fix: follow active Telegram transcript after rotation

cron_tasks/ingest_transcript_to_memory.py

@@ -14,6 +14,7 @@ from __future__ import annotations
 
 import json
 import os
+import re
 from dataclasses import dataclass
 from datetime import datetime, timezone
 from pathlib import Path
@@ -29,6 +30,8 @@ WORKSPACE = Path("/root/.openclaw/workspace")
 MEMORY_DIR = WORKSPACE / "memory"
 SOURCES_PATH = MEMORY_DIR / "session_sources.json"
 STATE_PATH = MEMORY_DIR / "session_ingest_state.json"
+SESSIONS_DIR = Path("/root/.openclaw/agents/main/sessions")
+SESSIONS_INDEX = SESSIONS_DIR / "sessions.json"
 
 
 def _local_tz():
@@ -91,6 +94,24 @@ class Source:
     transcript_path: Path
 
 
+def _extract_chat_id(label: str) -> Optional[str]:
+    match = re.match(r"^[a-zA-Z0-9_-]+:(\d+)$", (label or "").strip())
+    return match.group(1) if match else None
+
+
+def _discover_transcript_for_label(label: str) -> Optional[Path]:
+    chat_id = _extract_chat_id(label)
+    if not chat_id:
+        return None
+    index = _load_json(SESSIONS_INDEX, {})
+    direct = index.get(f"agent:main:telegram:direct:{chat_id}") if isinstance(index, dict) else None
+    session_file = direct.get("sessionFile") if isinstance(direct, dict) else None
+    if not isinstance(session_file, str):
+        return None
+    path = Path(session_file)
+    return path if path.exists() else None
+
+
 def _load_sources() -> List[Source]:
     """
     Sources file format:
@@ -109,7 +130,8 @@ def _load_sources() -> List[Source]:
         p = item.get("path")
         if not isinstance(p, str) or not p:
             continue
-        sources.append(Source(label=label, transcript_path=Path(p)))
+        transcript_path = _discover_transcript_for_label(label) or Path(p)
+        sources.append(Source(label=label, transcript_path=transcript_path))
     return sources