[Bug] Message feed hangs after large change during compacting with subsequent compact errors

Bug Description
Feed gets stuck, doesn't goes on, happens after a big change - seems it has something to do with compacting, messages don't help anymore, doesn't respond to anything, compacting again gives compacting error message

Environment Info

• Platform: darwin
• Terminal: vscode
• Version: 2.0.60
• Feedback ID: 6c0f3cbf-fa9b-4000-ad54-a8efbdc69be6

Errors

[{"error":"Error: EISDIR: illegal operation on a directory, read\n    at Module.readFileSync (node:fs:449:20)\n    at Object.readFileSync (file:///Users/nielsvanderwerf/.nvm/versions/node/v20.19.5/lib/node_modules/@anthropic-ai/claude-code/cli.js:9:299)\n    at W12 (file:///Users/nielsvanderwerf/.nvm/versions/node/v20.19.5/lib/node_modules/@anthropic-ai/claude-code/cli.js:4456:17608)\n    at Object.call (file:///Users/nielsvanderwerf/.nvm/versions/node/v20.19.5/lib/node_modules/@anthropic-ai/claude-code/cli.js:1455:909)\n    at fx7 (file:///Users/nielsvanderwerf/.nvm/versions/node/v20.19.5/lib/node_modules/@anthropic-ai/claude-code/cli.js:3094:16957)\n    at runNextTicks (node:internal/process/task_queues:60:5)\n    at process.processImmediate (node:internal/timers:454:9)","timestamp":"2025-12-06T23:07:58.816Z"},{"error":"MaxFileReadTokenExceededError: File content (27879 tokens) exceeds maximum allowed tokens (25000). Please use offset and limit parameters to read specific portions of the file, or use the GrepTool to search for specific content.\n    at I12 (file:///Users/nielsvanderwerf/.nvm/versions/node/v20.19.5/lib/node_modules/@anthropic-ai/claude-code/cli.js:1446:10603)\n    at process.processTicksAndRejections (node:internal/process/task_queues:95:5)\n    at async Object.call (file:///Users/nielsvanderwerf/.nvm/versions/node/v20.19.5/lib/node_modules/@anthropic-ai/claude-code/cli.js:1455:963)\n    at async file:///Users/nielsvanderwerf/.nvm/versions/node/v20.19.5/lib/node_modules/@anthropic-ai/claude-code/cli.js:1671:1465","timestamp":"2025-12-07T00:24:50.115Z"},{"error":"MaxFileReadTokenExceededError: File content (37905 tokens) exceeds maximum allowed tokens (25000). Please use offset and limit parameters to read specific portions of the file, or use the GrepTool to search for specific content.\n    at I12 (file:///Users/nielsvanderwerf/.nvm/versions/node/v20.19.5/lib/node_modules/@anthropic-ai/claude-code/cli.js:1446:10603)\n    at process.processTicksAndRejections (node:internal/process/task_queues:95:5)\n    at async Object.call (file:///Users/nielsvanderwerf/.nvm/versions/node/v20.19.5/lib/node_modules/@anthropic-ai/claude-code/cli.js:1455:963)\n    at async file:///Users/nielsvanderwerf/.nvm/versions/node/v20.19.5/lib/node_modules/@anthropic-ai/claude-code/cli.js:1671:1465","timestamp":"2025-12-07T00:24:50.402Z"},{"error":"MaxFileReadTokenExceededError: File content (27879 tokens) exceeds maximum allowed tokens (25000). Please use offset and limit parameters to read specific portions of the file, or use the GrepTool to search for specific content.\n    at I12 (file:///Users/nielsvanderwerf/.nvm/versions/node/v20.19.5/lib/node_modules/@anthropic-ai/claude-code/cli.js:1446:10603)\n    at process.processTicksAndRejections (node:internal/process/task_queues:95:5)\n    at async Object.call (file:///Users/nielsvanderwerf/.nvm/versions/node/v20.19.5/lib/node_modules/@anthropic-ai/claude-code/cli.js:1455:963)\n    at async file:///Users/nielsvanderwerf/.nvm/versions/node/v20.19.5/lib/node_modules/@anthropic-ai/claude-code/cli.js:1671:1465","timestamp":"2025-12-07T00:24:55.948Z"},{"error":"MaxFileReadTokenExceededError: File content (37905 tokens) exceeds maximum allowed tokens (25000). Please use offset and limit parameters to read specific portions of the file, or use the GrepTool to search for specific content.\n    at I12 (file:///Users/nielsvanderwerf/.nvm/versions/node/v20.19.5/lib/node_modules/@anthropic-ai/claude-code/cli.js:1446:10603)\n    at process.processTicksAndRejections (node:internal/process/task_queues:95:5)\n    at async Object.call (file:///Users/nielsvanderwerf/.nvm/versions/node/v20.19.5/lib/node_modules/@anthropic-ai/claude-code/cli.js:1455:963)\n    at async file:///Users/nielsvanderwerf/.nvm/versions/node/v20.19.5/lib/node_modules/@anthropic-ai/claude-code/cli.js:1671:1465","timestamp":"2025-12-07T00:24:57.485Z"},{"error":"MaxFileReadTokenExceededError: File content (32337 tokens) exceeds maximum allowed tokens (25000). Please use offset and limit parameters to read specific portions of the file, or use the GrepTool to search for specific content.\n    at I12 (file:///Users/nielsvanderwerf/.nvm/versions/node/v20.19.5/lib/node_modules/@anthropic-ai/claude-code/cli.js:1446:10603)\n    at process.processTicksAndRejections (node:internal/process/task_queues:95:5)\n    at async Object.call (file:///Users/nielsvanderwerf/.nvm/versions/node/v20.19.5/lib/node_modules/@anthropic-ai/claude-code/cli.js:1455:963)\n    at async file:///Users/nielsvanderwerf/.nvm/versions/node/v20.19.5/lib/node_modules/@anthropic-ai/claude-code/cli.js:1671:1465","timestamp":"2025-12-07T00:25:37.198Z"},{"error":"Error: Request was aborted.\n    at Ao._createMessage (file:///

Note: Error logs were truncated.