chatgpt-mcp/PROJECT_STATE.md

# PROJECT_STATE.md

## Project

ChatGPT MCP Server

## Status

Planning complete.
Phase 0 complete. Phase 1 complete. Phase 2 complete. Phase 3 complete. Task 4.1 complete. Task 4.2 complete. Task 4.3 complete. Task 4.4 complete.

## Current Phase

Phase 4 - Tool Handlers

## Completed Tasks

- Task 0.1 — Create repository skeleton ✅
- Task 0.2 — package.json with dependencies ✅
- Task 1.1 — Configuration loader ✅
- Task 1.2 — Secret redaction utility (`src/utils/redact.js`) ✅
- Task 1.3 — Context budget utility (`src/utils/context-budget.js`) ✅
- Task 1.4 — Safe logging helper (`src/utils/logging.js`) ✅
- Task 2.1 — OpenAI client wrapper (`src/openai/client.js`) ✅
- Task 2.2 — Response builder (`src/openai/responses.js`) ✅
- Task 2.3 — Error handling and edge cases for OpenAI integration (tests) ✅
- Task 3.1 — Zod input validation schemas (`src/tools/schemas.js`, `test/tools/schemas.test.js`) ✅
- Task 3.2 — Base prompt template (`src/prompts/base.js`, `test/prompts/base.test.js`) ✅
- Task 3.3 — ask_chatgpt prompt builder (`src/prompts/ask-chatgpt.js`, `test/prompts/ask-chatgpt.test.js`) ✅
- Task 3.4 — review_plan prompt builder (`src/prompts/review-plan.js`, `test/prompts/review-plan.test.js`) ✅
- 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`) ✅
- Task 4.2 — review_plan MCP tool handler (`src/tools/review-plan.js`, `test/tools/review-plan.test.js`) ✅
- Task 4.3 — review_code MCP tool handler (`src/tools/review-code.js`, `test/tools/review-code.test.js`) ✅
- Task 4.4 — debug_issue tool handler (`src/tools/debug-issue.js`, `test/tools/debug-issue.test.js`) ✅

## Phase 3 Completion Summary

Phase 3 — Tool Inputs and Prompts — is now complete.

**Completed prompt builders:**
- `buildBasePrompt` — base system prompt (ARCHITECTURE.md §11)
- `buildAskChatGptPrompt` — general second-opinion advisor
- `buildReviewPlanPrompt` — plan review before implementation
- `buildReviewCodePrompt` — focused code/diff review
- `buildDebugIssuePrompt` — error/log/stack trace analysis
- `buildArchitectureReviewPrompt` — architecture decision trade-off review

**What Phase 3 established:**
- Prompt layer complete with composition pattern established.
- All prompt builders tested (56 tests for architecture-review alone; 384 total).
- Each builder follows the same pattern: `buildBasePrompt()` → `\n\n---\n\n` → tool-specific section.
- Guard rails reinforced in every builder (Claude Code is executor; ChatGPT is advisory only).

**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

### 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

**Task 4.3 — review_code MCP Tool Handler ✅**

Implemented `src/tools/review-code.js` with dependency-injected handler and 28 orchestration-only tests in `test/tools/review-code.test.js`.

**Key design decisions:**
- Execution order: validate → loadConfig → checkContextBudget → buildReviewCodePrompt → 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 4.1/4.2 structure with one test verifying buildReviewCodePrompt is called with budget.input

**Next pending task:**
- Task 4.5 — architecture_review tool handler (`src/tools/architecture-review.js`, `test/tools/architecture-review.test.js`)

**Not done yet (Phase 4):**
- No MCP tool registration