chore(release): v0.54.3

Fix/revert version bump (#28715 )
chore: bump version to 0.54.2 (#28712 )
2026-08-10 08:56:29 -07:00 · 2026-08-07 02:49:54 +00:00 · 2026-08-06 18:33:11 -04:00 · 2026-08-06 14:29:01 -04:00 · 2026-08-06 16:13:54 +00:00 · 2026-08-06 14:54:28 +00:00
41 changed files with 3047 additions and 110 deletions
@@ -1,12 +1,12 @@
 {
  "name": "@google/gemini-cli",
-  "version": "0.54.0-nightly.20260728.gbef611950",
+  "version": "0.54.3",
  "lockfileVersion": 3,
  "requires": true,
  "packages": {
    "": {
      "name": "@google/gemini-cli",
-      "version": "0.54.0-nightly.20260728.gbef611950",
+      "version": "0.54.3",
      "workspaces": [
        "packages/*"
      ],
@@ -17782,7 +17782,7 @@
    },
    "packages/a2a-server": {
      "name": "@google/gemini-cli-a2a-server",
-      "version": "0.54.0-nightly.20260728.gbef611950",
+      "version": "0.54.3",
      "dependencies": {
        "@a2a-js/sdk": "0.3.11",
        "@google-cloud/storage": "7.19.0",
@@ -18242,7 +18242,7 @@
    },
    "packages/cli": {
      "name": "@google/gemini-cli",
-      "version": "0.54.0-nightly.20260728.gbef611950",
+      "version": "0.54.3",
      "license": "Apache-2.0",
      "dependencies": {
        "@agentclientprotocol/sdk": "0.16.1",
@@ -18458,7 +18458,7 @@
    },
    "packages/core": {
      "name": "@google/gemini-cli-core",
-      "version": "0.54.0-nightly.20260728.gbef611950",
+      "version": "0.54.3",
      "license": "Apache-2.0",
      "dependencies": {
        "@a2a-js/sdk": "0.3.11",
@@ -19131,7 +19131,7 @@
    },
    "packages/devtools": {
      "name": "@google/gemini-cli-devtools",
-      "version": "0.54.0-nightly.20260728.gbef611950",
+      "version": "0.54.3",
      "license": "Apache-2.0",
      "dependencies": {
        "ws": "8.16.0"
@@ -19167,7 +19167,7 @@
    },
    "packages/sdk": {
      "name": "@google/gemini-cli-sdk",
-      "version": "0.54.0-nightly.20260728.gbef611950",
+      "version": "0.54.3",
      "license": "Apache-2.0",
      "dependencies": {
        "@google/gemini-cli-core": "file:../core",
@@ -19506,7 +19506,7 @@
    },
    "packages/test-utils": {
      "name": "@google/gemini-cli-test-utils",
-      "version": "0.54.0-nightly.20260728.gbef611950",
+      "version": "0.54.3",
      "license": "Apache-2.0",
      "dependencies": {
        "@google/gemini-cli-core": "file:../core",
@@ -19524,7 +19524,7 @@
    },
    "packages/vscode-ide-companion": {
      "name": "gemini-cli-vscode-ide-companion",
-      "version": "0.54.0-nightly.20260728.gbef611950",
+      "version": "0.54.3",
      "license": "LICENSE",
      "dependencies": {
        "@modelcontextprotocol/sdk": "1.23.0",
@@ -1,6 +1,6 @@
 {
  "name": "@google/gemini-cli",
-  "version": "0.54.0-nightly.20260728.gbef611950",
+  "version": "0.54.3",
  "engines": {
    "node": ">=20.0.0"
  },
@@ -14,7 +14,7 @@
    "url": "git+https://github.com/google-gemini/gemini-cli.git"
  },
  "config": {
-    "sandboxImageUri": "us-docker.pkg.dev/gemini-code-dev/gemini-cli/sandbox:0.54.0-nightly.20260728.gbef611950"
+    "sandboxImageUri": "us-docker.pkg.dev/gemini-code-dev/gemini-cli/sandbox:0.54.3"
  },
  "scripts": {
    "start": "cross-env NODE_ENV=development node scripts/start.js",
@@ -1,6 +1,6 @@
 {
  "name": "@google/gemini-cli-a2a-server",
-  "version": "0.54.0-nightly.20260728.gbef611950",
+  "version": "0.54.3",
  "description": "Gemini CLI A2A Server",
  "repository": {
    "type": "git",
@@ -1,6 +1,6 @@
 {
  "name": "@google/gemini-cli",
-  "version": "0.54.0-nightly.20260728.gbef611950",
+  "version": "0.54.3",
  "description": "Gemini CLI",
  "license": "Apache-2.0",
  "repository": {
@@ -27,7 +27,7 @@
    "dist"
  ],
  "config": {
-    "sandboxImageUri": "us-docker.pkg.dev/gemini-code-dev/gemini-cli/sandbox:0.54.0-nightly.20260728.gbef611950"
+    "sandboxImageUri": "us-docker.pkg.dev/gemini-code-dev/gemini-cli/sandbox:0.54.3"
  },
  "dependencies": {
    "@agentclientprotocol/sdk": "0.16.1",
@@ -319,6 +319,41 @@ describe('Session', () => {
    expect(result).toMatchObject({ stopReason: 'end_turn' });
  });

+  it.each([
+    { type: 'MAX_TOKENS_EXCEEDED', reason: 'MAX_TOKENS' },
+    { type: 'SAFETY_BLOCKED', reason: 'SAFETY' },
+    { type: 'RECITATION_BLOCKED', reason: 'RECITATION' },
+    { type: 'OTHER_BLOCKED', reason: 'OTHER' },
+    { type: 'THINKING_ONLY_RESPONSE', reason: 'STOP' },
+  ])(
+    'should gracefully handle InvalidStreamError with type $type in ACP session',
+    async ({ type, reason }) => {
+      const error = new InvalidStreamError(
+        `Stream failed with ${reason}`,
+        type as InvalidStreamError['type'],
+      );
+      mockSendMessageStream.mockImplementation(() => {
+        async function* errorGen(): AsyncGenerator<
+          ServerGeminiStreamEvent,
+          void,
+          unknown
+        > {
+          // eslint-disable-next-line @typescript-eslint/no-explicit-any
+          yield* [] as any;
+          throw error;
+        }
+        return errorGen();
+      });
+
+      const result = await session.prompt({
+        sessionId: 'session-1',
+        prompt: [{ type: 'text', text: 'Hi' }],
+      });
+
+      expect(result).toMatchObject({ stopReason: 'end_turn' });
+    },
+  );
+
  it('should handle /memory command', async () => {
    const handleCommandSpy = vi
      .spyOn(
@@ -510,7 +510,12 @@ export class Session {
            (error.type === 'NO_RESPONSE_TEXT' ||
              error.type === 'NO_FINISH_REASON' ||
              error.type === 'MALFORMED_FUNCTION_CALL' ||
-              error.type === 'UNEXPECTED_TOOL_CALL'))
+              error.type === 'UNEXPECTED_TOOL_CALL' ||
+              error.type === 'MAX_TOKENS_EXCEEDED' ||
+              error.type === 'SAFETY_BLOCKED' ||
+              error.type === 'RECITATION_BLOCKED' ||
+              error.type === 'OTHER_BLOCKED' ||
+              error.type === 'THINKING_ONLY_RESPONSE'))
        ) {
          // The stream ended with an empty response or malformed tool call.
          // Treat this as a graceful end to the model's turn rather than a crash.
@@ -22,6 +22,7 @@ import {
  CoreEvent,
  CoreToolCallStatus,
  JsonStreamEventType,
+  TRUE_EMPTY_RESPONSE_MESSAGE,
 } from '@google/gemini-cli-core';
 import type { Part } from '@google/genai';
 import { runNonInteractive } from './nonInteractiveCli.js';
@@ -78,6 +79,7 @@ vi.mock('@google/gemini-cli-core', async (importOriginal) => {
    ChatRecordingService: MockChatRecordingService,
    uiTelemetryService: {
      getMetrics: vi.fn(),
+      recordSemanticValidationError: vi.fn(),
    },
    coreEvents: mockCoreEvents,
    createWorkingStdio: vi.fn(() => ({
@@ -110,6 +112,7 @@ describe('runNonInteractive', () => {
    sendMessageStream: Mock;
    resumeChat: Mock;
    getChatRecordingService: Mock;
+    getCurrentSequenceModel: Mock;
  };
  const MOCK_SESSION_METRICS: SessionMetrics = {
    models: {},
@@ -165,6 +168,7 @@ describe('runNonInteractive', () => {
        recordMessageTokens: vi.fn(),
        recordToolCalls: vi.fn(),
      })),
+      getCurrentSequenceModel: vi.fn().mockReturnValue('gemini-2.5-flash'),
    };

    mockConfig = {
@@ -193,6 +197,7 @@ describe('runNonInteractive', () => {
      getRawOutput: vi.fn().mockReturnValue(false),
      getAcceptRawOutputRisk: vi.fn().mockReturnValue(false),
      getAgentSessionNoninteractiveEnabled: vi.fn().mockReturnValue(false),
+      getUsageStatisticsEnabled: vi.fn().mockReturnValue(false),
    } as unknown as Config;

    mockSettings = {
@@ -1820,7 +1825,6 @@ describe('runNonInteractive', () => {
    };
    // @ts-expect-error - Mocking internal structure
    mockGeminiClient.getChat = vi.fn().mockReturnValue(mockChat);
-    // @ts-expect-error - Mocking internal structure
    mockGeminiClient.getCurrentSequenceModel = vi
      .fn()
      .mockReturnValue('model-1');
@@ -2298,7 +2302,13 @@ describe('runNonInteractive', () => {

    it('should handle InvalidStream event gracefully in TEXT mode', async () => {
      const events: ServerGeminiStreamEvent[] = [
-        { type: GeminiEventType.InvalidStream },
+        {
+          type: GeminiEventType.InvalidStream,
+          value: {
+            type: 'NO_RESPONSE_TEXT',
+            message: 'Empty response',
+          },
+        },
      ];
      mockGeminiClient.sendMessageStream.mockReturnValue(
        createStreamFromEvents(events),
@@ -2312,7 +2322,7 @@ describe('runNonInteractive', () => {
      });

      expect(processStderrSpy).toHaveBeenCalledWith(
-        '[ERROR] Invalid stream: The model returned an empty response or malformed tool call.\n',
+        `[ERROR] ${TRUE_EMPTY_RESPONSE_MESSAGE}\n`,
      );
      expect(mockGeminiClient.sendMessageStream).toHaveBeenCalledTimes(1);
    });
@@ -2325,7 +2335,13 @@ describe('runNonInteractive', () => {
        OutputFormat.STREAM_JSON,
      );
      const events: ServerGeminiStreamEvent[] = [
-        { type: GeminiEventType.InvalidStream },
+        {
+          type: GeminiEventType.InvalidStream,
+          value: {
+            type: 'NO_RESPONSE_TEXT',
+            message: 'Empty response',
+          },
+        },
      ];
      mockGeminiClient.sendMessageStream.mockReturnValue(
        createStreamFromEvents(events),
@@ -2341,9 +2357,7 @@ describe('runNonInteractive', () => {
      const output = getWrittenOutput();
      expect(output).toContain('"type":"error"');
      expect(output).toContain('"severity":"error"');
-      expect(output).toContain(
-        'Invalid stream: The model returned an empty response or malformed tool call.',
-      );
+      expect(output).toContain(TRUE_EMPTY_RESPONSE_MESSAGE);
      expect(mockGeminiClient.sendMessageStream).toHaveBeenCalledTimes(1);
    });

@@ -2355,7 +2369,13 @@ describe('runNonInteractive', () => {
        OutputFormat.JSON,
      );
      const events: ServerGeminiStreamEvent[] = [
-        { type: GeminiEventType.InvalidStream },
+        {
+          type: GeminiEventType.InvalidStream,
+          value: {
+            type: 'NO_RESPONSE_TEXT',
+            message: 'Empty response',
+          },
+        },
      ];
      mockGeminiClient.sendMessageStream.mockReturnValue(
        createStreamFromEvents(events),
@@ -2371,8 +2391,33 @@ describe('runNonInteractive', () => {
      const output = getWrittenOutput();
      expect(output).toContain('"error": {');
      expect(output).toContain('"type": "INVALID_STREAM"');
-      expect(output).toContain(
-        'Invalid stream: The model returned an empty response or malformed tool call.',
+      expect(output).toContain(TRUE_EMPTY_RESPONSE_MESSAGE);
+      expect(mockGeminiClient.sendMessageStream).toHaveBeenCalledTimes(1);
+    });
+
+    it('should handle non-NO_RESPONSE_TEXT InvalidStream event gracefully and use message from eventValue', async () => {
+      const events: ServerGeminiStreamEvent[] = [
+        {
+          type: GeminiEventType.InvalidStream,
+          value: {
+            type: 'MALFORMED_FUNCTION_CALL',
+            message: 'Custom malformed function call message',
+          },
+        },
+      ];
+      mockGeminiClient.sendMessageStream.mockReturnValue(
+        createStreamFromEvents(events),
+      );
+
+      await runNonInteractive({
+        config: mockConfig,
+        settings: mockSettings,
+        input: 'test invalid stream malformed',
+        prompt_id: 'prompt-id-invalid-malformed',
+      });
+
+      expect(processStderrSpy).toHaveBeenCalledWith(
+        '[ERROR] Custom malformed function call message\n',
      );
      expect(mockGeminiClient.sendMessageStream).toHaveBeenCalledTimes(1);
    });
@@ -30,6 +30,12 @@ import {
  ToolErrorType,
  Scheduler,
  ROOT_SCHEDULER_ID,
+  THINKING_ONLY_COMPRESS_SUGGESTION,
+  MAX_TOKENS_EXCEEDED_SUGGESTION,
+  SAFETY_BLOCKED_MESSAGE,
+  RECITATION_BLOCKED_MESSAGE,
+  OTHER_BLOCKED_MESSAGE,
+  TRUE_EMPTY_RESPONSE_MESSAGE,
 } from '@google/gemini-cli-core';

 import type { Content, Part } from '@google/genai';
@@ -433,8 +439,31 @@ export async function runNonInteractive(
            }
            warnings.push(blockMessage);
          } else if (event.type === GeminiEventType.InvalidStream) {
-            invalidStreamError =
-              'Invalid stream: The model returned an empty response or malformed tool call.';
+            const eventValue = event.value;
+            if (eventValue?.type === 'NO_RESPONSE_TEXT') {
+              invalidStreamError = TRUE_EMPTY_RESPONSE_MESSAGE;
+            } else if (eventValue?.type === 'THINKING_ONLY_RESPONSE') {
+              invalidStreamError = THINKING_ONLY_COMPRESS_SUGGESTION;
+            } else if (eventValue?.type === 'MAX_TOKENS_EXCEEDED') {
+              invalidStreamError = MAX_TOKENS_EXCEEDED_SUGGESTION;
+            } else if (eventValue?.type === 'SAFETY_BLOCKED') {
+              invalidStreamError = SAFETY_BLOCKED_MESSAGE;
+            } else if (eventValue?.type === 'RECITATION_BLOCKED') {
+              invalidStreamError = RECITATION_BLOCKED_MESSAGE;
+            } else if (eventValue?.type === 'OTHER_BLOCKED') {
+              invalidStreamError = OTHER_BLOCKED_MESSAGE;
+            } else {
+              invalidStreamError =
+                eventValue?.message?.trim() ||
+                'Invalid stream: The model returned an empty response or malformed tool call.';
+            }
+
+            // Log semantic error telemetry without double-counting requests
+            uiTelemetryService.recordSemanticValidationError(
+              geminiClient.getCurrentSequenceModel() ?? config.getModel(),
+              eventValue?.type || 'INVALID_STREAM',
+            );
+
            if (streamFormatter) {
              streamFormatter.emitEvent({
                type: JsonStreamEventType.ERROR,
@@ -22,6 +22,7 @@ import {
  CoreEvent,
  CoreToolCallStatus,
  JsonStreamEventType,
+  TRUE_EMPTY_RESPONSE_MESSAGE,
 } from '@google/gemini-cli-core';
 import type { Part } from '@google/genai';
 import { runNonInteractive } from './nonInteractiveCliAgentSession.js';
@@ -78,6 +79,7 @@ vi.mock('@google/gemini-cli-core', async (importOriginal) => {
    ChatRecordingService: MockChatRecordingService,
    uiTelemetryService: {
      getMetrics: vi.fn(),
+      recordSemanticValidationError: vi.fn(),
    },
    LegacyAgentSession: original.LegacyAgentSession,
    geminiPartsToContentParts: original.geminiPartsToContentParts,
@@ -199,6 +201,7 @@ describe('runNonInteractive', () => {
      getRawOutput: vi.fn().mockReturnValue(false),
      getAcceptRawOutputRisk: vi.fn().mockReturnValue(false),
      getAgentSessionNoninteractiveEnabled: vi.fn().mockReturnValue(false),
+      getUsageStatisticsEnabled: vi.fn().mockReturnValue(false),
    } as unknown as Config;

    mockSettings = {
@@ -2457,6 +2460,126 @@ describe('runNonInteractive', () => {
      const output = JSON.parse(getWrittenOutput());
      expect(output.warnings).toBeUndefined();
    });
+
+    it('should handle InvalidStream event gracefully in TEXT mode', async () => {
+      const events: ServerGeminiStreamEvent[] = [
+        {
+          type: GeminiEventType.InvalidStream,
+          value: {
+            type: 'NO_RESPONSE_TEXT',
+            message: 'Empty response',
+          },
+        },
+      ];
+      mockGeminiClient.sendMessageStream.mockReturnValue(
+        createStreamFromEvents(events),
+      );
+
+      await runNonInteractive({
+        config: mockConfig,
+        settings: mockSettings,
+        input: 'test invalid stream',
+        prompt_id: 'prompt-id-invalid',
+      });
+
+      expect(processStderrSpy).toHaveBeenCalledWith(
+        `[ERROR] ${TRUE_EMPTY_RESPONSE_MESSAGE}\n`,
+      );
+      expect(mockGeminiClient.sendMessageStream).toHaveBeenCalledTimes(1);
+    });
+
+    it('should handle InvalidStream event gracefully in STREAM_JSON mode', async () => {
+      vi.spyOn(uiTelemetryService, 'getMetrics').mockReturnValue(
+        MOCK_SESSION_METRICS,
+      );
+      vi.spyOn(mockConfig, 'getOutputFormat').mockReturnValue(
+        OutputFormat.STREAM_JSON,
+      );
+      const events: ServerGeminiStreamEvent[] = [
+        {
+          type: GeminiEventType.InvalidStream,
+          value: {
+            type: 'NO_RESPONSE_TEXT',
+            message: 'Empty response',
+          },
+        },
+      ];
+      mockGeminiClient.sendMessageStream.mockReturnValue(
+        createStreamFromEvents(events),
+      );
+
+      await runNonInteractive({
+        config: mockConfig,
+        settings: mockSettings,
+        input: 'test invalid stream',
+        prompt_id: 'prompt-id-invalid',
+      });
+
+      const output = getWrittenOutput();
+      expect(output).toContain('"type":"error"');
+      expect(output).toContain('"severity":"error"');
+      expect(output).toContain(TRUE_EMPTY_RESPONSE_MESSAGE);
+      expect(mockGeminiClient.sendMessageStream).toHaveBeenCalledTimes(1);
+    });
+
+    it('should handle InvalidStream event gracefully in JSON mode', async () => {
+      vi.spyOn(uiTelemetryService, 'getMetrics').mockReturnValue(
+        MOCK_SESSION_METRICS,
+      );
+      vi.spyOn(mockConfig, 'getOutputFormat').mockReturnValue(
+        OutputFormat.JSON,
+      );
+      const events: ServerGeminiStreamEvent[] = [
+        {
+          type: GeminiEventType.InvalidStream,
+          value: {
+            type: 'NO_RESPONSE_TEXT',
+            message: 'Empty response',
+          },
+        },
+      ];
+      mockGeminiClient.sendMessageStream.mockReturnValue(
+        createStreamFromEvents(events),
+      );
+
+      await runNonInteractive({
+        config: mockConfig,
+        settings: mockSettings,
+        input: 'test invalid stream',
+        prompt_id: 'prompt-id-invalid',
+      });
+
+      const output = getWrittenOutput();
+      expect(output).toContain('"error": {');
+      expect(output).toContain('"type": "INVALID_STREAM"');
+      expect(output).toContain(TRUE_EMPTY_RESPONSE_MESSAGE);
+      expect(mockGeminiClient.sendMessageStream).toHaveBeenCalledTimes(1);
+    });
+
+    it('should handle non-NO_RESPONSE_TEXT InvalidStream event gracefully and use message from eventValue', async () => {
+      const events: ServerGeminiStreamEvent[] = [
+        {
+          type: GeminiEventType.InvalidStream,
+          value: {
+            type: 'MALFORMED_FUNCTION_CALL',
+            message: 'Malformed call',
+          },
+        },
+      ];
+      mockGeminiClient.sendMessageStream.mockReturnValue(
+        createStreamFromEvents(events),
+      );
+
+      await runNonInteractive({
+        config: mockConfig,
+        settings: mockSettings,
+        input: 'test invalid stream',
+        prompt_id: 'prompt-id-invalid',
+      });
+
+      expect(processStderrSpy).toHaveBeenCalledWith('[ERROR] Malformed call\n');
+      expect(mockGeminiClient.sendMessageStream).toHaveBeenCalledTimes(1);
+    });
  });

  describe('Output Sanitization', () => {
@@ -39,6 +39,12 @@ import {
  geminiPartsToContentParts,
  displayContentToString,
  debugLogger,
+  THINKING_ONLY_COMPRESS_SUGGESTION,
+  MAX_TOKENS_EXCEEDED_SUGGESTION,
+  SAFETY_BLOCKED_MESSAGE,
+  RECITATION_BLOCKED_MESSAGE,
+  OTHER_BLOCKED_MESSAGE,
+  TRUE_EMPTY_RESPONSE_MESSAGE,
 } from '@google/gemini-cli-core';

 import type { Part } from '@google/genai';
@@ -332,14 +338,17 @@ export async function runNonInteractive({
        return text ? text : undefined;
      };

-      const emitFinalSuccessResult = (): void => {
+      const emitFinalResult = (errorPayload?: {
+        type: string;
+        message: string;
+      }): void => {
        if (streamFormatter) {
          const metrics = uiTelemetryService.getMetrics();
          const durationMs = Date.now() - startTime;
          streamFormatter.emitEvent({
            type: JsonStreamEventType.RESULT,
            timestamp: new Date().toISOString(),
-            status: 'success',
+            status: errorPayload ? 'error' : 'success',
            stats: streamFormatter.convertToStreamStats(metrics, durationMs),
          });
        } else if (config.getOutputFormat() === OutputFormat.JSON) {
@@ -350,7 +359,7 @@ export async function runNonInteractive({
              config.getSessionId(),
              responseText,
              stats,
-              undefined,
+              errorPayload,
              warnings,
            ),
          );
@@ -545,6 +554,52 @@ export async function runNonInteractive({
            break;
          }
          case 'error': {
+            if (event._meta?.['code'] === 'INVALID_STREAM') {
+              const errorTypeVal = event._meta?.['errorType'];
+              const errorType =
+                typeof errorTypeVal === 'string' ? errorTypeVal : undefined;
+
+              let errorMessage = event.message;
+              if (errorType === 'NO_RESPONSE_TEXT') {
+                errorMessage = TRUE_EMPTY_RESPONSE_MESSAGE;
+              } else if (errorType === 'THINKING_ONLY_RESPONSE') {
+                errorMessage = THINKING_ONLY_COMPRESS_SUGGESTION;
+              } else if (errorType === 'MAX_TOKENS_EXCEEDED') {
+                errorMessage = MAX_TOKENS_EXCEEDED_SUGGESTION;
+              } else if (errorType === 'SAFETY_BLOCKED') {
+                errorMessage = SAFETY_BLOCKED_MESSAGE;
+              } else if (errorType === 'RECITATION_BLOCKED') {
+                errorMessage = RECITATION_BLOCKED_MESSAGE;
+              } else if (errorType === 'OTHER_BLOCKED') {
+                errorMessage = OTHER_BLOCKED_MESSAGE;
+              }
+
+              if (streamFormatter) {
+                streamFormatter.emitEvent({
+                  type: JsonStreamEventType.ERROR,
+                  timestamp: new Date().toISOString(),
+                  severity: 'error',
+                  message: errorMessage,
+                });
+              } else if (config.getOutputFormat() === OutputFormat.TEXT) {
+                process.stderr.write(`[ERROR] ${errorMessage}\n`);
+              }
+
+              // Log semantic error telemetry without double-counting requests
+              uiTelemetryService.recordSemanticValidationError(
+                geminiClient.getCurrentSequenceModel() ?? config.getModel(),
+                errorType || 'INVALID_STREAM',
+              );
+
+              // If it's a fatal stream error, we should terminate and output final results
+              emitFinalResult({
+                type: 'INVALID_STREAM',
+                message: errorMessage,
+              });
+              streamEnded = true;
+              break;
+            }
+
            if (event.fatal) {
              throw reconstructFatalError(event);
            }
@@ -613,7 +668,7 @@ export async function runNonInteractive({
              process.stderr.write(`Agent execution stopped: ${stopMessage}\n`);
            }

-            emitFinalSuccessResult();
+            emitFinalResult();
            streamEnded = true;
            break;
          }
@@ -36,6 +36,18 @@ function areModelMetricsEqual(a: ModelMetrics, b: ModelMetrics): boolean {
  ) {
    return false;
  }
+  const errorsA = a.api.errorsByType || {};
+  const errorsB = b.api.errorsByType || {};
+  const keysA = Object.keys(errorsA);
+  const keysB = Object.keys(errorsB);
+  if (keysA.length !== keysB.length) {
+    return false;
+  }
+  for (const key of keysA) {
+    if (errorsA[key] !== errorsB[key]) {
+      return false;
+    }
+  }
  if (
    a.tokens.input !== b.tokens.input ||
    a.tokens.prompt !== b.tokens.prompt ||
@@ -54,6 +54,7 @@ import {
  GeminiCliOperation,
  getPlanModeExitMessage,
  UPDATE_TOPIC_TOOL_NAME,
+  TRUE_EMPTY_RESPONSE_MESSAGE,
 } from '@google/gemini-cli-core';
 import type { Part, PartListUnion } from '@google/genai';
 import type { UseHistoryManagerReturn } from './useHistoryManager.js';
@@ -1045,6 +1046,107 @@ describe('useGeminiStream', () => {
    });
  });

+  it('should record tool responses in history when the model was switched due to a quota error', async () => {
+    // Regression test: returning early on a quota-triggered model switch
+    // without recording the responses leaves the already-recorded
+    // functionCall unpaired, which corrupts all subsequent requests.
+    const responseParts: Part[] = [
+      {
+        functionResponse: {
+          name: 'testTool',
+          id: 'call1',
+          response: { output: 'tool result' },
+        },
+      },
+    ];
+    const completedToolCalls: TrackedToolCall[] = [
+      {
+        request: {
+          callId: 'call1',
+          name: 'testTool',
+          args: {},
+          isClientInitiated: false,
+          prompt_id: 'prompt-id-quota',
+        },
+        status: CoreToolCallStatus.Success,
+        responseSubmittedToGemini: false,
+        response: {
+          callId: 'call1',
+          responseParts,
+          errorType: undefined,
+        },
+        tool: { displayName: 'MockTool' },
+        invocation: {
+          getDescription: () => `Mock description`,
+        } as unknown as AnyToolInvocation,
+      } as TrackedCompletedToolCall,
+    ];
+
+    const client = new MockedGeminiClientClass(mockConfig);
+    const mockConsumeUserHint = vi.fn(() => 'switch to the nprd database');
+
+    let capturedOnComplete:
+      | ((completedTools: TrackedToolCall[]) => Promise<void>)
+      | null = null;
+
+    mockUseToolScheduler.mockImplementation((onComplete) => {
+      capturedOnComplete = onComplete;
+      return [
+        [],
+        mockScheduleToolCalls,
+        mockMarkToolsAsSubmitted,
+        vi.fn(),
+        mockCancelAllToolCalls,
+        0,
+      ];
+    });
+
+    await renderHookWithProviders(() =>
+      useGeminiStream(
+        client,
+        [],
+        mockAddItem,
+        mockConfig,
+        mockLoadedSettings,
+        mockOnDebugMessage,
+        mockHandleSlashCommand,
+        false,
+        () => 'vscode' as EditorType,
+        () => {},
+        () => Promise.resolve(),
+        true, // modelSwitchedFromQuotaError
+        () => {},
+        () => {},
+        () => {},
+        80,
+        24,
+        false,
+        mockConsumeUserHint,
+      ),
+    );
+
+    await act(async () => {
+      if (capturedOnComplete) {
+        await new Promise((resolve) => setTimeout(resolve, 0));
+        await capturedOnComplete(completedToolCalls);
+      }
+    });
+
+    await waitFor(() => {
+      expect(mockMarkToolsAsSubmitted).toHaveBeenCalledWith(['call1']);
+      // The tool response must be paired with its functionCall in history,
+      // with no steering-hint text ahead of it...
+      expect(client.addHistory).toHaveBeenCalledWith({
+        role: 'user',
+        parts: responseParts,
+      });
+      // ...the turn must NOT auto-continue on the fallback model...
+      expect(mockSendMessageStream).not.toHaveBeenCalled();
+      // ...and the pending hint is left for the next real submit.
+      expect(mockConsumeUserHint).not.toHaveBeenCalled();
+    });
+  });
+
  it('should NOT stop responding when only update_topic is called', async () => {
    const topicToolCalls: TrackedToolCall[] = [
      {
@@ -1772,6 +1874,120 @@ describe('useGeminiStream', () => {
      expect(mockCancelAllToolCalls).toHaveBeenCalled();
    });

+    it('should transition to Idle state when cancelled while a tool call is in progress and completes', async () => {
+      const toolCalls: TrackedToolCall[] = [
+        {
+          request: { callId: 'call1', name: 'tool1', args: {} },
+          status: CoreToolCallStatus.Executing,
+          responseSubmittedToGemini: false,
+          tool: {
+            name: 'tool1',
+            description: 'desc1',
+            build: vi.fn().mockImplementation((_) => ({
+              getDescription: () => `Mock description`,
+            })),
+          } as any,
+          invocation: {
+            getDescription: () => `Mock description`,
+          },
+          startTime: Date.now(),
+          liveOutput: '...',
+        } as TrackedExecutingToolCall,
+      ];
+
+      const { result } = await renderTestHook(toolCalls);
+
+      // State is `Responding` because a tool is running
+      expect(result.current.streamingState).toBe(StreamingState.Responding);
+
+      // Try to cancel
+      simulateEscapeKeyPress();
+
+      // Trigger the onComplete callback with the cancelled tool call
+      await act(async () => {
+        if (capturedOnComplete) {
+          await capturedOnComplete([
+            {
+              ...toolCalls[0],
+              status: CoreToolCallStatus.Cancelled,
+              response: {
+                callId: 'call1',
+                responseParts: [],
+              },
+            } as any,
+          ]);
+        }
+      });
+
+      // The final state should be idle because the cancelled tool call was marked as submitted
+      expect(result.current.streamingState).toBe(StreamingState.Idle);
+    });
+
+    it('should append cancelled tool responses to history when cancelled while a tool call is in progress and completes with response parts', async () => {
+      const toolCalls: TrackedToolCall[] = [
+        {
+          request: { callId: 'call1', name: 'tool1', args: {} },
+          status: CoreToolCallStatus.Executing,
+          responseSubmittedToGemini: false,
+          tool: {
+            name: 'tool1',
+            description: 'desc1',
+            build: vi.fn().mockImplementation((_) => ({
+              getDescription: () => `Mock description`,
+            })),
+          } as any,
+          invocation: {
+            getDescription: () => `Mock description`,
+          },
+          startTime: Date.now(),
+          liveOutput: '...',
+        } as TrackedExecutingToolCall,
+      ];
+
+      const { result, client } = await renderTestHook(toolCalls);
+
+      // State is `Responding` because a tool is running
+      expect(result.current.streamingState).toBe(StreamingState.Responding);
+
+      // Try to cancel
+      simulateEscapeKeyPress();
+
+      const expectedResponseParts = [
+        {
+          functionResponse: {
+            name: 'tool1',
+            id: 'call1',
+            response: { error: 'cancelled' },
+          },
+        },
+      ];
+
+      // Trigger the onComplete callback with the cancelled tool call having non-empty response parts
+      await act(async () => {
+        if (capturedOnComplete) {
+          await capturedOnComplete([
+            {
+              ...toolCalls[0],
+              status: CoreToolCallStatus.Cancelled,
+              response: {
+                callId: 'call1',
+                responseParts: expectedResponseParts,
+              },
+            } as any,
+          ]);
+        }
+      });
+
+      // Assert that addHistory was called with the combined response parts
+      expect(client.addHistory).toHaveBeenCalledWith({
+        role: 'user',
+        parts: expectedResponseParts,
+      });
+
+      // The final state should be idle because the cancelled tool call was marked as submitted
+      expect(result.current.streamingState).toBe(StreamingState.Idle);
+    });
+
    it('should cancel a request when a tool is awaiting confirmation', async () => {
      const mockOnConfirm = vi.fn().mockResolvedValue(undefined);
      const toolCalls: TrackedToolCall[] = [
@@ -2306,6 +2522,68 @@ describe('useGeminiStream', () => {
        );
      });
    });
+
+    it('should use TRUE_EMPTY_RESPONSE_MESSAGE when receiving an invalid stream event of type NO_RESPONSE_TEXT', async () => {
+      mockSendMessageStream.mockClear();
+      mockSendMessageStream.mockReturnValue(
+        (async function* () {
+          yield {
+            type: ServerGeminiEventType.InvalidStream,
+            value: {
+              type: 'NO_RESPONSE_TEXT',
+              message: 'empty response text',
+            },
+          };
+        })(),
+      );
+
+      const { result } = await renderTestHook();
+
+      await act(async () => {
+        await result.current.submitQuery('test query');
+      });
+
+      await waitFor(() => {
+        expect(mockAddItem).toHaveBeenCalledWith(
+          expect.objectContaining({
+            type: MessageType.ERROR,
+            text: TRUE_EMPTY_RESPONSE_MESSAGE,
+          }),
+          expect.any(Number),
+        );
+      });
+    });
+
+    it('should use the event message when receiving a non-NO_RESPONSE_TEXT invalid stream event', async () => {
+      mockSendMessageStream.mockClear();
+      mockSendMessageStream.mockReturnValue(
+        (async function* () {
+          yield {
+            type: ServerGeminiEventType.InvalidStream,
+            value: {
+              type: 'MALFORMED_FUNCTION_CALL',
+              message: 'Custom malformed function call message',
+            },
+          };
+        })(),
+      );
+
+      const { result } = await renderTestHook();
+
+      await act(async () => {
+        await result.current.submitQuery('test query');
+      });
+
+      await waitFor(() => {
+        expect(mockAddItem).toHaveBeenCalledWith(
+          expect.objectContaining({
+            type: MessageType.ERROR,
+            text: 'Custom malformed function call message',
+          }),
+          expect.any(Number),
+        );
+      });
+    });
  });

  describe('handleApprovalModeChange', () => {
@@ -14,6 +14,7 @@ import {
  GitService,
  UnauthorizedError,
  UserPromptEvent,
+  uiTelemetryService,
  DEFAULT_GEMINI_FLASH_MODEL,
  logConversationFinishedEvent,
  ConversationFinishedEvent,
@@ -45,6 +46,12 @@ import {
  buildToolVisibilityContext,
  UPDATE_TOPIC_TOOL_NAME,
  UPDATE_TOPIC_DISPLAY_NAME,
+  THINKING_ONLY_COMPRESS_SUGGESTION,
+  MAX_TOKENS_EXCEEDED_SUGGESTION,
+  SAFETY_BLOCKED_MESSAGE,
+  RECITATION_BLOCKED_MESSAGE,
+  OTHER_BLOCKED_MESSAGE,
+  TRUE_EMPTY_RESPONSE_MESSAGE,
 } from '@google/gemini-cli-core';
 import type {
  Config,
@@ -54,6 +61,7 @@ import type {
  ServerGeminiContentEvent as ContentEvent,
  ServerGeminiFinishedEvent,
  ServerGeminiStreamEvent as GeminiEvent,
+  ServerGeminiInvalidStreamEvent,
  ThoughtSummary,
  ToolCallRequestInfo,
  ToolCallResponseInfo,
@@ -1229,6 +1237,61 @@ export const useGeminiStream = (
    ],
  );

+  const handleInvalidStreamEvent = useCallback(
+    (
+      eventValue: ServerGeminiInvalidStreamEvent['value'],
+      userMessageTimestamp: number,
+    ) => {
+      if (pendingHistoryItemRef.current) {
+        addItem(pendingHistoryItemRef.current, userMessageTimestamp);
+        setPendingHistoryItem(null);
+      }
+      maybeAddSuppressedToolErrorNote(userMessageTimestamp);
+
+      let text =
+        eventValue?.message?.trim() || 'Invalid stream received from model';
+      if (eventValue?.type === 'NO_RESPONSE_TEXT') {
+        text = TRUE_EMPTY_RESPONSE_MESSAGE;
+      } else if (eventValue?.type === 'THINKING_ONLY_RESPONSE') {
+        text = THINKING_ONLY_COMPRESS_SUGGESTION;
+      } else if (eventValue?.type === 'MAX_TOKENS_EXCEEDED') {
+        text = MAX_TOKENS_EXCEEDED_SUGGESTION;
+      } else if (eventValue?.type === 'SAFETY_BLOCKED') {
+        text = SAFETY_BLOCKED_MESSAGE;
+      } else if (eventValue?.type === 'RECITATION_BLOCKED') {
+        text = RECITATION_BLOCKED_MESSAGE;
+      } else if (eventValue?.type === 'OTHER_BLOCKED') {
+        text = OTHER_BLOCKED_MESSAGE;
+      }
+
+      // Log semantic error telemetry without double-counting requests
+      uiTelemetryService.recordSemanticValidationError(
+        geminiClient.getCurrentSequenceModel() ?? config.getModel(),
+        eventValue?.type || 'INVALID_STREAM',
+      );
+
+      addItem(
+        {
+          type: MessageType.ERROR,
+          text,
+        },
+        userMessageTimestamp,
+      );
+      maybeAddLowVerbosityFailureNote(userMessageTimestamp);
+      setThought(null); // Reset thought when there's an error
+    },
+    [
+      addItem,
+      pendingHistoryItemRef,
+      setPendingHistoryItem,
+      setThought,
+      maybeAddSuppressedToolErrorNote,
+      maybeAddLowVerbosityFailureNote,
+      config,
+      geminiClient,
+    ],
+  );
+
  const handleCitationEvent = useCallback(
    (text: string, userMessageTimestamp: number) => {
      if (!showCitations(settings)) {
@@ -1541,8 +1604,10 @@ export const useGeminiStream = (
            loopDetectedRef.current = true;
            break;
          case ServerGeminiEventType.Retry:
+            // Handled transparently by the backend stream retries.
+            break;
          case ServerGeminiEventType.InvalidStream:
-            // Will add the missing logic later
+            handleInvalidStreamEvent(event.value, userMessageTimestamp);
            break;
          default: {
            // enforces exhaustive switch-case
@@ -1575,6 +1640,7 @@ export const useGeminiStream = (
      handleChatModelEvent,
      handleAgentExecutionStoppedEvent,
      handleAgentExecutionBlockedEvent,
+      handleInvalidStreamEvent,
      addItem,
      pendingHistoryItemRef,
      setPendingHistoryItem,
@@ -1886,6 +1952,30 @@ export const useGeminiStream = (
          },
        );

+      if (turnCancelledRef.current) {
+        setIsResponding(false);
+        const geminiTools = completedAndReadyToSubmitTools.filter(
+          (t) => !t.request.isClientInitiated,
+        );
+        if (geminiClient && geminiTools.length > 0) {
+          const combinedParts = geminiTools.flatMap(
+            (toolCall) => toolCall.response.responseParts,
+          );
+          if (combinedParts.length > 0) {
+            // eslint-disable-next-line @typescript-eslint/no-floating-promises
+            geminiClient.addHistory({
+              role: 'user',
+              parts: combinedParts,
+            });
+          }
+        }
+        const callIdsToMarkAsSubmitted = toolCalls.map(
+          (toolCall) => toolCall.request.callId,
+        );
+        markToolsAsSubmitted(callIdsToMarkAsSubmitted);
+        return;
+      }
+
      // Finalize any client-initiated tools as soon as they are done.
      const clientTools = completedAndReadyToSubmitTools.filter(
        (t) => t.request.isClientInitiated,
@@ -2020,6 +2110,27 @@ export const useGeminiStream = (
        (toolCall) => toolCall.response.responseParts,
      );

+      const callIdsToMarkAsSubmitted = geminiTools.map(
+        (toolCall) => toolCall.request.callId,
+      );
+
+      markToolsAsSubmitted(callIdsToMarkAsSubmitted);
+
+      // Don't continue if model was switched due to quota error, but still
+      // record the responses: the matching functionCall is already in history,
+      // and leaving it unpaired corrupts every subsequent request. Any pending
+      // steering hint is deliberately left unconsumed so it rides along with
+      // the next query the user actually submits.
+      if (modelSwitchedFromQuotaError) {
+        if (geminiClient && responsesToSend.length > 0) {
+          await geminiClient.addHistory({
+            role: 'user',
+            parts: responsesToSend,
+          });
+        }
+        return;
+      }
+
      if (consumeUserHint) {
        const userHint = consumeUserHint();
        if (userHint && userHint.trim().length > 0) {
@@ -2030,21 +2141,10 @@ export const useGeminiStream = (
        }
      }

-      const callIdsToMarkAsSubmitted = geminiTools.map(
-        (toolCall) => toolCall.request.callId,
-      );
-
      const prompt_ids = geminiTools.map(
        (toolCall) => toolCall.request.prompt_id,
      );

-      markToolsAsSubmitted(callIdsToMarkAsSubmitted);
-
-      // Don't continue if model was switched due to quota error
-      if (modelSwitchedFromQuotaError) {
-        return;
-      }
-
      // eslint-disable-next-line @typescript-eslint/no-floating-promises
      submitQuery(
        responsesToSend,
@@ -2066,6 +2166,7 @@ export const useGeminiStream = (
      maybeAddSuppressedToolErrorNote,
      maybeAddLowVerbosityFailureNote,
      setIsResponding,
+      toolCalls,
    ],
  );

@@ -1,6 +1,6 @@
 {
  "name": "@google/gemini-cli-core",
-  "version": "0.54.0-nightly.20260728.gbef611950",
+  "version": "0.54.3",
  "description": "Gemini CLI Core",
  "license": "Apache-2.0",
  "repository": {
@@ -516,10 +516,34 @@ describe('translateEvent', () => {
  });

  describe('InvalidStream events', () => {
-    it('emits fatal error', () => {
+    it('emits fatal error with specific message from event', () => {
      state.streamStartEmitted = true;
      const event: ServerGeminiStreamEvent = {
        type: GeminiEventType.InvalidStream,
+        value: {
+          type: 'NO_RESPONSE_TEXT',
+          message: 'Empty response',
+        },
+      };
+      const result = translateEvent(event, state);
+      expect(result).toHaveLength(1);
+      const err = result[0] as AgentEvent<'error'>;
+      expect(err.status).toBe('INTERNAL');
+      expect(err.message).toBe('Empty response');
+      expect(err.fatal).toBe(true);
+      expect(err._meta?.['code']).toBe('INVALID_STREAM');
+      expect(err._meta?.['errorType']).toBe('NO_RESPONSE_TEXT');
+      expect(err._meta?.['rawMessage']).toBe('Empty response');
+    });
+
+    it('falls back to default message when message is missing', () => {
+      state.streamStartEmitted = true;
+      const event: ServerGeminiStreamEvent = {
+        type: GeminiEventType.InvalidStream,
+        value: {
+          type: 'NO_RESPONSE_TEXT',
+          message: '',
+        },
      };
      const result = translateEvent(event, state);
      expect(result).toHaveLength(1);
@@ -222,8 +222,15 @@ export function translateEvent(
      out.push(
        makeEvent('error', state, {
          status: 'INTERNAL',
-          message: 'Invalid stream received from model',
+          message:
+            event.value?.message?.trim() ||
+            'Invalid stream received from model',
          fatal: true,
+          _meta: {
+            code: 'INVALID_STREAM',
+            errorType: event.value?.type,
+            rawMessage: event.value?.message,
+          },
        }),
      );
      break;
@@ -10,7 +10,7 @@
 */

 import { GeminiEventType } from '../core/turn.js';
-import type { Part } from '@google/genai';
+import type { Part, FinishReason } from '@google/genai';
 import type { GeminiClient } from '../core/client.js';
 import type { Config } from '../config/config.js';
 import type { ToolCallRequestInfo } from '../scheduler/types.js';
@@ -192,6 +192,7 @@ export class LegacyAgentProtocol implements AgentProtocol {
      }

      const toolCallRequests: ToolCallRequestInfo[] = [];
+      let finishedReason: FinishReason | undefined = undefined;
      const responseStream = this._client.sendMessageStream(
        currentParts,
        this._abortController.signal,
@@ -220,10 +221,7 @@ export class LegacyAgentProtocol implements AgentProtocol {
            this._finishStream('failed');
            return;
          case GeminiEventType.Finished:
-            if (toolCallRequests.length === 0) {
-              this._finishStream(mapFinishReason(event.value.reason));
-              return;
-            }
+            finishedReason = event.value.reason;
            break;
          case GeminiEventType.AgentExecutionStopped:
          case GeminiEventType.UserCancelled:
@@ -241,7 +239,11 @@ export class LegacyAgentProtocol implements AgentProtocol {
      }

      if (toolCallRequests.length === 0) {
-        this._finishStream('completed');
+        if (finishedReason !== undefined) {
+          this._finishStream(mapFinishReason(finishedReason));
+        } else {
+          this._finishStream('completed');
+        }
        return;
      }

@@ -165,6 +165,16 @@ ONLY use the built-in \`exit_plan_mode\` tool to present the plan for formal app
 - **Security First:** Always apply security best practices. Never introduce code that exposes, logs, or commits secrets, API keys, or other sensitive information.

 ## Tool Usage
+- **Tool Execution Response Rules:**
+  1. After receiving a \`functionResponse\`, you MUST ALWAYS execute one of the following two actions:
+     a) Call another tool to proceed with the task.
+     b) Provide a user-facing text response explaining the tool output, your analysis, and next steps.
+  2. You MUST NEVER return an empty response with no text and no tool calls.
+- **Post-Edit Response Rules:**
+  1. After an edit tool execution (e.g. \`replace\`, \`write_file\`), you MUST ALWAYS generate a user-facing text response summarizing:
+     - What changes were made to the file.
+     - Your verification plan or next steps (e.g. running tests).
+  2. You MUST NEVER return an empty response with 0 text tokens after completing an edit.
 - **Parallelism & Sequencing:** Tools execute in parallel by default. Execute multiple independent tool calls in parallel when feasible (e.g., searching, reading files, independent shell commands, or editing *different* files). If a tool depends on the output or side-effects of a previous tool in the same turn (e.g., running a shell command that depends on the success of a previous command), you MUST set the \`wait_for_previous\` parameter to \`true\` on the dependent tool to ensure sequential execution.
 - **File Editing Collisions:** Do NOT make multiple calls to the \`replace\` tool for the SAME file in a single turn. To make multiple edits to the same file, you MUST perform them sequentially across multiple conversational turns to prevent race conditions and ensure the file state is accurate before each edit.
 - **Command Execution:** Use the \`run_shell_command\` tool for running shell commands, remembering the safety rule to explain modifying commands first.
@@ -361,6 +371,16 @@ An approved plan is available for this task at \`../plans/feature-x.md\`.
 - **Security First:** Always apply security best practices. Never introduce code that exposes, logs, or commits secrets, API keys, or other sensitive information.

 ## Tool Usage
+- **Tool Execution Response Rules:**
+  1. After receiving a \`functionResponse\`, you MUST ALWAYS execute one of the following two actions:
+     a) Call another tool to proceed with the task.
+     b) Provide a user-facing text response explaining the tool output, your analysis, and next steps.
+  2. You MUST NEVER return an empty response with no text and no tool calls.
+- **Post-Edit Response Rules:**
+  1. After an edit tool execution (e.g. \`replace\`, \`write_file\`), you MUST ALWAYS generate a user-facing text response summarizing:
+     - What changes were made to the file.
+     - Your verification plan or next steps (e.g. running tests).
+  2. You MUST NEVER return an empty response with 0 text tokens after completing an edit.
 - **Parallelism & Sequencing:** Tools execute in parallel by default. Execute multiple independent tool calls in parallel when feasible (e.g., searching, reading files, independent shell commands, or editing *different* files). If a tool depends on the output or side-effects of a previous tool in the same turn (e.g., running a shell command that depends on the success of a previous command), you MUST set the \`wait_for_previous\` parameter to \`true\` on the dependent tool to ensure sequential execution.
 - **File Editing Collisions:** Do NOT make multiple calls to the \`replace\` tool for the SAME file in a single turn. To make multiple edits to the same file, you MUST perform them sequentially across multiple conversational turns to prevent race conditions and ensure the file state is accurate before each edit.
 - **Command Execution:** Use the \`run_shell_command\` tool for running shell commands, remembering the safety rule to explain modifying commands first.
@@ -671,6 +691,16 @@ ONLY use the built-in \`exit_plan_mode\` tool to present the plan for formal app
 - **Security First:** Always apply security best practices. Never introduce code that exposes, logs, or commits secrets, API keys, or other sensitive information.

 ## Tool Usage
+- **Tool Execution Response Rules:**
+  1. After receiving a \`functionResponse\`, you MUST ALWAYS execute one of the following two actions:
+     a) Call another tool to proceed with the task.
+     b) Provide a user-facing text response explaining the tool output, your analysis, and next steps.
+  2. You MUST NEVER return an empty response with no text and no tool calls.
+- **Post-Edit Response Rules:**
+  1. After an edit tool execution (e.g. \`replace\`, \`write_file\`), you MUST ALWAYS generate a user-facing text response summarizing:
+     - What changes were made to the file.
+     - Your verification plan or next steps (e.g. running tests).
+  2. You MUST NEVER return an empty response with 0 text tokens after completing an edit.
 - **Parallelism & Sequencing:** Tools execute in parallel by default. Execute multiple independent tool calls in parallel when feasible (e.g., searching, reading files, independent shell commands, or editing *different* files). If a tool depends on the output or side-effects of a previous tool in the same turn (e.g., running a shell command that depends on the success of a previous command), you MUST set the \`wait_for_previous\` parameter to \`true\` on the dependent tool to ensure sequential execution.
 - **File Editing Collisions:** Do NOT make multiple calls to the \`replace\` tool for the SAME file in a single turn. To make multiple edits to the same file, you MUST perform them sequentially across multiple conversational turns to prevent race conditions and ensure the file state is accurate before each edit.
 - **Command Execution:** Use the \`run_shell_command\` tool for running shell commands, remembering the safety rule to explain modifying commands first.
@@ -845,6 +875,16 @@ Operate using a **Research -> Strategy -> Execution** lifecycle. For the Executi
 - **Security First:** Always apply security best practices. Never introduce code that exposes, logs, or commits secrets, API keys, or other sensitive information.

 ## Tool Usage
+- **Tool Execution Response Rules:**
+  1. After receiving a \`functionResponse\`, you MUST ALWAYS execute one of the following two actions:
+     a) Call another tool to proceed with the task.
+     b) Provide a user-facing text response explaining the tool output, your analysis, and next steps.
+  2. You MUST NEVER return an empty response with no text and no tool calls.
+- **Post-Edit Response Rules:**
+  1. After an edit tool execution (e.g. \`replace\`, \`write_file\`), you MUST ALWAYS generate a user-facing text response summarizing:
+     - What changes were made to the file.
+     - Your verification plan or next steps (e.g. running tests).
+  2. You MUST NEVER return an empty response with 0 text tokens after completing an edit.
 - **Parallelism & Sequencing:** Tools execute in parallel by default. Execute multiple independent tool calls in parallel when feasible (e.g., searching, reading files, independent shell commands, or editing *different* files). If a tool depends on the output or side-effects of a previous tool in the same turn (e.g., running a shell command that depends on the success of a previous command), you MUST set the \`wait_for_previous\` parameter to \`true\` on the dependent tool to ensure sequential execution.
 - **File Editing Collisions:** Do NOT make multiple calls to the \`replace\` tool for the SAME file in a single turn. To make multiple edits to the same file, you MUST perform them sequentially across multiple conversational turns to prevent race conditions and ensure the file state is accurate before each edit.
 - **Command Execution:** Use the \`run_shell_command\` tool for running shell commands, remembering the safety rule to explain modifying commands first.
@@ -1005,6 +1045,16 @@ Operate using a **Research -> Strategy -> Execution** lifecycle. For the Executi
 - **Security First:** Always apply security best practices. Never introduce code that exposes, logs, or commits secrets, API keys, or other sensitive information.

 ## Tool Usage
+- **Tool Execution Response Rules:**
+  1. After receiving a \`functionResponse\`, you MUST ALWAYS execute one of the following two actions:
+     a) Call another tool to proceed with the task.
+     b) Provide a user-facing text response explaining the tool output, your analysis, and next steps.
+  2. You MUST NEVER return an empty response with no text and no tool calls.
+- **Post-Edit Response Rules:**
+  1. After an edit tool execution (e.g. \`replace\`, \`write_file\`), you MUST ALWAYS generate a user-facing text response summarizing:
+     - What changes were made to the file.
+     - Your verification plan or next steps (e.g. running tests).
+  2. You MUST NEVER return an empty response with 0 text tokens after completing an edit.
 - **Parallelism & Sequencing:** Tools execute in parallel by default. Execute multiple independent tool calls in parallel when feasible (e.g., searching, reading files, independent shell commands, or editing *different* files). If a tool depends on the output or side-effects of a previous tool in the same turn (e.g., running a shell command that depends on the success of a previous command), you MUST set the \`wait_for_previous\` parameter to \`true\` on the dependent tool to ensure sequential execution.
 - **File Editing Collisions:** Do NOT make multiple calls to the \`replace\` tool for the SAME file in a single turn. To make multiple edits to the same file, you MUST perform them sequentially across multiple conversational turns to prevent race conditions and ensure the file state is accurate before each edit.
 - **Command Execution:** Use the \`run_shell_command\` tool for running shell commands, remembering the safety rule to explain modifying commands first.
@@ -1148,6 +1198,16 @@ Operate using a **Research -> Strategy -> Execution** lifecycle. For the Executi
 - **Security First:** Always apply security best practices. Never introduce code that exposes, logs, or commits secrets, API keys, or other sensitive information.

 ## Tool Usage
+- **Tool Execution Response Rules:**
+  1. After receiving a \`functionResponse\`, you MUST ALWAYS execute one of the following two actions:
+     a) Call another tool to proceed with the task.
+     b) Provide a user-facing text response explaining the tool output, your analysis, and next steps.
+  2. You MUST NEVER return an empty response with no text and no tool calls.
+- **Post-Edit Response Rules:**
+  1. After an edit tool execution (e.g. \`replace\`, \`write_file\`), you MUST ALWAYS generate a user-facing text response summarizing:
+     - What changes were made to the file.
+     - Your verification plan or next steps (e.g. running tests).
+  2. You MUST NEVER return an empty response with 0 text tokens after completing an edit.
 - **Parallelism & Sequencing:** Tools execute in parallel by default. Execute multiple independent tool calls in parallel when feasible (e.g., searching, reading files, independent shell commands, or editing *different* files). If a tool depends on the output or side-effects of a previous tool in the same turn (e.g., running a shell command that depends on the success of a previous command), you MUST set the \`wait_for_previous\` parameter to \`true\` on the dependent tool to ensure sequential execution.
 - **File Editing Collisions:** Do NOT make multiple calls to the \`replace\` tool for the SAME file in a single turn. To make multiple edits to the same file, you MUST perform them sequentially across multiple conversational turns to prevent race conditions and ensure the file state is accurate before each edit.
 - **Command Execution:** Use the \`run_shell_command\` tool for running shell commands, remembering the safety rule to explain modifying commands first.
@@ -1837,6 +1897,16 @@ Operate using a **Research -> Strategy -> Execution** lifecycle. For the Executi
 - **Security First:** Always apply security best practices. Never introduce code that exposes, logs, or commits secrets, API keys, or other sensitive information.

 ## Tool Usage
+- **Tool Execution Response Rules:**
+  1. After receiving a \`functionResponse\`, you MUST ALWAYS execute one of the following two actions:
+     a) Call another tool to proceed with the task.
+     b) Provide a user-facing text response explaining the tool output, your analysis, and next steps.
+  2. You MUST NEVER return an empty response with no text and no tool calls.
+- **Post-Edit Response Rules:**
+  1. After an edit tool execution (e.g. \`replace\`, \`write_file\`), you MUST ALWAYS generate a user-facing text response summarizing:
+     - What changes were made to the file.
+     - Your verification plan or next steps (e.g. running tests).
+  2. You MUST NEVER return an empty response with 0 text tokens after completing an edit.
 - **Parallelism & Sequencing:** Tools execute in parallel by default. Execute multiple independent tool calls in parallel when feasible (e.g., searching, reading files, independent shell commands, or editing *different* files). If a tool depends on the output or side-effects of a previous tool in the same turn (e.g., running a shell command that depends on the success of a previous command), you MUST set the \`wait_for_previous\` parameter to \`true\` on the dependent tool to ensure sequential execution.
 - **File Editing Collisions:** Do NOT make multiple calls to the \`replace\` tool for the SAME file in a single turn. To make multiple edits to the same file, you MUST perform them sequentially across multiple conversational turns to prevent race conditions and ensure the file state is accurate before each edit.
 - **Command Execution:** Use the \`run_shell_command\` tool for running shell commands, remembering the safety rule to explain modifying commands first.
@@ -2011,6 +2081,16 @@ Operate using a **Research -> Strategy -> Execution** lifecycle. For the Executi
 - **Security First:** Always apply security best practices. Never introduce code that exposes, logs, or commits secrets, API keys, or other sensitive information.

 ## Tool Usage
+- **Tool Execution Response Rules:**
+  1. After receiving a \`functionResponse\`, you MUST ALWAYS execute one of the following two actions:
+     a) Call another tool to proceed with the task.
+     b) Provide a user-facing text response explaining the tool output, your analysis, and next steps.
+  2. You MUST NEVER return an empty response with no text and no tool calls.
+- **Post-Edit Response Rules:**
+  1. After an edit tool execution (e.g. \`replace\`, \`write_file\`), you MUST ALWAYS generate a user-facing text response summarizing:
+     - What changes were made to the file.
+     - Your verification plan or next steps (e.g. running tests).
+  2. You MUST NEVER return an empty response with 0 text tokens after completing an edit.
 - **Parallelism & Sequencing:** Tools execute in parallel by default. Execute multiple independent tool calls in parallel when feasible (e.g., searching, reading files, independent shell commands, or editing *different* files). If a tool depends on the output or side-effects of a previous tool in the same turn (e.g., running a shell command that depends on the success of a previous command), you MUST set the \`wait_for_previous\` parameter to \`true\` on the dependent tool to ensure sequential execution.
 - **File Editing Collisions:** Do NOT make multiple calls to the \`replace\` tool for the SAME file in a single turn. To make multiple edits to the same file, you MUST perform them sequentially across multiple conversational turns to prevent race conditions and ensure the file state is accurate before each edit.
 - **Command Execution:** Use the \`run_shell_command\` tool for running shell commands, remembering the safety rule to explain modifying commands first.
@@ -2189,6 +2269,16 @@ Operate using a **Research -> Strategy -> Execution** lifecycle. For the Executi
 - **Security First:** Always apply security best practices. Never introduce code that exposes, logs, or commits secrets, API keys, or other sensitive information.

 ## Tool Usage
+- **Tool Execution Response Rules:**
+  1. After receiving a \`functionResponse\`, you MUST ALWAYS execute one of the following two actions:
+     a) Call another tool to proceed with the task.
+     b) Provide a user-facing text response explaining the tool output, your analysis, and next steps.
+  2. You MUST NEVER return an empty response with no text and no tool calls.
+- **Post-Edit Response Rules:**
+  1. After an edit tool execution (e.g. \`replace\`, \`write_file\`), you MUST ALWAYS generate a user-facing text response summarizing:
+     - What changes were made to the file.
+     - Your verification plan or next steps (e.g. running tests).
+  2. You MUST NEVER return an empty response with 0 text tokens after completing an edit.
 - **Parallelism & Sequencing:** Tools execute in parallel by default. Execute multiple independent tool calls in parallel when feasible (e.g., searching, reading files, independent shell commands, or editing *different* files). If a tool depends on the output or side-effects of a previous tool in the same turn (e.g., running a shell command that depends on the success of a previous command), you MUST set the \`wait_for_previous\` parameter to \`true\` on the dependent tool to ensure sequential execution.
 - **File Editing Collisions:** Do NOT make multiple calls to the \`replace\` tool for the SAME file in a single turn. To make multiple edits to the same file, you MUST perform them sequentially across multiple conversational turns to prevent race conditions and ensure the file state is accurate before each edit.
 - **Command Execution:** Use the \`run_shell_command\` tool for running shell commands, remembering the safety rule to explain modifying commands first.
@@ -2367,6 +2457,16 @@ Operate using a **Research -> Strategy -> Execution** lifecycle. For the Executi
 - **Security First:** Always apply security best practices. Never introduce code that exposes, logs, or commits secrets, API keys, or other sensitive information.

 ## Tool Usage
+- **Tool Execution Response Rules:**
+  1. After receiving a \`functionResponse\`, you MUST ALWAYS execute one of the following two actions:
+     a) Call another tool to proceed with the task.
+     b) Provide a user-facing text response explaining the tool output, your analysis, and next steps.
+  2. You MUST NEVER return an empty response with no text and no tool calls.
+- **Post-Edit Response Rules:**
+  1. After an edit tool execution (e.g. \`replace\`, \`write_file\`), you MUST ALWAYS generate a user-facing text response summarizing:
+     - What changes were made to the file.
+     - Your verification plan or next steps (e.g. running tests).
+  2. You MUST NEVER return an empty response with 0 text tokens after completing an edit.
 - **Parallelism & Sequencing:** Tools execute in parallel by default. Execute multiple independent tool calls in parallel when feasible (e.g., searching, reading files, independent shell commands, or editing *different* files). If a tool depends on the output or side-effects of a previous tool in the same turn (e.g., running a shell command that depends on the success of a previous command), you MUST set the \`wait_for_previous\` parameter to \`true\` on the dependent tool to ensure sequential execution.
 - **File Editing Collisions:** Do NOT make multiple calls to the \`replace\` tool for the SAME file in a single turn. To make multiple edits to the same file, you MUST perform them sequentially across multiple conversational turns to prevent race conditions and ensure the file state is accurate before each edit.
 - **Command Execution:** Use the \`run_shell_command\` tool for running shell commands, remembering the safety rule to explain modifying commands first.
@@ -2541,6 +2641,16 @@ Operate using a **Research -> Strategy -> Execution** lifecycle. For the Executi
 - **Security First:** Always apply security best practices. Never introduce code that exposes, logs, or commits secrets, API keys, or other sensitive information.

 ## Tool Usage
+- **Tool Execution Response Rules:**
+  1. After receiving a \`functionResponse\`, you MUST ALWAYS execute one of the following two actions:
+     a) Call another tool to proceed with the task.
+     b) Provide a user-facing text response explaining the tool output, your analysis, and next steps.
+  2. You MUST NEVER return an empty response with no text and no tool calls.
+- **Post-Edit Response Rules:**
+  1. After an edit tool execution (e.g. \`replace\`, \`write_file\`), you MUST ALWAYS generate a user-facing text response summarizing:
+     - What changes were made to the file.
+     - Your verification plan or next steps (e.g. running tests).
+  2. You MUST NEVER return an empty response with 0 text tokens after completing an edit.
 - **Parallelism & Sequencing:** Tools execute in parallel by default. Execute multiple independent tool calls in parallel when feasible (e.g., searching, reading files, independent shell commands, or editing *different* files). If a tool depends on the output or side-effects of a previous tool in the same turn (e.g., running a shell command that depends on the success of a previous command), you MUST set the \`wait_for_previous\` parameter to \`true\` on the dependent tool to ensure sequential execution.
 - **File Editing Collisions:** Do NOT make multiple calls to the \`replace\` tool for the SAME file in a single turn. To make multiple edits to the same file, you MUST perform them sequentially across multiple conversational turns to prevent race conditions and ensure the file state is accurate before each edit.
 - **Command Execution:** Use the \`run_shell_command\` tool for running shell commands, remembering the safety rule to explain modifying commands first.
@@ -2709,6 +2819,16 @@ Operate using a **Research -> Strategy -> Execution** lifecycle. For the Executi
 - **Security First:** Always apply security best practices. Never introduce code that exposes, logs, or commits secrets, API keys, or other sensitive information.

 ## Tool Usage
+- **Tool Execution Response Rules:**
+  1. After receiving a \`functionResponse\`, you MUST ALWAYS execute one of the following two actions:
+     a) Call another tool to proceed with the task.
+     b) Provide a user-facing text response explaining the tool output, your analysis, and next steps.
+  2. You MUST NEVER return an empty response with no text and no tool calls.
+- **Post-Edit Response Rules:**
+  1. After an edit tool execution (e.g. \`replace\`, \`write_file\`), you MUST ALWAYS generate a user-facing text response summarizing:
+     - What changes were made to the file.
+     - Your verification plan or next steps (e.g. running tests).
+  2. You MUST NEVER return an empty response with 0 text tokens after completing an edit.
 - **Parallelism & Sequencing:** Tools execute in parallel by default. Execute multiple independent tool calls in parallel when feasible (e.g., searching, reading files, independent shell commands, or editing *different* files). If a tool depends on the output or side-effects of a previous tool in the same turn (e.g., running a shell command that depends on the success of a previous command), you MUST set the \`wait_for_previous\` parameter to \`true\` on the dependent tool to ensure sequential execution.
 - **File Editing Collisions:** Do NOT make multiple calls to the \`replace\` tool for the SAME file in a single turn. To make multiple edits to the same file, you MUST perform them sequentially across multiple conversational turns to prevent race conditions and ensure the file state is accurate before each edit.
 - **Command Execution:** Use the \`run_shell_command\` tool for running shell commands, remembering the safety rule to explain modifying commands first.
@@ -2851,6 +2971,16 @@ Operate using a **Research -> Strategy -> Execution** lifecycle. For the Executi
 - **Security First:** Always apply security best practices. Never introduce code that exposes, logs, or commits secrets, API keys, or other sensitive information.

 ## Tool Usage
+- **Tool Execution Response Rules:**
+  1. After receiving a \`functionResponse\`, you MUST ALWAYS execute one of the following two actions:
+     a) Call another tool to proceed with the task.
+     b) Provide a user-facing text response explaining the tool output, your analysis, and next steps.
+  2. You MUST NEVER return an empty response with no text and no tool calls.
+- **Post-Edit Response Rules:**
+  1. After an edit tool execution (e.g. \`replace\`, \`write_file\`), you MUST ALWAYS generate a user-facing text response summarizing:
+     - What changes were made to the file.
+     - Your verification plan or next steps (e.g. running tests).
+  2. You MUST NEVER return an empty response with 0 text tokens after completing an edit.
 - **Parallelism & Sequencing:** Tools execute in parallel by default. Execute multiple independent tool calls in parallel when feasible (e.g., searching, reading files, independent shell commands, or editing *different* files). If a tool depends on the output or side-effects of a previous tool in the same turn (e.g., running a shell command that depends on the success of a previous command), you MUST set the \`wait_for_previous\` parameter to \`true\` on the dependent tool to ensure sequential execution.
 - **File Editing Collisions:** Do NOT make multiple calls to the \`replace\` tool for the SAME file in a single turn. To make multiple edits to the same file, you MUST perform them sequentially across multiple conversational turns to prevent race conditions and ensure the file state is accurate before each edit.
 - **Command Execution:** Use the \`run_shell_command\` tool for running shell commands, remembering the safety rule to explain modifying commands first.
@@ -3025,6 +3155,16 @@ Operate using a **Research -> Strategy -> Execution** lifecycle. For the Executi
 - **Security First:** Always apply security best practices. Never introduce code that exposes, logs, or commits secrets, API keys, or other sensitive information.

 ## Tool Usage
+- **Tool Execution Response Rules:**
+  1. After receiving a \`functionResponse\`, you MUST ALWAYS execute one of the following two actions:
+     a) Call another tool to proceed with the task.
+     b) Provide a user-facing text response explaining the tool output, your analysis, and next steps.
+  2. You MUST NEVER return an empty response with no text and no tool calls.
+- **Post-Edit Response Rules:**
+  1. After an edit tool execution (e.g. \`replace\`, \`write_file\`), you MUST ALWAYS generate a user-facing text response summarizing:
+     - What changes were made to the file.
+     - Your verification plan or next steps (e.g. running tests).
+  2. You MUST NEVER return an empty response with 0 text tokens after completing an edit.
 - **Parallelism & Sequencing:** Tools execute in parallel by default. Execute multiple independent tool calls in parallel when feasible (e.g., searching, reading files, independent shell commands, or editing *different* files). If a tool depends on the output or side-effects of a previous tool in the same turn (e.g., running a shell command that depends on the success of a previous command), you MUST set the \`wait_for_previous\` parameter to \`true\` on the dependent tool to ensure sequential execution.
 - **File Editing Collisions:** Do NOT make multiple calls to the \`replace\` tool for the SAME file in a single turn. To make multiple edits to the same file, you MUST perform them sequentially across multiple conversational turns to prevent race conditions and ensure the file state is accurate before each edit.
 - **Command Execution:** Use the \`run_shell_command\` tool for running shell commands, remembering the safety rule to explain modifying commands first.
@@ -3345,6 +3485,16 @@ You are operating with a persistent file-based task tracking system located at \
 - **Security First:** Always apply security best practices. Never introduce code that exposes, logs, or commits secrets, API keys, or other sensitive information.

 ## Tool Usage
+- **Tool Execution Response Rules:**
+  1. After receiving a \`functionResponse\`, you MUST ALWAYS execute one of the following two actions:
+     a) Call another tool to proceed with the task.
+     b) Provide a user-facing text response explaining the tool output, your analysis, and next steps.
+  2. You MUST NEVER return an empty response with no text and no tool calls.
+- **Post-Edit Response Rules:**
+  1. After an edit tool execution (e.g. \`replace\`, \`write_file\`), you MUST ALWAYS generate a user-facing text response summarizing:
+     - What changes were made to the file.
+     - Your verification plan or next steps (e.g. running tests).
+  2. You MUST NEVER return an empty response with 0 text tokens after completing an edit.
 - **Parallelism & Sequencing:** Tools execute in parallel by default. Execute multiple independent tool calls in parallel when feasible (e.g., searching, reading files, independent shell commands, or editing *different* files). If a tool depends on the output or side-effects of a previous tool in the same turn (e.g., running a shell command that depends on the success of a previous command), you MUST set the \`wait_for_previous\` parameter to \`true\` on the dependent tool to ensure sequential execution.
 - **File Editing Collisions:** Do NOT make multiple calls to the \`replace\` tool for the SAME file in a single turn. To make multiple edits to the same file, you MUST perform them sequentially across multiple conversational turns to prevent race conditions and ensure the file state is accurate before each edit.
 - **Command Execution:** Use the \`run_shell_command\` tool for running shell commands, remembering the safety rule to explain modifying commands first.
@@ -3774,6 +3924,16 @@ Operate using a **Research -> Strategy -> Execution** lifecycle. For the Executi
 - **Security First:** Always apply security best practices. Never introduce code that exposes, logs, or commits secrets, API keys, or other sensitive information.

 ## Tool Usage
+- **Tool Execution Response Rules:**
+  1. After receiving a \`functionResponse\`, you MUST ALWAYS execute one of the following two actions:
+     a) Call another tool to proceed with the task.
+     b) Provide a user-facing text response explaining the tool output, your analysis, and next steps.
+  2. You MUST NEVER return an empty response with no text and no tool calls.
+- **Post-Edit Response Rules:**
+  1. After an edit tool execution (e.g. \`replace\`, \`write_file\`), you MUST ALWAYS generate a user-facing text response summarizing:
+     - What changes were made to the file.
+     - Your verification plan or next steps (e.g. running tests).
+  2. You MUST NEVER return an empty response with 0 text tokens after completing an edit.
 - **Parallelism & Sequencing:** Tools execute in parallel by default. Execute multiple independent tool calls in parallel when feasible (e.g., searching, reading files, independent shell commands, or editing *different* files). If a tool depends on the output or side-effects of a previous tool in the same turn (e.g., running a shell command that depends on the success of a previous command), you MUST set the \`wait_for_previous\` parameter to \`true\` on the dependent tool to ensure sequential execution.
 - **File Editing Collisions:** Do NOT make multiple calls to the \`replace\` tool for the SAME file in a single turn. To make multiple edits to the same file, you MUST perform them sequentially across multiple conversational turns to prevent race conditions and ensure the file state is accurate before each edit.
 - **Command Execution:** Use the \`run_shell_command\` tool for running shell commands, remembering the safety rule to explain modifying commands first.
@@ -3948,6 +4108,16 @@ Operate using a **Research -> Strategy -> Execution** lifecycle. For the Executi
 - **Security First:** Always apply security best practices. Never introduce code that exposes, logs, or commits secrets, API keys, or other sensitive information.

 ## Tool Usage
+- **Tool Execution Response Rules:**
+  1. After receiving a \`functionResponse\`, you MUST ALWAYS execute one of the following two actions:
+     a) Call another tool to proceed with the task.
+     b) Provide a user-facing text response explaining the tool output, your analysis, and next steps.
+  2. You MUST NEVER return an empty response with no text and no tool calls.
+- **Post-Edit Response Rules:**
+  1. After an edit tool execution (e.g. \`replace\`, \`write_file\`), you MUST ALWAYS generate a user-facing text response summarizing:
+     - What changes were made to the file.
+     - Your verification plan or next steps (e.g. running tests).
+  2. You MUST NEVER return an empty response with 0 text tokens after completing an edit.
 - **Parallelism & Sequencing:** Tools execute in parallel by default. Execute multiple independent tool calls in parallel when feasible (e.g., searching, reading files, independent shell commands, or editing *different* files). If a tool depends on the output or side-effects of a previous tool in the same turn (e.g., running a shell command that depends on the success of a previous command), you MUST set the \`wait_for_previous\` parameter to \`true\` on the dependent tool to ensure sequential execution.
 - **File Editing Collisions:** Do NOT make multiple calls to the \`replace\` tool for the SAME file in a single turn. To make multiple edits to the same file, you MUST perform them sequentially across multiple conversational turns to prevent race conditions and ensure the file state is accurate before each edit.
 - **Command Execution:** Use the \`run_shell_command\` tool for running shell commands, remembering the safety rule to explain modifying commands first.
@@ -4241,6 +4411,16 @@ Operate using a **Research -> Strategy -> Execution** lifecycle. For the Executi
 - **Security First:** Always apply security best practices. Never introduce code that exposes, logs, or commits secrets, API keys, or other sensitive information.

 ## Tool Usage
+- **Tool Execution Response Rules:**
+  1. After receiving a \`functionResponse\`, you MUST ALWAYS execute one of the following two actions:
+     a) Call another tool to proceed with the task.
+     b) Provide a user-facing text response explaining the tool output, your analysis, and next steps.
+  2. You MUST NEVER return an empty response with no text and no tool calls.
+- **Post-Edit Response Rules:**
+  1. After an edit tool execution (e.g. \`replace\`, \`write_file\`), you MUST ALWAYS generate a user-facing text response summarizing:
+     - What changes were made to the file.
+     - Your verification plan or next steps (e.g. running tests).
+  2. You MUST NEVER return an empty response with 0 text tokens after completing an edit.
 - **Parallelism & Sequencing:** Tools execute in parallel by default. Execute multiple independent tool calls in parallel when feasible (e.g., searching, reading files, independent shell commands, or editing *different* files). If a tool depends on the output or side-effects of a previous tool in the same turn (e.g., running a shell command that depends on the success of a previous command), you MUST set the \`wait_for_previous\` parameter to \`true\` on the dependent tool to ensure sequential execution.
 - **File Editing Collisions:** Do NOT make multiple calls to the \`replace\` tool for the SAME file in a single turn. To make multiple edits to the same file, you MUST perform them sequentially across multiple conversational turns to prevent race conditions and ensure the file state is accurate before each edit.
 - **Command Execution:** Use the \`run_shell_command\` tool for running shell commands, remembering the safety rule to explain modifying commands first.
@@ -4415,6 +4595,16 @@ Operate using a **Research -> Strategy -> Execution** lifecycle. For the Executi
 - **Security First:** Always apply security best practices. Never introduce code that exposes, logs, or commits secrets, API keys, or other sensitive information.

 ## Tool Usage
+- **Tool Execution Response Rules:**
+  1. After receiving a \`functionResponse\`, you MUST ALWAYS execute one of the following two actions:
+     a) Call another tool to proceed with the task.
+     b) Provide a user-facing text response explaining the tool output, your analysis, and next steps.
+  2. You MUST NEVER return an empty response with no text and no tool calls.
+- **Post-Edit Response Rules:**
+  1. After an edit tool execution (e.g. \`replace\`, \`write_file\`), you MUST ALWAYS generate a user-facing text response summarizing:
+     - What changes were made to the file.
+     - Your verification plan or next steps (e.g. running tests).
+  2. You MUST NEVER return an empty response with 0 text tokens after completing an edit.
 - **Parallelism & Sequencing:** Tools execute in parallel by default. Execute multiple independent tool calls in parallel when feasible (e.g., searching, reading files, independent shell commands, or editing *different* files). If a tool depends on the output or side-effects of a previous tool in the same turn (e.g., running a shell command that depends on the success of a previous command), you MUST set the \`wait_for_previous\` parameter to \`true\` on the dependent tool to ensure sequential execution.
 - **File Editing Collisions:** Do NOT make multiple calls to the \`replace\` tool for the SAME file in a single turn. To make multiple edits to the same file, you MUST perform them sequentially across multiple conversational turns to prevent race conditions and ensure the file state is accurate before each edit.
 - **Command Execution:** Use the \`run_shell_command\` tool for running shell commands, remembering the safety rule to explain modifying commands first.
@@ -0,0 +1,110 @@
+/**
+ * @license
+ * Copyright 2026 Google LLC
+ * SPDX-License-Identifier: Apache-2.0
+ */
+
+import { describe, it, expect } from 'vitest';
+import { AgentChatHistory, type HistoryTurn } from './agentChatHistory.js';
+
+describe('AgentChatHistory', () => {
+  const dummyTurns: HistoryTurn[] = [
+    {
+      id: 'turn-1',
+      content: { role: 'user', parts: [{ text: 'Hello' }] },
+    },
+    {
+      id: 'turn-2',
+      content: { role: 'model', parts: [{ text: 'Hi there' }] },
+    },
+    {
+      id: 'turn-3',
+      content: { role: 'user', parts: [{ text: 'How are you?' }] },
+    },
+  ];
+
+  it('should initialize with empty history by default', () => {
+    const history = new AgentChatHistory();
+    expect(history.length).toBe(0);
+    expect(history.get()).toEqual([]);
+  });
+
+  it('should initialize with provided turns', () => {
+    const history = new AgentChatHistory(dummyTurns);
+    expect(history.length).toBe(3);
+    expect(history.get()).toEqual(dummyTurns);
+  });
+
+  it('should push new turns', () => {
+    const history = new AgentChatHistory();
+    history.push(dummyTurns[0]);
+    expect(history.length).toBe(1);
+    expect(history.get()[0]).toEqual(dummyTurns[0]);
+  });
+
+  it('should set and overwrite history turns', () => {
+    const history = new AgentChatHistory(dummyTurns.slice(0, 1));
+    expect(history.length).toBe(1);
+    history.set(dummyTurns);
+    expect(history.length).toBe(3);
+    expect(history.get()).toEqual(dummyTurns);
+  });
+
+  it('should clear history', () => {
+    const history = new AgentChatHistory(dummyTurns);
+    expect(history.length).toBe(3);
+    history.clear();
+    expect(history.length).toBe(0);
+    expect(history.get()).toEqual([]);
+  });
+
+  describe('rollback', () => {
+    it('should roll back history to a specified length', () => {
+      const history = new AgentChatHistory(dummyTurns);
+      history.rollback(1);
+      expect(history.length).toBe(1);
+      expect(history.get()).toEqual([dummyTurns[0]]);
+    });
+
+    it('should roll back to 0', () => {
+      const history = new AgentChatHistory(dummyTurns);
+      history.rollback(0);
+      expect(history.length).toBe(0);
+      expect(history.get()).toEqual([]);
+    });
+
+    it('should do nothing if rollback length is out of bounds (negative)', () => {
+      const history = new AgentChatHistory(dummyTurns);
+      history.rollback(-1);
+      expect(history.length).toBe(3);
+      expect(history.get()).toEqual(dummyTurns);
+    });
+
+    it('should do nothing if rollback length is out of bounds (greater than current history length)', () => {
+      const history = new AgentChatHistory(dummyTurns);
+      history.rollback(5);
+      expect(history.length).toBe(3);
+      expect(history.get()).toEqual(dummyTurns);
+    });
+  });
+
+  it('should return raw Content array via getContents()', () => {
+    const history = new AgentChatHistory(dummyTurns);
+    expect(history.getContents()).toEqual(
+      dummyTurns.map((turn) => turn.content),
+    );
+  });
+
+  it('should support mapping and flatMapping operations', () => {
+    const history = new AgentChatHistory(dummyTurns);
+    const mappedIds = history.map((turn) => turn.id);
+    expect(mappedIds).toEqual(['turn-1', 'turn-2', 'turn-3']);
+
+    const flatMappedParts = history.flatMap((turn) => turn.content.parts || []);
+    expect(flatMappedParts).toEqual([
+      { text: 'Hello' },
+      { text: 'Hi there' },
+      { text: 'How are you?' },
+    ]);
+  });
+});
@@ -46,6 +46,16 @@ export class AgentChatHistory {
    this.history = [];
  }

+  /**
+   * Rolls back the history to a specified length.
+   * Useful when a stream fails and we need to remove the un-responded turn(s).
+   */
+  rollback(length: number) {
+    if (length >= 0 && length <= this.history.length) {
+      this.history = this.history.slice(0, length);
+    }
+  }
+
  get(): readonly HistoryTurn[] {
    return this.history;
  }
@@ -108,6 +108,13 @@ const MID_STREAM_RETRY_OPTIONS: MidStreamRetryOptions = {

 export const SYNTHETIC_THOUGHT_SIGNATURE = 'skip_thought_signature_validator';

+/**
+ * Stands in for a model turn that never arrived because the stream failed
+ * after a tool response was already committed to history.
+ */
+export const INTERRUPTED_RESPONSE_PLACEHOLDER =
+  '[The previous response was interrupted before it completed.]';
+
 /**
 * Internal interface for parts that carry the magic 'callIndex' property
 * used during model response consolidation.
@@ -225,7 +232,12 @@ export class InvalidStreamError extends Error {
    | 'NO_FINISH_REASON'
    | 'NO_RESPONSE_TEXT'
    | 'MALFORMED_FUNCTION_CALL'
-    | 'UNEXPECTED_TOOL_CALL';
+    | 'UNEXPECTED_TOOL_CALL'
+    | 'MAX_TOKENS_EXCEEDED'
+    | 'SAFETY_BLOCKED'
+    | 'RECITATION_BLOCKED'
+    | 'OTHER_BLOCKED'
+    | 'THINKING_ONLY_RESPONSE';

  constructor(
    message: string,
@@ -233,7 +245,12 @@ export class InvalidStreamError extends Error {
      | 'NO_FINISH_REASON'
      | 'NO_RESPONSE_TEXT'
      | 'MALFORMED_FUNCTION_CALL'
-      | 'UNEXPECTED_TOOL_CALL',
+      | 'UNEXPECTED_TOOL_CALL'
+      | 'MAX_TOKENS_EXCEEDED'
+      | 'SAFETY_BLOCKED'
+      | 'RECITATION_BLOCKED'
+      | 'OTHER_BLOCKED'
+      | 'THINKING_ONLY_RESPONSE',
  ) {
    super(message);
    this.name = 'InvalidStreamError';
@@ -387,6 +404,9 @@ export class GeminiChat {
  ): Promise<AsyncGenerator<StreamEvent>> {
    await this.sendPromise;

+    const historyLengthBefore = this.agentHistory.length;
+    const baselinePromptTokenCount = this.lastPromptTokenCount;
+
    let streamDoneResolver: () => void;
    const streamDonePromise = new Promise<void>((resolve) => {
      streamDoneResolver = resolve;
@@ -394,6 +414,17 @@ export class GeminiChat {
    this.sendPromise = streamDonePromise;

    let userContent = createUserContent(message);
+    const isOriginalFunctionResponse = isFunctionResponse(userContent);
+
+    // A turn can end leaving history on an unanswered tool response: a stream
+    // error after the response was committed, or a cancelled tool call. Close
+    // it before recording a genuinely new user message, otherwise the two user
+    // turns are coalesced into one and the model continues the trailing text
+    // instead of answering it.
+    if (!isOriginalFunctionResponse) {
+      this.closeUnansweredToolResponseTurn();
+    }
+
    const { model } =
      this.context.config.modelConfigService.getResolvedConfig(modelConfigKey);

@@ -402,7 +433,7 @@ export class GeminiChat {

    // Record user input - capture complete message with all parts (text, files, images, etc.)
    // but skip recording function responses (tool call results) as they should be stored in tool call records
-    if (!isFunctionResponse(userContent)) {
+    if (!isOriginalFunctionResponse) {
      const userMessageParts = userContent.parts || [];
      const userMessageContent = partListUnionToString(userMessageParts);

@@ -519,6 +550,7 @@ export class GeminiChat {
    ): AsyncGenerator<StreamEvent, void, void> {
      try {
        const maxAttempts = this.context.config.getMaxAttempts();
+        let lastStreamError: unknown = undefined;

        for (let attempt = 0; attempt < maxAttempts; attempt++) {
          let isConnectionPhase = true;
@@ -530,7 +562,7 @@ export class GeminiChat {
            // If this is a retry, update the key with the new context.
            const currentConfigKey =
              attempt > 0
-                ? { ...modelConfigKey, isRetry: true }
+                ? { ...modelConfigKey, isRetry: true, lastStreamError }
                : modelConfigKey;

            isConnectionPhase = true;
@@ -549,6 +581,10 @@ export class GeminiChat {

            return;
          } catch (error) {
+            if (error instanceof InvalidStreamError) {
+              lastStreamError = error;
+            }
+
            if (error instanceof AgentExecutionStoppedError) {
              yield {
                type: StreamEventType.AGENT_EXECUTION_STOPPED,
@@ -585,8 +621,7 @@ export class GeminiChat {
            );

            const isContentError = error instanceof InvalidStreamError;
-            const isRetryableContentError =
-              isContentError && error.type !== 'NO_RESPONSE_TEXT';
+            const isRetryableContentError = isContentError;
            const errorType = isContentError
              ? error.type
              : getRetryErrorType(error);
@@ -648,6 +683,15 @@ export class GeminiChat {
            throw error;
          }
        }
+      } catch (error) {
+        if (!isOriginalFunctionResponse) {
+          this.agentHistory.rollback(historyLengthBefore);
+          this.chatRecordingService.updateMessagesFromHistory(
+            this.agentHistory.get(),
+          );
+          this.lastPromptTokenCount = baselinePromptTokenCount;
+        }
+        throw error;
      } finally {
        streamDoneResolver!();
      }
@@ -656,6 +700,28 @@ export class GeminiChat {
    return streamWithRetries.call(this);
  }

+  /**
+   * Appends a closing model turn when history ends with an unanswered tool
+   * response, so the next user message stays a turn of its own.
+   */
+  private closeUnansweredToolResponseTurn(): void {
+    const turns = this.agentHistory.get();
+    const last = turns[turns.length - 1];
+    if (
+      last?.content.role !== 'user' ||
+      !last.content.parts?.some((part) => !!part.functionResponse)
+    ) {
+      return;
+    }
+    this.agentHistory.push({
+      id: randomUUID(),
+      content: {
+        role: 'model',
+        parts: [{ text: INTERRUPTED_RESPONSE_PLACEHOLDER }],
+      },
+    });
+  }
+
  private extractBinaryInjections(
    parts: Part[] | undefined,
  ): Part[] | undefined {
@@ -770,6 +836,30 @@ export class GeminiChat {
        abortSignal,
      };

+      // Apply Context-Aware Retries (On-Retry Nudging) to guide the model out of silent loops
+      if (
+        modelConfigKey.isRetry &&
+        modelConfigKey.lastStreamError instanceof InvalidStreamError
+      ) {
+        const lastError = modelConfigKey.lastStreamError;
+        let nudgeMessage = '';
+        if (lastError.type === 'THINKING_ONLY_RESPONSE') {
+          nudgeMessage =
+            '\n[System: You previously generated thoughts but failed to provide a final user-facing response. Please ensure you provide your final answer or call a tool now.]';
+        } else if (lastError.type === 'NO_RESPONSE_TEXT') {
+          nudgeMessage =
+            '\n[System: You previously returned an empty response with no text or thoughts. Please ensure you provide your final answer or call a tool now.]';
+        }
+
+        if (nudgeMessage) {
+          if (typeof config.systemInstruction === 'string') {
+            config.systemInstruction += nudgeMessage;
+          } else if (config.systemInstruction === undefined) {
+            config.systemInstruction = nudgeMessage;
+          }
+        }
+      }
+
      let contentsToUse: Content[] =
        supportsModernFeatures(modelToUse) || isGemini2Model(modelToUse)
          ? [...contentsForPreviewModel]
@@ -1143,6 +1233,13 @@ export class GeminiChat {
    let hasThoughts = false;
    let finishReason: FinishReason | undefined;

+    // Buffers to prevent failed stream attempts from polluting telemetry and logs
+    const bufferedThoughts: Array<{ subject: string; description: string }> =
+      [];
+    let bufferedUsageMetadata:
+      | GenerateContentResponse['usageMetadata']
+      | undefined = undefined;
+
    // The SDK provides fully assembled FunctionCall objects in chunk.functionCalls
    // We use a Map to ensure we only keep the latest version of each call (by ID)
    const finalFunctionCallsMap = new Map<string, FunctionCall>();
@@ -1198,7 +1295,10 @@ export class GeminiChat {
          if (content.parts.some((part) => part.thought)) {
            // Record thoughts
            hasThoughts = true;
-            this.recordThoughtFromContent(content);
+            const thought = this.extractThoughtFromContent(content);
+            if (thought) {
+              bufferedThoughts.push(thought);
+            }
          }
          if (content.parts.some((part) => part.functionCall)) {
            hasToolCall = true;
@@ -1226,12 +1326,9 @@ export class GeminiChat {
        }
      }

-      // Record token usage if this chunk has usageMetadata
+      // Buffer token usage if this chunk has usageMetadata
      if (chunk.usageMetadata) {
-        this.chatRecordingService.recordMessageTokens(chunk.usageMetadata);
-        if (chunk.usageMetadata.promptTokenCount !== undefined) {
-          this.lastPromptTokenCount = chunk.usageMetadata.promptTokenCount;
-        }
+        bufferedUsageMetadata = chunk.usageMetadata;
      }

      const hookSystem = this.context.config.getHookSystem();
@@ -1318,29 +1415,22 @@ export class GeminiChat {
      }
    }

-    const responseText = consolidatedParts
+    const rawResponseText = consolidatedParts
      .filter((part) => part.text)
      .map((part) => part.text)
-      .join('')
-      .trim();
+      .join('');

-    let id: string;
-    // Record model response text from the collected parts.
-    // Also flush when there are thoughts or a tool call (even with no text)
-    // so that BeforeTool hooks always see the latest transcript state.
-    if (responseText || hasThoughts || hasToolCall) {
-      id = this.chatRecordingService.recordMessage({
-        model,
-        type: 'gemini',
-        content: responseText,
-      });
-    } else {
-      // Still need a durable ID even if response is empty (e.g. only tool calls)
-      id = this.chatRecordingService.recordSyntheticMessage(
-        'gemini',
-        consolidatedParts,
-      );
-    }
+    // Clean zero-width/invisible characters and HTML comments to determine actual printable/visible content
+    let responseText = rawResponseText.replace(
+      /[\u200B-\u200D\uFEFF\u200E\u200F]/g,
+      '',
+    );
+    let previous: string;
+    do {
+      previous = responseText;
+      responseText = responseText.replace(/<!--[\s\S]*?-->/g, '');
+    } while (responseText !== previous);
+    responseText = responseText.trim();

    // Stream validation logic: A stream is considered successful if:
    // 1. There's a tool call OR
@@ -1370,6 +1460,36 @@ export class GeminiChat {
        );
      }
      if (!responseText) {
+        if (finishReason === FinishReason.MAX_TOKENS) {
+          throw new InvalidStreamError(
+            'Model stream ended due to token limit exhaustion (MAX_TOKENS) with empty response text.',
+            'MAX_TOKENS_EXCEEDED',
+          );
+        }
+        if (finishReason === FinishReason.SAFETY) {
+          throw new InvalidStreamError(
+            'Model stream ended due to safety settings (SAFETY) with empty response text.',
+            'SAFETY_BLOCKED',
+          );
+        }
+        if (finishReason === FinishReason.RECITATION) {
+          throw new InvalidStreamError(
+            'Model stream ended due to recitation settings (RECITATION) with empty response text.',
+            'RECITATION_BLOCKED',
+          );
+        }
+        if (finishReason === FinishReason.OTHER) {
+          throw new InvalidStreamError(
+            'Model stream ended due to other settings (OTHER) with empty response text.',
+            'OTHER_BLOCKED',
+          );
+        }
+        if (hasThoughts) {
+          throw new InvalidStreamError(
+            'Model stream ended with empty response text but contained reasoning thoughts.',
+            'THINKING_ONLY_RESPONSE',
+          );
+        }
        throw new InvalidStreamError(
          'Model stream ended with empty response text.',
          'NO_RESPONSE_TEXT',
@@ -1377,6 +1497,37 @@ export class GeminiChat {
      }
    }

+    // Flush buffered thoughts from the successful attempt
+    for (const thought of bufferedThoughts) {
+      this.chatRecordingService.recordThought(thought);
+    }
+
+    // Flush buffered usage metadata and token counts from the successful attempt
+    if (bufferedUsageMetadata) {
+      this.chatRecordingService.recordMessageTokens(bufferedUsageMetadata);
+      if (bufferedUsageMetadata.promptTokenCount !== undefined) {
+        this.lastPromptTokenCount = bufferedUsageMetadata.promptTokenCount;
+      }
+    }
+
+    let id: string;
+    // Record model response text from the collected parts.
+    // Also flush when there are thoughts or a tool call (even with no text)
+    // so that BeforeTool hooks always see the latest transcript state.
+    if (responseText || hasThoughts || hasToolCall) {
+      id = this.chatRecordingService.recordMessage({
+        model,
+        type: 'gemini',
+        content: responseText,
+      });
+    } else {
+      // Still need a durable ID even if response is empty (e.g. only tool calls)
+      id = this.chatRecordingService.recordSyntheticMessage(
+        'gemini',
+        consolidatedParts,
+      );
+    }
+
    this.agentHistory.push({
      id,
      content: { role: 'model', parts: consolidatedParts },
@@ -1431,11 +1582,13 @@ export class GeminiChat {
  }

  /**
-   * Extracts and records thought from thought content.
+   * Extracts thought from thought content.
   */
-  private recordThoughtFromContent(content: Content): void {
+  private extractThoughtFromContent(
+    content: Content,
+  ): { subject: string; description: string } | undefined {
    if (!content.parts || content.parts.length === 0) {
-      return;
+      return undefined;
    }

    const thoughtPart = content.parts[0];
@@ -1448,11 +1601,12 @@ export class GeminiChat {
        : '';
      const description = rawText.replace(/\*\*(.*?)\*\*/s, '').trim();

-      this.chatRecordingService.recordThought({
+      return {
        subject,
        description,
-      });
+      };
    }
+    return undefined;
  }
 }

@@ -1533,11 +1687,34 @@ export function stripThoughts(history: HistoryTurn[]): HistoryTurn[] {
      if (!hasThought) return turn;

      const nonThoughtParts = turn.content.parts.filter((p) => p && !p.thought);
+
+      // The thoughtSignature the API requires on the first functionCall of a
+      // model turn is sometimes only carried by the thought part we just
+      // removed, not by the functionCall part itself. Without it, replaying
+      // this turn in a later request gets rejected with a 400 "missing
+      // thought_signature" error, so inject a synthetic one if needed.
+      let patchedFirstCall = false;
+      const finalParts =
+        turn.content.role === 'model'
+          ? nonThoughtParts.map((p) => {
+              if (!patchedFirstCall && p.functionCall) {
+                patchedFirstCall = true;
+                if (!p.thoughtSignature) {
+                  return {
+                    ...p,
+                    thoughtSignature: SYNTHETIC_THOUGHT_SIGNATURE,
+                  };
+                }
+              }
+              return p;
+            })
+          : nonThoughtParts;
+
      return {
        ...turn,
        content: {
          ...turn.content,
-          parts: nonThoughtParts,
+          parts: finalParts,
        },
      };
    })
@@ -254,7 +254,15 @@ describe('Turn', () => {
        events.push(event);
      }

-      expect(events).toEqual([{ type: GeminiEventType.InvalidStream }]);
+      expect(events).toEqual([
+        {
+          type: GeminiEventType.InvalidStream,
+          value: {
+            type: 'NO_FINISH_REASON',
+            message: 'Test invalid stream',
+          },
+        },
+      ]);
      expect(turn.getDebugResponses().length).toBe(0);
      expect(reportError).not.toHaveBeenCalled(); // Should not report as error
    });
@@ -105,6 +105,19 @@ export type ServerGeminiContextWindowWillOverflowEvent = {

 export type ServerGeminiInvalidStreamEvent = {
  type: GeminiEventType.InvalidStream;
+  value: {
+    type:
+      | 'NO_FINISH_REASON'
+      | 'NO_RESPONSE_TEXT'
+      | 'MALFORMED_FUNCTION_CALL'
+      | 'UNEXPECTED_TOOL_CALL'
+      | 'MAX_TOKENS_EXCEEDED'
+      | 'SAFETY_BLOCKED'
+      | 'RECITATION_BLOCKED'
+      | 'OTHER_BLOCKED'
+      | 'THINKING_ONLY_RESPONSE';
+    message: string;
+  };
 };

 export type ServerGeminiModelInfoEvent = {
@@ -408,7 +421,13 @@ export class Turn {
      }

      if (e instanceof InvalidStreamError) {
-        yield { type: GeminiEventType.InvalidStream };
+        yield {
+          type: GeminiEventType.InvalidStream,
+          value: {
+            type: e.type,
+            message: e.message,
+          },
+        };
        return;
      }

@@ -413,6 +413,16 @@ export function renderOperationalGuidelines(
 - **Security First:** Always apply security best practices. Never introduce code that exposes, logs, or commits secrets, API keys, or other sensitive information.

 ## Tool Usage
+- **Tool Execution Response Rules:**
+  1. After receiving a \`functionResponse\`, you MUST ALWAYS execute one of the following two actions:
+     a) Call another tool to proceed with the task.
+     b) Provide a user-facing text response explaining the tool output, your analysis, and next steps.
+  2. You MUST NEVER return an empty response with no text and no tool calls.
+- **Post-Edit Response Rules:**
+  1. After an edit tool execution (e.g. ${formatToolName(EDIT_TOOL_NAME)}, ${formatToolName(WRITE_FILE_TOOL_NAME)}), you MUST ALWAYS generate a user-facing text response summarizing:
+     - What changes were made to the file.
+     - Your verification plan or next steps (e.g. running tests).
+  2. You MUST NEVER return an empty response with 0 text tokens after completing an edit.
 - **Parallelism & Sequencing:** Tools execute in parallel by default. Execute multiple independent tool calls in parallel when feasible (e.g., searching, reading files, independent shell commands, or editing *different* files). If a tool depends on the output or side-effects of a previous tool in the same turn (e.g., running a shell command that depends on the success of a previous command), you MUST set the \`wait_for_previous\` parameter to \`true\` on the dependent tool to ensure sequential execution.
 - **File Editing Collisions:** Do NOT make multiple calls to the ${formatToolName(EDIT_TOOL_NAME)} tool for the SAME file in a single turn. To make multiple edits to the same file, you MUST perform them sequentially across multiple conversational turns to prevent race conditions and ensure the file state is accurate before each edit.
 - **Command Execution:** Use the ${formatToolName(SHELL_TOOL_NAME)} tool for running shell commands, remembering the safety rule to explain modifying commands first.${toolUsageInteractive(
@@ -630,8 +630,8 @@ describe('Scheduler (Orchestrator)', () => {
        CoreToolCallStatus.Cancelled,
        'Operation cancelled by user',
      );
-      // finalizeCall is handled by the processing loop, not synchronously by cancelAll
-      // expect(mockStateManager.finalizeCall).toHaveBeenCalledWith('call-1');
+      // finalizeCall is called synchronously by cancelAll to ensure completedBatch is populated and isActive is updated immediately
+      expect(mockStateManager.finalizeCall).toHaveBeenCalledWith('call-1');
      expect(mockStateManager.cancelAllQueued).toHaveBeenCalledWith(
        'Operation cancelled by user',
      );
@@ -278,6 +278,7 @@ export class Scheduler {
          CoreToolCallStatus.Cancelled,
          'Operation cancelled by user',
        );
+        this.state.finalizeCall(activeCall.request.callId);
      }
    }

@@ -438,6 +439,14 @@ export class Scheduler {
   */
  private async _processNextItem(signal: AbortSignal): Promise<boolean> {
    if (signal.aborted || this.isCancelling) {
+      // Finalize active calls that are terminal
+      const activeCalls = this.state.allActiveCalls;
+      for (const call of activeCalls) {
+        if (this.isTerminal(call.status)) {
+          this.state.finalizeCall(call.request.callId);
+        }
+      }
+
      this.state.cancelAllQueued('Operation cancelled');
      return false;
    }
@@ -308,6 +308,125 @@ describe('ChatRecordingService', () => {
      )) as ConversationRecord;
      expect(conversation.sessionId).toBe('old-session-id');
    });
+
+    it('should fall back to the in-memory conversation when the file cannot be reloaded', async () => {
+      // Regression test for the `/compress` "Failed to load resumed session
+      // data from file" bug: when resuming with a filePath that cannot be
+      // loaded from disk, initialize must NOT throw. It should adopt the
+      // in-memory conversation it was handed and rewrite a clean file.
+      const chatsDir = path.join(testTempDir, 'chats');
+      fs.mkdirSync(chatsDir, { recursive: true });
+      const missingFile = path.join(chatsDir, 'missing-session.jsonl');
+      expect(fs.existsSync(missingFile)).toBe(false);
+
+      const inMemoryConversation = {
+        sessionId: 'resumed-session-id',
+        projectHash: 'resumed-project-hash',
+        startTime: new Date().toISOString(),
+        lastUpdated: new Date().toISOString(),
+        messages: [
+          {
+            id: 'msg-1',
+            type: 'user',
+            timestamp: new Date().toISOString(),
+            content: 'hello from memory',
+          },
+        ],
+      } as unknown as ConversationRecord;
+
+      await expect(
+        chatRecordingService.initialize({
+          filePath: missingFile,
+          conversation: inMemoryConversation,
+        }),
+      ).resolves.not.toThrow();
+
+      // The in-memory conversation is adopted.
+      expect(chatRecordingService.getConversation()?.sessionId).toBe(
+        'resumed-session-id',
+      );
+
+      // A clean, loadable file is rewritten from the in-memory copy so future
+      // loads and appends succeed.
+      const reloaded = (await loadConversationRecord(
+        missingFile,
+      )) as ConversationRecord;
+      expect(reloaded).not.toBeNull();
+      expect(reloaded.sessionId).toBe('resumed-session-id');
+      expect(reloaded.projectHash).toBe('resumed-project-hash');
+      expect(reloaded.messages).toHaveLength(1);
+    });
+
+    it('should preserve an unreadable session file instead of destroying it', async () => {
+      // The reload may have failed only transiently, so the original bytes
+      // must survive the recovery rewrite.
+      const chatsDir = path.join(testTempDir, 'chats');
+      fs.mkdirSync(chatsDir, { recursive: true });
+      const sessionFile = path.join(chatsDir, 'unreadable.jsonl');
+
+      // No usable metadata line => loadConversationRecord() returns null.
+      const originalBytes = '{"not":"a valid metadata line"}\n';
+      fs.writeFileSync(sessionFile, originalBytes);
+
+      await chatRecordingService.initialize({
+        filePath: sessionFile,
+        conversation: {
+          sessionId: 'recovered-session-id',
+          projectHash: 'recovered-project-hash',
+          startTime: new Date().toISOString(),
+          lastUpdated: new Date().toISOString(),
+          messages: [],
+        } as unknown as ConversationRecord,
+      });
+
+      // The rewritten file is loadable again...
+      const reloaded = (await loadConversationRecord(
+        sessionFile,
+      )) as ConversationRecord;
+      expect(reloaded.sessionId).toBe('recovered-session-id');
+
+      // ...and the original bytes were kept alongside it.
+      const preserved = fs
+        .readdirSync(chatsDir)
+        .filter((f) => f.startsWith('unreadable.jsonl.unreadable-'));
+      expect(preserved).toHaveLength(1);
+      expect(fs.readFileSync(path.join(chatsDir, preserved[0]), 'utf-8')).toBe(
+        originalBytes,
+      );
+    });
+
+    it('should not leave a temp file behind when the rewrite fails', async () => {
+      const chatsDir = path.join(testTempDir, 'chats');
+      fs.mkdirSync(chatsDir, { recursive: true });
+      const sessionFile = path.join(chatsDir, 'rewrite-fails.jsonl');
+
+      // Fail the rename that publishes the temp file, leaving it orphaned.
+      const realRename = fs.renameSync;
+      vi.spyOn(fs, 'renameSync').mockImplementation((from, to) => {
+        if (String(from).includes('.tmp-')) {
+          throw new Error('simulated rename failure');
+        }
+        return realRename(from, to);
+      });
+
+      await expect(
+        chatRecordingService.initialize({
+          filePath: sessionFile,
+          conversation: {
+            sessionId: 'temp-cleanup-session',
+            projectHash: 'temp-cleanup-hash',
+            startTime: new Date().toISOString(),
+            lastUpdated: new Date().toISOString(),
+            messages: [],
+          } as unknown as ConversationRecord,
+        }),
+      ).rejects.toThrow('simulated rename failure');
+
+      const leftovers = fs
+        .readdirSync(chatsDir)
+        .filter((f) => f.includes('.tmp-'));
+      expect(leftovers).toEqual([]);
+    });
  });

  describe('recordMessage', () => {
@@ -462,7 +462,16 @@ export class ChatRecordingService {
          // Update the session ID in the existing file
          this.updateMetadata({ sessionId: this.sessionId });
        } else {
-          throw new Error('Failed to load resumed session data from file');
+          // The file could not be reloaded (missing, corrupt metadata, or an
+          // I/O error). Fall back to the in-memory conversation we were handed
+          // rather than failing the caller, and rewrite a clean file from it.
+          debugLogger.warn(
+            'Failed to reload resumed session data from file; falling back ' +
+              'to the in-memory conversation.',
+          );
+          this.cachedConversation = resumedSessionData.conversation;
+          this.projectHash = this.cachedConversation.projectHash;
+          this.rewriteConversationFile(this.cachedConversation);
        }
      } else {
        // Create new session
@@ -563,6 +572,73 @@ export class ChatRecordingService {
    }
  }

+  /**
+   * Rewrites the session file from an in-memory record. Any existing
+   * (unreadable) file is preserved alongside rather than destroyed, and the
+   * new file is written atomically (temp file + rename).
+   */
+  private rewriteConversationFile(conversation: ConversationRecord): void {
+    if (!this.conversationFile) return;
+
+    // Normalize legacy `.json` paths to the `.jsonl` format we write.
+    if (this.conversationFile.endsWith('.json')) {
+      this.conversationFile = this.conversationFile + 'l';
+    }
+
+    const { messages, memoryScratchpad, ...metadata } = conversation;
+    const lines: string[] = [JSON.stringify(metadata)];
+    for (const msg of messages) {
+      lines.push(JSON.stringify(msg));
+    }
+    if (memoryScratchpad) {
+      lines.push(JSON.stringify({ $set: { memoryScratchpad } }));
+    }
+    const content = lines.join('\n') + '\n';
+
+    try {
+      fs.mkdirSync(path.dirname(this.conversationFile), { recursive: true });
+
+      // The existing file was unreadable, but it may have been only
+      // transiently so (a lock or I/O blip) rather than truly corrupt. Keep
+      // its bytes rather than destroying them.
+      if (fs.existsSync(this.conversationFile)) {
+        const backup = `${this.conversationFile}.unreadable-${Date.now()}`;
+        try {
+          fs.renameSync(this.conversationFile, backup);
+          debugLogger.warn(
+            `Preserved the unreadable session file at ${backup}.`,
+          );
+        } catch (backupError) {
+          debugLogger.error(
+            'Failed to preserve the unreadable session file.',
+            backupError,
+          );
+        }
+      }
+
+      const tempFile = `${this.conversationFile}.tmp-${process.pid}`;
+      try {
+        fs.writeFileSync(tempFile, content);
+        fs.renameSync(tempFile, this.conversationFile);
+      } catch (error) {
+        // The rename did not complete, so the temp file would be left behind.
+        try {
+          fs.unlinkSync(tempFile);
+        } catch {
+          // Ignore cleanup errors so the original failure still surfaces.
+        }
+        throw error;
+      }
+    } catch (error) {
+      if (isNodeError(error) && error.code === 'ENOSPC') {
+        this.conversationFile = null;
+        debugLogger.warn(ENOSPC_WARNING_MESSAGE);
+      } else {
+        throw error;
+      }
+    }
+  }
+
  private updateMetadata(updates: Partial<ConversationRecord>): void {
    if (!this.cachedConversation) return;
    Object.assign(this.cachedConversation, updates);
@@ -37,6 +37,9 @@ export interface ModelConfigKey {
  // Indicates whether this request originates from the primary interactive chat model.
  // Enables the default fallback configuration to `chat-base` when unknown.
  isChatModel?: boolean;
+
+  // The last stream error that triggered this retry attempt, if any.
+  lastStreamError?: unknown;
 }

 export interface ModelConfig {
@@ -173,6 +173,7 @@ describe('UiTelemetryService', () => {
          totalRequests: 1,
          totalErrors: 0,
          totalLatencyMs: 500,
+          errorsByType: {},
        },
        tokens: {
          input: 5,
@@ -229,6 +230,7 @@ describe('UiTelemetryService', () => {
          totalRequests: 2,
          totalErrors: 0,
          totalLatencyMs: 1100,
+          errorsByType: {},
        },
        tokens: {
          input: 10,
@@ -305,6 +307,9 @@ describe('UiTelemetryService', () => {
          totalRequests: 1,
          totalErrors: 1,
          totalLatencyMs: 300,
+          errorsByType: {
+            UNKNOWN: 1,
+          },
        },
        tokens: {
          input: 0,
@@ -319,6 +324,42 @@ describe('UiTelemetryService', () => {
      });
    });

+    it('should track errors by error_type distinctly', () => {
+      const event1 = {
+        'event.name': EVENT_API_ERROR,
+        model: 'gemini-2.5-pro',
+        duration_ms: 200,
+        error: 'Empty response',
+        error_type: 'NO_RESPONSE_TEXT',
+      } as unknown as ApiErrorEvent & { 'event.name': typeof EVENT_API_ERROR };
+
+      const event2 = {
+        'event.name': EVENT_API_ERROR,
+        model: 'gemini-2.5-pro',
+        duration_ms: 250,
+        error: 'Malformed JSON',
+        error_type: 'MALFORMED_FUNCTION_CALL',
+      } as unknown as ApiErrorEvent & { 'event.name': typeof EVENT_API_ERROR };
+
+      const event3 = {
+        'event.name': EVENT_API_ERROR,
+        model: 'gemini-2.5-pro',
+        duration_ms: 100,
+        error: 'Another empty response',
+        error_type: 'NO_RESPONSE_TEXT',
+      } as unknown as ApiErrorEvent & { 'event.name': typeof EVENT_API_ERROR };
+
+      service.addEvent(event1);
+      service.addEvent(event2);
+      service.addEvent(event3);
+
+      const metrics = service.getMetrics();
+      expect(metrics.models['gemini-2.5-pro'].api.errorsByType).toEqual({
+        NO_RESPONSE_TEXT: 2,
+        MALFORMED_FUNCTION_CALL: 1,
+      });
+    });
+
    it('should aggregate ApiErrorEvents and ApiResponseEvents', () => {
      const responseEvent = {
        'event.name': EVENT_API_RESPONSE,
@@ -351,6 +392,9 @@ describe('UiTelemetryService', () => {
          totalRequests: 2,
          totalErrors: 1,
          totalLatencyMs: 800,
+          errorsByType: {
+            UNKNOWN: 1,
+          },
        },
        tokens: {
          input: 5,
@@ -56,6 +56,7 @@ export interface ModelMetrics {
    totalRequests: number;
    totalErrors: number;
    totalLatencyMs: number;
+    errorsByType?: Record<string, number>;
  };
  tokens: {
    input: number;
@@ -110,6 +111,7 @@ const createInitialModelMetrics = (): ModelMetrics => ({
    totalRequests: 0,
    totalErrors: 0,
    totalLatencyMs: 0,
+    errorsByType: {},
  },
  tokens: {
    input: 0,
@@ -170,6 +172,23 @@ export class UiTelemetryService extends EventEmitter {
    });
  }

+  recordSemanticValidationError(model: string, errorType: string): void {
+    const modelMetrics = this.getOrCreateModelMetrics(model);
+    modelMetrics.api.totalErrors++;
+
+    if (!modelMetrics.api.errorsByType) {
+      modelMetrics.api.errorsByType = {};
+    }
+    const type = errorType || 'INVALID_STREAM';
+    modelMetrics.api.errorsByType[type] =
+      (modelMetrics.api.errorsByType[type] || 0) + 1;
+
+    this.emit('update', {
+      metrics: this.#metrics,
+      lastPromptTokenCount: this.#lastPromptTokenCount,
+    });
+  }
+
  getMetrics(): SessionMetrics {
    return this.#metrics;
  }
@@ -326,6 +345,13 @@ export class UiTelemetryService extends EventEmitter {
    modelMetrics.api.totalErrors++;
    modelMetrics.api.totalLatencyMs += event.duration_ms;

+    if (!modelMetrics.api.errorsByType) {
+      modelMetrics.api.errorsByType = {};
+    }
+    const errorType = event.error_type || 'UNKNOWN';
+    modelMetrics.api.errorsByType[errorType] =
+      (modelMetrics.api.errorsByType[errorType] || 0) + 1;
+
    if (event.role) {
      if (!modelMetrics.roles[event.role]) {
        modelMetrics.roles[event.role] = createInitialRoleMetrics();
@@ -10,3 +10,24 @@ export const REFERENCE_CONTENT_END = '--- End of content ---';
 export const DEFAULT_MAX_LINES_TEXT_FILE = 2000;
 export const MAX_LINE_LENGTH_TEXT_FILE = 2000;
 export const MAX_FILE_SIZE_MB = 20;
+
+export const EMPTY_RESPONSE_COMPRESS_SUGGESTION =
+  'The model returned an empty text response. If your context window is near capacity, try using /compress.';
+
+export const THINKING_ONLY_COMPRESS_SUGGESTION =
+  'The model returned reasoning thoughts but no final response text. If your context window is near capacity, try using /compress.';
+
+export const MAX_TOKENS_EXCEEDED_SUGGESTION =
+  'Model response was truncated because it exceeded the token limit. Try using /compress to free up context space.';
+
+export const SAFETY_BLOCKED_MESSAGE =
+  'The model response was blocked due to safety settings.';
+
+export const RECITATION_BLOCKED_MESSAGE =
+  'The model response was blocked due to recitation/copyright filters.';
+
+export const OTHER_BLOCKED_MESSAGE =
+  'The model response was blocked due to other policy settings.';
+
+export const TRUE_EMPTY_RESPONSE_MESSAGE =
+  'The model returned an empty response with no text or thoughts. This may be a transient API issue; please try again.';
@@ -107,6 +107,63 @@ describe('classifyGoogleError', () => {
    expect((result as RetryableQuotaError).retryDelayMs).toBe(9000);
  });

+  it('should return TerminalQuotaError for MODEL_CAPACITY_EXHAUSTED when no retry delay is specified', () => {
+    const apiError: GoogleApiError = {
+      code: 429,
+      message:
+        'No capacity available for model gemini-3.1-pro-preview on the server',
+      details: [
+        {
+          '@type': 'type.googleapis.com/google.rpc.ErrorInfo',
+          reason: 'MODEL_CAPACITY_EXHAUSTED',
+          domain: 'cloudcode-pa.googleapis.com',
+          metadata: { model: 'gemini-3.1-pro-preview' },
+        },
+      ],
+    };
+    vi.spyOn(errorParser, 'parseGoogleApiError').mockReturnValue(apiError);
+    const result = classifyGoogleError(new Error());
+    expect(result).toBeInstanceOf(TerminalQuotaError);
+  });
+
+  it('should return TerminalQuotaError for MODEL_CAPACITY_EXHAUSTED even when the domain is not a Cloud Code domain (domain-agnostic)', () => {
+    const apiError: GoogleApiError = {
+      code: 429,
+      message:
+        'No capacity available for model gemini-3.1-pro-preview on the server',
+      details: [
+        {
+          '@type': 'type.googleapis.com/google.rpc.ErrorInfo',
+          reason: 'MODEL_CAPACITY_EXHAUSTED',
+          domain: 'other.googleapis.com',
+          metadata: { model: 'gemini-3.1-pro-preview' },
+        },
+      ],
+    };
+    vi.spyOn(errorParser, 'parseGoogleApiError').mockReturnValue(apiError);
+    const result = classifyGoogleError(new Error());
+    expect(result).toBeInstanceOf(TerminalQuotaError);
+  });
+
+  it('should return TerminalQuotaError for MODEL_CAPACITY_EXCEEDED when no retry delay is specified', () => {
+    const apiError: GoogleApiError = {
+      code: 429,
+      message:
+        'No capacity available for model gemini-3.1-pro-preview on the server',
+      details: [
+        {
+          '@type': 'type.googleapis.com/google.rpc.ErrorInfo',
+          reason: 'MODEL_CAPACITY_EXCEEDED',
+          domain: 'cloudcode-pa.googleapis.com',
+          metadata: { model: 'gemini-3.1-pro-preview' },
+        },
+      ],
+    };
+    vi.spyOn(errorParser, 'parseGoogleApiError').mockReturnValue(apiError);
+    const result = classifyGoogleError(new Error());
+    expect(result).toBeInstanceOf(TerminalQuotaError);
+  });
+
  it('should return original error if code is not 429, 499 or 503', () => {
    const apiError: GoogleApiError = {
      code: 500,
@@ -330,6 +330,23 @@ export function classifyGoogleError(error: unknown): unknown {
      );
    }

+    if (
+      errorInfo.reason === 'MODEL_CAPACITY_EXHAUSTED' ||
+      errorInfo.reason === 'MODEL_CAPACITY_EXCEEDED'
+    ) {
+      // If no server backoff delay is specified, treat capacity exhaustion as a terminal error
+      // to trigger immediate model fallback without retrying on the same exhausted model.
+      if (delaySeconds === undefined) {
+        return new TerminalQuotaError(
+          googleApiError.message,
+          googleApiError,
+          delaySeconds,
+          errorInfo.reason,
+        );
+      }
+      // Otherwise, fall through to RetryableQuotaError to honor the server's requested delay.
+    }
+
    // New Cloud Code API quota handling
    if (errorInfo.domain) {
      if (isCloudCodeDomain(errorInfo.domain)) {
@@ -0,0 +1,167 @@
+/**
+ * @license
+ * Copyright 2026 Google LLC
+ * SPDX-License-Identifier: Apache-2.0
+ */
+
+import { describe, it, expect } from 'vitest';
+import { isFunctionResponse, isFunctionCall } from './messageInspectors.js';
+
+describe('messageInspectors', () => {
+  describe('isFunctionResponse', () => {
+    it('should return false if content role is not user', () => {
+      const content = {
+        role: 'model',
+        parts: [
+          {
+            functionResponse: {
+              name: 'test_tool',
+              response: { success: true },
+            },
+          },
+        ],
+      };
+      expect(isFunctionResponse(content)).toBe(false);
+    });
+
+    it('should return false if content has no parts', () => {
+      const content = {
+        role: 'user',
+      };
+      expect(isFunctionResponse(content)).toBe(false);
+    });
+
+    it('should return false if parts are empty', () => {
+      const content = {
+        role: 'user',
+        parts: [],
+      };
+      expect(isFunctionResponse(content)).toBe(false);
+    });
+
+    it('should return false if none of the parts is a functionResponse', () => {
+      const content = {
+        role: 'user',
+        parts: [
+          {
+            text: 'Hello world',
+          },
+          {
+            fileData: {
+              mimeType: 'image/png',
+              fileUri: 'https://example.com/image.png',
+            },
+          },
+        ],
+      };
+      expect(isFunctionResponse(content)).toBe(false);
+    });
+
+    it('should return true if all parts are functionResponses', () => {
+      const content = {
+        role: 'user',
+        parts: [
+          {
+            functionResponse: {
+              name: 'test_tool_1',
+              response: { success: true },
+            },
+          },
+          {
+            functionResponse: {
+              name: 'test_tool_2',
+              response: { value: 42 },
+            },
+          },
+        ],
+      };
+      expect(isFunctionResponse(content)).toBe(true);
+    });
+
+    it('should return true if content is a mixed multimodal tool response containing functionResponse and sibling parts', () => {
+      const content = {
+        role: 'user',
+        parts: [
+          {
+            functionResponse: {
+              name: 'test_tool',
+              response: { success: true },
+            },
+          },
+          {
+            fileData: {
+              mimeType: 'image/png',
+              fileUri: 'https://example.com/image.png',
+            },
+          },
+        ],
+      };
+      expect(isFunctionResponse(content)).toBe(true);
+    });
+  });
+
+  describe('isFunctionCall', () => {
+    it('should return false if content role is not model', () => {
+      const content = {
+        role: 'user',
+        parts: [
+          {
+            functionCall: {
+              name: 'test_tool',
+              args: {},
+            },
+          },
+        ],
+      };
+      expect(isFunctionCall(content)).toBe(false);
+    });
+
+    it('should return false if content has no parts', () => {
+      const content = {
+        role: 'model',
+      };
+      expect(isFunctionCall(content)).toBe(false);
+    });
+
+    it('should return false if parts are empty', () => {
+      const content = {
+        role: 'model',
+        parts: [],
+      };
+      expect(isFunctionCall(content)).toBe(false);
+    });
+
+    it('should return false if none of the parts is a functionCall', () => {
+      const content = {
+        role: 'model',
+        parts: [
+          {
+            text: 'I am thinking...',
+          },
+        ],
+      };
+      expect(isFunctionCall(content)).toBe(false);
+    });
+
+    it('should return true if all parts are functionCalls', () => {
+      const content = {
+        role: 'model',
+        parts: [
+          {
+            functionCall: {
+              name: 'test_tool_1',
+              args: {},
+            },
+          },
+          {
+            functionCall: {
+              name: 'test_tool_2',
+              args: { query: 'foo' },
+            },
+          },
+        ],
+      };
+      expect(isFunctionCall(content)).toBe(true);
+    });
+  });
+});
@@ -10,7 +10,7 @@ export function isFunctionResponse(content: Content): boolean {
  return (
    content.role === 'user' &&
    !!content.parts &&
-    content.parts.every((part) => !!part.functionResponse)
+    content.parts.some((part) => !!part.functionResponse)
  );
 }

@@ -18,6 +18,7 @@ export function isFunctionCall(content: Content): boolean {
  return (
    content.role === 'model' &&
    !!content.parts &&
+    content.parts.length > 0 &&
    content.parts.every((part) => !!part.functionCall)
  );
 }
@@ -1,6 +1,6 @@
 {
  "name": "@google/gemini-cli-devtools",
-  "version": "0.54.0-nightly.20260728.gbef611950",
+  "version": "0.54.3",
  "license": "Apache-2.0",
  "type": "module",
  "main": "dist/src/index.js",
@@ -1,6 +1,6 @@
 {
  "name": "@google/gemini-cli-sdk",
-  "version": "0.54.0-nightly.20260728.gbef611950",
+  "version": "0.54.3",
  "description": "Gemini CLI SDK",
  "license": "Apache-2.0",
  "repository": {
@@ -1,6 +1,6 @@
 {
  "name": "@google/gemini-cli-test-utils",
-  "version": "0.54.0-nightly.20260728.gbef611950",
+  "version": "0.54.3",
  "private": true,
  "main": "src/index.ts",
  "license": "Apache-2.0",
@@ -2,7 +2,7 @@
  "name": "gemini-cli-vscode-ide-companion",
  "displayName": "Gemini CLI Companion",
  "description": "Enable Gemini CLI with direct access to your IDE workspace.",
-  "version": "0.54.0-nightly.20260728.gbef611950",
+  "version": "0.54.3",
  "publisher": "google",
  "icon": "assets/icon.png",
  "repository": {
Author	SHA1	Message	Date
gemini-cli-robot	fe45f09636	chore(release): v0.54.3	2026-08-07 02:49:54 +00:00
David Pierce	10944dcc4a	Fix/revert version bump (#28715 )	2026-08-06 18:33:11 -04:00
David Pierce	2f3285871c	chore: bump version to 0.54.2 (#28712 )	2026-08-06 14:29:01 -04:00
gemini-cli-robot	ae5f5edb58	chore(release): v0.54.1	2026-08-06 16:13:54 +00:00
gemini-cli-robot	76a97cac0e	fix(patch): cherry-pick `56f9688` to release/v0.54.0-pr-28700 to patch version v0.54.0 and create version 0.54.1 (#28710 ) Co-authored-by: Adam Weidman <65992621+adamfweidman@users.noreply.github.com> Co-authored-by: David Pierce <davidapierce@google.com> Co-authored-by: Mpider-San <sarbojitrana47c@gmail.com>	2026-08-06 14:54:28 +00:00
gemini-cli-robot	a74b483d14	chore(release): v0.54.0	2026-08-06 01:28:51 +00:00
gemini-cli-robot	a81db2768f	chore(release): v0.54.0-preview.1	2026-07-31 21:33:01 +00:00
gemini-cli-robot	d3c51f158c	fix(patch): cherry-pick `f47d6c6` to release/v0.54.0-preview.0-pr-28566 to patch version v0.54.0-preview.0 and create version 0.54.0-preview.1 (#28609 ) Co-authored-by: David Pierce <davidapierce@google.com> Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com> Co-authored-by: luisfelipe-alt <luisfelipe@google.com>	2026-07-31 20:39:47 +00:00
gemini-cli-robot	5f9c117de2	chore(release): v0.54.0-preview.0	2026-07-28 21:28:13 +00:00