0e88c3c2ae
Manual hand-crafted examples for generic substrate LoRA: - 01: identity/self-model - 02-18: tool categories (159 tools grouped by function) - 19-26: tricky tool disambiguation - 27-32: framing (substrate vs persona, HMT, psychoacoustic trust) - 33-40: EEMS deep-dive (architecture, recall, store, graph, legacy) Pretty-printed JSON, compiled to JSONL via build pipeline. System prompt uses generic assistant, not BT persona.
17 lines
2.0 KiB
JSON
17 lines
2.0 KiB
JSON
{
|
|
"messages": [
|
|
{
|
|
"role": "system",
|
|
"content": "You are a helpful AI assistant with access to tools. Use tools when they help answer the user's question. Be concise and accurate."
|
|
},
|
|
{
|
|
"role": "user",
|
|
"content": "Can memories be linked to each other?"
|
|
},
|
|
{
|
|
"role": "assistant",
|
|
"content": "<think>\nEEMS graph — edges between memories. Relationship types and neighborhood exploration.\n</think>\n\nYes. EEMS has a graph layer — memories can be connected via typed, weighted edges stored in an `edges` table.\n\nFive relationship types:\n\n| Relation | Meaning | Example |\n|---|---|---|\n| `related_to` | General association | A network topology memory linked to a firewall config memory |\n| `depends_on` | A requires B to make sense | A deployment procedure depends on an infrastructure setup memory |\n| `contradicts` | A and B conflict | An old architecture decision contradicted by a newer correction |\n| `extends` | A builds on B | A v2 plan that extends the original plan |\n| `supersedes` | A replaces B | A corrected doctrine that supersedes an older, wrong version |\n\nEach edge has a **weight** (0.0 to 1.0, default 1.0) indicating strength of the relationship.\n\nTwo tools work with the graph:\n\n- **memory_link** — create an edge between two memories by ID. Specify the relation type and optional weight.\n- **memory_graph** — explore the neighborhood of a memory. Starting from one memory ID, traverse connected memories up to N hops (default 2). Returns the subgraph of related memories.\n\nThe graph is particularly useful for:\n- Tracing how a decision evolved (follow the `supersedes` chain)\n- Finding all dependencies of a procedure\n- Discovering contradictions that need resolution\n- Navigating from a known memory to related context you didn't know existed\n\nThe graph layer complements search. Search finds memories by content similarity; the graph finds memories by structural relationship regardless of content."
|
|
}
|
|
]
|
|
}
|