peiyuwang54/deepseek-harness-cli--packages-client-ui-message-feedback ↗★ 62

@deepseek-ai/dsh-client-ui-message-feedback

为助手消息操作条添加点赞、点踩及可选备注反馈控件。 适合需要逐条评价助手回复的用户,反馈经宿主远程接口提交。

包名
@deepseek-ai/dsh-client-ui-message-feedback
兼容性
待验证
Harness 依赖范围
workspace:^
Cordis 依赖范围
workspace:^
版本
0.1.0-rc.14
许可证
MIT
最近更新
2026年9月13日

同名包的其他仓库

安装

此插件尚未提供可验证的 bundle,或兼容性检查未通过。请先阅读仓库说明。 阅读完整 README ↗

@deepseek-ai/dsh-client-ui-message-feedback

English | 中文

Per-message feedback plugin, browser half: a Like/Dislike pair plus an optional note, contributed as the feedback entry (order 10) of the conversation.chat.assistant-actions strip. The strip is declared by ui-conversation and rendered inside the finalized assistant message's IconActions row, between copy and branch, so the controls inherit that row's chrome and hover behavior. The note editor itself does not sit in that row: it is a role="dialog" popover portaled to document.body and anchored under its trigger, so the row keeps its single line whether the editor is open or closed and the panel is not clipped by the conversation column. A rating or list-load failure shows inline in the row; a note-save failure shows inside the popover, which stays open so the draft can be corrected. Only finalized messages reach the slot — an interruption-frozen partial carries no messageId and therefore no feedback controls. The strip renders once per turn, on the closing assistant message that owns the turn's IconActions row: earlier steps of a multi-step turn produce tool rows rather than a rateable body, so they present no controls even though the Host would accept them as targets.

One MessageFeedbackController per Session backs every message control in that Session, so a single messageFeedback.list read seeds the whole transcript. The read is deferred to the first hover or focus rather than fired on mount, because the controls mount once per settled message in the visible history.

Mutations go through ctx.remote.messageFeedback; the Host owns per-item compare-and-set. Every put and delete carries the version this controller last observed, and a version-conflict reply carries the authoritative item, so a lost race reconciles from the reply itself instead of refetching the Session. Mutations serialize per Session, so a queued operation always compares against the committed version. Re-clicking the recorded rating retracts the feedback; switching sides carries the existing note forward.

The /client exports are the plugin body (apply/inject), the MessageFeedbackActions component, the MessageFeedbackController class, and the injected face types.

Model Experience

None, as feedback is a sidecar that never enters the append-only Session log, the model context, or telemetry; no rating or note is ever visible to the model.

KV Cache effect

None; no feedback mutation touches the history tail.

Known Limitations and Deferred Work

  • Note size is a Host policy — the deployment configures maxNoteBytes (8192 in the Web bundle) and the Host rejects an oversized note with note-too-large. The editor does not pre-check the limit, so an oversized note fails on save rather than while typing.
  • No cross-tab push — a second tab's rating becomes visible on reconnect or on the next conflict reply, not immediately; the sidecar publishes no live frames.
  • Chat view only — the trajectory and waterfall views render no feedback controls even though their assistant nodes now carry the same messageId.