Skip to content

This release includes 2 security fixes for security teams reviewing exposed deployments.

✓ No known CVEs patched
Read the diff → Tool health → What is this tool? →
This release patches 2 known CVEs

Topics

fastapi kubernetes langgraph llm mlops multi-agent

Affected surfaces

deps auth rbac

Summary

AI summary

Updates Highlights, HR/legal/finance, and Syft across a mixed release.

Full changelog

Highlights

  • LLM_PROVIDER=mock fully works end-to-end. BaseAgent no longer crashes calling bind_tools() on the mock chat model, and the mock's canned LLM responses now match the real pipeline's call sequence — a fresh clone + uv sync + LLM_PROVIDER=mock gives a coherent POST /run response with zero cost and no API key. cp .env.example .env also no longer crashes on the empty PACK_DEFAULT_BUDGET_USD default.
  • Current-generation LLM model defaults across every provider: Anthropic claude-sonnet-5, OpenAI gpt-5.5, Google gemini-3.5-flash, Bedrock anthropic.claude-sonnet-5 (config, .env.example, and the core/cost.py pricing table).
  • api/main.py split into modulesapi/app.py, lifespan.py, middleware.py, dependencies.py, router_factory.py, api/endpoints/* — instead of one monolithic file.
  • 13 domain packs, namespaced by business domain (research/, productivity/, hr/, finance/, legal/), each with typed request/response schemas and auto-generated API routes. Regulated verticals (HR/legal/finance) ship compliance guardrails and are gated behind REGULATED_PACKS_ENABLED=false (HTTP 403 until you opt in after completing the pack's COMPLIANCE.md).
  • Security hardening: Security Scanning workflow green on main (gitleaks allowlist for confirmed false positives, patched starlette/langsmith CVEs), plus the existing rate limiting, input validation, and prompt-injection guards.
  • Supply chain: GHCR images signed with Cosign and published with an SBOM (Syft) on every main build.
  • README rewritten for public launch: an honest "Why this instead of…" section (vs. LangGraph Platform, vs. generic agent-service-toolkit templates), a bulletproof quickstart (mock-provider callout, uv install link, cost estimate, mock-search note), and credibility signals (758+ tests, ~87% coverage, scaling guidance, PR template, SECURITY.md).

Upgrading

No breaking config changes since 0.5.0 for existing deployments. If you pin ANTHROPIC_MODEL / OPENAI_MODEL / GOOGLE_MODEL / BEDROCK_MODEL explicitly in your .env, your override is unaffected — only the defaults changed.

See CHANGELOG.md for the full list of changes.

Security Fixes

  • Patched `starlette` and `langsmith` CVEs; Security Scanning workflow now green on `main`
  • Added gitleaks allowlist for confirmed false positives

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 Production-grade LangGraph template

Get notified when new releases ship.

Sign up free

About Production-grade LangGraph template

All releases →

Related context

Beta — feedback welcome: [email protected]