scrum4me-mcp/src/tools/update-idea-plan-md.ts
Madhura68 fdf3dc4471 feat: M12 idea-job support — version 0.6.0
Adds the 4 new MCP-tools for the Scrum4Me M12 Idea-entity flow + extends
3 existing tools to handle the new ClaudeJobKind discriminator.

New tools:
- get_idea_context: full idea + product + open questions + recent logs
- update_idea_grill_md: save grill-result + status → GRILLED + IdeaLog
- update_idea_plan_md: server-side yaml parser validates frontmatter;
  ok → PLAN_READY, fail → PLAN_FAILED + line-info errors
- log_idea_decision: DECISION/NOTE entries on the timeline

Extended tools:
- ask_user_question: xor schema (story_id | idea_id); idea-questions are
  user-private with productId derived from idea.product_id
- wait_for_job: returns \`kind\` discriminator; IDEA_* payloads include
  idea + prompt_text (from src/prompts/idea/) and skip worktree creation
- update_job_status: failed on IDEA_* auto-transitions idea-status to
  GRILL_FAILED / PLAN_FAILED + IdeaLog{JOB_EVENT}; auto-PR + worktree-
  cleanup skipped for idea-jobs

Other changes:
- Health version now read dynamically from package.json (was hardcoded
  '0.1.0' which caused deploy-sync confusion)
- Schema synced to Scrum4Me M12 (Idea + IdeaLog + enums + ClaudeJob/
  Question nullable-FKs + check-constraints + pg_notify-trigger update)
- New @scrum4me-mcp/lib/idea-plan-parser duplicates Scrum4Me's parser
  (drift detected by vendor schema-watchdog)
- Embedded grill+make-plan prompts copied to src/prompts/idea/
- New userOwnsIdea access helper

Tests: 153/153 green; tsc + build clean.

Migration: requires Scrum4Me M12 migration (20260504172747_add_ideas_and_grill_jobs)
applied on the target DB. See vendor/scrum4me/docs/runbooks/mcp-integration.md
for the updated batch-loop with kind-switch.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-04 22:12:36 +02:00

90 lines
3 KiB
TypeScript

// MCP-tool: schrijft het plan_md-resultaat na een IDEA_MAKE_PLAN-job en
// transitioneert de idea-status naar PLAN_READY (bij geldige yaml-frontmatter)
// of PLAN_FAILED (bij parse-fout).
//
// Wordt aangeroepen door de worker als laatste stap van een make-plan-sessie.
import { z } from 'zod'
import type { McpServer } from '@modelcontextprotocol/sdk/server/mcp.js'
import { prisma } from '../prisma.js'
import { requireWriteAccess } from '../auth.js'
import { userOwnsIdea } from '../access.js'
import { toolError, toolJson, withToolErrors } from '../errors.js'
import { parsePlanMd } from '../lib/idea-plan-parser.js'
const inputSchema = z.object({
idea_id: z.string().min(1),
markdown: z.string().min(1).max(64_000),
})
export function registerUpdateIdeaPlanMdTool(server: McpServer) {
server.registerTool(
'update_idea_plan_md',
{
title: 'Update idea plan_md',
description:
'Save the make-plan-result markdown for an idea. Server validates yaml-frontmatter; on success status → PLAN_READY, on parse-fail → PLAN_FAILED. Forbidden for demo accounts.',
inputSchema,
},
async ({ idea_id, markdown }) =>
withToolErrors(async () => {
const auth = await requireWriteAccess()
if (!(await userOwnsIdea(idea_id, auth.userId))) {
return toolError('Idea not found')
}
const parsed = parsePlanMd(markdown)
if (!parsed.ok) {
// Persist md + flip to PLAN_FAILED + log de errors zodat de UI ze
// aan de user kan tonen.
const result = await prisma.$transaction([
prisma.idea.update({
where: { id: idea_id },
data: { plan_md: markdown, status: 'PLAN_FAILED' },
select: { id: true, status: true, code: true },
}),
prisma.ideaLog.create({
data: {
idea_id,
type: 'JOB_EVENT',
content: 'plan_md parse failed',
metadata: { errors: parsed.errors },
},
}),
])
return toolJson({
ok: false,
idea: result[0],
errors: parsed.errors,
})
}
const result = await prisma.$transaction([
prisma.idea.update({
where: { id: idea_id },
data: { plan_md: markdown, status: 'PLAN_READY' },
select: { id: true, status: true, code: true },
}),
prisma.ideaLog.create({
data: {
idea_id,
type: 'PLAN_RESULT',
content: `Plan ready: ${parsed.plan.stories.length} stories, ${parsed.plan.stories.reduce((n, s) => n + s.tasks.length, 0)} tasks`,
metadata: {
pbi_title: parsed.plan.pbi.title,
story_count: parsed.plan.stories.length,
task_count: parsed.plan.stories.reduce((n, s) => n + s.tasks.length, 0),
},
},
}),
])
return toolJson({
ok: true,
idea: result[0],
})
}),
)
}