[ralph-bitgo]

Description

Restore Claude workflows by upgrading the pinned action to v1.0.260 and selecting the active Sonnet 5.5 global Bedrock inference profile through ANTHROPIC_MODEL. The upgrade applies to both pull-request reviews and the iyarc-prune workflow from the linked failed run.

Migrate the bare @claude review path to the supported prompt input, include repository and pull-request context, require explicit GitHub CLI targeting, and allow the commands needed to read and publish the review. Keep custom mentions in interactive mode so the action supplies comment and conversation context. Replace the ignored timeout_minutes input with a ten-minute job timeout and document operation in .github/README.md.

The linked failure used action v1.0.194, which carried Claude Code 2.1.234. Sonnet 5.5 requires Claude Code 2.1.280 or newer; action v1.0.260 carries Claude Agent SDK 0.3.309 and a sufficiently new runtime.

No application code or dependencies change. Existing AWS roles, region, and permissions are unchanged.

Issue Number

WAL-2202

Type of change

• Bug fix (non-breaking change which fixes an issue)
• New feature
• Breaking change
• This change requires a documentation update

How Has This Been Tested?

• actionlint passed for .github/workflows/claude-pr.yml and .github/workflows/iyarc-prune.yml using the repository's locked Nix tool source.
• A targeted harness verified action v1.0.260, the global Sonnet 5.5 profile, MAX_THINKING_TOKENS=0, explicit GitHub CLI targeting, removal of obsolete inputs, and prompt selection for bare, whitespace-padded, and custom mentions.
• Verified prompt-versus-interactive mode behavior and accepted inputs against the pinned action source.
• Verified the pinned action carries Claude Agent SDK 0.3.309.

Live inference was not exercised because comment-triggered review workflows use the default branch definition. After merge, request a bare @claude review and a custom mention; confirm successful inference and posted feedback. The inference role must allow the global Sonnet 5.5 profile and its destination models. Application builds and unit tests are not applicable to this workflow-only change.

Checklist

• My code follows the style guidelines of this project
• I have performed a self-review of my own code
• Application code compiles correctly — not applicable; no application changes
• Workflow operation is documented
• The commit follows Conventional Commits
• The ticket is linked
• Documentation is updated
• Permanent tests added — targeted workflow harness used; no implementation-detail test checked in
• Application unit tests run — not applicable; workflow-only change

[linear-code]

WAL-2202

[zahin-mohammad]

AI-generated review — updated after validating the linked Sonnet 5.5 failure. Please use your own judgment before acting on any findings.

---

PR Review: #10014 — restore Claude workflows with Sonnet 5.5

Changes: +36 / -11 across 3 files

Summary

This PR upgrades pull-request reviews and iyarc-prune to claude-code-action v1.0.260, whose Claude Agent software development kit (SDK) dependency is 0.3.309, and selects the global Sonnet 5.5 Bedrock inference profile (.github/workflows/claude-pr.yml:84, .github/workflows/claude-pr.yml:87, .github/workflows/iyarc-prune.yml:73, .github/workflows/iyarc-prune.yml:82).

flowchart TD
    A[Claude workflow starts] --> B[claude-code-action v1.0.260]
    B --> C[Claude Code 2.1.280 or newer]
    C --> D[Global Bedrock Sonnet 5.5 profile]
    D --> E{Workflow}
    E -->|PR review| F[Post review to triggering pull request]
    E -->|iyarc-prune| G[Analyze and update dependency policy]

Loading

Findings

• ✅ Fixed: run 40019548206 used action v1.0.194 and Claude Code 2.1.234; the runtime rejected Sonnet 5.5 because it requires 2.1.280 or newer. iyarc-prune now uses v1.0.260 (.github/workflows/iyarc-prune.yml:73).
• ✅ Fixed: every affected workflow now uses AWS's global Sonnet 5.5 profile rather than the US-only profile (.github/workflows/claude-pr.yml:87, .github/workflows/iyarc-prune.yml:82).
• ✅ Fixed: review commands explicitly target the triggering repository and PR (.github/workflows/claude-pr.yml:101).
• ✅ Aligned with WAL-2202: bare reviews and interactive mentions retain their intended modes.

Verification

actionlint (.github/workflows/claude-pr.yml .github/workflows/iyarc-prune.yml): PASS
latest-action/profile harness: PASS
commitlint: 0 errors
Mermaid render: PASS (202490 bytes)

Remaining live check: comment-triggered review workflows use the default-branch definition, so actual review inference must be verified after merge (.github/README.md:15). The inference role must permit the global profile and its worldwide destination-model resources.

---

Generated by the wallet-platform:review-pr skill

[zahin-mohammad]

Recreated under @zahin-mohammad as #10057.