feat(orchestrator): Phase 2 engine + tokenizer + tool dispatch

Orchestrator engine:
- engine.rs: unified Mistral Conversations API tool loop that emits
  OrchestratorEvent instead of calling Matrix/gRPC directly
- tool_dispatch.rs: ToolSide routing (client vs server tools)
- Memory loading stubbed (migrates in Phase 4)

Server-side tokenizer:
- tokenizer.rs: HuggingFace tokenizers-rs with Mistral's BPE tokenizer
- count_tokens() for accurate usage metrics
- Loads from local tokenizer.json or falls back to bundled vocab
- Config: mistral.tokenizer_path (optional)

No behavior change — engine is wired but not yet called from
sync.rs or session.rs (Phase 2 continuation).

dev/sol-dev.toml

@@ -17,6 +17,7 @@ default_model = "mistral-medium-latest"
 evaluation_model = "ministral-3b-latest"
 research_model = "mistral-large-latest"
 max_tool_iterations = 250
+# tokenizer_path = "dev/tokenizer.json"  # uncomment to use a local tokenizer file
 
 [behavior]
 response_delay_min_ms = 0