v1.8.1

v1.8.1

Follow-up bugfix on v1.8.0.

• Replaced 42 float == comparisons in the test suite with pytest.approx() so CI doesn't flake on rounding (Sonar S1244).
• Restored the _render_prompt return-type annotation so callers importing the pre-1.8.0 signature keep working.

Full changelog: v1.8.0...v1.8.1

v1.8.0

v1.8.0

Eight feature drops focused on memory, observability, and safety.

Features

• Prompt caching for system prompts and role templates. Repeated role-prompt runs now read from the Anthropic prompt cache, cutting input-token cost on warm paths.
• Structured memory layer. Episodic (per-session event trace) and semantic (long-lived facts) stores, queryable from any adapter.
• Shared memory with actor-aware tagging. Cross-agent writes are tagged with the writing agent so reads can filter/scope without manual bookkeeping.
• Pluggable guardrail pipeline. Policy checks run as ordered pluggy hooks, so custom guardrails drop in without forking the orchestrator.
• Agent-specific operational metrics. Per-adapter dashboards for latency, error rate, and tool-use distribution.
• Compound error rate tracking. Separates "agent errored" from "tool errored within agent" so retries target the right layer.
• Structured SSE event types. TUI/web stream consumers get typed events instead of a JSON grab-bag.
• OpenTelemetry semantic conventions for agent spans. Spans now match the OTel GenAI conventions — plug into existing APM without custom parsing.
• Claude Code Routines integration for scripted agent sessions.

Fixes

• Strengthened path-traversal mitigation in the changelog command (Sonar S2083, BLOCKER).
• Resolved 40+ SonarCloud issues across the codebase.
• .sdd/ state directory is no longer tracked in git.
• Dropped unused imports flagged by ruff.

Dependencies

• Bumped python-multipart in the uv group.

Full changelog: v1.7.4...v1.8.0

v1.7.4

v1.7.4

No user-visible changes.
Full changelog: v1.7.3...v1.7.4

v1.7.3

v1.7.3

New features

• complete Cloudflare integration platform (cf-001 through cf-012)

Bug fixes

• remove unreachable code in MCP remote transport (vulture)
• resolve SonarCloud quality gate failures in CF integration
• split ambiguous regex to resolve S5850/S6395 conflict

Documentation

• update index.md — use in-action.gif, fix adapter count
• add Cloudflare integration documentation and update existing docs

Chores

• deps: bump agents

Full changelog: v1.7.2...v1.7.3

v1.7.2

v1.7.2

New features

• improve community spotlight generator script
• add spotlight auto-generator script (cherry-picked from #780)

Bug fixes

• resolve SonarCloud quality gate bugs in new code
• resolve 400+ SonarCloud issues across entire codebase

Documentation

• remove retired VS Marketplace and empty codecov badges
• add #783 to Alex Smith's contributor entry
• fill in April 2026 Community Spotlight with real contributor data
• create community spotlight template and update CONTRIBUTING.md

Style

• auto-format 43 files missed by refactoring agents
• fix import ordering in migration gate test

Full changelog: v1.7.1...v1.7.2

v1.7.1

v1.7.1

CI / Infrastructure

• fix npm publish when version already matches tag

Chores

• deps-dev: bump follow-redirects

Full changelog: v1.7.0...v1.7.1

v1.7.0

v1.7.0

New features

• add bernstein cost CLI with cache tracking and peak-hour scheduling
• add API quota tracking with alerts and agent image optimization
• add 'Built with Bernstein' badge to README

Bug fixes

• ci: eliminate tick guard race condition with event-based sync
• ci: increase tick guard sleep for slow macOS CI VMs
• cleanup workflow now deletes orphaned runs from deleted workflows

Documentation

• update README comparison table date and adapter count
• update TROUBLESHOOTING, LIFECYCLE, MODEL_POLICY, and operational docs
• update ARCHITECTURE, DESIGN, GETTING_STARTED, CONFIG to match current code
• update ADAPTER_GUIDE, FEATURE_MATRIX, compatibility, GLOSSARY with current features
• update README and root docs to reflect current architecture

CI / Infrastructure

• disable cancel-in-progress to let CI complete
• make SonarCloud non-blocking (continue-on-error)
• fix empty schedule blocks causing unnamed workflows in sidebar
• workflow audit cleanup
• add manual workflow to bulk-delete failed/cancelled/skipped action runs
• remove redundant tests from Publish workflow

Style

• ruff format 3 new cost/quota files

Chores

• v1.7.0 - workflow cleanup + code scanning fixes

Full changelog: v1.6.11...v1.7.0

v1.6.11

v1.6.11

SonarCloud quality gate: PASS

All conditions met:

• Security Rating: A (0 vulnerabilities, 0 unreviewed hotspots)
• Reliability Rating: A (0 bugs on new code)
• Maintainability Rating: A
• Duplication: 1.8% (under 3% threshold)

Code quality

• ~300 cognitive complexity refactors across 90+ files
• 14 regex simplifications, 60+ float equality fixes
• HTML accessibility, JS catch clauses, CSS contrast improvements
• 9 stale TODOs resolved

Distribution

All channels: PyPI, npm (bernstein-orchestrator), Docker (ghcr.io), Homebrew, VS Code, COPR.
Conda-Forge PR pending: conda-forge/staged-recipes#32954

v1.6.10

v1.6.10

Windows support

Full Windows compatibility across the entire codebase, contributed by @oldschoola:

• Agent spawn: Windows environment variable passthrough (SYSTEMROOT, WINDIR, COMSPEC, etc.)
• Unicode safety: encoding='utf-8', errors='replace' on 90+ subprocess calls
• Terminal handling: msvcrt keypress detection for plan display on Windows
• Process management: PowerShell/kernel32 fallbacks for stop command and process detection
• Worktree cleanup: Windows file-lock retry logic for git worktree removal

New features

• --task/-t flag: Filter backlog tasks by pattern (bernstein run --task gh-62)
• --auto-pr flag: Automatically create a GitHub PR when all tasks complete
• Codex config.toml: Auto-detect model configuration from ~/.codex/config.toml
• Prompt optimizer: SPRT-based A/B testing for prompt versions with automatic promotion

Code quality

• Resolved 800+ SonarCloud issues (1,525 -> ~700) across 11 parallel agents
• 85+ cognitive complexity refactors, 163 duplicate literals extracted, 140 bug fixes
• All security hotspots and vulnerabilities resolved
• Full CI green: 928 tests passing on Linux, macOS, Windows

External contributions

8 PRs by @oldschoola covering Windows support, codex config, task filtering, auto-PR, and prompt optimization.

v1.6.9

v1.6.9

The largest internal restructuring in Bernstein's history - a full module decomposition of the monolithic core/ directory into focused subpackages, plus 100+ CI fixes to make all 927 tests pass.

Module decomposition

The 4,000+ line god-modules have been broken into focused, maintainable subpackages:

• orchestrator.py (4,198 lines) -> 7 sub-modules in core/orchestration/
• spawner.py (2,914 lines) -> 4 sub-modules in core/agents/
• task_store.py (1,853 lines) -> deduplicated into task_store_core.py
• seed.py (1,795 lines) -> 3 sub-modules in core/config/
• gate_runner.py (1,290 lines) -> 3 sub-modules in core/quality/

207+ modules moved into 15 subpackages: agents/, config/, cost/, git/, knowledge/, observability/, orchestration/, persistence/, planning/, plugins_core/, protocols/, quality/, routing/, security/, tasks/, tokens/.

All backward-compatible - existing imports through shim modules continue to work.

Code quality

• Resolved all SonarCloud BLOCKER vulnerabilities and security hotspots (0 remaining)
• Hardened 25+ regex patterns against ReDoS
• Reduced code duplication from 9.6% to under 3% on new code
• 927 tests passing across Python 3.12, 3.13 on Linux, macOS, Windows

Security

• Added Zip Slip path traversal validation for archive extraction
• Seeded RNG for non-cryptographic test data generation
• Annotated localhost URLs and intentional signal handling

External contributions

• PR #724 by @vbhavh - cost-per-line efficiency metric
• PR #726 by @oldschoola - Windows compatibility for terminal handling

Bug fixes

• Fixed circular imports in server subpackage
• Fixed midnight-boundary timezone flake in quality metrics test
• Updated 120+ test mock patch targets for decomposed modules
• Fixed cancel-in-progress CI setting to allow test runs to complete