feat: WP-0003 — RoutingPolicy (FR-2) and HTTP serve mode (FR-1)

FR-2 RoutingPolicy:
- RoutingPolicy + RoutingRule dataclasses in llm_connect/routing.py
- resolve(task_type, estimated_cost_per_1k=None) with cost-cap fallback
- Exported from llm_connect.__init__; contract doc at contracts/functional/routing-policy.md
- 11 tests covering rule match, cost-cap, fallback, unknown type, no-match

FR-1 HTTP serve mode:
- LLMServer in llm_connect/server.py (stdlib http.server, zero extra deps)
- POST /execute + GET /health; CLI via python -m llm_connect.server
- [server] optional-dep group added to pyproject.toml
- Contract doc at contracts/functional/server.md
- 9 tests: health, round-trip, 400/404/500 errors, config forwarding
- Added "mock" provider to factory for CLI default

All 101 tests pass.

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

llm_connect/server.py

@@ -0,0 +1,164 @@
+"""
+Minimal HTTP server for llm_connect — serve mode (FR-1).
+
+Exposes:
+  POST /execute  — run a prompt through the configured adapter
+  GET  /health   — liveness probe
+
+Usage (programmatic)::
+
+    from llm_connect import MockLLMAdapter
+    from llm_connect.server import LLMServer
+
+    server = LLMServer(adapter=MockLLMAdapter(), port=8080)
+    server.start()      # background thread
+    # ...
+    server.stop()
+
+Usage (CLI)::
+
+    python -m llm_connect.server --port 8080 --provider openrouter --model anthropic/claude-sonnet-4
+"""
+
+import argparse
+import json
+import threading
+from http.server import BaseHTTPRequestHandler, HTTPServer
+from typing import Optional
+
+from llm_connect.adapter import LLMAdapter
+from llm_connect.models import RunConfig
+
+
+class _Handler(BaseHTTPRequestHandler):
+    """Request handler — adapter injected via server.adapter."""
+
+    def log_message(self, format, *args):  # suppress default access log
+        pass
+
+    # ── GET ────────────────────────────────────────────────────────
+
+    def do_GET(self):
+        if self.path == "/health":
+            self._respond(200, {"status": "ok"})
+        else:
+            self._respond(404, {"error": "not found"})
+
+    # ── POST ───────────────────────────────────────────────────────
+
+    def do_POST(self):
+        if self.path != "/execute":
+            self._respond(404, {"error": "not found"})
+            return
+
+        length = int(self.headers.get("Content-Length", 0))
+        raw = self.rfile.read(length)
+        try:
+            data = json.loads(raw)
+        except (json.JSONDecodeError, ValueError):
+            self._respond(400, {"error": "invalid JSON body"})
+            return
+
+        prompt = data.get("prompt")
+        if not prompt:
+            self._respond(400, {"error": "missing required field: 'prompt'"})
+            return
+
+        cfg = data.get("config", {})
+        config = RunConfig(
+            model_name=cfg.get("model_name", "gpt-4"),
+            temperature=float(cfg.get("temperature", 0.7)),
+            max_tokens=int(cfg.get("max_tokens", 2000)),
+            timeout_seconds=int(cfg.get("timeout_seconds", 300)),
+        )
+
+        try:
+            response = self.server.adapter.execute_prompt(prompt, config)  # type: ignore[attr-defined]
+            self._respond(200, response.to_dict())
+        except Exception as exc:
+            self._respond(500, {"error": str(exc)})
+
+    # ── helpers ────────────────────────────────────────────────────
+
+    def _respond(self, status: int, body: dict) -> None:
+        payload = json.dumps(body).encode()
+        self.send_response(status)
+        self.send_header("Content-Type", "application/json")
+        self.send_header("Content-Length", str(len(payload)))
+        self.end_headers()
+        self.wfile.write(payload)
+
+
+class LLMServer:
+    """HTTP server wrapping an :class:`~llm_connect.adapter.LLMAdapter`.
+
+    Args:
+        adapter: The adapter that handles ``POST /execute`` requests.
+        host: Bind address (default ``"127.0.0.1"``).
+        port: TCP port (default ``8080``; ``0`` picks a free port).
+    """
+
+    def __init__(
+        self,
+        adapter: LLMAdapter,
+        host: str = "127.0.0.1",
+        port: int = 8080,
+    ) -> None:
+        self._httpd = HTTPServer((host, port), _Handler)
+        self._httpd.adapter = adapter  # type: ignore[attr-defined]
+        self._thread: Optional[threading.Thread] = None
+
+    @property
+    def port(self) -> int:
+        """Actual bound port (useful when ``port=0`` was requested)."""
+        return self._httpd.server_address[1]
+
+    @property
+    def host(self) -> str:
+        return self._httpd.server_address[0]
+
+    def start(self) -> None:
+        """Start serving in a daemon background thread."""
+        self._thread = threading.Thread(target=self._httpd.serve_forever, daemon=True)
+        self._thread.start()
+
+    def stop(self) -> None:
+        """Shut down the server and join the background thread."""
+        self._httpd.shutdown()
+        if self._thread is not None:
+            self._thread.join()
+
+    def serve_forever(self) -> None:
+        """Block the calling thread until interrupted."""
+        self._httpd.serve_forever()
+
+
+# ── CLI entry point ────────────────────────────────────────────────────────────
+
+def _build_adapter(provider: str, model: Optional[str]) -> LLMAdapter:
+    from llm_connect.factory import create_adapter
+    return create_adapter(provider, model=model)
+
+
+def main(argv=None) -> None:
+    parser = argparse.ArgumentParser(
+        prog="python -m llm_connect.server",
+        description="Start llm_connect HTTP serve mode.",
+    )
+    parser.add_argument("--port", type=int, default=8080, help="TCP port (default: 8080)")
+    parser.add_argument("--host", default="127.0.0.1", help="Bind address (default: 127.0.0.1)")
+    parser.add_argument("--provider", default="mock", help="Provider name passed to create_adapter")
+    parser.add_argument("--model", default=None, help="Model name (optional)")
+    args = parser.parse_args(argv)
+
+    adapter = _build_adapter(args.provider, args.model)
+    server = LLMServer(adapter=adapter, host=args.host, port=args.port)
+    print(f"llm_connect server listening on http://{args.host}:{args.port}")
+    try:
+        server.serve_forever()
+    except KeyboardInterrupt:
+        print("\nShutting down.")
+
+
+if __name__ == "__main__":
+    main()