Load recommended model metadata from JSON

tests/test_tracker_routing.py

@@ -78,7 +78,8 @@ def test_tracker_exposes_registered_model_metadata():
     finally:
         tracker.stop()
 
-    kimi = next(model for model in models["data"] if model["id"] == "unsloth/Kimi-K2.7-Code")
+    kimi = next(model for model in models["data"] if model["id"] == "kimi-k2.7")
+    assert kimi["hf_repo"] == "unsloth/Kimi-K2.7-Code"
     assert kimi["metadata"]["total_parameters"] == "1T"
     assert kimi["metadata"]["activated_parameters"] == "32B"
     assert kimi["metadata"]["num_layers"] == 61
@@ -87,6 +88,113 @@ def test_tracker_exposes_registered_model_metadata():
     assert registered["model_metadata"]["context_length"] == 256000
 
 
+def test_tracker_lists_recommended_kimi_before_nodes_register():
+    tracker = TrackerServer()
+    port = tracker.start()
+    url = f"http://127.0.0.1:{port}"
+    try:
+        models = _get_json(f"{url}/v1/models")
+        network_map = _get_json(f"{url}/v1/network/map")
+    finally:
+        tracker.stop()
+
+    kimi = next(model for model in models["data"] if model["id"] == "kimi-k2.7")
+    assert kimi["hf_repo"] == "unsloth/Kimi-K2.7-Code"
+    assert "Kimi-K2.7-Code" in kimi["aliases"]
+    assert kimi["metadata"]["download_size_gb"] == 595
+    assert kimi["deployment"]["native_quantization"] == "int4"
+    assert kimi["deployment"]["deployable"] is False
+    assert network_map["pool"]["node_count"] == 0
+    assert network_map["recommended_models"][0]["id"] == "kimi-k2.7"
+
+
+def test_network_map_exposes_pool_size_and_speed_summary():
+    tracker = TrackerServer()
+    port = tracker.start()
+    url = f"http://127.0.0.1:{port}"
+    try:
+        _post_json(
+            f"{url}/v1/nodes/register",
+            {
+                "endpoint": "http://127.0.0.1:7101",
+                "model": "inventory-a",
+                "vram_bytes": 10_000,
+                "ram_bytes": 20_000,
+                "benchmark_tokens_per_sec": 4.0,
+                "hardware_profile": {},
+            },
+        )
+        _post_json(
+            f"{url}/v1/nodes/register",
+            {
+                "endpoint": "http://127.0.0.1:7102",
+                "model": "inventory-b",
+                "vram_bytes": 0,
+                "ram_bytes": 30_000,
+                "benchmark_tokens_per_sec": 6.0,
+                "hardware_profile": {},
+            },
+        )
+
+        network_map = _get_json(f"{url}/v1/network/map")
+    finally:
+        tracker.stop()
+
+    pool = network_map["pool"]
+    assert pool["node_count"] == 2
+    assert pool["total_vram_bytes"] == 10_000
+    assert pool["total_ram_bytes"] == 50_000
+    assert pool["total_memory_budget_bytes"] == 40_000
+    assert pool["total_benchmark_tokens_per_sec"] == 10.0
+    assert pool["total_effective_throughput"] == 10.0
+
+
+def test_recommended_kimi_becomes_deployable_when_pool_is_large_enough():
+    tracker = TrackerServer()
+    port = tracker.start()
+    url = f"http://127.0.0.1:{port}"
+    gib = 1024 * 1024 * 1024
+    try:
+        for idx in range(2):
+            _post_json(
+                f"{url}/v1/nodes/register",
+                {
+                    "endpoint": f"http://127.0.0.1:{7200 + idx}",
+                    "model": f"inventory-{idx}",
+                    "vram_bytes": 0,
+                    "ram_bytes": 400 * gib,
+                    "benchmark_tokens_per_sec": 5.0,
+                    "hardware_profile": {},
+                },
+            )
+
+        models = _get_json(f"{url}/v1/models")
+    finally:
+        tracker.stop()
+
+    kimi = next(model for model in models["data"] if model["id"] == "kimi-k2.7")
+    assert kimi["deployment"]["deployable"] is True
+    assert kimi["deployment"]["missing_effective_memory_bytes"] == 0
+
+
+def test_network_assign_can_start_recommended_kimi_by_short_name():
+    tracker = TrackerServer()
+    port = tracker.start()
+    url = f"http://127.0.0.1:{port}"
+    try:
+        assignment = _get_json(
+            f"{url}/v1/network/assign?device=cpu&ram_mb=204800&hf_repo=kimi-k2.7"
+        )
+    finally:
+        tracker.stop()
+
+    assert assignment["model"] == "kimi-k2.7"
+    assert assignment["hf_repo"] == "unsloth/Kimi-K2.7-Code"
+    assert assignment["num_layers"] == 61
+    assert assignment["shard_start"] == 0
+    assert 0 <= assignment["shard_end"] < 60
+
+
 def test_tracker_serves_health_while_proxy_request_is_in_flight():
     """Long inference proxy requests must not block heartbeats/health checks."""