SpecsRelay 1.0.0 update: better long-chat handoffs and model advice

Hi makers! Today's update (September 21, 2026): I've prepared the SpecsRelay 1.0.0 build, focused on the gap between discussing an idea with AI and giving a coding agent a clear task.

What's new:

• Long-conversation assistance. Optional TypeSafe Jev support selects relevant older assistant replies before your chosen model organizes the requirements. All user messages and the newest turns stay intact. If Jev is unavailable, SpecsRelay uses the full conversation. When input is reduced, you see an estimated token reduction.

• Model and reasoning advice. After the requirements are ready, an optional advisor suggests a model capability tier and reasoning effort. Supported agent families can also receive a concrete model suggestion. You keep control of the agent and model selection.

• A clearer step-by-step flow. Finish organizing and clarifying the requirements, choose a local coding agent, then review the exact handoff. Later steps appear when you're ready for them.

• Keep clarification answers connected to the original chat. Copy your confirmed answers back as a record, with a reminder to recapture the conversation if you continue discussing the task.

The core workflow runs in the browser extension with your own organizer API; the local Companion is optional. The two Jev features are independently optional and require your own TypeSafe key. You still review and send the task yourself in the coding agent.

This post covers the 1.0.0 build prepared today; availability depends on the version shown in the Chrome Web Store listing:

https://chromewebstore.google.com/detail/djgfjiijnimjacnfedacpbdpmmfjcepm

Where does your AI-chat-to-coding-agent handoff lose the most context today?