Skip to content

Claude fails to return valid structured output

LLM apps4 posts from 3 people4d active+33 posts in the last 7 days, 0 the 7 days before (rising)

Posts per day

Posts per day4 posts, Sep 7 to Sep 25

The posts behind it

4, newest first
PostDate
`ChatAnthropic` sends unsupported tool choice and thinking configurations for Claude Opus 5.5### 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/langchainChampionsZhangSep 232 days ago
ChatAnthropic.bind_tools() raises ValueError on Anthropic's documented browser_toolset_20260801### 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/langchainChampionsZhangSep 223 days ago
[Bug]: StreamingAgentChatResponse silently drops ThinkingBlock and ToolCallBlock when writing to history### Bug Description In `llama-index-core/llama_index/core/chat_engine/types.py`, `StreamingAgentChatResponse.write_response_to_history` (line 200) and `awrite_response_to_history` (line 259) call `_set_message_content(chat.message, final_text.strip())` before persisting the...run-llama/llama_indextruecallerabrehamSep 205 days ago
server-filesystem: missing inputSchema.type breaks JSON Schema 2020-12 validators (all versions 0.6.2–2025.8.21)...server to work normally in the main chat window (which tolerates the missing field) but fail to start under the "Cowork and Code sessions" shared-pool context, which validates strictly. Log excerpt: [filesystem] [error] Couldn't start for Cowork and Code sessions. Error: Invalid...modelcontextprotocol/serversCraigBetxSep 72 weeks ago

Companies and products named

Company or productPosts naming it
Claude4
DeepSeek3
OpenAI2
Perplexity2
Ollama2
Hugging Face2
About this problem

Evidence

4 posts from 3 people in 3 places, about 1 a week over 17 days. Mostly on langchain-ai/langchain, run-llama/llama_index, modelcontextprotocol/servers. Tools named alongside: DeepSeek, OpenAI, Perplexity, 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 Claude. First post Sep 7, 2026, latest Sep 23, 2026. Corroborated: 3 or more posts from 2 or more people or places. Method

History

  • 2026-09-25 Momentum: new to rising
  • 2026-09-25 Added: Claude fails to return valid structured output (3 posts)

Rising problems by email

Mondays: the problems in data, tech and AI that grew fastest that week.

Double opt-in. Unsubscribe any time.