Add gptel-reasoning-effort and add it to the transient menu#1338
Open
djr7C4 wants to merge 2 commits intokarthink:masterfrom
Open
Add gptel-reasoning-effort and add it to the transient menu#1338djr7C4 wants to merge 2 commits intokarthink:masterfrom
djr7C4 wants to merge 2 commits intokarthink:masterfrom
Conversation
Contributor
Author
|
Also, the |
Owner
|
Thanks for the PR @djr7C4, I'll take a look soon. |
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
This PR implements adds a gptel-reasoning-effort variable and adds it to the
transient menu. It currently only supports OpenAI's responses API. I haven't
tested the gptel-org.el code yet and suspect that it is broken but I thought I'd
send what I have to see if you think the approach is reasonable before I invest
more effort.
Selecting reasoning effort from the transient menu is working for OpenAI models
through the responses API. If the approach seems good, I'll fix any issues with
the implementation in gptel-org.el and implement it for Gemini and Anthropic as
well. Adding it to gptel-openai.el is also possible but I'd have to investigate
how reasoning effort works for non-OpenAI models on platforms like OpenRouter.