fix: use openai key for Azure provider options#20333
Closed
ToastyTheBot wants to merge 5 commits intoanomalyco:devfrom
Closed
fix: use openai key for Azure provider options#20333ToastyTheBot wants to merge 5 commits intoanomalyco:devfrom
ToastyTheBot wants to merge 5 commits intoanomalyco:devfrom
Conversation
…leakage When generating session titles, the user's model variant (e.g., "max" which maps to output_config.effort) was leaking into the LLM.stream call for the title agent. Since the title agent uses a small model (e.g., haiku) that does not support the effort parameter, this caused a 400 error from the Anthropic API that was silently swallowed by Effect.ignore. This fix strips the variant from the user info when calling LLM.stream for title generation, ensuring the small model receives only compatible parameters. Fixes anomalyco#20269
When a custom provider uses npm: "@ai-sdk/azure", the getLanguage function was falling back to sdk.languageModel() which bypasses the useCompletionUrls option check. This caused the Azure provider to use the /responses endpoint instead of /chat/completions even when useCompletionUrls was set to true. The fix adds a check in getLanguage to apply Azure-specific logic for any model using @ai-sdk/azure, ensuring useCompletionUrls is respected for both built-in and custom Azure providers. Fixes anomalyco#20287
The protocol version 2024-11-05 is deprecated and rejected by GitLab 18.9+. Updated to 2025-06-18 which is supported by GitLab MCP server.
The mcp auth and mcp debug commands were not forwarding headers configured under mcp.<name>.headers during the OAuth flow, causing 404 errors instead of 401 from servers requiring custom headers for routing. Fixed three code paths: 1. startAuth in src/mcp/index.ts - added requestInit with headers 2. McpDebugCommand fetch probe - added headers to fetch call 3. McpDebugCommand OAuth transport - added requestInit with headers Fixes anomalyco#20286
@ai-sdk/azure delegates to OpenAIChatLanguageModel which hardcodes provider: 'openai' in parseProviderOptions. Model options like reasoningEffort were being placed under 'azure' key and silently ignored. Now using 'openai' key for @ai-sdk/azure provider options. Fixes anomalyco#20275
github-actions
bot
added
the
needs:compliance
Contributor
|
This PR doesn't fully meet our contributing guidelines and PR template. What needs to be fixed:
Please edit this PR description to address the above within 2 hours, or it will be automatically closed. If you believe this was flagged incorrectly, please let a maintainer know. |
Contributor
|
The following comment was made by an LLM, it may be inaccurate: Potential Duplicate FoundPR #20272 - "fix: use 'openai' as providerOptions key for @ai-sdk/azure" This PR appears to be addressing the exact same issue as the current PR #20333. Both are fixing the Azure provider options configuration by using the 'openai' key instead of 'azure' for the |
Collaborator
|
denounce |
Collaborator
|
Sorry dont want bots spamming prs. |
jeromelau
pushed a commit
to jeromelau/opencode
that referenced
this pull request
Apr 2, 2026
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
reasoningEffortbeing silently ignored for custom Azure providers@ai-sdk/azuredelegates toOpenAIChatLanguageModelwhich hardcodesprovider: 'openai'inparseProviderOptions'azure'key and silently droppedChanges
providerOptionsinsrc/provider/transform.tsto use'openai'key for@ai-sdk/azureTest plan
reasoningEffortoptionreasoning_effortappears in HTTP request bodyFixes #20275