desirecore/config-center
2
0
Fork 0
mirror of https://git.openapi.site/https://github.com/desirecore/config-center.git synced 2026-10-21 04:44:26 +08:00
Code Issues Packages Projects Releases Wiki Activity

fix(compute): GLM-5.3 系列在 anthropic 协议按官网用 output_config.effort 控制思考强度 (#120)

Browse Source 
智谱官网（国内 coding-plan/latest-model、国际 devpack/latest-model）写明 /api/anthropic
以 thinking.type 与 output_config.effort 控制思考强度，thinking.type=enabled 一律按默认 max
处理，budget_tokens 不是控制项。两个 anthropic-messages 接入面的 GLM-5.3 系列此前只有按
OpenAI 协议文档写的 low/high/max 矩阵，客户端按 budget 形态发送：low/high 在上游都成了 max，
max（也是默认档）在客户端本机被拒绝；经 new-api 的 OpenAI 类渠道转换时 low 变成
reasoning_effort=medium，被智谱标准 API 拒绝。

- zhipu、zhipu-coding 接入面的 GLM-5.3 / 5.3-Flash / 5.3-FlashX 声明 adaptiveThinking
- GLM-5.3 系列规格加 anthropic-messages 协议 profile（V1 副本为 spec.extra.adaptiveThinking），
  覆盖经 ModelSpec 补全的云端条目
- 来源记录补国际 Coding Plan 页；按量 API Key 与 FlashX 按同一端点推定，未列入已核字段
- presetDataVersion 130
This commit is contained in:
yi-ge
2026-10-05 09:17:43 -07:00
committed by GitHub
parent e8122c1d77
commit 73b278df51
19 changed files with 170 additions and 35 deletions
Download Patch File Download Diff File Expand all files Collapse all files

16
docs/source-gaps/providers/zhipu.md
View File

@@ -49,14 +49,14 @@
| --- | --- | --- | --- |
| [`glm-5.2`](../../model-sources/providers/zhipu/models/glm-5.2.md) | [`compute/providers/zhipu.json`](../../../compute/providers/zhipu.json) | `contextWindow`、`defaultTemperature`、`defaultTopP`、`extra.cacheHitPrice`、`extra.cacheStoragePrice`、`inputPrice`、`maxOutputTokens`、`modelName`、`outputPrice` | [glm52-cn-api](../../model-sources/providers/zhipu/SOURCES.md#glm52-cn-api)：fetched |
| [`glm-5.2`](../../model-sources/providers/zhipu/models/glm-5.2.md) | [`compute/coding-plans/zhipu-coding.json`](../../../compute/coding-plans/zhipu-coding.json) | `contextWindow`、`maxOutputTokens`、`modelName` | [glm52-intl-api](../../model-sources/providers/zhipu/SOURCES.md#glm52-intl-api)：fetched |
| [`glm-5.3-flash`](../../model-sources/providers/zhipu/models/glm-5.3-flash.md) | [`compute/providers/zhipu.json`](../../../compute/providers/zhipu.json) | `contextWindow`、`defaultTemperature`、`defaultTopP`、`maxOutputTokens` | [glm-pricing](../../model-sources/providers/zhipu/SOURCES.md#glm-pricing)：fetched；[glm53-flash](../../model-sources/providers/zhipu/SOURCES.md#glm53-flash)：fetched |
| [`glm-5.3-flash`](../../model-sources/providers/zhipu/models/glm-5.3-flash.md) | [`compute/coding-plans/zhipu-coding.json`](../../../compute/coding-plans/zhipu-coding.json) | `contextWindow`、`defaultTemperature`、`defaultTopP`、`maxOutputTokens` | [glm53-flash](../../model-sources/providers/zhipu/SOURCES.md#glm53-flash)：fetched |
| [`glm-5.3-flash`](../../model-sources/providers/zhipu/models/glm-5.3-flash.md) | [`compute/model-specs/zhipu.json`](../../../compute/model-specs/zhipu.json) | `spec.contextWindow`、`spec.defaultTemperature`、`spec.defaultTopP`、`spec.maxOutputTokens`、`spec.supportsReasoning` | [glm53-flash](../../model-sources/providers/zhipu/SOURCES.md#glm53-flash)：fetched |
| [`glm-5.3-flashx`](../../model-sources/providers/zhipu/models/glm-5.3-flashx.md) | [`compute/providers/zhipu.json`](../../../compute/providers/zhipu.json) | `contextWindow`、`maxOutputTokens` | [glm-pricing](../../model-sources/providers/zhipu/SOURCES.md#glm-pricing)：fetched；[glm53-flash](../../model-sources/providers/zhipu/SOURCES.md#glm53-flash)：fetched |
| [`glm-5.3-flashx`](../../model-sources/providers/zhipu/models/glm-5.3-flashx.md) | [`compute/model-specs/zhipu.json`](../../../compute/model-specs/zhipu.json) | `spec.contextWindow`、`spec.maxOutputTokens`、`spec.supportsReasoning` | [glm53-flash](../../model-sources/providers/zhipu/SOURCES.md#glm53-flash)：fetched |
| [`glm-5.3`](../../model-sources/providers/zhipu/models/glm-5.3.md) | [`compute/providers/zhipu.json`](../../../compute/providers/zhipu.json) | `contextWindow`、`defaultTemperature`、`defaultTopP`、`maxOutputTokens` | [glm-pricing](../../model-sources/providers/zhipu/SOURCES.md#glm-pricing)：fetched；[glm53](../../model-sources/providers/zhipu/SOURCES.md#glm53)：fetched |
| [`glm-5.3`](../../model-sources/providers/zhipu/models/glm-5.3.md) | [`compute/coding-plans/zhipu-coding.json`](../../../compute/coding-plans/zhipu-coding.json) | `contextWindow`、`defaultTemperature`、`defaultTopP`、`maxOutputTokens` | [glm53](../../model-sources/providers/zhipu/SOURCES.md#glm53)：fetched |
| [`glm-5.3`](../../model-sources/providers/zhipu/models/glm-5.3.md) | [`compute/model-specs/zhipu.json`](../../../compute/model-specs/zhipu.json) | `spec.contextWindow`、`spec.defaultTemperature`、`spec.defaultTopP`、`spec.maxOutputTokens`、`spec.supportsReasoning` | [glm53](../../model-sources/providers/zhipu/SOURCES.md#glm53)：fetched |
| [`glm-5.3-flash`](../../model-sources/providers/zhipu/models/glm-5.3-flash.md) | [`compute/providers/zhipu.json`](../../../compute/providers/zhipu.json) | `contextWindow`、`defaultTemperature`、`defaultTopP`、`extra.adaptiveThinking`、`maxOutputTokens` | [glm-pricing](../../model-sources/providers/zhipu/SOURCES.md#glm-pricing)：fetched；[glm53-flash](../../model-sources/providers/zhipu/SOURCES.md#glm53-flash)：fetched |
| [`glm-5.3-flash`](../../model-sources/providers/zhipu/models/glm-5.3-flash.md) | [`compute/coding-plans/zhipu-coding.json`](../../../compute/coding-plans/zhipu-coding.json) | `contextWindow`、`defaultTemperature`、`defaultTopP`、`maxOutputTokens` | [glm-plan-intl](../../model-sources/providers/zhipu/SOURCES.md#glm-plan-intl)：fetched；[glm53-flash](../../model-sources/providers/zhipu/SOURCES.md#glm53-flash)：fetched |
| [`glm-5.3-flash`](../../model-sources/providers/zhipu/models/glm-5.3-flash.md) | [`compute/model-specs/zhipu.json`](../../../compute/model-specs/zhipu.json) | `spec.contextWindow`、`spec.defaultTemperature`、`spec.defaultTopP`、`spec.maxOutputTokens`、`spec.supportsReasoning` | [glm-plan](../../model-sources/providers/zhipu/SOURCES.md#glm-plan)：fetched；[glm53-flash](../../model-sources/providers/zhipu/SOURCES.md#glm53-flash)：fetched |
| [`glm-5.3-flashx`](../../model-sources/providers/zhipu/models/glm-5.3-flashx.md) | [`compute/providers/zhipu.json`](../../../compute/providers/zhipu.json) | `contextWindow`、`extra.adaptiveThinking`、`maxOutputTokens` | [glm-pricing](../../model-sources/providers/zhipu/SOURCES.md#glm-pricing)：fetched；[glm53-flash](../../model-sources/providers/zhipu/SOURCES.md#glm53-flash)：fetched |
| [`glm-5.3-flashx`](../../model-sources/providers/zhipu/models/glm-5.3-flashx.md) | [`compute/model-specs/zhipu.json`](../../../compute/model-specs/zhipu.json) | `spec.contextWindow`、`spec.extra.adaptiveThinking`、`spec.maxOutputTokens`、`spec.supportsReasoning` | [glm53-flash](../../model-sources/providers/zhipu/SOURCES.md#glm53-flash)：fetched |
| [`glm-5.3`](../../model-sources/providers/zhipu/models/glm-5.3.md) | [`compute/providers/zhipu.json`](../../../compute/providers/zhipu.json) | `contextWindow`、`defaultTemperature`、`defaultTopP`、`extra.adaptiveThinking`、`maxOutputTokens` | [glm-pricing](../../model-sources/providers/zhipu/SOURCES.md#glm-pricing)：fetched；[glm53](../../model-sources/providers/zhipu/SOURCES.md#glm53)：fetched |
| [`glm-5.3`](../../model-sources/providers/zhipu/models/glm-5.3.md) | [`compute/coding-plans/zhipu-coding.json`](../../../compute/coding-plans/zhipu-coding.json) | `contextWindow`、`defaultTemperature`、`defaultTopP`、`maxOutputTokens` | [glm-plan-intl](../../model-sources/providers/zhipu/SOURCES.md#glm-plan-intl)：fetched；[glm53](../../model-sources/providers/zhipu/SOURCES.md#glm53)：fetched |
| [`glm-5.3`](../../model-sources/providers/zhipu/models/glm-5.3.md) | [`compute/model-specs/zhipu.json`](../../../compute/model-specs/zhipu.json) | `spec.contextWindow`、`spec.defaultTemperature`、`spec.defaultTopP`、`spec.maxOutputTokens`、`spec.supportsReasoning` | [glm-plan](../../model-sources/providers/zhipu/SOURCES.md#glm-plan)：fetched；[glm53](../../model-sources/providers/zhipu/SOURCES.md#glm53)：fetched |
## 历史身份/参数不证明当前可用性（0 条）