sheawinkler/ContextLattice

v3.2.4 Feature

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

Published 2mo AI Agents & Assistants

View tool

✓ No known CVEs patched

Read the diff → Tool health → What is this tool? →

✓ No known CVEs patched in this version

Topics

agent-framework agent-orchestration ai-infra ai-interface context-engineering context-management

+4 more

go long-horizon-agents long-horizon-intelligence rust

Summary

AI summary

Minor fixes and improvements.

Full changelog

ContextLattice v3.2.4

Runtime updates

Task inference default is now TASK_MODEL_PROVIDER=auto.
On Apple Silicon (M-series macOS), auto mode selects ollama/coreml by default.
Non-M-series hosts remain on standard Ollama in auto mode.
Public v3 keeps ANE sidecar disabled by default.

Orchestrator task-runner integration

Added shared inference route utility (scripts/inference_router.py).
Updated task worker and generic runner to use the same route selection path.
Added canary runner wrappers for opencode, goose, and eliza.

Performance/reporting sync

Synced Issue #69 finalization memo:
- docs/perf-candidate-notes/issue-69-finalization-2026-03-22.md
Added benchmark artifact:
- bench/results/perf_shortlist_matrix_20260322T195851Z.json

Verification

pytest route/context tests pass for updated runner wiring.
go test pass in services/gateway-go (with API-key env vars unset for test isolation).

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 sheawinkler/ContextLattice

Get notified when new releases ship.

About sheawinkler/ContextLattice

Private-by-default memory and context layer for agents with Go/Rust runtime, staged retrieval across fused data backends, and long-horizon context continuity.

All releases →