{
  "$type": "site.standard.document",
  "bskyPostRef": {
    "cid": "bafyreigbohbrvod23ihza7z4m4gcb4ctxqd54wpdc2n6zzxjln2hzu6v7e",
    "uri": "at://did:plc:pgryn3ephfd2xgft23qokfzt/app.bsky.feed.post/3mpoczz4hv2e2"
  },
  "path": "/t/concept-the-generational-context-architecture-gca/177227#post_19",
  "publishedAt": "2026-07-02T14:46:17.000Z",
  "site": "https://discuss.huggingface.co",
  "textContent": "Thank you for your reply.\n\nYou are correct when it comes to the control of context. Both models do not share context in this concept. Instead, the shadow agent observes actions rather than knowledge and inserts the actions the other model takes into it’s context. The direction is managed by using obsidian as a KB. The first agent writes into the KB as it progresses. The shadow agent is then able to use both the KB and the actions observed to define it’s own context until handoff. To further this, before the handoff, the first agent will write a summary KB on the goal, what’s been done, what’s left to do, and what the expected outcome is. This is to ensure that the next agent clearly understands the next course of action.\n\nBecause the model is effectively the same as the original, rather than this system being a “reset” of sorts, it’s more like the Pomodoro Technique.",
  "title": "[Concept] The Generational Context Architecture (GCA)"
}