SpecsRelay for DeepSeek 0.10.0: long chats and easier clarification

by

I just shipped SpecsRelay for DeepSeek 0.10.0, focused on the steps between discussing an idea and handing it to a coding Agent.

SpecsRelay opens DeepSeek inside DSH Desktop and turns your conversation into requirements you can review and send to a local project. Here's what's new today:

Continue clarification in the original conversation. When SpecsRelay finds an unresolved question, you can now copy the questions back into DeepSeek, discuss them there, then recapture the updated conversation and organize it again. You can still answer directly in the panel. Copying never sends a message automatically.

Optional help with long conversations. The organizer plans what to look for—goals, confirmed decisions, constraints, acceptance criteria and open questions—then Jev selects original evidence before the organizer writes the requirements. It all happens within “Organize current conversation,” with no separate compression step. Short conversations use the full text, and planning or screening failures fall back to the full conversation.

A more consistent desktop layout. DeepSeek stays on the left and SpecsRelay on the right, including in narrower windows. This update also fixes titlebar spacing in enhanced mode on macOS and Windows and makes page-startup errors more specific.

Optional continuation routing. Jev can also help choose an auxiliary model when continuing a session. It does not change your Coding Agent's main model.

Both Jev options are off by default and require your own TypeSafe API key when enabled. The regular workflow still uses your existing DSH model. Long-conversation enhancement sends conversation excerpts to TypeSafe; the README explains configuration and data handling.

This release supports DSH Desktop by anywhere-labs only. Support for the other desktop clients has been removed. Update the plugin and restart a compatible DSH Desktop installation.

SpecsRelay remains an independent, MIT-licensed community project.

· ·

Where does your conversation-to-code handoff still break: recovering earlier decisions, clarifying missing requirements, or getting the Agent started with the right context?

1 view

Add a comment

Replies

Be the first to comment