---
type: feature-request
id: fr-2026-03-09--threephoenix--state-hub--update-workstream-tool
target_org: threephoenix
target_repo: state-hub
status: draft
created: "2026-03-09"
source_repo: railiance-infra
related_workstream_id: 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:

```python
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_id` on 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.