Conversation
m1guelpf
commented
Aug 10, 2026
agg23
reviewed
Aug 10, 2026
m1guelpf
marked this pull request as ready for review
August 11, 2026 00:51
Author
|
@agg23 I've marked |
This reverts commit 53e7a52.
Member
|
I updated to latest |
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
2 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
This PR ensures all the AI providers use their more modern APIs. Specifically, it switches the OpenAI provider to always use the Responses API (previously it only did so when web search was enabled), and Gemini to use the Interactions API.
Rationale
This will enable support for user-configured MCP servers in a future PR, which makes adding functionality to the AI Pin much easier. For example, adding Google Calendar support back doesn't need system changes, just connecting to the official MCP server from the PenumbraOS Center.
The OpenAI Responses API, Anthropic Messages API, and the Gemini Interactions API all have native support for connecting MCP servers. This wouldn't be supported by openai-compatible providers (for now?).
Notes
While building this, I noticed a bug with the existing Responses API implementation. It rewrites the function schemas in
sanitize_schema, which forces the model to invent parameters for all fields, even nullable ones. I have left this issue in place at the maintainer's request.