fix(file-summary): 同步压缩包工作流状态与结果刷新

review_agent/file_summary/skills/archive_extract.py

@@ -2,6 +2,7 @@ from __future__ import annotations
 
 import logging
 from pathlib import Path
+import re
 
 from review_agent.models import FileSummaryBatchAttachment
 
@@ -13,34 +14,56 @@ from .base import BaseSkill, SkillResult, WorkflowContext
 logger = logging.getLogger("review_agent.file_summary.skills.archive_extract")
 
 
+def _safe_archive_dir_name(binding: FileSummaryBatchAttachment) -> str:
+    stem = Path(binding.attachment.original_name).stem or "archive"
+    safe_stem = re.sub(r"[^A-Za-z0-9._-]+", "_", stem).strip("._") or "archive"
+    return f"{binding.attachment_id}_{safe_stem}"
+
+
 class ArchiveExtractSkill(BaseSkill):
     name = "archive_extract"
 
     def run(self, context: WorkflowContext) -> SkillResult:
         extracted_count = 0
-        target_dir = Path(context.batch.work_dir or "")
-        if not target_dir:
-            logger.info(
-                "Archive extract skipped without work dir",
+        if not context.batch.work_dir:
+            message = "批次工作目录为空，无法解压压缩包。"
+            logger.error(
+                "Archive extract failed without work dir",
                 extra={"batch_id": context.batch.pk, "batch_no": context.batch.batch_no},
             )
-            return SkillResult(success=True, data={"extracted_count": 0})
+            return SkillResult(success=False, message=message, data={"extracted_count": 0})
+        target_root = Path(context.batch.work_dir)
 
+        archive_count = 0
         for binding in FileSummaryBatchAttachment.objects.filter(batch=context.batch):
             path = resolve_storage_path(binding.attachment.storage_path)
             if path.suffix.lower().lstrip(".") not in ARCHIVE_EXTENSIONS:
                 continue
+            archive_count += 1
+            target_dir = target_root / "extracted" / _safe_archive_dir_name(binding)
             logger.info(
                 "Archive extract started",
                 extra={
                     "batch_id": context.batch.pk,
                     "attachment_id": binding.attachment_id,
                     "path": str(path),
+                    "target_dir": str(target_dir),
                 },
             )
             extracted_count += len(extract_archive(path, target_dir))
+        if archive_count and extracted_count == 0:
+            message = "压缩包未解出任何可扫描文件，请检查压缩包内容或格式。"
+            logger.warning(
+                "Archive extract produced no files",
+                extra={"batch_id": context.batch.pk, "archive_count": archive_count},
+            )
+            return SkillResult(success=False, message=message, data={"extracted_count": 0})
         logger.info(
             "Archive extract finished",
-            extra={"batch_id": context.batch.pk, "extracted_count": extracted_count},
+            extra={
+                "batch_id": context.batch.pk,
+                "archive_count": archive_count,
+                "extracted_count": extracted_count,
+            },
         )
         return SkillResult(success=True, data={"extracted_count": extracted_count})

review_agent/file_summary/skills/file_inventory.py

@@ -2,10 +2,12 @@ from __future__ import annotations
 
 import logging
 from pathlib import Path
+import re
 
 from review_agent.models import FileSummaryBatchAttachment
 
 from ..paths import resolve_storage_path
+from ..services.archive import ARCHIVE_EXTENSIONS
 from ..services.inventory import scan_files_to_items
 from .base import BaseSkill, SkillResult, WorkflowContext
 
@@ -13,14 +15,44 @@ from .base import BaseSkill, SkillResult, WorkflowContext
 logger = logging.getLogger("review_agent.file_summary.skills.file_inventory")
 
 
+def _safe_archive_dir_name(binding: FileSummaryBatchAttachment) -> str:
+    stem = Path(binding.attachment.original_name).stem or "archive"
+    safe_stem = re.sub(r"[^A-Za-z0-9._-]+", "_", stem).strip("._") or "archive"
+    return f"{binding.attachment_id}_{safe_stem}"
+
+
 class FileInventorySkill(BaseSkill):
     name = "file_inventory"
 
     def run(self, context: WorkflowContext) -> SkillResult:
-        roots = [
-            resolve_storage_path(binding.attachment.storage_path)
-            for binding in FileSummaryBatchAttachment.objects.filter(batch=context.batch)
-        ]
+        roots: list[Path] = []
+        missing_extract_roots: list[str] = []
+        for binding in FileSummaryBatchAttachment.objects.filter(batch=context.batch):
+            original_path = resolve_storage_path(binding.attachment.storage_path)
+            is_archive = original_path.suffix.lower().lstrip(".") in ARCHIVE_EXTENSIONS
+            if not is_archive:
+                roots.append(original_path)
+                continue
+
+            extracted_root = (
+                Path(context.batch.work_dir)
+                / "extracted"
+                / _safe_archive_dir_name(binding)
+            )
+            if extracted_root.exists():
+                roots.append(extracted_root)
+            else:
+                missing_extract_roots.append(str(extracted_root))
+        if missing_extract_roots:
+            message = "压缩包解压目录不存在，无法扫描解压后的文件。"
+            logger.warning(
+                "File inventory missing extracted roots",
+                extra={
+                    "batch_id": context.batch.pk,
+                    "missing_extract_roots": missing_extract_roots,
+                },
+            )
+            return SkillResult(success=False, message=message)
         logger.info(
             "File inventory started",
             extra={