feat(core): thinking block cross-turn retention with idle cleanup

docs/users/configuration/settings.md

@@ -206,6 +206,7 @@ The `extra_body` field allows you to add custom parameters to the request body s
 | `context.fileFiltering.respectQwenIgnore`         | boolean                    | Respect .qwenignore files when searching.                                                                                                                                                                                                                                                                                                                             | `true`      |
 | `context.fileFiltering.enableRecursiveFileSearch` | boolean                    | Whether to enable searching recursively for filenames under the current tree when completing `@` prefixes in the prompt.                                                                                                                                                                                                                                              | `true`      |
 | `context.fileFiltering.enableFuzzySearch`         | boolean                    | When `true`, enables fuzzy search capabilities when searching for files. Set to `false` to improve performance on projects with a large number of files.                                                                                                                                                                                                              | `true`      |
+| `context.gapThresholdMinutes`                     | number                     | Minutes of inactivity after which retained thinking blocks are cleared to free context tokens. Aligns with typical provider prompt-cache TTL. Set higher if your provider has a longer cache TTL.                                                                                                                                                                     | `5`         |
 
 #### Troubleshooting File Search Performance
 

packages/cli/src/config/config.ts

@@ -1069,6 +1069,7 @@ export async function loadCliConfig(
     telemetry: telemetrySettings,
     usageStatisticsEnabled: settings.privacy?.usageStatisticsEnabled ?? true,
     fileFiltering: settings.context?.fileFiltering,
+    thinkingIdleThresholdMinutes: settings.context?.gapThresholdMinutes,
     checkpointing:
       argv.checkpointing || settings.general?.checkpointing?.enabled,
     proxy:

packages/cli/src/config/settingsSchema.ts

@@ -914,6 +914,16 @@ const SETTINGS_SCHEMA = {
           },
         },
       },
+      gapThresholdMinutes: {
+        type: 'number',
+        label: 'Thinking Block Idle Threshold (minutes)',
+        category: 'Context',
+        requiresRestart: false,
+        default: 5,
+        description:
+          'Minutes of inactivity after which retained thinking blocks are cleared to free context tokens. Aligns with provider prompt-cache TTL.',
+        showInDialog: false,
+      },
     },
   },
 

packages/core/src/config/config.ts

@@ -370,6 +370,8 @@ export interface ConfigParameters {
   model?: string;
   outputLanguageFilePath?: string;
   maxSessionTurns?: number;
+  /** Minutes of inactivity before clearing retained thinking blocks. */
+  thinkingIdleThresholdMinutes?: number;
   sessionTokenLimit?: number;
   experimentalZedIntegration?: boolean;
   cronEnabled?: boolean;
@@ -557,6 +559,7 @@ export class Config {
   private ideMode: boolean;
 
   private readonly maxSessionTurns: number;
+  private readonly thinkingIdleThresholdMs: number;
   private readonly sessionTokenLimit: number;
   private readonly listExtensions: boolean;
   private readonly overrideExtensions?: string[];
@@ -683,6 +686,8 @@ export class Config {
     this.fileDiscoveryService = params.fileDiscoveryService ?? null;
     this.bugCommand = params.bugCommand;
     this.maxSessionTurns = params.maxSessionTurns ?? -1;
+    this.thinkingIdleThresholdMs =
+      (params.thinkingIdleThresholdMinutes ?? 5) * 60 * 1000;
     this.sessionTokenLimit = params.sessionTokenLimit ?? -1;
     this.experimentalZedIntegration =
       params.experimentalZedIntegration ?? false;
@@ -1329,6 +1334,10 @@ export class Config {
     return this.maxSessionTurns;
   }
 
+  getThinkingIdleThresholdMs(): number {
+    return this.thinkingIdleThresholdMs;
+  }
+
   getSessionTokenLimit(): number {
     return this.sessionTokenLimit;
   }

packages/core/src/core/client.test.ts

@@ -323,6 +323,7 @@ describe('Gemini Client (client.ts)', () => {
       getWorkingDir: vi.fn().mockReturnValue('/test/dir'),
       getFileService: vi.fn().mockReturnValue(fileService),
       getMaxSessionTurns: vi.fn().mockReturnValue(0),
+      getThinkingIdleThresholdMs: vi.fn().mockReturnValue(5 * 60 * 1000),
       getSessionTokenLimit: vi.fn().mockReturnValue(32000),
       getNoBrowser: vi.fn().mockReturnValue(false),
       getUsageStatisticsEnabled: vi.fn().mockReturnValue(true),
@@ -427,6 +428,119 @@ describe('Gemini Client (client.ts)', () => {
     });
   });
 
+  describe('thinking block idle cleanup and latch', () => {
+    let mockChat: Partial<GeminiChat>;
+
+    beforeEach(() => {
+      const mockStream = (async function* () {
+        yield {
+          type: GeminiEventType.Content,
+          value: 'response',
+        };
+      })();
+      mockTurnRunFn.mockReturnValue(mockStream);
+
+      mockChat = {
+        addHistory: vi.fn(),
+        getHistory: vi.fn().mockReturnValue([]),
+        stripThoughtsFromHistory: vi.fn(),
+        stripThoughtsFromHistoryKeepRecent: vi.fn(),
+      };
+      client['chat'] = mockChat as GeminiChat;
+    });
+
+    it('should not strip thoughts on active session (< 5min idle)', async () => {
+      // Simulate a recent API completion (2 minutes ago — within default 5 min threshold)
+      client['lastApiCompletionTimestamp'] = Date.now() - 2 * 60 * 1000;
+      client['thinkingClearLatched'] = false;
+
+      const gen = client.sendMessageStream(
+        [{ text: 'Hello' }],
+        new AbortController().signal,
+        'prompt-1',
+        { type: SendMessageType.UserQuery },
+      );
+      for await (const _ of gen) {
+        /* drain */
+      }
+
+      expect(
+        mockChat.stripThoughtsFromHistoryKeepRecent,
+      ).not.toHaveBeenCalled();
+    });
+
+    it('should latch and strip thoughts after > 5min idle', async () => {
+      // Simulate an old API completion (10 minutes ago — exceeds default 5 min threshold)
+      client['lastApiCompletionTimestamp'] = Date.now() - 10 * 60 * 1000;
+      client['thinkingClearLatched'] = false;
+
+      const gen = client.sendMessageStream(
+        [{ text: 'Hello' }],
+        new AbortController().signal,
+        'prompt-2',
+        { type: SendMessageType.UserQuery },
+      );
+      for await (const _ of gen) {
+        /* drain */
+      }
+
+      expect(client['thinkingClearLatched']).toBe(true);
+      expect(mockChat.stripThoughtsFromHistoryKeepRecent).toHaveBeenCalledWith(
+        1,
+      );
+    });
+
+    it('should keep stripping once latched even if idle < 5min', async () => {
+      // Pre-set latch with a recent timestamp (2 minutes ago — within threshold)
+      client['lastApiCompletionTimestamp'] = Date.now() - 2 * 60 * 1000;
+      client['thinkingClearLatched'] = true;
+
+      const gen = client.sendMessageStream(
+        [{ text: 'Hello' }],
+        new AbortController().signal,
+        'prompt-3',
+        { type: SendMessageType.UserQuery },
+      );
+      for await (const _ of gen) {
+        /* drain */
+      }
+
+      expect(client['thinkingClearLatched']).toBe(true);
+      expect(mockChat.stripThoughtsFromHistoryKeepRecent).toHaveBeenCalledWith(
+        1,
+      );
+    });
+
+    it('should update lastApiCompletionTimestamp after API call', async () => {
+      client['lastApiCompletionTimestamp'] = null;
+
+      const before = Date.now();
+      const gen = client.sendMessageStream(
+        [{ text: 'Hello' }],
+        new AbortController().signal,
+        'prompt-4',
+        { type: SendMessageType.UserQuery },
+      );
+      for await (const _ of gen) {
+        /* drain */
+      }
+
+      expect(client['lastApiCompletionTimestamp']).toBeGreaterThanOrEqual(
+        before,
+      );
+    });
+
+    it('should reset latch and timestamp on resetChat', async () => {
+      client['lastApiCompletionTimestamp'] = Date.now();
+      client['thinkingClearLatched'] = true;
+
+      await client.resetChat();
+
+      expect(client['thinkingClearLatched']).toBe(false);
+      expect(client['lastApiCompletionTimestamp']).toBeNull();
+    });
+  });
+
   describe('tryCompressChat', () => {
     const mockGetHistory = vi.fn();
 
@@ -436,6 +550,7 @@ describe('Gemini Client (client.ts)', () => {
         addHistory: vi.fn(),
         setHistory: vi.fn(),
         stripThoughtsFromHistory: vi.fn(),
+        stripThoughtsFromHistoryKeepRecent: vi.fn(),
       } as unknown as GeminiChat;
     });
 
@@ -457,6 +572,7 @@ describe('Gemini Client (client.ts)', () => {
         getHistory: vi.fn((_curated?: boolean) => chatHistory),
         setHistory: vi.fn(),
         stripThoughtsFromHistory: vi.fn(),
+        stripThoughtsFromHistoryKeepRecent: vi.fn(),
       };
       client['chat'] = mockOriginalChat as GeminiChat;
 
@@ -1149,6 +1265,7 @@ describe('Gemini Client (client.ts)', () => {
         addHistory: vi.fn(),
         getHistory: vi.fn().mockReturnValue([]),
         stripThoughtsFromHistory: vi.fn(),
+        stripThoughtsFromHistoryKeepRecent: vi.fn(),
       } as unknown as GeminiChat;
       client['chat'] = mockChat;
 
@@ -1204,6 +1321,7 @@ Other open files:
         addHistory: vi.fn(),
         getHistory: vi.fn().mockReturnValue([]),
         stripThoughtsFromHistory: vi.fn(),
+        stripThoughtsFromHistoryKeepRecent: vi.fn(),
       };
       client['chat'] = mockChat as GeminiChat;
 
@@ -1260,6 +1378,7 @@ Other open files:
         addHistory: vi.fn(),
         getHistory: vi.fn().mockReturnValue([]),
         stripThoughtsFromHistory: vi.fn(),
+        stripThoughtsFromHistoryKeepRecent: vi.fn(),
       };
       client['chat'] = mockChat as GeminiChat;
 
@@ -1326,6 +1445,7 @@ hello
         addHistory: vi.fn(),
         getHistory: vi.fn().mockReturnValue([]),
         stripThoughtsFromHistory: vi.fn(),
+        stripThoughtsFromHistoryKeepRecent: vi.fn(),
       };
       client['chat'] = mockChat as GeminiChat;
 
@@ -1365,6 +1485,7 @@ Other open files:
         addHistory: vi.fn(),
         getHistory: vi.fn().mockReturnValue([]),
         stripThoughtsFromHistory: vi.fn(),
+        stripThoughtsFromHistoryKeepRecent: vi.fn(),
       };
       client['chat'] = mockChat as GeminiChat;
 
@@ -1410,6 +1531,7 @@ Other open files:
         addHistory: vi.fn(),
         getHistory: vi.fn().mockReturnValue([]),
         stripThoughtsFromHistory: vi.fn(),
+        stripThoughtsFromHistoryKeepRecent: vi.fn(),
       };
       client['chat'] = mockChat as GeminiChat;
 
@@ -1498,6 +1620,7 @@ Other open files:
         addHistory: vi.fn(),
         getHistory: vi.fn().mockReturnValue([]),
         stripThoughtsFromHistory: vi.fn(),
+        stripThoughtsFromHistoryKeepRecent: vi.fn(),
       };
       client['chat'] = mockChat as GeminiChat;
 
@@ -1555,6 +1678,7 @@ Other open files:
         addHistory: vi.fn(),
         getHistory: vi.fn().mockReturnValue([]),
         stripThoughtsFromHistory: vi.fn(),
+        stripThoughtsFromHistoryKeepRecent: vi.fn(),
       };
       client['chat'] = mockChat as GeminiChat;
 
@@ -1636,6 +1760,7 @@ Other open files:
               { role: 'user', parts: [{ text: 'previous message' }] },
             ]),
           stripThoughtsFromHistory: vi.fn(),
+          stripThoughtsFromHistoryKeepRecent: vi.fn(),
         };
         client['chat'] = mockChat as GeminiChat;
       });
@@ -1889,6 +2014,7 @@ Other open files:
           getHistory: vi.fn().mockReturnValue([]), // Default empty history
           setHistory: vi.fn(),
           stripThoughtsFromHistory: vi.fn(),
+          stripThoughtsFromHistoryKeepRecent: vi.fn(),
         };
         client['chat'] = mockChat as GeminiChat;
 
@@ -2228,6 +2354,7 @@ Other open files:
         addHistory: vi.fn(),
         getHistory: vi.fn().mockReturnValue([]),
         stripThoughtsFromHistory: vi.fn(),
+        stripThoughtsFromHistoryKeepRecent: vi.fn(),
       };
       client['chat'] = mockChat as GeminiChat;
 
@@ -2265,6 +2392,7 @@ Other open files:
         addHistory: vi.fn(),
         getHistory: vi.fn().mockReturnValue([]),
         stripThoughtsFromHistory: vi.fn(),
+        stripThoughtsFromHistoryKeepRecent: vi.fn(),
       };
       client['chat'] = mockChat as GeminiChat;
 
@@ -2305,6 +2433,7 @@ Other open files:
         addHistory: vi.fn(),
         getHistory: vi.fn().mockReturnValue([]),
         stripThoughtsFromHistory: vi.fn(),
+        stripThoughtsFromHistoryKeepRecent: vi.fn(),
       };
       client['chat'] = mockChat as GeminiChat;
 
@@ -2329,6 +2458,7 @@ Other open files:
           getHistory: vi.fn().mockReturnValue([]),
           setHistory: vi.fn(),
           stripThoughtsFromHistory: vi.fn(),
+          stripThoughtsFromHistoryKeepRecent: vi.fn(),
           stripOrphanedUserEntriesFromHistory: vi.fn(),
         };
         client['chat'] = mockChat as GeminiChat;
@@ -2361,6 +2491,7 @@ Other open files:
           getHistory: vi.fn().mockReturnValue([]),
           setHistory: vi.fn(),
           stripThoughtsFromHistory: vi.fn(),
+          stripThoughtsFromHistoryKeepRecent: vi.fn(),
           stripOrphanedUserEntriesFromHistory: vi.fn(),
         };
         client['chat'] = mockChat as GeminiChat;
@@ -2405,6 +2536,7 @@ Other open files:
           addHistory: vi.fn(),
           getHistory: vi.fn().mockReturnValue([]),
           stripThoughtsFromHistory: vi.fn(),
+          stripThoughtsFromHistoryKeepRecent: vi.fn(),
         };
         client['chat'] = mockChat as GeminiChat;
       });