feat(mistral-ai/mistral-code-fim-latest): add new models [bot]

[models-bot]

Auto-generated by model-addition-agent for mistral-ai/mistral-code-fim-latest.

---

Note

Low Risk
Single declarative model config file with no application logic or security-sensitive changes.

Overview
Adds a new Mistral AI provider definition for mistral-code-fim-latest, exposing it as an active model for completion and chat (with function_calling).

The entry sets per-token pricing, a 256k context window, text/code input and output modalities, and a default temperature of 0.3.

^{Reviewed by Cursor Bugbot for commit b1999f1. Bugbot is set up for automated code reviews on this repo. Configure here.}

[cursor]

Cursor Bugbot has reviewed your changes and found 2 potential issues.

^{❌ Bugbot Autofix is OFF. To automatically fix reported issues with cloud agents, enable autofix in the Cursor dashboard.}

^{Reviewed by Cursor Bugbot for commit e7cfe39. Configure here.}

[cursor]

FIM model advertises chat tools

Medium Severity

mistral-code-fim-latest declares function_calling and supportedModes including chat, but Mistral’s fill-in-the-middle API is a separate completions surface without chat messages or tools. Consumers may route or enable capabilities this model does not support.

 

^{Reviewed by Cursor Bugbot for commit e7cfe39. Configure here.}

[github-actions]

/test-models

[harshiv-26]

Gateway test results

• Total: 4
• Passed: 0
• Failed: 1
• Validation failed: 0
• Errored: 3
• Skipped: 0
• Success rate: 0.0%

Provider	Model	Scenarios
mistral-ai	mistral-code-fim-latest	failure: params error: tool-call:stream, tool-call, params:stream

Failures (4)

mistral-ai/mistral-code-fim-latest — tool-call:stream (error)

Error

Endpoint returned no snippets

mistral-ai/mistral-code-fim-latest — tool-call (error)

Error

Endpoint returned no snippets

mistral-ai/mistral-code-fim-latest — params:stream (error)

Error

Endpoint returned empty snippet

mistral-ai/mistral-code-fim-latest — params (failure)

Error

Traceback (most recent call last):
  File "/tmp/tmpnb3e31wn/snippet.py", line 5, in <module>
    response = client.completions.create(
               ^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.11/site-packages/openai/_utils/_utils.py", line 286, in wrapper
    return func(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.11/site-packages/openai/resources/completions.py", line 541, in create
    return self._post(
           ^^^^^^^^^^^
  File "/usr/local/lib/python3.11/site-packages/openai/_base_client.py", line 1259, in post
    return cast(ResponseT, self.request(cast_to, opts, stream=stream, stream_cls=stream_cls))
                           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.11/site-packages/openai/_base_client.py", line 1047, in request
    raise self._make_status_error_from_response(err.response) from None
openai.BadRequestError: Error code: 400 - {'status': 'failure', 'message': 'Request translation failed: complete is not supported by mistral-ai', 'error': {'message': 'Request translation failed: complete is not supported by mistral-ai', 'type': 'APIError', 'code': '400'}, 'error_origin_level': 'api_error', 'provider': 'mistral-ai'}

Code snippet

from openai import OpenAI

client = OpenAI(api_key="***", base_url="https://internal.devtest.truefoundry.tech/api/llm")

response = client.completions.create(
    model="test-v2-mistral-ai/mistral-code-fim-latest",
    prompt="What is the capital of France?",
    max_tokens=256,
    temperature=0.3,
)

print(response.choices[0].text)