Error listings
Using LiteLLM virtual keys with token-per-minute/rate-per-minute limits causes internal _litellm_* parameters to be leaked into upstream provider API calls, corrupting requests and breaking automatic fallback routing Includes evidence for LiteLLM troubleshooting demand.
Virtual keys with tpm/rpm limits leak _litellm_* params into provider API calls, breaking fallback chains Developer trying to use images/edit endpoint with image_url JSON input gets 400 error — doc claims it's supported but implementation rejects it Includes evidence for OpenAI API troubleshooting demand.
client.images.edit() raises 400 error when passing image_url instead of file object Handle transient 404 Not Found errors when calling Anthropic Batch API retrieve/results endpoints shortly after batch creation Includes evidence for Anthropic API troubleshooting demand.
batches.retrieve() / batches.results() returns NotFoundError (404) intermittently seconds after successful creation — server-side propagation delay across Anthropic infrastructure nodes Fix broken pagination in Anthropic beta.skills.list endpoint returning only first 100 items regardless of total count Includes evidence for Anthropic API troubleshooting demand.
beta.skills.list hard-capped at 100 items with broken pagination — has_more always false, no cursor available Fix retry/error-handling logic when OpenAI Responses API background polling returns status=failed without raising a typed SDK exception Includes evidence for OpenAI API troubleshooting demand.
server_error in background response payload has no corresponding typed exception; retries/backoff logic cannot work for background=True runs due to opaque error.code string Fix middleware route scoping bug that causes deployment failures in Vercel Services-Mode Includes evidence for Vercel troubleshooting demand.
Middleware routes are not exempted from scopeRoutesToServiceOwnership, breaking deploy outputs in Services-Mode deployments Diagnose why the claude.ai billing dashboard merges two distinct charge types (API direct pay-as-you-go vs subscription extra usage) into one block, preventing users from accurately understanding spending patterns and incorrectly attributing API charges to plan overages Includes evidence for Anthropic API troubleshooting demand.
Billing console conflates API direct charges with subscription overages — users cannot distinguish charge sources in single undifferentiated Usage block Fix LiteLLM chatgpt provider where database-registered models bypass ChatGPTResponsesAPIConfig causing streaming requests to fail with explicit error 'Stream must be set to true', breaking integration between Claude Code and OpenRouter-hosted ChatGPT-compatible endpoints Includes evidence for LiteLLM troubleshooting demand.
chatgpt provider: DB-registered models skip ChatGPTResponsesAPIConfig — streaming requests fail with 'Stream must be set to true' Add dedicated insufficient_quota exception to OpenAI Python SDK so applications can catch quota-specific errors separately from generic rate-limit errors, enabling proper retry logic and user-facing messaging for paid API accounts Includes evidence for OpenAI API troubleshooting demand.
insufficient_quota in _exceptions.py — missing exception class for 429 quota exceeded errors Debug why Next.js Server Actions using Vercel Functions silently fail when exceeding invocation time limits, with no client-side error indication, blocking production debugging for deployed apps Includes evidence for Vercel troubleshooting demand.
FUNCTION_INVOCATION_TIMEOUT — Server Action fails silently on timeout Developers confused why API calls fail with rate limit even after confirming sufficient Anthropic credits exist — need to understand billing caps vs token limits. Includes evidence for Anthropic API troubleshooting demand.
API rate limit reached while using Anthropic credits; confusing monthly spend cap vs token balance User needs to fix recurring API rate limit errors that block their AI orchestrator (e.g., OpenClaw, Telegram bot) mid-task despite having available credits/balance. Includes evidence for OpenAI API troubleshooting demand.
API rate limit reached. Please try again later. Users need to fix Claude Code failing to authenticate MCP servers, specifically GitHub MCP and custom connectors returning auth failure codes. Includes evidence for Claude Code troubleshooting demand.
MCP error -32603: Authentication Failed: Requires authentication Users proxying long-running requests through LiteLLM face premature 60s kill; need to properly configure timeout propagation to underlying provider. Includes evidence for LiteLLM troubleshooting demand.
LiteLLM kills request after 60s default timeout despite router_settings.timeout being set higher Developers using LiteLLM proxy need to fix retry mechanism that doesn't respect rate limit headers or configured delays, causing cascading 429 errors. Includes evidence for LiteLLM troubleshooting demand.
litellm.RateLimitError: Rate limit exceeded without proper retry delay Users of official Todoist MCP with Claude desktop app experience daily auth loss; need stable OAuth refresh or permanent fix. Includes evidence for Claude Code troubleshooting demand.
MCP OAuth session expires daily — connector loses authorization requiring full reconnect Fix Permission Denied (403 Forbidden) errors when declaring explicit permissions causes all other permissions to default to none, breaking checkout and Docker push steps Includes evidence for GitHub Actions troubleshooting demand.
Resource not accessible by integration (HTTP 403) — checkout step fails after adding explicit permissions block missing contents: read Fix GitHub Actions token leakage into CI logs caused by Composer's old regex rejecting new GITHUB_TOKEN format with hyphens Includes evidence for GitHub Actions troubleshooting demand.
GitHub OAuth token contains invalid characters — Composer rejects GITHUB_TOKEN due to hyphen regex miss, exposing plaintext tokens in job logs Fix Vercel deployment failure occurring after successful build during Deploying outputs phase — caused by region failures, corrupted config, or platform incidents Includes evidence for Vercel troubleshooting demand.
We encountered an internal error. Please try again. (during Deploying outputs phase) 开发者遇到 Anthropic API 使用限制报错，错误消息无法区分具体是哪个配额被触发（会话级、周级、API RPM/TPM），需要知道重置时间以便调整调用策略 Includes evidence for Anthropic API troubleshooting demand.
You've reached your usage limit. Please try again later.