Bring the upstream v1 `claude_args` input and `structured_output` output
into this Gitea fork so downstream workflows can run the agent with
arbitrary Claude CLI flags (notably `--json-schema`) and read the
schema-validated verdict back as an action output, without an
agent-written file.
Approach (issue Option B, ported rather than bumped): the production
"Run Claude Code" step previously delegated to the external
anthropics/claude-code-base-action@v0.0.63, which has neither input.
Upstream base-action main has them but has migrated to the Claude Agent
SDK — a wholesale divergence that would change v0.0.63 behavior every
downstream step relies on. Instead this invokes the vendored base-action
directly via `bun run ${github.action_path}/base-action/src/index.ts`
(the same github.action_path pattern prepare.ts already uses, reliable
on Gitea), and ports only the two features onto the v0.0.63 process-spawn
engine.
- base-action/src/run-claude.ts: tokenize claude_args with shell-quote
(comment-line stripping; quoted/file-path schemas survive intact) and
append after the byte-identical BASE_ARGS, so empty claude_args yields
an unchanged arg list; extract structured_output from the stream-json
result event when --json-schema is present, failing loudly if absent.
- base-action/src/index.ts: forward INPUT_CLAUDE_ARGS.
- base-action/action.yml: add claude_args input + structured_output output.
- action.yml: add claude_args input + structured_output output; replace
the external base-action delegation with a direct bun-run of the
vendored copy (full INPUT_*/provider env contract derived from the
vendored validate-env/index); bump the default Claude CLI install to
2.1.160 (--json-schema requires a newer CLI than 1.0.117).
- shell-quote added to both package.json files; root bun.lock reconciled
(it was stale vs package.json — non-frozen installs already resolved
the newer tree).
- Tests for tokenizer, hasJsonSchema, and structured-output extraction.
- README: inputs/outputs tables, "Structured output" + "Version pins".
- examples/gitea-structured-output.yml.
Follow-up (cannot be done from this repo): consumers using a pre-baked
runner image (path_to_claude_code_executable) must rebuild that image
with a --json-schema-capable Claude CLI and restart the runner.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* feat: integrate Claude Code SDK to replace process spawning
- Add @anthropic-ai/claude-code dependency to base-action
- Replace mkfifo/cat process spawning with direct SDK usage
- Remove global Claude Code installation from action.yml files
- Maintain full compatibility with existing options
- Add comprehensive tests for SDK integration
This change makes the implementation cleaner and more reliable by
eliminating the complexity of managing child processes and named pipes.
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
* fix: add debugging and bun executable for Claude Code SDK
- Add stderr handler to capture CLI errors
- Explicitly set bun as the executable for the SDK
- This should help diagnose why the CLI is exiting with code 1
* fix: extract mcpServers from parsed MCP config
The SDK expects just the servers object, not the wrapper object with mcpServers property.
* tsc
---------
Co-authored-by: Claude <noreply@anthropic.com>
reza
Ashwin Bhat