chore: major type fixes

.gitignore

@@ -36,7 +36,6 @@ piped_mlx.egg-info/
 .coverage
 
 .idea/
-.vscode/
 .DS_Store
 .ruff_cache/
 .logs/

.vscode/.gitignore

@@ -0,0 +1,5 @@
+*
+
+# ignore everything but itself & tasks
+!.gitignore
+!tasks.json

.vscode/tasks.json

@@ -0,0 +1,101 @@
+{
+  "version": "2.0.0",
+  "tasks": [
+    {
+      "label": "Start API (8080 + 58080)",
+      "type": "shell",
+      "command": "uv",
+      "args": [
+        "run",
+        "dnet-api",
+        "--http-port",
+        "8080",
+        "--grpc-port",
+        "58080"
+      ],
+      "group": "build",
+      "presentation": {
+        "echo": true,
+        "reveal": "always",
+        "focus": false,
+        "panel": "new",
+        "showReuseMessage": true,
+        "clear": false
+      }
+    },
+    {
+      "label": "Start Shard (8081 + 58081)",
+      "type": "shell",
+      "command": "uv",
+      "args": [
+        "run",
+        "dnet-shard",
+        "--http-port",
+        "8081",
+        "--grpc-port",
+        "58081"
+      ],
+      "group": "build",
+      "presentation": {
+        "echo": true,
+        "reveal": "always",
+        "focus": false,
+        "panel": "new",
+        "showReuseMessage": true,
+        "clear": false
+      }
+    },
+    {
+      "label": "Health (Shard 8081)",
+      "type": "shell",
+      "command": "curl -s http://localhost:8081/health -H \"Content-Type: application/json\" | bun -p \"Bun.inspect(await Bun.stdin.json(), { colors: true })\""
+    },
+    {
+      "label": "Start Shard (8082 + 58082)",
+      "type": "shell",
+      "command": "uv",
+      "args": [
+        "run",
+        "dnet-shard",
+        "--http-port",
+        "8082",
+        "--grpc-port",
+        "58082"
+      ],
+      "group": "build",
+      "presentation": {
+        "echo": true,
+        "reveal": "always",
+        "focus": false,
+        "panel": "new",
+        "showReuseMessage": true,
+        "clear": false
+      }
+    },
+    {
+      "label": "Prepare Topology (Qwen/Qwen3-4B-MLX-4bit)",
+      "type": "shell",
+      "command": "curl -X POST http://localhost:8080/v1/prepare_topology -H \"Content-Type: application/json\" -d '{ \"model\": \"Qwen/Qwen3-4B-MLX-4bit\" }' | bun -p \"Bun.inspect(await Bun.stdin.json(), { colors: true })\""
+    },
+    {
+      "label": "Prepare & Load (Qwen/Qwen3-4B-MLX-4bit)",
+      "type": "shell",
+      "command": "uv run ./scripts/prepare_model.py Qwen/Qwen3-4B-MLX-4bit"
+    },
+    {
+      "label": "Get API Devices",
+      "type": "shell",
+      "command": "curl -s http://localhost:8080/v1/devices -H \"Content-Type: application/json\" | bun -p \"Bun.inspect(await Bun.stdin.json(), { colors: true })\""
+    },
+    {
+      "label": "Get API Topology",
+      "type": "shell",
+      "command": "curl -s http://localhost:8080/v1/topology -H \"Content-Type: application/json\" | bun -p \"Bun.inspect(await Bun.stdin.json(), { colors: true })\""
+    },
+    {
+      "label": "Chat Completions (Qwen/Qwen3-4B-MLX-4bit)",
+      "type": "shell",
+      "command": "curl -X POST http://localhost:8080/v1/chat/completions -H \"Content-Type: application/json\" -d '{\"model\":\"Qwen/Qwen3-4B-MLX-4bit\", \"messages\": [{\"role\": \"user\", \"content\": \"What is the capital of France?\"}], \"max_tokens\": 100}' | bun -p \"Bun.inspect(await Bun.stdin.json(), { colors: true })\""
+    }
+  ]
+}

Makefile

@@ -14,10 +14,14 @@ format:
 protos:
 		uv run ./scripts/generate_protos.py
 
-.PHONY: update #         | Update git submodules
+.PHONY: update #       | Update git submodules
 update:
 		git submodule update --init --recursive
 
+.PHONY: test #         | Run tests
+test:
+		uv run pytest -v
+
 .PHONY: help #         | List targets
 help:                                                                                                                    
 		@grep '^.PHONY: .* #' Makefile | sed 's/\.PHONY: \(.*\) # \(.*\)/\1 \2/' | expand -t20

README.md

@@ -158,12 +158,26 @@ curl http://localhost:8080/v1/devices \
 
 ## Testing
 
-You can lint the code using Ruff:
+You can run Pytest tests via:
 
 ```sh
+uv run pytest -v
+```
+
+You can check linting and formatting via Ruff:
+
+```sh
+# lint
 uvx ruff check
+
+# format
+uvx ruff format --diff
 ```
 
+> [!TIP]
+>
+> If you are using VsCode, we have prepared [tasks](./.vscode/tasks.json) that you can run easily from the <kbd> Command Palette > Tasks: Run Task </kbd>.
+
 ## License
 
 You can find the license [here](./LICENSE).

pyproject.toml

@@ -50,10 +50,10 @@ requires = ["uv_build>=0.8.17,<0.9.0"]
 build-backend = "uv_build"
 
 [tool.pytest.ini_options]
-python_files = ["dnet/**/*_test.py", "tests/*.py"]
+python_files = ["src/dnet/**/*_test.py", "tests/*.py"]
 python_functions = ["test_"]
 log_cli = true
 
 [tool.ruff]
 exclude = [".git", ".venv", "__pycache__", "build", "dist", "lib"]
-line-length = 88 # black
+line-length = 88                                                   # black

src/dnet/ring/api/models.py

@@ -65,15 +65,17 @@ class ChatBaseParams(BaseModel):
 class ChatParams(ChatBaseParams):
     """Extended parameters for chat requests."""
 
-    stream: Optional[bool] = False
-    max_tokens: Optional[int] = Field(default=100, ge=0)
-    logit_bias: Optional[Dict[int, float]] = Field(default_factory=dict)
-    logprobs: Optional[int] = Field(default=-1)
-    stop: Optional[Union[str, List[str]]] = []
-    profile: Optional[bool] = False
+    stream: bool = Field(default=False)
+    max_tokens: int = Field(default=100, ge=0)
+    logit_bias: Dict[int, float] = Field(default_factory=dict)
+    logprobs: int = Field(default=-1)
+    stop: Union[str, List[str]] = Field(default_factory=list)
+    profile: bool = Field(default=False)
 
     def __init__(self, **data: Any):
         super().__init__(**data)
+
+        # FIXME: why do this?
         if isinstance(self.stop, str):
             self.stop = [self.stop]