From 948f75d087d1f3a9c39463387cb2e38ebcb817eb Mon Sep 17 00:00:00 2001 From: Madhura68 Date: Thu, 7 May 2026 17:43:37 +0200 Subject: [PATCH] feat(PBI-58): codegen script for in-app manual TOC scripts/build-manual.mjs walks docs/manual/, parses YAML front-matter, strips it from the body, and emits lib/manual.generated.ts with a typed ManualEntry[] containing slug, title, description, filePath, and the embedded markdown body. Pure Node 20, mirrors generate-docs-index.mjs. Inlining the markdown at build time keeps runtime serverless functions free of filesystem reads, which avoids whole-project NFT tracing. Co-Authored-By: Claude Opus 4.7 (1M context) --- lib/manual.generated.ts | 865 +++++++++++++++++++++++++++++++++++++++ scripts/build-manual.mjs | 159 +++++++ 2 files changed, 1024 insertions(+) create mode 100644 lib/manual.generated.ts create mode 100644 scripts/build-manual.mjs diff --git a/lib/manual.generated.ts b/lib/manual.generated.ts new file mode 100644 index 0000000..b69294e --- /dev/null +++ b/lib/manual.generated.ts @@ -0,0 +1,865 @@ +// AUTO-GENERATED by scripts/build-manual.mjs. Do not edit by hand. +// Run `npm run manual:build` to regenerate. + +export type ManualEntry = { + slug: readonly string[] + title: string + description: string + filePath: string + markdown: string +} + +export const MANUAL_TOC: readonly ManualEntry[] = [ + { + slug: [] as const, + title: 'Scrum4Me Developer Manual', + description: 'Welcome. This manual is the **map** of Scrum4Me — a guided tour through the moving parts of the project. It is written for a new human contributor who needs to understand how the pieces fit together before diving into the authoritative reference docs (the runbooks, ADRs, and patterns under [`docs/`](../INDEX.md)).', + filePath: 'docs/manual/index.md', + markdown: `# Scrum4Me Developer Manual + +Welcome. This manual is the **map** of Scrum4Me — a guided tour through the moving parts of the project. It is written for a new human contributor who needs to understand how the pieces fit together before diving into the authoritative reference docs (the runbooks, ADRs, and patterns under [\`docs/\`](../INDEX.md)). + +> **The manual is the map. The runbooks are the territory.** +> When two sources disagree, trust the runbook or ADR linked from this manual. + +## Audience + +- **New human contributors** picking up the project for the first time. +- **Returning contributors** who want a quick refresher on how a specific subsystem (statuses, git, MCP, Docker) fits into the whole. +- **Not for**: AI agents — they should follow [\`CLAUDE.md\`](../../CLAUDE.md) and the agent-specific runbooks under [\`docs/runbooks/\`](../runbooks/). + +## How to read this manual + +| You want to… | Read | +|---|---| +| …get the elevator pitch and project structure | [01 — Overview](./01-overview.md) | +| …understand how a PBI/Story/Task moves through its lifecycle | [02 — Statuses & Transitions](./02-statuses-and-transitions.md) | +| …know when to branch, commit, push, and open a PR | [03 — Git Workflow](./03-git-workflow.md) | +| …see how Claude Code drives stories via the MCP server | [04 — MCP Integration](./04-mcp-integration.md) | +| …run the worker container locally or understand the deploy topology | [05 — Docker](./05-docker.md) | +| …diagnose an error code, stuck job, or weird state | [06 — Troubleshooting](./06-troubleshooting.md) | + +A linear read takes about 30 minutes. As a lookup reference, jump straight to a chapter — each one stands alone. + +## Conventions + +- **Cross-references** use relative links (\`../runbooks/...\`) so they work both in GitHub and inside the in-app \`/manual\` viewer. +- **Callouts** use blockquotes prefixed with a label: \`> **Note:**\`, \`> **Warning:**\`, \`> **Hardstop:**\` (a non-negotiable rule from [\`CLAUDE.md\`](../../CLAUDE.md)). +- **Code blocks** show shell commands with no \`$\` prefix, so they're copy-pasteable. +- **State diagrams** use Mermaid \`stateDiagram-v2\`; they render in GitHub and in the in-app viewer. +- **Status labels** are written in \`UPPER_SNAKE\` when referring to the database value and \`lowercase\` when referring to the API representation — see [02 — Statuses & Transitions](./02-statuses-and-transitions.md#db-vs-api-mapping) for the contract. + +## In-app rendering + +Every chapter in this manual is also browsable inside the running Scrum4Me app at \`/manual\`. The in-app sidebar mirrors this index, and Mermaid diagrams render in place. The markdown files under \`docs/manual/\` are the **source of truth** — the in-app page reads them at build time via the \`scripts/build-manual.mjs\` generator. + +## What this manual does **not** cover + +- **REST API reference** → [\`docs/api/rest-contract.md\`](../api/rest-contract.md) +- **Component & dialog specs** → [\`docs/specs/dialogs/\`](../specs/dialogs/) +- **Architecture deep-dives** → [\`docs/architecture.md\`](../architecture.md) breadcrumb +- **Decision rationale** → [\`docs/adr/\`](../adr/) +- **Implementation patterns** → [\`docs/patterns/\`](../patterns/) +- **AI-agent instructions** → [\`CLAUDE.md\`](../../CLAUDE.md) and [\`docs/runbooks/mcp-integration.md\`](../runbooks/mcp-integration.md) + +## Table of contents + +1. [Overview](./01-overview.md) — what Scrum4Me is, the entity hierarchy, the stack, repository layout +2. [Statuses & Transitions](./02-statuses-and-transitions.md) — state machines for every entity +3. [Git Workflow](./03-git-workflow.md) — branching, commits, PRs, deploy controls +4. [MCP Integration](./04-mcp-integration.md) — the agent loop, idea jobs, the Q&A channel +5. [Docker](./05-docker.md) — worker container, local dev, scrum4me-docker +6. [Troubleshooting](./06-troubleshooting.md) — error codes, stuck jobs, recovery procedures +`, + }, + { + slug: ['01-overview'] as const, + title: 'Overview', + description: 'Scrum4Me is a **desktop-first fullstack web app for solo developers and small Scrum teams** who manage multiple software projects in parallel. It models the Scrum hierarchy explicitly (Product → PBI → Story → Task), supports Sprints with split-screen drag-and-drop planning, and integrates Claude Code as an automated implementation worker — every result the agent produces is logged back into the originating story.', + filePath: 'docs/manual/01-overview.md', + markdown: `# 01 — Overview + +## What is Scrum4Me? + +Scrum4Me is a **desktop-first fullstack web app for solo developers and small Scrum teams** who manage multiple software projects in parallel. It models the Scrum hierarchy explicitly (Product → PBI → Story → Task), supports Sprints with split-screen drag-and-drop planning, and integrates Claude Code as an automated implementation worker — every result the agent produces is logged back into the originating story. + +The app is deployable to **Vercel + Neon** (default) and can run **fully local** via the worker container. A built-in demo user has read-only access; Product Owners add Developers by username, and those Developers gain write access to that product's stories, tasks, and sprints. + +## Entity hierarchy + +\`\`\`mermaid +flowchart TB + Product["Product
(per repo)"] + Idea["Idea
(pre-PBI staging)"] + PBI["PBI
(Product Backlog Item)"] + Story["Story"] + Task["Task"] + Sprint["Sprint
(cross-cutting)"] + + Product --> Idea + Idea -.->|"AI-grilled & planned"| PBI + Product --> PBI + PBI --> Story + Story --> Task + Sprint -.->|"contains stories
denormalised on tasks"| Story + Sprint -.-> Task +\`\`\` + +- **Product** — one row per repo. \`repo_url\`, \`definition_of_done\`, members. +- **Idea** — pre-PBI staging entity introduced in M12. Goes through \`IDEA_GRILL\` (AI Q&A loop) and \`IDEA_MAKE_PLAN\` jobs to produce a structured plan that can be turned into a PBI tree. +- **PBI** — a Product Backlog Item. Has \`priority\` (1–4) and \`sort_order\` (float, see [\`docs/patterns/sort-order.md\`](../patterns/sort-order.md)). +- **Story** — a unit of value under a PBI; has acceptance criteria. Lives in the backlog (\`OPEN\`) until added to a sprint. +- **Task** — the smallest unit; has an \`implementation_plan\` consumed by the Claude worker. \`sprint_id\` is denormalised from the parent story for query efficiency. +- **Sprint** — cross-cutting time-box. Stories are added to a sprint; tasks inherit \`sprint_id\`. Sprint execution has two modes: \`PER_TASK\` and \`SPRINT_BATCH\` — see [\`docs/architecture/sprint-execution-modes.md\`](../architecture/sprint-execution-modes.md). + +For status lifecycles of each entity, see [02 — Statuses & Transitions](./02-statuses-and-transitions.md). + +## Stack + +| Layer | Technology | +|---|---| +| Framework | Next.js 16 (App Router) + React 19 | +| Language | TypeScript (strict) | +| Styling | Tailwind CSS + shadcn/ui + Material Design 3 tokens via [\`app/styles/theme.css\`](../../app/styles/theme.css) | +| Client state | Zustand + dnd-kit | +| Database | Prisma v7 + PostgreSQL (Neon) | +| Auth | iron-session + bcryptjs | +| Utilities | Zod, Sonner, Sharp, Vercel Analytics | +| Hosting | Vercel (app), Neon (DB), Mac/NAS Docker (worker) | + +For the rationale behind each choice and the technologies we explicitly **don't** use, see [\`docs/architecture/overview.md\`](../architecture/overview.md). + +## Repository layout + +\`\`\` +Scrum4Me/ +├── app/ # Next.js App Router routes +│ ├── (app)/ # authenticated desktop UI +│ ├── (auth)/ # login, register, demo +│ ├── (mobile)/ # /m/* mobile shell (3 screens) +│ ├── api/ # REST route handlers (Claude integration) +│ └── styles/ # MD3 token CSS +├── components/ # shared UI components +├── lib/ # server/client utilities +│ └── task-status.ts # the ONLY place DB↔API enum mapping happens +├── prisma/ # schema + migrations +├── docs/ # this manual + ADRs, runbooks, patterns, specs +└── scripts/ # codegen, seeders, link checkers +\`\`\` + +The \`*-server.ts\` filename suffix marks server-only modules (DB, Node APIs). They must never be imported into a client component — see the hardstop in [\`CLAUDE.md\`](../../CLAUDE.md#hardstop-regels). + +For a deeper structural breakdown including stores, realtime channels, and the job queue, see [\`docs/architecture/project-structure.md\`](../architecture/project-structure.md). + +## Glossary refresh + +A few terms used throughout this manual that often differ from "generic Scrum" usage: + +- **PBI** — Product Backlog Item. Not "Feature" or "Epic". +- **Story** — A unit of work under a PBI. Not "Ticket" or "Issue". +- **Sprint Goal** — The narrative for a sprint. Not "Objective". +- **Worker** — A Claude Code agent claiming jobs from the Scrum4Me queue (M13). +- **Demo user** — A read-only built-in user; writes return \`403\`. See [\`docs/adr/0006-demo-user-three-layer-policy.md\`](../adr/0006-demo-user-three-layer-policy.md). +- **Idea** — Pre-PBI staging artefact (M12). Has its own state machine; see [02](./02-statuses-and-transitions.md#idea). + +The complete glossary lives at [\`docs/glossary.md\`](../glossary.md). + +## What's next + +→ [02 — Statuses & Transitions](./02-statuses-and-transitions.md) covers how each entity moves through its lifecycle, with state-machine diagrams. +`, + }, + { + slug: ['02-statuses-and-transitions'] as const, + title: 'Statuses & Transitions', + description: 'Every persistent entity in Scrum4Me has an explicit status enum. This chapter documents them all, with state-machine diagrams showing allowed transitions, the trigger for each transition (user action vs system / job-driven), and the side effects.', + filePath: 'docs/manual/02-statuses-and-transitions.md', + markdown: `# 02 — Statuses & Transitions + +Every persistent entity in Scrum4Me has an explicit status enum. This chapter documents them all, with state-machine diagrams showing allowed transitions, the trigger for each transition (user action vs system / job-driven), and the side effects. + +> **Hardstop:** the database stores enums in \`UPPER_SNAKE\`; the REST API exposes them in \`lowercase\`. Conversion happens **only** through [\`lib/task-status.ts\`](../../lib/task-status.ts) — never call \`.toLowerCase()\` or \`.toUpperCase()\` directly. See the [DB vs API mapping](#db-vs-api-mapping) section at the end. + +## Quick reference + +| Entity | Source enum | Statuses | +|---|---|---| +| [PBI](#pbi) | \`PbiStatus\` | \`READY\`, \`BLOCKED\`, \`DONE\`, \`FAILED\` | +| [Story](#story) | \`StoryStatus\` | \`OPEN\`, \`IN_SPRINT\`, \`DONE\`, \`FAILED\` | +| [Task](#task) | \`TaskStatus\` | \`TO_DO\`, \`IN_PROGRESS\`, \`REVIEW\`, \`DONE\`, \`FAILED\` | +| [Sprint](#sprint) | \`SprintStatus\` | \`ACTIVE\`, \`COMPLETED\`, \`FAILED\` | +| [SprintRun](#sprintrun) | \`SprintRunStatus\` | \`QUEUED\`, \`RUNNING\`, \`PAUSED\`, \`DONE\`, \`FAILED\`, \`CANCELLED\` | +| [ClaudeJob](#claudejob) | \`ClaudeJobStatus\` | \`QUEUED\`, \`CLAIMED\`, \`RUNNING\`, \`DONE\`, \`FAILED\`, \`CANCELLED\`, \`SKIPPED\` | +| [Idea](#idea) | \`IdeaStatus\` | \`DRAFT\`, \`GRILLING\`, \`GRILL_FAILED\`, \`GRILLED\`, \`PLANNING\`, \`PLAN_FAILED\`, \`PLAN_READY\`, \`PLANNED\` | + +## PBI + +A **Product Backlog Item** holds one or more stories. Its status reflects whether the PBI as a whole is ready to be picked up, blocked on something external, finished, or written off. + +\`\`\`mermaid +stateDiagram-v2 + [*] --> READY: create_pbi + READY --> BLOCKED: user marks blocked + BLOCKED --> READY: user unblocks + READY --> DONE: all stories DONE + READY --> FAILED: user gives up + BLOCKED --> FAILED: user gives up + DONE --> [*] + FAILED --> [*] +\`\`\` + +| Transition | Trigger | Side effect | +|---|---|---| +| \`* → READY\` | \`create_pbi\` MCP tool or PBI dialog | New PBI lands in \`priority\` group, \`sort_order = last + 1\` | +| \`READY ↔ BLOCKED\` | User toggles via PBI dialog | None besides log entry | +| \`READY → DONE\` | All child stories reach \`DONE\` | Auto-promotion (see [ST-1109 plan](../plans/ST-1109-pbi-status.md)) | +| \`* → FAILED\` | User gives up on the PBI | Stories may remain \`OPEN\`; PBI is filtered out of active boards | + +## Story + +A **Story** sits under a PBI. It moves out of the backlog when added to a Sprint, and reaches \`DONE\` when its tasks are complete and the implementation is verified. + +\`\`\`mermaid +stateDiagram-v2 + [*] --> OPEN: create_story + OPEN --> IN_SPRINT: added to sprint + IN_SPRINT --> OPEN: removed from sprint + IN_SPRINT --> DONE: all tasks DONE + verify passes + IN_SPRINT --> FAILED: verify fails / abandoned + DONE --> [*] + FAILED --> [*] +\`\`\` + +| Transition | Trigger | Side effect | +|---|---|---| +| \`* → OPEN\` | \`create_story\` MCP tool or Story dialog | Lives in product backlog | +| \`OPEN ↔ IN_SPRINT\` | Drag onto Sprint board, or sprint-removal | Tasks denormalise \`sprint_id\` | +| \`IN_SPRINT → DONE\` | Story completion via MCP / UI; auto-PR flow may trigger | Auto-PR flow ([\`runbooks/auto-pr-flow.md\`](../runbooks/auto-pr-flow.md)) may run; PBI is re-evaluated for \`READY → DONE\` | +| \`IN_SPRINT → FAILED\` | Verification failure or manual abandon | Logged in story log | + +## Task + +A **Task** is the smallest unit. The Claude worker mainly reads \`implementation_plan\` and writes status transitions through MCP tools. + +\`\`\`mermaid +stateDiagram-v2 + [*] --> TO_DO: create_task + TO_DO --> IN_PROGRESS: agent claims / user starts + IN_PROGRESS --> REVIEW: implementation done, awaiting verify + REVIEW --> DONE: verify passes + REVIEW --> IN_PROGRESS: verify fails, retry + IN_PROGRESS --> FAILED: unrecoverable error + REVIEW --> FAILED: gives up after retries + DONE --> [*] + FAILED --> [*] +\`\`\` + +| Transition | Trigger | Side effect | +|---|---|---| +| \`* → TO_DO\` | \`create_task\` MCP tool / Task dialog | Inherits \`sprint_id\` from parent story | +| \`TO_DO → IN_PROGRESS\` | Worker claim or user starts | Story may auto-promote to \`IN_SPRINT\` | +| \`IN_PROGRESS → REVIEW\` | Implementation logged | Optional \`verify_task_against_plan\` runs | +| \`REVIEW → DONE\` | Verify passes / human accepts | When all sibling tasks are \`DONE\`, the parent story is eligible for \`DONE\` | +| \`* → FAILED\` | Unrecoverable error or human marks failed | Story may auto-promote to \`FAILED\` | + +The MCP tool is \`update_task_status({ task_id, status })\` accepting lowercase API values: \`todo | in_progress | review | done | failed\`. + +## Sprint + +A **Sprint** is the cross-cutting time-box. Its status tracks the overall sprint container, not the agent execution. + +\`\`\`mermaid +stateDiagram-v2 + [*] --> ACTIVE: create sprint + ACTIVE --> COMPLETED: user closes sprint + ACTIVE --> FAILED: user abandons sprint + COMPLETED --> [*] + FAILED --> [*] +\`\`\` + +For execution semantics (PER_TASK vs SPRINT_BATCH) see [\`docs/architecture/sprint-execution-modes.md\`](../architecture/sprint-execution-modes.md). + +## SprintRun + +A **SprintRun** is one execution attempt of a sprint by the agent worker. Multiple runs may exist over a sprint's lifetime (if a run is cancelled or paused and restarted). + +\`\`\`mermaid +stateDiagram-v2 + [*] --> QUEUED: trigger sprint run + QUEUED --> RUNNING: worker claims + RUNNING --> PAUSED: pause requested + PAUSED --> RUNNING: resume + RUNNING --> DONE: all tasks done + RUNNING --> FAILED: unrecoverable + QUEUED --> CANCELLED: user cancels + RUNNING --> CANCELLED: user cancels + PAUSED --> CANCELLED: user cancels + DONE --> [*] + FAILED --> [*] + CANCELLED --> [*] +\`\`\` + +The cascade rules (which task transitions automatically promote the SprintRun) are described in [\`docs/plans/sprint-pr-worktree-state-machines.md\`](../plans/sprint-pr-worktree-state-machines.md). When calling \`update_task_status\` from inside a sprint run, pass the optional \`sprint_run_id\` so the server can validate ownership and propagate cascades. + +## ClaudeJob + +The agent **job queue** (M13). Each enqueued unit of work is a \`ClaudeJob\` with a \`kind\` (\`TASK_IMPLEMENTATION\`, \`IDEA_GRILL\`, \`IDEA_MAKE_PLAN\`, \`PLAN_CHAT\`, \`SPRINT_IMPLEMENTATION\`). + +\`\`\`mermaid +stateDiagram-v2 + [*] --> QUEUED: enqueue + QUEUED --> CLAIMED: wait_for_job (FOR UPDATE SKIP LOCKED) + CLAIMED --> RUNNING: worker starts + RUNNING --> DONE: update_job_status('done') + RUNNING --> FAILED: update_job_status('failed') + QUEUED --> CANCELLED: user cancels + CLAIMED --> QUEUED: stale (>30min) + QUEUED --> SKIPPED: superseded + DONE --> [*] + FAILED --> [*] + CANCELLED --> [*] + SKIPPED --> [*] +\`\`\` + +| Transition | Trigger | Side effect | +|---|---|---| +| \`QUEUED → CLAIMED\` | \`wait_for_job\` atomically claims | Bearer token is bound to the job (\`claimed_by_token_id\`) | +| \`CLAIMED → QUEUED\` | Stale claim (>30 min) | Auto-requeue on next \`wait_for_job\` | +| \`RUNNING → DONE\` | \`update_job_status('done')\` | Optional token-cost telemetry stored on the row | +| \`RUNNING → FAILED\` | \`update_job_status('failed')\` | For \`IDEA_GRILL\`/\`IDEA_MAKE_PLAN\`, idea status auto-rolls to \`GRILL_FAILED\` / \`PLAN_FAILED\` | + +For idempotency rules and recovery procedures see [\`docs/runbooks/worker-idempotency.md\`](../runbooks/worker-idempotency.md). + +## Idea + +The **Idea** entity (M12) is a pre-PBI staging area. It goes through two AI-driven phases: a **grill** (Q&A loop with the user to clarify the idea) and a **plan** (single-pass output of a structured PBI tree). Failures are explicit terminal-ish states that allow retry. + +\`\`\`mermaid +stateDiagram-v2 + [*] --> DRAFT: create idea + DRAFT --> GRILLING: enqueue IDEA_GRILL + GRILLING --> GRILLED: update_idea_grill_md + GRILLING --> GRILL_FAILED: job failed + GRILL_FAILED --> GRILLING: retry + GRILLED --> PLANNING: enqueue IDEA_MAKE_PLAN + PLANNING --> PLAN_READY: update_idea_plan_md (parse ok) + PLANNING --> PLAN_FAILED: parsePlanMd rejected + PLAN_FAILED --> PLANNING: retry + PLAN_READY --> PLANNED: PBI tree created + PLANNED --> [*] +\`\`\` + +| Transition | Trigger | Side effect | +|---|---|---| +| \`DRAFT → GRILLING\` | User clicks "Grill" | Enqueues \`IDEA_GRILL\` job; worker reads \`prompt_text\` + \`idea.grill_md\` | +| \`GRILLING → GRILLED\` | \`update_idea_grill_md\` | Logs \`IdeaLog{GRILL_RESULT}\` | +| \`* → GRILL_FAILED\` | \`update_job_status('failed')\` for \`IDEA_GRILL\` | Idea remains usable; user can retry | +| \`GRILLED → PLANNING\` | User clicks "Make plan" | Enqueues \`IDEA_MAKE_PLAN\`; worker outputs strict YAML-frontmatter | +| \`PLANNING → PLAN_READY\` | \`update_idea_plan_md\` parse ok | Logs \`IdeaLog{PLAN_RESULT}\` | +| \`PLANNING → PLAN_FAILED\` | \`parsePlanMd\` rejected | Logs \`IdeaLog{JOB_EVENT, errors}\` | +| \`PLAN_READY → PLANNED\` | PBI tree generated from plan | Idea is archived; PBI/Story/Task tree appears in the backlog | + +For the full Idea workflow, prompts, and \`prompt_text\` contents, see [\`docs/plans/M12-ideas.md\`](../plans/M12-ideas.md). + +## DB vs API mapping + +> **Hardstop:** never bypass [\`lib/task-status.ts\`](../../lib/task-status.ts). + +The database stores enums in \`UPPER_SNAKE\` (\`TO_DO\`, \`IN_PROGRESS\`, \`IN_SPRINT\`, …) because Prisma + PostgreSQL prefer that convention. The REST API exposes them in \`lowercase\` (\`todo\`, \`in_progress\`, \`in_sprint\`, …) because that's the convention HTTP consumers expect. + +The two are mapped **only** through the helpers in [\`lib/task-status.ts\`](../../lib/task-status.ts): + +\`\`\`ts +taskStatusToApi(status) // DB → API +taskStatusFromApi(input) // API → DB (returns null on bad input) +storyStatusToApi(status) +storyStatusFromApi(input) +pbiStatusToApi(status) +pbiStatusFromApi(input) +sprintStatusToApi(status) +sprintStatusFromApi(input) +sprintRunStatusToApi(status) +sprintRunStatusFromApi(input) +\`\`\` + +Bad input on the inbound side (\`*FromApi\`) returns \`null\` — the route handler converts that to a \`422\` Zod-style error. See [\`docs/adr/0004-status-enum-mapping.md\`](../adr/0004-status-enum-mapping.md) for the rationale. + +## What's next + +→ [03 — Git Workflow](./03-git-workflow.md) covers branching, commits, and the cost-driven PR rules. +`, + }, + { + slug: ['03-git-workflow'] as const, + title: 'Git Workflow', + description: 'The Scrum4Me git workflow is shaped by two pressures that don\'t usually appear together:', + filePath: 'docs/manual/03-git-workflow.md', + markdown: `# 03 — Git Workflow + +The Scrum4Me git workflow is shaped by two pressures that don't usually appear together: + +1. An **AI agent** that can produce many commits per hour without human review, +2. A **Vercel Hobby plan** that meters preview deployments and bills for them. + +These two together drive a workflow that looks unusual compared to "feature-branch + PR-per-story". This chapter explains the *why*; the authoritative *how* lives in the runbooks linked at the bottom. + +## The five guiding rules + +### 1. One branch per milestone, not per story + +A milestone (e.g. \`M10-qr-login\`) groups multiple stories that ship together. The agent runs through them on a single branch named \`feat/M{N}-{slug}\` (or \`feat/ST-XXX-{slug}\` for one-off stories without a milestone). All commits accumulate on that branch. + +> **Why?** Every push to a feature branch triggers a Vercel preview build. Pushing per story would multiply the build cost without producing more reviewable units of work — the user reviews the milestone, not the story. + +See [\`docs/adr/0003-one-branch-per-milestone.md\`](../adr/0003-one-branch-per-milestone.md) for the full rationale. + +### 2. Commit per layer, not per task + +A single task can touch the database, the API, and the UI. Each of those layers gets its own commit. The pattern: + +\`\`\` +feat(ST-XXX): add field X to Prisma schema # DB +feat(ST-XXX): add Y endpoint accepting X # API +feat(ST-XXX): wire X into the editor component # UI +chore(ST-XXX): configure sharp for X processing # config +docs(ST-XXX): document the X feature # docs +\`\`\` + +> **Why?** Reviewers and \`git bisect\` both benefit when one commit can be reverted without touching unrelated layers. A \`feat: add profile system\` mega-commit is an antipattern. + +### 3. Push only after the user has tested + +Commits accumulate **locally** until the milestone is functionally complete and the user has confirmed it works. Then — and only then — \`git push\` and \`gh pr create\`. + +> **Why?** Same cost reason as rule 1. Mid-milestone "save points" should be local tags or \`git stash\`, not pushes. Some exceptions exist (planning-only PRs, emergency hotfixes); they're enumerated in [\`branch-and-commit.md\`](../runbooks/branch-and-commit.md#uitzonderingen-op-de-push-regel). + +### 4. One PR per batch → one preview build + +When the worker runs through a queue of jobs, the entire run produces **one** PR with one commit per task. No interim pushes, no force-pushes to clean up history, no PR-per-story splits. + +The end-to-end verification — that one batch produces exactly one Vercel deployment — is in [\`branch-and-commit.md\`](../runbooks/branch-and-commit.md) (see the *End-to-end verificatie* section). + +### 5. Auto-PR flow at the end + +Once a story reaches \`DONE\`, the auto-PR flow takes over: it pushes the branch, opens a PR, waits for the scope to be complete, waits for checks, and merges. The contract for "scope complete" and the path-filter / label rules that decide whether a deploy actually runs are split between two runbooks: + +- **End-to-end pipeline**: [\`docs/runbooks/auto-pr-flow.md\`](../runbooks/auto-pr-flow.md) +- **Selective deploy controls** (\`skip-deploy\` label, path-filter for \`app/\`/\`components/\`/\`lib/\`): [\`docs/runbooks/deploy-control.md\`](../runbooks/deploy-control.md) + +## Commit message format + +\`\`\` +(ST-XXX): short description +\`\`\` + +Where \`\` is one of \`feat\`, \`fix\`, \`chore\`, \`docs\`. The story code in parentheses links the commit back to the Scrum4Me MCP entity. + +For PBI-level work (no single story), use the PBI code: \`docs(PBI-58): scaffold developer manual\`. + +## Merge conflicts + +| Scenario | Conflict? | Mitigation | +|---|---|---| +| Multiple tasks on the same batch branch | No — they stack linearly on one branch | None needed | +| Two parallel batches touching the same files | Yes, possible | Serialise batches via the MCP \`get_claude_context\` flow (one story at a time per agent), or rebase before push | +| Long-lived branch drifting from \`main\` | Yes, possible | \`git fetch origin main && git rebase origin/main\` before \`gh pr create\` | + +\`git push --force\` to "wipe" earlier preview builds is forbidden — it costs the same build again on recreation, defeating the purpose of the cost-control rules. + +## When **not** to follow the strict rules + +When the Vercel account moves to Pro (or another billing tier without per-build cost), this workflow can revert to the more conventional "branch + PR per story". When that happens, update the rule in [\`branch-and-commit.md\`](../runbooks/branch-and-commit.md) and log the change in [\`docs/decisions/agent-instructions-history.md\`](../decisions/agent-instructions-history.md). + +## Deep links + +| Topic | Authoritative source | +|---|---| +| Branch & commit rules (full normative spec) | [\`docs/runbooks/branch-and-commit.md\`](../runbooks/branch-and-commit.md) | +| Auto-PR flow (story-DONE → merged-PR pipeline) | [\`docs/runbooks/auto-pr-flow.md\`](../runbooks/auto-pr-flow.md) | +| Deploy controls (labels, path-filter) | [\`docs/runbooks/deploy-control.md\`](../runbooks/deploy-control.md) | +| Vercel deployment specifics | [\`docs/runbooks/deploy-vercel.md\`](../runbooks/deploy-vercel.md) | +| Decision rationale (one-branch-per-milestone) | [\`docs/adr/0003-one-branch-per-milestone.md\`](../adr/0003-one-branch-per-milestone.md) | +| Worker idempotency & job-status protocol | [\`docs/runbooks/worker-idempotency.md\`](../runbooks/worker-idempotency.md) | + +## What's next + +→ [04 — MCP Integration](./04-mcp-integration.md) covers how the Claude agent drives this workflow from the queue side. +`, + }, + { + slug: ['04-mcp-integration'] as const, + title: 'MCP Integration', + description: 'Scrum4Me exposes its REST API as native Claude Code tools through a dedicated **MCP server** living in [`madhura68/scrum4me-mcp`](https://github.com/madhura68/scrum4me-mcp). Schemas are shared via a git submodule (`vendor/scrum4me`) so there\'s exactly one definition of every type. From the agent\'s perspective, Scrum4Me looks like a set of native tools prefixed `mcp__scrum4me__*`.', + filePath: 'docs/manual/04-mcp-integration.md', + markdown: `# 04 — MCP Integration + +Scrum4Me exposes its REST API as native Claude Code tools through a dedicated **MCP server** living in [\`madhura68/scrum4me-mcp\`](https://github.com/madhura68/scrum4me-mcp). Schemas are shared via a git submodule (\`vendor/scrum4me\`) so there's exactly one definition of every type. From the agent's perspective, Scrum4Me looks like a set of native tools prefixed \`mcp__scrum4me__*\`. + +This chapter is the **onboarding tour**. The full tool reference (all 18 tools, their parameters, and edge cases) is in [\`docs/runbooks/mcp-integration.md\`](../runbooks/mcp-integration.md). + +## Three ways the agent works + +| Mode | Triggered by | Loop | +|---|---|---| +| **Track A — MCP-driven** | User says *"implement the next story"* | \`get_claude_context\` → execute tasks → \`update_task_status\` → commit per layer → repeat until queue empty → push + PR | +| **Track B — Manual** | User describes a one-off change in chat | Read pattern + styling → edit → verify → wait for \`commit it\` → commit | +| **Worker — Queue-driven** | Background worker container running on a Mac/NAS | \`wait_for_job\` (blocks ≤600s) → switch on \`kind\` → execute → \`update_job_status\` → loop forever | + +CLAUDE.md describes Track A and Track B; this manual focuses on the **Worker** mode because it's the most novel and the most likely to surprise a new contributor reading server logs. + +## A typical Track A run + +\`\`\`mermaid +sequenceDiagram + participant U as User + participant C as Claude + participant M as MCP server + participant DB as Postgres + + U->>C: "implement the next story" + C->>M: get_claude_context(product_id) + M->>DB: SELECT product, sprint, next story, tasks + M-->>C: { story, tasks[], pbi, sprint } + loop per task in sort_order + C->>M: update_task_status(task_id, 'in_progress') + C->>C: read pattern + styling, edit files + C->>M: log_implementation(story_id, content) + C->>M: update_task_status(task_id, 'review') + C->>M: log_test_result(story_id, 'PASSED') + C->>M: update_task_status(task_id, 'done') + end + C->>U: "milestone ready for your test" + U->>C: "looks good, push it" + C->>C: git push + gh pr create +\`\`\` + +The contract every step relies on: + +- All inputs are **lowercase API enums** (\`'in_progress'\`, never \`'IN_PROGRESS'\`); the MCP server applies [\`lib/task-status.ts\`](../../lib/task-status.ts) under the hood. +- Status writes are **forbidden for demo accounts** — they return \`403\`. See [02 — Statuses](./02-statuses-and-transitions.md#db-vs-api-mapping) and [\`docs/adr/0006-demo-user-three-layer-policy.md\`](../adr/0006-demo-user-three-layer-policy.md). +- Bearer tokens are bound to a product. \`list_products\` returns only what the token can see; \`get_claude_context\` is product-scoped. + +## Idea jobs vs task implementation + +The worker \`wait_for_job\` returns a payload with a \`kind\` discriminator. The agent must switch on it: + +| \`kind\` | Behaviour | +|---|---| +| \`TASK_IMPLEMENTATION\` | Default. Execute the \`implementation_plan\`, follow the [git workflow](./03-git-workflow.md), end with \`update_job_status('done')\`. | +| \`IDEA_GRILL\` | Read embedded \`prompt_text\` + existing \`idea.grill_md\`. Iterate with \`ask_user_question\` / \`get_question_answer\`. End with \`update_idea_grill_md(markdown)\`. | +| \`IDEA_MAKE_PLAN\` | Read \`prompt_text\` + \`idea.grill_md\`. **Do not ask questions** — single-pass output in strict YAML-frontmatter. End with \`update_idea_plan_md(markdown)\`. Server-side parser may reject → \`PLAN_FAILED\`. | +| \`PLAN_CHAT\` | Conversational refinement loop on an existing plan (M12+). | +| \`SPRINT_IMPLEMENTATION\` | Sprint-level run that cascades through every task; \`update_task_status\` calls must include the \`sprint_run_id\`. | + +For the full Idea state machine (DRAFT → GRILLING → … → PLANNED) see [02 — Statuses & Transitions § Idea](./02-statuses-and-transitions.md#idea). + +## The Q&A channel + +When Claude needs a human decision mid-run, it doesn't block silently — it posts a question through the MCP and either polls or returns control: + +\`\`\`mermaid +sequenceDiagram + participant C as Claude + participant M as MCP + participant DB as Postgres + participant U as User (NavBar bell) + C->>M: ask_user_question({ story_id, question, wait_seconds: 600 }) + M->>DB: INSERT user_question; NOTIFY user_question_created + DB-->>U: SSE event → bell pulses + U->>M: POST /api/questions/:id/answer + M->>DB: UPDATE user_question; NOTIFY user_question_answered + DB-->>C: ask_user_question returns { answer } + C->>C: continue execution +\`\`\` + +Key facts: + +- \`wait_seconds\` is capped at 600. If the user doesn't answer in time, \`ask_user_question\` returns with status \`pending\`; Claude can resume later via \`get_question_answer(question_id)\`. +- Idea questions (\`{ idea_id }\` instead of \`{ story_id }\`) are **user-private** — they bypass \`productAccessFilter\`, so collaborators don't see them. +- A question can be cancelled by the asker via \`cancel_question\`. + +The persistent design (table + \`LISTEN/NOTIFY\`) is documented in [\`docs/architecture/claude-question-channel.md\`](../architecture/claude-question-channel.md). + +## The worker's pre-flight quota check + +The worker doesn't blindly call \`wait_for_job\`. Each iteration it first checks Anthropic API quota via \`bin/worker-quota-probe.sh\` so it doesn't burn a 10-minute block on a queue it can't actually process. The full algorithm — settings, \`worker_heartbeat\` SSE event, sleep-until-reset — is in [\`docs/runbooks/mcp-integration.md\`](../runbooks/mcp-integration.md#pre-flight-quota-check-m13). The Docker chapter ([05](./05-docker.md#quota-probe)) shows how to test it locally. + +## Schema-drift watchdog + +If Scrum4Me's Prisma schema changes but \`scrum4me-mcp\` isn't synced, the MCP server will fail at runtime — not at deploy. To prevent that, a remote agent runs every Monday at 08:00 Amsterdam time, syncs \`vendor/scrum4me\`, and runs \`prisma:generate\` + \`tsc --noEmit\` in \`scrum4me-mcp\`. Drift reports must be resolved **before** any Scrum4Me PR with schema changes can merge. See [\`docs/runbooks/mcp-integration.md\`](../runbooks/mcp-integration.md#schema-drift-bewaking). + +## Deep links + +| Topic | Authoritative source | +|---|---| +| Tool reference (all 18 tools) | [\`docs/runbooks/mcp-integration.md\`](../runbooks/mcp-integration.md) | +| Worker idempotency & job-status protocol | [\`docs/runbooks/worker-idempotency.md\`](../runbooks/worker-idempotency.md) | +| Q&A channel architecture (table + LISTEN/NOTIFY) | [\`docs/architecture/claude-question-channel.md\`](../architecture/claude-question-channel.md) | +| Idea-laag plan & prompts | [\`docs/plans/M12-ideas.md\`](../plans/M12-ideas.md) | +| Sprint execution modes (PER_TASK vs SPRINT_BATCH) | [\`docs/architecture/sprint-execution-modes.md\`](../architecture/sprint-execution-modes.md) | +| Realtime NOTIFY payload contract | [\`docs/patterns/realtime-notify-payload.md\`](../patterns/realtime-notify-payload.md) | +| Demo-user write protection | [\`docs/adr/0006-demo-user-three-layer-policy.md\`](../adr/0006-demo-user-three-layer-policy.md) | + +## What's next + +→ [05 — Docker](./05-docker.md) covers how the worker container is run, debugged, and operated. +`, + }, + { + slug: ['05-docker'] as const, + title: 'Docker', + description: 'This chapter is the contributor\'s tour of the Docker side of Scrum4Me. Two important up-front facts:', + filePath: 'docs/manual/05-docker.md', + markdown: `# 05 — Docker + +This chapter is the contributor's tour of the Docker side of Scrum4Me. Two important up-front facts: + +1. **The Next.js app is not containerised.** The web UI, API routes, server actions, and database connection all run on **Vercel** (serverless functions + Edge runtime). There is no \`Dockerfile\` in this repo and no \`docker-compose.yml\`. +2. **Only the worker is containerised.** The "worker" is a Claude Code agent in a long-running container that polls the Scrum4Me job queue via MCP and executes \`TASK_IMPLEMENTATION\` / \`IDEA_GRILL\` / \`IDEA_MAKE_PLAN\` / \`SPRINT_IMPLEMENTATION\` jobs. + +The container image and its supporting scripts live in a **separate repo**: [\`madhura68/scrum4me-docker\`](https://github.com/madhura68/scrum4me-docker). This manual documents the consumer side — what the worker is, how it relates to Scrum4Me, and how to diagnose issues. The container internals (Dockerfile, entrypoint, agent provisioning) are out of scope for this manual; see that repo's README. + +> **Note:** A separate sandbox repo \`scrum4me-sbx\` ([\`SC-4\`](https://github.com/madhura68/scrum4me-sbx)) exists for Docker exploration. Treat it as a scratchpad, not as the production worker. + +## Topology + +\`\`\`mermaid +flowchart LR + subgraph Vercel + App[Next.js app
+ API routes] + end + subgraph Neon + DB[(Postgres)] + end + subgraph Mac["Mac (default) / NAS (opt-in)"] + Worker[Worker container
Claude Code + MCP] + end + Worker -- MCP over HTTPS --> App + App -- Prisma --> DB + Worker -- git push --> GH[GitHub] + GH -- webhooks --> App +\`\`\` + +- The worker **never connects to the database directly**. All state changes go through MCP tools, which call the Vercel-hosted REST API, which writes to Neon via Prisma. +- The worker **does** push commits directly to GitHub. GitHub then notifies Vercel and the auto-PR flow ([03 — Git Workflow](./03-git-workflow.md)) takes over. + +## Mac vs NAS + +| Flow | When to use | Status | +|---|---|---| +| **Mac-native (arm64)** | Default for development and small teams | Active | +| **NAS** | Self-hosted always-on worker on a Synology / Asustor / similar | Opt-in, validated by historical smoke tests in [\`docs/docker-smoke/\`](../docker-smoke/) | + +The Mac flow is the default because it doesn't require dedicated hardware. The container runs natively on Apple Silicon (arm64) — no x86 emulation overhead. + +## Environment variables the worker needs + +The worker container needs **only** what's required to authenticate to MCP and push to GitHub: + +| Var | Purpose | +|---|---| +| \`SCRUM4ME_BEARER_TOKEN\` | Bearer token bound to a product. Returned by the user's API-token settings page. | +| \`SCRUM4ME_BASE_URL\` | Usually \`https://scrum4me.vercel.app\` (or the user's domain). | +| \`GITHUB_TOKEN\` | Personal access token with \`repo\` scope, used by \`git push\` and \`gh pr create\`. | +| \`ANTHROPIC_API_KEY\` | The Claude API key used by the worker process. | +| \`MIN_QUOTA_PCT\` | Optional. Worker pauses if Anthropic quota drops below this percentage. | + +> **Hardstop:** the worker does **not** need \`DATABASE_URL\`, \`SESSION_SECRET\`, or \`CRON_SECRET\`. Those belong to the Next.js app; the worker only talks to MCP. If you find yourself adding DB env vars to the worker, stop — you're solving the wrong problem. + +The full list and provisioning instructions live in the [\`scrum4me-docker\` README](https://github.com/madhura68/scrum4me-docker). **TODO:** link to specific sections of that README once it's stable. + +## What the worker loop does, on a single iteration + +\`\`\`mermaid +sequenceDiagram + participant W as Worker + participant Q as worker-quota-probe.sh + participant M as MCP server + W->>Q: probe Anthropic quota + Q-->>W: { pct, reset_at_iso } + alt pct < MIN_QUOTA_PCT + W->>M: worker_heartbeat(pct, last_quota_check_at) + W->>W: sleep until reset_at_iso (cap 1h) + else quota ok + W->>M: worker_heartbeat(pct, last_quota_check_at) + W->>M: wait_for_job (block ≤600s, claim atomically) + alt queue empty + W->>W: continue (no work, loop again) + else got job + W->>W: execute by \`kind\` + W->>M: update_job_status(done|failed) + end + end + Note over W: continue forever +\`\`\` + +The loop is described authoritatively in [\`docs/runbooks/mcp-integration.md\`](../runbooks/mcp-integration.md#batch-loop-verplichte-agent-flow) and [\`docs/runbooks/worker-idempotency.md\`](../runbooks/worker-idempotency.md). + +### Quota probe + +\`bin/worker-quota-probe.sh\` (in \`scrum4me-docker\`) makes a tiny call to the Anthropic API to read the current quota percentage and reset time. Cost: ~1 output token per probe (~12 tokens/hour at 5-minute intervals). The default \`MIN_QUOTA_PCT\` is **20%** — typically high enough on Pro/Max plans that the worker never pauses during normal day-job hours. + +### Heartbeat + +Every iteration the worker calls \`worker_heartbeat({ last_quota_pct, last_quota_check_at })\`. The MCP server emits an SSE event so the NavBar in the Next.js app shows the worker as live. A heartbeat older than 15 seconds is rendered as "offline" / "stand-by" in the UI. + +### Stale-claim recovery + +If a worker dies mid-job (process crash, container kill, network partition), its claimed job stays as \`CLAIMED\` in the database. After **30 minutes** the next \`wait_for_job\` call automatically requeues it (\`CLAIMED → QUEUED\`) before claiming a fresh one. No manual intervention is required for clean recovery. + +When you **do** need to manually requeue a job (e.g. you killed it intentionally and don't want to wait 30 min), the operator route is the admin board → "Requeue job" button. **TODO:** confirm the exact UI path; this is not yet documented in \`docs/runbooks/\`. + +## Running the worker locally + +The intended local workflow per the project's standing memory is **Mac-native Docker** (the user's \`project_docker_default_target\` memory). High-level steps (verify against the [scrum4me-docker README](https://github.com/madhura68/scrum4me-docker) for exact commands): + +1. Clone \`scrum4me-docker\` next to \`Scrum4Me/\` (so \`~/Development/Scrum4Me/scrum4me-docker/\`). +2. Provision the env vars above (typically a \`.env\` file in that repo, **not committed**). +3. \`docker build\` the image and \`docker run\` it with the env file mounted. +4. Watch container logs for the heartbeat/quota cycle. +5. Trigger a job from the UI ("Voer alle uit" on the Solo Board) and verify the worker picks it up within ~5 seconds. + +> **TODO:** once the \`scrum4me-docker\` README has stabilised, replace the bullets above with copy-paste-ready commands. Until then, defer to that repo for canonical instructions. + +## Debugging a stuck worker + +| Symptom | Likely cause | Fix | +|---|---|---| +| Worker shows offline in NavBar but container is running | \`worker_heartbeat\` not reaching MCP | Check \`SCRUM4ME_BASE_URL\` and \`SCRUM4ME_BEARER_TOKEN\`; tail container logs for HTTP errors | +| Worker logs say "stand-by" indefinitely | \`pct < MIN_QUOTA_PCT\` and reset_at not reached | Lower \`MIN_QUOTA_PCT\` for testing, or wait for the printed \`reset_at_iso\` | +| Job stuck \`CLAIMED\` for >30 min | Worker died mid-job | Wait — auto-requeue triggers on next \`wait_for_job\` | +| Worker claims job but never updates status | Crashed before \`update_job_status\`; container restarted in a loop | Check \`docker logs\`; the next \`wait_for_job\` will requeue stale claims | +| \`update_job_status\` returns \`403\` | Bearer token doesn't match \`claimed_by_token_id\` | The token was rotated mid-run; restart with fresh token | + +For deeper troubleshooting see [06 — Troubleshooting](./06-troubleshooting.md). + +## Smoke-test references + +Historical Docker smoke tests live in [\`docs/docker-smoke/\`](../docker-smoke/). They validated the worktree-isolation + branch-per-story flow when the Docker worker was first introduced. They are **historical** — don't expect them to be runnable as-is — but they're a useful reference when you want to verify the same flow on a new container image. + +## Deep links + +| Topic | Source | +|---|---| +| Container image, Dockerfile, build | [\`scrum4me-docker\` repo](https://github.com/madhura68/scrum4me-docker) | +| Worker loop & quota check | [\`docs/runbooks/mcp-integration.md\`](../runbooks/mcp-integration.md#pre-flight-quota-check-m13) | +| Worker idempotency / job-status protocol | [\`docs/runbooks/worker-idempotency.md\`](../runbooks/worker-idempotency.md) | +| Historical smoke tests | [\`docs/docker-smoke/\`](../docker-smoke/) | +| Sandbox / exploration repo | [\`scrum4me-sbx\` repo](https://github.com/madhura68/scrum4me-sbx) | + +## What's next + +→ [06 — Troubleshooting](./06-troubleshooting.md) covers error codes and recovery procedures across the full stack. +`, + }, + { + slug: ['06-troubleshooting'] as const, + title: 'Troubleshooting', + description: 'This chapter is the **first place to look** when something is wrong. Each row links to the authoritative source so you can dig deeper without losing your trail.', + filePath: 'docs/manual/06-troubleshooting.md', + markdown: `# 06 — Troubleshooting + +This chapter is the **first place to look** when something is wrong. Each row links to the authoritative source so you can dig deeper without losing your trail. + +## Error code reference + +These three HTTP status codes are non-negotiable hardstops in the API surface — they always mean the same thing across every route handler. + +| Code | Meaning | Where it comes from | +|---|---|---| +| **\`400\`** | JSON parse error | Body couldn't be parsed as JSON. Usually a malformed request from a client. | +| **\`422\`** | Zod validation error | Body parsed, but failed schema validation. Response includes the offending field path. | +| **\`403\`** | Demo-user write blocked | Authenticated user \`is_demo = true\` attempted a write. Three layers enforce this — see [\`docs/adr/0006-demo-user-three-layer-policy.md\`](../adr/0006-demo-user-three-layer-policy.md). | + +> **Hardstop:** these codes are reserved. Do not use \`400\` for validation errors or \`422\` for unauthorised access. The contract is enforced at the route-handler level — see the [Route Handler pattern](../patterns/route-handler.md). + +Other common codes: + +| Code | Meaning | +|---|---| +| \`401\` | No session / invalid bearer token | +| \`404\` | Resource not found, or token does not have access | +| \`409\` | State conflict — e.g. trying to claim a job that's already \`CLAIMED\` | +| \`429\` | Rate-limited — typically the Anthropic quota cap, not Scrum4Me itself | +| \`500\` | Unhandled server error. Always check Vercel function logs. | + +## Symptom → cause → fix + +### MCP + +| Symptom | Likely cause | Fix | +|---|---|---| +| \`mcp__scrum4me__get_claude_context\` returns \`null\` or empty story | Bearer token doesn't have access to that product | Run \`mcp__scrum4me__list_products\` to confirm scope; rotate the token if needed | +| \`mcp__scrum4me__update_task_status\` returns \`403\` | Demo user, or token mismatch in a sprint run | Check user identity; if inside a sprint run, the bearer token must match \`claimed_by_token_id\` of the parent job | +| \`mcp__scrum4me__wait_for_job\` returns nothing for the full 600s block | Queue is genuinely empty | This is normal — loop and call again. See [\`runbooks/mcp-integration.md\`](../runbooks/mcp-integration.md#batch-loop-verplichte-agent-flow) | +| Job stays \`CLAIMED\` for >30 minutes | Worker died mid-job | Auto-requeue triggers on next \`wait_for_job\`; no manual action needed | +| \`update_idea_plan_md\` causes idea to flip to \`PLAN_FAILED\` | \`parsePlanMd\` server-side rejected the YAML-frontmatter | Inspect \`IdeaLog{JOB_EVENT, errors}\` for the parse error; re-run \`IDEA_MAKE_PLAN\` after fixing the prompt | + +### Statuses & data integrity + +| Symptom | Likely cause | Fix | +|---|---|---| +| Status displayed differently in DB vs UI | Some code path bypassed \`lib/task-status.ts\` | Grep the codebase for direct enum string usage; force everything through the mappers. See [\`adr/0004-status-enum-mapping.md\`](../adr/0004-status-enum-mapping.md) | +| Story stuck \`IN_SPRINT\` when all tasks are \`DONE\` | Auto-promotion not triggered | Check the most recent \`update_task_status\` call — it may have failed silently. Re-issue with the correct task | +| PBI not auto-promoting to \`DONE\` | Not all child stories are \`DONE\` yet | List stories under the PBI; one is probably still \`OPEN\` or \`IN_SPRINT\` | +| \`422\` from \`create_pbi\` / \`create_story\` / \`create_task\` | Zod validation failed (length cap, missing required field) | Response body includes field path — fix and retry | +| \`IdeaStatus\` stays \`GRILLING\` long after the worker stopped | The job ended without calling \`update_idea_grill_md\` | Check the worker logs for an exception; manually requeue or mark \`GRILL_FAILED\` to allow retry | + +### Git & deploy + +| Symptom | Likely cause | Fix | +|---|---|---| +| Unexpected Vercel preview build appeared mid-batch | An interim push happened that shouldn't have | Inspect \`git log --all --graph\` for the offending push; review [\`runbooks/branch-and-commit.md\`](../runbooks/branch-and-commit.md) | +| PR has multiple Vercel deployments for the same commit range | Force-push, or push-then-revert | Don't force-push. If genuinely needed, document in the PR description | +| Auto-PR didn't open after story \`DONE\` | Story not actually \`DONE\`, or auto-PR pre-conditions unmet | Walk through [\`runbooks/auto-pr-flow.md\`](../runbooks/auto-pr-flow.md); typically a missing \`update_task_status('done')\` for the last task | +| Vercel skipped the deploy entirely | \`skip-deploy\` label or path-filter excluded the changed paths | See [\`runbooks/deploy-control.md\`](../runbooks/deploy-control.md) for the rules | +| Merge conflict between two parallel batches | Two branches touched the same files | Serialise: merge the first PR before pushing the second. Then \`git fetch origin main && git rebase origin/main\` | + +### Realtime + +| Symptom | Likely cause | Fix | +|---|---|---| +| Solo Board doesn't update when status changes | SSE connection dropped, or NOTIFY payload missing fields | Reload the page; if it persists, check \`DIRECT_URL\` (LISTEN/NOTIFY needs the pooler-bypass URL). See [\`patterns/realtime-notify-payload.md\`](../patterns/realtime-notify-payload.md) | +| NavBar bell doesn't pulse on new question | SSE/event channel mismatched, or payload missing required fields | Confirm the question was actually inserted (\`mcp__scrum4me__list_open_questions\`); inspect the Network tab for the SSE connection | +| Worker shows offline despite a running container | \`worker_heartbeat\` not reaching MCP | Verify \`SCRUM4ME_BASE_URL\` and bearer token; tail container logs | + +### Auth & sessions + +| Symptom | Likely cause | Fix | +|---|---|---| +| Login redirects in a loop | Session cookie not set; usually \`SESSION_SECRET\` mismatch between deployments | Check Vercel env vars for \`SESSION_SECRET\` (must be ≥32 chars); see [\`patterns/iron-session.md\`](../patterns/iron-session.md) | +| All write buttons disabled with "Niet beschikbaar in demo-modus" tooltip | You're logged in as the demo user | Log out and log in with a real account | +| \`403\` on a route that should be allowed | Proxy or server-action layer rejected the request | Walk through the three layers in [\`adr/0006-demo-user-three-layer-policy.md\`](../adr/0006-demo-user-three-layer-policy.md); each can independently say "no" | + +### Build & dev-server + +| Symptom | Likely cause | Fix | +|---|---|---| +| \`npm run build\` fails with \`Cannot find module '@/...'\` | TypeScript path alias mismatch | Check \`tsconfig.json\` \`paths\`; rerun \`npm run prebuild\` if codegen is stale | +| Mermaid diagram renders as plain text in the in-app \`/manual\` viewer | \`MermaidBlock\` not picking up \`language-mermaid\` | See [04 — MCP Integration](./04-mcp-integration.md) won't help here — open \`app/(app)/manual/_components/mermaid-block.tsx\` and confirm the dynamic import is \`ssr: false\` | +| "Server-only" import error in browser | A \`*-server.ts\` module was imported into a client component | Refactor — split server logic out, or use a server action. Hardstop in [\`CLAUDE.md\`](../../CLAUDE.md#hardstop-regels) | +| \`npm run dev\` shows hydration mismatch | Server and client render diverge — usually time-based or random values | Wrap in \`useEffect\` for client-only state, or pass server time as a prop | + +## When in doubt + +1. **Read the runbook.** Each runbook in [\`docs/runbooks/\`](../runbooks/) starts with a \`when_to_read\` field — match the situation. +2. **Check the ADRs.** The ADR index in [\`docs/INDEX.md\`](../INDEX.md) lists the rationale for every cross-cutting decision. If your fix would contradict an ADR, talk to a maintainer first. +3. **Read the agent-flow pitfalls log.** [\`docs/runbooks/agent-flow-pitfalls.md\`](../runbooks/agent-flow-pitfalls.md) is a living list of issues found during agent runs and how they were resolved. +4. **Look at recent commits.** \`git log --oneline --since='7 days ago'\` often reveals the very change that broke whatever you're debugging. + +## Escalation + +If after the steps above the issue is still unresolved: + +- **AI agent / MCP issues** → file in the [\`scrum4me-mcp\` repo](https://github.com/madhura68/scrum4me-mcp). +- **Worker container issues** → file in the [\`scrum4me-docker\` repo](https://github.com/madhura68/scrum4me-docker). +- **App / data / status issues** → file in the [\`Scrum4Me\` repo](https://github.com/madhura68/Scrum4Me). + +## What's next + +You've reached the end of the manual. Bookmark this troubleshooting chapter — it's the most-revisited page once you're past onboarding. + +Back to [index](./index.md). +`, + }, +] as const; diff --git a/scripts/build-manual.mjs b/scripts/build-manual.mjs new file mode 100644 index 0000000..99abf5f --- /dev/null +++ b/scripts/build-manual.mjs @@ -0,0 +1,159 @@ +#!/usr/bin/env node +// Generate lib/manual.generated.ts — a typed TOC of the docs/manual/ chapters. +// Walks docs/manual/, parses front-matter, extracts title and description, and +// emits a single TS file consumed by the in-app /manual route. +// +// Usage: `npm run manual:build` (also chained into `prebuild`). +// +// Pure Node 20 — no external deps. Mirrors scripts/generate-docs-index.mjs. + +import { readdir, readFile, writeFile } from 'node:fs/promises'; +import { join, relative, basename, sep } from 'node:path'; +import { fileURLToPath } from 'node:url'; + +const SCRIPT_DIR = fileURLToPath(new URL('.', import.meta.url)); +const REPO_ROOT = join(SCRIPT_DIR, '..'); +const MANUAL_DIR = join(REPO_ROOT, 'docs', 'manual'); +const OUT_PATH = join(REPO_ROOT, 'lib', 'manual.generated.ts'); + +async function walk(dir) { + const entries = await readdir(dir, { withFileTypes: true }); + const files = []; + for (const e of entries) { + const full = join(dir, e.name); + if (e.isDirectory()) { + files.push(...(await walk(full))); + } else if (e.isFile() && e.name.endsWith('.md')) { + files.push(full); + } + } + return files; +} + +function parseFrontMatter(content) { + if (!content.startsWith('---\n')) return { data: {}, body: content }; + const end = content.indexOf('\n---\n', 4); + if (end === -1) return { data: {}, body: content }; + const block = content.slice(4, end); + const data = {}; + for (const raw of block.split('\n')) { + const line = raw.trim(); + if (!line || line.startsWith('#')) continue; + const m = line.match(/^([A-Za-z][\w-]*)\s*:\s*(.*?)\s*$/); + if (!m) continue; + let val = m[2]; + if ( + (val.startsWith('"') && val.endsWith('"')) || + (val.startsWith("'") && val.endsWith("'")) + ) { + val = val.slice(1, -1); + } + data[m[1]] = val; + } + return { data, body: content.slice(end + 5) }; +} + +function extractFirstH1(body) { + const m = body.match(/^#\s+(.+?)\s*$/m); + return m ? m[1] : null; +} + +function extractFirstParagraph(body) { + // Skip leading H1, then take the first non-heading, non-blank block. + const lines = body.split('\n'); + let i = 0; + while (i < lines.length && (lines[i].trim() === '' || lines[i].startsWith('#'))) i++; + const para = []; + while (i < lines.length && lines[i].trim() !== '') { + if (lines[i].startsWith('>') || lines[i].startsWith('|') || lines[i].startsWith('```')) break; + para.push(lines[i]); + i++; + } + return para.join(' ').replace(/\s+/g, ' ').trim(); +} + +// docs/manual/01-overview.md → ['01-overview'] +// docs/manual/index.md → [] +function fileToSlug(rel) { + const stripped = rel.replace(/^docs\/manual\//, '').replace(/\.md$/, ''); + if (stripped === 'index') return []; + return stripped.split('/'); +} + +function escapeTs(s) { + return String(s).replace(/\\/g, '\\\\').replace(/'/g, "\\'"); +} + +function escapeBacktick(s) { + return String(s).replace(/\\/g, '\\\\').replace(/`/g, '\\`').replace(/\$\{/g, '\\${'); +} + +function stripFrontMatter(content) { + if (!content.startsWith('---\n')) return content; + const end = content.indexOf('\n---\n', 4); + if (end === -1) return content; + return content.slice(end + 5).replace(/^\s*\n/, ''); +} + +async function main() { + const files = (await walk(MANUAL_DIR)).sort(); + const entries = []; + + for (const full of files) { + const rel = relative(REPO_ROOT, full).split(sep).join('/'); + const content = await readFile(full, 'utf8'); + const { data, body } = parseFrontMatter(content); + const slug = fileToSlug(rel); + const title = data.title || extractFirstH1(body) || basename(full, '.md'); + const description = extractFirstParagraph(body) || ''; + const markdown = stripFrontMatter(content); + entries.push({ + slug, + title, + description, + filePath: rel, + markdown, + }); + } + + // Sort: index first, then by filename so numeric prefixes drive order. + entries.sort((a, b) => { + if (a.slug.length === 0) return -1; + if (b.slug.length === 0) return 1; + return a.filePath.localeCompare(b.filePath); + }); + + const lines = []; + lines.push('// AUTO-GENERATED by scripts/build-manual.mjs. Do not edit by hand.'); + lines.push('// Run `npm run manual:build` to regenerate.'); + lines.push(''); + lines.push('export type ManualEntry = {'); + lines.push(' slug: readonly string[]'); + lines.push(' title: string'); + lines.push(' description: string'); + lines.push(' filePath: string'); + lines.push(' markdown: string'); + lines.push('}'); + lines.push(''); + lines.push('export const MANUAL_TOC: readonly ManualEntry[] = ['); + for (const e of entries) { + const slugLit = '[' + e.slug.map((s) => `'${escapeTs(s)}'`).join(', ') + '] as const'; + lines.push(' {'); + lines.push(` slug: ${slugLit},`); + lines.push(` title: '${escapeTs(e.title)}',`); + lines.push(` description: '${escapeTs(e.description)}',`); + lines.push(` filePath: '${escapeTs(e.filePath)}',`); + lines.push(` markdown: \`${escapeBacktick(e.markdown)}\`,`); + lines.push(' },'); + } + lines.push('] as const;'); + lines.push(''); + + await writeFile(OUT_PATH, lines.join('\n'), 'utf8'); + console.log(`Wrote ${relative(REPO_ROOT, OUT_PATH)} (${entries.length} chapters)`); +} + +main().catch((err) => { + console.error(err); + process.exit(1); +});