New features
- Model policy control. Set
ARKA_MODEL_POLICYtolocal-first,hosted-first,local-only, orhosted-onlyto reorder LLM fallback chains without editing config. - Launch browser apps by name.
arka open brave,open chrome,open firefox,open safari,open edge,open arc,open vivaldi, andopen operanow open the desktop app instead of the matching.comsite.
Improvements
- Faster
arka --help. The CLI defers loading heavy dependencies (OpenAI SDK, faster-whisper, and others) until the matching subcommand runs, so top-level help returns immediately. - Simple arithmetic in chat. Questions like
what is 12 * 7 + 3are recognized as math and routed to the math path directly. - Configurable web search timeouts. DuckDuckGo lookups honor
DDGS_TIMEOUT(default 20s) andDDGS_RETRIES(default 2) so slow networks no longer stall chat. - Chat survives web failures. If web-context gathering fails, chat prints the error and continues instead of aborting the turn.
- Gemini quota handling. When Gemini returns a rate or quota error, Arka marks all Gemini models exhausted for the run instead of rotating API keys and retrying.
Bug fixes
- Docker status finds the CLI everywhere.
arka docker statusnow locates thedockerbinary at/usr/local/bin/dockerand/usr/bin/dockerwhen it isn’t onPATH, and skips host/container parity checks when the CLI is unavailable inside a container.