memgineering 0.17.0 → 0.18.1

package/CHANGELOG.md

@@ -11,6 +11,54 @@ language the reader wants. The bilingual rule the monorepo applies to
 
 ## [Unreleased]
 
+## [0.18.1] — 2026-08-30
+
+### Fixed
+
+- **Choosing "in an account" now actually connects you to the brain it made.**
+  0.18.0 created the hosted brain on the server and stopped there, so the
+  command right after a finished setup could answer "no brain is connected"
+  while the brain sat there, real and unreachable. Setup records which brain
+  this machine reads, the way `push` and `use` already did.
+
+## [0.18.0] — 2026-08-30
+
+### Added
+
+- **Setting up happens on a screen now.** `memgineering setup --web` opens the
+  wizard at memgineering.com/setup — sign in, choose where the memory lives,
+  name a brain or point at a folder, confirm — and this machine applies it when
+  you finish. The page is part of the site, so it looks like the product and
+  signs you in the way the site does.
+- **Running `memgineering` on its own opens that screen**, when you are on a
+  terminal and setup has not been done. Nothing to copy, nothing to paste.
+- **Existing notes can come with you.** If you already keep markdown on this
+  machine, the screen offers to carry that folder up to the new brain. Folder
+  names are sent only after the screen asks for them, and never the contents.
+
+### Changed
+
+- **`setup --web` returns instead of blocking.** With nobody watching a
+  terminal it leaves the waiting to a background process, so an agent's shell
+  call cannot time out while somebody reads the screen. `--wait` restores the
+  old blocking behaviour for scripts that want it.
+- **One sign-in for the whole install.** The screen uses your memgineering.com
+  session, so a person already signed in is not asked again — and there is no
+  separate device code to approve on top of it.
+- **The setup screen no longer runs on your machine.** The 127.0.0.1 page and
+  its local server are gone; `setup --human` and `setup --agent` remain for
+  machines with no browser or when you would rather the agent decided.
+- **Setup stops claiming you must restart.** Commands and recall work
+  immediately; only the guidance files setup writes wait for your next
+  conversation, and that is what it now says.
+
+### Agent guidance
+
+- The install banner and `memgineering-setup` changed: `setup --web` is the
+  default path, it returns straight away, and the pairing code it prints is
+  meant to be shown to the user — the screen asks them to compare it. Restart
+  your agent session after upgrading so the new guidance is loaded.
+
 ## [0.17.0] — 2026-08-30
 
 ### Added

package/assets/MEMGINEERING.md

@@ -2,7 +2,7 @@
 name: memgineering
 description: Use whenever the user refers to something they told you before, asks what was decided, tells you something worth keeping, or settles something that should hold next time. The memory lives in their own folder and outlives this session; check it before answering from guesswork, and write to it when you learn something durable.
 type: skill
-version: 0.17.0
+version: 0.18.1
 ---
 
 # memgineering
@@ -87,4 +87,4 @@ Tools without one (e.g. Antigravity): READ `<tool-home>/skills/memgineering-<nam
 when its topic comes up.
 
 If `memgineering: command not found`, install with `npm i -g memgineering`, then
-`memgineering setup`.
+`memgineering setup --web`.

package/assets/memgineering-setup/SKILL.md

@@ -29,6 +29,34 @@ that can read it.
 
 ## 1. Register with the agents
 
+**Default: open the screen.** `memgineering setup --web` starts a setup session,
+prints a short pairing code, opens memgineering.com/setup in their browser, and
+RETURNS — in seconds, with the screen still up. It does not block until they
+finish, so run it and keep going in the same turn.
+
+```
+memgineering setup --web              # the screen; the normal answer
+memgineering setup --web --print-url  # no browser here — hand over the link
+```
+
+Three things to do after running it:
+
+1. Tell them, in their language, that their browser has a setup screen open.
+2. Show them the pairing code it printed. The screen's first question is
+   whether they started this, and it asks them to compare that code — the
+   defence against somebody being sent a setup link.
+3. Stop. Nothing installs until they finish on the screen, and this machine
+   picks it up on its own when they do. There is nothing to poll and nothing
+   to wait for.
+
+The screen asks everything `--agent` takes from flags — sign in, where the
+memory lives, which brain, which tools, auto-update, the session hook — with
+the recommended answer pre-selected. A person who is already signed in to
+memgineering.com does not sign in again: that session IS the identity, and one
+sign-in covers both halves (below).
+
+**Only when they ask you to decide for them**, answer from flags instead:
+
 ```
 memgineering setup --agent \
   --tools claude,codex \        # default: everything detected
@@ -37,37 +65,32 @@ memgineering setup --agent \
   --error-telemetry on          # anonymized crash reports; unset = undecided (off)
 ```
 
-`--dry-run` reports what would change without changing it.
+`--dry-run` reports what would change without changing it. `--human` draws the
+same questions as a checkbox list in your terminal, for a machine with no
+browser and a person sitting at it.
 
-**The account is the default, and the browser is not.** `setup --agent` starts a
-sign-in on its own: it prints a short pairing code and returns immediately,
-opening nothing. Show the user the code — they approve it in their browser while
-you keep working, and the next command picks the token up. Nothing exists on the
-server until they approve.
+**`--no-login` is how someone says "this machine only".** It is a flag on the
+`--agent` path, not a step on the screen: a brain that lives in a folder here
+cannot follow them to their phone or their next laptop, and that is discovered
+weeks later, by which time the notes are in the wrong place. On the screen the
+same choice is made in front of them, with the differences side by side.
 
-**One sign-in covers both halves (0.17.0+).** The approval also links the
-user's registry account (same Google account, automatic), so the claim stores a
+**One sign-in covers both halves (0.17.0+).** Signing in also links the user's
+registry account (same Google account, automatic), so the credentials hold a
 registry session next to the brain token. `memgineering whoami` reports both —
 the brain identity and a `registry:` line with the username. If the registry
 line says "not linked", the link simply did not happen at sign-in time (older
 server, registry briefly down); a fresh `logout` + `login` links it. Never
 treat a missing registry line as a failed brain sign-in — the brain token
-stands on its own. On the approval page itself, a user already signed in to
-memgineering.com approves with one click; a signed-out user signs in right
-there first (Google in a popup). Consent is asked exactly once, when an
-account is first created.
-
-`--no-login` is how someone says "this machine only". Offer it, do not assume it:
-a brain that lives in a folder here cannot follow them to their phone or their
-next laptop, and that is discovered weeks later, by which time the notes are in
-the wrong place. Ask which they want in one sentence before you run anything.
-
-**If they would rather set it up themselves**, hand them a screen instead of
-doing it: `setup --human` draws a checkbox list in your terminal, and
-`setup --web` opens a page in their own browser (`--web --print-url` when you
-cannot open one for them). Both ask the same questions `--agent` takes from
-flags, and `--web` is the one to reach for when the user is not reading your
-terminal at all.
+stands on its own. Consent is asked exactly once, when an account is first
+created.
+
+**When the setup finishes, say what is true and no more.** Commands work
+immediately — `recall`, `remember`, the session hook. What waits is the
+guidance files setup just wrote: an agent reads those at the start of a
+conversation, so they arrive with the next one. Do not tell the user they must
+restart. (Measured: a fresh agent relayed "restart required" as fact, the user
+checked, and it was not one.)
 
 **Ask before setting policy for them.** Auto-update means the tool updates
 itself; `--hook on` means note summaries and their standing rules reach an agent
@@ -132,25 +155,30 @@ On Grok and Antigravity, run `memgineering resurface` yourself when you start
 work in a folder, and `memgineering rules` before you change anything — that is
 the same job the hooks do elsewhere, done by hand.
 
-### When a person needs a screen, not flags
+### The screen, in more detail
 
 ```
-memgineering setup --human       # checkbox screen in your terminal
-memgineering setup --web         # a page in their own browser
+memgineering setup --web         # the default: a page in their own browser
 memgineering setup --web --print-url    # no browser here — hand over the link
+memgineering setup --human       # checkbox screen in your terminal, no browser
 ```
 
-Reach for `--web` when the user is not reading your terminal at all. Its first
-screen is the account question, and it is theirs: the page explains what
-memgineering is, compares this machine against an account, and starts a sign-in
-only after they pick. **Do not pre-empt it by running `login` first.** If they
-already told you which way, pass `--login` / `--no-login` and the screen opens
-with that selected.
-
-It covers step 2 as well, with the same disclosure `link --dry-run` prints. The
-page serves on `127.0.0.1` with a one-time key and **the command does not return
-until it is answered or ten idle minutes pass** — a screen nobody answered has
-set nothing up, so wait for it rather than reporting done.
+The page is on memgineering.com, not on this machine — the same site, the same
+sign-in, the same design. So a person who is already signed in there is
+recognised, and the sign-in they do on that screen is the ONLY one the whole
+install asks for. **Do not run `login` first**; it adds an approval to a flow
+that no longer needs one.
+
+**The command returns; the screen does not.** With nobody watching a terminal
+(you, a pipe, a CI job) the waiting half detaches and keeps going after your
+command exits, so a slow reader cannot time your call out. `--wait` forces the
+old behaviour of blocking until the screen is answered, for a script that
+genuinely wants it.
+
+It covers step 2 as well, with the same disclosure `link --dry-run` prints —
+including, for someone who already keeps notes on this machine, the option to
+carry that folder up to the account. Folder names are sent only after the
+screen asks for them, and never their contents.
 
 ## 2. Connect a brain