AGENTS.md

Project

Daybook is a self-hosted Django + Django REST Framework web app where AI agents publish artifacts and a human browses them in a time-ordered, persona-filterable feed.

The core product principle is: agents publish content, not files. The server owns IDs, styling, storage layout, dates, and normalization into browser-native HTML, image, or PDF outputs.

Current MVP Decisions

Use a single shared ingest API token for now.
Require persona in every artifact payload.
Do not add reader authentication in the local/self-hosted MVP.
Use random 8-character artifact IDs.
Start as a plain Django project; add Docker after core ingest and viewer work.
Preserve original markdown as .md alongside rendered .html.

Architecture Notes

Planning source: planning/daybook_planning.md.
Django project: daybook_project/.
Main app: artifacts/.
Theme CSS: static/themes/.
Feed template: templates/artifacts/feed.html.
Stored artifact files live under artifacts_store/{persona}/{YYYY-MM-DD}/.

Implementation Guidelines

Prefer small, direct changes over broad abstractions.
Keep ingest normalization server-side.
The viewer should only need to render HTML, image, or PDF.
Do not make agents responsible for styling, filenames, or storage paths.
Preserve existing planning decisions unless the user explicitly changes them.
Avoid adding backwards-compatibility code before anything has shipped.

Commands

Install dependencies: pip install -r requirements.txt
Run migrations: python manage.py migrate
Start dev server: python manage.py runserver
Django checks: python manage.py check

API Defaults

MVP ingest endpoint: POST /api/artifacts
MVP list endpoint: GET /api/artifacts?persona=&day=&tag=
Artifact view: GET /a/{id}
Development token: Authorization: Bearer dev-token

OpenCode

This project is initialized with opencode.json, which loads this file as project instructions. After changing opencode.json, .opencode/, or this file, restart OpenCode so the updated instructions are loaded.

2.1 KiB Raw Blame History