chore: update claude-code-base-action to v0.0.14

Add ROADMAP.md documenting planned features and improvements for reaching v1.0:
- GitHub Action CI results visibility
- Cross-repo support
- Workflow file modification capabilities
- Additional event trigger support
- Configurable commit signing
- Enhanced code review features
- Bot user trigger support
- Customizable base prompts

The roadmap provides transparency on development priorities and invites
community feedback and contributions.

.github/workflows/claude-review.yml

@@ -29,4 +29,4 @@ jobs:
 
             Be constructive and specific in your feedback. Give inline comments where applicable.
           anthropic_api_key: ${{ secrets.ANTHROPIC_API_KEY }}
-          allowed_tools: "mcp__github__add_pull_request_review_comment"
+          allowed_tools: "mcp__github__create_pending_pull_request_review,mcp__github__add_pull_request_review_comment_to_pending_review,mcp__github__submit_pending_pull_request_review,mcp__github__get_pull_request_diff"

README.md

@@ -70,6 +70,8 @@ jobs:
           #   NODE_ENV: test
           #   DEBUG: true
           #   API_URL: https://api.example.com
+          # Optional: limit the number of conversation turns
+          # max_turns: "5"
 ```
 
 ## Inputs
@@ -78,6 +80,7 @@ jobs:
 | --------------------- | -------------------------------------------------------------------------------------------------------------------- | -------- | --------- |
 | `anthropic_api_key`   | Anthropic API key (required for direct API, not needed for Bedrock/Vertex)                                           | No\*     | -         |
 | `direct_prompt`       | Direct prompt for Claude to execute automatically without needing a trigger (for automated workflows)                | No       | -         |
+| `max_turns`           | Maximum number of conversation turns Claude can take (limits back-and-forth exchanges)                               | No       | -         |
 | `timeout_minutes`     | Timeout in minutes for execution                                                                                     | No       | `30`      |
 | `github_token`        | GitHub token for Claude to operate with. **Only include this if you're connecting a custom GitHub app of your own!** | No       | -         |
 | `model`               | Model to use (provider-specific format required for Bedrock/Vertex)                                                  | No       | -         |
@@ -311,6 +314,24 @@ You can pass custom environment variables to Claude Code execution using the `cl
 
 The `claude_env` input accepts YAML format where each line defines a key-value pair. These environment variables will be available to Claude Code during execution, allowing it to run tests, build processes, or other commands that depend on specific environment configurations.
 
+### Limiting Conversation Turns
+
+You can use the `max_turns` parameter to limit the number of back-and-forth exchanges Claude can have during task execution. This is useful for:
+
+- Controlling costs by preventing runaway conversations
+- Setting time boundaries for automated workflows
+- Ensuring predictable behavior in CI/CD pipelines
+
+```yaml
+- uses: anthropics/claude-code-action@beta
+  with:
+    anthropic_api_key: ${{ secrets.ANTHROPIC_API_KEY }}
+    max_turns: "5" # Limit to 5 conversation turns
+    # ... other inputs
+```
+
+When the turn limit is reached, Claude will stop execution gracefully. Choose a value that gives Claude enough turns to complete typical tasks while preventing excessive usage.
+
 ### Custom Tools
 
 By default, Claude only has access to:

ROADMAP.md

@@ -0,0 +1,20 @@
+# Claude Code GitHub Action Roadmap
+
+Thank you for trying out the beta of our GitHub Action! This document outlines our path to `v1.0`. Items are not necessarily in priority order.
+
+## Path to 1.0
+
+- **Ability to see GitHub Action CI results** - This will enable Claude to look at CI failures and make updates to PRs to fix test failures, lint errors, and the like.
+- **Cross-repo support** - Enable Claude to work across multiple repositories in a single session
+- **Ability to modify workflow files** - Let Claude update GitHub Actions workflows and other CI configuration files
+- **Support for workflow_dispatch and repository_dispatch events** - Dispatch Claude on events triggered via API from other workflows or from other services
+- **Ability to disable commit signing** - Option to turn off GPG signing for environments where it's not required. This will enable Claude to use normal `git` bash commands for committing. This will likely become the default behavior once added.
+- **Better code review behavior** - Support inline comments on specific lines, provide higher quality reviews with more actionable feedback
+- **Support triggering @claude from bot users** - Allow automation and bot accounts to invoke Claude
+- **Customizable base prompts** - Full control over Claude's initial context with template variables like `$PR_COMMENTS`, `$PR_FILES`, etc. Users can replace our default prompt entirely while still accessing key contextual data
+
+---
+
+**Note:** This roadmap represents our current vision for reaching `v1.0` and is subject to change based on user feedback and development priorities.
+
+We welcome feedback on these planned features! If you're interested in contributing to any of these features, please open an issue to discuss implementation details with us. We're also open to suggestions for new features not listed here.

action.yml

@@ -62,6 +62,10 @@ inputs:
     required: false
     default: "false"
 
+  max_turns:
+    description: "Maximum number of conversation turns"
+    required: false
+    default: ""
   timeout_minutes:
     description: "Timeout in minutes for execution"
     required: false
@@ -96,6 +100,7 @@ runs:
         ASSIGNEE_TRIGGER: ${{ inputs.assignee_trigger }}
         BASE_BRANCH: ${{ inputs.base_branch }}
         ALLOWED_TOOLS: ${{ inputs.allowed_tools }}
+        DISALLOWED_TOOLS: ${{ inputs.disallowed_tools }}
         CUSTOM_INSTRUCTIONS: ${{ inputs.custom_instructions }}
         DIRECT_PROMPT: ${{ inputs.direct_prompt }}
         MCP_CONFIG: ${{ inputs.mcp_config }}
@@ -105,12 +110,13 @@ runs:
     - name: Run Claude Code
       id: claude-code
       if: steps.prepare.outputs.contains_trigger == 'true'
-      uses: anthropics/claude-code-base-action@79b8cfc932eb13806c23905842145e6f05c89e2e # v0.0.13
+      uses: anthropics/claude-code-base-action@a0d79f9c1798b06292dbc80f8f95cf742ce7a213 # v0.0.14
       with:
         prompt_file: ${{ runner.temp }}/claude-prompts/claude-prompt.txt
         allowed_tools: ${{ env.ALLOWED_TOOLS }}
         disallowed_tools: ${{ env.DISALLOWED_TOOLS }}
         timeout_minutes: ${{ inputs.timeout_minutes }}
+        max_turns: ${{ inputs.max_turns }}
         model: ${{ inputs.model || inputs.anthropic_model }}
         mcp_config: ${{ steps.prepare.outputs.mcp_config }}
         use_bedrock: ${{ inputs.use_bedrock }}

examples/claude-auto-review.yml

@@ -35,4 +35,4 @@ jobs:
 
             Provide constructive feedback with specific suggestions for improvement.
             Use inline comments to highlight specific areas of concern.
-          # allowed_tools: "mcp__github__add_pull_request_review_comment"
+          # allowed_tools: "mcp__github__create_pending_pull_request_review,mcp__github__add_pull_request_review_comment_to_pending_review,mcp__github__submit_pending_pull_request_review,mcp__github__get_pull_request_diff"