fix: support Azure provider with reasoning models #3

New issue

Open

opened 2025-10-14 15:37:53 -06:00 by navan · 0 comments

navan commented

2025-10-14 15:37:53 -06:00

Owner

Originally created by @Crunchyman-ralph on 10/14/2025

Add azure, openrouter, bedrock, and ollama to VALIDATED_PROVIDERS array
Add Azure reasoning models (GPT-5, o1, o3, o3-mini, o4-mini) to supported-models.json
Implement automatic API endpoint detection for Azure reasoning models
Add dual endpoint support (chat/completions vs responses) in AzureProvider
Add smart URL adjustment logic for different Azure configurations
Maintain backward compatibility with existing Azure setups

Fixes #638

🤖 Generated with Claude Code

What type of PR is this?

🐛 Bug fix
✨ Feature
🔌 Integration
📝 Docs
🧹 Refactor
Other:

Description

How to Test This

# Example commands or steps

Expected result:

Contributor Checklist

Created changeset: npm run changeset
Tests pass: npm test
Format check passes: npm run format-check (or npm run format to fix)
Addressed CodeRabbit comments (if any)
Linked related issues (if any)
Manually tested the changes

Changelog Entry

For Maintainers

PR title follows conventional commits
Target branch correct
Labels added
Milestone assigned (if applicable)

Summary by CodeRabbit

New Features
- Added support for new Azure OpenAI models: gpt-5, o1, o3, o3-mini, and o4-mini, with consistent max token limits (up to 100k).
Improvements
- Automatic endpoint selection for reasoning models using the Responses API, reducing setup and errors.
- Expanded provider validation to include Azure, OpenRouter, Bedrock, and Ollama for more reliable compatibility checks.

*Originally created by @Crunchyman-ralph on 10/14/2025* - Add azure, openrouter, bedrock, and ollama to VALIDATED_PROVIDERS array - Add Azure reasoning models (GPT-5, o1, o3, o3-mini, o4-mini) to supported-models.json - Implement automatic API endpoint detection for Azure reasoning models - Add dual endpoint support (chat/completions vs responses) in AzureProvider - Add smart URL adjustment logic for different Azure configurations - Maintain backward compatibility with existing Azure setups Fixes #638 🤖 Generated with [Claude Code](https://claude.ai/code) # What type of PR is this?  - [ ] 🐛 Bug fix - [ ] ✨ Feature - [ ] 🔌 Integration - [ ] 📝 Docs - [ ] 🧹 Refactor - [ ] Other: ## Description  ## Related Issues  ## How to Test This  ```bash # Example commands or steps ``` **Expected result:**  ## Contributor Checklist - [ ] Created changeset: `npm run changeset` - [ ] Tests pass: `npm test` - [ ] Format check passes: `npm run format-check` (or `npm run format` to fix) - [ ] Addressed CodeRabbit comments (if any) - [ ] Linked related issues (if any) - [ ] Manually tested the changes ## Changelog Entry   --- ### For Maintainers - [ ] PR title follows conventional commits - [ ] Target branch correct - [ ] Labels added - [ ] Milestone assigned (if applicable)  ## Summary by CodeRabbit * **New Features** * Added support for new Azure OpenAI models: gpt-5, o1, o3, o3-mini, and o4-mini, with consistent max token limits (up to 100k). * **Improvements** * Automatic endpoint selection for reasoning models using the Responses API, reducing setup and errors. * Expanded provider validation to include Azure, OpenRouter, Bedrock, and Ollama for more reliable compatibility checks.