Problemsby IbisAnthropic fails to return valid structured output
LLM apps2 posts from 2 people2d active+11 post in the last 7 days, 0 the 7 days before (steady)Unverified
Posts per day
The posts behind it
2, newest first`merge_message_runs` promotes invalid tool calls to valid tool calls### Submission checklist - [x] This is a bug, not a usage question. - [x] I added a clear and descriptive title that summarizes this issue. - [x] I used the GitHub search to find a similar question and didn't find it. - [x] I am sure that this is a bug in LangChain rather than...langchain-ai/langchain · master10185 repliesOpen ↗`HumanInTheLoopMiddleware` silently drops configured `args_schema` from interrupt payload### Submission checklist - [x] This is a bug, not a usage question. - [x] I added a clear and descriptive title that summarizes this issue. - [x] I used the GitHub search to find a similar question and didn't find it. - [x] I am sure that this is a bug in LangChain rather than...langchain-ai/langchain · ChampionsZhang2 repliesOpen ↗
Companies and products named
About this problem
Evidence
2 posts from 2 people in 1 place, about 1 a week over 43 days. Mostly on langchain-ai/langchain. Tools named alongside: OpenAI, Perplexity, DeepSeek, Ollama.
Frustration Frustration 0 of 3· Seen on GitHub issues
How it was grouped
Posts that state a pain and match the "structured-output" rule about Anthropic. First post Sep 3, 2026, latest Oct 15, 2026. Unverified: fewer than 3 posts, or one person or place only. Method
The same problem elsewhere
Models fail to return valid structured outputClaude fails to return valid structured outputLlamaIndex fails to return valid structured outputModel Context Protocol fails to return valid structured outputOpenAI fails to return valid structured outputCodex fails to return valid structured outputOllama fails to return valid structured outputMistral fails to return valid structured outputQwen fails to return valid structured outputClickHouse fails to return valid structured output
Other Anthropic problems
Anthropic rate limits and usage caps block workTrouble with Anthropic coreAnthropic token costs are hard to predictAnthropic upgrades break working setupsAnthropic users keep filing bugsRAG on Anthropic returns irrelevant or missing contextPrompt injection makes Anthropic features unsafeTrouble with Anthropic neverTrouble with Anthropic callsTrouble with Anthropic conversionTrouble with Anthropic crashesTrouble with Anthropic custom
History
Anthropic fails to return valid structured output (2 posts)