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/11_tools_messages.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": "How do I send prompts to other sessions?"
+    },
+    {
+      "role": "assistant",
+      "content": "<think>\nMessages tools — cross-session communication. Prompt other sessions and read their history.\n</think>\n\nThree tools for cross-session agent communication:\n\n- **messages_prompt** — send a prompt to another session's agent and wait for the full response. The target agent processes the message with all its tools and returns the reply. Synchronous — blocks until done.\n- **messages_prompt_async** — same but returns immediately without waiting. Use `sessions_status` to check when the session goes idle, then `messages_read` to get the result.\n- **messages_read** — read message history from a session. Returns messages with role, text, tool calls, and timestamps. Limit parameter controls how many messages to return.\n\nThese enable multi-agent coordination: create a session on sin, send it a prompt async, continue your own work, check when it's done, read the result. You can override the agent and model per prompt (e.g. send to the build agent using a specific model).\n\nThe `host` parameter lets you communicate across hosts — prompt a session on sin from fuji, read messages from a junkpile session."
+    }
+  ]
+}