15 lines
1.2 KiB
Markdown
15 lines
1.2 KiB
Markdown
|
# PR Review Roadmap
|
||
|
|
|
||
|
|
## Phase 1: Codex CLI Integration (current)
|
||
|
|
|
||
|
|
Spawn the real Codex CLI for adversarial PR review. Runtime copied from openai/codex-plugin-cc into `codex/` subdirectory. Commands (`/codex-review`, `/codex-setup`, `/codex-status`) call `codex-companion.mjs`. Stop-review-gate hook runs Codex review before session ends. Deep agent runs adversarial review as a mandatory gate before `[complete]`.
|
||
|
|
|
||
|
|
## Phase 2: Claude-Native PR Review (future)
|
||
|
|
|
||
|
|
Replace Codex CLI dependency with native Claude Code agents:
|
||
|
|
|
||
|
|
1. **Create `codeflash-pr-review` agent** — adapts codex adversarial review prompt for Claude, with attack surface taxonomy and structured JSON output. Focused on general PR review (not optimization-specific like existing `codeflash-review` agent).
|
||
|
|
2. **Create `/codeflash-pr-review` command** — handles scope selection (working-tree/branch/PR number), gathers git context, launches the agent. Replaces codex-companion.mjs logic with native git commands.
|
||
|
|
3. **Add review output schema** to `agents/references/shared/review-output.schema.json`.
|
||
|
|
4. **Create stop-review-gate hook** — uses the stop-review-gate prompt concept, still powered by Codex CLI (OpenAI models are better reviewers, Claude is better at implementing the fixes).
|