Error listings
Fix LiteLLM Bedrock authentication failure caused by case-sensitive Content-Type header key collision causing double headers in SigV4 signing Includes evidence for LiteLLM troubleshooting demand.
SigV4 401 Unauthorized on bedrock/claude_platform/* route — signature never matches due to duplicate Content-Type header values Fix 400 error when creating Claude agent via Managed Agents beta API despite same API key working with Messages API Includes evidence for Anthropic API troubleshooting demand.
Error code: 400 - {"type": "invalid_request_error", "message": "`model.id`: model \"claude-sonnet-4-6\": model is not supported"} Fix regression in Next.js 16.2 Turbopack where Web Worker instantiation via import.meta.url crashes in production, breaking language-service workers Includes evidence for Vercel troubleshooting demand.
Turbopack production build: e.indexOf is not a function → TypeError: Cannot read properties of undefined (reading 'toUrl') when Web Worker created via new URL(..., import.meta.url) Recover locked-out Claude Code Pro or Max subscriber account that returns 403 on organization API endpoints after a platform outage, with human support refusing escalation Includes evidence for Claude Code troubleshooting demand.
/api/organizations returns 403 Forbidden, account inaccessible after outage, support loop unresolved for 60+ hours Fix regression where Claude Code Remote Routine sessions start with blank MCP OAuth accessToken values, triggering repeated dynamic OAuth client registrations that exhaust per-client registration rate limits Includes evidence for Claude Code troubleshooting demand.
MCP OAuth access tokens empty on every fresh container — SDK auth failed: You have exceeded the rate limit for client registration requests Fix unreliable background-mode response polling where failed runs return opaque error.code strings instead of mapped SDK exceptions (RateLimitError, InternalServerError, etc.), preventing deterministic retry logic Includes evidence for OpenAI API troubleshooting demand.
Background responses failures lack a stable code/name that maps to an exception class; HTTP 200 OK returned with status="failed" but no typed exception raised Understand and fix structured output grammar size limit error when using complex schemas with Claude API Includes evidence for Anthropic API troubleshooting demand.
compiled grammar is too large — Structured output validation fails for complex Pydantic schemas with Claude Investigate why prompt cache shows ~40% miss rate even for consecutive identical API calls with Anthropic Messages API Includes evidence for Anthropic API troubleshooting demand.
Cache misses on second back-to-back client.messages.create() (~40% rate) — Prompt caching efficiency drops significantly on consecutive identical calls Resolve 429 quota error when using third-party apps with ChatGPT Plus OAuth authentication Includes evidence for OpenAI API troubleshooting demand.
OAuth login succeeds → API call returns 429 quota exceeded despite active ChatGPT Plus subscription Fix LiteLLM proxy fallback chain broken by leaked internal rate-limiting parameters into provider API calls Includes evidence for LiteLLM troubleshooting demand.
BadRequestError / RateLimitError: Unrecognized request arguments supplied: _litellm_rate_limit_descriptors, _litellm_tpm_reserved_model (when using virtual keys with tpm/rpm limits + fallback chains) Fix prompt caching not being applied on Claude Opus 4.5 and Haiku 4.5 models despite cache_control parameter set Includes evidence for Anthropic API troubleshooting demand.
prompt_caching not activated on new model families (Opus 4.5/Haiku 4.5) — Cache control header ignored, costing more tokens than expected Fix 500 error when using OpenAI Responses API structured output with Decimal type fields in Pydantic models Includes evidence for OpenAI API troubleshooting demand.
HTTP 500 Internal Server Error — An error occurred while processing your request (server_error) when calling responses.parse() with gpt-5 and Pydantic models containing decimal.Decimal fields Debug Claude Code silently failing to connect to OAuth-protected MCP servers without proper DCR configuration Includes evidence for Claude Code troubleshooting demand.
[BUG] HTTP MCP servers requiring OAuth silently fail when Dynamic Client Registration (DCR) is not enabled — no tools appear, no error shown Fix Cursor IDE crash caused by spawning concurrent Claude Code processes inside the editor Includes evidence for Cursor troubleshooting demand.
[Bug] Cursor IDE crashes/becomes unresponsive when running multiple concurrent Claude Code CLI instances within Cursor Understand why LiteLLM masks rate limit 429 errors with misleading 'no deployments' message instead of surfacing the actual rate limit Includes evidence for LiteLLM troubleshooting demand.
RateLimitError: Error code: 429 - {'error': {'message': 'No deployments available for model…'}} Fix OpenAI API 429 rate limit error caused by exceeding daily/quota limits on paid accounts Includes evidence for OpenAI API troubleshooting demand.
RateLimitError: code: 429 - {'error': {'message': 'You exceeded your current quota, please check your plan and billing details.'}} Resolve Vercel deployment failures caused by webpack build errors and missing modules in production builds Includes evidence for Vercel troubleshooting demand.
Build failed because of webpack errors / Deployment Failed with error Module not found Developer configures custom MCP connector in Claude Code via claude.json, OAuth authentication succeeds initially but tokens fail to persist across sessions causing SDK auth failures Includes evidence for Claude Code troubleshooting demand.
Error: SDK auth failed Developer uses HTTP-based MCP servers with OAuth (e.g., Slack MCP at mcp.slack.com) in Claude Code; dynamic client registration (RFC 7591) fails with incompatible auth server error Includes evidence for Claude Code troubleshooting demand.
SDK auth failed: Incompatible auth server Developer starts Claude Code but one or more configured MCP servers fail to connect — covering failure across discovery, auth, schema validation, or streaming phases Includes evidence for Claude Code troubleshooting demand.
one or more MCP server processes or remote transports failed during discovery, authentication, schema validation, or streaming