feat: add ask_chatgpt tool handler

PROJECT_STATE.md

@@ -7,13 +7,13 @@ ChatGPT MCP Server
 ## Status
 
 Planning complete.
-Phase 0 complete. Phase 1 complete. Phase 2 complete. Phase 3 complete.
+Phase 0 complete. Phase 1 complete. Phase 2 complete. Phase 3 complete. Task 4.1 complete.
 
 ## Current Phase
 
 Phase 4 - Tool Handlers
 
-## Completed Tasks (Phase 3 Complete)
+## Completed Tasks
 
 - Task 0.1 — Create repository skeleton ✅
 - Task 0.2 — package.json with dependencies ✅
@@ -31,6 +31,7 @@ Phase 4 - Tool Handlers
 - Task 3.5 — review_code prompt builder (`src/prompts/review-code.js`, `test/prompts/review-code.test.js`) ✅
 - Task 3.6 — debug_issue prompt builder (`src/prompts/debug-issue.js`, `test/prompts/debug-issue.test.js`) ✅
 - Task 3.7 — architecture_review prompt builder (`src/prompts/architecture-review.js`, `test/prompts/architecture-review.test.js`) ✅
+- Task 4.1 — ask_chatgpt MCP tool handler (`src/tools/ask-chatgpt.js`, `test/tools/ask-chatgpt.test.js`) ✅
 
 ## Phase 3 Completion Summary
 
@@ -53,3 +54,21 @@ Phase 3 — Tool Inputs and Prompts — is now complete.
 **Not done yet (belongs to Phase 4):**
 - No MCP tool registration.
 - No tool handlers.
+
+## Completed Tasks (Phase 4)
+
+### Task 4.1 — ask_chatgpt MCP Tool Handler ✅
+
+Implemented `src/tools/ask-chatgpt.js` with dependency-injected handler and 27 orchestration-only tests in `test/tools/ask-chatgpt.test.js`.
+
+**Key design decisions:**
+- Execution order: validate → loadConfig → checkContextBudget → buildAskChatGptPrompt → 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
+- 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
+
+**Not done yet (Phase 4):**
+- No MCP tool registration
+- Other tool handlers (review_plan, review_code, debug_issue, architecture_review)