v0.10.7

What's Changed

Agent Reliability Boost

We've turned the Agent's patience up to eleven! The LLM request timeout now has a generous 10‑minute floor, meaning your agents won’t bail on those marathon reasoning sessions. Plus, we’ve cranked the retry count from 3 to a heroic 8 attempts (thanks to #231), so even flaky models get a second (and third…) chance to shine. In short: your Agents are now sturdier, more forgiving, and ready for the long haul.

OpenRouter Web Search & Fetch Power‑Up

Say hello to native web_search and web_fetch support for OpenRouter! With this addition, agents can now tap directly into the web via OpenRouter’s server‑side tools, pulling fresh content and fetching resources without a hitch. It’s like giving your AI a built‑in browser—fast, reliable, and ready to fetch the latest data on demand.

---

Commits

• e7a1565 fix(agent): raise LLM request timeout floor to 10 min by @lvndry
• c0eacf8 fix(agent): bump DEFAULT_MAX_LLM_RETRIES from 3 to 8 (#231) by @lvndry
• 2d4a909 feat(openrouter): native web_search and web_fetch server tool support (#230) by @lvndry

Full diff

v0.10.6...v0.10.7