Topic hub pagination
Continue browsing this topic cluster with SEO-safe static pagination.
Fix LiteLLM max_parallel_requests counter not decrementing on cancelled streams Includes evidence for LiteLLM troubleshooting demand.
max_parallel_requests Current limit: N, Remaining: 0 Fix LiteLLM not capturing reasoning/thinking content from Ollama models like Qwen3 and DeepSeek-R1 Includes evidence for LiteLLM troubleshooting demand.
LiteLLM Ollama reasoning_content always null — /api/generate doesn't return thinking field Fix LiteLLM reasoning_content missing after Anthropic to OpenAI format conversion Includes evidence for LiteLLM / Anthropic API troubleshooting demand.
LiteLLM Anthropic to OpenAI conversion drops reasoning_content, breaks multi-turn with reasoning models Fix LiteLLM cache_control not forwarding to Anthropic when using Responses API Includes evidence for LiteLLM / Anthropic API troubleshooting demand.
LiteLLM Responses API silently drops cache_control on input_text content blocks during transformation Fix LiteLLM Azure OAI authentication error after upgrading to 1.84.0 when using enable_azure_ad_token_refresh Includes evidence for LiteLLM troubleshooting demand.
LiteLLM AuthenticationError: AzureException AuthenticationError - The api_key client option must be set either by passing api_key to the client or by setting the OPENAI_API_KEY environment variable Fix LiteLLM global_max_parallel_requests not enforcing the configured limit, allowing unlimited concurrent requests through Includes evidence for LiteLLM troubleshooting demand.
set global_max_parallel_requests not work Fix LiteLLM 401 Unauthorized when querying single model info via /v1/models/{model} Includes evidence for LiteLLM troubleshooting demand.
Only proxy admin can be used to generate, delete, update info for new keys/users/teams. Route=/v1/models/{model} Fix LiteLLM A2A /a2a/{id}/message/send returning -32603 Stream consumed error Includes evidence for LiteLLM troubleshooting demand.
-32603 Internal error: Stream consumed Fix LiteLLM budget enforcement blocking free model discovery API access Includes evidence for LiteLLM troubleshooting demand.
Budget enforcement blocks model discovery endpoints (allow accessing free models) Fix LiteLLM ghost models not being cleared when using --num_workers > 1 Includes evidence for LiteLLM troubleshooting demand.
Ghost models with --num_workers > 1: Deleted models not cleared from other workers' local cache Fix LiteLLM not returning Retry-After header when all deployments are in cooldown Includes evidence for LiteLLM troubleshooting demand.
No Retry-After header on RouterRateLimitError (all deployments in cooldown) Fix LiteLLM proxy error 'context_management: Extra inputs are not permitted' when using Claude Code with Bedrock InvokeModel Includes evidence for LiteLLM troubleshooting demand.
context_management: Extra inputs are not permitted Fix LiteLLM /metrics endpoint returning 401 unauthorized after upgrading to 1.84.0 Includes evidence for LiteLLM troubleshooting demand.
LiteLLM /metrics endpoint returning 401 after upgrade to 1.84.0 Fix LiteLLM virtual keys not enforcing TPM rate limits correctly Includes evidence for LiteLLM troubleshooting demand.
Incorrect TPM limiting for virtual keys — rate limit not enforced correctly Fix LiteLLM passthrough to AWS Bedrock failing when using Anthropic's /v1/messages endpoint with context_management feature Includes evidence for LiteLLM troubleshooting demand.
LiteLLM /v1/messages passthrough to Bedrock InvokeModel fails — missing compact-2026-01-12 beta header Fix CerebrasException missing credentials error in CI pipeline when using LiteLLM to route to Cerebras provider Includes evidence for LiteLLM troubleshooting demand.
CerebrasException - Missing credentials. Please pass an api_key, workload_identity, admin_api_key, or set CEREBRAS_API_KEY Fix LiteLLM Proxy /metrics endpoint returning unauthorized error after upgrading to version 1.84.0 when behind a reverse proxy Includes evidence for LiteLLM troubleshooting demand.
LiteLLM Proxy /metrics endpoint returns unauthorized error after upgrade to 1.84.0 Fix LiteLLM proxy 400 validation error when Claude Code sends multi-turn conversations Includes evidence for LiteLLM troubleshooting demand.
177 validation errors: Input should be a valid string Fix LiteLLM budget exceeded blocking model discovery endpoints Includes evidence for LiteLLM troubleshooting demand.
LiteLLM HTTP 429 Budget Exceeded on GET /v1/models Fix LiteLLM additional_drop_params not working on /v1/messages endpoint for Bedrock Includes evidence for LiteLLM troubleshooting demand.
LiteLLM additional_drop_params ignored: context_management field forwarded to Bedrock causing 400