feat: ServerState data model with serialization

Add dataclasses for ServerState, LoadingInfo, and Metrics to represent
the server's runtime state. ServerState includes a to_dict() method for
serialization with timestamp.

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

log_parser.py

@@ -24,3 +24,39 @@ def classify_line(line: str) -> tuple[str, Optional[int], str]:
     if m:
         return ('child', int(m.group(1)), line[m.end():])
     return ('router', None, line)
+
+
+# ── Data model ───────────────────────────────────────────────────────────────
+
+@dataclass
+class LoadingInfo:
+    stages: list
+    current: str
+    progress: float  # 0.0 – 1.0
+
+
+@dataclass
+class Metrics:
+    prompt_speed: Optional[float] = None   # tokens/sec during prompt eval
+    prompt_tokens: Optional[int] = None    # total prompt tokens
+    gen_speed: Optional[float] = None      # tokens/sec during generation
+    n_decoded: Optional[int] = None        # tokens decoded so far
+
+
+@dataclass
+class ServerState:
+    state: str = "offline"
+    model: Optional[str] = None
+    loading: Optional[LoadingInfo] = None
+    metrics: Metrics = field(default_factory=Metrics)
+    request_count: int = 0
+
+    def to_dict(self) -> dict:
+        return {
+            "state": self.state,
+            "model": self.model,
+            "loading": asdict(self.loading) if self.loading else None,
+            "metrics": asdict(self.metrics),
+            "request_count": self.request_count,
+            "timestamp": datetime.now().isoformat(timespec="seconds"),
+        }