This release fixes issues for SREs watching stability and regressions.
✓ No known CVEs patched in this version
Summary
AI summaryFixed compliance scorer false positives by ignoring task‑irrelevant injected facts.
Full changelog
v0.3.22
Fix: Compliance scorer false positive for task-irrelevant injected facts
When a session spans multiple task domains on the same entity (e.g., release work followed by marketing copy), the Attendant would surface entity-relevant but task-irrelevant facts (like CI status during a marketing turn). The compliance scorer then penalized the agent for not using those facts, producing false-positive compliance violations.
What changed:
- Added
task_irrelevantevidence kind to the memory attribution system - At injection time, the Attendant now captures
inferredTaskTypefrom the session brief - At scoring time,
injectedFactsAreTaskRelevant()checks token overlap between the task context and injected fact keys/summaries - Facts identified as task-irrelevant count as "used" so the compliance counter does not increment
- The compliance reason is set to
injected_facts_not_relevant_to_current_taskfor observability
Testing:
- New unit test suite
test:compliance-task-relevancewith 10 cases covering key-based relevance, summary-based relevance, edge cases, and mixed scenarios - Updated protocol enforcement tests (route + MCP) to use task-relevant fact data
- Added to
test:hardening-fastCI chain
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
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.
Related context
Related tools
Beta — feedback welcome: [email protected]