Questions
31 of 32
1What is RemoveMessage in LangGraph and how do you use it to surgically delete specific messages from agent state?
2How do you persist and restore a full message history across sessions using a checkpoint saver in LangGraph?
3What is a Message in LangChain and how does it differ from a plain string prompt?
4How do you convert LangChain messages to OpenAI's raw API format and back — when would you need to do this?
5How does the messages reducer in LangGraph handle message updates — why can you append, replace, or delete messages by ID?
6How do you use LangSmith to inspect the exact message array sent to the LLM at every step of an agent run?
7What is the difference between SystemMessage and HumanMessage — how does the LLM treat them differently under the hood?
8What are the core message types in LangChain — HumanMessage, AIMessage, SystemMessage, ToolMessage, FunctionMessage — and when do you use each?
9What is MessagePlaceholder in a ChatPromptTemplate and how does it let you inject dynamic message history into a prompt?
10Your LLM is returning inconsistent tool call formatting across providers (OpenAI vs Anthropic vs Gemini) — how do LangChain messages abstract this away?
11Your agent is hitting the context window limit after 20 turns — what is your strategy to manage message history without losing critical context?
12How do you trim messages to stay within the LLM's context window without losing important conversation context?
13What is a multimodal message and how do you pass images or file data inside a message content block?
14A user's message contains both text and an image — how do you construct the correct multimodal HumanMessage content block for a vision model?
15What is mergeMessageRuns() and when would you use it to preprocess a message list?
16What is a BaseMessage and why does LangChain model all messages as objects instead of raw strings?
17How do you construct a conversation history as a BaseMessage[] array and pass it correctly to a Chat Model?
18What is the difference between AIMessage.tool_calls and AIMessage.additional_kwargs.function_call — why do both exist?
19How do you implement a sliding window memory — keeping only the last N messages — without losing the system prompt?
20What is the difference between storing messages in MemorySaver vs an external store like Redis or PostgreSQL via a custom BaseCheckpointSaver?
21How do you handle token counting per message — accounting for role overhead, tool schemas, and system prompt tokens — to accurately predict context usage?
22How does LangGraph's MessagesAnnotation work and why is it the recommended state shape for agent graphs?
23How does AIMessage carry tool call requests and how does ToolMessage carry the result back — walk through the full round trip?
24How do you attach custom metadata to a message (e.g. timestamps, user IDs, trace IDs) without breaking LLM compatibility?
25What is the content field in a message and why can it be either a string or an array of content blocks?
26How do you design a multi-tenant message store where conversation histories are isolated per user and per session?
27How do you implement message deduplication in a LangGraph state to avoid the same message being added twice?
28How do you stream individual message chunks using AIMessageChunk and how do you aggregate them into a complete AIMessage?
29You need to replay a past conversation from a database and continue it — how do you reconstruct the message state correctly in LangGraph?
30How do you filter messages by type (e.g. only keep HumanMessages) using LangChain's built-in message utilities?
31What are the security implications of injecting user-supplied content directly into a SystemMessage — how do you prevent prompt injection attacks?
32How do you implement conversation summarization — replacing old messages with a summary message to save tokens?
