claude-code - 💡(How to fix) Fix [Bug Report: Model performance degradation or unexpected behavior changes] [1 comments, 2 participants]

[{"error":"Error: 400 {"type":"error","error":{"type":"invalid_request_error","message":"prompt is too long: 206472 tokens > 200000 maximum"},"request_id":"req_011Cab49tdGeEFVhCvuGTPq3"}\n at dq.generate (file:///opt/homebrew/lib/node_modules/@anthropic-ai/claude-code/cli.js:8:51908)\n at ML.makeStatusError (file:///opt/homebrew/lib/node_modules/@anthropic-ai/claude-code/cli.js:47:1652)\n at ML.makeRequest (file:///opt/homebrew/lib/node_modules/@anthropic-ai/claude-code/cli.js:47:4928)\n at process.processTicksAndRejections (node:internal/process/task_queues:104:5)","timestamp":"2026-05-01T02:24:42.685Z"},{"error":"Error: 400 {"type":"error","error":{"type":"invalid_request_error","message":"prompt is too long: 217424 tokens > 200000 maximum"},"request_id":"req_011Cab4A5NBiFjdSt4yKqyjG"}\n at dq.generate (file:///opt/homebrew/lib/node_modules/@anthropic-ai/claude-code/cli.js:8:51908)\n at ML.makeStatusError (file:///opt/homebrew/lib/node_modules/@anthropic-ai/claude-code/cli.js:47:1652)\n at ML.makeRequest (file:///opt/homebrew/lib/node_modules/@anthropic-ai/claude-code/cli.js:47:4928)\n at process.processTicksAndRejections (node:internal/process/task_queues:104:5)","timestamp":"2026-05-01T02:24:45.920Z"},{"error":"Error: 400 {"type":"error","error":{"type":"invalid_request_error","message":"prompt is too long: 206554 tokens > 200000 maximum"},"request_id":"req_011Cab4ALBui8dRc7p1yamk6"}\n at dq.generate (file:///opt/homebrew/lib/node_modules/@anthropic-ai/claude-code/cli.js:8:51908)\n at ML.makeStatusError (file:///opt/homebrew/lib/node_modules/@anthropic-ai/claude-code/cli.js:47:1652)\n at ML.makeRequest (file:///opt/homebrew/lib/node_modules/@anthropic-ai/claude-code/cli.js:47:4928)\n at process.processTicksAndRejections (node:internal/process/task_queues:104:5)","timestamp":"2026-05-01T02:24:48.929Z"},{"error":"Error: 400 {"type":"error","error":{"type":"invalid_request_error","message":"prompt is too long: 201886 tokens > 200000 maximum"},"request_id":"req_011Cab4AY8WTRfSCYnDfUmjw"}\n at dq.generate (file:///opt/homebrew/lib/node_modules/@anthropic-ai/claude-code/cli.js:8:51908)\n at ML.makeStatusError (file:///opt/homebrew/lib/node_modules/@anthropic-ai/claude-code/cli.js:47:1652)\n at ML.makeRequest (file:///opt/homebrew/lib/node_modules/@anthropic-ai/claude-code/cli.js:47:4928)\n at process.processTicksAndRejections (node:internal/process/task_queues:104:5)","timestamp":"2026-05-01T02:24:53.298Z"},{"error":"Error: 400 {"type":"error","error":{"type":"invalid_request_error","message":"prompt is too long: 207348 tokens > 200000 maximum"},"request_id":"req_011Cab4AsgVoi5PcnQn5sBCK"}\n at dq.generate (file:///opt/homebrew/lib/node_modules/@anthropic-ai/claude-code/cli.js:8:51908)\n at ML.makeStatusError (file:///opt/homebrew/lib/node_modules/@anthropic-ai/claude-code/cli.js:47:1652)\n at ML.makeRequest (file:///opt/homebrew/lib/node_modules/@anthropic-ai/claude-code/cli.js:47:4928)\n at process.processTicksAndRejections (node:internal/process/task_queues:104:5)","timestamp":"2026-05-01T02:24:56.217Z"},{"error":"Error: 400 {"type":"error","error":{"type":"invalid_request_error","message":"prompt is too long: 202720 tokens > 200000 maximum"},"request_id":"req_011Cab4B5XdVHf8bCZnk5tLa"}\n at dq.generate (file:///opt/homebrew/lib/node_modules/@anthropic-ai/claude-code/cli.js:8:51908)\n at ML.makeStatusError (file:///opt/homebrew/lib/node_modules/@anthropic-ai/claude-code/cli.js:47:1652)\n at ML.makeRequest (file:///opt/homebrew/lib/node_modules/@anthropic-ai/claude-code/cli.js:47:4928)\n at process.processTicksAndRejections (node:internal/process/task_queues:104:5)","timestamp":"2026-05-01T02:24:58.411Z"},{"error":"Error: 400 {"type":"error","error":{"type":"invalid_request_error","message":"prompt is too long: 207563 tokens > 200000 maximum"},"request_id":"req_011Cab4BF2dWHj6xLdXoy2j3"}\n at dq.generate (file:///opt/homebrew/lib/node_modules/@anthropic-ai/claude-code/cli.js:8:51908)\n at ML.makeStatusError (file:///opt/homebrew/lib/node_modules/@anthropic-ai/claude-code/cli.js:47:1652)\n at ML.makeRequest (file:///opt/homebrew/lib/node_modules/@anthropic-ai/claude-code/cli.js:47:4928)\n at process.processTicksAndRejections (node:internal/process/task_queues:104:5)","timestamp":"2026-05-01T02:25:00.642Z"},{"error":"Error: 400 {"type":"error","error":{"type…

TL;DR

The most likely fix is to reduce the length of the prompt to below 200,000 tokens.

Guidance

• Verify the prompt length by checking the error messages, which indicate that the prompt exceeds the 200,000 token limit.
• Shorten the prompt by removing unnecessary information or splitting it into smaller, more focused prompts.
• Consider implementing a prompt validation check to prevent similar errors in the future.
• Review the code that generates the prompt to identify areas where token count can be optimized.

Example

No code snippet is provided as the issue is related to prompt length, not code syntax.

Notes

The provided error messages are truncated, but the pattern of "prompt is too long" errors suggests that the issue is related to exceeding the token limit. Reducing the prompt length should resolve the issue.

Recommendation

Apply a workaround by shortening the prompt to below 200,000 tokens, as this is the most direct solution to the error messages provided.