Merge pull request #2897 from QwenLM/feat/thinking-cross-turn-retention-idle-cleanup

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

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

@@ -924,6 +924,16 @@ 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,
+      },
     },
   },