feat(cohere/north-mini-code-1-0): add new models [bot]#1318
Conversation
|
/test-models |
Gateway test results
|
There was a problem hiding this comment.
Cursor Bugbot has reviewed your changes and found 2 potential issues.
There are 3 total unresolved issues (including 1 from previous review).
❌ Bugbot Autofix is OFF. To automatically fix reported issues with cloud agents, enable autofix in the Cursor dashboard.
Reviewed by Cursor Bugbot for commit b93e60b. Configure here.
|
/test-models |
Gateway test results
Failures (6)
Error
Error
Error
Error
Error
ErrorCode snippetfrom openai import OpenAI
client = OpenAI(api_key="***", base_url="https://internal.devtest.truefoundry.tech/api/llm")
response = client.completions.create(
model="test-v2-cohere/north-mini-code-1-0",
prompt="What is the capital of France?",
max_tokens=256,
temperature=0.7,
)
print(response.choices[0].text) |
|
/test-models |
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-cohere/north-mini-code-1-0",
messages=[
{"role": "system", "content": "You are a helpful assistant. Respond in JSON format."},
{"role": "user", "content": "Hi"},
{"role": "assistant", "content": "Hi, how can I help you"},
{"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")
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-cohere/north-mini-code-1-0",
messages=[
{"role": "system", "content": "You are a helpful assistant. Respond in JSON format."},
{"role": "user", "content": "Hi"},
{"role": "assistant", "content": "Hi, how can I help you"},
{"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")Successes (4)
Output
Output
Output
Output |
|
/test-models |
|
/test-models |
Gateway test results
Successes (4)
Output
Output
Output
Output |
Gateway test results
Successes (4)
Output
Output
Output
Output |

Auto-generated by model-addition-agent for
cohere/north-mini-code-1-0.Note
Low Risk
Additive model metadata only; no runtime, auth, or routing logic changes.
Overview
Adds a new Cohere provider catalog entry for
north-mini-code-1-0, registering it as an active serverless chat model with text in/out.The definition sets 256k context and 64k max output, enables tool_choice and function_calling, and explicitly notes json_output is not supported. Pricing is listed as 0.0 per input/output token (region
*), with a Hugging Face source link.Reviewed by Cursor Bugbot for commit 49dd200. Bugbot is set up for automated code reviews on this repo. Configure here.