Commit Graph

Select branches

Hide Pull Requests

feat/dashscope-image-models

feat/dashscope-token-plan

feat/fix-watermark-and-sync-batch

feat/incremental-sync-batch-1

feat/reintroduce-anthropic-claude-provider

main

#1

#10

#11

#12

#13

#14

#15

#16

#17

#18

#19

#2

#20

#21

#22

#23

#24

#25

#26

#27

#28

#29

#3

#30

#31

#32

#33

#34

#35

#36

#37

#38

#39

#4

#40

#41

#42

#43

#44

#45

#46

#47

#48

#49

#5

#50

#51

#51

#52

#53

#54

#55

#56

#57

#58

#59

#6

#60

#61

#62

#63

#63

#7

#8

#9

Mono Color

• 768da94ad0 feat: sync missing models from OpenRouter (fix watermark) feat/fix-watermark-and-sync-batch Johnson 2026-07-21 16:24:03 +08:00
• e59adbb166 feat: add Kimi K3 model spec (#62) main Johnson-LYS 2026-07-20 20:00:19 +08:00
• 29ef625f32 fix(compute): match MiMo V2.5 ASR exactly (#61) Johnson-LYS 2026-07-20 17:29:05 +08:00
• 523e667b40 fix(compute): enforce reasoning effort boundaries (#60) Yige 2026-07-19 21:47:10 +08:00
• 55999ce633 feat(compute): declare GPT-5.6 reasoning efforts (#59) Yige 2026-07-19 20:58:00 +08:00
• d5d0dfafbd fix(compute): Codex displayName 去掉冗余 (订阅) 后缀 (#58) Yige 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) Yige 2026-07-19 15:30:16 +08:00
• ce1a936284 fix: restore provider-based pricing currencies (#56) Yige 2026-07-13 16:16:03 +08:00
• 5a9b9c87c4 fix: align DeepSeek V4 model specs with official profile Yige 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) Yige 2026-07-09 18:25:16 +08:00
• c2edba2cef Revert "revert(compute): 回滚 Claude 订阅 provider（#47/#48/#49），presetDataVersion → 70 (#50)" feat/reintroduce-anthropic-claude-provider yi-ge 2026-07-09 13:07:03 +08:00
• 0349473fd4 feat: add Seedance video generation models to volcengine (#53) Johnson-LYS 2026-07-09 17:51:09 +08:00
• 57937a93b7 feat: add Seedance video generation models to volcengine (#52) Johnson-LYS 2026-07-09 17:29:47 +08:00
• 6ed4b1a66a revert(compute): 回滚 Claude 订阅 provider（#47/#48/#49），presetDataVersion → 70 (#50) Yige 2026-07-08 23:19:11 +08:00
• 717ae69635 chore(compute): bump presetDataVersion to 69 (Claude provider now loads) (#49) Yige 2026-07-07 22:52:02 +08:00
• a1ec69ee71 fix(compute): rename anthropic-claude provider file to match _index basename (#48) Yige 2026-07-07 22:47:39 +08:00
• 1261460734 feat(compute): 新增 Claude 订阅 provider（anthropic-claude） (#47) Yige 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) Yige 2026-07-07 19:23:22 +08:00
• c67dfc2143 chore: refresh vendor model presets Yige 2026-07-07 16:31:24 +08:00
• 92e0d4651a chore: refresh GLM model configs Yige 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) Yige 2026-07-07 16:04:14 +08:00
• 847f4bd139 更新 Kimi 模型配置 (#40) Yige 2026-07-07 15:51:36 +08:00
• f0e14a8b5e 更新 DeepSeek 官方模型配置 Yige 2026-07-07 15:47:06 +08:00
• 66113b06cf 更新 Qwen 模型配置 (#41) Yige 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) Yige 2026-07-06 14:41:57 +08:00
• 1f51224901 Revert "Revert "feat(compute): 新增 ChatGPT 订阅 (Codex) Provider 预设 (#33)" (#36)" (#37) Johnson-LYS 2026-07-04 11:31:02 +08:00
• e73b607706 feat: add HappyHorse (快乐马) video generation models (#39) Johnson-LYS 2026-07-03 13:37:51 +08:00
• 6df9fa600c chore: bump presetDataVersion to 63 feat/incremental-sync-batch-1 Johnson 2026-06-29 22:23:58 +08:00
• 51935c0d54 chore(internal-testing): 退役内置 provider；bump presetDataVersion to 61 (#26) Johnson-LYS 2026-06-29 20:52:13 +08:00
• d85810da79 Revert "feat(compute): 新增 ChatGPT 订阅 (Codex) Provider 预设 (#33)" (#36) Johnson-LYS 2026-06-29 16:21:09 +08:00
• d8e458c3ca feat(compute): 新增 ChatGPT 订阅 (Codex) Provider 预设 (#33) Johnson-LYS 2026-06-29 16:17:40 +08:00
• 65a8bc4af5 feat(coding-plan): 新增百度千帆 Coding Plan 配置（presetDataVersion 58→59） (#32) xyx 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) Yige 2026-06-09 09:54:27 +08:00
• e84edec964 feat(model-specs): 新增模型规格库——跨 provider 模型参数统一维护（presetDataVersion 54→58） Johnson-LYS 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) Yige 2026-05-30 15:05:04 +08:00
• 161eb04d39 fix(deepseek): 更新 DeepSeek 模型至 V4 系列，修正价格与参数 (#28) xyx 2026-05-28 14:50:28 +08:00
• 55f948a725 fix: mark internal testing models as tool-capable (#27) xyx 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) Yige 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) Yige 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) Yige 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) Yige 2026-05-18 22:37:08 +08:00
• fffa2b1980 chore(internal-testing): 新增 DeepSeek V4 Pro/Flash；bump presetDataVersion to 47 (#21) Yige 2026-05-12 11:29:19 +08:00
• 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) xyx 2026-05-10 00:58:56 +08:00
• 82ad03d9eb feat: 新增小米 MiMo Provider 配置 (#19) xyx 2026-05-09 15:04:55 +08:00
• 75f507b6fd chore: 新增 CI 拦截 AI 贡献痕迹 (#18) Yige 2026-05-08 17:48:34 +08:00
• 34a75a7b25 chore(internal-testing): 默认模型改为 GLM-5；bump presetDataVersion to 43 yi-ge 2026-05-08 15:48:20 +08:00
• 86329ef928 chore: bump presetDataVersion to 42 (#17) xyx 2026-05-08 12:51:04 +08:00
• 7c5cbca1c2 chore: bump presetDataVersion to 41 (#16) xyx 2026-05-08 12:40:02 +08:00
• 483356b9e7 chore: bump presetDataVersion to 40 xieyuanxiang 2026-05-07 22:07:09 +08:00
• 8a4a08b642 fix(dashscope): Token Plan 回退为客户端兼容字段 (#15) xyx 2026-05-07 22:05:30 +08:00
• 799a11192e chore: bump presetDataVersion to 39 xieyuanxiang 2026-05-07 21:16:30 +08:00
• a0c9ac7bc4 feat(schema): 扩展 provider schema 支持 Token Plan feat/dashscope-token-plan xieyuanxiang 2026-05-07 20:15:58 +08:00
• 4192a19ecf Merge pull request #14 from desirecore/feat/dashscope-token-plan xyx 2026-05-07 20:51:50 +08:00
• 37d51e6e4d feat(schema): 扩展 provider schema 支持 Token Plan xieyuanxiang 2026-05-07 20:15:58 +08:00
• f4706b1558 fix: Token Plan schema 兼容修复（accessMode/codingPlan/method） xieyuanxiang 2026-05-07 20:12:45 +08:00
• 01764d447d feat(dashscope): 更新 Coding Plan 模型 + 新增 Token Plan + providers 补充 qwen-image 系列 xieyuanxiang 2026-05-07 19:44:20 +08:00
• 11e9e9888b feat(dashscope): 更新 Coding Plan 模型 + 新增 Token Plan + providers 补充 qwen-image 系列 feat/dashscope-image-models xieyuanxiang 2026-05-07 19:44:20 +08:00
• 5d68ed4bc4 Merge pull request #13 from desirecore/feat/dashscope-image-models xyx 2026-05-07 19:13:39 +08:00
• 199a2bc528 feat(dashscope): 添加 mediaBaseUrl 和万相新模型系列 xieyuanxiang 2026-05-07 19:09:30 +08:00
• 648839c5dd feat(internal-testing): add Xiaomi MiMo V2.5 and V2.5 Pro models (#12) Yige 2026-05-02 00:57:54 +08:00
• e9cbb99f40 Merge pull request #11 from desirecore/fix/volcengine-config xyx 2026-04-29 21:45:03 +08:00
• f29e6966dc fix(schema): allow mediaBaseUrl in provider schema xieyuanxiang 2026-04-29 21:41:42 +08:00
• 7ac60f9c3c fix(volcengine): update provider and coding plan models xieyuanxiang 2026-04-29 21:24:59 +08:00
• 2d98f45fbc Merge pull request #10 from desirecore/fix/halve-context-window-internal-testing xyx 2026-04-29 21:01:35 +08:00
• 244154ee06 fix: 临时将 internal-testing 所有模型 contextWindow 减半 xieyuanxiang 2026-04-29 20:14:24 +08:00
• e65c3f4c23 fix(minimax): Token Plan 改用 anthropic-messages 格式（与 API provider 一致） xieyuanxiang 2026-04-28 22:04:17 +08:00
• 32203fb2a9 fix(minimax): codingPlan 结构适配 schema（移除不兼容的嵌套配额） xieyuanxiang 2026-04-28 21:36:22 +08:00
• 9da3d12a4f chore: Coding Plan 统一改名为 Token (Coding) Plan xieyuanxiang 2026-04-28 21:14:03 +08:00
• a1c9c7351b fix(minimax): 补全模型列表，Token Plan 升级为全模态 xieyuanxiang 2026-04-28 20:55:45 +08:00
• f128d2adc7 Merge pull request #9 from desirecore/fix/minimax-anthropic-format xyx 2026-04-28 12:03:27 +08:00
• ad0f83ead5 fix: MiniMax 切换为 Anthropic 消息格式 + mediaBaseUrl xieyuanxiang 2026-04-27 23:49:21 +08:00
• 1c71483e25 feat: MiniMax Provider 合并媒体能力（图片/语音/视频/音乐） (#8) xyx 2026-04-27 22:17:12 +08:00
• d1271bd894 fix: 补充缺失的 vision 能力声明 (#7) xyx 2026-04-27 18:56:55 +08:00
• 6e5d03b6df Stop tracking generated audit docs xieyuanxiang 2026-04-26 17:44:03 +08:00
• 370c3d17d1 chore: preserve field audit artifacts and tools (#5) xyx 2026-04-26 10:34:19 +08:00
• 8aa03dbb4e fix(ci): drop npm install fallback and use explicit test file path (#4) Yige 2026-04-25 21:50:07 +08:00
• b238e9e496 Merge pull request #3 from desirecore/feat/schema-validation Yige 2026-04-25 21:40:06 +08:00
• 380e99c577 修复算力模型采样默认值 xieyuanxiang 2026-04-25 21:39:51 +08:00
• 96bd5d0de4 chore: commit package-lock.json for CI cache yi-ge 2026-04-25 21:11:24 +08:00
• bd448f6c43 feat: frozen schema + CI validation to prevent client-breaking data yi-ge 2026-04-25 21:09:23 +08:00
• 10465e3570 chore: bump presetDataVersion to 30 to roll back PR #1 yi-ge 2026-04-25 19:35:39 +08:00
• 371336cdd6 Revert "Merge pull request #1 from desirecore/model-field-official-audit" yi-ge 2026-04-25 19:34:29 +08:00
• 88a8cf2db6 Merge pull request #1 from desirecore/model-field-official-audit Yige 2026-04-25 17:56:48 +08:00
• b0e0cead04 chore: update field audit tables and provider configs xieyuanxiang 2026-04-24 20:12:57 +08:00
• 5b9c8ac61f fix: restore CNY pricing for MiniMax and Zhipu (Chinese providers) xieyuanxiang 2026-04-24 20:06:24 +08:00
• cc2fb7b9a5 fix: remove irrelevant text-model fields from non-text providers xieyuanxiang 2026-04-24 19:53:57 +08:00
• 7159e1cf59 fix(coding-plans): revert incorrect model name suffix and align MiniMax Token Plan labels xieyuanxiang 2026-04-24 15:12:13 +08:00
• c57cd4723d audit model field values against official docs xieyuanxiang 2026-04-24 12:20:24 +08:00
• ca99ea272f feat(internal-testing): restore MiniMax-M2.5 yi-ge 2026-04-20 11:10:37 +08:00
• 719407d82c feat: add per-provider tombstones whitelist for explicit model deletion yi-ge 2026-04-20 00:42:35 +08:00
• 2ed86a9561 refactor(internal-testing): drop MiniMax-M2.5/M2.7, keep only M2.7-highspeed yi-ge 2026-04-19 23:43:10 +08:00
• 5276339aa5 feat(internal-testing): add MiniMax-M2.7-highspeed as provider default model yi-ge 2026-04-19 23:28:39 +08:00
• c7a24a7acd feat(zhipu): switch to anthropic-messages endpoint and split embedding provider yi-ge 2026-04-19 23:19:35 +08:00
• ae3b36463a chore:更新版本和时间 张馨元 2026-04-18 15:32:40 +08:00
• b580622aa4 增加内测模型glm-4.7 张馨元 2026-04-18 15:23:50 +08:00
• 344a9fe4c6 feat: 内测渠道增加 Kimi K2.6 Code Preview 模型支持 张馨元 2026-04-16 15:34:44 +08:00
• 97c2c16643 fix: 修复 22 处模型能力标签与实际能力不一致的问题 张馨元 2026-04-15 15:30:00 +08:00
• b2726851e8 chore: bump presetDataVersion to 17 yi-ge 2026-04-08 17:43:58 +08:00
• c8d4061422 feat: 内测 provider 新增 qwen3.6-plus、qwen3.5-35b-a3b、qwen3.5-27b 三个模型 yi-ge 2026-04-08 16:52:35 +08:00
• 8ea6fa7bba feat: 内测渠道增加 GLM-5.1 模型支持 yi-ge 2026-03-28 23:36:03 +08:00