nexo-brain 7.8.0 → 7.8.1

package/.claude-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "nexo-brain",
-  "version": "7.8.0",
+  "version": "7.8.1",
   "description": "Local cognitive runtime for Claude Code \u2014 persistent memory, overnight learning, doctor diagnostics, personal scripts, recovery-aware jobs, startup preflight, and optional dashboard/power helper.",
   "author": {
     "name": "NEXO Brain",

package/README.md

@@ -18,7 +18,9 @@
 
 [Watch the overview video](https://nexo-brain.com/watch/) · [Watch on YouTube](https://www.youtube.com/watch?v=i2lkGhKyVqI) · [Open the infographic](https://nexo-brain.com/assets/nexo-brain-infographic-v5.png)
 
-Version `7.8.0` is the current packaged-runtime line. Minor release that closes the PostCompact continuity work Francisco requested after v7.7: `src/hooks/post_compact.py` is a real registered hook (part of the canonical 9-hook set, was 8), `pre-compact.sh` resolves the exact NEXO SID from `CLAUDE_SESSION_ID` instead of falling back to "latest active session" (that was actively wrong in multi-conversation Desktop), the sidecar moves from `/tmp` to `$NEXO_HOME/runtime/data/compacting-sid.txt` so two concurrent compactions on two conversations cannot race on `/tmp`, `post-compact.sh` removes its "latest checkpoint" fallback (fail-closed to a diagnostic systemMessage instead of restoring the wrong conversation), and the hook cross-checks the sidecar SID against the env-resolved one so a "SID mismatch" is logged as such. Pre- and post-compact now emit NDJSON events the engine drains on every periodic tick via `_consume_pending_hook_events()`; the queue file is truncated after read so an event never fires twice. A new contract test (`tests/test_v78_compaction_continuity.py`) pins 11 invariants across ten rails including the hook registration, the exact-SID resolution path, fail-closed behaviour, and that `compaction_count` only increments on real restore. Pytest 2086 passing (+16 vs v7.7). No Desktop bump — v0.27.0 continues to ship.
+Version `7.8.1` is the current packaged-runtime line. Patch release that closes the last compaction-continuity gap Francisco flagged after v7.8.0: `pre-compact.sh` Layer 2 emergency auto-diary and Layer 3 `compaction_memory.record_auto_flush` now use the exact `TARGET_SID` resolved from `CLAUDE_SESSION_ID` instead of falling back to `ORDER BY last_update_epoch DESC LIMIT 1` ("latest active session"). In multi-conversation Desktop that fallback routinely wrote the emergency diary against the wrong conversation even though the main restore path was already exact-SID in v7.8.0. `last_diary_ts` is also scoped by `session_id` now. Fail-closed when no `CLAUDE_SESSION_ID` resolves. New behavioural tests drive the real shell script with two sessions in the DB to pin the invariant. Fixed a latent bash-escape bug in `pre-compact.sh` where a double-quoted string inside a Python comment silently closed the `python3 -c "..."` argument early — caught by adding the behavioural tests. Pytest 2092 passing (+2 new behavioural). No Desktop bump.
+
+Previously in `7.8.0`: minor release that closed the PostCompact continuity work Francisco requested after v7.7: `src/hooks/post_compact.py` is a real registered hook (part of the canonical 9-hook set, was 8), `pre-compact.sh` resolves the exact NEXO SID from `CLAUDE_SESSION_ID` instead of falling back to "latest active session" (that was actively wrong in multi-conversation Desktop), the sidecar moves from `/tmp` to `$NEXO_HOME/runtime/data/compacting-sid.txt` so two concurrent compactions on two conversations cannot race on `/tmp`, `post-compact.sh` removes its "latest checkpoint" fallback (fail-closed to a diagnostic systemMessage instead of restoring the wrong conversation), and the hook cross-checks the sidecar SID against the env-resolved one so a "SID mismatch" is logged as such. Pre- and post-compact now emit NDJSON events the engine drains on every periodic tick via `_consume_pending_hook_events()`; the queue file is truncated after read so an event never fires twice. A new contract test (`tests/test_v78_compaction_continuity.py`) pins 11 invariants across ten rails including the hook registration, the exact-SID resolution path, fail-closed behaviour, and that `compaction_count` only increments on real restore. Pytest 2086 passing (+16 vs v7.7). No Desktop bump — v0.27.0 continues to ship.
 
 Previously in `7.7.0`: minor release that closed the six gaps left partial after v7.6.0's constructor-guardian-90 pass 1 (autonomous detector for `multi_step_task_detected`, R16 vocabulary expansion, R_CATALOG extended to plain Edit/Write, new `R_PRIMITIVE_CHOICE` rule, `R11_plugin_load_pre_inventory` hardened, 12 new contract tests). Post-review hotfix on the same release wired `task_open` rearm properly (discarded from `tools_called` + per-instance pin cleared on `task_close`), added live `on_event` triggers in R14 and R16, and called `on_tool_call_before` before `on_tool_call` in `run_with_enforcement` so before_tool rules fire in Brain the same way Desktop fires `onBeforeToolCall`.
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "nexo-brain",
-  "version": "7.8.0",
+  "version": "7.8.1",
   "mcpName": "io.github.wazionapps/nexo",
   "description": "NEXO Brain \u2014 Shared brain for AI agents. Persistent memory, semantic RAG, natural forgetting, metacognitive guard, trust scoring, 150+ MCP tools. Works with Claude Code, Codex, Claude Desktop & any MCP client. 100% local, free.",
   "homepage": "https://nexo-brain.com",

package/src/hooks/pre-compact.sh

@@ -117,10 +117,17 @@ except Exception:
 fi
 
 # ── Layer 2: Emergency auto-diary before compaction ──────────────────
-# Write an actual session_diary entry (not draft) with mechanical summary
-# This is the parachute — if the LLM never wrote a diary, at least this exists
-if [ -f "$NEXO_DB" ]; then
-    python3 -c "
+# Write an actual session_diary entry (not draft) with mechanical summary.
+# This is the parachute — if the LLM never wrote a diary, at least this exists.
+#
+# v7.8.1 hotfix: must target the EXACT session compacting. Pre-v7.8.1 used
+# "latest active session" (ORDER BY last_update_epoch DESC LIMIT 1) which in
+# multi-conversation Desktop routinely wrote the diary onto the wrong conv.
+# Now we read TARGET_SID resolved from CLAUDE_SESSION_ID above. If it is
+# missing or does not exist in sessions, we fail-closed: no emergency diary
+# > wrong emergency diary. Layer 3 auto_flush is wired to the same SID.
+if [ -f "$NEXO_DB" ] && [ -n "$TARGET_SID" ] && [[ "$TARGET_SID" =~ ^nexo-[0-9]+-[0-9]+$ ]]; then
+    NEXO_PRECOMPACT_SID="$TARGET_SID" python3 -c "
 import json, sqlite3, os, sys
 from datetime import datetime
 
@@ -130,15 +137,21 @@ log_file = '$LOG_FILE'
 conn = sqlite3.connect(db_path, timeout=3)
 conn.row_factory = sqlite3.Row
 
-# Get latest active session
+# v7.8.1 — use the EXACT SID resolved by Layer 1 (from CLAUDE_SESSION_ID),
+# not the pre-v7.8 latest-active row which routinely belongs to a
+# different conversation.
+sid = os.environ.get('NEXO_PRECOMPACT_SID', '')
+if not sid:
+    conn.close()
+    sys.exit(0)
 row = conn.execute(
-    'SELECT sid, task FROM sessions ORDER BY last_update_epoch DESC LIMIT 1'
+    'SELECT sid, task FROM sessions WHERE sid = ? LIMIT 1', (sid,)
 ).fetchone()
 if not row:
+    # SID not present — fail-closed, better skip than write against the
+    # wrong session.
     conn.close()
     sys.exit(0)
-
-sid = row['sid']
 task = row['task'] or 'unknown'
 
 # Check if a real diary already exists for this session
@@ -149,9 +162,12 @@ if has_diary:
     conn.close()
     sys.exit(0)  # LLM already wrote one, no need for emergency diary
 
-# Find last diary timestamp to know where to start reading logs
+# v7.8.1 — last_diary_ts must be scoped to THIS session too. Otherwise
+# a recent diary of another conversation would truncate this conv's
+# mechanical summary window.
 last_diary = conn.execute(
-    'SELECT created_at FROM session_diary ORDER BY created_at DESC LIMIT 1'
+    'SELECT created_at FROM session_diary WHERE session_id = ? ORDER BY created_at DESC LIMIT 1',
+    (sid,),
 ).fetchone()
 last_diary_ts = last_diary['created_at'] if last_diary else '1970-01-01T00:00:00Z'