refactor: channel router + scheduler use SDK clients

ChannelRouter: replace raw httpx with AsyncTurnstoneServer (single-node)
and AsyncTurnstoneConsole route methods (multi-node). Remove _post()
helper, _route_path(), and manual JSON construction.

Scheduler: replace raw httpx.Client with TurnstoneServer (sync). Lazy
per-node client cache with token rotation and stale client pruning.

Clean remaining Redis/MQ references from tests, docs, and config:
- test_tls_admin: redis.internal -> app.internal
- test_config: [redis] test data -> [database]
- docs/channels.md, console.md: rewrite for HTTP architecture
- docs/api-reference.md, openshell.md: remove stale diagram/Redis refs
- turnstone.example.toml: remove [redis] section
- .pre-commit-config.yaml: remove types-redis dependency
- QUICKSTART.md: remove bridge/Redis from deployment descriptions

QUICKSTART.md

@@ -45,9 +45,9 @@ That's it — no flags, no arguments. The wizard prompts for everything.
 The wizard supports two deployment modes:
 
 - **Single-node production** (`docker compose --profile production up`) —
-  1 server + bridge + console + PostgreSQL + Redis. Good for most use cases.
+  1 server + console + PostgreSQL. Good for most use cases.
 - **Multi-node cluster** (`docker compose --profile cluster up`) —
-  10-node server/bridge fleet + PostgreSQL + Redis. For high-throughput or
+  10-node server fleet + console + PostgreSQL. For high-throughput or
   HA deployments.
 
 ## Example Session