memory-lancedb-pro 1.0.5 → 1.0.7

package/CHANGELOG.md

@@ -1,5 +1,14 @@
 # Changelog
 
+## 1.0.7
+
+- Fix: resolve `agentId` from hook context (`ctx?.agentId`) for `before_agent_start` and `agent_end`, restoring per-agent scope isolation when using multi-agent setups.
+
+## 1.0.6
+
+- Fix: auto-recall injection now correctly skips cron prompts wrapped as `[cron:...] run ...` (reduces token usage for cron jobs).
+- Fix: JSONL distill extractor filters more transcript/system noise (BOOT.md, HEARTBEAT, CLAUDE_CODE_DONE, queued blocks) to avoid polluting distillation batches.
+
 ## 1.0.5
 
 - Add: optional JSONL session distillation workflow (incremental cursor + batch format) via `scripts/jsonl_distill.py`.

package/index.ts

@@ -365,14 +365,14 @@ const memoryLanceDBProPlugin = {
 
     // Auto-recall: inject relevant memories before agent starts
     if (config.autoRecall !== false) {
-      api.on("before_agent_start", async (event) => {
+      api.on("before_agent_start", async (event, ctx) => {
         if (!event.prompt || shouldSkipRetrieval(event.prompt)) {
           return;
         }
 
         try {
           // Determine agent ID and accessible scopes
-          const agentId = event.agentId || "main";
+          const agentId = ctx?.agentId || "main";
           const accessibleScopes = scopeManager.getAccessibleScopes(agentId);
 
           const results = await retriever.retrieve({
@@ -409,14 +409,14 @@ const memoryLanceDBProPlugin = {
 
     // Auto-capture: analyze and store important information after agent ends
     if (config.autoCapture !== false) {
-      api.on("agent_end", async (event) => {
+      api.on("agent_end", async (event, ctx) => {
         if (!event.success || !event.messages || event.messages.length === 0) {
           return;
         }
 
         try {
           // Determine agent ID and default scope
-          const agentId = event.agentId || "main";
+          const agentId = ctx?.agentId || "main";
           const defaultScope = scopeManager.getDefaultScope(agentId);
 
           // Extract text content from messages

package/openclaw.plugin.json

@@ -2,7 +2,7 @@
   "id": "memory-lancedb-pro",
   "name": "Memory (LanceDB Pro)",
   "description": "Enhanced LanceDB-backed long-term memory with hybrid retrieval, multi-scope isolation, and management CLI",
-  "version": "1.0.5",
+  "version": "1.0.7",
   "kind": "memory",
   "configSchema": {
     "type": "object",

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "memory-lancedb-pro",
-  "version": "1.0.5",
+  "version": "1.0.7",
   "description": "OpenClaw enhanced LanceDB memory plugin with hybrid retrieval (Vector + BM25), cross-encoder rerank, multi-scope isolation, and management CLI",
   "type": "module",
   "main": "index.ts",
@@ -18,7 +18,7 @@
   ],
   "repository": {
     "type": "git",
-    "url": "https://github.com/win4r/memory-lancedb-pro"
+    "url": "git+https://github.com/win4r/memory-lancedb-pro.git"
   },
   "author": "win4r",
   "license": "MIT",

package/scripts/jsonl_distill.py

@@ -104,6 +104,11 @@ def _clean_text(s: str) -> str:
     if "<relevant-memories>" in s:
         s = re.sub(r"<relevant-memories>[\s\S]*?</relevant-memories>", "", s)
 
+    # Strip OpenClaw transcript headers that add noise but not meaning.
+    # Keep the actual user content that follows.
+    s = re.sub(r"^Conversation info \(untrusted metadata\):\s*\n+", "", s, flags=re.IGNORECASE)
+    s = re.sub(r"^Replied message \(untrusted, for context\):\s*\n+", "", s, flags=re.IGNORECASE)
+
     # Drop embedded JSON blocks (often metadata) to reduce token waste.
     s = re.sub(r"```json[\s\S]*?```", "", s)
 
@@ -118,12 +123,27 @@ def _is_noise(s: str) -> bool:
     for p in NOISE_PREFIXES:
         if s.startswith(p):
             return True
+
+    lower = s.lower()
+
+    # Drop transcript/system boilerplate that should never become memories.
+    if "[queued messages while agent was busy]" in lower:
+        return True
+    if "you are running a boot check" in lower or "boot.md — gateway startup health check" in lower:
+        return True
+    if "read heartbeat.md" in lower:
+        return True
+    if "[claude_code_done]" in lower or "claude_code_done" in lower:
+        return True
+
     # Skip overly long blocks (logs / dumps). The distiller can still capture the essence later.
     if len(s) > 2000:
         return True
+
     # Skip pure code fences (usually tool output).
     if s.strip().startswith("```") and s.strip().endswith("```"):
         return True
+
     return False
 
 

package/src/adaptive-retrieval.ts

@@ -32,12 +32,38 @@ const FORCE_RETRIEVE_PATTERNS = [
   /(你记得|之前|上次|以前|还记得|提到过|说过)/i,
 ];
 
+/**
+ * Normalize the raw prompt before applying skip/force rules.
+ *
+ * OpenClaw may wrap cron prompts like:
+ *   "[cron:<jobId> <jobName>] run ..."
+ *
+ * We strip such prefixes so command-style prompts are properly detected and we
+ * can skip auto-recall injection (saves tokens).
+ */
+function normalizeQuery(query: string): string {
+  let s = query.trim();
+
+  // Strip OpenClaw cron wrapper prefix.
+  s = s.replace(/^\[cron:[^\]]+\]\s*/i, "");
+
+  // Strip OpenClaw injected metadata header used in some transcripts.
+  if (/^Conversation info \(untrusted metadata\):/i.test(s)) {
+    s = s.replace(/^Conversation info \(untrusted metadata\):\s*/i, "");
+    // If there is a blank-line separator, keep only the part after it.
+    const parts = s.split(/\n\s*\n/, 2);
+    if (parts.length === 2) s = parts[1];
+  }
+
+  return s.trim();
+}
+
 /**
  * Determine if a query should skip memory retrieval.
  * Returns true if retrieval should be skipped.
  */
 export function shouldSkipRetrieval(query: string): boolean {
-  const trimmed = query.trim();
+  const trimmed = normalizeQuery(query);
 
   // Force retrieve if query has memory-related intent (checked FIRST,
   // before length check, so short CJK queries like "你记得吗" aren't skipped)