Let the agent join the workflow's shared editing and execution session
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
- 領域
- backend, full-stack
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:
- 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.
- 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.
- 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_executiontool. An execution the agent asks for does not end one that is still going (todaySyncExecutionResourceshuts 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.
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
- Dockerfile・Docker Compose ファイルなし
- プルリクエストのテンプレートあり
- コントリビューションガイドを読む
はじめの一歩
- 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。
- 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。
- リポジトリをフォークし、ブランチを切って変更します。
- 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
-
難易度 2/5 1〜3時間 初心者へのやさしさ 75/100
メンテナーはふだん 1 日以内に返信
-
難易度 2/5 1〜3時間 初心者へのやさしさ 82/100
メンテナーはふだん 1 日以内に返信
-
addOperator returns an error but still adds the operator対応中かも @sunny-kavixo が 5 日前に担当しました。 オープン
難易度 2/5 1〜3時間 初心者へのやさしさ 78/100
apache/texera#9121 · コメント 1 件 ·
メンテナーはふだん 1 日以内に返信
-
Failed tool calls are marked as succeeded (isError is always false)対応中かも @oliarmak-web が 14 日前に担当しました。 オープン
難易度 2/5 1〜3時間 初心者へのやさしさ 80/100
apache/texera#9120 · コメント 8 件 · 担当者 1 名 ·
メンテナーはふだん 1 日以内に返信
-
難易度 2/5 1〜3時間 初心者へのやさしさ 62/100
apache/texera#8682 · コメント 5 件 ·
メンテナーはふだん 1 日以内に返信
似ている issue
-
? - Needs Triage bug
難易度 2/5 1〜3時間 初心者へのやさしさ 75/100
NVIDIA/cudf-spark#16937 ·
メンテナーはふだん 1 日以内に返信
-
LFST not-issued-store count truncation can incorrectly clear strictShouldWait対応中かも @weidingliu が今日担当しました。 オープンmodule: memory type: bug/reported
難易度 2/5 1〜3時間 初心者へのやさしさ 68/100
OpenXiangShan/XiangShan#6974 · コメント 1 件 · 担当者 1 名 ·
メンテナーはふだん 3 日以内に返信
-
bug indigo
難易度 2/5 1〜3時間 初心者へのやさしさ 82/100
PurpleKingdomGames/indigoengine#300 · コメント 1 件 ·
-
JavaReservoirSampleOperator returns the whole input when the dataset size is unknown対応中かも @sasmith-14 が 2 日前に担当しました。 オープン
難易度 2/5 1〜3時間 初心者へのやさしさ 72/100
apache/wayang#884 · コメント 3 件 ·
メンテナーはふだん 2 日以内に返信
-
AI Generated CI/CD ⚒️ Flaky-tests 🐦 python 🐍
難易度 2/5 1〜3時間 初心者へのやさしさ 62/100
valkey-io/valkey-glide#7722 ·
メンテナーはふだん 1 日以内に返信