This release includes 1 breaking change for platform teams planning a safe upgrade.
✓ No known CVEs patched in this version
Topics
+10 more
Affected surfaces
Summary
AI summaryUpdates Bug Fixes, chore, and Performance Improvements across a mixed release.
Full changelog
4.0.0 (2026-01-04)
Bug Fixes
- adversarial tester condition and README accuracy (c12109b)
- ci: use correct agent state in status-footer test (c6f54a8)
- cli: ensure PROCESS_SPAWNED sets EXECUTING_TASK state (4c3cc9c)
- ledger: prevent write-after-close race condition (6b64fcf)
- release: allow semantic-release to query remote tags (0be475b)
- release: explicitly fetch tags for semantic-release (cecf735)
- tests: ensure first-run tests are isolated from module cache (e55dbe7)
- tests: move env var and module setup to before() hook (cf787ff)
- tests: use validateConfig for modelRules catch-all validation (4092d78)
chore
- bump version to 4.0.0 (95844e8)
Features
- context: enforce maximum informativeness, minimum verbosity (f99a7b7)
- prompts: add universal language/task support with LLM antipattern detection (906102b)
Performance Improvements
- ci: reduce matrix from 6 jobs to 1 (save ~90% minutes) (cad652d)
- validators: remove relevance/notes fields to save tokens (b775e5a)
BREAKING CHANGES
- CREW_* env vars renamed to ZEROSHOT_*
🤖 Generated with Claude Code
Co-Authored-By: Claude Opus 4.5 [email protected]
- prompts: Validator prompts no longer include language-specific examples
Breaking Changes
- CREW_* environment variables renamed to ZEROSHOT_*
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 zeroshot
Your autonomous engineering team in a CLI. The agent loop produces senior-level code that you can actually trust in prod because of non-negotiable feedback from independent reviewers. Supports Claude Code, OpenAI Codex, OpenCode, and Gemini CLI with trivial setup.
Related context
Related tools
Beta — feedback welcome: [email protected]