desirecore/config-center
2
0
Fork 0
mirror of https://git.openapi.site/https://github.com/desirecore/config-center.git synced 2026-06-06 09:10:52 +08:00
Code Issues Packages Projects Releases Wiki Activity

chore: preserve field audit artifacts and tools (#5)

Browse Source 
* 备份同步前的配置审计修改

* 更新字段审计产物
This commit is contained in:
谢源祥
2026-04-26 10:34:19 +08:00
committed by GitHub
parent 8aa03dbb4e
commit 370c3d17d1
79 changed files with 12480 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

269
outputs/field-audit/official-review-checklist.md Normal file
View File

@@ -0,0 +1,269 @@
# Official Review Checklist
GeneratedAt: 2026-04-25T16:15:04.854Z
Source: /Users/xieyuanxiang/config-center/outputs/field-audit/zenmux-sync-report.json
Purpose: verify unresolved models with official vendor docs before write-back.
## Summary
- actual models: **160**
- unresolved models: **103**
- providers involved: **27**
- null sampling fields: **0**
## Provider: baichuan
- official docs:
- https://platform.baichuan-ai.com/docs
- pending models:
- `Baichuan-M3-Plus` (compute/providers/baichuan.json) -> no ZenMux match
- `Baichuan-M3` (compute/providers/baichuan.json) -> no ZenMux match
- `Baichuan-M2-Plus` (compute/providers/baichuan.json) -> no ZenMux match
- `Baichuan-M2` (compute/providers/baichuan.json) -> no ZenMux match
## Provider: baidu
- official docs:
- https://cloud.baidu.com/doc/qianfan/
- pending models:
- `ernie-4.5-turbo-128k` (compute/providers/baidu.json) -> no ZenMux match
- `ernie-4.5-turbo-20260402` (compute/providers/baidu.json) -> no ZenMux match
## Provider: cohere
- official docs:
- https://docs.cohere.com/docs/models
- https://cohere.com/pricing
- pending models:
- `command-a-03-2025` (compute/providers/cohere.json) -> no ZenMux match
- `command-r7b-12-2024` (compute/providers/cohere.json) -> no ZenMux match
- `embed-v4.0` (compute/providers/cohere.json) -> no ZenMux match
- `rerank-v3.5` (compute/providers/cohere.json) -> no ZenMux match
## Provider: dashscope
- official docs:
- https://help.aliyun.com/zh/model-studio/getting-started/models
- https://help.aliyun.com/zh/model-studio/pricing
- pending models:
- `qwen3.6-flash` (compute/providers/dashscope.json) -> ambiguous match candidates: qwen/qwen3.6-plus,qwen/qwen3.5-flash
- `qwen-max` (compute/providers/dashscope.json) -> no ZenMux match
- `qwen-plus` (compute/providers/dashscope.json) -> no ZenMux match
- `qwen-turbo` (compute/providers/dashscope.json) -> no ZenMux match
- `qwen-long` (compute/providers/dashscope.json) -> no ZenMux match
- `qwen3-vl-flash` (compute/providers/dashscope.json) -> ambiguous match candidates: qwen/qwen3.5-flash,qwen/qwen3-vl-plus
- `text-embedding-v3` (compute/providers/dashscope.json) -> no ZenMux match
- `text-embedding-v4` (compute/providers/dashscope.json) -> no ZenMux match
- `qwen3-rerank` (compute/providers/dashscope.json) -> no ZenMux match
- `cosyvoice-v2` (compute/providers/dashscope.json) -> no ZenMux match
- `paraformer-v2` (compute/providers/dashscope.json) -> no ZenMux match
- `wanx-v2` (compute/providers/dashscope.json) -> no ZenMux match
- `wanx-video` (compute/providers/dashscope.json) -> no ZenMux match
- `cosyvoice-clone` (compute/providers/dashscope.json) -> no ZenMux match
- `qwen-omni-turbo` (compute/providers/dashscope.json) -> no ZenMux match
## Provider: google
- official docs:
- https://ai.google.dev/gemini-api/docs/models
- https://ai.google.dev/pricing
- pending models:
- `text-embedding-005` (compute/providers/google.json) -> no ZenMux match
## Provider: infini
- official docs:
- (add link manually)
- pending models:
- `deepseek-v3` (compute/coding-plans/infini-coding.json) -> no ZenMux match
## Provider: internal-testing
- official docs:
- (add link manually)
- pending models:
- `MiniMax-M2.7-highspeed` (compute/providers/internal-testing.json) -> no ZenMux match
- `glm-5.1` (compute/providers/internal-testing.json) -> no ZenMux match
- `glm-5` (compute/providers/internal-testing.json) -> no ZenMux match
- `glm-5-turbo` (compute/providers/internal-testing.json) -> no ZenMux match
- `glm-4.7` (compute/providers/internal-testing.json) -> no ZenMux match
- `kimi-k2.6-code-preview` (compute/providers/internal-testing.json) -> no ZenMux match
- `kimi-k2.5` (compute/providers/internal-testing.json) -> no ZenMux match
- `MiniMax-M2.5` (compute/providers/internal-testing.json) -> no ZenMux match
- `qwen3.6-plus` (compute/providers/internal-testing.json) -> no ZenMux match
- `qwen3.5-plus` (compute/providers/internal-testing.json) -> no ZenMux match
- `qwen3.5-35b-a3b` (compute/providers/internal-testing.json) -> no ZenMux match
- `qwen3.5-27b` (compute/providers/internal-testing.json) -> no ZenMux match
- `qwen3-max-2026-01-23` (compute/providers/internal-testing.json) -> no ZenMux match
- `doubao-seed-2-0-code-preview-260215` (compute/providers/internal-testing.json) -> no ZenMux match
## Provider: kling
- official docs:
- (add link manually)
- pending models:
- `kling-v2-5-turbo` (compute/providers/kling.json) -> no ZenMux match
- `kling-v2-5-turbo-pro` (compute/providers/kling.json) -> no ZenMux match
- `kling-v2` (compute/providers/kling.json) -> no ZenMux match
- `kling-v2-master` (compute/providers/kling.json) -> no ZenMux match
## Provider: kwai
- official docs:
- (add link manually)
- pending models:
- `kwai-coder` (compute/coding-plans/kwai-coding.json) -> no ZenMux match
## Provider: lingyiwanwu
- official docs:
- (add link manually)
- pending models:
- `yi-lightning` (compute/providers/lingyiwanwu.json) -> no ZenMux match
- `yi-vision-v2` (compute/providers/lingyiwanwu.json) -> no ZenMux match
## Provider: local-whisper
- official docs:
- (add link manually)
- pending models:
- `whisper-large-v3` (compute/providers/local-whisper.json) -> no ZenMux match
## Provider: minimax
- official docs:
- https://platform.minimax.io/docs/api-reference/api-overview
- https://platform.minimax.io/docs/guides/pricing-paygo
- pending models:
- `MiniMax-M1` (compute/coding-plans/minimax-coding.json) -> no ZenMux match
- `MiniMax-M2.5-highspeed` (compute/providers/minimax.json) -> ambiguous match candidates: minimax/minimax-m2.5,minimax/minimax-m2.7-highspeed,minimax/minimax-m2.5-lightning,minimax/minimax-m2,minimax/minimax-m2.7
- `MiniMax-M2.1-highspeed` (compute/providers/minimax.json) -> ambiguous match candidates: minimax/minimax-m2.1,minimax/minimax-m2.7-highspeed,minimax/minimax-m2,minimax/minimax-m2.7,minimax/minimax-m2.5
- `MiniMax-Text-01` (compute/providers/minimax.json) -> no ZenMux match
## Provider: mistral
- official docs:
- https://docs.mistral.ai/getting-started/models
- https://mistral.ai/pricing
- pending models:
- `mistral-small-latest` (compute/providers/mistral.json) -> no ZenMux match
- `codestral-latest` (compute/providers/mistral.json) -> no ZenMux match
## Provider: moonshot
- official docs:
- https://platform.moonshot.cn/docs/guide/overview
- https://platform.moonshot.cn/docs/pricing/chat
- pending models:
- `kimi-k2` (compute/coding-plans/moonshot-coding.json) -> ambiguous match candidates: moonshotai/kimi-k2.6,moonshotai/kimi-k2.5,moonshotai/kimi-k2-thinking,moonshotai/kimi-k2-0905,moonshotai/kimi-k2-0711
- `kimi-k2` (compute/providers/moonshot.json) -> ambiguous match candidates: moonshotai/kimi-k2.6,moonshotai/kimi-k2.5,moonshotai/kimi-k2-thinking,moonshotai/kimi-k2-0905,moonshotai/kimi-k2-0711
- `moonshot-v1-8k` (compute/providers/moonshot.json) -> no ZenMux match
- `moonshot-v1-32k` (compute/providers/moonshot.json) -> no ZenMux match
- `moonshot-v1-128k` (compute/providers/moonshot.json) -> no ZenMux match
## Provider: moorethread
- official docs:
- (add link manually)
- pending models:
- `mt-coder` (compute/coding-plans/moorethread-coding.json) -> no ZenMux match
## Provider: ollama
- official docs:
- (add link manually)
- pending models:
- `llama3.1:70b` (compute/providers/ollama.json) -> no ZenMux match
## Provider: openai
- official docs:
- https://platform.openai.com/docs/models
- https://platform.openai.com/docs/pricing
- pending models:
- `text-embedding-3-small` (compute/providers/openai.json) -> no ZenMux match
- `text-embedding-3-large` (compute/providers/openai.json) -> no ZenMux match
- `tts-1` (compute/providers/openai.json) -> no ZenMux match
- `tts-1-hd` (compute/providers/openai.json) -> no ZenMux match
- `whisper-1` (compute/providers/openai.json) -> no ZenMux match
- `o3` (compute/providers/openai.json) -> no ZenMux match
- `o3-pro` (compute/providers/openai.json) -> no ZenMux match
- `o3-mini` (compute/providers/openai.json) -> no ZenMux match
- `dall-e-3` (compute/providers/openai.json) -> no ZenMux match
- `gpt-4o-realtime` (compute/providers/openai.json) -> ambiguous match candidates: openai/gpt-4o,openai/gpt-4o-mini
- `gpt-4o-realtime-preview` (compute/providers/openai.json) -> ambiguous match candidates: openai/gpt-4o,openai/gpt-4o-mini
## Provider: openrouter
- official docs:
- https://openrouter.ai/models
- pending models:
- `openrouter/auto` (compute/providers/openrouter.json) -> no ZenMux match
- `openai/gpt-oss-120b:free` (compute/providers/openrouter.json) -> no ZenMux match
- `qwen/qwen3-coder:free` (compute/providers/openrouter.json) -> no ZenMux match
## Provider: perplexity
- official docs:
- https://docs.perplexity.ai
- pending models:
- `sonar-pro` (compute/providers/perplexity.json) -> no ZenMux match
- `sonar-reasoning-pro` (compute/providers/perplexity.json) -> no ZenMux match
- `sonar` (compute/providers/perplexity.json) -> no ZenMux match
## Provider: siliconflow
- official docs:
- https://www.siliconflow.com/models
- https://siliconflow.cn/pricing
- pending models:
- `Qwen/Qwen3-Coder-480B-A35B-Instruct` (compute/providers/siliconflow.json) -> no ZenMux match
- `Qwen/Qwen3-235B-A22B-Instruct-2507` (compute/providers/siliconflow.json) -> ambiguous match candidates: qwen/qwen3-235b-a22b-2507,qwen/qwen3-235b-a22b-thinking-2507
- `BAAI/bge-m3` (compute/providers/siliconflow.json) -> no ZenMux match
## Provider: stability
- official docs:
- (add link manually)
- pending models:
- `stable-diffusion-3.5-large` (compute/providers/stability.json) -> no ZenMux match
## Provider: tencent
- official docs:
- https://cloud.tencent.com/document/product/1729
- pending models:
- `hunyuan-turbos-latest` (compute/providers/tencent.json) -> no ZenMux match
## Provider: volcengine
- official docs:
- https://www.volcengine.com/docs/82379
- pending models:
- `ark-code-latest` (compute/coding-plans/volcengine-coding.json) -> no ZenMux match
- `doubao-2.0-pro` (compute/providers/volcengine.json) -> ambiguous match candidates: bytedance/doubao-seed-2.0-pro,bytedance/doubao-seed-2.0-mini,bytedance/doubao-seed-2.0-lite,bytedance/doubao-seed-2.0-code
- `doubao-seed-1.6` (compute/providers/volcengine.json) -> ambiguous match candidates: bytedance/doubao-seed-1.8,bytedance/doubao-seed-code
- `doubao-seed-1.6-lite` (compute/providers/volcengine.json) -> ambiguous match candidates: bytedance/doubao-seed-1.8,bytedance/doubao-seed-2.0-lite
- `deepseek-v3.2` (compute/providers/volcengine.json) -> no ZenMux match
- `deepseek-r1` (compute/providers/volcengine.json) -> no ZenMux match
- `kimi-k2-volcengine` (compute/providers/volcengine.json) -> no ZenMux match
- `glm-4-7` (compute/providers/volcengine.json) -> no ZenMux match
- `doubao-embedding` (compute/providers/volcengine.json) -> no ZenMux match
- `volc-mega-tts-clone` (compute/providers/volcengine.json) -> no ZenMux match
- `volc-realtime-voice` (compute/providers/volcengine.json) -> no ZenMux match
- `volc-simultaneous` (compute/providers/volcengine.json) -> no ZenMux match
- `volc-translation` (compute/providers/volcengine.json) -> no ZenMux match
## Provider: xai
- official docs:
- https://docs.x.ai/docs/models
- pending models:
- `grok-4.20-0309-reasoning` (compute/providers/xai.json) -> ambiguous match candidates: x-ai/grok-4-fast-non-reasoning,x-ai/grok-4,x-ai/grok-4.2-fast-non-reasoning,x-ai/grok-4.1-fast-non-reasoning
- `grok-4-1-fast-reasoning` (compute/providers/xai.json) -> ambiguous match candidates: x-ai/grok-4.1-fast-non-reasoning,x-ai/grok-4.1-fast,x-ai/grok-4-fast-non-reasoning,x-ai/grok-4-fast,x-ai/grok-4.2-fast-non-reasoning
## Provider: xunfei
- official docs:
- https://www.xfyun.cn/doc/
- pending models:
- `spark-x` (compute/providers/xunfei.json) -> no ZenMux match
- `4.0Ultra` (compute/providers/xunfei.json) -> no ZenMux match
## Provider: zhipu
- official docs:
- https://docs.bigmodel.cn/cn/guide/models/text/
- https://www.bigmodel.cn/pricing
- pending models:
- `glm-4.7-thinking` (compute/providers/zhipu.json) -> ambiguous match candidates: z-ai/glm-4.7,z-ai/glm-4.7-flashx,z-ai/glm-4.7-flash-free,z-ai/glm-4.6v,z-ai/glm-4.6
## Provider: zhipu-embedding
- official docs:
- https://docs.bigmodel.cn/cn/guide/models/embedding
- pending models:
- `embedding-3` (compute/providers/zhipu-embedding.json) -> no ZenMux match
## Field-by-Field Verification Rule
- `modelName`: must exactly match provider API model ID or official alias rule.
- `contextWindow`: use official model spec limit.
- `maxOutputTokens`: use official output cap; do not infer from context.
- `inputPrice`/`outputPrice`: use official published API pricing and the provider currency.
- `capabilities`: project taxonomy field; keep local semantics unless official docs clearly contradict the capability.
- `defaultTemperature`/`defaultTopP`: only fill with numeric values when provider docs define a safe default; omit unsupported fields instead of using `null`.

14
outputs/field-audit/zenmux-risk-audit.md Normal file
View File

@@ -0,0 +1,14 @@
# ZenMux Risk Audit
GeneratedAt: 2026-04-25T16:15:04.854Z
Source: /Users/xieyuanxiang/config-center/outputs/field-audit/zenmux-sync-report.json
- HIGH: 0
- MEDIUM: 15
- LOW: 88
## Notes
- HIGH covers schema-breaking sampling defaults such as `null`.
- MEDIUM covers ambiguous third-party model matches.
- LOW covers models without a ZenMux match; these require official-doc review but do not by themselves indicate JSON invalidity.

177
outputs/field-audit/zenmux-sync-detailed.md Normal file
View File

@@ -0,0 +1,177 @@
# ZenMux Sync Detailed Report
GeneratedAt: 2026-04-25T16:15:04.854Z
## Summary
- actualModels: 160
- sourceModels: 133
- matchedModels: 57
- unmatchedModels: 88
- ambiguousModels: 15
- nullSamplingFields: 0
## Current Model Inventory
| File | Provider | Model | Match | ZenMux |
|---|---|---|---|---|
| compute/coding-plans/dashscope-coding.json | dashscope | `qwen3-coder-plus` | exact | `qwen/qwen3-coder-plus` |
| compute/coding-plans/dashscope-coding.json | dashscope | `qwen3-max` | exact | `qwen/qwen3-max` |
| compute/coding-plans/infini-coding.json | infini | `deepseek-v3` | none | |
| compute/coding-plans/kwai-coding.json | kwai | `kwai-coder` | none | |
| compute/coding-plans/minimax-coding.json | minimax | `MiniMax-M1` | none | |
| compute/coding-plans/moonshot-coding.json | moonshot | `kimi-k2` | ambiguous | |
| compute/coding-plans/moorethread-coding.json | moorethread | `mt-coder` | none | |
| compute/coding-plans/volcengine-coding.json | volcengine | `ark-code-latest` | none | |
| compute/coding-plans/zhipu-coding.json | zhipu | `glm-5` | exact | `z-ai/glm-5` |
| compute/coding-plans/zhipu-coding.json | zhipu | `glm-4.7` | exact | `z-ai/glm-4.7` |
| compute/providers/anthropic.json | anthropic | `claude-opus-4-7` | normalized | `anthropic/claude-opus-4.7` |
| compute/providers/anthropic.json | anthropic | `claude-sonnet-4-6` | normalized | `anthropic/claude-sonnet-4.6` |
| compute/providers/anthropic.json | anthropic | `claude-haiku-4-5` | normalized | `anthropic/claude-haiku-4.5` |
| compute/providers/baichuan.json | baichuan | `Baichuan-M3-Plus` | none | |
| compute/providers/baichuan.json | baichuan | `Baichuan-M3` | none | |
| compute/providers/baichuan.json | baichuan | `Baichuan-M2-Plus` | none | |
| compute/providers/baichuan.json | baichuan | `Baichuan-M2` | none | |
| compute/providers/baidu.json | baidu | `ernie-5.0-thinking-latest` | stripped | `baidu/ernie-5.0-thinking-preview` |
| compute/providers/baidu.json | baidu | `ernie-5.0` | similar | `baidu/ernie-5.0-thinking-preview` |
| compute/providers/baidu.json | baidu | `ernie-4.5-turbo-128k` | none | |
| compute/providers/baidu.json | baidu | `ernie-4.5-turbo-20260402` | none | |
| compute/providers/baidu.json | baidu | `ernie-x1.1` | stripped | `baidu/ernie-x1.1-preview` |
| compute/providers/cohere.json | cohere | `command-a-03-2025` | none | |
| compute/providers/cohere.json | cohere | `command-r7b-12-2024` | none | |
| compute/providers/cohere.json | cohere | `embed-v4.0` | none | |
| compute/providers/cohere.json | cohere | `rerank-v3.5` | none | |
| compute/providers/dashscope.json | dashscope | `qwen3.6-plus` | exact | `qwen/qwen3.6-plus` |
| compute/providers/dashscope.json | dashscope | `qwen3.6-flash` | ambiguous | |
| compute/providers/dashscope.json | dashscope | `qwen3.5-plus` | exact | `qwen/qwen3.5-plus` |
| compute/providers/dashscope.json | dashscope | `qwen-max` | none | |
| compute/providers/dashscope.json | dashscope | `qwen-plus` | none | |
| compute/providers/dashscope.json | dashscope | `qwen-turbo` | none | |
| compute/providers/dashscope.json | dashscope | `qwen-long` | none | |
| compute/providers/dashscope.json | dashscope | `qwen3-max` | exact | `qwen/qwen3-max` |
| compute/providers/dashscope.json | dashscope | `qwen3-vl-plus` | exact | `qwen/qwen3-vl-plus` |
| compute/providers/dashscope.json | dashscope | `qwen3-vl-flash` | ambiguous | |
| compute/providers/dashscope.json | dashscope | `text-embedding-v3` | none | |
| compute/providers/dashscope.json | dashscope | `text-embedding-v4` | none | |
| compute/providers/dashscope.json | dashscope | `qwen3-rerank` | none | |
| compute/providers/dashscope.json | dashscope | `cosyvoice-v2` | none | |
| compute/providers/dashscope.json | dashscope | `paraformer-v2` | none | |
| compute/providers/dashscope.json | dashscope | `wanx-v2` | none | |
| compute/providers/dashscope.json | dashscope | `wanx-video` | none | |
| compute/providers/dashscope.json | dashscope | `cosyvoice-clone` | none | |
| compute/providers/dashscope.json | dashscope | `qwen-omni-turbo` | none | |
| compute/providers/dashscope.json | dashscope | `qwen3-max-trans` | similar | `qwen/qwen3-max` |
| compute/providers/deepseek.json | deepseek | `deepseek-chat` | exact | `deepseek/deepseek-chat` |
| compute/providers/deepseek.json | deepseek | `deepseek-reasoner` | exact | `deepseek/deepseek-reasoner` |
| compute/providers/google.json | google | `gemini-3.1-pro-preview` | exact | `google/gemini-3.1-pro-preview` |
| compute/providers/google.json | google | `gemini-3-flash-preview` | exact | `google/gemini-3-flash-preview` |
| compute/providers/google.json | google | `gemini-3.1-flash-lite-preview` | exact | `google/gemini-3.1-flash-lite-preview` |
| compute/providers/google.json | google | `gemini-2.5-pro` | exact | `google/gemini-2.5-pro` |
| compute/providers/google.json | google | `gemini-2.5-flash` | exact | `google/gemini-2.5-flash` |
| compute/providers/google.json | google | `text-embedding-005` | none | |
| compute/providers/internal-testing.json | internal-testing | `MiniMax-M2.7-highspeed` | none | |
| compute/providers/internal-testing.json | internal-testing | `glm-5.1` | none | |
| compute/providers/internal-testing.json | internal-testing | `glm-5` | none | |
| compute/providers/internal-testing.json | internal-testing | `glm-5-turbo` | none | |
| compute/providers/internal-testing.json | internal-testing | `glm-4.7` | none | |
| compute/providers/internal-testing.json | internal-testing | `kimi-k2.6-code-preview` | none | |
| compute/providers/internal-testing.json | internal-testing | `kimi-k2.5` | none | |
| compute/providers/internal-testing.json | internal-testing | `MiniMax-M2.5` | none | |
| compute/providers/internal-testing.json | internal-testing | `qwen3.6-plus` | none | |
| compute/providers/internal-testing.json | internal-testing | `qwen3.5-plus` | none | |
| compute/providers/internal-testing.json | internal-testing | `qwen3.5-35b-a3b` | none | |
| compute/providers/internal-testing.json | internal-testing | `qwen3.5-27b` | none | |
| compute/providers/internal-testing.json | internal-testing | `qwen3-max-2026-01-23` | none | |
| compute/providers/internal-testing.json | internal-testing | `doubao-seed-2-0-code-preview-260215` | none | |
| compute/providers/kling.json | kling | `kling-v2-5-turbo` | none | |
| compute/providers/kling.json | kling | `kling-v2-5-turbo-pro` | none | |
| compute/providers/kling.json | kling | `kling-v2` | none | |
| compute/providers/kling.json | kling | `kling-v2-master` | none | |
| compute/providers/lingyiwanwu.json | lingyiwanwu | `yi-lightning` | none | |
| compute/providers/lingyiwanwu.json | lingyiwanwu | `yi-vision-v2` | none | |
| compute/providers/local-whisper.json | local-whisper | `whisper-large-v3` | none | |
| compute/providers/minimax.json | minimax | `MiniMax-M2.7` | normalized | `minimax/minimax-m2.7` |
| compute/providers/minimax.json | minimax | `MiniMax-M2.7-highspeed` | normalized | `minimax/minimax-m2.7-highspeed` |
| compute/providers/minimax.json | minimax | `MiniMax-M2.5` | normalized | `minimax/minimax-m2.5` |
| compute/providers/minimax.json | minimax | `MiniMax-M2.5-highspeed` | ambiguous | |
| compute/providers/minimax.json | minimax | `MiniMax-M2.1` | normalized | `minimax/minimax-m2.1` |
| compute/providers/minimax.json | minimax | `MiniMax-M2.1-highspeed` | ambiguous | |
| compute/providers/minimax.json | minimax | `MiniMax-Text-01` | none | |
| compute/providers/mistral.json | mistral | `mistral-large-latest` | similar | `mistralai/mistral-large-2512` |
| compute/providers/mistral.json | mistral | `mistral-small-latest` | none | |
| compute/providers/mistral.json | mistral | `codestral-latest` | none | |
| compute/providers/moonshot.json | moonshot | `kimi-k2.6` | exact | `moonshotai/kimi-k2.6` |
| compute/providers/moonshot.json | moonshot | `kimi-k2.5` | exact | `moonshotai/kimi-k2.5` |
| compute/providers/moonshot.json | moonshot | `kimi-k2` | ambiguous | |
| compute/providers/moonshot.json | moonshot | `kimi-k2-thinking` | exact | `moonshotai/kimi-k2-thinking` |
| compute/providers/moonshot.json | moonshot | `moonshot-v1-8k` | none | |
| compute/providers/moonshot.json | moonshot | `moonshot-v1-32k` | none | |
| compute/providers/moonshot.json | moonshot | `moonshot-v1-128k` | none | |
| compute/providers/ollama.json | ollama | `llama3.1:70b` | none | |
| compute/providers/openai.json | openai | `gpt-5.2` | exact | `openai/gpt-5.2` |
| compute/providers/openai.json | openai | `gpt-5.2-pro` | exact | `openai/gpt-5.2-pro` |
| compute/providers/openai.json | openai | `gpt-5.1` | exact | `openai/gpt-5.1` |
| compute/providers/openai.json | openai | `gpt-5` | exact | `openai/gpt-5` |
| compute/providers/openai.json | openai | `gpt-5-pro` | exact | `openai/gpt-5-pro` |
| compute/providers/openai.json | openai | `gpt-5-mini` | exact | `openai/gpt-5-mini` |
| compute/providers/openai.json | openai | `gpt-5-nano` | exact | `openai/gpt-5-nano` |
| compute/providers/openai.json | openai | `gpt-4.1` | exact | `openai/gpt-4.1` |
| compute/providers/openai.json | openai | `gpt-4.1-mini` | exact | `openai/gpt-4.1-mini` |
| compute/providers/openai.json | openai | `gpt-4.1-nano` | exact | `openai/gpt-4.1-nano` |
| compute/providers/openai.json | openai | `gpt-4o` | exact | `openai/gpt-4o` |
| compute/providers/openai.json | openai | `gpt-4o-mini` | exact | `openai/gpt-4o-mini` |
| compute/providers/openai.json | openai | `text-embedding-3-small` | none | |
| compute/providers/openai.json | openai | `text-embedding-3-large` | none | |
| compute/providers/openai.json | openai | `tts-1` | none | |
| compute/providers/openai.json | openai | `tts-1-hd` | none | |
| compute/providers/openai.json | openai | `whisper-1` | none | |
| compute/providers/openai.json | openai | `o3` | none | |
| compute/providers/openai.json | openai | `o3-pro` | none | |
| compute/providers/openai.json | openai | `o3-mini` | none | |
| compute/providers/openai.json | openai | `o4-mini` | exact | `openai/o4-mini` |
| compute/providers/openai.json | openai | `dall-e-3` | none | |
| compute/providers/openai.json | openai | `gpt-4o-realtime` | ambiguous | |
| compute/providers/openai.json | openai | `gpt-4o-realtime-preview` | ambiguous | |
| compute/providers/openrouter.json | openrouter | `openrouter/auto` | none | |
| compute/providers/openrouter.json | openrouter | `openai/gpt-oss-120b:free` | none | |
| compute/providers/openrouter.json | openrouter | `qwen/qwen3-coder:free` | none | |
| compute/providers/perplexity.json | perplexity | `sonar-pro` | none | |
| compute/providers/perplexity.json | perplexity | `sonar-reasoning-pro` | none | |
| compute/providers/perplexity.json | perplexity | `sonar` | none | |
| compute/providers/siliconflow.json | siliconflow | `Qwen/Qwen3-Coder-480B-A35B-Instruct` | none | |
| compute/providers/siliconflow.json | siliconflow | `Qwen/Qwen3-235B-A22B-Instruct-2507` | ambiguous | |
| compute/providers/siliconflow.json | siliconflow | `BAAI/bge-m3` | none | |
| compute/providers/stability.json | stability | `stable-diffusion-3.5-large` | none | |
| compute/providers/tencent.json | tencent | `hunyuan-2.0-thinking-20251109` | stripped | `tencent/hunyuan-2.0-thinking` |
| compute/providers/tencent.json | tencent | `hunyuan-2.0-instruct-20251111` | similar | `tencent/hunyuan-2.0-thinking` |
| compute/providers/tencent.json | tencent | `hunyuan-turbos-latest` | none | |
| compute/providers/volcengine.json | volcengine | `doubao-2.0-pro` | ambiguous | |
| compute/providers/volcengine.json | volcengine | `doubao-seed-1.8` | exact | `bytedance/doubao-seed-1.8` |
| compute/providers/volcengine.json | volcengine | `doubao-seed-1.6` | ambiguous | |
| compute/providers/volcengine.json | volcengine | `doubao-seed-1.6-thinking` | similar | `bytedance/doubao-seed-1.8` |
| compute/providers/volcengine.json | volcengine | `doubao-seed-1.6-flash` | similar | `bytedance/doubao-seed-1.8` |
| compute/providers/volcengine.json | volcengine | `doubao-seed-1.6-lite` | ambiguous | |
| compute/providers/volcengine.json | volcengine | `doubao-seed-1.6-vision` | similar | `bytedance/doubao-seed-1.8` |
| compute/providers/volcengine.json | volcengine | `doubao-seed-code` | exact | `bytedance/doubao-seed-code` |
| compute/providers/volcengine.json | volcengine | `deepseek-v3.2` | none | |
| compute/providers/volcengine.json | volcengine | `deepseek-r1` | none | |
| compute/providers/volcengine.json | volcengine | `kimi-k2-volcengine` | none | |
| compute/providers/volcengine.json | volcengine | `glm-4-7` | none | |
| compute/providers/volcengine.json | volcengine | `doubao-embedding` | none | |
| compute/providers/volcengine.json | volcengine | `volc-mega-tts-clone` | none | |
| compute/providers/volcengine.json | volcengine | `volc-realtime-voice` | none | |
| compute/providers/volcengine.json | volcengine | `volc-simultaneous` | none | |
| compute/providers/volcengine.json | volcengine | `volc-translation` | none | |
| compute/providers/xai.json | xai | `grok-4.20-0309-reasoning` | ambiguous | |
| compute/providers/xai.json | xai | `grok-4-1-fast-reasoning` | ambiguous | |
| compute/providers/xunfei.json | xunfei | `spark-x` | none | |
| compute/providers/xunfei.json | xunfei | `4.0Ultra` | none | |
| compute/providers/zhipu-embedding.json | zhipu-embedding | `embedding-3` | none | |
| compute/providers/zhipu.json | zhipu | `glm-5.1` | exact | `z-ai/glm-5.1` |
| compute/providers/zhipu.json | zhipu | `glm-5-turbo` | exact | `z-ai/glm-5-turbo` |
| compute/providers/zhipu.json | zhipu | `glm-5` | exact | `z-ai/glm-5` |
| compute/providers/zhipu.json | zhipu | `glm-4.7` | exact | `z-ai/glm-4.7` |
| compute/providers/zhipu.json | zhipu | `glm-4.7-thinking` | ambiguous | |
| compute/providers/zhipu.json | zhipu | `glm-5v-turbo` | exact | `z-ai/glm-5v-turbo` |
| compute/providers/zhipu.json | zhipu | `glm-4.6v` | exact | `z-ai/glm-4.6v` |
| compute/providers/zhipu.json | zhipu | `glm-4.6` | exact | `z-ai/glm-4.6` |

5058
outputs/field-audit/zenmux-sync-report.json Normal file
View File

File diff suppressed because it is too large Load Diff

186
outputs/field-audit/zenmux-sync-report.md Normal file
View File

@@ -0,0 +1,186 @@
# ZenMux Sync Report
- source: `/tmp/zenmux-models.json`
- generatedAt: `2026-04-25T16:15:04.854Z`
- actualModels: **160**
- sourceModels: **133**
- matchedModels: **57**
- unmatchedModels: **88**
- ambiguousModels: **15**
- nullSamplingFields: **0**
- updatedModels: **0**
- updatedFiles: **0**
## Field Coverage
- synced: none; this audit run is read-only and does not mutate JSON config.
- reviewed from JSON: `modelName`, `displayName`, `serviceType`, `contextWindow`, `maxOutputTokens`, `inputPrice`, `outputPrice`, `capabilities`, `defaultTemperature`, `defaultTopP`, `extra`.
- guardrail: `defaultTemperature` and `defaultTopP` must be omitted or numbers; `null` is invalid.
## Updated Models
- (none)
## Skipped / Reviewed Models
- compute/coding-plans/dashscope-coding.json :: qwen3-coder-plus -> matched-exact:qwen/qwen3-coder-plus
- compute/coding-plans/dashscope-coding.json :: qwen3-max -> matched-exact:qwen/qwen3-max
- compute/coding-plans/infini-coding.json :: deepseek-v3 -> no-match
- compute/coding-plans/kwai-coding.json :: kwai-coder -> no-match
- compute/coding-plans/minimax-coding.json :: MiniMax-M1 -> no-match
- compute/coding-plans/moonshot-coding.json :: kimi-k2 -> ambiguous:moonshotai/kimi-k2.6,moonshotai/kimi-k2.5,moonshotai/kimi-k2-thinking,moonshotai/kimi-k2-0905,moonshotai/kimi-k2-0711
- compute/coding-plans/moorethread-coding.json :: mt-coder -> no-match
- compute/coding-plans/volcengine-coding.json :: ark-code-latest -> no-match
- compute/coding-plans/zhipu-coding.json :: glm-5 -> matched-exact:z-ai/glm-5
- compute/coding-plans/zhipu-coding.json :: glm-4.7 -> matched-exact:z-ai/glm-4.7
- compute/providers/anthropic.json :: claude-opus-4-7 -> matched-normalized:anthropic/claude-opus-4.7
- compute/providers/anthropic.json :: claude-sonnet-4-6 -> matched-normalized:anthropic/claude-sonnet-4.6
- compute/providers/anthropic.json :: claude-haiku-4-5 -> matched-normalized:anthropic/claude-haiku-4.5
- compute/providers/baichuan.json :: Baichuan-M3-Plus -> no-match
- compute/providers/baichuan.json :: Baichuan-M3 -> no-match
- compute/providers/baichuan.json :: Baichuan-M2-Plus -> no-match
- compute/providers/baichuan.json :: Baichuan-M2 -> no-match
- compute/providers/baidu.json :: ernie-5.0-thinking-latest -> matched-stripped:baidu/ernie-5.0-thinking-preview
- compute/providers/baidu.json :: ernie-5.0 -> matched-similar:baidu/ernie-5.0-thinking-preview
- compute/providers/baidu.json :: ernie-4.5-turbo-128k -> no-match
- compute/providers/baidu.json :: ernie-4.5-turbo-20260402 -> no-match
- compute/providers/baidu.json :: ernie-x1.1 -> matched-stripped:baidu/ernie-x1.1-preview
- compute/providers/cohere.json :: command-a-03-2025 -> no-match
- compute/providers/cohere.json :: command-r7b-12-2024 -> no-match
- compute/providers/cohere.json :: embed-v4.0 -> no-match
- compute/providers/cohere.json :: rerank-v3.5 -> no-match
- compute/providers/dashscope.json :: qwen3.6-plus -> matched-exact:qwen/qwen3.6-plus
- compute/providers/dashscope.json :: qwen3.6-flash -> ambiguous:qwen/qwen3.6-plus,qwen/qwen3.5-flash
- compute/providers/dashscope.json :: qwen3.5-plus -> matched-exact:qwen/qwen3.5-plus
- compute/providers/dashscope.json :: qwen-max -> no-match
- compute/providers/dashscope.json :: qwen-plus -> no-match
- compute/providers/dashscope.json :: qwen-turbo -> no-match
- compute/providers/dashscope.json :: qwen-long -> no-match
- compute/providers/dashscope.json :: qwen3-max -> matched-exact:qwen/qwen3-max
- compute/providers/dashscope.json :: qwen3-vl-plus -> matched-exact:qwen/qwen3-vl-plus
- compute/providers/dashscope.json :: qwen3-vl-flash -> ambiguous:qwen/qwen3.5-flash,qwen/qwen3-vl-plus
- compute/providers/dashscope.json :: text-embedding-v3 -> no-match
- compute/providers/dashscope.json :: text-embedding-v4 -> no-match
- compute/providers/dashscope.json :: qwen3-rerank -> no-match
- compute/providers/dashscope.json :: cosyvoice-v2 -> no-match
- compute/providers/dashscope.json :: paraformer-v2 -> no-match
- compute/providers/dashscope.json :: wanx-v2 -> no-match
- compute/providers/dashscope.json :: wanx-video -> no-match
- compute/providers/dashscope.json :: cosyvoice-clone -> no-match
- compute/providers/dashscope.json :: qwen-omni-turbo -> no-match
- compute/providers/dashscope.json :: qwen3-max-trans -> matched-similar:qwen/qwen3-max
- compute/providers/deepseek.json :: deepseek-chat -> matched-exact:deepseek/deepseek-chat
- compute/providers/deepseek.json :: deepseek-reasoner -> matched-exact:deepseek/deepseek-reasoner
- compute/providers/google.json :: gemini-3.1-pro-preview -> matched-exact:google/gemini-3.1-pro-preview
- compute/providers/google.json :: gemini-3-flash-preview -> matched-exact:google/gemini-3-flash-preview
- compute/providers/google.json :: gemini-3.1-flash-lite-preview -> matched-exact:google/gemini-3.1-flash-lite-preview
- compute/providers/google.json :: gemini-2.5-pro -> matched-exact:google/gemini-2.5-pro
- compute/providers/google.json :: gemini-2.5-flash -> matched-exact:google/gemini-2.5-flash
- compute/providers/google.json :: text-embedding-005 -> no-match
- compute/providers/internal-testing.json :: MiniMax-M2.7-highspeed -> no-match
- compute/providers/internal-testing.json :: glm-5.1 -> no-match
- compute/providers/internal-testing.json :: glm-5 -> no-match
- compute/providers/internal-testing.json :: glm-5-turbo -> no-match
- compute/providers/internal-testing.json :: glm-4.7 -> no-match
- compute/providers/internal-testing.json :: kimi-k2.6-code-preview -> no-match
- compute/providers/internal-testing.json :: kimi-k2.5 -> no-match
- compute/providers/internal-testing.json :: MiniMax-M2.5 -> no-match
- compute/providers/internal-testing.json :: qwen3.6-plus -> no-match
- compute/providers/internal-testing.json :: qwen3.5-plus -> no-match
- compute/providers/internal-testing.json :: qwen3.5-35b-a3b -> no-match
- compute/providers/internal-testing.json :: qwen3.5-27b -> no-match
- compute/providers/internal-testing.json :: qwen3-max-2026-01-23 -> no-match
- compute/providers/internal-testing.json :: doubao-seed-2-0-code-preview-260215 -> no-match
- compute/providers/kling.json :: kling-v2-5-turbo -> no-match
- compute/providers/kling.json :: kling-v2-5-turbo-pro -> no-match
- compute/providers/kling.json :: kling-v2 -> no-match
- compute/providers/kling.json :: kling-v2-master -> no-match
- compute/providers/lingyiwanwu.json :: yi-lightning -> no-match
- compute/providers/lingyiwanwu.json :: yi-vision-v2 -> no-match
- compute/providers/local-whisper.json :: whisper-large-v3 -> no-match
- compute/providers/minimax.json :: MiniMax-M2.7 -> matched-normalized:minimax/minimax-m2.7
- compute/providers/minimax.json :: MiniMax-M2.7-highspeed -> matched-normalized:minimax/minimax-m2.7-highspeed
- compute/providers/minimax.json :: MiniMax-M2.5 -> matched-normalized:minimax/minimax-m2.5
- compute/providers/minimax.json :: MiniMax-M2.5-highspeed -> ambiguous:minimax/minimax-m2.5,minimax/minimax-m2.7-highspeed,minimax/minimax-m2.5-lightning,minimax/minimax-m2,minimax/minimax-m2.7
- compute/providers/minimax.json :: MiniMax-M2.1 -> matched-normalized:minimax/minimax-m2.1
- compute/providers/minimax.json :: MiniMax-M2.1-highspeed -> ambiguous:minimax/minimax-m2.1,minimax/minimax-m2.7-highspeed,minimax/minimax-m2,minimax/minimax-m2.7,minimax/minimax-m2.5
- compute/providers/minimax.json :: MiniMax-Text-01 -> no-match
- compute/providers/mistral.json :: mistral-large-latest -> matched-similar:mistralai/mistral-large-2512
- compute/providers/mistral.json :: mistral-small-latest -> no-match
- compute/providers/mistral.json :: codestral-latest -> no-match
- compute/providers/moonshot.json :: kimi-k2.6 -> matched-exact:moonshotai/kimi-k2.6
- compute/providers/moonshot.json :: kimi-k2.5 -> matched-exact:moonshotai/kimi-k2.5
- compute/providers/moonshot.json :: kimi-k2 -> ambiguous:moonshotai/kimi-k2.6,moonshotai/kimi-k2.5,moonshotai/kimi-k2-thinking,moonshotai/kimi-k2-0905,moonshotai/kimi-k2-0711
- compute/providers/moonshot.json :: kimi-k2-thinking -> matched-exact:moonshotai/kimi-k2-thinking
- compute/providers/moonshot.json :: moonshot-v1-8k -> no-match
- compute/providers/moonshot.json :: moonshot-v1-32k -> no-match
- compute/providers/moonshot.json :: moonshot-v1-128k -> no-match
- compute/providers/ollama.json :: llama3.1:70b -> no-match
- compute/providers/openai.json :: gpt-5.2 -> matched-exact:openai/gpt-5.2
- compute/providers/openai.json :: gpt-5.2-pro -> matched-exact:openai/gpt-5.2-pro
- compute/providers/openai.json :: gpt-5.1 -> matched-exact:openai/gpt-5.1
- compute/providers/openai.json :: gpt-5 -> matched-exact:openai/gpt-5
- compute/providers/openai.json :: gpt-5-pro -> matched-exact:openai/gpt-5-pro
- compute/providers/openai.json :: gpt-5-mini -> matched-exact:openai/gpt-5-mini
- compute/providers/openai.json :: gpt-5-nano -> matched-exact:openai/gpt-5-nano
- compute/providers/openai.json :: gpt-4.1 -> matched-exact:openai/gpt-4.1
- compute/providers/openai.json :: gpt-4.1-mini -> matched-exact:openai/gpt-4.1-mini
- compute/providers/openai.json :: gpt-4.1-nano -> matched-exact:openai/gpt-4.1-nano
- compute/providers/openai.json :: gpt-4o -> matched-exact:openai/gpt-4o
- compute/providers/openai.json :: gpt-4o-mini -> matched-exact:openai/gpt-4o-mini
- compute/providers/openai.json :: text-embedding-3-small -> no-match
- compute/providers/openai.json :: text-embedding-3-large -> no-match
- compute/providers/openai.json :: tts-1 -> no-match
- compute/providers/openai.json :: tts-1-hd -> no-match
- compute/providers/openai.json :: whisper-1 -> no-match
- compute/providers/openai.json :: o3 -> no-match
- compute/providers/openai.json :: o3-pro -> no-match
- compute/providers/openai.json :: o3-mini -> no-match
- compute/providers/openai.json :: o4-mini -> matched-exact:openai/o4-mini
- compute/providers/openai.json :: dall-e-3 -> no-match
- compute/providers/openai.json :: gpt-4o-realtime -> ambiguous:openai/gpt-4o,openai/gpt-4o-mini
- compute/providers/openai.json :: gpt-4o-realtime-preview -> ambiguous:openai/gpt-4o,openai/gpt-4o-mini
- compute/providers/openrouter.json :: openrouter/auto -> no-match
- compute/providers/openrouter.json :: openai/gpt-oss-120b:free -> no-match
- compute/providers/openrouter.json :: qwen/qwen3-coder:free -> no-match
- compute/providers/perplexity.json :: sonar-pro -> no-match
- compute/providers/perplexity.json :: sonar-reasoning-pro -> no-match
- compute/providers/perplexity.json :: sonar -> no-match
- compute/providers/siliconflow.json :: Qwen/Qwen3-Coder-480B-A35B-Instruct -> no-match
- compute/providers/siliconflow.json :: Qwen/Qwen3-235B-A22B-Instruct-2507 -> ambiguous:qwen/qwen3-235b-a22b-2507,qwen/qwen3-235b-a22b-thinking-2507
- compute/providers/siliconflow.json :: BAAI/bge-m3 -> no-match
- compute/providers/stability.json :: stable-diffusion-3.5-large -> no-match
- compute/providers/tencent.json :: hunyuan-2.0-thinking-20251109 -> matched-stripped:tencent/hunyuan-2.0-thinking
- compute/providers/tencent.json :: hunyuan-2.0-instruct-20251111 -> matched-similar:tencent/hunyuan-2.0-thinking
- compute/providers/tencent.json :: hunyuan-turbos-latest -> no-match
- compute/providers/volcengine.json :: doubao-2.0-pro -> ambiguous:bytedance/doubao-seed-2.0-pro,bytedance/doubao-seed-2.0-mini,bytedance/doubao-seed-2.0-lite,bytedance/doubao-seed-2.0-code
- compute/providers/volcengine.json :: doubao-seed-1.8 -> matched-exact:bytedance/doubao-seed-1.8
- compute/providers/volcengine.json :: doubao-seed-1.6 -> ambiguous:bytedance/doubao-seed-1.8,bytedance/doubao-seed-code
- compute/providers/volcengine.json :: doubao-seed-1.6-thinking -> matched-similar:bytedance/doubao-seed-1.8
- compute/providers/volcengine.json :: doubao-seed-1.6-flash -> matched-similar:bytedance/doubao-seed-1.8
- compute/providers/volcengine.json :: doubao-seed-1.6-lite -> ambiguous:bytedance/doubao-seed-1.8,bytedance/doubao-seed-2.0-lite
- compute/providers/volcengine.json :: doubao-seed-1.6-vision -> matched-similar:bytedance/doubao-seed-1.8
- compute/providers/volcengine.json :: doubao-seed-code -> matched-exact:bytedance/doubao-seed-code
- compute/providers/volcengine.json :: deepseek-v3.2 -> no-match
- compute/providers/volcengine.json :: deepseek-r1 -> no-match
- compute/providers/volcengine.json :: kimi-k2-volcengine -> no-match
- compute/providers/volcengine.json :: glm-4-7 -> no-match
- compute/providers/volcengine.json :: doubao-embedding -> no-match
- compute/providers/volcengine.json :: volc-mega-tts-clone -> no-match
- compute/providers/volcengine.json :: volc-realtime-voice -> no-match
- compute/providers/volcengine.json :: volc-simultaneous -> no-match
- compute/providers/volcengine.json :: volc-translation -> no-match
- compute/providers/xai.json :: grok-4.20-0309-reasoning -> ambiguous:x-ai/grok-4-fast-non-reasoning,x-ai/grok-4,x-ai/grok-4.2-fast-non-reasoning,x-ai/grok-4.1-fast-non-reasoning
- compute/providers/xai.json :: grok-4-1-fast-reasoning -> ambiguous:x-ai/grok-4.1-fast-non-reasoning,x-ai/grok-4.1-fast,x-ai/grok-4-fast-non-reasoning,x-ai/grok-4-fast,x-ai/grok-4.2-fast-non-reasoning
- compute/providers/xunfei.json :: spark-x -> no-match
- compute/providers/xunfei.json :: 4.0Ultra -> no-match
- compute/providers/zhipu-embedding.json :: embedding-3 -> no-match
- compute/providers/zhipu.json :: glm-5.1 -> matched-exact:z-ai/glm-5.1
- compute/providers/zhipu.json :: glm-5-turbo -> matched-exact:z-ai/glm-5-turbo
- compute/providers/zhipu.json :: glm-5 -> matched-exact:z-ai/glm-5
- compute/providers/zhipu.json :: glm-4.7 -> matched-exact:z-ai/glm-4.7
- compute/providers/zhipu.json :: glm-4.7-thinking -> ambiguous:z-ai/glm-4.7,z-ai/glm-4.7-flashx,z-ai/glm-4.7-flash-free,z-ai/glm-4.6v,z-ai/glm-4.6
- compute/providers/zhipu.json :: glm-5v-turbo -> matched-exact:z-ai/glm-5v-turbo
- compute/providers/zhipu.json :: glm-4.6v -> matched-exact:z-ai/glm-4.6v
- compute/providers/zhipu.json :: glm-4.6 -> matched-exact:z-ai/glm-4.6

BIN
outputs/field-audit/模型字段映射-官方文档核对.xlsx Normal file
View File

Binary file not shown.