marauder-actual
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
2.3 KiB
JSON
17 lines
2.3 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": "How are memories organized in EEMS?"
|
|
},
|
|
{
|
|
"role": "assistant",
|
|
"content": "<think>\nSubject namespacing — the organizational system for EEMS memories. Dot-namespaced categories.\n</think>\n\nMemories are organized by **subjects** — dot-namespaced category strings that group related knowledge. Think of them as a filing system where the dots create a hierarchy.\n\nCommon subject prefixes:\n\n| Prefix | Purpose | Examples |\n|---|---|---|\n| `doctrine.*` | Patterns, principles, locked decisions | `doctrine.training.lora`, `doctrine.mesh-io` |\n| `infra.*` | Infrastructure knowledge | `infra.network`, `infra.vllm.sin-compatible-models` |\n| `project.*` | Project-specific state and decisions | `project.lora.bt7274-v4`, `project.madcat-ml` |\n| `user.*` | Operator preferences and profile | `user.identity.self-model-v5`, `user.psych-profile` |\n| `procedure.*` | Operational procedures | `procedure.lora-training-pipeline` |\n| `research.*` | Research findings | `research.vllm-qwen3-coder-tool-optimizations` |\n| `session.*` | Session handover logs | `session.h200-qwen35-lora-smoke-2026-05-30` |\n| `progress.*` | Sprint/project progress snapshots | `progress.madcat-ml`, `progress.chat-saiden` |\n| `reference.*` | External system pointers | `reference.eems-memories-schema` |\n| `correction.*` | Explicit corrections to earlier knowledge | `correction.specialist-lora-serving-plan` |\n| `architecture.*` | System architecture decisions | `architecture.fs-eems-mirror-pattern` |\n| `vision.*` | Product vision and roadmap | `vision.cart-distribution` |\n\nThe convention is: the prefix tells you the *kind* of knowledge, the rest tells you *what about*. `doctrine.training.lora` is a training doctrine about LoRA. `infra.network` is infrastructure knowledge about the network.\n\nUse `memory_list` to see all subjects with entry counts. Use the `subject` filter on `memory_recall` to narrow search to a specific category. Subjects are exact-match for filtering but semantic recall is robust to slight variations in queries."
|
|
}
|
|
]
|
|
}
|