Calyntro 1.16 ships four improvements focused on the AI Briefing feature and navigation clarity. The headline: AI Briefing can now be deployed on shared instances with a monthly request cap, and works with OpenAI in addition to Anthropic and local models.

The sidebar now groups related views under labelled sections — Code Analysis (Risk Matrix, Change Coupling, Team Architecture) and Reporting (Review Briefing, AI Briefing). This replaces a flat list where these views had no visible context. All routes and functionality are unchanged.

AI Briefing — consistent layout and new name

The AI Briefing view has been aligned with the Review Briefing layout: a Parameters card at the top, the generate button outside the card, and an info hint below. The feature was previously called “AI Brief” and is now called AI Briefing across the interface and navigation.

Monthly request cap for shared instances

You can now set a monthly request limit for AI Briefing per instance:

ai_brief:
  max_requests_per_month: 50   # 0 = unlimited

When the limit is reached, the interface shows a clear message and the counter resets automatically on the first of the following month. This is intended for demo and shared deployments where open-ended LLM usage would be impractical.

OpenAI as an alternative provider

In addition to Anthropic and Ollama, AI Briefing now works with OpenAI models. Switch provider in config with no code changes required:

ai_brief:
  provider: openai
  model: gpt-4o
  api_key: ${AI_BRIEF_API_KEY}

Based on our testing, gpt-4o produces meaningfully better risk synthesis than gpt-4o-mini for this use case — it groups related signals and identifies cross-module patterns rather than treating each finding in isolation.

Update

Pull the latest image and restart your stack:

./manage.sh pull-latest
./manage.sh up

No database migrations or configuration changes required unless you want to use the new max_requests_per_month or provider options.