Serve the agent's workflow tools from a Texera MCP server

Aperta
#9,457 0 commenti 0 reazioni 0 assegnatari Vedi su GitHub

I maintainer di solito rispondono entro 1 giorno

Nessuno ha ancora preso questa issue.

Valutazione

Difficoltà
4/5
Tempo stimato
3-5 giorni
Idoneità per principianti
22/100
Tipo di issue
Refactoring
Chiarezza
Da chiarire
Stato di attività
Attiva
Stack tecnologico
scala
Ambito
ai, backend

Direzione di ricerca

Start with the linked context: #5610 (the inline-tools decision being revisited), #9464 (moves the agent onto the shared workflow and is a prerequisite), and #8663 (aicam's prototype, the open question of whether to build on it). Locate where the agent service currently registers its workflow tools and operator lookup, then trace how the once-loaded private workflow copy is read. Done means one Texera MCP server exposing those tools and the operator lookup, authenticated with the user's token and editing the shared workflow, with the agent and outside assistants both calling it.

Scritto dal modello di indicizzazione a partire dal testo della issue.

Descrizione

Task Summary

Today the agent's tools run inside the agent service and edit a private copy of the workflow. That copy is loaded once, before the first prompt, so a change the user makes between prompts gets overwritten. #9464 fixes this by moving the agent onto the shared workflow.

This task moves the tools from #9481 onto one Texera MCP server, with the same names and inputs. The agent and outside assistants (#8663) call it, and its tools edit the shared workflow through #9464. This revisits the inline-tools decision in #5610.

  • The server holds no session: every tool takes the workflow id, so any copy of the server can answer, as the current MCP revision (2026-07-28) expects.
  • It is built on the official server SDK (@modelcontextprotocol/server, Apache-2.0), which runs on Bun like the agent service.
  • Each tool says whether it only reads (readOnlyHint), so a client can ask the person before a change.
  • From aicam's prototype in #8663, the shared client package and the test harness can be kept. Its workflow editing holds a session in the server's memory (workflow_open to workflow_save), which the shared session replaces.
  • The agent calls the server with the user's token, as its backend calls do today. The MCP specification, though, has a server accept only tokens issued for it, and today's Texera tokens name no audience. So an outside assistant can use a token the person pastes in, while signing in from an assistant needs an authorization server, which Texera does not have yet.

The dataset tools from #9377, which also cover #4588, will come later on the endpoints from #9395. Review mode (#9075) waits on #9464.

A change made between two prompts is lost After: one MCP server and one copy of the workflow
Task Type
  • Refactor / Cleanup
  • DevOps / Deployment / CI
  • Testing / QA
  • Documentation
  • Performance
  • Other
Lingua principale
Scala
Stelle
333
Fork
202
Merge medio
3g 11h
PR unite (30g)
185

Preparare l'ambiente

Come iniziare

  1. Leggi tutta la issue e poi la guida ai contributi del progetto.
  2. Commenta sulla issue per dire che te ne occupi tu — evita che due persone facciano lo stesso lavoro.
  3. Fai un fork del repository e lavora su un branch.
  4. Apri una pull request che faccia riferimento al numero della issue.

Altre issue di apache/texera

Tutte le issue di apache/texera

Issue simili

Altre issue su Scala

Ricevi le nuove issue nella tua casella

Un breve riepilogo di issue GitHub adatte ai principianti.