github vercel/eve eve@0.26.1

latest releases: eve@0.27.0, eve@0.26.2
23 hours ago

Patch Changes

  • 1f04ff7: The dev TUI renders Markdown through a real GFM parser (width-fitted tables, code blocks, task lists, links), presents every builtin tool with semantic activity copy (Fetch <url>, Run <command>, Search <query> — including web_search across provider input shapes, todo, ask_question, agent, and connection_search), and shows rejected tool approvals as denied instead of successful. Tool activity now accumulates in place: an in-flight batch renders as one counted header with its newest calls listed first behind a rail and a … (N more) elision, then collapses to a single past-tense line (▪ Fetched 30 URLs) once every call settles — failures keep their itemized per-call error rail — and each write_file keeps its own block rendering a real line diff (+/- rows with context, computed from content the session has already seen — prior writes and full-file reads; new files show all additions). ask_question prompts open as a numbered overlay panel above the input (number keys select directly, the "Type your own answer" row focuses its inline editor on reach, Esc dismisses to plain text input), committing as ? question ⎿ answer in the transcript. The todo tool no longer emits transcript blocks; it drives a pinned panel above the input showing per-task state, which commits as a completed block once every task settles. An empty prompt now shows a quiet mark with a rotating placeholder of things to try, switching to the active once typing starts. Reasoning defaults to a fixed one-line thinking indicator that updates in place (persisting as ○ Thought for 12s only for long thoughts; --reasoning full restores the streaming trace), the prompt stays anchored during a turn with Enter inert (the draft carries into the next prompt), and completed turns close with a └ Done in <duration> stats coda (per-turn token flow, context fill) when the turn was long or expensive. Subagent calls render as individual ※ subagent(<name>) #N sections in the tool column whose child rows window to the three most recently active (failures stay itemized while settled work condenses to one counted row) and close on a corner that reports Done once the call's final message arrives; captured server output renders as one open-railed ○ stderr / ○ stdout stream section per source (streams are continuous — no closing corner, and interleaved activity never fragments them): the section sits at its newest write's position — everything that happened after the last error displays after it — and shows only that newest write, with earlier ones behind an … (N more) count (the stored-diagnostics pointer carries the history); the status bar names the model's actual routing and credential (via ai-gateway(oidc:<project>), via ai-gateway(api-key), or via <provider>⌝ for a directly-authored endpoint); an empty prompt no longer submits; and a mid-conversation session replacement marks the context cut with a ┌── Session restarted, clear context. boundary line.

Don't miss a new eve release

NewReleases is sending notifications on new releases.