Error listings
Fix silent failure when adding HTTP OAuth MCP servers that don't support DCR; Claude Code gives no error, tools never load into session. Includes evidence for Claude Code troubleshooting demand.
Incompatible auth server: does not support dynamic client registration (DCR); silent failure with no error message Configure automatic model group fallback in LiteLLM when primary provider hits rate limits; prevent complete service outage. Includes evidence for LiteLLM troubleshooting demand.
LiteLLM rate limit errors cause proxy to crash/fail instead of falling back to secondary model group Fix API key rejected by Cursor IDE despite being valid elsewhere (works in other apps); need resolution for paid Cursor subscription users. Includes evidence for Cursor troubleshooting demand.
We encountered an issue when using your API key: Streaming error Developer needs reliable way to catch and classify background mode API errors for retry/backoff logic in production applications using openai-python SDK Responses API with background=True Includes evidence for OpenAI API troubleshooting demand.
background responses failures lack a stable error.code mapping to SDK exception class; HTTP 200 OK with status="failed" returns opaque error.code string like "server_error" or "rate_limit_exceeded" but no typed exception raised Developer using Cline CLI with LiteLLM-compatible corporate proxy gets 404 errors because CLI uses wrong API endpoint; VS Code extension works fine but CLI does not Includes evidence for Cline CLI troubleshooting demand.
litellm provider hardcodes protocol:"openai-responses" causing requests to go to /v1/responses instead of /v1/chat/completions; many LiteLLM-compatible proxies implement only /chat/completions resulting in 404 Not Found macOS developer cannot run Docker commands after system update or Docker Desktop restart; socket file permissions broken after macOS upgrade Includes evidence for Docker troubleshooting demand.
Cannot connect to the Docker daemon at unix:///var/run/docker.sock. Is the docker daemon running? docker: permission denied trying to access /var/run/docker.sock on macOS DevOps engineer debugging Kubernetes pods repeatedly crashing with OutOfMemory killer; needs help configuring appropriate resource requests/limits and Java heap settings in containerized environment Includes evidence for Kubernetes troubleshooting demand.
Pod CrashLoopBackOff with last state terminated.reason=OOMKilled; Java application exceeding container memory limits set in Kubernetes deployment manifests Developer deploying Next.js on Vercel behind Cloudflare finds proxy.ts middleware silently skipped in production, breaking API proxy and security header functionality Includes evidence for Cloudflare troubleshooting demand.
proxy.ts does not execute in production when behind Cloudflare Proxy; middleware.ts works but proxy.ts bypassed entirely when Cloudflare is in the path Fix Chrome MCP extension returning empty browser list after idle period — misleading error message when extension IS installed Includes evidence for Claude Code troubleshooting demand.
Browser extension is not connected. Please ensure the Claude browser extension is installed and running Fix persistent ConnectionRefused error when using Claude Code CLI on Linux after uninstall/reinstall — works on other machines Includes evidence for Claude Code troubleshooting demand.
Unable to connect to API (ConnectionRefused) for 10 times (takes 3m) and then fails with an error Fix unexpected subscription downgrade to Free mid-cycle causing double charge and loss of paid access Includes evidence for Claude Code troubleshooting demand.
Plan silently reverted to Free despite active paid subscription; double charged for overlapping billing period Fix misclassified 500 error caused by passing string timeout instead of numeric value — confusing users about root cause Includes evidence for LiteLLM troubleshooting demand.
string-valued timeout produces misleading 'Security scan failed' 500 Handle background Responses API failures (server_error, rate_limit_exceeded) that return 200 OK with opaque error codes Includes evidence for OpenAI API troubleshooting demand.
HTTP poll returns 200 OK but status='failed' or 'incomplete' with no typed SDK exception raised Fix crash in LiteLLM OpenTelemetry guardrail integration when guardrail mode is configured as a Python list instead of single value Includes evidence for LiteLLM troubleshooting demand.
OpenTelemetry integration crashes with 'unhashable type: ''list'' when guardrail mode is a list' Fix Cursor IDE refusing to use custom models (GPT-4, Claude) when custom API key (BYOK) mode is enabled, particularly breaking Agent and Edit features that depend on custom models Includes evidence for Cursor troubleshooting demand.
The model gpt-4 does not work with your current plan or api key Fix self-hosted runner JWT authentication tokens expiring during long sequential workflow runs (hours-long pipelines), causing intermittent runner registration failures mid-pipeline Includes evidence for GitHub Actions troubleshooting demand.
JIT Token Expiration with Long-Running Sequential Workflows Fix container jobs failing with permission denied errors after upgrading GitHub Actions runner from v2.330.0 to v2.332.0, especially with non-root container users on ARC/Kubernetes Includes evidence for GitHub Actions troubleshooting demand.
/__w/_temp/_runner_file_commands/set_env_XXXX: Permission denied Fix LiteLLM rate-limiting where TPM limits apply independently per pod replica, effectively multiplying the intended rate limit by number of replicas and allowing far more requests than configured Includes evidence for LiteLLM troubleshooting demand.
Deployment-level TPM enforcement is per-pod, not cross-pod: effective limit becomes tpm_limit × N_replica Fix LiteLLM proxy buffering Anthropic SSE streams instead of sending real-time deltas, when both OpenAI and Anthropic share same proxy config Includes evidence for LiteLLM troubleshooting demand.
Anthropic proxied response is buffered: delta JSON lines sent in one large batch despite stream=true configuration Fix LiteLLM streaming fallback mechanism failing to route to backup models when primary Gemini 3 Preview returns HTTP 429, leaving clients without any response during peak usage Includes evidence for LiteLLM troubleshooting demand.
Fallbacks on STREAMING do not work with Pydantic-AI when Gemini 3 Preview throws 429 rate limit error