fix(storage): 严格解析本地策略并原子执行数据库迁移

backend/app/database/db.py

@@ -32,8 +32,12 @@ def connect() -> sqlite3.Connection:
     # 关闭 Python sqlite3 的隐式事务，提交时机由 transaction() 或显式 commit 控制。
     conn.isolation_level = None
     conn.execute("PRAGMA foreign_keys = ON")
+    try:
         _load_extension(conn)
         migrate(conn)
+    except BaseException:
+        conn.close()
+        raise
     return conn
 
 

backend/app/database/migrations.py

@@ -6,6 +6,7 @@
 """
 
 from datetime import datetime, timezone
+import sqlite3
 
 from app.constants import EMBEDDING_DIM
 
@@ -134,6 +135,18 @@ MIGRATIONS: list[str] = [
 ]
 
 
+def _statements(script: str):
+    """Split complete SQLite statements without executescript's implicit COMMIT."""
+    pending = ""
+    for char in script:
+        pending += char
+        if char == ";" and sqlite3.complete_statement(pending):
+            yield pending
+            pending = ""
+    if pending.strip():
+        yield pending
+
+
 def migrate(conn) -> None:
     """把尚未应用的迁移脚本按序应用到给定连接。"""
     conn.execute(
@@ -145,9 +158,28 @@ def migrate(conn) -> None:
     for idx, script in enumerate(MIGRATIONS, start=1):
         if idx in applied:
             continue
-        conn.executescript(script)
+        conn.execute("BEGIN IMMEDIATE")
+        try:
+            # Another connection may have migrated while this one waited.
+            if not conn.execute("SELECT 1 FROM schema_migrations WHERE version=?", (idx,)).fetchone():
+                recovered_v6 = False
+                if idx == 6:
+                    column = next((row for row in conn.execute("PRAGMA table_info(blocks)")
+                                   if row["name"] == "embedding_local_only"), None)
+                    if column is not None:
+                        # Recover the precise partial state left by the old v6 runner.
+                        if column["type"].upper() != "INTEGER" or column["notnull"] != 1 or column["dflt_value"] != "0":
+                            raise sqlite3.DatabaseError("Unexpected embedding_local_only column schema")
+                        recovered_v6 = True
+                if not recovered_v6:
+                    for statement in _statements(script):
+                        conn.execute(statement)
                 conn.execute(
                     "INSERT INTO schema_migrations (version, applied_at) VALUES (?, ?)",
                     (idx, datetime.now(timezone.utc).isoformat()),
                 )
-        conn.commit()
+            conn.execute("COMMIT")
+        except BaseException:
+            if conn.in_transaction:
+                conn.execute("ROLLBACK")
+            raise

backend/app/knowledge/parser.py

@@ -13,7 +13,10 @@ from dataclasses import dataclass, field
 from datetime import datetime
 from pathlib import Path
 
+import yaml
+
 from app.contracts import NoteBlock
+from app.errors import ApiError
 from app.textutils import count_tokens
 
 _HEADING_RE = re.compile(r"^(#{1,6})[ \t]+(.*?)\s*$")
@@ -70,7 +73,7 @@ def parse_note(
         created_at=created_at,
         updated_at=updated_at,
         blocks=blocks,
-        embedding_local_only=str(frontmatter.get("embedding_local_only", "")).lower() == "true",
+        embedding_local_only=_embedding_policy(markdown),
     )
 
 
@@ -184,6 +187,35 @@ def _utf16_len(text: str) -> int:
     return len(text.encode("utf-16-le")) // 2
 
 
+def _embedding_policy(markdown: str) -> bool:
+    end = markdown.find("\n---", 3) if markdown.startswith("---") else -1
+    if end == -1:
+        return False
+    try:
+        # Compose nodes without constructing objects. This accepts YAML comments,
+        # quoted keys and indentation while retaining duplicate-key information.
+        node = yaml.compose(markdown[3:end], Loader=yaml.SafeLoader)
+    except yaml.YAMLError as exc:
+        raise ApiError(422, "INVALID_EMBEDDING_POLICY", "Frontmatter YAML 无效，无法确认本地索引策略。") from exc
+    if node is None:
+        return False
+    if not isinstance(node, yaml.MappingNode):
+        raise ApiError(422, "INVALID_EMBEDDING_POLICY", "Frontmatter 必须是 YAML 键值映射。")
+    if any(key.tag == "tag:yaml.org,2002:merge" for key, _ in node.value):
+        raise ApiError(422, "INVALID_EMBEDDING_POLICY", "Frontmatter 不支持 YAML 合并键，请显式声明索引策略。")
+    values = [value for key, value in node.value
+              if isinstance(key, yaml.ScalarNode) and key.value.lower() == "embedding_local_only"]
+    if not values:
+        return False
+    if len(values) > 1:
+        raise ApiError(422, "INVALID_EMBEDDING_POLICY", "embedding_local_only 不能重复声明。")
+    value = values[0]
+    if (not isinstance(value, yaml.ScalarNode) or value.tag != "tag:yaml.org,2002:bool"
+            or value.value.lower() not in {"true", "false", "yes", "no", "on", "off"}):
+        raise ApiError(422, "INVALID_EMBEDDING_POLICY", "embedding_local_only 必须是 YAML 布尔值 true 或 false。")
+    return value.value.lower() in {"true", "yes", "on"}
+
+
 def _extract_frontmatter(markdown: str) -> dict[str, str]:
     """极简 frontmatter 解析，只提取 key: value 行。"""
     if not markdown.startswith("---"):

backend/tests/test_media_jobs.py

@@ -125,6 +125,8 @@ def test_local_only_export_and_rebuild_keep_local_embedding_policy(monkeypatch):
         job = await jobs.create_transcription('lecture.txt', local_only=True)
         note = await create_transcript_note(job.job_id, TranscriptNoteRequest(title='Private'))
         assert note.markdown.startswith('---\nembedding_local_only: true\n---')
+        await note_service.update_note(note.note_id, markdown=note.markdown.replace(
+            'embedding_local_only: true', 'embedding_local_only: true # keep local'))
         await index_service.rebuild(IndexRebuildRequest())
-        assert len(calls) >= 2 and all(calls)
+        assert len(calls) >= 3 and all(calls)
     asyncio.run(scenario())

backend/tests/test_policy_and_migrations.py

@@ -0,0 +1,110 @@
+import sqlite3
+from datetime import datetime, timezone
+from concurrent.futures import ThreadPoolExecutor
+
+import pytest
+
+from app.database import migrations
+from app.database.db import _load_extension
+from app.errors import ApiError
+from app.knowledge.parser import parse_note
+
+
+def parsed(value):
+    return parse_note(markdown='---\nembedding_local_only: '+value+'\n---\nbody', file_path='note.md', folder='',
+                      created_at=datetime.now(timezone.utc), updated_at=datetime.now(timezone.utc))
+
+
+@pytest.mark.parametrize('value,expected', [('true', True), ('true # keep local', True), ('TRUE # comment', True), ('false # explicit', False)])
+def test_policy_parses_yaml_boolean_with_comments(value, expected):
+    assert parsed(value).embedding_local_only is expected
+
+
+@pytest.mark.parametrize('value', ['truth', '1', '', 'null', '"true"', '[true]', '{broken', 'true\nembedding_local_only: false'])
+def test_invalid_policy_never_silently_enables_remote(value):
+    with pytest.raises(ApiError) as error:
+        parsed(value)
+    assert error.value.code == 'INVALID_EMBEDDING_POLICY'
+
+
+def connection(path, factory=sqlite3.Connection):
+    conn = sqlite3.connect(path, isolation_level=None, factory=factory)
+    conn.row_factory = sqlite3.Row
+    _load_extension(conn)
+    return conn
+
+
+def seed_v5(path, monkeypatch):
+    conn = connection(path)
+    with monkeypatch.context() as patch:
+        patch.setattr(migrations, 'MIGRATIONS', migrations.MIGRATIONS[:5])
+        migrations.migrate(conn)
+    conn.execute("INSERT INTO search_history(query) VALUES ('retained')")
+    conn.close()
+
+
+@pytest.mark.parametrize('failure', [sqlite3.OperationalError, KeyboardInterrupt])
+def test_migration_and_version_write_rollback_together(tmp_path, monkeypatch, failure):
+    path = tmp_path / 'migration.db'
+    seed_v5(path, monkeypatch)
+    class Interrupted(sqlite3.Connection):
+        def execute(self, sql, parameters=()):
+            if sql.startswith('INSERT INTO schema_migrations') and parameters[0] == 6:
+                raise failure('interrupted')
+            return super().execute(sql, parameters)
+    conn = connection(path, Interrupted)
+    try:
+        with pytest.raises(failure):
+            migrations.migrate(conn)
+        assert not conn.in_transaction
+        assert not any(r['name'] == 'embedding_local_only' for r in conn.execute('pragma table_info(blocks)'))
+    finally:
+        conn.close()
+    conn = connection(path)
+    try:
+        migrations.migrate(conn)
+        assert conn.execute('select count(*) from schema_migrations where version=6').fetchone()[0] == 1
+        assert conn.execute('select query from search_history').fetchone()[0] == 'retained'
+    finally:
+        conn.close()
+
+
+def test_old_partial_v6_recovers_without_duplicate_column(tmp_path, monkeypatch):
+    path = tmp_path / 'partial.db'
+    seed_v5(path, monkeypatch)
+    conn = connection(path)
+    try:
+        conn.executescript(migrations.MIGRATIONS[5])
+        migrations.migrate(conn)
+        migrations.migrate(conn)
+        assert conn.execute('select count(*) from schema_migrations where version=6').fetchone()[0] == 1
+        assert conn.execute('select query from search_history').fetchone()[0] == 'retained'
+    finally:
+        conn.close()
+
+
+def test_concurrent_connections_can_upgrade(tmp_path, monkeypatch):
+    path = tmp_path / 'concurrent.db'
+    seed_v5(path, monkeypatch)
+    def upgrade(_):
+        conn = connection(path)
+        try:
+            migrations.migrate(conn)
+            return conn.execute('select count(*) from schema_migrations where version=6').fetchone()[0]
+        finally:
+            conn.close()
+    with ThreadPoolExecutor(max_workers=2) as pool:
+        assert list(pool.map(upgrade, range(2))) == [1, 1]
+
+
+@pytest.mark.parametrize('header', ['"embedding_local_only": true # comment', '  embedding_local_only: true', 'embedding_local_only:\n  true', 'local: &local true\nembedding_local_only: *local'])
+def test_policy_supports_yaml_key_and_scalar_forms(header):
+    note = parse_note(markdown='---\n'+header+'\n---\nbody',file_path='note.md',folder='',created_at=datetime.now(timezone.utc),updated_at=datetime.now(timezone.utc))
+    assert note.embedding_local_only
+
+
+def test_merge_policy_is_rejected_instead_of_ignored():
+    with pytest.raises(ApiError):
+        parsed('true\n<<: {embedding_local_only: false}')
+    with pytest.raises(ApiError):
+        parsed('!!bool invalid')