don't use S3 CreateBucket and clean up

Pass S3_REGION and S3_PUBLIC_USE_SSL through compose, treat blank public
SSL as unset, and skip CreateBucket when IAM only allows access to an
existing bucket.

.env.example

@@ -1,5 +1,6 @@
 S3_ENDPOINT=seaweedfs:8333
 S3_PUBLIC_ENDPOINT=localhost:8333
+S3_BUCKET=officeconvert
 S3_USE_SSL=false
 # Presigned URLs; omit to match S3_USE_SSL (internal client uses S3_ENDPOINT).
 S3_PUBLIC_USE_SSL=false

Makefile

@@ -2,7 +2,7 @@ SHELL := /bin/sh
 
 BUF ?= buf
 
-.PHONY: buf-lint buf-generate py-sync py-test go-test test compose-up compose-up-dev run-server
+.PHONY: buf-lint buf-generate py-sync py-test go-test test compose-up compose-up-dev s3-init run-server
 
 buf-lint:
 	$(BUF) lint
@@ -32,7 +32,21 @@ compose-up:
 compose-up-dev:
 	docker compose --env-file .env.example -f deploy/docker-compose.dev.yml up
 
-run-server:
+s3-init:
+	@set -a; \
+	if [ -f .env ]; then . ./.env; fi; \
+	set +a; \
+	endpoint="$${S3_ENDPOINT:-localhost:8333}"; \
+	case "$$endpoint" in seaweedfs:8333) endpoint=localhost:8333 ;; esac; \
+	bucket="$${S3_BUCKET:-officeconvert}"; \
+	access_key="$${S3_ACCESS_KEY:-minioadmin}"; \
+	secret_key="$${S3_SECRET_KEY:-minioadmin}"; \
+	port="$${endpoint#*:}"; \
+	docker run --rm --add-host=host.docker.internal:host-gateway minio/mc:latest /bin/sh -c " \
+	  mc alias set local http://host.docker.internal:$$port '$$access_key' '$$secret_key' && \
+	  mc mb local/$$bucket --ignore-existing"
+
+run-server: s3-init
 	@set -a; \
 	if [ -f .env ]; then . ./.env; fi; \
 	set +a; \
@@ -41,6 +55,7 @@ run-server:
 	if [ "$${S3_PUBLIC_ENDPOINT:-}" = "seaweedfs:8333" ]; then S3_PUBLIC_ENDPOINT=localhost:8333; fi; \
 	export S3_ENDPOINT="$${S3_ENDPOINT:-localhost:8333}"; \
 	export S3_PUBLIC_ENDPOINT="$${S3_PUBLIC_ENDPOINT:-localhost:8333}"; \
+	export S3_BUCKET="$${S3_BUCKET:-officeconvert}"; \
 	export S3_USE_SSL="$${S3_USE_SSL:-false}"; \
 	export S3_ACCESS_KEY="$${S3_ACCESS_KEY:-minioadmin}"; \
 	export S3_SECRET_KEY="$${S3_SECRET_KEY:-minioadmin}"; \

README.md

@@ -135,9 +135,75 @@ Use `.env.example` as your baseline env configuration.
 
 ## Storage Backend Notes
 
-- This project defaults to **SeaweedFS S3 API** for object transit in development and compose deployments.
+- Local development defaults to **SeaweedFS** (S3-compatible) via Docker Compose. Compose runs an `s3-init` step that creates the dev bucket before the server starts.
-- The Python server uses the `minio` Python SDK, which is intentional because SeaweedFS is S3-compatible.
+- Production can use any S3-compatible provider; **AWS S3** is the expected choice.
+- The Python server uses the `minio` Python SDK against the S3 API.
 - Runtime configuration uses `S3_*` environment variables.
+- All conversions share one bucket (`S3_BUCKET`, required). Each conversion's objects live under a `{conversion_id}/` key prefix (for example `{conversion_id}/input/source.pptx` and `{conversion_id}/output/slide-0001.jpg`).
+
+### AWS setup
+
+**Bucket**
+
+1. Create one bucket (for example `officeconvert-prod`) in the region where the server runs.
+2. Leave **Block Public Access** enabled. Presigned URLs work without a public bucket.
+3. Optional: add a lifecycle rule to expire objects after a few days as a safety net if cleanup fails.
+
+**Server environment**
+
+Set at minimum:
+
+```bash
+S3_BUCKET=officeconvert-prod
+S3_ENDPOINT=s3.us-east-1.amazonaws.com
+S3_PUBLIC_ENDPOINT=s3.us-east-1.amazonaws.com
+S3_REGION=us-east-1
+S3_USE_SSL=true
+S3_PUBLIC_USE_SSL=true
+S3_ACCESS_KEY=...
+S3_SECRET_KEY=...
+```
+
+Use your bucket's regional hostname for both endpoints unless you deliberately split internal vs client-facing access. `S3_PUBLIC_ENDPOINT` must be reachable by whatever uploads and downloads via presigned URLs (clients, not just the server).
+
+On startup the server verifies the bucket exists via HeadBucket and fails fast if it is missing. **Pre-create the bucket** before deploying (see IAM below).
+
+**IAM permissions**
+
+Scope access to the single bucket. Object keys are per-conversion prefixes, so list/delete can target the whole bucket. Startup verification uses HeadBucket, which is satisfied by `s3:ListBucket` on the bucket ARN:
+
+```json
+{
+  "Version": "2012-10-17",
+  "Statement": [
+    {
+      "Effect": "Allow",
+      "Action": ["s3:ListBucket", "s3:HeadBucket"],
+      "Resource": "arn:aws:s3:::officeconvert-prod"
+    },
+    {
+      "Effect": "Allow",
+      "Action": ["s3:GetObject", "s3:PutObject", "s3:DeleteObject"],
+      "Resource": "arn:aws:s3:::officeconvert-prod/*"
+    }
+  ]
+}
+```
+
+**CORS**
+
+Required only if uploads or downloads go **directly from a browser** to presigned URLs. Server-side clients (`curl`, the Go client) do not need CORS. Allow `PUT` and `GET` for your web origin on the bucket.
+
+**IAM roles vs IAM users**
+
+AWS recommends **roles** over long-lived **IAM user** access keys when the server runs on AWS compute (ECS, EC2, Lambda): a role grants **temporary** credentials that rotate automatically, with no static keys to store or leak.
+
+For this project today, the server reads explicit `S3_ACCESS_KEY` and `S3_SECRET_KEY` via the MinIO SDK. That maps cleanly to:
+
+| Where you run | Practical choice |
+|---------------|------------------|
+| Docker on a VPS, bare metal, or outside AWS | IAM **user** with the policy above; store keys in env or a secrets manager. Fine for a single service at low volume. |
+| ECS / EC2 / EKS on AWS | Prefer an IAM **role** attached to the task or instance. Your orchestrator injects short-lived credentials; you still pass them into `S3_ACCESS_KEY` / `S3_SECRET_KEY` (and a session token if your runtime provides one — the server does not yet read a dedicated `S3_SESSION_TOKEN` env var). |
 
 ## Conversion Tuning Notes
 

deploy/docker-compose.yml

@@ -14,16 +14,34 @@ services:
     volumes:
       - seaweedfs_data:/data
 
+  s3-init:
+    image: minio/mc:latest
+    depends_on:
+      - seaweedfs
+    environment:
+      AWS_ACCESS_KEY_ID: ${S3_ACCESS_KEY:-minioadmin}
+      AWS_SECRET_ACCESS_KEY: ${S3_SECRET_KEY:-minioadmin}
+      S3_BUCKET: ${S3_BUCKET:-officeconvert}
+    entrypoint: >
+      /bin/sh -c "
+      until mc alias set local http://seaweedfs:8333 $$AWS_ACCESS_KEY_ID $$AWS_SECRET_ACCESS_KEY; do sleep 1; done &&
+      mc mb local/$$S3_BUCKET --ignore-existing
+      "
+
   server:
     build:
       context: ..
       dockerfile: Dockerfile.server
     depends_on:
-      - seaweedfs
+      s3-init:
+        condition: service_completed_successfully
     environment:
       S3_ENDPOINT: ${S3_ENDPOINT:-seaweedfs:8333}
       S3_PUBLIC_ENDPOINT: ${S3_PUBLIC_ENDPOINT:-localhost:8333}
+      S3_BUCKET: ${S3_BUCKET:-officeconvert}
+      S3_REGION: ${S3_REGION:-}
       S3_USE_SSL: ${S3_USE_SSL:-false}
+      S3_PUBLIC_USE_SSL: ${S3_PUBLIC_USE_SSL:-}
       S3_ACCESS_KEY: ${S3_ACCESS_KEY:-minioadmin}
       S3_SECRET_KEY: ${S3_SECRET_KEY:-minioadmin}
       S3_SESSION_TTL_SECONDS: ${S3_SESSION_TTL_SECONDS:-3600}

docker-compose.yml

@@ -15,14 +15,32 @@ services:
     volumes:
       - seaweedfs_data:/data
 
-  server:
+  s3-init:
-    image: gitea.auvem.com/end/officeconvert-server:${OFFICECONVERT_IMAGE_TAG:-latest}
+    image: minio/mc:latest
     depends_on:
       - seaweedfs
+    environment:
+      AWS_ACCESS_KEY_ID: ${S3_ACCESS_KEY:-minioadmin}
+      AWS_SECRET_ACCESS_KEY: ${S3_SECRET_KEY:-minioadmin}
+      S3_BUCKET: ${S3_BUCKET:-officeconvert}
+    entrypoint: >
+      /bin/sh -c "
+      until mc alias set local http://seaweedfs:8333 $$AWS_ACCESS_KEY_ID $$AWS_SECRET_ACCESS_KEY; do sleep 1; done &&
+      mc mb local/$$S3_BUCKET --ignore-existing
+      "
+
+  server:
+    image: gitea.auvem.com/end/officeconvert-server:${OFFICECONVERT_IMAGE_TAG:-latest}
+    depends_on:
+      s3-init:
+        condition: service_completed_successfully
     environment:
       S3_ENDPOINT: ${S3_ENDPOINT:-seaweedfs:8333}
       S3_PUBLIC_ENDPOINT: ${S3_PUBLIC_ENDPOINT:-localhost:8333}
+      S3_BUCKET: ${S3_BUCKET:-officeconvert}
+      S3_REGION: ${S3_REGION:-}
       S3_USE_SSL: ${S3_USE_SSL:-false}
+      S3_PUBLIC_USE_SSL: ${S3_PUBLIC_USE_SSL:-}
       S3_ACCESS_KEY: ${S3_ACCESS_KEY:-minioadmin}
       S3_SECRET_KEY: ${S3_SECRET_KEY:-minioadmin}
       S3_SESSION_TTL_SECONDS: ${S3_SESSION_TTL_SECONDS:-3600}

gen/go/officeconvertapi/v1/conversion.pb.go

@@ -777,7 +777,6 @@ type CreateConversionResponse struct {
 	state protoimpl.MessageState `protogen:"open.v1"`
 	// Session identifier: KSUID in standard base62 text form. Well-formed values are at most 27 characters (see https://github.com/segmentio/ksuid).
 	ConversionId    string                 `protobuf:"bytes,1,opt,name=conversion_id,json=conversionId,proto3" json:"conversion_id,omitempty"`
-	UploadBucket    string                 `protobuf:"bytes,2,opt,name=upload_bucket,json=uploadBucket,proto3" json:"upload_bucket,omitempty"`
 	UploadObjectKey string                 `protobuf:"bytes,3,opt,name=upload_object_key,json=uploadObjectKey,proto3" json:"upload_object_key,omitempty"`
 	UploadUrl       string                 `protobuf:"bytes,4,opt,name=upload_url,json=uploadUrl,proto3" json:"upload_url,omitempty"`
 	ExpiresAt       *timestamppb.Timestamp `protobuf:"bytes,5,opt,name=expires_at,json=expiresAt,proto3" json:"expires_at,omitempty"`
@@ -822,13 +821,6 @@ func (x *CreateConversionResponse) GetConversionId() string {
 	return ""
 }
 
-func (x *CreateConversionResponse) GetUploadBucket() string {
-	if x != nil {
-		return x.UploadBucket
-	}
-	return ""
-}
-
 func (x *CreateConversionResponse) GetUploadObjectKey() string {
 	if x != nil {
 		return x.UploadObjectKey
@@ -1330,15 +1322,14 @@ const file_officeconvertapi_v1_conversion_proto_rawDesc = "" +
 	"\x0fsource_filename\x18\x01 \x01(\tR\x0esourceFilename\x12;\n" +
 	"\x04full\x18\x02 \x01(\v2'.officeconvertapi.v1.SlideRasterOptionsR\x04full\x12E\n" +
 	"\tthumbnail\x18\x03 \x01(\v2'.officeconvertapi.v1.SlideRasterOptionsR\tthumbnail\x127\n" +
-	"\x05notes\x18\x04 \x01(\v2!.officeconvertapi.v1.NotesOptionsR\x05notes\"\xea\x01\n" +
+	"\x05notes\x18\x04 \x01(\v2!.officeconvertapi.v1.NotesOptionsR\x05notes\"\xda\x01\n" +
 	"\x18CreateConversionResponse\x12#\n" +
-	"\rconversion_id\x18\x01 \x01(\tR\fconversionId\x12#\n" +
+	"\rconversion_id\x18\x01 \x01(\tR\fconversionId\x12*\n" +
-	"\rupload_bucket\x18\x02 \x01(\tR\fuploadBucket\x12*\n" +
 	"\x11upload_object_key\x18\x03 \x01(\tR\x0fuploadObjectKey\x12\x1d\n" +
 	"\n" +
 	"upload_url\x18\x04 \x01(\tR\tuploadUrl\x129\n" +
 	"\n" +
-	"expires_at\x18\x05 \x01(\v2\x1a.google.protobuf.TimestampR\texpiresAt\"=\n" +
+	"expires_at\x18\x05 \x01(\v2\x1a.google.protobuf.TimestampR\texpiresAtJ\x04\b\x02\x10\x03R\rupload_bucket\"=\n" +
 	"\x16StartConversionRequest\x12#\n" +
 	"\rconversion_id\x18\x01 \x01(\tR\fconversionId\"}\n" +
 	"\x17StartConversionResponse\x12#\n" +

gen/python/officeconvertapi/v1/conversion_pb2.pyi

@@ -149,18 +149,16 @@ class CreateConversionRequest(_message.Message):
     def __init__(self, source_filename: _Optional[str] = ..., full: _Optional[_Union[SlideRasterOptions, _Mapping]] = ..., thumbnail: _Optional[_Union[SlideRasterOptions, _Mapping]] = ..., notes: _Optional[_Union[NotesOptions, _Mapping]] = ...) -> None: ...
 
 class CreateConversionResponse(_message.Message):
-    __slots__ = ("conversion_id", "upload_bucket", "upload_object_key", "upload_url", "expires_at")
+    __slots__ = ("conversion_id", "upload_object_key", "upload_url", "expires_at")
     CONVERSION_ID_FIELD_NUMBER: _ClassVar[int]
-    UPLOAD_BUCKET_FIELD_NUMBER: _ClassVar[int]
     UPLOAD_OBJECT_KEY_FIELD_NUMBER: _ClassVar[int]
     UPLOAD_URL_FIELD_NUMBER: _ClassVar[int]
     EXPIRES_AT_FIELD_NUMBER: _ClassVar[int]
     conversion_id: str
-    upload_bucket: str
     upload_object_key: str
     upload_url: str
     expires_at: _timestamp_pb2.Timestamp
-    def __init__(self, conversion_id: _Optional[str] = ..., upload_bucket: _Optional[str] = ..., upload_object_key: _Optional[str] = ..., upload_url: _Optional[str] = ..., expires_at: _Optional[_Union[datetime.datetime, _timestamp_pb2.Timestamp, _Mapping]] = ...) -> None: ...
+    def __init__(self, conversion_id: _Optional[str] = ..., upload_object_key: _Optional[str] = ..., upload_url: _Optional[str] = ..., expires_at: _Optional[_Union[datetime.datetime, _timestamp_pb2.Timestamp, _Mapping]] = ...) -> None: ...
 
 class StartConversionRequest(_message.Message):
     __slots__ = ("conversion_id",)

proto/officeconvertapi/v1/conversion.proto

@@ -136,7 +136,8 @@ message CreateConversionRequest {
 message CreateConversionResponse {
   // Session identifier: KSUID in standard base62 text form. Well-formed values are at most 27 characters (see https://github.com/segmentio/ksuid).
   string conversion_id = 1;
-  string upload_bucket = 2;
+  reserved 2;
+  reserved "upload_bucket";
   string upload_object_key = 3;
   string upload_url = 4;
   google.protobuf.Timestamp expires_at = 5;

python/packages/server/pyproject.toml

@@ -8,6 +8,7 @@ dependencies = [
   "connectrpc>=0.10.0",
   "minio>=7.2.18",
   "officeconvert",
+  "protobuf>=7.35.0",
   "svix-ksuid>=0.7.0",
   "uvicorn>=0.35.0",
 ]

python/packages/server/src/officeconvert_server/app.py

@@ -10,7 +10,9 @@ from officeconvertapi.v1.conversion_connect import ConversionServiceASGIApplicat
 
 from officeconvert_server.config import load_server_config
 from officeconvert_server.service import ConversionServiceImpl
-from officeconvert_server.storage import S3Store
+from officeconvert_server.storage import S3Store, log_s3_error
+
+from minio.error import S3Error
 
 logger = logging.getLogger(__name__)
 
@@ -44,6 +46,7 @@ def create_app() -> ConversionServiceASGIApplication:
     _configure_application_logging()
     config = load_server_config()
     store = S3Store(
+        bucket=config.s3_bucket,
         endpoint=config.s3_endpoint,
         access_key=config.s3_access_key,
         secret_key=config.s3_secret_key,
@@ -55,6 +58,16 @@ def create_app() -> ConversionServiceASGIApplication:
     if os.getenv("OFFICECONVERT_S3_TRACE", "").lower() in ("1", "true", "yes"):
         store.enable_http_trace(sys.stderr)
         logger.warning("OFFICECONVERT_S3_TRACE enabled: S3 HTTP dumps on stderr")
+    try:
+        store.require_bucket()
+    except S3Error as exc:
+        log_s3_error(
+            "require_bucket",
+            endpoint=config.s3_endpoint,
+            secure=config.s3_secure,
+            exc=exc,
+        )
+        raise
     service = ConversionServiceImpl(config=config, store=store)
     return ConversionServiceASGIApplication(service)
 

python/packages/server/src/officeconvert_server/config.py

@@ -10,6 +10,7 @@ import os
 class ServerConfig:
     """Defines environment-driven settings for server orchestration."""
 
+    s3_bucket: str
     s3_endpoint: str
     s3_access_key: str
     s3_secret_key: str
@@ -30,14 +31,18 @@ class ServerConfig:
 def load_server_config() -> ServerConfig:
     """Load server configuration from environment variables."""
     s3_secure = os.getenv("S3_USE_SSL", "false").lower() == "true"
-    public_ssl_env = os.getenv("S3_PUBLIC_USE_SSL")
+    public_ssl_env = os.getenv("S3_PUBLIC_USE_SSL", "").strip()
     s3_public_secure = (
         public_ssl_env.lower() == "true"
-        if public_ssl_env is not None
+        if public_ssl_env
         else s3_secure
     )
     region_env = os.getenv("S3_REGION", "").strip()
+    s3_bucket = os.getenv("S3_BUCKET", "").strip()
+    if not s3_bucket:
+        raise ValueError("S3_BUCKET is required")
     return ServerConfig(
+        s3_bucket=s3_bucket,
         s3_endpoint=os.getenv("S3_ENDPOINT", "localhost:8333"),
         s3_access_key=os.getenv("S3_ACCESS_KEY", "minioadmin"),
         s3_secret_key=os.getenv("S3_SECRET_KEY", "minioadmin"),

python/packages/server/src/officeconvert_server/models.py

@@ -23,7 +23,7 @@ class ConversionSession:
     thumbnail_resolution: conversion_pb2.ConversionResolution
     full_jpeg_quality: int
     thumbnail_jpeg_quality: int
-    bucket_name: str
+    object_prefix: str
     upload_object_key: str
     status: conversion_pb2.ConversionStatus
     notes: conversion_pb2.NotesOptions | None = None

python/packages/server/src/officeconvert_server/service.py

@@ -122,23 +122,12 @@ class ConversionServiceImpl(conversion_connect.ConversionService):
 
         ksuid = Ksuid()
         conversion_id = str(ksuid)
-        bucket_name = f"oc-{bytes(ksuid).hex()}"
+        object_prefix = f"{conversion_id}/"
-        upload_key = "input/source.pptx"
+        upload_key = f"{object_prefix}input/source.pptx"
         expires_at = utc_now() + timedelta(seconds=self._config.s3_session_ttl_seconds)
 
-        try:
-            self._store.ensure_bucket(bucket_name)
-        except S3Error as exc:
-            log_s3_error(
-                "ensure_bucket",
-                endpoint=self._config.s3_endpoint,
-                secure=self._config.s3_secure,
-                exc=exc,
-            )
-            raise
         try:
             upload_url = self._store.presigned_put_url(
-                bucket_name,
                 upload_key,
                 ttl_seconds=self._config.s3_session_ttl_seconds,
             )
@@ -159,7 +148,7 @@ class ConversionServiceImpl(conversion_connect.ConversionService):
             full_jpeg_quality=full_jpeg_quality,
             thumbnail_jpeg_quality=thumbnail_jpeg_quality,
             notes=request.notes if request.HasField("notes") else None,
-            bucket_name=bucket_name,
+            object_prefix=object_prefix,
             upload_object_key=upload_key,
             status=conversion_pb2.CONVERSION_STATUS_PENDING,
         )
@@ -168,7 +157,6 @@ class ConversionServiceImpl(conversion_connect.ConversionService):
 
         return conversion_pb2.CreateConversionResponse(
             conversion_id=conversion_id,
-            upload_bucket=bucket_name,
             upload_object_key=upload_key,
             upload_url=upload_url,
             expires_at=_to_timestamp(expires_at),
@@ -265,7 +253,10 @@ class ConversionServiceImpl(conversion_connect.ConversionService):
         if session.conversion_task is not None and not session.conversion_task.done():
             session.conversion_task.cancel()
         await self._cleanup_local_artifacts(session)
-        await asyncio.to_thread(self._store.remove_bucket_tree, session.bucket_name)
+        await asyncio.to_thread(
+            self._store.remove_prefix,
+            session.object_prefix,
+        )
         return conversion_pb2.DeleteConversionResponse(
             conversion_id=session.conversion_id,
             deleted=True,
@@ -295,7 +286,6 @@ class ConversionServiceImpl(conversion_connect.ConversionService):
         try:
             await asyncio.to_thread(
                 self._store.fget_object,
-                session.bucket_name,
                 session.upload_object_key,
                 source_path,
             )
@@ -436,10 +426,11 @@ class ConversionServiceImpl(conversion_connect.ConversionService):
         upload_total = slide_total * 2
         upload_index = 0
         for slide in slides:
-            object_key = f"output/slide-{slide.index:04d}{slide.image_path.suffix}"
+            object_key = (
-            self._store.fput_object(session.bucket_name, object_key, slide.image_path)
+                f"{session.object_prefix}output/slide-{slide.index:04d}{slide.image_path.suffix}"
+            )
+            self._store.fput_object(object_key, slide.image_path)
             image_url = self._store.presigned_get_url(
-                session.bucket_name,
                 object_key,
                 ttl_seconds=self._config.s3_session_ttl_seconds,
             )
@@ -447,15 +438,14 @@ class ConversionServiceImpl(conversion_connect.ConversionService):
             if progress_callback is not None:
                 progress_callback(upload_index, upload_total)
             thumbnail_object_key = (
-                f"output/thumb/slide-{slide.index:04d}{slide.thumbnail_path.suffix}"
+                f"{session.object_prefix}output/thumb/slide-{slide.index:04d}"
+                f"{slide.thumbnail_path.suffix}"
             )
             self._store.fput_object(
-                session.bucket_name,
                 thumbnail_object_key,
                 slide.thumbnail_path,
             )
             thumbnail_image_url = self._store.presigned_get_url(
-                session.bucket_name,
                 thumbnail_object_key,
                 ttl_seconds=self._config.s3_session_ttl_seconds,
             )
@@ -515,7 +505,10 @@ class ConversionServiceImpl(conversion_connect.ConversionService):
         """Delete storage resources after the configured session retention period."""
         try:
             await asyncio.sleep(self._config.conversion_cleanup_delay_seconds)
-            await asyncio.to_thread(self._store.remove_bucket_tree, session.bucket_name)
+            await asyncio.to_thread(
+                self._store.remove_prefix,
+                session.object_prefix,
+            )
         except asyncio.CancelledError:
             return
         finally:

python/packages/server/src/officeconvert_server/storage.py

@@ -6,7 +6,6 @@ import logging
 from datetime import timedelta
 from pathlib import Path
 from typing import TextIO
-from urllib.parse import urlparse
 
 from minio import Minio
 from minio.deleteobjects import DeleteObject
@@ -54,6 +53,7 @@ class S3Store:
     def __init__(
         self,
         *,
+        bucket: str,
         endpoint: str,
         access_key: str,
         secret_key: str,
@@ -63,6 +63,7 @@ class S3Store:
         public_secure: bool,
     ) -> None:
         """Initialize S3 clients for internal and public URL generation."""
+        self._bucket = bucket
         self._client = Minio(
             endpoint,
             access_key=access_key,
@@ -83,61 +84,62 @@ class S3Store:
         self._client.trace_on(stream)
         self._public_client.trace_on(stream)
 
-    def ensure_bucket(self, bucket_name: str) -> None:
+    def require_bucket(self) -> None:
-        """Create a bucket if it does not already exist.
+        """Verify the configured bucket exists before serving traffic."""
+        if not self._client.bucket_exists(self._bucket):
+            raise RuntimeError(
+                f"S3 bucket {self._bucket!r} does not exist; create it before starting the server"
+            )
 
-        Uses CreateBucket only, not HeadBucket. Some S3-compatible stores
+    def presigned_put_url(self, object_key: str, *, ttl_seconds: int) -> str:
-        (including SeaweedFS) mishandle or over-restrict HeadBucket; the MinIO
-        client's bucket_exists() maps non-NoSuchBucket errors to failures.
-        Idempotent create covers the same contract with fewer round trips.
-        """
-        try:
-            self._client.make_bucket(bucket_name)
-        except S3Error as exc:
-            if exc.code in ("BucketAlreadyOwnedByYou", "BucketAlreadyExists"):
-                return
-            raise
-
-    def presigned_put_url(self, bucket_name: str, object_key: str, *, ttl_seconds: int) -> str:
         """Generate a presigned PUT URL for a single object upload."""
         return self._public_client.presigned_put_object(
-            bucket_name,
+            self._bucket,
             object_key,
             expires=timedelta(seconds=ttl_seconds),
         )
 
-    def presigned_get_url(self, bucket_name: str, object_key: str, *, ttl_seconds: int) -> str:
+    def presigned_get_url(self, object_key: str, *, ttl_seconds: int) -> str:
         """Generate a presigned GET URL for downloading one object."""
         return self._public_client.presigned_get_object(
-            bucket_name,
+            self._bucket,
             object_key,
             expires=timedelta(seconds=ttl_seconds),
         )
 
-    def fget_object(self, bucket_name: str, object_key: str, output_path: Path) -> None:
+    def fget_object(self, object_key: str, output_path: Path) -> None:
         """Download one object from storage to a local filesystem path."""
         output_path.parent.mkdir(parents=True, exist_ok=True)
-        self._client.fget_object(bucket_name, object_key, str(output_path))
+        self._client.fget_object(self._bucket, object_key, str(output_path))
 
-    def fput_object(self, bucket_name: str, object_key: str, source_path: Path) -> None:
+    def fput_object(self, object_key: str, source_path: Path) -> None:
         """Upload one local filesystem object to storage."""
-        self._client.fput_object(bucket_name, object_key, str(source_path))
+        self._client.fput_object(self._bucket, object_key, str(source_path))
+
+    def remove_prefix(self, prefix: str) -> None:
+        """Remove all objects under a key prefix within the configured bucket."""
+        normalized_prefix = prefix if prefix.endswith("/") else f"{prefix}/"
+        objects = list(
+            self._client.list_objects(
+                self._bucket,
+                prefix=normalized_prefix,
+                recursive=True,
+            )
+        )
+        if not objects:
+            return
 
-    def remove_bucket_tree(self, bucket_name: str) -> None:
-        """Remove all objects in a bucket and then delete the bucket."""
-        objects = list(self._client.list_objects(bucket_name, recursive=True))
-        if objects:
         delete_requests: list[DeleteObject] = []
         for obj in objects:
             object_name = obj.object_name
             if object_name is None:
                 raise RuntimeError(
-                        "encountered unnamed object while removing bucket contents"
+                    "encountered unnamed object while removing prefix contents"
                 )
             delete_requests.append(DeleteObject(object_name))
 
         errors = self._client.remove_objects(
-                bucket_name,
+            self._bucket,
             delete_requests,
         )
         for err in errors:
@@ -146,16 +148,3 @@ class S3Store:
             raise RuntimeError(
                 f"failed to delete object {object_name}: {message}"
             )
-        try:
-            self._client.remove_bucket(bucket_name)
-        except S3Error as exc:
-            # Concurrent cleanup paths may race to remove the same bucket.
-            if exc.code != "NoSuchBucket":
-                raise
-
-
-def object_key_from_presigned_url(url: str) -> str:
-    """Extract object key from a presigned URL path for diagnostics."""
-    path = urlparse(url).path
-    path_parts = [part for part in path.split("/") if part]
-    return "/".join(path_parts[1:]) if len(path_parts) >= 2 else ""

python/uv.lock

@@ -292,6 +292,7 @@ dependencies = [
     { name = "connectrpc" },
     { name = "minio" },
     { name = "officeconvert" },
+    { name = "protobuf" },
     { name = "svix-ksuid" },
     { name = "uvicorn" },
 ]
@@ -301,6 +302,7 @@ requires-dist = [
     { name = "connectrpc", specifier = ">=0.10.0" },
     { name = "minio", specifier = ">=7.2.18" },
     { name = "officeconvert", editable = "packages/officeconvert" },
+    { name = "protobuf", specifier = ">=7.35.0" },
     { name = "svix-ksuid", specifier = ">=0.7.0" },
     { name = "uvicorn", specifier = ">=0.35.0" },
 ]
@@ -394,17 +396,17 @@ wheels = [
 
 [[package]]
 name = "protobuf"
-version = "7.34.1"
+version = "7.35.1"
 source = { registry = "https://pypi.org/simple" }
-sdist = { url = "https://files.pythonhosted.org/packages/6b/6b/a0e95cad1ad7cc3f2c6821fcab91671bd5b78bd42afb357bb4765f29bc41/protobuf-7.34.1.tar.gz", hash = "sha256:9ce42245e704cc5027be797c1db1eb93184d44d1cdd71811fb2d9b25ad541280", size = 454708, upload-time = "2026-03-20T17:34:47.036Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/da/01/9ef0afd7999eb9badb3a768b4aedd78c86d4c65cfaf1958ab276199e76b4/protobuf-7.35.1.tar.gz", hash = "sha256:ce115a26fe0c39a2c29973d914d327e516a6455464489fe3cd1e51a1b354f81a", size = 458717, upload-time = "2026-06-11T21:55:40.257Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/ec/11/3325d41e6ee15bf1125654301211247b042563bcc898784351252549a8ad/protobuf-7.34.1-cp310-abi3-macosx_10_9_universal2.whl", hash = "sha256:d8b2cc79c4d8f62b293ad9b11ec3aebce9af481fa73e64556969f7345ebf9fc7", size = 429247, upload-time = "2026-03-20T17:34:37.024Z" },
+    { url = "https://files.pythonhosted.org/packages/10/03/8aeeb7458d22546bf64b5250ca1daeb5ff757d900e8e4a7476c6f0db843e/protobuf-7.35.1-cp310-abi3-macosx_10_9_universal2.whl", hash = "sha256:24f857477359a85c0c235261b8ba905fd51b2562f4a64ca1df5473f29850cbf6", size = 433226, upload-time = "2026-06-11T21:55:31.719Z" },
-    { url = "https://files.pythonhosted.org/packages/eb/9d/aa69df2724ff63efa6f72307b483ce0827f4347cc6d6df24b59e26659fef/protobuf-7.34.1-cp310-abi3-manylinux2014_aarch64.whl", hash = "sha256:5185e0e948d07abe94bb76ec9b8416b604cfe5da6f871d67aad30cbf24c3110b", size = 325753, upload-time = "2026-03-20T17:34:38.751Z" },
+    { url = "https://files.pythonhosted.org/packages/37/4b/dfb89eb0e652a1ff073c39a59fb5e3a83cfe9b57a2c83fa6d78270101767/protobuf-7.35.1-cp310-abi3-manylinux2014_aarch64.whl", hash = "sha256:11d6b0ec246892d85215b0a13ca6e0233cf5284b68f0ac02646427f4ff88a799", size = 328847, upload-time = "2026-06-11T21:55:34.035Z" },
-    { url = "https://files.pythonhosted.org/packages/92/e8/d174c91fd48e50101943f042b09af9029064810b734e4160bbe282fa1caa/protobuf-7.34.1-cp310-abi3-manylinux2014_s390x.whl", hash = "sha256:403b093a6e28a960372b44e5eb081775c9b056e816a8029c61231743d63f881a", size = 340198, upload-time = "2026-03-20T17:34:39.871Z" },
+    { url = "https://files.pythonhosted.org/packages/0f/58/dc12f2cd484951524af6e3382c785869b9b3fb5e52ee95ae23add53ee8f9/protobuf-7.35.1-cp310-abi3-manylinux2014_s390x.whl", hash = "sha256:b73f9489a4b8b1c9cb1f8ed951c736392592edb24b9d6819f36d2e10b171d5b4", size = 344030, upload-time = "2026-06-11T21:55:34.941Z" },
-    { url = "https://files.pythonhosted.org/packages/53/1b/3b431694a4dc6d37b9f653f0c64b0a0d9ec074ee810710c0c3da21d67ba7/protobuf-7.34.1-cp310-abi3-manylinux2014_x86_64.whl", hash = "sha256:8ff40ce8cd688f7265326b38d5a1bed9bfdf5e6723d49961432f83e21d5713e4", size = 324267, upload-time = "2026-03-20T17:34:41.1Z" },
+    { url = "https://files.pythonhosted.org/packages/e4/be/5b3cfe508bfab6761414ff944e3366eb13be4fd71efcd69450f89ba39f43/protobuf-7.35.1-cp310-abi3-manylinux2014_x86_64.whl", hash = "sha256:74758715c53d7158fb76caf4f0cfdacc5329a4b1bb994f865d6cf302d413a1c4", size = 327130, upload-time = "2026-06-11T21:55:35.921Z" },
-    { url = "https://files.pythonhosted.org/packages/85/29/64de04a0ac142fb685fd09999bc3d337943fb386f3a0ec57f92fd8203f97/protobuf-7.34.1-cp310-abi3-win32.whl", hash = "sha256:34b84ce27680df7cca9f231043ada0daa55d0c44a2ddfaa58ec1d0d89d8bf60a", size = 426628, upload-time = "2026-03-20T17:34:42.536Z" },
+    { url = "https://files.pythonhosted.org/packages/d8/bc/6d6c7ba8709c85f8f2c390b2b118d6fb08a783676a572271851bf45a7d22/protobuf-7.35.1-cp310-abi3-win32.whl", hash = "sha256:353652e4efd0bca5b5fc2656abf8307ef351f0cf938c9eba09f0e09c20a25c30", size = 428945, upload-time = "2026-06-11T21:55:37.034Z" },
-    { url = "https://files.pythonhosted.org/packages/4d/87/cb5e585192a22b8bd457df5a2c16a75ea0db9674c3a0a39fc9347d84e075/protobuf-7.34.1-cp310-abi3-win_amd64.whl", hash = "sha256:e97b55646e6ce5cbb0954a8c28cd39a5869b59090dfaa7df4598a7fba869468c", size = 437901, upload-time = "2026-03-20T17:34:44.112Z" },
+    { url = "https://files.pythonhosted.org/packages/0a/19/8d0cb6f20a1ef7b18f1c8986ad5783f22f84cce39c6ce9a6e645ea55192e/protobuf-7.35.1-cp310-abi3-win_amd64.whl", hash = "sha256:230a75ddfc2de4806e56696ce9640c1cdfdb6543b7cfce98d42a4c0a0e7bdb87", size = 439996, upload-time = "2026-06-11T21:55:38.123Z" },
-    { url = "https://files.pythonhosted.org/packages/88/95/608f665226bca68b736b79e457fded9a2a38c4f4379a4a7614303d9db3bc/protobuf-7.34.1-py3-none-any.whl", hash = "sha256:bb3812cd53aefea2b028ef42bd780f5b96407247f20c6ef7c679807e9d188f11", size = 170715, upload-time = "2026-03-20T17:34:45.384Z" },
+    { url = "https://files.pythonhosted.org/packages/19/c7/5f7c636ec43e0c545e28d1f1db71990108306f7bdcb89f069ba97e428e7f/protobuf-7.35.1-py3-none-any.whl", hash = "sha256:4bc97768d8fe4ad6743c8a19403e314511ed9f6d13205b687e52421c023ac1b9", size = 171659, upload-time = "2026-06-11T21:55:39.155Z" },
 ]
 
 [[package]]