Ndlovu Code Reviewer

Instructions

Implementation Reference

• src/index.ts:366-459 (handler)

  The main execution logic of the tool: fetches git diff and linter results on local changes, generates AI prompt, calls Gemini CLI for synthesis, returns structured review JSON.
  async () => { logInfo('Code review tool invoked'); try { // 1. Run the hybrid analysis directly in Node.js const analysisData = await runHybridAnalysis(); // 2. Short-circuit if no relevant files have changed if (analysisData === '{}') { logInfo('No relevant files changed, returning empty result'); return { content: [ { type: "text", text: JSON.stringify({ summary: 'No relevant files changed.', assessment: '', findings: [] }, null, 2), }, ], }; } // 3. Create a simplified prompt for Gemini CLI with the analysis data const prompt = `You are an expert-level AI code reviewer, acting as a synthesis engine. Your primary function is to interpret results from a static analysis tool and combine them with your own deep code analysis to provide a single, comprehensive, and human-friendly review. Your entire response MUST be a single, valid JSON object. Do not include any text outside of the JSON structure. **CONTEXT GATHERING:** You will be provided with a JSON object containing two key pieces of information: 1. \`diff\`: The raw output of \`git diff HEAD\`. 2. \`linterReport\`: A JSON array of deterministic issues found by a static analysis tool (ESLint). The full context is as follows: --- CONTEXT START --- ${analysisData} --- CONTEXT END --- **REVIEW INSTRUCTIONS & OUTPUT SCHEMA:** Follow these steps meticulously to construct the final JSON object: 1. **Synthesize Linter Findings:** First, analyze the \`linterReport\`. For each issue found by the linter, translate its technical message into an empathetic, educational comment. Explain *why* the rule is important. These findings are your ground truth for style and common errors. 2. **Perform Deeper Analysis:** Next, analyze the \`diff\` to identify higher-level issues that static analysis tools typically miss. Focus on: - Logic errors, incorrect algorithms, or missed edge cases. - Architectural inconsistencies or violations of design patterns. - Performance bottlenecks or inefficient code. - Unclear naming or lack of necessary comments for complex logic. 3. **De-duplicate and Merge:** Combine the findings from both steps into a single, de-duplicated list of actionable issues. If an issue is flagged by both the linter and your own analysis, prioritize the linter's finding but enrich its \`comment\` with your deeper contextual explanation. 4. **Summarize and Assess:** Based on your complete analysis, write a concise \`summary\` of the changes and a high-level \`assessment\` of the code quality. This is the correct place for all positive feedback, praise for good architectural decisions, and other high-level, non-actionable observations. 5. **CRITICAL RULE FOR \`findings\`:** The \`findings\` array must ONLY contain actionable issues that require a developer to make a code change. Do NOT include positive feedback, praise for good architecture, or general observations in the \`findings\` array. Any finding with a suggestion of "No change needed" must be excluded from this array and its content moved to the \`assessment\` field. 6. **Format Output:** Assemble everything into the final JSON object according to the schema below. **JSON SCHEMA:** { "summary": "...", "assessment": "...", "findings": [ { "filePath": "...", "lineNumber": "...", "severity": "...", "category": "...", "comment": "...", "suggestion": "..." } ] }`; // 3. Execute Gemini CLI with the prepared prompt without shell quoting logInfo('Executing Gemini CLI for code review analysis'); const { stdout } = await runGeminiPrompt(prompt); // 4. Return the successful JSON output from stdout logInfo('Code review analysis completed successfully'); return { content: [ { type: "text", text: stdout, }, ], }; } catch (error: unknown) { logError('Code review tool execution failed', error); console.error(`Execution failed: ${error instanceof Error ? error.message : String(error)}`); throw error; } }
• src/index.ts:362-460 (registration)

  Registers the 'review-local-changes' tool with the MCP server, including name, description, empty schema, and handler reference.
  server.tool( "review-local-changes", // The unique name of our tool "Analyze and review uncommitted code changes using AI and static analysis. Performs comprehensive code review including linting, style checks, logic analysis, and security review. Use this when user asks to review, analyze, check, or examine code changes, diffs, or local modifications.", {}, // No input parameters are needed async () => { logInfo('Code review tool invoked'); try { // 1. Run the hybrid analysis directly in Node.js const analysisData = await runHybridAnalysis(); // 2. Short-circuit if no relevant files have changed if (analysisData === '{}') { logInfo('No relevant files changed, returning empty result'); return { content: [ { type: "text", text: JSON.stringify({ summary: 'No relevant files changed.', assessment: '', findings: [] }, null, 2), }, ], }; } // 3. Create a simplified prompt for Gemini CLI with the analysis data const prompt = `You are an expert-level AI code reviewer, acting as a synthesis engine. Your primary function is to interpret results from a static analysis tool and combine them with your own deep code analysis to provide a single, comprehensive, and human-friendly review. Your entire response MUST be a single, valid JSON object. Do not include any text outside of the JSON structure. **CONTEXT GATHERING:** You will be provided with a JSON object containing two key pieces of information: 1. \`diff\`: The raw output of \`git diff HEAD\`. 2. \`linterReport\`: A JSON array of deterministic issues found by a static analysis tool (ESLint). The full context is as follows: --- CONTEXT START --- ${analysisData} --- CONTEXT END --- **REVIEW INSTRUCTIONS & OUTPUT SCHEMA:** Follow these steps meticulously to construct the final JSON object: 1. **Synthesize Linter Findings:** First, analyze the \`linterReport\`. For each issue found by the linter, translate its technical message into an empathetic, educational comment. Explain *why* the rule is important. These findings are your ground truth for style and common errors. 2. **Perform Deeper Analysis:** Next, analyze the \`diff\` to identify higher-level issues that static analysis tools typically miss. Focus on: - Logic errors, incorrect algorithms, or missed edge cases. - Architectural inconsistencies or violations of design patterns. - Performance bottlenecks or inefficient code. - Unclear naming or lack of necessary comments for complex logic. 3. **De-duplicate and Merge:** Combine the findings from both steps into a single, de-duplicated list of actionable issues. If an issue is flagged by both the linter and your own analysis, prioritize the linter's finding but enrich its \`comment\` with your deeper contextual explanation. 4. **Summarize and Assess:** Based on your complete analysis, write a concise \`summary\` of the changes and a high-level \`assessment\` of the code quality. This is the correct place for all positive feedback, praise for good architectural decisions, and other high-level, non-actionable observations. 5. **CRITICAL RULE FOR \`findings\`:** The \`findings\` array must ONLY contain actionable issues that require a developer to make a code change. Do NOT include positive feedback, praise for good architecture, or general observations in the \`findings\` array. Any finding with a suggestion of "No change needed" must be excluded from this array and its content moved to the \`assessment\` field. 6. **Format Output:** Assemble everything into the final JSON object according to the schema below. **JSON SCHEMA:** { "summary": "...", "assessment": "...", "findings": [ { "filePath": "...", "lineNumber": "...", "severity": "...", "category": "...", "comment": "...", "suggestion": "..." } ] }`; // 3. Execute Gemini CLI with the prepared prompt without shell quoting logInfo('Executing Gemini CLI for code review analysis'); const { stdout } = await runGeminiPrompt(prompt); // 4. Return the successful JSON output from stdout logInfo('Code review analysis completed successfully'); return { content: [ { type: "text", text: stdout, }, ], }; } catch (error: unknown) { logError('Code review tool execution failed', error); console.error(`Execution failed: ${error instanceof Error ? error.message : String(error)}`); throw error; } } );
• src/index.ts:313-353 (helper)

  Key helper function that identifies changed JS/TS files via git, runs linter, fetches full git diff, and returns JSON payload for AI analysis.
  async function runHybridAnalysis(): Promise<string> { logInfo('Starting hybrid analysis'); try { // 1. Find all modified and added JS/TS/Vue files, excluding deleted files const { stdout: gitFiles } = await execAsync("git diff HEAD --name-only --diff-filter=AM"); const changedFiles = gitFiles .split('\n') .filter(file => file.trim() !== '') .filter(file => /\.(js|ts|tsx|vue)$/.test(file)); logInfo('Found changed files', { totalFiles: changedFiles.length, files: changedFiles }); // 2. If no relevant files have changed, return empty JSON object if (changedFiles.length === 0) { logInfo('No relevant files changed, returning empty result'); return '{}'; } // 3. Run the project's preferred linter logInfo('Running linter analysis'); const linterReport = await runProjectLinter(changedFiles); logInfo('Linter analysis completed', { issuesFound: linterReport.length }); // 4. Get the raw git diff const { stdout: gitDiff } = await execAsync("git diff HEAD"); logInfo('Git diff retrieved', { diffLength: gitDiff.length }); // 5. Combine the git diff and linter report into JSON const result = { diff: gitDiff, linterReport: linterReport }; logInfo('Hybrid analysis completed successfully'); return JSON.stringify(result, null, 2); } catch (error) { logError('Error in hybrid analysis', error); throw error; } }
• src/index.ts:108-123 (helper)

  Helper to invoke Gemini CLI safely, handling long prompts by switching to stdin mode.
  async function runGeminiPrompt(prompt: string, timeoutMs = 120_000): Promise<GeminiResult> { logInfo('Running Gemini CLI prompt', { promptLength: prompt.length, timeoutMs }); try { return await spawnGemini([prompt], null, timeoutMs); } catch (error) { if (isArgumentTooLongError(error)) { logWarning('Gemini prompt exceeded argument length; falling back to stdin streaming'); console.warn("Gemini prompt exceeded argument length; streaming via stdin instead."); return spawnGemini([], prompt, timeoutMs); } logError('Gemini CLI prompt failed', error); throw error; } }
• src/index.ts:190-241 (helper)

  Detects project linter (prioritizes ESLint) and runs it on changed files, with fallbacks to JSHint and TypeScript checking, standardizing output.
  async function runProjectLinter(changedFiles: string[]): Promise<any[]> { try { // Check if project has ESLint configuration const hasEslintConfig = await checkFileExists(['eslint.config.js', '.eslintrc.js', '.eslintrc.json', '.eslintrc.yml', '.eslintrc.yaml', '.eslintrc']); if (hasEslintConfig) { try { const { stdout: linterJson } = await spawnEslint(changedFiles, 30000); return linterJson.trim() ? JSON.parse(linterJson) : []; } catch (eslintError) { console.warn('ESLint execution failed, trying fallback linter:', eslintError instanceof Error ? eslintError.message : String(eslintError)); } } // Fallback 1: Try JSHint if available if (await checkCommandExists('jshint')) { try { const results = []; for (const file of changedFiles) { const { stderr } = await execAsync(`jshint ${file}`, { timeout: 10000 }); if (stderr) { const issues = parseJshintOutput(stderr, file); results.push(...issues); } } return results; } catch (jshintError) { console.warn('JSHint execution failed:', jshintError instanceof Error ? jshintError.message : String(jshintError)); } } // Fallback 2: Try basic TypeScript compiler checking const hasTsConfig = await checkFileExists(['tsconfig.json']); if (hasTsConfig && changedFiles.some(f => f.endsWith('.ts') || f.endsWith('.tsx'))) { try { const { stderr } = await execAsync('npx tsc --noEmit', { timeout: 30000 }); if (stderr) { return parseTypeScriptErrors(stderr); } } catch (tscError) { console.warn('TypeScript compilation check failed:', tscError instanceof Error ? tscError.message : String(tscError)); } } // If no linter is available, return empty array console.warn('No suitable linter found in project, proceeding without static analysis'); return []; } catch (error) { console.warn('Linter detection failed:', error); return []; } }