LangChain rate limits and usage caps block work

LLM apps2 posts from 2 people2d active+11 post in the last 7 days, 0 the 7 days before (steady)Unverified

Posts per day2 posts, Aug 29 to Sep 27

The posts behind it

2, newest first

Post	Where	Date
[FEATURE] Let LLMGuardrail use a separate LLM from the agent it judges (currently the same instance by default)### Feature Area Agent capabilities ### Is your feature request related to a an existing bug? Please link it here. Related to #7150 (raised there under "Additional context"; separated out as offered). ### Describe the solution you'd like When a task or agent has a string...crewAIInc/crewAIAlkur123	crewAIInc/crewAIAlkur1231 replies	Sep 252 days ago
structuredContent is dropped from isError=True tool results (but preserved on success)## Summary `_convert_call_tool_result` extracts `CallToolResult.structuredContent` into the `MCPToolArtifact` only on the success path. When `isError=True` it raises `_MCPToolExecutionError` before `structuredContent` is read, so a machine-readable error payload is silently...langchain-ai/langchainglenlouis8	langchain-ai/langchainglenlouis811 replies	Aug 294 weeks ago

Companies and products named

Company or product	Posts naming it
LangChain	2
Model Context Protocol	1

About this problem

Evidence

2 posts from 2 people in 2 places, about 1 a week over 28 days. Mostly on langchain-ai/langchain, crewAIInc/crewAI. Tools named alongside: Model Context Protocol.

Frustration Frustration 0 of 3· Seen on GitHub issues

How it was grouped

Posts that state a pain and match the "rate-limits" rule about LangChain. First post Aug 29, 2026, latest Sep 25, 2026. Unverified: fewer than 3 posts, or one person or place only. Method

The same problem elsewhere

Posts per day

The posts behind it

Companies and products named

Rising problems by email