Error listings
开发者在通过 Cloudflare 代理长流式 API（如 LLM streaming）时遇到 524 超时错误，需要配置或解决方案 Includes evidence for Cloudflare troubleshooting demand.
Cloudflare Error 524: A Timeout Occurred — streaming response incomplete within gateway timeout 开发者通过 LiteLLM 代理调用 Modal Endpoint 时持续收到 404，但直接使用 Modal Client 和 Postman 正常，需要修复代理配置或排查兼容性问题 Includes evidence for LiteLLM troubleshooting demand.
404 Error with Modal Endpoint — works via Modal Client and PostMan but fails through LiteLLM proxy 使用 LiteLLM Proxy 的用户发现 stream_timeout 参数在首 chunk 未生效，导致慢启动 provider（如 Bedrock）请求被错误终止 Includes evidence for LiteLLM troubleshooting demand.
stream_timeout not enforced on first chunk; hanging providers cause completions to fail Fix handling of Anthropic API overloaded_error (429) responses when making multiple concurrent requests through SDK or proxy Includes evidence for Anthropic API troubleshooting demand.
overloaded_error: We're experiencing high demand — please retry after X seconds Fix Claude Code binary crashing on startup when run from VS Code integrated terminal or extension, while working fine in standalone Terminal.app Includes evidence for Claude Code troubleshooting demand.
error: An unknown error occurred (Unexpected) — exit code 1, crash ~8ms after spawn from VS Code parent process Handle insufficient_quota errors from OpenAI API in Python code with proper exception type instead of generic APIError Includes evidence for OpenAI API troubleshooting demand.
insufficient_quota in _exceptions.py — SDK does not raise dedicated InsufficientQuota exception Find solution to refresh/reconnect MCP tools in an active Claude Code Remote Control session without killing the entire session Includes evidence for Claude Code troubleshooting demand.
/mcp isn't available over Remote Control; in-session tool list frozen at boot-time snapshot after MCP server restart Resolve Claude Code subprocess timeout during initialization caused by auth failure or network connectivity issues Includes evidence for Claude Code troubleshooting demand.
Subprocess initialization did not complete within 60000ms — check authentication and network connectivity Fix crash when Bedrock returns rate_limit_error inside streaming SSE response — SDK raises unhandled AttributeError instead of typed rate limit exception Includes evidence for Anthropic API troubleshooting demand.
AttributeError: 'NoneType' object has no attribute 'model' / 'usage' — Bedrock cross-region inference SSE error payload returned as BetaRawMessageStartEvent with None message field Fix Docker daemon crashes caused by healthcheck mechanism causing intermittent service disruption Includes evidence for Docker troubleshooting demand.
Docker Daemon dies due to healthcheck Stop infinite reconnection loop when Codex CLI encounters unavailable model — recover cleanly instead of looping forever Includes evidence for OpenAI API troubleshooting demand.
404 "Model not found gpt-5.2" causes WebSocket fallback + reconnect loop in Codex CLI Handle background mode API failures reliably — classify retries vs non-retriable errors based on error type Includes evidence for OpenAI API troubleshooting demand.
Background Responses API error.code not mapped to SDK exception class; rate_limit_exceeded, server_error return opaque strings without typed exceptions Fix GitHub Actions checkout action v6 credential passing to Docker container actions, blocking CI/CD pipelines that push to repos from within containerized job steps Includes evidence for GitHub Actions troubleshooting demand.
checkout@v6 credentials don't work with Docker container actions — authentication fails in multi-container CI workflows with persistent open issue and 13+ comments Fix SDK crashing when AWS Bedrock cross-region inference profile returns HTTP 200 with rate_limit_error SSE payload, causing AttributeError on event.message access during AsyncAnthropicBedrock streaming Includes evidence for Anthropic API troubleshooting demand.
AttributeError: 'NoneType' object has no attribute 'model' — Bedrock returns rate_limit_error SSE causing SDK crash on first streaming event Fix Turbopack route loader timeout in Pages Router deployment builds where chunks succeed but page registration never completes, causing infinite hang Includes evidence for Vercel troubleshooting demand.
Pages Router Turbopack route loader times out before page registration despite successful chunk compilation — deployment hangs indefinitely Fix Next.js standalone mode output to include sourcemaps so production deployments retain ability to debug minified code in browser DevTools Includes evidence for Vercel troubleshooting demand.
The .next/standalone/ output folder doesn't contain any sourcemaps — production deployments via standalone mode have zero debuggability Need advance warning (email/push/webhook/SSE) before Anthropic session or weekly budget exhaustion so production AI systems can self-throttle and avoid unexpected service disruption Includes evidence for Anthropic API troubleshooting demand.
Sessions stop abruptly when budget exhausted with no X-Budget-Remaining-Pct header or webhook alert — no programmatic way to subscribe to limit events or throttle automation before hard stops Fix Turbopack hash generation mismatch between build-time module references and runtime installed packages in monorepo or custom node_modules setups Includes evidence for Vercel troubleshooting demand.
Turbopack generates external module references with hashes that don't match installed packages when node_modules structure differs — build succeeds but runtime fails with module resolution errors Understand why Azure OpenAI Realtime API token counts from the response.done event don't match expected/consumed tokens; fix billing measurement accuracy Includes evidence for OpenAI API troubleshooting demand.
response.done server event usage object does not match actual token consumption — measuring token usage via OpenAI.Realtime .NET SDK shows discrepancy between reported and expected values Fix 401 authentication failure when routing Azure OpenAI through LiteLLM proxy; authenticate properly using Azure AD tokens instead of api_key Includes evidence for LiteLLM / Azure OpenAI troubleshooting demand.
Authentication Error 401 — Connecting Azure OpenAI via LiteLLM (v1.63.7) with DSPy framework fails with 401 when using Azure AD Token Refresh method