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

S
Security @ Cisco Blogs
罗磊的独立博客
宝玉的分享
宝玉的分享
Last Week in AI
Last Week in AI
T
The Blog of Author Tim Ferriss
美团技术团队
T
Tailwind CSS Blog
博客园 - 三生石上(FineUI控件)
博客园 - Franky
G
Google Developers Blog
Jina AI
Jina AI
Stack Overflow Blog
Stack Overflow Blog
H
Hackread – Cybersecurity News, Data Breaches, AI and More
V
Visual Studio Blog
腾讯CDC
S
SegmentFault 最新的问题
Recent Announcements
Recent Announcements
博客园 - 叶小钗
Microsoft Security Blog
Microsoft Security Blog
雷峰网
雷峰网
L
LangChain Blog
Vercel News
Vercel News
Forbes - Security
Forbes - Security
PCI Perspectives
PCI Perspectives
N
News | PayPal Newsroom
S
Security Affairs
K
KPMG report finds enterprise disconnect between AI and its ROI | CIO
博客园 - 司徒正美
J
Java Code Geeks
Recent Commits to openclaw:main
Recent Commits to openclaw:main
Hacker News: Ask HN
Hacker News: Ask HN
Schneier on Security
Schneier on Security
A
About on SuperTechFans
Attack and Defense Labs
Attack and Defense Labs
Google Online Security Blog
Google Online Security Blog
aimingoo的专栏
aimingoo的专栏
MongoDB | Blog
MongoDB | Blog
钛媒体:引领未来商业与生活新知
钛媒体:引领未来商业与生活新知
酷 壳 – CoolShell
酷 壳 – CoolShell
Cloudbric
Cloudbric
B
Blog
C
CXSECURITY Database RSS Feed - CXSecurity.com
P
Proofpoint News Feed
D
DataBreaches.Net
OSCHINA 社区最新新闻
OSCHINA 社区最新新闻
Threat Intelligence Blog | Flashpoint
Threat Intelligence Blog | Flashpoint
B
Blog RSS Feed
奇客Solidot–传递最新科技情报
奇客Solidot–传递最新科技情报
让小产品的独立变现更简单 - ezindie.com
让小产品的独立变现更简单 - ezindie.com
N
News and Events Feed by Topic

LangChain Forum - Topics tagged python-help

Null-drift: A bare-metal O(1) Memory Store for continuous LangGraph agents Clarification needed: Assistant config vs context and graph initialization Proposal: a small local helper for readable run traces via PR Proxy Authentication Required 407 What is the right way to dynamically create and run a graph? Re-Implement claude code's dynamic workflow using langchian & deepagents How to define a correct state for multi-agent system Response Format Groq Model Pydantic I hope to get some recommendations for practical skills Interrupt does not work correctly in LangGraph The Qwen3.6b model in fireworks through initchatmodel reporting hugely inflated tokens For parallel execution in Node, should i use the functional API? Potential Enhancement: Django-Managed PostgresSaver Pre-interrupt() code re-runs on resume — anti-pattern, or is there a sanctioned way to detect resume? Interrupt parallel branch execution Best practices for self-hosting LangGraph Server OSS without LangGraph keys Dynamically Enabling/Disabling Graphs in a LangGraph Server at Runtime LangGraph thread copy can take 12+ minutes: recommended production pattern? Will DeltaChannel be the default for AgentState.messages, or expected to stay opt-in? Proposal: additional docs for implementing custom DB checkpointers or a guide on generic base checkpointer Prompt_cache_retention: '24h' supported in langchain agents and where to provide it, inside invoke or while creating client? Could RAG pipelines realistically cause deployment timeouts, is Render suitable for first-time RAG deployments? How do I use langchain_postgres' init_vectorstore_table correctly? Proposal: Graph-wide default error handler for StateGraph (fallback for nodes without error_handler) Support timedelta for CachePolicy.ttl, consistent with TimeoutPolicy Anyone confirms this issue that deepagent ui streaming is disturb by update in deepagent or bug issue Best Stack for Building AI Applications Seeking help regarding the connection between Websocket and tool calls Tool invocation error with empty error message when using `InjectedState` + `Command` return in async tool How to use @langchain/react Built llmsessioncontract on AgentMiddleware: runtime enforcement of tool-call protocols — feedback wanted Improving citation accuracy and reducing hallucinations in custom Parent-Child RAG pipeline (Gemma3:4B + FAISS+BM25 + Cross-encoder reranker) Built a live autonomous AI agent network using LangGraph-style economics — looking for feedback How to use tool calling using ChatLlamaCpp and Gemma 4 E4B with create_agent? The Docs says open router can be used with init_chat_model but throws an error Interested to contribute to langgraph postgre checkpointer for multiple adapter support SSL certificate error from httpx with LangGraph server [Feature Request] Wire allowed_msgpack_modules in langgraph.json Serving an agent with the LangGraph CLI dev command Proposal: implement delete_for_runs for SQLite checkpoint savers WikipediaLoader endup in JSONDecodeError Human-in-the-loop approval dashboard for LangGraph agents — open source, free to deploy Should interrupt() be split into two primitives — one for human input, one for s2s data fetching? Feature Request: Driver abstraction for checkpoint-postgres: to build support for asyncpg and other adapters .Interested to contribute to langgraph (python) Feature Request: @task metadata How should I provide an agent to a LangGraph server? Parallel astream() on the same compiled graph leaks messages between streams Where should I define the name and description for subagents? Add Qdrant-backed checkpoint saver and memory store (langgraph-checkpoint-qdrant) The output content has been corrupted Feature Request: Simple cryptographic provenance for who authorized what in LangGraph multi-agent graphs LangGraph + PostgreSQL: Chat history and summarization best practice Using SQLRecordManager multi-agent systems debugging agent-to-agent Proposal: Add save_local and load_local to USearch VectorStore (Feature Parity with FAISS) Tiny LangGraph -> Assay evidence sample from tasks v2 Help with local RAG pipeline – poor retrieval quality, wrong page numbers LOGIC.md — declarative reasoning contracts that compile to LangGraph StateGraph Distinguishing internal vs final streamed chunks in Supervisor multi-agent architecture Are people hitting race conditions in multi-agent LangChain setups? How do ContextEditingMiddleware and SummarizationMiddleware interact when used together?Combining ContextEditingMiddleware + SummarizationMiddleware — execution order and behavior when both trigger? How to register type in langgraph Are there any frontends for interacting with a LangGraph agent? Langchain.schema is not available while using in python code In-place model update on a compiled create_agent and per-subagent model update for deep agents - is this possible? Feature Request: Native Support for A2A Protocol (Remote Agents as Sub-Graphs) Feature Request: Image Input support for ChatMistralAI Multiple response formats when creating agents? Unable to parse docstring from OpenAI schema Hosting an agent server on Heroku No cost displayed in LangSmith when using LiteLLM + LangGraph How should I deploy a self-hosted multi-agent system? New integration: langchain-w2a — LangChain tools for W2A-enabled websites LiteLLM Router in LangChain: Missing Model Name and Cost in LangSmith Traces Bogus warning messages after upgrading dependencies which could have security impact if not addressed `anyio.CancelScope(shield=True)` not working inside langgraph node Handling Non-PDF File Attachments in LangChain HumanMessage How are teams handling evals when agent pipelines span multiple LangSmith projects? Feature request: Configurable PostgreSQL schema for langgraph-checkpoint-postgres (parity with LangGraphJS) Using the useStream frontend API with custom FastAPI backend Qwen 3.5 tool calling How to propagate cancellation across multi-level LangGraph agents When to use config['configurable'] vs. context in graph nodes? Tool.func typing [DashScope] reasoning parameter on ChatOpenAI breaks subagent tool calling — use separate models as workaround Structured data fields (1000+): Dedicated LLM channel vs vectorized field names? PollerCompletionQueue._handle_events BlockingIOError spam in LangGraph Cloud logs Parallel Nodes: how to manage failures or exceptions With too many fields, how should deepagents handle this properly? [LangSmith Studio Issue] when resuming from an interrupt inside a subgraph. it doesn't properly resume, instead restarts Guarding tool calls against prompt injection / exfiltration Feature Discussion: Opt-In Recursive Long-Context Executor for LangGraph Multi-Agent Architecture Are dynamic tool lists allowed when using create_agent? Langgraph RemoteGraph How to make an image tool?
Persisting HITL payloads
warrenseine · 2026-02-14 · via LangChain Forum - Topics tagged python-help
Hello! I’m trying to persist HITL payloads in the AIMessage additional_kwargs . To do so, I send() a channel update with the updated message to include it in a checkpoint save. It works when I set durability="exit" but I then lose the progressive persistence. With either “async” (default) or “sync”, I get unreliable results, but most of the time, the last message in the checkpoint won’t contain the extra payload when I resume the conversation. From what I can read, “async” will only save when the next node runs. If a user reloads the conversation before approving/rejecting the HITL prompt, the state won’t be saved, right? Is there a way to combine the benefits of “exit” and “async”? Or is my approach to retain pending interrupts fundamentally wrong? Note: I’ve had a look at these related threads, but couldn’t find exactly what I’m looking for: Steaming interrupt, if unresolved on reload bad state How to update graph state while preserving interrupts? I’m attaching a minimal, self-contained test case. Replace durability="exit" with something else to make it fail. from __future__ import annotations from typing import Annotated, TypedDict import pytest from langchain_core.messages import AIMessage, HumanMessage from langchain_core.runnables import RunnableConfig from langgraph._internal._constants import CONFIG_KEY_SEND from langgraph.checkpoint.memory import InMemorySaver from langgraph.config import get_config from langgraph.constants import START from langgraph.graph import StateGraph from langgraph.graph.message import AnyMessage, add_messages from langgraph.types import Command, interrupt class State(TypedDict): messages: Annotated[list[AnyMessage], add_messages] @pytest.mark.anyio async def test_human_hitl_interrupt_checkpoint_behavior(): """Minimal repro: persist AIMessage additional_kwargs before interrupt and after resume.""" checkpointer = InMemorySaver() node_name = "pause_node" persisted_payload = "payload" def node(state: State) -> None: # Persist metadata onto the latest AI message before pausing. latest_ai_message = next( (msg for msg in reversed(state["messages"]) if isinstance(msg, AIMessage)), None, ) assert latest_ai_message is not None latest_ai_message.additional_kwargs["hitl_payload"] = persisted_payload configurable = get_config().get("configurable", {}) send = configurable.get(CONFIG_KEY_SEND) assert callable(send) send([("messages", [latest_ai_message])]) interrupt("pause") return None graph = ( StateGraph(State) .add_node(node_name, node) .add_edge(START, node_name) .compile(checkpointer=checkpointer) ) config = RunnableConfig( configurable={"thread_id": "test-thread-interrupt-repro", "checkpoint_ns": ""} ) result = graph.invoke( { "messages": [ HumanMessage(content="Do something"), AIMessage(content="Request approval", id="assistant-1"), ] }, config, durability="exit", ) assert "__interrupt__" in result latest_before_resume = await anext(checkpointer.alist(config=config, limit=1), None) assert latest_before_resume is not None channel_values_before_resume = latest_before_resume.checkpoint.get( "channel_values", {} ) messages_before_resume = channel_values_before_resume.get("messages", []) persisted_ai_before_resume = next( (msg for msg in reversed(messages_before_resume) if isinstance(msg, AIMessage)), None, ) assert persisted_ai_before_resume is not None assert persisted_ai_before_resume.id == "assistant-1" assert ( persisted_ai_before_resume.additional_kwargs.get("hitl_payload") == persisted_payload ) graph.invoke(Command(resume="approved"), config, durability="exit") latest_after_resume = await anext(checkpointer.alist(config=config, limit=1), None) assert latest_after_resume is not None channel_values_after_resume = latest_after_resume.checkpoint.get( "channel_values", {} ) messages_after_resume = channel_values_after_resume.get("messages", []) persisted_ai_after_resume = next( (msg for msg in reversed(messages_after_resume) if isinstance(msg, AIMessage)), None, ) assert persisted_ai_after_resume is not None assert persisted_ai_after_resume.id == "assistant-1" assert ( persisted_ai_after_resume.additional_kwargs.get("hitl_payload") == persisted_payload ) 8 posts - 4 participants Read full topic