Initial Version

packages/cli/src/config/config.ts

@@ -70,6 +70,11 @@ export interface CliArgs {
   prompt: string | undefined;
   promptInteractive: string | undefined;
 
+  ralphWiggum: boolean | undefined;
+  completionPromise: string | undefined;
+  maxIterations: number | undefined;
+  memoryFile: string | undefined;
+
   yolo: boolean | undefined;
   approvalMode: string | undefined;
   allowedMcpServerNames: string[] | undefined;
@@ -141,6 +146,31 @@ export async function parseArguments(
           description: 'Run in sandbox?',
         })
 
+        .option('ralph-wiggum', {
+          alias: 'ralphWiggum',
+          type: 'boolean',
+          description:
+            'Enable Ralph Wiggum mode (iterative loop with YOLO mode).',
+        })
+        .option('completion-promise', {
+          alias: 'completionPromise',
+          type: 'string',
+          description:
+            'The string to look for in the output to signal completion in Ralph Wiggum mode.',
+        })
+        .option('max-iterations', {
+          alias: 'maxIterations',
+          type: 'number',
+          description: 'Maximum number of iterations for Ralph Wiggum mode.',
+        })
+        .option('memory-file', {
+          alias: 'memoryFile',
+          type: 'string',
+          description:
+            'Task-specific memory file for Ralph Wiggum mode (defaults to memories.md).',
+          default: 'memories.md',
+        })
+
         .option('yolo', {
           alias: 'y',
           type: 'boolean',

packages/cli/src/gemini.test.tsx

@@ -476,6 +476,10 @@ describe('gemini.tsx main function kitty protocol', () => {
       prompt: undefined,
       promptInteractive: undefined,
       query: undefined,
+      ralphWiggum: undefined,
+      completionPromise: undefined,
+      maxIterations: undefined,
+      memoryFile: undefined,
       yolo: undefined,
       approvalMode: undefined,
       allowedMcpServerNames: undefined,

packages/cli/src/gemini.tsx

@@ -24,7 +24,7 @@ import { loadSettings, SettingScope } from './config/settings.js';
 import { getStartupWarnings } from './utils/startupWarnings.js';
 import { getUserStartupWarnings } from './utils/userStartupWarnings.js';
 import { ConsolePatcher } from './ui/utils/ConsolePatcher.js';
-import { runNonInteractive } from './nonInteractiveCli.js';
+import { runNonInteractive, runRalphWiggum } from './nonInteractiveCli.js';
 import {
   cleanupCheckpoints,
   registerCleanup,
@@ -740,13 +740,25 @@ export async function main() {
 
     initializeOutputListenersAndFlush();
 
-    await runNonInteractive({
-      config,
-      settings,
-      input,
-      prompt_id,
-      resumedSessionData,
-    });
+    if (argv.ralphWiggum) {
+      await runRalphWiggum({
+        config,
+        settings,
+        input,
+        prompt_id,
+        resumedSessionData,
+        completionPromise: argv.completionPromise,
+        maxIterations: argv.maxIterations,
+      });
+    } else {
+      await runNonInteractive({
+        config,
+        settings,
+        input,
+        prompt_id,
+        resumedSessionData,
+      });
+    }
     // Call cleanup before process.exit, which causes cleanup to not run
     await runExitCleanup();
     process.exit(ExitCodes.SUCCESS);

packages/cli/src/nonInteractiveCli.ts

@@ -55,13 +55,187 @@ interface RunNonInteractiveParams {
   resumedSessionData?: ResumedSessionData;
 }
 
+interface IterationResult {
+  iteration: number;
+  status: 'Success' | 'Failed';
+  testsPassed?: number;
+  testsFailed?: number;
+  testsTotal?: number;
+}
+
+function extractTestStats(output: string): {
+  passed?: number;
+  failed?: number;
+  total?: number;
+} {
+  // Common patterns for test runners (Vitest, Jest, Mocha, etc.)
+  const patterns = [
+    // Vitest/Jest: "Tests:       3 passed, 1 failed, 4 total"
+    /Tests:\s*(?:(\d+)\s+passed)?(?:,\s*)?(?:(\d+)\s+failed)?(?:,\s*)?(?:(\d+)\s+total)?/i,
+    // Mocha: "3 passing (10ms)"
+    /(\d+)\s+passing/i,
+    // Mocha: "1 failing"
+    /(\d+)\s+failing/i,
+    // Generic: "Passed: 3, Failed: 1"
+    /Passed:\s*(\d+)/i,
+    /Failed:\s*(\d+)/i,
+  ];
+
+  let passed: number | undefined;
+  let failed: number | undefined;
+  let total: number | undefined;
+
+  // Try Vitest/Jest pattern first as it is most comprehensive
+  const vitestMatch = output.match(patterns[0]);
+  if (vitestMatch && (vitestMatch[1] || vitestMatch[2] || vitestMatch[3])) {
+    passed = vitestMatch[1] ? parseInt(vitestMatch[1], 10) : 0;
+    failed = vitestMatch[2] ? parseInt(vitestMatch[2], 10) : 0;
+    total = vitestMatch[3] ? parseInt(vitestMatch[3], 10) : 0;
+    return { passed, failed, total };
+  }
+
+  // Fallback to individual patterns
+  const passingMatch = output.match(patterns[1]);
+  if (passingMatch) {
+    passed = parseInt(passingMatch[1], 10);
+  } else {
+    const passedMatch = output.match(patterns[3]);
+    if (passedMatch) passed = parseInt(passedMatch[1], 10);
+  }
+
+  const failingMatch = output.match(patterns[2]);
+  if (failingMatch) {
+    failed = parseInt(failingMatch[1], 10);
+  } else {
+    const failedMatch = output.match(patterns[4]);
+    if (failedMatch) failed = parseInt(failedMatch[1], 10);
+  }
+
+  return { passed, failed, total };
+}
+
+function printSummary(results: IterationResult[]) {
+  process.stderr.write('\n--- Ralph Wiggum Mode Summary ---\n');
+  process.stderr.write(
+    '| Iteration | Status  | Tests Passed | Tests Failed |\n',
+  );
+  process.stderr.write(
+    '|-----------|---------|--------------|--------------|\n',
+  );
+  for (const result of results) {
+    const passed = result.testsPassed !== undefined ? result.testsPassed : '-';
+    const failed = result.testsFailed !== undefined ? result.testsFailed : '-';
+    process.stderr.write(
+      `| ${result.iteration.toString().padEnd(9)} | ${result.status.padEnd(7)} | ${passed.toString().padEnd(12)} | ${failed.toString().padEnd(12)} |\n`,
+    );
+  }
+  process.stderr.write('---------------------------------\n\n');
+}
+
+import fs from 'node:fs';
+import path from 'node:path';
+
+// ... (existing imports)
+
+export async function runRalphWiggum({
+  config,
+  settings,
+  input,
+  prompt_id,
+  resumedSessionData,
+  completionPromise,
+  maxIterations,
+  memoryFile,
+}: RunNonInteractiveParams & {
+  completionPromise?: string;
+  maxIterations?: number;
+  memoryFile?: string;
+}): Promise<void> {
+  const effectiveMaxIterations = maxIterations ?? 10;
+  let iterations = 0;
+  let currentResumedSessionData = resumedSessionData;
+  const results: IterationResult[] = [];
+  const effectiveMemoryFile = memoryFile || 'memories.md';
+  const memoriesPath = path.join(process.cwd(), effectiveMemoryFile);
+
+  if (!fs.existsSync(memoriesPath)) {
+    fs.writeFileSync(
+      memoriesPath,
+      `# Ralph Wiggum Memories\n\nTask: ${input}\n\nUse this file (${effectiveMemoryFile}) to store notes on what worked and what didn't work across iterations. The agent will read this at the start of each run.\n\n`,
+    );
+  }
+
+  process.stderr.write(
+    `[Ralph Wiggum] Starting loop. Max iterations: ${effectiveMaxIterations}\n`,
+  );
+
+  while (iterations < effectiveMaxIterations) {
+    iterations++;
+    process.stderr.write(
+      `[Ralph Wiggum] Iteration ${iterations}/${effectiveMaxIterations}\n`,
+    );
+
+    let currentInput = input;
+    try {
+      if (fs.existsSync(memoriesPath)) {
+        const memories = fs.readFileSync(memoriesPath, 'utf-8');
+        if (memories.trim()) {
+          currentInput = `Context from previous iterations (${effectiveMemoryFile}):\n${memories}\n\nTask:\n${input}`;
+          process.stderr.write(
+            `[Ralph Wiggum] Loaded context from ${effectiveMemoryFile}\n`,
+          );
+        }
+      }
+    } catch (error) {
+      process.stderr.write(
+        `[Ralph Wiggum] Failed to read ${effectiveMemoryFile}: ${error}\n`,
+      );
+    }
+
+    const output = await runNonInteractive({
+      config,
+      settings,
+      input: currentInput,
+      prompt_id,
+      resumedSessionData: currentResumedSessionData,
+    });
+
+    const stats = extractTestStats(output);
+    const success =
+      completionPromise && output.includes(completionPromise) ? true : false;
+
+    results.push({
+      iteration: iterations,
+      status: success ? 'Success' : 'Failed',
+      testsPassed: stats.passed,
+      testsFailed: stats.failed,
+      testsTotal: stats.total,
+    });
+
+    if (success) {
+      process.stderr.write(
+        `[Ralph Wiggum] Completion promise "${completionPromise}" met. Exiting.\n`,
+      );
+      printSummary(results);
+      return;
+    }
+
+    // Clear resumedSessionData so we don't try to resume partially through
+    currentResumedSessionData = undefined;
+  }
+  process.stderr.write(
+    `[Ralph Wiggum] Max iterations reached without meeting completion promise.\n`,
+  );
+  printSummary(results);
+}
+
 export async function runNonInteractive({
   config,
   settings,
   input,
   prompt_id,
   resumedSessionData,
-}: RunNonInteractiveParams): Promise<void> {
+}: RunNonInteractiveParams): Promise<string> {
   return promptIdContext.run(prompt_id, async () => {
     const consolePatcher = new ConsolePatcher({
       stderr: true,
@@ -181,6 +355,9 @@ export async function runNonInteractive({
       }
     };
 
+    // Store accumulated response text to return
+    let fullResponseText = '';
+
     let errorToHandle: unknown | undefined;
     try {
       consolePatcher.patch();
@@ -316,6 +493,13 @@ export async function runNonInteractive({
             const isRaw =
               config.getRawOutput() || config.getAcceptRawOutputRisk();
             const output = isRaw ? event.value : stripAnsi(event.value);
+
+            // Accumulate full response
+            if (event.value) {
+              fullResponseText += event.value;
+              responseText += output;
+            }
+
             if (streamFormatter) {
               streamFormatter.emitEvent({
                 type: JsonStreamEventType.MESSAGE,
@@ -325,7 +509,7 @@ export async function runNonInteractive({
                 delta: true,
               });
             } else if (config.getOutputFormat() === OutputFormat.JSON) {
-              responseText += output;
+              // responseText is already updated
             } else {
               if (event.value) {
                 textOutput.write(output);
@@ -381,7 +565,7 @@ export async function runNonInteractive({
                 ),
               });
             }
-            return;
+            return fullResponseText;
           } else if (event.type === GeminiEventType.AgentExecutionBlocked) {
             const blockMessage = `Agent execution blocked: ${event.value.systemMessage?.trim() || event.value.reason}`;
             if (config.getOutputFormat() === OutputFormat.TEXT) {
@@ -488,7 +672,7 @@ export async function runNonInteractive({
             } else {
               textOutput.ensureTrailingNewline(); // Ensure a final newline
             }
-            return;
+            return fullResponseText;
           }
 
           currentMessages = [{ role: 'user', parts: toolResponseParts }];
@@ -512,7 +696,7 @@ export async function runNonInteractive({
           } else {
             textOutput.ensureTrailingNewline(); // Ensure a final newline
           }
-          return;
+          return fullResponseText;
         }
       }
     } catch (error) {
@@ -528,5 +712,6 @@ export async function runNonInteractive({
     if (errorToHandle) {
       handleError(errorToHandle, config);
     }
+    return fullResponseText;
   });
 }