{
  "schema": "vedokrok.public-item.v1",
  "release_id": "MHC-RPUB-20260920-75ad787a",
  "url": "/knowledge/separate-session-state-from-long-term-memory",
  "id": "MHC-D-RESEARCH-0703",
  "version": "0.1.0",
  "title": "Separate session state from long-term memory",
  "summary": "What the agent needs for the next hour is not the same thing it should remember next month.",
  "kind": "principle",
  "body": "Keep short-lived execution state—current step, temporary errors, open tool handles—separate from durable project knowledge such as decisions, accepted terminology, architecture, source references and unresolved risks. Persist only the latter deliberately. This makes it possible to restart a worker without turning every transient event into permanent memory.",
  "limits": [
    "Some transient-looking events become important evidence after failure; retain raw logs according to audit and incident needs even if they are not promoted into memory."
  ],
  "topics": [
    "union-ai-context-memory-skills"
  ],
  "intents": [],
  "source_ids": [
    "RS-8822822B8E30525B"
  ],
  "evidence": [
    {
      "claim": "Current long-horizon agent practice distinguishes transient working context from durable state that can survive context resets or worker replacement.",
      "source_id": "RS-8822822B8E30525B",
      "role": "supports",
      "note": "A durable log is one architecture; structured snapshots or databases may be better for other systems.",
      "locator": "Durable history, disposable execution"
    }
  ],
  "use_when": [
    "A project spans multiple conversations, workers or models."
  ],
  "avoid_when": [
    "Some transient-looking events become important evidence after failure; retain raw logs according to audit and incident needs even if they are not promoted into memory."
  ],
  "example": "A failed test command belongs in the session log; the discovery that a specific interface requires a legacy mapping belongs in durable project memory.",
  "check": "A new worker can recover durable decisions without inheriting every temporary detour.",
  "sources": [
    {
      "id": "RS-8822822B8E30525B",
      "title": "The Log Is The Agent",
      "url": "https://ai.engineer/talks/UPwGaM2MKHY-log-is-agent"
    }
  ],
  "relations": [
    {
      "from": "MHC-D-RESEARCH-0703",
      "to": "MHC-D-RESEARCH-0704",
      "type": "use_before",
      "url": "/knowledge/give-agent-memory-a-write-manage-read-policy"
    }
  ],
  "collections": [
    {
      "id": "RC-74B3DD1F3F9BDCB4",
      "title": "Give AI the right context, memory and reusable skills",
      "url": "/collections/give-ai-the-right-context-memory-and-reusable-skills"
    }
  ]
}