Skip to content

wazionapps/nexo

v6.0.4 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

Fixed terminal launcher and dashboard actions to honor preferences.default_resonance.

Full changelog

NEXO Brain v6.0.4

Interactive terminal launchers now honour preferences.default_resonance.

Fixed

  • nexo chat ignored preferences.default_resonance. build_interactive_client_command picked --model / --effort straight from client_runtime_profiles in config/schedule.json, so users who switched their Resonance in NEXO Desktop Preferences (Alto → writes calibration.json) kept getting the stale tier cached in the legacy profile (usually max). Headless runs (run_automation_prompt) and NEXO Desktop new-sessions already honoured the preference correctly; only the terminal launcher was stuck.
  • Dashboard "Open followup in Terminal" had the same bug. build_followup_terminal_shell_command also pulled from client_runtime_profiles, so the Terminal window the dashboard spawned ran at the stale tier instead of the user current preference.

Changed

  • src/agent_runner.py — new _resolve_interactive_model_and_effort(caller, backend, ...) helper consults resonance_map.resolve_model_and_effort first (honouring user_default / explicit tier) and falls back to client_runtime_profiles only when the resonance contract is missing. Both builders now use it. build_interactive_client_command accepts a caller= kwarg (default nexo_chat) and tier= override, which run_automation_interactive propagates.
  • src/resonance_map.py — registers nexo_followup_terminal in USER_FACING_CALLERS with the user-default sentinel so the dashboard "Open in Terminal" action resolves against the user preference.

Tests

  • 8 existing pytest cases updated across tests/test_agent_runner.py, tests/test_cli_scripts.py, tests/test_resonance_map.py. Full suite stays green.

Upgrade

  • nexo update picks up the new agent_runner.py. No config migration needed.

Full changelog: https://nexo-brain.com/changelog/#v604

What's Changed

  • fix: v6.0.4 — interactive launchers honour default_resonance by @wazionapps in https://github.com/wazionapps/nexo/pull/207

Full Changelog: https://github.com/wazionapps/nexo/compare/v6.0.3...v6.0.4

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]