Anthropic API Anthropic API Updated May 13, 2026
Fix Anthropic API prompt caching not working for prompts under 2048 tokens Includes evidence for Anthropic API troubleshooting demand.
Prompt caching for Claude Sonnet appears to start at 2048 tokens instead of documented 1024 Anthropic API Anthropic API Updated May 13, 2026
Fix Anthropic API structured output error when using complex JSON schemas Includes evidence for Anthropic API troubleshooting demand.
compiled grammar is too large Anthropic API Anthropic API Updated May 13, 2026
Fix Anthropic SDK computer-use feature broken after upgrading to v0.75.0 Includes evidence for Anthropic API troubleshooting demand.
Extra 'caller' Field in Request Breaks computer-use Between v0.74.1 and v0.75.0 Anthropic API Anthropic API Updated May 13, 2026
Fix Anthropic SDK error where API returns empty text blocks that the SDK rejects Includes evidence for Anthropic API troubleshooting demand.
SDK returns empty text blocks, but does not accept them Docker Docker Updated May 13, 2026
Fix Docker BuildKit 'failed to compute cache key' error in newer Docker versions Includes evidence for Docker troubleshooting demand.
Failed to compute cache key in newer version GitHub Actions GitHub Actions Updated May 13, 2026
Fix GitHub Actions self-hosted runner stuck waiting to pick up jobs Includes evidence for GitHub Actions troubleshooting demand.
Self-hosted runner stuck on 'Waiting for a runner to pick up this job...' LiteLLM LiteLLM Updated May 13, 2026
Fix LiteLLM performance degradation after upgrading to v1.81.x Includes evidence for LiteLLM troubleshooting demand.
Significant performance regression after upgrading from 1.80.5 to 1.81.x (UI + API slowness) LiteLLM LiteLLM Updated May 13, 2026
Fix LiteLLM proxy memory leak causing high RAM usage over extended operation Includes evidence for LiteLLM troubleshooting demand.
Heavy RAM Usage over time Deployment Next.js Updated May 13, 2026
Fix Next.js edge runtime package export error in server components Includes evidence for Next.js troubleshooting demand.
ERR_PACKAGE_PATH_NOT_EXPORTED: Package subpath './server.edge' is not defined by "exports" Ollama Ollama Updated May 13, 2026
Fix Ollama out of memory when loading Gemma3 or other large language models Includes evidence for Ollama troubleshooting demand.
Out of memory errors when running gemma3 npm pnpm Updated May 13, 2026
Fix pnpm ERR_PNPM_FETCH_429 rate limit error when installing dependencies Includes evidence for pnpm troubleshooting demand.
ERR_PNPM_FETCH_429 GitHub Actions GitHub Actions Updated May 13, 2026
Fix GitHub Actions cron-scheduled workflows that don't run on self-hosted runners Includes evidence for GitHub Actions troubleshooting demand.
GitHub Actions scheduled cron task does not trigger on self-hosted runner LiteLLM LiteLLM Updated May 13, 2026
Fix LiteLLM bulk invite generated API keys that don't have sk- prefix and get rejected Includes evidence for LiteLLM troubleshooting demand.
Bulk invite API keys missing sk- prefix, rejected on any call LiteLLM LiteLLM Updated May 13, 2026
Fix LiteLLM llm_requests_hanging alert spam when requests are not actually hanging Includes evidence for LiteLLM troubleshooting demand.
llm_requests_hanging alert fires continuously for requests below 600s threshold LiteLLM LiteLLM Updated May 13, 2026
Fix LiteLLM proxy where deleted models remain available on some workers after deletion via /model/delete API Includes evidence for LiteLLM troubleshooting demand.
Deleted models persist in other workers' local cache when running LiteLLM with --num_workers > 1 LiteLLM LiteLLM Updated May 13, 2026
Fix LiteLLM guardrail evaluation errors when using self-hosted vLLM models like Gemma Includes evidence for LiteLLM troubleshooting demand.
litellm.BadRequestError when using llm_as_a_judge guardrail with self-hosted vllm model LiteLLM LiteLLM Updated May 13, 2026
Fix LiteLLM MCP gateway returning empty tools instead of propagating upstream 401 authentication errors Includes evidence for LiteLLM troubleshooting demand.
LiteLLM returns 200 {"tools":[]} instead of upstream 401 for token-forwarding MCP servers Ollama Ollama Updated May 13, 2026
Fix Ollama Vulkan backend returning wrong or unrelated responses with Gemma4 models on AMD integrated graphics Includes evidence for Ollama troubleshooting demand.
Vulkan output unrelated to prompt when using gemma4 models with AMD Ryzen iGPU Cursor Cursor Updated May 13, 2026
Fix terminal code command launching Cursor instead of VS Code Includes evidence for Cursor troubleshooting demand.
code . command opens Cursor IDE instead of VS Code Cloud Platforms Vercel AI SDK Updated May 13, 2026
Fix tool call failures when using DeepSeek or other OpenAI-compatible providers with Vercel AI SDK Includes evidence for Vercel AI SDK troubleshooting demand.
Invalid schema for function 'functionName': schema must be a JSON Schema of 'type: "object"', got 'type: null'