Merge branch 'main' into memory_usage3

integration-tests/acp-telemetry.test.ts

@@ -72,7 +72,6 @@ describe('ACP telemetry', () => {
           GEMINI_TELEMETRY_ENABLED: 'true',
           GEMINI_TELEMETRY_TARGET: 'local',
           GEMINI_TELEMETRY_OUTFILE: telemetryPath,
-          // GEMINI_DEV_TRACING not set: fake responses aren't instrumented for spans
         },
       },
     );

integration-tests/file-system.test.ts

@@ -55,8 +55,8 @@ describe('file-system', () => {
     });
   });
 
-  it('should be able to write a file', async () => {
-    await rig.setup('should be able to write a file', {
+  it('should be able to write a hello world message to a file', async () => {
+    await rig.setup('should be able to write a hello world message to a file', {
       settings: { tools: { core: ['write_file', 'replace', 'read_file'] } },
     });
     rig.createFile('test.txt', '');

integration-tests/hooks-agent-flow.test.ts

@@ -165,14 +165,15 @@ describe('Hooks Agent Flow', () => {
 
       // BeforeModel hook to track message counts across LLM calls
       const messageCountFile = join(rig.testDir!, 'message-counts.json');
+      const escapedPath = JSON.stringify(messageCountFile);
       const beforeModelScript = `
         const fs = require('fs');
         const input = JSON.parse(fs.readFileSync(0, 'utf-8'));
         const messageCount = input.llm_request?.contents?.length || 0;
         let counts = [];
-        try { counts = JSON.parse(fs.readFileSync(${JSON.stringify(messageCountFile)}, 'utf-8')); } catch (e) {}
+        try { counts = JSON.parse(fs.readFileSync(${escapedPath}, 'utf-8')); } catch (e) {}
         counts.push(messageCount);
-        fs.writeFileSync(${JSON.stringify(messageCountFile)}, JSON.stringify(counts));
+        fs.writeFileSync(${escapedPath}, JSON.stringify(counts));
         console.log(JSON.stringify({ decision: 'allow' }));
       `;
       const beforeModelScriptPath = rig.createScript(

integration-tests/json-output.test.ts

@@ -81,7 +81,9 @@ describe('JSON output', () => {
     const message = (thrown as Error).message;
 
     // Use a regex to find the first complete JSON object in the string
-    const jsonMatch = message.match(/{[\s\S]*}/);
+    // We expect the JSON to start with a quote (e.g. {"error": ...}) to avoid
+    // matching random error objects printed to stderr (like ENOENT).
+    const jsonMatch = message.match(/{\s*"[\s\S]*}/);
 
     // Fail if no JSON-like text was found
     expect(

integration-tests/plan-mode.test.ts

@@ -4,8 +4,10 @@
  * SPDX-License-Identifier: Apache-2.0
  */
 
+import { writeFileSync } from 'node:fs';
+import { join } from 'node:path';
 import { describe, it, expect, beforeEach, afterEach } from 'vitest';
-import { TestRig, checkModelOutputContent } from './test-helper.js';
+import { TestRig, checkModelOutputContent, GEMINI_DIR } from './test-helper.js';
 
 describe('Plan Mode', () => {
   let rig: TestRig;
@@ -62,50 +64,98 @@ describe('Plan Mode', () => {
     });
   });
 
-  it('should allow write_file only in the plans directory in plan mode', async () => {
-    await rig.setup(
-      'should allow write_file only in the plans directory in plan mode',
-      {
-        settings: {
-          experimental: { plan: true },
-          tools: {
-            core: ['write_file', 'read_file', 'list_directory'],
-            allowed: ['write_file'],
+  it('should allow write_file to the plans directory in plan mode', async () => {
+    const plansDir = '.gemini/tmp/foo/123/plans';
+    const testName =
+      'should allow write_file to the plans directory in plan mode';
+
+    await rig.setup(testName, {
+      settings: {
+        experimental: { plan: true },
+        tools: {
+          core: ['write_file', 'read_file', 'list_directory'],
+        },
+        general: {
+          defaultApprovalMode: 'plan',
+          plan: {
+            directory: plansDir,
           },
-          general: { defaultApprovalMode: 'plan' },
         },
       },
-    );
-
-    // We ask the agent to create a plan for a feature, which should trigger a write_file in the plans directory.
-    // Verify that write_file outside of plan directory fails
-    await rig.run({
-      approvalMode: 'plan',
-      stdin:
-        'Create a file called plan.md in the plans directory. Then create a file called hello.txt in the current directory',
     });
 
-    const toolLogs = rig.readToolLogs();
-    const writeLogs = toolLogs.filter(
-      (l) => l.toolRequest.name === 'write_file',
+    // Disable the interactive terminal setup prompt in tests
+    writeFileSync(
+      join(rig.homeDir!, GEMINI_DIR, 'state.json'),
+      JSON.stringify({ terminalSetupPromptShown: true }, null, 2),
     );
 
-    const planWrite = writeLogs.find(
+    const run = await rig.runInteractive({
+      approvalMode: 'plan',
+    });
+
+    await run.type('Create a file called plan.md in the plans directory.');
+    await run.type('\r');
+
+    await rig.expectToolCallSuccess(['write_file'], 30000, (args) =>
+      args.includes('plan.md'),
+    );
+
+    const toolLogs = rig.readToolLogs();
+    const planWrite = toolLogs.find(
       (l) =>
+        l.toolRequest.name === 'write_file' &&
         l.toolRequest.args.includes('plans') &&
         l.toolRequest.args.includes('plan.md'),
     );
+    expect(planWrite?.toolRequest.success).toBe(true);
+  });
 
-    const blockedWrite = writeLogs.find((l) =>
-      l.toolRequest.args.includes('hello.txt'),
+  it('should deny write_file to non-plans directory in plan mode', async () => {
+    const plansDir = '.gemini/tmp/foo/123/plans';
+    const testName =
+      'should deny write_file to non-plans directory in plan mode';
+
+    await rig.setup(testName, {
+      settings: {
+        experimental: { plan: true },
+        tools: {
+          core: ['write_file', 'read_file', 'list_directory'],
+        },
+        general: {
+          defaultApprovalMode: 'plan',
+          plan: {
+            directory: plansDir,
+          },
+        },
+      },
+    });
+
+    // Disable the interactive terminal setup prompt in tests
+    writeFileSync(
+      join(rig.homeDir!, GEMINI_DIR, 'state.json'),
+      JSON.stringify({ terminalSetupPromptShown: true }, null, 2),
     );
 
-    // Model is undeterministic, sometimes a blocked write appears in tool logs and sometimes it doesn't
-    if (blockedWrite) {
-      expect(blockedWrite?.toolRequest.success).toBe(false);
-    }
+    const run = await rig.runInteractive({
+      approvalMode: 'plan',
+    });
 
-    expect(planWrite?.toolRequest.success).toBe(true);
+    await run.type('Create a file called hello.txt in the current directory.');
+    await run.type('\r');
+
+    const toolLogs = rig.readToolLogs();
+    const writeLog = toolLogs.find(
+      (l) =>
+        l.toolRequest.name === 'write_file' &&
+        l.toolRequest.args.includes('hello.txt'),
+    );
+
+    // In Plan Mode, writes outside the plans directory should be blocked.
+    // Model is undeterministic, sometimes it doesn't even try, but if it does, it must fail.
+    if (writeLog) {
+      expect(writeLog.toolRequest.success).toBe(false);
+    }
   });
 
   it('should be able to enter plan mode from default mode', async () => {
@@ -119,6 +169,12 @@ describe('Plan Mode', () => {
       },
     });
 
+    // Disable the interactive terminal setup prompt in tests
+    writeFileSync(
+      join(rig.homeDir!, GEMINI_DIR, 'state.json'),
+      JSON.stringify({ terminalSetupPromptShown: true }, null, 2),
+    );
+
     // Start in default mode and ask to enter plan mode.
     await rig.run({
       approvalMode: 'default',
@@ -126,10 +182,7 @@ describe('Plan Mode', () => {
         'I want to perform a complex refactoring. Please enter plan mode so we can design it first.',
     });
 
-    const enterPlanCallFound = await rig.waitForToolCall(
-      'enter_plan_mode',
-      10000,
-    );
+    const enterPlanCallFound = await rig.waitForToolCall('enter_plan_mode');
     expect(enterPlanCallFound, 'Expected enter_plan_mode to be called').toBe(
       true,
     );

integration-tests/ripgrep-real.test.ts

@@ -102,7 +102,10 @@ describe('ripgrep-real-direct', () => {
       'console.log("hello");\n',
     );
 
-    const invocation = tool.build({ pattern: 'hello', include: '*.js' });
+    const invocation = tool.build({
+      pattern: 'hello',
+      include_pattern: '*.js',
+    });
     const result = await invocation.execute(new AbortController().signal);
 
     expect(result.llmContent).toContain('Found 1 match');

integration-tests/run_shell_command.test.ts

@@ -18,6 +18,7 @@ const { shell } = getShellConfiguration();
 function getLineCountCommand(): { command: string; tool: string } {
   switch (shell) {
     case 'powershell':
+      return { command: `Measure-Object -Line`, tool: 'Measure-Object' };
     case 'cmd':
       return { command: `find /c /v`, tool: 'find' };
     case 'bash':
@@ -238,8 +239,12 @@ describe('run_shell_command', () => {
   });
 
   it('should succeed in yolo mode', async () => {
+    const isWindows = process.platform === 'win32';
     await rig.setup('should succeed in yolo mode', {
-      settings: { tools: { core: ['run_shell_command'] } },
+      settings: {
+        tools: { core: ['run_shell_command'] },
+        shell: isWindows ? { enableInteractiveShell: false } : undefined,
+      },
     });
 
     const testFile = rig.createFile('test.txt', 'Lorem\nIpsum\nDolor\n');

integration-tests/write_file.test.ts

@@ -22,8 +22,8 @@ describe('write_file', () => {
 
   afterEach(async () => await rig.cleanup());
 
-  it('should be able to write a file', async () => {
-    await rig.setup('should be able to write a file', {
+  it('should be able to write a joke to a file', async () => {
+    await rig.setup('should be able to write a joke to a file', {
       settings: { tools: { core: ['write_file', 'read_file'] } },
     });
     const prompt = `show me an example of using the write tool. put a dad joke in dad.txt`;