Refactor the agent service around native messages, skills, MCP tools, a UI message stream and a shared session
维护者通常 1 天内回复
@bobbai00 已经在做这个了。
开始于 2026年11月15日。
评估
这个 Issue 还没有评估数据。
描述
Task Summary
This refactor reshapes the agent service around four ideas.
- Standard tool-call state. The agent keeps tool calls and their results in the AI SDK's own message history, instead of rebuilding a summary by hand at every step (#9455).
- A few tools, with edits as patches. The agent reads a workflow, looks up operators, executes, and edits with one tool whose input is a patch: one call can add, modify and delete several operators and their links, and is applied whole or not at all (#9481). Later the same tools are served from a Texera MCP server, one of many the agent can connect to (#9457).
- Skills. The system prompt shrinks to the essentials, and Texera's know-how moves into skills loaded only when needed (#9456).
- One protocol to the browser, and one shared session. The agent streams its turns to the browser in the AI SDK's own UI message stream, which the SDK's chat clients read in Angular today and in React later (#9482). Instead of editing its own copy, the agent joins the workflow's shared editing and execution session, so the agent and the user see the same workflow and the same executions (#9464).
The order: #9454 first, so every later step can report its score. Then the loop, the tools and the protocol: #9455, then #9481 and #9482, then #9456. Then the shared session (#9464), and last the MCP server (#9457), whose tools edit the shared workflow.
Saving conversations with an owner (#5267, #5268) moves to the resource unification in #9395, where a conversation becomes a resource kind. In the picture, the session store comes with that work, and add_operator and edit_operator are one edit_workflow tool.
For background, see #9377 and #9395. A few open fixes should land first: #9149, #9259, #8753 and #9043.
Task Type
- Refactor / Cleanup
- DevOps / Deployment / CI
- Testing / QA
- Documentation
- Performance
- Other
- 主要语言
- Scala
- 星标
- 333
- 派生
- 202
- 平均合并
- 3 天 11 小时
- 30 天内合并 PR
- 185
环境准备
- 没有 Dockerfile 或 Docker Compose 文件
- 有 Pull Request 模板
- 阅读贡献指南
从这里开始
- 先读完整个 Issue,再读项目的贡献指南。
- 在 Issue 下留言说明你要接手 —— 这能避免两个人做同样的事。
- Fork 仓库,在一个分支上完成修改。
- 提交 Pull Request,并在描述里引用这个 Issue 编号。
apache/texera 的其他 Issue
-
难度 2/5 1-3 小时 新手友好度 75/100
维护者通常 1 天内回复
-
难度 2/5 1-3 小时 新手友好度 82/100
维护者通常 1 天内回复
-
addOperator returns an error but still adds the operator可能已有人在做 @sunny-kavixo 于 5 天前认领。 未关闭
难度 2/5 1-3 小时 新手友好度 78/100
维护者通常 1 天内回复
-
Failed tool calls are marked as succeeded (isError is always false)可能已有人在做 @oliarmak-web 于 14 天前认领。 未关闭
难度 2/5 1-3 小时 新手友好度 80/100
apache/texera#9120 · 8 条评论 · 已指派 1 人 ·
维护者通常 1 天内回复
-
难度 2/5 1-3 小时 新手友好度 62/100
维护者通常 1 天内回复
相似的 Issue
-
? - Needs Triage bug
难度 2/5 1-3 小时 新手友好度 75/100
NVIDIA/cudf-spark#16937 ·
维护者通常 1 天内回复
-
LFST not-issued-store count truncation can incorrectly clear strictShouldWait可能已有人在做 @weidingliu 今天认领。 未关闭module: memory type: bug/reported
难度 2/5 1-3 小时 新手友好度 68/100
OpenXiangShan/XiangShan#6974 · 1 条评论 · 已指派 1 人 ·
维护者通常 3 天内回复
-
bug indigo
难度 2/5 1-3 小时 新手友好度 82/100
PurpleKingdomGames/indigoengine#300 · 1 条评论 ·
-
JavaReservoirSampleOperator returns the whole input when the dataset size is unknown可能已有人在做 @sasmith-14 于 2 天前认领。 未关闭
难度 2/5 1-3 小时 新手友好度 72/100
维护者通常 2 天内回复
-
AI Generated CI/CD ⚒️ Flaky-tests 🐦 python 🐍
难度 2/5 1-3 小时 新手友好度 62/100
valkey-io/valkey-glide#7722 ·
维护者通常 1 天内回复