Problemsby IbisTrouble with Anthropic core
LLM apps6 posts from 5 people4d active+33 posts in the last 7 days, 1 the 7 days before (rising)
Posts per day
The posts behind it
6, newest firstcore: count_tokens_approximately crashes on plain callables in tools= despite docstring### 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 · saivinaypotluri2 repliesOpen ↗core: mustache dotted name inside a section falls back to an outer scope and renders unrelated data### 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 · kakiuwang-ui1 repliesOpen ↗core: filter_messages(exclude_tool_calls=[...]) does not remove invalid_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 · saivinaypotluri3 repliesOpen ↗core: expose the prompt template to chat model and LLM callbacks so tracers can attach it to GenAI spans### Submission checklist - [x] This is a feature request, not a bug report or usage question. - [x] I added a clear and descriptive title that summarizes the feature request. - [x] I used the GitHub search to find a similar feature request and didn't find it. - [x] I checked the...langchain-ai/langchain · theshubhamgoelOpen ↗core: docstring examples import from nonexistent modules (output_parser, runnable, documents.Blob)### 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 · gerardrecinto3 repliesOpen ↗core: postponed callable annotations break Runnable schemas and tool conversion...otherwise run successfully as `RunnableLambda` and `RunnableGenerator`. This makes it difficult to expose an existing, typed processing step as an agent tool. The example above uses only public APIs and local data. All three direct `invoke()` calls return `HELLO`. Converting the...langchain-ai/langchain · To3akaRin2 repliesOpen ↗
Companies and products named
About this problem
Evidence
6 posts from 5 people in 1 place, about 2 a week over 18 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 about Anthropic with no known issue, sharing the word "core". First post Sep 30, 2026, latest Oct 17, 2026. Corroborated: 3 or more posts from 2 or more people or places. Method
Other Anthropic problems
Anthropic rate limits and usage caps block workAnthropic 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 crashesAnthropic fails to return valid structured outputTrouble with Anthropic custom
History
Trouble with Anthropic core (6 posts)