@cartanova/qgrid-ai-sdk 2.14.1 → 2.15.1

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (4) hide show
  1. package/README.ko.md +6 -4
  2. package/README.md +6 -4
  3. package/dist/index.d.ts +1 -1
  4. package/package.json +1 -1
package/README.ko.md CHANGED
@@ -207,7 +207,7 @@ const { text } = await generateText({
207
207
  | `logger` | `boolean` | 공통 | qgrid request log 저장 여부. 기본값은 `true`. `false`로 설정해도 client tool 실행과 multi-step 연결은 계속 동작 |
208
208
  | `sessionKey` | `string` | OpenAI 전용 | 전체 history 재전송 시 불투명 prompt-cache affinity를 파생하는 멀티턴 대화 식별자 ([아래](#멀티턴-prompt-cache-sessionkey) 참조) |
209
209
  | `thinking` | `boolean` | 공통 | 생략하면 기존 모델별 동작 유지. `true`는 effort로 깊이를 조절하고, `false`는 요청 effort와 config `defaultEffort`를 무시. 모델·실행 경로 미지원 시 오류 |
210
- | `effort` | OpenAI: `"low"` \| `"medium"` \| `"high"` \| `"xhigh"` \| `"max"` \| `"ultra"` | OpenAI 전용 (`QgridOpenAIProviderOptions`) | ChatGPT 구독 Codex 경로의 reasoning 깊이. GPT-6 Astra/Sol과 GPT-5.6 Sol/Terra는 `"ultra"`까지, GPT-6 Luna와 GPT-5.6 Luna는 `"max"`까지 지원하며, 모델이 지원하지 않는 값은 서버가 조용히 무시하고 백엔드 기본값을 적용. `"none"`/`"minimal"`은 공개 effort 값이 아니며 thinking 비활성화에는 `thinking: false`를 사용 |
210
+ | `effort` | OpenAI: `"low"` \| `"medium"` \| `"high"` \| `"xhigh"` \| `"max"` \| `"ultra"` | OpenAI 전용 (`QgridOpenAIProviderOptions`) | ChatGPT 구독 Codex 경로의 reasoning 깊이. GPT-6 Astra, GPT-6/6.1 Sol, GPT-6.1 Terra, GPT-5.6 Sol/Terra는 `"ultra"`까지 지원하되 qgrid는 `"ultra"`를 백엔드에 `"max"`로 보내며(Codex의 ultra는 qgrid가 실행하지 않는 하위 에이전트 위임을 포함), GPT-6 Luna와 GPT-5.6 Luna는 `"max"`까지 지원하며, 모델이 지원하지 않는 값은 서버가 조용히 무시하고 백엔드 기본값을 적용. `"none"`/`"minimal"`은 공개 effort 값이 아니며 thinking 비활성화에는 `thinking: false`를 사용 |
211
211
  | `effort` | Anthropic: `"low"` \| `"medium"` \| `"high"` \| `"xhigh"` \| `"max"` | Anthropic 전용 (`QgridAnthropicProviderOptions`) | Claude Code `--effort` 허용값. 집합 밖의 값은 서버가 조용히 무시하고 qgrid 기본(`"low"`)을 적용. 모델별 상한(예: Sonnet 4.6은 `"xhigh"` 없음)은 Claude Code가 처리 |
212
212
  | `verbosity` | `"low"` \| `"medium"` \| `"high"` | OpenAI 전용 | 응답 텍스트의 상세도 |
213
213
  | `reasoningSummary` | `"auto"` \| `"concise"` \| `"detailed"` \| `"none"` | OpenAI 전용 | 추론 요약 출력 방식 |
@@ -239,7 +239,7 @@ Thinking 비활성화 정책 스냅샷(2026-10-10, Claude Code 조사 기준 2.1
239
239
 
240
240
  | Provider | 현재 정책에서 off를 허용하는 모델 ID |
241
241
  | --- | --- |
242
- | OpenAI | `gpt-6-sol`, `gpt-6-luna`, `gpt-5.6-sol`, `gpt-5.6-terra`, `gpt-5.6-luna`, `gpt-5.5` |
242
+ | OpenAI | `gpt-6.1-terra`, `gpt-6-sol`, `gpt-6-luna`, `gpt-5.6-sol`, `gpt-5.6-terra`, `gpt-5.6-luna`, `gpt-5.5` |
243
243
  | Anthropic | `claude-haiku-5-5`, `claude-sonnet-5-5`, `claude-haiku-4-5`, `claude-sonnet-4-5`, `claude-sonnet-4-6`, `claude-sonnet-5`, `claude-opus-4-5`, `claude-opus-4-6`, `claude-opus-4-7`, `claude-opus-4-8`, `claude-opus-5` |
244
244
 
245
245
  위 ID에 평소처럼 `openai/` 또는 `anthropic/` prefix를 붙입니다. 백엔드가 명시적으로 거부한 모델은 `gpt-6-astra`, `gpt-6.1-sol`, `claude-fable-5`, `claude-fable-5-1`, `claude-opus-5-5`입니다. Haiku 5.5와 Sonnet 5.5의 네이티브 전달은 Claude Code 2.1.295에서 검증했습니다. off 요청에서 서버는 CLI 버전을 확인하며 2.1.295 미만이거나 확인할 수 없으면 입력 오류를 반환합니다. 나머지 모델도 off 미확인으로 구분하며 모델 접근 실패를 thinking 강제의 근거로 보지 않습니다. 이 제한은 명시적 false에만 적용됩니다.
@@ -561,6 +561,7 @@ type QgridSupportedModel =
561
561
  // OpenAI (direct private Codex Responses backend)
562
562
  | "openai/gpt-6-astra"
563
563
  | "openai/gpt-6.1-sol"
564
+ | "openai/gpt-6.1-terra"
564
565
  | "openai/gpt-6-sol"
565
566
  | "openai/gpt-6-luna"
566
567
  | "openai/gpt-5.6-sol"
@@ -600,11 +601,12 @@ type QgridSupportedModel =
600
601
  | 모델 | Context (Codex 카탈로그) | 최대 출력 (공개 API) | 1M tokens당 input / cached input / cache write / output |
601
602
  | --- | ---: | ---: | ---: |
602
603
  | `openai/gpt-6-astra` | 272K | 128K | $10 / $1 / $12.50 / $50 |
603
- | `openai/gpt-6.1-sol` | 272K | 128K | $2 / $0.10 / $2.50 / $10 |
604
+ | `openai/gpt-6.1-sol` | 500K | 128K | $2 / $0.10 / $2.50 / $10 |
605
+ | `openai/gpt-6.1-terra` | 500K | 128K | $1 / $0.05 / $1.25 / $5 |
604
606
  | `openai/gpt-6-sol` | 272K | 128K | $2 / $0.20 / $2.50 / $10 |
605
607
  | `openai/gpt-6-luna` | 272K | 128K | $0.10 / $0.01 / $0.125 / $0.50 |
606
608
 
607
- 2026-09-23에 조회한 Codex 카탈로그는 Astra, Sol, Luna 모두 272K context window를 제공합니다. Astra와 Sol은 `ultra`까지, Luna는 `max`까지 reasoning effort를 지원합니다. 백엔드 기본값은 세 모델 모두 `medium`이며, qgrid SDK의 기본값은 기존대로 `low`이니 다른 깊이가 필요하면 effort를 명시하세요. [Astra](https://developers.openai.com/api/docs/models/gpt-6-astra), [Sol](https://developers.openai.com/api/docs/models/gpt-6-sol), [Luna](https://developers.openai.com/api/docs/models/gpt-6-luna)의 공개 API 문서는 별도로 1.05M context, 최대 입력 922K, 최대 출력 128K와 `max`까지의 effort를 명시하며 `ultra`는 포함하지 않습니다. 이 공개 API 한도를 구독 경로의 한도로 간주하지 않습니다. Qgrid 비용 추정에는 [표준 API 단가](https://developers.openai.com/api/docs/pricing)를 사용합니다. Cache write는 uncached input 단가의 1.25x이며, 입력이 272K tokens를 넘으면 요청 전체에 input/cache 2x, output 1.5x 단가가 적용됩니다. GPT-6 Sol과 Luna(2026-09-22 출시)는 GPT-5.6 Sol/Luna의 절반 단가이며, 기존 모델 단가는 2026-09-23에 재확인했고 변동이 없습니다. [GPT-6.1 Sol](https://developers.openai.com/api/docs/models/gpt-6.1-sol)(2026-09-29 출시)은 GPT-6 Sol과 단가가 같고 cached input만 $0.10입니다. 2026-09-30에 조회한 Codex 카탈로그는 272K context window, `ultra`까지의 effort, 백엔드 기본값 `low`를 명시하며, 같은 날 qgrid 요청 형태로 라이브 생성에 성공했습니다. `openai/gpt-5.5`는 2026-10-14에 Codex/ChatGPT 경로에서 은퇴하므로 `openai/gpt-6.1-sol` 또는 `openai/gpt-6-luna`로 옮기세요.
609
+ 2026-09-23에 조회한 Codex 카탈로그는 Astra, Sol, Luna 모두 272K context window를 제공합니다. Astra와 Sol은 `ultra`까지, Luna는 `max`까지 reasoning effort를 지원합니다. 백엔드 기본값은 세 모델 모두 `medium`이며, qgrid SDK의 기본값은 기존대로 `low`이니 다른 깊이가 필요하면 effort를 명시하세요. [Astra](https://developers.openai.com/api/docs/models/gpt-6-astra), [Sol](https://developers.openai.com/api/docs/models/gpt-6-sol), [Luna](https://developers.openai.com/api/docs/models/gpt-6-luna)의 공개 API 문서는 별도로 1.05M context, 최대 입력 922K, 최대 출력 128K와 `max`까지의 effort를 명시하며 `ultra`는 포함하지 않습니다. 이 공개 API 한도를 구독 경로의 한도로 간주하지 않습니다. Qgrid 비용 추정에는 [표준 API 단가](https://developers.openai.com/api/docs/pricing)를 사용합니다. Cache write는 uncached input 단가의 1.25x이며, 입력이 272K tokens를 넘으면 요청 전체에 input/cache 2x, output 1.5x 단가가 적용됩니다. GPT-6 Sol과 Luna(2026-09-22 출시)는 GPT-5.6 Sol/Luna의 절반 단가이며, 기존 모델 단가는 2026-09-23에 재확인했고 변동이 없습니다. [GPT-6.1 Sol](https://developers.openai.com/api/docs/models/gpt-6.1-sol)(2026-09-29 출시)은 GPT-6 Sol과 단가가 같고 cached input만 $0.10입니다. 2026-09-30에 조회한 Codex 카탈로그는 272K context window, `ultra`까지의 effort, 백엔드 기본값 `low`를 명시하며, 같은 날 qgrid 요청 형태로 라이브 생성에 성공했습니다. [GPT-6.1 Terra](https://developers.openai.com/api/docs/models/gpt-6.1-terra)(2026-10-26 출시)는 GPT-6.1 Sol의 정확히 절반 단가($1 / $0.05 / $1.25 / $5)이며 272K 할증 배율은 같습니다. 2026-10-27에 조회한 Codex 카탈로그는 500K context window, `ultra`까지의 effort, 백엔드 기본값 `low`를 명시하며, 같은 날 qgrid 경로로 라이브 생성, structured output, thinking off에 성공했습니다. 같은 카탈로그에서 GPT-6.1 Sol의 context window도 500K로 바뀌었습니다. `openai/gpt-5.5`는 2026-10-14에 Codex/ChatGPT 경로에서 은퇴하므로 `openai/gpt-6.1-sol` 또는 `openai/gpt-6-luna`로 옮기세요.
608
610
 
609
611
  ### GPT-5.6 사양
610
612
 
package/README.md CHANGED
@@ -216,7 +216,7 @@ const { text } = await generateText({
216
216
  | `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 |
217
217
  | `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)) |
218
218
  | `thinking` | `boolean` | Both providers | Omit to preserve existing model behavior. `true` enables thinking with effort; `false` ignores request effort and config `defaultEffort`. Unsupported models or runtimes return an error |
219
- | `effort` | OpenAI: `"low"` \| `"medium"` \| `"high"` \| `"xhigh"` \| `"max"` \| `"ultra"` | OpenAI only (`QgridOpenAIProviderOptions`) | Reasoning depth on the ChatGPT-subscription Codex route. GPT-6 Astra, GPT-6 Sol, and GPT-5.6 Sol/Terra support effort through `"ultra"`; GPT-6 Luna and GPT-5.6 Luna support it through `"max"`; a value the model does not support is silently ignored by the server and the backend default applies. `"none"`/`"minimal"` are not public effort values; use `thinking: false` to disable thinking |
219
+ | `effort` | OpenAI: `"low"` \| `"medium"` \| `"high"` \| `"xhigh"` \| `"max"` \| `"ultra"` | OpenAI only (`QgridOpenAIProviderOptions`) | Reasoning depth on the ChatGPT-subscription Codex route. GPT-6 Astra, GPT-6/6.1 Sol, GPT-6.1 Terra, and GPT-5.6 Sol/Terra support effort through `"ultra"`, which qgrid sends to the backend as `"max"` (Codex's ultra adds sub-agent delegation that qgrid does not run); GPT-6 Luna and GPT-5.6 Luna support it through `"max"`; a value the model does not support is silently ignored by the server and the backend default applies. `"none"`/`"minimal"` are not public effort values; use `thinking: false` to disable thinking |
220
220
  | `effort` | Anthropic: `"low"` \| `"medium"` \| `"high"` \| `"xhigh"` \| `"max"` | Anthropic only (`QgridAnthropicProviderOptions`) | Claude Code `--effort` levels. Values outside this set are silently ignored and qgrid's default (`"low"`) applies; per-model limits (for example no `"xhigh"` on Sonnet 4.6) are handled by Claude Code |
221
221
  | `verbosity` | `"low"` \| `"medium"` \| `"high"` | OpenAI only | Response text verbosity |
222
222
  | `reasoningSummary` | `"auto"` \| `"concise"` \| `"detailed"` \| `"none"` | OpenAI only | Reasoning summary output mode |
@@ -248,7 +248,7 @@ Thinking-off policy snapshot (2026-10-10; Claude Code investigation baseline 2.1
248
248
 
249
249
  | Provider | Off-capable model IDs in the current policy |
250
250
  | --- | --- |
251
- | OpenAI | `gpt-6-sol`, `gpt-6-luna`, `gpt-5.6-sol`, `gpt-5.6-terra`, `gpt-5.6-luna`, `gpt-5.5` |
251
+ | OpenAI | `gpt-6.1-terra`, `gpt-6-sol`, `gpt-6-luna`, `gpt-5.6-sol`, `gpt-5.6-terra`, `gpt-5.6-luna`, `gpt-5.5` |
252
252
  | Anthropic | `claude-haiku-5-5`, `claude-sonnet-5-5`, `claude-haiku-4-5`, `claude-sonnet-4-5`, `claude-sonnet-4-6`, `claude-sonnet-5`, `claude-opus-4-5`, `claude-opus-4-6`, `claude-opus-4-7`, `claude-opus-4-8`, `claude-opus-5` |
253
253
 
254
254
  Use the usual `openai/` or `anthropic/` prefix with these IDs. Explicitly rejected by the backend: `gpt-6-astra`, `gpt-6.1-sol`, `claude-fable-5`, `claude-fable-5-1`, and `claude-opus-5-5`. Native delivery for Haiku 5.5 and Sonnet 5.5 was verified with Claude Code 2.1.295. For their off requests, the server checks the CLI version and returns an input error if it is older than 2.1.295 or cannot be determined. Other model IDs are unverified for off; model-access failures do not prove mandatory thinking. These restrictions apply only to explicit false.
@@ -574,6 +574,7 @@ type QgridSupportedModel =
574
574
  // OpenAI (direct private Codex Responses backend)
575
575
  | "openai/gpt-6-astra"
576
576
  | "openai/gpt-6.1-sol"
577
+ | "openai/gpt-6.1-terra"
577
578
  | "openai/gpt-6-sol"
578
579
  | "openai/gpt-6-luna"
579
580
  | "openai/gpt-5.6-sol"
@@ -613,11 +614,12 @@ type QgridSupportedModel =
613
614
  | Model | Context (Codex catalog) | Max output (public API) | Input / cached input / cache write / output per 1M tokens |
614
615
  | --- | ---: | ---: | ---: |
615
616
  | `openai/gpt-6-astra` | 272K | 128K | $10 / $1 / $12.50 / $50 |
616
- | `openai/gpt-6.1-sol` | 272K | 128K | $2 / $0.10 / $2.50 / $10 |
617
+ | `openai/gpt-6.1-sol` | 500K | 128K | $2 / $0.10 / $2.50 / $10 |
618
+ | `openai/gpt-6.1-terra` | 500K | 128K | $1 / $0.05 / $1.25 / $5 |
617
619
  | `openai/gpt-6-sol` | 272K | 128K | $2 / $0.20 / $2.50 / $10 |
618
620
  | `openai/gpt-6-luna` | 272K | 128K | $0.10 / $0.01 / $0.125 / $0.50 |
619
621
 
620
- The Codex catalog fetched on 2026-09-23 advertises a 272K context window for Astra, Sol, and Luna. Astra and Sol support reasoning effort through `ultra`; Luna supports it through `max`. The backend default is `medium` for all three, while qgrid's SDK defaults to `low`; select an effort explicitly to override it. The public API model pages for [Astra](https://developers.openai.com/api/docs/models/gpt-6-astra), [Sol](https://developers.openai.com/api/docs/models/gpt-6-sol), and [Luna](https://developers.openai.com/api/docs/models/gpt-6-luna) separately list a 1.05M context window, 922K maximum input, 128K maximum output, and reasoning effort through `max` (no `ultra`). Those public limits do not establish the subscription route's limits. [Standard API pricing](https://developers.openai.com/api/docs/pricing) is used for qgrid's cost estimate: cache writes cost 1.25x the uncached input rate, and input over 272K tokens applies 2x input/cache and 1.5x output rates to the full request. GPT-6 Sol and Luna (released 2026-09-22) are priced at half of GPT-5.6 Sol and Luna; existing model prices were re-verified on 2026-09-23 and did not change. [GPT-6.1 Sol](https://developers.openai.com/api/docs/models/gpt-6.1-sol) (released 2026-09-29) keeps GPT-6 Sol's prices except cached input at $0.10; the Codex catalog fetched on 2026-09-30 lists a 272K context window, effort through `ultra`, and a `low` backend default, and a live generation through qgrid's request shape succeeded the same day. `openai/gpt-5.5` retires from the Codex/ChatGPT route on 2026-10-14; migrate to `openai/gpt-6.1-sol` or `openai/gpt-6-luna`.
622
+ The Codex catalog fetched on 2026-09-23 advertises a 272K context window for Astra, Sol, and Luna. Astra and Sol support reasoning effort through `ultra`; Luna supports it through `max`. The backend default is `medium` for all three, while qgrid's SDK defaults to `low`; select an effort explicitly to override it. The public API model pages for [Astra](https://developers.openai.com/api/docs/models/gpt-6-astra), [Sol](https://developers.openai.com/api/docs/models/gpt-6-sol), and [Luna](https://developers.openai.com/api/docs/models/gpt-6-luna) separately list a 1.05M context window, 922K maximum input, 128K maximum output, and reasoning effort through `max` (no `ultra`). Those public limits do not establish the subscription route's limits. [Standard API pricing](https://developers.openai.com/api/docs/pricing) is used for qgrid's cost estimate: cache writes cost 1.25x the uncached input rate, and input over 272K tokens applies 2x input/cache and 1.5x output rates to the full request. GPT-6 Sol and Luna (released 2026-09-22) are priced at half of GPT-5.6 Sol and Luna; existing model prices were re-verified on 2026-09-23 and did not change. [GPT-6.1 Sol](https://developers.openai.com/api/docs/models/gpt-6.1-sol) (released 2026-09-29) keeps GPT-6 Sol's prices except cached input at $0.10; the Codex catalog fetched on 2026-09-30 lists a 272K context window, effort through `ultra`, and a `low` backend default, and a live generation through qgrid's request shape succeeded the same day. [GPT-6.1 Terra](https://developers.openai.com/api/docs/models/gpt-6.1-terra) (released 2026-10-26) costs exactly half of GPT-6.1 Sol ($1 / $0.05 / $1.25 / $5) with the same 272K multipliers; the Codex catalog fetched on 2026-10-27 lists a 500K context window, effort through `ultra`, and a `low` backend default, and live generation, structured output, and thinking off succeeded through qgrid the same day. The same catalog now lists a 500K context window for GPT-6.1 Sol as well. `openai/gpt-5.5` retires from the Codex/ChatGPT route on 2026-10-14; migrate to `openai/gpt-6.1-sol` or `openai/gpt-6-luna`.
621
623
 
622
624
  ### GPT-5.6 specifications
623
625
 
package/dist/index.d.ts CHANGED
@@ -164,7 +164,7 @@ declare const qgridXaiProviderOptionsSchema: z.ZodObject<{
164
164
  }>>>>;
165
165
  }, z.core.$strip>;
166
166
  type QgridXaiProviderOptions = z.infer<typeof qgridXaiProviderOptionsSchema>;
167
- type QgridSupportedModel = "openai/gpt-6-astra" | "openai/gpt-6.1-sol" | "openai/gpt-6-sol" | "openai/gpt-6-luna" | "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" | "anthropic/claude-opus-5-5" | "anthropic/claude-sonnet-5-5" | "anthropic/claude-haiku-5-5" | QgridGrokModel;
167
+ type QgridSupportedModel = "openai/gpt-6-astra" | "openai/gpt-6.1-sol" | "openai/gpt-6.1-terra" | "openai/gpt-6-sol" | "openai/gpt-6-luna" | "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" | "anthropic/claude-opus-5-5" | "anthropic/claude-sonnet-5-5" | "anthropic/claude-haiku-5-5" | QgridGrokModel;
168
168
  /** Observed image response values. Usage is response-level and appears on the first image only. */
169
169
  type QgridImageGenerationMetadata = {
170
170
  route: "codex-images" | "codex-responses";
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@cartanova/qgrid-ai-sdk",
3
- "version": "2.14.1",
3
+ "version": "2.15.1",
4
4
  "description": "AI SDK LanguageModelV3 and ImageModelV3 provider for qgrid",
5
5
  "repository": {
6
6
  "type": "git",