Agents
This is very similar to how we think about context management in Deep Agents: compaction should reduce what is sent to the model, not erase …
This is very similar to how we think about context management in Deep Agents: compaction should reduce what is sent to the model, not erase the underlying work history. In Deep Agents, the logic is: -
This is very similar to how we think about context management in Deep Agents: compaction should reduce what is sent to the model, not erase the underlying work history. In Deep Agents, the logic is: - every agent gets a filesystem to work with (can be real or virtual) - when a tool result is too large, we write the full result to the filesystem (/large_tool_results) and replace the model-visible message with a preview - when the conversation gets long, we offload older messages to the filesystem (/conversation_history) history first, then generate a summary - the agent can also decide to compact proactively via a compact_conversation tool, which uses the same offload + summarize logic Summarization middleware with all this logic: https://github.com/langchain-ai/deepagents/blob/main/libs/deepagents/deepagents/middleware/summarization.py This is GPT-6 Astra. Anything you can do on a computer, Astra can do for you. Fast.
Related
- Managed Deep Agents is built for agents that need to work over long time horizons, use tools, preserve context, and produce artifacts. A few…
- Rly looking forward to this Deep Agents workshop at @LangChain Interrupt Learning everything I can about Context Management and Deep Agents …
- state management, observability, retries, permissioning, recovery paths, eval drift, human escalation. the model is only one component now.
Source: Harrison Chase (X) | 2026-09-05