Let the agent join the workflow's shared editing and execution session

オープン
#9,464 コメント 0 件 リアクション 0 件 担当者 0 名 GitHub で見る

メンテナーはふだん 1 日以内に返信

まだ誰も着手していません。

評価

難易度
5/5
見積もり時間
1週間以上
初心者へのやさしさ
14/100
issue の種類
リファクタリング
明瞭さ
おおむね明確
活発さ
活発
技術スタック
scala

調査の方向性

Read the agent service's current workflow loading path (the copy it takes when a chat starts) alongside the existing collaboration client the open canvas uses to join the editing room and subscribe to computing-unit execution events; that client is the model for the new shared session client. Then trace how the agent's chat loop consumes execution events and where it would instead apply edits to the shared workflow and summarize deltas for the model. Done means the agent edits the server-saved workflow and sees every execution's events regardless of who started it, verified with two clients (browser plus agent) on one workflow.

索引モデルが issue の本文から書いたものです。

説明

Task Summary

Today the agent works on its own copy of the workflow, loaded when the chat starts, and only hears about executions it starts itself. So the user's later edits can be lost, and the agent can't tell why the user's execution failed or came back empty.

Texera already shares edits and executions live: every open canvas joins the workflow's editing room and receives the computing unit's execution events. The agent is the only participant left out. The room has gaps of its own, though. Its server is the stock y-websocket server, which checks no one's access. It runs on Kubernetes and in local development, but single-node starts none, so shared editing does not work there. And every browser loads the workflow into the room when it opens it, and saves the whole workflow five seconds after a change.

This task makes the session the server's, in three parts:

  1. A session service. It replaces the y-websocket server in every deployment. It checks each person's token and access to the workflow (viewers get a read-only connection), loads the workflow from the Dashboard Service, and saves it shortly after edits stop. Browsers no longer load or save the workflow themselves. The live service of the Texera 2.0 prototype does this on Hocuspocus (MIT) and can be ported. The shared document keeps main's layout, so the Angular app, this service and later the React app read it the same way.
  2. Reads and edits from the server. The service lets the agent's tools read the workflow as it stands and apply a patch from #9481 as one change, tagged with the user and the chat, so review mode (#9075) can tell the agent's changes apart. The agent shows among the co-editors while it works.
  3. Executions. A new read of the workflow's current or last execution on its computing unit, whoever started it: its state, each operator's state and row counts, and its errors and console errors. This becomes the get_execution tool. An execution the agent asks for does not end one that is still going (today SyncExecutionResource shuts the previous one down): the tool says who started it, and the agent asks the person first.

With them:

  • The agent edits the shared workflow instead of a copy.
  • It sees every execution, no matter who started it.
  • Its model sees a short summary of what changed at each step.
  • The server saves the workflow, so the agent's edits are kept even when no browser is open.

This also settles the open question in #9457 about which copy the agent edits, and makes the browser report in #9423 unnecessary.

The agent and the user in one shared session
Task Type
  • Refactor / Cleanup
  • DevOps / Deployment / CI
  • Testing / QA
  • Documentation
  • Performance
  • Other
主要言語
Scala
スター
333
フォーク
202
平均マージ
3日 11時間
マージ済み PR(30日)
185

環境構築

はじめの一歩

  1. issue を最後まで読み、次にプロジェクトのコントリビューションガイドを読みます。
  2. 着手することを issue にコメントします — 二人が同じ作業をするのを防げます。
  3. リポジトリをフォークし、ブランチを切って変更します。
  4. issue 番号を参照したプルリクエストを送ります。

apache/texera のほかの issue

apache/texera の issue をすべて見る

似ている issue

Scala の issue をもっと見る

新しい issue をメールで受け取る

初心者向けの GitHub issue を短くまとめたダイジェスト。