ci: fix model config and add MemCan to review workflow

[lklimek]

Summary

• Fix model configuration: Replace invalid claude_model input (doesn't exist in claudius-review-action) with ANTHROPIC_MODEL env var — the correct way to control the model
• Add MemCan support: Wire memcan_url (repo variable) and memcan_api_key (secret) so the review agent has persistent memory across reviews

Setup required

Type	Name	Value
Variable	MEMCAN_URL	MemCan server URL (e.g., http://host:8190)
Secret	MEMCAN_API_KEY	MemCan API key

Test plan

• Verify MEMCAN_URL variable and MEMCAN_API_KEY secret are configured in repo settings
• Label a test PR with claudius-review and confirm the review workflow runs successfully
• Check workflow logs for MemCan pre-flight message (should show available, not warning)

_{🤖 Co-authored by Claudius the Magnificent AI Agent}

Summary by CodeRabbit

• Chores
  • Updated GitHub Actions workflow configuration for code review automation processes.

[coderabbitai]

📝 Walkthrough

Walkthrough

GitHub Actions workflow updated to modify review job configuration. The claude_model input replaced with memcan_url and memcan_api_key inputs, and ANTHROPIC_MODEL environment variable added to the review job step.

Changes

Cohort / File(s)	Summary
GitHub Actions Workflow Configuration .github/workflows/claude-code-review.yml	Modified review job to use ANTHROPIC_MODEL environment variable and replaced direct model input with memory cache URL and API key configuration for the claudius-review action.

Estimated code review effort

🎯 1 (Trivial) | ⏱️ ~2 minutes

Poem

🐰 The workflow hops with a brand new way,
Swapping models for cache, hip-hooray!
With memcan URLs and keys held tight,
The review job shines with memory's light! ✨

🚥 Pre-merge checks | ✅ 3

✅ Passed checks (3 passed)

Check name	Status	Explanation
Description Check	✅ Passed	Check skipped - CodeRabbit’s high-level summary is enabled.
Title check	✅ Passed	The title clearly and concisely summarizes the two main changes: fixing model configuration and adding MemCan support to the review workflow, matching the actual modifications in the changeset.
Docstring Coverage	✅ Passed	No functions found in the changed files to evaluate docstring coverage. Skipping docstring coverage check.

_{✏️ Tip: You can configure your own custom pre-merge checks in the settings.}

✨ Finishing Touches

🧪 Generate unit tests (beta)

• Create PR with unit tests
• Post copyable unit tests in a comment
• Commit unit tests in branch ci/fix-review-workflow-config

📝 Coding Plan

• Generate coding plan for human review comments

---

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

• X
• Mastodon
• Reddit
• LinkedIn

_{Comment @coderabbitai help to get the list of available commands and usage tips.}

Tip

You can disable sequence diagrams in the walkthrough.

Disable the reviews.sequence_diagrams setting to disable sequence diagrams in the walkthrough.

[Copilot]

Pull request overview

Updates the Claudius code review GitHub Actions workflow to correctly configure the Anthropic model selection and to enable persistent memory support via MemCan.

Changes:

• Replace the workflow’s (invalid) claude_model action input with a job-level ANTHROPIC_MODEL environment variable.
• Add MemCan configuration inputs (memcan_url, memcan_api_key) to the review action invocation.

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

[coderabbitai]

🧹 Nitpick comments (1)

.github/workflows/claude-code-review.yml (1)

34-35: Consider adding validation for MemCan credentials if they are required.

The PR description lists MEMCAN_URL and MEMCAN_API_KEY under "Required setup." If the workflow depends on MemCan being available, consider adding an early validation step that fails explicitly when these are not configured.

If MemCan is optional (nice-to-have but not required), this can be ignored.

🛡️ Proposed validation step (if MemCan is required)

     steps:
+      - name: Validate MemCan configuration
+        if: ${{ vars.MEMCAN_URL == '' || secrets.MEMCAN_API_KEY == '' }}
+        run: |
+          echo "::error::MemCan is not configured. Set MEMCAN_URL (variable) and MEMCAN_API_KEY (secret) in repository settings."
+          exit 1
       - name: Claudius Review
         uses: lklimek/claudius-review-action@main

Based on learnings: "In GitHub Actions workflow files, prefer failing a job explicitly when a required secret or token is missing, instead of silently skipping steps."

🤖 Prompt for AI Agents

Verify each finding against the current code and only fix it if needed.

In @.github/workflows/claude-code-review.yml around lines 34 - 35, Add an early
validation step in the GitHub Actions workflow
(.github/workflows/claude-code-review.yml) that checks the required MemCan
inputs MEMCAN_URL and MEMCAN_API_KEY and fails the job explicitly if either is
missing; implement this by adding a job step (e.g., "Validate MemCan
credentials") that runs a shell check referencing ${{ vars.MEMCAN_URL }} and ${{
secrets.MEMCAN_API_KEY }} and exits non‑zero with a clear error message when
they are empty, or gate subsequent MemCan-using steps with an explicit
conditional using those same symbols if you prefer conditional skipping.

🤖 Prompt for all review comments with AI agents

Verify each finding against the current code and only fix it if needed.

Nitpick comments:
In @.github/workflows/claude-code-review.yml:
- Around line 34-35: Add an early validation step in the GitHub Actions workflow
(.github/workflows/claude-code-review.yml) that checks the required MemCan
inputs MEMCAN_URL and MEMCAN_API_KEY and fails the job explicitly if either is
missing; implement this by adding a job step (e.g., "Validate MemCan
credentials") that runs a shell check referencing ${{ vars.MEMCAN_URL }} and ${{
secrets.MEMCAN_API_KEY }} and exits non‑zero with a clear error message when
they are empty, or gate subsequent MemCan-using steps with an explicit
conditional using those same symbols if you prefer conditional skipping.

---

ℹ️ Review info

⚙️ Run configuration

Configuration used: Path: .coderabbit.yaml

Review profile: CHILL

Plan: Pro

Run ID: 0a954875-9cdb-44c0-97b5-86fcc98e1f94

📥 Commits

Reviewing files that changed from the base of the PR and between 47e6905 and eed62e4.

📒 Files selected for processing (1)

• .github/workflows/claude-code-review.yml