relaying/ RPC

QUICKSTART.md

@@ -120,6 +120,10 @@ $env:HF_HOME = "D:\DEV\models"
   --port 8005
 ```
 
+The example above starts the Windows node as the second half of a split Qwen
+model. To run the full model on Windows instead, omit `--shard-start` and
+`--shard-end`.
+
 `--host 0.0.0.0` binds the node to all Windows interfaces. `--advertise-host`
 is what the tracker gives to other nodes, so it must be the Windows LAN IP that
 the tracker and peer nodes can actually reach.
@@ -139,10 +143,10 @@ lines like:
 curl http://192.168.0.42:8005/v1/health
 ```
 
-If that endpoint returns 404, that is okay: it still proves the TCP connection
-reached the node process. If it times out or connection-refuses, check the
-Windows Firewall rule, `--host 0.0.0.0`, the selected LAN IP, and that the node is
-still running.
+If that endpoint returns 404 or 501, that is okay: it still proves the TCP
+connection reached the node process. If it times out or connection-refuses, check
+the Windows Firewall rule, `--host 0.0.0.0`, the selected LAN IP, and that the
+node is still running.
 
 ### Public tracker + WSS relay
 

tests/test_mining_cli.py

@@ -452,6 +452,7 @@ def test_default_cli_passes_advertise_host(monkeypatch):
         "meshnet-node",
         "--tracker", "http://192.168.0.179:8081",
         "--advertise-host", "192.168.0.42",
+        "--debug",
         "--no-tui",
     ])
 
@@ -465,3 +466,4 @@ def test_default_cli_passes_advertise_host(monkeypatch):
 
     assert captured["tracker_url"] == "http://192.168.0.179:8081"
     assert captured["advertise_host"] == "192.168.0.42"
+    assert captured["debug"] is True

tests/test_real_model_backend.py

@@ -81,6 +81,38 @@ class _FakeFullBackend(_FakeBackend):
         return 1
 
 
+class _FakeChatTokenizer:
+    eos_token = ""
+
+    def apply_chat_template(self, messages, add_generation_prompt=True, tokenize=False):
+        assert add_generation_prompt is True
+        assert tokenize is False
+        return "debug prompt"
+
+
+class _FakePipelineHeadBackend(_FakeBackend):
+    tokenizer = _FakeChatTokenizer()
+
+    def encode_prompt(self, prompt: str) -> TensorPayload:
+        assert prompt == "debug prompt"
+        return TensorPayload(
+            body=b"\x00" * (1 * 6 * 8 * 2),
+            shape=[1, 6, 8],
+            attention_mask_header=None,
+            position_ids_header=None,
+        )
+
+
+class _FakePipelineTailBackend(_FakeTailBackend):
+    def __init__(self) -> None:
+        self.start_layers: list[int | None] = []
+
+    def forward_bytes(self, body, shape, attention_mask_header, position_ids_header, start_layer=None):
+        self.start_layers.append(start_layer)
+        assert len(body) == 1 * 6 * 8 * 2
+        return " token"
+
+
 def test_quantization_flag_validation():
     assert validate_quantization("bfloat16") == "bfloat16"
     assert validate_quantization("int8") == "int8"
@@ -198,6 +230,75 @@ def test_full_model_chat_completion_uses_generation_not_single_token_decode():
         node.stop()
 
 
+def test_pipeline_hop_logs_are_suppressed_without_debug(capsys):
+    tail_backend = _FakePipelineTailBackend()
+    head = TorchNodeServer(backend=_FakePipelineHeadBackend(), tracker_mode=True)
+    tail = TorchNodeServer(backend=tail_backend)
+    head_port = head.start()
+    tail_port = tail.start()
+    try:
+        payload = json.dumps({
+            "model": "fake-model",
+            "messages": [{"role": "user", "content": "hello"}],
+            "max_tokens": 1,
+        }).encode()
+        req = urllib.request.Request(
+            f"http://127.0.0.1:{head_port}/v1/chat/completions",
+            data=payload,
+            headers={
+                "Content-Type": "application/json",
+                "X-Meshnet-Route": json.dumps([
+                    {"endpoint": f"http://127.0.0.1:{tail_port}", "start_layer": 22},
+                ]),
+            },
+            method="POST",
+        )
+        with urllib.request.urlopen(req, timeout=5) as resp:
+            body = json.loads(resp.read())
+    finally:
+        head.stop()
+        tail.stop()
+
+    out = capsys.readouterr().out
+    assert body["choices"][0]["message"]["content"] == " token"
+    assert tail_backend.start_layers == [22]
+    assert "pipeline hop 0:" not in out
+    assert "pipeline hop 0 returned text" not in out
+
+
+def test_pipeline_hop_logs_are_enabled_with_debug(capsys):
+    head = TorchNodeServer(backend=_FakePipelineHeadBackend(), tracker_mode=True, debug=True)
+    tail = TorchNodeServer(backend=_FakePipelineTailBackend())
+    head_port = head.start()
+    tail_port = tail.start()
+    try:
+        payload = json.dumps({
+            "model": "fake-model",
+            "messages": [{"role": "user", "content": "hello"}],
+            "max_tokens": 1,
+        }).encode()
+        req = urllib.request.Request(
+            f"http://127.0.0.1:{head_port}/v1/chat/completions",
+            data=payload,
+            headers={
+                "Content-Type": "application/json",
+                "X-Meshnet-Route": json.dumps([
+                    {"endpoint": f"http://127.0.0.1:{tail_port}", "start_layer": 22},
+                ]),
+            },
+            method="POST",
+        )
+        with urllib.request.urlopen(req, timeout=5) as resp:
+            json.loads(resp.read())
+    finally:
+        head.stop()
+        tail.stop()
+
+    out = capsys.readouterr().out
+    assert f"  [node] pipeline hop 0: http://127.0.0.1:{tail_port} start_layer=22" in out
+    assert "  [node] pipeline hop 0 returned text=' token'" in out
+
+
 def test_int_tensor_header_serializes_torch_tensors():
     torch = pytest.importorskip("torch")