Skip to content

Llmff

v0.1.6 Feature

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

Published 8d LLM Frameworks
✓ No known CVEs patched
Read the diff → Tool health → What is this tool? →

✓ No known CVEs patched in this version

Summary

AI summary

Supervised batch execution, interrupted run handling, and provider readiness documentation are hardened.

Full changelog

llmff v0.1.6

Functionality hardening release. This release builds on the agent harness
contract by making supervised batch execution, interrupted runs, provider
readiness, plugin review fixtures, and real-world workflow examples more
explicit and testable.

Supported Install

cargo install --git https://github.com/syndicalt/llmff --tag v0.1.6 llmff

Included Since v0.1.5

  • llmff run --run-dir <dir> now supports explicit batch input and output
    paths, while still owning run-scoped supervisor artifacts.
  • Batch runs emit aggregate result.json data, per-item batch reports, trace
    records, and checkpoint progress suitable for external supervisors.
  • Interrupted --run-dir executions write a structured result with failure kind
    interrupted, exit code 130, and a resume-oriented retry recommendation.
  • Manifest fingerprints are normalized across inspect reports, run results, and
    checkpoints so supervisors can compare public hashes consistently.
  • Schema fixtures now cover run-result success, stage-failure, and interrupted
    outcomes.
  • The compatibility matrix documents core contract support across recent
    releases for manifest, trace, event, result, plugin, and CLI JSON surfaces.
  • Real-world examples now cover CI jobs, queue workers, scheduled jobs, and
    failure triage using the current bounded runner model.
  • Provider readiness docs now include support tiers, live smoke history,
    OpenAI-compatible guidance, Ollama guidance, and an Anthropic-compatible
    example manifest.
  • Plugin ecosystem docs now include promotion policy, registry trust metadata,
    and reviewed protocol-v1 fixture records.
  • The release preflight now runs schema, manifest reproducibility, plugin,
    provider, ecosystem readiness, agent adoption, OpenTelemetry bridge, and
    real-world workflow gates.
  • The Python subprocess supervisor, batch supervisor, Node.js streaming supervisor,
    agent runner adoption guide, OpenTelemetry bridge, and ecosystem readiness
    gates remain part of the release contract.

Packaged Artifacts

Release-tag CI is expected to publish:

  • Linux x86_64 .tar.gz archive, .deb package, and Arch PKGBUILD plus
    llmff-0.1.6-arch.SRCINFO metadata.
  • macOS Apple Silicon and Intel .tar.gz archives and unsigned .pkg
    installers.
  • Windows x86_64 unsigned .zip archive and unsigned MSI installer.
  • Adjacent SHA-256 checksums and llmff-0.1.6-release-trust.json.

Manual workflow dispatch keeps generated files as Actions artifacts instead of
GitHub Release assets.

Known Limitations

  • This is a pipeline runner, not a native inference kernel, model converter,
    serving platform, or full agent framework.
  • Windows and macOS native artifacts are unsigned in this release.
  • Package-manager distribution through Homebrew, winget, Scoop, apt
    repositories, or an official AUR package remains parked until maintainers
    decide those channels are support-ready.
  • Authenticode signing, Apple Developer ID signing, and notarization remain
    deferred paid distribution tracks.
  • Live provider smoke jobs remain opt-in and require maintainers to configure
    secrets and runner expectations explicitly.
  • --run-dir owns trace, events, and checkpoint paths. Batch mode can use
    --run-dir with explicit --batch-input and --batch-output-dir paths.

Verification

Release preflight and release verification should pass before tagging:

scripts/release-preflight.sh v0.1.6
scripts/smoke-install.sh --git https://github.com/syndicalt/llmff --tag v0.1.6

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 Llmff

Get notified when new releases ship.

Sign up free

About Llmff

All releases →

Beta — feedback welcome: [email protected]