fix(config): infer LLM provider from model string#97
Closed
mikolajbadyl wants to merge 4 commits intomainfrom
Closed
fix(config): infer LLM provider from model string#97mikolajbadyl wants to merge 4 commits intomainfrom
mikolajbadyl wants to merge 4 commits intomainfrom
Conversation
…d ExportTests tool to prompt
…ely solely on config package
… provided via environment
| @@ -135,13 +135,12 @@ func GetActiveLLMConfig() (provider, apiKey, baseURL, modelName string) { | |||
| } | |||
|
|
|||
| if provider == "" { | |||
There was a problem hiding this comment.
WARNING: Breaking change - the automatic API key lookup from provider-specific environment variables (OPENAI_API_KEY, ANTHROPIC_API_KEY, GOOGLE_API_KEY) has been removed. Users must now use OCTRAFIC_API_KEY or configure their API key in the saved config file. This may break existing setups that rely on the provider-specific env vars.
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Description
Fixed a bug where the CLI incorrectly falls back to Anthropic Claude when a model string is provided via environment variables (e.g.
OCTRAFIC_MODEL=gemini-2.5-flash) but the provider string is omitted.This change introduces intelligent inference so that if
OCTRAFIC_PROVIDERis empty, the CLI parses the model prefix:gpt-*, o1, o3-> OpenAIgemini-*-> GeminiTesting
Verified that
OCTRAFIC_MODEL=gemini-2.19-flash octraficnow correctly routes through the Gemini client.