The repo had no .gitattributes at all, so nothing pinned line endings —
`git ls-files --eol backend/docker-entrypoint.sh` showed an empty attr/.
Git for Windows installs with core.autocrlf=true, which rewrites the
entrypoint to CRLF on checkout. The image then ships a script whose
shebang is "#!/bin/sh\r" and the container dies at startup with
exec /usr/local/bin/docker-entrypoint.sh: no such file or directory
naming the file it just copied in, which reads like the COPY failed.
Verified by building an image from a deliberately CRLF-ified copy of the
entrypoint: it reproduces that exact error, and passes with the sed.
Pin *.sh (and the Dockerfiles) to LF, and strip CR in the image before
chmod as well — .gitattributes only helps fresh clones, and a Windows
contributor who cloned before this commit still has CRLF on disk.
Renormalizing changes no tracked file today; this is purely a guard.
The arm64/Apple Silicon failure that prompted this is already fixed by
6127a0a (Turbopack has no musl/arm64 binding; the build uses webpack).
Confirmed by building both images on an arm64 Mac. Release publishes
linux/amd64 + linux/arm64, there are no bind mounts, no platform: keys
and no host.docker.internal, so the remaining cross-platform hazard was
just the line endings.
Also tighten .dockerignore: backend was shipping docker-compose.tunnel
.yml, fly.toml, railway.json, render.yaml, .env.example and
drizzle.config.ts into the build context; frontend was shipping
tsconfig.tsbuildinfo.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
`docker compose up` now works with no .env editing. A new entrypoint
(docker-entrypoint.sh) generates any missing secret (BETTER_AUTH_SECRET,
AI_CREDENTIALS_KEY) on first start and persists it to the temetro_secrets
volume, so values stay stable across restarts (rotating them would log users
out / invalidate stored AI keys). Real values passed via .env/compose still win.
This also fixes the boot failure where the compose backend ran with
NODE_ENV=production but never passed AI_CREDENTIALS_KEY through, tripping the
production guard. The secret is now an optional pass-through and BETTER_AUTH_SECRET
no longer hard-fails when unset.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
The build stage ran `npm ci`, which tried to compile better-sqlite3 — a
dev-only transitive dependency of @better-auth/cli — and failed in Alpine for
lack of Python/node-gyp. The build step is just `tsc` (no native binaries
needed) and better-sqlite3 is never used at runtime (the prod stage omits dev
deps), so install dev deps with --ignore-scripts.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Implements the first temetro backend: an Express 5 API on Postgres via
Drizzle ORM, with authentication and multi-tenant clinics powered by
Better Auth.
- Auth: email/password with required email verification, password reset,
rate limiting, CSRF/trusted-origins, secure cookies, session audit hook.
- Organizations (clinics) with RBAC (owner/admin/member/viewer) and an
extended `patient` permission set; member invitations by email.
- Org-scoped patient records mirroring the frontend Patient shape, with
CRUD endpoints gated by permission (read/write/delete).
- Email helper logs links to the console when SMTP is unset (zero-setup
local dev); Dockerfile + docker-compose (db + backend + frontend) with
migrations applied on startup and a configurable Postgres host port.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>