feat: add Vertex AI support for all providers

.github/workflows/ci.yml

@@ -85,6 +85,7 @@ jobs:
       - uses: ./.github/actions/setup-python-uv
         with:
           python-version: ${{ matrix.python-version }}
+      - run: uv sync --extra gcp
       - run: uv run pytest tests/unit_tests -v --cov=celeste --cov-report=term-missing --cov-report=xml --cov-report=html --cov-fail-under=80
       - uses: codecov/codecov-action@v4
         if: matrix.os == 'ubuntu-latest' && matrix.python-version == '3.12'

.github/workflows/claude-code-review.yml

@@ -41,4 +41,3 @@ jobs:
           prompt: '/code-review:code-review ${{ github.repository }}/pull/${{ github.event.pull_request.number }}'
           # See https://github.com/anthropics/claude-code-action/blob/main/docs/usage.md
           # or https://code.claude.com/docs/en/cli-reference for available options
-

.github/workflows/claude.yml

@@ -47,4 +47,3 @@ jobs:
           # See https://github.com/anthropics/claude-code-action/blob/main/docs/usage.md
           # or https://code.claude.com/docs/en/cli-reference for available options
           # claude_args: '--allowed-tools Bash(gh pr:*)'
-

.github/workflows/publish.yml

@@ -58,6 +58,7 @@ jobs:
           workload_identity_provider: ${{ secrets.GCP_WORKLOAD_IDENTITY_PROVIDER }}
           service_account: ${{ secrets.GCP_SERVICE_ACCOUNT }}
       - uses: ./.github/actions/setup-python-uv
+      - run: uv sync --extra gcp
       - name: Run ${{ matrix.package }} integration tests
         env:
           OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}

src/celeste/client.py

@@ -296,9 +296,8 @@ def _handle_error_response(self, response: httpx.Response) -> None:
         """Handle error responses from provider APIs."""
         if not response.is_success:
             try:
-                error_data = response.json()
-                error_msg = error_data.get("error", {}).get("message", response.text)
-            except JSONDecodeError:
+                error_msg = response.json()["error"]["message"]
+            except (JSONDecodeError, KeyError, TypeError, IndexError):
                 error_msg = response.text or f"HTTP {response.status_code}"
 
             raise httpx.HTTPStatusError(

src/celeste/modalities/images/providers/google/gemini.py

@@ -82,7 +82,7 @@ def _init_request(self, inputs: ImageInput) -> dict[str, Any]:
         parts.append({"text": inputs.prompt})
 
         return {
-            "contents": [{"parts": parts}],
+            "contents": [{"role": "user", "parts": parts}],
             "generationConfig": {
                 "responseModalities": ["TEXT", "IMAGE"],
                 "imageConfig": {},
@@ -113,8 +113,7 @@ def _parse_content(
                 if not base64_data:
                     continue
                 mime_type = ImageMimeType(inline_data.get("mimeType", "image/png"))
-                image_bytes = base64.b64decode(base64_data)
-                artifacts.append(ImageArtifact(data=image_bytes, mime_type=mime_type))
+                artifacts.append(ImageArtifact(data=base64_data, mime_type=mime_type))
 
         if not artifacts:
             return ImageArtifact()

src/celeste/modalities/images/providers/google/imagen.py

@@ -1,6 +1,5 @@
 """Imagen client for Google images modality."""
 
-import base64
 from typing import Any, Unpack
 
 from celeste.artifacts import ImageArtifact
@@ -61,8 +60,7 @@ def _parse_content(
             if not base64_data:
                 continue
             mime_type = ImageMimeType(prediction.get("mimeType", "image/png"))
-            image_bytes = base64.b64decode(base64_data)
-            images.append(ImageArtifact(data=image_bytes, mime_type=mime_type))
+            images.append(ImageArtifact(data=base64_data, mime_type=mime_type))
 
         num_images_requested = parameters.get("num_images")
         if num_images_requested == 1:

src/celeste/modalities/videos/providers/google/client.py

@@ -3,6 +3,7 @@
 from typing import Any, Unpack
 
 from celeste.artifacts import VideoArtifact
+from celeste.mime_types import VideoMimeType
 from celeste.parameters import ParameterMapper
 from celeste.providers.google.veo import config
 from celeste.providers.google.veo.client import GoogleVeoClient as GoogleVeoMixin
@@ -51,6 +52,12 @@ def _parse_content(
     ) -> VideoArtifact:
         """Parse content from response."""
         video_data = super()._parse_content(response_data)
+        # Handle inline base64 response (Vertex can return bytesBase64Encoded)
+        if "bytesBase64Encoded" in video_data:
+            mime_type = video_data.get("mimeType", VideoMimeType.MP4)
+            return VideoArtifact(
+                data=video_data["bytesBase64Encoded"], mime_type=mime_type
+            )
         return VideoArtifact(url=video_data.get("uri"))
 
     def _parse_finish_reason(self, response_data: dict[str, Any]) -> VideoFinishReason:
@@ -62,13 +69,16 @@ async def download_content(self, artifact: VideoArtifact) -> VideoArtifact:
         """Download video content from GCS URL.
 
         Args:
-            artifact: VideoArtifact with URL to download.
+            artifact: VideoArtifact with URL or inline data to download.
 
         Returns:
             VideoArtifact with downloaded bytes data.
         """
+        if artifact.data is not None:
+            return artifact
+
         if artifact.url is None:
-            msg = "Artifact has no URL to download"
+            msg = "Artifact has no URL or data to download"
             raise ValueError(msg)
 
         video_bytes = await super().download_content(artifact.url)

src/celeste/providers/anthropic/messages/client.py

@@ -7,6 +7,7 @@
 from celeste.core import UsageField
 from celeste.io import FinishReason
 from celeste.mime_types import ApplicationMimeType
+from celeste.providers.google.auth import GoogleADC
 
 from . import config
 
@@ -22,6 +23,10 @@ class AnthropicMessagesClient(APIMixin):
     - _parse_finish_reason() - Extract finish reason from response
     - _build_metadata() - Filter content fields
 
+    Auth-based endpoint selection:
+    - GoogleADC auth -> Vertex AI endpoints (Claude on Google Cloud)
+    - API key auth -> Anthropic API endpoints
+
     Usage:
         class AnthropicTextGenerationClient(AnthropicMessagesClient, TextGenerationClient):
             def _parse_content(self, response_data, **parameters):
@@ -32,6 +37,23 @@ def _parse_content(self, response_data, **parameters):
                 return ""
     """
 
+    def _get_vertex_endpoint(
+        self, anthropic_endpoint: str, streaming: bool = False
+    ) -> str:
+        """Map Anthropic endpoint to Vertex AI endpoint."""
+        if streaming:
+            return config.VertexAnthropicEndpoint.STREAM_MESSAGE
+        return config.VertexAnthropicEndpoint.CREATE_MESSAGE
+
+    def _build_url(self, endpoint: str, streaming: bool = False) -> str:
+        """Build full URL based on auth type."""
+        if isinstance(self.auth, GoogleADC):
+            return self.auth.build_url(
+                self._get_vertex_endpoint(endpoint, streaming=streaming),
+                model_id=self.model.id,
+            )
+        return f"{config.BASE_URL}{endpoint}"
+
     def _build_headers(self, request_body: dict[str, Any]) -> dict[str, str]:
         """Build headers with beta features extracted from request."""
         beta_features: list[str] = request_body.pop("_beta_features", [])
@@ -85,7 +107,7 @@ async def _make_request(
             endpoint = config.AnthropicMessagesEndpoint.CREATE_MESSAGE
 
         response = await self.http_client.post(
-            f"{config.BASE_URL}{endpoint}",
+            url=self._build_url(endpoint, streaming=False),
             headers=headers,
             json_body=request_body,
         )
@@ -111,7 +133,7 @@ def _make_stream_request(
             endpoint = config.AnthropicMessagesEndpoint.CREATE_MESSAGE
 
         return self.http_client.stream_post(
-            f"{config.BASE_URL}{endpoint}",
+            url=self._build_url(endpoint, streaming=True),
             headers=headers,
             json_body=request_body,
         )

src/celeste/providers/anthropic/messages/config.py

@@ -12,6 +12,13 @@ class AnthropicMessagesEndpoint(StrEnum):
     GET_MODEL = "/v1/models/{model_id}"
 
 
+class VertexAnthropicEndpoint(StrEnum):
+    """Endpoints for Anthropic on Vertex AI."""
+
+    CREATE_MESSAGE = "/v1/projects/{project_id}/locations/{location}/publishers/anthropic/models/{model_id}:rawPredict"
+    STREAM_MESSAGE = "/v1/projects/{project_id}/locations/{location}/publishers/anthropic/models/{model_id}:streamRawPredict"
+
+
 BASE_URL = "https://api.anthropic.com"
 
 # Required

src/celeste/providers/deepseek/chat/client.py

@@ -7,6 +7,7 @@
 from celeste.core import UsageField
 from celeste.io import FinishReason
 from celeste.mime_types import ApplicationMimeType
+from celeste.providers.google.auth import GoogleADC
 
 from . import config
 
@@ -31,6 +32,22 @@ def _parse_content(self, response_data, **parameters):
                 return self._transform_output(content, **parameters)
     """
 
+    def _get_vertex_endpoint(self, deepseek_endpoint: str) -> str:
+        """Map DeepSeek endpoint to Vertex AI endpoint."""
+        mapping: dict[str, str] = {
+            config.DeepSeekChatEndpoint.CREATE_CHAT: config.VertexDeepSeekEndpoint.CREATE_CHAT,
+        }
+        vertex_endpoint = mapping.get(deepseek_endpoint)
+        if vertex_endpoint is None:
+            raise ValueError(f"No Vertex AI endpoint mapping for: {deepseek_endpoint}")
+        return vertex_endpoint
+
+    def _build_url(self, endpoint: str) -> str:
+        """Build full URL based on auth type."""
+        if isinstance(self.auth, GoogleADC):
+            return self.auth.build_url(self._get_vertex_endpoint(endpoint))
+        return f"{config.BASE_URL}{endpoint}"
+
     def _build_request(
         self,
         inputs: Any,
@@ -64,7 +81,7 @@ async def _make_request(
         }
 
         response = await self.http_client.post(
-            f"{config.BASE_URL}{endpoint}",
+            self._build_url(endpoint),
             headers=headers,
             json_body=request_body,
         )
@@ -89,7 +106,7 @@ def _make_stream_request(
         }
 
         return self.http_client.stream_post(
-            f"{config.BASE_URL}{endpoint}",
+            self._build_url(endpoint),
             headers=headers,
             json_body=request_body,
         )
@@ -100,8 +117,8 @@ def map_usage_fields(usage_data: dict[str, Any]) -> dict[str, int | float | None
 
         Shared by client and streaming across all capabilities.
         """
-        prompt_tokens_details = usage_data.get("prompt_tokens_details", {})
-        completion_tokens_details = usage_data.get("completion_tokens_details", {})
+        prompt_tokens_details = usage_data.get("prompt_tokens_details") or {}
+        completion_tokens_details = usage_data.get("completion_tokens_details") or {}
         return {
             UsageField.INPUT_TOKENS: usage_data.get("prompt_tokens"),
             UsageField.OUTPUT_TOKENS: usage_data.get("completion_tokens"),

src/celeste/providers/deepseek/chat/config.py

@@ -10,4 +10,10 @@ class DeepSeekChatEndpoint(StrEnum):
     LIST_MODELS = "/models"
 
 
+class VertexDeepSeekEndpoint(StrEnum):
+    """Endpoints for DeepSeek on Vertex AI (OpenAI-compatible)."""
+
+    CREATE_CHAT = "/v1/projects/{project_id}/locations/{location}/endpoints/openapi/chat/completions"
+
+
 BASE_URL = "https://api.deepseek.com"

src/celeste/providers/google/auth.py

@@ -68,5 +68,30 @@ def get_vertex_base_url(self) -> str:
             return VERTEX_GLOBAL_BASE_URL
         return VERTEX_BASE_URL.format(location=self.location)
 
+    def build_url(self, vertex_endpoint: str, model_id: str | None = None) -> str:
+        """Build a complete Vertex AI URL from an endpoint template.
+
+        Args:
+            vertex_endpoint: Endpoint template with {project_id}, {location}, and
+                optionally {model_id} placeholders.
+            model_id: Model identifier for endpoints that include it in the path.
+        """
+        project_id = self.resolved_project_id
+        if project_id is None:
+            raise ValueError(
+                "Vertex AI requires a project_id. "
+                "Pass project_id to GoogleADC() or ensure credentials have a project."
+            )
+        base_url = self.get_vertex_base_url()
+        if model_id is not None:
+            endpoint = vertex_endpoint.format(
+                project_id=project_id, location=self.location, model_id=model_id
+            )
+        else:
+            endpoint = vertex_endpoint.format(
+                project_id=project_id, location=self.location
+            )
+        return f"{base_url}{endpoint}"
+
 
 __all__ = ["GoogleADC"]

src/celeste/providers/google/cloud_tts/client.py

@@ -51,7 +51,8 @@ def map_usage_fields(usage_data: dict[str, Any]) -> dict[str, int | float | None
     def model_post_init(self, _context: Any) -> None:
         """Override auth to use ADC for Cloud TTS (not API key like Gemini)."""
         super().model_post_init(_context)  # type: ignore[misc]
-        object.__setattr__(self, "auth", GoogleADC())
+        if not isinstance(self.auth, GoogleADC):
+            object.__setattr__(self, "auth", GoogleADC())
 
     async def _make_request(
         self,