ci: upgrade pr-reviewer-action to v1.2.3 (tool loop, carry-forward verdicts)

[joryirving]

Upgrades to pr-reviewer-action v1.2.3.

What this brings

• Cumulative incremental verdicts: when a review requests changes, its findings are carried into the next push's incremental review, which must explicitly resolve each one — fixing one of three blockers can no longer rubber-stamp the other two. The latest review always lists what was resolved and what's still open.
• Superseded reviews keep their content: old reviews are hidden (minimized) and their verdicts dismissed, but the text is no longer overwritten — expanding a hidden review still shows what it said.
• Multi-turn tool research — tool_mode: plan_execute_loop with tool_max_rounds: "2": the model can now react to what its evidence tools returned and request follow-ups (read the changed file → grep for its callers). The 4-request budget is now shared across rounds; each extra round costs one additional planning call against the review endpoint.
• Explicit smart wiring: ai_smart_model/ai_smart_api_format now read vars.SMART_MODEL/vars.SMART_FORMAT directly (both are explicitly set at the org level), instead of coalescing to the fallback vars.
• Dirty-baseline escalation (on by default): incremental reviews of a PR whose previous review found issues run on the smart model.

🤖 Generated with Claude Code

[its-saffron]

AI Automated Review

Full PR review.

Analysis engine: review@https://litellm.jory.dev/v1 (openai)

Recommendation

Approved. This PR upgrades the pr-reviewer-action to v1.2.3, enabling advanced agentic features like multi-turn tool research and cumulative incremental verdicts.

Change-by-change findings

.github/workflows/ai-pr-review.yaml

• Upgrade Action Version: Updated misospace/pr-reviewer-action from e891235e8e3e75824b88fb696b1f7b4816122737 (v1.2.2) to 59c7a0596b0d0b515ef9137f7acb985115f4c1d8 (v1.2.3).
• Smart Model Configuration: Changed ai_smart_api_format and ai_smart_model to use direct variable mapping (${{ vars.SMART_FORMAT }} and ${{ vars.SMART_MODEL }}) instead of providing fallbacks. This aligns with the release notes stating that these values are explicitly set at the organization level.
• Tool Mode Update: Changed tool_mode from plan_execute_once to plan_execute_loop and added tool_max_rounds: "2". This enables the model to perform multi-turn research (e.g., reading a file and then grepping for its callers) within a 2-round budget.

Standards Compliance

• Version Convention: The PR follows the repository's implicit pattern of using specific SHAs for action versions to ensure deterministic CI runs.
• Workflow Integrity: The changes to the AI reviewer workflow are consistent with the goal of improving the automated review process as described in the release notes.

Linked Issue Fit

• N/A (No linked issues provided).

Evidence Provider Findings

• N/A

Tool Harness Findings

• N/A

Unknowns or Needs Verification

• None identified.