Error listings
Fix Ollama codex-app browser trust error: launching codex-app via ollama breaks built-in browser with pipe bridge trust failure Includes evidence for Ollama troubleshooting demand.
Error: privileged native pipe bridge is not available; browser-client is not trusted Fix OpenAI Realtime API MCP integration: tool calls never execute despite MCP server being connected and verified with inspector Includes evidence for OpenAI API troubleshooting demand.
Realtime does not execute tool calls with mcp — MCP server connected but tool calls silently never fire, only instruction text returned Fix Claude Code VS Code extension failing to load when opening folders from UNC network paths, with ENOENT error referencing non-existent mapped drive Includes evidence for Claude Code troubleshooting demand.
ENOENT: no such file or directory, lstat 'G:\Grupos' Fix Cloudflare Workers container deployment failure where wrangler targets wrong API endpoint for container app registration after successful image push Includes evidence for Cloudflare troubleshooting demand.
wrangler deploy --dispatch-namespace fails: container registration uses non-WfP API endpoint Fix GitHub Actions self-hosted runner REST API returning stale busy state, causing auto-scaler to terminate running jobs Includes evidence for GitHub Actions troubleshooting demand.
GET /repos/{owner}/{repo}/actions/runners/{id} returns busy:false while runner is actively executing a job with valid lease Fix inability to remove budget limits from LiteLLM API keys once they have been configured, blocking billing flexibility Includes evidence for LiteLLM troubleshooting demand.
budget_limits on LiteLLM keys cannot be removed/overridden after initial set via UI or API Fix Ollama MLX runner infinite repetition loop hang during large-context inference with no detection or circuit breaker Includes evidence for Ollama troubleshooting demand.
Ollama MLX runner enters repetition loop at 60K+ tokens context, no abort mechanism, streams same phrase hundreds of times indefinitely Fix OpenAI Responses API background mode failures where error codes like 'server_error' don't map to typed SDK exceptions, breaking retry logic Includes evidence for OpenAI API troubleshooting demand.
Background response failed with opaque error.code string not mapped to SDK exception class Fix missing rate limit information in Claude Code status bar for paid users Includes evidence for Claude Code troubleshooting demand.
rate_limits field is null from statusLine JSON on 2.1.141 (OAuth Pro, firstParty) Fix Claude Code session becoming permanently broken after hitting Anthropic rate limit Includes evidence for Claude Code troubleshooting demand.
Upstream 429 then every retry returns 400 previous_message_id Fix frequent red error banner in Claude Code VS Code extension Includes evidence for Claude Code troubleshooting demand.
Unhandled case: [object Object] red banner in VS Code chat panel Fix Cloudflare scaffolding failure with pnpm 10+ due to ERR_PNPM_IGNORED_BUILDS Includes evidence for Cloudflare troubleshooting demand.
ERR_PNPM_IGNORED_BUILDS: Ignored builds during pnpm create cloudflare Fix LiteLLM v1.84.0 Docker container failing to start Includes evidence for LiteLLM troubleshooting demand.
Docker image ghcr.io/berriai/litellm:1.84.0 start failure in container logs Fix Anthropic API 400 error when text content blocks are empty in messages.create request Includes evidence for Anthropic API troubleshooting demand.
API Error: 400 messages: text content blocks must be non-empty Fix LiteLLM fallback configuration not triggering when primary model fails Includes evidence for LiteLLM troubleshooting demand.
No fallback model group found for original model_group=primary Fix Ollama gemma4 repetition loop when generating structured JSON with format parameter Includes evidence for Ollama troubleshooting demand.
Word repetition loop fills num_predict budget, JSON unterminated — repeat_penalty has no effect Fix Ollama structured output being ignored when think=false is set Includes evidence for Ollama troubleshooting demand.
think=false with format parameter causes format constraint to be silently ignored — outputs plain text instead of JSON Fix OpenAI API request timeout after extended processing time Includes evidence for OpenAI API troubleshooting demand.
timeout at ~616 seconds with status: interrupted Fix Anthropic API overloaded_error when Claude models are at capacity during paid API calls Includes evidence for Anthropic API troubleshooting demand.
overloaded_error — Anthropic API returns 529 or 503 when Claude models are at capacity Fix AWS Bedrock ValidationException when invoking Anthropic Claude models — requires inference profile instead of direct model ID Includes evidence for Anthropic API troubleshooting demand.
Invocation of model ID anthropic.claude-3-5-sonnet-20241022-v2:0 with on-demand throughput isn't supported