Commit Graph

110 Commits

Author SHA1 Message Date
Johnson-LYS
29ef625f32 fix(compute): match MiMo V2.5 ASR exactly (#61)
Co-authored-by: DesireCore CI <ci@desirecore.test>
2026-07-20 17:29:05 +08:00
523e667b40 fix(compute): enforce reasoning effort boundaries (#60) 2026-07-19 21:47:10 +08:00
55999ce633 feat(compute): declare GPT-5.6 reasoning efforts (#59)
Declare model-level reasoning effort capabilities for GPT-5.6 Sol, Terra, and Luna, extend validation schema, and bump preset data version.
2026-07-19 20:58:00 +08:00
d5d0dfafbd fix(compute): Codex displayName 去掉冗余 (订阅) 后缀 (#58)
* fix(compute): Codex 模型 displayName 去掉多余的"(订阅)"后缀

整个 openai-codex provider 就是 ChatGPT 订阅接入,displayName 上
逐个标注"(订阅)"是冗余信息,用户在 provider 层面已经清楚。

* chore(manifest): bump presetDataVersion 74 -> 75
2026-07-19 17:46:40 +08:00
97bde1fe00 feat(compute): Codex 补充 GPT-5.6 家族并下线三个已停用 -codex 模型 (#57)
* feat(compute): Codex 订阅接入补充 GPT-5.6 家族并下线三个已停用 -codex 模型

新增 gpt-5.6-sol/terra/luna(2026-07-09 发布)、gpt-5.4-mini、
gpt-5.3-codex-spark(ChatGPT Pro 专属研究预览);将已从 ChatGPT 订阅接入
下线的 gpt-5.3-codex/gpt-5.2-codex/gpt-5.1-codex-mini 移入 tombstones。
presetDataVersion 73 -> 74。

* fix(compute): 补全 Luna 的 reasoning 与 Spark 的 tool_use 能力标签

采纳 Codex review 意见:GPT-5.6 Luna 官方文档确认支持 reasoning token;
GPT-5.3 Codex Spark 官方公告确认可做代码编辑、按需运行测试,属于 tool_use。
2026-07-19 15:30:16 +08:00
ce1a936284 fix: restore provider-based pricing currencies (#56)
Restore MiniMax domestic CNY pricing and enforce provider-based currency classification.
2026-07-13 16:16:03 +08:00
5a9b9c87c4 fix: align DeepSeek V4 model specs with official profile
Align the shared DeepSeek V4 Pro and Flash specifications with the official 1M context, 384K output, and high/max reasoning profile. Consolidate duplicate specs, add regression coverage, and bump presetDataVersion to 72.
2026-07-10 11:47:40 +08:00
6d7a3a70c3 feat(schemas): provider 加可选 requiredClientVersion 字段 + 向后兼容规约 (#54)
配合 desirecore #1038 的 provider 级版本门槛:新凭据源/新能力 provider 必须
声明最低客户端版本,≥#1038 的客户端据此优雅门控为「需更新客户端」。
带 pattern 收紧格式(客户端 schema 端故意开放 string + fail-open,源头把关
放这里)。CLAUDE.md 补充「enum 扩值 vs 新增可选字段」的风险区别与推送时序规约。
2026-07-09 18:25:16 +08:00
Johnson-LYS
0349473fd4 feat: add Seedance video generation models to volcengine (#53)
- Add 6 Seedance models: 2.0/2.0-fast/2.0-mini/1.5-pro/1.0-pro/1.0-pro-fast
- doubao-seedance-2.0: 4-15s 2K video, native synced audio, 9 images+3 videos+3 audio refs
- Data source: Volcengine Ark model list + seedance2-video.com version history
- Bump presetDataVersion 70→71

Co-authored-by: DesireCore CI <ci@desirecore.test>
2026-07-09 17:51:09 +08:00
Johnson-LYS
57937a93b7 feat: add Seedance video generation models to volcengine (#52)
- Add 6 Seedance models: 2.0/2.0-fast/2.0-mini/1.5-pro/1.0-pro/1.0-pro-fast
- doubao-seedance-2.0: 4-15s 2K video, native synced audio, 9 images+3 videos+3 audio refs
- Data source: Volcengine Ark model list + seedance2-video.com version history
- Bump presetDataVersion 70→71

Co-authored-by: DesireCore CI <ci@desirecore.test>
2026-07-09 17:29:47 +08:00
6ed4b1a66a revert(compute): 回滚 Claude 订阅 provider(#47/#48/#49),presetDataVersion → 70 (#50)
* Revert "chore(compute): bump presetDataVersion to 69 (Claude provider now loads) (#49)"

This reverts commit 717ae69635.

* Revert "fix(compute): rename anthropic-claude provider file to match _index basename (#48)"

This reverts commit a1ec69ee71.

* Revert "feat(compute): 新增 Claude 订阅 provider(anthropic-claude) (#47)"

This reverts commit 1261460734.

* chore(compute): bump presetDataVersion to 70(推送回滚后的干净数据给已同步 v68/v69 的客户端)
2026-07-08 23:19:11 +08:00
717ae69635 chore(compute): bump presetDataVersion to 69 (Claude provider now loads) (#49)
PR #47 bumped to 68 but the provider file was misnamed and never loaded; the
rename (#48) kept v68, so clients that already synced v68 will not re-merge.
Bump to 69 so existing clients pick up the now-loadable anthropic-claude provider.
2026-07-07 22:52:02 +08:00
a1ec69ee71 fix(compute): rename anthropic-claude provider file to match _index basename (#48)
provider-loader loads <basename>.json from _index order; the file must be
anthropic-claude.json (was anthropic-claude-plan.json) or it is not loaded.
2026-07-07 22:47:39 +08:00
1261460734 feat(compute): 新增 Claude 订阅 provider(anthropic-claude) (#47)
* feat(compute): 新增 Claude 订阅 provider(anthropic-claude,credentialSource=claude-oauth)

* chore(schemas): credentialSource enum 增加 claude-oauth
2026-07-07 21:29:37 +08:00
4c17911630 chore(schemas): runtime-recommended 收紧 sha256 为必填(6 平台齐全) (#46)
与主仓库 lib/schemas/agent-service/runtime-manifest.ts 同源导出,强化归档防篡改校验
2026-07-07 19:23:22 +08:00
c67dfc2143 chore: refresh vendor model presets
Refresh vendor model presets and bump config data version.
2026-07-07 16:31:24 +08:00
92e0d4651a chore: refresh GLM model configs
## Summary
- add GLM-5.2 and GLM-4.7-FlashX to Zhipu provider config
- update GLM context/output/pricing tiers from official BigModel docs and pricing
- align Zhipu Coding Plan with official GLM-5.2, GLM-5-Turbo, and GLM-4.7 availability
- sync existing GLM max output values in DashScope configs
- address Copilot review by using extra.pricingTiers consistently

## Validation
- npm run validate
- npm test
- git diff --check
2026-07-07 16:25:21 +08:00
255e5a5b1b feat(runtimes): 新增推荐运行时清单与离线兜底版本清单 (#44)
- runtimes/recommended.json:Python 3.13.9 (hatch 1.16.5 pin) + Node.js 24.18.0 LTS,
  含 6 平台归档路径与 SHA-256,供主仓库构建时打包离线运行时与首启导入
- runtimes/versions-fallback.json:Node/Python/包管理器版本快照,
  客户端联网查询失败时的兜底列表
- schemas + validate.mjs 映射 + 测试(与主仓库 lib/schemas/agent-service/runtime-manifest.ts 同源导出)
- 不递增 presetDataVersion:runtimes/ 由客户端直接读取,不参与 compute.json 合并
2026-07-07 16:04:14 +08:00
847f4bd139 更新 Kimi 模型配置 (#40)
更新 Kimi 模型配置

- 更新 Moonshot/Kimi 官方 provider 模型清单
- 新增 K2.7 Code、K2.7 Code HighSpeed 和 V1 vision-preview 模型
- 移除已下线 K2 系列并添加 tombstones
- 同步 Kimi Code coding plan 参数

验证:
- npm run validate
- npm test
2026-07-07 15:51:36 +08:00
f0e14a8b5e 更新 DeepSeek 官方模型配置
更新 DeepSeek 官方模型配置
2026-07-07 15:47:06 +08:00
66113b06cf 更新 Qwen 模型配置 (#41)
更新 Qwen 模型配置
2026-07-07 15:41:24 +08:00
da0397f74b feat(compute): 补齐媒体生成 provider 能力声明(Seedream/Seedance/快乐马) (#34)
- volcengine:services 增 image_gen/video_gen;新增 doubao-seedream-4-0-250828(真 img2img/多图融合)与 doubao-seedance-2-0-260128(多素材视频)模型
- dashscope:新增快乐马 happyhorse-1.0-t2v/i2v/r2v 视频模型
- service-map:默认 image_gen→minimax/image-01、video_gen→minimax/MiniMax-Hailuo-2.3(指向已有内置工具适配器的后端)

使算力配置 UI 能展示这些 provider 的图像/视频能力标签与模型,用户填 key 时即可显式知晓其用途。
2026-07-06 14:41:57 +08:00
Johnson-LYS
1f51224901 Revert "Revert "feat(compute): 新增 ChatGPT 订阅 (Codex) Provider 预设 (#33)" (#36)" (#37)
This reverts commit d85810da79.
2026-07-04 11:31:02 +08:00
Johnson-LYS
e73b607706 feat: add HappyHorse (快乐马) video generation models (#39)
- Add happyhorse.json with 6 models: 1.1/1.0 × T2V/I2V/R2V
- T2V: text-to-video, I2V: image-to-video, R2V: reference-to-video (up to 9 images)
- Provider: HappyHorse via Alibaba Cloud Bailian
- Register in _index.json (now 22 providers)
- Bump presetDataVersion 62→63
2026-07-03 13:37:51 +08:00
Johnson-LYS
51935c0d54 chore(internal-testing): 退役内置 provider;bump presetDataVersion to 61 (#26)
* chore(internal-testing): 退役内置 provider;bump presetDataVersion to 52

internal-testing 一直作为内测阶段的硬编码 provider 存在,现在客户端已切换到
登录后绑定 desirecore-cloud(NewAPI 网关)方案,internal-testing 不再需要。

从此 commit 起:
- compute/providers/internal-testing.json 删除
- _index.json 移除 internal-testing 条目
- presetDataVersion 51 → 52,触发客户端重新合并预置

客户端需配套实现 retired-providers 清理逻辑:在 mergeBuiltinIfNewer 之后
执行一次性清理,移除本地 compute.json 中残留的 provider-internal-testing-001
+ secrets.json#internal-testing。

* chore: bump preset data version to 61

* feat: 增量同步 16 个厂商旗舰模型 (首批精选)

首次从 OpenRouter 增量同步,覆盖 13 家厂商的最新旗舰:

概要
---
- 新增 .sync-watermark 水位线文件 (1782276303 / 2026-06-24)
- presetDataVersion: 61 → 62
- 校验 70/70 全部通过

新增模型
---
OpenAI:     gpt-image-2 (image_gen), gpt-5.5, gpt-5.4
Anthropic:  claude-fable-5, claude-opus-4.8
Google:     gemini-3.5-flash, gemini-3.1-flash-image (Nano Banana 2)
DeepSeek:   deepseek-v4-pro
Qwen:       qwen3.7-max, qwen3.7-plus
MiniMax:    MiniMax-M3
Moonshot:   kimi-k2.7-code
Zhipu:      glm-5.2
xAI:        grok-4.3
Mistral:    mistral-medium-3.5
Tencent:    hy3-preview
Cohere:     north-mini-code

后续机制
---
每日 10:00 心跳检查 OpenRouter 新模型,对比 .sync-watermark
增量入库,有更新才提 PR,无更新静默。
2026-06-29 20:52:13 +08:00
Johnson-LYS
d85810da79 Revert "feat(compute): 新增 ChatGPT 订阅 (Codex) Provider 预设 (#33)" (#36)
This reverts commit d8e458c3ca.
2026-06-29 16:21:09 +08:00
Johnson-LYS
d8e458c3ca feat(compute): 新增 ChatGPT 订阅 (Codex) Provider 预设 (#33)
自动检测客户端本地 Codex CLI 的 ChatGPT 订阅授权(~/.codex/auth.json),
以用户订阅额度调用 gpt-5.x/codex 模型,无需 API Key。

- compute/providers/openai-codex.json:accessMode=coding-plan +
  credentialSource=codex-cli + apiFormat=openai-codex-responses,5 个模型,
  enabled=false(由客户端检测器按本地凭证自动启用)
- schemas/provider.schema.json:frozen baseline 新增 credentialSource 字段
- manifest.json:presetDataVersion 59 → 60

⚠️ 发布顺序:本数据引入老客户端不识别的 credentialSource 字段。必须先发布带
compute.json 韧性(容忍未知字段)的客户端并等自动更新铺开,再合并本 PR——
否则更早的客户端合并时会因严格 schema 校验失败而停收所有预设更新。
2026-06-29 16:17:40 +08:00
xyx
65a8bc4af5 feat(coding-plan): 新增百度千帆 Coding Plan 配置(presetDataVersion 58→59) (#32)
- 新增 baidu-coding.json:10 个模型(qianfan-code-latest 自动路由、
  deepseek-v3.2/v4-flash、ernie-4.5-turbo、glm-5/5.1、kimi-k2.5/k2.6、
  minimax-m2.5/m2.7)
- baseUrl: https://qianfan.baidubce.com/v2/coding
- accessMode: coding-plan
- 更新 _index.json 添加 baidu-coding 条目
2026-06-12 14:30:12 +08:00
ef632d4e6a feat(api-providers): 新增 web_search / image_understanding 声明式后端默认配置 (#31)
- api-providers/{web-search,image-understanding}/*.json + _index.json
- 新增 schemas/api-provider.schema.json,validate.mjs 纳入校验(CI 自检)
- 不改 compute/ 与 manifest,presetDataVersion 不变:老客户端忽略新目录,线上不受影响

Co-authored-by: yi-ge <jackyoncode@gmail.com>
2026-06-09 09:54:27 +08:00
Johnson-LYS
e84edec964 feat(model-specs): 新增模型规格库——跨 provider 模型参数统一维护(presetDataVersion 54→58)
* feat(model-specs): 新增模型规格库与 schema 契约

- compute/model-specs/:按厂商维护模型内在参数(上下文窗口/最大输出/能力/serviceType/默认温度,不含价签)
- schemas/model-spec.schema.json:Draft-07 契约,spec 允许 null(新文件不影响老客户端 frozen 契约)
- scripts/validate.mjs:pickSchemaKey 纳入 model-specs 校验
- manifest.presetDataVersion 54→55

* feat(model-specs): 新增小米 MiMo 系列模型规格;bump presetDataVersion 55→56

* feat(model-specs): 补全全量模型规格;presetDataVersion 56→57

* feat(model-specs): 新增 releasedAt/retiredAt 时间戳字段;补充 mimo 退役日期
2026-06-01 19:45:14 +08:00
9633df0219 chore(internal-testing): 默认模型改为 MiMo V2.5 Pro(小米 Pro);bump presetDataVersion to 54 (#29) 2026-05-30 15:05:04 +08:00
xyx
161eb04d39 fix(deepseek): 更新 DeepSeek 模型至 V4 系列,修正价格与参数 (#28)
- 新增 deepseek-v4-flash(主力)和 deepseek-v4-pro(旗舰)
- 上下文窗口 128K → 1M,最大输出 8K/64K → 384K
- 价格更新:V4 Flash 输入 1 元/M 输出 2 元/M;V4 Pro 输入 3 元/M 输出 6 元/M
- 保留 deepseek-chat / deepseek-reasoner 作为旧别名(标记 2026-07-24 弃用)
- bump presetDataVersion to 52

Co-authored-by: Yige <a@wyr.me>
2026-05-28 14:50:28 +08:00
xyx
55f948a725 fix: mark internal testing models as tool-capable (#27) 2026-05-28 14:49:07 +08:00
e17a00d48b chore(internal-testing): 新增 Qwen3.7 Max 并设为默认模型;bump presetDataVersion to 51 (#25) 2026-05-23 10:24:58 +08:00
cc3f0b53da chore(internal-testing): 回退 DeepSeek V4 Pro/Flash 视觉与 OCR 能力(实测不支持);bump presetDataVersion to 50 (#24) 2026-05-20 13:37:45 +08:00
b8019c4a30 chore(internal-testing): DeepSeek V4 Pro/Flash 新增视觉(图像理解)与 OCR 能力;bump presetDataVersion to 49 (#23) 2026-05-20 12:35:23 +08:00
72163bac46 chore(internal-testing): 默认模型改为 DeepSeek V4 Pro;bump presetDataVersion to 48 (#22) 2026-05-18 22:37:08 +08:00
fffa2b1980 chore(internal-testing): 新增 DeepSeek V4 Pro/Flash;bump presetDataVersion to 47 (#21)
- deepseek-v4-pro:1.6T/49B MoE 旗舰,1M 上下文,思考型(reasoning),省略温度参数
- deepseek-v4-flash:284B/13B MoE 高速版,1M 上下文,serviceType=[chat, fast]
- 价格统一保持 0,遵循内测专用 provider 惯例
- manifest: presetDataVersion 46→47,updatedAt 2026-05-12
2026-05-12 11:29:19 +08:00
xyx
00e148af8e feat: 算力配置全面审计 — 6 家供应商 + Token/Coding Plan 对齐官方文档 (#20)
Providers:
- moonshot: 移除到期模型 kimi-k2/k2-thinking,修正 k2.6 maxOutputTokens 32768、k2.5 contextWindow 262144
- tencent: 修正 hunyuan-t1-latest 上下文/输出/价格,新增 hunyuan-t1-vision/turbos-vision
- volcengine: doubao-seed-2.0-lite/mini 新增 audio_understanding/video_understanding
- internal-testing: services 扩展为全部 18 种类型,新增 mediaBaseUrl

Coding Plans:
- dashscope-token-plan: baseUrl 修正为 coding.dashscope.aliyuncs.com,移除非 Coding Plan 模型,新增 kimi-k2.5/qwen3.5-plus/qwen3-coder-plus/glm-4.7
- minimax-coding: 修正 usageTracking 端点,services 扩展为 7 种含媒体类型
- moonshot-coding: maxOutputTokens 修正为 32768
- zhipu-coding: 新增 glm-5.1/glm-5-turbo/glm-4.5-air,修正 glm-5 contextWindow 200000
- volcengine-coding: 新增 glm-5.1/kimi-k2.6/minimax-m2.7
- tencent-token: 新增腾讯云 Token Plan(10 个模型)

presetDataVersion: 45 → 46
2026-05-10 00:58:56 +08:00
xyx
82ad03d9eb feat: 新增小米 MiMo Provider 配置 (#19)
- 添加 xiaomi.json:MiMo-V2.5-Pro(chat/reasoning)+ TTS 系列(tts/voicedesign/voiceclone)
- 更新 _index.json 加载顺序
- presetDataVersion 42 → 43
2026-05-09 15:04:55 +08:00
75f507b6fd chore: 新增 CI 拦截 AI 贡献痕迹 (#18)
- scripts/check-no-ai-attribution.sh:扫描指定 git 范围,命中 AI 身份、Co-Authored-By trailer、Generated/Authored 声明或机器人 emoji 时报错
- scripts/ai-attribution-patterns.txt:外置 AI 工具/厂商关键字清单,便于按需扩展
- .github/workflows/no-ai-attribution.yml:PR (target main) 与 push (main) 时对增量 commit 范围运行扫描
- CLAUDE.md:项目级 commit 身份规范,禁止任何 AI 署名/辅助标记
2026-05-08 17:48:34 +08:00
34a75a7b25 chore(internal-testing): 默认模型改为 GLM-5;bump presetDataVersion to 43
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-08 15:48:20 +08:00
xyx
86329ef928 chore: bump presetDataVersion to 42 (#17) 2026-05-08 12:51:04 +08:00
xyx
7c5cbca1c2 chore: bump presetDataVersion to 41 (#16)
验证 DashScope Token Plan + 文生图配置可用:
- dashscope-token-plan coding plan 已验证
- dashscope.json mediaBaseUrl 配置已验证
- 配合主仓库 media-proxy 动态路由修复
2026-05-08 12:40:02 +08:00
483356b9e7 chore: bump presetDataVersion to 40 2026-05-07 22:07:09 +08:00
xyx
8a4a08b642 fix(dashscope): Token Plan 回退为客户端兼容字段 (#15)
线上客户端 schema 尚未支持 tokenPlan/accessMode:"token-plan",
同步后导致 compute.json 校验失败。临时回退为 codingPlan + coding-plan,
待主仓库升级 schema 后再切换为语义正确的字段。
2026-05-07 22:05:30 +08:00
799a11192e chore: bump presetDataVersion to 39 2026-05-07 21:16:30 +08:00
xyx
4192a19ecf Merge pull request #14 from desirecore/feat/dashscope-token-plan
feat(dashscope): 新增 Token Plan + 更新 Coding Plan + 补充 qwen-image 模型
2026-05-07 20:51:50 +08:00
37d51e6e4d feat(schema): 扩展 provider schema 支持 Token Plan
- accessMode enum 新增 "token-plan"
- 新增顶层 tokenPlan 属性(与 codingPlan 结构对齐)
- usageTracking.method enum 新增 "credits"(Token Plan 使用 Credits 计量)
- dashscope-token-plan.json 恢复语义正确的 tokenPlan 配置
2026-05-07 20:15:58 +08:00
f4706b1558 fix: Token Plan schema 兼容修复(accessMode/codingPlan/method) 2026-05-07 20:12:45 +08:00