From 52ce6bfdf5d06e3db9453a1690e573a851aff3a2 Mon Sep 17 00:00:00 2001
From: root <root@localhost.localdomain>
Date: Sat, 11 Apr 2026 23:04:13 +0800
Subject: [PATCH] fix: validate article summary extracted path input

---
 src/summary_mcp/runtime/article_summary_jobs.py | 17 +++++++++++++----
 src/summary_mcp/server.py                       |  4 ++--
 2 files changed, 15 insertions(+), 6 deletions(-)

diff --git a/src/summary_mcp/runtime/article_summary_jobs.py b/src/summary_mcp/runtime/article_summary_jobs.py
index 630c3a0..4db2cdb 100644
--- a/src/summary_mcp/runtime/article_summary_jobs.py
+++ b/src/summary_mcp/runtime/article_summary_jobs.py
@@ -76,6 +76,17 @@ def _load_result(job_id: str) -> dict[str, Any] | None:
     return json.loads(path.read_text(encoding="utf-8-sig"))
 
 
+def _validate_article_summary_extracted_path(extracted_path: Path) -> None:
+    if not extracted_path.exists():
+        raise FileNotFoundError(f"extracted_path does not exist: {extracted_path}")
+    if extracted_path.is_dir():
+        raise ValueError(
+            "extracted_path must be a JSON file, not a directory. "
+            "Pass a single extracted file like outputs/freshrss/rerun/<run-id>/extracted/item-01.extracted.json, "
+            "or a batch extracted JSON file."
+        )
+
+
 def start_article_summary_job(
     *,
     extracted_path: Path,
@@ -87,8 +98,7 @@ def start_article_summary_job(
     llm_model: str | None = None,
     llm_api_url: str | None = None,
 ) -> dict[str, Any]:
-    if not extracted_path.exists():
-        raise FileNotFoundError(f"extracted_path does not exist: {extracted_path}")
+    _validate_article_summary_extracted_path(extracted_path)
     if not selected_ids:
         raise ValueError("selected_ids must not be empty")
 
@@ -166,8 +176,7 @@ def run_article_summary_job(*, job_id: str) -> dict[str, Any]:
         extracted_path = Path(input_payload["extracted_path"])
         output_dir = Path(input_payload["output_dir"])
         selected_ids = list(input_payload["selected_ids"])
-        if not extracted_path.exists():
-            raise FileNotFoundError(f"extracted_path does not exist: {extracted_path}")
+        _validate_article_summary_extracted_path(extracted_path)
         if not selected_ids:
             raise ValueError("selected_ids must not be empty")
         store.finish_stage(
diff --git a/src/summary_mcp/server.py b/src/summary_mcp/server.py
index 2b9d0ed..8239ac8 100644
--- a/src/summary_mcp/server.py
+++ b/src/summary_mcp/server.py
@@ -27,6 +27,7 @@ from summary_mcp.runtime.article_summary_jobs import (
     get_article_summary_job_result as load_article_summary_job_result,
     get_article_summary_job_status as load_article_summary_job_status,
     start_article_summary_job as launch_article_summary_job,
+    _validate_article_summary_extracted_path,
 )
 from summary_mcp.runtime.resume_service import resume_run as resume_existing_run
 from summary_mcp.workflows import run_freshrss_pipeline
@@ -300,8 +301,7 @@ def generate_article_summaries(
     """
 
     extracted_path_obj = Path(extracted_path)
-    if not extracted_path_obj.exists():
-        raise FileNotFoundError(f"extracted_path does not exist: {extracted_path}")
+    _validate_article_summary_extracted_path(extracted_path_obj)
 
     if output_dir is None:
         default_dir = extracted_path_obj.parent / "single_summaries"