langchain-model-inference
Best for Production code using LangC…Works with GitHub
⌘source
- author
@jeremylongshore- language
- Python
★2kstars
268forks
Apr 22, 2026
✦overview.md
Key Features
- ·Handles AIMessage.content list-vs-string divergence
- ·Manages withstructuredoutput quirks for Optional[list] fields
- ·Addresses temperature=0 non-determinism on Anthropic
- ·Works with Claude, GPT-4o, and Gemini through LangChain 1.0
- ·Avoids content-block and token-accounting pitfalls
Use Cases
- →Initializing chat models across multiple providers
- →Routing AI requests between Claude, GPT-4o, and Gemini
- →Iterating through AIMessage content blocks safely
- →Choosing appropriate structured-output methods for schemas
Best for
- ✓Production code using LangChain 1.0
- ✓Multi-provider AI applications
- ✓Teams working with Claude's structured responses
Not ideal for
- !Simple single-provider implementations
- !Projects not using LangChain
FAQs
name
langchain-model-inference
description
Invoke Claude, GPT-4o, and Gemini through LangChain 1.0 without tripping on
the content-block, token-accounting, and structured-output quirks that silently
break production code. Use when initializing chat models, routing across providers,
iterating AIMessage content, or choosing a structured-output method.
Trigger with "langchain model inference", "ChatAnthropic", "ChatOpenAI",
"with_structured_output", "AIMessage content blocks", "langchain routing".
license
MIT
allowed-tools:Read, Write, Edit, Bash(python:*), Bash(pip:*), Grep
version:2.0.0
author:Jeremy Longshore <jeremy@intentsolutions.io>
tags:["saas","langchain","langgraph","python","langchain-1.0","model-inference"]
compatible-with:claude-code, codex
LangChain Model Inference (Python)
Overview
AIMessage.content is a str on simple OpenAI calls and a list[dict] on Claude
the instant any tool_use, thinking, or image block enters the response.
Code that does message.content.lower() crashes with
AttributeError: 'list' object has no attribute 'lower' — the #1 first-production-call
LangChain 1.0 bug on Anthropic. And that is one of four separate "content shape"
pitfalls in this skill:
- P02 —
AIMessage.contentlist-vs-string divergence - P03 —
with_structured_output(method="function_calling")silently dropsOptional[list[X]]fields on ~40% of real schemas - P05 —
temperature=0is not deterministic on Anthropic even though it is on OpenAI - P58 — Claude expects the system message at position 0; middleware that reorders messages makes it silently ignored
This skill walks through ChatAnthropic, ChatOpenAI, and ChatGoogleGenerativeAI
initialization; model routing; token counting that is actually correct during
streaming; content-block iteration; and a decision tree for with_structured_output
methods that holds up on real schemas. Pin: langchain-core 1.0.x,
$install
1-click copynpx skills add jeremylongshore/claude-code-plugins-plus-skills --skill langchain-model-inferenceSafety assessment
★
Clarity score
How clear and easy to understand the SKILL.md instructions are, rated from 1 to 5.
3/ 5
goodMostly clear, but there are still a few confusing or poorly structured parts.
◎
Actionability score
How directly an agent can act on the SKILL.md instructions, rated from 1 to 5.
3/ 5
mediumPartially actionable with several concrete steps, but still missing important details.