From c528e0abc7efd1d4ce7bcaf592671e372c195f5a Mon Sep 17 00:00:00 2001
From: root <root@localhost.localdomain>
Date: Mon, 13 Apr 2026 17:38:40 +0800
Subject: [PATCH] =?UTF-8?q?fix(article-summary):=20=E4=BF=AE=E5=A4=8D=20ar?=
 =?UTF-8?q?ticle=5Fsummary=20pipeline=20=E7=9A=84=203=20=E4=B8=AA=20bug?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

1. Bug 3 (文件名含斜杠导致路径错误):
   - safe_title 生成时用 .replace('/', '-') 处理 '/' 字符
   - 同时清理连续 dash (--+) 和首尾 dash
   - 原本只处理空格，导致含 '/' 的标题写出路径错误

2. Bug 2 (delivery payload 格式不匹配):
   - 新增 '_iter_selected_items' 对 'candidates' 数组格式的支持
   - 自动 normalize selected_ids 的 'cand:' 前缀
   - candidate 条目同时支持 item_id 字段(新增)和 candidate_id(兼容)
   - 传入 delivery payload + candidate_id 时可正常匹配

3. Pipeline 补充 item_id 字段:
   - OpenClawCandidateInput 加 item_id 字段
   - build_openclaw_candidate_input 填充 item_id
   - 使得后续 article-summary 可通过 item_id 关联 extracted 文件
---
 src/summary_mcp/models/article_candidate.py  |  2 ++
 src/summary_mcp/workflows/article_summary.py | 35 ++++++++++++++++++--
 2 files changed, 34 insertions(+), 3 deletions(-)

diff --git a/src/summary_mcp/models/article_candidate.py b/src/summary_mcp/models/article_candidate.py
index 844d08c..91f0845 100644
--- a/src/summary_mcp/models/article_candidate.py
+++ b/src/summary_mcp/models/article_candidate.py
@@ -66,6 +66,7 @@ class ArticleCandidateRecord(BaseModel):
 
 class OpenClawCandidateInput(BaseModel):
     candidate_id: str
+    item_id: str | None = None
     title: str
     url: HttpUrl
     canonical_url: HttpUrl | None = None
@@ -169,6 +170,7 @@ def build_openclaw_candidate_input(record: ArticleCandidateRecord) -> OpenClawCa
 
     return OpenClawCandidateInput(
         candidate_id=record.candidate_id,
+        item_id=item.item_id if item is not None else None,
         title=title,
         url=raw_url,
         canonical_url=normalize_candidate_url(raw_url),
diff --git a/src/summary_mcp/workflows/article_summary.py b/src/summary_mcp/workflows/article_summary.py
index 6bed434..b456639 100644
--- a/src/summary_mcp/workflows/article_summary.py
+++ b/src/summary_mcp/workflows/article_summary.py
@@ -110,6 +110,32 @@ def _iter_selected_items(
             }
         return
 
+    # Fallback: pipeline delivery payload with top-level "candidates" array.
+    # Each entry has item_id (the raw FreshRSS item_id) and candidate_id (with cand: prefix).
+    # Normalize selected_ids by stripping "cand:" prefix so they match item_id.
+    candidates = extracted_payload.get("candidates")
+    if isinstance(candidates, list):
+        norm_selected = {
+            sid.removeprefix("cand:") if sid.startswith("cand:") else sid
+            for sid in selected_ids
+        }
+        for entry in candidates:
+            if not isinstance(entry, Mapping):
+                continue
+            # Support both item_id field (new) and candidate_id (legacy fallback)
+            raw_item_id = entry.get("item_id") or ""
+            if not raw_item_id and entry.get("candidate_id"):
+                raw_item_id = entry["candidate_id"].removeprefix("cand:")
+            item_id = str(raw_item_id) if raw_item_id else None
+            if not item_id or item_id not in norm_selected:
+                continue
+            # Candidates store article fields directly, not nested under "article"
+            yield item_id, {
+                "item": {},
+                "extraction": {"article": entry, "warnings": []},
+            }
+        return
+
     # Fallback: legacy payload with top-level "items" array.
     items = extracted_payload.get("items")
     if isinstance(items, list):
@@ -120,11 +146,10 @@ def _iter_selected_items(
             item_id = str(raw_item_id) if raw_item_id is not None else None
             if not item_id or item_id not in selected_set:
                 continue
-
             yield item_id, item
         return
 
-    # Format 3: single-item extracted file produced by run_freshrss_pipeline debug mode.
+    # Format 3: single-item extracted file produced by run_freshrss_pipeline.
     # Shape: {"success": bool, "article": {"item_id": "...", ...}, "warnings": [...]}
     article = extracted_payload.get("article")
     if isinstance(article, Mapping):
@@ -293,8 +318,12 @@ def summarize_selected_articles(
             lines.append("、".join(topics))
             lines.append("")
 
+        # Normalize: collapse spaces/slashes/underscores to single dash, strip punctuation, collapse multi-dashes
+        normalized = str(title).lower()
+        for sep in (" ", "/", "_", "——", "―", "‐"):
+            normalized = normalized.replace(sep, "-")
         safe_title = "-".join(
-            str(title).lower().strip().replace(" ", "-").split()
+            part for part in normalized.split("-") if part
         )[:80]
         filename = f"{safe_title or item_id}.md"
         output_path = output_dir / filename