feat: sync latest ARR implementation

arr_processing/source_message.py

@@ -4,7 +4,7 @@ from __future__ import annotations
 
 from dataclasses import dataclass
 from typing import Any, Dict, Protocol
-from urllib.parse import urlparse
+from urllib.parse import quote, urlparse
 
 from arr_ingestion.contracts import ArtifactRef, ROLE_CONTRACTS
 from arr_processing.contracts import ProcessingRequest, canonical_json_bytes
@@ -13,7 +13,7 @@ from arr_storage.aliyun_oss_v2 import AliyunOssConfig
 from arr_storage.contracts import valid_object_key
 
 
-PROGRAM_INPUT_VERSION = "arr-opera-daily-program-input-2"
+PROGRAM_INPUT_VERSION = "arr-opera-daily-program-input-3"
 
 
 class ProcessingSourceResolver(Protocol):
@@ -23,12 +23,12 @@ class ProcessingSourceResolver(Protocol):
 
 @dataclass(frozen=True)
 class OssProcessingMessageBuilder:
-    """Resolve the ARR-owned source object and expose only non-secret OSS routing.
+    """Resolve one ARR-owned source to its public-read HTTPS object URL.
 
-    ``fetch_oss_file`` owns the download and its credential provider.  The Agent
-    receives the same attachment-shaped descriptor used by the existing hotel
-    runtime: bucket, endpoint host, exact object key, hash and size.  AccessKey,
-    Secret, local paths and signed URLs never enter the message.
+    The Agent receives an attachment-shaped descriptor containing the exact URL
+    that ``fetch_oss_file`` must use, plus non-secret provenance and integrity
+    fields. AccessKey, Secret, local paths and signed URLs never enter the
+    message.
     """
 
     config: AliyunOssConfig
@@ -37,6 +37,7 @@ class OssProcessingMessageBuilder:
     def message(self, request: ProcessingRequest) -> str:
         source = self.sources.source_for_attempt(request.job_id, request.attempt_no)
         self._validate_source(request, source)
+        endpoint_host = self._endpoint_host()
         if request.submission_grant is None:
             raise ProcessingError(
                 "PROCESSING_SUBMISSION_GRANT_MISSING",
@@ -60,8 +61,12 @@ class OssProcessingMessageBuilder:
                     "source_ref": {"source": "oss_attachments", "index": 0},
                     "oss": {
                         "bucket": self.config.bucket,
-                        "endpoint": self._endpoint_host(),
+                        "endpoint": endpoint_host,
                         "object_key": source.object_key,
+                        "url": self._public_object_url(
+                            endpoint_host,
+                            source.object_key,
+                        ),
                     },
                 }
             ],
@@ -101,12 +106,22 @@ class OssProcessingMessageBuilder:
             )
 
     def _endpoint_host(self) -> str:
+        expected_host = f"oss-{self.config.region}.aliyuncs.com"
         if self.config.endpoint:
             parsed = urlparse(self.config.endpoint)
-            if parsed.scheme != "https" or not parsed.hostname:
+            if (
+                parsed.scheme != "https"
+                or parsed.hostname != expected_host
+                or parsed.username is not None
+                or parsed.password is not None
+                or parsed.port is not None
+            ):
                 raise ProcessingError(
                     "PROCESSING_SOURCE_INVALID",
-                    "OSS endpoint is unavailable",
+                    "public OSS endpoint is unavailable",
                 )
-            return parsed.netloc
-        return f"oss-{self.config.region}.aliyuncs.com"
+        return expected_host
+
+    def _public_object_url(self, endpoint_host: str, object_key: str) -> str:
+        encoded_key = quote(object_key, safe="/")
+        return f"https://{self.config.bucket}.{endpoint_host}/{encoded_key}"