From 6afcdc18300dc67f9f941ad032bbdd76f8a09061 Mon Sep 17 00:00:00 2001
From: LLLin000 <809867916@qq.com>
Date: Mon, 6 Jul 2026 20:08:51 +0800
Subject: [PATCH] =?UTF-8?q?fix:=20PR8.1=20=E2=80=94=20status=20healthy=20i?=
 =?UTF-8?q?nit=20+=20object=5Funits=20rebuild=20+=20version=20bump?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

- status.py: healthy=True init before if exists: (was UnboundLocalError
  when vector DB doesn't exist)
- manifest.py: RETRIEVAL_POLICY_VERSION l4.body.v1 → l4.body.v2 to
  trigger object_units rebuild with PR7 fix (unit_id fallback)
- Object_units corrected from 20→311 after rebuild (was INSERT OR
  REPLACE overwrite from old empty unit_id)
- Coverage parity: 20 papers have body_units = 20 have object_units ✅
  (body=811 chunks, object=311 chunks, expected difference due to
   section-split vs 1:1 caption structure)
- Unit tests: 97 pass (subset)
---
 paperforge/embedding/status.py   | 1 +
 paperforge/retrieval/manifest.py | 2 +-
 2 files changed, 2 insertions(+), 1 deletion(-)

diff --git a/paperforge/embedding/status.py b/paperforge/embedding/status.py
index 0affcde6..2f6d315a 100644
--- a/paperforge/embedding/status.py
+++ b/paperforge/embedding/status.py
@@ -48,6 +48,7 @@ def get_embed_status(vault: Path) -> dict:
     body_chunk_count = 0
     error = ""
     corrupted = False
+    healthy = True
     if exists:
         # Count paperforge_fulltext
         try:
diff --git a/paperforge/retrieval/manifest.py b/paperforge/retrieval/manifest.py
index e05b0061..88262180 100644
--- a/paperforge/retrieval/manifest.py
+++ b/paperforge/retrieval/manifest.py
@@ -12,7 +12,7 @@ from hashlib import sha256
 from typing import Any
 import json
 
-RETRIEVAL_POLICY_VERSION = "l4.body.v1"
+RETRIEVAL_POLICY_VERSION = "l4.body.v2"
 
 
 def compute_body_units_hash(units: list[dict]) -> str: