feat: add review_plan tool handler

PROJECT_STATE.md

@@ -7,7 +7,7 @@ ChatGPT MCP Server
 ## Status
 
 Planning complete.
-Phase 0 complete. Phase 1 complete. Phase 2 complete. Phase 3 complete. Task 4.1 complete.
+Phase 0 complete. Phase 1 complete. Phase 2 complete. Phase 3 complete. Task 4.1 complete. Task 4.2 complete.
 
 ## Current Phase
 
@@ -69,6 +69,21 @@ Implemented `src/tools/ask-chatgpt.js` with dependency-injected handler and 27 o
 - Every path returns structured `{ ok, answer|error, warnings }` — never throws to caller
 - 27 tests covering: success path, validation failure, config failure, budget failure, client creation failure, OpenAI failure, dependency call order, error handling for null/string throws, warning propagation, result shape, and short-circuit behavior
 
+### Task 4.2 — review_plan MCP Tool Handler ✅
+
+Implemented `src/tools/review-plan.js` with dependency-injected handler and 28 orchestration-only tests in `test/tools/review-plan.test.js`.
+
+**Key design decisions:**
+- Execution order: validate → loadConfig → checkContextBudget → buildReviewPlanPrompt → createOpenAIClient → sendOpenAIResponse
+- All external deps injected (loadConfig, createOpenAIClient, sendOpenAIResponse); internal utilities imported directly
+- OpenAI errors pass through `String(err)` unchanged — no wrapping or reformatting
+- Budget check short-circuits before prompt building or client creation
+- Every path returns structured `{ ok, answer|error, warnings }` — never throws to caller
+- 28 tests mirroring 4.1 structure with one additional test verifying buildReviewPlanPrompt is called with budget.input
+
+**Next pending task:**
+- Task 4.3 — review_code tool handler (`src/tools/review-code.js`, `test/tools/review-code.test.js`)
+
 **Not done yet (Phase 4):**
 - No MCP tool registration
-- Other tool handlers (review_plan, review_code, debug_issue, architecture_review)
+- Other tool handlers (review_code, debug_issue, architecture_review)