my-dsh/oh-my-dsh--packages-client-ui-message-feedback ↗★ 2

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

逐条消息反馈控件,为助手消息操作栏提供点赞点踩与备注。 适合希望对助手回复进行点赞点踩并附备注的网页用户与维护者。

套件
@deepseek-ai/dsh-client-ui-message-feedback
相容性
待驗證
Cordis 依賴範圍
workspace:^
版本
0.1.2-alpha.2
授權
MIT
最近更新
2026年9月10日

同名套件的其他儲存庫

安裝

此插件尚未提供可驗證的 bundle,或相容性檢查未通過。請先閱讀倉庫說明。 閱讀完整 README ↗


description: "Per-message feedback for the Web GUI: the Like/Dislike pair and optional note in the finalized assistant message's action row; for users and maintainers of the feedback experience." kind: "package-reference"

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

English | 中文

Summary

This package adds per-message feedback to the Web GUI: a Like/Dislike pair plus an optional note, contributed as the feedback entry of the finalized assistant message's action strip. It renders on the closing assistant message of each turn — earlier steps of a multi-step turn produce tool rows rather than a rateable body. One controller per Session backs every message control in that Session, so a single list read seeds the whole transcript. Feedback is a sidecar: ratings and notes never enter the session log, the model context, or telemetry.

Table of Contents


Use this package

Mount this plugin alongside ui-conversation; the Like/Dislike pair then appears in the action row of each turn's closing assistant message, between copy and branch. Clicking the recorded rating retracts the feedback; switching sides carries the existing note forward. The note editor is a dialog popover anchored under its trigger, so the row keeps its single line whether the editor is open or closed.

Failures

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.


Understand the implementation

Implementation internals — click to expand

The package contributes the feedback entry (order 10) of conversation.chat.assistant-actions, declared by ui-conversation and rendered inside the finalized assistant message's IconActions row. 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. 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. Mutations serialize per Session, so a queued operation always compares against the committed version.


Further Exploration

Read these pages when the feedback surface is not enough. They move from the browser strip to the sidecar backend and the conversation shell.


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

These limits define the current feedback surface. They are current package constraints, not a general rating comparison or a task backlog.

  • 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 carry the same messageId.

Dev Note

Working context for maintainers — click to expand

None.