v3.8 model serving 部署成功

2026-01-06 22:43:29 +08:00
parent 63963eba29
commit 686739fea2
39 changed files with 6772 additions and 1830 deletions
--- a/src/mvp/py/tests/test_app_serving_api.py
+++ b/src/mvp/py/tests/test_app_serving_api.py
@@ -0,0 +1,282 @@
+from __future__ import annotations
+
+from pathlib import Path
+
+import yaml
+from fastapi.testclient import TestClient
+
+
+def _write_config(tmp_path: Path) -> Path:
+    cfg = {
+        "ray": {
+            "address": "http://127.0.0.1:8265",
+            "shared_root": "/private",
+            "entrypoint_resources": {"worker_node": 1},
+            "runtime_env": {"env_vars": {}},
+        },
+        "data": {
+            "user_root": str(tmp_path / "users"),
+        },
+        "service": {
+            "api": {"host": "127.0.0.1", "port": 0},
+            "auth": {"token_env": "MVP_INTERNAL_TOKEN"},
+            "sqlite": {"db_path": str(tmp_path / "mvp.sqlite3")},
+            "scheduler": {"tick_s": 1, "retry_interval_s": 1, "max_running_tasks": 1},
+        },
+        "serving": {
+            "serve": {"http_port": 8000, "proxy_location": "HeadOnly"},
+            "llm": {"accelerator_type": "H20"},
+        },
+    }
+    p = tmp_path / "cfg.yaml"
+    p.write_text(yaml.safe_dump(cfg), encoding="utf-8")
+    return p
+
+
+def test_serving_api_crud_flow(tmp_path: Path, monkeypatch):
+    from argus.service import app as app_mod
+
+    cfg_path = _write_config(tmp_path)
+    monkeypatch.setenv("MVP_INTERNAL_TOKEN", "admin-token")
+
+    class _Scheduler:
+        def __init__(self, **kwargs):
+            self.tool = object()
+
+        def run_forever(self, stop_flag):
+            return None
+
+    monkeypatch.setattr(app_mod, "Scheduler", _Scheduler)
+    monkeypatch.setattr(app_mod, "new_model_key", lambda user_id: f"mk-{user_id}")
+
+    app = app_mod.create_app(str(cfg_path))
+
+    admin_headers = {"authorization": "Bearer admin-token"}
+    with TestClient(app) as c:
+        r = c.post("/api/v2/users", headers=admin_headers, json={"user_id": "alice"})
+        assert r.status_code == 200
+        r2 = c.post("/api/v2/users/alice/tokens", headers=admin_headers)
+        assert r2.status_code == 200
+        user_token = r2.json()["token"]
+
+        headers = {"authorization": f"Bearer {user_token}"}
+
+        spec_yaml = (
+            "model_id: qwen-0.5b\n"
+            "model_source: $HOME/common/hf/models--Qwen--Qwen2.5-0.5B-Instruct/snapshots/sha\n"
+            "num_replicas: 1\n"
+            "gpus_per_replica: 1\n"
+        )
+        r3 = c.post("/api/v2/serve/models", headers=headers, data=spec_yaml)
+        assert r3.status_code == 200
+        assert r3.json()["model_key"] == "mk-alice"
+        assert r3.json()["state"] == "QUEUED"
+
+        r4 = c.get("/api/v2/serve/models?limit=10&offset=0", headers=headers)
+        assert r4.status_code == 200
+        obj = r4.json()
+        assert obj["openai_base_url"] == "http://testserver:8000/v1"
+        assert len(obj["items"]) == 1
+        assert obj["items"][0]["model_key"] == "mk-alice"
+
+        r5 = c.get("/api/v2/serve/models/mk-alice", headers=headers)
+        assert r5.status_code == 200
+        detail = r5.json()
+        assert detail["model"]["model_key"] == "mk-alice"
+        assert "model_id_prefix" in detail["model"]
+        assert "resolved_spec_yaml" in detail
+        assert isinstance(detail.get("events"), list)
+
+        r6 = c.patch("/api/v2/serve/models/mk-alice", headers=headers, json={"num_replicas": 2})
+        assert r6.status_code == 200
+        assert r6.json()["state"] == "QUEUED"
+
+        r7 = c.delete("/api/v2/serve/models/mk-alice", headers=headers)
+        assert r7.status_code == 200
+        assert r7.json()["state"] == "DELETING"
+
+        # Admin status endpoint
+        r8 = c.get("/api/v2/serve/status", headers=admin_headers)
+        assert r8.status_code == 200
+        assert r8.json()["http_port"] == 8000
+
+
+def test_serving_api_rejects_path_outside_user_and_hf(tmp_path: Path, monkeypatch):
+    from argus.service import app as app_mod
+
+    cfg_path = _write_config(tmp_path)
+    monkeypatch.setenv("MVP_INTERNAL_TOKEN", "admin-token")
+
+    class _Scheduler:
+        def __init__(self, **kwargs):
+            self.tool = object()
+
+        def run_forever(self, stop_flag):
+            return None
+
+    monkeypatch.setattr(app_mod, "Scheduler", _Scheduler)
+    monkeypatch.setattr(app_mod, "new_model_key", lambda user_id: f"mk-{user_id}")
+
+    app = app_mod.create_app(str(cfg_path))
+
+    admin_headers = {"authorization": "Bearer admin-token"}
+    with TestClient(app) as c:
+        c.post("/api/v2/users", headers=admin_headers, json={"user_id": "alice"})
+        r2 = c.post("/api/v2/users/alice/tokens", headers=admin_headers)
+        user_token = r2.json()["token"]
+        headers = {"authorization": f"Bearer {user_token}"}
+
+        spec_yaml = (
+            "model_id: x\n"
+            "model_source: /private/users/bob/models/evil\n"
+            "num_replicas: 1\n"
+            "gpus_per_replica: 1\n"
+        )
+        r3 = c.post("/api/v2/serve/models", headers=headers, data=spec_yaml)
+        assert r3.status_code == 403
+
+
+def test_serving_api_invalid_yaml_and_non_mapping(tmp_path: Path, monkeypatch):
+    from argus.service import app as app_mod
+
+    cfg_path = _write_config(tmp_path)
+    monkeypatch.setenv("MVP_INTERNAL_TOKEN", "admin-token")
+
+    class _Scheduler:
+        def __init__(self, **kwargs):
+            self.tool = object()
+
+        def run_forever(self, stop_flag):
+            return None
+
+    monkeypatch.setattr(app_mod, "Scheduler", _Scheduler)
+    monkeypatch.setattr(app_mod, "new_model_key", lambda user_id: f"mk-{user_id}")
+    app = app_mod.create_app(str(cfg_path))
+
+    with TestClient(app) as c:
+        # Create a user token
+        admin_headers = {"authorization": "Bearer admin-token"}
+        c.post("/api/v2/users", headers=admin_headers, json={"user_id": "alice"})
+        token = c.post("/api/v2/users/alice/tokens", headers=admin_headers).json()["token"]
+        headers = {"authorization": f"Bearer {token}"}
+
+        r = c.post("/api/v2/serve/models", headers=headers, data=": bad\n")
+        assert r.status_code == 400
+
+        r2 = c.post("/api/v2/serve/models", headers=headers, data="- 1\n- 2\n")
+        assert r2.status_code == 400
+
+
+def test_serving_api_engine_kwargs_binary_rejected(tmp_path: Path, monkeypatch):
+    """
+    yaml !!binary is parsed as bytes, which is not JSON-serializable.
+    """
+    from argus.service import app as app_mod
+
+    cfg_path = _write_config(tmp_path)
+    monkeypatch.setenv("MVP_INTERNAL_TOKEN", "admin-token")
+
+    class _Scheduler:
+        def __init__(self, **kwargs):
+            self.tool = object()
+
+        def run_forever(self, stop_flag):
+            return None
+
+    monkeypatch.setattr(app_mod, "Scheduler", _Scheduler)
+    monkeypatch.setattr(app_mod, "new_model_key", lambda user_id: f"mk-{user_id}")
+    app = app_mod.create_app(str(cfg_path))
+
+    admin_headers = {"authorization": "Bearer admin-token"}
+    with TestClient(app) as c:
+        c.post("/api/v2/users", headers=admin_headers, json={"user_id": "alice"})
+        token = c.post("/api/v2/users/alice/tokens", headers=admin_headers).json()["token"]
+        headers = {"authorization": f"Bearer {token}"}
+
+        spec_yaml = (
+            "model_id: x\n"
+            "model_source: $HOME/common/hf/x\n"
+            "engine_kwargs:\n"
+            "  blob: !!binary \"AQID\"\n"
+        )
+        r = c.post("/api/v2/serve/models", headers=headers, data=spec_yaml)
+        assert r.status_code == 400
+
+
+def test_serving_api_list_include_deleted_and_forwarded_base_url(tmp_path: Path, monkeypatch):
+    from argus.service import app as app_mod
+    from argus.service.config import V2Config
+    from argus.service.db import Db
+
+    cfg_path = _write_config(tmp_path)
+    monkeypatch.setenv("MVP_INTERNAL_TOKEN", "admin-token")
+
+    class _Scheduler:
+        def __init__(self, **kwargs):
+            self.tool = object()
+
+        def run_forever(self, stop_flag):
+            return None
+
+    monkeypatch.setattr(app_mod, "Scheduler", _Scheduler)
+    keys = iter(["mk-alice-1", "mk-alice-2"])
+    monkeypatch.setattr(app_mod, "new_model_key", lambda user_id: next(keys))
+
+    app = app_mod.create_app(str(cfg_path))
+
+    admin_headers = {"authorization": "Bearer admin-token"}
+    with TestClient(app) as c:
+        c.post("/api/v2/users", headers=admin_headers, json={"user_id": "alice"})
+        token = c.post("/api/v2/users/alice/tokens", headers=admin_headers).json()["token"]
+        headers = {"authorization": f"Bearer {token}"}
+
+        spec_yaml = "model_id: x\nmodel_source: $HOME/common/hf/x\n"
+        c.post("/api/v2/serve/models", headers=headers, data=spec_yaml)
+        c.post("/api/v2/serve/models", headers=headers, data=spec_yaml)
+
+        # Mark one model as DELETED directly in DB (sets deleted_at).
+        root = yaml.safe_load(cfg_path.read_text(encoding="utf-8"))
+        v2_cfg = V2Config.from_root_dict(root)
+        db = Db(v2_cfg.sqlite.db_path)
+        db.set_serve_model_state(model_key="mk-alice-2", state="DELETED")
+
+        r1 = c.get(
+            "/api/v2/serve/models?limit=10&offset=0&include_deleted=0",
+            headers={**headers, "x-forwarded-host": "example.com:8080", "x-forwarded-proto": "https"},
+        )
+        assert r1.status_code == 200
+        assert r1.json()["openai_base_url"] == "https://example.com:8000/v1"
+        assert {m["model_key"] for m in r1.json()["items"]} == {"mk-alice-1"}
+
+        r2 = c.get("/api/v2/serve/models?include_deleted=1", headers=headers)
+        assert r2.status_code == 200
+        assert {m["model_key"] for m in r2.json()["items"]} == {"mk-alice-1", "mk-alice-2"}
+
+
+def test_serving_api_patch_invalid_num_replicas(tmp_path: Path, monkeypatch):
+    from argus.service import app as app_mod
+
+    cfg_path = _write_config(tmp_path)
+    monkeypatch.setenv("MVP_INTERNAL_TOKEN", "admin-token")
+
+    class _Scheduler:
+        def __init__(self, **kwargs):
+            self.tool = object()
+
+        def run_forever(self, stop_flag):
+            return None
+
+    monkeypatch.setattr(app_mod, "Scheduler", _Scheduler)
+    monkeypatch.setattr(app_mod, "new_model_key", lambda user_id: "mk-alice")
+
+    app = app_mod.create_app(str(cfg_path))
+
+    admin_headers = {"authorization": "Bearer admin-token"}
+    with TestClient(app) as c:
+        c.post("/api/v2/users", headers=admin_headers, json={"user_id": "alice"})
+        token = c.post("/api/v2/users/alice/tokens", headers=admin_headers).json()["token"]
+        headers = {"authorization": f"Bearer {token}"}
+
+        c.post("/api/v2/serve/models", headers=headers, data="model_id: x\nmodel_source: $HOME/common/hf/x\n")
+        r = c.patch("/api/v2/serve/models/mk-alice", headers=headers, json={"num_replicas": 0})
+        assert r.status_code == 422