[Coly010]

Summary

Points the AI review pipeline's Codex side at gpt-6-sol, which shipped on
2026-09-22 and supersedes gpt-5.6-sol for complex coding and agentic work. It
is also cheaper — $2/$10 per million input/output tokens against 5.6-sol's
$4/$20 — with a 1.05M context window, so both the independent-review and
adjudication passes get more diff headroom per run at lower cost.

The model only entered the Codex CLI's model catalog in 0.156.1 (a hotfix on
0.156.0, released 2026-09-23), so the codex-version input moves with it. Three
things worth stating explicitly, since the pinning here is deliberate:

• The action pin does not move. openai/codex-action stays on the v1.11
  commit: Fix action hang when descendants keep stdio open openai/codex-action#151 (descendant process keeps the step alive) and
  drop-sudo (default safety-strategy) chmods /run service sockets to 0700, breaking D-Bus and systemd-resolved — GitHub-hosted runners die mid-job at ~55 minutes openai/codex-action#160 (drop-sudo chmods /run sockets) are both still open,
  and codex-version is an independent input to the action, so the CLI can be
  bumped without touching the action SHA or the dependabot.yml ignore entry.
• The codex exec flag surface is unchanged between 0.150.1 and 0.156.1.
  codex-rs/exec/src/cli.rs is identical across the two tags, so everything the
  pinned action passes — --skip-git-repo-check, --cd,
  --output-last-message, --output-schema, --model,
  --config model_reasoning_effort=…, --sandbox — still parses.
• 0.156's new background daemon is TUI-scoped. --no-daemon and the daemon
  startup path live under codex-rs/tui/ and codex-rs/cli/src/main.rs only, so
  codex exec will not spawn one and this cannot reintroduce the
  lingering-descendant hang class that forced the v1.11 downgrade.

effort: high is unchanged and still valid; gpt-6-sol additionally supports
xhigh and max, which we can revisit separately if review depth turns out to
matter more than runtime.

It is a six-minor jump on the CLI against a release that is hours old, so this
wants a workflow_dispatch run against a real PR before it is trusted on the
automatic path.

Linked issue

No linked issue — maintainer change.

Checklist

• The PR title follows Conventional Commits (e.g. fix(cli): …).
• Tests added or updated for the change. — n/a, workflow configuration only. The gpt-5.6-sol strings in post-review.test.ts are fixture inputs to the footer builder, not assertions about the live model (they already pair it with claude-fable-5), so they are left alone.
• From the repository root, pnpm check:all passes; relevant package tests pass for every touched workspace, and pnpm types:check passes for each touched TypeScript workspace (or workspace declaring it).

🤖 Generated with Claude Code

[github-actions]

Superseded by a newer AI review

🤖 AI Review

Both independent reviews completed. The PR consistently changes the Codex model to gpt-6-sol and pins both Codex steps to CLI 0.156.1; the code shows no current mismatch. Claude’s four findings are supported by the checked-out workflow, though they concern maintenance, documentation, and a conditional failure path rather than a demonstrated failure of the new version. Codex reported no findings.

Findings

Severity	Location	Category	Sources	Claim
🟡 MINOR	.github/workflows/ai-review.yml:311	maintainability	claude	The CLI version is repeated in two Codex steps, so a future update could change one pin without changing the other.
🟡 MINOR	.github/workflows/ai-review.yml:462	ci-resilience	claude	If the shared Codex model or CLI pin fails, adjudication cannot complete and the workflow posts no review or failure comment to the PR.
⚪ NIT	.github/workflows/ai-review.yml:462	documentation	claude	The second CLI version pin has no rationale comment or cross-reference to the first pin.
⚪ NIT	.github/workflows/ai-review.yml:311	dependency-management	claude	The pinned Codex CLI version is manually maintained and has no automated update tracking in this repository.

Stats

Claude findings: 4 · Codex findings: 0 · Confirmed: 4 · Refuted: 0 · Uncertain: 0

---

Models: claude-opus-5 + gpt-6-sol · Trigger: auto · Workflow run

This review runs once per PR. A maintainer can request another with a /ai-review comment.

[github-actions]

🤖 AI Review

The model and both CLI pins were updated consistently, with no current workflow mismatch. Claude’s single maintainability finding is confirmed as a nit; Codex reported no findings.

Findings

Severity	Location	Category	Sources	Claim
⚪ NIT	.github/workflows/ai-review.yml:311	maintainability	claude	The Codex CLI version remains duplicated across the independent-review and adjudication steps, while the new version rationale appears only beside the first pin. A later update could change one step without changing the other.

Stats

Claude findings: 1 · Codex findings: 0 · Confirmed: 1 · Refuted: 0 · Uncertain: 0

---

Models: claude-opus-5 + gpt-6-sol · Trigger: manual · Workflow run

This review runs once per PR. A maintainer can request another with a /ai-review comment.

[jgoux]

Reviewed head 9267ef4. Both Codex jobs resolve to the same model and CLI version. A branch-scoped workflow_dispatch run succeeded with the new model and version; the subsequent change shares the version through a valid YAML alias. No actionable findings.