Skip to content

wazionapps/nexo

v7.11.6 Bugfix

This release fixes issues for SREs watching stability and regressions.

Published 1mo MCP Developer Tools
✓ No known CVEs patched
Read the diff → Tool health → What is this tool? →

✓ No known CVEs patched in this version

Topics

ai-memory atkinson-shiffrin autonomous-agent claude-code claude-code-plugin codex
+14 more
cognitive-architecture knowledge-graph local-first mcp mcp-server memory metacognition model-context-protocol natural-forgetting llm semantic-search shared-brain trust-scoring vector-db

Summary

AI summary

Guardian G4 now rejects additional false‑positive path fragments and session drift is downgraded to a warning if heartbeated within the last 5 minutes.

Full changelog

Fixed

  • Guardian G4 now rejects more false-positive path fragments before they become protocol debt, including regex and date-like slash tokens.
  • strict_protocol_write_without_task now downgrades active-session drift to warn when the same session heartbeated in the last 5 minutes.
  • Deep Sleep extraction now validates the live JSON contract and records deterministic json_schema failures instead of accepting structurally degraded payloads.

Verification

  • pytest -q tests/test_hook_guardrails.py tests/test_deep_sleep_extract.py50 passed
  • scripts/verify_release_readiness.py --ci → green
  • scripts/pre-release-verify.sh --release v7.11.62326 passed, 2 skipped, 1 xfailed, 4 xpassed

What's Changed

  • Release v7.11.6 by @wazionapps in https://github.com/wazionapps/nexo/pull/313

Full Changelog: https://github.com/wazionapps/nexo/compare/v7.11.5...v7.11.6

Weekly OSS security release digest.

The CVE patches and breaking changes that affected production tools this week. One email, every Sunday.

No spam, unsubscribe anytime.

Share this release

Track wazionapps/nexo

Get notified when new releases ship.

Sign up free

About wazionapps/nexo

Cognitive memory for AI agents with Atkinson-Shiffrin memory model (STM/LTM/sensory register), semantic RAG, Ebbinghaus decay, trust scoring, and 76+ MCP tools.

All releases →

Beta — feedback welcome: [email protected]