Skip to content

nfemmanuel/iranti

v0.4.1 Bugfix

This release fixes issues for SREs watching stability and regressions.

Published 1mo AI Agents & Assistants
✓ No known CVEs patched
Read the diff → Tool health → What is this tool? →

✓ No known CVEs patched in this version

Summary

AI summary

Fixed post-response extraction returning prose instead of JSON, ensuring correct parsing.

Full changelog

Fixes

Post-response attend extractor fixed — The LLM inside the post-response extraction pipeline was returning prose instead of a JSON array, causing JSON.parse() to throw on every turn. Both extraction prompts in AttendantInstance.ts now open with an explicit JSON-only instruction, and a regex fallback strips any preamble before parsing. Bidirectional attend now captures response content as expected.

Changes

  • src/attendant/AttendantInstance.ts — tighten extractor prompts and add JSON.parse fallback at both tool-result and response-content extraction sites
View diff on GitHub

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

Share on X Share on Bluesky

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 →

Related context

Beta — feedback welcome: [email protected]