2 Commits

Author	SHA1	Message	Date
Ashwin Bhat	a3c96305c1	fix: move critical outputs to immediately after prepare step ... Previously, outputs like GITHUB_TOKEN and branch_name were set after Claude execution completed. This caused issues if Claude failed, as downstream cleanup steps wouldn't have access to these outputs. Now outputs are set immediately after prepare() completes, ensuring they're available even if Claude execution fails.	2025-08-06 08:24:21 -07:00
Ashwin Bhat	923d1d0592	feat: merge prepare and run-claude steps into unified entrypoint ... - Create run-claude-core.ts as the central Claude execution function - Update action.yml to use single "Run Claude" step - Create src/entrypoints/run.ts that combines prepare + run-claude logic - Pass environment variables as object to Claude instead of setting process.env - Update create-prompt to return tools (still exports env vars for compatibility) - Add TODO comments for future refactoring to remove env var dependency - Both action.yml and base-action continue to work correctly This simplifies the action flow by removing intermediate steps and environment variable passing between prepare and run-claude phases. 🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <noreply@anthropic.com>	2025-08-06 08:24:20 -07:00