The invite gate was unreachable. PIG shares its identity provider with another
application, and self-registration there is deliberately switched off — so
somebody with a personal address and a valid invite code could never obtain a
token, and therefore could never reach the endpoint that accepts the code. The
gate was real and nothing could ever arrive at it.
Opening self-registration on the provider would have opened it for the
neighbouring application too, which is precisely why it was closed. So PIG now
mints the account itself through the provider's admin API, and only after the
invite validates. The provider stays shut; the invite becomes the actual gate.
Order is deliberate: validate the invite, create the auth account, create the
profile, consume the invite. If the profile write fails the auth account is
deleted again — otherwise someone could sign in with no profile and no way to
obtain one, because their invite would look spent.
An administrator's address does NOT bypass this. The bypass in /api/signup
exists to bootstrap the first admin from an account that already exists; here
an account is created from nothing, and an ungated version of that is simply
an open registration endpoint.
Registration signs the person in on success rather than returning them to a
login form to retype the password they entered ten seconds earlier. An address
that already exists in the provider but has no PIG profile is detected and
pointed at sign-in, since /api/signup handles that case properly.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
The server mounted static files at /assets only, so every top-level file fell
through to the SPA catch-all. og.png, apple-touch-icon.png, icon-192.png and
manifest.webmanifest each returned `200 text/html` containing the app shell.
This is a nearly invisible failure. The app works. The tab shows an icon,
because browsers cache the SVG. Nothing errors anywhere. But a link shared to
iMessage, Slack or X fetches og.png, receives HTML, and renders a card with no
image — which is the entire point of having made one.
Now the whole dist directory is served, with /api excluded so routes are never
answered from disk, and the SPA fallback still catching client-side routes that
have no file behind them.
Found by fetching the asset from an outside host instead of trusting that
adding the file was enough. Verified: og.png is image/png at 53KB, the icons
and manifest carry their real types, /margin and /capacity still receive the
shell, and the API is unaffected.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
z.coerce.boolean() calls Boolean(value), so the string "false" is true. So are
"0", "no" and "off". Every feature flag set to false was silently on.
Caught by reading a startup warning that should not have been there: the
deployment logged "PRIME_SYNC_ENABLED is on but PRIME_API_KEY is unset" while
the .env plainly said false. Had the key been present, PIG would have started
polling a third-party API nobody asked it to poll.
Replaced with an explicit parser accepting 1/true/yes/on, treating an empty or
absent value as the default. Demonstrated both behaviours side by side before
committing.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Social and icons. A 1200x630 card, apple-touch-icon, and maskable PWA icons,
generated from an HTML template by a script so the mark, wordmark and tagline
cannot drift from the product. The apple-touch-icon referenced in index.html
was a 404 until now. Icons are drawn on an opaque plate with inset because iOS
rounds corners and Android may apply a circle — an edge-to-edge mark loses its
ears to that crop. og:image is absolute, which is the single most common
reason a card unfurls blank.
PIG_INVITE_CODE was a lie. Signup validates against the invites table, so
setting the variable only flipped a label in the UI — an operator would set it,
hand the code to a colleague, and watch them be rejected. It is now reconciled
into a real invite row at boot: setting it issues, changing it rotates and
revokes the predecessor, and removing it revokes. Verified all three, plus that
a restart with an unchanged code does not duplicate.
Two bugs found while doing that:
- `uses_remaining` was jsonb, so the SQL decrement could never have worked.
Now integer. The generated migration failed because Postgres has no implicit
jsonb->integer cast, so the USING clause is hand-written.
- Redemption keyed off `redeemedAt`, which would have made every reusable
invite single-use — a confusing way to lock a team out. Availability now
comes from `usesRemaining`, and redemption records who used it most recently
without consuming it.
Sign-in gains a password option alongside the magic link, defaulting to
password since that is the daily path. PIG stores neither; both are handled by
the identity provider and PIG only ever sees the resulting token.
autocomplete is set so password managers and iOS can fill.
Verified: full migration chain applies to a fresh Postgres, the CSP hash for
the inline theme script is unchanged by the rebuild.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Deploying and then trying to actually use it surfaced a dead end: /api/signup
was exempted from auth but never implemented, so a real person could sign in,
receive 403 needs_profile, and have nowhere to go. Authentication worked;
joining did not.
The route is mounted before the auth middleware, because requiring membership
to reach the route that grants membership is circular. It verifies the token
itself and then requires one of two things:
- A valid invite code. Stored hashed, optionally pinned to an address,
optionally expiring, consumed on redemption with the redeemer recorded.
- Presence in PIG_ADMIN_EMAILS. The bootstrap path, which exists because on a
fresh deployment nobody can issue an invite since nobody can sign in to
issue one.
The bootstrap path is narrow by construction: the address must be listed in
server-side configuration AND match the verified email claim on the token.
Admin rights are never read from the request body, so a crafted payload
cannot grant them.
Two behaviours worth noting. A row that was invited but never signed into is
claimed rather than rejected, binding it to the identity that just proved
ownership of the address. And a resubmitted form returns the existing user
instead of erroring, because a double-tap should be harmless.
The front end now treats needs_profile as a step in the flow rather than an
error, showing a team picker. Sending someone back to a login screen they have
already completed is a loop with no exit.
Also: the seed no longer creates the dev@localhost admin row under
NODE_ENV=production. It was unreachable (no auth subject, so nobody can sign
in as it), but an admin-flagged placeholder in a real deployment is a trap.
Verified: rejects a missing token, rejects an invalid body, claims a pre-existing
row, and is idempotent on resubmission.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
apps/web — React, Vite, Tailwind, shadcn-idiom components. Mobile Safari is a
first-class target, not an afterthought:
- Two navigation treatments rather than one compromise. A bottom tab bar on
phones, because the top of a large phone is out of thumb reach; a persistent
sidebar from lg upward, so an iPad in portrait gets it too.
- Safe-area insets throughout, so the tab bar clears the home indicator and the
last row of a list is actually reachable.
- Inputs are pinned to a 16px minimum, which is the correct fix for Safari
zooming on focus. user-scalable=no is not used: it breaks pinch-zoom for
everyone and recent iOS ignores it anyway.
- The pipeline board becomes a stage picker on phones. An eight-column board
scrolling horizontally on a 390px screen is technically responsive and
practically useless.
Theming: users pick an accent and the whole interface re-tints. Accent values
live once, in @pig/core, and are written onto the root element at runtime —
there is no CSS copy to drift from the TypeScript. Preferences are stored
server-side so they follow a person between laptop and phone, mirrored into
localStorage only so the pre-paint script can avoid a white flash. Status
colours stay fixed regardless of accent: if "at risk" re-tinted to whatever
someone picked, the signal would be gone.
Seed data is public research, every record carrying a confidence grade and a
source URL. No email addresses are seeded or inferred — none are published, and
guessing them from a name and a domain is unreliable and rude. Authorship is
not promoted to employment: contributors, residency participants and alumni are
recorded as what the evidence actually shows, and a name that could not be
sourced at all is listed as unresolved rather than invented.
Three defects found and fixed by actually running it rather than assuming:
1. The seed was not idempotent. onConflictDoNothing() with no target is a no-op
without a matching unique constraint, so a second run duplicated 27
contacts. There is deliberately no unique index on (account, name) — two
people at one company can share a name — so idempotency is enforced in the
seed instead of by bending the schema.
2. /capacity scrolled sideways on a phone. Grid items default to
min-width:auto and `truncate` sets nowrap, so a long title became
unshrinkable content and widened the track. Fixed with min-w-0 on every
truncating grid child.
3. The idle-capacity alert silently failed to fire at exactly 80% utilisation,
losing a float comparison against a 0.2 threshold. Moved to 0.15, which is
also a more sensible line for "worth attention".
The worked example is tuned to teach rather than to flatter: 70% sold at a 53%
markup lands at +6.7% margin with 20% still idle, so both the healthy number
and the alert are visible. Drop the sold share to 55% and the same block goes
underwater — that sensitivity is the argument for the product.
Verified in a real browser at 393px and 1440px, light and dark: zero horizontal
overflow on every route, zero console errors.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
packages/prime — a hand-written typed client, because the first-party SDK is
Python only. Deliberately narrow: PIG reads availability and nothing else, and
the key it holds should be scoped so it could not provision even if the code
tried. Rate limits are undocumented upstream, so it backs off empirically with
full jitter and honours Retry-After. Unknown fields survive in `raw` rather
than being dropped.
apps/api — Hono, with authentication and authorization kept firmly apart. A
verified JWT proves someone has an account in the identity project, which may
be shared with other applications; it does NOT prove they belong here. Access
requires a row in PIG's own users table, and a token without one gets 403
needs_profile rather than entry.
The capacity service is the business logic: availability counts sold and held
separately, so a live hold removes inventory from everyone else's availability
without inflating utilisation. Expired holds are ignored at read time, so the
numbers stay right even when the sweeper is behind. Matching treats
interconnect as a hard filter and excludes Unknown as well as Ethernet —
unverified is not the same as adequate.
apps/mcp — nine tools over stdio, so a team member drives PIG from Claude
Code, Codex, prime-agent, or a Buzz agent. It holds an API key and calls the
same HTTP API the browser does, with no database credentials, so an agent can
never reach further than the person it acts for. Results are formatted as
prose rather than raw JSON.
Theme preferences live in the database rather than localStorage, so a chosen
accent follows someone from laptop to phone. Status colours stay independent
of the accent: if "at risk" re-tinted to whatever a user picked, the signal
would be gone.
Note on the SDK import: its package exports use a `./*` wildcard whose types
entry resolves server/mcp.js to server/mcp.js.d.ts, which does not exist. The
runtime specifier must keep the .js suffix, so the types are mapped via
tsconfig paths rather than by writing an import that would fail at runtime.
Verified: all five packages typecheck; the MCP server constructs and registers
its tools.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>