Error listings
Fix Ollama crash during multi-turn tool-calling on macOS Apple Silicon Includes evidence for Ollama troubleshooting demand.
model runner has unexpectedly stopped / llama runner process has terminated Fix Vercel env add trailing newline causing API key authentication errors Includes evidence for Vercel troubleshooting demand.
vercel env add: API key silently invalid due to trailing newline Fix Vercel deploy failing at 'Deploying outputs' with middleware and services-mode Includes evidence for Vercel troubleshooting demand.
An unexpected error occurred when running this build — Deploying outputs stage failure with middleware.ts in services-mode Fix Claude Code background mode '--bg' flag showing 'not enabled' error and failing to resume sessions Includes evidence for Claude Code troubleshooting demand.
--bg is not enabled. If this is unexpected, retry in a moment. Fix Claude Code background session failing with 'not-a-git-repo' error when worktree mode is enabled for repositories containing git submodules Includes evidence for Claude Code troubleshooting demand.
Background full checkout fails with not-a-git-repo when worktree mode is on for a repo with submodules Investigate and stop Claude Code consuming API tokens during idle periods when no user sessions are active Includes evidence for Claude Code troubleshooting demand.
Claude Code unexpected API usage increase ~5% overnight with zero user interaction Fix LiteLLM virtual key incorrectly rejecting requests with BudgetExceededError despite /key/info showing spend below max_budget Includes evidence for LiteLLM troubleshooting demand.
BudgetExceededError: spend exceeds max_budget for virtual key Fix missing rate limit headers on LiteLLM streaming API responses so clients can properly throttle requests Includes evidence for LiteLLM troubleshooting demand.
x-ratelimit-remaining / x-ratelimit-limit headers missing on streaming responses Fix LiteLLM deployment-level TPM rate limit being enforced per-pod instead of across all replicas in multi-replica Kubernetes deployments Includes evidence for LiteLLM troubleshooting demand.
Deployment-level TPM limit enforced per-pod, not cross-pod — effective limit = tpm_limit × N_replicas Fix LiteLLM crash with TypeError 'async for requires an object with aiter method' when streaming from models with reasoning/thinking output Includes evidence for LiteLLM troubleshooting demand.
TypeError: 'async for' requires an object with __aiter__ method, got NoneType Fix Ollama Cloud Pro service returning empty responses or timeouts across all cloud models including glm-5.1, kimi-k2.5, qwen3.5, and deepseek-v3.2 Includes evidence for Ollama troubleshooting demand.
Ollama Cloud: empty response or timeout on /api/chat and /api/generate for all cloud models Fix Ollama Cloud streaming read timeout after ~2 minutes on long generation tasks with large context Includes evidence for Ollama troubleshooting demand.
ReadTimeout: ollama-cloud stream drop after ~120-145s on long responses Fix Claude Code CLI login showing temporary service disruption page preventing authentication Includes evidence for Claude Code troubleshooting demand.
Claude is currently experiencing a temporary service disruption (Error code: 08XN6TZ) Fix Gemini API returning 429 Resource Exhausted errors despite being within paid tier limits Includes evidence for Gemini API troubleshooting demand.
429 RESOURCE_EXHAUSTED Fix Ollama Cloud streaming requests timing out after approximately 2 minutes on long generation tasks Includes evidence for Ollama troubleshooting demand.
ollama-cloud stream drop (ReadTimeout) after ~120-145s Fix Anthropic Python SDK not handling Bedrock streaming SSE error events gracefully Includes evidence for Anthropic API troubleshooting demand.
Bedrock SSE stream internalServerException — unexpected error during processing Fix AttributeError when Anthropic Bedrock streaming returns error SSE event as first event Includes evidence for Anthropic API troubleshooting demand.
AttributeError: 'NoneType' object has no attribute 'model' on streaming error SSE event Fix Claude Code freezing due to severe native memory leak on macOS Includes evidence for Claude Code troubleshooting demand.
Severe native memory leak (~738 GB/h) — CLI fully unresponsive, slash commands frozen Fix Codex Desktop Browser Use not working after update — Node REPL execution tool not exposed Includes evidence for Codex troubleshooting demand.
Browser Use broken: no node_repl/js or no Codex IAB backend discovered Fix LiteLLM BudgetExceededError rejecting requests when actual spend is below budget limit Includes evidence for LiteLLM troubleshooting demand.
BudgetExceededError: stale spend reported while /key/info shows spend below max_budget