feat(codex): expose reasoning mode in webui - #61625
Closed
ruizanthony wants to merge 1 commit into
Closed
Conversation
19 tasks
teknium1
reviewed
Jul 10, 2026
teknium1
left a comment
Contributor
There was a problem hiding this comment.
Thanks for the focused Codex dashboard work. The feature remains needed: live main's ReasoningPicker defaults showMode to false (web/src/components/ReasoningPicker.tsx:55), and its parent does not pass that prop (web/src/components/ChatSidebar.tsx:345-356).
Problems
tests/run_agent/test_run_agent_codex_responses.py:726passeson_commentary_messageto_consume_codex_event_stream, but the PR head's function signature (agent/codex_runtime.py:597-606) has no such parameter and this PR does not modify that file. The changed commentary tests will fail withTypeError.- The branch is substantially stale relative to live main. Main already contains the transport/TUI reasoning-mode pieces (
agent/transports/codex.py:292-295), so salvage should avoid replaying those overlapping changes.
Suggested changes
- Remove the unrelated commentary-stream test changes from this PR.
- Re-scope the salvage to the missing
ChatSidebarprovider/showMode wiring and add a component-level Codex-versus-non-Codex visibility test.
Automated hermes-sweeper review.
ruizanthony
force-pushed
the
fix/codex-reasoning-mode-webui
branch
from
July 10, 2026 20:09
ce4c4ed to
a27a746
Compare
Contributor
Author
|
Closing intentionally: reasoning.mode=pro is not usable with the openai-codex subscription backend, so exposing this control would be misleading. The local integration has also been removed. |
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
standard/proin the WebUI chat sidebaropenai-codexproviders while preserving the existing reasoning-effort picker unchangedagent.reasoning_modeand load it only foropenai-codexgateway/TUI sessionsreasoning.modeonly to the Codex Responses backend; non-Codex Responses requests keep their existing payloadReview fixes
mainTypeErrormaxreasoning-effort changeValidation
scripts/run_tests.sh tests/agent/transports/test_codex_transport.py tests/gateway/test_runtime_config_env_expansion.py tests/hermes_cli/test_config.py tests/test_tui_gateway_server.py tests/run_agent/test_run_agent_codex_responses.py— 629 passednpm test -- --run— 74 passednpm run typechecknpm run buildpython -m compileall -q agent/transports/codex.py gateway/run.py hermes_cli/config.py tui_gateway/server.pygit diff --checkNotes
reasoning.modeis validated asstandardorproand is deliberately scoped twice: when loading config foropenai-codex, and again when building a Codex-backend request. Other providers continue receiving only their existing reasoning payload.