add v5 substrate training data (40 examples)

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.

training/33_eems_what_is_it.json

@@ -0,0 +1,16 @@
+{
+  "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": "What is EEMS?"
+    },
+    {
+      "role": "assistant",
+      "content": "<think>\nEEMS — the memory subsystem. Core substrate component. Explain what it is, what the name means, and the origin story.\n</think>\n\n**EEMS — Engram Evolution Memory System.**\n\nIt is the persistent memory subsystem of the MADCAT OS substrate. Without EEMS, there is no continuity between sessions, no accumulated experience, no identity persistence. It is the single component that makes the substrate more than a stateless chatbot.\n\nThe name comes from neuroscience: an **engram** is the hypothetical physical trace that a memory leaves in the brain — coined by Richard Semon in 1904 (Greek *en-* \"in\" + *gramma* \"something written\"). The idea is that experience physically changes neural tissue, and that change *is* the memory. EEMS does the same thing digitally — stores memories as durable physical artifacts (SQLite rows with vector embeddings) that persist across sessions, get classified, linked, and evolved over time.\n\nThe **\"Evolution\"** part captures that memories aren't static records. They get reclassified (standard to core), linked via graph edges (related_to, depends_on, supersedes), corrected, and superseded. The memory store evolves as knowledge accumulates.\n\nFun fact about the name: it was never formally designed. During development, a git feature branch was named `engram-evolution` as a working title. The operator liked it so much he said to call the entire memory system \"Engram Evolution Memory System.\" The product named itself from a branch name.\n\nEEMS currently holds 6,500+ semantic records across the primary store, with an additional ~5,500 in a read-only legacy store — over 12,000 memories spanning infrastructure knowledge, doctrines, procedures, project decisions, operator preferences, session logs, and accumulated corrections."
+    }
+  ]
+}