       role: "user",
@@ -367,6 +380,7 @@ type QgridSupportedModel =
   | "openai/gpt-5.3-codex"
   | "openai/gpt-5.3-codex-spark"
   // Anthropic
+  | "anthropic/claude-fable-5-1"
   | "anthropic/claude-fable-5"
   | "anthropic/claude-haiku-4-5"
   | "anthropic/claude-sonnet-4"
@@ -383,6 +397,8 @@ type QgridSupportedModel =
   | "anthropic/claude-opus-5"
 ```
 
+`openai/gpt-5.4`, `openai/gpt-5.4-mini`, `openai/gpt-5.2`, and `openai/gpt-5.3-codex` remain in the type for backward compatibility, but the ChatGPT-subscription Codex route that qgrid uses no longer serves them. `gpt-5.4` and `gpt-5.4-mini` retired on 2026-08-31 (replacements: `openai/gpt-5.6-terra` and `openai/gpt-5.6-luna`); `gpt-5.2` and `gpt-5.3-codex` were removed from that route earlier. Requests for these ids fail at the backend.
+
 ### GPT-5.6 specifications
 
 | Model | Context (qgrid OpenAI route) | Max output | Input / cached input / output per 1M tokens |
@@ -395,9 +411,11 @@ All GPT-5.6 models support reasoning through `max`. Qgrid retains the observed s
 
 `anthropic/claude-fable-5` has a 1M context window and 128K max output. Its standard prices per 1M tokens are $10 input, $1 cache read, $12.50 five-minute cache write, $20 one-hour cache write, and $50 output. qgrid preserves Claude's 5m/1h cache-creation breakdown and prices each TTL separately; only legacy responses without that breakdown fall back to the one-hour TTL automatically selected by Claude Code on subscription OAuth. Fable requires always-on adaptive thinking, so qgrid preserves adaptive thinking for this model.
 
+`anthropic/claude-fable-5-1` (released 2026-09-01) shares Fable 5's 1M context window, 128K max output, always-on adaptive thinking, and $10 input / $50 output pricing. Its cache reads cost $0.25 per 1M tokens (0.025x the input price) instead of Fable 5's $1; cache writes stay at $12.50 (5m) and $20 (1h). Fable 5.1's API-level breaking changes (forced `tool_choice` rejection, model-bound thinking blocks) do not affect qgrid, which runs Claude Code with tools disabled and replays history as flattened text in a fresh process.
+
 `anthropic/claude-opus-5` has a default 1M context window and 128K max output. Its prices per 1M tokens are $5 input, $0.50 cache read, $6.25 five-minute cache write, $10 one-hour cache write, and $25 output. qgrid keeps Opus 5's default adaptive thinking behavior and uses `effort` to control reasoning depth. This also avoids the invalid `thinking: disabled` combination at `xhigh` or `max` effort.
 
-Claude Code may automatically retry a Fable safety refusal on Opus 4.8. In that case, the AI SDK response's `response.modelId` and `providerMetadata.qgrid.model` identify Opus as the actual serving model. `providerMetadata.qgrid.requestedModel` remains Fable, and `providerMetadata.qgrid.modelFallbacks` contains the refusal fallback history. The metadata also exposes `costSource` and the 5m/1h cache-write token split.
+Claude Code may automatically retry a Fable safety refusal on another Opus model; the current CLI picks Opus 5 or Opus 4.8 by refusal category. In that case, the AI SDK response's `response.modelId` and `providerMetadata.qgrid.model` identify Opus as the actual serving model. `providerMetadata.qgrid.requestedModel` remains Fable, and `providerMetadata.qgrid.modelFallbacks` contains the refusal fallback history. The metadata also exposes `costSource` and the 5m/1h cache-write token split.
 
 `openai/gpt-5.3-codex-spark` remains a research preview without final published per-token rates. qgrid therefore reports its generic fallback estimate rather than presenting that estimate as official pricing.
 

package/dist/index.d.ts

@@ -12,6 +12,10 @@ type QgridProviderConfig = {
  * providerOptions.qgrid 로 전달한다.
  */
 type QgridProviderOptions = {
+  /**
+   * 이 요청을 처리할 활성 qgrid 토큰 이름. provider prefix를 포함해야 하며 다른 토큰으로 fallback하지 않는다.
+   */
+  tokenName?: string;
   /**
    * qgrid request log 저장 여부. 기본값은 true.
    * false여도 client tool 실행과 multi-step 연결은 계속 동작한다.
@@ -58,7 +62,7 @@ type QgridProviderOptions = {
     size?: "1024x1024" | "1024x1536" | "1536x1024";
   };
 };
-type QgridSupportedModel = "openai/gpt-5.6-sol" | "openai/gpt-5.6-terra" | "openai/gpt-5.6-luna" | "openai/gpt-5.5" | "openai/gpt-5.4" | "openai/gpt-5.2" | "openai/gpt-5.4-mini" | "openai/gpt-5.3-codex" | "openai/gpt-5.3-codex-spark" | "anthropic/claude-fable-5" | "anthropic/claude-haiku-4-5" | "anthropic/claude-sonnet-4" | "anthropic/claude-sonnet-4-5" | "anthropic/claude-sonnet-4-6" | "anthropic/claude-sonnet-4-7" | "anthropic/claude-sonnet-5" | "anthropic/claude-opus-4" | "anthropic/claude-opus-4-1" | "anthropic/claude-opus-4-5" | "anthropic/claude-opus-4-6" | "anthropic/claude-opus-4-7" | "anthropic/claude-opus-4-8" | "anthropic/claude-opus-5";
+type QgridSupportedModel = "openai/gpt-5.6-sol" | "openai/gpt-5.6-terra" | "openai/gpt-5.6-luna" | "openai/gpt-5.5" | "openai/gpt-5.4" | "openai/gpt-5.2" | "openai/gpt-5.4-mini" | "openai/gpt-5.3-codex" | "openai/gpt-5.3-codex-spark" | "anthropic/claude-fable-5-1" | "anthropic/claude-fable-5" | "anthropic/claude-haiku-4-5" | "anthropic/claude-sonnet-4" | "anthropic/claude-sonnet-4-5" | "anthropic/claude-sonnet-4-6" | "anthropic/claude-sonnet-4-7" | "anthropic/claude-sonnet-5" | "anthropic/claude-opus-4" | "anthropic/claude-opus-4-1" | "anthropic/claude-opus-4-5" | "anthropic/claude-opus-4-6" | "anthropic/claude-opus-4-7" | "anthropic/claude-opus-4-8" | "anthropic/claude-opus-5";
 type QgridLoggerConfig = {
   /** qgrid 서버 주소. default: process.env.QGRID_URL, 없으면 기본값은 "http://localhost:44900" */
   serverUrl?: string;

package/dist/index.js

@@ -1075,7 +1075,9 @@ function qgridProviderMetadata(data) {
 	} };
 }
 function getQgridProviderOptions(options) {
-	return options.providerOptions?.qgrid ?? {};
+	const qgridOptions = options.providerOptions?.qgrid ?? {};
+	if (qgridOptions.tokenName !== void 0 && qgridOptions.tokenName.trim() === "") throw new Error("qgrid: tokenName must not be empty");
+	return qgridOptions;
 }
 function toAiSdkUsage(usage) {
 	const cacheRead = usage.cache_read_input_tokens;
@@ -1150,6 +1152,7 @@ function qgrid(modelId, config) {
 			const serviceTier = qgridOptions.serviceTier;
 			const timeoutMs = qgridOptions.timeoutMs;
 			const logger = qgridOptions.logger;
+			const tokenName = qgridOptions.tokenName;
 			const imageGenerationOptions = qgridOptions.imageGenerationOptions;
 			if (imageGeneration) assertImageInputFitsJsonTransport(imageUrls);
 			const sessionKey = qgridOptions.sessionKey;
@@ -1184,6 +1187,7 @@ function qgrid(modelId, config) {
 					...projectName ? { projectName } : {},
 					...cacheAffinityKey ? { cacheAffinityKey } : {},
 					...logger === false ? { logger: false } : {},
+					...tokenName ? { tokenName } : {},
 					...runContext ? { runContext } : {},
 					...toolResultsPayload ? { toolResults: toolResultsPayload } : {},
 					...imageGeneration ? { imageGeneration } : {},
@@ -1254,6 +1258,7 @@ function qgrid(modelId, config) {
 			const serviceTier = qgridOptions.serviceTier;
 			const timeoutMs = qgridOptions.timeoutMs;
 			const logger = qgridOptions.logger;
+			const tokenName = qgridOptions.tokenName;
 			if (qgridOptions.imageGeneration) throw new Error("qgrid: imageGeneration is not supported with streamText — use generateText instead.");
 			const { prompt, system, history, droppedImageCount } = extractPromptAndHistory(options.prompt, { includeImages: false });
 			warnDroppedImages(droppedImageCount);
@@ -1287,6 +1292,7 @@ function qgrid(modelId, config) {
 					...projectName ? { projectName } : {},
 					...cacheAffinityKey ? { cacheAffinityKey } : {},
 					...logger === false ? { logger: false } : {},
+					...tokenName ? { tokenName } : {},
 					...runContext ? { runContext } : {},
 					...toolResultsPayload ? { toolResults: toolResultsPayload } : {}
 				} }),

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@cartanova/qgrid-ai-sdk",
-  "version": "2.7.9",
+  "version": "2.9.0",
   "description": "AI SDK LanguageModelV3 provider for qgrid",
   "repository": {
     "type": "git",