feat(openclaw): implement two-tier session maintenance with nightly resets for state-externalized agents

k8s/openclaw/setup-compaction-cron.sh

@@ -2,7 +2,13 @@
 # ==============================================================================
 # setup-compaction-cron.sh
 # Declaratively registers the Multi-Agent Nightly Session Compaction in OpenClaw.
-# Schedule: Every night at 03:30 Europe/Berlin (cron: 30 3 * * *)
+# Schedule: Every night at 04:45 Europe/Berlin (02:45 UTC) (cron: 45 4 * * *)
+#
+# Architecture:
+# - Tier A: Daily Hard-Reset to 0 for koch (Topic 21), hebamme (Topic 22), shopping (Topic 115)
+#   (100% externalized state in DuckDB/JSONL; resets prevent cross-day hallucination)
+# - Tier B: Smart Compaction for long-running project agents (itguy, recherche, regensburg, fitness, doktor)
+# - WAL checkpoints and SQLite optimization without blocking full VACUUM
 # ==============================================================================
 
 set -euo pipefail
@@ -12,21 +18,24 @@ POD_NAME="${POD_NAME:-openclaw-0}"
 CONTAINER_NAME="${CONTAINER_NAME:-openclaw}"
 
 JOB_NAME="nightly-session-compaction"
-CRON_SCHEDULE="30 3 * * *"
+CRON_SCHEDULE="45 4 * * *"
 TIMEZONE="Europe/Berlin"
 
-echo "=== Registering Multi-Agent Nightly Session Compaction in OpenClaw ($POD_NAME) ==="
+echo "=== Registering Multi-Agent Nightly Session Maintenance in OpenClaw ($POD_NAME) ==="
 
-# 1. Install or ensure python compaction script is present on PVC
+# 1. Install or ensure python maintenance script is present on PVC
 echo "Ensuring /home/node/.openclaw/scripts/compact_sessions.py exists..."
 kubectl exec -i -n "$NAMESPACE" "$POD_NAME" -c "$CONTAINER_NAME" -- /bin/sh -c 'cat << "EOF" > /home/node/.openclaw/scripts/compact_sessions.py
 #!/usr/bin/env python3
 """
-Nightly multi-agent session compaction and maintenance script for OpenClaw.
+Nightly multi-agent session maintenance and compaction script for OpenClaw.
 1. Pre-warms OS page cache for SQLite databases on spinning disks.
-2. Prunes abandoned isolated cron sessions (>48h old) to prevent token/state bloat.
+2. Recovers any wedged or locked sessions via recover_sessions.py.
-3. Compacts all active forum topics and main sessions exceeding the token threshold.
+3. Prunes abandoned isolated cron sessions (>48h old) to prevent token/state bloat.
-4. Checkpoints SQLite WAL journals across all agent databases to disk.
+4. Tier A Hard-Reset: Resets koch, hebamme, and shopping topics to 0 tokens (clean archive).
+5. Tier B Smart-Compaction: Compacts active sessions exceeding token thresholds (5s pacing).
+6. Checkpoints SQLite WAL journals across all agent databases to disk.
+7. Optimizes SQLite query planner without blocking full VACUUM.
 """
 import glob
 import json
@@ -42,6 +51,14 @@ THRESHOLD_EVENT_COUNT = 40
 CRON_MAX_AGE_HOURS = 48
 RPC_TIMEOUT_MS = 180000
 
+# Tier A: Event-logging agents whose state is 100% externalized (DuckDB / JSONL / Groceries DB).
+# Nightly reset to 0 prevents cross-day hallucination and eliminates LLM compaction token costs.
+TIER_A_RESET_TARGETS = [
+    ("koch", "agent:koch:telegram:group:-1004326921510:topic:21"),
+    ("hebamme", "agent:hebamme:telegram:group:-1004326921510:topic:22"),
+    ("shopping", "agent:shopping:telegram:group:-1004326921510:topic:115"),
+]
+
 def prewarm_page_cache():
     print("=== Pre-warming SQLite databases into OS page cache ===")
     t0 = time.time()
@@ -128,6 +145,32 @@ def prune_stale_cron_sessions():
 
     print(f"Cron pruning complete: {total_pruned} sessions pruned, {total_tokens_reclaimed} tokens reclaimed.")
 
+def reset_tier_a_sessions():
+    print("=== Tier A: Daily Hard-Reset to 0 (koch, hebamme, shopping) ===")
+    for agent, key in TIER_A_RESET_TARGETS:
+        db_path = f"/home/node/.openclaw/agents/{agent}/agent/openclaw-agent.sqlite"
+        if not os.path.exists(db_path):
+            continue
+        try:
+            con = sqlite3.connect(db_path, timeout=10.0)
+            row = con.execute("SELECT current_session_id FROM session_nodes WHERE session_key=?", (key,)).fetchone()
+            con.close()
+            if not row or not row[0]:
+                print(f"  [Tier A] {agent} ({key}) already at 0 (no active session).")
+                continue
+            print(f"  [Tier A] Resetting {agent} ({key})...")
+            r = subprocess.run(
+                ["openclaw", "sessions", "delete", key, "--agent", agent, "--yes"],
+                capture_output=True, text=True, timeout=60.0
+            )
+            if r.returncode == 0:
+                print(f"    ✓ Reset success: {r.stdout.strip()}")
+            else:
+                print(f"    ✗ Reset error: {r.stderr.strip()}")
+        except Exception as e:
+            print(f"    ✗ Exception resetting {agent}: {e}")
+        time.sleep(1)
+
 def get_session_metrics(agent, key, sid=None):
     db_path = f"/home/node/.openclaw/agents/{agent}/agent/openclaw-agent.sqlite"
     if not os.path.exists(db_path):
@@ -151,7 +194,8 @@ def get_session_metrics(agent, key, sid=None):
         return 0, 0
 
 def compact_active_sessions():
-    print(f"=== Running OpenClaw Multi-Agent Compaction (threshold: {THRESHOLD_TOKENS} tokens / {THRESHOLD_TRANSCRIPT_BYTES//1024}KB, LLM summarization) ===")
+    tier_a_keys = set(t[1] for t in TIER_A_RESET_TARGETS)
+    print(f"=== Tier B: Running Multi-Agent Compaction (threshold: {THRESHOLD_TOKENS} tokens / {THRESHOLD_TRANSCRIPT_BYTES//1024}KB, LLM summarization) ===")
     res = subprocess.run(["openclaw", "sessions", "--all-agents", "--json"], capture_output=True, text=True)
     if res.returncode != 0:
         print(f"Failed to list sessions: {res.stderr}")
@@ -167,6 +211,10 @@ def compact_active_sessions():
         tokens = s.get("totalTokens") or 0
         sid = s.get("sessionId")
 
+        # Skip Tier A agents as they are handled via hard-reset
+        if key in tier_a_keys:
+            continue
+
         # Target main sessions and all telegram sessions (topics and direct)
         is_target = (
             key == "agent:main:main" or 
@@ -204,7 +252,7 @@ def compact_active_sessions():
                         compacted += 1
                     else:
                         print(f"  ✗ Fallback failed: {fb_res.stderr.strip()}")
-                time.sleep(2)
+                time.sleep(5)  # 5s pause to avoid rotational HDD I/O saturation
             else:
                 skipped += 1
 
@@ -228,17 +276,16 @@ def checkpoint_wal_journals():
     print(f"WAL Checkpoint complete: {wal_freed / (1024*1024):.2f} MB merged to disk.")
 
 def vacuum_and_optimize():
-    print("=== Running SQLite VACUUM and OPTIMIZE across all databases ===")
+    print("=== Running SQLite OPTIMIZE across all databases ===")
     dbs = ["/home/node/.openclaw/state/openclaw.sqlite"] + glob.glob("/home/node/.openclaw/agents/*/agent/openclaw-agent.sqlite")
     for db in dbs:
         try:
-            con = sqlite3.connect(db, timeout=60.0)
+            con = sqlite3.connect(db, timeout=30.0)
             con.execute("PRAGMA optimize;")
-            con.execute("VACUUM;")
             con.close()
         except Exception as e:
-            print(f"  ✗ Error vacuuming {db}: {e}")
+            print(f"  ✗ Error optimizing {db}: {e}")
-    print("SQLite VACUUM and optimization complete.")
+    print("SQLite optimization complete.")
 
 def main():
     prewarm_page_cache()
@@ -247,6 +294,7 @@ def main():
     except Exception:
         pass
     prune_stale_cron_sessions()
+    reset_tier_a_sessions()
     compact_active_sessions()
     checkpoint_wal_journals()
     vacuum_and_optimize()
@@ -258,8 +306,18 @@ chmod +x /home/node/.openclaw/scripts/compact_sessions.py
 '
 
 # 2. Register / Update the OpenClaw cron job
-echo "Registering OpenClaw Cron automation '$JOB_NAME' ($CRON_SCHEDULE @ $TIMEZONE)..."
+echo "Checking existing OpenClaw Cron automation '$JOB_NAME'..."
-kubectl exec -n "$NAMESPACE" "$POD_NAME" -c "$CONTAINER_NAME" -- openclaw cron add \
+EXISTING_ID=$(kubectl exec -n "$NAMESPACE" "$POD_NAME" -c "$CONTAINER_NAME" -- openclaw cron list --json 2>/dev/null | python3 -c 'import sys, json; data=json.load(sys.stdin); print(next((j["id"] for j in data.get("jobs", []) if j.get("declarationKey") == "'"$JOB_NAME"'"), ""))' 2>/dev/null || true)
+
+if [ -n "$EXISTING_ID" ]; then
+  echo "Updating existing OpenClaw Cron automation '$EXISTING_ID' ($CRON_SCHEDULE @ $TIMEZONE)..."
+  kubectl exec -n "$NAMESPACE" "$POD_NAME" -c "$CONTAINER_NAME" -- openclaw cron edit "$EXISTING_ID" \
+    --cron "$CRON_SCHEDULE" \
+    --tz "$TIMEZONE" \
+    --command "python3 /home/node/.openclaw/scripts/compact_sessions.py"
+else
+  echo "Registering new OpenClaw Cron automation '$JOB_NAME' ($CRON_SCHEDULE @ $TIMEZONE)..."
+  kubectl exec -n "$NAMESPACE" "$POD_NAME" -c "$CONTAINER_NAME" -- openclaw cron add \
     --name "Nightly Session Compaction" \
     --declaration-key "$JOB_NAME" \
     --description "Nightly multi-agent session compaction and SQLite WAL checkpointing" \
@@ -268,6 +326,9 @@ kubectl exec -n "$NAMESPACE" "$POD_NAME" -c "$CONTAINER_NAME" -- openclaw cron a
     --session "isolated" \
     --no-deliver \
     --command "python3 /home/node/.openclaw/scripts/compact_sessions.py"
+fi
 
-echo "=== Compaction Cron automation successfully registered! ==="
+echo "=== Compaction Cron automation successfully registered/updated! ==="
-kubectl exec -n "$NAMESPACE" "$POD_NAME" -c "$CONTAINER_NAME" -- openclaw cron show "$JOB_NAME" 2>/dev/null || true
+if [ -n "$EXISTING_ID" ]; then
+  kubectl exec -n "$NAMESPACE" "$POD_NAME" -c "$CONTAINER_NAME" -- openclaw cron get "$EXISTING_ID" 2>/dev/null || true
+fi