fix: rebuild trustworthy local-day evidence (#99)

src/fenris/repair.py

@@ -1,8 +1,9 @@
-"""Historical repair and retention (issue #74).
+"""Historical repair and retention (issue #74, #99).
 
 Re-derives hour observations and day aggregates from surviving raw samples,
-with idempotent and interruption-safe guarantees. Preserves import markers,
-boundary anchors, and valid historical summaries.
+rebuilds legacy local-day evidence from surviving samples or trustworthy UTC
+hours, and preserves import markers, boundary anchors, and valid summaries.
+Repair is idempotent and interruption-safe.
 
 Contracts:
 - Idempotent: running repair multiple times produces no duplicates
@@ -71,7 +72,6 @@ def _set_repair_in_progress(conn: sqlite3.Connection, in_progress: bool) -> None
         "INSERT OR REPLACE INTO store_metadata (key, value) VALUES (?, ?)",
         ("repair_in_progress", "true" if in_progress else "false"),
     )
-    conn.commit()
 
 
 def _update_repair_status(conn: sqlite3.Connection, result: RepairResult) -> None:
@@ -100,8 +100,6 @@ def _update_repair_status(conn: sqlite3.Connection, result: RepairResult) -> Non
         "INSERT OR REPLACE INTO store_metadata (key, value) VALUES (?, ?)",
         ("days_derived", str(days)),
     )
-    
-    conn.commit()
 
 
 def get_repair_status(conn: sqlite3.Connection) -> RepairStatus:
@@ -364,20 +362,16 @@ def repair_derivation(
     elif hasattr(clock, 'utcnow'):
         clock = clock.utcnow()
     
-    # Check if repair is already in progress
-    if is_repair_in_progress(conn):
-        return RepairResult(
-            ok=False,
-            error="Repair already in progress",
-        )
-    
-    # Mark repair as in progress
-    _set_repair_in_progress(conn, True)
-    
     result = RepairResult(ok=True)
     
     try:
-        # Begin transaction
+        # A committed in-progress marker may be stale after process death.
+        # SQLite's write lock serializes active repairs; retry idempotently.
+        if conn.in_transaction:
+            conn.commit()
+        conn.execute("BEGIN IMMEDIATE")
+        _set_repair_in_progress(conn, True)
+        conn.commit()
         conn.execute("BEGIN IMMEDIATE")
         
         # 1. Find and derive intervals from sample pairs
@@ -407,7 +401,12 @@ def repair_derivation(
                     result.days_created += 1
                 else:
                     result.days_updated += 1
-        
+
+        # Rebuild only legacy or unavailable local-day activity. This shares
+        # the migration derivation and leaves trustworthy published totals intact.
+        from .local_day import repair_legacy_local_day_evidence
+        repair_legacy_local_day_evidence(conn)
+
         # 3. Count boundary anchors retained
         now = clock if isinstance(clock, datetime) else datetime.now(timezone.utc)
         cursor = conn.execute("SELECT ts FROM samples ORDER BY ts")
@@ -428,21 +427,22 @@ def repair_derivation(
         )
         result.legacy_summaries_preserved = cursor.fetchone()[0]
         
-        # Commit transaction
-        conn.commit()
-        
-        # Update repair status
+        # Publish derived rows and completion status together. A process
+        # interruption rolls back the in-progress marker with the repair.
         _update_repair_status(conn, result)
+        _set_repair_in_progress(conn, False)
+        conn.commit()
         
     except Exception as e:
         conn.rollback()
+        try:
+            _set_repair_in_progress(conn, False)
+            conn.commit()
+        except sqlite3.Error:
+            conn.rollback()
         logger.error("Repair failed: %s", e)
         return RepairResult(
             ok=False,
             error=str(e),
         )
-    finally:
-        # Mark repair as complete
-        _set_repair_in_progress(conn, False)
-    
     return result