Repository navigation
feat(models): onboard GPT-6 Astra, GPT-6.1 Sol, GPT-6 Sol, GPT-6 Luna - #27
Merged
Merged
Conversation
Plan: docs/openclaude/plans/2026-10-13-gpt6-astra-onboarding-plan.md. 4 full-spec descriptors; Codex-cap research empty so dated no-cap comment + first-500 monitoring flag. Codex picker entries, responses-API routing, GPT6 family regex, Ultra->max on flagships via legacy effort path. Gates: 290 tests pass; integrations:check + build clean; typecheck clean except pre-existing src/ink drift.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
Onboards four GPT-6 family models to the Codex OAuth lane, per
docs/openclaude/plans/2026-10-13-gpt6-astra-onboarding-plan.md:gpt-6-astra) — flagship, Light → Ultra reasoninggpt-6.1-sol) — flagship, Light → Ultra reasoninggpt-6-sol) — flagship, Light → Ultra reasoning (plus baregpt-6alias)gpt-6-luna) — fast / cost-effective, Light → Extra High reasoningThe
codexplanalias stays ongpt-5.6-sol(verified, 5.x untouched).What's wired
src/integrations/models/gpt6.ts(new): 4 shared descriptors (1,050,000 ctx / 128,000 out) + dated no-cap comment + FIRST-500 monitoring flagsrc/integrations/vendors/openai.ts: 4 catalog entries (flagships 5 effort levels incl. max, default high; Luna 4 levels, default medium)src/utils/model/modelOptions.ts: 4 Codex picker entries, prepended in native ordersrc/utils/model/model.ts: display names + copilot map + baregpt-6→gpt-6-solaliassrc/services/api/providerConfig.ts: 5CODEX_ALIASentries,gpt-6responses-API routing,GPT6_FAMILY_REsrc/utils/effort.ts: Ultra (max) exposed on the 3 flagships via the legacy Codex-route laddergpt6Catalog.test.ts+ additions to context / effort / providerConfig / codexTag suitesVerification
integrations:checkpass;bun run buildpasstypecheck: clean in all touched files (only pre-existing untouchedsrc/ink/*drift)runtimeMetadata.modelLimits; curated gateway catalogs (commandcode / llmtr / github) intentionally untouched; zero regressionsOpen item: Codex context cap
No public Codex-side cap found for Astra (research returned empty) — descriptors ship full-spec with a dated comment +
FIRST-500 MONITORINGflag instead of an invented cap or the 272k copy. Cap to be confirmed from production traffic.