fix: modifies openai request logic for reasoning models (#4221) #4294
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
myaple
force-pushed
the
fix/openai-request-effort
branch
from
1a0f6b2 to
a1ef534
Compare
myaple
force-pushed
the
fix/openai-request-effort
branch
from
a1ef534 to
fb346f6
Compare
michaelneale
requested changes
Sep 24, 2025
Collaborator
michaelneale
left a comment
michaelneale
left a comment
There was a problem hiding this comment.
@myaple thanks matt - looks like some errors and something missing from it, but seems like a resonable approach (not sure we do want another variable though, if can be avoided)
Collaborator
|
I agree with @michaelneale here. let's cut this down to just the change in the pattern recognition. no need for the test or variable. and let's get this merged! |
Contributor
Author
|
Sounds good, I'll rip the rest out this weekend and get it across the line. |
myaple
force-pushed
the
fix/openai-request-effort
branch
from
fb346f6 to
741e57c
Compare
DOsinga
approved these changes
Oct 4, 2025
michaelneale
approved these changes
Oct 6, 2025
Collaborator
|
so sorry, but I think you'll need to sync to main to get this to kick off the tests? we had a bug in main at some point |
Signed-off-by: Matt Yaple <[email protected]>
myaple
force-pushed
the
fix/openai-request-effort
branch
from
09e555a to
1210ea9
Compare
Contributor
Author
|
no worries, let me know if that fixes it |
zanesq
added a commit
that referenced
this pull request
Oct 13, 2025
…sion-streaming * 'main' of github.com:block/goose: (37 commits) Clear deeplinks after use (#5128) Revert "Fix gpt-5 input context limit (#4619)" (#5135) fix: missing cmake and protobuf for windows build, deduplicate sh/pws… (#5028) Fix bedrock tool input schema (#5064) Add self-test recipe for goose validation (#5111) fix: modifies openai request logic for reasoning models (#4221) (#4294) Fix race condition threat when set_param and set_secret of c… (#5109) Clean room implementation of the chat process (#5079) Bump rmcp (#5096) set version in an env variable for testing (#5100) fix : enhance fuzzy file search in goose desktop (#5071) Make async (#5126) docs: unlist tutorials for extensions with archived or moved servers (#5116) Add API Documentation Generator prompt (#5001) Add flag for enabling eleven labs voice dictation (#5095) force re-render fields to pick up custom params usage in instructions (#5112) Remove isUserInputDisabled (#5115) Improve Rust analysis output for `analyze` tool (#5072) Remove duplicate prepare_reply_context call (#5063) install react dev tools in development (#4979) ... # Conflicts: # ui/desktop/src/components/BaseChat2.tsx # ui/desktop/src/hooks/useChatStream.ts
katzdave
added a commit
that referenced
this pull request
Oct 15, 2025
* 'main' of github.com:block/goose: (49 commits) fixing video embed (#5171) chore: clean up random unused files (#5166) fix: adjust download_cli.sh to tolerate no OS variable (#5169) mcp tutorial page for firecrawl (#5152) Remove orphaned tool calls before compaction (#5059) feat: add copy as markdown button to documentation pages (#5158) chore: include vendored node executable (#5160) remove extra whitespace from message (#5159) Clear deeplinks after use (#5128) Revert "Fix gpt-5 input context limit (#4619)" (#5135) fix: missing cmake and protobuf for windows build, deduplicate sh/pws… (#5028) Fix bedrock tool input schema (#5064) Add self-test recipe for goose validation (#5111) fix: modifies openai request logic for reasoning models (#4221) (#4294) Fix race condition threat when set_param and set_secret of c… (#5109) Clean room implementation of the chat process (#5079) Bump rmcp (#5096) set version in an env variable for testing (#5100) fix : enhance fuzzy file search in goose desktop (#5071) Make async (#5126) ...
michaelneale
added a commit
that referenced
this pull request
Oct 16, 2025
* main: (35 commits) fix: include apple silicon build of the desktop app in build artifacts (#5174) fixing video embed (#5171) chore: clean up random unused files (#5166) fix: adjust download_cli.sh to tolerate no OS variable (#5169) mcp tutorial page for firecrawl (#5152) Remove orphaned tool calls before compaction (#5059) feat: add copy as markdown button to documentation pages (#5158) chore: include vendored node executable (#5160) remove extra whitespace from message (#5159) Clear deeplinks after use (#5128) Revert "Fix gpt-5 input context limit (#4619)" (#5135) fix: missing cmake and protobuf for windows build, deduplicate sh/pws… (#5028) Fix bedrock tool input schema (#5064) Add self-test recipe for goose validation (#5111) fix: modifies openai request logic for reasoning models (#4221) (#4294) Fix race condition threat when set_param and set_secret of c… (#5109) Clean room implementation of the chat process (#5079) Bump rmcp (#5096) set version in an env variable for testing (#5100) fix : enhance fuzzy file search in goose desktop (#5071) ...
Merged
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.
This is a first take at fixing the issue described in #4221 where the logic used in the litellm provider to create the requests is the same as the openai format, which has significant bias towards openai models. I've modified the name-based parsing to use more specific schemes, calling out o{1..4} instead of just "o" as the starting char.