fix(gateway,moa): surface and preserve extended reasoning efforts (salvage #64012) - #65651
Merged
Conversation
_clean_reasoning_effort kept its own whitelist that stopped at 'max', silently dropping 'ultra' from MoA slot configs. Route it through hermes_constants.parse_reasoning_effort — the same one-source-of-truth fix the salvaged commit applies to the gateway — so future effort levels can't drift here either. Docs updated to list ultra. Follow-up to salvaged PR #64012.
alt-glitch
added
type/bug
This was referenced Jul 16, 2026
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
/reasoningon the gateway now advertises the full effort ladder —maxandultra(added for GPT-5.6 in #62650) were accepted by the handler but every locale's status/error message still claimedxhighwas the ceiling, making the new levels undiscoverable.Salvage of #64012 by @karfly, cherry-picked onto current main with authorship preserved, plus a follow-up widening the same bug class in MoA.
Changes
gateway/slash_commands.py: route/reasoningeffort validation through the canonicalhermes_constants.parse_reasoning_effortinstead of a second hand-maintained whitelist (@karfly)locales/*.yaml(all 16):status+unknown_argstrings now listmaxandultra(@karfly)tests/run_agent/test_run_agent_codex_responses.py: wire regression —maxreaches the Responses API unchanged (@karfly)hermes_cli/moa_config.py: sibling site —_clean_reasoning_efforthad its own whitelist stopping atmax, silently droppingultrafrom MoA slot configs; now routes through the same canonical parser (follow-up)tests/hermes_cli/test_moa_config.py,website/docs/user-guide/features/mixture-of-agents.md: ultra coverage + docsscripts/release.py: AUTHOR_MAP entry for @karflyValidation
/reasoninghelpxhighmax,ultraadvertised in all 16 localesreasoning_effort: ultraTargeted:
tests/gateway/test_reasoning_command.py,tests/hermes_cli/test_moa_config.py,tests/run_agent/test_run_agent_codex_responses.py,tests/test_hermes_constants.py— 269 passed. E2E: real imports against temp HERMES_HOME confirmed all 16 locale strings rendermax|ultra, MoA round-trip preservesultra, junk values still rejected.Closes #64012. Refs #61634.
Infographic