Workflow & Automation

Two-level model circuit breaker with failover: trip a model or a whole provider after repeated request failures and route the next request to a configured fallback.

Model-based permission approval: an approval-request answerer backed by a separate reviewer model.

Engineering-discipline guard: grill the requirements before the first edit, enforce red/green test evidence gates, and audit the delivery with a forked adversary (grill-requirements skill + tool-policy gates).

Browser automation for DeepSeek Harness: Playwright-powered open/click/type/screenshot/eval tools so the agent can drive real web pages.

Independent read-only acceptance layer: spawns a read-only verifier before each top-level turn closes and steers non-pass gaps back into the agent.

Adds specification artifacts, skills, commands, goal-backed implementation, and task-progress context.

Scheduled agents on a cron: run a prompt on a schedule and get the digest where you already are, with overlap/missed-run/timeout safety defaults.

Settings-based scheduled tasks that run on time or during DeepSeek off-peak hours, with one-time and daily schedules backed by durable task state.

Cross-device workspace backup, restore, and ecosystem update via the uagent-sync CLI.

Claude-Code-style lifecycle hooks: configured shell commands run before/after model tool calls with a JSON payload on stdin; a non-zero pre-tool exit blocks the call.