chore: remove unnecessary empty ignore files and plan.md

fix(ui): always show context window warning on terminal overflow
This removes the early return in the `handleContextWindowWillOverflowEvent` hook. If the context window truly overflows and the message is blocked, we must tell the user why, regardless of their proactive warning settings. This prevents a silent block where the CLI appears to just swallow the user's input.
2026-07-23 08:10:57 -07:00 · 2026-04-10 13:42:51 -04:00 · 2026-04-10 13:32:18 -04:00 · 2026-03-24 23:15:54 -07:00 · 2026-03-24 17:20:13 -07:00 · 2026-03-24 15:53:55 -07:00
22 changed files with 621 additions and 609 deletions
@@ -46,38 +46,40 @@ they appear in the UI.

 ### UI

-| UI Label                             | Setting                                | Description                                                                                                                                                       | Default  |
-| ------------------------------------ | -------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------- | -------- |
-| Auto Theme Switching                 | `ui.autoThemeSwitching`                | Automatically switch between default light and dark themes based on terminal background color.                                                                    | `true`   |
-| Terminal Background Polling Interval | `ui.terminalBackgroundPollingInterval` | Interval in seconds to poll the terminal background color.                                                                                                        | `60`     |
-| Hide Window Title                    | `ui.hideWindowTitle`                   | Hide the window title bar                                                                                                                                         | `false`  |
-| Inline Thinking                      | `ui.inlineThinkingMode`                | Display model thinking inline: off or full.                                                                                                                       | `"off"`  |
-| Show Thoughts in Title               | `ui.showStatusInTitle`                 | Show Gemini CLI model thoughts in the terminal window title during the working phase                                                                              | `false`  |
-| Dynamic Window Title                 | `ui.dynamicWindowTitle`                | Update the terminal window title with current status icons (Ready: ◇, Action Required: ✋, Working: ✦)                                                            | `true`   |
-| Show Home Directory Warning          | `ui.showHomeDirectoryWarning`          | Show a warning when running Gemini CLI in the home directory.                                                                                                     | `true`   |
-| Show Compatibility Warnings          | `ui.showCompatibilityWarnings`         | Show warnings about terminal or OS compatibility issues.                                                                                                          | `true`   |
-| Hide Tips                            | `ui.hideTips`                          | Hide helpful tips in the UI                                                                                                                                       | `false`  |
-| Escape Pasted @ Symbols              | `ui.escapePastedAtSymbols`             | When enabled, @ symbols in pasted text are escaped to prevent unintended @path expansion.                                                                         | `false`  |
-| Show Shortcuts Hint                  | `ui.showShortcutsHint`                 | Show the "? for shortcuts" hint above the input.                                                                                                                  | `true`   |
-| Hide Banner                          | `ui.hideBanner`                        | Hide the application banner                                                                                                                                       | `false`  |
-| Hide Context Summary                 | `ui.hideContextSummary`                | Hide the context summary (GEMINI.md, MCP servers) above the input.                                                                                                | `false`  |
-| Hide CWD                             | `ui.footer.hideCWD`                    | Hide the current working directory in the footer.                                                                                                                 | `false`  |
-| Hide Sandbox Status                  | `ui.footer.hideSandboxStatus`          | Hide the sandbox status indicator in the footer.                                                                                                                  | `false`  |
-| Hide Model Info                      | `ui.footer.hideModelInfo`              | Hide the model name and context usage in the footer.                                                                                                              | `false`  |
-| Hide Context Window Percentage       | `ui.footer.hideContextPercentage`      | Hides the context window usage percentage.                                                                                                                        | `true`   |
-| Hide Footer                          | `ui.hideFooter`                        | Hide the footer from the UI                                                                                                                                       | `false`  |
-| Show Memory Usage                    | `ui.showMemoryUsage`                   | Display memory usage information in the UI                                                                                                                        | `false`  |
-| Show Line Numbers                    | `ui.showLineNumbers`                   | Show line numbers in the chat.                                                                                                                                    | `true`   |
-| Show Citations                       | `ui.showCitations`                     | Show citations for generated text in the chat.                                                                                                                    | `false`  |
-| Show Model Info In Chat              | `ui.showModelInfoInChat`               | Show the model name in the chat for each model turn.                                                                                                              | `false`  |
-| Show User Identity                   | `ui.showUserIdentity`                  | Show the signed-in user's identity (e.g. email) in the UI.                                                                                                        | `true`   |
-| Use Alternate Screen Buffer          | `ui.useAlternateBuffer`                | Use an alternate screen buffer for the UI, preserving shell history.                                                                                              | `false`  |
-| Use Background Color                 | `ui.useBackgroundColor`                | Whether to use background colors in the UI.                                                                                                                       | `true`   |
-| Incremental Rendering                | `ui.incrementalRendering`              | Enable incremental rendering for the UI. This option will reduce flickering but may cause rendering artifacts. Only supported when useAlternateBuffer is enabled. | `true`   |
-| Show Spinner                         | `ui.showSpinner`                       | Show the spinner during operations.                                                                                                                               | `true`   |
-| Loading Phrases                      | `ui.loadingPhrases`                    | What to show while the model is working: tips, witty comments, both, or nothing.                                                                                  | `"tips"` |
-| Error Verbosity                      | `ui.errorVerbosity`                    | Controls whether recoverable errors are hidden (low) or fully shown (full).                                                                                       | `"low"`  |
-| Screen Reader Mode                   | `ui.accessibility.screenReader`        | Render output in plain-text to be more screen reader accessible                                                                                                   | `false`  |
+| UI Label                             | Setting                                | Description                                                                                                                                                                | Default  |
+| ------------------------------------ | -------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | -------- |
+| Auto Theme Switching                 | `ui.autoThemeSwitching`                | Automatically switch between default light and dark themes based on terminal background color.                                                                             | `true`   |
+| Terminal Background Polling Interval | `ui.terminalBackgroundPollingInterval` | Interval in seconds to poll the terminal background color.                                                                                                                 | `60`     |
+| Hide Window Title                    | `ui.hideWindowTitle`                   | Hide the window title bar                                                                                                                                                  | `false`  |
+| Inline Thinking                      | `ui.inlineThinkingMode`                | Display model thinking inline: off or full.                                                                                                                                | `"off"`  |
+| Show Thoughts in Title               | `ui.showStatusInTitle`                 | Show Gemini CLI model thoughts in the terminal window title during the working phase                                                                                       | `false`  |
+| Dynamic Window Title                 | `ui.dynamicWindowTitle`                | Update the terminal window title with current status icons (Ready: ◇, Action Required: ✋, Working: ✦)                                                                     | `true`   |
+| Show Home Directory Warning          | `ui.showHomeDirectoryWarning`          | Show a warning when running Gemini CLI in the home directory.                                                                                                              | `true`   |
+| Show Compatibility Warnings          | `ui.showCompatibilityWarnings`         | Show warnings about terminal or OS compatibility issues.                                                                                                                   | `true`   |
+| Hide Tips                            | `ui.hideTips`                          | Hide helpful tips in the UI                                                                                                                                                | `false`  |
+| Escape Pasted @ Symbols              | `ui.escapePastedAtSymbols`             | When enabled, @ symbols in pasted text are escaped to prevent unintended @path expansion.                                                                                  | `false`  |
+| Show Shortcuts Hint                  | `ui.showShortcutsHint`                 | Show the "? for shortcuts" hint above the input.                                                                                                                           | `true`   |
+| Hide Banner                          | `ui.hideBanner`                        | Hide the application banner                                                                                                                                                | `false`  |
+| Hide Context Summary                 | `ui.hideContextSummary`                | Hide the context summary (GEMINI.md, MCP servers) above the input.                                                                                                         | `true`   |
+| Show Context Window Warning          | `ui.showContextWindowWarning`          | Show a warning message when the context window limit is nearly reached. If disabled, the CLI will attempt to automatically compress the history when the limit is reached. | `false`  |
+| Show Context Compression Messages    | `ui.showContextCompression`            | Show a message in the chat history when it is compressed.                                                                                                                  | `false`  |
+| Hide CWD                             | `ui.footer.hideCWD`                    | Hide the current working directory in the footer.                                                                                                                          | `false`  |
+| Hide Sandbox Status                  | `ui.footer.hideSandboxStatus`          | Hide the sandbox status indicator in the footer.                                                                                                                           | `false`  |
+| Hide Model Info                      | `ui.footer.hideModelInfo`              | Hide the model name and context usage in the footer.                                                                                                                       | `false`  |
+| Hide Context Window Percentage       | `ui.footer.hideContextPercentage`      | Hides the context window usage percentage.                                                                                                                                 | `true`   |
+| Hide Footer                          | `ui.hideFooter`                        | Hide the footer from the UI                                                                                                                                                | `false`  |
+| Show Memory Usage                    | `ui.showMemoryUsage`                   | Display memory usage information in the UI                                                                                                                                 | `false`  |
+| Show Line Numbers                    | `ui.showLineNumbers`                   | Show line numbers in the chat.                                                                                                                                             | `true`   |
+| Show Citations                       | `ui.showCitations`                     | Show citations for generated text in the chat.                                                                                                                             | `false`  |
+| Show Model Info In Chat              | `ui.showModelInfoInChat`               | Show the model name in the chat for each model turn.                                                                                                                       | `false`  |
+| Show User Identity                   | `ui.showUserIdentity`                  | Show the signed-in user's identity (e.g. email) in the UI.                                                                                                                 | `true`   |
+| Use Alternate Screen Buffer          | `ui.useAlternateBuffer`                | Use an alternate screen buffer for the UI, preserving shell history.                                                                                                       | `false`  |
+| Use Background Color                 | `ui.useBackgroundColor`                | Whether to use background colors in the UI.                                                                                                                                | `true`   |
+| Incremental Rendering                | `ui.incrementalRendering`              | Enable incremental rendering for the UI. This option will reduce flickering but may cause rendering artifacts. Only supported when useAlternateBuffer is enabled.          | `true`   |
+| Show Spinner                         | `ui.showSpinner`                       | Show the spinner during operations.                                                                                                                                        | `true`   |
+| Loading Phrases                      | `ui.loadingPhrases`                    | What to show while the model is working: tips, witty comments, both, or nothing.                                                                                           | `"tips"` |
+| Error Verbosity                      | `ui.errorVerbosity`                    | Controls whether recoverable errors are hidden (low) or fully shown (full).                                                                                                | `"low"`  |
+| Screen Reader Mode                   | `ui.accessibility.screenReader`        | Render output in plain-text to be more screen reader accessible                                                                                                            | `false`  |

 ### IDE

@@ -263,6 +263,16 @@ their corresponding top-level category object in your `settings.json` file.
 - **`ui.hideContextSummary`** (boolean):
  - **Description:** Hide the context summary (GEMINI.md, MCP servers) above the
    input.
+  - **Default:** `true`
+
+- **`ui.showContextWindowWarning`** (boolean):
+  - **Description:** Show a warning message when the context window limit is
+    nearly reached. If disabled, the CLI will attempt to automatically compress
+    the history when the limit is reached.
+  - **Default:** `false`
+
+- **`ui.showContextCompression`** (boolean):
+  - **Description:** Show a message in the chat history when it is compressed.
  - **Default:** `false`

 - **`ui.footer.items`** (array):
@@ -48,7 +48,8 @@ describe('Interactive Mode', () => {
      true,
    );

-    await run.expectText('Chat history compressed', 5000);
+    await run.expectText('Context compressed', 5000);
+    await run.expectText('Adjust threshold', 5000);
  });

  // TODO: Context compression is broken and doesn't include the system
@@ -2103,6 +2103,52 @@ describe('loadCliConfig compressionThreshold', () => {
  });
 });

+describe('loadCliConfig showContextWindowWarning', () => {
+  beforeEach(() => {
+    vi.resetAllMocks();
+    vi.mocked(os.homedir).mockReturnValue('/mock/home/user');
+    vi.stubEnv('GEMINI_API_KEY', 'test-api-key');
+    vi.spyOn(ExtensionManager.prototype, 'getExtensions').mockReturnValue([]);
+  });
+
+  afterEach(() => {
+    vi.unstubAllEnvs();
+    vi.restoreAllMocks();
+  });
+
+  it('should pass showContextWindowWarning from settings to config (true)', async () => {
+    process.argv = ['node', 'script.js'];
+    const argv = await parseArguments(createTestMergedSettings());
+    const settings = createTestMergedSettings({
+      ui: {
+        showContextWindowWarning: true,
+      },
+    });
+    const config = await loadCliConfig(settings, 'test-session', argv);
+    expect(config.getShowContextWindowWarning()).toBe(true);
+  });
+
+  it('should pass showContextWindowWarning from settings to config (false)', async () => {
+    process.argv = ['node', 'script.js'];
+    const argv = await parseArguments(createTestMergedSettings());
+    const settings = createTestMergedSettings({
+      ui: {
+        showContextWindowWarning: false,
+      },
+    });
+    const config = await loadCliConfig(settings, 'test-session', argv);
+    expect(config.getShowContextWindowWarning()).toBe(false);
+  });
+
+  it('should default to false if not in settings', async () => {
+    process.argv = ['node', 'script.js'];
+    const argv = await parseArguments(createTestMergedSettings());
+    const settings = createTestMergedSettings();
+    const config = await loadCliConfig(settings, 'test-session', argv);
+    expect(config.getShowContextWindowWarning()).toBe(false);
+  });
+});
+
 describe('loadCliConfig useRipgrep', () => {
  beforeEach(() => {
    vi.resetAllMocks();
@@ -955,6 +955,8 @@ export async function loadCliConfig(
    bugCommand: settings.advanced?.bugCommand,
    model: resolvedModel,
    maxSessionTurns: settings.model?.maxSessionTurns,
+    showContextWindowWarning: settings.ui?.showContextWindowWarning,
+    showContextCompression: settings.ui?.showContextCompression,

    listExtensions: argv.listExtensions || false,
    listSessions: argv.listSessions || false,
@@ -575,11 +575,31 @@ const SETTINGS_SCHEMA = {
        label: 'Hide Context Summary',
        category: 'UI',
        requiresRestart: false,
-        default: false,
+        default: true,
        description:
          'Hide the context summary (GEMINI.md, MCP servers) above the input.',
        showInDialog: true,
      },
+      showContextWindowWarning: {
+        type: 'boolean',
+        label: 'Show Context Window Warning',
+        category: 'UI',
+        requiresRestart: false,
+        default: false,
+        description:
+          'Show a warning message when the context window limit is nearly reached. If disabled, the CLI will attempt to automatically compress the history when the limit is reached.',
+        showInDialog: true,
+      },
+      showContextCompression: {
+        type: 'boolean',
+        label: 'Show Context Compression Messages',
+        category: 'UI',
+        requiresRestart: false,
+        default: false,
+        description:
+          'Show a message in the chat history when it is compressed.',
+        showInDialog: true,
+      },
      footer: {
        type: 'object',
        label: 'Footer',
@@ -4,28 +4,42 @@
 * SPDX-License-Identifier: Apache-2.0
 */

-import {
-  CompressionStatus,
-  type ChatCompressionInfo,
-  type GeminiClient,
-} from '@google/gemini-cli-core';
-import { vi, describe, it, expect, beforeEach } from 'vitest';
+import * as Core from '@google/gemini-cli-core';
+import { vi, describe, it, expect, beforeEach, afterEach } from 'vitest';
 import { compressCommand } from './compressCommand.js';
 import { createMockCommandContext } from '../../test-utils/mockCommandContext.js';
 import { MessageType } from '../types.js';

+vi.mock('@google/gemini-cli-core', async (importOriginal) => {
+  // eslint-disable-next-line @typescript-eslint/no-explicit-any
+  const actual = (await importOriginal()) as any;
+  return {
+    ...actual,
+    tokenLimit: vi.fn(),
+  };
+});
+
 describe('compressCommand', () => {
  let context: ReturnType<typeof createMockCommandContext>;
  let mockTryCompressChat: ReturnType<typeof vi.fn>;

+  afterEach(() => {
+    vi.restoreAllMocks();
+  });
+
  beforeEach(() => {
    mockTryCompressChat = vi.fn();
+    vi.mocked(Core.tokenLimit).mockReturnValue(1000);
    context = createMockCommandContext({
      services: {
        agentContext: {
+          config: {
+            getModel: () => 'test-model',
+            getContextWindowCompressionThreshold: () => 0.2,
+          },
          geminiClient: {
            tryCompressChat: mockTryCompressChat,
-          } as unknown as GeminiClient,
+          } as unknown as Core.GeminiClient,
        },
      },
    });
@@ -36,9 +50,10 @@ describe('compressCommand', () => {
      type: MessageType.COMPRESSION,
      compression: {
        isPending: true,
-        originalTokenCount: null,
-        newTokenCount: null,
+        beforePercentage: null,
+        afterPercentage: null,
        compressionStatus: null,
+        isManual: true,
      },
    };
    await compressCommand.action!(context, '');
@@ -54,9 +69,9 @@ describe('compressCommand', () => {
  });

  it('should set pending item, call tryCompressChat, and add result on success', async () => {
-    const compressedResult: ChatCompressionInfo = {
+    const compressedResult: Core.ChatCompressionInfo = {
      originalTokenCount: 200,
-      compressionStatus: CompressionStatus.COMPRESSED,
+      compressionStatus: Core.CompressionStatus.COMPRESSED,
      newTokenCount: 100,
    };
    mockTryCompressChat.mockResolvedValue(compressedResult);
@@ -68,8 +83,9 @@ describe('compressCommand', () => {
      compression: {
        isPending: true,
        compressionStatus: null,
-        originalTokenCount: null,
-        newTokenCount: null,
+        beforePercentage: null,
+        afterPercentage: null,
+        isManual: true,
      },
    });

@@ -83,9 +99,11 @@ describe('compressCommand', () => {
        type: MessageType.COMPRESSION,
        compression: {
          isPending: false,
-          compressionStatus: CompressionStatus.COMPRESSED,
-          originalTokenCount: 200,
-          newTokenCount: 100,
+          compressionStatus: Core.CompressionStatus.COMPRESSED,
+          beforePercentage: 20,
+          afterPercentage: 10,
+          isManual: true,
+          thresholdPercentage: 20,
        },
      },
      expect.any(Number),
@@ -6,6 +6,7 @@

 import { MessageType, type HistoryItemCompression } from '../types.js';
 import { CommandKind, type SlashCommand } from './types.js';
+import { tokenLimit, type CompressionStatus } from '@google/gemini-cli-core';

 export const compressCommand: SlashCommand = {
  name: 'compress',
@@ -14,7 +15,21 @@ export const compressCommand: SlashCommand = {
  kind: CommandKind.BUILT_IN,
  autoExecute: true,
  action: async (context) => {
-    const { ui } = context;
+    const { ui, services } = context;
+    const agentContext = services.agentContext;
+    if (!agentContext) {
+      ui.addItem(
+        {
+          type: MessageType.ERROR,
+          text: 'Agent context not found.',
+        },
+        Date.now(),
+      );
+      return;
+    }
+
+    const config = agentContext.config;
+
    if (ui.pendingItem) {
      ui.addItem(
        {
@@ -30,29 +45,43 @@ export const compressCommand: SlashCommand = {
      type: MessageType.COMPRESSION,
      compression: {
        isPending: true,
-        originalTokenCount: null,
-        newTokenCount: null,
+        beforePercentage: null,
+        afterPercentage: null,
        compressionStatus: null,
+        isManual: true,
      },
    };

    try {
      ui.setPendingItem(pendingMessage);
      const promptId = `compress-${Date.now()}`;
-      const compressed =
-        await context.services.agentContext?.geminiClient?.tryCompressChat(
-          promptId,
-          true,
-        );
+      const compressed = await agentContext.geminiClient.tryCompressChat(
+        promptId,
+        true,
+      );
      if (compressed) {
+        const limit = tokenLimit(config.getModel());
+        const threshold = config.getContextWindowCompressionThreshold();
+        const beforePercentage = Math.round(
+          (compressed.originalTokenCount / limit) * 100,
+        );
+        const afterPercentage = Math.round(
+          (compressed.newTokenCount / limit) * 100,
+        );
+
        ui.addItem(
          {
            type: MessageType.COMPRESSION,
            compression: {
              isPending: false,
-              originalTokenCount: compressed.originalTokenCount,
-              newTokenCount: compressed.newTokenCount,
-              compressionStatus: compressed.compressionStatus,
+              beforePercentage,
+              afterPercentage,
+              // eslint-disable-next-line @typescript-eslint/no-unsafe-type-assertion
+              compressionStatus: Number(
+                compressed.compressionStatus,
+              ) as unknown as CompressionStatus,
+              isManual: true,
+              thresholdPercentage: Math.round(threshold * 100),
            },
          } as HistoryItemCompression,
          Date.now(),
@@ -17,11 +17,7 @@ import {
 import { ConfigContext } from '../contexts/ConfigContext.js';
 import { SettingsContext } from '../contexts/SettingsContext.js';
 import { createMockSettings } from '../../test-utils/settings.js';
-import {
-  ApprovalMode,
-  tokenLimit,
-  CoreToolCallStatus,
-} from '@google/gemini-cli-core';
+import { ApprovalMode, CoreToolCallStatus } from '@google/gemini-cli-core';
 import type { Config } from '@google/gemini-cli-core';
 import { StreamingState } from '../types.js';
 import { TransientMessageType } from '../../utils/events.js';
@@ -733,37 +729,6 @@ describe('Composer', () => {
      expect(output).toContain('Press Esc again to rewind.');
      expect(output).not.toContain('ContextSummaryDisplay');
    });
-
-    it('shows context usage bleed-through when over 60%', async () => {
-      const model = 'gemini-2.5-pro';
-      const uiState = createMockUIState({
-        cleanUiDetailsVisible: false,
-        currentModel: model,
-        sessionStats: {
-          sessionId: 'test-session',
-          sessionStartTime: new Date(),
-          // eslint-disable-next-line @typescript-eslint/no-explicit-any
-          metrics: {} as any,
-          lastPromptTokenCount: Math.floor(tokenLimit(model) * 0.7),
-          promptCount: 0,
-        },
-      });
-      const settings = createMockSettings({
-        ui: {
-          footer: { hideContextPercentage: false },
-        },
-      });
-
-      const { lastFrame } = await renderComposer(uiState, settings);
-
-      await act(async () => {
-        await vi.advanceTimersByTimeAsync(250);
-      });
-
-      // StatusDisplay (which contains ContextUsageDisplay) should bleed through in minimal mode
-      expect(lastFrame()).toContain('StatusDisplay');
-      expect(lastFrame()).toContain('70% used');
-    });
  });

  describe('Error Details Display', () => {
@@ -20,13 +20,11 @@ import { useVimMode } from '../contexts/VimModeContext.js';
 import { useAlternateBuffer } from '../hooks/useAlternateBuffer.js';
 import { useTerminalSize } from '../hooks/useTerminalSize.js';
 import { isNarrowWidth } from '../utils/isNarrowWidth.js';
-import { isContextUsageHigh } from '../utils/contextUsage.js';
 import { theme } from '../semantic-colors.js';
 import { GENERIC_WORKING_LABEL } from '../textConstants.js';
 import { INTERACTIVE_SHELL_WAITING_PHRASE } from '../hooks/usePhraseCycler.js';
 import { StreamingState, type HistoryItemToolGroup } from '../types.js';
 import { LoadingIndicator } from './LoadingIndicator.js';
-import { ContextUsageDisplay } from './ContextUsageDisplay.js';
 import { StatusDisplay } from './StatusDisplay.js';
 import { HorizontalLine } from './shared/HorizontalLine.js';
 import { ToastDisplay, shouldShowToast } from './ToastDisplay.js';
@@ -257,11 +255,6 @@ export const Composer = ({ isFocused = true }: { isFocused?: boolean }) => {
  const miniMode_ShowShortcuts = shouldReserveSpaceForShortcutsHint;
  const miniMode_ShowStatus = showLoadingIndicator || hasAnyHooks;
  const miniMode_ShowTip = showTipLine;
-  const miniMode_ShowContext = isContextUsageHigh(
-    uiState.sessionStats.lastPromptTokenCount,
-    uiState.currentModel,
-    settings.merged.model?.compressionThreshold,
-  );

  // Composite Mini Mode Triggers
  const showRow1_MiniMode =
@@ -270,7 +263,7 @@ export const Composer = ({ isFocused = true }: { isFocused?: boolean }) => {
    miniMode_ShowShortcuts ||
    miniMode_ShowTip;

-  const showRow2_MiniMode = miniMode_ShowApprovalMode || miniMode_ShowContext;
+  const showRow2_MiniMode = miniMode_ShowApprovalMode;

  // Final Display Rules (Stable Footer Architecture)
  const showRow1 = showUiDetails || showRow1_MiniMode;
@@ -488,22 +481,9 @@ export const Composer = ({ isFocused = true }: { isFocused?: boolean }) => {
              alignItems="center"
              marginLeft={isNarrow ? 1 : 0}
            >
-              {(showUiDetails || miniMode_ShowContext) && (
+              {showUiDetails && (
                <StatusDisplay hideContextSummary={hideContextSummary} />
              )}
-              {miniMode_ShowContext && !showUiDetails && (
-                <Box marginLeft={1}>
-                  <ContextUsageDisplay
-                    promptTokenCount={uiState.sessionStats.lastPromptTokenCount}
-                    model={
-                      typeof uiState.currentModel === 'string'
-                        ? uiState.currentModel
-                        : undefined
-                    }
-                    terminalWidth={uiState.terminalWidth}
-                  />
-                </Box>
-              )}
            </Box>
          </Box>
        )}
@@ -72,7 +72,9 @@ const createMockConfig = (overrides = {}) => ({
 const renderStatusDisplay = async (
  props: { hideContextSummary: boolean } = { hideContextSummary: false },
  uiState: UIState = createMockUIState(),
-  settings = createMockSettings(),
+  settings = createMockSettings({
+    ui: { hideContextSummary: true },
+  }),
  config = createMockConfig(),
 ) => {
  const result = await render(
@@ -97,16 +99,21 @@ describe('StatusDisplay', () => {
    vi.restoreAllMocks();
  });

-  it('renders nothing by default if context summary is hidden via props', async () => {
-    const { lastFrame, unmount } = await renderStatusDisplay({
-      hideContextSummary: true,
-    });
+  it('renders nothing by default', async () => {
+    const { lastFrame, unmount } = await renderStatusDisplay();
    expect(lastFrame({ allowEmpty: true })).toBe('');
    unmount();
  });

-  it('renders ContextSummaryDisplay by default', async () => {
-    const { lastFrame, unmount } = await renderStatusDisplay();
+  it('renders ContextSummaryDisplay when hideContextSummary is false', async () => {
+    const settings = createMockSettings({
+      ui: { hideContextSummary: false },
+    });
+    const { lastFrame, unmount } = await renderStatusDisplay(
+      { hideContextSummary: false },
+      undefined,
+      settings,
+    );
    expect(lastFrame()).toMatchSnapshot();
    unmount();
  });
@@ -118,34 +125,6 @@ describe('StatusDisplay', () => {
    unmount();
  });

-  it('renders HookStatusDisplay when hooks are active', async () => {
-    const uiState = createMockUIState({
-      activeHooks: [{ name: 'hook', eventName: 'event' }],
-    });
-    const { lastFrame, unmount } = await renderStatusDisplay(
-      { hideContextSummary: false },
-      uiState,
-    );
-    expect(lastFrame()).toMatchSnapshot();
-    unmount();
-  });
-
-  it('does NOT render HookStatusDisplay if notifications are disabled in settings', async () => {
-    const uiState = createMockUIState({
-      activeHooks: [{ name: 'hook', eventName: 'event' }],
-    });
-    const settings = createMockSettings({
-      hooksConfig: { notifications: false },
-    });
-    const { lastFrame, unmount } = await renderStatusDisplay(
-      { hideContextSummary: false },
-      uiState,
-      settings,
-    );
-    expect(lastFrame()).toMatchSnapshot();
-    unmount();
-  });
-
  it('hides ContextSummaryDisplay if configured in settings', async () => {
    const settings = createMockSettings({
      ui: { hideContextSummary: true },
@@ -163,9 +142,13 @@ describe('StatusDisplay', () => {
    const uiState = createMockUIState({
      backgroundShellCount: 3,
    });
+    const settings = createMockSettings({
+      ui: { hideContextSummary: false },
+    });
    const { lastFrame, unmount } = await renderStatusDisplay(
      { hideContextSummary: false },
      uiState,
+      settings,
    );
    expect(lastFrame()).toContain('Shells: 3');
    unmount();
@@ -1,11 +1,6 @@
 // Vitest Snapshot v1, https://vitest.dev/guide/snapshot.html

-exports[`StatusDisplay > does NOT render HookStatusDisplay if notifications are disabled in settings 1`] = `
-"Mock Context Summary Display (Skills: 2, Shells: 0)
-"
-`;
-
-exports[`StatusDisplay > renders ContextSummaryDisplay by default 1`] = `
+exports[`StatusDisplay > renders ContextSummaryDisplay when hideContextSummary is false 1`] = `
 "Mock Context Summary Display (Skills: 2, Shells: 0)
 "
 `;
@@ -11,17 +11,22 @@ import {
 } from './CompressionMessage.js';
 import { CompressionStatus } from '@google/gemini-cli-core';
 import { type CompressionProps } from '../../types.js';
-import { describe, it, expect } from 'vitest';
+import { describe, it, expect, vi, afterEach } from 'vitest';

 describe('<CompressionMessage />', () => {
+  afterEach(() => {
+    vi.restoreAllMocks();
+  });
+
  const createCompressionProps = (
    overrides: Partial<CompressionProps> = {},
  ): CompressionDisplayProps => ({
    compression: {
      isPending: false,
-      originalTokenCount: null,
-      newTokenCount: null,
+      beforePercentage: null,
+      afterPercentage: null,
      compressionStatus: CompressionStatus.COMPRESSED,
+      isManual: true,
      ...overrides,
    },
  });
@@ -29,9 +34,10 @@ describe('<CompressionMessage />', () => {
  describe('pending state', () => {
    it('renders pending message when compression is in progress', async () => {
      const props = createCompressionProps({ isPending: true });
-      const { lastFrame, unmount } = await renderWithProviders(
+      const { lastFrame, waitUntilReady, unmount } = await renderWithProviders(
        <CompressionMessage {...props} />,
      );
+      await waitUntilReady();
      const output = lastFrame();

      expect(output).toContain('Compressing chat history');
@@ -43,56 +49,28 @@ describe('<CompressionMessage />', () => {
    it('renders success message when tokens are reduced', async () => {
      const props = createCompressionProps({
        isPending: false,
-        originalTokenCount: 100,
-        newTokenCount: 50,
+        beforePercentage: 22,
+        afterPercentage: 6,
        compressionStatus: CompressionStatus.COMPRESSED,
+        thresholdPercentage: 50,
      });
      const { lastFrame, unmount } = await renderWithProviders(
        <CompressionMessage {...props} />,
      );
      const output = lastFrame();

-      expect(output).toContain('✦');
+      expect(output).not.toContain('✦');
      expect(output).toContain(
-        'Chat history compressed from 100 to 50 tokens.',
+        'Context compressed (22% → 6%). Adjust threshold (50%) in /settings.',
      );
      unmount();
    });
-
-    it.each([
-      { original: 50000, newTokens: 25000 }, // Large compression
-      { original: 700000, newTokens: 350000 }, // Very large compression
-    ])(
-      'renders success message for large successful compression (from $original to $newTokens)',
-      async ({ original, newTokens }) => {
-        const props = createCompressionProps({
-          isPending: false,
-          originalTokenCount: original,
-          newTokenCount: newTokens,
-          compressionStatus: CompressionStatus.COMPRESSED,
-        });
-        const { lastFrame, unmount } = await renderWithProviders(
-          <CompressionMessage {...props} />,
-        );
-        const output = lastFrame();
-
-        expect(output).toContain('✦');
-        expect(output).toContain(
-          `compressed from ${original} to ${newTokens} tokens`,
-        );
-        expect(output).not.toContain('Skipping compression');
-        expect(output).not.toContain('did not reduce size');
-        unmount();
-      },
-    );
  });

  describe('skipped compression (tokens increased or same)', () => {
    it('renders skip message when compression would increase token count', async () => {
      const props = createCompressionProps({
        isPending: false,
-        originalTokenCount: 50,
-        newTokenCount: 75,
        compressionStatus:
          CompressionStatus.COMPRESSION_FAILED_INFLATED_TOKEN_COUNT,
      });
@@ -101,121 +79,12 @@ describe('<CompressionMessage />', () => {
      );
      const output = lastFrame();

-      expect(output).toContain('✦');
+      expect(output).not.toContain('✦');
      expect(output).toContain(
        'Compression was not beneficial for this history size.',
      );
      unmount();
    });
-
-    it('renders skip message when token counts are equal', async () => {
-      const props = createCompressionProps({
-        isPending: false,
-        originalTokenCount: 50,
-        newTokenCount: 50,
-        compressionStatus:
-          CompressionStatus.COMPRESSION_FAILED_INFLATED_TOKEN_COUNT,
-      });
-      const { lastFrame, unmount } = await renderWithProviders(
-        <CompressionMessage {...props} />,
-      );
-      const output = lastFrame();
-
-      expect(output).toContain(
-        'Compression was not beneficial for this history size.',
-      );
-      unmount();
-    });
-  });
-
-  describe('message content validation', () => {
-    it.each([
-      {
-        original: 200,
-        newTokens: 80,
-        expected: 'compressed from 200 to 80 tokens',
-      },
-      {
-        original: 500,
-        newTokens: 150,
-        expected: 'compressed from 500 to 150 tokens',
-      },
-      {
-        original: 1500,
-        newTokens: 400,
-        expected: 'compressed from 1500 to 400 tokens',
-      },
-    ])(
-      'displays correct compression statistics (from $original to $newTokens)',
-      async ({ original, newTokens, expected }) => {
-        const props = createCompressionProps({
-          isPending: false,
-          originalTokenCount: original,
-          newTokenCount: newTokens,
-          compressionStatus: CompressionStatus.COMPRESSED,
-        });
-        const { lastFrame, unmount } = await renderWithProviders(
-          <CompressionMessage {...props} />,
-        );
-        const output = lastFrame();
-
-        expect(output).toContain(expected);
-        unmount();
-      },
-    );
-
-    it.each([
-      { original: 50, newTokens: 60 }, // Increased
-      { original: 100, newTokens: 100 }, // Same
-      { original: 49999, newTokens: 50000 }, // Just under 50k threshold
-    ])(
-      'shows skip message for small histories when new tokens >= original tokens ($original -> $newTokens)',
-      async ({ original, newTokens }) => {
-        const props = createCompressionProps({
-          isPending: false,
-          originalTokenCount: original,
-          newTokenCount: newTokens,
-          compressionStatus:
-            CompressionStatus.COMPRESSION_FAILED_INFLATED_TOKEN_COUNT,
-        });
-        const { lastFrame, unmount } = await renderWithProviders(
-          <CompressionMessage {...props} />,
-        );
-        const output = lastFrame();
-
-        expect(output).toContain(
-          'Compression was not beneficial for this history size.',
-        );
-        expect(output).not.toContain('compressed from');
-        unmount();
-      },
-    );
-
-    it.each([
-      { original: 50000, newTokens: 50100 }, // At 50k threshold
-      { original: 700000, newTokens: 710000 }, // Large history case
-      { original: 100000, newTokens: 100000 }, // Large history, same count
-    ])(
-      'shows compression failure message for large histories when new tokens >= original tokens ($original -> $newTokens)',
-      async ({ original, newTokens }) => {
-        const props = createCompressionProps({
-          isPending: false,
-          originalTokenCount: original,
-          newTokenCount: newTokens,
-          compressionStatus:
-            CompressionStatus.COMPRESSION_FAILED_INFLATED_TOKEN_COUNT,
-        });
-        const { lastFrame, unmount } = await renderWithProviders(
-          <CompressionMessage {...props} />,
-        );
-        const output = lastFrame();
-
-        expect(output).toContain('compression did not reduce size');
-        expect(output).not.toContain('compressed from');
-        expect(output).not.toContain('Compression was not beneficial');
-        unmount();
-      },
-    );
  });

  describe('failure states', () => {
@@ -229,9 +98,9 @@ describe('<CompressionMessage />', () => {
      );
      const output = lastFrame();

-      expect(output).toContain('✦');
+      expect(output).not.toContain('✦');
      expect(output).toContain(
-        'Chat history compression failed: the model returned an empty summary.',
+        'Chat history compression failed: empty summary.',
      );
      unmount();
    });
@@ -22,11 +22,13 @@ export interface CompressionDisplayProps {
 export function CompressionMessage({
  compression,
 }: CompressionDisplayProps): React.JSX.Element {
-  const { isPending, originalTokenCount, newTokenCount, compressionStatus } =
-    compression;
-
-  const originalTokens = originalTokenCount ?? 0;
-  const newTokens = newTokenCount ?? 0;
+  const {
+    isPending,
+    beforePercentage,
+    afterPercentage,
+    compressionStatus,
+    thresholdPercentage,
+  } = compression;

  const getCompressionText = () => {
    if (isPending) {
@@ -34,20 +36,19 @@ export function CompressionMessage({
    }

    switch (compressionStatus) {
-      case CompressionStatus.COMPRESSED:
-        return `Chat history compressed from ${originalTokens} to ${newTokens} tokens.`;
-      case CompressionStatus.COMPRESSION_FAILED_INFLATED_TOKEN_COUNT:
-        // For smaller histories (< 50k tokens), compression overhead likely exceeds benefits
-        if (originalTokens < 50000) {
-          return 'Compression was not beneficial for this history size.';
+      case CompressionStatus.COMPRESSED: {
+        let text = `Context compressed (${beforePercentage}% → ${afterPercentage}%).`;
+        if (thresholdPercentage != null) {
+          text += ` Adjust threshold (${thresholdPercentage}%) in /settings.`;
        }
-        // For larger histories where compression should work but didn't,
-        // this suggests an issue with the compression process itself
-        return 'Chat history compression did not reduce size. This may indicate issues with the compression prompt.';
+        return text;
+      }
+      case CompressionStatus.COMPRESSION_FAILED_INFLATED_TOKEN_COUNT:
+        return 'Compression was not beneficial for this history size.';
      case CompressionStatus.COMPRESSION_FAILED_TOKEN_COUNT_ERROR:
        return 'Could not compress chat history due to a token counting error.';
      case CompressionStatus.COMPRESSION_FAILED_EMPTY_SUMMARY:
-        return 'Chat history compression failed: the model returned an empty summary.';
+        return 'Chat history compression failed: empty summary.';
      case CompressionStatus.NOOP:
        return 'Nothing to compress.';
      default:
@@ -58,20 +59,13 @@ export function CompressionMessage({
  const text = getCompressionText();

  return (
-    <Box flexDirection="row">
-      <Box marginRight={1}>
-        {isPending ? (
-          <CliSpinner type="dots" />
-        ) : (
-          <Text color={theme.text.accent}>✦</Text>
-        )}
-      </Box>
+    <Box flexDirection="row" paddingLeft={1} marginBottom={1}>
+      <Box marginRight={1}>{isPending && <CliSpinner type="dots" />}</Box>
      <Box>
        <Text
-          color={
-            compression.isPending ? theme.text.accent : theme.status.success
-          }
+          color={theme.text.secondary}
          aria-label={SCREEN_READER_MODEL_PREFIX}
+          italic
        >
          {text}
        </Text>
@@ -4,7 +4,7 @@
 * SPDX-License-Identifier: Apache-2.0
 */

-/* eslint-disable @typescript-eslint/no-explicit-any */
+/* eslint-disable @typescript-eslint/no-explicit-any -- TODO: Refactor to remove any usage */
 import {
  describe,
  it,
@@ -32,10 +32,7 @@ import type {
  Config,
  EditorType,
  AnyToolInvocation,
-  AnyDeclarativeTool,
  SpanMetadata,
-  CompletedToolCall,
-  ToolCallRequestInfo,
 } from '@google/gemini-cli-core';
 import {
  CoreToolCallStatus,
@@ -52,19 +49,15 @@ import {
  MCPDiscoveryState,
  GeminiCliOperation,
  getPlanModeExitMessage,
+  CompressionStatus,
 } from '@google/gemini-cli-core';
 import type { Part, PartListUnion } from '@google/genai';
 import type { UseHistoryManagerReturn } from './useHistoryManager.js';
-import type {
-  SlashCommandProcessorResult,
-  HistoryItemWithoutId,
-  HistoryItem,
-} from '../types.js';
+import type { SlashCommandProcessorResult } from '../types.js';
 import { MessageType, StreamingState } from '../types.js';

 import type { LoadedSettings } from '../../config/settings.js';
 import { findLastSafeSplitPoint } from '../utils/markdownUtilities.js';
-import { theme } from '../semantic-colors.js';

 // --- MOCKS ---
 const mockSendMessageStream = vi
@@ -145,6 +138,7 @@ const mockRunInDevTraceSpan = vi.hoisted(() =>
    };
    return await fn({
      metadata,
+      endSpan: vi.fn(),
    });
  }),
 );
@@ -249,10 +243,8 @@ describe('useGeminiStream', () => {
  let mockMarkToolsAsSubmitted: Mock;
  let handleAtCommandSpy: MockInstance;

-  const emptyHistory: HistoryItem[] = [];
-  let capturedOnComplete:
-    | ((tools: CompletedToolCall[]) => Promise<void>)
-    | null = null;
+  const emptyHistory: any[] = [];
+  let capturedOnComplete: any = null;
  const mockGetPreferredEditor = vi.fn(() => 'vscode' as EditorType);
  const mockOnAuthError = vi.fn();
  const mockPerformMemoryRefresh = vi.fn(() => Promise.resolve());
@@ -332,6 +324,9 @@ describe('useGeminiStream', () => {
    })),
    getIdeMode: vi.fn(() => false),
    getEnableHooks: vi.fn(() => false),
+    getShowContextWindowWarning: vi.fn(() => false),
+    getShowContextCompression: vi.fn(() => false),
+    getContextWindowCompressionThreshold: vi.fn(() => 0.2),
  } as unknown as Config;

  beforeEach(() => {
@@ -411,17 +406,13 @@ describe('useGeminiStream', () => {
        lastToolCalls,
        mockScheduleToolCalls,
        mockMarkToolsAsSubmitted,
-        (
-          updater:
-            | TrackedToolCall[]
-            | ((prev: TrackedToolCall[]) => TrackedToolCall[]),
-        ) => {
+        (updater: any) => {
          lastToolCalls =
            typeof updater === 'function' ? updater(lastToolCalls) : updater;
          rerender({ ...initialProps, toolCalls: lastToolCalls });
        },
-        (signal: AbortSignal) => {
-          mockCancelAllToolCalls(signal);
+        (...args: any[]) => {
+          mockCancelAllToolCalls(...args);
          lastToolCalls = lastToolCalls.map((tc) => {
            if (
              tc.status === CoreToolCallStatus.AwaitingApproval ||
@@ -888,7 +879,7 @@ describe('useGeminiStream', () => {
    const fn = spanArgs[1];
    const metadata = { attributes: {} };
    await act(async () => {
-      await fn({ metadata });
+      await fn({ metadata, endSpan: vi.fn() });
    });
    expect(metadata).toMatchObject({
      input: sentParts,
@@ -982,7 +973,7 @@ describe('useGeminiStream', () => {
  });

  it('should stop agent execution immediately when a tool call returns STOP_EXECUTION error', async () => {
-    const stopExecutionToolCalls: TrackedCompletedToolCall[] = [
+    const stopExecutionToolCalls: TrackedToolCall[] = [
      {
        request: {
          callId: 'stop-call',
@@ -1054,7 +1045,7 @@ describe('useGeminiStream', () => {
  });

  it('should add a compact suppressed-error note before STOP_EXECUTION terminal info in low verbosity mode', async () => {
-    const stopExecutionToolCalls: TrackedCompletedToolCall[] = [
+    const stopExecutionToolCalls: TrackedToolCall[] = [
      {
        request: {
          callId: 'stop-call',
@@ -1081,10 +1072,9 @@ describe('useGeminiStream', () => {
      } as unknown as TrackedCompletedToolCall,
    ];
    const lowVerbositySettings = {
-      // eslint-disable-next-line @typescript-eslint/no-misused-spread
-      ...mockLoadedSettings,
+      ...(mockLoadedSettings as any),
      merged: {
-        ...mockLoadedSettings.merged,
+        ...(mockLoadedSettings.merged as any),
        ui: { errorVerbosity: 'low' },
      },
    } as LoadedSettings;
@@ -1935,120 +1925,6 @@ describe('useGeminiStream', () => {
        expect(mockHandleSlashCommand).not.toHaveBeenCalled();
      });
    });
-
-    it('should record client-initiated tool calls in GeminiChat history', async () => {
-      const { result, client: mockGeminiClient } = await renderTestHook();
-
-      mockHandleSlashCommand.mockResolvedValue({
-        type: 'schedule_tool',
-        toolName: 'activate_skill',
-        toolArgs: { name: 'test-skill' },
-      });
-
-      await act(async () => {
-        await result.current.submitQuery('/test-skill');
-      });
-
-      // Simulate tool completion
-      const completedTool = {
-        request: {
-          callId: 'test-call-id',
-          name: 'activate_skill',
-          args: { name: 'test-skill' },
-          isClientInitiated: true,
-        },
-        status: CoreToolCallStatus.Success,
-        invocation: {
-          getDescription: () => 'Activating skill test-skill',
-        },
-        tool: {
-          isOutputMarkdown: true,
-        },
-        response: {
-          responseParts: [
-            {
-              functionResponse: {
-                name: 'activate_skill',
-                response: { content: 'skill instructions' },
-              },
-            },
-          ],
-        },
-      } as unknown as TrackedCompletedToolCall;
-
-      await act(async () => {
-        if (capturedOnComplete) {
-          await capturedOnComplete([completedTool]);
-        }
-      });
-
-      // Verify that the tool call and response were added to GeminiChat history
-      expect(mockGeminiClient.addHistory).toHaveBeenCalledWith({
-        role: 'model',
-        parts: [
-          {
-            functionCall: {
-              name: 'activate_skill',
-              args: { name: 'test-skill' },
-            },
-          },
-        ],
-      });
-      expect(mockGeminiClient.addHistory).toHaveBeenCalledWith({
-        role: 'user',
-        parts: completedTool.response.responseParts,
-      });
-    });
-
-    it('should NOT record other client-initiated tool calls (like save_memory) in history', async () => {
-      const { result, client: mockGeminiClient } = await renderTestHook();
-
-      mockHandleSlashCommand.mockResolvedValue({
-        type: 'schedule_tool',
-        toolName: 'save_memory',
-        toolArgs: { fact: 'test fact' },
-      });
-
-      await act(async () => {
-        await result.current.submitQuery('/memory add "test fact"');
-      });
-
-      // Simulate tool completion
-      const completedTool = {
-        request: {
-          callId: 'test-call-id',
-          name: 'save_memory',
-          args: { fact: 'test fact' },
-          isClientInitiated: true,
-        },
-        status: CoreToolCallStatus.Success,
-        invocation: {
-          getDescription: () => 'Saving memory',
-        },
-        tool: {
-          isOutputMarkdown: true,
-        },
-        response: {
-          responseParts: [
-            {
-              functionResponse: {
-                name: 'save_memory',
-                response: { success: true },
-              },
-            },
-          ],
-        },
-      } as unknown as TrackedCompletedToolCall;
-
-      await act(async () => {
-        if (capturedOnComplete) {
-          await capturedOnComplete([completedTool]);
-        }
-      });
-
-      // Verify that addHistory was NOT called
-      expect(mockGeminiClient.addHistory).not.toHaveBeenCalled();
-    });
  });

  describe('Memory Refresh on save_memory', () => {
@@ -2076,7 +1952,7 @@ describe('useGeminiStream', () => {
          displayName: 'save_memory',
          description: 'Saves memory',
          build: vi.fn(),
-        } as unknown as AnyDeclarativeTool,
+        } as any,
        invocation: {
          getDescription: () => `Mock description`,
        } as unknown as AnyToolInvocation,
@@ -2150,8 +2026,7 @@ describe('useGeminiStream', () => {
      );

      const testConfig = {
-        // eslint-disable-next-line @typescript-eslint/no-misused-spread
-        ...mockConfig,
+        ...(mockConfig as any),
        getContentGenerator: vi.fn(),
        getContentGeneratorConfig: vi.fn(() => ({
          authType: mockAuthType,
@@ -2316,7 +2191,7 @@ describe('useGeminiStream', () => {
            displayName: 'replace',
            description: 'Replace text',
            build: vi.fn(),
-          } as unknown as AnyDeclarativeTool,
+          } as any,
          invocation: {
            getDescription: () => 'Mock description',
          } as unknown as AnyToolInvocation,
@@ -2357,7 +2232,7 @@ describe('useGeminiStream', () => {
            displayName: 'write_file',
            description: 'Write file',
            build: vi.fn(),
-          } as unknown as AnyDeclarativeTool,
+          } as any,
          invocation: {
            getDescription: () => 'Mock description',
          } as unknown as AnyToolInvocation,
@@ -2474,22 +2349,32 @@ describe('useGeminiStream', () => {

      it.each([
        {
-          name: 'without suggestion when remaining tokens are > 75% of limit',
+          name: 'add a message when remaining tokens overflow, regardless of showContextWindowWarning setting',
          requestTokens: 20,
          remainingTokens: 80,
+          shouldShow: false, // The setting itself is false
          expectedMessage:
-            'Sending this message (20 tokens) might exceed the context window limit (80 tokens left).',
+            'Context 20% full. Message may exceed window. Reduce size or /compress.',
        },
        {
-          name: 'with suggestion when remaining tokens are < 75% of limit',
+          name: 'add a message when showContextWindowWarning is true',
          requestTokens: 30,
          remainingTokens: 70,
+          shouldShow: true,
          expectedMessage:
-            'Sending this message (30 tokens) might exceed the context window limit (70 tokens left). Please try reducing the size of your message or use the `/compress` command to compress the chat history.',
+            'Context 30% full. Message may exceed window. Reduce size or /compress.',
        },
      ])(
-        'should add message $name',
-        async ({ requestTokens, remainingTokens, expectedMessage }) => {
+        'should $name',
+        async ({
+          requestTokens,
+          remainingTokens,
+          shouldShow,
+          expectedMessage,
+        }) => {
+          vi.mocked(mockConfig.getShowContextWindowWarning).mockReturnValue(
+            shouldShow,
+          );
          mockSendMessageStream.mockReturnValue(
            (async function* () {
              yield {
@@ -2509,10 +2394,12 @@ describe('useGeminiStream', () => {
          });

          await waitFor(() => {
-            expect(mockAddItem).toHaveBeenCalledWith({
-              type: 'info',
-              text: expectedMessage,
-            });
+            expect(mockAddItem).toHaveBeenCalledWith(
+              expect.objectContaining({
+                type: 'info',
+                text: expectedMessage,
+              }),
+            );
          });
        },
      );
@@ -2566,8 +2453,12 @@ describe('useGeminiStream', () => {
      });
    });

-    it('should add informational messages when ChatCompressed event is received', async () => {
+    it('should add informational messages when ChatCompressed event is received and showContextCompression is true', async () => {
      vi.mocked(tokenLimit).mockReturnValue(10000);
+      vi.mocked(
+        mockConfig.getContextWindowCompressionThreshold,
+      ).mockReturnValue(0.2);
+      vi.mocked(mockConfig.getShowContextCompression).mockReturnValue(true);
      // Setup mock to return a stream with ChatCompressed event
      mockSendMessageStream.mockReturnValue(
        (async function* () {
@@ -2576,7 +2467,22 @@ describe('useGeminiStream', () => {
            value: {
              originalTokenCount: 1000,
              newTokenCount: 500,
-              compressionStatus: 'compressed',
+              compressionStatus: CompressionStatus.COMPRESSED,
+            },
+          };
+          yield {
+            type: ServerGeminiEventType.Content,
+            value: 'Response after compression',
+          };
+          yield {
+            type: ServerGeminiEventType.Finished,
+            value: {
+              finishReason: 'STOP',
+              usageMetadata: {
+                promptTokenCount: 10,
+                candidatesTokenCount: 20,
+                totalTokenCount: 30,
+              },
            },
          };
        })(),
@@ -2593,10 +2499,129 @@ describe('useGeminiStream', () => {
      await waitFor(() => {
        expect(mockAddItem).toHaveBeenCalledWith(
          expect.objectContaining({
-            type: MessageType.INFO,
-            text: 'Context compressed from 10% to 5%.',
-            secondaryText: 'Change threshold in /settings.',
-            color: theme.status.warning,
+            type: 'compression',
+            compression: {
+              isPending: false,
+              beforePercentage: 10,
+              afterPercentage: 5,
+              compressionStatus: CompressionStatus.COMPRESSED,
+              isManual: false,
+              thresholdPercentage: 20,
+            },
+          }),
+          expect.any(Number),
+        );
+      });
+    });
+
+    it('should NOT add informational messages when ChatCompressed event is received and showContextCompression is false', async () => {
+      vi.mocked(tokenLimit).mockReturnValue(10000);
+      vi.mocked(
+        mockConfig.getContextWindowCompressionThreshold,
+      ).mockReturnValue(0.2);
+      vi.mocked(mockConfig.getShowContextCompression).mockReturnValue(false);
+      // Setup mock to return a stream with ChatCompressed event
+      mockSendMessageStream.mockReturnValue(
+        (async function* () {
+          yield {
+            type: ServerGeminiEventType.ChatCompressed,
+            value: {
+              originalTokenCount: 1000,
+              newTokenCount: 500,
+              compressionStatus: CompressionStatus.COMPRESSED,
+            },
+          };
+          yield {
+            type: ServerGeminiEventType.Content,
+            value: 'Response after compression',
+          };
+          yield {
+            type: ServerGeminiEventType.Finished,
+            value: {
+              finishReason: 'STOP',
+              usageMetadata: {
+                promptTokenCount: 10,
+                candidatesTokenCount: 20,
+                totalTokenCount: 30,
+              },
+            },
+          };
+        })(),
+      );
+
+      const { result } = await renderHookWithDefaults();
+
+      // Submit a query
+      await act(async () => {
+        await result.current.submitQuery('Test compression');
+      });
+
+      // Check that NO compression message was added
+      await waitFor(() => {
+        expect(mockAddItem).not.toHaveBeenCalledWith(
+          expect.objectContaining({
+            type: 'compression',
+          }),
+        );
+      });
+    });
+
+    it('should add informational messages when ChatCompressed event is received with a large prompt even if showContextCompression is false', async () => {
+      vi.mocked(tokenLimit).mockReturnValue(10000);
+      vi.mocked(
+        mockConfig.getContextWindowCompressionThreshold,
+      ).mockReturnValue(0.2); // 20%
+      vi.mocked(mockConfig.getShowContextCompression).mockReturnValue(false);
+
+      // Setup mock to return a stream with ChatCompressed event and a large requestTokenCount (25%)
+      mockSendMessageStream.mockReturnValue(
+        (async function* () {
+          yield {
+            type: ServerGeminiEventType.ChatCompressed,
+            value: {
+              originalTokenCount: 1000,
+              newTokenCount: 500,
+              compressionStatus: CompressionStatus.COMPRESSED,
+              requestTokenCount: 2500, // 25% > 20%
+            },
+          };
+          yield {
+            type: ServerGeminiEventType.Content,
+            value: 'Response after compression',
+          };
+          yield {
+            type: ServerGeminiEventType.Finished,
+            value: {
+              finishReason: 'STOP',
+              usageMetadata: {
+                promptTokenCount: 10,
+                candidatesTokenCount: 20,
+                totalTokenCount: 30,
+              },
+            },
+          };
+        })(),
+      );
+
+      const { result } = await renderHookWithDefaults();
+
+      // Submit a query
+      await act(async () => {
+        await result.current.submitQuery('Test large prompt compression');
+      });
+
+      // Check that compression message WAS added despite the setting
+      await waitFor(() => {
+        expect(mockAddItem).toHaveBeenCalledWith(
+          expect.objectContaining({
+            type: 'compression',
+            compression: expect.objectContaining({
+              beforePercentage: 10,
+              afterPercentage: 5,
+              compressionStatus: CompressionStatus.COMPRESSED,
+              isManual: false,
+              thresholdPercentage: 20,
+            }),
          }),
          expect.any(Number),
        );
@@ -2702,14 +2727,14 @@ describe('useGeminiStream', () => {

  it('should flush pending text rationale before scheduling tool calls to ensure correct history order', async () => {
    const addItemOrder: string[] = [];
-    let capturedOnComplete: (tools: CompletedToolCall[]) => Promise<void>;
+    let capturedOnComplete: any;

    const mockScheduleToolCalls = vi.fn(async (requests) => {
      addItemOrder.push('scheduleToolCalls_START');
      // Simulate tools completing and triggering onComplete immediately.
      // This mimics the behavior that caused the regression where tool results
      // were added to history during the await scheduleToolCalls(...) block.
-      const tools = requests.map((r: ToolCallRequestInfo) => ({
+      const tools = requests.map((r: any) => ({
        request: r,
        status: CoreToolCallStatus.Success,
        tool: { displayName: r.name, name: r.name },
@@ -2724,7 +2749,7 @@ describe('useGeminiStream', () => {
      addItemOrder.push('scheduleToolCalls_END');
    });

-    mockAddItem.mockImplementation((item: HistoryItemWithoutId) => {
+    mockAddItem.mockImplementation((item: any) => {
      addItemOrder.push(`addItem:${item.type}`);
    });

@@ -2954,10 +2979,9 @@ describe('useGeminiStream', () => {
  describe('Thought Reset', () => {
    it('should keep full thinking entries in history when mode is full', async () => {
      const fullThinkingSettings: LoadedSettings = {
-        // eslint-disable-next-line @typescript-eslint/no-misused-spread
-        ...mockLoadedSettings,
+        ...(mockLoadedSettings as any),
        merged: {
-          ...mockLoadedSettings.merged,
+          ...(mockLoadedSettings.merged as any),
          ui: { inlineThinkingMode: 'full' },
        },
      } as unknown as LoadedSettings;
@@ -4036,7 +4060,7 @@ describe('useGeminiStream', () => {

    const spanMetadata = {} as SpanMetadata;
    await act(async () => {
-      await userPromptCall![1]({ metadata: spanMetadata });
+      await userPromptCall![1]({ metadata: spanMetadata, endSpan: vi.fn() });
    });
    expect(spanMetadata.input).toBe('telemetry test query');
  });
@@ -38,22 +38,20 @@ import {
  GeminiCliOperation,
  getPlanModeExitMessage,
  isBackgroundExecutionData,
+  type CompressionStatus,
  Kind,
-  ACTIVATE_SKILL_TOOL_NAME,
-} from '@google/gemini-cli-core';
-import type {
-  Config,
-  EditorType,
-  GeminiClient,
-  ServerGeminiChatCompressedEvent,
-  ServerGeminiContentEvent as ContentEvent,
-  ServerGeminiFinishedEvent,
-  ServerGeminiStreamEvent as GeminiEvent,
-  ThoughtSummary,
-  ToolCallRequestInfo,
-  ToolCallResponseInfo,
-  GeminiErrorEventValue,
-  RetryAttemptPayload,
+  type Config,
+  type EditorType,
+  type GeminiClient,
+  type ServerGeminiChatCompressedEvent,
+  type ServerGeminiContentEvent as ContentEvent,
+  type ServerGeminiFinishedEvent,
+  type ServerGeminiStreamEvent as GeminiEvent,
+  type ThoughtSummary,
+  type ToolCallRequestInfo,
+  type ToolCallResponseInfo,
+  type GeminiErrorEventValue,
+  type RetryAttemptPayload,
 } from '@google/gemini-cli-core';
 import { type Part, type PartListUnion, FinishReason } from '@google/genai';
 import type {
@@ -61,7 +59,6 @@ import type {
  HistoryItemThinking,
  HistoryItemWithoutId,
  HistoryItemToolGroup,
-  HistoryItemInfo,
  IndividualToolCallDisplay,
  SlashCommandProcessorResult,
  HistoryItemModel,
@@ -257,6 +254,8 @@ export const useGeminiStream = (
  const [_isFirstToolInGroup, isFirstToolInGroupRef, setIsFirstToolInGroup] =
    useStateAndRef<boolean>(true);
  const processedMemoryToolsRef = useRef<Set<string>>(new Set());
+  const handleCompletedToolsRef =
+    useRef<(completedTools: TrackedToolCall[]) => Promise<void>>(undefined);
  const { startNewPrompt, getPromptCount } = useSessionStats();
  const storage = config.storage;
  const logger = useLogger(storage);
@@ -302,22 +301,23 @@ export const useGeminiStream = (
            }),
          );
        }
-
        // Clear the live-updating display now that the final state is in history.
        setToolCallsForDisplay([]);

        // Record tool calls with full metadata before sending responses.
        try {
          const currentModel =
-            config.getGeminiClient().getCurrentSequenceModel() ??
-            config.getModel();
-          config
-            .getGeminiClient()
-            .getChat()
-            .recordCompletedToolCalls(
-              currentModel,
-              completedToolCallsFromScheduler,
-            );
+            (typeof geminiClient.getCurrentSequenceModel === 'function'
+              ? geminiClient.getCurrentSequenceModel()
+              : undefined) ?? config.getModel();
+          const chat =
+            typeof geminiClient.getChat === 'function'
+              ? geminiClient.getChat()
+              : undefined;
+          chat?.recordCompletedToolCalls(
+            currentModel,
+            completedToolCallsFromScheduler,
+          );

          await recordToolCallInteractions(
            config,
@@ -330,7 +330,7 @@ export const useGeminiStream = (
        }

        // Handle tool response submission immediately when tools complete
-        await handleCompletedTools(
+        await handleCompletedToolsRef.current?.(
          completedToolCallsFromScheduler as TrackedToolCall[],
        );
      }
@@ -549,9 +549,11 @@ export const useGeminiStream = (
      if (tc.request.name === ASK_USER_TOOL_NAME && isInProgress) {
        return false;
      }
-      // ToolGroupMessage now shows all non-canceled tools, so they are visible
-      // in pending and we need to draw the closing border for them.
-      return true;
+      return (
+        tc.status !== 'scheduled' &&
+        tc.status !== 'validating' &&
+        tc.status !== 'awaiting_approval'
+      );
    });

    if (
@@ -1145,21 +1147,43 @@ export const useGeminiStream = (
      }

      const limit = tokenLimit(config.getModel());
-      const originalPercentage = Math.round(
-        ((eventValue?.originalTokenCount ?? 0) / limit) * 100,
-      );
-      const newPercentage = Math.round(
-        ((eventValue?.newTokenCount ?? 0) / limit) * 100,
-      );
+      const beforePercentage =
+        eventValue?.originalTokenCount != null
+          ? Math.round((eventValue.originalTokenCount / limit) * 100)
+          : null;
+      const afterPercentage =
+        eventValue?.newTokenCount != null
+          ? Math.round((eventValue.newTokenCount / limit) * 100)
+          : null;
+
+      const threshold = config.getContextWindowCompressionThreshold();
+      const isLargePrompt =
+        eventValue?.requestTokenCount != null &&
+        eventValue.requestTokenCount / limit > threshold;
+
+      if (!config.getShowContextCompression() && !isLargePrompt) {
+        return;
+      }

      addItem(
        {
-          type: MessageType.INFO,
-          text: `Context compressed from ${originalPercentage}% to ${newPercentage}%.`,
-          secondaryText: `Change threshold in /settings.`,
-          color: theme.status.warning,
-          marginBottom: 1,
-        } as HistoryItemInfo,
+          type: 'compression',
+          compression: {
+            isPending: false,
+            beforePercentage,
+            afterPercentage,
+            /* eslint-disable @typescript-eslint/no-unsafe-type-assertion */
+            compressionStatus: eventValue
+              ? (Number(
+                  eventValue.compressionStatus,
+                ) as unknown as CompressionStatus)
+              : null,
+            /* eslint-enable @typescript-eslint/no-unsafe-type-assertion */
+            isManual: false,
+            thresholdPercentage: Math.round(threshold * 100),
+          },
+          timestamp: new Date(userMessageTimestamp),
+        } as HistoryItemWithoutId,
        userMessageTimestamp,
      );
    },
@@ -1182,16 +1206,11 @@ export const useGeminiStream = (
      onCancelSubmit(true);

      const limit = tokenLimit(config.getModel());
+      const usedPercentage = Math.round(
+        ((limit - remainingTokenCount) / limit) * 100,
+      );

-      const isMoreThan25PercentUsed =
-        limit > 0 && remainingTokenCount < limit * 0.75;
-
-      let text = `Sending this message (${estimatedRequestTokenCount} tokens) might exceed the context window limit (${remainingTokenCount.toLocaleString()} tokens left).`;
-
-      if (isMoreThan25PercentUsed) {
-        text +=
-          ' Please try reducing the size of your message or use the `/compress` command to compress the chat history.';
-      }
+      const text = `Context ${usedPercentage}% full. Message may exceed window. Reduce size or /compress.`;

      addItem({
        type: 'info',
@@ -1538,8 +1557,7 @@ export const useGeminiStream = (
                    setLoopDetectionConfirmationRequest(null);

                    if (result.userSelection === 'disable') {
-                      config
-                        .getGeminiClient()
+                      geminiClient
                        .getLoopDetectionService()
                        .disableForSession();
                      addItem({
@@ -1657,7 +1675,7 @@ export const useGeminiStream = (
      ) {
        let awaitingApprovalCalls = toolCalls.filter(
          (call): call is TrackedWaitingToolCall =>
-            call.status === 'awaiting_approval' && !call.request.forcedAsk,
+            call.status === 'awaiting_approval',
        );

        // For AUTO_EDIT mode, only approve edit tools (replace, write_file)
@@ -1715,42 +1733,24 @@ export const useGeminiStream = (
          },
        );

+      // Check if all tools in the batch are in a terminal state
+      const allTerminal = completedToolCallsFromScheduler.every(
+        (tc) =>
+          tc.status === 'success' ||
+          tc.status === 'error' ||
+          tc.status === 'cancelled',
+      );
+
+      if (!allTerminal) {
+        return;
+      }
+
      // Finalize any client-initiated tools as soon as they are done.
      const clientTools = completedAndReadyToSubmitTools.filter(
        (t) => t.request.isClientInitiated,
      );
      if (clientTools.length > 0) {
        markToolsAsSubmitted(clientTools.map((t) => t.request.callId));
-
-        if (geminiClient) {
-          for (const tool of clientTools) {
-            // Only manually record skill activations in the chat history.
-            // Other client-initiated tools (like save_memory) update the system
-            // prompt/context and don't strictly need to be in the history.
-            if (tool.request.name !== ACTIVATE_SKILL_TOOL_NAME) {
-              continue;
-            }
-
-            // Add both the call (model turn) and the result (user turn) to history.
-            // Client-initiated calls are essentially "synthetic" turns that let
-            // subsequent model calls understand what just happened in the UI.
-            await geminiClient.addHistory({
-              role: 'model',
-              parts: [
-                {
-                  functionCall: {
-                    name: tool.request.name,
-                    args: tool.request.args,
-                  },
-                },
-              ],
-            });
-            await geminiClient.addHistory({
-              role: 'user',
-              parts: tool.response.responseParts,
-            });
-          }
-        }
      }

      // Identify new, successful save_memory calls that we haven't processed yet.
@@ -1906,6 +1906,7 @@ export const useGeminiStream = (
      setIsResponding,
    ],
  );
+  handleCompletedToolsRef.current = handleCompletedTools;

  const pendingHistoryItems = useMemo(
    () =>
@@ -138,9 +138,11 @@ export interface IndividualToolCallDisplay {

 export interface CompressionProps {
  isPending: boolean;
-  originalTokenCount: number | null;
-  newTokenCount: number | null;
+  beforePercentage: number | null;
+  afterPercentage: number | null;
  compressionStatus: CompressionStatus | null;
+  isManual: boolean;
+  thresholdPercentage?: number | null;
 }

 /**
@@ -673,6 +673,8 @@ export interface ConfigParameters {
    agents?: AgentSettings;
  }>;
  enableConseca?: boolean;
+  showContextWindowWarning?: boolean;
+  showContextCompression?: boolean;
  billing?: {
    overageStrategy?: OverageStrategy;
  };
@@ -708,6 +710,8 @@ export class Config implements McpContext, AgentLoopContext {
  private readonly question: string | undefined;
  private readonly worktreeSettings: WorktreeSettings | undefined;
  readonly enableConseca: boolean;
+  private readonly showContextWindowWarning: boolean;
+  private readonly showContextCompression: boolean;

  private readonly coreTools: string[] | undefined;
  private readonly mainAgentTools: string[] | undefined;
@@ -1146,6 +1150,8 @@ export class Config implements McpContext, AgentLoopContext {
    this.fileExclusions = new FileExclusions(this);
    this.eventEmitter = params.eventEmitter;
    this.enableConseca = params.enableConseca ?? false;
+    this.showContextWindowWarning = params.showContextWindowWarning ?? false;
+    this.showContextCompression = params.showContextCompression ?? false;

    // Initialize Safety Infrastructure
    const contextBuilder = new ContextBuilder(this);
@@ -2053,6 +2059,18 @@ export class Config implements McpContext, AgentLoopContext {
    return this.mcpEnabled;
  }

+  getShowContextWindowWarning(): boolean {
+    return this.showContextWindowWarning;
+  }
+
+  getShowContextCompression(): boolean {
+    return this.showContextCompression;
+  }
+
+  getContextWindowCompressionThreshold(): number {
+    return this.compressionThreshold ?? 0.5;
+  }
+
  getMcpEnablementCallbacks(): McpEnablementCallbacks | undefined {
    return this.mcpEnablementCallbacks;
  }
@@ -248,6 +248,9 @@ describe('Gemini Client (client.ts)', () => {
      getEnableHooks: vi.fn().mockReturnValue(false),
      getChatCompression: vi.fn().mockReturnValue(undefined),
      getCompressionThreshold: vi.fn().mockReturnValue(undefined),
+      getShowContextWindowWarning: vi.fn().mockReturnValue(false),
+      getShowContextCompression: vi.fn().mockReturnValue(false),
+      getContextWindowCompressionThreshold: vi.fn().mockReturnValue(0.2),
      getSkipNextSpeakerCheck: vi.fn().mockReturnValue(false),
      getShowModelInfoInChat: vi.fn().mockReturnValue(false),
      getContinueOnFailedApiCall: vi.fn(),
@@ -1617,6 +1620,7 @@ ${JSON.stringify(
            originalTokenCount: initialTokenCount,
            newTokenCount: 400,
            compressionStatus: CompressionStatus.COMPRESSED,
+            requestTokenCount: 50, // Added to match updated interface
          };
        });

@@ -1643,10 +1647,13 @@ ${JSON.stringify(
        }),
      );

-      // 2. Should contain compression event
+      // 2. Should contain compression event with requestTokenCount
      expect(events).toContainEqual(
        expect.objectContaining({
          type: GeminiEventType.ChatCompressed,
+          value: expect.objectContaining({
+            requestTokenCount: expect.any(Number),
+          }),
        }),
      );

@@ -608,17 +608,6 @@ export class GeminiClient {
    // Check for context window overflow
    const modelForLimitCheck = this._getActiveModelForCurrentTurn();

-    const compressed = await this.tryCompressChat(prompt_id, false);
-
-    if (compressed.compressionStatus === CompressionStatus.COMPRESSED) {
-      yield { type: GeminiEventType.ChatCompressed, value: compressed };
-    }
-
-    const remainingTokenCount =
-      tokenLimit(modelForLimitCheck) - this.getChat().getLastPromptTokenCount();
-
-    await this.tryMaskToolOutputs(this.getHistory());
-
    // Estimate tokens. For text-only requests, we estimate based on character length.
    // For requests with non-text parts (like images, tools), we use the countTokens API.
    const estimatedRequestTokenCount = await calculateRequestTokenCount(
@@ -627,12 +616,48 @@ export class GeminiClient {
      modelForLimitCheck,
    );

+    const compressed = await this.tryCompressChat(
+      prompt_id,
+      false,
+      estimatedRequestTokenCount,
+    );
+
+    if (compressed.compressionStatus === CompressionStatus.COMPRESSED) {
+      yield { type: GeminiEventType.ChatCompressed, value: compressed };
+    }
+
+    let remainingTokenCount =
+      tokenLimit(modelForLimitCheck) - this.getChat().getLastPromptTokenCount();
+
+    await this.tryMaskToolOutputs(this.getHistory());
+
    if (estimatedRequestTokenCount > remainingTokenCount) {
-      yield {
-        type: GeminiEventType.ContextWindowWillOverflow,
-        value: { estimatedRequestTokenCount, remainingTokenCount },
-      };
-      return turn;
+      if (!this.config.getShowContextWindowWarning()) {
+        const forcedCompressed = await this.tryCompressChat(
+          prompt_id,
+          true,
+          estimatedRequestTokenCount,
+        );
+        if (
+          forcedCompressed.compressionStatus === CompressionStatus.COMPRESSED
+        ) {
+          yield {
+            type: GeminiEventType.ChatCompressed,
+            value: forcedCompressed,
+          };
+          remainingTokenCount =
+            tokenLimit(modelForLimitCheck) -
+            this.getChat().getLastPromptTokenCount();
+        }
+      }
+
+      if (estimatedRequestTokenCount > remainingTokenCount) {
+        yield {
+          type: GeminiEventType.ContextWindowWillOverflow,
+          value: { estimatedRequestTokenCount, remainingTokenCount },
+        };
+        return turn;
+      }
    }

    // Prevent context updates from being sent while a tool call is
@@ -1158,6 +1183,7 @@ export class GeminiClient {
  async tryCompressChat(
    prompt_id: string,
    force: boolean = false,
+    requestTokenCount?: number,
  ): Promise<ChatCompressionInfo> {
    // If the model is 'auto', we will use a placeholder model to check.
    // Compression occurs before we choose a model, so calling `count_tokens`
@@ -1173,6 +1199,11 @@ export class GeminiClient {
      this.hasFailedCompressionAttempt,
    );

+    const resultInfo = {
+      ...info,
+      requestTokenCount,
+    };
+
    if (
      info.compressionStatus ===
      CompressionStatus.COMPRESSION_FAILED_INFLATED_TOKEN_COUNT
@@ -1208,7 +1239,7 @@ export class GeminiClient {
      }
    }

-    return info;
+    return resultInfo;
  }

  /**
@@ -188,6 +188,7 @@ export interface ChatCompressionInfo {
  originalTokenCount: number;
  newTokenCount: number;
  compressionStatus: CompressionStatus;
+  requestTokenCount?: number;
 }

 export type ServerGeminiChatCompressedEvent = {
@@ -327,7 +327,21 @@
        "hideContextSummary": {
          "title": "Hide Context Summary",
          "description": "Hide the context summary (GEMINI.md, MCP servers) above the input.",
-          "markdownDescription": "Hide the context summary (GEMINI.md, MCP servers) above the input.\n\n- Category: `UI`\n- Requires restart: `no`\n- Default: `false`",
+          "markdownDescription": "Hide the context summary (GEMINI.md, MCP servers) above the input.\n\n- Category: `UI`\n- Requires restart: `no`\n- Default: `true`",
+          "default": true,
+          "type": "boolean"
+        },
+        "showContextWindowWarning": {
+          "title": "Show Context Window Warning",
+          "description": "Show a warning message when the context window limit is nearly reached. If disabled, the CLI will attempt to automatically compress the history when the limit is reached.",
+          "markdownDescription": "Show a warning message when the context window limit is nearly reached. If disabled, the CLI will attempt to automatically compress the history when the limit is reached.\n\n- Category: `UI`\n- Requires restart: `no`\n- Default: `false`",
+          "default": false,
+          "type": "boolean"
+        },
+        "showContextCompression": {
+          "title": "Show Context Compression Messages",
+          "description": "Show a message in the chat history when it is compressed.",
+          "markdownDescription": "Show a message in the chat history when it is compressed.\n\n- Category: `UI`\n- Requires restart: `no`\n- Default: `false`",
          "default": false,
          "type": "boolean"
        },
Author	SHA1	Message	Date
Yuna Seol	bd5d18c210	chore: remove unnecessary empty ignore files and plan.md	2026-04-10 13:42:51 -04:00
Yuna Seol	4f9293e8e9	fix(ui): always show context window warning on terminal overflow This removes the early return in the `handleContextWindowWillOverflowEvent` hook. If the context window truly overflows and the message is blocked, we must tell the user why, regardless of their proactive warning settings. This prevents a silent block where the CLI appears to just swallow the user's input.	2026-04-10 13:32:18 -04:00
Keith Guerin	9b51ccf82a	fix(cli): resolve CI test failures and stabilize mocks	2026-03-24 23:15:54 -07:00
Keith Guerin	c47bca8374	fix(cli): address CI build and lint failures by using stable geminiClient reference	2026-03-24 17:20:13 -07:00
Keith Guerin	2c83cf9603	fix(cli): address CI build and lint failures	2026-03-24 15:53:55 -07:00
Keith Guerin	84432ddaa8	fix(ci): address final test and build issues after rebase	2026-03-24 14:02:02 -07:00
Keith Guerin	05d29d68aa	fix(ci): address final test and build issues after rebase	2026-03-23 23:13:30 -07:00
Keith Guerin	99ddc299ad	feat(ui): refine context messaging with window terminology and large prompt override	2026-03-23 22:24:11 -07:00
Keith Guerin	cd4c8821cb	fix(ci): address lint, build and test failures after merge	2026-03-23 22:24:11 -07:00
Keith Guerin	8d0c2a3acb	fix(cli): resolve CI build and lint failures by fixing TS types and formatting	2026-03-23 22:24:11 -07:00
Keith Guerin	184a9abb59	docs(settings): regenerate schema and docs, and fix lint issue	2026-03-23 22:24:11 -07:00
Keith Guerin	4b2c117af3	fix(cli): resolve merge conflicts and align with async test helpers	2026-03-23 22:24:11 -07:00
Keith Guerin	511cbc54c9	fix(cli): resolve merge conflicts and align with async test helpers	2026-03-23 22:23:26 -07:00
Keith Guerin	692c34c834	fix(cli): fix missing awaits in tests after merge	2026-03-23 22:22:02 -07:00
Keith Guerin	3be1de915f	fix(cli): resolve compilation errors and update test mocks	2026-03-23 22:22:02 -07:00
Keith Guerin	16485afa96	feat(ui): finalize compression UX with threshold hint and large prompt override	2026-03-23 22:21:11 -07:00
Keith Guerin	375afc7199	feat(ui): restore threshold hint and thin arrow to compression message	2026-03-23 22:21:11 -07:00
Keith Guerin	fd8d218911	docs(ui): refine documentation and test eslint-disable for context UI changes	2026-03-23 22:20:51 -07:00
Keith Guerin	1de0367faa	docs(ui): update settings.md and settingsSchema descriptions for context UI changes	2026-03-23 22:20:15 -07:00
Keith Guerin	b6231f561b	docs(settings): rename context compression setting to use 'Messages' for clarity	2026-03-23 22:19:16 -07:00
Keith Guerin	252dbeb39a	feat(ui): add showContextCompression setting and simplify message wording	2026-03-23 22:19:16 -07:00
Keith Guerin	39fb7b11a8	feat(ui): finalize context and compression messaging with symbolic arrow and refined wording	2026-03-23 22:17:47 -07:00
Keith Guerin	eb3e540f3f	feat(ui): redesign context and compression UI for a more seamless experience - Added ui.showContextWindowWarning setting (default false). - Implemented forced auto-compression on context overflow when warning is disabled. - Redesigned compression messages to be subtle (gray, no icon, left border). - Removed automatic context usage percentage from the minimal/focus UI. - Changed ui.hideContextSummary default to true. - Updated and verified all relevant tests. Note: Includes a behavioral change where the CLI now attempts to force-compress history when the context window is full rather than blocking by default.	2026-03-23 22:03:31 -07:00