惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

Martin Fowler
Martin Fowler
OSCHINA 社区最新新闻
OSCHINA 社区最新新闻
IT之家
IT之家
美团技术团队
酷 壳 – CoolShell
酷 壳 – CoolShell
Y
Y Combinator Blog
T
Tailwind CSS Blog
D
Docker
博客园 - Franky
freeCodeCamp Programming Tutorials: Python, JavaScript, Git & More
Google DeepMind News
Google DeepMind News
腾讯CDC
Vercel News
Vercel News
Engineering at Meta
Engineering at Meta
U
Unit 42
The Cloudflare Blog
S
SegmentFault 最新的问题
WordPress大学
WordPress大学
爱范儿
爱范儿
Recent Announcements
Recent Announcements
博客园 - 聂微东
博客园 - 叶小钗
H
Help Net Security
MyScale Blog
MyScale Blog

LangChain Forum - Topics tagged intro-to-langgraph

Does HITL approval actually bind the action that reaches the executor? Production use of PostgresSaver: service-owned migrations and checkpoint retention in Node.js How are you guys stopping agents from silent loops/stampedes? Standard step_counters feel like garbage Introducing Langshark a local-first companion observability tool for self-hosted Langgraph deployments Help Needed : Best practices for client-side metadata filtering in custom checkpoint implementations? How do you actually decide between LangGraph, AutoGen, and which model to use for a task? Feedback requested: evaluating commit-time action validity in LangGraph workflows Research Q: what blocks your first LangGraph prod deploy? (not a pitch) A LangGraph checkpointer with provable thread deletion (signed erasure receipts) — feedback welcome Adding an end-to-end example: from locally-served model to agentic flow orchestration Deep Agent state cumbersome Sanity-check my LangGraph design before product demo LangGraph orchestration Problem Re-execute / restart from a specific task in a functional API AttributeError: 'AsyncSandboxClient' object has no attribute 'get_template' What is the equivalent of a transaction log for agent systems? Null-drift: A bare-metal O(1) Memory Store for continuous LangGraph agents Interrupt does not work correctly in LangGraph Pre-interrupt() code re-runs on resume — anti-pattern, or is there a sanctioned way to detect resume? Would pre-inference routing help long-context agent workflows? Improving citation accuracy and reducing hallucinations in custom Parent-Child RAG pipeline (Gemma3:4B + FAISS+BM25 + Cross-encoder reranker) WikipediaLoader endup in JSONDecodeError Using LangGraph interrupt for multi-step wizards with branching — right tool or wrong abstraction? Built NORNR for spend governance in agent workflows LangGraph + PostgreSQL: Chat history and summarization best practice Discussion about why LangGraph JS ToolNode doesn’t inject ToolRuntime.state like Python does, and what the correct workaround or intended design pattern is. No cost displayed in LangSmith when using LiteLLM + LangGraph LiteLLM Router in LangChain: Missing Model Name and Cost in LangSmith Traces I find langgraph chat in documents useful, how can I hook it up as mcp or skill or a tool for the Claude Code? Can I get User IDs and Bot IDs of bots used in Slack channels for personal projects
DeltaChannel + RemoveMessage message compression — how to...
pengben945 · 2026-07-14 · via LangChain Forum - Topics tagged intro-to-langgraph

Background I currently use add_messages for message state management. Every checkpoint stores the full message list into PostgreSQL, which causes O(n²) storage growth over long conversations. I’d like to migrate to DeltaChannel for incremental storage. My graph also performs message compression — using RemoveMessage to delete old messages to keep context window manageable. My Confusion With add_messages, RemoveMessageis interpreted by the reducer and the target message is removed from the ac...