Skip to content

nfemmanuel/iranti

v0.3.13 Feature

This release adds 3 notable features for engineering teams evaluating rollout.

✓ No known CVEs patched
Read the diff → Tool health → What is this tool? →

✓ No known CVEs patched in this version

Summary

AI summary

DB-backed bootstrap restores handshake and attend state across processes, allowing full protocol sequences after restarts.

Full changelog

Fix: Cross-process protocol enforcement for Copilot CLI

GitHub Copilot CLI (and any MCP host that restarts the subprocess per tool call) was getting blocked on iranti_attend and iranti_search after a successful iranti_handshake because each fresh process started with an empty in-memory AgentProtocolTracker.

What changed

  • DB-backed bootstrap on startup: iranti-mcp now reads attendant_state from the database at process start and restores handshake/attend state before handling the first tool call. This allows a full handshake → attend → search sequence to succeed across three independent processes.
  • AgentProtocolTracker.bootstrapState() — new method to restore tracker state from DB values
  • Iranti.loadProtocolStateFromLedger() — reads the attendant_state KnowledgeEntry and calls bootstrapState() within TTL windows (10 min handshake, 3 min attend)
  • Attend phase is now stored in session ledger event metadata for observability

Upgrade

npm install -g [email protected]

or update your MCP config to pick up the new version.

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 nfemmanuel/iranti

Get notified when new releases ship.

Sign up free

About nfemmanuel/iranti

Persistent shared memory for AI coding agents. Stores facts as `entity/key/value` triples with hybrid semantic search, task checkpoints, and conflict resolution — shared across Claude Code, Codex CLI, and GitHub Copilot.

All releases →

Beta — feedback welcome: [email protected]