Vale construir sua versão de FileChanger?

Build me a personal file conversion service in an empty repo. Requirements:

- Python 3.12, FastAPI, uv for dependencies, SQLite for job state. One process,
  no broker, no microservices, no alternative stacks.
- Never write a converter. Shell out to pandoc for markup and documents,
  LibreOffice headless for Office, ImageMagick for images, FFmpeg for media.
- POST /convert takes a file, a source and a target format and returns the bytes
  below a size threshold set in config. Above it the same route returns a job
  id, GET /jobs/{id} reports its state and GET /jobs/{id}/result streams the
  file. One background worker thread is enough, do not add Celery.
- Build the format matrix at startup from `pandoc --list-input-formats`,
  `--list-output-formats`, `ffmpeg -formats` and `magick -list format` rather
  than hardcoding it, and serve it at GET /formats.
- Treat every upload as hostile: convert in a temp dir with a wall-clock
  timeout, an output size cap and no network, then delete the inputs whether it
  worked or not. Log the failing command and its stderr, never return either.
- Ship an MCP server over stdio using the official Python SDK, exposing convert
  and formats as tools so agents can convert without going through HTTP.
- Authenticate with API keys stored hashed in SQLite. Show the plaintext once at
  creation and support revocation.
- One HTML page, no JS framework: pick a file, pick a target from /formats,
  download the result.
- One Dockerfile installing pandoc, typst, libreoffice-core, imagemagick and
  ffmpeg, a compose file with a volume for the database, config in .env and a
  committed .env.example.
- Out of scope: accounts, billing, metering, quotas, telemetry, multi-tenancy
  and any hosted control plane.
- Test one round trip per engine (Markdown to PDF, PNG to WebP, WAV to MP3), an
  oversized upload and a conversion that hits the timeout. README covers setup,
  formats, security assumptions and where data lives. Finish by running the
  tests and listing the commands used.