[Platform] Migrate OpenAI to Responses API #871
Conversation
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
paulinevos
requested review from
Nyholm,
OskarStark and
chr-hertel
as code owners
carsonbot
changed the title
Contributor
Author
|
lol, please hold. Forgot to add a whole bunch of tests. Feel free to review functionality in the meantime |
paulinevos
changed the title
chr-hertel
reviewed
Nov 14, 2025
chr-hertel
added
Status: Needs Work
Platform
carsonbot
changed the title
chr-hertel
changed the title
paulinevos
force-pushed
the
responses-migration
branch
from
47ae95d to
57f7762
Compare
paulinevos
force-pushed
the
responses-migration
branch
from
57f7762 to
546019d
Compare
paulinevos
force-pushed
the
responses-migration
branch
from
546019d to
9af9306
Compare
paulinevos
force-pushed
the
responses-migration
branch
from
9af9306 to
064c45e
Compare
Since `o1` models are deprecated, and the Responses API no longer supports `o1`. See: https://platform.openai.com/docs/deprecations#2025-04-28-o1-preview-and-o1-mini
paulinevos
force-pushed
the
responses-migration
branch
from
064c45e to
70d3673
Compare
Since we're migrating to the Responses API (from chat completions), and
that API doesn't support audio yet. It should be added back when it does
("coming soon", apparently)
See: https://platform.openai.com/docs/guides/migrate-to-responses
As every OpenAI model with vision capabilities also support PDF input, as per docs: https://platform.openai.com/docs/guides/pdf-files?api-mode=responses
In order to migrate from chat completions to Responses, which enforces different data structures
Since we're migration from chat completions to Responses, which has a differnt data structure for function calls
To migrate from OpenAI's chat completions to Responses, we need to change incoming messages to the updated data structure
Chat completions is deprecated. Responses is the recommended API to use now. See: https://platform.openai.com/docs/guides/migrate-to-responses
paulinevos
force-pushed
the
responses-migration
branch
from
70d3673 to
8166232
Compare
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
4 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 migrates OpenAI from chat completions (deprecated) to the Responses API. I tried to keep the scope small and just support everything already in place as seamlessly as possible. The Responses API does offer some more functionality that we should look into supporting (e.g. MCP tool calling, expanded reasoning functionality), but I found that OOS for this migration.
One thing to note it that the Responses API as of now lacks Audio capabilities ("coming soon", according to the docs), so that example is temporarily disabled and so is the
Gptaudio capability for now.Note: my PRs are best reviewed commit by commit