Update all operational references to reflect the new repo name per ADR-003 (OAS S1 Infrastructure Substrate). Historical text in ADRs and state-hub-inbox files preserved as-is. Gitea remote URL updated locally (Gitea repo rename is a manual step). Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
1.9 KiB
type, id, target_org, target_repo, status, created, source_repo, related_workstream_id
| type | id | target_org | target_repo | status | created | source_repo | related_workstream_id |
|---|---|---|---|---|---|---|---|
| feature-request | fr-2026-03-09--threephoenix--state-hub--update-workstream-tool | threephoenix | state-hub | draft | 2026-03-09 | railiance-infra | bf40b47e-be5b-4930-a7d2-362e76b943bb |
FR: update_workstream MCP Tool
Problem
The MCP server exposes update_workstream_status (status changes only) but no
general update_workstream tool. This means fields like repo_goal_id, title,
description, owner, and due_date cannot be updated via MCP once a workstream
is created.
This was discovered during offline-inbox drain: the workplan file RAIL-HO-WP-0001
correctly references repo_goal_id: 9e835b82-acca-493a-943f-2553ffe0bf54, but the
DB workstream (bf40b47e) has repo_goal_id: null because the field was not set
at creation time. There is no tool to fix this without a direct API call.
The goal_guidance section of get_domain_summary() then surfaces a false
needs_workplan warning for the linked goal, because the DB record is incomplete.
Proposed Solution
Add an update_workstream MCP tool:
update_workstream(
workstream_id: str,
title: str | None = None,
description: str | None = None,
owner: str | None = None,
due_date: str | None = None, # ISO date
repo_goal_id: str | None = None, # UUID
repo_id: str | None = None, # UUID
)
Semantics: patch — only provided fields are updated. Returns the updated workstream.
Acceptance Criteria
- Claude can set
repo_goal_idon an existing workstream - Partial updates (only provided fields change, others unchanged)
get_domain_summary()goal_guidance reflects the updated linkage after the call
Priority
Medium. Workaround is a direct API call, but this breaks the MCP-only workflow and leaves audit gaps when agents operate without direct API access.