Add Mistral AI provider and models support #1
Conversation
- Add mistral provider configuration (v1/providers/mistral.yaml)
- OpenAI-compatible API format
- Support for Mistral-specific parameters (parallel_tool_calls, safe_prompt, etc.)
- SSE streaming support
- Tool calling support
- Add Mistral model definitions (v1/models/mistral.yaml)
- 8 models: mistral-small/medium/large-latest, pixtral-small/large-latest,
open-mistral-7b, open-mixtral-8x7b, mistral-tiny
- Includes capabilities, context windows, and metadata
Based on official Mistral AI API documentation: https://docs.mistral.ai/api
![cursor[bot]](https://avatars.githubusercontent.com/in/1210556?s=60&v=4){kind=small}
There was a problem hiding this comment.
This PR is being reviewed by Cursor Bugbot
Details
You are on the Bugbot Free tier. On this plan, Bugbot will review limited PRs each billing cycle.
To receive Bugbot reviews on all of your PRs, visit the Cursor dashboard to activate Pro and start your 14-day free trial.
| type_path: "error.type" | ||
| param_path: "error.param" | ||
|
|
||
| capabilities: [chat, tools, streaming, parallel_tools, agentic] |
There was a problem hiding this comment.
Provider missing vision capability declared by Pixtral models
Medium Severity
The Mistral provider's capabilities list at line 159 is [chat, tools, streaming, parallel_tools, agentic] but does not include vision. However, pixtral-small-latest and pixtral-large-latest models both declare vision in their capabilities. Other providers (anthropic, openai, gemini, qwen) all include vision at the provider level when their models support it. This inconsistency could cause capability validation failures or prevent vision functionality from being properly detected for Pixtral models.
Additional Locations (2)
|
merge it |
Add mistral provider configuration (v1/providers/mistral.yaml)
Add Mistral model definitions (v1/models/mistral.yaml)
Based on official Mistral AI API documentation: https://docs.mistral.ai/api
Note
Introduces Mistral as a first-class provider with OpenAI-style chat compatibility and comprehensive runtime mappings.
v1/providers/mistral.yaml: configures base URL/auth, OpenAI-compatiblechat/completionsendpoint,list_modelsservice, termination reason normalization, tool-calling normalization, rate-limit headers, retry policy, parameter mappings (incl.parallel_tool_calls,safe_prompt), response paths, SSE streaming decoder/event map, multi-candidate support, and error/response mappingsv1/models/mistral.yaml: registers 8 models (mistral-*-latest,pixtral-*-latest,open-mistral-7b,open-mixtral-8x7b,mistral-tiny) with context windows, capabilities (chat/tools/streaming/vision/agentic), and tagsWritten by Cursor Bugbot for commit 93041b8. This will update automatically on new commits. Configure here.