fix: retire models, feature fixes#1299
Conversation
|
/test-models |
There was a problem hiding this comment.
Cursor Bugbot has reviewed your changes and found 1 potential issue.
❌ Bugbot Autofix is OFF. To automatically fix reported issues with cloud agents, enable autofix in the Cursor dashboard.
Reviewed by Cursor Bugbot for commit 547fd5c. Configure here.
Gateway test results
Skipped (4)
Skip reason
Skip reason
Skip reason
Skip reason |
Gateway test results
Successes (4)
Output
Output
Output
OutputSkipped (1)
Skip reason |
Gateway test results
Skipped (6)
Skip reason
Skip reason
Skip reason
Skip reason
Skip reason
Skip reason |
Gateway test results
Skipped (1)
Skip reason |
|
/test-models |
Gateway test results
Skipped (6)
Skip reason
Skip reason
Skip reason
Skip reason
Skip reason
Skip reason |
Gateway test results
Failures (2)
ErrorCode snippetfrom openai import OpenAI
client = OpenAI(api_key="***", base_url="https://internal.devtest.truefoundry.tech/api/llm")
response = client.chat.completions.create(
model="test-v2-deepinfra/ByteDance-Seed-2.0-code",
messages=[
{"role": "user", "content": "List 3 colors with their hex codes in JSON."},
],
response_format={"type": "json_object"},
stream=True,
)
import json as _json
_accumulated = ""
for chunk in response:
if chunk.choices and len(chunk.choices) > 0:
delta = chunk.choices[0].delta
if delta.content is not None:
_accumulated += delta.content
print(delta.content, end="", flush=True)
if not _accumulated:
raise Exception("VALIDATION FAILED: json-output stream - no content received")
_json.loads(_accumulated)
print("\nVALIDATION: json-output stream SUCCESS")
ErrorCode snippetfrom openai import OpenAI
client = OpenAI(api_key="***", base_url="https://internal.devtest.truefoundry.tech/api/llm")
response = client.chat.completions.create(
model="test-v2-deepinfra/ByteDance-Seed-2.0-code",
messages=[
{"role": "user", "content": "List 3 colors with their hex codes in JSON."},
],
response_format={"type": "json_object"},
stream=False,
)
import json as _json
_content = response.choices[0].message.content
print(_content)
if not _content:
raise Exception("VALIDATION FAILED: json-output - response content is empty")
_json.loads(_content)
print("VALIDATION: json-output SUCCESS")Successes (6)
Output
Output
Output
Output
Output
OutputSkipped (1)
Skip reason |
Gateway test results
Skipped (1)
Skip reason |
Gateway test results
Skipped (4)
Skip reason
Skip reason
Skip reason
Skip reason |

Note
Medium Risk
Catalog-only changes, but marking models retired affects routing and discoverability for anyone still referencing those IDs; incorrect entries could hide usable models or leave bad ones selectable.
Overview
This PR updates provider model catalog YAML to reflect models that are no longer available or should not be selected, plus a couple of capability/param fixes.
Lifecycle: Many entries across google-gemini, google-vertex, deepinfra, and openrouter move to
status: retired(fromactiveordeprecated). Several Gemini 2.0 Flash / Flash Lite variants on Vertex also gainisDeprecated: truealongside retirement. OpenRouter listings for Mistral, Baidu ERNIE, Alibaba Tongyi, Arcee Trinity, and related Gemini 2.0 routes follow the same pattern.Metadata tweaks: ByteDance/Seed-2.0-code on DeepInfra replaces the
json_outputfeature withstructured_output. anthropic/claude-opus-4-8 on Google Vertex addsremoveParams: [temperature]so callers do not send an unsupported parameter.Reviewed by Cursor Bugbot for commit 123f1a5. Bugbot is set up for automated code reviews on this repo. Configure here.