Skip to content

fix: select the newest available ChatGPT model - #27

Merged
JJLiebig merged 1 commit into
mainfrom
fix/smart-model-picker
Oct 7, 2026
Merged

JJLiebig merged 1 commit into
mainfrom
fix/smart-model-picker

Conversation

@JJLiebig

@JJLiebig JJLiebig commented Oct 7, 2026 •

Copy link
Copy Markdown
Owner

ChatGPT now shows GPT-6 instead of Latest, so ask-pro could not select a model and stopped before submission. Prefer the rolling Latest row when available; otherwise choose the highest numbered visible, enabled GPT model. Compare versions numerically so 5.10 beats 5.9, and keep Pro intelligence confirmation mandatory before sending.

Validation:

  • 326 tests passed; build, lint/typecheck, formatting, package dry run, and plugin validation passed. The configured validator path is missing on this machine; validation used the bundled plugin-creator copy in harness-playground.
  • Fast Review Suite rvw_e7b24eb3 completed with two clean signoffs. CodeRabbit found no actionable comments.
  • Windows, macOS, and Linux CI passed on 693eb2b.
  • Live, signed-in no-submit UI inspection confirmed visible enabled terminal GPT-6, GPT-5.6 Sol, and GPT-5.5 rows, GPT-6 checked, and Pro at 5/5.
  • The optional full CLI smoke stopped at NEEDS_USER_AUTH before model selection; no prompt was submitted. That full smoke is waived for this change because it requires human login to the separate managed profile. The adapter behavior is covered locally and current picker controls were inspected live.

@coderabbitai

coderabbitai Bot commented Oct 7, 2026 •

Copy link
Copy Markdown

Review in Change Stack →

No actionable comments were generated in the recent review. 🎉

ℹ️ Recent review info
⚙️ Run configuration
  • Configuration used: defaults
  • Review profile: CHILL
  • Plan: Advanced
  • Run ID: e9e31eb9-5d84-4914-8cb4-1f5e8d3eb6f6
📥 Commits

Reviewing files that changed from the base of the PR and between 16796d7 and 693eb2b.

📒 Files selected for processing (10)
  • AGENTS.md
  • CHANGELOG.md
  • README.md
  • docs/05-command-surface.md
  • docs/11-risk-register.md
  • docs/manual-tests.md
  • docs/windows-work.md
  • skills/ask-pro/SKILL.md
  • src/browser/actions/modelSelection.ts
  • tests/browser/modelSelection.test.ts

Included review availability: This review used your included allowance. Your plan provides up to 1 included review per hour; 0 remain after this review.


📝 Walkthrough

Walkthrough

The model picker now considers eligible numbered GPT models for the Latest target and selects the highest numeric version when needed. Tests and project documentation describe the fallback and the separate Pro intelligence requirement.

Changes

GPT model selection

Layer / File(s) Summary
Picker fallback selection
src/browser/actions/modelSelection.ts, tests/browser/modelSelection.test.ts, AGENTS.md, CHANGELOG.md, README.md, docs/05-command-surface.md, docs/11-risk-register.md, docs/manual-tests.md, docs/windows-work.md, skills/ask-pro/SKILL.md
For the Latest target, the picker filters out hidden, disabled, and submenu options, then compares numeric GPT versions. Tests cover numeric ordering, suffixed labels, ineligible options, missing choices, and collapsed model controls. Instructions and documentation describe the Latest preference and numbered-model fallback.

Priority: ➖ Normal

Estimated code review effort: 2 (Simple) | ~10 minutes

Change: Bug fix

Merge Risk: ⚪ Minimal · up to 693eb

The picker now falls back to the highest-numbered available GPT model when Latest is absent, and Pro confirmation is unchanged. No merge-blocking risk was found.

🚥 Pre-merge checks | ✅ 5
✅ Passed checks (5 passed)
Check name Status Explanation
Docstring Coverage ✅ Passed Docstring coverage is 100.00% which is sufficient. The required threshold is 80.00%. Docstring coverage is scoped to functions touched by this diff. Analyzed 1 functions across 2 files. (8 skipped: 8 …
Linked Issues check ✅ Passed Check skipped because no linked issues were found for this pull request.
Out of Scope Changes check ✅ Passed Check skipped because no linked issues were found for this pull request.
Description Check ✅ Passed Check skipped - CodeRabbit’s high-level summary is enabled.
Title check ✅ Passed The title clearly and concisely describes the main change: selecting the newest available ChatGPT model.
✨ Finishing Touches
📝 Generate docstrings
  • Commit to this branch
  • Create a new PR
🧪 Generate unit tests (beta)
  • Commit to this branch
  • Create a new PR
  • Autopilot · Keep fixing CodeRabbit findings and required CI, and resolving merge conflicts

Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out.

❤️ Share

Comment @coderabbitai help to get the list of available commands.

@JJLiebig
JJLiebig merged commit a673c37 into main Oct 7, 2026
5 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant