Problemsby IbisOpenAI runs out of context on real work
LLM apps2 posts from 2 people2d active+00 posts in the last 7 days, 1 the 7 days before (fading)Unverified
Posts per day
The posts behind it
2, newest first[BUG] BaseLLM.get_input_tokens_count fallback ignores tools and response_model## Description `BaseLLM.get_input_tokens_count()` (`lib/crewai/src/crewai/llms/base_llm.py`) is the fallback estimator used when a provider has no native token-count endpoint. It documents `tools` and `response_model` as "included in the request" and promises "a conservative...crewAIInc/crewAI · WinorenOpen ↗[Bug]: OpenAI "exceeds the context window" and Moonshot "exceeded model token limit" errors not mapped to ContextWindowExceededError### What happened? These context window errors come through as plain `BadRequestError` rather than `ContextWindowExceededError`, so `context_window_fallbacks` do not trigger and clients cannot tell them apart from other 400s: - **OpenAI's current message** (code...BerriAI/litellm · jjallaire2 repliesOpen ↗
Companies and products named
About this problem
Evidence
2 posts from 2 people in 2 places, about 1 a week over 21 days. Mostly on BerriAI/litellm, crewAIInc/crewAI. Tools named alongside: Claude Code, Perplexity, Mistral, GitHub.
Frustration Frustration 0 of 3· Seen on GitHub issues
How it was grouped
Posts that state a pain and match the "context-window" rule about OpenAI. First post Sep 24, 2026, latest Oct 14, 2026. Unverified: fewer than 3 posts, or one person or place only. Method
The same problem elsewhere
Context windows run out on real workloadsClaude Code runs out of context on real workClaude runs out of context on real workChatGPT runs out of context on real workCursor runs out of context on real workOllama runs out of context on real workllama.cpp runs out of context on real workvLLM runs out of context on real workCodex runs out of context on real workQwen runs out of context on real workLlamaIndex runs out of context on real workAnthropic runs out of context on real work
Other OpenAI problems
Fine-tuning OpenAI is costly and unpredictableOpenAI users keep asking for helpRunning OpenAI locally hits memory and speed limitsOpenAI upgrades break working setupsTrouble with OpenAI chatTrouble with OpenAI responsesOpenAI fails to return valid structured outputTrouble with OpenAI astraTrouble with OpenAI customTrouble with OpenAI imageOpenAI tables suffer from small files and skewTrouble with OpenAI crashes
History
steady to fading
OpenAI runs out of context on real work (2 posts)