feat: unified model registry with role-based routing

Introduces model_registry.py as the single source of truth for all LLM
backend configuration. Replaces scattered backend settings across user_settings,
config distill_backend_*, and the UI toggle.

model_registry.py:
- Per-user home/{user}/model_registry.json with version, hosts, models, roles
- Models have: type (local_openai|claude_cli|gemini_cli|gemini_api), label,
  model_name, host_id, context_k (tokens), tags (capability labels)
- Roles map to priority chains: primary, backup_1..backup_4
- Built-in IDs (claude_cli, gemini_cli, gemini_api) always resolvable
- Auto-migrates existing local_llm.json on first access
- CRUD: save_host, remove_host, save_model, remove_model, set_role
- get_model_for_role(): registry → .env default → hardcoded fallback

config.py:
- role_chat/orchestrator/distill/coder/research .env defaults
- defined_roles: comma-separated standard role list (extensible)
- get_defined_roles() and get_role_default() helper methods

llm_client.complete():
- New role= parameter (default "chat") for registry-based routing
- model= still accepted for explicit UI toggle override
- _claude() and _local() accept model_cfg dict instead of raw string
- _local() uses pre-resolved config from registry

memory_distiller.py:
- distill_mid/long now use role="distill" (no more distill_backend_* .env vars needed)

cron_runner.py:
- brief jobs use role="chat"

routers/chat.py + auth.py:
- Use model_registry instead of user_settings for local model info

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

cortex/memory_distiller.py

@@ -92,7 +92,6 @@ async def distill_mid(username: str | None = None, persona: str | None = None) -
     if not short_content.strip() or "Not yet populated" in short_content:
         return {"error": "MEMORY_SHORT.md is empty — run distill/short first"}
 
-    backend_override = settings.distill_backend_mid or None
     budget_tokens = settings.memory_budget_mid
     system_prompt = (
         f"You are {settings.agent_name}'s memory distillation system. "
@@ -107,7 +106,7 @@ async def distill_mid(username: str | None = None, persona: str | None = None) -
     response_text, backend = await complete(
         system_prompt=system_prompt,
         messages=[{"role": "user", "content": short_content}],
-        model=backend_override,
+        role="distill",
     )
 
     now = datetime.now().strftime("%Y-%m-%d %H:%M")
@@ -146,7 +145,6 @@ async def distill_long(username: str | None = None, persona: str | None = None)
     if not mid_content.strip() or "Not yet populated" in mid_content:
         return {"error": "MEMORY_MID.md is empty — run distill/mid first"}
 
-    backend_override = settings.distill_backend_long or None
     budget_tokens = settings.memory_budget_long
     system_prompt = (
         f"You are {settings.agent_name}'s long-term memory curator. "
@@ -165,7 +163,7 @@ async def distill_long(username: str | None = None, persona: str | None = None)
     response_text, backend = await complete(
         system_prompt=system_prompt,
         messages=[{"role": "user", "content": user_content}],
-        model=backend_override,
+        role="distill",
     )
 
     # Ensure the file has the right header if the LLM dropped it