internal/router/scheduler: add serial scheduler, default on this fork

Add a strict one-model-at-a-time scheduler. Requests run in exact
arrival order; at most one runs at a time; switching to a different
model evicts every other running model first so a single model occupies
memory at a time. Unlike fifo it never reorders or batches same-model
requests, and it ignores group/matrix co-residency entirely, making the
single-model guarantee a property of the scheduler rather than the config.

- new Serial scheduler implementing the Scheduler interface
- register "serial" in scheduler.New; default routing.scheduler.use to
  "serial" at config load (fifo still selectable for upstream behavior)
- update config schema, example config, and config defaults tests

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

config.example.yaml

@@ -556,11 +556,21 @@ routing:
           # expands to: [L]
           full: "L"
 
-  # scheduler: how queued requests are ordered.
-  # The default and only valid scheduler is "fifo"
+  # scheduler: how queued requests are ordered and run.
+  # - optional, default on this fork: "serial"
+  # - valid values:
+  #   - "serial": strict one-model-at-a-time. Requests run in exact arrival
+  #     order; only one request runs at a time; switching to a different model
+  #     evicts every other running model first so a single model occupies memory
+  #     at a time. This ignores group/matrix co-residency entirely. The "fifo"
+  #     settings below (priority) do not apply.
+  #   - "fifo": throughput-oriented. Same-model requests are batched to reduce
+  #     swaps and a model serves up to its concurrencyLimit in parallel; models
+  #     in non-exclusive groups can run concurrently. Requests may be reordered.
   scheduler:
-    use: fifo
+    use: serial
     settings:
+      # fifo settings only apply when use: fifo
       fifo:
         # priority: a dictionary of model ID -> priority
         # - optional, default: empty dictionary