Skip to content

chernistry/bernstein

v1.10.7 Feature

This release adds 2 notable features for engineering teams evaluating rollout.

Published 23d AI Agents & Assistants
✓ No known CVEs patched
Read the diff → Tool health → What is this tool? →

✓ No known CVEs patched in this version

Topics

agent-framework agent-orchestrator agentic-ai ai-agents ai-coding aider
+14 more
anthropic claude-code cli-tool codex-cli coding-agent deterministic-scheduler hmac-audit llm mcp-server model-context-protocol multi-agent parallel-worktrees python swe-bench

ReleasePort's take

Light signal
editorial:auto 13d

The v1.10.7 release adds the `bernstein export` CLI command for shareable post-run reports and introduces 16 new scenario YAMLs plus three workflow DAGs.

Why it matters: Test the new `bernstein export` command in dev environments to ensure report generation meets sharing requirements; review added scenarios and workflows before production use.

Summary

AI summary

New bernstein export CLI command for shareable run reports and 16 added planning scenarios.

Changes in this release

Feature Medium

`bernstein export` CLI command introduced for shareable post-run reports.

`bernstein export` CLI command introduced for shareable post-run reports.

Source: llm_adapter@2026-05-21

Confidence: high

 —
Feature Medium

16 new scenario YAMLs added to `.bernstein/scenarios/` and `.bernstein/workflows/`.

16 new scenario YAMLs added to `.bernstein/scenarios/` and `.bernstein/workflows/`.

Source: llm_adapter@2026-05-21

Confidence: low

 —
Feature Medium

Three new workflow DAGs: `audit-evidence-pack`, `parallel-review-merge`, `sequential-deprecation-rollout`.

Three new workflow DAGs: `audit-evidence-pack`, `parallel-review-merge`, `sequential-deprecation-rollout`.

Source: llm_adapter@2026-05-21

Confidence: low

 —
Bugfix Medium

README “Why the name?” section updated with Bernstein backstory details.

README “Why the name?” section updated with Bernstein backstory details.

Source: llm_adapter@2026-05-21

Confidence: low

 —
Refactor Medium

Internal CI hygiene fixes applied (no user-facing impact).

Internal CI hygiene fixes applied (no user-facing impact).

Source: llm_adapter@2026-05-21

Confidence: low

 —
Full changelog

v1.10.7

A small operator-visible release. One new CLI command — bernstein export for shareable post-run reports — and a 16-scenario expansion of the planning library.

New: bernstein export — shareable run reports

bernstein export reads a finished run from .sdd/archive/tasks.jsonl, .sdd/runs/{run_id}/, and .sdd/metrics/, then renders either a self-contained HTML page (inline CSS, no external assets) or a Markdown summary. Output is capped at 500 KB so the artefact is paste-friendly into a PR comment, Slack channel, or postmortem doc without surprising anyone with a multi-megabyte attachment.

Flags:

  • --last — most recent run in the workdir.
  • --run-id <id> — pick a specific run.
  • --format html|md — default HTML.
  • --output <path> — write to a file; otherwise stdout.
  • --workdir <path> — alternate .sdd root.

The data-assembly path (run_export.py) is testable in isolation and the rendering path uses no template engine — just stdlib helpers — so the binary surface is unchanged. Closes #764.

Planning library expansion

.bernstein/scenarios/ and .bernstein/workflows/ gain 16 scenario YAMLs and 3 workflow DAGs covering five categories:

  • software (6) — api-breaking-migration, dead-code-removal, dependency-upgrade-sweep, large-codebase-audit, monorepo-extraction, security-fix-sweep, test-coverage-uplift.
  • enterprise (3) — legacy-modernization-program, regulator-audit-evidence-pack, supply-chain-hardening.
  • docs (2) — rfc-drafting, wiki-refresh-from-code.
  • research (2) — market-scan, paper-digest-pipeline.
  • growth (2) — contributor-onboarding, issue-triage-workflow.

Two of them — dependency-upgrade-sweep (18 tasks) and regulator-audit-evidence-pack (22 tasks) — are drilled to task level and immediately runnable; the rest are higher-level templates the operator fills in. New workflow DAGs: audit-evidence-pack, parallel-review-merge, sequential-deprecation-rollout. All validate against the existing ci-pipeline.yaml schema.

Also

  • README "Why the name?" section anchors the Bernstein/Leonard Bernstein backstory; AGENTS.md derivatives synced.
  • Internal CI hygiene fixes (no user-facing impact).

Install

pipx install --upgrade bernstein
# or
pip install --upgrade bernstein

Full changelog: https://github.com/sipyourdrink-ltd/bernstein/compare/v1.10.6...v1.10.7

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 chernistry/bernstein

Get notified when new releases ship.

Sign up free

About chernistry/bernstein

Deterministic multi-agent orchestrator for 18 CLI coding agents (Claude Code, Codex, Cursor, Aider, Gemini CLI, OpenAI Agents SDK, and more). MCP server mode (stdio + HTTP/SSE) exposes the orchestrator to any MCP client. Git worktree isolation per agent, HMAC-chained audit trail, cost-aware model routing via contextual bandit. ~11K monthly PyPI downloads, Apache 2.0.

All releases →

Related context

Beta — feedback welcome: [email protected]