llama-deploy-core 0.3.0a11__py3-none-any.whl → 0.3.0a13__py3-none-any.whl

llama_deploy/core/client/manage_client.py

@@ -1,8 +1,7 @@
-import contextlib
-from typing import Iterator, List
+from typing import AsyncIterator, Callable, List
 
 import httpx
-from llama_deploy.core.schema.base import LogEvent
+from llama_deploy.core.schema import LogEvent
 from llama_deploy.core.schema.deployments import (
     DeploymentCreate,
     DeploymentResponse,
@@ -14,30 +13,41 @@ from llama_deploy.core.schema.git_validation import (
     RepositoryValidationResponse,
 )
 from llama_deploy.core.schema.projects import ProjectsListResponse, ProjectSummary
+from llama_deploy.core.schema.public import VersionResponse
 
 
 class ClientError(Exception):
     """Base class for client errors."""
 
-    def __init__(self, message: str) -> None:
+    def __init__(self, message: str, status_code: int | None = None) -> None:
         super().__init__(message)
+        self.status_code = status_code
 
 
 class BaseClient:
-    def __init__(self, base_url: str) -> None:
+    def __init__(self, base_url: str, api_key: str | None = None) -> None:
         self.base_url = base_url.rstrip("/")
-        self.client = httpx.Client(
+
+        headers: dict[str, str] = {}
+        if api_key:
+            headers["Authorization"] = f"Bearer {api_key}"
+
+        self.client = httpx.AsyncClient(
             base_url=self.base_url,
+            headers=headers,
             event_hooks={"response": [self._handle_response]},
         )
-        self.hookless_client = httpx.Client(base_url=self.base_url)
+        self.hookless_client = httpx.AsyncClient(
+            base_url=self.base_url, headers=headers
+        )
 
-    def _handle_response(self, response: httpx.Response) -> None:
+    async def _handle_response(self, response: httpx.Response) -> None:
         try:
             response.raise_for_status()
         except httpx.HTTPStatusError as e:
             try:
-                response.read()
+                # Ensure content is loaded for JSON/text extraction
+                await response.aread()
                 error_data = e.response.json()
                 if isinstance(error_data, dict) and "detail" in error_data:
                     error_message = error_data["detail"]
@@ -45,24 +55,30 @@ class BaseClient:
                     error_message = str(error_data)
             except (ValueError, KeyError):
                 error_message = e.response.text
-            raise ClientError(f"HTTP {e.response.status_code}: {error_message}") from e
+            raise ClientError(
+                f"HTTP {e.response.status_code}: {error_message}",
+                e.response.status_code,
+            ) from e
         except httpx.RequestError as e:
             raise ClientError(f"Request failed: {e}") from e
 
+    async def aclose(self) -> None:
+        await self.client.aclose()
+        await self.hookless_client.aclose()
+
 
 class ControlPlaneClient(BaseClient):
     """Unscoped client for non-project endpoints."""
 
-    def health_check(self) -> dict:
-        response = self.client.get("/health")
-        return response.json()
+    def __init__(self, base_url: str, api_key: str | None = None) -> None:
+        super().__init__(base_url, api_key)
 
-    def server_version(self) -> dict:
-        response = self.client.get("/version")
-        return response.json()
+    async def server_version(self) -> VersionResponse:
+        response = await self.client.get("/api/v1beta1/deployments-public/version")
+        return VersionResponse.model_validate(response.json())
 
-    def list_projects(self) -> List[ProjectSummary]:
-        response = self.client.get("/api/v1beta1/deployments/list-projects")
+    async def list_projects(self) -> List[ProjectSummary]:
+        response = await self.client.get("/api/v1beta1/deployments/list-projects")
         projects_response = ProjectsListResponse.model_validate(response.json())
         return [project for project in projects_response.projects]
 
@@ -74,62 +90,63 @@ class ProjectClient(BaseClient):
         self,
         base_url: str,
         project_id: str,
+        api_key: str | None = None,
     ) -> None:
-        super().__init__(base_url)
+        super().__init__(base_url, api_key)
         self.project_id = project_id
 
-    def list_deployments(self) -> List[DeploymentResponse]:
-        response = self.client.get(
+    async def list_deployments(self) -> List[DeploymentResponse]:
+        response = await self.client.get(
             "/api/v1beta1/deployments",
             params={"project_id": self.project_id},
         )
         deployments_response = DeploymentsListResponse.model_validate(response.json())
         return [deployment for deployment in deployments_response.deployments]
 
-    def get_deployment(
+    async def get_deployment(
         self, deployment_id: str, include_events: bool = False
     ) -> DeploymentResponse:
-        response = self.client.get(
+        response = await self.client.get(
             f"/api/v1beta1/deployments/{deployment_id}",
             params={"project_id": self.project_id, "include_events": include_events},
         )
         return DeploymentResponse.model_validate(response.json())
 
-    def create_deployment(
+    async def create_deployment(
         self, deployment_data: DeploymentCreate
     ) -> DeploymentResponse:
-        response = self.client.post(
+        response = await self.client.post(
             "/api/v1beta1/deployments",
             params={"project_id": self.project_id},
             json=deployment_data.model_dump(exclude_none=True),
         )
         return DeploymentResponse.model_validate(response.json())
 
-    def delete_deployment(self, deployment_id: str) -> None:
-        self.client.delete(
+    async def delete_deployment(self, deployment_id: str) -> None:
+        await self.client.delete(
             f"/api/v1beta1/deployments/{deployment_id}",
             params={"project_id": self.project_id},
         )
 
-    def update_deployment(
+    async def update_deployment(
         self,
         deployment_id: str,
         update_data: DeploymentUpdate,
     ) -> DeploymentResponse:
-        response = self.client.patch(
+        response = await self.client.patch(
             f"/api/v1beta1/deployments/{deployment_id}",
             params={"project_id": self.project_id},
             json=update_data.model_dump(),
         )
         return DeploymentResponse.model_validate(response.json())
 
-    def validate_repository(
+    async def validate_repository(
         self,
         repo_url: str,
         deployment_id: str | None = None,
         pat: str | None = None,
     ) -> RepositoryValidationResponse:
-        response = self.client.post(
+        response = await self.client.post(
             "/api/v1beta1/deployments/validate-repository",
             params={"project_id": self.project_id},
             json=RepositoryValidationRequest(
@@ -140,21 +157,19 @@ class ProjectClient(BaseClient):
         )
         return RepositoryValidationResponse.model_validate(response.json())
 
-    def stream_deployment_logs(
+    async def stream_deployment_logs(
         self,
         deployment_id: str,
         *,
         include_init_containers: bool = False,
         since_seconds: int | None = None,
         tail_lines: int | None = None,
-    ) -> tuple["Closer", Iterator[LogEvent]]:
+    ) -> AsyncIterator[LogEvent]:
         """Stream logs as LogEvent items from the control plane using SSE.
 
-        This yields `LogEvent` models until the stream ends (e.g. rollout).
+        Yields `LogEvent` models until the stream ends (e.g., rollout completes).
         """
-        # Use a separate client without response hooks so we don't consume the stream
-
-        params = {
+        params: dict[str, object] = {
             "project_id": self.project_id,
             "include_init_containers": include_init_containers,
         }
@@ -166,54 +181,30 @@ class ProjectClient(BaseClient):
         url = f"/api/v1beta1/deployments/{deployment_id}/logs"
         headers = {"Accept": "text/event-stream"}
 
-        stack = contextlib.ExitStack()
-        response = stack.enter_context(
-            self.hookless_client.stream(
-                "GET", url, params=params, headers=headers, timeout=None
-            )
-        )
-        try:
+        async with self.hookless_client.stream(
+            "GET", url, params=params, headers=headers, timeout=None
+        ) as response:
             response.raise_for_status()
-        except Exception:
-            stack.close()
-            raise
-
-        return stack.close, _iterate_log_stream(response, stack.close)
-
-
-def _iterate_log_stream(
-    response: httpx.Response, closer: "Closer"
-) -> Iterator[LogEvent]:
-    event_name: str | None = None
-    data_lines: list[str] = []
-
-    try:
-        for line in response.iter_lines():
-            if line is None:
-                continue
-            line = line.decode() if isinstance(line, (bytes, bytearray)) else line
-            print("got line", line)
-            if line.startswith("event:"):
-                event_name = line[len("event:") :].strip()
-            elif line.startswith("data:"):
-                data_lines.append(line[len("data:") :].lstrip())
-            elif line.strip() == "":
-                if event_name == "log" and data_lines:
-                    data_str = "\n".join(data_lines)
-                    try:
-                        yield LogEvent.model_validate_json(data_str)
-                        print("yielded log event", data_str)
-                    except Exception:
-                        # If parsing fails, skip malformed event
-                        pass
-                # reset for next event
-                event_name = None
-                data_lines = []
-    finally:
-        try:
-            closer()
-        except Exception:
-            pass
-
 
-type Closer = callable[tuple[()], None]
+            event_name: str | None = None
+            data_lines: list[str] = []
+            async for line in response.aiter_lines():
+                if line is None:
+                    continue
+                line = line.decode() if isinstance(line, (bytes, bytearray)) else line
+                if line.startswith("event:"):
+                    event_name = line[len("event:") :].strip()
+                elif line.startswith("data:"):
+                    data_lines.append(line[len("data:") :].lstrip())
+                elif line.strip() == "":
+                    if event_name == "log" and data_lines:
+                        data_str = "\n".join(data_lines)
+                        try:
+                            yield LogEvent.model_validate_json(data_str)
+                        except Exception:
+                            pass
+                    event_name = None
+                    data_lines = []
+
+
+Closer = Callable[[], None]

llama_deploy/core/deployment_config.py

@@ -3,7 +3,7 @@ from __future__ import annotations
 import json
 import tomllib
 from pathlib import Path
-from typing import Any
+from typing import Any, TypeVar
 
 import yaml
 from llama_deploy.core.path_util import validate_path_traversal
@@ -229,7 +229,10 @@ class DeploymentConfig(BaseModel):
         )
 
 
-def _pick_non_default[T](a: T, b: T, default: T) -> T:
+T = TypeVar("T")
+
+
+def _pick_non_default(a: T, b: T, default: T) -> T:
     if a != default:
         return a
     return b or default

llama_deploy/core/schema/__init__.py

@@ -1,4 +1,4 @@
-from .base import Base, LogEvent
+from .base import Base
 from .deployments import (
     DeploymentCreate,
     DeploymentResponse,
@@ -6,10 +6,12 @@ from .deployments import (
     DeploymentUpdate,
     LlamaDeploymentPhase,
     LlamaDeploymentSpec,
+    LogEvent,
     apply_deployment_update,
 )
 from .git_validation import RepositoryValidationRequest, RepositoryValidationResponse
 from .projects import ProjectsListResponse, ProjectSummary
+from .public import VersionResponse
 
 __all__ = [
     "Base",
@@ -25,4 +27,5 @@ __all__ = [
     "RepositoryValidationRequest",
     "ProjectSummary",
     "ProjectsListResponse",
+    "VersionResponse",
 ]

llama_deploy/core/schema/base.py

@@ -1,5 +1,3 @@
-from datetime import datetime
-
 from pydantic import BaseModel, ConfigDict
 
 base_config = ConfigDict(
@@ -20,10 +18,3 @@ base_config = ConfigDict(
 
 class Base(BaseModel):
     model_config = base_config
-
-
-class LogEvent(Base):
-    pod: str
-    container: str
-    text: str
-    timestamp: datetime

llama_deploy/core/schema/deployments.py

@@ -205,3 +205,10 @@ def apply_deployment_update(
         secret_adds=secret_adds,
         secret_removes=secret_removes,
     )
+
+
+class LogEvent(Base):
+    pod: str
+    container: str
+    text: str
+    timestamp: datetime

llama_deploy/core/schema/projects.py

@@ -5,6 +5,7 @@ class ProjectSummary(Base):
     """Summary of a project with deployment count"""
 
     project_id: str
+    project_name: str
     deployment_count: int
 
 

llama_deploy/core/schema/public.py

@@ -0,0 +1,5 @@
+from .base import Base
+
+
+class VersionResponse(Base):
+    version: str

llama_deploy/core/server/manage_api/__init__.py

@@ -1,9 +1,13 @@
-from ._abstract_deployments_service import AbstractDeploymentsService
+from ._abstract_deployments_service import (
+    AbstractDeploymentsService,
+    AbstractPublicDeploymentsService,
+)
 from ._create_deployments_router import create_v1beta1_deployments_router
 from ._exceptions import DeploymentNotFoundError, ReplicaSetNotFoundError
 
 __all__ = [
     "AbstractDeploymentsService",
+    "AbstractPublicDeploymentsService",
     "create_v1beta1_deployments_router",
     "DeploymentNotFoundError",
     "ReplicaSetNotFoundError",

llama_deploy/core/server/manage_api/_abstract_deployments_service.py

@@ -2,11 +2,27 @@ from abc import ABC, abstractmethod
 from typing import AsyncGenerator, cast
 
 from llama_deploy.core import schema
-from llama_deploy.core.schema.base import LogEvent
+from llama_deploy.core.schema import LogEvent
 from llama_deploy.core.schema.deployments import DeploymentResponse
 
 
+class AbstractPublicDeploymentsService(ABC):
+    @abstractmethod
+    async def get_version(self) -> schema.VersionResponse:
+        """
+        Get the version of the server
+        """
+        ...
+
+
 class AbstractDeploymentsService(ABC):
+    @abstractmethod
+    async def get_projects(self) -> schema.ProjectsListResponse:
+        """
+        Get a list of projects
+        """
+        ...
+
     @abstractmethod
     async def validate_repository(
         self,

llama_deploy/core/server/manage_api/_create_deployments_router.py

@@ -1,14 +1,16 @@
 import logging
 from typing import Awaitable, Callable
 
-from fastapi import APIRouter, Depends, HTTPException, Request, Response
+from fastapi import APIRouter, Depends, HTTPException, Request, Response, params
 from fastapi.params import Query
 from fastapi.responses import StreamingResponse
-from llama_deploy.control_plane import k8s_client
 from llama_deploy.core import schema
 from typing_extensions import Annotated
 
-from ._abstract_deployments_service import AbstractDeploymentsService
+from ._abstract_deployments_service import (
+    AbstractDeploymentsService,
+    AbstractPublicDeploymentsService,
+)
 from ._exceptions import DeploymentNotFoundError, ReplicaSetNotFoundError
 
 logger = logging.getLogger(__name__)
@@ -20,15 +22,29 @@ async def get_project_id(project_id: Annotated[str, Query()]) -> str:
 
 def create_v1beta1_deployments_router(
     deployments_service: AbstractDeploymentsService,
+    public_service: AbstractPublicDeploymentsService,
     get_project_id: Callable[[str], Awaitable[str]] = get_project_id,
+    dependencies: list[params.Depends] = [],
+    public_dependencies: list[params.Depends] = [],
 ) -> APIRouter:
-    router = APIRouter(prefix="/api/v1beta1/deployments", tags=["v1beta1-deployments"])
+    base_router = APIRouter(prefix="/api/v1beta1")
+    public_router = APIRouter(
+        tags=["v1beta1-deployments-public"],
+        dependencies=public_dependencies,
+    )
+    router = APIRouter(
+        tags=["v1beta1-deployments"],
+        dependencies=dependencies,
+    )
+
+    @public_router.get("/version")
+    async def get_version() -> schema.VersionResponse:
+        return await public_service.get_version()
 
     @router.get("/list-projects")
     async def get_projects() -> schema.ProjectsListResponse:
         """Get all unique projects with their deployment counts"""
-        projects_data = await k8s_client.get_projects_with_deployment_count()
-        return schema.ProjectsListResponse(projects=projects_data)
+        return await deployments_service.get_projects()
 
     @router.post("/validate-repository")
     async def validate_repository(
@@ -164,4 +180,6 @@ def create_v1beta1_deployments_router(
             # Deployment exists but hasn't created a ReplicaSet yet
             raise HTTPException(status_code=409, detail=str(e))
 
-    return router
+    base_router.include_router(public_router, prefix="/deployments-public")
+    base_router.include_router(router, prefix="/deployments")
+    return base_router

{llama_deploy_core-0.3.0a11.dist-info → llama_deploy_core-0.3.0a13.dist-info}/METADATA

@@ -1,15 +1,16 @@
 Metadata-Version: 2.3
 Name: llama-deploy-core
-Version: 0.3.0a11
+Version: 0.3.0a13
 Summary: Core models and schemas for LlamaDeploy
 License: MIT
 Requires-Dist: fastapi>=0.115.0
+Requires-Dist: overrides>=7.7.0
 Requires-Dist: pydantic>=2.0.0
 Requires-Dist: pyyaml>=6.0.2
 Requires-Dist: types-pyyaml>=6.0.12.20250822
 Requires-Dist: httpx>=0.27.0 ; extra == 'client'
 Requires-Dist: fastapi>=0.115.0 ; extra == 'server'
-Requires-Python: >=3.12, <4
+Requires-Python: >=3.11, <4
 Provides-Extra: client
 Provides-Extra: server
 Description-Content-Type: text/markdown

llama_deploy_core-0.3.0a13.dist-info/RECORD

@@ -0,0 +1,21 @@
+llama_deploy/core/__init__.py,sha256=112612bf2e928c2e0310d6556bb13fc28c00db70297b90a8527486cd2562e408,43
+llama_deploy/core/client/manage_client.py,sha256=87ec120c3d8e781a7c5ea5fe9cd75fb90620c52500bbf7bfe25dbdf0fbba7e54,7715
+llama_deploy/core/config.py,sha256=69bb0ea8ac169eaa4e808cd60a098b616bddd3145d26c6c35e56db38496b0e6a,35
+llama_deploy/core/deployment_config.py,sha256=b052fa66bd140fa39dea2de6cda362b39f8aca22f9c1cc0011c9f4a025263d0c,15117
+llama_deploy/core/git/git_util.py,sha256=c581c1da13871b4e89eda58f56ddb074139454c06ae9b04c0b396fdb2b9a5176,9193
+llama_deploy/core/path_util.py,sha256=14d50c0c337c8450ed46cafc88436027056b365a48370a69cdb76c88d7c26fd1,798
+llama_deploy/core/py.typed,sha256=e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855,0
+llama_deploy/core/schema/__init__.py,sha256=d1459ee50c690779a682130eff72f61dc1a687d2d4b26d8a5d3620a72d92d831,802
+llama_deploy/core/schema/base.py,sha256=2de6d23e58c36b6bb311ec0aea4b902661867056c1250c6b7ce3bad17141fe15,677
+llama_deploy/core/schema/deployments.py,sha256=d9254d9a478d7aeaf3d28ec6205215ea892dcfb245966d726d69d0418e03b03d,6486
+llama_deploy/core/schema/git_validation.py,sha256=27b306aa6ecabe58cab6381d92551545f263fe7550c58b3087115410bc71fd21,1915
+llama_deploy/core/schema/projects.py,sha256=b3820037cd6d222bcc5fb2f1e74bde9741845a423dd01aa0fa65874e28ba802a,316
+llama_deploy/core/schema/public.py,sha256=d73def6f5b642c0e7b738ff6ff6bc9d8ce2e7800da537e906c5721430e0ab4c1,71
+llama_deploy/core/server/manage_api/__init__.py,sha256=e477ccab59cfd084edbad46f209972a282e623eb314d0847a754a46a16361db5,457
+llama_deploy/core/server/manage_api/_abstract_deployments_service.py,sha256=85ceab2a343c3642db7f77d4a665d5710a14bca920bbfdc25c5f1168cce30b22,4638
+llama_deploy/core/server/manage_api/_create_deployments_router.py,sha256=cde496f5922a74ae6199224abb25aefa1a357bb45c06ce25de79283d6f1a7174,6622
+llama_deploy/core/server/manage_api/_exceptions.py,sha256=ee71cd9c2354a665e6905cd9cc752d2d65f71f0b936d33fec3c1c5229c38accf,246
+llama_deploy/core/ui_build.py,sha256=290dafa951918e5593b9035570fa4c66791d7e5ea785bd372ad11e99e8283857,1514
+llama_deploy_core-0.3.0a13.dist-info/WHEEL,sha256=66530aef82d5020ef5af27ae0123c71abb9261377c5bc519376c671346b12918,79
+llama_deploy_core-0.3.0a13.dist-info/METADATA,sha256=74764be1b14a49b143f75cc1c41fa83fc6409a9abf9d5c3e1c9885e640f19f22,659
+llama_deploy_core-0.3.0a13.dist-info/RECORD,,

llama_deploy_core-0.3.0a11.dist-info/RECORD

@@ -1,20 +0,0 @@
-llama_deploy/core/__init__.py,sha256=112612bf2e928c2e0310d6556bb13fc28c00db70297b90a8527486cd2562e408,43
-llama_deploy/core/client/manage_client.py,sha256=c098a12def4ece9897d1d5d70c69bf2bd7140de5ec970cae30a5927901e2a3da,7499
-llama_deploy/core/config.py,sha256=69bb0ea8ac169eaa4e808cd60a098b616bddd3145d26c6c35e56db38496b0e6a,35
-llama_deploy/core/deployment_config.py,sha256=ff10cc96f2c64abc4761eb83c5372fd22f3770159b45503818264723b578de4e,15092
-llama_deploy/core/git/git_util.py,sha256=c581c1da13871b4e89eda58f56ddb074139454c06ae9b04c0b396fdb2b9a5176,9193
-llama_deploy/core/path_util.py,sha256=14d50c0c337c8450ed46cafc88436027056b365a48370a69cdb76c88d7c26fd1,798
-llama_deploy/core/py.typed,sha256=e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855,0
-llama_deploy/core/schema/__init__.py,sha256=cc60a6fb54983d7ca13e2cc86d414a0d006a79c20e44344701f9fbe3b1d21577,739
-llama_deploy/core/schema/base.py,sha256=c02e33e35e7e4540b3065a82267febeb6da169222210a1d1c2479f6a7f1c6a4b,802
-llama_deploy/core/schema/deployments.py,sha256=1e310548f6847ee000b06d655b3fec006148bd2994b4c6b7d073582a7c312ec1,6392
-llama_deploy/core/schema/git_validation.py,sha256=27b306aa6ecabe58cab6381d92551545f263fe7550c58b3087115410bc71fd21,1915
-llama_deploy/core/schema/projects.py,sha256=c97eda38207d80354c2ee3a237cba9c3f6838148197cfa2d97b9a18d3da1a38b,294
-llama_deploy/core/server/manage_api/__init__.py,sha256=ed814d76fcade150d43205631b12bcae0b06bc2b8456a81fee24d6cf867adbc8,370
-llama_deploy/core/server/manage_api/_abstract_deployments_service.py,sha256=1bb1fbe904f84f892f092fb82d931cb2c2ca6a7563a64fb6ab52be21c02d75e5,4290
-llama_deploy/core/server/manage_api/_create_deployments_router.py,sha256=9b3fd2eeae027e3095da4db1785cdcc971b49023de615efe13b0a9e5f649982d,6081
-llama_deploy/core/server/manage_api/_exceptions.py,sha256=ee71cd9c2354a665e6905cd9cc752d2d65f71f0b936d33fec3c1c5229c38accf,246
-llama_deploy/core/ui_build.py,sha256=290dafa951918e5593b9035570fa4c66791d7e5ea785bd372ad11e99e8283857,1514
-llama_deploy_core-0.3.0a11.dist-info/WHEEL,sha256=66530aef82d5020ef5af27ae0123c71abb9261377c5bc519376c671346b12918,79
-llama_deploy_core-0.3.0a11.dist-info/METADATA,sha256=c8e44fcfa8c82bb7d0a3c2fa07f6fd8381e30f3876f01deb929dc199d9b5260d,627
-llama_deploy_core-0.3.0a11.dist-info/RECORD,,