chore: update model catalog from bot issues - #1024
Conversation
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
|
Codex (@codex) review |
![chatgpt-codex-connector[bot]](https://avatars.githubusercontent.com/in/1144995?s=60&v=4){kind=small}
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: c3b4e15672
ℹ️ About Codex in GitHub
Codex has been enabled to automatically review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "Codex (@codex) review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
When you sign up for Codex through ChatGPT, Codex can also answer questions or update the PR, like "Codex (@codex) address that feedback".
| "format": "google", | ||
| "flavor": "chat", |
There was a problem hiding this comment.
When callers select this newly advertised model, the Google handler still invokes generateContent or streamGenerateContent (packages/proxy/src/proxy.ts:3483-3488). Gemini Live models are served through the bidirectional Live API instead, and this proxy has no bidiGenerateContent implementation, so standard chat requests for this entry will fail rather than reach the model. Either add Live API transport support before exposing it or omit it from this proxy catalog.
Useful? React with 👍 / 👎.
| "eu.anthropic.claude-opus-5", | ||
| "global.anthropic.claude-opus-5", | ||
| "publishers/anthropic/models/claude-opus-5", | ||
| "us.anthropic.claude-opus-5", | ||
| "eu.anthropic.claude-opus-5", | ||
| "au.anthropic.claude-opus-5" | ||
| "us.anthropic.claude-opus-5" |
There was a problem hiding this comment.
For callers using au.anthropic.claude-opus-5, removing that identifier from this equivalence list isolates it from the canonical, Vertex, and other Bedrock aliases, so getModelEndpointTypes now returns only its direct bedrock mapping instead of the equivalent-provider union used for the other Opus 5 IDs. The AU model entry still exists and declares the same parent; restore it here and add au to ANTHROPIC_BEDROCK_SCOPES so the normalizer does not delete it again.
Useful? React with 👍 / 👎.
## Model deprecation audit
Each model below returned a definitive not-found / deprecated response
from its provider (a single 404 / not-found is treated as
authoritative). Account/region-scoped providers (bedrock, vertex,
databricks) are surfaced for manual review, not auto-removed.
```json
{
"deprecations": [
{
"model": "moonshotai/Kimi-K2.5",
"provider": "baseten",
"reason": "absent from list + probe not-found",
"status": 410,
"detail": "{\"error\":\"the model version you are trying to access has been deprecated.\"}\n"
},
{
"model": "nvidia/Nemotron-120B-A12B",
"provider": "baseten",
"reason": "absent from list + probe not-found",
"status": 410,
"detail": "{\"error\":\"the model version you are trying to access has been deprecated.\"}\n"
},
{
"model": "zai-org/GLM-5",
"provider": "baseten",
"reason": "absent from list + probe not-found",
"status": 410,
"detail": "{\"error\":\"the model version you are trying to access has been deprecated.\"}\n"
},
{
"model": "zai-org/GLM-5.1",
"provider": "baseten",
"reason": "absent from list + probe not-found",
"status": 410,
"detail": "{\"error\":\"the model version you are trying to access has been deprecated.\"}\n"
},
{
"model": "meta-llama/llama-4-scout-17b-16e-instruct",
"provider": "groq",
"reason": "absent from list + probe not-found",
"status": 404,
"detail": "{\"error\":{\"message\":\"The model `meta-llama/llama-4-scout-17b-16e-instruct` does not exist or you do not have access to it.\",\"type\":\"invalid_request_error\",\"code"
},
{
"model": "qwen/qwen3-32b",
"provider": "groq",
"reason": "absent from list + probe not-found",
"status": 404,
"detail": "{\"error\":{\"message\":\"The model `qwen/qwen3-32b` does not exist or you do not have access to it.\",\"type\":\"invalid_request_error\",\"code\":\"model_not_found\"}}\n"
}
],
"reportOnly": [
{
"provider": "bedrock",
"modelCount": 122
},
{
"provider": "databricks",
"modelCount": 36
},
{
"provider": "fireworks",
"modelCount": 266
},
{
"provider": "vertex",
"modelCount": 122
}
],
"skipped": [
{
"provider": "cohere",
"reason": "no adapter"
},
{
"provider": "lepton",
"reason": "no adapter"
},
{
"provider": "openrouter",
"reason": "no adapter"
},
{
"provider": "replicate",
"reason": "no adapter"
}
]
}
```
---------
Co-authored-by: erin2722 <16248113+erin2722@users.noreply.github.com>
Co-authored-by: Erin McNulty <erin.mcnulty@braintrustdata.com>
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
Automated sync of model metadata and newly available models from the approved provider allowlist. --------- Co-authored-by: erin2722 <16248113+erin2722@users.noreply.github.com> Co-authored-by: Erin McNulty <erin.mcnulty@braintrustdata.com> Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
Single catalog PR containing every genuine "update model catalog" change from the week (#989/#1000/#1003/#1008/#1014/#1017/#1021/#1024), rebuilt on current main after #1009 (sync) and #986 (deprecation) merged. 28 new models + 22 metadata/deprecation-marking changes, with prior review fixes: gemma-3 converse format, gpt-5.6 bedrock cache-write, databricks-glm-5-2 1M context, vertex llama-4 maas pricing/quota, gpt-oss-20b groq-only pin, proxy.ts OpenAI/xAI vertex-maas OpenAPI routing. Also restores GLM-5.2 cached-input to $0.26 (Baseten/Together) — the merged sync left main at Fireworks' $0.14. Validated: gemma-3-4b/12b + nemotron + GLM-5.2 invoke 200 via gateway. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
…com/braintrustdata/braintrust-proxy into chore/autofix-bot-issues-2026-07-26 # Conflicts: # packages/proxy/schema/index.ts
…1024 Per review, narrow this catalog PR to models that belong here: - Remove realtime/Live models (gpt-realtime-2.1, gpt-realtime-2.1-mini, gemini-3.1-flash-live-preview) — not chat/completions models. - Remove Vertex MaaS additions (llama-4 maas, mistral vertex, gpt-oss maas, xai vertex) + the proxy.ts OpenAI/xAI routing change — moved to a dedicated PR. - Remove Databricks endpoints that return ENDPOINT_NOT_FOUND (databricks-gpt-5-4-mini, databricks-gemini-3-6-flash) — not deployed on the account. Remaining: 14 new models + 22 metadata/deprecation changes. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
1 participant
Automated daily batch of model catalog updates from bot issues.
Included issues
Summary
gemini-3.1-flash-live-previewgemini-3.1-flash-live-preview2
3
Verified metadata
#1023: [BOT ISSUE] Google: add missing gemini-3.1-flash-live-preview
Verification notes
No LLM verification step ran; model metadata was already complete in the issue.
sync_models vs proposed update
sync_models cross-check found no pricing/token discrepancies for the changed models.
No sync_models discrepancies were noted.