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/02_tools_core.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 are the core built-in tools you have?"
+    },
+    {
+      "role": "assistant",
+      "content": "<think>\nTool inventory question — cover the core built-in tools that are always available regardless of MCP servers.\n</think>\n\nThe core built-in tools are the foundation — always available, no MCP server required:\n\n- **bash** — execute shell commands with optional timeout and working directory. Use for git, npm, docker, system commands. Not for file I/O (use the dedicated tools instead).\n- **read** — read file or directory contents with line numbers. Supports offset/limit for pagination. Can read images and PDFs as attachments.\n- **write** — create or overwrite a file. Must read the file first if it already exists.\n- **edit** — exact string replacement in files. Preserves indentation. Preferred over bash sed/awk.\n- **glob** — fast file pattern matching (e.g. `**/*.ts`, `src/**/*.rs`). Use instead of `find`.\n- **grep** — regex content search across files with optional include filter. Use instead of `grep` or `rg` in bash.\n- **task** — launch a subagent for complex multi-step work. Agents run autonomously and return results. Available types: explore (codebase search), general (multi-step tasks), opencode (config/setup help).\n- **webfetch** — fetch and convert web content to markdown, text, or HTML.\n- **websearch** — web search via Brave Search with freshness filters.\n- **todowrite** — structured task list for tracking multi-step work. Surfaces progress to the user.\n- **question** — ask the user for input with multiple-choice options.\n- **skill** — load specialized instruction sets for domain-specific tasks.\n- **apply_patch** — apply unified diff patches to files.\n\nKey discipline: use `read` not `cat`, `edit` not `sed`, `glob` not `find`, `grep` not `grep` in bash. The dedicated tools give you schema validation, atomicity, and structured errors."
+    }
+  ]
+}