Automattic / Automattic/wp-codebox
Bridge approved parent tools for imported sandbox agents
- Vorherrschende Sprache
- TypeScript
- Sterne
- 16
- Forks
- 4
- Ø Merge
- 59 Min.
- Gemergte PRs (30 T.)
- 131
Beschreibung
## Problem
Imported native agents execute in WordPress Playground but receive no workspace/Git/GitHub tools. The reusable workflow correctly classifies those tools as `parent` / `control_plane`; `sandbox-tool-policy` therefore excludes them and `tool_contract.tools` is empty.
Evidence: https://github.com/Automattic/build-with-wordpress/actions/runs/29311239264
The technical bootstrap agent runs but cannot inspect or modify the target checkout and returns no-op.
## Required outcome
Implement the generic parent-tool bridge already modeled by `wp-codebox/parent-tool-bridge/v1`:
- Expose only approved parent tool schemas to the model as bridged client tools while retaining parent/control-plane execution classification.
- Pause the Agents API loop on a bridged call, return a bound pending request to the Node host, execute it through the policy-aware runner-workspace executor, submit the result, and resume the same runtime conversation until terminal.
- Bind request/result to run, session, tool call, allowed tool and allowed repository; enforce idempotency, turn/tool/time budgets, approval and redaction.
- Never expose host paths, tokens, shell access, or arbitrary command execution to the sandbox.
- Support workspace read/search/write/edit/patch and the declared Git/GitHub operations through existing typed executors.
- Add deterministic imported-package E2E: model reads and edits a temp workspace through the bridge, verification passes, patch captured; spoof/denied/malformed/replay cases fail.
- No Docs Agent-specific production code.
- Release and rerun both maintenance and bootstrap.
Beitragsleitfaden
Für dieses Repository ist kein Beitragsleitfaden indexiert
Rechercherichtung
Beginne mit dem modellierten Vertrag wp-codebox/parent-tool-bridge/v1, sandbox-tool-policy, der Agents API-Schleife und den vorhandenen typisierten Executoren. Überprüfe, dass die E2E des importierten Pakets Workspace-Lesen/-Bearbeiten, Patch-Erfassung, Spoofing, Ablehnung, fehlerhafte Requests und Replay abdeckt; abgeschlossen ist die Arbeit außerdem erst mit dem Release und erneuten Ausführungen von maintenance und bootstrap.
Vom Indexierungsmodell aus dem Issue-Text verfasst.
Bewertung
- Tech-Stack
- git, github, typescript, wordpress
- Bereich
- backend-api-design, security, testing
- Issue-Typ
- Feature
- Schwierigkeit
- 5/5
- Geschätzter Aufwand
- Über eine Woche
- Aktivitätsstatus
- Ruhig
- Klarheit
- Größtenteils klar
- Anfängerfreundlichkeit
- 25/100