feat(providers): adopt gpt-5.6 model family and new codex effort tiers#131
Merged
Conversation
- Replace the Codex picker lineup with gpt-5.6-sol/terra/luna plus gpt-5.5 as the previous-generation fallback; gpt-5.4 variants and codex-spark move to legacy display names only - Make gpt-5.6-terra the Codex default model (shortcuts, presets, recommended group) and switch the turn-summary light model to gpt-5.6-luna - Extend codexReasoningEffort with max/ultra across provider types, IPC schemas, store settings, effort cycle, and the settings picker; drop legacy minimal from selectable options while still validating and normalizing persisted values to low - Claude effort scale reviewed: no new tiers upstream, no changes needed Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
heath-s
approved these changes
Jul 10, 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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Respond to the GPT-5.6 release (2026-07-09): refresh the Codex model catalog around the new Sol/Terra/Luna family with
gpt-5.6-terraas the default, and extend the Codex reasoning-effort scale with the newmax/ultratiers.Changes
Features
gpt-5.6-sol(frontier/high),gpt-5.6-terra(heavy/medium), andgpt-5.6-luna(light/low) to the Codex catalog; keepgpt-5.5as the previous-generation fallbackgpt-5.6-terrathe Codex default model across shortcuts (Alt+2→Terra,Alt+3→Sol), task presets, and the recommended selector groupcodexReasoningEffortwithmaxandultra(GPT-5.6 Codex CLI scale) across provider types, IPC schemas, store settings, the effort cycle, and the settings pickergpt-5.4-minitogpt-5.6-lunaRefactors / Chores
gpt-5.4,gpt-5.4-mini, andgpt-5.3-codex-sparkfrom the picker; legacy display names and effort heuristics kept so historical records still render correctlyminimaleffort from selectable options; persisted values still validate and normalize tolowat runtimeTest Evidence
bun run typecheckpassesNotes
low..maxunchanged), so no Claude-side changesturn.effort/plan_mode_reasoning_effort), so no protocol changes were neededMODEL_CAPABILITIESand easy to retune🤖 Generated with Claude Code