chore(models): use GPT-6 Luna for text generation - #13115
juliusmarminge merged 1 commit into
Conversation
ApprovabilityVerdict: Not approved Macroscope's review found this PR not approvable — This PR changes the production default text-generation model used for new settings and fallback selection, while removing the direct test for the previous default. Although the code change is small and persisted choices are preserved, product-default changes require human review. You can add or adjust custom eligibility rules. Learn more. |
|
Navigate logical layers of code changes, visualize relationships, and explore their blast radius. No actionable comments were generated in the recent review. 🎉 ℹ️ Recent review info⚙️ Run configurationConfiguration used: Repository: pingdotgg/t3code/.coderabbit.yaml Review profile: CHILL Plan: Advanced Run ID: 📒 Files selected for processing (2)
💤 Files with no reviewable changes (1)
Included review availability: Your plan provides up to 10 included reviews per hour; 9 remain after this review. 📝 WalkthroughWalkthroughThe Codex text generation default changes from ChangesCodex model default
Priority: ⬇️ Low Estimated code review effort: 1 (Trivial) | ~3 minutes Change: Bug fix Suggested reviewers: Merge Risk: 🔵 Low · up to The change is mergeable, but a focused settings-default regression assertion would reduce the risk of silently selecting the wrong model later. 🚥 Pre-merge checks | ✅ 5✅ Passed checks (5 passed)
✨ Finishing Touches🧪 Generate unit tests (beta)
Comment |
## What's Changed * chore(mobile): drop dead nitro-markdown tgz override and @expo/metro-runtime by @juliusmarminge in pingdotgg/t3code#13148 * feat(web): show settings scope as a sentence at the top of the page by @juliusmarminge in pingdotgg/t3code#13139 * refactor(web): move settings scope pickers into breadcrumbs by @Yash-Singh1 in pingdotgg/t3code#13165 * feat(auth): share provider sign-in flows and credential bindings by @juliusmarminge in pingdotgg/t3code#12983 * refactor(mobile): git sheets use uniwind platform variants instead of className ternaries by @juliusmarminge in pingdotgg/t3code#13161 * chore(mobile): name the two project favicon caches by their job by @juliusmarminge in pingdotgg/t3code#13160 * revert(mobile): git sheets back to Platform.OS ternaries (un-guarded uniwind variants broke both platforms) by @juliusmarminge in pingdotgg/t3code#13169 * docs(mobile): document the two mobile routes that intentionally skip deep links by @juliusmarminge in pingdotgg/t3code#13164 * refactor(mobile): break module cycles with focused extractions by @juliusmarminge in pingdotgg/t3code#13151 * fix(server): generate PR diffs from branch changes by @Yash-Singh1 in pingdotgg/t3code#13170 * fix(web): preserve nested scroll behavior in chat timeline by @Yash-Singh1 in pingdotgg/t3code#13167 * test(web): cover usage model ordering without static markup by @flamboh in pingdotgg/t3code#13104 * fix(desktop): find linuxbrew node for the WSL backend by @CodyRay in pingdotgg/t3code#7827 * chore(models): use GPT-6 Luna for text generation by @extoci in pingdotgg/t3code#13115 * fix(mobile): keep ordinary offline outbox failures out of console.warn by @juliusmarminge in pingdotgg/t3code#13144 * feat(providers): check remote compatibility ranges by @juliusmarminge in pingdotgg/t3code#13130 * chore(lint): keep mobile theme escape-hatch allowlist honest by @juliusmarminge in pingdotgg/t3code#13146 * fix(web): the pull request badge reads at the meta size again by @juliusmarminge in pingdotgg/t3code#13175 * fix(mobile): uniwind platform variants stay guarded on both platforms by @juliusmarminge in pingdotgg/t3code#13172 * refactor(mobile): git sheets use uniwind platform variants instead of className ternaries by @juliusmarminge in pingdotgg/t3code#13185 * refactor(mobile): remaining className platform ternaries become class variants by @juliusmarminge in pingdotgg/t3code#13188 * fix(web): align provider emails without clipping by @Derpedyea in pingdotgg/t3code#13174 * perf(mobile): recycle the default v2 home list and scope the snooze minute tick by @juliusmarminge in pingdotgg/t3code#13149 * refactor(mobile): retire the legacy grouped thread list by @juliusmarminge in pingdotgg/t3code#13183 * fix(server): background PR checks spend less GitHub quota by @juliusmarminge in pingdotgg/t3code#13189 * fix(server): background PR sync reads summaries in batches by @juliusmarminge in pingdotgg/t3code#13198 * fix(server): GitHub PR lookups stop probing owner-qualified heads by @juliusmarminge in pingdotgg/t3code#13200 * chore(mobile): clear the legacy-list deletion fallout by @juliusmarminge in pingdotgg/t3code#13203 ## New Contributors * @CodyRay made their first contribution in pingdotgg/t3code#7827 **Full Changelog**: pingdotgg/t3code@v0.0.43-nightly.20260922.2123...v0.0.43-nightly.20260923.2135 Upstream release: https://github.com/pingdotgg/t3code/releases/tag/v0.0.43-nightly.20260923.2135
Upstream intake is chronological, so maintainers need a way to assess whether a later fix can be imported early without creating conflicts as the intervening upstream changes are taken in. File overlap alone treats many independent changes as dependencies, while a clean cherry-pick against today's fork does not check the intervening history. Add an `early` command to the upstream queue. For selected PRs, it applies their source patches at the reconciled upstream boundary, replays intervening integrations in order, adds conflicting PRs or direct commits as dependencies, verifies the final upstream tree, and checks the selected set against fork `main`. It also offers a quick file-overlap scan, reuses settled PR metadata when the target advances, and removes its temporary Git objects after each run. This reports a plan; it does not change the chronological intake or promotion policy. Validation: In a standalone worktree based on current fork `main`, `pingdotgg#13115` replayed 1,043 intervening integrations to the same upstream tree with no dependencies and applied cleanly to fork `main`. A combined selection of `pingdotgg#9753` and `pingdotgg#13115` replayed upstream cleanly but reported the existing fork conflict at `pingdotgg#9753`. Focused queue tests passed (19), along with scripts typecheck, targeted lint, formatting, and a check that simulation objects were removed. No early import was performed. --- Written by an agent (Codex, GPT-6).
The tracked upstream PR report currently shows days since each PR merged. That number grows with time even when the fork's intake position has not changed, so it does not show how far the fork must advance to reach the PR. Show the merge-time distance between each pending PR and the fork's last reconciled upstream integration in both `upstream-queue.ts status` and the tracked PR report. The report derives the tip from the same intake replay used by the lag report. Add `pingdotgg#9753`, `pingdotgg#10113`, and `pingdotgg#13115` to the watchlist so their intake status stays visible. Validation: The tracked report ran against fetched fork and upstream refs and showed `pingdotgg#10113` 1.3 days ahead of the fork tip and `pingdotgg#13115` 17.9 days ahead. The queue status command showed matching distances. Focused intake and tracked PR tests passed (16 tests), as did scripts typecheck, targeted lint, formatting, and `git diff --check`. --- Written by an agent (Codex, GPT-6).
What Changed
gpt-6-lunaas the default Codex text generation model, retaining low reasoning effort.Why
The model manifest already lists GPT-6 Luna as a current Codex model. New settings should select it automatically, while saved model choices remain intact. The removed test asserted the configuration literal rather than observable behavior.
Verification
vp test run packages/contracts/src/settings.test.ts apps/server/src/serverSettings.test.ts(188 tests passed)pnpm --filter @t3tools/contracts typecheckChecklist
Model: GPT-6 Astra; harness: Codex.
Summary by CodeRabbit