Merge branch 'rig-work'

Converts CSV, xlsx/xls/ods, directories, ZIPs and globs into one INSERT
file per table. Producer-specific layouts (header/data rows found by a
marker cell) and sheet naming live in a gitignored dataconvert.json, with
dataconvert-example.json as the template. --max-rows samples each table
and SCHEMA.md records columns, types, row counts and full sizes.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>

.gitattributes

@@ -0,0 +1,27 @@
+# Copied verbatim from rig/.gitattributes, and deliberately duplicated rather
+# than shared: rig/ must carry its own so it survives being handed over on its
+# own, and spr had none at all despite shipping ctrl/*.sh and generating
+# gen/<room>/ctrl/*.sh.
+#
+# Line endings are normalised to LF in the repository and on checkout, on every
+# platform. Without this, a checkout on Windows/WSL rewrites files to CRLF and
+# every one of them shows up as modified without anyone having touched it.
+#
+# For the scripts it is not cosmetic: a shell script with CRLF fails on Linux
+# with `bad interpreter: /usr/bin/env bash^M`, which reads as a broken installer
+# rather than a line-ending problem — the worst possible first impression on a
+# machine where nothing has been proven yet.
+* text=auto eol=lf
+
+*.sh   text eol=lf
+*.py   text eol=lf
+*.env  text eol=lf
+*.yaml text eol=lf
+*.yml  text eol=lf
+
+# Never touch binaries.
+*.png binary
+*.jpg binary
+*.zip binary
+*.tar binary
+*.gz  binary

.gitignore

@@ -34,3 +34,11 @@ cfg/amar/
 cfg/dlt/
 # Add new rooms here as they are created
 # cfg/<room>/
+
+# Client rigs. A rig is a copy of rig/ renamed after the environment it models,
+# so its k8s files spell out a real architecture — exactly the thing that must
+# not land here. They are versioned in their own repo.
+#
+# Anchored at the ROOT on purpose: a copy is a SIBLING of rig/, so a rule inside
+# rig/.gitignore cannot see it.
+*-rig/

CLAUDE.md

@@ -129,7 +129,7 @@ Every script stays runnable on its own — the standalone rule holds:
 ```bash
 python build.py --cfg amar         # -> gen/amar/
 cd gen/standalone && python run.py # bare-metal
-./ctrl/kind-up.sh                  # still works directly
+./ctrl/cluster.sh up               # still runs directly; rig builds the cluster
 cd gen/<room> && ./ctrl/start.sh   # each room owns its lifecycle scripts
 ```
 

Makefile

@@ -13,7 +13,7 @@
 #   make component ARGS="publish soleprint-ui /tmp/out --dist"
 #   make deploy    ARGS="--build"
 #
-# Every script stays runnable on its own (./ctrl/kind-up.sh still works, and each
+# Every script stays runnable on its own (./ctrl/cluster.sh up still works, and each
 # built room keeps its own gen/<room>/ctrl/*.sh) — the standalone rule holds, and
 # this only saves typing.
 #
@@ -33,10 +33,16 @@ ifneq ($(ARGS),)
 # then fails with "No rule to make target 'sample'", because make reads every
 # word on the line as something it has been asked to build.
 $(eval $(ARGS):;@:)
+# ...and as PHONY, because some of those words name real directories. `cfg`,
+# `ctrl`, `docs`, `gen` and `init` all exist at this level, and make considers a
+# target that is an existing directory already built — so `make build ctrl` ran
+# the build and then printed "make: 'ctrl' is up to date". The empty rule above
+# is not enough on its own; only .PHONY stops make consulting the filesystem.
+.PHONY: $(ARGS)
 endif
 
 .DEFAULT_GOAL := help
-.PHONY: help build start stop dist docs cluster deploy component
+.PHONY: help build start stop dist theme docs cluster deploy component
 
 help:                          ## list targets
 	@grep -hE '^[a-z]+:.*?##' $(MAKEFILE_LIST) | sed 's/:.*##/\t/' | expand -t16
@@ -55,6 +61,11 @@ stop:                          ## stop a running room  [<room>]
 dist:                          ## compile the plexus UIs to single files  [<room>]
 	bash ctrl/dist.sh $(or $(ARGS),$(ROOM))
 
+# ── theme ──────────────────────────────────────────────────────────────────
+
+theme:                         ## ad-hoc pages  [new|parts|bake|check|export|run FILE]
+	bash ctrl/theme.sh $(or $(ARGS),bake)
+
 # ── docs ───────────────────────────────────────────────────────────────────
 
 docs:                          ## documentation  [serve [port]|graphs [theme]]  (default serve)

berth/.gitignore

@@ -0,0 +1,21 @@
+# Machine-local config and credentials. Never committed.
+ctrl/.env
+
+# Rendered output. Regenerate with `make services render <target>`.
+# Generated config is an artifact, not source — the estate file is the source.
+#
+# The path is ctrl/render/out/, NOT render/out/. A pattern containing a slash is
+# anchored to the directory holding this .gitignore, so `render/out/` would mean
+# berth/render/out/ — which does not exist, and the real output would have been
+# committed. Caught by `git check-ignore -v`, which is the only way to be sure.
+ctrl/render/out/
+
+# The "default" scratch bucket: always gitignored, never versioned.
+def/
+
+# Key material. NEVER committed.
+#
+# Anchored to ctrl/ for the same reason as render/out/ above: a pattern with a
+# slash resolves against this file's own directory. `git check-ignore -v` is the
+# only way to confirm it, and ctrl/vpn.sh refuses to write a key until it does.
+ctrl/.secrets/

berth/Makefile

@@ -0,0 +1,78 @@
+# One target per ctrl/ script; the subcommand is an argument, not a second
+# target: `make estate show`, not `make estate-show`. The logic lives in the
+# scripts, never here.
+#
+# Config layers, weakest first: ctrl/versions.env < ctrl/env.d/<target>.env <
+# ctrl/.env < the environment. So `make estate plan TARGET=gcp` beats all.
+#
+# Every target defaults to its READ-ONLY verb, and the verbs that change a live
+# estate are not reachable by a bare word. Rationale: README.md.
+
+ESTATE := $(or $(shell sed -n 's/^ESTATE=//p' ctrl/.env 2>/dev/null),$(shell ls estate/*.json 2>/dev/null | head -1 | xargs -r basename | sed 's/\.json$$//'))
+TARGET := $(or $(shell sed -n 's/^TARGET=//p' ctrl/.env 2>/dev/null),aws)
+
+.PHONY: help check selftest estate services vpn dns certs host ports registry docs
+
+help:                          ## list targets
+	@grep -hE '^[a-z][a-z-]*:.*?##' $(MAKEFILE_LIST) | sed 's/:.*##/\t/' | expand -t16
+
+# ── preflight ──────────────────────────────────────────────────────────────
+
+check:                         ## is this estate coherent? reports, never fixes
+	bash ctrl/check.sh
+
+selftest:                      ## does berth still do what it says? exits 1 if not
+	bash ctrl/selftest.sh
+
+ports:                         ## port map  [show|verify]  (default show)
+	bash ctrl/ports.sh $(or $(ARGS),show)
+
+# ── the estate ─────────────────────────────────────────────────────────────
+
+estate:                        ## the estate  [show|list|plan|apply|destroy]  (default show)
+	bash ctrl/estate.sh $(or $(ARGS),show)
+
+services:                      ## gateway routes  [list|render <target>|deploy]  (default list)
+	bash ctrl/services.sh $(or $(ARGS),list)
+
+# ── the network ────────────────────────────────────────────────────────────
+
+vpn:                           ## overlays  [list|show <ov>|check|render|keygen]  (default list)
+	bash ctrl/vpn.sh $(or $(ARGS),list)
+
+# ── names and trust ────────────────────────────────────────────────────────
+
+dns:                           ## DNS records  [list|add|add-wildcard|remove]  (default list)
+	bash ctrl/dns.sh $(or $(ARGS),list)
+
+certs:                         ## TLS  [status|verify|renew|push]  (default status)
+	bash ctrl/certs.sh $(or $(ARGS),status)
+
+# ── the box ────────────────────────────────────────────────────────────────
+
+host:                          ## the remote box  [status|ports|services]  (default status)
+	bash ctrl/host.sh $(or $(ARGS),status)
+
+registry:                      ## the image registry  [status]  (default status)
+	bash ctrl/registry.sh $(or $(ARGS),status)
+
+# ── docs ───────────────────────────────────────────────────────────────────
+
+docs:                          ## documentation  [serve|graphs]  (default serve)
+	bash ctrl/docs.sh $(or $(ARGS),serve)
+
+# ── swallowing the argument words — MUST BE LAST IN THIS FILE ──────────────
+#
+# Words after the target are arguments, but make reads each as a goal, so each
+# gets a no-op rule. This block must come AFTER the real targets: when an
+# argument names one (`make host ports`, `make vpn check`), the last definition
+# wins, and it has to be the no-op. With it first, make ran both scripts.
+#
+# Make's "overriding recipe" warning is the swallow working as intended.
+ARGS := $(wordlist 2,$(words $(MAKECMDGOALS)),$(MAKECMDGOALS))
+ifneq ($(ARGS),)
+$(eval $(ARGS):;@:)
+# .PHONY too: some of those words name real directories (ctrl, estate, render),
+# and make treats an existing directory as already built.
+.PHONY: $(ARGS)
+endif

berth/README.md

@@ -0,0 +1,250 @@
+# berth
+
+spr's deploy half. A rig is a mobile installation; a **berth** is the allocated, paid-for
+place where it is moored and actually operates. Local rig → remote berth.
+
+```bash
+make check              # is this estate coherent? reports, never fixes
+make estate show        # the description, resolved
+make vpn check          # the overlay: addresses, routing, bindings, key hygiene
+make services render aws
+make ports verify       # does the local map still agree with rig?
+```
+
+`rm -rf berth/` is the uninstall.
+
+---
+
+## What berth is
+
+**One description of an estate, with a swappable executor.** The description is the artifact;
+the tool that runs it is a rendering.
+
+| layer | what berth uses | note |
+| --- | --- | --- |
+| overlay | **WireGuard**, config generated per peer | GPL-2.0, in-kernel, and **no coordination server** |
+| infra | **OpenTofu** — one executor, not a pair | plain `.tf`; `terraform` works identically |
+| gateway | Caddy locally, nginx on the box | a projection with per-target rules, not a format conversion |
+| pipeline | Woodpecker | Actions/GitLab reachable from the same description; not built |
+
+The estate's facts — domain, hosts, ports, instance size, firewall rules, services — live in
+**one file every rendering reads** (`estate/<name>.json`), rather than being restated in
+one tool's language and again in another's. **Swappability is bought by the description, not
+by maintaining two renderings** — a rendering you *can* produce, not one you *must* keep in
+step. Two live renderings cost you every resource twice, forever, with nothing enforcing that
+they agree.
+
+**The seam belongs in a script, not in a tool.** A tool's schema is a ceiling you do not
+control.
+
+*(This once leaned on a specific precedent, since withdrawn — `✖ B2` in [STALE.md](STALE.md).)*
+
+**OpenTofu, and only OpenTofu.** Terraform has been BUSL-licensed since 2023; OpenTofu is the
+CLI-compatible MPL-2.0 fork (Linux Foundation). Write plain `.tf` that runs under both; the
+scripts say `tofu`, and `terraform` works identically.
+
+**Pipelines are the second executor axis, and are not built.** Woodpecker is the
+self-hosted rendering; Actions and GitLab CI are the standards that must be reachable from
+the same description. Named here so the infra seam is not designed in a way that forecloses
+it.
+
+---
+
+## The overlay is berth's network layer
+
+Two instances in different clouds cannot share a VPC. A WireGuard overlay gives them one flat
+address space that berth owns and can reproduce on any provider — and, under a flaky
+environment, a second layer beneath whatever the provider offers.
+
+That inverts the usual cloud pattern. Instead of a VPC with security groups and private
+subnets, each instance gets a public IP, opens **only** the WireGuard port, and carries
+everything else inside the tunnel. **The security boundary moves out of the provider's VPC
+and into a layer that is identical on AWS, on GCP, and on a laptop behind NAT.**
+
+**Plain WireGuard, not Tailscale/Headscale/NetBird.** Tailscale's client is open but its
+coordination plane is proprietary SaaS; Headscale and NetBird are open but add a control plane
+to run. Plain WireGuard needs no server at all.
+
+**The cost is real and accepted:** no NAT traversal, no relay, no peer discovery. A peer behind
+NAT must dial one with a public endpoint. Fine here — the instances have public IPs and the dev
+box roams — but two roaming peers cannot reach each other. That is why `PersistentKeepalive` is
+a checked invariant rather than a detail.
+
+**Keys never enter the description.** Private keys are generated on the peer that owns them
+(`make vpn keygen`) into `ctrl/.secrets/` and injected only at render time; public keys live in
+the estate, because a config cannot be built without them. `vpn.sh` **refuses to write** either
+a key or a rendered config until `git check-ignore` confirms the path is ignored — this repo
+has already been bitten once by a `.gitignore` pattern anchoring to the wrong directory.
+
+This also decides something about the IaC layer: **OpenTofu must never generate a WireGuard
+private key**, because Terraform-lineage state stores every resource attribute in plaintext.
+
+---
+
+## Two rules that are not style preferences
+
+### 1. Every default is the read-only verb
+
+```
+make estate    -> show      make certs  -> status
+make dns       -> list      make host   -> status
+make estate apply / destroy -> print the plan, then refuse without --yes
+```
+
+rig's `make cluster` defaults to `up`, because every rig verb is safe — a kind cluster is
+disposable. berth's are not: `tofu destroy` costs money and takes live DNS with it. **A
+tool where every verb is safe must not grow verbs that are not.**
+
+The failure this prevents is not hypothetical. `ppl/ctrl/certs.sh:42` is `CMD="${1:-all}"`,
+so a bare `./ctrl/certs.sh` there issues a real Let's Encrypt cert, rsyncs it to the gateway,
+and reloads nginx. berth's `certs` defaults to `status`.
+
+### 2. berth and rig share a convention, not code
+
+Neither imports the other. They match on **shape** — the `make <noun> <verb>` dispatch, the
+four-source config layering, the key names — and consistency is verified by
+**recomputation**: `make ports verify` recomputes rig's `20000 + (cksum(name) % 200) * 10`
+to check the local map, rather than sourcing rig's `lib/config.sh`.
+
+Copying three stable lines is the whole cost of not coupling them. A shared library would
+put something outside `rig/` on rig's path, and rig's promise is that
+`grep -rIn -iE 'soleprint|\bspr\b'` across it returns nothing.
+
+**rig is also unaware that berth exists.** `ppl/local/Caddyfile` is berth's to generate; rig
+must not reference `local.ar` — its handover scrub refuses the string.
+
+---
+
+## The gateway doctrine
+
+Practised across this codebase for a long time and never written down, so: written down.
+
+- **Caddy where routing is dynamic and config-driven** — the in-cluster gateway that
+  multiplexes by Host header, and the host-side `.local.ar` name→port map.
+- **nginx where it is a static server or a plain long-running compose service on the box.**
+- **Envoy in `mpr`** — a deliberate one-off, not a third pattern.
+- **`ingress-nginx` only as a kind addon** — a different thing again from either gateway.
+
+### Rendering is a projection, not a format conversion
+
+The local Caddyfile and the box's nginx are not two spellings of the same content:
+
+| | local (Caddy) | cloud (nginx) |
+| --- | --- | --- |
+| granularity | one file | one file per vhost |
+| blocks per service | one | two (`:80` redirect + `:443` server) |
+| TLS | none; every address needs an explicit `:80` | one shared wildcard cert |
+| upstream | `localhost:<port>` | container name + `resolver 127.0.0.11` |
+| name depth | free | constrained by the cert |
+| ambiguity | most specific wins | exact, else `default_server` (= load order) |
+
+The `:80` is not decoration: without it Caddy 2 defaults each site to `:443` with auto-HTTPS,
+which on `*.local.ar` means cert provisioning that fails and breaks the listener. The
+variable upstream is not decoration either: naming the upstream in a variable forces runtime
+DNS resolution, so nginx **starts when the upstream container is absent** — which is what
+lets one nginx front a dozen independent compose stacks.
+
+Because the two disambiguate by **opposite** rules, a name set that is unambiguous locally
+can be ambiguous on the box. `make check` asserts against the projection, not the source.
+
+### Installing generated vhosts — an order that is not optional
+
+1. Generated config lands in `conf.d/generated/`, **not** `conf.d/`. `ppl/ctrl/deploy.sh`
+   rsyncs with `--delete`; sharing a directory means one set gets erased.
+2. `nginx.conf` needs a **third** include line — its `conf.d/*.conf` glob does not recurse,
+   which is why `conf.d/soleprint/*.conf` already needs its own.
+3. That include changes **load order**, and load order decides which `:443` block catches
+   unmatched names. So `default.conf`'s commented-out `:443 default_server` must be restored
+   **first**. `make check` fails on it deliberately: it is a gate, not a warning.
+
+---
+
+## What the checks assert, and why
+
+The scripts are deliberately thin on comment — the reasoning lives here. Every check below
+corresponds to something that is wrong, or was wrong, in a real estate.
+
+### `make check` — the estate
+
+| assertion | the failure it catches |
+| --- | --- |
+| every service name is covered by an issued cert SAN | **a wildcard matches exactly one label.** `*.d.com` covers `a.d.com` but not `a.b.d.com`, which needs its own SAN. Surfaces otherwise as a browser TLS warning, far from its cause |
+| a `:443 default_server` exists | DNS and the cert are wildcard but nginx matches `server_name` exactly, so without one the fallback for any unknown name is whichever vhost loads first — alphabetically, by accident |
+| firewall rules and listeners agree | a rule allowing a port nothing listens on is **dead config**; a service no compose file declares is **undocumented state**. Neither is visible from one side alone, which is why the inventory has two halves |
+| `HOST` is an ssh alias, never a hostname | there is no `Host <domain>` block, so a bare hostname falls through to the global defaults, ssh offers every key in the agent in turn, and `MaxAuthTries` (6) trips with *"Too many authentication failures"* before reaching the right one. The aliases set `IdentitiesOnly yes` |
+
+### `make vpn check` — the overlay
+
+| assertion | the failure it catches |
+| --- | --- |
+| peer addresses unique and inside the subnet | a duplicate is a silent misroute, never an error |
+| AllowedIPs do not overlap | AllowedIPs is **cryptokey routing** — the route table and the ACL at once. Overlapping ranges resolve to the last match, so an overlap is both a misroute and an unintended grant |
+| something carries `PersistentKeepalive` if anything roams | without it a NAT mapping expires and the tunnel works only while traffic flows outward — *"works sometimes"*, the hardest failure to read. Note it is **not** a property of the roaming peer's own entry: the roaming machine sets it on the entry for the peer it **dials** |
+| the listen port is in the firewall | otherwise no peer can be dialed at all |
+| no private key in the description | public keys are *also* 44-char base64, so the shape proves nothing. The real assertions are **no field named `priv*`** and **no key outside a `public_key` field** |
+| overlay-reached services bind a reachable address | **a tunnel cannot reach loopback.** A service on `127.0.0.1` is unreachable over the overlay; one on `0.0.0.0` is reachable but also exposed to the whole LAN |
+
+### Capturing the overlay
+
+```bash
+sudo wg show | make vpn capture --write
+```
+
+`wg show` has three forms and **only the first is safe**:
+
+| form | safe | why |
+| --- | --- | --- |
+| `wg show` | **yes** | prints `private key: (hidden)` |
+| `wg show <if> dump` | **no** | field 1 of the first line *is* the private key |
+| `wg showconf <if>` | **no** | prints `PrivateKey=` outright |
+
+`capture` refuses the latter two by shape. It matches peers by **allowed-ips address, not
+public key** — the keys are exactly what is missing at that point — and **drops a roaming
+peer's endpoint in the parser**, since that value is a home ISP address and a roaming peer
+has no stable endpoint anyway.
+
+## Layout
+
+```
+berth/
+├── Makefile              one target per ctrl/ script; the verb is an argument
+├── STALE.md              withdrawn assumptions, each with a check that runs
+├── estate/<name>.json    THE ARTIFACT — one description, many renderings
+└── ctrl/
+    ├── check.sh          reports and instructs; never fixes
+    ├── estate.sh         show | list | plan | apply --yes | destroy --yes
+    ├── services.sh       list | render <aws|gcp|local> | deploy
+    ├── ports.sh          show | verify   (the rig coincidence check)
+    ├── dns.sh certs.sh host.sh registry.sh docs.sh
+    ├── versions.env      pinned toolchain          (weakest layer)
+    ├── env.d/<target>.env  provider shape: aws | gcp
+    ├── .env.example      -> ctrl/.env, machine-local  (gitignored)
+    ├── lib/config.sh     the four-layer load, from rig
+    ├── lib/estate.sh     reading and projecting the estate
+    └── render/*.tmpl     nginx vhost shapes, substituted with sed
+```
+
+Config layers, weakest first: `versions.env` → `env.d/<target>.env` → `ctrl/.env` → the
+caller's environment. So `make estate plan TARGET=gcp` beats everything.
+
+**Identity is explicit — the inversion of rig.** rig derives its name from its folder so that
+copies never collide. berth refuses to guess, because a deployment has exactly one production
+and a wrong guess acts on the wrong estate. `ESTATE` names a file; the only convenience is
+that a single `estate/*.json` is used without being asked for.
+
+**`python3`, not `jq`.** rig ships a pinned static `jq` because its floor is "docker and
+nothing else" on a machine it does not control. berth's floor is already higher, so
+`python3` is a dependency it *has* rather than one it *adds* — the same reasoning by which
+rig chose `sed` over `envsubst`.
+
+---
+
+## Status
+
+**B0 (this) is the shape.** `estate/mcrn.json` is marked `UNVERIFIED`: it records what the
+repos *claim*, because `ppl/infra/` was written and never applied — no `~/.pulumi`, no
+`venv`, no stack state, files dated `mar 6`. B1's read-only inventory is what replaces those
+claims with observations. Until then, `estate plan` and `estate apply` refuse: there is
+nothing truthful to compare against yet.
+
+`make check` currently fails on two real things — see `def/plans/36.0/berth.md`.

berth/STALE.md

@@ -0,0 +1,104 @@
+# berth — withdrawn assumptions
+
+**Everything in this file is no longer true.**
+
+It exists so the live docs stay short and so a withdrawn assumption cannot quietly return:
+each entry carries a **check**, and `ctrl/selftest.sh` runs every one of them. A retraction
+that is only prose is a retraction nobody re-reads.
+
+Kept rather than deleted for the reason the docgen thread already wrote down —
+*a requirement that disappears without explanation comes back.*
+
+### For agents
+
+- **Do not restate these** in a plan, a README or a comment. One line pointing here is enough.
+- **Ids are stable.** Cite `✖ B3`; do not re-explain it.
+- **When you withdraw an assumption, move it here** — quoted claim, where it came from, what
+  superseded it and why, what changed in the code, and a check that proves it is gone.
+- **Only withdrawn things belong here.** A warning that is still actionable is a live rule,
+  however historical it sounds, and stays where it is.
+
+---
+
+**✖ B1 — "Pulumi is the source in spr, and Terraform must match the config."**
+*(INDEX §5, carried from 35.3)* Withdrawn 2026-09-12. berth uses **OpenTofu and only
+OpenTofu**. The rule assumed *open source* and *industry standard* pull apart — Terraform
+being BUSL, Pulumi being the open alternative. OpenTofu is both: the standard language, plain
+Terraform-compatible HCL, under MPL-2.0. Swappability was never bought by keeping two
+renderings; it is bought by `estate/*.json` being the artifact — a rendering you *can*
+produce, not one you *must* maintain.
+**Gone from:** `ctrl/versions.env` (no `PULUMI_VERSION`), `ctrl/estate.sh` (`plan` runs one
+executor), `ctrl/lib/config.sh` (`PULUMI_STACK` → `TOFU_WORKSPACE`), `ctrl/check.sh`
+(toolchain list).
+**Deliberately kept:** `README.md` and `estate/mcrn.json` both record that `ppl/infra/` was
+written and never applied — *"no `~/.pulumi`, no venv, no stack state"*. That is a historical
+fact about the estate, not a live dependency.
+**Check:** no `pulumi` in `ctrl/` or `Makefile`.
+
+**✖ B2 — "ctlptl's rejection is the precedent for *the seam belongs in a script, not a tool*."**
+*(INDEX §5, `berth/README.md`)* Withdrawn 2026-09-12. **ctlptl was reinstated** — pinned in
+`rig/ctrl/versions.env` at v0.9.4 — and had been removed for the wrong reason. The rule may
+still hold; it now has to stand on its own reasoning rather than that example.
+**Gone from:** `README.md` — the argument is stated directly, with no borrowed evidence.
+**Check:** `ctlptl` appears nowhere in berth.
+
+**✖ B3 — "`wg show` is safe; `wg showconf` is not."** *(my own note, 2026-09-12)* Incomplete,
+and the gap is the dangerous one. There are **three** forms, and `wg show <if> dump` puts the
+**private key in field 1 of the first line**. Stated as a two-way distinction, the `dump` form
+reads as safe.
+**Now:** `wg show` plain is safe; `dump` and `showconf` are not. `ctrl/vpn.sh capture` refuses
+the latter two **by shape**, rather than parsing around them.
+**Check:** `vpn.sh` names all three forms, and `capture` rejects both unsafe ones.
+
+**✖ B4 — "A roaming peer must set `PersistentKeepalive` on its own entry."**
+*(`ctrl/vpn.sh`, first draft)* Wrong side, and wrong in the direction that looks fine:
+`PersistentKeepalive` is set per-peer in a config, so the roaming machine sets it on the entry
+for the peer it **dials**. The original check would have **warned on a correctly configured
+overlay**.
+**Now:** checked once per overlay — if anything roams, some peer entry must carry a keepalive.
+**Check:** the invariant is not keyed on the roaming peer's own `keepalive` field.
+
+**✖ B5 — "The Makefile's pass-through block goes near the top, with the other variables."**
+*(`Makefile`, inherited from rig's layout)* Withdrawn 2026-09-12. When a subcommand **names a
+real target**, make has two recipes for it and the **last definition wins** — so with the block
+first, `make host ports` ran `ctrl/host.sh ports` *and* `ctrl/ports.sh ports`, the second
+failing because `ports` is not one of its verbs. Same for `make host services`, `make vpn
+check`, `make vpn show estate`.
+**Now:** the `$(eval $(ARGS):;@:)` block is **last in the file**, so the no-op wins and the
+word is swallowed — which is what an argument is. Make's *"overriding recipe"* warning is the
+swallow working.
+**Check:** every colliding invocation dispatches to exactly one script.
+
+**✖ B6 — "A base64 key in the description can be caught by its shape."**
+*(`ctrl/vpn.sh check`, first draft)* WireGuard **public** keys are also 44-char base64 and
+legitimately live in the estate, so shape alone proves nothing and would flag correct data.
+**Now:** two assertions instead — **no field named `priv*`**, and **no base64 key outside a
+`public_key` field**.
+**Check:** the estate's public keys do not trip the secret check.
+
+**✖ B7 — "`network.wireguard` is where the overlay is described."** *(`estate/mcrn.json`)*
+Superseded 2026-09-12: WireGuard is berth's network layer, not one service's transport, so it
+is a top-level `vpn` block with named overlays and peers. `ctrl/check.sh` and
+`ctrl/registry.sh` were repointed.
+**Gone from:** the estate schema — a `wireguard_moved` tombstone marks the old key.
+**Check:** nothing reads `network.wireguard.*`.
+
+**✖ B8 — "berth and rig are related through their first uses."** *(early framing)* Withdrawn:
+**rig and berth are peers — neither depends on the other.** They match on shape (dispatch,
+config layering, key names) and consistency is verified by **recomputation**, never by
+dependency. A shared library would put something outside `rig/` on rig's path.
+**Check:** berth imports nothing from rig; `ports.sh` recomputes the port formula and agrees
+with rig's golden values.
+
+**✖ B9 — "`langfuse.mcrn.ar` is an exception that cannot be generated."**
+*(`estate/mcrn.json`, `raw: true`)* Withdrawn 2026-09-14. It was filed as the one route a
+template could not express — a static `upstream{}` to a WireGuard address, with no `resolver`
+and no `set $var`. It was not an exception; it was **the first instance of the general case**.
+Those three properties are not three decisions, they are one: *this service is reached by
+address on the overlay, not by name on the docker network.* Naming that decision —
+`placement` — makes the file renderable.
+**Gone from:** `estate/mcrn.json` — `lng` and `langfuse` were **two entries for one socket**
+and are now one service with `placement: local`, `peer: nrft`, and a `local_host` for the
+name it answers to locally. `raw` is dropped.
+**Check:** the generated vhost matches the hand-written one, normalised for comments and
+whitespace — proof against a live route rather than an assertion.

berth/ctrl/.env.example

@@ -0,0 +1,18 @@
+# Machine-local config. Copy to ctrl/.env (gitignored) and edit.
+#
+# The estate's FACTS live in estate/<name>.json.
+# The provider's SHAPE lives in ctrl/env.d/<target>.env.
+# This file is only what differs between machines, plus credentials.
+
+# ESTATE is required when estate/ holds more than one file.
+# ESTATE=mcrn
+# TARGET=aws
+
+# ssh ALIASES, never hostnames — check.sh refuses a value containing a dot.
+# HOST=mcrn              # app user, no sudo
+# HOST_ADMIN=mcrn-admin  # sudo, only where genuinely required
+
+# Credentials: names only, never values. The secrets stay in ~/.aws and
+# ~/.config/gcloud where their own tooling manages them.
+# AWS_PROFILE=default
+# GCP_PROJECT=

berth/ctrl/certs.sh

@@ -0,0 +1,58 @@
+#!/usr/bin/env bash
+# The wildcard TLS cert for the gateway.
+#
+# Usage:
+#   ./certs.sh status     # SANs issued vs SANs the services need
+#   ./certs.sh verify     # inspect the cert served on :443
+#   ./certs.sh renew      # refuses: issues a real cert
+#   ./certs.sh push       # refuses: ships to a live gateway
+
+set -euo pipefail
+cd "$(dirname "$0")"
+
+source ./lib/config.sh
+source ./lib/estate.sh
+load_config
+
+status() {
+    local issued; issued=$(estate_get "certs.issued" | python3 -c 'import json,sys
+try: print("\n".join(json.load(sys.stdin)))
+except Exception: pass')
+    echo "issued SANs (estate/${ESTATE}.json: certs.issued):"
+    echo "$issued" | sed 's/^/  /'
+    echo
+    echo "SANs the services NEED (derived from services[]):"
+    estate_sans | sed 's/^/  /'
+    echo
+    local missing=0 s
+    while IFS= read -r s; do
+        [ -z "$s" ] && continue
+        grep -qxF "$s" <<< "$issued" || { echo "MISSING: $s"; missing=1; }
+    done < <(estate_sans)
+    [ "$missing" = 0 ] && echo "the issued cert covers every derived name."
+    echo
+    echo "certbot image: $(eval echo "\$$CERTBOT_IMAGE_VAR")   provider: $DNS_PROVIDER"
+}
+
+verify() {
+    echo "would run:"
+    echo "  echo | openssl s_client -connect ${DOMAIN}:443 -servername ${DOMAIN} 2>/dev/null \\"
+    echo "    | openssl x509 -noout -dates -ext subjectAltName"
+    echo
+    echo "read-only against a live host — announce and approve first (§7)."
+}
+
+refuse() {
+    echo "REFUSING: '$1' acts on a live cert and a live gateway." >&2
+    echo "  renew issues a real Let's Encrypt cert (rate-limited)." >&2
+    echo "  push rsyncs to the gateway and reloads nginx." >&2
+    echo "  Neither runs without explicit approval." >&2
+    exit 1
+}
+
+case "${1:-status}" in
+    status)      status ;;
+    verify)      verify ;;
+    renew|push)  refuse "$1" ;;
+    *) echo "usage: $0 [status|verify|renew|push]" >&2; exit 1 ;;
+esac

berth/ctrl/check.sh

@@ -0,0 +1,153 @@
+#!/usr/bin/env bash
+# Is this estate coherent? Reports and instructs; never fixes.
+#
+# Takes no subcommand — there is one question to ask.
+# Every check corresponds to something wrong in the estate today.
+
+set -euo pipefail
+cd "$(dirname "$0")"
+
+source ./lib/config.sh
+source ./lib/estate.sh
+load_config
+
+WORST=0
+note() { echo "  $*"; }
+warn() { echo "  WARN  $*"; [ "$WORST" -lt 1 ] && WORST=1; return 0; }
+bad()  { echo "  FAIL  $*"; WORST=2; return 0; }
+
+echo "estate: $ESTATE   target: $TARGET   domain: $DOMAIN"
+echo
+
+# 1. cert coverage: a wildcard matches exactly one label.
+echo "certs — does the cert cover every name the services serve?"
+issued=$(estate_get "certs.issued" | python3 -c 'import json,sys
+try: print("\n".join(json.load(sys.stdin)))
+except Exception: pass')
+if [ -z "$issued" ]; then
+    warn "no certs.issued in the estate file — cannot check coverage."
+else
+    while IFS=$'\x1f' read -r name host up kind raw placement peer port lhost; do
+        [ -z "$host" ] && continue
+        fqdn="${host}.${DOMAIN}"
+        # A '*' host stands for "any single label here" — check the deepest
+        # name it can produce, which is the one that fails.
+        probe="$fqdn"
+        case "$host" in \*.*) probe="anyroom.${host#\*.}.${DOMAIN}" ;; esac
+        covered=""
+        while IFS= read -r san; do
+            [ -z "$san" ] && continue
+            if san_covers "$probe" "$san"; then covered=1; break; fi
+        done <<< "$issued"
+        if [ -z "$covered" ]; then
+            bad "$name: '$probe' is covered by NO issued SAN"
+            note "      issued: $(echo "$issued" | tr '\n' ' ')"
+            note "      a wildcard matches exactly ONE label — reissue with"
+            note "      -d '*.${host#\*.}.${DOMAIN}' or move the name one level up"
+        fi
+    done < <(estate_services "$TARGET")
+    [ "$WORST" -lt 2 ] && note "every service name is covered."
+fi
+echo
+
+# 2. unmatched names: DNS and the cert are wildcard, nginx is exact, so
+#    without a :443 default_server the fallback is whichever vhost loads first.
+echo "gateway — is there a deliberate answer for unmatched names?"
+DEFAULT_CONF="${PPL_DIR:-$HOME/wdir/semester/ppl}/gateway/nginx/conf.d/default.conf"
+if [ ! -f "$DEFAULT_CONF" ]; then
+    note "ppl not on this machine at $DEFAULT_CONF — skipped."
+elif grep -qE '^\s*listen\s+443.*default_server' "$DEFAULT_CONF"; then
+    note "default.conf has a :443 default_server."
+else
+    bad "default.conf has NO :443 default_server."
+    note "      Unmatched names fall through to the first-loaded vhost."
+    note "      This is a PREREQUISITE for generating any config: adding a"
+    note "      generated include changes load order, and load order is what"
+    note "      currently decides the fallback."
+fi
+echo
+
+# 3. a rule allowing a port nothing listens on is dead config; a service no
+#    compose file declares is undocumented state. Needs both halves to see.
+echo "firewall — rules against listeners"
+estate_get "firewall" | python3 -c '
+import json,sys
+try: fw = json.load(sys.stdin)
+except Exception: fw = []
+for r in fw:
+    n = r.get("note")
+    print("  %-6s %-5s %s" % (r["port"], r.get("proto","tcp"), r.get("desc","")))
+    if n: print("        UNRESOLVED: " + n)
+'
+note "listener side: unknown until captured (ss -ltnp over ssh $HOST)."
+# Ask the structure, not the prose: the condition is "does a peer still lack a
+# public key", not "is there a _status string". _status is ALWAYS non-empty —
+# capture rewrites it to "CAPTURED ..." — so testing it for emptiness pinned
+# this warning on permanently, including after the capture it asks for.
+uncaptured=$(estate_get "vpn.overlays.estate.peers" 2>/dev/null | python3 -c '
+import json, sys
+try:
+    peers = json.load(sys.stdin)
+except Exception:
+    sys.exit(0)
+print(" ".join(n for n, p in peers.items() if not p.get("public_key")))
+' 2>/dev/null)
+if [ -n "$uncaptured" ]; then
+    warn "overlay: public keys not captured for:$uncaptured — see 'make vpn check'"
+    note "      10.8.0.1 carries the registry and woodpecker gRPC;"
+    note "      10.8.0.2 backs langfuse. Nothing in the tree creates the"
+    note "      interface — a fresh box cannot start the gateway compose."
+    note "      capture with: sudo wg show | make vpn capture --write"
+else
+    note "overlay: $(estate_get 'vpn._status')"
+fi
+note "overlay detail: make vpn show estate"
+echo
+
+# 4. ssh aliases, never hostnames: a bare hostname offers every agent key and
+#    trips MaxAuthTries before reaching the right one.
+echo "ssh — aliases, never hostnames"
+for var in HOST HOST_ADMIN; do
+    val="${!var:-}"
+    if [ -z "$val" ]; then
+        warn "$var is unset."
+    elif [[ "$val" == *.* ]]; then
+        bad "$var='$val' looks like a hostname, not a ~/.ssh/config alias."
+        note "      A bare hostname trips MaxAuthTries before reaching the key."
+    elif [ -f "$HOME/.ssh/config" ] && grep -qiE "^\s*Host\s+.*\b${val}\b" "$HOME/.ssh/config"; then
+        note "$var=$val — Host block present."
+    else
+        warn "$var='$val' has no matching Host block in ~/.ssh/config."
+    fi
+done
+for f in "$HOME/wdir/semester/ppl/ctrl/.env"; do
+    [ -f "$f" ] || continue
+    if grep -qE '^SERVER=.*\.' "$f"; then
+        warn "$f sets SERVER to a hostname, not an alias — every ppl script inherits it."
+    fi
+done
+echo
+
+# ── 5. toolchain ───────────────────────────────────────────────────────────
+echo "toolchain"
+for t in python3 "$TOFU_BIN" aws gcloud ssh rsync wg; do
+    if command -v "$t" >/dev/null 2>&1; then
+        note "$(printf '%-8s' "$t") present"
+    else
+        note "$(printf '%-8s' "$t") MISSING  — $(case $t in
+            tofu)   echo 'blocks: estate plan/apply; terraform works identically' ;;
+            wg)     echo 'blocks: vpn keygen and the overlay checks' ;;
+            aws)    echo 'blocks: the control-plane inventory, dns on route53' ;;
+            gcloud) echo 'blocks: the gcp estate' ;;
+            *)      echo 'blocks: most things' ;;
+        esac)"
+    fi
+done
+echo
+
+case "$WORST" in
+    0) echo "OK" ;;
+    1) echo "OK, with warnings" ;;
+    2) echo "PROBLEMS FOUND — see FAIL lines above" ;;
+esac
+exit 0

berth/ctrl/dns.sh

@@ -0,0 +1,81 @@
+#!/usr/bin/env bash
+# DNS records, over whichever provider the target names.
+#
+# Usage:
+#   ./dns.sh list
+#   ./dns.sh add <subdomain>       # <sub>.<domain> -> <domain>
+#   ./dns.sh add-wildcard <sub>
+#   ./dns.sh remove <subdomain>
+#
+# Read-only verbs announce and wait; mutating ones refuse.
+
+set -euo pipefail
+cd "$(dirname "$0")"
+
+source ./lib/config.sh
+source ./lib/estate.sh
+load_config
+
+announce() {
+    echo "would run:"
+    printf '  %s\n' "$*"
+}
+
+list() {
+    case "$DNS_PROVIDER" in
+        route53)
+            announce "aws route53 list-resource-record-sets --hosted-zone-id $AWS_HOSTED_ZONE_ID" \
+                     "--query 'ResourceRecordSets[].[Name,Type,TTL,ResourceRecords[0].Value]' --output table"
+            ;;
+        google)
+            announce "gcloud dns record-sets list --zone=${ESTATE}-zone --project=${GCP_PROJECT:-<unset>}"
+            ;;
+        *) echo "unknown DNS_PROVIDER: $DNS_PROVIDER" >&2; exit 1 ;;
+    esac
+    echo
+    echo "read-only, but NOT run: each batch is announced and"
+    echo "waited on. Approve it and it runs."
+}
+
+mutate() {
+    local verb="$1" sub="${2:-}"
+    [ -z "$sub" ] && { echo "usage: $0 $verb <subdomain>" >&2; exit 1; }
+    local name
+    case "$verb" in
+        add)          name="${sub}.${DOMAIN}" ;;
+        add-wildcard) name="*.${sub}.${DOMAIN}" ;;
+        remove)       name="${sub}.${DOMAIN}" ;;
+    esac
+    echo "$verb: $name  ->  $DOMAIN   (provider: $DNS_PROVIDER)"
+    echo
+
+    # The wildcard-depth rule again, applied BEFORE the record is created rather
+    # than discovered in a browser afterwards.
+    if [ "$verb" = "add" ]; then
+        local issued; issued=$(estate_get "certs.issued" | python3 -c 'import json,sys
+try: print("\n".join(json.load(sys.stdin)))
+except Exception: pass')
+        local covered=""
+        while IFS= read -r san; do
+            [ -z "$san" ] && continue
+            san_covers "$name" "$san" && { covered=1; break; }
+        done <<< "$issued"
+        [ -z "$covered" ] && {
+            echo "WARNING: '$name' is covered by no issued SAN." >&2
+            echo "         A wildcard matches ONE label. The record would" >&2
+            echo "         resolve and then fail TLS. Reissue the cert first." >&2
+            echo >&2
+        }
+    fi
+
+    echo "REFUSING: this changes live DNS." >&2
+    echo "  Nothing is created, modified or deleted on any account without" >&2
+    echo "  explicit approval for that specific action." >&2
+    exit 1
+}
+
+case "${1:-list}" in
+    list)                     list ;;
+    add|add-wildcard|remove)  mutate "$@" ;;
+    *) echo "usage: $0 [list|add <sub>|add-wildcard <sub>|remove <sub>]" >&2; exit 1 ;;
+esac

berth/ctrl/docs.sh

@@ -0,0 +1,27 @@
+#!/usr/bin/env bash
+# Documentation.
+#
+# Usage:
+#   ./docs.sh serve|graphs
+
+set -euo pipefail
+cd "$(dirname "$0")"
+
+source ./lib/config.sh
+source ./lib/estate.sh
+load_config
+
+case "${1:-serve}" in
+    serve)
+        echo "berth has no doc server yet — the README is the documentation."
+        echo "  $(cd .. && pwd)/README.md"
+        echo
+        echo "the estate, resolved:  make estate show"
+        ;;
+    graphs)
+        echo "not implemented. The estate file is the graph's source; a"
+        echo "renderer belongs with docgen/graphgen, which is another thread's"
+        echo "another thread's — so this is a handoff, not a stub to fill in here."
+        ;;
+    *) echo "usage: $0 [serve|graphs]" >&2; exit 1 ;;
+esac

berth/ctrl/env.d/aws.env

@@ -0,0 +1,14 @@
+# Target: AWS — the estate that actually runs today (mcrn.ar).
+TARGET_NAME=aws
+CLOUD=aws
+REGION=us-east-1
+INSTANCE_TYPE=t3.small
+
+# The Route53 hosted zone. It ALREADY EXISTS and is reused, never created —
+# see estate.sh's refusal to create a zone on this target.
+AWS_HOSTED_ZONE_ID=Z02279903503ZMIB5FC1N
+SSH_KEY_NAME=mcrn
+
+# certbot's DNS-01 plugin for this provider.
+CERTBOT_IMAGE_VAR=CERTBOT_AWS_IMAGE
+DNS_PROVIDER=route53

berth/ctrl/env.d/gcp.env

@@ -0,0 +1,17 @@
+# Target: GCP — the replica, on its own domain.
+#
+# The domain differs from AWS's on purpose: this target CREATES a DNS zone
+# where aws reuses one, so a shared domain would create a second authoritative
+# zone and break live DNS. The domain lives in estate/nrft.json, not here.
+TARGET_NAME=gcp
+CLOUD=gcp
+REGION=us-central1
+INSTANCE_TYPE=e2-small
+
+GCP_PROJECT=
+GCP_ZONE=us-central1-a
+
+# Delegation order: create the zone and let it answer first, then set the
+# nameservers at the registrar — it validates that they respond.
+CERTBOT_IMAGE_VAR=CERTBOT_GCP_IMAGE
+DNS_PROVIDER=google

berth/ctrl/estate.sh

@@ -0,0 +1,101 @@
+#!/usr/bin/env bash
+# The estate: what it is, what would change, and — behind a gate — changing it.
+#
+# Usage:
+#   ./estate.sh              # show
+#   ./estate.sh list         # every estate/*.json
+#   ./estate.sh plan         # tofu plan, read-only
+#   ./estate.sh apply --yes  # refuses without --yes
+#   ./estate.sh destroy --yes
+#
+# Why the default is read-only: ../README.md
+
+set -euo pipefail
+cd "$(dirname "$0")"
+
+source ./lib/config.sh
+source ./lib/estate.sh
+load_config
+
+show() {
+    echo "estate:   $ESTATE   ($ESTATE_FILE)"
+    echo "target:   $TARGET   (cloud=$CLOUD region=$REGION)"
+    echo "domain:   $DOMAIN"
+    echo "host:     $HOST   (sudo: $HOST_ADMIN)"
+    echo "workspace: $TOFU_WORKSPACE"
+    echo
+    local status; status=$(estate_get "_meta.status")
+    [ -n "$status" ] && echo "  !! $status" && echo
+
+    echo "services in scope for '$TARGET':"
+    local name host up kind raw
+    while IFS=$'\x1f' read -r name host up kind raw placement peer port lhost; do
+        [ -z "$name" ] && continue
+        printf '  %-12s %-14s %-24s %s%s\n' \
+            "$name" "${host:--}" "${up:--}" "$kind" \
+            "$([ -n "$raw" ] && echo '  [hand-written]')"
+    done < <(estate_services "$TARGET")
+
+    echo
+    echo "cert SANs (derived, not listed):"
+    estate_sans | sed 's/^/  /'
+}
+
+list() {
+    local f n
+    printf '%-12s %-16s %s\n' ESTATE DOMAIN STATUS
+    for f in ../estate/*.json; do
+        [ -f "$f" ] || continue
+        n=$(basename "$f" .json)
+        printf '%-12s %-16s %s%s\n' "$n" \
+            "$(python3 -c 'import json,sys;print(json.load(open(sys.argv[1])).get("domain",""))' "$f")" \
+            "$(python3 -c 'import json,sys;print(json.load(open(sys.argv[1])).get("_meta",{}).get("status",""))' "$f")" \
+            "$([ "$n" = "$ESTATE" ] && echo '   <- this one')"
+    done
+}
+
+# Read-only. Meaningful only once state is imported: against empty state,
+# plan reports "create N resources", which is not drift.
+plan() {
+    echo "== $TOFU_BIN plan =="
+    if ! command -v "$TOFU_BIN" >/dev/null; then
+        echo "   $TOFU_BIN not installed — skipped." >&2
+        echo "   OpenTofu is the MPL-2.0 fork; 'terraform' works identically." >&2
+    else
+        echo "   would run: $TOFU_BIN plan -var-file=<(estate)"
+    fi
+    echo
+    echo "NOTE: not wired up yet, and that is the point. tofu plan against empty"
+    echo "      state reports \"create N resources\" — which is not drift, it is an"
+    echo "      empty state. It becomes the check that proves the description"
+    echo "      matches reality only once state is IMPORTED from the inventory."
+    echo "      ppl/infra/ describes an aspiration: it was never applied."
+}
+
+# The gate. Two things have to be true: --yes present, AND the plan shown first.
+require_yes() {
+    local verb="$1"; shift
+    local yes=""
+    for a in "$@"; do [ "$a" = "--yes" ] && yes=1; done
+    if [ -z "$yes" ]; then
+        echo "refusing to $verb without --yes." >&2
+        echo >&2
+        echo "  $verb changes a live, billable estate and can take DNS with it." >&2
+        echo "  Read the plan first:  make estate plan" >&2
+        echo "  Then:                 ./ctrl/estate.sh $verb --yes" >&2
+        exit 1
+    fi
+    echo "refusing to $verb: not implemented, and deliberately so." >&2
+    echo "  The executor is not wired up, and nothing is imported yet, so" >&2
+    echo "  there is nothing truthful to apply." >&2
+    exit 1
+}
+
+case "${1:-show}" in
+    show)    show ;;
+    list)    list ;;
+    plan)    plan ;;
+    apply)   shift; require_yes apply "$@" ;;
+    destroy) shift; require_yes destroy "$@" ;;
+    *)       echo "usage: $0 [show|list|plan|apply --yes|destroy --yes]" >&2; exit 1 ;;
+esac

berth/ctrl/host.sh

@@ -0,0 +1,63 @@
+#!/usr/bin/env bash
+# The remote box — the other half of the inventory.
+#
+# Usage:
+#   ./host.sh status|ports|services
+#
+# Announces what it would run over `ssh $HOST` and does not run it. Always the
+# ssh alias, never a hostname: there is no `Host mcrn.ar` block, so a bare
+# hostname offers every agent key and trips MaxAuthTries.
+
+set -euo pipefail
+cd "$(dirname "$0")"
+
+source ./lib/config.sh
+source ./lib/estate.sh
+load_config
+
+guard_alias() {
+    if [[ "$HOST" == *.* ]]; then
+        echo "HOST='$HOST' is a hostname, not a ~/.ssh/config alias. Refusing." >&2
+        exit 1
+    fi
+}
+
+announce_batch() {
+    echo "would run, over 'ssh $HOST':"
+    printf '  %s\n' "$@"
+    echo
+    echo "read-only, and NOT run. Announce-first applies to EACH batch, not"
+    echo "once per session — so the commands can be read and"
+    echo "learned rather than scrolled past."
+}
+
+guard_alias
+case "${1:-status}" in
+    status)
+        announce_batch \
+            "uname -a; uptime; df -h /" \
+            "docker ps --format '{{.Names}}\t{{.Image}}\t{{.Ports}}'" \
+            "docker network inspect gateway --format '{{range .Containers}}{{.Name}} {{end}}'" \
+            "systemctl list-units --type=service --state=running --no-pager" \
+            "systemctl list-timers --no-pager"
+        echo
+        echo "sudo-only, over 'ssh $HOST_ADMIN' and only where genuinely needed:"
+        echo "  wg show           # the WireGuard peers that exist nowhere in the tree"
+        ;;
+    ports)
+        announce_batch "ss -ltnp"
+        echo "the estate declares these firewall rules:"
+        estate_get "firewall" | python3 -c '
+import json,sys
+for r in json.load(sys.stdin):
+    print("  %-6s %-5s %s" % (r["port"], r.get("proto","tcp"), r.get("desc","")))'
+        ;;
+    services)
+        announce_batch "docker compose -f ~/ppl/gateway/docker-compose.yml ps"
+        echo "the estate declares $(estate_services "$TARGET" | grep -c . ) service(s) for target '$TARGET'."
+        echo "the gateway compose declares 8. The difference is sibling repos'"
+        echo "stacks joining the shared 'gateway' network — intended design, but"
+        echo "nothing in the tree lists it. The inventory produces that list."
+        ;;
+    *) echo "usage: $0 [status|ports|services]" >&2; exit 1 ;;
+esac

berth/ctrl/lib/config.sh

@@ -0,0 +1,94 @@
+# Shared config loading. Sourced, never executed. Run from ctrl/.
+#
+# Precedence, weakest first:
+#   ctrl/versions.env        pinned toolchain          (committed)
+#   ctrl/env.d/<target>.env  provider shape: aws|gcp   (committed)
+#   ctrl/.env                machine-local + secrets   (gitignored)
+#   the caller's env         `make estate plan TARGET=gcp`  (always wins)
+
+CONFIG_OVERRIDABLE="TARGET ESTATE CLOUD REGION INSTANCE_TYPE
+                    HOST HOST_ADMIN AWS_PROFILE AWS_HOSTED_ZONE_ID
+                    GCP_PROJECT GCP_ZONE TOFU_WORKSPACE"
+
+# rig's port formula, reproduced rather than imported. cksum because it is
+# POSIX and gives the same value on every machine. Used to verify, not allocate.
+derive_port_base() {
+    local h; h=$(printf '%s' "$1" | cksum | awk '{print $1}')
+    echo $((20000 + (h % 200) * 10))
+}
+
+_config_restore() {
+    local line
+    while IFS= read -r line; do
+        if [ -n "$line" ]; then
+            eval "export $line"
+        fi
+    done <<< "$1"
+    # A while loop returns its last body command's status; the trailing empty
+    # line would otherwise make this return 1 and trip `set -e` in the caller.
+    return 0
+}
+
+load_config() {
+    local k saved=""
+    for k in $CONFIG_OVERRIDABLE; do
+        # ${!k+x} distinguishes "set but empty" from "unset" — an explicit
+        # FOO= on the command line is a real choice and must survive.
+        if [ -n "${!k+x}" ]; then
+            saved+="$k=$(printf '%q' "${!k}")"$'\n'
+        fi
+    done
+
+    set -a
+    source ./versions.env
+    [ -f ./.env ] && source ./.env
+    set +a
+
+    # Re-apply overrides now so TARGET is the caller's before we pick the file.
+    _config_restore "$saved"
+
+    local target="${TARGET:-aws}"
+    if [ ! -f "./env.d/${target}.env" ]; then
+        echo "no such target: env.d/${target}.env" >&2
+        echo "available: $(ls env.d/*.env 2>/dev/null | xargs -n1 basename | sed 's/\.env$//' | tr '\n' ' ')" >&2
+        exit 1
+    fi
+
+    set -a
+    source "./env.d/${target}.env"
+    [ -f ./.env ] && source ./.env
+    set +a
+
+    _config_restore "$saved"
+
+    TARGET="$target"
+
+    # Identity is explicit: berth never guesses which estate it is acting on.
+    # The one convenience: a single estate/*.json is used without being asked.
+    if [ -z "${ESTATE:-}" ]; then
+        local n; n=$(ls ../estate/*.json 2>/dev/null | wc -l)
+        if [ "$n" = "1" ]; then
+            ESTATE=$(basename "$(ls ../estate/*.json)" .json)
+        else
+            echo "ESTATE is not set and estate/ holds $n candidates — refusing to guess." >&2
+            echo "available: $(ls ../estate/*.json 2>/dev/null | xargs -n1 basename | sed 's/\.json$//' | tr '\n' ' ')" >&2
+            echo "set it: make estate show ESTATE=<name>, or ESTATE= in ctrl/.env" >&2
+            exit 1
+        fi
+    fi
+
+    ESTATE_FILE="../estate/${ESTATE}.json"
+    if [ ! -f "$ESTATE_FILE" ]; then
+        echo "no such estate: estate/${ESTATE}.json" >&2
+        echo "available: $(ls ../estate/*.json 2>/dev/null | xargs -n1 basename | sed 's/\.json$//' | tr '\n' ' ')" >&2
+        exit 1
+    fi
+
+    # Facts come from the estate file, never restated in a target env.
+    DOMAIN=$(estate_get "domain")
+    HOST="${HOST:-$(estate_get "host")}"
+    HOST_ADMIN="${HOST_ADMIN:-$(estate_get "host_admin")}"
+
+    # Workspace == target, so the two can never mean different things.
+    TOFU_WORKSPACE="${TOFU_WORKSPACE:-$TARGET}"
+}

berth/ctrl/lib/estate.sh

@@ -0,0 +1,147 @@
+# Reading and projecting estate/<name>.json. Sourced, never executed.
+#
+# python3 rather than jq: berth's floor already includes python3, so it is a
+# dependency berth has rather than one it adds.
+
+estate_get() {
+    python3 -c '
+import json, sys
+d = json.load(open(sys.argv[1]))
+for k in sys.argv[2].split("."):
+    if isinstance(d, list):
+        try: k = int(k)
+        except ValueError: sys.exit(0)
+    try: d = d[k]
+    except Exception: sys.exit(0)
+print("" if d is None else d if isinstance(d, str) else json.dumps(d))
+' "$ESTATE_FILE" "$1"
+}
+
+# Services in scope for one target. A service names its targets; absent = all.
+# Fields are US-separated (0x1f), not tab: tab is IFS whitespace, so bash
+# collapses a run of them and an empty field would shift every later column.
+estate_services() {
+    local target="${1:-$TARGET}"
+    python3 -c '
+import json, sys
+d = json.load(open(sys.argv[1]))
+target = sys.argv[2]
+for s in d.get("services", []):
+    tg = s.get("targets")
+    if tg is not None and target not in tg:
+        continue
+    print("\x1f".join([
+        s.get("name", ""),
+        s.get("host", ""),
+        str(s.get(target + "_upstream", s.get("upstream", "")) or ""),
+        s.get("kind", "proxy"),
+        "raw" if s.get("raw") else "",
+        s.get("placement", "box"),
+        s.get("peer", ""),
+        str(s.get("port", "") or ""),
+        s.get("local_host", s.get("host", "")),
+    ]))
+' "$ESTATE_FILE" "$target"
+}
+
+# The SAN list the services need, derived — never a literal list.
+estate_sans() {
+    python3 -c '
+import json, sys
+d = json.load(open(sys.argv[1]))
+domain = d["domain"]
+sans = [domain]
+depths = set()
+for s in d.get("services", []):
+    h = s.get("host", "")
+    if not h:
+        continue
+    # A wildcard matches exactly ONE label. "git" needs *.domain; "dlt.spr"
+    # needs *.spr.domain. The parent of the leaf is what has to be covered.
+    parent = h.split(".", 1)[1] if "." in h else ""
+    depths.add(parent)
+for p in sorted(depths):
+    sans.append("*." + (p + "." if p else "") + domain)
+for s in sans:
+    print(s)
+' "$ESTATE_FILE"
+}
+
+# Is <fqdn> covered by <san>? A wildcard matches exactly one label.
+san_covers() {
+    local fqdn="$1" san="$2"
+    [ "$fqdn" = "$san" ] && return 0
+    case "$san" in
+        \*.*)
+            local suffix="${san#\*.}"
+            # Must end in .suffix AND have exactly one extra label.
+            case "$fqdn" in
+                *".$suffix") [ "${fqdn%".$suffix"}" = "${fqdn%%.*}" ] && return 0 ;;
+            esac
+            ;;
+    esac
+    return 1
+}
+
+# ── the overlay ────────────────────────────────────────────────────────────
+
+# Every overlay name, one per line.
+overlay_names() {
+    python3 -c '
+import json, sys
+d = json.load(open(sys.argv[1]))
+for n in d.get("vpn", {}).get("overlays", {}):
+    print(n)
+' "$ESTATE_FILE"
+}
+
+# Peers of one overlay, US-separated:
+#   name, address, role, endpoint, public_key, allowed_ips, keepalive
+overlay_peers() {
+    python3 -c '
+import json, sys
+d = json.load(open(sys.argv[1]))
+ov = d.get("vpn", {}).get("overlays", {}).get(sys.argv[2], {})
+for name, p in ov.get("peers", {}).items():
+    print("\x1f".join(str(x) if x is not None else "" for x in [
+        name, p.get("address"), p.get("role"), p.get("endpoint"),
+        p.get("public_key"), p.get("allowed_ips"), p.get("keepalive"),
+    ]))
+' "$ESTATE_FILE" "$1"
+}
+
+overlay_get() { estate_get "vpn.overlays.$1.$2"; }
+
+# Is an address inside a CIDR? Pure python so there is no ipcalc dependency —
+# berth's floor already includes python3 because the IaC side needs it.
+addr_in_subnet() {
+    python3 -c '
+import ipaddress, sys
+try:
+    sys.exit(0 if ipaddress.ip_address(sys.argv[1]) in ipaddress.ip_network(sys.argv[2], strict=False) else 1)
+except ValueError:
+    sys.exit(2)
+' "$1" "$2"
+}
+
+# The upstream a service actually resolves to, as "host:port".
+#
+# A PLACED service has no literal `upstream` field: ✖ B9 replaced langfuse's
+# hand-written `10.8.0.2:3000` with placement+peer+port, because being reached
+# by address on the overlay is ONE decision, not three properties. Everything
+# that asks "what does this service point at" must therefore resolve it the
+# same way, or it silently sees an empty string and skips the service — which
+# is exactly how vpn.sh's bindings invariant went quiet after B9 landed.
+#
+# usage: service_upstream <up> <placement> <peer> <port>
+service_upstream() {
+    local up="$1" placement="$2" peer="$3" port="$4"
+    case "$placement" in
+        local|instance)
+            local addr; addr="$(overlay_get estate "peers.${peer}.address")"
+            [ -z "$addr" ] && return 1
+            printf '%s:%s' "$addr" "$port"
+            ;;
+        *) printf '%s' "$up" ;;
+    esac
+}

berth/ctrl/ports.sh

@@ -0,0 +1,78 @@
+#!/usr/bin/env bash
+# The local port map, and whether it still agrees with rig.
+#
+# Usage:
+#   ./ports.sh show     # DERIVED / ACTIVE / SOURCE
+#   ./ports.sh verify   # recompute rig's formula, report drift
+#
+# berth recomputes rig's port formula rather than importing it, so neither
+# depends on the other. See ../README.md.
+
+set -euo pipefail
+cd "$(dirname "$0")"
+
+source ./lib/config.sh
+source ./lib/estate.sh
+load_config
+
+# name<US>host<US>local_port for everything that has one.
+_local_ports() {
+    python3 -c '
+import json, sys
+d = json.load(open(sys.argv[1]))
+for s in d.get("services", []):
+    p = s.get("local_port")
+    if p:
+        print("\x1f".join([s.get("name",""), s.get("host",""), str(p)]))
+' "$ESTATE_FILE"
+}
+
+show() {
+    local ld; ld=$(estate_get "local_domain"); : "${ld:=local.ar}"
+    printf '%-12s %-22s %-8s %-8s %s\n' NAME ADDRESS ACTIVE DERIVED SOURCE
+    local name host port base
+    while IFS=$'\x1f' read -r name host port; do
+        [ -z "$name" ] && continue
+        base=$(derive_port_base "$host")
+        if [ "$port" = "$base" ]; then
+            printf '%-12s %-22s %-8s %-8s %s\n' "$name" "${host}.${ld}" "$port" "$base" "derived"
+        else
+            printf '%-12s %-22s %-8s %-8s %s\n' "$name" "${host}.${ld}" "$port" "$base" "override"
+        fi
+    done < <(_local_ports)
+    echo
+    echo "DERIVED is what rig's formula gives for that name. ACTIVE is what the"
+    echo "estate records. 'override' is not an error — most of these were never"
+    echo "rigs. 'make ports verify' says which ones should have matched."
+}
+
+verify() {
+    local name host port base rc=0 checked=0
+    while IFS=$'\x1f' read -r name host port; do
+        [ -z "$name" ] && continue
+        # Only 20000-21999 is rig's to predict; anything else was never derived.
+        if [ "$port" -lt 20000 ] || [ "$port" -gt 21999 ]; then
+            continue
+        fi
+        checked=$((checked + 1))
+        base=$(derive_port_base "$host")
+        if [ "$port" != "$base" ]; then
+            echo "DRIFT  $name (${host}): estate says $port, rig's formula gives $base"
+            echo "       either the rig pinned HTTP_PORT in its ctrl/.env, or the"
+            echo "       folder was renamed. The Caddy map is stale either way."
+            rc=1
+        else
+            echo "ok     $name (${host}): $port"
+        fi
+    done < <(_local_ports)
+    echo
+    echo "checked $checked rig-shaped port(s) in 20000-21999."
+    [ "$rc" = 0 ] && echo "no drift." || echo "drift found — regenerate with 'make services render local'."
+    return 0
+}
+
+case "${1:-show}" in
+    show)   show ;;
+    verify) verify ;;
+    *)      echo "usage: $0 [show|verify]" >&2; exit 1 ;;
+esac

berth/ctrl/registry.sh

@@ -0,0 +1,33 @@
+#!/usr/bin/env bash
+# The image registry — remote, and reachable only over the overlay.
+#
+# Usage:
+#   ./registry.sh status
+#
+# One verb: berth reports on a registry running on someone else's box. Starting
+# and stopping it is that box's business.
+
+set -euo pipefail
+cd "$(dirname "$0")"
+
+source ./lib/config.sh
+source ./lib/estate.sh
+load_config
+
+status() {
+    local wg_server; wg_server=$(overlay_get estate "peers.box.address")
+    echo "registry:  registry.${DOMAIN}   (public pull via /v2/)"
+    echo "push:      ${wg_server}:5000    (WireGuard-only, not in the firewall)"
+    echo
+    echo "would run:"
+    echo "  curl -s https://registry.${DOMAIN}/v2/_catalog"
+    echo
+    echo "NOTE: the push endpoint binds ${wg_server}, and $(estate_get 'vpn._status')."
+    echo "      A freshly-provisioned box cannot start the gateway compose file"
+    echo "      at all, because that bind fails."
+}
+
+case "${1:-status}" in
+    status) status ;;
+    *) echo "usage: $0 [status]" >&2; exit 1 ;;
+esac

berth/ctrl/render/nginx-proxy.tmpl

@@ -0,0 +1,32 @@
+# ${NAME} — GENERATED by berth from estate/${ESTATE}.json. Do not edit.
+# Edit the estate file and re-run: make services render aws
+
+server {
+    listen 80;
+    server_name ${FQDN};
+    return 301 https://$host$request_uri;
+}
+
+server {
+    listen 443 ssl;
+    server_name ${FQDN};
+
+    ssl_certificate     /etc/nginx/certs/live/${DOMAIN}/fullchain.pem;
+    ssl_certificate_key /etc/nginx/certs/live/${DOMAIN}/privkey.pem;
+
+    # Docker's embedded DNS. Naming the upstream in a VARIABLE forces runtime
+    # resolution, so nginx STARTS even when the upstream container is absent.
+    # With a literal proxy_pass, one stopped container takes the whole gateway
+    # down at reload — which is what makes one nginx able to front a dozen
+    # independent compose stacks.
+    resolver 127.0.0.11 valid=30s;
+
+    location / {
+        set $upstream_${NAME} ${UPSTREAM_HOST};
+        proxy_pass http://$upstream_${NAME}:${UPSTREAM_PORT};
+        proxy_set_header Host              $host;
+        proxy_set_header X-Real-IP         $remote_addr;
+        proxy_set_header X-Forwarded-For   $proxy_add_x_forwarded_for;
+        proxy_set_header X-Forwarded-Proto $scheme;
+    }
+}

berth/ctrl/render/nginx-static.tmpl

@@ -0,0 +1,23 @@
+# ${NAME} — GENERATED by berth from estate/${ESTATE}.json. Do not edit.
+# Edit the estate file and re-run: make services render aws
+
+server {
+    listen 80;
+    server_name ${FQDN};
+    return 301 https://$host$request_uri;
+}
+
+server {
+    listen 443 ssl;
+    server_name ${FQDN};
+
+    ssl_certificate     /etc/nginx/certs/live/${DOMAIN}/fullchain.pem;
+    ssl_certificate_key /etc/nginx/certs/live/${DOMAIN}/privkey.pem;
+
+    root /usr/share/nginx/html/${NAME};
+    index index.html;
+
+    location / {
+        try_files $uri $uri/ =404;
+    }
+}

berth/ctrl/render/nginx-upstream.tmpl

@@ -0,0 +1,32 @@
+# ${NAME} — GENERATED by berth from estate/${ESTATE}.json. Do not edit.
+# Placement: ${PLACEMENT} (${PEER}) — reached over the overlay, not the docker network.
+
+upstream ${NAME}_backend {
+    server ${UPSTREAM_HOST}:${UPSTREAM_PORT};
+}
+
+server {
+    listen 80;
+    server_name ${FQDN};
+    return 301 https://$host$request_uri;
+}
+
+server {
+    listen 443 ssl;
+    server_name ${FQDN};
+
+    ssl_certificate /etc/nginx/certs/live/${DOMAIN}/fullchain.pem;
+    ssl_certificate_key /etc/nginx/certs/live/${DOMAIN}/privkey.pem;
+
+    # No `resolver`, and no `set $var` indirection — deliberately. Those exist so
+    # nginx starts when a CONTAINER is absent; this upstream is a literal address
+    # on the overlay, which needs no DNS at all. The three properties are one
+    # decision, and placement is what decides them.
+    location / {
+        proxy_pass http://${NAME}_backend;
+        proxy_set_header Host              $host;
+        proxy_set_header X-Real-IP         $remote_addr;
+        proxy_set_header X-Forwarded-For   $proxy_add_x_forwarded_for;
+        proxy_set_header X-Forwarded-Proto $scheme;
+    }
+}

berth/ctrl/selftest.sh

@@ -0,0 +1,210 @@
+#!/usr/bin/env bash
+# What berth has settled, and what it has withdrawn, written down as assertions.
+#
+# Two halves:
+#   - decisions that hold. Failing one means "you are about to undo this".
+#   - every entry in ../STALE.md. Failing one means a withdrawn assumption came
+#     back. That is the half that makes STALE.md an audit surface and not an
+#     archive — a retraction nobody re-reads is a retraction that decays.
+#
+# Scope: no cloud, no ssh, no sudo, no network. Cheap enough to actually run.
+# `make check` reports on the world and never fails; this exits 1, like rig's.
+#
+# Usage: make selftest   (or: bash ctrl/selftest.sh)
+set -uo pipefail          # NOT -e: one failing check must not abort the rest
+cd "$(dirname "$0")"
+
+source ./lib/config.sh
+
+rc=0
+passed=0
+check() {   # name, expected, actual
+    if [ "$2" = "$3" ]; then
+        printf '  ok    %s\n' "$1"
+        passed=$((passed + 1))
+    else
+        printf '  FAIL  %s\n        expected: %s\n        got:      %s\n' "$1" "$2" "$3"
+        rc=1
+    fi
+}
+note() { printf '\n%s\n' "$1"; }
+skip() { printf '  skip  %s (%s)\n' "$1" "$2"; }
+
+# An absence check must not match the files that RECORD the absence. STALE.md
+# names every withdrawn thing by definition, and this file names them again to
+# assert them — so both are excluded, or every check fails on itself. rig hits
+# the same wall and assembles its pattern from fragments for the same reason.
+NOSELF="--exclude=selftest.sh --exclude=STALE.md"
+absent() { grep -rIl $NOSELF "$@" 2>/dev/null | wc -l; }
+
+# A throwaway estate, for the checks that have to run berth rather than read it.
+TMP_ESTATE=_selftest
+cleanup() { rm -f "../estate/${TMP_ESTATE}.json"; }
+trap cleanup EXIT
+
+note "the withdrawn assumptions — ../STALE.md, one check each"
+
+# B1 — Pulumi. The two surviving mentions are historical fact about ppl/infra
+# and live in README.md and the estate, not in anything that runs.
+check "B1  no pulumi in the code" "0" "$(absent -i pulumi . ../Makefile)"
+
+# B2 — the ctlptl precedent. Withdrawn; the argument stands on its own now.
+check "B2  the withdrawn precedent is cited nowhere" "0" "$(absent -i ctlptl ..)"
+
+# B3 — `wg show <if> dump` leaks the private key in field 1. Stating only
+# show-vs-showconf makes the dump form read as safe.
+check "B3  all three wg forms are named" "yes" \
+    "$(grep -q 'dump' vpn.sh && grep -q 'showconf' vpn.sh && echo yes || echo no)"
+check "B3  capture refuses showconf-shaped input" "1" \
+    "$(printf '[Interface]\nPrivateKey = x\n' | bash vpn.sh capture >/dev/null 2>&1; echo $?)"
+check "B3  capture refuses dump-shaped input" "1" \
+    "$(printf 'priv\tpub\t51820\toff\n' | bash vpn.sh capture >/dev/null 2>&1; echo $?)"
+
+# B4 — keepalive belongs to the peer that DIALS, not the one that roams. The
+# first version warned on a correctly configured overlay, so the check is run
+# against one: hub carries the keepalive, nrft roams.
+python3 - <<'PY'
+import json, collections
+d = json.load(open("../estate/mcrn.json"), object_pairs_hook=collections.OrderedDict)
+d["vpn"]["overlays"]["estate"]["peers"]["box"]["keepalive"] = 25
+json.dump(d, open("../estate/_selftest.json", "w"), indent=2, ensure_ascii=False)
+PY
+check "B4  a correct overlay raises no keepalive warning" "0" \
+    "$(ESTATE=$TMP_ESTATE bash vpn.sh check 2>/dev/null | grep -ci 'no peer entry carries')"
+
+# B6 — public keys are 44-char base64 too, so shape alone would flag correct
+# data. Same fixture, with a real-shaped public key on a peer.
+python3 - <<'PY'
+import base64, collections, json, os
+d = json.load(open("../estate/_selftest.json"), object_pairs_hook=collections.OrderedDict)
+d["vpn"]["overlays"]["estate"]["peers"]["box"]["public_key"] = base64.b64encode(os.urandom(32)).decode()
+json.dump(d, open("../estate/_selftest.json", "w"), indent=2, ensure_ascii=False)
+PY
+check "B6  a public key does not trip the secret check" "0" \
+    "$(ESTATE=$TMP_ESTATE bash vpn.sh check 2>/dev/null | grep -c 'FAIL.*key')"
+
+cleanup   # the fixture is done with; two estate files would make load_config
+          # refuse to guess below, which is right but reads as a config failure
+
+# B5 — the pass-through block must be LAST, or a subcommand that names a real
+# target runs that target too. Checked through make, not by reading the file.
+note "B5  a subcommand that names a target dispatches once"
+for combo in "host ports" "host services" "vpn check" "vpn show estate" "estate show"; do
+    check "    make $combo" "1" \
+        "$(cd .. && make -n $combo 2>/dev/null | grep -c 'bash ctrl/')"
+done
+
+# B7 — the overlay moved out of network.wireguard into a top-level vpn block.
+check "B7  nothing reads network.wireguard" "0" "$(absent 'network\.wireguard' .)"
+
+# B8 — peers, not relatives. berth sources nothing from rig.
+check "B8  berth sources nothing from rig" "0" "$(absent -E 'rig/ctrl|\.\./rig' .)"
+
+# B9 — langfuse was filed as an exception a template could not express. It was
+# the general case. The proof is a live route: render it and diff against the
+# hand-written file, normalised for comments and whitespace.
+LIVE=/home/mariano/wdir/semester/ppl/gateway/nginx/conf.d/langfuse.conf
+if [ -f "$LIVE" ]; then
+    norm() { sed -e 's/#.*//' -e 's/[[:space:]]\+/ /g' -e 's/^ //' -e 's/ $//' -e '/^$/d' "$1"; }
+    bash services.sh render aws >/dev/null 2>&1
+    check "B9  the generated vhost reproduces the live one" "same" \
+        "$(diff -q <(norm ./render/out/aws/langfuse.conf) <(norm "$LIVE") >/dev/null 2>&1 \
+            && echo same || echo different)"
+else
+    skip "B9  generated vhost matches the live one" "ppl not on this machine"
+fi
+
+note "the safety contract — berth's verbs are not all safe"
+
+check "estate defaults to show"   "show"   "$(cd .. && make -n estate 2>/dev/null | grep -oE 'estate\.sh [a-z]+' | awk '{print $2}')"
+check "certs defaults to status"  "status" "$(cd .. && make -n certs  2>/dev/null | grep -oE 'certs\.sh [a-z]+'  | awk '{print $2}')"
+check "dns defaults to list"      "list"   "$(cd .. && make -n dns    2>/dev/null | grep -oE 'dns\.sh [a-z]+'    | awk '{print $2}')"
+check "vpn defaults to list"      "list"   "$(cd .. && make -n vpn    2>/dev/null | grep -oE 'vpn\.sh [a-z]+'    | awk '{print $2}')"
+
+for verb in apply destroy; do
+    check "estate $verb refuses without --yes" "1" \
+        "$(bash estate.sh "$verb" >/dev/null 2>&1; echo $?)"
+done
+for verb in renew push; do
+    check "certs $verb refuses"                "1" \
+        "$(bash certs.sh "$verb" >/dev/null 2>&1; echo $?)"
+done
+check "dns add refuses to change live DNS" "1" \
+    "$(bash dns.sh add selftest >/dev/null 2>&1; echo $?)"
+check "vpn up refuses without --yes" "1" \
+    "$(bash vpn.sh up >/dev/null 2>&1; echo $?)"
+
+note "config — the caller's env beats the files"
+
+# Generated from CONFIG_OVERRIDABLE, so a new key enrols itself.
+test_value() {
+    case "$1" in
+        TARGET)  echo "gcp" ;;
+        ESTATE)  echo "mcrn" ;;
+        *)       echo "selftest-sentinel" ;;
+    esac
+}
+for key in $CONFIG_OVERRIDABLE; do
+    want="$(test_value "$key")"
+    got="$(export "$key=$want"; load_config >/dev/null 2>&1; echo "${!key}")"
+    check "  caller's $key wins" "$want" "$got"
+done
+
+note "rig agreement — recomputed, never imported"
+
+# rig pins these same constants in its own selftest. Both arrive at them from
+# the same formula with no shared code, which is the coupling rule made testable.
+check "derive_port_base rig"     "20310" "$(derive_port_base rig)"
+check "derive_port_base foo"     "21690" "$(derive_port_base foo)"
+check "derive_port_base my-proj" "21030" "$(derive_port_base my-proj)"
+
+note "containment — berth writes nothing outside berth/"
+
+check "no tracked change outside berth/" "0" \
+    "$(cd ../.. && git status --porcelain 2>/dev/null | grep -vc '^.. berth/')"
+check "generated output is ignored" "yes" \
+    "$(cd .. && git check-ignore -q ctrl/render/out && echo yes || echo no)"
+# A trailing-slash pattern matches directories only, so ask about a path
+# inside it rather than the (not-yet-existing) directory itself.
+check "key material is ignored" "yes" \
+    "$(cd .. && git check-ignore -q ctrl/.secrets/vpn/any.key && echo yes || echo no)"
+
+note "capture and the checks that read it — three bugs found by running, 2026-09-14"
+
+# 1. A placed service's upstream is DERIVED (✖ B9). Anything reading the raw
+#    `upstream` field sees "" and skips it — which is how vpn.sh's bindings
+#    invariant, the "my configurations broke" detector, went quiet the day
+#    placement landed while still printing OK. Vacuous passes are the failure
+#    mode this whole file exists to catch.
+check "a placed service resolves to a real upstream" "10.8.0.2:3000" \
+    "$(bash -c 'source ./lib/config.sh; source ./lib/estate.sh; load_config >/dev/null;
+       service_upstream "" local nrft 3000')"
+check "bindings actually inspects a service" "1" \
+    "$(bash ./vpn.sh check 2>/dev/null | grep -c 'no service currently has an overlay address' \
+       | awk '{print 1-$1}')"
+
+# 2. A listen port belongs to a PEER. The roaming peer's is an ephemeral source
+#    port; writing it to the overlay renames the port the firewall rule is
+#    checked against — silently, since both are plausible integers.
+check "a roaming peer's port is not the overlay's port" "51820" \
+    "$(python3 -c 'import json;print(json.load(open("../estate/mcrn.json"))["vpn"]["overlays"]["estate"]["listen_port"])')"
+
+# 3. _status is always non-empty — capture rewrites it rather than clearing it —
+#    so a warning gated on "is it set" can never turn off, including after the
+#    capture it asks for. Gate on the structure instead.
+check "the capture warning clears once keys are in" "0" \
+    "$(bash ./check.sh 2>/dev/null | grep -c 'public keys not captured')"
+
+note "every STALE entry has a check here"
+
+# Not "$0": line 15 cd's into this script's directory, so a relative $0 no
+# longer resolves. After the cd the file is simply selftest.sh.
+# Ids are counted wherever they appear — B5's sits in a note(), not a check name.
+entries="$(grep -c '^\*\*✖ B' ../STALE.md)"
+checked="$(grep -oE '\bB[1-9][0-9]?\b' selftest.sh | sort -u | wc -l)"
+check "STALE.md entries are all covered" "$entries" "$checked"
+
+printf '\n%d passed' "$passed"
+[ "$rc" -ne 0 ] && printf ', SOME FAILED'
+printf '\n'
+exit "$rc"

berth/ctrl/services.sh

@@ -0,0 +1,183 @@
+#!/usr/bin/env bash
+# Gateway routes, projected from the estate onto one target.
+#
+# Usage:
+#   ./services.sh                 # list
+#   ./services.sh render aws      # -> render/out/aws/*.conf   (nginx vhosts)
+#   ./services.sh render local    # -> render/out/local/Caddyfile
+#   ./services.sh deploy          # refuses; ppl/ctrl/deploy.sh ships config
+#
+# Each target is a projection with its own rules, not a format conversion.
+# The nine axes they disagree on, and the install order: ../README.md
+
+set -euo pipefail
+cd "$(dirname "$0")"
+
+source ./lib/config.sh
+source ./lib/estate.sh
+load_config
+
+OUT_ROOT="./render/out"
+
+list() {
+    printf '%-12s %-16s %-22s %-9s %s\n' NAME FQDN UPSTREAM PLACEMENT SOURCE
+    local name host up kind raw
+    while IFS=$'\x1f' read -r name host up kind raw placement peer port lhost; do
+        [ -z "$name" ] && continue
+        # A placed service has no literal `upstream` — it is derived from the
+        # peer's overlay address, so show what it actually resolves to.
+        local shown; shown="$(service_upstream "$up" "$placement" "$peer" "$port")" || shown=""
+        printf '%-12s %-16s %-22s %-9s %s\n' \
+            "$name" "${host}.${DOMAIN}" "${shown:--}" "$placement" \
+            "$([ -n "$raw" ] && echo 'hand-written' || echo 'generated')"
+    done < <(estate_services "$TARGET")
+    echo
+    echo "hand-written entries are NOT generated and NOT overwritten."
+    echo "run 'make estate show' to see why each one is an exception."
+}
+
+render_cloud() {
+    # Two statements: `local a="$1" b="$a"` expands all arguments before any
+    # assignment, so $a would still be unset.
+    local target="$1"
+    local out="$OUT_ROOT/$target"
+    rm -rf "$out"; mkdir -p "$out"
+    local name host up kind raw uhost uport n=0 skipped=0
+
+    while IFS=$'\x1f' read -r name host up kind raw placement peer port lhost; do
+        [ -z "$name" ] && continue
+        if [ -n "$raw" ]; then
+            skipped=$((skipped + 1))
+            continue
+        fi
+        # Placement picks the rendering. A container on the estate's own network
+        # is reached by NAME through docker's resolver; anything on the overlay
+        # is reached by ADDRESS and needs no DNS. That is one decision, not the
+        # three properties (upstream{}, no resolver, no set $var) it produces.
+        local tmpl
+        case "$placement" in
+            local|instance)
+                tmpl=./render/nginx-upstream.tmpl
+                uhost="$(overlay_get estate "peers.${peer}.address")"
+                uport="$port"   # resolved via service_upstream's same rule
+                if [ -z "$uhost" ]; then
+                    echo "  ! $name: placement '$placement' names peer '$peer', which has no address" >&2
+                    continue
+                fi
+                ;;
+            hosted)
+                echo "  ! $name: placement 'hosted' is declared but not rendered yet" >&2
+                continue
+                ;;
+            *)
+                if [ "$kind" = "static" ]; then
+                    tmpl=./render/nginx-static.tmpl
+                    uhost=""; uport=""
+                else
+                    tmpl=./render/nginx-proxy.tmpl
+                    uhost="${up%%:*}"; uport="${up##*:}"
+                fi
+                ;;
+        esac
+        sed -e "s|\${NAME}|${name}|g" \
+            -e "s|\${ESTATE}|${ESTATE}|g" \
+            -e "s|\${FQDN}|${host}.${DOMAIN}|g" \
+            -e "s|\${DOMAIN}|${DOMAIN}|g" \
+            -e "s|\${PLACEMENT}|${placement}|g" \
+            -e "s|\${PEER}|${peer}|g" \
+            -e "s|\${UPSTREAM_HOST}|${uhost}|g" \
+            -e "s|\${UPSTREAM_PORT}|${uport}|g" \
+            "$tmpl" > "$out/${name}.conf"
+        n=$((n + 1))
+    done < <(estate_services "$target")
+
+    echo "wrote $n vhost(s) to $out/  ($skipped hand-written, left alone)"
+    cat <<EONOTE
+
+TO INSTALL THESE, THREE THINGS MUST HAPPEN IN THIS ORDER — and the order is the
+whole reason this is not a one-liner:
+
+ 1. These land in conf.d/generated/, NOT conf.d/. ppl/ctrl/deploy.sh rsyncs the
+    gateway with --delete; generated and hand-written config sharing one
+    directory means one of them gets erased.
+
+ 2. nginx.conf needs a THIRD include line. Its conf.d/*.conf glob does not
+    recurse — which is exactly why conf.d/soleprint/*.conf already needs its
+    own line at nginx.conf:28-30.
+
+ 3. That new include changes LOAD ORDER, and load order decides which :443
+    block catches unmatched names. So default.conf's commented-out
+    ':443 default_server' must be restored FIRST. 'make check' fails on this
+    today, deliberately — it is a gate, not a warning.
+EONOTE
+}
+
+render_local() {
+    local out="$OUT_ROOT/local"; mkdir -p "$out"
+    local ld; ld=$(estate_get "local_domain")
+    : "${ld:=local.ar}"
+    local name host up kind raw port drift=0
+
+    {
+        cat <<EOH
+# GENERATED by berth from estate/${ESTATE}.json. Do not edit.
+# Regenerate: make services render local
+#
+# Install: sudo ln -sf \$PWD/Caddyfile /etc/caddy/Caddyfile && sudo systemctl reload caddy
+# All *.${ld} resolve to 127.0.0.1 via dnsmasq.
+#
+# Every site address carries an explicit :80. Without it Caddy 2 defaults to
+# :443 with auto-HTTPS, which on *.${ld} means cert provisioning attempts that
+# fail and break the listener. Plain HTTP only on this host.
+#
+# Caddy matches the MOST SPECIFIC site address, not the first — the opposite of
+# nginx, which matches exactly and otherwise falls to default_server. A name set
+# that is unambiguous here can be ambiguous on the box.
+EOH
+        while IFS=$'\x1f' read -r name host up kind raw placement peer port lhost; do
+            [ -z "$name" ] && continue
+            port=$(python3 -c '
+import json,sys
+d=json.load(open(sys.argv[1]))
+for s in d.get("services",[]):
+    if s.get("name")==sys.argv[2]:
+        print(s.get("local_port") or ""); break
+' "$ESTATE_FILE" "$name")
+            [ -z "$port" ] && continue
+            echo
+            echo "${lhost}.${ld}:80, *.${lhost}.${ld}:80 {"
+            echo "	reverse_proxy localhost:${port}"
+            echo "}"
+        done < <(estate_services local)
+    } > "$out/Caddyfile"
+
+    echo "wrote $out/Caddyfile"
+    echo
+    echo "rig is not consulted and does not know this exists — its handover"
+    echo "scrub refuses the string '${ld}'. Where a port belongs to a rig,"
+    echo "'make ports verify' RECOMPUTES rig's formula to check it rather than"
+    echo "importing rig's code. Convention, verified; not a dependency."
+}
+
+case "${1:-list}" in
+    list)   list ;;
+    render)
+        shift
+        # `case "${1:-X}"` defaults the match but leaves $1 empty.
+        t="${1:-$TARGET}"
+        case "$t" in
+            local)     render_local ;;
+            aws|gcp)   render_cloud "$t" ;;
+            *) echo "usage: $0 render [aws|gcp|local]" >&2; exit 1 ;;
+        esac
+        ;;
+    deploy)
+        echo "berth does not ship config; ppl/ctrl/deploy.sh does." >&2
+        echo "  berth's half is the DESCRIPTION and the render. Shipping is" >&2
+        echo "  rsync + compose against a live box, and it belongs where the" >&2
+        echo "  credentials are: berth is the tool, ppl is the estate that" >&2
+        echo "  holds the secrets." >&2
+        exit 1
+        ;;
+    *) echo "usage: $0 [list|render [aws|gcp|local]|deploy]" >&2; exit 1 ;;
+esac

berth/ctrl/versions.env

@@ -0,0 +1,11 @@
+# Pinned toolchain. Committed. The weakest config layer.
+
+# The infra executor. One, not a pair — see README.md.
+# This pin is a placeholder; set it from `tofu version` once installed.
+TOFU_VERSION=1.9.0
+TOFU_BIN=tofu
+
+# certbot runs as a throwaway container so the DNS plugin's credentials never
+# have to be installed on this machine.
+CERTBOT_AWS_IMAGE=certbot/dns-route53:latest
+CERTBOT_GCP_IMAGE=certbot/dns-google:latest

berth/ctrl/vpn.sh

@@ -0,0 +1,478 @@
+#!/usr/bin/env bash
+# Overlays — WireGuard as berth's network layer.
+#
+# Usage:
+#   ./vpn.sh                        # list
+#   ./vpn.sh show <overlay>         # topology
+#   ./vpn.sh check                  # invariants
+#   ./vpn.sh render <peer>          # peer's wg0.conf -> render/out/vpn/
+#   ./vpn.sh keygen <peer>          # keypair -> .secrets/; prints only the public key
+#   ./vpn.sh up|down --yes          # refuses; the host operates its own tunnel
+#
+#   sudo wg show | ./vpn.sh capture [--write]
+#
+# `wg show` is the only safe form: `wg show <if> dump` puts the private key in
+# field 1, and `wg showconf` prints it outright. capture refuses both.
+#
+# Rationale, topology and key handling: ../README.md
+
+set -euo pipefail
+cd "$(dirname "$0")"
+
+source ./lib/config.sh
+source ./lib/estate.sh
+load_config
+
+SECRETS_DIR="./.secrets/vpn"
+OUT_DIR="./render/out/vpn"
+
+WORST=0
+note() { echo "  $*"; }
+warn() { echo "  WARN  $*"; [ "$WORST" -lt 1 ] && WORST=1; return 0; }
+bad()  { echo "  FAIL  $*"; WORST=2; return 0; }
+
+# Which addresses belong to THIS machine, so checks can distinguish what they
+# can actually see from what needs capturing elsewhere.
+my_overlay_addrs() { ip -4 -o addr show 2>/dev/null | awk '{split($4,a,"/"); print a[1]}'; }
+is_me() { my_overlay_addrs | grep -qxF "$1"; }
+
+list() {
+    local n sub port peers
+    for n in $(overlay_names); do
+        sub=$(overlay_get "$n" subnet)
+        port=$(overlay_get "$n" listen_port)
+        peers=$(overlay_peers "$n" | grep -c . || true)
+        printf '%-10s %-16s port %-7s %s peer(s)\n' "$n" "$sub" "$port" "$peers"
+        note "$(overlay_get "$n" purpose)"
+    done
+    local st; st=$(estate_get "vpn._status")
+    [ -n "$st" ] && { echo; echo "  !! $st"; }
+}
+
+show() {
+    local ov="${1:-}"
+    [ -z "$ov" ] && { echo "usage: $0 show <overlay>" >&2; exit 1; }
+    overlay_names | grep -qxF "$ov" || {
+        echo "no such overlay: $ov" >&2
+        echo "available: $(overlay_names | tr '\n' ' ')" >&2; exit 1; }
+
+    echo "overlay: $ov   subnet $(overlay_get "$ov" subnet)   udp/$(overlay_get "$ov" listen_port)"
+    echo
+    printf '%-8s %-12s %-9s %-22s %s\n' PEER ADDRESS ROLE ENDPOINT PUBKEY
+    local name addr role ep pk aips ka
+    while IFS=$'\x1f' read -r name addr role ep pk aips ka; do
+        [ -z "$name" ] && continue
+        printf '%-8s %-12s %-9s %-22s %s%s\n' \
+            "$name" "$addr" "$role" "${ep:-—}" "${pk:-—}" \
+            "$(is_me "$addr" && echo '   <- this machine')"
+    done < <(overlay_peers "$ov")
+}
+
+check() {
+    local ov name addr role ep pk aips ka
+    for ov in $(overlay_names); do
+        local sub port
+        sub=$(overlay_get "$ov" subnet); port=$(overlay_get "$ov" listen_port)
+        echo "overlay '$ov' — $sub udp/$port"
+
+        # 1. addresses: unique, and inside the subnet. Two peers sharing an
+        #    address is a silent misroute, never an error message.
+        local addrs; addrs=$(overlay_peers "$ov" | cut -d$'\x1f' -f2 | grep -v '^$' || true)
+        local dupes; dupes=$(echo "$addrs" | sort | uniq -d)
+        [ -n "$dupes" ] && bad "duplicate peer addresses: $(echo "$dupes" | tr '\n' ' ')"
+        while IFS= read -r a; do
+            [ -z "$a" ] && continue
+            addr_in_subnet "$a" "$sub" || bad "$a is outside $sub"
+        done <<< "$addrs"
+
+        while IFS=$'\x1f' read -r name addr role ep pk aips ka; do
+            [ -z "$name" ] && continue
+
+            # AllowedIPs is cryptokey routing — route table and ACL at once.
+            case "$aips" in
+                *0.0.0.0/0*) warn "$name: AllowedIPs includes 0.0.0.0/0 — full-tunnel. Deliberate?" ;;
+            esac
+
+            # A peer with no endpoint cannot be dialed; it must initiate.
+            if [ -z "$ep" ] && [ "$role" != "roaming" ]; then
+                warn "$name: role '$role' but no endpoint — nothing can dial it."
+            fi
+            # Keepalive is NOT on the roaming peer's own entry — it is set on
+            # the entry for the peer it dials. Checked per-overlay below.
+            [ -z "$pk" ] && note "$name: public_key not captured yet"
+        done < <(overlay_peers "$ov")
+
+        # If anything roams, some peer entry must carry a keepalive.
+        if overlay_peers "$ov" | cut -d$'\x1f' -f3 | grep -qx roaming; then
+            if ! overlay_peers "$ov" | cut -d$'\x1f' -f7 | grep -qE '^[0-9]+$'; then
+                warn "a peer roams but no peer entry carries PersistentKeepalive"
+                note "      the roaming side sets it on the entry for the peer it dials;"
+                note "      without it the NAT mapping expires and the tunnel works only"
+                note "      while traffic flows outward — 'works sometimes'"
+            else
+                note "keepalive present on the dialed peer."
+            fi
+        fi
+
+        # 4. the listen port must be open wherever a peer is dialable.
+        local fwports; fwports=$(estate_get "firewall" | python3 -c '
+import json,sys
+try: print(" ".join(str(r.get("port")) for r in json.load(sys.stdin)))
+except Exception: pass')
+        case " $fwports " in
+            *" $port "*) note "udp/$port present in the firewall description." ;;
+            *) bad "udp/$port is in no firewall rule — no peer could be dialed." ;;
+        esac
+        echo
+    done
+
+    # Public keys are also 44-char base64, so shape alone proves nothing. The
+    # assertions are: no field named private, no key outside a public_key field.
+    echo "secrets — the description must never carry a private key"
+    local leaked
+    leaked=$(python3 - estate/../../estate/*.json <<'PY' 2>/dev/null || true
+import json, re, sys, glob
+KEY = re.compile(r'^[A-Za-z0-9+/]{43}=$')
+bad = []
+for f in glob.glob("../estate/*.json"):
+    def walk(node, path):
+        if isinstance(node, dict):
+            for k, v in node.items():
+                if re.search(r'priv', k, re.I):
+                    bad.append(f"{f}: field '{'.'.join(path+[k])}' is named private")
+                walk(v, path + [k])
+        elif isinstance(node, list):
+            for i, v in enumerate(node): walk(v, path + [str(i)])
+        elif isinstance(node, str) and KEY.match(node):
+            if not path or 'public' not in path[-1]:
+                bad.append(f"{f}: base64 key at '{'.'.join(path)}' is not a public_key field")
+    walk(json.load(open(f)), [])
+print("\n".join(bad))
+PY
+)
+    if [ -n "$leaked" ]; then
+        echo "$leaked" | while IFS= read -r l; do [ -n "$l" ] && bad "$l"; done
+    else
+        note "clean — no private-named field, no stray key material."
+    fi
+    echo
+
+    # A service reached over the overlay must bind an address the tunnel can
+    # reach. Loopback cannot be reached through a tunnel.
+    echo "bindings — services reached over the overlay must bind a reachable address"
+    local checked=0
+    while IFS=$'\x1f' read -r name host up kind raw placement peer port lhost; do
+        # Resolve placement first: a placed service's upstream is derived, not
+        # literal, so reading `up` alone skips it and this invariant goes quiet.
+        up="$(service_upstream "$up" "$placement" "$peer" "$port")" || true
+        [ -z "$up" ] && continue
+        local uhost="${up%%:*}" uport="${up##*:}"
+        addr_in_subnet "$uhost" "$(overlay_get estate subnet)" 2>/dev/null || continue
+        checked=$((checked + 1))
+        if is_me "$uhost"; then
+            local binds; binds=$(ss -ltn 2>/dev/null | awk -v p=":$uport\$" '$4 ~ p {print $4}')
+            if [ -z "$binds" ]; then
+                bad "$name: nothing listens on :$uport here, but $uhost:$uport is its upstream"
+            elif echo "$binds" | grep -q '^127\.0\.0\.1:'; then
+                bad "$name: :$uport binds 127.0.0.1 — unreachable over the overlay"
+                note "      the tunnel cannot reach loopback; bind 0.0.0.0 or $uhost"
+            else
+                note "$name: :$uport binds $(echo "$binds" | tr '\n' ' ')— reachable"
+                echo "$binds" | grep -q '^0\.0\.0\.0:' && \
+                    note "      (0.0.0.0 also exposes it to the LAN; $uhost alone would be tighter)"
+            fi
+        else
+            note "$name: upstream $uhost is another peer — needs capture there"
+        fi
+    done < <(estate_services "$TARGET")
+    [ "$checked" = 0 ] && note "no service currently has an overlay address as its upstream."
+    echo
+
+    case "$WORST" in
+        0) echo "OK" ;;
+        1) echo "OK, with warnings" ;;
+        2) echo "PROBLEMS FOUND — see FAIL lines above" ;;
+    esac
+    return 0
+}
+
+# A .gitignore pattern containing a slash anchors to its own directory, so the
+# only way to know a path is ignored is to ask git.
+assert_ignored() {
+    local path="$1"
+    if ! git check-ignore -q "$path" 2>/dev/null; then
+        echo "REFUSING: '$path' is not gitignored." >&2
+        echo "  Writing key material there would stage it on the next 'git add'." >&2
+        echo "  Verify with: git check-ignore -v $path" >&2
+        exit 1
+    fi
+}
+
+keygen() {
+    local peer="${1:-}"
+    [ -z "$peer" ] && { echo "usage: $0 keygen <peer>" >&2; exit 1; }
+    command -v wg >/dev/null || { echo "wg not installed." >&2; exit 1; }
+
+    mkdir -p "$SECRETS_DIR"
+    assert_ignored "$SECRETS_DIR"
+    local kf="$SECRETS_DIR/${peer}.key"
+    [ -e "$kf" ] && { echo "REFUSING: $kf exists. Delete it deliberately to rotate." >&2; exit 1; }
+
+    ( umask 077; wg genkey > "$kf" )
+    echo "private key -> $kf  (0600, gitignored, never leaves this machine)"
+    echo
+    echo "public key for the estate description:"
+    echo "  $(wg pubkey < "$kf")"
+    echo
+    echo "Paste that into estate/*.json under vpn.overlays.<ov>.peers.${peer}.public_key."
+    echo "The private key stays here and is injected only at render time."
+}
+
+render() {
+    local peer="${1:-}"
+    [ -z "$peer" ] && { echo "usage: $0 render <peer>" >&2; exit 1; }
+    mkdir -p "$OUT_DIR"
+    assert_ignored "$OUT_DIR"
+
+    local ov=estate
+    local found=""
+    local name addr role ep pk aips ka
+    while IFS=$'\x1f' read -r name addr role ep pk aips ka; do
+        [ "$name" = "$peer" ] && found=1 && break
+    done < <(overlay_peers "$ov")
+    [ -z "$found" ] && { echo "no such peer '$peer' in overlay '$ov'" >&2; exit 1; }
+
+    local missing=""
+    while IFS=$'\x1f' read -r name addr role ep pk aips ka; do
+        [ -z "$pk" ] && missing="$missing $name"
+    done < <(overlay_peers "$ov")
+    if [ -n "$missing" ]; then
+        echo "REFUSING to render: public keys not captured for:$missing" >&2
+        echo "  A config without every peer's public key is a config that silently" >&2
+        echo "  drops those peers. Capture first: sudo wg show | $0 capture --write" >&2
+        exit 1
+    fi
+    echo "would write $OUT_DIR/${peer}.conf (all keys present)"
+}
+
+# Reads `wg show` on stdin. Peers match by allowed-ips address, not public key,
+# because the keys are what is missing. A roaming peer's endpoint is a home
+# address and has no stable value — dropped in the parser, not just unused.
+capture() {
+    local write="" as_peer=""
+    while [ $# -gt 0 ]; do
+        case "$1" in
+            --write) write=1 ;;
+            --as)    shift; as_peer="${1:-}"
+                     [ -z "$as_peer" ] && { echo "--as needs a peer name" >&2; exit 1; } ;;
+            *)       echo "capture: unknown argument '$1'" >&2; exit 1 ;;
+        esac
+        shift
+    done
+
+    local input; input=$(cat)
+    if [ -z "$input" ]; then
+        echo "nothing on stdin." >&2
+        echo "  run: sudo wg show | $0 capture" >&2
+        exit 1
+    fi
+    # Refuse the unsafe forms outright rather than parsing around them.
+    if printf '%s' "$input" | grep -qiE '^\s*PrivateKey\s*=|^\[Interface\]'; then
+        echo "REFUSING: this looks like 'wg showconf' output — it contains a PRIVATE KEY." >&2
+        echo "  Use 'sudo wg show' (plain). It prints 'private key: (hidden)'." >&2
+        exit 1
+    fi
+    if ! printf '%s' "$input" | grep -q 'interface:'; then
+        echo "REFUSING: this does not look like 'wg show' output." >&2
+        echo "  If it was 'wg show <if> dump': that form's first field IS the" >&2
+        echo "  private key. Use 'sudo wg show' with no subcommand." >&2
+        exit 1
+    fi
+
+    WRITE="$write" AS_PEER="$as_peer" INPUT="$input" python3 - "$ESTATE_FILE" <<'PYCAP'
+import collections, ipaddress, json, os, re, sys
+
+text  = os.environ["INPUT"]
+write = os.environ.get("WRITE") == "1"
+path  = sys.argv[1]
+
+iface, peers, cur = {}, [], None
+for line in text.splitlines():
+    st = line.strip()
+    if st.startswith("interface:"):
+        cur = iface; cur["name"] = st.split(":", 1)[1].strip(); continue
+    if st.startswith("peer:"):
+        cur = {"public_key": st.split(":", 1)[1].strip()}; peers.append(cur); continue
+    if cur is None or ":" not in st:
+        continue
+    k, v = st.split(":", 1)
+    k, v = k.strip().lower(), v.strip()
+    if k == "private key":
+        continue                     # never recorded, whatever it says
+    if k == "public key":   cur["public_key"] = v
+    elif k == "listening port": cur["listen_port"] = v
+    elif k == "allowed ips":    cur["allowed_ips"] = v
+    elif k == "endpoint":       cur["endpoint"] = v
+    elif k == "persistent keepalive":
+        m = re.search(r"(\d+)", v)
+        if m: cur["keepalive"] = int(m.group(1))
+
+d  = json.load(open(path), object_pairs_hook=collections.OrderedDict)
+ov = d["vpn"]["overlays"]["estate"]
+
+# address -> peer name, from what the estate already declares
+by_addr = {p["address"]: n for n, p in ov["peers"].items() if p.get("address")}
+by_key  = {p["public_key"]: n for n, p in ov["peers"].items() if p.get("public_key")}
+subnet  = ipaddress.ip_network(ov["subnet"]) if ov.get("subnet") else None
+hubs    = [n for n, p in ov["peers"].items() if p.get("role") == "hub"]
+
+# Whose interface block is this? `--as` names it explicitly, and that is the only
+# thing that works for output captured over ssh: the addresses on THIS machine
+# say nothing about the machine the output came from.
+as_peer = os.environ.get("AS_PEER") or ""
+if as_peer:
+    if as_peer not in ov["peers"]:
+        print("no peer named %r in this overlay. known: %s"
+              % (as_peer, ", ".join(ov["peers"])))
+        raise SystemExit(1)
+    me = as_peer
+else:
+    me = None
+    local = os.popen(
+        "ip -4 -o addr show 2>/dev/null | awk '{split($4,a,\"/\"); print a[1]}'"
+    ).read().split()
+    for n, p in ov["peers"].items():
+        if p.get("address") and p["address"] in local:
+            me = n
+
+changes = []
+conflicts = []
+staged = {}
+def setf(peer, field, val, why=""):
+    p = ov["peers"][peer]
+    if val is None or p.get(field) == val:
+        return
+    # Two values for one field means the input is from another machine.
+    prev = staged.get((peer, field))
+    if prev is not None and prev != val:
+        conflicts.append((peer, field, prev, val))
+        return
+    staged[(peer, field)] = val
+    changes.append((peer, field, p.get(field), val, why))
+    if write:
+        p[field] = val
+
+if me and iface.get("public_key"):
+    setf(me, "public_key", iface["public_key"], "(this machine's interface)")
+
+def match(pr):
+    # 1. The public key IS the identity. Use it whenever the estate knows it.
+    n = by_key.get(pr["public_key"])
+    if n:
+        return n
+    nets = [a.strip() for a in pr.get("allowed_ips", "").split(",") if a.strip()]
+    # 2. An allowed-ip that is a declared peer address — the ordinary spoke case.
+    for a in nets:
+        if a.split("/")[0] in by_addr:
+            return by_addr[a.split("/")[0]]
+    # 3. A peer routing the WHOLE overlay is the hub seen from a spoke. Its
+    #    allowed_ips is the subnet itself, so no single address ever matches it.
+    if subnet and len(hubs) == 1:
+        for a in nets:
+            try:
+                if ipaddress.ip_network(a, strict=False).supernet_of(subnet):
+                    return hubs[0]
+            except ValueError:
+                continue
+    return None
+
+for pr in peers:
+    name = match(pr)
+    if not name:
+        changes.append(("?", "UNMATCHED", None,
+                        "allowed_ips=%s key=%s" % (pr.get("allowed_ips"), pr["public_key"][:12] + "..."),
+                        "no estate peer has this key, this address, or this route"))
+        continue
+    setf(name, "public_key", pr.get("public_key"))
+    setf(name, "allowed_ips", pr.get("allowed_ips"))
+    setf(name, "keepalive", pr.get("keepalive"))
+    # endpoint: recorded ONLY for a non-roaming peer. For a roaming one the
+    # value is a home ISP address and is deliberately dropped here.
+    if pr.get("endpoint"):
+        if ov["peers"][name].get("role") == "roaming":
+            changes.append((name, "endpoint", None, "(dropped: roaming peer)",
+                            "a home address is the one sensitive field; roaming peers have no stable endpoint"))
+        else:
+            setf(name, "endpoint", pr["endpoint"])
+
+if me and iface.get("listen_port"):
+    try:
+        lp = int(iface["listen_port"])
+    except ValueError:
+        lp = None
+    if lp is not None:
+        # A listen port belongs to the PEER, not to the overlay. A roaming peer's
+        # is an ephemeral source port chosen by the kernel; writing it to the
+        # overlay would rename the port the firewall rule is checked against.
+        setf(me, "listen_port", lp)
+        if ov["peers"][me].get("role") == "hub" and ov.get("listen_port") != lp:
+            changes.append(("(overlay)", "listen_port", ov.get("listen_port"), lp,
+                            "the hub's port is the overlay's port"))
+            if write:
+                ov["listen_port"] = lp
+
+if conflicts:
+    print("REFUSING: the same field was reported twice with different values.\n")
+    for peer, field, a, b in conflicts:
+        print("  %s.%s: %s  vs  %s" % (peer, field, a, b))
+    print("\nThis usually means `wg show` output from one machine was piped into")
+    print("capture on another. Run capture on the machine the output came from.")
+    raise SystemExit(1)
+
+if not changes:
+    print("nothing to record — the estate already matches what wg reports.")
+else:
+    print("%-9s %-12s %-22s %s" % ("PEER", "FIELD", "WAS", "WOULD BE"))
+    for peer, field, was, val, why in changes:
+        print("%-9s %-12s %-22s %s" % (peer, field, was if was is not None else "—", val))
+        if why: print("          %s" % why)
+
+if write:
+    still = [n for n, p in ov["peers"].items() if not p.get("public_key")]
+    if not still:
+        d["vpn"]["_status"] = ("CAPTURED %s — public keys, allowed-ips and keepalive read from "
+                               "`wg show`. Roaming endpoints deliberately not recorded."
+                               % __import__("datetime").date.today())
+    json.dump(d, open(path, "w"), indent=2, ensure_ascii=False)
+    open(path, "a").write("\n")
+    print("\nwritten to %s" % path)
+else:
+    print("\nnothing written. Add --write to record it.")
+PYCAP
+}
+
+refuse() {
+    local verb="$1"; shift
+    local yes=""
+    for a in "$@"; do [ "$a" = "--yes" ] && yes=1; done
+    [ -z "$yes" ] && {
+        echo "refusing to $verb without --yes." >&2
+        echo "  $verb changes live networking — it can cut the path this session" >&2
+        echo "  is reaching the estate through. Read 'make vpn check' first." >&2
+        exit 1; }
+    echo "refusing to $verb: not implemented. Bringing a tunnel up or down is" >&2
+    echo "  the host's business, and the live one is systemd-managed" >&2
+    echo "  (wg-quick@wg0). berth describes and renders; it does not operate." >&2
+    exit 1
+}
+
+case "${1:-list}" in
+    list)     list ;;
+    show)     shift; show "${1:-}" ;;
+    check)    check ;;
+    render)   shift; render "${1:-}" ;;
+    keygen)   shift; keygen "${1:-}" ;;
+    capture)  shift; capture "$@" ;;
+    up|down)  v="$1"; shift; refuse "$v" "$@" ;;
+    *) echo "usage: $0 [list|show <ov>|check|render <peer>|keygen <peer>|capture [--as <peer>] [--write]|up --yes|down --yes]" >&2; exit 1 ;;
+esac

berth/estate/mcrn.json

@@ -0,0 +1,326 @@
+{
+  "_meta": {
+    "status": "UNVERIFIED — derived from the repos, not from the estate",
+    "why": "ppl/infra/ was written and never applied: no ~/.pulumi, no infra/venv, no stack state, files dated 'mar 6'. The estate was built in the console and the IaC is aspirational. B1's inventory is what replaces these values with observed ones; until it runs, every field here is a CLAIM.",
+    "never_record": "credential values. Resource ids and settings only. nova's gateway secret is deliberately absent from this file even though it is committed in plaintext in ppl/gateway/nginx/conf.d/nova.conf — see services[].raw.",
+    "sources": [
+      "ppl/infra/__main__.py",
+      "ppl/ctrl/dns.sh",
+      "ppl/ctrl/certs.sh",
+      "ppl/gateway/docker-compose.yml",
+      "ppl/gateway/nginx/conf.d/",
+      "ppl/local/Caddyfile"
+    ],
+    "placement": {
+      "box": "a container on the estate's own docker network — upstream is the container name",
+      "local": "a rig cluster on a peer, reached over the overlay — upstream is that peer's address",
+      "instance": "a dedicated cloud instance on the overlay — same rendering as `local`",
+      "hosted": "a managed endpoint. Declared so moving to one is a one-line change; unused.",
+      "_why": "A service says WHERE it runs. How it is reached follows from that, and the three properties of a static-upstream vhost — upstream{}, no resolver, no set $var — are one decision rather than three."
+    }
+  },
+  "domain": "mcrn.ar",
+  "local_domain": "local.ar",
+  "host": "mcrn",
+  "host_admin": "mcrn-admin",
+  "instance": {
+    "type": "t3.small",
+    "disk_gb": 30,
+    "disk_type": "gp3",
+    "image": "debian-12",
+    "user": "mariano"
+  },
+  "firewall": [
+    {
+      "port": 22,
+      "proto": "tcp",
+      "desc": "SSH"
+    },
+    {
+      "port": 80,
+      "proto": "tcp",
+      "desc": "HTTP"
+    },
+    {
+      "port": 443,
+      "proto": "tcp",
+      "desc": "HTTPS"
+    },
+    {
+      "port": 3022,
+      "proto": "tcp",
+      "desc": "Gitea SSH",
+      "note": "compose maps 3022:22 but GITEA__server__SSH_PORT=22, so gitea advertises :22 in clone URLs while listening on :3022. B1 confirms which is real."
+    },
+    {
+      "port": 51820,
+      "proto": "udp",
+      "desc": "WireGuard",
+      "note": "ABSENT from ppl/infra/__main__.py's four rules — but the tunnel is live (ping 10.8.0.1 succeeds), so the real security group must already allow it. The code therefore does not describe the estate. Confirm in V1."
+    }
+  ],
+  "network": {
+    "docker_network": "gateway",
+    "docker_network_note": "A fixed, externally-joinable bridge name. Every unrelated app stack on the box joins it so nginx can resolve them by container name. This is why the gateway compose declares 8 services while nginx routes 20+ hostnames.",
+    "wireguard_moved": "superseded by the top-level `vpn` block"
+  },
+  "vpn": {
+    "_status": "CAPTURED 2026-09-14 — public keys, allowed-ips and keepalive read from `wg show`. Roaming endpoints deliberately not recorded.",
+    "_never_record": "private keys. `wg show` prints 'private key: (hidden)' and is the safe capture command. `wg showconf` dumps PrivateKey= in clear — never use it.",
+    "overlays": {
+      "estate": {
+        "purpose": "Connects the estate's machines across clouds without a shared VPC, and carries everything that does not need to be publicly reachable.",
+        "subnet": "10.8.0.0/24",
+        "listen_port": 51820,
+        "peers": {
+          "box": {
+            "address": "10.8.0.1",
+            "role": "hub",
+            "note": "mcrn.ar. Has a public IP, so it is the peer others dial. Carries the registry (:5000) and woodpecker's gRPC (:9000), both bound to this address and therefore overlay-only.",
+            "endpoint": "3.23.204.197:51820",
+            "public_key": "zVYCmi3xucuX7k/aDhrOUPyN4GRk96ffSDD6dUFQjh4=",
+            "allowed_ips": "10.8.0.0/24",
+            "keepalive": 25,
+            "listen_port": 51820
+          },
+          "nrft": {
+            "address": "10.8.0.2",
+            "role": "roaming",
+            "note": "The dev box. Behind NAT, so it must initiate and needs PersistentKeepalive. Verified: wg0 UP at 10.8.0.2/24, ping 10.8.0.1 0% loss at 153ms.",
+            "endpoint": null,
+            "public_key": "zlIBGs4y5rt6uVdmFBasHpafht6ErxG+R3ySCg5rh3s=",
+            "allowed_ips": "10.8.0.2/32, 192.168.1.0/24",
+            "keepalive": null,
+            "listen_port": 36145
+          },
+          "work": {
+            "address": "10.8.0.3",
+            "role": "roaming",
+            "note": "A work computer, granted access when it was needed. Identified by the user at capture time, 2026-09-14 — it was NOT in the description before, and the wire is where it was found. No handshake and no transfer have ever been recorded for it, so it is a standing grant rather than a live peer: it can connect, and never has. Whether to keep or revoke it is the host's call.",
+            "endpoint": null,
+            "public_key": "ruSZwKt/p60GVsTLSAhcKBIXKkSZsf0gWSmSH1+UgE0=",
+            "allowed_ips": "10.8.0.3/32",
+            "keepalive": null
+          }
+        }
+      }
+    }
+  },
+  "databases": [
+    "gitea",
+    "woodpecker",
+    "umami"
+  ],
+  "certs": {
+    "issued": [
+      "mcrn.ar",
+      "*.mcrn.ar",
+      "*.spr.mcrn.ar"
+    ],
+    "issued_source": "ppl/ctrl/certs.sh:92 — the -d flags passed to certbot",
+    "note": "What the cert ACTUALLY covers. estate_sans() derives what the services NEED. check.sh compares the two; the difference is the finding, not a restatement."
+  },
+  "services": [
+    {
+      "name": "gitea",
+      "host": "git",
+      "upstream": "gitea:3000",
+      "targets": [
+        "aws"
+      ]
+    },
+    {
+      "name": "woodpecker",
+      "host": "ci",
+      "upstream": "woodpecker-server:8000",
+      "targets": [
+        "aws"
+      ]
+    },
+    {
+      "name": "registry",
+      "host": "registry",
+      "upstream": "registry:5000",
+      "targets": [
+        "aws"
+      ]
+    },
+    {
+      "name": "umami",
+      "host": "analytics",
+      "upstream": "umami:3000",
+      "targets": [
+        "aws"
+      ]
+    },
+    {
+      "name": "docserve",
+      "host": "docs",
+      "upstream": "docserve:8020",
+      "targets": [
+        "aws"
+      ]
+    },
+    {
+      "name": "ghost",
+      "host": "notes",
+      "upstream": "ghost:2368",
+      "targets": [
+        "aws"
+      ]
+    },
+    {
+      "name": "deskmeter",
+      "host": "deskmeter",
+      "upstream": "dmweb:10000",
+      "targets": [
+        "aws"
+      ],
+      "local_port": 10000
+    },
+    {
+      "name": "sysmonstm",
+      "host": "sysmonstm",
+      "upstream": "sysmonstm-edge:8080",
+      "targets": [
+        "aws"
+      ],
+      "local_port": 8020
+    },
+    {
+      "name": "malvalava",
+      "host": "malvalava",
+      "upstream": "mlvclean-frontend:80",
+      "targets": [
+        "aws"
+      ],
+      "local_port": 30090
+    },
+    {
+      "name": "soleprint",
+      "host": "soleprint",
+      "upstream": "soleprint:8000",
+      "targets": [
+        "aws"
+      ],
+      "local_port": 12000
+    },
+    {
+      "name": "dlt",
+      "host": "dlt.spr",
+      "upstream": "dlt_spr:8000",
+      "targets": [
+        "aws"
+      ]
+    },
+    {
+      "name": "sample",
+      "host": "sample.spr",
+      "upstream": "sample_spr:8000",
+      "targets": [
+        "aws"
+      ]
+    },
+    {
+      "name": "mariano",
+      "host": "mariano",
+      "kind": "static",
+      "targets": [
+        "aws"
+      ]
+    },
+    {
+      "name": "rigui",
+      "host": "rig",
+      "kind": "static",
+      "targets": [
+        "aws"
+      ],
+      "local_port": 20310
+    },
+    {
+      "name": "unt",
+      "host": "unt",
+      "targets": [
+        "local"
+      ],
+      "local_port": 8040
+    },
+    {
+      "name": "mpr",
+      "host": "mpr",
+      "targets": [
+        "local"
+      ],
+      "local_port": 30080
+    },
+    {
+      "name": "nvi",
+      "host": "nvi",
+      "targets": [
+        "local"
+      ],
+      "local_port": 8060
+    },
+    {
+      "name": "eth",
+      "host": "eth",
+      "targets": [
+        "local"
+      ],
+      "local_port": 8050
+    },
+    {
+      "name": "amar",
+      "host": "amar",
+      "targets": [
+        "local"
+      ],
+      "local_port": 8030
+    },
+    {
+      "name": "nova",
+      "host": "nova",
+      "upstream": "nova-ui:80",
+      "targets": [
+        "aws"
+      ],
+      "raw": true,
+      "raw_why": "Gated on an X-Gateway-Secret header whose value is committed in plaintext. The value is NOT recorded here. Worse: stellarair.conf proxies to the SAME nova-ui:80 upstream WITHOUT the check, so the gate is bypassable by hostname. Stays hand-written until that is decided."
+    },
+    {
+      "name": "stellarair",
+      "host": "stellarair",
+      "upstream": "nova-ui:80",
+      "targets": [
+        "aws"
+      ],
+      "raw": true,
+      "raw_why": "See nova. Same upstream, no header gate."
+    },
+    {
+      "name": "langfuse",
+      "host": "langfuse",
+      "local_host": "lng",
+      "placement": "local",
+      "peer": "nrft",
+      "port": 3000,
+      "targets": [
+        "aws",
+        "local"
+      ],
+      "local_port": 3000,
+      "note": "One service, one socket, two names. It was two entries with one flagged `raw`; placement is what made the exception expressible, so it is generated now."
+    },
+    {
+      "name": "legacy",
+      "host": "*.soleprint",
+      "upstream": "soleprint:8000",
+      "targets": [
+        "aws"
+      ],
+      "raw": true,
+      "raw_why": "A regex server_name with a named capture plus sub_filter injection — not expressible as a template. ALSO BROKEN: its /api/, /admin/, /static/ and / blocks proxy to 127.0.0.1, i.e. inside the nginx container where nothing listens, so every legacy room 502s. Only /wrapper/ uses the correct container-name form."
+    }
+  ]
+}

build.py

@@ -80,6 +80,30 @@ def _rmtree_resilient(path: Path):
     )
 
 
+# Never swept into a built room, wherever they appear in a source tree.
+#
+# This is a SECURITY boundary, not tidiness. gen/<room>/ is the docker build
+# context, soleprint/Dockerfile is `COPY . .`, and there is no .dockerignore —
+# so anything that reaches gen/ reaches an image layer, and registry.mcrn.ar is
+# public-read. That is how station/tools/tester/.env, gitignored since the last
+# incident, still ended up baked into soleprint_localtest-soleprint:latest with
+# its API key intact. .gitignore does not bind shutil.
+#
+# Applied to bulk directory copies only. A caller naming a single file is making
+# an explicit request (cfg/<room>/.env.example is the one that matters) and is
+# left alone.
+ALWAYS_IGNORE = {".git", "__pycache__", "node_modules", ".venv", "venv", ".env"}
+ALWAYS_IGNORE_SUFFIXES = (".pyc", ".pyo")
+
+
+def is_ignored(name: str) -> bool:
+    return name in ALWAYS_IGNORE or name.endswith(ALWAYS_IGNORE_SUFFIXES)
+
+
+def _copytree_ignore(directory, files):
+    return {f for f in files if is_ignored(f)}
+
+
 def copy_path(source: Path, target: Path, quiet: bool = False):
     """Copy file or directory, resolving symlinks."""
     if target.is_symlink():
@@ -91,7 +115,7 @@ def copy_path(source: Path, target: Path, quiet: bool = False):
             target.unlink()
 
     if source.is_dir():
-        shutil.copytree(source, target, symlinks=False)
+        shutil.copytree(source, target, symlinks=False, ignore=_copytree_ignore)
         if not quiet:
             log.info(f"  {target.name}/")
     else:
@@ -111,6 +135,8 @@ def merge_into(source: Path, target: Path):
     for item in source.rglob("*"):
         if item.is_file():
             rel = item.relative_to(source)
+            if any(is_ignored(part) for part in rel.parts):
+                continue
             dest = target / rel
             dest.parent.mkdir(parents=True, exist_ok=True)
             shutil.copy2(item, dest)
@@ -687,6 +713,7 @@ def build_soleprint(output_dir: Path, room: str):
         "index.html",
         "requirements.txt",
         "Dockerfile",
+        ".dockerignore",
     ]:
         if (soleprint / name).exists():
             copy_path(soleprint / name, output_dir / name)

ctrl/cluster.sh

@@ -6,16 +6,50 @@
 #   ./ctrl/cluster.sh down     # delete it (drops every room's namespace)
 #   ./ctrl/cluster.sh status   # what's running on it
 #
-# One target, one script — the variants live here. The kind-*.sh files stay
-# exactly as they are and remain runnable on their own; this only dispatches.
+# spr depends on rig, never the other way round. Building and deleting a cluster
+# is rig's job, so up and down hand straight to rig/ctrl/cluster.sh, carrying the
+# the things that make this cluster spr's rather than rig's defaults:
+#
+#   CLUSTER=spr          rooms deploy into the kind-spr context
+#   KIND_CONFIG          spr's own kind config, which maps the rooms' gateway NodePorts
+#   REGISTRY_MODE=none   rooms load images straight into the node
+#   PROFILE= ADDONS=     set empty here, so rig's own ctrl/.env can never quietly
+#                        pick a profile or add addons to spr's cluster
+#
+# status stays here: it answers a question about rooms, not about the cluster.
 set -e
 
 SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+RIG_CTRL="$SCRIPT_DIR/../rig/ctrl"
+
+rig() {
+    CLUSTER=spr \
+    KIND_CONFIG="$SCRIPT_DIR/k8s/kind-config.yaml" \
+    REGISTRY_MODE=none \
+    PROFILE= \
+    ADDONS= \
+        bash "$RIG_CTRL/cluster.sh" "$@"
+}
 
 case "${1:-status}" in
-    up)     exec "$SCRIPT_DIR/kind-up.sh" ;;
-    down)   exec "$SCRIPT_DIR/kind-down.sh" ;;
-    status) exec "$SCRIPT_DIR/kind-status.sh" ;;
+    up)
+        rig up
+        echo
+        echo "Per-room deploy:"
+        echo "  cd gen/<room> && ./ctrl/k8s-up.sh"
+        ;;
+    down)
+        rig down
+        ;;
+    status)
+        if ! kind get clusters 2>/dev/null | grep -qx spr; then
+            echo "No 'spr' kind cluster — run: make cluster up"
+            exit 0
+        fi
+        kubectl --context kind-spr get namespaces -l soleprint-room
+        echo
+        kubectl --context kind-spr get pods -A -l soleprint-room
+        ;;
     *)
         echo "Unknown subcommand: $1" >&2
         echo "Usage: cluster.sh [up|down|status]" >&2

ctrl/k8s/kind-config.yaml

@@ -3,9 +3,15 @@ apiVersion: kind.x-k8s.io/v1alpha4
 # Single shared cluster for all soleprint rooms.
 # Each room deploys into its own namespace; gateway Services pick a
 # NodePort from the 30080-30099 range mapped here.
-name: spr
+#
+# Built by rig, not by spr: ctrl/cluster.sh hands this file to
+# rig/ctrl/cluster.sh, which substitutes CLUSTER and NODE_IMAGE (named without
+# braces here so this comment survives the substitution). The shape is spr's —
+# what its cluster needs is spr's business. Building it is rig's.
+name: ${CLUSTER}
 nodes:
   - role: control-plane
+    image: ${NODE_IMAGE}
     extraPortMappings:
       # Room gateway NodePorts (one per active room).
       - {containerPort: 30080, hostPort: 30080, protocol: TCP}

ctrl/kind-down.sh

@@ -1,12 +0,0 @@
-#!/bin/bash
-# Delete the shared `spr` kind cluster (drops every room's namespace too).
-# Use `gen/<room>/ctrl/k8s-down.sh` instead if you only want to remove
-# a single room's namespace.
-set -e
-
-if kind get clusters 2>/dev/null | grep -q '^spr$'; then
-    echo "Deleting kind cluster 'spr'..."
-    kind delete cluster --name spr
-else
-    echo "No kind cluster 'spr' to delete."
-fi

ctrl/kind-status.sh

@@ -1,12 +0,0 @@
-#!/bin/bash
-# Show what's running on the shared `spr` cluster.
-set -e
-
-if ! kind get clusters 2>/dev/null | grep -q '^spr$'; then
-    echo "No 'spr' kind cluster — run ctrl/kind-up.sh"
-    exit 0
-fi
-
-kubectl --context kind-spr get namespaces -l soleprint-room
-echo
-kubectl --context kind-spr get pods -A -l soleprint-room

ctrl/kind-up.sh

@@ -1,21 +0,0 @@
-#!/bin/bash
-# Create (or no-op) the single shared `spr` kind cluster used by every
-# soleprint room. Per-room work happens inside namespaces — see
-# `gen/<room>/ctrl/k8s-up.sh`.
-set -e
-
-SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
-KIND_CONFIG="$SCRIPT_DIR/k8s/kind-config.yaml"
-
-if kind get clusters 2>/dev/null | grep -q '^spr$'; then
-    echo "Kind cluster 'spr' already exists."
-else
-    echo "Creating kind cluster 'spr'..."
-    kind create cluster --config "$KIND_CONFIG"
-fi
-
-kubectl config use-context kind-spr >/dev/null
-
-echo
-echo "Cluster ready. Per-room deploy:"
-echo "  cd gen/<room> && ./ctrl/k8s-up.sh"

ctrl/theme.sh

@@ -0,0 +1,80 @@
+#!/usr/bin/env bash
+# Bake the theme and its parts into the pages that use them.
+#
+# Usage:
+#   ./ctrl/theme.sh             # bake — rewrite every generated block
+#   ./ctrl/theme.sh check       # fail if any page is stale; changes nothing
+#   ./ctrl/theme.sh new [title] # a scaffold page to start from
+#   ./ctrl/theme.sh run FILE [--list|--check] [--only NAME]
+#                               # every page a run file lists, each with a contract
+#   ./ctrl/theme.sh parts       # what can be added, and the markup that adds it
+#   ./ctrl/theme.sh export [name...]   # the contract for a subset, as one doc
+#
+# `export` is for handing a vetted LLM what it needs to write an ad-hoc page —
+# the chosen parts, their markup, and the tokens resolved to literal values, so
+# the document stands alone. Naming parts is the point: hand over everything and
+# you get back a page built from Vue components that cannot run standalone.
+#
+#   ./ctrl/theme.sh export panel split > /tmp/contract.md
+#
+# Call the script directly when piping; `make` echoes its recipe to stdout.
+# For whole-repo context this is the wrong tool — station/tools/distill already
+# flattens a tree to one budgeted document.
+#
+# A page that says `background: var(--bg)` and never gets `--bg` is UNSTYLED,
+# not merely unbranded — the declaration is invalid at computed-value time. That
+# is why every page carries a baked default, and why `check` is worth running.
+#
+# This exists because bake.py was reachable by no command at all: not from the
+# Makefile, not from ctrl/, not from build.py. A drift check nobody runs is a
+# drift check that reports nothing, and the evidence was already on disk —
+# histgen's page linked /theme.css for months, was missing from the old
+# hardcoded page list, and so was never baked once.
+set -e
+
+# Where the caller stood. A run file is named relative to there, and the cd below
+# would otherwise make `run ./theme.toml` mean a different file.
+CALLER_DIR="$PWD"
+
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+ROOT_DIR="$(dirname "$SCRIPT_DIR")"
+cd "$ROOT_DIR/soleprint"
+
+PYTHON="${PYTHON:-python3}"
+
+case "${1:-bake}" in
+    bake)  exec "$PYTHON" common/theme/bake.py ;;
+    check) exec "$PYTHON" common/theme/bake.py --check ;;
+    parts)
+        exec "$PYTHON" common/theme/bake.py --parts
+        ;;
+    run)
+        # A run file: every page a project has, its context, and a contract per
+        # page for the LLM. See soleprint/common/theme/theme.example.toml.
+        shift
+        args=() file="" prev=""
+        for a in "$@"; do
+            if [[ -z "$file" && "$a" != -* && "$prev" != "--only" ]]; then
+                file="$(cd "$CALLER_DIR" && realpath -m -- "$a")"
+                args+=("$file")
+            else
+                args+=("$a")
+            fi
+            prev="$a"
+        done
+        exec "$PYTHON" common/theme/bake.py --run "${args[@]}"
+        ;;
+    new)
+        shift
+        exec "$PYTHON" common/theme/bake.py --new "$@"
+        ;;
+    export)
+        shift
+        exec "$PYTHON" common/theme/bake.py --export "$@"
+        ;;
+    *)
+        echo "Unknown: $1" >&2
+        echo "Usage: ./ctrl/theme.sh [new [title]|parts|bake|check|export [name...]|run FILE]" >&2
+        exit 1
+        ;;
+esac

docs/data/en/station-cabinets.md

@@ -57,8 +57,7 @@ compose, the same dependency installs as a rig addon of that name:
 
 ```bash
 cd rig
-PROFILE=data make cluster up
-PROFILE=data make addons install
+PROFILE=data make cluster up      # installs the addons too
 
 kubectl -n data port-forward svc/postgres 5432:5432
 kubectl -n data port-forward svc/airflow  8080:8080

rig/.gitattributes

@@ -0,0 +1,22 @@
+# Line endings are normalised to LF in the repository and on checkout, on every
+# platform. Without this, a checkout on Windows/WSL rewrites files to CRLF and
+# every one of them shows up as modified without anyone having touched it.
+#
+# For the scripts it is not cosmetic: a shell script with CRLF fails on Linux
+# with `bad interpreter: /usr/bin/env bash^M`, which reads as a broken installer
+# rather than a line-ending problem — the worst possible first impression on a
+# machine where nothing has been proven yet.
+* text=auto eol=lf
+
+*.sh   text eol=lf
+*.py   text eol=lf
+*.env  text eol=lf
+*.yaml text eol=lf
+*.yml  text eol=lf
+
+# Never touch binaries.
+*.png binary
+*.jpg binary
+*.zip binary
+*.tar binary
+*.gz  binary

rig/.gitignore

@@ -0,0 +1,21 @@
+# def/ — the "default" scratch bucket: always gitignored, never versioned
+def
+
+# local env (commit the .env.example, never the .env)
+.env
+.env.local
+ctrl/.env
+
+# generated: the .dot is a build artifact rendered from arch/*.json, never hand-edited.
+# The .svg IS committed — onboarding material should render in a repo browser.
+arch/*.dot
+# ctrl/Tiltfile.gen was here for a generator that no longer exists. ctrl/Tiltfile
+# is now a real, committed file that derives its values when Tilt parses it, so
+# there is nothing generated to ignore.
+
+# binaries pulled by `make deps-bundle` for the air-gapped installer image
+vendor
+
+# Client rigs are NOT ignored here. A copy is a SIBLING of this directory
+# (../acme-rig), so a rule in this file cannot see it — the rules live in the
+# parent repo's .gitignore, anchored at its root, where `*-rig/` matches them.

rig/BOOTSTRAP.md

@@ -0,0 +1,285 @@
+# From a machine with nothing on it to a project you can work in
+
+The README says the prerequisite is Docker and nothing else. This is what that
+actually looks like end to end: a bare Linux box, and a new project running under
+Tilt at the end of it.
+
+A copy of this directory is a sibling of it, named after the environment it
+models (`acme-rig`). Paths below are relative to the parent checkout.
+
+It spans three repos because the work does. **rig** prepares the machine — the
+pinned toolchain, the cluster, the port arithmetic. **all** owns the shape a
+project takes, in `all/projects/templates/conventions.md` and the `broad`
+scaffold beside it. **ppl** owns everything after local, and is where this
+document stops.
+
+Read it once before running anything. Three of the steps below need root and one
+needs a logout, so knowing about them in advance is cheaper than meeting them
+halfway through.
+
+
+## Docker, and the two sysctls Tilt depends on
+
+rig installs a toolchain; it does not install Docker. That line is not modesty —
+Docker is a daemon, a group membership and usually a logout, and a script that
+did it would have to be trusted with root on a machine it knows nothing about.
+
+```bash
+sudo apt-get install -y docker.io && sudo usermod -aG docker "$USER"
+```
+
+Then log out and back in, and check `docker info` answers. Until it does, nothing
+below works and everything below reports the same failure.
+
+While you have root, raise the inotify limits:
+
+```bash
+echo -e 'fs.inotify.max_user_watches=524288\nfs.inotify.max_user_instances=512' \
+  | sudo tee /etc/sysctl.d/99-rig.conf
+sudo sysctl --system
+```
+
+kind and Tilt both watch large trees, and WSL ships 8192 watches and 128
+instances — far too low. The failure mode is the reason this is here at step
+zero rather than mentioned later: Tilt does not error, it simply stops noticing
+that files changed, and you lose an afternoon to a hot reload that silently
+isn't.
+
+
+## Read the docs before installing anything
+
+```bash
+cd rig
+make docs
+```
+
+`ctrl/docs.sh` runs a throwaway `nginx:alpine` over a read-only bind mount of
+`docs/` and prints the URL. That is deliberate: the docs are the instructions for
+building everything else, so they cannot live in the cluster and cannot need
+`python3 -m http.server` either — a minimal Debian has no python. What it has,
+by definition, is Docker.
+
+The port is this environment's `HTTP_PORT + 4`. Nothing is installed and nothing
+persists; ctrl-c ends it.
+
+
+## Ask what is wrong with this machine
+
+```bash
+make check
+cp ctrl/.env.example ctrl/.env
+```
+
+`check.sh` reports and instructs, and fixes nothing. It runs bare rather than
+in a container because host detection only ever reads `/proc` and `/etc` — no
+dependency beyond coreutils.
+
+Read the whole output, but the `ports` block is the one to read carefully. Every
+port rig binds derives from this directory's name, so the answer is specific to
+this copy, and a clash here surfaces as an opaque `failed to bind host port` in
+the middle of cluster creation if you skip it.
+
+Copy the `.env` even though the check only warns about it. It is gitignored, it is
+where a machine-local override goes, and `ports.sh persist` expects it to exist.
+
+
+## Install the toolchain — through the container
+
+This is the step where "nothing installed" stops being rhetorical.
+
+`make deps` runs `ctrl/deps.sh install` directly on the host, and the installer
+fetches with `curl`. A stock `debian:trixie-slim` has no curl — detection runs
+fine, then the first download dies with `curl: command not found` and an exit
+code of 127. That is the bootstrap paradox `ctrl/Dockerfile.deps` exists
+to kill — the installer carries its own toolchain so the host needs only Docker —
+but building the image and running it are two different things, and only the
+build has a Makefile target today. **On a genuinely bare machine, run it by
+hand:**
+
+```bash
+make deps image                          # builds rig-deps:deps
+mkdir -p ~/.local/bin
+docker run --rm \
+  -v /:/host:ro \
+  -v /var/run/docker.sock:/var/run/docker.sock \
+  -v "$HOME/.local/bin:/out/bin" \
+  -e HOST_UID="$(id -u)" -e HOST_GID="$(id -g)" \
+  rig-deps:deps install dev
+```
+
+The image name follows the directory, like everything else here: in `rig`
+it is `rig-deps`, in a copy called `acme-rig` it is `acme-rig-deps`. The
+tag is `deps` (or `full`, below), not `latest`.
+
+None of the four arguments are guessable, so:
+
+- **`/:/host:ro`** — the installer reads the *host's* `/etc/os-release` and
+  `/etc/wsl.conf`, not the container's. `HOST_ROOT=/host` is already baked into
+  the image; this is what it points at. Read-only, and it is the only reason
+  detection inside a container tells you anything about the machine.
+- **the docker socket** — how detection reaches the daemon it is reporting on,
+  and how it counts kind clusters already running.
+- **`/out/bin`** — the image's `OUT_BIN`. Whatever you mount here is where the
+  four binaries land.
+- **`HOST_UID` / `HOST_GID`** — the installer runs as root so it can reach that
+  socket, which means everything it writes into a mounted volume is root-owned
+  and useless to you. These drive the `chown` back. Omit them and the install
+  looks like it worked.
+
+`dev` is kubectl, jq, kind and tilt. `core` is kubectl and jq alone — no cluster
+tooling — which is the right answer on a managed or corporate-issued machine and
+is why the split exists.
+
+Then put them on PATH, which the installer will remind you about because it cannot
+edit your shell for you:
+
+```bash
+export PATH="$HOME/.local/bin:$PATH"     # and add the same line to ~/.bashrc
+```
+
+If something else on this machine already provides `kubectl`, the installer says so
+by name rather than shadowing it quietly. `OUT_BIN=$PWD/def/bin` installs
+somewhere private instead.
+
+**Two variants worth knowing before you need them.** `make deps image full` bakes
+every pinned binary into the image at build time (`DEPS_SOURCE=baked`), so
+`docker save` gives you the entire installer as one file to carry into an
+air-gapped network. And `DEPS_SOURCE=artifactory` with `DEPS_ARTIFACTORY_URL`
+pulls from a generic internal repo, which is usually the only thing a locked-down
+client allows.
+
+From here on this machine has curl, so **`make deps` is the short form** for
+every later run and every later copy of this directory. The container path is
+the first-time path.
+
+
+## Prove the machine before blaming the project
+
+```bash
+make check
+make cluster up
+kubectl get nodes
+```
+
+`make check` re-runs every check — host, docker, toolchain, memory, ports — and
+changes nothing. Run now, it should end with nothing left to do by hand, and that
+is the point: it is the scoreboard, not the installer.
+
+`make cluster up` builds rig's built-in defaults — one node, no addons,
+boots fast. You do not need it to develop anything, but you do want to know that
+kind, the kubeconfig context and the derived port block work *before* a new
+project has any problems of its own to confuse them with. `make cluster down`
+when you are done looking.
+
+Before starting a second cluster, and it will not be long:
+
+```bash
+make cluster list
+```
+
+Available memory, per-cluster usage and each cluster's port block. On a 16 GiB
+box four single-node clusters are comfortable and six push into swap, so this is
+worth reading before rather than after. `make cluster free <names>` stops
+clusters without deleting them; `docker start` brings them back untouched.
+
+
+## Scaffold the project
+
+The canonical layout is [`all/projects/templates/conventions.md`](../all/projects/templates/conventions.md).
+Read it — it is short, opinionated, and exists precisely so nobody
+reverse-engineers a layout from whichever repo they happened to open. What
+follows is only the mechanical part.
+
+```bash
+SLUG=<slug>                                    # short, lowercase, no separators
+cp -r ~/wdir/semester/all/projects/templates/broad ~/wdir/semester/"$SLUG"
+cd ~/wdir/semester/"$SLUG"
+grep -rl '<slug>' ctrl | xargs sed -i "s/<slug>/$SLUG/g"
+cp ctrl/k8s/.env.example ctrl/k8s/.env
+git init && git add -A && git commit -m "scaffold $SLUG from broad"
+```
+
+`<slug>` is the only placeholder and it lives only under `ctrl/` — cluster name,
+namespace, ConfigMap name, and the `NAME=` in `kind-up.sh` / `kind-down.sh`. One
+sed does all of it.
+
+The slug is the folder name, lowercase and short — `mpr`, `unt`, `nvi`. The
+cluster takes that name and the context becomes `kind-<slug>`, derived by the
+scaffold's Makefile from the directory, so there is nothing to edit for either.
+
+**Pick the Tilt port deliberately.** `ctrl/k8s/.env.example` ships a value that
+is already in use, so copying it unchanged puts two projects on one port:
+
+```bash
+grep -h '^TILT_PORT=' ~/wdir/semester/*/ctrl/k8s/.env 2>/dev/null | sort
+```
+
+Choose a free one in `10300–10399` — the range ALL reserves in
+`projects/index.json` under `policy` — avoiding `10350`, which is Tilt's own
+default. Currently taken: `nvi` 10330, `unt` 10340, `mpr` 10360, `mlv` 10370,
+`eth` 10380, `lng` 10390. This is the Tilt *web UI* port, not a service port;
+each project owns its own service ports separately. The scaffold ships it blank
+on purpose, so there is nothing to collide with until you choose.
+
+The scaffold's `ctrl/k8s/` is the same shape as every other project here, and it
+builds as shipped:
+
+```
+kind-config.yaml       one node; gateway NodePort 30080 -> hostPort 8080
+base/                  namespace, configmap, app (Deployment + Service)
+overlays/dev/          promotes the app Service to NodePort 30080
+```
+
+Check it before `kind` spends minutes on anything — this renders the whole tree
+without a cluster and catches a broken patch immediately:
+
+```bash
+kubectl kustomize ctrl/k8s/overlays/dev
+```
+
+The workload is an nginx placeholder so a fresh copy reaches something that
+answers; replace it. Keep `30080` in step between the overlay patch and
+`kind-config.yaml`'s `containerPort` — the hostPort is this project's to pick.
+Reachability is a plain kind port mapping: no ingress controller and no MetalLB.
+Caddy maps `<slug>.local.ar` onto the host port (`~/wdir/semester/ppl/local/Caddyfile`),
+with `*.local.ar` resolving to 127.0.0.1 through dnsmasq. That is the whole chain.
+
+**For `ctrl/Tiltfile`, copy rig's** rather than a live project's. rig ships one
+that derives its cluster, context, ports and manifest directory from
+`ctrl/ports.sh active` instead of hardcoding a slug, and carries a catalogue of
+the blocks every project here ends up needing. Copying from `unt` or `nvi` is
+what the estate did until now, and it is why the same Tiltfile preamble exists
+in six places with the slug typed in by hand five times each.
+
+> **Two things in this document disagree with rig and are not settled.** It
+> mandates Tilt ports in `10300–10399`, while rig derives a block from the
+> directory name at `20000+` so copies cannot collide — a rig-managed project
+> takes rig's. And it names `ctrl/k8s/.env.example`, which is the `broad`
+> scaffold's layout; rig's is `ctrl/.env.example`. Both are this document
+> describing the house scaffold from inside rig's tree.
+
+
+## Run it
+
+```bash
+make kind-up      # idempotent create, then selects the context
+make tilt-up      # context + your assigned port
+```
+
+`tilt-up` passes `--context kind-<slug>` every time, which is the point of going
+through `make` at all: tilt cannot deploy into whichever cluster you last looked
+at.
+
+`make tilt-down` and `make kind-down` close the loop, and `make kind-reset` is
+delete-and-recreate for when a cluster wedges.
+
+
+## Register it
+
+The project exists; now it is findable. Add an entry to
+`~/wdir/semester/all/projects/index.json` and write its `projects/<slug>.md` beside the
+others. Structured fields in the index, prose in the markdown.
+
+Putting it on the CI server and deploying it is `ppl`'s half, and it starts at
+`~/wdir/semester/ppl/ctrl/init-repo.sh` — gitea remote, then Woodpecker. That is a
+different document.

rig/Makefile

@@ -0,0 +1,99 @@
+# Thin control Makefile: the subcommand is an argument (`make cluster down`); logic lives in ctrl/ scripts.
+#   make check | deps | cluster up | tilt | docs     (`make help` lists all)
+# Start with:  make check && make deps && make cluster up
+# Notes: docs/notes/Makefile.md
+
+# Identity and ports, asked once of ctrl/ports.sh, read positionally (selftest pins the order):
+#   CLUSTER KUBECONTEXT HTTP HTTPS TILT REGISTRY MANIFESTS_DIR
+FACTS     := $(shell bash ctrl/ports.sh active 2>/dev/null)
+SLUG      := $(shell echo '$(notdir $(CURDIR))' | tr '[:upper:]' '[:lower:]' | tr -c 'a-z0-9-' '-' | sed 's/^-*//; s/-*$$//')
+# Fall back to the folder name, not empty, if ports.sh fails on a broken config.
+CLUSTER   := $(or $(word 1,$(FACTS)),$(SLUG))
+KCTX      := --context $(or $(word 2,$(FACTS)),kind-$(SLUG))
+TILT_PORT := $(word 5,$(FACTS))
+DEPSIMG   := $(SLUG)-deps
+
+# Words after the target become the script's subcommand. Make would otherwise
+# treat them as goals of their own, so each gets a no-op rule.
+ARGS := $(wordlist 2,$(words $(MAKECMDGOALS)),$(MAKECMDGOALS))
+ifneq ($(ARGS),)
+$(eval $(ARGS):;@:)
+# ...and as PHONY, because some of those words name real directories (ctrl, docs, ...).
+.PHONY: $(ARGS)
+endif
+
+.PHONY: help check deps cluster tilt docs selftest standalone \
+        kind-up kind-down kind-reset tilt-up tilt-down
+
+help:                          ## list targets
+	@grep -hE '^[a-z][a-z-]*:.*?##' $(MAKEFILE_LIST) | sed 's/:.*##/\t/' | expand -t16
+
+# ── this machine ───────────────────────────────────────────────────────────
+
+# Everything that looks and never changes anything: host, docker, toolchain,
+# config, memory, ports, registry, addons. `check mem` goes deeper on memory —
+# how far it really climbs, and the WSL .wslconfig backup/restore.
+check:                         ## is this machine ready?  [all] [mem [status|push|all|backup|restore]]
+	bash ctrl/check.sh $(ARGS)
+
+# `deps image` is for a machine with nothing but Docker: the installer runs from
+# the image instead — see BOOTSTRAP.md. `full` bakes every binary in.
+deps:                          ## install the toolchain  [core|dev]  [image [full]]
+ifeq ($(word 1,$(ARGS)),image)
+	docker build -f ctrl/Dockerfile.deps \
+	  --target $(if $(filter full,$(ARGS)),deps-full,deps) \
+	  -t $(DEPSIMG):$(if $(filter full,$(ARGS)),full,deps) .
+else
+	bash ctrl/deps.sh install $(or $(ARGS),dev)
+endif
+
+# ── the cluster ────────────────────────────────────────────────────────────
+
+# up also starts the registry and installs the profile's addons, and the ports
+# derive from the folder name — there is nothing else to run first.
+cluster:                       ## this env + the machine  [up|down|reset|list|free]
+	bash ctrl/cluster.sh $(or $(ARGS),up)
+
+# ── dev loop + docs ────────────────────────────────────────────────────────
+
+docs:                          ## documentation  [serve|graphs]        (default serve)
+	bash ctrl/docs.sh $(or $(ARGS),serve)
+
+# --port only when TILT_PORT resolved; the Tiltfile asks ports.sh for the rest itself.
+tilt:                          ## dev loop  [up|down]                  (default up)
+	cd ctrl && tilt $(or $(ARGS),up) $(KCTX) $(if $(filter down,$(ARGS)),,$(if $(TILT_PORT),--port $(TILT_PORT)))
+
+# ── maintaining rig ────────────────────────────────────────────────────────
+
+# The counterpart to check: that one asks about the MACHINE and never fails,
+# this one asks about RIG and exits 1. Checks are written as the decisions they
+# defend, so a failure names what is being undone.
+selftest:                      ## does rig still do what it says? exits 1 if not
+	bash ctrl/selftest.sh
+
+# The one-file versions of rig's tools, one folder per profile, for machines the
+# full rig is not going to. Generated from rig as it is, never edited by hand;
+# `check` is what selftest runs to catch a kit left behind by a change to rig.
+standalone:                    ## single-file kits  [write|check|export DIR]  (default write)
+	bash ctrl/standalone.sh $(or $(ARGS),write)
+
+# ── the shape every other project uses ─────────────────────────────────────
+# Aliases matching other projects' kind-up / tilt-up; each calls the same script.
+# Nothing else reads these names: rename, delete or add freely (and update .PHONY).
+
+kind-up:                       ## alias for `cluster up`
+	bash ctrl/cluster.sh up
+
+kind-down:                     ## alias for `cluster down`
+	bash ctrl/cluster.sh down
+
+kind-reset:                    ## alias for `cluster reset`
+	bash ctrl/cluster.sh reset
+
+# These two match the other projects' spelling. rig ships ctrl/Tiltfile, so they
+# run — it deploys the examples in k8s/base until you replace them.
+tilt-up:                       ## alias for `tilt up`
+	cd ctrl && tilt up $(KCTX) $(if $(TILT_PORT),--port $(TILT_PORT))
+
+tilt-down:                     ## alias for `tilt down`
+	cd ctrl && tilt down $(KCTX)

rig/README.md

@@ -0,0 +1,206 @@
+# rig
+
+A runnable local model of a large, regulated estate — legacy and new side by
+side. Its job is onboarding and exploration, not a production replica: most
+services are deliberately mocked, because what has to be faithful is the
+topology, not the workloads.
+
+## Prerequisite
+
+**Docker.** Nothing else — no curl, no jq, no python, no apt repositories.
+
+### Starting from plain Windows
+
+Everything here is bash and runs *inside* a Linux shell, so on a Windows machine
+that means WSL. Nothing in rig installs WSL, and nothing will: `wsl --install`
+enables Windows features and requires a reboot, which is not something a script
+should do to a machine on your behalf — and there is no tested undo for it.
+
+From an elevated PowerShell or Command Prompt, once:
+
+```powershell
+wsl --install
+```
+
+Then reboot and open the Linux shell it installed.
+
+**If you cloned this on the Windows side, copy it into WSL before carrying on.**
+WSL can reach the Windows drives at `/mnt/c`, and working from there mostly
+functions — slowly — but file watching does not: that filesystem raises no
+inotify events, so anything watching for edits silently stops seeing them.
+
+```bash
+cp -r /mnt/c/Users/<you>/rig ~/rig
+cd ~/rig
+```
+
+`make deps` reports it if you are running from `/mnt/...`. Then carry on below.
+
+If it fails, the usual causes give unhelpful messages:
+
+| symptom | cause |
+| --- | --- |
+| "the virtual machine could not be started" | virtualization disabled in BIOS/UEFI |
+| the command is not recognised | Windows build too old — needs 2004 or later |
+| the install starts, then nothing works | a reboot is still pending |
+
+Running the scripts from **Git Bash, MSYS or Cygwin does not work** — those look
+close enough to a Linux shell to get started and then fail without `/proc` or a
+docker socket. `ctrl/deps.sh` detects that and says so rather than letting you
+find out the slow way.
+
+## Read the docs first
+
+```bash
+make docs      # serves on localhost, prints the URL
+```
+
+They run before anything is installed, which matters because they are the
+instructions for everything else. No cluster and no toolchain required.
+
+Why the code is the way it is — the reasoning, measurements and gotchas — lives
+in [`docs/notes/`](docs/notes/), one file per script, so the code keeps short comments.
+
+## Then
+
+```bash
+make check         # is this machine ready? short; `make check all` for every detail
+make deps          # install the toolchain (add `core` on a managed machine)
+make cluster up    # cluster + registry + the profile's addons
+```
+
+That is the whole setup. `make cluster up` also starts this environment's local
+registry and wires it into the node, so an image built locally is pullable by the
+cluster without going near docker.io. `make check` shows its port, among
+everything else:
+
+```bash
+make check                  # ... registry    localhost:<port>  (running)
+docker build -t localhost:<port>/app:1 .
+docker push localhost:<port>/app:1
+kubectl --context kind-$(basename $PWD) run app --image=localhost:<port>/app:1
+```
+
+The port block is derived from the directory name, so two copies of rig never
+collide — nothing to configure. `make check all` lists it; `bash ctrl/ports.sh persist`
+pins it into `ctrl/.env` if you want it fixed:
+
+```bash
+make cluster list                          # every cluster on this machine, with memory
+make cluster free                          # stop the others if memory is tight
+make cluster down                          # remove this cluster and its registry
+```
+
+**The verbs are yours to change.** `cluster` is the script — `ctrl/cluster.sh` —
+and every spelling above is a `Makefile` target that calls it. `make kind-up` is
+an alias for `make cluster up`, kept because the other projects on this machine
+answer to that spelling and muscle memory spans repos rather than stopping at
+one. Nothing outside the `Makefile` reads these names, so rename them, drop the
+ones you never type, or add whatever your own projects already say: each alias
+is two lines at the bottom of the file, calling the same script the canonical
+target does.
+
+**`make tilt` works on a fresh copy, unedited.** rig ships `ctrl/Tiltfile`, and
+`k8s/base` already boots, so the dev loop comes up with the two examples running
+and nothing to configure first.
+
+It hardcodes nothing. It asks `ctrl/ports.sh active` for this environment's
+cluster name, kube context, ports and manifest directory — the same values every
+other rig script resolves through `ctrl/lib/config.sh` — so a copied and renamed
+rig deploys into its own cluster with no edits. Every other project here writes
+its slug into the Tiltfile five or six times by hand, which is exactly the
+collision `kind-config.yaml.tpl` exists to avoid.
+
+What it deploys is `MANIFESTS_DIR`, defaulting to rig's own `ctrl/k8s/overlays/dev`.
+Point that at an overlay versioned elsewhere and rig stops owning the manifests.
+
+Replace the examples, then add your images and resources in the two marked
+sections. The catalogue below them holds the blocks that recur across every
+project here — `docker_build`, resource ordering, gateway reload, port-forwards —
+with the parts that are easy to get wrong already commented.
+
+`make help` lists every target.
+
+On a machine where Docker really is the only thing installed, `make deps` has
+nothing to download with — see [BOOTSTRAP.md](BOOTSTRAP.md), which runs the
+toolchain through the installer container and carries on to scaffolding and running
+a new project.
+
+## One directory is one environment
+
+Copy this directory, rename it, run it. Cluster name, kubectl context, image
+tags and the host port block all derive from the directory name, so copies never
+collide and neither one's teardown can touch the other.
+
+A copy of this directory is a **sibling** of it, named after the environment it
+models (`acme-rig`). That is why the ignore rules for copies sit in the *parent*
+repo's `.gitignore` rather than here: a rule in this directory cannot see a
+directory beside it.
+
+## Profiles
+
+**rig needs no profile.** With none named it runs on built-in defaults: one node,
+no addons, a local registry, the newest Kubernetes version it pins. A profile is
+an optional overlay — a file in `ctrl/env.d/`, named by `PROFILE` — for when you
+want different addons or registry.
+
+rig ships **examples**, not active profiles, because each one is a use case rather
+than something every rig needs. Copy one to use it:
+
+| example | what it changes |
+| --- | --- |
+| `client.env.example` | images through a mirror of a corporate registry |
+| `offline.env.example` | air-gapped: everything from a preloaded local registry |
+| `data.env.example` | databases and a scheduler: postgres, redis, airflow |
+
+```bash
+cp ctrl/env.d/data.env.example ctrl/env.d/data.env
+PROFILE=data make cluster up      # installs the profile's addons too
+PROFILE=data make check           # what the profile wants, and what exists
+```
+
+The **cluster itself** is one file, `ctrl/k8s/kind-config.yaml.tpl` (one node).
+To change it — more nodes, other port mappings — edit it and `make cluster
+reset`. The node count is read back out of it, so there is nothing to drift. The layout under `ctrl/k8s/` is the
+same as every other project here — a kind config, a kustomize `base/`, an
+`overlays/dev/` — see [`ctrl/k8s/README.md`](ctrl/k8s/README.md).
+
+## Addons
+
+Each addon is its own idempotent script in `ctrl/addons/`, and a profile names
+the ones it wants in `ADDONS`. Adding one is adding a file — there is no
+dispatcher to edit.
+
+**There is no ingress controller, deliberately.** They pin a narrow window of
+Kubernetes versions, so depending on one would constrain which k8s a rig can be
+built with — and running a trailing-edge control plane to model a legacy estate
+is the whole point. Services are reached through MetalLB and
+`type: LoadBalancer`, which carries no such constraint and is also what a real
+cluster does.
+
+| Addon | Does |
+| --- | --- |
+| `metallb` | gives `type: LoadBalancer` an address it can actually reach |
+| `cert-manager` | a local CA, so TLS works offline |
+| `metrics-server` | makes `kubectl top` work on kind |
+| `postgres` | database, in the `data` namespace |
+| `redis` | cache and broker |
+| `airflow` | scheduled pipelines; needs postgres and redis |
+
+The last three are **cabinets**: a public service dropped in as-is, the upstream
+image unmodified, reachable at a known address. A cabinet is declared once and
+installs on either target — a `service.yml` composes it for a laptop, and these
+install the same one here. The names match on purpose: each cabinet carries a
+`rig_addon` field pointing at `ctrl/addons/<name>.sh`.
+
+Plain manifests rather than helm charts, like every other addon: a chart repo is
+a network dependency, and the `offline` profile exists precisely so there is a
+path with none. Images are pinned in `ctrl/versions.env` and can be preloaded.
+
+Passwords are generated on first install and kept across re-runs, so re-running
+an addon never rotates a credential out from under something already connected:
+
+```bash
+kubectl -n data get secret postgres -o jsonpath='{.data.POSTGRES_PASSWORD}' | base64 -d
+kubectl -n data port-forward svc/airflow 8080:8080
+```

rig/ctrl/.env.example

@@ -0,0 +1,39 @@
+# Machine-local config. Copy to ctrl/.env (gitignored) and edit.
+# Cluster SHAPE: an optional profile in ctrl/env.d/. Architecture MODEL: arch/<name>.json.
+# Notes: docs/notes/env.md
+
+# A profile in ctrl/env.d/ to build. Empty means rig's built-in defaults, which
+# need no profile at all. Copy an env.d/*.env.example to <name>.env to add one.
+PROFILE=
+
+# Cluster name; the kubectl context becomes kind-<CLUSTER>.
+# LEAVE UNSET: it defaults to this folder's name, which keeps the folder copyable.
+# CLUSTER=
+
+# Host ports. LEAVE UNSET — derived from the directory name (see ctrl/ports.sh).
+# `bash ctrl/ports.sh persist` pins them here; set a value only to override.
+# HTTP_PORT=
+# HTTPS_PORT=
+# TILT_PORT=
+# REGISTRY_PORT=
+
+# Where the application manifests live; repoint at their own repo, e.g.
+#   MANIFESTS_DIR=../platform-manifests/overlays/dev
+MANIFESTS_DIR=ctrl/k8s/overlays/dev
+
+# Where the installer fetches the pinned binaries from:
+#   upstream (needs internet) | artifactory (generic repo) | baked (in the image)
+DEPS_SOURCE=upstream
+DEPS_ARTIFACTORY_URL=
+
+# --- Registry -------------------------------------------------------------
+# Mode comes from the profile (REGISTRY_MODE). Secrets required for mirror/remote:
+REGISTRY_REMOTE_URL=
+REGISTRY_USER=
+REGISTRY_PASSWORD=
+
+# Corporate root CA, if Artifactory is fronted by an internal CA.
+# Symptom when missing: x509: certificate signed by unknown authority
+REGISTRY_CA_FILE=
+
+# (The local registry's host port is part of the derived block above.)

rig/ctrl/Dockerfile.deps

@@ -0,0 +1,34 @@
+# Toolchain installer image: installs the pinned toolchain onto the host; Docker is the only prerequisite.
+#   docker build -f ctrl/Dockerfile.deps --target deps        -t <slug>-deps        .
+#   docker build -f ctrl/Dockerfile.deps --target deps-full -t <slug>-deps:full   .
+# Notes: docs/notes/Dockerfile.deps.md
+
+FROM debian:trixie-slim AS deps
+
+# curl: fetch and verify; graphviz + python3: diagrams. docker-cli, NOT docker.io
+# (which lacks the `docker` binary under --no-install-recommends).
+RUN apt-get update && apt-get install -y --no-install-recommends \
+        ca-certificates curl jq graphviz python3 docker-cli \
+    && rm -rf /var/lib/apt/lists/*
+
+# The installer is the generated one-file standalone kit, pins frozen in.
+ARG PROFILE=default
+WORKDIR /work
+COPY standalone/${PROFILE}/rigdeps.sh /work/rigdeps.sh
+RUN chmod +x /work/rigdeps.sh
+
+# Defaults; every one is overridable with -e at run time.
+ENV DEPS_SOURCE=upstream \
+    OUT_BIN=/out/bin \
+    HOST_ROOT=/host
+
+ENTRYPOINT ["/work/rigdeps.sh"]
+CMD ["install"]
+
+
+# ---------------------------------------------------------------------------
+# deps-full — same image, binaries baked in, works with no network at all.
+FROM deps AS deps-full
+RUN /work/rigdeps.sh fetch --to /opt/rig/bin
+ENV DEPS_SOURCE=baked \
+    BAKED_BIN=/opt/rig/bin

rig/ctrl/Dockerfile.example

@@ -0,0 +1,24 @@
+# EXAMPLE component image. Copy, rename, replace:
+#   ctrl/Dockerfile.api  ->  image <cluster>-api  ->  image: in k8s/base/api.yaml
+# COPY paths are relative to the REPO ROOT (Tilt context='..'), not this directory.
+# Notes: docs/notes/Dockerfile.example.md
+
+FROM python:3.12-slim
+
+WORKDIR /app
+
+# Dependencies first, in their own layer, so a source edit does not reinstall them.
+COPY api/requirements.txt ./
+RUN pip install --no-cache-dir -r requirements.txt
+
+# Repo-root relative — see above.
+COPY api/ ./api/
+
+# Match this with the containerPort in the manifest and the target of the
+# Service in front of it.
+EXPOSE 8000
+
+CMD ["python", "-m", "api"]
+
+# live_update: Tiltfile's sync('../api', '/app/api') must match COPY api/ + WORKDIR /app,
+# or edits silently do nothing.

rig/ctrl/Tiltfile

@@ -0,0 +1,97 @@
+# The dev loop. `make tilt` from the project root, or `cd ctrl && tilt up`.
+# Works unedited; replace the two EXAMPLES and add yours in the marked sections.
+# rig supplies this file but does not own it, and nothing here names this directory.
+# Notes: docs/notes/Tiltfile.md
+
+# ── who we are, and on which ports ─────────────────────────────────────────
+# Asked of ctrl/ports.sh (via lib/config.sh), never recomputed here in Starlark.
+_facts   = str(local('bash ports.sh active', quiet=True)).split()
+CLUSTER  = _facts[0]
+CTX      = _facts[1]
+HTTP     = _facts[2]
+HTTPS    = _facts[3]
+TILT     = _facts[4]
+REGISTRY = _facts[5]
+
+# Where the manifests live (MANIFESTS_DIR, see k8s/README.md).
+# The value is REPO-ROOT relative and this file runs in ctrl/, so prefix '../'.
+MANIFESTS = '../' + _facts[6]
+
+# ── refuse to deploy into the wrong cluster ────────────────────────────────
+# Tilt fixes the context before parsing this file, so it can only be refused here.
+# `make tilt` passes --context; this catches a bare `tilt up`.
+allow_k8s_contexts(CTX)
+if k8s_context() != CTX:
+    fail("Wrong kubectl context: '%s'. This is %s — run: make tilt, or tilt up --context %s"
+         % (k8s_context(), CLUSTER, CTX))
+
+# The namespace has to exist before anything lands in it, and kustomize does not
+# guarantee ordering across resources. Creating it here is idempotent.
+local('kubectl --context %s create namespace %s --dry-run=client -o yaml | kubectl --context %s apply -f -'
+      % (CTX, CLUSTER, CTX), quiet=True)
+
+# ── images go to this environment's own registry ───────────────────────────
+# Fail closed: name the registry rather than let Tilt infer it, or a miss pushes
+# an unqualified image to docker.io.
+default_registry('localhost:' + REGISTRY)
+
+k8s_yaml(kustomize(MANIFESTS))
+
+# ── Images ─────────────────────────────────────────────────────────────────
+# (nothing yet — rig's examples run upstream images. Add docker_build calls here.)
+
+
+# ── Resources ──────────────────────────────────────────────────────────────
+# (nothing yet — add k8s_resource calls here to name and order what you deploy.)
+
+
+# Everything with no dev loop of its own, gathered so it does not clutter the UI.
+k8s_resource(
+    objects=[CLUSTER + ':namespace'],
+    new_name='infra',
+)
+
+# ═══════════════════════════════════════════════════════════════════════════
+# Catalogue — paste what you need, delete the rest.
+# Commented out so this file runs as-is.
+# ═══════════════════════════════════════════════════════════════════════════
+#
+# ── build an image ─────────────────────────────────────────────────────────
+# context= is the REPO ROOT ('..'); dockerfile= is relative to THIS file (ctrl/).
+# So every COPY is repo-root relative, even for files beside the Dockerfile.
+#
+# docker_build(
+#     CLUSTER + '-api',                  # must match `image:` in the manifest —
+#     context='..',                      #   that string is the only thing
+#     dockerfile='Dockerfile.api',       #   connecting the two
+#     ignore=['.git', 'def', '.venv', 'node_modules', '__pycache__'],
+#     live_update=[sync('../api', '/app/api')],
+# )
+#
+# ── name and order a resource ──────────────────────────────────────────────
+# k8s_resource('api', resource_deps=['postgres'], labels=['app'])
+# k8s_resource('gateway', resource_deps=['api', 'ui'], labels=['app'])
+#
+# ── reload the gateway when its config changes ─────────────────────────────
+# A hash-less configMapGenerator ConfigMap never changes name, so edits do NOT
+# roll the pod on their own.
+#
+# local_resource(
+#     'gateway-reload',
+#     cmd='kubectl --context %s -n %s rollout restart deployment/gateway' % (CTX, CLUSTER),
+#     deps=['k8s/base/Caddyfile'],
+#     resource_deps=['gateway'],
+#     auto_init=False,
+# )
+#
+# ── an overlay whose secretGenerator reads outside its own directory ───────
+# kustomize refuses to read above the kustomization root unless told to. Only
+# add this if you actually have such a generator; it loosens a safety check.
+#
+# k8s_yaml(kustomize(MANIFESTS, flags=['--load-restrictor=LoadRestrictionsNone']))
+#
+# ── reach a service directly, bypassing the gateway ────────────────────────
+# Prefer the gateway; host ports are shared machine-wide. If you need one, take it
+# from this environment's own port block.
+#
+# k8s_resource('postgres', port_forwards=[str(int(HTTP) + 5) + ':5432'])

rig/ctrl/addons.sh

@@ -0,0 +1,38 @@
+#!/usr/bin/env bash
+# Install the addons the active profile asked for, in the order listed.
+# One idempotent script per addon in ctrl/addons/.
+# Usage: addons.sh install | list
+# Notes: docs/notes/addons.md
+set -euo pipefail
+cd "$(dirname "$0")"
+
+source ./lib/config.sh
+load_config
+
+install() {
+    if [ -z "${ADDONS// /}" ]; then
+        echo "no addons in profile '$PROFILE_NAME'"
+        return
+    fi
+    local a
+    for a in $ADDONS; do
+        if [ ! -f "addons/${a}.sh" ]; then
+            echo "no such addon: addons/${a}.sh" >&2
+            exit 1
+        fi
+        echo "addon: $a"
+        bash "addons/${a}.sh"
+    done
+}
+
+list() {
+    echo "profile '$PROFILE_NAME' wants: ${ADDONS:-none}"
+    echo "available:"
+    ls addons/*.sh 2>/dev/null | xargs -n1 basename | sed 's/\.sh$//' | sed 's/^/  /'
+}
+
+case "${1:-list}" in
+    install) install ;;
+    list)    list ;;
+    *)       echo "usage: $0 [install|list]" >&2; exit 1 ;;
+esac

rig/ctrl/addons/airflow.sh

@@ -0,0 +1,109 @@
+#!/usr/bin/env bash
+# Apache Airflow — the cluster half of the airflow cabinet (one `standalone` pod).
+# Requires the postgres addon; refuses to install without it.
+# Notes: docs/notes/addons.md
+set -euo pipefail
+cd "$(dirname "$0")/.."
+
+source ./lib/config.sh
+load_config
+
+K="kubectl --context ${KUBECONTEXT}"
+NS="${DATA_NAMESPACE:-data}"
+
+if ! $K get deployment -n "$NS" postgres >/dev/null 2>&1; then
+    echo "  ! airflow needs the postgres addon, and it is not installed" >&2
+    echo "    add it before airflow in the profile's ADDONS:" >&2
+    echo "      ADDONS=\"... postgres airflow\"" >&2
+    exit 1
+fi
+
+# Reuse the credential postgres generated rather than storing a second copy.
+db_user=$($K get secret -n "$NS" postgres -o jsonpath='{.data.POSTGRES_USER}' | base64 -d)
+db_pass=$($K get secret -n "$NS" postgres -o jsonpath='{.data.POSTGRES_PASSWORD}' | base64 -d)
+db_name=$($K get secret -n "$NS" postgres -o jsonpath='{.data.POSTGRES_DB}' | base64 -d)
+
+if $K get secret -n "$NS" airflow >/dev/null 2>&1; then
+    echo "  secret exists, keeping the current admin password and fernet key"
+else
+    admin_password=$(head -c 18 /dev/urandom | base64 | tr -d '/+=' | head -c 24)
+    # Airflow requires a 32-byte urlsafe-base64 key; without a fixed one every
+    # restart invalidates every stored connection.
+    fernet_key=$(head -c 32 /dev/urandom | base64 | tr '+/' '-_')
+    $K create secret generic airflow -n "$NS" \
+        --from-literal=ADMIN_USER="${AIRFLOW_ADMIN_USER:-admin}" \
+        --from-literal=ADMIN_PASSWORD="$admin_password" \
+        --from-literal=FERNET_KEY="$fernet_key" \
+        --from-literal=SQL_ALCHEMY_CONN="postgresql+psycopg2://${db_user}:${db_pass}@postgres:5432/${db_name}" \
+        >/dev/null
+    echo "  generated an admin password (read it back with the command below)"
+fi
+
+echo "  applying manifests"
+$K apply -n "$NS" -f - >/dev/null <<YAML
+apiVersion: v1
+kind: Service
+metadata:
+  name: airflow
+spec:
+  selector:
+    app: airflow
+  ports:
+    - port: 8080
+      targetPort: 8080
+---
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: airflow
+spec:
+  replicas: 1
+  strategy:
+    type: Recreate
+  selector:
+    matchLabels:
+      app: airflow
+  template:
+    metadata:
+      labels:
+        app: airflow
+    spec:
+      containers:
+        - name: airflow
+          image: ${AIRFLOW_IMAGE}
+          args: ["standalone"]
+          env:
+            - name: AIRFLOW__CORE__EXECUTOR
+              value: LocalExecutor
+            - name: AIRFLOW__CORE__LOAD_EXAMPLES
+              value: "false"
+            - name: AIRFLOW__DATABASE__SQL_ALCHEMY_CONN
+              valueFrom:
+                secretKeyRef: {name: airflow, key: SQL_ALCHEMY_CONN}
+            - name: AIRFLOW__CORE__FERNET_KEY
+              valueFrom:
+                secretKeyRef: {name: airflow, key: FERNET_KEY}
+            - name: _AIRFLOW_WWW_USER_USERNAME
+              valueFrom:
+                secretKeyRef: {name: airflow, key: ADMIN_USER}
+            - name: _AIRFLOW_WWW_USER_PASSWORD
+              valueFrom:
+                secretKeyRef: {name: airflow, key: ADMIN_PASSWORD}
+          ports:
+            - containerPort: 8080
+          readinessProbe:
+            httpGet:
+              path: /health
+              port: 8080
+            # First boot runs the whole migration before it serves anything.
+            initialDelaySeconds: 60
+            periodSeconds: 15
+            failureThreshold: 20
+YAML
+
+echo "  waiting for airflow (the first boot migrates the database, so this is slow)..."
+$K rollout status deployment/airflow -n "$NS" --timeout=600s
+
+echo "  in-cluster: http://airflow.${NS}.svc.cluster.local:8080"
+echo "  reach it:   kubectl --context ${KUBECONTEXT} -n ${NS} port-forward svc/airflow 8080:8080"
+echo "  password:   kubectl --context ${KUBECONTEXT} -n ${NS} get secret airflow -o jsonpath='{.data.ADMIN_PASSWORD}' | base64 -d"

rig/ctrl/addons/cert-manager.sh

@@ -0,0 +1,61 @@
+#!/usr/bin/env bash
+# cert-manager plus a self-signed cluster issuer (offline local CA).
+# Notes: docs/notes/addons.md
+set -euo pipefail
+cd "$(dirname "$0")/.."
+
+source ./lib/config.sh
+load_config
+
+K="kubectl --context ${KUBECONTEXT}"
+
+if $K get deployment -n cert-manager cert-manager >/dev/null 2>&1; then
+    echo "  already installed"
+else
+    $K apply -f "https://github.com/cert-manager/cert-manager/releases/download/${CERT_MANAGER_VERSION}/cert-manager.yaml"
+fi
+
+echo "  waiting for cert-manager..."
+$K wait --namespace cert-manager \
+    --for=condition=ready pod --selector=app.kubernetes.io/instance=cert-manager \
+    --timeout=240s
+
+# A self-signed root, then a CA issuer chained off it. Workloads reference
+# ClusterIssuer/local-ca and get a cert from a CA you can actually distribute.
+echo "  creating local CA issuer"
+$K apply -f - <<'YAML' >/dev/null
+apiVersion: cert-manager.io/v1
+kind: ClusterIssuer
+metadata:
+  name: selfsigned-root
+spec:
+  selfSigned: {}
+---
+apiVersion: cert-manager.io/v1
+kind: Certificate
+metadata:
+  name: local-ca
+  namespace: cert-manager
+spec:
+  isCA: true
+  commonName: rig-local-ca
+  secretName: local-ca-key-pair
+  duration: 87600h
+  privateKey:
+    algorithm: ECDSA
+    size: 256
+  issuerRef:
+    name: selfsigned-root
+    kind: ClusterIssuer
+---
+apiVersion: cert-manager.io/v1
+kind: ClusterIssuer
+metadata:
+  name: local-ca
+spec:
+  ca:
+    secretName: local-ca-key-pair
+YAML
+
+echo "  export the CA for your browser/client with:"
+echo "    kubectl --context ${KUBECONTEXT} -n cert-manager get secret local-ca-key-pair -o jsonpath='{.data.tls\\.crt}' | base64 -d"

rig/ctrl/addons/metallb.sh

@@ -0,0 +1,92 @@
+#!/usr/bin/env bash
+# MetalLB — makes `Service type: LoadBalancer` actually get an address.
+# The pool is derived from the kind Docker network at install time.
+# Notes: docs/notes/addons.md
+set -euo pipefail
+cd "$(dirname "$0")/.."
+
+source ./lib/config.sh
+load_config
+
+K="kubectl --context ${KUBECONTEXT}"
+
+# ── work out an address range ──────────────────────────────────────────────
+# kind hands node addresses out from the bottom of the subnet, so the top is
+# free. Taking a slice there avoids collisions with current and future nodes.
+subnet=$(docker network inspect kind \
+         -f '{{range .IPAM.Config}}{{.Subnet}} {{end}}' 2>/dev/null \
+         | tr ' ' '\n' | grep -E '^[0-9]+\.' | head -1)
+
+if [ -z "$subnet" ]; then
+    echo "  ! could not read the kind Docker network subnet" >&2
+    echo "    (is the cluster up? MetalLB needs the network to exist first)" >&2
+    exit 1
+fi
+
+base="${subnet%/*}"; prefix="${subnet#*/}"
+o1=$(echo "$base" | cut -d. -f1); o2=$(echo "$base" | cut -d. -f2)
+o3=$(echo "$base" | cut -d. -f3)
+
+case "$prefix" in
+    16) pool_start="${o1}.${o2}.255.200"; pool_end="${o1}.${o2}.255.250" ;;
+    24) pool_start="${o1}.${o2}.${o3}.200"; pool_end="${o1}.${o2}.${o3}.250" ;;
+    *)
+        # Guessing a range inside an unexpected prefix risks handing out
+        # addresses that belong to something else. Say so instead.
+        echo "  ! kind network is $subnet — only /16 and /24 are handled" >&2
+        echo "    set the pool by hand in ctrl/addons/metallb.sh" >&2
+        exit 1
+        ;;
+esac
+
+echo "  kind network $subnet → pool ${pool_start}-${pool_end}"
+
+# ── install ────────────────────────────────────────────────────────────────
+
+if $K get deployment -n metallb-system controller >/dev/null 2>&1; then
+    echo "  already installed"
+else
+    $K apply -f "https://raw.githubusercontent.com/metallb/metallb/${METALLB_VERSION}/config/manifests/metallb-native.yaml"
+fi
+
+# `rollout status`, not `kubectl wait`: wait errors out while the pod doesn't exist yet.
+echo "  waiting for the controller..."
+$K rollout status deployment/controller -n metallb-system --timeout=240s
+$K rollout status daemonset/speaker -n metallb-system --timeout=240s
+
+# The webhook rejects IPAddressPools until it is actually serving, and it comes
+# up a moment after the pod is Ready — so retry rather than fail the whole run
+# on a race that resolves itself in seconds.
+echo "  configuring the address pool"
+for attempt in 1 2 3 4 5 6 7 8 9 10; do
+    if $K apply -f - >/dev/null 2>&1 <<YAML
+apiVersion: metallb.io/v1beta1
+kind: IPAddressPool
+metadata:
+  name: default
+  namespace: metallb-system
+spec:
+  addresses:
+    - ${pool_start}-${pool_end}
+---
+# Layer 2 mode: one node answers ARP for each address. No BGP peer needed, which
+# is what makes this work on a laptop.
+apiVersion: metallb.io/v1beta1
+kind: L2Advertisement
+metadata:
+  name: default
+  namespace: metallb-system
+spec:
+  ipAddressPools:
+    - default
+YAML
+    then
+        echo "  pool ready: ${pool_start}-${pool_end}"
+        exit 0
+    fi
+    sleep 3
+done
+
+echo "  ! the pool was rejected after 10 attempts — is the webhook up?" >&2
+$K get pods -n metallb-system >&2
+exit 1

rig/ctrl/addons/metrics-server.sh

@@ -0,0 +1,21 @@
+#!/usr/bin/env bash
+# metrics-server — makes `kubectl top` work (patched with --kubelet-insecure-tls for kind).
+# Notes: docs/notes/addons.md
+set -euo pipefail
+cd "$(dirname "$0")/.."
+
+source ./lib/config.sh
+load_config
+
+K="kubectl --context ${KUBECONTEXT}"
+
+if ! $K get deployment -n kube-system metrics-server >/dev/null 2>&1; then
+    $K apply -f "https://github.com/kubernetes-sigs/metrics-server/releases/download/${METRICS_SERVER_VERSION}/components.yaml"
+fi
+
+$K patch deployment metrics-server -n kube-system --type=json \
+    -p '[{"op":"add","path":"/spec/template/spec/containers/0/args/-","value":"--kubelet-insecure-tls"}]' \
+    >/dev/null 2>&1 || true
+
+echo "  waiting for metrics-server..."
+$K rollout status deployment/metrics-server -n kube-system --timeout=180s

rig/ctrl/addons/postgres.sh

@@ -0,0 +1,105 @@
+#!/usr/bin/env bash
+# PostgreSQL — the cluster half of the postgres cabinet: plain manifests, one replica on a PVC.
+# Notes: docs/notes/addons.md
+set -euo pipefail
+cd "$(dirname "$0")/.."
+
+source ./lib/config.sh
+load_config
+
+K="kubectl --context ${KUBECONTEXT}"
+NS="${DATA_NAMESPACE:-data}"
+
+$K get namespace "$NS" >/dev/null 2>&1 || $K create namespace "$NS"
+
+# The password is generated once and then left alone, so re-running this does
+# not rotate the credential out from under whatever is already connected.
+if $K get secret -n "$NS" postgres >/dev/null 2>&1; then
+    echo "  secret exists, keeping the current password"
+else
+    password=$(head -c 18 /dev/urandom | base64 | tr -d '/+=' | head -c 24)
+    $K create secret generic postgres -n "$NS" \
+        --from-literal=POSTGRES_DB="${POSTGRES_DB:-postgres}" \
+        --from-literal=POSTGRES_USER="${POSTGRES_USER:-postgres}" \
+        --from-literal=POSTGRES_PASSWORD="$password" >/dev/null
+    echo "  generated a password (read it back with the command printed below)"
+fi
+
+echo "  applying manifests"
+$K apply -n "$NS" -f - >/dev/null <<YAML
+apiVersion: v1
+kind: PersistentVolumeClaim
+metadata:
+  name: postgres-data
+spec:
+  accessModes: [ReadWriteOnce]
+  resources:
+    requests:
+      storage: ${POSTGRES_STORAGE:-2Gi}
+---
+apiVersion: v1
+kind: Service
+metadata:
+  name: postgres
+spec:
+  selector:
+    app: postgres
+  ports:
+    - port: 5432
+      targetPort: 5432
+---
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: postgres
+spec:
+  replicas: 1
+  # One volume, one writer. Rolling would start a second pod against the same
+  # PVC before the first exits, and Postgres refuses to share a data directory.
+  strategy:
+    type: Recreate
+  selector:
+    matchLabels:
+      app: postgres
+  template:
+    metadata:
+      labels:
+        app: postgres
+    spec:
+      containers:
+        - name: postgres
+          image: ${POSTGRES_IMAGE}
+          envFrom:
+            - secretRef:
+                name: postgres
+          env:
+            # The image initialises into the volume root otherwise, and a
+            # lost+found from the PVC makes it refuse to initdb.
+            - name: PGDATA
+              value: /var/lib/postgresql/data/pgdata
+          ports:
+            - containerPort: 5432
+          volumeMounts:
+            - name: data
+              mountPath: /var/lib/postgresql/data
+          readinessProbe:
+            exec:
+              command: ["sh", "-c", "pg_isready -U \$POSTGRES_USER -d \$POSTGRES_DB"]
+            initialDelaySeconds: 5
+            periodSeconds: 5
+          livenessProbe:
+            exec:
+              command: ["sh", "-c", "pg_isready -U \$POSTGRES_USER -d \$POSTGRES_DB"]
+            initialDelaySeconds: 30
+            periodSeconds: 15
+      volumes:
+        - name: data
+          persistentVolumeClaim:
+            claimName: postgres-data
+YAML
+
+echo "  waiting for postgres..."
+$K rollout status deployment/postgres -n "$NS" --timeout=240s
+
+echo "  in-cluster: postgres.${NS}.svc.cluster.local:5432"
+echo "  password:   kubectl --context ${KUBECONTEXT} -n ${NS} get secret postgres -o jsonpath='{.data.POSTGRES_PASSWORD}' | base64 -d"

rig/ctrl/addons/redis.sh

@@ -0,0 +1,57 @@
+#!/usr/bin/env bash
+# Redis — the cluster half of the redis cabinet: cache/broker, no persistence.
+# Notes: docs/notes/addons.md
+set -euo pipefail
+cd "$(dirname "$0")/.."
+
+source ./lib/config.sh
+load_config
+
+K="kubectl --context ${KUBECONTEXT}"
+NS="${DATA_NAMESPACE:-data}"
+
+$K get namespace "$NS" >/dev/null 2>&1 || $K create namespace "$NS"
+
+echo "  applying manifests"
+$K apply -n "$NS" -f - >/dev/null <<YAML
+apiVersion: v1
+kind: Service
+metadata:
+  name: redis
+spec:
+  selector:
+    app: redis
+  ports:
+    - port: 6379
+      targetPort: 6379
+---
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: redis
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: redis
+  template:
+    metadata:
+      labels:
+        app: redis
+    spec:
+      containers:
+        - name: redis
+          image: ${REDIS_IMAGE}
+          ports:
+            - containerPort: 6379
+          readinessProbe:
+            exec:
+              command: ["redis-cli", "ping"]
+            initialDelaySeconds: 3
+            periodSeconds: 5
+YAML
+
+echo "  waiting for redis..."
+$K rollout status deployment/redis -n "$NS" --timeout=180s
+
+echo "  in-cluster: redis://redis.${NS}.svc.cluster.local:6379/0"

rig/ctrl/check.sh

@@ -0,0 +1,186 @@
+#!/usr/bin/env bash
+# Readiness check: is this machine ready to run rig? Reports and instructs; never fixes.
+# Usage: check.sh [all | mem [status|push|all|backup|restore]]   (all = every detail)
+# Notes: docs/notes/check.md
+set -euo pipefail
+cd "$(dirname "$0")"
+
+# `check mem` goes deeper on memory than the summary below: how far allocation
+# really climbs, and the WSL .wslconfig backup/restore.
+if [ "${1:-}" = mem ]; then
+    shift
+    exec bash ./mem.sh "${@:-status}"
+fi
+
+# Compact by default: facts only with `all`; problems (!) always print.
+VERBOSE=""
+if [ "${1:-}" = all ]; then VERBOSE=1; fi
+fact() { if [ -n "$VERBOSE" ]; then echo "$@"; fi; }
+
+bash ./deps.sh detect ${VERBOSE:+all}
+
+source ./lib/config.sh
+load_config
+
+# A /proc/meminfo field in MB, 0 if absent. MEMINFO/OVERCOMMIT_FILE override for testing.
+mb_of() {
+    awk -v k="$1:" '$1 == k { printf "%d", $2 / 1024; found = 1 }
+                    END      { if (!found) printf "0" }' "${MEMINFO:-/proc/meminfo}"
+}
+
+# NODE_MB (cost of one node) comes from load_config in lib/config.sh; do not copy it here.
+
+# Every running container's working set in MB, tagged with its kind cluster ('-' if none).
+container_mb() {
+    docker info >/dev/null 2>&1 || return 0
+    awk -F'\t' '
+        FILENAME == ARGV[1] { cl[$1] = ($2 == "" ? "-" : $2); if ($2 != "") isc[$2] = 1; next }
+        {
+            grp = ($1 in cl ? cl[$1] : "-")
+            # A kind cluster'"'"'s local registry is a plain container with no kind
+            # label, named <cluster>-registry, so on its own it would read as a
+            # stranger. It belongs to its cluster — but only if that cluster exists:
+            # a registry whose cluster is gone is a genuine stray, and says so.
+            if (grp == "-" && $1 ~ /-registry$/) {
+                base = $1; sub(/-registry$/, "", base)
+                if (base in isc) grp = base
+            }
+            split($2, u, " "); v = u[1]; mb = 0
+            if      (v ~ /GiB$/) { sub(/GiB$/, "", v); mb = v * 1024 }
+            else if (v ~ /MiB$/) { sub(/MiB$/, "", v); mb = v }
+            else if (v ~ /KiB$/) { sub(/KiB$/, "", v); mb = v / 1024 }
+            else if (v ~ /B$/)   { sub(/B$/,   "", v); mb = v / 1048576 }
+            printf "%d\t%s\t%s\n", mb, grp, $1
+        }
+    ' <(docker ps --format '{{.Names}}\t{{.Label "io.x-k8s.kind.cluster"}}' 2>/dev/null) \
+      <(docker stats --no-stream --format '{{.Name}}\t{{.MemUsage}}' 2>/dev/null)
+}
+
+port_busy() {
+    if command -v ss >/dev/null 2>&1; then
+        ss -ltn "sport = :$1" 2>/dev/null | grep -q LISTEN && return 0 || return 1
+    fi
+    # iproute2 is absent from a minimal Debian, so fall back to procfs rather
+    # than silently reporting everything as free.
+    local hex; hex=$(printf ':%04X' "$1")
+    grep -qi "^ *[0-9]*: [0-9A-F]*$hex " /proc/net/tcp /proc/net/tcp6 2>/dev/null
+}
+
+echo
+echo "rig"
+echo "  cluster     ${CLUSTER} (${KUBECONTEXT})  profile ${PROFILE_NAME}, ${NODES} node(s), registry ${REGISTRY_MODE}"
+fact "  ingress     ${INGRESS_MODE}"
+if [ ! -f ./.env ]; then
+    fact "  .env        none — built-in defaults (cp ctrl/.env.example ctrl/.env to set values)"
+fi
+
+# ── memory: does this cluster fit right now? Warns; never blocks. ──────────
+total_mb=$(mb_of MemTotal)
+avail_mb=$(mb_of MemAvailable)
+swap_used_mb=$(( $(mb_of SwapTotal) - $(mb_of SwapFree) ))
+overcommit=$(cat "${OVERCOMMIT_FILE:-/proc/sys/vm/overcommit_memory}" 2>/dev/null || echo '?')
+need_mb=$(( NODES * NODE_MB ))
+
+rows=$(container_mb)
+# If our cluster is already up, its memory is already out of MemAvailable: need nothing more.
+ours_mb=$(awk -F'\t' -v c="$CLUSTER" '$2 == c { s += $1 } END { print s + 0 }' <<< "$rows")
+still_mb=$(( ours_mb > 0 ? 0 : need_mb ))
+headroom=$(( avail_mb - still_mb ))
+
+# The biggest things holding memory, other than this cluster: kind clusters summed, the rest by name.
+others=$(awk -F'\t' -v c="$CLUSTER" '
+            $2 != c && $2 != "-" && $2 != "" { k["kind cluster \x27" $2 "\x27"] += $1 }
+            $2 == "-"                         { k["container \x27" $3 "\x27"]    += $1 }
+            END { for (n in k) printf "%d\t%s\n", k[n], n }' <<< "$rows" | sort -rn)
+
+if [ "$still_mb" -eq 0 ] && [ "$headroom" -ge 512 ]; then
+    printf "  memory      up, holding %d MB — %d MB headroom for what you deploy\n" "$ours_mb" "$headroom"
+elif [ "$still_mb" -eq 0 ]; then
+    printf "  ! memory    up, but only %d MB headroom for anything you deploy\n" "$headroom"
+elif [ "$headroom" -ge 512 ]; then
+    printf "  memory      fits — ~%d MB for %s node(s), %d MB headroom\n" "$need_mb" "$NODES" "$headroom"
+elif [ "$headroom" -ge 0 ]; then
+    printf "  ! memory    fits, but only %d MB headroom (~%d MB for %s node(s))\n" "$headroom" "$need_mb" "$NODES"
+else
+    printf "  ! memory    does not fit: ~%d MB needed, %d MB available\n" "$still_mb" "$avail_mb"
+    # Two failures with opposite fixes, and telling them apart is the point.
+    if [ "$still_mb" -le "$total_mb" ]; then
+        echo "              something else holds it (below) — stopping that helps, a bigger VM would not."
+        if grep -q 'kind cluster' <<< "$others"; then
+            echo "              'make cluster free' stops the other kind clusters. It stops, never deletes."
+        fi
+    else
+        echo "              the machine itself is too small: ${total_mb} MB total."
+    fi
+fi
+if [ -n "$others" ] && { [ -n "$VERBOSE" ] || [ "$headroom" -lt 512 ]; }; then
+    echo "              held elsewhere:"
+    head -6 <<< "$others" | awk -F'\t' '{ printf "              %6d MB  %s\n", $1, $2 }'
+    n_others=$(wc -l <<< "$others")
+    if [ "$n_others" -gt 6 ]; then
+        echo "              ... and $((n_others - 6)) more"
+    fi
+fi
+if [ "$swap_used_mb" -gt 0 ]; then
+    fact "              ${swap_used_mb} MB already in swap, which 'available' does not count: expect slow before failing"
+fi
+if [ "$overcommit" = "1" ]; then
+    fact "              overcommit=1: allocations never fail, so read 'fits' as a ceiling (OOM killer settles up)"
+fi
+
+# ── ports: checked before creation; docker reports a clash only halfway through. ──
+# Ports held by our own cluster are not clashes. Second grep, not `tr -d ':->'` (a tr range).
+ours=$(docker ps --filter "label=io.x-k8s.kind.cluster=${CLUSTER}" \
+        --format '{{.Ports}}' 2>/dev/null | tr ',' '\n' \
+        | grep -oE ':[0-9]+->' | grep -oE '[0-9]+' || true)
+
+clash=0 list="" mine=0
+for entry in "HTTP:${HTTP_PORT}" "HTTPS:${HTTPS_PORT}" \
+             "TILT:${TILT_PORT}" "REGISTRY:${REGISTRY_PORT}"; do
+    name="${entry%%:*}"; p="${entry#*:}"
+    [ -n "$p" ] || continue
+    list+="$p "
+    if ! port_busy "$p"; then
+        fact "$(printf "    %-9s %-6s free" "$name" "$p")"
+    elif echo "$ours" | grep -qx "$p"; then
+        mine=1
+        fact "$(printf "    %-9s %-6s in use by this environment's cluster" "$name" "$p")"
+    else
+        printf "  ! ports     %s %s IN USE by something else\n" "$name" "$p"
+        clash=1
+    fi
+done
+if [ "$clash" -eq 1 ]; then
+    echo "              override it in ctrl/.env (e.g. HTTP_PORT=21080), or rename this directory"
+elif [ "$mine" -eq 1 ]; then
+    echo "  ports       ${list% }  held by this cluster"
+else
+    echo "  ports       ${list% }  free"
+fi
+fact "              derived from the directory name; pin them: bash ctrl/ports.sh persist"
+
+# ── what `make cluster up` wires in beside the cluster ─────────────────────
+REG_NAME="${CLUSTER}-registry"
+if state=$(docker inspect -f '{{.State.Status}}' "$REG_NAME" 2>/dev/null); then
+    echo "  registry    localhost:${REGISTRY_PORT}  ($state)"
+else
+    fact "  registry    no container yet — 'make cluster up' starts it"
+fi
+echo "  addons      ${ADDONS:-none}"
+fact "              available: $(ls addons/*.sh 2>/dev/null | xargs -n1 basename | sed 's/\.sh$//' | tr '\n' ' ')"
+
+# The CA reaches three places and only one of them is ours. Report the other two.
+if [ -n "${REGISTRY_CA_FILE:-}" ]; then
+    if [ ! -r "$REGISTRY_CA_FILE" ]; then
+        echo "  ! CA        REGISTRY_CA_FILE not readable: $REGISTRY_CA_FILE"
+    else
+        fact "  CA          $REGISTRY_CA_FILE"
+        host="${REGISTRY_REMOTE_URL#*://}"; host="${host%%/*}"
+        if [ -n "$host" ] && [ ! -f "/etc/docker/certs.d/${host}/ca.crt" ]; then
+            echo "  ! CA        the HOST docker daemon does not trust it yet:"
+            echo "                sudo mkdir -p /etc/docker/certs.d/${host}"
+            echo "                sudo cp ${REGISTRY_CA_FILE} /etc/docker/certs.d/${host}/ca.crt"
+            echo "              (kind nodes are handled by registry.sh; in-cluster clients are the workload's job)"
+        fi
+    fi
+fi

rig/ctrl/cluster.sh

@@ -0,0 +1,138 @@
+#!/usr/bin/env bash
+# Cluster lifecycle (convergent, not exit-early), plus what else runs on this machine.
+# Usage: cluster.sh up | down | reset | list | free
+# Notes: docs/notes/cluster.md
+set -euo pipefail
+cd "$(dirname "$0")"
+
+source ./lib/config.sh
+load_config
+
+up() {
+    if kind get clusters 2>/dev/null | grep -qx "$CLUSTER"; then
+        echo "cluster '$CLUSTER' exists — converging"
+    else
+        # Say what this profile locks in BEFORE spending minutes building it:
+        # the kind config is fixed at creation and cannot be changed later.
+        echo "creating cluster '$CLUSTER' from profile '$PROFILE_NAME'"
+        echo "  kind config ${KIND_CONFIG}"
+        echo "  nodes       $NODES"
+        echo "  image       $NODE_IMAGE"
+        echo "  ingress     $INGRESS_MODE"
+        echo "  registry    $REGISTRY_MODE"
+        echo "  (fixed at creation — edit the kind config, then 'make cluster reset')"
+        echo
+
+        render_kind_config | kind create cluster --config -
+    fi
+
+    # The cluster can exist while its context does not — a reset or a switched
+    # KUBECONFIG loses it, and then nothing works despite a healthy cluster.
+    if ! kubectl config get-contexts -o name 2>/dev/null | grep -qx "$KUBECONTEXT"; then
+        echo "context '$KUBECONTEXT' missing from kubeconfig — re-exporting"
+        kind export kubeconfig --name "$CLUSTER"
+    fi
+    kubectl config use-context "$KUBECONTEXT" >/dev/null
+
+    bash registry.sh up
+
+    if [ -n "${ADDONS// /}" ]; then
+        bash addons.sh install
+    fi
+
+    echo
+    echo "cluster '$CLUSTER' ready (context $KUBECONTEXT)"
+}
+
+down() {
+    # The registry is a standalone container outside the cluster; take it down
+    # first so a reset doesn't leave it orphaned and holding a port.
+    bash registry.sh down || true
+
+    if kind get clusters 2>/dev/null | grep -qx "$CLUSTER"; then
+        echo "deleting cluster '$CLUSTER'..."
+        kind delete cluster --name "$CLUSTER"
+    else
+        echo "no cluster '$CLUSTER' to delete"
+    fi
+}
+
+# The escape hatch for a wedged cluster, and the only way to change a
+# creation-time setting such as the node count or port mappings.
+reset() {
+    down
+    echo
+    up
+}
+
+# ── the whole machine ──────────────────────────────────────────────────────
+# Every cluster is a running container tree whether or not you are using it, and
+# an idle one is the usual reason a new one will not fit.
+
+list() {
+    local total avail
+    total=$(awk '/^MemTotal:/{printf "%.1f", $2/1024/1024}' /proc/meminfo)
+    avail=$(awk '/^MemAvailable:/{printf "%.1f", $2/1024/1024}' /proc/meminfo)
+    echo "memory: ${avail} GB available of ${total} GB"
+    echo
+
+    local names; names=$(kind get clusters 2>/dev/null || true)
+    if [ -z "$names" ]; then
+        echo "no clusters"
+        return
+    fi
+
+    printf "%-16s %-10s %8s %6s  %-13s %s\n" CLUSTER STATE MEM NODES PORTS ""
+    local c nodes state mem base
+    for c in $names; do
+        nodes=$(docker ps -a --filter "label=io.x-k8s.kind.cluster=$c" --format '{{.Names}}' | wc -l)
+        state=$(docker inspect -f '{{.State.Status}}' "${c}-control-plane" 2>/dev/null || echo unknown)
+        if [ "$state" = "running" ]; then
+            mem=$(docker stats --no-stream --format '{{.MemUsage}}' \
+                  $(docker ps --filter "label=io.x-k8s.kind.cluster=$c" -q) 2>/dev/null \
+                  | awk '{gsub(/GiB/,"");gsub(/MiB/,"e-3");s+=$1} END {printf "%.1fG", s}')
+        else
+            mem="-"
+        fi
+        # A cluster's name is its directory slug, so its port block is derivable
+        # here without reading that directory's config.
+        base=$(derive_port_base "$c")
+        printf "%-16s %-10s %8s %6s  %-13s %s\n" "$c" "$state" "$mem" "$nodes" \
+            "${base}-$((base + 3))" \
+            "$([ "$c" = "$CLUSTER" ] && echo "<- this one")"
+    done
+}
+
+# Stop the OTHER clusters to free memory. Stops, never deletes — a stopped
+# cluster restarts with `docker start`, so nothing is lost.
+free() {
+    local targets=("$@")
+    if [ ${#targets[@]} -eq 0 ]; then
+        mapfile -t targets < <(kind get clusters 2>/dev/null | grep -vx "$CLUSTER" || true)
+    fi
+    if [ ${#targets[@]} -eq 0 ]; then
+        echo "nothing to stop"
+        return
+    fi
+
+    local c ids
+    for c in "${targets[@]}"; do
+        ids=$(docker ps --filter "label=io.x-k8s.kind.cluster=$c" -q)
+        if [ -z "$ids" ]; then
+            echo "cluster '$c' is not running"
+            continue
+        fi
+        echo "stopping '$c' (restart with: docker start \$(docker ps -aq -f label=io.x-k8s.kind.cluster=$c))"
+        # shellcheck disable=SC2086
+        docker stop $ids >/dev/null
+    done
+}
+
+case "${1:-up}" in
+    up)    up ;;
+    down)  down ;;
+    reset) reset ;;
+    list)  list ;;
+    free)  shift; free "$@" ;;
+    *)     echo "usage: $0 [up|down|reset|list|free]" >&2; exit 1 ;;
+esac

rig/ctrl/deps.sh

@@ -0,0 +1,740 @@
+#!/usr/bin/env bash
+# rig:standalone rigdeps detect
+# Toolchain installer: detect the host, install pinned tools into $OUT_BIN, report
+# host actions it will not perform (no sudo, no apt). Usually via `make deps`.
+# Usage: deps.sh [detect [all] | list | verify [core|dev] | fetch [core|dev] [--to DIR] | install [core|dev]]
+# Notes: docs/notes/deps.md
+
+set -euo pipefail
+
+# Keep the caller's cwd so a relative --to resolves there, not against ctrl/.
+INVOKED_FROM="$PWD"
+cd "$(dirname "$0")"
+
+# Pins arrive through load_config, not by sourcing versions.env, so `make
+# standalone` can freeze them in.
+source ./lib/config.sh
+load_config
+
+# Resolve a possibly-relative path against the caller's original directory.
+abspath() {
+    case "$1" in
+        /*) echo "$1" ;;
+        *)  echo "$INVOKED_FROM/$1" ;;
+    esac
+}
+
+OUT_BIN="${OUT_BIN:-$HOME/.local/bin}"
+HOST_ROOT="${HOST_ROOT:-/}"
+DEPS_SOURCE="${DEPS_SOURCE:-upstream}"
+DEPS_ARTIFACTORY_URL="${DEPS_ARTIFACTORY_URL:-}"
+BAKED_BIN="${BAKED_BIN:-/opt/rig/bin}"
+
+# Collected by detect(), printed by report_manual() at the very end.
+MANUAL=()
+
+# Facts print only with VERBOSE (`detect all`); problems (! and -) always print.
+fact() { if [ -n "${VERBOSE:-}" ]; then echo "$@"; fi; }
+
+# Host FILES are read through $HOST_ROOT; kernel facts are shared with the container.
+# A /proc/meminfo field in MB, 0 if absent. MEMINFO overrides the source for testing.
+mb_of() {
+    awk -v k="$1:" '$1 == k { printf "%d", $2 / 1024; found = 1 }
+                    END      { if (!found) printf "0" }' "${MEMINFO:-/proc/meminfo}"
+}
+
+host_file() {
+    local p="${1#/}"
+    if [ "$HOST_ROOT" != "/" ] && [ -e "$HOST_ROOT/$p" ]; then
+        echo "$HOST_ROOT/$p"
+    else
+        echo "/$p"
+    fi
+}
+
+# ── the tools this script itself needs ─────────────────────────────────────
+
+arch() {
+    case "$(uname -m)" in
+        x86_64|amd64)  echo amd64 ;;
+        aarch64|arm64) echo arm64 ;;
+        *)             uname -m ;;
+    esac
+}
+
+# Pins are amd64 only: refuse elsewhere and print how to get the right checksums.
+require_amd64() {
+    local a; a=$(arch)
+    [ "$a" = "amd64" ] && return 0
+    cat >&2 <<EOF
+This machine is ${a} ($(uname -m)); every pin in this script is linux/amd64.
+
+Nothing here would run, so it does not download. To make an ${a} version, the
+URLs need the ${a} artifact and the checksums need to come from each project's
+own published list — not from these values, and not from a download you did:
+
+    curl -sSL https://github.com/kubernetes-sigs/kind/releases/download/${KIND_VERSION}/checksums.txt
+    curl -sSL https://dl.k8s.io/release/${KUBECTL_VERSION}/bin/linux/${a}/kubectl.sha256
+    curl -sSL https://github.com/tilt-dev/tilt/releases/download/v${TILT_VERSION}/checksums.txt
+    curl -sSL https://github.com/tilt-dev/ctlptl/releases/download/v${CTLPTL_VERSION}/checksums.txt
+    curl -sSL https://github.com/jqlang/jq/releases/download/jq-${JQ_VERSION}/sha256sum.txt
+
+Edit the pinned block at the top of this file with what those print.
+EOF
+    exit 1
+}
+
+DL=""
+pick_downloader() {
+    if command -v curl >/dev/null 2>&1; then DL=curl
+    elif command -v wget >/dev/null 2>&1; then DL=wget
+    else
+        echo "neither curl nor wget is installed, so nothing can be downloaded." >&2
+        echo "Install one first:  $(pkg_install_cmd curl)" >&2
+        exit 1
+    fi
+}
+
+download() {
+    local url="$1" out="$2"
+    case "$DL" in
+        curl) curl -fsSL --retry 3 -o "$out" "$url" ;;
+        wget) wget -q --tries=3 -O "$out" "$url" ;;
+    esac
+}
+
+SHA=""
+pick_sha() {
+    if command -v sha256sum >/dev/null 2>&1; then SHA=sha256sum
+    elif command -v shasum >/dev/null 2>&1; then SHA="shasum -a 256"
+    else
+        echo "no sha256sum and no shasum — downloads could not be verified." >&2
+        echo "Refusing to install unverified binaries." >&2
+        exit 1
+    fi
+}
+
+# ── package manager, for the instructions only ─────────────────────────────
+# Never runs one; names the right one so reported actions are pasteable.
+
+pkg_install_cmd() {
+    local pkg="$1"
+    if command -v apt-get >/dev/null 2>&1; then echo "sudo apt-get update && sudo apt-get install -y $pkg"
+    elif command -v dnf >/dev/null 2>&1;     then echo "sudo dnf install -y $pkg"
+    elif command -v yum >/dev/null 2>&1;     then echo "sudo yum install -y $pkg"
+    elif command -v zypper >/dev/null 2>&1;  then echo "sudo zypper install -y $pkg"
+    elif command -v apk >/dev/null 2>&1;     then echo "sudo apk add $pkg"
+    else echo "install '$pkg' with this system's package manager"
+    fi
+}
+
+docker_pkg() {
+    # Debian and Ubuntu call it docker.io; the RPM distros call it docker.
+    if command -v apt-get >/dev/null 2>&1; then echo docker.io; else echo docker; fi
+}
+
+# ── detect ─────────────────────────────────────────────────────────────────
+
+# Windows outside WSL (Git Bash, MSYS, Cygwin) fails confusingly; name it instead.
+require_linux() {
+    case "$(uname -s)" in
+        MINGW*|MSYS*|CYGWIN*)
+            cat >&2 <<'EOF'
+This has to run inside WSL, not Git Bash / MSYS / Cygwin.
+
+If WSL is not installed yet, from an elevated PowerShell or Command Prompt:
+
+    wsl --install
+
+That enables Windows features and needs a reboot, so it is not something this
+script will do for you. Afterwards, open the Linux shell it installs and run
+this from there.
+
+See "Starting from plain Windows" in README.md.
+EOF
+            exit 1 ;;
+    esac
+}
+
+is_wsl() { grep -qi microsoft /proc/version 2>/dev/null; }
+
+detect() {
+    echo "host"
+    fact "  kernel      $(uname -r)"
+
+    local osr distro=""; osr=$(host_file /etc/os-release)
+    [ -r "$osr" ] && distro=$(sed -n 's/^PRETTY_NAME="\(.*\)"/\1/p' "$osr")
+    echo "  distro      ${distro:-unknown}  $(arch), $(if is_wsl; then echo WSL; else echo native linux; fi)"
+
+    # In MB (whole GB rounds away too much). Facts only; check.sh judges sufficiency.
+    local total_mb avail_mb swap_total_mb swap_used_mb om
+    total_mb=$(mb_of MemTotal)
+    avail_mb=$(mb_of MemAvailable)
+    swap_total_mb=$(mb_of SwapTotal)
+    swap_used_mb=$(( swap_total_mb - $(mb_of SwapFree) ))
+    printf "  memory      %d MB total, %d MB available%s\n" "$total_mb" "$avail_mb" \
+        "$(if [ "$swap_used_mb" -gt 0 ]; then echo ", $swap_used_mb MB in swap"; fi)"
+
+    # Overcommit mode: with 1 the OOM killer settles up later, after a clean start.
+    om=$(cat "${OVERCOMMIT_FILE:-/proc/sys/vm/overcommit_memory}" 2>/dev/null || echo '?')
+    case "$om" in
+        0) fact "  overcommit  0 heuristic — allocations are granted on a guess" ;;
+        1) fact "  overcommit  1 always — every allocation succeeds; the OOM killer is the only limit" ;;
+        2) fact "  overcommit  2 strict — an allocation fails honestly instead of killing later" ;;
+    esac
+
+    fact "  install to  $OUT_BIN"
+    detect_libc
+    detect_prereqs
+    detect_wsl
+    detect_filesystem
+    detect_docker
+    detect_inotify
+    detect_toolchain
+}
+
+detect_wsl() {
+    if ! is_wsl; then
+        return
+    fi
+
+    # systemd is off by default in WSL; enabling it needs a Windows-side restart.
+    local wc; wc=$(host_file /etc/wsl.conf)
+    if [ -r "$wc" ] && grep -qE '^\s*systemd\s*=\s*true' "$wc"; then
+        fact "  systemd     enabled in wsl.conf"
+    else
+        echo "  ! systemd not enabled in /etc/wsl.conf"
+        MANUAL+=("Enable systemd — add to /etc/wsl.conf:
+      [boot]
+      systemd=true
+  then from a WINDOWS terminal (not this shell):  wsl --shutdown")
+    fi
+
+    # WSL regenerates /etc/resolv.conf on every boot, which silently reverts any
+    # local DNS setup.
+    if [ -r "$wc" ] && grep -qE '^\s*generateResolvConf\s*=\s*false' "$wc"; then
+        fact "  resolv.conf pinned (generateResolvConf=false)"
+    else
+        fact "  - resolv.conf is WSL-generated; DNS_MODE=dnsmasq would be reverted on reboot"
+    fi
+
+    local wcfg
+    wcfg=$(ls "$HOST_ROOT"/mnt/c/Users/*/.wslconfig 2>/dev/null | head -1 || true)
+    if [ -n "$wcfg" ] && grep -qE '^\s*memory\s*=' "$wcfg"; then
+        fact "  wslconfig   memory set: $(grep -E '^\s*memory\s*=' "$wcfg" | tr -d ' ')"
+    else
+        MANUAL+=("Cap/raise the WSL VM memory — see what is set versus what booted:
+      make check mem
+  It prints the edit to make and the command to apply it.")
+    fi
+}
+
+# Filesystem types that deliver no inotify events (9p, drvfs, network, fuse).
+# Checks the fs type, not the path.
+watch_hostile_fs() {
+    local dir="$1" fstype
+    fstype=$(findmnt -no FSTYPE --target "$dir" 2>/dev/null || true)
+    [ -n "$fstype" ] || fstype=$(stat -f -c %T "$dir" 2>/dev/null || true)
+    case "$fstype" in
+        9p|v9fs|drvfs|cifs|smb3|nfs|nfs4|fuse.sshfs|fuseblk) echo "$fstype" ;;
+        *) echo "" ;;
+    esac
+}
+
+detect_filesystem() {
+    local root fstype
+    root=$(cd .. && pwd -P)
+    fstype=$(watch_hostile_fs "$root")
+    if [ -n "$fstype" ]; then
+        echo "  ! this directory is on $fstype — file watching will not work"
+        MANUAL+=("Move this onto the local disk. Nothing watching files sees changes
+  on a $fstype mount, and everything else is slower:
+      cp -r \"$root\" ~/ && cd ~/$(basename "$root")")
+    else
+        fact "  filesystem  $root  ($(findmnt -no FSTYPE --target "$root" 2>/dev/null || echo local))"
+    fi
+}
+
+# tilt needs glibc >= 2.34 (measured on Amazon Linux 2). Report the version here;
+# `verify` catches the actual failure after installing.
+detect_libc() {
+    local v=""
+    if command -v ldd >/dev/null 2>&1; then
+        v=$(ldd --version 2>/dev/null | head -1 | grep -oE '[0-9]+\.[0-9]+$' || true)
+    fi
+    if [ -z "$v" ]; then
+        fact "  libc        unknown (no ldd) — 'verify' is the real test"
+        return 0
+    fi
+    fact "  libc        glibc $v"
+    if [ "$(printf '%s\n2.34\n' "$v" | sort -V | head -1)" != "2.34" ]; then
+        echo "  ! older than glibc 2.34, which tilt needs. kubectl, kind, jq and"
+        echo "    ctlptl are static or libc-only and work here; tilt will not start."
+        echo "    Install the core tier, or run tilt from a container."
+    fi
+    return 0
+}
+
+# What this script itself needs, so `detect` answers "will install work?".
+detect_prereqs() {
+    local missing=""
+    if command -v curl >/dev/null 2>&1; then fact "  download    curl"
+    elif command -v wget >/dev/null 2>&1; then fact "  download    wget"
+    else echo "  ! no curl and no wget — nothing can be downloaded"; missing+=" curl"
+    fi
+
+    if command -v sha256sum >/dev/null 2>&1 || command -v shasum >/dev/null 2>&1; then
+        fact "  checksums   ok"
+    else
+        echo "  ! no sha256sum or shasum — downloads could not be verified"
+        missing+=" coreutils"
+    fi
+
+    if command -v tar >/dev/null 2>&1 && command -v gzip >/dev/null 2>&1; then
+        fact "  archives    tar + gzip"
+    else
+        echo "  ! no tar/gzip — tilt and ctlptl ship as tarballs, so the dev tier"
+        echo "    cannot be unpacked. The core tier is two bare binaries and is fine."
+        missing+=" tar gzip"
+    fi
+
+    if [ -n "$missing" ]; then
+        MANUAL+=("Install what this script needs to run at all:
+      $(pkg_install_cmd "${missing# }")")
+    fi
+    return 0
+}
+
+detect_docker() {
+    # Daemon reachability is the real question; the CLI is only how we ask.
+    if ! command -v docker >/dev/null 2>&1; then
+        if [ -S /var/run/docker.sock ]; then
+            echo "  docker      socket present (no cli in this context)"
+        else
+            echo "  ! docker not found and no socket at /var/run/docker.sock"
+            MANUAL+=("Install Docker — the one true prerequisite, and the only thing here
+  that needs root:
+      $(pkg_install_cmd "$(docker_pkg)")
+      sudo systemctl enable --now docker
+      sudo usermod -aG docker \"\$USER\"
+  then log out and back in, so the new group applies to your shell.")
+        fi
+        return
+    fi
+    if docker info >/dev/null 2>&1; then
+        echo "  docker      $(docker version --format '{{.Server.Version}}' 2>/dev/null)"
+        local n
+        n=$(docker ps --filter "label=io.x-k8s.kind.cluster" --format '{{.Names}}' 2>/dev/null | wc -l)
+        # Must be an `if`, not `[ ] && echo`: a zero count would return 1 under set -e.
+        if [ "$n" -gt 0 ]; then
+            echo "  kind        $n node container(s) running — 'make cluster list'"
+        fi
+    else
+        echo "  ! docker cli present but the daemon is unreachable"
+        MANUAL+=("Start Docker, or add yourself to the docker group:
+      sudo usermod -aG docker \"\$USER\"   # then log out and back in")
+    fi
+}
+
+# kind and Tilt both watch large trees. WSL ships defaults (8192/128) far too low,
+# and the failure mode is silent: Tilt simply stops noticing file changes.
+detect_inotify() {
+    local w i
+    w=$(cat /proc/sys/fs/inotify/max_user_watches 2>/dev/null || echo 0)
+    i=$(cat /proc/sys/fs/inotify/max_user_instances 2>/dev/null || echo 0)
+    fact "  inotify     watches=$w instances=$i"
+
+    if [ "$w" -lt 524288 ] || [ "$i" -lt 512 ]; then
+        echo "  ! inotify limits are low — Tilt will silently stop noticing file changes"
+        MANUAL+=("Raise inotify limits (needs root on the host):
+      echo -e 'fs.inotify.max_user_watches=524288\\nfs.inotify.max_user_instances=512' \\
+        | sudo tee /etc/sysctl.d/99-rig.conf
+      sudo sysctl --system")
+    fi
+}
+
+# ── fetch ──────────────────────────────────────────────────────────────────
+
+# Resolve where a given artifact comes from, honouring DEPS_SOURCE.
+resolve_url() {
+    local upstream="$1"
+    case "$DEPS_SOURCE" in
+        upstream)    echo "$upstream" ;;
+        artifactory)
+            if [ -z "$DEPS_ARTIFACTORY_URL" ]; then
+                echo "DEPS_SOURCE=artifactory but DEPS_ARTIFACTORY_URL is empty" >&2
+                exit 1
+            fi
+            echo "${DEPS_ARTIFACTORY_URL%/}/$(basename "$upstream")"
+            ;;
+        *) echo "unsupported DEPS_SOURCE '$DEPS_SOURCE' for a download" >&2; exit 1 ;;
+    esac
+}
+
+verify() {
+    local file="$1" want="$2" name="$3" got
+    got=$($SHA "$file" | awk '{print $1}')
+    if [ "$got" != "$want" ]; then
+        echo "checksum mismatch for $name" >&2
+        echo "  expected $want" >&2
+        echo "  got      $got" >&2
+        exit 1
+    fi
+}
+
+# fetch_bin <name> <url> <sha256> <dest-dir>  — a bare binary
+fetch_bin() {
+    local name="$1" url="$2" sha="$3" dest="$4"
+    local tmp="$dest/.$name.tmp"
+    echo "  fetching $name"
+    download "$(resolve_url "$url")" "$tmp"
+    verify "$tmp" "$sha" "$name"
+    mv "$tmp" "$dest/$name"
+    chmod +x "$dest/$name"
+}
+
+# fetch_tgz <name> <url> <sha256> <dest-dir> <path-inside-archive> <strip>
+# Archive layouts differ — tilt's is flat (the binary at the root, strip=0),
+# others nest it a directory down — so the caller says which.
+fetch_tgz() {
+    local name="$1" url="$2" sha="$3" dest="$4" inner="$5" strip="$6"
+    local tmp="$dest/.$name.tgz"
+    echo "  fetching $name"
+    download "$(resolve_url "$url")" "$tmp"
+    verify "$tmp" "$sha" "$name"
+    # --no-same-owner: as root, tar would restore the archive's uid/gid.
+    tar -xzf "$tmp" -C "$dest" --strip-components="$strip" --no-same-owner "$inner"
+    rm -f "$tmp"
+    chmod +x "$dest/$name"
+}
+
+# The installer runs as root; hand files in a mounted dir back to the mount point's owner.
+fix_ownership() {
+    local dir="$1"
+    [ -d "$dir" ] || return 0
+    local owner="${HOST_UID:-}:${HOST_GID:-}"
+    if [ "$owner" = ":" ]; then
+        owner=$(stat -c '%u:%g' "$dir")
+    fi
+    [ "$owner" = "0:0" ] && return 0
+    chown -R "$owner" "$dir" 2>/dev/null || true
+}
+
+# core: talk to a cluster someone else runs. dev: core plus tools that build clusters.
+CORE_TOOLS="kubectl jq"
+# No helm (nothing uses a chart). ctlptl wires in a local registry; compose is often
+# missing from distro docker packages.
+DEV_TOOLS="kind tilt ctlptl docker-compose"
+
+# ── what is already on this machine ───────────────────────────────────────
+# A tool already on PATH at its pinned version is left where it is.
+
+pin_of() {
+    case "$1" in
+        kubectl) echo "$KUBECTL_VERSION" ;;
+        jq)      echo "$JQ_VERSION" ;;
+        kind)    echo "$KIND_VERSION" ;;
+        tilt)    echo "$TILT_VERSION" ;;
+        ctlptl)  echo "$CTLPTL_VERSION" ;;
+        docker-compose) echo "$COMPOSE_VERSION" ;;
+    esac
+}
+
+# The version string a binary reports (kubectl needs --client).
+reported_version() {
+    local tool="$1" path="$2"
+    case "$tool" in
+        kubectl) "$path" version --client 2>/dev/null ;;
+        jq)      "$path" --version 2>/dev/null ;;
+        *)       "$path" version 2>/dev/null ;;
+    esac
+}
+
+# Does the binary at PATH report PIN? Whole-token match, leading v optional.
+# Bash regex rather than grep, deliberately.
+version_matches() {
+    local tool="$1" path="$2" pin="$3" out v re
+    out=$(reported_version "$tool" "$path") || return 1
+    v="${pin#v}"
+    v="${v//./\\.}"
+    re="(^|[^0-9.])v?${v}([^0-9.]|\$)"
+    [[ $out =~ $re ]]
+}
+
+# DEPS_ONLY narrows a fetch to the tools it names; unset means the whole tier.
+# Only install() sets it.
+want() { [ -z "${DEPS_ONLY:-}" ] || [[ " $DEPS_ONLY " == *" $1 "* ]]; }
+
+# Every tool in the tier with its state, probed once and reported once. What
+# still needs fetching is left in TOOLCHAIN_NEED for install() to act on.
+TOOLCHAIN_NEED=""
+detect_toolchain() {
+    local tier="${TIER:-dev}" b pin path found
+    TOOLCHAIN_NEED=""
+    local n=0
+    echo
+    fact "toolchain  (pinned, tier '$tier')"
+    for b in $(tier_tools "$tier"); do
+        n=$((n + 1))
+        pin=$(pin_of "$b")
+        path=$(command -v "$b" 2>/dev/null || true)
+        # compose is normally a docker CLI plugin, not on PATH: ask docker instead.
+        if [ "$b" = docker-compose ] && [ -z "$path" ]; then
+            if found=$(docker compose version --short 2>/dev/null) && [ -n "$found" ]; then
+                if [ "${found#v}" = "${pin#v}" ]; then
+                    fact "$(printf "    %-8s %-9s %s" "$b" "$pin" "docker cli plugin")"
+                else
+                    printf "  ! %-8s wants %s, the docker cli plugin reports '%s'\n" \
+                        "$b" "$pin" "$found"
+                    TOOLCHAIN_NEED+="$b "
+                fi
+                continue
+            fi
+        fi
+        if [ -z "$path" ]; then
+            printf "  - %-8s %-9s not found\n" "$b" "$pin"
+            TOOLCHAIN_NEED+="$b "
+        elif version_matches "$b" "$path" "$pin"; then
+            fact "$(printf "    %-8s %-9s %s" "$b" "$pin" "$path")"
+        else
+            found=$(reported_version "$b" "$path" 2>/dev/null | head -1 || true)
+            printf "  ! %-8s wants %s, %s reports '%s'\n" "$b" "$pin" "$path" "$found"
+            TOOLCHAIN_NEED+="$b "
+        fi
+    done
+    if [ -z "$TOOLCHAIN_NEED" ]; then
+        if [ -n "${VERBOSE:-}" ]; then echo "  all $n on PATH — nothing to fetch"
+        else echo "toolchain   all $n pinned tools on PATH  (tier $tier)"; fi
+    else
+        echo "toolchain   'make deps' fetches only: ${TOOLCHAIN_NEED% }"
+    fi
+}
+
+fetch() {
+    local dest="$OUT_BIN" tier="${TIER:-dev}"
+    while [ $# -gt 0 ]; do
+        case "$1" in
+            --to)      dest="$2"; shift 2 ;;
+            core|dev)  tier="$1"; shift ;;
+            *)         echo "unknown argument: $1" >&2; exit 1 ;;
+        esac
+    done
+    dest="$(abspath "$dest")"
+    mkdir -p "$dest"
+    TIER="$tier"
+
+    if [ "$DEPS_SOURCE" = "baked" ]; then
+        echo "installing baked binaries from $BAKED_BIN"
+        cp -a "$BAKED_BIN"/. "$dest"/
+        fix_ownership "$dest"
+        return
+    fi
+
+    if [ -n "${DEPS_ONLY:-}" ]; then
+        echo "fetching ${DEPS_ONLY% } (source: $DEPS_SOURCE)"
+    else
+        echo "fetching '$tier' toolchain (source: $DEPS_SOURCE)"
+    fi
+    if want kubectl; then fetch_bin kubectl "$KUBECTL_URL" "$KUBECTL_SHA256" "$dest"; fi
+    if want jq;      then fetch_bin jq      "$JQ_URL"      "$JQ_SHA256"      "$dest"; fi
+    if [ "$tier" = "dev" ]; then
+        if want kind;   then fetch_bin kind   "$KIND_URL"   "$KIND_SHA256"   "$dest"; fi
+        if want tilt;   then fetch_tgz tilt   "$TILT_URL"   "$TILT_SHA256"   "$dest" tilt   0; fi
+        if want ctlptl; then fetch_tgz ctlptl "$CTLPTL_URL" "$CTLPTL_SHA256" "$dest" ctlptl 0; fi
+        if want docker-compose; then
+            fetch_bin docker-compose "$COMPOSE_URL" "$COMPOSE_SHA256" "$dest"
+        fi
+    fi
+
+    fix_ownership "$dest"
+    # kind writes the kubeconfig as root too; hand that back as well.
+    fix_ownership "${KUBE_DIR:-/out/kube}"
+}
+
+# ── install ────────────────────────────────────────────────────────────────
+
+report_manual() {
+    echo
+    if [ ${#MANUAL[@]} -eq 0 ]; then
+        echo "nothing left to do by hand."
+        return
+    fi
+    echo "host actions this cannot perform (${#MANUAL[@]}):"
+    echo
+    local n=1
+    for m in "${MANUAL[@]}"; do
+        echo "  $n. $m"
+        echo
+        n=$((n + 1))
+    done
+}
+
+# A verified download proves the right file, not that this machine can run it
+# (old glibc breaks tilt). Run each one now.
+verify_tools() {
+    local tier="${1:-dev}" b bin out rc broke=0
+    echo "checking that each one actually runs"
+    for b in $(tier_tools "$tier"); do
+        bin="$OUT_BIN/$b"
+        if [ ! -x "$bin" ]; then
+            printf '  %-14s not installed\n' "$b"
+            continue
+        fi
+        # Not piped into `head`: under pipefail, SIGPIPE (141) looked like failure.
+        rc=0
+        case "$b" in
+            kubectl) out=$("$bin" version --client 2>&1) || rc=$? ;;
+            jq)      out=$("$bin" --version 2>&1) || rc=$? ;;
+            *)       out=$("$bin" version 2>&1) || rc=$? ;;
+        esac
+        out=${out%%$'\n'*}
+        if [ "$rc" -eq 0 ]; then
+            printf '  %-14s %s\n' "$b" "$out"
+        else
+            printf '  ! %-12s does not run here: %s\n' "$b" "$out"
+            broke=1
+        fi
+    done
+    if [ "$broke" -eq 1 ]; then
+        echo
+        echo "  A binary that downloads and verifies but will not start is almost"
+        echo "  always this distro's libc being older than the release needs."
+        echo "  'detect' prints the glibc version. The core tier (kubectl + jq)"
+        echo "  has no such dependency and will work regardless."
+    fi
+    return 0
+}
+
+list() {
+    echo "pinned, linux/amd64 only:"
+    printf '  %-14s %s\n' kubectl "$KUBECTL_VERSION"
+    printf '  %-14s %s\n' jq      "$JQ_VERSION"
+    printf '  %-14s %s\n' kind    "$KIND_VERSION"
+    printf '  %-14s %s\n' tilt    "$TILT_VERSION"
+    printf '  %-14s %s\n' ctlptl  "$CTLPTL_VERSION"
+    printf '  %-14s %s\n' docker-compose "$COMPOSE_VERSION"
+    echo
+    echo "  core = $CORE_TOOLS"
+    echo "  dev  = $CORE_TOOLS $DEV_TOOLS"
+    echo
+    echo "Checksums are pinned in the block at the top of this file. To bump one,"
+    echo "take the new checksum from the publisher's own release list — the header"
+    echo "comment has the exact commands."
+    return 0
+}
+
+tier_tools() { [ "$1" = "core" ] && echo "$CORE_TOOLS" || echo "$CORE_TOOLS $DEV_TOOLS"; }
+
+warn_shadowing() {
+    local b existing shadowed="" tier="${1:-dev}"
+    for b in $(tier_tools "$tier"); do
+        [ -x "$OUT_BIN/$b" ] || continue
+        # Where would this resolve if OUT_BIN weren't in the way?
+        existing=$(PATH=$(echo "$PATH" | tr ':' '\n' | grep -vx "$OUT_BIN" | paste -sd:) \
+                   command -v "$b" 2>/dev/null || true)
+        [ -n "$existing" ] || continue
+        [ "$existing" = "$OUT_BIN/$b" ] && continue
+        # The same version in both places is not a conflict: nothing changes for
+        # any other project whichever copy PATH happens to find first.
+        if version_matches "$b" "$existing" "$(pin_of "$b")"; then continue; fi
+        shadowed+="      $b  $existing"$'\n'
+    done
+
+    [ -n "$shadowed" ] || return 0
+
+    case ":${PATH}:" in
+        *":$OUT_BIN:"*) ;;
+        *) return 0 ;;   # not on PATH yet, so nothing is being shadowed
+    esac
+
+    echo
+    echo "  ! these were already installed elsewhere and are now shadowed by $OUT_BIN:"
+    printf '%s' "$shadowed"
+    echo "    Other projects on this machine will pick up the new versions."
+    MANUAL+=("Decide which toolchain wins. To keep the previous one, remove what
+  was just installed:
+      rm -f $(for b in $(tier_tools "$tier"); do printf '%s ' "$OUT_BIN/$b"; done)
+  Or install somewhere private instead:
+      OUT_BIN=\$PWD/def/bin make deps   # then put that dir first in PATH")
+}
+
+# Link the fetched docker-compose into ~/.docker/cli-plugins so `docker compose` works.
+install_compose_plugin() {
+    local src="$OUT_BIN/docker-compose" dir="$HOME/.docker/cli-plugins"
+    [ -x "$src" ] || return 0
+    mkdir -p "$dir"
+    # A real file there belongs to something else (docker-desktop, distro): don't overwrite.
+    if [ -e "$dir/docker-compose" ] && [ ! -L "$dir/docker-compose" ]; then
+        MANUAL+=("Something already installs the compose plugin at
+      $dir/docker-compose
+  To use rig's pinned build instead:
+      ln -sf $src $dir/docker-compose")
+        return 0
+    fi
+    ln -sfn "$src" "$dir/docker-compose"
+    echo "  compose plugin -> $dir/docker-compose"
+    return 0
+}
+
+install() {
+    local tier="${1:-dev}" b
+    TIER="$tier"
+    detect
+
+    # detect_toolchain has already probed PATH. Fetch only what it found missing
+    # or at the wrong version; a tool already present at its pin stays where it is.
+    if [ -n "$TOOLCHAIN_NEED" ]; then
+        echo
+        DEPS_ONLY="$TOOLCHAIN_NEED" fetch "$tier"
+        echo
+        echo "installed to $OUT_BIN ($tier):"
+        for b in $TOOLCHAIN_NEED; do
+            if [ -x "$OUT_BIN/$b" ]; then echo "  $b"; fi
+        done
+        if [ "$tier" = "core" ]; then
+            echo "  (no kind/tilt — 'make deps dev' adds them)"
+        fi
+        # Only when compose was fetched, never at a copy rig did not install.
+        case " $TOOLCHAIN_NEED " in
+            *" docker-compose "*) install_compose_plugin ;;
+        esac
+
+        # PATH advice only when something actually landed in OUT_BIN.
+        case ":${PATH}:" in
+            *":$OUT_BIN:"*) ;;
+            *) MANUAL+=("Put the toolchain on your PATH — add to ~/.bashrc:
+      export PATH=\"${OUT_BIN}:\$PATH\"") ;;
+        esac
+    fi
+    warn_shadowing "$tier"
+
+    report_manual
+}
+
+# ── main ───────────────────────────────────────────────────────────────────
+
+require_linux
+
+# Shift only if there is an argument: a bare `shift` returns 1 under set -e.
+cmd="${1:-install}"
+[ $# -gt 0 ] && shift
+
+# Baked mode copies binaries already in the image, so it needs no downloader.
+need_downloads() {
+    require_amd64
+    if [ "$DEPS_SOURCE" != baked ]; then pick_downloader; fi
+    pick_sha
+}
+
+case "$cmd" in
+    detect)  if [ "${1:-}" = all ]; then VERBOSE=1; fi; detect; report_manual ;;
+    list)    list ;;
+    verify)  verify_tools "${1:-dev}" ;;
+    fetch)   need_downloads; fetch "$@" ;;
+    install) need_downloads; install "${1:-dev}" ;;
+    *)       echo "usage: $0 [detect [all]|list|verify|fetch|install]" >&2
+             echo "       install [core|dev]           (default dev)" >&2
+             echo "       fetch   [core|dev] [--to DIR]" >&2
+             echo "       OUT_BIN=<dir> overrides the install directory" >&2
+             exit 1 ;;
+esac

rig/ctrl/docs.sh

@@ -0,0 +1,49 @@
+#!/usr/bin/env bash
+# Documentation: render the diagrams, and serve the pages from a throwaway nginx container.
+# Usage: docs.sh serve | graphs
+# Notes: docs/notes/docs.md
+set -euo pipefail
+cd "$(dirname "$0")"
+
+source ./lib/config.sh
+load_config
+
+REPO="$(cd .. && pwd)"
+DOCS_PORT="${DOCS_PORT:-$((HTTP_PORT + 4))}"   # +4 sits inside this env's block
+
+serve() {
+    if [ ! -f "$REPO/docs/index.html" ]; then
+        echo "no docs/index.html" >&2
+        exit 1
+    fi
+    echo "docs for '$CLUSTER' on http://localhost:${DOCS_PORT}"
+    echo "  (ctrl-c to stop; nothing is installed and nothing persists)"
+    docker run --rm \
+        --name "${CLUSTER}-docs" \
+        -p "${DOCS_PORT}:80" \
+        -v "$REPO/docs:/usr/share/nginx/html:ro" \
+        nginx:alpine
+}
+
+graphs() {
+    if ! command -v dot >/dev/null 2>&1; then
+        echo "graphviz not found — install with: sudo apt install graphviz" >&2
+        echo "(only needed to re-render; the committed .svg files already work)" >&2
+        exit 1
+    fi
+    shopt -s nullglob
+    local found=0 f out
+    for f in "$REPO"/docs/graphs/*.dot; do
+        out="${f%.dot}.svg"
+        echo "  graphviz $(basename "$f") → $(basename "$out")"
+        dot -Tsvg "$f" -o "$out"
+        found=1
+    done
+    [ "$found" -eq 1 ] || echo "  no .dot files in docs/graphs/"
+}
+
+case "${1:-serve}" in
+    serve)  serve ;;
+    graphs) graphs ;;
+    *)      echo "usage: $0 [serve|graphs]" >&2; exit 1 ;;
+esac

rig/ctrl/env.d/client.env.example

@@ -0,0 +1,20 @@
+# EXAMPLE PROFILE (optional): copy to client.env, then PROFILE=client; overlays the defaults.
+# client — images via a pull-through cache of the corporate registry, TLS and metrics addons.
+# Notes: docs/notes/env.md
+
+PROFILE_NAME=client
+K8S_VERSION=v1_36
+ADDONS="metallb cert-manager metrics-server"
+REGISTRY_MODE=mirror
+INGRESS_MODE=hostport
+DNS_MODE=hosts
+
+# Ports derive from the directory name by default (see ctrl/ports.sh).
+# Real ports only if this is the ONLY environment and nothing owns :80; `make check` tests it.
+# HTTP_PORT=80
+# HTTPS_PORT=443
+
+# Set these in ctrl/.env (gitignored), not here:
+#   REGISTRY_REMOTE_URL=https://artifactory.corp.example/artifactory/api/docker/docker-virtual
+#   REGISTRY_USER / REGISTRY_PASSWORD
+#   REGISTRY_CA_FILE=/path/to/corp-root-ca.crt

rig/ctrl/env.d/data.env.example

@@ -0,0 +1,26 @@
+# EXAMPLE PROFILE (optional): copy to data.env, then PROFILE=data; overlays the defaults.
+# data — postgres, redis and airflow (upstream images) in the `data` namespace.
+# Notes: docs/notes/env.md
+
+PROFILE_NAME=data
+K8S_VERSION=v1_36
+# Order matters: addons.sh installs in the order listed, and airflow refuses to
+# start without a metadata database, so postgres comes first.
+ADDONS="metallb postgres redis airflow"
+# local, not none — see the defaults in lib/config.sh: `none` has no outward-push guard.
+REGISTRY_MODE=local
+INGRESS_MODE=hostport
+DNS_MODE=hosts
+
+# Namespace for the dependency containers.
+DATA_NAMESPACE=data
+
+# Postgres identity. The password is generated once by postgres.sh and kept.
+POSTGRES_DB=app
+POSTGRES_USER=app
+POSTGRES_STORAGE=2Gi
+
+AIRFLOW_ADMIN_USER=admin
+
+# Reach the databases with port-forward, e.g.
+#   kubectl -n data port-forward svc/postgres 5432:5432

rig/ctrl/env.d/offline.env.example

@@ -0,0 +1,15 @@
+# EXAMPLE PROFILE (optional): copy to offline.env, then PROFILE=offline; overlays the defaults.
+# offline — air-gapped: images from a preloaded local registry; pair with DEPS_SOURCE=baked.
+# Notes: docs/notes/env.md
+
+PROFILE_NAME=offline
+K8S_VERSION=v1_36
+ADDONS="metallb"
+REGISTRY_MODE=local
+INGRESS_MODE=hostport
+DNS_MODE=hosts
+
+# Derived from the directory name by default — see ctrl/ports.sh.
+# Uncomment for the real ports, but only if this is the only environment.
+# HTTP_PORT=80
+# HTTPS_PORT=443

rig/ctrl/k8s/README.md

@@ -0,0 +1,60 @@
+# `ctrl/k8s` — the cluster, and what runs on it
+
+Same layout as every other project here: a kind config, a kustomize `base/`,
+and an `overlays/dev/` that patches it.
+
+```
+kind-config.yaml.tpl    the cluster itself — nodes, ports
+base/                   the components, as plain manifests
+overlays/dev/           how this rig differs from the base
+```
+
+## Why the cluster config is a template
+
+Every other project checks in a literal `kind-config.yaml`, because there is
+exactly one `unt` and one `nvi`. A rig is copied and renamed to make a second
+environment, and both the cluster name and the host port block follow the
+directory name — so a literal would make every copy collide on both.
+
+`ctrl/cluster.sh` renders it with `sed`, substituting `${CLUSTER}`,
+`${NODE_IMAGE}`, `${HTTP_PORT}` and `${HOST_WORKDIR}`. Not `envsubst`: that is
+`gettext-base`, which a minimal Debian does not have, and Docker being the only
+prerequisite is the one promise rig makes.
+
+**To change the cluster, edit this file** — more nodes, other port mappings —
+then `make cluster reset`: a kind config is fixed at creation, not re-applied.
+`lib/config.sh` reads the node count back out of it, so nothing restates it.
+
+A project that builds its own cluster through rig passes its own file as
+`KIND_CONFIG=<path>`; it is rendered the same way.
+
+## `base/` — replace these
+
+**The two components in `base/` are examples, not the system.** They exist so
+the real manifests have a shape to be written against.
+
+The real ones are expected to be versioned **separately from the installer** —
+they change on a different cadence, by different people, under different review.
+Point `MANIFESTS_DIR` in `ctrl/.env` at their overlay and rig stops owning them:
+
+```
+MANIFESTS_DIR=../platform-manifests/overlays/dev
+```
+
+Until then it defaults to `ctrl/k8s/overlays/dev`.
+
+### The three states a component can be in
+
+Switching between them should be a one-line change, never a rewrite. The DNS
+name stays the same in every case, so callers never know the difference:
+
+| state | what exists | when |
+| --- | --- | --- |
+| **real** | an image built from source, hot-reloaded | the one thing you are working on |
+| **mock** | a stub returning canned responses (`example-mock.yaml`) | everything else — most of the estate |
+| **remote** | no pod at all, just a Service (`example-remote.yaml`) | when the real system is reachable and you want it |
+
+Most components should be **mock**. What has to be faithful is the topology —
+names, ports, dependency order, who can reach whom, how it fails. The workloads
+are noise, and mocking them is what makes several copies of a large estate fit
+on one laptop.

rig/ctrl/k8s/base/example-mock.yaml

@@ -0,0 +1,104 @@
+# EXAMPLE — a mocked component. Copy, rename, replace.
+#
+# A stub that answers on the right name and port with canned responses. No image
+# to build: the script is mounted from the ConfigMap, so changing the behaviour
+# is a kubectl apply, not a rebuild.
+#
+# Deliberately boring and readable. This is onboarding material — someone should
+# be able to read the generated object and recognise what it is.
+apiVersion: v1
+kind: ConfigMap
+metadata:
+  name: example-service-stub
+data:
+  # Canned responses by path. Add entries as the contract becomes clear;
+  # anything unmatched returns 404 so a missing route is visible, not silent.
+  routes.json: |
+    {
+      "/health":     {"status": 200, "body": {"status": "ok"}},
+      "/v1/example": {"status": 200, "body": {"items": [], "mocked": true}}
+    }
+  serve.py: |
+    import json, os
+    from http.server import BaseHTTPRequestHandler, HTTPServer
+
+    ROUTES = json.load(open("/etc/stub/routes.json"))
+    NAME = os.environ.get("STUB_NAME", "stub")
+
+    class H(BaseHTTPRequestHandler):
+        def do_GET(self):
+            r = ROUTES.get(self.path)
+            if r is None:
+                self.send_response(404)
+                self.end_headers()
+                # Say which stub rejected it — with everything mocked, "404"
+                # alone tells you nothing about where the call actually landed.
+                self.wfile.write(json.dumps(
+                    {"error": "no canned route", "stub": NAME, "path": self.path}
+                ).encode())
+                return
+            body = json.dumps(r["body"]).encode()
+            self.send_response(r["status"])
+            self.send_header("Content-Type", "application/json")
+            self.send_header("X-Mocked-By", NAME)
+            self.end_headers()
+            self.wfile.write(body)
+
+        def log_message(self, fmt, *args):
+            print("%s %s" % (NAME, fmt % args), flush=True)
+
+    HTTPServer(("0.0.0.0", 8080), H).serve_forever()
+---
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: example-service
+  labels:
+    app: example-service
+    rig.component/impl: mock      # so `kubectl get deploy -L rig.component/impl`
+                                  # shows at a glance what is real and what is not
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: example-service
+  template:
+    metadata:
+      labels:
+        app: example-service
+    spec:
+      containers:
+        - name: stub
+          image: python:3.12-slim
+          command: ["python3", "/etc/stub/serve.py"]
+          env:
+            - name: STUB_NAME
+              value: example-service
+          ports:
+            - containerPort: 8080
+          volumeMounts:
+            - name: stub
+              mountPath: /etc/stub
+          readinessProbe:
+            httpGet: { path: /health, port: 8080 }
+            initialDelaySeconds: 2
+          # Small enough that a whole estate of these fits alongside the real
+          # thing you are working on.
+          resources:
+            requests: { memory: 32Mi, cpu: 10m }
+            limits:   { memory: 64Mi }
+      volumes:
+        - name: stub
+          configMap:
+            name: example-service-stub
+---
+apiVersion: v1
+kind: Service
+metadata:
+  name: example-service
+spec:
+  selector:
+    app: example-service
+  ports:
+    - port: 80
+      targetPort: 8080

rig/ctrl/k8s/base/example-remote.yaml

@@ -0,0 +1,46 @@
+# EXAMPLE — a component that is NOT simulated, pointed at the real system.
+#
+# This is the payoff of keeping the topology honest: there is no pod here at
+# all, yet `example-remote.<namespace>.svc.cluster.local` resolves exactly as it
+# does when the same component is mocked. Callers are identical in both cases,
+# so moving a dependency from mocked to real is a one-line change and nothing
+# downstream is touched.
+#
+# Use this when the real system is reachable and you want it in the loop.
+# Note that reachability depends on where you are running: systems restricted to
+# a managed workspace will not resolve from a laptop at all, which is the whole
+# reason most components should stay mocked.
+apiVersion: v1
+kind: Service
+metadata:
+  name: example-remote
+  labels:
+    rig.component/impl: remote
+spec:
+  type: ExternalName
+  externalName: real-system.internal.example.com
+---
+# If the real system has no DNS name — only an IP, which is common for legacy
+# hosts — ExternalName cannot express it. Use a bare Service plus manual
+# Endpoints instead, and delete the block above.
+#
+# apiVersion: v1
+# kind: Service
+# metadata:
+#   name: example-remote
+#   labels:
+#     rig.component/impl: remote
+# spec:
+#   ports:
+#     - port: 80
+#       targetPort: 8080
+# ---
+# apiVersion: v1
+# kind: Endpoints
+# metadata:
+#   name: example-remote      # must match the Service name exactly
+# subsets:
+#   - addresses:
+#       - ip: 10.0.0.42
+#     ports:
+#       - port: 8080

rig/ctrl/k8s/base/kustomization.yaml

@@ -0,0 +1,11 @@
+apiVersion: kustomize.config.k8s.io/v1beta1
+kind: Kustomization
+
+# The namespace every component lands in. The overlay overrides it, so a rig
+# modelling two estates can apply the same base twice under different names.
+namespace: rig
+
+resources:
+  - namespace.yaml
+  - example-mock.yaml
+  - example-remote.yaml

rig/ctrl/k8s/base/namespace.yaml

@@ -0,0 +1,4 @@
+apiVersion: v1
+kind: Namespace
+metadata:
+  name: rig

rig/ctrl/k8s/kind-config.yaml.tpl

@@ -0,0 +1,23 @@
+# The cluster. Add nodes or port mappings here, then `make cluster reset`.
+# ctrl/cluster.sh substitutes (sed): CLUSTER, NODE_IMAGE, HTTP_PORT, HOST_WORKDIR
+# lib/config.sh reads the node count back from this file.
+# Notes: docs/notes/kind-config.md
+kind: Cluster
+apiVersion: kind.x-k8s.io/v1alpha4
+name: ${CLUSTER}
+
+# containerd reads per-host registry config from certs.d (written by registry.sh).
+containerdConfigPatches:
+  - |-
+    [plugins."io.containerd.grpc.v1.cri".registry]
+      config_path = "/etc/containerd/certs.d"
+
+nodes:
+  - role: control-plane
+    image: ${NODE_IMAGE}
+    # One NodePort bridged to the host, owned by an in-cluster gateway (no ingress controller).
+    extraPortMappings:
+      - containerPort: 30080
+        hostPort: ${HTTP_PORT}
+        listenAddress: "0.0.0.0"
+        protocol: TCP

rig/ctrl/k8s/overlays/dev/kustomization.yaml

@@ -0,0 +1,22 @@
+apiVersion: kustomize.config.k8s.io/v1beta1
+kind: Kustomization
+
+resources:
+  - ../../base
+
+# The dev overlay is where a rig says how its estate differs from the base —
+# which components are real, which are mocked, which point at a live system.
+# Kept empty on purpose: the base already boots, and an overlay full of examples
+# is harder to read than one that starts blank.
+#
+# The shape a patch takes, for when the first one is needed:
+#
+# patches:
+#   - target: {kind: Service, name: example-service}
+#     patch: |
+#       - op: replace
+#         path: /spec/type
+#         value: NodePort
+#       - op: add
+#         path: /spec/ports/0/nodePort
+#         value: 30080

rig/ctrl/lib/config.sh

@@ -0,0 +1,224 @@
+# Shared config loading: how the config layers compose. Sourced, never executed.
+# Precedence, weakest first: defaults < versions.env < env.d/<profile> < .env < caller's env.
+# Run from ctrl/.
+# Notes: docs/notes/config.md
+
+# Per-invocation overrides: restored after the files are read, so the caller wins.
+# NODES is deliberately not here (read from the kind config).
+CONFIG_OVERRIDABLE="PROFILE CLUSTER K8S_VERSION KIND_CONFIG ADDONS
+                    REGISTRY_MODE INGRESS_MODE DNS_MODE TILT_PORT
+                    SOURCE ARCH DEPS_SOURCE HTTP_PORT HTTPS_PORT
+                    REGISTRY_PORT MANIFESTS_DIR"
+
+# The repo folder's name, reduced to a DNS label kind accepts as a cluster name.
+default_cluster_name() {
+    local n
+    n=$(basename "$(cd .. && pwd)")
+    n=$(echo "$n" | tr '[:upper:]' '[:lower:]' | tr -c 'a-z0-9-' '-')
+    n=$(echo "$n" | sed 's/^-*//; s/-*$//')
+    echo "${n:-rig}"
+}
+
+# Base of this environment's 10-port block; cksum so it is the same on every machine.
+derive_port_base() {
+    local h; h=$(printf '%s' "$1" | cksum | awk '{print $1}')
+    echo $((20000 + (h % 200) * 10))
+}
+
+load_config() {
+    local k saved=""
+    for k in $CONFIG_OVERRIDABLE; do
+        # ${!k+x} distinguishes "set but empty" from "unset" — an explicit
+        # FOO= on the command line is a real choice and must survive.
+        if [ -n "${!k+x}" ]; then
+            saved+="$k=$(printf '%q' "${!k}")"$'\n'
+        fi
+    done
+
+    set -a
+    source ./versions.env
+    # RIG_PORTABLE skips the machine-local .env (set by config_snapshot for kits).
+    if [ -z "${RIG_PORTABLE:-}" ] && [ -f ./.env ]; then source ./.env; fi
+    set +a
+
+    # Re-apply overrides now so PROFILE is the caller's before we pick the file.
+    _config_restore "$saved"
+
+    # A profile is optional; naming one that does not exist is an error.
+    local profile="${PROFILE:-}"
+    if [ -n "$profile" ] && [ "$profile" != default ]; then
+        if [ ! -f "./env.d/${profile}.env" ]; then
+            echo "no such profile: env.d/${profile}.env" >&2
+            echo "available: $(config_profiles | tr '\n' ' ')" >&2
+            exit 1
+        fi
+        set -a
+        source "./env.d/${profile}.env"
+        if [ -z "${RIG_PORTABLE:-}" ] && [ -f ./.env ]; then source ./.env; fi
+        set +a
+        _config_restore "$saved"
+    fi
+
+    # The defaults a profile would otherwise have to supply. Weakest of all: a
+    # profile, ctrl/.env and the caller each override them.
+    PROFILE_NAME="${PROFILE_NAME:-default}"
+    ADDONS="${ADDONS-}"
+    # local, not none: with no registry an unqualified image name means
+    # docker.io/library/<name>, and a default must not make that disclosure.
+    REGISTRY_MODE="${REGISTRY_MODE:-local}"
+    INGRESS_MODE="${INGRESS_MODE:-hostport}"
+    DNS_MODE="${DNS_MODE:-hosts}"
+    # The newest node image versions.env pins, found rather than restated, so
+    # bumping the pins moves the default with them.
+    if [ -z "${K8S_VERSION:-}" ]; then
+        K8S_VERSION=$(compgen -v NODE_IMAGE_v | sort -V | tail -1)
+        K8S_VERSION="${K8S_VERSION#NODE_IMAGE_}"
+    fi
+
+    # Identity follows the folder, so a renamed copy is a distinct environment.
+    CLUSTER="${CLUSTER:-$(default_cluster_name)}"
+    KUBECONTEXT="kind-${CLUSTER}"
+
+    # Host ports: fill only the gaps from the derived block; anything already set wins.
+    local base; base=$(derive_port_base "$CLUSTER")
+    HTTP_PORT="${HTTP_PORT:-$base}"
+    HTTPS_PORT="${HTTPS_PORT:-$((base + 1))}"
+    TILT_PORT="${TILT_PORT:-$((base + 2))}"
+    REGISTRY_PORT="${REGISTRY_PORT:-$((base + 3))}"
+
+    # Where the workload's manifests live, repo-root relative; always resolved.
+    # See k8s/README.md.
+    MANIFESTS_DIR="${MANIFESTS_DIR:-ctrl/k8s/overlays/dev}"
+
+    # Profiles name a k8s minor (v1_36); versions.env holds the pinned digest.
+    local var="NODE_IMAGE_${K8S_VERSION}"
+    NODE_IMAGE="${!var:-}"
+    if [ -z "$NODE_IMAGE" ]; then
+        echo "K8S_VERSION='${K8S_VERSION}' has no NODE_IMAGE_${K8S_VERSION} in versions.env" >&2
+        exit 1
+    fi
+
+    # The cluster is one file: k8s/kind-config.yaml.tpl. To change it, edit it.
+    # KIND_CONFIG is only "use this file instead", for a project that builds its
+    # own cluster through rig (a path relative to ctrl/, or absolute).
+    KIND_CONFIG="${KIND_CONFIG:-./k8s/kind-config.yaml.tpl}"
+    if [ ! -f "$KIND_CONFIG" ]; then
+        echo "no kind config at KIND_CONFIG=${KIND_CONFIG}" >&2
+        exit 1
+    fi
+
+    # Read the node count back out of the file rather than restating it:
+    # check.sh and the memory tool size their budget on NODES.
+    NODES=$(grep -c '^  - role:' "$KIND_CONFIG")
+
+    # Measured MB per node (cluster alone, errs high for workers); shared by
+    # check.sh, the memory tool and standalone kits.
+    NODE_MB=800
+}
+
+# Render the kind config to stdout with sed (not envsubst) over an explicit variable list.
+# HOST_WORKDIR must be a host path: the host dockerd resolves hostPath entries.
+render_kind_config() {
+    local host_workdir="${HOST_WORKDIR:-$(cd .. && pwd)}"
+    sed -e "s|\${CLUSTER}|${CLUSTER}|g" \
+        -e "s|\${NODE_IMAGE}|${NODE_IMAGE}|g" \
+        -e "s|\${HTTP_PORT}|${HTTP_PORT}|g" \
+        -e "s|\${HOST_WORKDIR}|${host_workdir}|g" \
+        "$KIND_CONFIG"
+}
+
+_config_restore() {
+    local line
+    while IFS= read -r line; do
+        if [ -n "$line" ]; then
+            eval "export $line"
+        fi
+    done <<< "$1"
+    # A while loop returns its last body command's status; the trailing empty
+    # line would otherwise make this return 1 and trip `set -e` in the caller.
+    return 0
+}
+
+# ── what a standalone kit needs to know ────────────────────────────────────
+# The questions ctrl/standalone.sh asks, so it never knows how config is stored.
+
+# Every configuration rig can run as, one per line: each profile, or `default`
+# when there are none. Never empty.
+config_profiles() {
+    local f found=""
+    for f in ./env.d/*.env; do
+        [ -e "$f" ] || continue
+        f=${f##*/}; echo "${f%.env}"; found=1
+    done
+    [ -n "$found" ] || echo default
+}
+
+# What load_config sets, minus the machine-local layer, as `declare -p` lines.
+# Usage: config_snapshot <profile> | --current   (found by difference, not a list)
+config_snapshot() {
+    local _rig_snap_choices
+    if [ "$1" = --current ]; then
+        _rig_snap_choices=$( (
+            load_config >/dev/null || exit 1
+            for _rig_snap_n in $CONFIG_OVERRIDABLE; do
+                if [ -n "${!_rig_snap_n+x}" ]; then printf 'export %s=%q\n' "$_rig_snap_n" "${!_rig_snap_n}"; fi
+            done
+        ) ) || return 1
+    else
+        _rig_snap_choices="export PROFILE=$(printf '%q' "$1")"
+    fi
+    (
+        # Nothing from the caller's shell may leak into a kit.
+        for _rig_snap_n in $CONFIG_OVERRIDABLE; do unset "$_rig_snap_n"; done
+        declare -A _rig_snap_was=()
+        for _rig_snap_n in $(compgen -v); do
+            _rig_snap_was[$_rig_snap_n]="${!_rig_snap_n-}"
+        done
+        eval "$_rig_snap_choices"
+        RIG_PORTABLE=1 load_config >/dev/null
+        for _rig_snap_n in $(compgen -v); do
+            case "$_rig_snap_n" in
+                _rig_snap_*|RIG_PORTABLE|BASH*|FUNCNAME|PIPESTATUS|LINENO|RANDOM|SRANDOM|\
+                SECONDS|EPOCH*|HISTCMD|COLUMNS|LINES|PWD|OLDPWD|_|SHLVL|OPTIND|OPTERR) continue ;;
+            esac
+            if [ -z "${_rig_snap_was[$_rig_snap_n]+x}" ] \
+               || [ "${_rig_snap_was[$_rig_snap_n]}" != "${!_rig_snap_n-}" ]; then
+                declare -p "$_rig_snap_n"
+            fi
+        done
+    )
+}
+
+# The profile this machine runs, as load_config resolves it here.
+config_current_profile() { ( load_config >/dev/null && echo "$PROFILE_NAME" ); }
+
+# Names (never values) of .env keys an export does not carry, e.g. credentials.
+config_left_out() {
+    [ -f ./.env ] || return 0
+    local k
+    for k in $(sed -nE 's/^[[:space:]]*(export[[:space:]]+)?([A-Za-z_][A-Za-z0-9_]*)=.*/\2/p' ./.env | sort -u); do
+        case " $(echo $CONFIG_OVERRIDABLE) " in
+            *" $k "*) ;;
+            *) echo "$k" ;;
+        esac
+    done
+}
+
+# Print a load_config with a resolution frozen in, for a standalone kit to carry.
+# The caller's env still wins; derived values (e.g. ports) stay fixed.
+config_freeze() {
+    local snap
+    snap=$(config_snapshot "$1") || return 1
+    cat <<'EOF'
+load_config() {
+    local k saved=""
+    for k in $CONFIG_OVERRIDABLE; do
+        if [ -n "${!k+x}" ]; then saved+="$k=$(printf '%q' "${!k}")"$'\n'; fi
+    done
+EOF
+    printf '%s\n' "$snap" | sed -E 's/^declare --* /    declare -g /; s/^declare -([a-zA-Z]+) /    declare -g\1 /'
+    cat <<'EOF'
+    _config_restore "$saved"
+}
+EOF
+}

rig/ctrl/mem.sh

@@ -0,0 +1,684 @@
+#!/usr/bin/env bash
+# rig:standalone rigmini status
+# rig's memory tool (also generated as rigmini.sh): what the machine advertises vs. what it survives.
+# Usage: mem.sh status | push [--to GB] [--to-oom] | all [--budget GB] | backup | restore (WSL)
+# Notes: docs/notes/mem.md
+set -euo pipefail
+cd "$(dirname "$0")"
+source ./lib/config.sh
+
+# ── defaults ───────────────────────────────────────────────────────────────
+
+STEP_MB=0             # per allocation; 0 means scale it to the ceiling. See push().
+STEP_EXPLICIT=no      # whether --step was given, which turns the scaling off.
+TO_MB=""              # --to: stop here regardless. Empty means no hard cap.
+TO_OOM=no             # --to-oom: opt in to running until the kernel intervenes.
+BUDGET_GB=""          # --budget; empty means what this profile's cluster needs, from rig.
+BUDGET_EXPLICIT=no    # whether --budget was given, which retires the guess below.
+
+# ── platform ───────────────────────────────────────────────────────────────
+
+# Refuse Git Bash / MSYS / Cygwin and kernels without /proc, with a clear message.
+require_linux() {
+    case "$(uname -s)" in
+        MINGW*|MSYS*|CYGWIN*)
+            cat >&2 <<'EOF'
+This has to run inside WSL, not Git Bash / MSYS / Cygwin.
+
+If WSL is not installed yet, from an elevated PowerShell or Command Prompt:
+
+    wsl --install
+
+That enables Windows features and needs a reboot, so it is not something this
+script will do for you. Afterwards, open the Linux shell it installs and run
+this from there.
+EOF
+            exit 1 ;;
+    esac
+
+    # Everything below reads /proc. Without it there is nothing to measure, and
+    # failing here beats printing a page of empty fields.
+    if [ ! -r /proc/meminfo ]; then
+        echo "no readable /proc/meminfo — this needs a Linux kernel." >&2
+        echo "On macOS or a BSD none of the numbers below exist." >&2
+        exit 1
+    fi
+}
+
+is_wsl() { grep -qi microsoft /proc/version 2>/dev/null; }
+
+is_container() {
+    [ -f /.dockerenv ] && return 0
+    grep -qE '(docker|containerd|kubepods|lxc|podman)' /proc/1/cgroup 2>/dev/null
+}
+
+platform() {
+    if is_wsl; then echo WSL
+    elif is_container; then echo container
+    else echo "native linux"
+    fi
+}
+
+# ── reading memory ─────────────────────────────────────────────────────────
+
+mb() { echo $(( $(awk "/^$1:/{print \$2}" /proc/meminfo) / 1024 )); }
+
+# MemAvailable arrived in kernel 3.14. Older kernels — and they turn up on
+# corporate images — need the estimate it replaced, which is worse but not wrong.
+avail_meminfo_mb() {
+    if grep -q '^MemAvailable:' /proc/meminfo; then
+        mb MemAvailable
+    else
+        awk '/^(MemFree|Buffers|Cached):/{t+=$2} END{print int(t/1024)}' /proc/meminfo
+    fi
+}
+
+# This cgroup's limit/usage files, set once by find_cgroup (cheap for the poll loop).
+CG_MAX_FILE=""
+CG_CUR_FILE=""
+CG_VERSION=""
+
+find_cgroup() {
+    local rel
+
+    # Top of tree first (right inside a container), then this shell's own slice
+    # from /proc/self/cgroup (right on a host).
+    if [ -r /sys/fs/cgroup/memory.max ]; then
+        CG_VERSION=v2
+        CG_MAX_FILE=/sys/fs/cgroup/memory.max
+        CG_CUR_FILE=/sys/fs/cgroup/memory.current
+    elif [ -r /sys/fs/cgroup/memory/memory.limit_in_bytes ]; then
+        CG_VERSION=v1
+        CG_MAX_FILE=/sys/fs/cgroup/memory/memory.limit_in_bytes
+        CG_CUR_FILE=/sys/fs/cgroup/memory/memory.usage_in_bytes
+    fi
+
+    rel=$(awk -F: '$1=="0"{print $3; exit}' /proc/self/cgroup 2>/dev/null || true)
+    if [ -n "$rel" ] && [ "$rel" != "/" ] && [ -r "/sys/fs/cgroup${rel}/memory.max" ]; then
+        CG_VERSION=v2
+        CG_MAX_FILE="/sys/fs/cgroup${rel}/memory.max"
+        CG_CUR_FILE="/sys/fs/cgroup${rel}/memory.current"
+        return 0
+    fi
+
+    rel=$(awk -F: '$2 ~ /(^|,)memory(,|$)/{print $3; exit}' /proc/self/cgroup 2>/dev/null || true)
+    if [ -n "$rel" ] && [ "$rel" != "/" ] \
+       && [ -r "/sys/fs/cgroup/memory${rel}/memory.limit_in_bytes" ]; then
+        CG_VERSION=v1
+        CG_MAX_FILE="/sys/fs/cgroup/memory${rel}/memory.limit_in_bytes"
+        CG_CUR_FILE="/sys/fs/cgroup/memory${rel}/memory.usage_in_bytes"
+    fi
+    return 0
+}
+
+# The cap in MB, or "" when unlimited ("max", or any value >= MemTotal).
+cgroup_cap_mb() {
+    local raw cap
+    [ -n "$CG_MAX_FILE" ] && [ -r "$CG_MAX_FILE" ] || { echo ""; return 0; }
+    raw=$(cat "$CG_MAX_FILE" 2>/dev/null || echo max)
+    [ "$raw" = "max" ] && { echo ""; return 0; }
+    case "$raw" in ''|*[!0-9]*) echo ""; return 0 ;; esac
+    cap=$((raw / 1024 / 1024))
+    [ "$cap" -ge "$(mb MemTotal)" ] && { echo ""; return 0; }
+    echo "$cap"
+}
+
+cgroup_used_mb() {
+    local raw
+    [ -n "$CG_CUR_FILE" ] && [ -r "$CG_CUR_FILE" ] || { echo ""; return 0; }
+    raw=$(cat "$CG_CUR_FILE" 2>/dev/null || echo "")
+    case "$raw" in ''|*[!0-9]*) echo ""; return 0 ;; esac
+    echo $((raw / 1024 / 1024))
+}
+
+# ulimit -v is a per-process address-space cap. It stops YOU long before the box
+# does, and because it is inherited from a login shell it is easy to hit without
+# knowing it is set.
+ulimit_v_mb() {
+    local v; v=$(ulimit -v 2>/dev/null || echo unlimited)
+    [ "$v" = "unlimited" ] && { echo ""; return 0; }
+    case "$v" in ''|*[!0-9]*) echo ""; return 0 ;; esac
+    echo $((v / 1024))
+}
+
+# The number everything else is about: the lowest of the things that can stop
+# you. Printed at the end of `status` and used as the sanity bound in `push`.
+effective_ceiling_mb() {
+    local c; c=$(mb MemTotal)
+    local cap; cap=$(cgroup_cap_mb)
+    local ul;  ul=$(ulimit_v_mb)
+    [ -n "$cap" ] && [ "$cap" -lt "$c" ] && c="$cap"
+    [ -n "$ul" ]  && [ "$ul"  -lt "$c" ] && c="$ul"
+    echo "$c"
+}
+
+# Room left right now: cgroup cap minus usage when capped, else MemAvailable.
+headroom_mb() {
+    local cap used
+    cap=$(cgroup_cap_mb)
+    used=$(cgroup_used_mb)
+    if [ -n "$cap" ] && [ -n "$used" ]; then
+        echo $(( cap - used ))
+    else
+        avail_meminfo_mb
+    fi
+}
+
+# ── status ─────────────────────────────────────────────────────────────────
+
+# Ask Windows for %USERPROFILE%; fall back to whichever profile owns a .wslconfig.
+wslconfig_path() {
+    local profile winpath found
+    profile=$(cmd.exe /c "echo %USERPROFILE%" 2>/dev/null | tr -d "\r\n" || true)
+    case "$profile" in
+        ""|*%*) ;;
+        *) winpath=$(wslpath -u "$profile" 2>/dev/null || true)
+           if [ -n "$winpath" ] && [ -d "$winpath" ]; then
+               echo "$winpath/.wslconfig"; return 0
+           fi ;;
+    esac
+    found=$(ls -d /mnt/c/Users/*/.wslconfig 2>/dev/null | head -1 || true)
+    [ -n "$found" ] && echo "$found"
+    return 0
+}
+
+hogs() {
+    echo "  holding the most:"
+    ps -eo rss,comm --sort=-rss 2>/dev/null \
+      | awk 'NR>1 && NR<=6 {printf "    %6.0f MB  %s\n", $1/1024, $2}'
+    return 0
+}
+
+status() {
+    local total avail swap_total swap_free cap ul cur
+
+    echo "host"
+    echo "  platform    $(platform)"
+    echo "  kernel      $(uname -r)"
+    [ -r /etc/os-release ] && \
+        echo "  distro      $(sed -n 's/^PRETTY_NAME="\(.*\)"/\1/p' /etc/os-release)"
+    echo "  cpu         $(getconf _NPROCESSORS_ONLN 2>/dev/null || echo '?') online, load $(cut -d' ' -f1-3 /proc/loadavg)"
+
+    # ── the caps first, because they decide what the totals below are worth ──
+    echo
+    echo "caps"
+    cap=$(cgroup_cap_mb)
+    if [ -n "$cap" ]; then
+        cur=$(cgroup_used_mb)
+        echo "  cgroup      ${cap} MB  (${CG_VERSION}, ${CG_CUR_FILE##*/} says ${cur:-?} MB used)"
+        echo "  ! /proc/meminfo below describes the HOST, not this cgroup."
+        echo "    $(mb MemTotal) MB total is not yours; ${cap} MB is."
+    elif [ -n "$CG_VERSION" ]; then
+        echo "  cgroup      none  (${CG_VERSION} present, no memory limit set)"
+    else
+        echo "  cgroup      no memory controller found"
+    fi
+
+    ul=$(ulimit_v_mb)
+    if [ -n "$ul" ]; then
+        echo "  ! ulimit -v  ${ul} MB — a per-process cap, inherited from your shell"
+        echo "    it stops this process long before the machine runs out"
+    else
+        echo "  ulimit -v   unlimited"
+    fi
+
+    # Overcommit mode decides whether limits show as failed mallocs or OOM kills.
+    local om or_
+    om=$(cat /proc/sys/vm/overcommit_memory 2>/dev/null || echo '?')
+    or_=$(cat /proc/sys/vm/overcommit_ratio 2>/dev/null || echo '?')
+    case "$om" in
+        0) echo "  overcommit  0 heuristic — allocations are granted on a guess," ;;
+        1) echo "  overcommit  1 always — every allocation succeeds; the OOM killer is the only limit," ;;
+        2) echo "  overcommit  2 strict (ratio ${or_}%) — allocation fails honestly instead of killing later," ;;
+        *) echo "  overcommit  ${om}" ;;
+    esac
+    [ "$om" != "?" ] && echo "              so RSS is the number to trust, not what a process asked for"
+
+    # ── what it says it has ──
+    total=$(mb MemTotal); avail=$(avail_meminfo_mb)
+    swap_total=$(mb SwapTotal); swap_free=$(mb SwapFree)
+    echo
+    echo "memory"
+    echo "  total       ${total} MB"
+    echo "  available   ${avail} MB"
+    echo "  swap        ${swap_total} MB  ($(( swap_total - swap_free )) MB used)"
+    if [ "$swap_total" -eq 0 ]; then
+        echo "  - no swap: this box has no cushion. It goes from fine to OOM-killed"
+        echo "    with nothing in between, which is the abrupt failure you get in a VM."
+    fi
+
+    # postgres puts its shared buffers in /dev/shm. Docker's default is 64 MB,
+    # and the resulting failure names neither shm nor the size.
+    if [ -d /dev/shm ]; then
+        local shm; shm=$(df -Pm /dev/shm 2>/dev/null | awk 'NR==2{print $2}')
+        if [ -n "$shm" ]; then
+            if [ "$shm" -le 64 ]; then
+                echo "  ! /dev/shm   ${shm} MB — postgres puts shared memory here and 64 MB"
+                echo "    is docker's default. Raise it with --shm-size when postgres fails."
+            else
+                echo "  /dev/shm    ${shm} MB"
+            fi
+        fi
+    fi
+
+    echo
+    echo "disk"
+    local d
+    for d in / /tmp /var/lib/docker; do
+        [ -d "$d" ] || continue
+        df -Pm "$d" 2>/dev/null | awk -v p="$d" 'NR==2{printf "  %-12s %s MB free of %s MB\n", p, $4, $2}'
+    done
+
+    # kind and Tilt both watch large trees, and the failure mode is silent:
+    # they simply stop noticing file changes. Cheap to report while we are here.
+    local w i
+    w=$(cat /proc/sys/fs/inotify/max_user_watches 2>/dev/null || echo 0)
+    i=$(cat /proc/sys/fs/inotify/max_user_instances 2>/dev/null || echo 0)
+    echo
+    echo "tooling"
+    echo "  inotify     watches=$w instances=$i"
+    if [ "$w" -lt 524288 ] || [ "$i" -lt 512 ]; then
+        echo "  ! low — anything watching files will silently stop seeing changes"
+    fi
+
+    if ! command -v docker >/dev/null 2>&1; then
+        if [ -S /var/run/docker.sock ]; then
+            echo "  docker      socket present, no cli"
+        else
+            echo "  docker      not installed"
+        fi
+    elif docker info >/dev/null 2>&1; then
+        local n
+        n=$(docker ps -q 2>/dev/null | wc -l)
+        echo "  docker      $(docker version --format '{{.Server.Version}}' 2>/dev/null), ${n} container(s) running"
+    else
+        echo "  ! docker     cli present but the daemon is unreachable"
+    fi
+
+    # WSL: report the .wslconfig cap and whether it was applied (needs wsl --shutdown).
+    if is_wsl; then
+        local cfg conf conf_mb n
+        cfg=$(wslconfig_path)
+        echo
+        echo "wsl"
+        if [ -z "$cfg" ]; then
+            echo "  ! cannot tell which Windows profile owns .wslconfig"
+        else
+            echo "  config      $cfg"
+            conf=$(configured_memory "$cfg")
+            if [ -n "$conf" ]; then
+                conf_mb=$(to_mb "$conf")
+                echo "  configured  $conf  (${conf_mb} MB), booted ${total} MB"
+                # The VM reports a little less than allocated; 15% covers the
+                # kernel without calling every healthy machine a mismatch.
+                if [ -n "$conf_mb" ] && [ "$total" -lt $(( conf_mb * 85 / 100 )) ]; then
+                    echo "  ! configured ${conf_mb} MB but booted ${total} MB — not applied yet."
+                    echo "    From a WINDOWS terminal:  wsl --shutdown   then start the distro again."
+                fi
+            else
+                echo "  configured  no memory= set (WSL defaults to 50% of host RAM, or 8 GB,"
+                echo "              whichever is less). To raise it, add on the Windows side:"
+                echo "                  [wsl2]"
+                echo "                  memory=8GB"
+                echo "              then from a WINDOWS terminal:  wsl --shutdown"
+            fi
+            n=$(ls "$cfg".*.bak 2>/dev/null | wc -l)
+            if [ "$n" -gt 0 ]; then
+                echo "  backups     $n  (newest: $(ls -t "$cfg".*.bak 2>/dev/null | head -1))"
+            fi
+        fi
+    else
+        echo
+        echo "  - native linux: no VM allocation to raise. If memory is tight the levers"
+        echo "    are freeing something or adding swap."
+    fi
+
+    echo
+    echo "effective ceiling  $(effective_ceiling_mb) MB"
+    echo "  the lowest of MemTotal, the cgroup cap and ulimit -v. What the box"
+    echo "  claims. 'push' measures what it will actually hand over."
+
+    [ "$avail" -lt $(( total / 5 )) ] && { echo; hogs; }
+    return 0
+}
+
+# ── .wslconfig ─────────────────────────────────────────────────────────────
+
+require_wsl() {
+    if ! is_wsl; then
+        echo "$1 acts on .wslconfig, which only exists under WSL." >&2
+        echo "This is native Linux — there is no VM allocation to save or roll back." >&2
+        echo "Use 'status' to see what the machine actually has." >&2
+        exit 1
+    fi
+}
+
+# backup and restore act on the file, so unlike status they must not guess.
+wslconfig_required() {
+    local cfg; cfg=$(wslconfig_path)
+    if [ -z "$cfg" ]; then
+        echo "cannot tell which Windows profile owns .wslconfig. Candidates:" >&2
+        ls -d /mnt/c/Users/*/ 2>/dev/null \
+          | grep -viE "/(All Users|Default|Default User|Public)/$" | sed "s/^/  /" >&2
+        exit 1
+    fi
+    echo "$cfg"
+}
+
+configured_memory() {
+    [ -r "$1" ] || { echo ""; return; }
+    sed -n 's/^[[:space:]]*memory[[:space:]]*=[[:space:]]*//p' "$1" | tail -1 | tr -d '[:space:]'
+}
+
+# "9GB" / "8192MB" / "9G" -> MB, so it can be compared with /proc/meminfo.
+to_mb() {
+    local v="${1^^}" n
+    n=$(echo "$v" | tr -dc '0-9')
+    [ -n "$n" ] || { echo ""; return; }
+    case "$v" in
+        *GB|*G) echo $(( n * 1024 )) ;;
+        *MB|*M) echo "$n" ;;
+        *)      echo $(( n / 1024 / 1024 )) ;;
+    esac
+}
+
+backup() {
+    require_wsl backup
+    local cfg dest
+    cfg=$(wslconfig_required)
+    [ -r "$cfg" ] || { echo "nothing to back up: $cfg does not exist" >&2; exit 1; }
+    # Timestamped, never overwritten.
+    dest="${cfg}.$(date +%Y%m%d-%H%M%S).bak"
+    cp "$cfg" "$dest"
+    echo "backed up  $dest"
+    echo
+    echo "Edit $cfg by hand, then from a WINDOWS terminal:  wsl --shutdown"
+}
+
+restore() {
+    require_wsl restore
+    local cfg newest count
+    cfg=$(wslconfig_required)
+    newest=$(ls -t "$cfg".*.bak 2>/dev/null | head -1 || true)
+    [ -n "$newest" ] || { echo "no backups found beside $cfg" >&2; exit 1; }
+
+    echo "restoring  $newest"
+    echo "        -> $cfg"
+    echo
+
+    # Restores the newest; list the others in case an older one is wanted.
+    count=$(ls "$cfg".*.bak 2>/dev/null | wc -l)
+    if [ "$count" -gt 1 ]; then
+        echo "$count backups exist, newest first:"
+        ls -t "$cfg".*.bak | sed 's/^/  /'
+        echo "  (restoring the newest; copy another by hand to pick an older one)"
+        echo
+    fi
+
+    if [ -r "$cfg" ]; then
+        echo "what changes:"
+        if diff "$cfg" "$newest" > /tmp/mem.diff 2>&1 && [ ! -s /tmp/mem.diff ]; then
+            echo "  nothing — that backup is identical to the current config"
+        else
+            sed 's/^/  /' /tmp/mem.diff
+        fi
+        rm -f /tmp/mem.diff
+        echo
+    fi
+
+    printf "proceed? [y/N] "
+    read -r reply
+    case "$reply" in
+        y|Y|yes|Yes) ;;
+        *) echo "left alone"; return 0 ;;
+    esac
+    cp "$newest" "$cfg"
+    echo "restored. From a WINDOWS terminal:  wsl --shutdown"
+}
+
+# ── push ───────────────────────────────────────────────────────────────────
+
+STATE=""
+CHILD=""
+
+cleanup() {
+    if [ -n "$CHILD" ] && kill -0 "$CHILD" 2>/dev/null; then
+        kill -KILL "$CHILD" 2>/dev/null || true
+        wait "$CHILD" 2>/dev/null || true
+    fi
+    [ -n "$STATE" ] && rm -f "$STATE"
+    return 0
+}
+
+# Runs as a child that may be OOM-killed; the parent survives to report.
+allocator() {
+    # Make this process the preferred OOM victim (raising needs no privilege).
+    echo 1000 > "/proc/$BASHPID/oom_score_adj" 2>/dev/null || true
+
+    local arr=() held=0 i=0 rss swapped avail first_swap=0
+    local bytes=$((STEP_MB * 1024 * 1024))
+    local swap_used_start
+    swap_used_start=$(( $(mb SwapTotal) - $(mb SwapFree) ))
+
+    while :; do
+        # Write straight into the element (one copy, not three) and touch every page.
+        printf -v "arr[$i]" '%*s' "$bytes" ''
+        i=$((i + 1)); held=$((held + STEP_MB))
+
+        rss=$(awk '/^VmRSS:/{print int($2/1024)}' "/proc/$BASHPID/status" 2>/dev/null || echo 0)
+        avail=$(headroom_mb)
+        swapped=$(( $(mb SwapTotal) - $(mb SwapFree) - swap_used_start ))
+        [ "$swapped" -lt 0 ] && swapped=0
+
+        printf '%8s MB held   rss %7s MB   headroom %7s MB   swap +%s MB\n' \
+            "$held" "$rss" "$avail" "$swapped"
+        printf '%s %s %s %s\n' "$held" "$rss" "$avail" "$swapped" >> "$STATE"
+
+        # First swap is reported separately: slow comes before killed.
+        if [ "$swapped" -gt 0 ] && [ "$first_swap" -eq 0 ]; then
+            first_swap=$held
+            echo "  - first swap page at ${held} MB — past here it works but crawls"
+            echo "swapat $held" >> "$STATE"
+        fi
+
+        if [ -n "$TO_MB" ] && [ "$held" -ge "$TO_MB" ]; then
+            echo "stop reached-the-cap" >> "$STATE"; return 0
+        fi
+        if [ "$TO_OOM" = no ] && [ "$avail" -lt "$FLOOR_MB" ]; then
+            echo "stop floor" >> "$STATE"; return 0
+        fi
+    done
+}
+
+push() {
+    local total ceiling rc=0 last held rss swapat stop
+    total=$(mb MemTotal)
+    ceiling=$(effective_ceiling_mb)
+
+    # Default step: ceiling/64, clamped to 4..256 MB.
+    if [ "$STEP_EXPLICIT" = no ]; then
+        STEP_MB=$(( ceiling / 64 ))
+        [ "$STEP_MB" -lt 4 ] && STEP_MB=4
+        [ "$STEP_MB" -gt 256 ] && STEP_MB=256
+    fi
+
+    # Stop with a cushion: 64 MB under a cgroup cap, 512 MB on a host, or 5% of ceiling if larger.
+    if [ -n "$(cgroup_cap_mb)" ]; then FLOOR_MB=64; else FLOOR_MB=512; fi
+    [ $(( ceiling / 20 )) -gt "$FLOOR_MB" ] && FLOOR_MB=$(( ceiling / 20 ))
+
+    STATE=$(mktemp "${TMPDIR:-/tmp}/rigmini.XXXXXX")
+    trap cleanup EXIT
+    # Ctrl-C kills the child, frees the memory, and still prints the summary.
+    trap 'echo; echo "  interrupted"; echo "stop interrupted" >> "$STATE"; [ -n "$CHILD" ] && kill -KILL "$CHILD" 2>/dev/null || true' INT
+
+    echo "push"
+    echo "  step        ${STEP_MB} MB per allocation, every page touched"
+    echo "  ceiling     ${ceiling} MB claimed"
+    if [ -n "$TO_MB" ]; then
+        echo "  stopping    at ${TO_MB} MB (--to)"
+    elif [ "$TO_OOM" = yes ]; then
+        echo "  ! stopping   only when the kernel stops it (--to-oom)"
+        echo "    the allocating child is marked as the preferred OOM victim,"
+        echo "    but nothing about an OOM kill is entirely polite. Not on a box"
+        echo "    running anything you mind losing."
+    else
+        echo "  stopping    when headroom drops below ${FLOOR_MB} MB"
+    fi
+    echo
+
+    allocator &
+    CHILD=$!
+    wait "$CHILD" || rc=$?
+    CHILD=""
+    trap - INT
+
+    last=$(grep -E '^[0-9]' "$STATE" 2>/dev/null | tail -1 || true)
+    held=$(echo "$last" | awk '{print $1}')
+    rss=$(echo "$last"  | awk '{print $2}')
+    swapat=$(awk '/^swapat/{print $2}' "$STATE" 2>/dev/null | head -1 || true)
+    stop=$(awk '/^stop/{print $2}' "$STATE" 2>/dev/null | head -1 || true)
+
+    echo
+    if [ -z "$held" ]; then
+        echo "  ! nothing was allocated. Even one ${STEP_MB} MB chunk failed —"
+        echo "    try a smaller --step, or check ulimit -v in 'status'."
+        return 1
+    fi
+
+    echo "  reached     ${rss:-$held} MB resident"
+    [ -n "$swapat" ] && echo "  swapping    from ${swapat} MB"
+
+    case "$stop" in
+        reached-the-cap)
+            echo "  outcome     stopped at the --to cap, not at a limit."
+            echo "              The box held ${TO_MB} MB without complaint; there is more." ;;
+        floor)
+            echo "  outcome     stopped with a cushion intact, by choice."
+            echo "              The real ceiling is higher — --to-oom finds it, at the"
+            echo "              cost of an actual OOM kill." ;;
+        interrupted)
+            echo "  outcome     interrupted at ${rss:-$held} MB — where you stopped it,"
+            echo "              not where the box did." ;;
+        *)
+            # No stop line means the child did not decide to stop: it was ended.
+            if [ "$rc" -ge 128 ]; then
+                echo "  outcome     the child was killed (signal $((rc - 128))) at ${rss:-$held} MB."
+            elif [ "$rc" -ne 0 ]; then
+                echo "  outcome     the allocation failed at ${rss:-$held} MB (exit ${rc})."
+                echo "              bash could not get the next chunk — an honest malloc"
+                echo "              failure rather than a kill. That is the strict-overcommit"
+                echo "              or ulimit path."
+            else
+                echo "  outcome     ended at ${rss:-$held} MB."
+            fi
+            local ev
+            ev=$(dmesg 2>/dev/null | tail -80 | grep -iE 'oom-kill|killed process' | tail -1 || true)
+            if [ -n "$ev" ]; then
+                echo "  kernel      ${ev#*] }"
+            else
+                echo "  - dmesg is unreadable here (dmesg_restrict, or no privilege),"
+                echo "    so the kill cannot be confirmed from this side. The number stands."
+            fi ;;
+    esac
+
+    # Warn about claimed-vs-measured gap only when the box, not us, chose the stop.
+    local got="${rss:-$held}"
+    echo
+    if [ -z "$stop" ] && [ "$got" -lt $(( ceiling * 70 / 100 )) ]; then
+        echo "  ! claimed ${ceiling} MB, gave up ${got} MB — under 70% of it."
+        echo "    Something is taking the difference. 'status' names the candidates:"
+        echo "    a cgroup cap, ulimit -v, or memory already resident."
+    fi
+    return 0
+}
+
+# ── all ────────────────────────────────────────────────────────────────────
+
+all() {
+    status
+    echo
+    echo "────────────────────────────────────────────────────────────"
+    echo
+    push
+
+    local got budget_mb ceiling
+    load_config
+    if [ -n "$BUDGET_GB" ]; then
+        budget_mb=$(( BUDGET_GB * 1024 ))
+    else
+        budget_mb=$(( NODES * NODE_MB ))
+    fi
+    ceiling=$(effective_ceiling_mb)
+    got=$(grep -E '^[0-9]' "$STATE" 2>/dev/null | tail -1 | awk '{print $2}' || true)
+    [ -n "$got" ] || got=0
+
+    echo
+    echo "verdict"
+    if [ -n "$BUDGET_GB" ]; then
+        echo "  budget      ${budget_mb} MB  (--budget)"
+    else
+        # rig's own figure for this profile: nodes times what one node costs.
+        # Addons carry no memory figure in rig yet, so this is the cluster alone
+        # and whatever you deploy comes on top. --budget once you know that too.
+        echo "  budget      ${budget_mb} MB — profile ${PROFILE_NAME}: ${NODES} node(s) x ${NODE_MB} MB,"
+        echo "              the cluster alone; your workload comes on top (--budget GB)"
+    fi
+    echo "  measured    ${got} MB handed over"
+
+    if [ "$got" -ge "$budget_mb" ]; then
+        echo "  fits, with $(( got - budget_mb )) MB spare."
+        if [ "$got" -lt $(( budget_mb * 130 / 100 )) ]; then
+            echo "  - under 30% spare is thin once a workload runs on top: memory use"
+            echo "    is spiky, and the spikes are what get killed."
+        fi
+    else
+        echo "  ! short by $(( budget_mb - got )) MB."
+        if [ "$ceiling" -ge "$budget_mb" ]; then
+            echo "    The box CLAIMS enough (${ceiling} MB) but did not deliver it."
+            echo "    Free something, or read the caps section again."
+        else
+            echo "    The box does not have it to give. A bigger machine, or a profile"
+            echo "    with fewer nodes."
+        fi
+    fi
+    return 0
+}
+
+# ── main ───────────────────────────────────────────────────────────────────
+
+parse_flags() {
+    while [ $# -gt 0 ]; do
+        case "$1" in
+            --to)      TO_MB=$(( ${2:?--to needs a value in GB} * 1024 )); shift 2 ;;
+            --to-mb)   TO_MB="${2:?--to-mb needs a value in MB}"; shift 2 ;;
+            --step)    STEP_MB="${2:?--step needs a value in MB}"; STEP_EXPLICIT=yes; shift 2 ;;
+            --to-oom)  TO_OOM=yes; shift ;;
+            --budget)  BUDGET_GB="${2:?--budget needs a value in GB}"; BUDGET_EXPLICIT=yes; shift 2 ;;
+            *) echo "unknown argument: $1" >&2; exit 1 ;;
+        esac
+    done
+    if [ "$TO_OOM" = yes ] && [ -n "$TO_MB" ]; then
+        echo "--to and --to-oom contradict each other: one stops early, the other" >&2
+        echo "refuses to stop at all. Pick one." >&2
+        exit 1
+    fi
+    return 0
+}
+
+require_linux
+find_cgroup
+
+cmd="${1:-status}"
+[ $# -gt 0 ] && shift
+
+case "$cmd" in
+    status) parse_flags "$@"; status ;;
+    push)   parse_flags "$@"; push ;;
+    all)    parse_flags "$@"; all ;;
+    backup)  backup ;;
+    restore) restore ;;
+    *)      echo "usage: $0 [status|push|all|backup|restore]" >&2
+            echo "       push [--to GB] [--to-mb MB] [--step MB] [--to-oom]" >&2
+            echo "       all  [--budget GB]" >&2
+            exit 1 ;;
+esac

rig/ctrl/ports.sh

@@ -0,0 +1,95 @@
+#!/usr/bin/env bash
+# Give each environment its own block of host ports, derived from the directory name.
+#   base = 20000 + (hash(slug) % 200) * 10;  +0 HTTP +1 HTTPS +2 TILT +3 REGISTRY
+# Usage: ports.sh show | active | derive | persist
+# Notes: docs/notes/ports.md
+set -euo pipefail
+cd "$(dirname "$0")"
+
+source ./lib/config.sh
+
+# derive_port_base lives in lib/config.sh so every script resolves the same block
+# without going through this one.
+derive_base() { derive_port_base "$1"; }
+
+derive() {
+    load_config
+    local base; base=$(derive_base "$CLUSTER")
+    DERIVED_HTTP=$base
+    DERIVED_HTTPS=$((base + 1))
+    DERIVED_TILT=$((base + 2))
+    DERIVED_REGISTRY=$((base + 3))
+}
+
+# Resolved facts for consumers outside bash, space-separated, positional:
+#   CLUSTER KUBECONTEXT HTTP HTTPS TILT REGISTRY MANIFESTS_DIR
+# Read this, not `derive` (which ignores ctrl/.env).
+active() {
+    load_config
+    echo "$CLUSTER $KUBECONTEXT $HTTP_PORT $HTTPS_PORT $TILT_PORT $REGISTRY_PORT $MANIFESTS_DIR"
+}
+
+show() {
+    derive
+    echo "environment  $CLUSTER"
+    echo "derived base $(derive_base "$CLUSTER")"
+    echo
+    printf "  %-14s %-8s %-8s %s\n" KEY DERIVED ACTIVE SOURCE
+    _row HTTP_PORT     "$DERIVED_HTTP"
+    _row HTTPS_PORT    "$DERIVED_HTTPS"
+    _row TILT_PORT     "$DERIVED_TILT"
+    _row REGISTRY_PORT "$DERIVED_REGISTRY"
+}
+
+_row() {
+    local key="$1" derived="$2" active="${!1:-}" src="derived"
+    if [ -n "$active" ] && [ "$active" != "$derived" ]; then
+        src="override"
+    elif [ -z "$active" ]; then
+        active="$derived"
+    fi
+    printf "  %-14s %-8s %-8s %s\n" "$key" "$derived" "$active" "$src"
+}
+
+# Write the derived block into ctrl/.env, once. Existing keys are never
+# rewritten — an override stays an override.
+persist() {
+    derive
+    [ -f ./.env ] || cp ./.env.example ./.env
+
+    local wrote=0 key val
+    for key in HTTP_PORT:$DERIVED_HTTP \
+               HTTPS_PORT:$DERIVED_HTTPS \
+               TILT_PORT:$DERIVED_TILT \
+               REGISTRY_PORT:$DERIVED_REGISTRY; do
+        val="${key#*:}"; key="${key%%:*}"
+        if grep -qE "^${key}=[0-9]" ./.env 2>/dev/null; then
+            continue
+        fi
+        if [ "$wrote" -eq 0 ]; then
+            {
+                echo ""
+                echo "# Port block for this environment, derived from the directory name"
+                echo "# so copies never collide. Pinned here on first use — edit freely."
+            } >> ./.env
+            wrote=1
+        fi
+        # Replace a commented/empty placeholder if present, else append.
+        if grep -qE "^#?\s*${key}=" ./.env 2>/dev/null; then
+            sed -i "s|^#\?\s*${key}=.*|${key}=${val}|" ./.env
+        else
+            echo "${key}=${val}" >> ./.env
+        fi
+    done
+
+    [ "$wrote" -eq 1 ] && echo "pinned port block into ctrl/.env" || echo "ports already set in ctrl/.env"
+    return 0
+}
+
+case "${1:-show}" in
+    show)    show ;;
+    derive)  derive; echo "$DERIVED_HTTP $DERIVED_HTTPS $DERIVED_TILT $DERIVED_REGISTRY" ;;
+    active)  active ;;
+    persist) persist ;;
+    *)       echo "usage: $0 [show|active|derive|persist]" >&2; exit 1 ;;
+esac

rig/ctrl/registry.sh

@@ -0,0 +1,186 @@
+#!/usr/bin/env bash
+# Registry plumbing: REGISTRY_MODE none | local | mirror | remote. A script, not ctlptl,
+# because ctlptl cannot express `mirror`.
+# Usage: registry.sh up | down | status
+# Notes: docs/notes/registry.md
+set -euo pipefail
+cd "$(dirname "$0")"
+
+source ./lib/config.sh
+load_config
+
+REG_NAME="${CLUSTER}-registry"
+REG_PORT="${REGISTRY_PORT:-5005}"
+K="kubectl --context ${KUBECONTEXT}"
+
+# ── CA trust ───────────────────────────────────────────────────────────────
+# Copy REGISTRY_CA_FILE into every kind node's trust store (nodes don't inherit host trust).
+install_ca_into_nodes() {
+    [ -n "${REGISTRY_CA_FILE:-}" ] || return 0
+
+    if [ ! -r "$REGISTRY_CA_FILE" ]; then
+        echo "REGISTRY_CA_FILE is set but not readable: $REGISTRY_CA_FILE" >&2
+        exit 1
+    fi
+
+    echo "  distributing CA to kind nodes"
+    local node
+    for node in $(kind get nodes --name "$CLUSTER"); do
+        docker cp "$REGISTRY_CA_FILE" "$node:/usr/local/share/ca-certificates/corp-registry.crt"
+        docker exec "$node" update-ca-certificates >/dev/null 2>&1
+        docker exec "$node" systemctl restart containerd
+    done
+}
+
+# Point containerd at a registry host. The cluster config already set
+# config_path=/etc/containerd/certs.d, so this is a per-node drop-in and needs no
+# cluster recreate — which is what lets registry mode change on a live cluster.
+write_hosts_toml() {
+    local host="$1" upstream="$2" skip_verify="${3:-false}"
+    local node
+    for node in $(kind get nodes --name "$CLUSTER"); do
+        docker exec "$node" mkdir -p "/etc/containerd/certs.d/${host}"
+        docker exec -i "$node" cp /dev/stdin "/etc/containerd/certs.d/${host}/hosts.toml" <<TOML
+server = "${upstream}"
+
+[host."${upstream}"]
+  capabilities = ["pull", "resolve"]
+  skip_verify = ${skip_verify}
+TOML
+    done
+}
+
+# ── the local container (local + mirror) ───────────────────────────────────
+
+start_registry_container() {
+    if [ "$(docker inspect -f '{{.State.Running}}' "$REG_NAME" 2>/dev/null || true)" = "true" ]; then
+        echo "  registry container '$REG_NAME' already running"
+        return
+    fi
+    docker rm -f "$REG_NAME" >/dev/null 2>&1 || true
+
+    local args=(-d --restart=always --name "$REG_NAME"
+                -p "127.0.0.1:${REG_PORT}:5000")
+
+    if [ "$REGISTRY_MODE" = "mirror" ]; then
+        if [ -z "${REGISTRY_REMOTE_URL:-}" ]; then
+            echo "REGISTRY_MODE=mirror needs REGISTRY_REMOTE_URL in ctrl/.env" >&2
+            exit 1
+        fi
+        echo "  starting pull-through cache of ${REGISTRY_REMOTE_URL}"
+        args+=(-e "REGISTRY_PROXY_REMOTEURL=${REGISTRY_REMOTE_URL}")
+        [ -n "${REGISTRY_USER:-}" ]     && args+=(-e "REGISTRY_PROXY_USERNAME=${REGISTRY_USER}")
+        [ -n "${REGISTRY_PASSWORD:-}" ] && args+=(-e "REGISTRY_PROXY_PASSWORD=${REGISTRY_PASSWORD}")
+        if [ -n "${REGISTRY_CA_FILE:-}" ]; then
+            args+=(-v "$(readlink -f "$REGISTRY_CA_FILE"):/etc/ssl/certs/corp-ca.crt:ro")
+        fi
+    else
+        echo "  starting local registry"
+    fi
+
+    docker run "${args[@]}" "$REGISTRY_IMAGE" >/dev/null
+}
+
+# The registry must share a network with the nodes so they can resolve it by
+# container name; localhost inside a node is the node, not the host.
+join_kind_network() {
+    if docker inspect -f '{{json .NetworkSettings.Networks}}' "$REG_NAME" | grep -q '"kind"'; then
+        return
+    fi
+    docker network connect kind "$REG_NAME" >/dev/null 2>&1 || true
+}
+
+# The documented contract that tells tooling (Tilt, skaffold) where the local
+# registry is, so they don't have to be configured separately.
+apply_hosting_configmap() {
+    $K apply -f - <<YAML >/dev/null
+apiVersion: v1
+kind: ConfigMap
+metadata:
+  name: local-registry-hosting
+  namespace: kube-public
+data:
+  localRegistryHosting.v1: |
+    host: "localhost:${REG_PORT}"
+    help: "https://kind.sigs.k8s.io/docs/user/local-registry/"
+YAML
+}
+
+# ── modes ──────────────────────────────────────────────────────────────────
+
+up() {
+    echo "registry: ${REGISTRY_MODE}"
+    case "$REGISTRY_MODE" in
+        none)
+            echo "  no registry — images are built straight into the node"
+            ;;
+
+        local|mirror)
+            start_registry_container
+            join_kind_network
+            install_ca_into_nodes
+            # Nodes reach the registry by container name on the shared network;
+            # the host reaches it on localhost:PORT. Both names must resolve.
+            write_hosts_toml "localhost:${REG_PORT}" "http://${REG_NAME}:5000"
+            if [ "$REGISTRY_MODE" = "mirror" ]; then
+                # Anything asking for docker.io transparently goes to the cache.
+                write_hosts_toml "docker.io" "http://${REG_NAME}:5000"
+            fi
+            apply_hosting_configmap
+            echo "  ready at localhost:${REG_PORT}"
+            ;;
+
+        remote)
+            if [ -z "${REGISTRY_REMOTE_URL:-}" ]; then
+                echo "REGISTRY_MODE=remote needs REGISTRY_REMOTE_URL in ctrl/.env" >&2
+                exit 1
+            fi
+            install_ca_into_nodes
+            local host="${REGISTRY_REMOTE_URL#*://}"; host="${host%%/*}"
+            if [ -n "${REGISTRY_USER:-}" ]; then
+                echo "  creating imagePullSecret for ${host}"
+                $K create secret docker-registry regcred \
+                    --docker-server="$host" \
+                    --docker-username="$REGISTRY_USER" \
+                    --docker-password="$REGISTRY_PASSWORD" \
+                    --dry-run=client -o yaml | $K apply -f - >/dev/null
+                # Attach to the default ServiceAccount so plain pods inherit it.
+                $K patch serviceaccount default \
+                    -p '{"imagePullSecrets":[{"name":"regcred"}]}' >/dev/null
+            fi
+            echo "  pulling directly from ${host}"
+            ;;
+
+        *)
+            echo "unknown REGISTRY_MODE '$REGISTRY_MODE' (expected none|local|mirror|remote)" >&2
+            exit 1
+            ;;
+    esac
+}
+
+down() {
+    if docker inspect "$REG_NAME" >/dev/null 2>&1; then
+        echo "removing registry container '$REG_NAME'"
+        docker rm -f "$REG_NAME" >/dev/null
+    fi
+}
+
+status() {
+    echo "mode      ${REGISTRY_MODE}"
+    if docker inspect "$REG_NAME" >/dev/null 2>&1; then
+        echo "container ${REG_NAME}  $(docker inspect -f '{{.State.Status}}' "$REG_NAME")"
+        echo "endpoint  localhost:${REG_PORT}"
+    else
+        echo "container none"
+    fi
+    [ -n "${REGISTRY_REMOTE_URL:-}" ] && echo "upstream  ${REGISTRY_REMOTE_URL}"
+    [ -n "${REGISTRY_CA_FILE:-}" ]    && echo "ca        ${REGISTRY_CA_FILE}"
+    return 0
+}
+
+case "${1:-status}" in
+    up)     up ;;
+    down)   down ;;
+    status) status ;;
+    *)      echo "usage: $0 [up|down|status]" >&2; exit 1 ;;
+esac

rig/ctrl/selftest.sh

@@ -0,0 +1,209 @@
+#!/usr/bin/env bash
+# What rig has settled, written down as assertions: one decision per check.
+# No cluster, docker or network; exits 1 on failure (unlike `make check`).
+# Usage: make selftest   (or: bash ctrl/selftest.sh)
+# Notes: docs/notes/selftest.md
+set -uo pipefail          # NOT -e: one failing check must not abort the rest
+cd "$(dirname "$0")"
+
+source ./lib/config.sh
+
+rc=0
+passed=0
+
+check() {   # name, expected, actual
+    if [ "$2" = "$3" ]; then
+        printf '  ok    %s\n' "$1"
+        passed=$((passed + 1))
+    else
+        printf '  FAIL  %s\n        expected: %s\n        got:      %s\n' "$1" "$2" "$3"
+        rc=1
+    fi
+}
+
+note() { printf '\n%s\n' "$1"; }
+
+# Resolve one key the way every rig script does, in a clean shell so the
+# caller's exported value is the only thing in play.
+resolved() {
+    bash -c 'source ./lib/config.sh; load_config >/dev/null 2>&1; printf "%s" "${!1}"' _ "$1"
+}
+
+
+note "rig needs no profile"
+# No env.d/ must still resolve and generate a kit; an unknown profile stays an error.
+NP="$(mktemp -d)"
+cp -r .. "$NP/rig"; rm -rf "$NP/rig/ctrl/env.d"; sed -i '/^PROFILE=/d' "$NP/rig/ctrl/.env" 2>/dev/null
+check "no env.d: config resolves" "default" \
+    "$(cd "$NP/rig/ctrl" && bash -c 'source ./lib/config.sh; load_config >/dev/null && echo "$PROFILE_NAME"' 2>&1)"
+check "no env.d: the k8s version comes from the pins" "yes" \
+    "$(cd "$NP/rig/ctrl" && bash -c 'source ./lib/config.sh; load_config >/dev/null && [ -n "$NODE_IMAGE" ] && echo yes' 2>&1)"
+check "no env.d: ports.sh active works" "7" \
+    "$(cd "$NP/rig/ctrl" && bash ports.sh active 2>/dev/null | wc -w)"
+check "no env.d: a kit is generated for the defaults" "yes" \
+    "$( (cd "$NP/rig/ctrl" && rm -rf ../standalone/*/ && bash standalone.sh write >/dev/null 2>&1) && [ -f "$NP/rig/standalone/default/rigdeps.sh" ] && echo yes || echo no)"
+check "a profile that does not exist is still an error" "yes" \
+    "$( (cd "$NP/rig/ctrl" && PROFILE=no-such-profile bash -c 'source ./lib/config.sh; load_config' >/dev/null 2>&1) && echo no || echo yes)"
+rm -rf "$NP"
+
+
+note "the ports.sh active contract"
+# ports.sh active is read positionally by the Makefile and Tiltfile: pin field count and order.
+FACTS="$(bash ports.sh active)"
+check "active: exactly 7 fields"          "7" "$(printf '%s' "$FACTS" | wc -w)"
+read -r F_CLUSTER F_CTX F_HTTP F_HTTPS F_TILT F_REG F_MANIFESTS <<< "$FACTS"
+check "active: field 2 is kind-<cluster>" "kind-$F_CLUSTER" "$F_CTX"
+check "active: fields 3-6 are numeric"    "yes" \
+    "$([[ "$F_HTTP$F_HTTPS$F_TILT$F_REG" =~ ^[0-9]+$ ]] && echo yes || echo no)"
+check "active: field 7 is a path"         "yes" \
+    "$([ -n "$F_MANIFESTS" ] && [ "${F_MANIFESTS#-}" = "$F_MANIFESTS" ] && echo yes || echo no)"
+# derive answers a different question and must keep its own shape: it reports
+# what the directory name implies, ignoring ctrl/.env, so nothing should
+# configure itself from it.
+check "derive: still 4 fields, not 7"     "4" "$(bash ports.sh derive | wc -w)"
+
+
+note "the caller's env beats the files"
+# Every key in CONFIG_OVERRIDABLE must lose to the caller's env; the loop follows the list.
+test_value() {
+    case "$1" in
+        # Picked from what exists, never named: rig must not need any particular
+        # profile, template or pinned version to be present for this to run.
+        PROFILE)        config_profiles | head -1 ;;
+        K8S_VERSION)    (set -a; source ./versions.env; compgen -v NODE_IMAGE_v | sort -V | head -1 | sed 's/^NODE_IMAGE_//') ;;
+        # An absolute path, as a project passing its own file does. Never equal
+        # to the default, so the check cannot pass by accident.
+        KIND_CONFIG)    echo "$PWD/k8s/kind-config.yaml.tpl" ;;
+        *_PORT)         echo "19999" ;;
+        CLUSTER)        echo "selftest-name" ;;
+        MANIFESTS_DIR)  echo "../elsewhere/overlays/dev" ;;
+        ADDONS)         echo "metallb" ;;
+        *)              echo "selftest-sentinel" ;;
+    esac
+}
+for key in $CONFIG_OVERRIDABLE; do
+    [ -n "$key" ] || continue
+    want="$(test_value "$key")"
+    if [ -z "$want" ]; then
+        check "precedence: $key has a test value" "yes" "no — add one to test_value()"
+        continue
+    fi
+    got="$(export "$key=$want"; resolved "$key")"
+    check "precedence: caller's $key wins" "$want" "$got"
+done
+
+
+note "one derivation, not three"
+# The Makefile must take context/port from ports.sh active, checked on real `make -n` output.
+# --no-print-directory + grep, not tail -1: under `make selftest` this is a recursive make.
+MK="$(cd .. && make --no-print-directory -n tilt 2>/dev/null | grep -m1 'tilt ')"
+check "Makefile: --context comes from active" "$F_CTX" \
+    "$(printf '%s' "$MK" | sed -n 's/.*--context \([^ ]*\).*/\1/p')"
+check "Makefile: --port comes from active"    "$F_TILT" \
+    "$(printf '%s' "$MK" | sed -n 's/.*--port \([^ ]*\).*/\1/p')"
+
+
+note "identity follows the folder, safely"
+# The cluster name is the folder name made a DNS label, derived only in lib/config.sh.
+TMP="$(mktemp -d)"
+trap 'rm -rf "$TMP"' EXIT
+mkdir -p "$TMP/My_Proj"
+cp -r . "$TMP/My_Proj/ctrl"
+# A pinned CLUSTER in .env would be an override, not a derivation, and this
+# check is about the derivation.
+sed -i '/^CLUSTER=/d' "$TMP/My_Proj/ctrl/.env" 2>/dev/null
+COPY="$(cd "$TMP/My_Proj/ctrl" && bash ports.sh active)"
+check "a dir named My_Proj derives a DNS label" "my-proj"      "$(awk '{print $1}' <<< "$COPY")"
+check "and a context to match"                  "kind-my-proj" "$(awk '{print $2}' <<< "$COPY")"
+check "a renamed copy gets a DIFFERENT block"   "different" \
+    "$([ "$(awk '{print $3}' <<< "$COPY")" != "$F_HTTP" ] && echo different || echo COLLIDES)"
+
+
+note "ports are stable across versions"
+# Ports are derived, never stored: a changed derivation moves every existing env's ports.
+check "derive_port_base rig"     "20310" "$(derive_port_base rig)"
+check "derive_port_base foo"     "21690" "$(derive_port_base foo)"
+check "derive_port_base my-proj" "21030" "$(derive_port_base my-proj)"
+
+
+note "rig stays standalone"
+# rig must be copyable out of its host project: no references to the host.
+# The pattern is assembled from fragments so this file does not match itself.
+HOST_PAT="$(printf '%s' 'sole' 'print' '|\b' 'sp' 'r\b')"
+check "no host-project references" "0" \
+    "$(cd .. && grep -rIl -iE "$HOST_PAT" . --exclude-dir=def 2>/dev/null | wc -l)"
+
+
+note "the Tiltfile hardcodes nothing"
+# The Tiltfile asks ports.sh for its context; a literal kind-<name> would undo that.
+check "no literal kind-<name>"  "0" "$(grep -cE "['\"]kind-[a-z0-9]" Tiltfile)"
+check "guards on the variable"  "1" "$(grep -c 'allow_k8s_contexts(CTX)' Tiltfile)"
+check "asks ports.sh for facts" "1" "$(grep -c "local('bash ports.sh active'" Tiltfile)"
+
+
+note "standalone kits are generated, current, and call only real verbs"
+# A kit left stale by a change to rig fails here, not on another machine.
+check "every kit matches what rig generates now" "yes" \
+    "$(bash standalone.sh check >/dev/null 2>&1 && echo yes || echo "no — run make standalone")"
+
+# Every kit Makefile target must call a verb its script's own dispatch accepts.
+verbs_of() {
+    sed -n '/^case "\$cmd" in/,/^esac/p' "$1" | grep -oE '^    [a-z]+\)' | tr -d ' )'
+}
+kits=0
+for mk in ../standalone/*/Makefile; do
+    [ -f "$mk" ] || continue
+    kit=$(dirname "$mk"); kits=$((kits + 1))
+    for target in $(grep -oE '^[a-z][a-z-]*:' "$mk" | tr -d ':' | grep -vx help); do
+        line="$(make --no-print-directory -s -n -f "$mk" "$target" 2>/dev/null | head -1)"
+        script=$(basename "$(printf '%s' "$line" | awk '{print $2}')")
+        verb=$(printf '%s' "$line" | awk '{print $NF}')
+        check "$(basename "$kit"): make $target -> $script $verb, a verb it accepts" "yes" \
+            "$(verbs_of "$kit/$script" | grep -qx "$verb" && echo yes || echo "no: '$verb'")"
+    done
+    check "$(basename "$kit"): no \`mini\` target, which already means minimal footprint" "0" \
+        "$(grep -cE '^mini:' "$mk")"
+done
+check "there is a kit for every profile" "$(config_profiles | wc -l)" "$kits"
+
+# An export carries this machine's choices but never its credentials; committed kits carry neither.
+# Proven with sentinel values in a scratch copy, since the real ctrl/.env may leave them empty.
+SX="$TMP/export-proof"; mkdir -p "$SX"; cp -r .. "$SX/rig"
+cat >> "$SX/rig/ctrl/.env" <<'EOF'
+REGISTRY_USER=selftest-sentinel-user
+REGISTRY_PASSWORD=selftest-sentinel-password
+MANIFESTS_DIR=../selftest-sentinel-choice/overlays/dev
+EOF
+( cd "$SX/rig/ctrl" && bash standalone.sh export "$SX/out" >/dev/null 2>&1 )
+count_in() { grep -rcF -- "$1" "$2" 2>/dev/null | awk -F: '{s+=$2} END{print s+0}'; }
+check "export: carries this machine's choices" "yes" \
+    "$([ "$(count_in selftest-sentinel-choice "$SX/out")" -gt 0 ] && echo yes || echo no)"
+check "export: carries no credential" "0" \
+    "$(( $(count_in selftest-sentinel-user "$SX/out") + $(count_in selftest-sentinel-password "$SX/out") ))"
+check "per-profile kits: carry neither, whatever this machine has" "0" \
+    "$( (cd "$SX/rig/ctrl" && source ./lib/config.sh && for p in $(config_profiles); do config_snapshot "$p"; done) \
+        | grep -cE 'selftest-sentinel-(choice|user|password)')"
+check "export: refuses to write inside the repository" "yes" \
+    "$( (bash standalone.sh export ../standalone/selftest-mine >/dev/null 2>&1) && echo no || echo yes)"
+
+
+note "optional — needs tilt and this rig's cluster"
+# Tilt needs a cluster context to parse the Tiltfile, so this is skipped without one.
+if ! command -v tilt >/dev/null; then
+    printf '  skip  tilt is not installed\n'
+elif ! kubectl config get-contexts -o name 2>/dev/null | grep -qx "$F_CTX"; then
+    printf "  skip  no %s context — run 'make cluster up' to include this\n" "$F_CTX"
+else
+    out="$(tilt alpha tiltfile-result --context "$F_CTX" 2>&1)"
+    check "Tiltfile evaluates" "yes" \
+        "$(printf '%s' "$out" | grep -q '"Manifests"' && echo yes || echo "no: $(printf '%s' "$out" | tail -1)")"
+fi
+
+
+printf '\n'
+if [ "$rc" -eq 0 ]; then
+    printf '%d checks passed — rig still does what it says\n' "$passed"
+else
+    printf 'FAILED — a decision above has drifted; read the comment next to it\n' >&2
+fi
+exit "$rc"

rig/ctrl/standalone.sh

@@ -0,0 +1,350 @@
+#!/usr/bin/env bash
+# Generate standalone kits: rig's tools flattened into single files, one folder per profile.
+# Usage: standalone.sh write|check   generate (or diff) standalone/<profile>/
+#        standalone.sh export DIR    one kit for this machine's config, no credentials, outside the repo
+# Notes: docs/notes/standalone.md
+set -euo pipefail
+cd "$(dirname "$0")"
+
+CTRL="$PWD"
+ROOT="$(cd .. && pwd)"
+OUT="$ROOT/standalone"
+SELF_REL="ctrl/${0##*/}"
+
+GENERATED_TAG="GENERATED by make standalone — do not edit"
+
+# The contract's own functions: questions rig answers FOR this generator. They
+# are never carried into a kit — load_config is replaced by the frozen one, and
+# the rest mean nothing without rig's tree. The only names this file knows.
+CONTRACT_FUNCS="load_config config_profiles config_snapshot config_freeze config_current_profile config_left_out"
+FROZEN_OPEN="# ── configuration, frozen"
+FROZEN_CLOSE="# ── end of frozen configuration"
+
+refuse() { echo >&2; echo "standalone: refusing — $*" >&2; exit 1; }
+
+# A clean bash with nothing from the caller's shell in it. What the kit carries
+# must not depend on who ran the generator or what they had exported.
+clean_bash() { env -i PATH="$PATH" HOME="$HOME" CONTRACT_FUNCS="$CONTRACT_FUNCS" bash --noprofile --norc "$@"; }
+
+# ── 1. entry points ────────────────────────────────────────────────────────
+entries() {
+    grep -rlE --include='*.sh' '^# rig:standalone [a-z0-9-]+ [a-z0-9-]+' . 2>/dev/null \
+        | sed 's|^\./||' | LC_ALL=C sort
+}
+marker_of() {  # entry -> "kit verb"
+    sed -nE 's/^# rig:standalone ([a-z0-9-]+) ([a-z0-9-]+).*/\1 \2/p' "$1" | head -1
+}
+
+# ── 2. the libraries an entry point sources ────────────────────────────────
+# Only the entry point's own `source` lines are read as text. Everything those
+# libraries pull in is resolved by bash when they are sourced in step 3.
+libs_of() {  # entry -> one resolved lib path per line, relative to ctrl/
+    local entry="$1" dir line n path
+    dir=$(dirname "$entry")
+    while IFS=: read -r n line; do
+        path=$(printf '%s' "$line" | sed -E 's/^[[:space:]]*(source|\.)[[:space:]]+//; s/[[:space:]]+(#.*)?$//')
+        path=${path#\"}; path=${path%\"}; path=${path#\'}; path=${path%\'}
+        case "$path" in
+            *'$'*) refuse "$entry:$n sources '$path' — a path with a variable in it cannot be resolved; name the file" ;;
+        esac
+        case "$path" in
+            *.sh) ;;
+            *) refuse "$entry:$n sources '$path' directly — only libraries (.sh) may be sourced; configuration has to enter through load_config" ;;
+        esac
+        path="$dir/${path#./}"; path=${path#./}
+        [ -f "$path" ] || refuse "$entry:$n sources '$path', which does not exist"
+        printf '%s\n' "$path"
+    done < <(grep -nE '^[[:space:]]*(source|\.)[[:space:]]+[^=]' "$entry" || true)
+}
+
+# Into the global array `libs`. Not `mapfile < <(libs_of ...)`: a refusal inside
+# a process substitution only ends that subshell, so generation would carry on
+# past it and fail later with a message about something else entirely.
+libs_into() {
+    local out
+    out=$(libs_of "$1") || exit 1
+    libs=()
+    [ -n "$out" ] && mapfile -t libs <<< "$out"
+    return 0
+}
+
+# ── 3. what the libraries define, read back from bash itself ───────────────
+# The frozen config replaces load_config, and the generator's own two questions
+# are useless inside a kit, so none of the three is carried.
+lib_defs() {  # entry lib... -> declare -p globals, then declare -f functions
+    local entry="$1"; shift
+    ( cd "$(dirname "$entry")" && clean_bash -c '
+        skip_var() { case "$1" in CONTRACT_FUNCS|BASH*|FUNCNAME|PIPESTATUS|LINENO|RANDOM|SRANDOM|SECONDS|EPOCH*|HISTCMD|COLUMNS|LINES|PWD|OLDPWD|_|SHLVL|OPTIND|OPTERR|IFS|PS4|PATH|HOME|v|f|l|before_v|before_f) return 0 ;; esac; return 1; }
+        before_v=" $(compgen -v | tr "\n" " ") "
+        before_f=" $(compgen -A function | tr "\n" " ") "
+        for l in "$@"; do source "$l" || { echo "__FAIL__ sourcing $l" ; exit 1; }; done
+        for v in $(compgen -v); do
+            skip_var "$v" && continue
+            case "$before_v" in *" $v "*) continue ;; esac
+            declare -p "$v"
+        done
+        for f in $(compgen -A function); do
+            case "$before_f" in *" $f "*) continue ;; esac
+            case " skip_var $CONTRACT_FUNCS " in *" $f "*) continue ;; esac
+            declare -f "$f"
+        done
+    ' _ "$@" ) || refuse "$entry: its libraries could not be sourced cleanly"
+}
+
+# ── 4. ask rig for profiles and resolved config ────────────────────────────
+ask() {  # entry lib... -- function args... -> that function's stdout
+    local entry="$1"; shift
+    local libs=() a
+    while [ $# -gt 0 ] && [ "$1" != -- ]; do libs+=("$1"); shift; done
+    shift
+    ( cd "$(dirname "$entry")" && clean_bash -c '
+        n=0; for a in "$@"; do n=$((n+1)); [ "$a" = -- ] && break; done
+        for l in "${@:1:$((n-1))}"; do source "$l"; done
+        shift "$n"
+        declare -F "$1" >/dev/null || exit 3
+        "$@"
+    ' _ "${libs[@]}" -- "$@" )
+}
+
+# ── 5. assemble one kit file ───────────────────────────────────────────────
+assemble() {  # entry profile out-file lib...
+    local entry="$1" profile="$2" dest="$3"; shift 3
+    local libs=("$@") calls_config=no
+    grep -qE '(^|[^A-Za-z0-9_])load_config([^A-Za-z0-9_]|$)' "$entry" && calls_config=yes
+
+    {
+        echo '#!/usr/bin/env bash'
+        echo "# $GENERATED_TAG"
+        echo "#"
+        echo "# $(basename "$dest") for ${KIT_LABEL:-profile '$profile'}, flattened from:"
+        echo "#   ctrl/$entry"
+        local l; for l in ${libs[@]+"${libs[@]}"}; do echo "#   ctrl/$l"; done
+        echo "# Edit those and run \`make standalone\`. Changes made here are lost, and"
+        echo "# \`make selftest\` fails while this file differs from what rig generates."
+        echo
+
+        if [ ${#libs[@]} -gt 0 ]; then
+            echo "# ── from the libraries ──"
+            lib_defs "$entry" "${libs[@]}"
+            echo
+        fi
+
+        if [ "$calls_config" = yes ]; then
+            local frozen
+            frozen=$(ask "$entry" ${libs[@]+"${libs[@]}"} -- config_freeze "${FREEZE_ARG:-$profile}") \
+                || refuse "ctrl/$entry calls load_config, but its libraries do not answer config_freeze ${FREEZE_ARG:-$profile}"
+            echo "$FROZEN_OPEN for ${KIT_LABEL:-profile '$profile'} ──"
+            printf '%s\n' "$frozen"
+            echo "$FROZEN_CLOSE ──"
+            echo
+        fi
+
+        echo "# ── ctrl/$entry ──"
+        # The entry point itself, minus its shebang and marker, with each source
+        # line it made replaced by a note — what it sourced is already above.
+        awk '
+            NR == 1 && /^#!/ { next }
+            /^# rig:standalone / { next }
+            /^[[:space:]]*(source|\.)[[:space:]]+[^=]/ { print "# (sourced library inlined above)"; next }
+            { print }
+        ' "$entry"
+    } > "$dest"
+    chmod +x "$dest"
+}
+
+# ── 6. the kit's Makefile, from the markers ────────────────────────────────
+verbs_of() {  # entry -> its top-level dispatch arms
+    awk '/^case / { inb=1; next } /^esac/ { inb=0 } inb && match($0, /^    [a-z][a-z-]*\)/) { v=substr($0, 5, RLENGTH-5); printf "%s%s", (n++ ? "|" : ""), v }' "$1"
+}
+makefile() {  # out-dir entry...
+    local dir="$1"; shift
+    local e kit verb target verbs targets=""
+    for e in "$@"; do targets+=" $(basename "$e" .sh)"; done
+    {
+        echo "# $GENERATED_TAG"
+        echo "#"
+        echo "# Shorthand for the scripts beside it; they run without it. Every target"
+        echo "# calls a verb its script accepts — read from that script's own dispatch."
+        echo
+        echo 'HERE := $(dir $(abspath $(lastword $(MAKEFILE_LIST))))'
+        echo 'ARGS := $(wordlist 2,$(words $(MAKECMDGOALS)),$(MAKECMDGOALS))'
+        echo 'ifneq ($(ARGS),)'
+        echo '$(eval $(ARGS):;@:)'
+        echo '.PHONY: $(ARGS)'
+        echo 'endif'
+        echo
+        echo '.DEFAULT_GOAL := help'
+        echo ".PHONY: help$targets"
+        echo
+        echo 'help:                          ## list targets'
+        printf '\t%s\n' "@grep -hE '^[a-z][a-z-]*:.*?##' \$(MAKEFILE_LIST) | sed 's/:.*##/\\t/' | expand -t16"
+        for e in "$@"; do
+            read -r kit verb <<< "$(marker_of "$e")"
+            target=$(basename "$e" .sh)
+            verbs=$(verbs_of "$e")
+            echo
+            printf '%-30s ## %s.sh  [%s]  (default %s)\n' "$target:" "$kit" "${verbs:-?}" "$verb"
+            printf '\tbash $(HERE)%s.sh $(or $(ARGS),%s)\n' "$kit" "$verb"
+        done
+    } > "$dir/Makefile"
+}
+
+# ── 7. prove a kit stands alone ────────────────────────────────────────────
+verify_kit() {  # dir profile entry...
+    local dir="$1" profile="$2"; shift 2
+    local e kit verb f bad smoke rc
+    for e in "$@"; do
+        read -r kit verb <<< "$(marker_of "$e")"
+        f="$dir/$kit.sh"
+
+        bash -n "$f" 2>/dev/null || refuse "$profile/$kit.sh does not parse: $(bash -n "$f" 2>&1 | head -1)"
+
+        # Code only: comments are free to mention anything, and the frozen block
+        # is data — a value that happens to hold a path is harmless unless code
+        # opens it, and opening it is what the smoke run below would catch.
+        bad=$(awk -v fz_open="$FROZEN_OPEN" -v fz_close="$FROZEN_CLOSE" '
+            index($0, fz_open) == 1 { fz=1; next }
+            index($0, fz_close) == 1 { fz=0; next }
+            fz || /^[[:space:]]*#/ { next }
+            /^[[:space:]]*(source|\.)[[:space:]]+[^=]/ { printf "%d: still sources: %s\n", NR, $0; next }
+            # Rig-relative only. The preceding character may not be "/", so an
+            # absolute system path such as /var/lib/docker is not mistaken for
+            # rig lib/; an explicit ./ or ../ prefix is matched on its own.
+            /(^|[^A-Za-z0-9_.\/])(ctrl\/|lib\/|env\.d\/)|\.\.?\/(ctrl\/|lib\/|env\.d\/)|versions\.env|(^|[^A-Za-z0-9_])\.env([^A-Za-z0-9_]|$)/ {
+                printf "%d: refers into rig'"'"'s tree: %s\n", NR, $0
+            }' "$f" | head -3)
+        [ -z "$bad" ] || refuse "$profile/$kit.sh does not stand alone —"$'\n'"$(printf '%s\n' "$bad" | sed 's/^/    line /')"
+    done
+
+    # The real test: a folder holding only this kit, and nothing else from rig.
+    smoke=$(mktemp -d)
+    cp "$dir"/* "$smoke"/
+    for e in "$@"; do
+        read -r kit verb <<< "$(marker_of "$e")"
+        rc=0
+        out=$( (cd "$smoke" && timeout 120 bash "./$kit.sh" "$verb") 2>&1 ) || rc=$?
+        if [ "$rc" -ne 0 ]; then
+            rm -rf "$smoke"
+            refuse "$profile/$kit.sh $verb exits $rc in an empty directory:"$'\n'"$(printf '%s\n' "$out" | tail -5 | sed 's/^/    /')"
+        fi
+    done
+    ( cd "$smoke" && make -s help >/dev/null ) || { rm -rf "$smoke"; refuse "$profile/Makefile: make help fails"; }
+    rm -rf "$smoke"
+}
+
+# ── generate ───────────────────────────────────────────────────────────────
+generate() {  # into-dir
+    local into="$1" e profiles="" p kit verb libs
+    local -a all_entries=()
+    while IFS= read -r e; do all_entries+=("$e"); done < <(entries)
+    [ ${#all_entries[@]} -gt 0 ] || refuse "no script under ctrl/ carries a '# rig:standalone <kit> <verb>' marker"
+
+    # Profiles come from whichever entry point's libraries can answer for them.
+    for e in "${all_entries[@]}"; do
+        libs_into "$e"
+        profiles=$(ask "$e" ${libs[@]+"${libs[@]}"} -- config_profiles 2>/dev/null) && [ -n "$profiles" ] && break
+        profiles=""
+    done
+    [ -n "$profiles" ] || refuse "no entry point's libraries answer config_profiles, so there is nothing to generate a kit per"
+
+    for p in $profiles; do
+        mkdir -p "$into/$p"
+        for e in "${all_entries[@]}"; do
+            read -r kit verb <<< "$(marker_of "$e")"
+            libs_into "$e"
+            assemble "$e" "$p" "$into/$p/$kit.sh" ${libs[@]+"${libs[@]}"}
+        done
+        makefile "$into/$p" "${all_entries[@]}"
+        verify_kit "$into/$p" "$p" "${all_entries[@]}"
+        echo "  $p: $(cd "$into/$p" && ls | tr '\n' ' ')"
+    done
+}
+
+# A kit folder is ours if its Makefile says so. Anything else under standalone/
+# is left alone, so a hand-written file there is never swept away.
+is_generated_dir() { grep -qF "$GENERATED_TAG" "$1/Makefile" 2>/dev/null; }
+
+cmd="${1:-write}"
+[ $# -gt 0 ] && shift
+
+case "$cmd" in
+    write)
+        tmp=$(mktemp -d); trap 'rm -rf "$tmp"' EXIT
+        echo "generating kits from rig's current tree"
+        generate "$tmp"
+        mkdir -p "$OUT"
+        for d in "$OUT"/*/; do
+            d=${d%/}; [ -d "$d" ] || continue
+            if is_generated_dir "$d" && [ ! -d "$tmp/${d##*/}" ]; then
+                echo "  removed $(basename "$d") — no such profile any more"
+                rm -rf "$d"
+            fi
+        done
+        for d in "$tmp"/*/; do
+            d=${d%/}
+            rm -rf "$OUT/${d##*/}"
+            cp -r "$d" "$OUT/${d##*/}"
+        done
+        echo "wrote standalone/<profile>/ — every kit verified to stand alone"
+        ;;
+    check)
+        tmp=$(mktemp -d); trap 'rm -rf "$tmp"' EXIT
+        generate "$tmp" >/dev/null
+        stale=0
+        for d in "$tmp"/*/; do
+            d=${d%/}; p=${d##*/}
+            if ! diff -rq "$d" "$OUT/$p" >/dev/null 2>&1; then
+                echo "stale: standalone/$p — $(diff -rq "$d" "$OUT/$p" 2>&1 | head -1)"
+                stale=1
+            fi
+        done
+        for d in "$OUT"/*/; do
+            d=${d%/}; [ -d "$d" ] || continue
+            if is_generated_dir "$d" && [ ! -d "$tmp/${d##*/}" ]; then
+                echo "stale: standalone/${d##*/} — no such profile any more"; stale=1
+            fi
+        done
+        [ "$stale" -eq 0 ] || { echo "run: make standalone"; exit 1; }
+        echo "every kit is current"
+        ;;
+    export)
+        dest="${1:-}"
+        [ -n "$dest" ] || refuse "export needs a directory, outside the repo: make standalone export ~/rig-kit"
+        dest=$(realpath -m "$dest")
+        top=$(git -C "$ROOT" rev-parse --show-toplevel 2>/dev/null || echo "$ROOT")
+        case "$dest/" in
+            "$top"/*) refuse "an export reflects this machine, so it does not go inside the repository — $dest is under $top. The committed per-profile kits are what standalone/ is for." ;;
+        esac
+        if [ -d "$dest" ] && [ -n "$(ls -A "$dest" 2>/dev/null)" ] && ! is_generated_dir "$dest"; then
+            refuse "$dest already holds something that is not a previous export — pick an empty directory"
+        fi
+
+        mapfile -t all_entries < <(entries)
+        [ ${#all_entries[@]} -gt 0 ] || refuse "no script under ctrl/ carries a '# rig:standalone <kit> <verb>' marker"
+        libs_into "${all_entries[0]}"
+        profile=$(ask "${all_entries[0]}" ${libs[@]+"${libs[@]}"} -- config_current_profile) \
+            || refuse "this machine's configuration does not resolve — run make check"
+        left=$(ask "${all_entries[0]}" ${libs[@]+"${libs[@]}"} -- config_left_out | tr '\n' ' ')
+
+        tmp=$(mktemp -d); trap 'rm -rf "$tmp"' EXIT
+        echo "exporting the configuration this machine runs (profile '$profile')"
+        FREEZE_ARG=--current
+        KIT_LABEL="the configuration exported from $(hostname -s 2>/dev/null || echo this machine) (profile '$profile', local choices included, credentials not)"
+        for e in "${all_entries[@]}"; do
+            read -r kit verb <<< "$(marker_of "$e")"
+            libs_into "$e"
+            assemble "$e" "$profile" "$tmp/$kit.sh" ${libs[@]+"${libs[@]}"}
+        done
+        makefile "$tmp" "${all_entries[@]}"
+        verify_kit "$tmp" "export" "${all_entries[@]}"
+
+        rm -rf "$dest"; mkdir -p "$(dirname "$dest")"; cp -r "$tmp" "$dest"
+        echo "  wrote $dest: $(cd "$dest" && ls | tr '\n' ' ')— verified to stand alone"
+        if [ -n "${left// /}" ]; then
+            echo
+            echo "  NOT carried — this machine's own, set them on the target if it needs them:"
+            for k in $left; do echo "    $k"; done
+        fi
+        ;;
+    *)  echo "usage: $SELF_REL [write|check|export DIR]" >&2; exit 1 ;;
+esac

rig/ctrl/versions.env

@@ -0,0 +1,54 @@
+# Pinned toolchain (linux/amd64, upstream SHA256) — the manifest ctrl/deps.sh installs from.
+# To bump, take the checksum from the release's own list, e.g.
+#   curl -sSL https://github.com/<org>/<repo>/releases/download/<tag>/checksums.txt | grep linux.x86_64
+# Notes: docs/notes/versions.md
+
+KIND_VERSION=v0.32.0
+KIND_SHA256=50030de23cf40a18505f20426f6a8506bedf13c6e509244bd1fa9463721b0f54
+KIND_URL=https://github.com/kubernetes-sigs/kind/releases/download/${KIND_VERSION}/kind-linux-amd64
+
+KUBECTL_VERSION=v1.36.3
+KUBECTL_SHA256=ebbd080e7c2e275093b55915722043257eb24004363e20acb3c4d71919f88336
+KUBECTL_URL=https://dl.k8s.io/release/${KUBECTL_VERSION}/bin/linux/amd64/kubectl
+
+TILT_VERSION=0.37.6
+TILT_SHA256=e9672b8a18d43501f35dcfe98465969a7db0e436b36cf0c50c7e6f8d40de5fe6
+TILT_URL=https://github.com/tilt-dev/tilt/releases/download/v${TILT_VERSION}/tilt.${TILT_VERSION}.linux.x86_64.tar.gz
+
+# ctlptl — kind cluster with a local registry wired in (keeps images off docker.io).
+CTLPTL_VERSION=0.9.4
+CTLPTL_SHA256=c63a1ec28e60bc3faf6becb76f53355c5cf5e0143dafdd27ad85db5584fa6b1e
+CTLPTL_URL=https://github.com/tilt-dev/ctlptl/releases/download/v${CTLPTL_VERSION}/ctlptl.${CTLPTL_VERSION}.linux.x86_64.tar.gz
+
+JQ_VERSION=1.8.2
+JQ_SHA256=b1c22172dd303f3be49e935aa56aa48a8b7a46e0bc838b4997d3bb451495870f
+JQ_URL=https://github.com/jqlang/jq/releases/download/jq-${JQ_VERSION}/jq-linux-amd64
+
+# docker compose — often missing from distro packages; deps.sh links it into
+# ~/.docker/cli-plugins.
+COMPOSE_VERSION=5.5.1
+COMPOSE_SHA256=db1889184726840f75c4f9c001048430d4f25b3be3cb084d3ddd762bc0aed576
+COMPOSE_URL=https://github.com/docker/compose/releases/download/v${COMPOSE_VERSION}/docker-compose-linux-x86_64
+
+# Node images for KIND_VERSION, pinned by digest; profiles pick one via K8S_VERSION.
+# Older entries are kept deliberately (legacy-estate simulation).
+NODE_IMAGE_v1_36=kindest/node:v1.36.1@sha256:3489c7674813ba5d8b1a9977baea8a6e553784dab7b84759d1014dbd78f7ebd5
+NODE_IMAGE_v1_35=kindest/node:v1.35.5@sha256:ce977ae6d65918d0b58a5f8b5e940429c2ce42fa3a5619ec2bbc60b949c0ac95
+NODE_IMAGE_v1_34=kindest/node:v1.34.8@sha256:02722c2dedddcfc00febf5d27fbeb9b7b2c14294c82109ff4a85d89ac9ba3256
+NODE_IMAGE_v1_33=kindest/node:v1.33.12@sha256:3f5c8443c620245e4d355cfe09e96a91ead32ceaa569d3f1ca9edf0cb2fe2ff4
+
+# Images pulled at runtime (registry, mocks). Pinned by tag; the registry mode
+# decides where they are pulled FROM.
+REGISTRY_IMAGE=registry:2
+STUB_IMAGE=python:3.12-slim
+
+# Addons, installed by ctrl/addons/<name>.sh when listed in a profile's ADDONS.
+CERT_MANAGER_VERSION=v1.21.1
+METRICS_SERVER_VERSION=v0.9.0
+METALLB_VERSION=v0.16.0
+
+# Cabinets — unmodified upstream images, usable on compose or in the cluster.
+# Pinned by tag; bump freely, and preload them for the offline profile.
+POSTGRES_IMAGE=postgres:16-alpine
+REDIS_IMAGE=redis:7-alpine
+AIRFLOW_IMAGE=apache/airflow:2.10.4

rig/docs/graphs/01-install.dot

@@ -0,0 +1,47 @@
+digraph rig_install {
+    rankdir=LR
+    bgcolor="#0a0e17"
+    fontname="Helvetica"
+    node [fontname="Helvetica" fontsize=11 style=filled color="#1e2a4a" fontcolor="#e8eaf0" shape=box]
+    edge [fontname="Helvetica" fontsize=9 fontcolor="#8892a8" color="#4a5568"]
+
+    label="Installation — the only host prerequisite is Docker"
+    labelloc=t
+    fontsize=16
+    fontcolor="#0066ff"
+
+    subgraph cluster_host {
+        label="Your machine"
+        style=dashed
+        color="#1e2a4a"
+        fontcolor="#8892a8"
+
+        docker  [label="Docker\n(the one prerequisite)" fillcolor="#1a1a3a" fontcolor="#0066ff" shape=octagon]
+        bin     [label="~/.local/bin\nkind · kubectl · tilt\njq" fillcolor="#121829" shape=cylinder]
+    }
+
+    subgraph cluster_installer {
+        label="Installer container (transient)"
+        style=dashed
+        color="#1e2a4a"
+        fontcolor="#8892a8"
+
+        installer [label="deps installer\ncurl · jq · python · graphviz" fillcolor="#121829"]
+        detect  [label="detect host\nWSL · memory · inotify · docker" fillcolor="#121829"]
+        fetch   [label="fetch + verify\nSHA256, pinned versions" fillcolor="#121829"]
+    }
+
+    upstream [label="upstream\nreleases / corporate mirror" fillcolor="#1a3a1a" fontcolor="#00c853" shape=octagon]
+    report   [label="report what it\nCANNOT do" fillcolor="#3a1a1a" fontcolor="#ffc107"]
+
+    docker  -> installer  [label="docker run"]
+    installer  -> detect
+    detect  -> fetch
+    fetch   -> upstream [label="pinned + checksummed" color="#00c853"]
+    fetch   -> bin      [label="install"]
+    detect  -> report   [style=dashed label="sudo / Windows-side steps" color="#ffc107"]
+
+    // The container is gone after this; nothing depends on it at run time.
+    installer -> gone [style=dotted label="exits"]
+    gone [label="(container discarded)" fillcolor="#0a0e17" fontcolor="#4a5568" color="#1e2a4a" style="filled,dashed"]
+}

rig/docs/graphs/01-install.svg

@@ -0,0 +1,128 @@
+<?xml version="1.0" encoding="UTF-8" standalone="no"?>
+<!DOCTYPE svg PUBLIC "-//W3C//DTD SVG 1.1//EN"
+ "http://www.w3.org/Graphics/SVG/1.1/DTD/svg11.dtd">
+<!-- Generated by graphviz version 14.1.2 (0)
+ -->
+<!-- Title: rig_install Pages: 1 -->
+<svg width="1145pt" height="287pt"
+ viewBox="0.00 0.00 1145.00 287.00" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink">
+<g id="graph0" class="graph" transform="scale(1 1) rotate(0) translate(4 283.29)">
+<title>rig_install</title>
+<polygon fill="#0a0e17" stroke="none" points="-4,4 -4,-283.29 1141.06,-283.29 1141.06,4 -4,4"/>
+<text xml:space="preserve" text-anchor="middle" x="568.53" y="-260.09" font-family="Helvetica,sans-Serif" font-size="16.00" fill="#0066ff">Installation — the only host prerequisite is Docker</text>
+<g id="clust1" class="cluster">
+<title>cluster_host</title>
+<polygon fill="#0a0e17" stroke="#1e2a4a" stroke-dasharray="5,2" points="898.49,-8 898.49,-190 1123.82,-190 1123.82,-8 898.49,-8"/>
+<text xml:space="preserve" text-anchor="middle" x="1011.15" y="-170.8" font-family="Helvetica,sans-Serif" font-size="16.00" fill="#8892a8">Your machine</text>
+</g>
+<g id="clust2" class="cluster">
+<title>cluster_installer</title>
+<polygon fill="#0a0e17" stroke="#1e2a4a" stroke-dasharray="5,2" points="8,-95 8,-175 745.5,-175 745.5,-95 8,-95"/>
+<text xml:space="preserve" text-anchor="middle" x="376.75" y="-155.8" font-family="Helvetica,sans-Serif" font-size="16.00" fill="#8892a8">Installer container (transient)</text>
+</g>
+<!-- docker -->
+<g id="node1" class="node">
+<title>docker</title>
+<polygon fill="#1a1a3a" stroke="#1e2a4a" points="1115.82,-31.9 1115.82,-54.1 1054.51,-69.79 967.8,-69.79 906.49,-54.1 906.49,-31.9 967.8,-16.21 1054.51,-16.21 1115.82,-31.9"/>
+<text xml:space="preserve" text-anchor="middle" x="1011.15" y="-46.05" font-family="Helvetica,sans-Serif" font-size="11.00" fill="#0066ff">Docker</text>
+<text xml:space="preserve" text-anchor="middle" x="1011.15" y="-32.55" font-family="Helvetica,sans-Serif" font-size="11.00" fill="#0066ff">(the one prerequisite)</text>
+</g>
+<!-- installer -->
+<g id="node3" class="node">
+<title>installer</title>
+<polygon fill="#121829" stroke="#1e2a4a" points="181.25,-139 16,-139 16,-103 181.25,-103 181.25,-139"/>
+<text xml:space="preserve" text-anchor="middle" x="98.62" y="-124.05" font-family="Helvetica,sans-Serif" font-size="11.00" fill="#e8eaf0">deps installer</text>
+<text xml:space="preserve" text-anchor="middle" x="98.62" y="-110.55" font-family="Helvetica,sans-Serif" font-size="11.00" fill="#e8eaf0">curl · jq · python · graphviz</text>
+</g>
+<!-- docker&#45;&gt;installer -->
+<g id="edge1" class="edge">
+<title>docker&#45;&gt;installer</title>
+<path fill="none" stroke="#4a5568" d="M906.12,-45.7C757.47,-50.51 475.98,-63.12 238.25,-94 223.38,-95.93 207.7,-98.48 192.45,-101.24"/>
+<polygon fill="#4a5568" stroke="#4a5568" points="192.13,-97.74 182.93,-103.01 193.4,-104.63 192.13,-97.74"/>
+<text xml:space="preserve" text-anchor="middle" x="506.62" y="-74.39" font-family="Helvetica,sans-Serif" font-size="9.00" fill="#8892a8">docker run</text>
+</g>
+<!-- bin -->
+<g id="node2" class="node">
+<title>bin</title>
+<path fill="#121829" stroke="#1e2a4a" d="M1069.03,-148.28C1069.03,-151.63 1043.09,-154.34 1011.15,-154.34 979.22,-154.34 953.28,-151.63 953.28,-148.28 953.28,-148.28 953.28,-93.72 953.28,-93.72 953.28,-90.37 979.22,-87.66 1011.15,-87.66 1043.09,-87.66 1069.03,-90.37 1069.03,-93.72 1069.03,-93.72 1069.03,-148.28 1069.03,-148.28"/>
+<path fill="none" stroke="#1e2a4a" d="M1069.03,-148.28C1069.03,-144.94 1043.09,-142.22 1011.15,-142.22 979.22,-142.22 953.28,-144.94 953.28,-148.28"/>
+<text xml:space="preserve" text-anchor="middle" x="1011.15" y="-130.8" font-family="Helvetica,sans-Serif" font-size="11.00" fill="#e8eaf0">~/.local/bin</text>
+<text xml:space="preserve" text-anchor="middle" x="1011.15" y="-117.3" font-family="Helvetica,sans-Serif" font-size="11.00" fill="#e8eaf0">kind · kubectl · tilt</text>
+<text xml:space="preserve" text-anchor="middle" x="1011.15" y="-103.8" font-family="Helvetica,sans-Serif" font-size="11.00" fill="#e8eaf0">jq</text>
+</g>
+<!-- detect -->
+<g id="node4" class="node">
+<title>detect</title>
+<polygon fill="#121829" stroke="#1e2a4a" points="429,-139 238.25,-139 238.25,-103 429,-103 429,-139"/>
+<text xml:space="preserve" text-anchor="middle" x="333.62" y="-124.05" font-family="Helvetica,sans-Serif" font-size="11.00" fill="#e8eaf0">detect host</text>
+<text xml:space="preserve" text-anchor="middle" x="333.62" y="-110.55" font-family="Helvetica,sans-Serif" font-size="11.00" fill="#e8eaf0">WSL · memory · inotify · docker</text>
+</g>
+<!-- installer&#45;&gt;detect -->
+<g id="edge2" class="edge">
+<title>installer&#45;&gt;detect</title>
+<path fill="none" stroke="#4a5568" d="M181.44,-121C195.97,-121 211.28,-121 226.37,-121"/>
+<polygon fill="#4a5568" stroke="#4a5568" points="226.33,-124.5 236.33,-121 226.33,-117.5 226.33,-124.5"/>
+</g>
+<!-- gone -->
+<g id="node8" class="node">
+<title>gone</title>
+<polygon fill="#0a0e17" stroke="#1e2a4a" stroke-dasharray="5,2" points="400.5,-47 266.75,-47 266.75,-11 400.5,-11 400.5,-47"/>
+<text xml:space="preserve" text-anchor="middle" x="333.62" y="-25.3" font-family="Helvetica,sans-Serif" font-size="11.00" fill="#4a5568">(container discarded)</text>
+</g>
+<!-- installer&#45;&gt;gone -->
+<g id="edge7" class="edge">
+<title>installer&#45;&gt;gone</title>
+<path fill="none" stroke="#4a5568" stroke-dasharray="1,5" d="M119.29,-102.62C138.26,-86 168.54,-62.29 199.25,-49.75 216.76,-42.6 236.49,-37.9 255.29,-34.81"/>
+<polygon fill="#4a5568" stroke="#4a5568" points="255.67,-38.29 265.04,-33.35 254.64,-31.37 255.67,-38.29"/>
+<text xml:space="preserve" text-anchor="middle" x="209.75" y="-52.45" font-family="Helvetica,sans-Serif" font-size="9.00" fill="#8892a8">exits</text>
+</g>
+<!-- fetch -->
+<g id="node5" class="node">
+<title>fetch</title>
+<polygon fill="#121829" stroke="#1e2a4a" points="737.5,-139 584.25,-139 584.25,-103 737.5,-103 737.5,-139"/>
+<text xml:space="preserve" text-anchor="middle" x="660.88" y="-124.05" font-family="Helvetica,sans-Serif" font-size="11.00" fill="#e8eaf0">fetch + verify</text>
+<text xml:space="preserve" text-anchor="middle" x="660.88" y="-110.55" font-family="Helvetica,sans-Serif" font-size="11.00" fill="#e8eaf0">SHA256, pinned versions</text>
+</g>
+<!-- detect&#45;&gt;fetch -->
+<g id="edge3" class="edge">
+<title>detect&#45;&gt;fetch</title>
+<path fill="none" stroke="#4a5568" d="M429.14,-121C474.43,-121 528.32,-121 572.63,-121"/>
+<polygon fill="#4a5568" stroke="#4a5568" points="572.46,-124.5 582.46,-121 572.46,-117.5 572.46,-124.5"/>
+</g>
+<!-- report -->
+<g id="node7" class="node">
+<title>report</title>
+<polygon fill="#3a1a1a" stroke="#1e2a4a" points="706.75,-219 615,-219 615,-183 706.75,-183 706.75,-219"/>
+<text xml:space="preserve" text-anchor="middle" x="660.88" y="-204.05" font-family="Helvetica,sans-Serif" font-size="11.00" fill="#ffc107">report what it</text>
+<text xml:space="preserve" text-anchor="middle" x="660.88" y="-190.55" font-family="Helvetica,sans-Serif" font-size="11.00" fill="#ffc107">CANNOT do</text>
+</g>
+<!-- detect&#45;&gt;report -->
+<g id="edge6" class="edge">
+<title>detect&#45;&gt;report</title>
+<path fill="none" stroke="#ffc107" stroke-dasharray="5,2" d="M409.65,-139.45C468.85,-154.02 550.13,-174.01 603.78,-187.2"/>
+<polygon fill="#ffc107" stroke="#ffc107" points="602.77,-190.56 613.32,-189.55 604.45,-183.76 602.77,-190.56"/>
+<text xml:space="preserve" text-anchor="middle" x="506.62" y="-180.06" font-family="Helvetica,sans-Serif" font-size="9.00" fill="#8892a8">sudo / Windows&#45;side steps</text>
+</g>
+<!-- fetch&#45;&gt;bin -->
+<g id="edge5" class="edge">
+<title>fetch&#45;&gt;bin</title>
+<path fill="none" stroke="#4a5568" d="M737.88,-121C798.58,-121 882.9,-121 941.56,-121"/>
+<polygon fill="#4a5568" stroke="#4a5568" points="941.43,-124.5 951.43,-121 941.43,-117.5 941.43,-124.5"/>
+<text xml:space="preserve" text-anchor="middle" x="811.38" y="-123.7" font-family="Helvetica,sans-Serif" font-size="9.00" fill="#8892a8">install</text>
+</g>
+<!-- upstream -->
+<g id="node6" class="node">
+<title>upstream</title>
+<polygon fill="#1a3a1a" stroke="#1e2a4a" points="1137.06,-213.9 1137.06,-236.1 1063.3,-251.79 959,-251.79 885.25,-236.1 885.25,-213.9 959,-198.21 1063.3,-198.21 1137.06,-213.9"/>
+<text xml:space="preserve" text-anchor="middle" x="1011.15" y="-228.05" font-family="Helvetica,sans-Serif" font-size="11.00" fill="#00c853">upstream</text>
+<text xml:space="preserve" text-anchor="middle" x="1011.15" y="-214.55" font-family="Helvetica,sans-Serif" font-size="11.00" fill="#00c853">releases / corporate mirror</text>
+</g>
+<!-- fetch&#45;&gt;upstream -->
+<g id="edge4" class="edge">
+<title>fetch&#45;&gt;upstream</title>
+<path fill="none" stroke="#00c853" d="M714.8,-139.5C759.85,-154.95 826.43,-177.11 885.25,-194 894.79,-196.74 904.78,-199.46 914.78,-202.09"/>
+<polygon fill="#00c853" stroke="#00c853" points="913.59,-205.4 924.15,-204.52 915.35,-198.62 913.59,-205.4"/>
+<text xml:space="preserve" text-anchor="middle" x="811.38" y="-191.36" font-family="Helvetica,sans-Serif" font-size="9.00" fill="#8892a8">pinned + checksummed</text>
+</g>
+</g>
+</svg>

rig/docs/graphs/02-environment.dot

@@ -0,0 +1,54 @@
+digraph rig_environment {
+    rankdir=TB
+    bgcolor="#0a0e17"
+    fontname="Helvetica"
+    node [fontname="Helvetica" fontsize=11 style=filled color="#1e2a4a" fontcolor="#e8eaf0" shape=box]
+    edge [fontname="Helvetica" fontsize=9 fontcolor="#8892a8" color="#4a5568"]
+
+    label="One environment per directory — copies never collide"
+    labelloc=t
+    fontsize=16
+    fontcolor="#0066ff"
+
+    dirname [label="directory name\ne.g. acmebank/" fillcolor="#1f6feb" fontcolor="#ffffff" shape=octagon]
+
+    subgraph cluster_derived {
+        label="Everything below is derived from it"
+        style=dashed
+        color="#1e2a4a"
+        fontcolor="#8892a8"
+
+        cname   [label="cluster name\nacmebank" fillcolor="#121829"]
+        ctx     [label="kubectl context\nkind-acmebank" fillcolor="#121829"]
+        img     [label="image tag\nacmebank-deps" fillcolor="#121829"]
+        ports   [label="port block\n21300–21309" fillcolor="#121829"]
+        reg     [label="registry container\nacmebank-registry" fillcolor="#121829"]
+    }
+
+    subgraph cluster_config {
+        label="Configuration — weakest first, later wins"
+        style=dashed
+        color="#1e2a4a"
+        fontcolor="#8892a8"
+
+        versions [label="versions.env\npinned toolchain" fillcolor="#121829"]
+        profile  [label="env.d/<profile>.env\noptional: addons · registry" fillcolor="#121829"]
+        localenv [label="ctrl/.env\nsecrets, overrides" fillcolor="#121829"]
+        shell    [label="the environment\nPROFILE=client make …" fillcolor="#1a3a1a" fontcolor="#00c853"]
+    }
+
+    dirname -> cname
+    dirname -> ctx
+    dirname -> img
+    dirname -> ports
+    dirname -> reg
+
+    versions -> profile  [label="overridden by"]
+    profile  -> localenv [label="overridden by"]
+    localenv -> shell    [label="overridden by" color="#00c853"]
+
+    cluster [label="kind cluster" fillcolor="#1a1a3a" fontcolor="#0066ff" shape=octagon]
+    cname -> cluster
+    ports -> cluster
+    shell -> cluster [style=dashed]
+}

rig/docs/graphs/02-environment.svg

@@ -0,0 +1,169 @@
+<?xml version="1.0" encoding="UTF-8" standalone="no"?>
+<!DOCTYPE svg PUBLIC "-//W3C//DTD SVG 1.1//EN"
+ "http://www.w3.org/Graphics/SVG/1.1/DTD/svg11.dtd">
+<!-- Generated by graphviz version 14.1.2 (0)
+ -->
+<!-- Title: rig_environment Pages: 1 -->
+<svg width="962pt" height="481pt"
+ viewBox="0.00 0.00 962.00 481.00" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink">
+<g id="graph0" class="graph" transform="scale(1 1) rotate(0) translate(4 476.83)">
+<title>rig_environment</title>
+<polygon fill="#0a0e17" stroke="none" points="-4,4 -4,-476.83 958,-476.83 958,4 -4,4"/>
+<text xml:space="preserve" text-anchor="middle" x="477" y="-453.63" font-family="Helvetica,sans-Serif" font-size="16.00" fill="#0066ff">One environment per directory — copies never collide</text>
+<g id="clust1" class="cluster">
+<title>cluster_derived</title>
+<polygon fill="#0a0e17" stroke="#1e2a4a" stroke-dasharray="5,2" points="8,-65 8,-144.5 596,-144.5 596,-65 8,-65"/>
+<text xml:space="preserve" text-anchor="middle" x="302" y="-125.3" font-family="Helvetica,sans-Serif" font-size="16.00" fill="#8892a8">Everything below is derived from it</text>
+</g>
+<g id="clust2" class="cluster">
+<title>cluster_config</title>
+<polygon fill="#0a0e17" stroke="#1e2a4a" stroke-dasharray="5,2" points="604,-65 604,-437.33 946,-437.33 946,-65 604,-65"/>
+<text xml:space="preserve" text-anchor="middle" x="775" y="-418.13" font-family="Helvetica,sans-Serif" font-size="16.00" fill="#8892a8">Configuration — weakest first, later wins</text>
+</g>
+<!-- dirname -->
+<g id="node1" class="node">
+<title>dirname</title>
+<polygon fill="#1f6feb" stroke="#1e2a4a" points="370.11,-197.44 370.11,-219.63 324.94,-235.33 261.06,-235.33 215.89,-219.63 215.89,-197.44 261.06,-181.75 324.94,-181.75 370.11,-197.44"/>
+<text xml:space="preserve" text-anchor="middle" x="293" y="-211.59" font-family="Helvetica,sans-Serif" font-size="11.00" fill="#ffffff">directory name</text>
+<text xml:space="preserve" text-anchor="middle" x="293" y="-198.09" font-family="Helvetica,sans-Serif" font-size="11.00" fill="#ffffff">e.g. acmebank/</text>
+</g>
+<!-- cname -->
+<g id="node2" class="node">
+<title>cname</title>
+<polygon fill="#121829" stroke="#1e2a4a" points="104,-109 16,-109 16,-73 104,-73 104,-109"/>
+<text xml:space="preserve" text-anchor="middle" x="60" y="-94.05" font-family="Helvetica,sans-Serif" font-size="11.00" fill="#e8eaf0">cluster name</text>
+<text xml:space="preserve" text-anchor="middle" x="60" y="-80.55" font-family="Helvetica,sans-Serif" font-size="11.00" fill="#e8eaf0">acmebank</text>
+</g>
+<!-- dirname&#45;&gt;cname -->
+<g id="edge1" class="edge">
+<title>dirname&#45;&gt;cname</title>
+<path fill="none" stroke="#4a5568" d="M228.68,-192.51C192.88,-182.36 148.52,-166.7 113,-144.5 101.4,-137.25 90.34,-127.04 81.36,-117.55"/>
+<polygon fill="#4a5568" stroke="#4a5568" points="84.07,-115.32 74.76,-110.26 78.88,-120.02 84.07,-115.32"/>
+</g>
+<!-- ctx -->
+<g id="node3" class="node">
+<title>ctx</title>
+<polygon fill="#121829" stroke="#1e2a4a" points="223.75,-109 122.25,-109 122.25,-73 223.75,-73 223.75,-109"/>
+<text xml:space="preserve" text-anchor="middle" x="173" y="-94.05" font-family="Helvetica,sans-Serif" font-size="11.00" fill="#e8eaf0">kubectl context</text>
+<text xml:space="preserve" text-anchor="middle" x="173" y="-80.55" font-family="Helvetica,sans-Serif" font-size="11.00" fill="#e8eaf0">kind&#45;acmebank</text>
+</g>
+<!-- dirname&#45;&gt;ctx -->
+<g id="edge2" class="edge">
+<title>dirname&#45;&gt;ctx</title>
+<path fill="none" stroke="#4a5568" d="M265.77,-181.32C245.77,-162.07 218.77,-136.06 199.05,-117.08"/>
+<polygon fill="#4a5568" stroke="#4a5568" points="201.55,-114.63 191.91,-110.21 196.69,-119.67 201.55,-114.63"/>
+</g>
+<!-- img -->
+<g id="node4" class="node">
+<title>img</title>
+<polygon fill="#121829" stroke="#1e2a4a" points="344.12,-109 241.88,-109 241.88,-73 344.12,-73 344.12,-109"/>
+<text xml:space="preserve" text-anchor="middle" x="293" y="-94.05" font-family="Helvetica,sans-Serif" font-size="11.00" fill="#e8eaf0">image tag</text>
+<text xml:space="preserve" text-anchor="middle" x="293" y="-80.55" font-family="Helvetica,sans-Serif" font-size="11.00" fill="#e8eaf0">acmebank&#45;deps</text>
+</g>
+<!-- dirname&#45;&gt;img -->
+<g id="edge3" class="edge">
+<title>dirname&#45;&gt;img</title>
+<path fill="none" stroke="#4a5568" d="M293,-181.32C293,-163.19 293,-139.07 293,-120.47"/>
+<polygon fill="#4a5568" stroke="#4a5568" points="296.5,-120.67 293,-110.67 289.5,-120.67 296.5,-120.67"/>
+</g>
+<!-- ports -->
+<g id="node5" class="node">
+<title>ports</title>
+<polygon fill="#121829" stroke="#1e2a4a" points="451.38,-109 362.62,-109 362.62,-73 451.38,-73 451.38,-109"/>
+<text xml:space="preserve" text-anchor="middle" x="407" y="-94.05" font-family="Helvetica,sans-Serif" font-size="11.00" fill="#e8eaf0">port block</text>
+<text xml:space="preserve" text-anchor="middle" x="407" y="-80.55" font-family="Helvetica,sans-Serif" font-size="11.00" fill="#e8eaf0">21300–21309</text>
+</g>
+<!-- dirname&#45;&gt;ports -->
+<g id="edge4" class="edge">
+<title>dirname&#45;&gt;ports</title>
+<path fill="none" stroke="#4a5568" d="M318.87,-181.32C337.78,-162.15 363.29,-136.3 382,-117.34"/>
+<polygon fill="#4a5568" stroke="#4a5568" points="384.47,-119.81 389,-110.24 379.49,-114.9 384.47,-119.81"/>
+</g>
+<!-- reg -->
+<g id="node6" class="node">
+<title>reg</title>
+<polygon fill="#121829" stroke="#1e2a4a" points="588.38,-109 469.62,-109 469.62,-73 588.38,-73 588.38,-109"/>
+<text xml:space="preserve" text-anchor="middle" x="529" y="-94.05" font-family="Helvetica,sans-Serif" font-size="11.00" fill="#e8eaf0">registry container</text>
+<text xml:space="preserve" text-anchor="middle" x="529" y="-80.55" font-family="Helvetica,sans-Serif" font-size="11.00" fill="#e8eaf0">acmebank&#45;registry</text>
+</g>
+<!-- dirname&#45;&gt;reg -->
+<g id="edge5" class="edge">
+<title>dirname&#45;&gt;reg</title>
+<path fill="none" stroke="#4a5568" d="M350.86,-190.3C383.87,-179.35 425.43,-163.64 460,-144.5 474.27,-136.6 488.83,-125.98 500.87,-116.36"/>
+<polygon fill="#4a5568" stroke="#4a5568" points="502.85,-119.26 508.36,-110.21 498.41,-113.84 502.85,-119.26"/>
+</g>
+<!-- cluster -->
+<g id="node11" class="node">
+<title>cluster</title>
+<polygon fill="#1a1a3a" stroke="#1e2a4a" points="460.81,-10.54 460.81,-25.46 429.29,-36 384.71,-36 353.19,-25.46 353.19,-10.54 384.71,0 429.29,0 460.81,-10.54"/>
+<text xml:space="preserve" text-anchor="middle" x="407" y="-14.3" font-family="Helvetica,sans-Serif" font-size="11.00" fill="#0066ff">kind cluster</text>
+</g>
+<!-- cname&#45;&gt;cluster -->
+<g id="edge9" class="edge">
+<title>cname&#45;&gt;cluster</title>
+<path fill="none" stroke="#4a5568" d="M93.35,-72.51C99.75,-69.67 106.48,-67 113,-65 189.55,-41.49 281.19,-29.58 341.58,-23.85"/>
+<polygon fill="#4a5568" stroke="#4a5568" points="341.71,-27.35 351.35,-22.96 341.07,-20.38 341.71,-27.35"/>
+</g>
+<!-- ports&#45;&gt;cluster -->
+<g id="edge10" class="edge">
+<title>ports&#45;&gt;cluster</title>
+<path fill="none" stroke="#4a5568" d="M407,-72.81C407,-65.23 407,-56.1 407,-47.54"/>
+<polygon fill="#4a5568" stroke="#4a5568" points="410.5,-47.54 407,-37.54 403.5,-47.54 410.5,-47.54"/>
+</g>
+<!-- versions -->
+<g id="node7" class="node">
+<title>versions</title>
+<polygon fill="#121829" stroke="#1e2a4a" points="750.38,-401.83 643.62,-401.83 643.62,-365.83 750.38,-365.83 750.38,-401.83"/>
+<text xml:space="preserve" text-anchor="middle" x="697" y="-386.88" font-family="Helvetica,sans-Serif" font-size="11.00" fill="#e8eaf0">versions.env</text>
+<text xml:space="preserve" text-anchor="middle" x="697" y="-373.38" font-family="Helvetica,sans-Serif" font-size="11.00" fill="#e8eaf0">pinned toolchain</text>
+</g>
+<!-- profile -->
+<g id="node8" class="node">
+<title>profile</title>
+<polygon fill="#121829" stroke="#1e2a4a" points="781.5,-318.58 612.5,-318.58 612.5,-282.58 781.5,-282.58 781.5,-318.58"/>
+<text xml:space="preserve" text-anchor="middle" x="697" y="-303.63" font-family="Helvetica,sans-Serif" font-size="11.00" fill="#e8eaf0">env.d/&lt;profile&gt;.env</text>
+<text xml:space="preserve" text-anchor="middle" x="697" y="-290.13" font-family="Helvetica,sans-Serif" font-size="11.00" fill="#e8eaf0">optional: addons · registry</text>
+</g>
+<!-- versions&#45;&gt;profile -->
+<g id="edge6" class="edge">
+<title>versions&#45;&gt;profile</title>
+<path fill="none" stroke="#4a5568" d="M697,-365.59C697,-355.32 697,-342.03 697,-330.21"/>
+<polygon fill="#4a5568" stroke="#4a5568" points="700.5,-330.58 697,-320.58 693.5,-330.58 700.5,-330.58"/>
+<text xml:space="preserve" text-anchor="middle" x="728.5" y="-339.28" font-family="Helvetica,sans-Serif" font-size="9.00" fill="#8892a8">overridden by</text>
+</g>
+<!-- localenv -->
+<g id="node9" class="node">
+<title>localenv</title>
+<polygon fill="#121829" stroke="#1e2a4a" points="752.88,-226.54 637.12,-226.54 637.12,-190.54 752.88,-190.54 752.88,-226.54"/>
+<text xml:space="preserve" text-anchor="middle" x="695" y="-211.59" font-family="Helvetica,sans-Serif" font-size="11.00" fill="#e8eaf0">ctrl/.env</text>
+<text xml:space="preserve" text-anchor="middle" x="695" y="-198.09" font-family="Helvetica,sans-Serif" font-size="11.00" fill="#e8eaf0">secrets, overrides</text>
+</g>
+<!-- profile&#45;&gt;localenv -->
+<g id="edge7" class="edge">
+<title>profile&#45;&gt;localenv</title>
+<path fill="none" stroke="#4a5568" d="M696.61,-282.22C696.34,-269.76 695.96,-252.69 695.64,-238.23"/>
+<polygon fill="#4a5568" stroke="#4a5568" points="699.14,-238.28 695.42,-228.36 692.14,-238.43 699.14,-238.28"/>
+<text xml:space="preserve" text-anchor="middle" x="727.68" y="-256.03" font-family="Helvetica,sans-Serif" font-size="9.00" fill="#8892a8">overridden by</text>
+</g>
+<!-- shell -->
+<g id="node10" class="node">
+<title>shell</title>
+<polygon fill="#1a3a1a" stroke="#1e2a4a" points="763.38,-109 614.62,-109 614.62,-73 763.38,-73 763.38,-109"/>
+<text xml:space="preserve" text-anchor="middle" x="689" y="-94.05" font-family="Helvetica,sans-Serif" font-size="11.00" fill="#00c853">the environment</text>
+<text xml:space="preserve" text-anchor="middle" x="689" y="-80.55" font-family="Helvetica,sans-Serif" font-size="11.00" fill="#00c853">PROFILE=client make …</text>
+</g>
+<!-- localenv&#45;&gt;shell -->
+<g id="edge8" class="edge">
+<title>localenv&#45;&gt;shell</title>
+<path fill="none" stroke="#00c853" d="M694.11,-190.49C693.16,-172.16 691.63,-142.72 690.49,-120.79"/>
+<polygon fill="#00c853" stroke="#00c853" points="694,-120.81 689.99,-111.01 687.01,-121.18 694,-120.81"/>
+<text xml:space="preserve" text-anchor="middle" x="724.21" y="-155.2" font-family="Helvetica,sans-Serif" font-size="9.00" fill="#8892a8">overridden by</text>
+</g>
+<!-- shell&#45;&gt;cluster -->
+<g id="edge11" class="edge">
+<title>shell&#45;&gt;cluster</title>
+<path fill="none" stroke="#4a5568" stroke-dasharray="5,2" d="M628.29,-72.6C618.83,-69.99 609.17,-67.38 600,-65 553.72,-52.99 500.89,-40.48 462.22,-31.54"/>
+<polygon fill="#4a5568" stroke="#4a5568" points="463.2,-28.18 452.67,-29.35 461.63,-35 463.2,-28.18"/>
+</g>
+</g>
+</svg>

rig/docs/graphs/03-architecture.dot

@@ -0,0 +1,56 @@
+// TODO: PLACEHOLDER — replace with the real estate topology.
+//
+// This is where the extracted platform diagrams land. The shape below is
+// illustrative only: it shows how a mocked dependency, a real service and a
+// remote system are meant to sit together, not what the system actually is.
+//
+// The intended end state is that this file stops being hand-written and is
+// generated from the running cluster, so the diagram becomes a report of what
+// exists rather than a drawing of what was once intended.
+digraph estate {
+    rankdir=LR
+    bgcolor="#0a0e17"
+    fontname="Helvetica"
+    node [fontname="Helvetica" fontsize=11 style=filled color="#1e2a4a" fontcolor="#e8eaf0" shape=box]
+    edge [fontname="Helvetica" fontsize=9 fontcolor="#8892a8" color="#4a5568"]
+
+    label="Estate topology — PLACEHOLDER"
+    labelloc=t
+    fontsize=16
+    fontcolor="#ffc107"
+
+    subgraph cluster_new {
+        label="New"
+        style=dashed
+        color="#1e2a4a"
+        fontcolor="#8892a8"
+
+        api     [label="service under work\n(real: built and hot-reloaded)" fillcolor="#1a3a1a" fontcolor="#00c853"]
+    }
+
+    subgraph cluster_core {
+        label="Core (mocked)"
+        style=dashed
+        color="#1e2a4a"
+        fontcolor="#8892a8"
+
+        svc_a   [label="upstream service\n(mock: canned responses)" fillcolor="#121829"]
+        db      [label="datastore\n(mock)" fillcolor="#121829" shape=cylinder]
+    }
+
+    subgraph cluster_legacy {
+        label="Legacy estate (mocked)"
+        style=dashed
+        color="#1e2a4a"
+        fontcolor="#8892a8"
+
+        batch   [label="batch drop\n(mock: writes files on a timer)" fillcolor="#121829"]
+    }
+
+    remote  [label="external system\n(remote: ExternalName,\nreachable only from a VDI)" fillcolor="#3a1a1a" fontcolor="#ffc107" shape=octagon]
+
+    api -> svc_a  [label="HTTP"]
+    api -> db     [label="query"]
+    api -> batch  [label="file handoff" style=dashed]
+    api -> remote [label="only when reachable" style=dashed color="#ffc107"]
+}

rig/docs/graphs/03-architecture.svg

@@ -0,0 +1,94 @@
+<?xml version="1.0" encoding="UTF-8" standalone="no"?>
+<!DOCTYPE svg PUBLIC "-//W3C//DTD SVG 1.1//EN"
+ "http://www.w3.org/Graphics/SVG/1.1/DTD/svg11.dtd">
+<!-- Generated by graphviz version 14.1.2 (0)
+ -->
+<!-- Title: estate Pages: 1 -->
+<svg width="579pt" height="362pt"
+ viewBox="0.00 0.00 579.00 362.00" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink">
+<g id="graph0" class="graph" transform="scale(1 1) rotate(0) translate(4 357.62)">
+<title>estate</title>
+<polygon fill="#0a0e17" stroke="none" points="-4,4 -4,-357.62 575.41,-357.62 575.41,4 -4,4"/>
+<text xml:space="preserve" text-anchor="middle" x="285.7" y="-334.42" font-family="Helvetica,sans-Serif" font-size="16.00" fill="#ffc107">Estate topology — PLACEHOLDER</text>
+<g id="clust1" class="cluster">
+<title>cluster_new</title>
+<polygon fill="#0a0e17" stroke="#1e2a4a" stroke-dasharray="5,2" points="8,-130.12 8,-210.12 199,-210.12 199,-130.12 8,-130.12"/>
+<text xml:space="preserve" text-anchor="middle" x="103.5" y="-190.92" font-family="Helvetica,sans-Serif" font-size="16.00" fill="#8892a8">New</text>
+</g>
+<g id="clust2" class="cluster">
+<title>cluster_core</title>
+<polygon fill="#0a0e17" stroke="#1e2a4a" stroke-dasharray="5,2" points="357.33,-172.12 357.33,-318.12 534.83,-318.12 534.83,-172.12 357.33,-172.12"/>
+<text xml:space="preserve" text-anchor="middle" x="446.08" y="-298.92" font-family="Helvetica,sans-Serif" font-size="16.00" fill="#8892a8">Core (mocked)</text>
+</g>
+<g id="clust3" class="cluster">
+<title>cluster_legacy</title>
+<polygon fill="#0a0e17" stroke="#1e2a4a" stroke-dasharray="5,2" points="341.83,-84.12 341.83,-164.12 551.33,-164.12 551.33,-84.12 341.83,-84.12"/>
+<text xml:space="preserve" text-anchor="middle" x="446.58" y="-144.92" font-family="Helvetica,sans-Serif" font-size="16.00" fill="#8892a8">Legacy estate (mocked)</text>
+</g>
+<!-- api -->
+<g id="node1" class="node">
+<title>api</title>
+<polygon fill="#1a3a1a" stroke="#1e2a4a" points="191,-174.12 16,-174.12 16,-138.12 191,-138.12 191,-174.12"/>
+<text xml:space="preserve" text-anchor="middle" x="103.5" y="-159.17" font-family="Helvetica,sans-Serif" font-size="11.00" fill="#00c853">service under work</text>
+<text xml:space="preserve" text-anchor="middle" x="103.5" y="-145.67" font-family="Helvetica,sans-Serif" font-size="11.00" fill="#00c853">(real: built and hot&#45;reloaded)</text>
+</g>
+<!-- svc_a -->
+<g id="node2" class="node">
+<title>svc_a</title>
+<polygon fill="#121829" stroke="#1e2a4a" points="526.83,-282.12 365.33,-282.12 365.33,-246.12 526.83,-246.12 526.83,-282.12"/>
+<text xml:space="preserve" text-anchor="middle" x="446.08" y="-267.17" font-family="Helvetica,sans-Serif" font-size="11.00" fill="#e8eaf0">upstream service</text>
+<text xml:space="preserve" text-anchor="middle" x="446.08" y="-253.67" font-family="Helvetica,sans-Serif" font-size="11.00" fill="#e8eaf0">(mock: canned responses)</text>
+</g>
+<!-- api&#45;&gt;svc_a -->
+<g id="edge1" class="edge">
+<title>api&#45;&gt;svc_a</title>
+<path fill="none" stroke="#4a5568" d="M149.07,-174.56C167.54,-182.07 189.23,-190.7 209,-198.12 258.25,-216.6 270.12,-222.85 320.75,-237.12 331.43,-240.13 342.71,-243 353.94,-245.67"/>
+<polygon fill="#4a5568" stroke="#4a5568" points="353.12,-249.07 363.66,-247.92 354.71,-242.25 353.12,-249.07"/>
+<text xml:space="preserve" text-anchor="middle" x="255.88" y="-234.24" font-family="Helvetica,sans-Serif" font-size="9.00" fill="#8892a8">HTTP</text>
+</g>
+<!-- db -->
+<g id="node3" class="node">
+<title>db</title>
+<path fill="#121829" stroke="#1e2a4a" d="M480.7,-223.81C480.7,-226.22 465.18,-228.18 446.08,-228.18 426.97,-228.18 411.45,-226.22 411.45,-223.81 411.45,-223.81 411.45,-184.43 411.45,-184.43 411.45,-182.02 426.97,-180.06 446.08,-180.06 465.18,-180.06 480.7,-182.02 480.7,-184.43 480.7,-184.43 480.7,-223.81 480.7,-223.81"/>
+<path fill="none" stroke="#1e2a4a" d="M480.7,-223.81C480.7,-221.39 465.18,-219.43 446.08,-219.43 426.97,-219.43 411.45,-221.39 411.45,-223.81"/>
+<text xml:space="preserve" text-anchor="middle" x="446.08" y="-207.17" font-family="Helvetica,sans-Serif" font-size="11.00" fill="#e8eaf0">datastore</text>
+<text xml:space="preserve" text-anchor="middle" x="446.08" y="-193.67" font-family="Helvetica,sans-Serif" font-size="11.00" fill="#e8eaf0">(mock)</text>
+</g>
+<!-- api&#45;&gt;db -->
+<g id="edge2" class="edge">
+<title>api&#45;&gt;db</title>
+<path fill="none" stroke="#4a5568" d="M191.32,-168.36C257.83,-177.73 346.91,-190.28 399.91,-197.75"/>
+<polygon fill="#4a5568" stroke="#4a5568" points="399.4,-201.22 409.79,-199.15 400.38,-194.29 399.4,-201.22"/>
+<text xml:space="preserve" text-anchor="middle" x="255.88" y="-185.69" font-family="Helvetica,sans-Serif" font-size="9.00" fill="#8892a8">query</text>
+</g>
+<!-- batch -->
+<g id="node4" class="node">
+<title>batch</title>
+<polygon fill="#121829" stroke="#1e2a4a" points="537.33,-128.12 354.83,-128.12 354.83,-92.12 537.33,-92.12 537.33,-128.12"/>
+<text xml:space="preserve" text-anchor="middle" x="446.08" y="-113.17" font-family="Helvetica,sans-Serif" font-size="11.00" fill="#e8eaf0">batch drop</text>
+<text xml:space="preserve" text-anchor="middle" x="446.08" y="-99.67" font-family="Helvetica,sans-Serif" font-size="11.00" fill="#e8eaf0">(mock: writes files on a timer)</text>
+</g>
+<!-- api&#45;&gt;batch -->
+<g id="edge3" class="edge">
+<title>api&#45;&gt;batch</title>
+<path fill="none" stroke="#4a5568" stroke-dasharray="5,2" d="M191.32,-144.39C237.67,-138.13 294.98,-130.39 343.4,-123.85"/>
+<polygon fill="#4a5568" stroke="#4a5568" points="343.61,-127.36 353.05,-122.55 342.67,-120.42 343.61,-127.36"/>
+<text xml:space="preserve" text-anchor="middle" x="255.88" y="-143.94" font-family="Helvetica,sans-Serif" font-size="9.00" fill="#8892a8">file handoff</text>
+</g>
+<!-- remote -->
+<g id="node5" class="node">
+<title>remote</title>
+<polygon fill="#3a1a1a" stroke="#1e2a4a" points="571.41,-21.74 571.41,-52.5 497.99,-74.24 394.17,-74.24 320.75,-52.5 320.75,-21.74 394.17,0 497.99,0 571.41,-21.74"/>
+<text xml:space="preserve" text-anchor="middle" x="446.08" y="-46.92" font-family="Helvetica,sans-Serif" font-size="11.00" fill="#ffc107">external system</text>
+<text xml:space="preserve" text-anchor="middle" x="446.08" y="-33.42" font-family="Helvetica,sans-Serif" font-size="11.00" fill="#ffc107">(remote: ExternalName,</text>
+<text xml:space="preserve" text-anchor="middle" x="446.08" y="-19.92" font-family="Helvetica,sans-Serif" font-size="11.00" fill="#ffc107">reachable only from a VDI)</text>
+</g>
+<!-- api&#45;&gt;remote -->
+<g id="edge4" class="edge">
+<title>api&#45;&gt;remote</title>
+<path fill="none" stroke="#ffc107" stroke-dasharray="5,2" d="M149.55,-137.68C167.9,-130.34 189.37,-121.97 209,-114.87 254.45,-98.43 305.32,-81.49 348.17,-67.64"/>
+<polygon fill="#ffc107" stroke="#ffc107" points="349,-71.05 357.44,-64.65 346.85,-64.39 349,-71.05"/>
+<text xml:space="preserve" text-anchor="middle" x="255.88" y="-117.57" font-family="Helvetica,sans-Serif" font-size="9.00" fill="#8892a8">only when reachable</text>
+</g>
+</g>
+</svg>

rig/docs/index.html

@@ -0,0 +1,580 @@
+<!DOCTYPE html>
+<html lang="en">
+<head>
+<meta charset="utf-8">
+<meta name="viewport" content="width=device-width, initial-scale=1">
+<title>rig — local environment installer</title>
+<style>
+  @import url('https://fonts.googleapis.com/css2?family=Inter:wght@400;500;600&family=JetBrains+Mono:wght@400;500&display=swap');
+
+  * { margin: 0; padding: 0; box-sizing: border-box; }
+
+  body {
+    background: #0a0e17;
+    color: #e8eaf0;
+    font-family: 'Inter', sans-serif;
+    line-height: 1.6;
+    height: 100vh;
+    overflow: hidden;
+    display: flex;
+    flex-direction: column;
+  }
+
+  header {
+    padding: 16px 24px;
+    border-bottom: 1px solid #1e2a4a;
+    display: flex;
+    align-items: baseline;
+    gap: 16px;
+    flex-shrink: 0;
+  }
+
+  header h1 {
+    font-family: 'JetBrains Mono', monospace;
+    font-size: 22px;
+    font-weight: 600;
+    letter-spacing: 3px;
+    color: #0066ff;
+  }
+
+  header .subtitle {
+    font-size: 13px;
+    color: #4a5568;
+    letter-spacing: 1px;
+    text-transform: uppercase;
+  }
+
+  .layout { display: flex; flex: 1; min-height: 0; }
+
+  nav {
+    display: flex;
+    flex-direction: column;
+    width: 200px;
+    flex-shrink: 0;
+    background: #121829;
+    border-right: 1px solid #1e2a4a;
+    padding: 8px 0;
+    overflow-y: auto;
+  }
+
+  nav a {
+    padding: 10px 20px;
+    font-family: 'JetBrains Mono', monospace;
+    font-size: 12px;
+    color: #8892a8;
+    text-decoration: none;
+    border-left: 2px solid transparent;
+    transition: all 0.15s;
+    cursor: pointer;
+  }
+
+  nav a:hover { color: #e8eaf0; background: #1a2340; }
+  nav a.active { color: #0066ff; border-left-color: #0066ff; background: #0d1a33; }
+
+  main { flex: 1; overflow: auto; padding: 32px 48px; }
+
+  .section { display: none; animation: fadeIn 0.2s ease; }
+  .section.active { display: block; }
+  @keyframes fadeIn { from { opacity: 0; } to { opacity: 1; } }
+
+  .section h2 {
+    font-family: 'JetBrains Mono', monospace;
+    font-size: 15px;
+    font-weight: 500;
+    color: #8892a8;
+    margin-bottom: 8px;
+    letter-spacing: 1px;
+    text-transform: uppercase;
+  }
+
+  .section > p.lede {
+    font-size: 13px;
+    color: #4a5568;
+    margin-bottom: 24px;
+    max-width: 800px;
+  }
+
+  .prose { max-width: 820px; }
+  .prose p { font-size: 14px; color: #b4bccf; line-height: 1.7; margin-bottom: 14px; }
+  .prose p b { color: #e8eaf0; }
+  .prose ul { margin: 0 0 16px 20px; }
+  .prose li { font-size: 14px; color: #b4bccf; margin-bottom: 6px; }
+
+  .prose h3 {
+    font-family: 'JetBrains Mono', monospace;
+    font-size: 13px;
+    text-transform: uppercase;
+    color: #e8eaf0;
+    margin: 32px 0 10px;
+    letter-spacing: 1px;
+  }
+
+  .prose code, pre code {
+    font-family: 'JetBrains Mono', monospace;
+    font-size: 12px;
+    color: #7ab0ff;
+    background: #121829;
+    padding: 1px 5px;
+    border-radius: 3px;
+  }
+
+  pre {
+    background: #121829;
+    border: 1px solid #1e2a4a;
+    padding: 16px;
+    overflow: auto;
+    margin-bottom: 16px;
+  }
+
+  pre code { background: none; padding: 0; }
+  pre .c { color: #4a5568; }
+  pre .k { color: #0066ff; }
+
+  .graph-container { margin: 16px 0; }
+  .graph-container img {
+    display: block;
+    max-width: 100%;
+    background: #0a0e17;
+    border: 1px solid #1e2a4a;
+    padding: 12px;
+  }
+
+  dl {
+    display: grid;
+    grid-template-columns: max-content 1fr;
+    gap: 10px 24px;
+    margin: 16px 0;
+    max-width: 820px;
+  }
+
+  dt {
+    font-family: 'JetBrains Mono', monospace;
+    color: #0066ff;
+    font-size: 13px;
+    padding-top: 2px;
+  }
+
+  dd { font-size: 14px; color: #b4bccf; line-height: 1.6; }
+
+  table { border-collapse: collapse; margin: 16px 0; max-width: 820px; }
+  th, td {
+    text-align: left;
+    padding: 7px 16px 7px 0;
+    font-size: 13px;
+    border-bottom: 1px solid #1e2a4a;
+    color: #b4bccf;
+  }
+  th {
+    font-family: 'JetBrains Mono', monospace;
+    font-size: 11px;
+    text-transform: uppercase;
+    color: #8892a8;
+    letter-spacing: 1px;
+  }
+  td code { white-space: nowrap; }
+
+  .note {
+    border-left: 2px solid #ffc107;
+    background: #17130a;
+    padding: 12px 16px;
+    margin: 16px 0;
+    max-width: 820px;
+  }
+  .note p { margin: 0; font-size: 13px; color: #b4bccf; }
+  .note b { color: #ffc107; }
+
+  .menu-toggle {
+    display: none;
+    background: transparent;
+    border: 1px solid #1e2a4a;
+    color: #8892a8;
+    padding: 6px 10px;
+    font-size: 14px;
+    cursor: pointer;
+    line-height: 1;
+    margin-left: auto;
+  }
+  .menu-toggle:hover { background: #1a2340; }
+
+  .nav-backdrop {
+    display: none;
+    position: absolute;
+    inset: 0;
+    background: rgba(0, 0, 0, 0.5);
+    z-index: 10;
+  }
+  .layout.nav-open .nav-backdrop { display: block; }
+
+  @media (max-width: 720px) {
+    header { padding: 10px 12px; gap: 8px; }
+    header h1 { font-size: 16px; letter-spacing: 1px; }
+    header .subtitle { display: none; }
+    .menu-toggle { display: inline-block; }
+    .layout { position: relative; }
+    nav {
+      position: absolute; left: 0; top: 0; bottom: 0;
+      width: 200px; z-index: 20;
+      transform: translateX(-100%);
+      transition: transform 0.2s ease;
+      box-shadow: 2px 0 8px rgba(0, 0, 0, 0.5);
+    }
+    .layout.nav-open nav { transform: translateX(0); }
+    main { padding: 16px; }
+    .section h2 { font-size: 13px; }
+    .prose p, .prose li { font-size: 13px; }
+  }
+</style>
+</head>
+<body>
+
+<header>
+  <h1>RIG</h1>
+  <span class="subtitle">local environment installer</span>
+  <button class="menu-toggle">&#9776;</button>
+</header>
+
+<div class="layout">
+  <div class="nav-backdrop"></div>
+  <nav>
+    <a href="#start">Start here</a>
+    <a href="#steps">The steps</a>
+    <a href="#install">Installation</a>
+    <a href="#environments">Environments</a>
+    <a href="#profiles">Profiles</a>
+    <a href="#registry">Registry</a>
+    <a href="#architecture">Architecture</a>
+    <a href="#troubleshooting">Troubleshooting</a>
+  </nav>
+
+  <main>
+
+  <section class="section" id="start">
+    <h2>Start here</h2>
+    <p class="lede">A runnable local model of a large, regulated estate — legacy and new side by side.</p>
+    <div class="prose">
+      <p>rig builds a disposable Kubernetes environment on your machine so you can
+      explore how a system fits together without needing access to any of it. Its
+      job is <b>onboarding and exploration</b>, not a production replica.</p>
+
+      <p>Most services in it are deliberately <b>not real</b>. What has to be faithful
+      is the topology — the names, the ports, the dependency order, who can reach whom,
+      and how it fails. The workloads themselves are noise. This is what makes the
+      whole estate fit on a laptop: a real 20-service platform will not fit even once
+      on 14&nbsp;GB, but mocks are about 30&nbsp;MB each, so three faithful copies do.</p>
+
+      <h3>The only prerequisite</h3>
+      <p><b>Docker.</b> No curl, no jq, no python, no apt repositories to configure.</p>
+<pre><code><span class="c"># then, in the environment directory:</span>
+make check     <span class="c"># is this machine ready? reports, never fixes</span>
+make deps        <span class="c"># install the pinned toolchain</span>
+make cluster up  <span class="c"># cluster + registry + addons; ports derive by themselves</span>
+</code></pre>
+      <p>Read <code>make check</code> before <code>make deps</code>. It never changes
+      anything — it prints what it found and, at the end, the steps it cannot perform
+      for you.</p>
+    </div>
+  </section>
+
+  <section class="section" id="steps">
+    <h2>The steps</h2>
+    <p class="lede">Start to finish, in order, with what each one actually does.</p>
+    <div class="prose">
+
+      <h3>1 &middot; make check</h3>
+      <p>Asks whether this machine is ready. It <b>changes nothing</b> — it
+      reports what it found and, at the end, the things only a human can do
+      (anything needing <code>sudo</code>, or a Windows-side restart). Read it
+      before installing anything; it is faster than discovering the same problems
+      one failure at a time.</p>
+<pre><code>make check</code></pre>
+
+      <h3>2 &middot; make deps</h3>
+      <p>Installs the pinned toolchain — only what is missing — and tells you
+      if its directory is not on PATH yet. Running it twice is safe.</p>
+<pre><code>make deps</code></pre>
+
+      <h3>3 &middot; make cluster up</h3>
+      <p>Builds the cluster, starts its registry and installs the profile's
+      addons — there is nothing else to run first. It prints what the profile
+      locks in <i>before</i> spending the time, because the kind config is
+      fixed at creation and cannot be changed afterwards.</p>
+      <p>Re-running is safe and, more importantly, <b>convergent</b>: if a first
+      attempt was interrupted before the CNI was installed, running it again
+      finishes the job rather than reporting "already exists" and leaving every
+      node permanently NotReady.</p>
+<pre><code>make cluster up                 <span class="c"># built-in defaults — no profile needed</span>
+make cluster up PROFILE=client  <span class="c"># after copying env.d/client.env.example: cached registry</span>
+make cluster reset              <span class="c"># destroy and rebuild — how an edited kind config takes effect</span>
+</code></pre>
+
+      <h3>4 &middot; make docs</h3>
+      <p>Serves this page from a throwaway container. Works with no cluster and
+      no toolchain, which is deliberate: these pages are the instructions for
+      building everything else, so they cannot depend on it.</p>
+<pre><code>make docs</code></pre>
+
+      <h3>Checking on things</h3>
+      <dl>
+        <dt>make cluster list</dt><dd>Every cluster on the machine, its memory cost and its port block. The usual reason a new one will not start is an old one you forgot about; <code>make cluster free</code> frees them without deleting.</dd>
+        <dt>make check</dt><dd>Short: host, toolchain, and whether this cluster fits, its ports, registry and addons. Details only appear when something needs attention; <code>make check all</code> prints every one.</dd>
+        <dt>make check mem</dt><dd>Memory in depth: what caps it, how far it really climbs, and on WSL the <code>.wslconfig</code> backup and restore.</dd>
+      </dl>
+
+      <h3>Running more than one</h3>
+      <p>Copy the directory, rename it, and run <code>make cluster up</code>. Cluster name,
+      context, image tags and the port block all follow the directory name, so
+      the second environment collides with nothing and neither one's teardown can
+      reach the other.</p>
+<pre><code>cp -r rig ../platform-v2 &amp;&amp; cd ../platform-v2
+make cluster up
+</code></pre>
+    </div>
+  </section>
+
+  <section class="section" id="install">
+    <h2>Installation</h2>
+    <p class="lede">A container installs onto the host and then gets out of the way.</p>
+    <div class="graph-container">
+      <a href="viewer.html?src=graphs/01-install.svg"><img src="graphs/01-install.svg" alt="Installation flow"></a>
+    </div>
+    <div class="prose">
+      <p>The installer is a container, not a shell script, for a specific reason: a
+      stock slim Debian has no <code>curl</code>, no <code>wget</code>, no
+      <code>jq</code>, no <code>python3</code> and <b>no CA bundle</b>. A shell
+      installer could not make a verified HTTPS request, let alone check one. The
+      container carries its own toolchain, so the host needs nothing but Docker.</p>
+
+      <p>The cluster never runs inside that container. Everything it installs —
+      kind, kubectl, tilt, jq — runs natively afterwards, so nothing pays a
+      container tax during daily work.</p>
+
+      <h3>Pinned and verified</h3>
+      <p>Every tool is a single binary fetched at a pinned version and checked
+      against a published SHA256. Node images are pinned <b>by digest</b>, so
+      upgrading kind cannot silently move your Kubernetes version.</p>
+
+      <h3>Not every machine should get cluster tooling</h3>
+      <p>A managed or corporate-issued machine — the kind that holds the access
+      you cannot get anywhere else — is not somewhere to install development
+      tools by default. So the toolchain comes in two tiers:</p>
+      <table>
+        <tr><th>tier</th><th>installs</th><th>for</th></tr>
+        <tr><td><code>core</code></td><td>kubectl, jq</td><td>talk to a cluster someone else runs</td></tr>
+        <tr><td><code>dev</code></td><td>+ kind, tilt</td><td>build clusters and hot-reload into them</td></tr>
+      </table>
+<pre><code>make deps core   <span class="c"># kubectl and jq only — nothing that creates a cluster</span>
+make deps        <span class="c"># dev, the default</span>
+</code></pre>
+      <p>Testing <i>in situ</i> on a managed machine is still possible — install
+      the <code>dev</code> tier deliberately when you need it. The point is that
+      it should be a decision rather than a side effect of installing.</p>
+      <p>The documentation itself needs neither tier: <code>make docs</code>
+      wants only Docker.</p>
+
+      <h3>Air-gapped</h3>
+<pre><code>make deps image full                       <span class="c"># bakes every binary into the image</span>
+docker save …-deps:full | gzip &gt; rig.tgz
+<span class="c"># carry that one file in, then:</span>
+docker load &lt; rig.tgz &amp;&amp; make cluster up PROFILE=offline   <span class="c"># from env.d/offline.env.example</span>
+</code></pre>
+    </div>
+  </section>
+
+  <section class="section" id="environments">
+    <h2>Environments</h2>
+    <p class="lede">One directory is one environment. Copy it, rename it, run it.</p>
+    <div class="graph-container">
+      <a href="viewer.html?src=graphs/02-environment.svg"><img src="graphs/02-environment.svg" alt="Environment derivation"></a>
+    </div>
+    <div class="prose">
+      <p>Running several versions of a system at once means several clusters on one
+      machine, not several machines. Everything that could collide is derived from
+      the directory name:</p>
+      <dl>
+        <dt>cluster + context</dt><dd><code>acmebank/</code> builds <code>acmebank</code> on <code>kind-acmebank</code>.</dd>
+        <dt>port block</dt><dd>Ten ports from a hash of the name, in the 20000+ range — clear of 80, 443, 3000, 5432, 8000 and 8080.</dd>
+        <dt>registry + images</dt><dd>Named after the environment, so two copies never share one.</dd>
+      </dl>
+      <p>Two copies therefore never collide, and neither one's
+      <code>make cluster down</code> can touch the other. <code>make check</code>
+      shows the block; <code>bash ctrl/ports.sh persist</code> freezes it into
+      <code>ctrl/.env</code> if you want it fixed rather than derived.</p>
+
+      <h3>Configuration layers</h3>
+      <p>Weakest first, later wins: built-in defaults → pinned versions → a
+      profile, if you name one → <code>ctrl/.env</code> → the environment. So
+      <code>make cluster up PROFILE=&lt;name&gt;</code> always beats every file.</p>
+    </div>
+  </section>
+
+  <section class="section" id="profiles">
+    <h2>Profiles</h2>
+    <p class="lede">Optional overlays — rig needs none.</p>
+    <div class="prose">
+      <table>
+        <tr><th>example</th><th>registry</th><th>for</th></tr>
+        <tr><td><i>none</i></td><td>local</td><td>the built-in defaults; no profile needed</td></tr>
+        <tr><td><code>client.env.example</code></td><td>mirror</td><td>images through a corporate registry</td></tr>
+        <tr><td><code>offline.env.example</code></td><td>local</td><td>air-gapped</td></tr>
+        <tr><td><code>data.env.example</code></td><td>local</td><td>postgres, redis, airflow</td></tr>
+      </table>
+
+      <div class="note"><p><b>The kind config cannot be re-applied.</b> Edit
+      <code>ctrl/k8s/kind-config.yaml.tpl</code>; it takes effect when the cluster is created. <code>cluster up</code> prints what it
+      locks in before spending the time, and <code>make cluster reset</code> is
+      the way out.</p></div>
+
+      <h3>LoadBalancer services</h3>
+      <p>Real manifests use <code>type: LoadBalancer</code>, because a real
+      cluster has one. On a bare local cluster those Services sit at
+      <code>EXTERNAL-IP &lt;pending&gt;</code> forever, with no error anywhere —
+      the deployment looks healthy and simply is not reachable.</p>
+      <p>The <code>metallb</code> addon fixes that, so the same manifests work
+      here as upstream and nothing has to be rewritten to NodePort. Its address
+      pool is derived from the cluster's Docker network at install time rather
+      than hardcoded, because Docker picks that subnet and it differs between
+      machines.</p>
+      <div class="note"><p><b>Where those addresses are reachable from.</b> The
+      pool lives on the Docker bridge, so LoadBalancer IPs work from the Linux
+      side — including from inside WSL. A browser on Windows has no route to
+      them. Use the ingress host ports for anything you need to open in a
+      browser.</p></div>
+
+      <h3>Networking</h3>
+      <p>The cluster uses kind's built-in networking, which <b>does</b> enforce
+      standard NetworkPolicy — verified against a no-policy control, not assumed.
+      The widely repeated claim that it accepts policies and silently ignores
+      them is out of date.</p>
+      <p>A pluggable CNI was tried and removed: it only added
+      GlobalNetworkPolicy, policy tiers and egress-CIDR rules, none of which are
+      needed yet, in exchange for a slower boot and one more thing that has to be
+      right at creation time. Worth revisiting only when a policy the built-in
+      cannot express actually comes up.</p>
+
+      <h3>Memory</h3>
+      <p>Every cluster is a running container tree whether you are using it or not.
+      <code>make cluster list</code> shows what exists and what it costs;
+      <code>make cluster free</code> stops the others without deleting them.</p>
+    </div>
+  </section>
+
+  <section class="section" id="registry">
+    <h2>Registry</h2>
+    <p class="lede">Local, cached, or straight to the corporate registry.</p>
+    <div class="prose">
+      <table>
+        <tr><th>mode</th><th>what it does</th></tr>
+        <tr><td><code>none</code></td><td>images are built straight into the node</td></tr>
+        <tr><td><code>local</code></td><td>a registry container wired into the cluster</td></tr>
+        <tr><td><code>mirror</code></td><td>that container as a <b>pull-through cache</b> of the corporate registry</td></tr>
+        <tr><td><code>remote</code></td><td>no local container; pull direct with an imagePullSecret</td></tr>
+      </table>
+      <p><code>mirror</code> is what a locked-down network actually looks like:
+      images originate from the corporate registry, you do not hammer it, and you
+      keep working when the connection drops.</p>
+
+      <div class="note"><p><b>The corporate CA will bite you.</b> A corporate
+      registry is usually behind an internal CA, and trust has to reach
+      <b>three</b> places: the host Docker daemon, every cluster node's containerd
+      (nodes do <i>not</i> inherit host trust), and any in-cluster client. Set
+      <code>REGISTRY_CA_FILE</code> and <code>make check</code> reports which is
+      still missing. The symptom otherwise is an opaque
+      <code>x509: certificate signed by unknown authority</code>.</p></div>
+
+      <p>Reachability also depends on where you are: if the registry is only
+      routable from a managed workspace, <code>mirror</code> and <code>remote</code>
+      will not resolve from a laptop at all. That is what <code>local</code> and
+      <code>offline</code> are for.</p>
+    </div>
+  </section>
+
+  <section class="section" id="architecture">
+    <h2>Architecture</h2>
+    <p class="lede">The estate being modelled.</p>
+    <div class="note"><p><b>TODO — placeholder.</b> The diagram below is
+    illustrative only: it shows how a mocked dependency, a service under active
+    work, and an unreachable remote system sit together. It is not the real
+    topology. Replace <code>docs/graphs/03-architecture.dot</code> with the
+    extracted platform diagrams, then run <code>make docs graphs</code>.</p></div>
+    <div class="graph-container">
+      <a href="viewer.html?src=graphs/03-architecture.svg"><img src="graphs/03-architecture.svg" alt="Estate topology (placeholder)"></a>
+    </div>
+    <div class="prose">
+      <p>Each component is one of three things, and switching between them should be
+      a one-line change rather than a rewrite:</p>
+      <dl>
+        <dt>real</dt><dd>Built from source and hot-reloaded. The thing you are actually working on — usually exactly one.</dd>
+        <dt>mock</dt><dd>A generic stub with canned responses. Everything you do not care about today.</dd>
+        <dt>remote</dt><dd>No pod at all: a Service of type ExternalName pointing at the real system. In-cluster DNS resolves identically, so callers never change.</dd>
+      </dl>
+      <p>The intended end state is that this diagram is <b>generated from the
+      running cluster</b> rather than drawn by hand — so it becomes a report of
+      what exists instead of a picture of what was once intended.</p>
+    </div>
+  </section>
+
+  <section class="section" id="troubleshooting">
+    <h2>Troubleshooting</h2>
+    <p class="lede">The failures that are hard to diagnose from their symptoms.</p>
+    <div class="prose">
+      <h3>Tilt stops noticing file changes</h3>
+      <p>Almost always <code>inotify</code> limits, and it fails <i>silently</i> —
+      nothing errors, changes just stop being picked up. Defaults on WSL are far too
+      low. <code>make check</code> reports it and prints the fix.</p>
+
+      <h3>Cluster creation dies halfway with a port error</h3>
+      <p>Docker reports <code>failed to bind host port … address already in use</code>
+      partway through creating the cluster. Run <code>make check</code> first — it
+      checks every port in this environment's block before anything is built.</p>
+
+      <h3>Every node stays NotReady</h3>
+      <p>Usually a cluster created with the default CNI disabled but the real CNI
+      never installed — typically an interrupted first run. Just run
+      <code>make cluster up</code> again: it converges rather than exiting early, and
+      will finish the missing steps.</p>
+
+      <h3>x509: certificate signed by unknown authority</h3>
+      <p>Corporate CA trust has not reached one of the three places it needs to be.
+      See <a href="#registry">Registry</a>.</p>
+
+      <h3>kubectl says the context does not exist</h3>
+      <p>The cluster can exist while its context does not — a reset or a switched
+      <code>KUBECONFIG</code> loses it. <code>make cluster up</code> detects this and
+      re-exports the context.</p>
+    </div>
+  </section>
+
+  </main>
+</div>
+
+<script>
+(function () {
+  var layout = document.querySelector('.layout');
+  var main = document.querySelector('main');
+
+  function syncActive() {
+    var hash = location.hash.slice(1) || 'start';
+    document.querySelectorAll('.section').forEach(function (s) { s.classList.remove('active'); });
+    document.querySelectorAll('nav a').forEach(function (a) { a.classList.remove('active'); });
+    var section = document.getElementById(hash);
+    if (section) section.classList.add('active');
+    var link = document.querySelector('nav a[href="#' + hash + '"]');
+    if (link) link.classList.add('active');
+    if (main) main.scrollTop = 0;
+    layout.classList.remove('nav-open');
+  }
+
+  window.addEventListener('hashchange', syncActive);
+  window.addEventListener('DOMContentLoaded', syncActive);
+  syncActive();
+
+  document.addEventListener('click', function (e) {
+    if (e.target.closest('.menu-toggle') || e.target.closest('.nav-backdrop')) {
+      layout.classList.toggle('nav-open');
+    }
+  });
+})();
+</script>
+
+</body>
+</html>

rig/docs/notes/Dockerfile.deps.md

@@ -0,0 +1,28 @@
+# ctrl/Dockerfile.deps
+
+## Purpose
+
+The toolchain installer image. It does NOT run the cluster — it installs a toolchain onto the host and gets out of the way.
+
+This exists to kill a bootstrap paradox: a plain bash installer needs curl, jq and sha256sum to already be present, and a minimal Debian has none of them. It carries its own toolchain, so the only host prerequisite is Docker.
+
+## Variants
+
+Two variants from one file:
+
+```
+docker build -f ctrl/Dockerfile.deps --target deps      -t <slug>-deps      .
+docker build -f ctrl/Dockerfile.deps --target deps-full -t <slug>-deps:full .
+```
+
+`deps-full` bakes every pinned binary in at build time. `docker save` it and you have the whole installer as one file to carry into an air-gapped network.
+
+## Packages
+
+ca-certificates + curl: fetch and verify. graphviz + python3: render diagrams and validate the arch model, so the host never needs an apt package.
+
+docker-cli, NOT docker.io: we only ever talk to the host's daemon through the mounted socket, and under `--no-install-recommends` the docker.io package ships docker-init without the actual `docker` binary.
+
+## The installer is the standalone kit
+
+The installer is the generated standalone kit, not deps.sh plus the files it reads. A kit is one file with its pins frozen in and is proven to run with nothing else from rig present — which is exactly what an image needs, and `make standalone` keeps it current. Pins are the same in every profile's kit.

rig/docs/notes/Dockerfile.example.md

@@ -0,0 +1,43 @@
+# ctrl/Dockerfile.example
+
+## Naming
+
+EXAMPLE — a component image. Copy, rename, replace. Named like the manifest it feeds and the resource it becomes:
+
+```
+ctrl/Dockerfile.api   ->  image <cluster>-api  ->  image: in k8s/base/api.yaml
+```
+
+That image string is the ONLY thing connecting the three. Nothing checks it; a typo shows up as a pod stuck in ImagePullBackOff pulling from the public index, which reads like a network problem and is not one.
+
+## COPY paths are repo-root relative (the one that catches everyone)
+
+The Tiltfile passes two paths with DIFFERENT bases, in adjacent arguments:
+
+```
+context='..'                 the REPO ROOT   (the Tiltfile is in ctrl/)
+dockerfile='Dockerfile.api'  relative to the TILTFILE, so ctrl/Dockerfile.api
+```
+
+So every COPY is resolved against the repo root, NOT against the Dockerfile's directory. A file sitting right beside it is still reached as `ctrl/`:
+
+```
+COPY ctrl/nginx.conf /etc/nginx/conf.d/default.conf     # correct
+COPY nginx.conf      /etc/nginx/conf.d/default.conf     # fails — no such file
+```
+
+Nothing warns you. The build just cannot find a file that is visibly there.
+
+## Dependency layer
+
+Dependencies first, in their own layer: they change far less often than the code, so a source edit does not reinstall them on every rebuild.
+
+## live_update
+
+The sync in the Tiltfile's `docker_build` must land where this image expects it:
+
+```
+live_update=[sync('../api', '/app/api')]
+```
+
+matches `COPY api/ ./api/` with `WORKDIR /app`. If the two disagree, Tilt syncs into a path nothing reads and the container keeps serving the built copy — edits appear to do nothing, with no error anywhere.

rig/docs/notes/Makefile.md

@@ -0,0 +1,56 @@
+# Makefile
+
+## Shape and config layers
+
+Thin control Makefile: few targets, and the subcommand is an argument rather than a second target: `make cluster down`, not `make cluster-down`.
+
+```
+make check          is this machine ready?        (never changes anything)
+make deps           install the toolchain
+make cluster up     cluster + registry + addons   (ports derive by themselves)
+make tilt / docs    work on it, read about it
+```
+
+The logic lives in the scripts, never here: `make cluster up` -> ctrl/cluster.sh up.
+
+Config layers, weakest first: built-in defaults < ctrl/versions.env (pinned toolchain) < ctrl/env.d/<profile>.env (optional) < ctrl/.env (local, gitignored) < the environment. So `make cluster up PROFILE=<name>` beats them all. See [config.md](config.md).
+
+Start with: `make check && make deps && make cluster up`
+
+## FACTS
+
+Identity follows the FOLDER NAME, so this directory can be copied elsewhere, renamed, and run as a separate environment with no edits. ctrl/.env overrides it when you want a name that differs from the directory.
+
+Asked once, of ctrl/ports.sh, which resolves it through lib/config.sh:
+
+```
+CLUSTER KUBECONTEXT HTTP HTTPS TILT REGISTRY MANIFESTS_DIR
+```
+
+Read positionally, so the order is a contract; ctrl/selftest.sh pins it.
+
+This used to be sed over ctrl/.env plus a slug computed in the Makefile, which is a SECOND derivation of values lib/config.sh already owns, and the two could disagree about the port after `ports.sh persist`, or about the name for any directory whose sanitised form differs from its raw one. One source now; the Tiltfile reads the same line.
+
+## CLUSTER / KCTX fallback
+
+The fallback matters: ports.sh sources config.sh, and if a profile or .env is broken it exits non-zero. Losing the cluster name would send --context to the wrong place, so fall back to the folder rather than to empty.
+
+## ARGS as .PHONY
+
+Words after the target become the script's subcommand; each gets a no-op rule so make does not treat them as goals. They are also marked PHONY, because some of those words name real directories. `cfg`, `ctrl`, `docs`, `gen` and `init` all exist at this level, and make considers a target that is an existing directory already built, so `make build ctrl` ran the build and then printed "make: 'ctrl' is up to date". The empty rule is not enough on its own; only .PHONY stops make consulting the filesystem.
+
+## tilt: --port guard
+
+--port is only passed when TILT_PORT resolved. It normally does, since FACTS asks ports.sh, but ports.sh can fail on a broken profile, and without the guard tilt receives a bare `--port` with no value and fails on the flag rather than on anything real. Tilt's own default is 10350, which is the number every project on this machine is trying not to collide on, so falling back to it silently is worse than not passing the flag.
+
+The Tiltfile asks ports.sh for the rest itself (cluster, registry and where the manifests are), so nothing needs passing here beyond what tilt's own flags require.
+
+## Aliases (kind-up, tilt-up, ...)
+
+Aliases, not a second implementation: each one calls the same script the canonical target does.
+
+The header argues for `make cluster down` over `make cluster-down`, and that still holds *within* the Makefile. But rig is one repo among several on the same machine, and every other one answers to kind-up / tilt-up. Muscle memory spanning six projects beats internal tidiness in one, so both spellings work.
+
+`cluster list` and `cluster free` have no hyphenated twin on purpose: they are rig's own, with nothing to be consistent with.
+
+Nothing outside the Makefile reads these names: the script is `ctrl/cluster.sh` and it takes the verb. So rename them, delete the ones you never type, or add the spelling your own projects use. An alias is two lines, and adding one costs nothing but a line in .PHONY.

rig/docs/notes/Tiltfile.md

@@ -0,0 +1,50 @@
+# ctrl/Tiltfile
+
+## Purpose and ownership
+
+This file ships with rig and works unedited: rig's own k8s/base already boots, so `make tilt` comes up with a running cluster and no editing at all. What it deploys is two EXAMPLES — replace them, and add your own images and resources in the two marked sections near the bottom. The catalogue after them has the blocks to paste, with the parts that are easy to get wrong already commented.
+
+rig supplies this file; it does not own it. Nothing in rig reads it back, and nothing here is regenerated — edit it freely, the way you would edit k8s/base/example-mock.yaml. rig owns the machine, you own the workload.
+
+## Nothing hardcoded to this directory
+
+Nothing in the Tiltfile is hardcoded to this directory, deliberately. Every other project here writes its slug into the Tiltfile five or six times by hand, so a copy of the project deploys into the original's cluster until someone remembers to edit all of them. A rig is meant to be copied and renamed, so it asks instead.
+
+## Who we are, and on which ports
+
+One question to rig, answered by ctrl/ports.sh, which resolves it through lib/config.sh — the same path every other rig script takes. That is the point: the cluster name is NOT the bare directory name (it is lowercased and reduced to a DNS label), and the ports honour anything pinned in ctrl/.env. Recomputing either of those here in Starlark is how two copies end up disagreeing about which cluster they are talking to.
+
+## Where the manifests live
+
+rig's own manifests are the default; point MANIFESTS_DIR in ctrl/.env at an overlay versioned somewhere else and rig stops owning them — see k8s/README.md. Real manifests usually change on a different cadence, by different people, under different review.
+
+The value is REPO-ROOT relative, because that is the root everything else in rig is expressed against. The Tiltfile runs in ctrl/, so prefix rather than assume: `'../' + 'ctrl/k8s/overlays/dev'` and `'../' + '../platform/overlays/dev'` are both right, where stripping a leading `ctrl/` would only fix the first.
+
+## Refuse to deploy into the wrong cluster
+
+Tilt snapshots the kubectl context at startup, BEFORE parsing this file, so it cannot be switched from here — only refused. `make tilt` passes --context for you; the guard catches a bare `tilt up` after some other project moved the global context.
+
+## Images go to this environment's own registry
+
+Fail closed. Tilt can usually infer the kind registry on its own, but "usually" is an inference, and when it misses, an unqualified name like `app` quietly means docker.io/library/app — a push to the public index instead of the registry two lines away. rig runs that registry; name it.
+
+## Catalogue
+
+The catalogue holds the shapes that recur across every project here, with the reasoning kept next to them. They are comments so the file runs as-is.
+
+## Catalogue: build an image
+
+The one genuinely non-obvious thing in the whole corpus: `context` and `dockerfile` are relative to DIFFERENT directories, in adjacent arguments, and nothing warns you.
+
+- `context=` the REPO ROOT — the Tiltfile is in ctrl/, so `'..'`
+- `dockerfile=` relative to THIS file — so `'Dockerfile.api'` is ctrl/Dockerfile.api
+
+Every COPY inside those Dockerfiles is therefore repo-root relative: a file sitting BESIDE the Dockerfile is still reached as `COPY ctrl/nginx.conf`.
+
+## Catalogue: reload the gateway when its config changes
+
+A Caddyfile arriving via configMapGenerator with disableNameSuffixHash does NOT roll the pod — the ConfigMap name never changes, so nothing tells the Deployment anything happened. Without the `gateway-reload` local_resource you edit the routes and watch nothing take effect.
+
+## Catalogue: reach a service directly, bypassing the gateway
+
+For a DB client or an admin UI. Prefer routing through the gateway: host ports are a single shared namespace across every project on this machine, which is why rig derives a block per environment in the first place. If you do need one, take it from this environment's own block rather than picking a number.

rig/docs/notes/addons.md

@@ -0,0 +1,73 @@
+# ctrl/addons.sh and ctrl/addons/*.sh
+
+## addons.sh
+
+Each addon is its own idempotent script in `ctrl/addons/` — adding one is adding
+a file, not editing a dispatcher.
+
+## airflow.sh
+
+Airflow needs a metadata database before it will start at all, so the script
+refuses rather than rolls a pod that will CrashLoopBackOff while the real problem
+(postgres missing from `ADDONS`) stays invisible in the logs.
+
+One pod on `standalone`, matching the compose cabinet: migration, admin user,
+scheduler and webserver in a single container. The official chart's five
+deployments model an installation; switching this on means wanting pipelines.
+
+## cert-manager.sh
+
+In a regulated estate almost everything is TLS, so the interesting question
+during onboarding is "does this service present a cert my client trusts" — not
+"can I reach a public ACME server". A local CA answers that offline, which is
+also what makes the air-gapped profile usable.
+
+## metallb.sh — why it matters
+
+Real manifests use LoadBalancer, because a real cluster has one. On a bare kind
+cluster those Services sit at `EXTERNAL-IP <pending>` forever with no error
+anywhere — the deployment looks fine and simply is not reachable. Without MetalLB,
+every such Service has to be edited to NodePort, which means the local manifests
+stop matching the ones being modelled.
+
+The address pool is derived from the kind Docker network at install time, not
+hardcoded: Docker picks that subnet, it differs between machines, and a pool
+outside it is silently unroutable.
+
+## metallb.sh — waiting for the controller
+
+`kubectl wait` on a selector errors out immediately when nothing matches yet, and
+right after apply the ReplicaSet has not created the pod — so it loses a race it
+looks like it should win. `rollout status` waits for the Deployment itself and
+handles the not-yet-created case.
+
+## metrics-server.sh
+
+kind nodes serve kubelet metrics over a self-signed cert, so the standard
+manifest never becomes ready without `--kubelet-insecure-tls`. That is fine here
+(it is a local cluster) and is the single most common reason metrics-server sits
+at 0/1 on kind.
+
+## postgres.sh — cabinets
+
+A cabinet is a public service dropped into the environment as-is — the upstream
+image, unmodified, reachable at a known address. `postgres.sh` is the cluster
+half of it; the compose half is a `service.yml` beside a `cabinet.json`. The
+declaration is made once and both paths read it, so nothing is remembered twice.
+
+## postgres.sh — plain manifests, one replica
+
+Plain manifests rather than a helm chart, matching the other addons: a chart repo
+is a network dependency, and the offline example profile exists precisely so
+there is a path with none. The image is pinned in `ctrl/versions.env` and can be
+preloaded into a local registry like every other image here.
+
+One replica on a PVC. This models a dependency for local work, not a
+highly-available database, and pretending otherwise on a kind node would be a
+more elaborate lie rather than a more useful one.
+
+## redis.sh
+
+Cache, and the broker anything queue-shaped runs on. No persistence: a broker
+that loses its queue on restart is the honest local model, and a PVC here buys
+nothing but a volume to clean up.

rig/docs/notes/check.md

@@ -0,0 +1,44 @@
+# ctrl/check.sh
+
+## Purpose
+
+Readiness check: is this machine ready to run rig?
+
+It reports and instructs; it never silently fixes anything. Everything it finds is either already fine, or something a human has to decide on.
+
+Runs ctrl/deps.sh host detection in a container when Docker is the only thing installed, or directly when the toolchain is already present. Then adds the checks that need this repo's config: profile sanity, CA trust, port clashes.
+
+## memory
+
+A profile on a box that is already full is the most common first failure, and it presents as pods stuck Pending rather than anything that says "memory". The check warns; it never blocks. Whether to try anyway is the user's call.
+
+## mb_of
+
+MEMINFO and OVERCOMMIT_FILE exist only so the tight and does-not-fit branches can be exercised against another machine's real numbers; in normal use they are the kernel's own files.
+
+## NODE_MB
+
+NODE_MB (what one node costs) comes from load_config (lib/config.sh), where its measurement is recorded. It lives there, not here, because the memory tool and every standalone kit need the same number: a copy of it is how rigmini.sh came to say 2 GB per node long after rig had measured 800 MB.
+
+## container_mb
+
+Every running container's working set in MB, tagged with the kind cluster it belongs to ('-' when it is not kind). docker stats reports usage minus page cache, which is what actually competes: cache is handed back under pressure. Counting only kind would hide the usual culprit on a managed workspace, where the memory is held by other containers entirely.
+
+## ours_mb / still_mb
+
+Once this environment's own cluster is running, its real footprint is already out of MemAvailable and the per-node estimate stops being relevant. Subtracting the measurement from the estimate would count the same memory twice, and a running cluster that happens to sit under 800 MB would still "need" the gap.
+
+## ports: our own cluster
+
+A port held by THIS environment's own cluster is not a clash; it is the thing working. Reporting it as a problem every time the cluster is up would train people to ignore this section, which is the opposite of the point.
+
+The ports are extracted with a second grep rather than `tr -d ':->'`: in tr, ':->' is the character RANGE ':' to '>', which does not contain '-', so the trailing dash survives and nothing ever matches.
+
+## Compact by default
+
+`make check` prints one line per question — host, toolchain, and for this rig: cluster, memory,
+ports, registry, addons — and adds detail only where something needs attention (`!` lines, the
+"held elsewhere" list when memory is tight, the clashing port). `make check all` prints every fact,
+as the full report did before 2026-09-17. `deps.sh detect all` is the same switch for the host part,
+so the standalone `rigdeps.sh detect` is short too. Changed because the long report buried the few
+lines that mattered.

rig/docs/notes/cluster.md

@@ -0,0 +1,15 @@
+# ctrl/cluster.sh
+
+## Why list and free live here
+
+`list` and `free` live in `cluster.sh` rather than in a separate script because a
+near-identical second name (cluster / clusters) is a trap — you reach for one and
+get the other. One target, one file, unambiguous subcommands.
+
+## Idempotent means convergent
+
+"Idempotent" here means convergent, not "exits early if the cluster exists".
+That distinction matters: an interrupted first run can leave a cluster created
+but not finished, and returning early on the re-run would strand it there. The
+create step is conditional; every step after it always runs, and each one is
+individually idempotent.

rig/docs/notes/config.md

@@ -0,0 +1,99 @@
+# ctrl/lib/config.sh
+
+## Purpose and precedence
+
+The ecosystem convention is that scripts are standalone with no shared log library, and that still holds. This file is not a logging lib; it is the single definition of how the config layers compose, which every script has to agree on exactly. Precedence, weakest first:
+
+```
+built-in defaults      in load_config; fill only what nothing else set
+ctrl/versions.env      pinned toolchain + image digests   (committed)
+ctrl/env.d/<profile>   addons, registry (OPTIONAL, examples ship as *.env.example)
+ctrl/.env              machine-local values and secrets   (gitignored)
+the caller's env       `make cluster up PROFILE=<name>`   (always wins)
+```
+
+That last rule is why this is more than a few `source` lines: .env sets PROFILE, so without snapshotting it would silently override the PROFILE the user just typed on the command line.
+
+Run from ctrl/.
+
+## CONFIG_OVERRIDABLE
+
+Values a user can reasonably override per-invocation. Anything set in the environment when load_config runs is restored after the files are read. NODES is deliberately NOT here: it is read back out of the kind config, so the file is the one place that decides it.
+
+REGISTRY_PORT and MANIFESTS_DIR were missing here while ctrl/.env set them, so the caller's env silently LOST to the file for those two, breaking the one precedence rule the header states. Both are now listed; the other twelve are unchanged.
+
+## default_cluster_name
+
+The containing folder's name, reduced to something kind accepts as a cluster name (a DNS label: lowercase alphanumerics and dashes). Run from ctrl/, so the repo root is the parent.
+
+## derive_port_base
+
+Base of this environment's 10-port block. cksum is used rather than $RANDOM or bash hashing because it is POSIX and returns the same value on every machine, which is what makes the block reproducible instead of merely unique.
+
+## load_config: RIG_PORTABLE
+
+RIG_PORTABLE skips the machine-local layer. config_snapshot sets it, so a generated standalone kit never carries this machine's .env, which holds local values and, by its own description, secrets.
+
+## load_config: profiles are optional
+
+A profile is an optional overlay, never a prerequisite. rig assumes no configuration: with no profile named, or no env.d/ at all, it runs on the built-in defaults. What IS an error is naming a profile that does not exist, because a typo must not quietly fall back to something else.
+
+## load_config: identity follows the folder
+
+Identity follows the FOLDER, so copying this directory somewhere else and renaming it yields a distinct environment with no further edits. Without this, two copies would share one cluster and `make cluster down` in either would destroy the other's.
+
+## load_config: host ports
+
+Host ports are a single shared namespace, so unlike the cluster name they cannot just follow the directory; they have to be spread out. Anything already set (ctrl/.env, a profile, the command line) wins; only the gaps are filled. See [ports.md](ports.md) for the reasoning.
+
+## load_config: MANIFESTS_DIR
+
+Where the workload's manifests live, repo-root relative. Defaulted here so it is always resolved rather than sometimes-set: it is the seam that lets the real manifests be versioned away from the installer, and a consumer should not have to know whether anyone filled it in. See k8s/README.md.
+
+## load_config: NODE_MB
+
+What one node costs, measured rather than guessed. On 2026-09-11 a minimal control-plane node ran at 620 MiB idle and ~728 MiB with a small mock, plus 16 MiB for the local registry: ~745 MiB of working set. 800 rounds that up, and agrees with the 800 MB observed independently on a larger rig. Worker nodes carry no etcd or apiserver and are lighter, so for a multi-node shape this errs high. It is the cluster alone: whatever you deploy comes on top.
+
+It is set here rather than in check.sh because the memory tool and every standalone kit need the same figure.
+
+## render_kind_config
+
+Renders the kind config to stdout. sed rather than envsubst: envsubst is gettext-base, absent from a minimal Debian, and Docker is meant to be the only prerequisite. The variable list is explicit so a template cannot quietly start depending on something the caller does not set.
+
+hostPath entries are resolved by the HOST dockerd, so HOST_WORKDIR must stay a host path even when this runs inside the installer container.
+
+## What a standalone kit needs to know
+
+The kit generator (ctrl/standalone.sh) asks these questions so that it never has to know how configuration is stored. Where profiles live, which files are layered and what is derived are config.sh's business and can change freely; the generator only calls these functions.
+
+## config_profiles
+
+Every configuration rig can be run as, one per line: each profile file, or, when there are none, `default`, the built-in configuration load_config uses when no profile is named. Never empty, because rig never needs a profile.
+
+## config_snapshot
+
+The resolved configuration, as `declare -p` lines: exactly what load_config leaves behind, minus the machine-local layer. A kit freezes this in place of load_config, so it carries rig's decisions and not this machine's secrets.
+
+```
+config_snapshot <profile>   that profile, as any machine would resolve it
+config_snapshot --current   what THIS machine runs: every overridable key as
+                            resolved here, handed back in as if typed on the
+                            command line, over the same portable resolution.
+                            Values derived from those choices follow them;
+                            anything else the local layer set (credentials)
+                            is not carried. config_left_out names it.
+```
+
+Found by difference, not by a list: whatever load_config sets today, it sets. A list here would be one more place to forget a variable.
+
+## config_left_out
+
+What an export of this machine's configuration does NOT carry, by name only: keys the machine-local layer sets that are not choices a caller may override. They are this machine's own (registry and mirror credentials, mostly), so the target has to be told to supply them. Values are never printed.
+
+## config_freeze
+
+A replacement for load_config with a resolution frozen in (a profile, or --current; see config_snapshot), printed as a function definition for a standalone kit to carry. The generator embeds whatever this prints and interprets none of it, so what "frozen" means stays rig's decision.
+
+It keeps load_config's one stated rule: the caller's env wins for anything in CONFIG_OVERRIDABLE. A kit therefore behaves like rig (`OUT_BIN=... rigdeps.sh` still works) rather than like a copy with everything pinned.
+
+What freezing does give up, knowingly: values DERIVED from an overridable one are fixed at generation. Override CLUSTER and the ports stay the ones derived for the original name. Re-deriving would mean carrying the layering itself, which is exactly what a kit exists not to need.

rig/docs/notes/deps.md

@@ -0,0 +1,158 @@
+# ctrl/deps.sh
+
+## Purpose and safety
+
+Toolchain installer: detect the host, install a pinned toolchain onto it, then report what it could not do.
+
+It never runs the cluster, never uses sudo or apt, and writes only into `$OUT_BIN` (default `~/.local/bin`). Everything that would touch the host proper — systemd, inotify limits, `.wslconfig`, docker group — is REPORTED for a human to decide on, never performed. That is what makes it safe to run on a machine that already has a working setup.
+
+## Usage
+
+Normally via `make deps`, or directly:
+
+```
+deps.sh detect            # report host facts only, change nothing
+deps.sh list              # the pinned versions
+deps.sh verify [core|dev] # run what is installed and see if it works
+deps.sh fetch [core|dev] [--to DIR]   # download + verify into DIR
+deps.sh install [core|dev]            # detect, fetch, install, report
+```
+
+Tiers: `core` is kubectl + jq (talk to a cluster); `dev` adds kind and tilt. Default is dev.
+
+## Container vs bare host
+
+Runs both inside the installer container and bare on a host. Inside the container, host files are read through `$HOST_ROOT` (mount `/` as `:ro`); bare, it falls back to `/`.
+
+Host FILES (`/etc/...`, `/mnt/c/...`) must be read through the mount. Kernel-level facts (kernel version, meminfo, inotify) are shared with the container, so the container's own view is already the host's.
+
+## INVOKED_FROM
+
+Keep the caller's cwd so a relative `--to` resolves where the user expects, not against `ctrl/` once we've moved.
+
+## load_config
+
+Pins arrive through `load_config` like every other setting, not by sourcing `versions.env` here. That is what lets `make standalone` freeze them into a one-file installer: configuration has exactly one way in.
+
+## mb_of
+
+A `/proc/meminfo` field in MB, 0 if the field is absent. `MEMINFO` exists so the tight and does-not-fit branches can be exercised against a real machine's numbers from somewhere else; in normal use it is always `/proc/meminfo`.
+
+## require_amd64
+
+The pins are amd64. Rather than download something that cannot execute and let it fail as "cannot execute binary file: Exec format error", say so here and hand over the commands that produce the right checksums.
+
+## pkg_install_cmd
+
+This never runs a package manager. It names one so the reported action is something you can paste, on the distro you are actually on — an apt line on Amazon Linux 2 is a wrong answer dressed up as help.
+
+## require_linux
+
+Windows outside WSL — Git Bash, MSYS, Cygwin — looks close enough to work and then fails in a pile of confusing ways: no /proc, no docker socket, none of the tooling. Detectable, so name it instead.
+
+## detect: memory
+
+In MB. Whole gigabytes lose nearly half a GB on exactly the machines where it matters: 1874 MB available used to print as "1 GB". Facts only — whether that is enough depends on the profile, which `check.sh` knows and this does not.
+
+## detect: overcommit
+
+How the kernel answers an allocation it cannot really satisfy. With 1 it always says yes and settles up later with the OOM killer, so a cluster that starts cleanly can still lose processes afterwards.
+
+## detect_wsl: systemd
+
+systemd is off by default in WSL, and the ingress/DNS paths that use a host service need it. Enabling it requires a Windows-side restart, which cannot be issued from inside the distro.
+
+## watch_hostile_fs
+
+Not a path check: `/mnt` is an ordinary mount point and an ext4 disk mounted there is perfectly fine. What matters is the filesystem. The Windows drives arrive as 9p (WSL2) or drvfs (WSL1); network and fuse mounts behave the same way. None of them deliver inotify events, so anything watching files goes quiet without saying why.
+
+## detect_libc
+
+tilt is the one binary here that needs a recent glibc. MEASURED, not guessed: tilt 0.37.6 on Amazon Linux 2 (glibc 2.26) fails with
+
+```
+/lib64/libc.so.6: version `GLIBC_2.34' not found (required by .../tilt)
+```
+
+which names a symbol rather than the problem. Amazon Linux 2 is a stock WorkSpaces bundle, so this is the likely case, not an exotic one. Report the version now; `verify` catches the actual failure after installing.
+
+## detect_prereqs
+
+What this script needs to do its own job. Reported here so `detect` answers "will install work?" instead of leaving you to find out one download in. Amazon Linux 2 ships without tar, which is exactly the surprise this catches.
+
+## detect_docker
+
+Reachability of the daemon is the real question, and the CLI is only how we ask it. When this runs inside the installer container, Docker necessarily exists on the host — otherwise nothing would be executing — so a missing CLI in there is an installer packaging bug, not a host problem.
+
+The kind-node count check must be an `if`, not `[ ] && echo`: as the last statement in the function the latter returns 1 when the count is zero, and `set -e` then kills the caller. That is the fresh-machine case — no clusters yet — so the bug only ever shows up where it does most harm.
+
+## fetch_tgz: --no-same-owner
+
+Extracting as root would otherwise restore the uid/gid baked into the archive (some ship as uid 1001), leaving a binary the host user does not own.
+
+## fix_ownership
+
+The installer runs as root so it can reach the docker socket, which means everything it writes into a mounted volume lands root-owned and unusable from the host. Hand it back to whoever owns the mount point (the host user created that directory before mounting it).
+
+kind writes the kubeconfig as root too; `fetch` hands that back as well when it's a mounted host directory rather than container-local state.
+
+## Tiers (CORE_TOOLS, DEV_TOOLS)
+
+Two tiers, because not every machine should get cluster tooling.
+
+- `core` — kubectl, jq: talk to a cluster someone else runs. Nothing that creates one. Appropriate on a managed or corporate-issued machine where development tools are not wanted by default.
+- `dev` — core plus kind and tilt: build clusters and hot-reload into them.
+
+The split exists because "install the toolchain" is not one decision: on a managed workspace the right answer is kubectl and nothing else.
+
+No helm: every addon installs with `kubectl apply -f <url>`, so nothing here has ever invoked it. Add it back the day something actually needs a chart.
+
+ctlptl is `dev` rather than `core` for the same reason kind is: core is "talk to a cluster someone else runs", and ctlptl builds them. It earns its place because it is what wires a cluster to a local registry — without one, an unqualified image name resolves to `docker.io/library/<name>` and there is nothing structural stopping a push there.
+
+docker-compose is `dev` for the same reason, and is here because the distro docker packages ship the daemon and CLI but frequently not the compose plugin — so `docker compose up` fails with "unknown command" on an otherwise working Docker, and nothing about that message names the missing piece.
+
+## What is already on this machine (pin_of)
+
+A tool already on PATH at its pinned version is left where it is. Without this, install downloads a second copy into `OUT_BIN` and then reports the first one as shadowed — noise, and wrong, when both are the same version. That is the normal state of any machine someone set up by hand, whatever directory they happened to choose.
+
+## reported_version
+
+Each tool spells the version question differently, and kubectl has to be told `--client` or it goes looking for a server to ask.
+
+## version_matches
+
+Matched as a whole version token, so 0.37.6 never matches 10.37.60, with the leading v optional either side: kind says v0.32.0, jq says jq-1.8.2, and tilt says v0.37.6 against a pin of 0.37.6.
+
+Bash's own regex rather than grep, deliberately. grep is not the same program on every machine — some builds reject patterns that others accept — and a failed grep inside a count reads exactly like a zero.
+
+## want / DEPS_ONLY
+
+`DEPS_ONLY` narrows a fetch to the tools it names. Unset means the whole tier, which is what an explicit `deps.sh fetch` always gets: "download these into DIR" must not quietly skip something because this machine happens to have it. Only `install()` sets it, to what `detect_toolchain` found missing or mismatched.
+
+## detect_toolchain: compose
+
+compose is the one tool that is normally NOT a binary on PATH. It is a docker CLI plugin, so a machine where `docker compose` works perfectly has no `docker-compose` to find — and probing only PATH would report it missing and re-download a copy that is already there. That is the exact noise the version-aware skip exists to prevent, so ask docker instead.
+
+## verify_tools
+
+Installing into a directory that sits early in PATH silently replaces whatever the machine was already using — which on a shared or client machine can break unrelated work (kubectl more than one minor away from a cluster is the common one). Say so; never decide it for them.
+
+Downloading a verified binary proves it is the right file, not that this machine can run it. On an old distro tilt fails here, with a linker error about a missing symbol, and finding that out now beats finding out during a first cluster build.
+
+Output is not piped into `head`. With `pipefail` set, a tool that prints more than one line gets SIGPIPE when head closes the pipe, and the pipeline reports 141 — so a working kubectl was announced as "does not run here", with its own correct version string as the evidence. The first line is taken afterwards, from the string.
+
+## install_compose_plugin
+
+A copy in `OUT_BIN` only gives you `docker-compose`. That hyphenated form is the retired v1 spelling; every compose file written in the last few years assumes `docker compose`, which resolves plugins BY NAME out of a plugin directory. So the binary is fetched like any other and then linked, in your own home — no root, and nothing outside it.
+
+If something else already owns that name — docker-desktop and some distro packages install a real file there — overwriting it would take the plugin away from whatever put it there, so say so and let the user decide.
+
+## install
+
+The plugin is linked only when compose was one of the things fetched: linking a binary that is already satisfied elsewhere on PATH would point the plugin at a copy rig did not install.
+
+The "put OUT_BIN on PATH" advice is only worth giving when something actually landed in `OUT_BIN`. When every tool was satisfied elsewhere, `OUT_BIN` may reasonably be off PATH, and telling the user to add it would be advice to fix nothing.
+
+## main: argument shift
+
+Read the command, THEN shift — and shift only if there is something there. A bare `shift` with no positional parameters returns 1, and under `set -e` that ended the script before a single line was printed: running this with no arguments at all, the documented default, did nothing and said nothing.

rig/docs/notes/docs.md

@@ -0,0 +1,14 @@
+# ctrl/docs.sh
+
+## Serving without the cluster or python
+
+The docs are the instructions for building the cluster, so they must work before
+anything else exists. That rules out serving them from the cluster, and it rules
+out `python -m http.server` too — a minimal Debian has no python3. What it does
+have, by definition, is Docker: the single prerequisite rig already demands. So a
+throwaway nginx container serves a read-only bind mount.
+
+## Committed SVGs
+
+Rendered SVGs are committed alongside their `.dot` sources for the same reason:
+the pages have to read on a machine with no Graphviz installed.

rig/docs/notes/env.md

@@ -0,0 +1,74 @@
+# ctrl/.env.example, ctrl/env.d/*.env.example
+
+## ctrl/.env.example: header
+
+Machine-local config. Copy to ctrl/.env (gitignored) and edit. The cluster SHAPE is an optional profile in ctrl/env.d/ — see the *.env.example there. The architecture MODEL lives in arch/<name>.json — not in .env either.
+
+## ctrl/.env.example: CLUSTER
+
+The kubectl context becomes kind-<CLUSTER>. LEAVE THIS UNSET unless you need a name that differs from the directory — it defaults to this folder's name, which is what makes the folder copyable: copy it, rename it, and you get a separate environment with no edits.
+
+## ctrl/.env.example: host ports
+
+LEAVE UNSET — they derive from the directory name so several environments coexist without negotiating (see ctrl/ports.sh). `make check` shows this environment's block; `bash ctrl/ports.sh persist` writes it into ctrl/.env so it stops being derived and becomes fixed. Set a value only to override.
+
+## ctrl/.env.example: MANIFESTS_DIR
+
+Where the application manifests live. The real ones are expected to be versioned separately from this installer — they change on a different cadence, by different people. Repoint this at their repo and rig stops owning them:
+
+    MANIFESTS_DIR=../platform-manifests/overlays/dev
+
+## ctrl/.env.example: DEPS_SOURCE
+
+Where the installer fetches the pinned binaries from.
+
+- `upstream` — GitHub releases / dl.k8s.io (needs internet)
+- `artifactory` — a generic repo; what a locked-down client usually allows
+- `baked` — already inside the installer image; no network at all
+
+## ctrl/.env.example: registry secrets
+
+The registry mode comes from the profile (REGISTRY_MODE). REGISTRY_REMOTE_URL, REGISTRY_USER and REGISTRY_PASSWORD are the secrets it needs, required for mirror/remote.
+
+## ctrl/.env.example: REGISTRY_CA_FILE
+
+Corporate root CA, if Artifactory is fronted by an internal CA (it usually is). Trust has to reach THREE places and nothing does it for you: the host docker daemon, every kind node's containerd, and any in-cluster client. registry.sh handles the first two; check.sh reports when it's configured but not trusted. Symptom when missing: `x509: certificate signed by unknown authority`.
+
+## env.d/*.env.example: profiles in general
+
+EXAMPLE PROFILES. rig needs none of these: with no profile it runs on its built-in defaults (lib/config.sh). To use one, copy it to <name>.env in ctrl/env.d/ and name it — PROFILE=<name> in ctrl/.env, or on the command line. It then overlays the defaults; anything it does not set, they still supply.
+
+## env.d/client.env.example
+
+client — images through a pull-through cache of the corporate registry, with TLS and metrics addons. More nodes or port mappings: edit k8s/kind-config.yaml.tpl.
+
+### Real ports (80/443)
+
+Ports derive from the directory name by default (see ctrl/ports.sh), so several environments run side by side.
+
+Opt in to the real ports only when this is the ONLY environment and nothing else owns :80. They fail to bind otherwise, and docker reports it as an opaque "failed to bind host port 0.0.0.0:80/tcp: address already in use" halfway through cluster creation. `make check` checks before you spend the time. Uncommenting also means only one environment can exist at a time.
+
+## env.d/data.env.example
+
+data — databases and a scheduler for an environment that needs them: postgres, redis and airflow, each an upstream image run unmodified.
+
+Everything lands in the `data` namespace (DATA_NAMESPACE to move it), so `make cluster reset` on the app namespace leaves the databases alone.
+
+Costs roughly 2-3 GB with airflow, under 1 without. Airflow's first boot runs the whole metadata migration, so expect a few minutes before it is ready.
+
+### Postgres password
+
+The password is not in the profile: postgres.sh generates one on first install and keeps it across re-runs, so re-running the addon never rotates the credential out from under whatever is already connected.
+
+### Reaching the databases
+
+Ports derive from the directory name by default — see ctrl/ports.sh. Reach the databases with port-forward rather than binding more host ports:
+
+    kubectl -n data port-forward svc/postgres 5432:5432
+    kubectl -n data port-forward svc/airflow 8080:8080
+
+## env.d/offline.env.example
+
+offline — air-gapped. Everything comes from a local registry that was loaded ahead of time; nothing reaches the internet. Pair with the deps-full image (DEPS_SOURCE=baked) so the toolchain install is offline too.
+
+The heavier addons are left out to keep first boot viable.

rig/docs/notes/kind-config.md

@@ -0,0 +1,23 @@
+# ctrl/k8s/kind-config.yaml.tpl
+
+## Why a template
+
+The cluster: one node by default — add nodes or port mappings by editing the file, then `make cluster reset`.
+
+It is a TEMPLATE rather than a plain kind-config.yaml because a rig is copied and renamed to make a second environment, and both the cluster name and the host port follow the directory. A checked-in literal would make every copy collide on both. ctrl/cluster.sh renders it with sed — not envsubst, which is gettext-base and absent from a minimal Debian, and rig's whole premise is that Docker is the only prerequisite.
+
+## Substituted variables
+
+Substituted by ctrl/cluster.sh: CLUSTER, NODE_IMAGE, HTTP_PORT, HOST_WORKDIR. The header comment names them without the `${...}` braces so that line survives the substitution.
+
+## Node count
+
+The node count is READ BACK from this file by lib/config.sh, so this YAML is the source of truth for it — there is no second place to update.
+
+## containerdConfigPatches
+
+Point containerd at a certs.d directory. registry.sh drops per-host hosts.toml files in there afterwards, so switching registry mode never requires recreating the cluster.
+
+## extraPortMappings
+
+One NodePort bridged to the host; an in-cluster gateway owns it. There is deliberately no ingress controller — they pin a narrow window of k8s versions, and running a trailing-edge control plane is the point.

rig/docs/notes/mem.md

@@ -0,0 +1,96 @@
+# ctrl/mem.sh
+
+## Purpose
+
+How much memory this machine will actually give you before something dies. This is rig's memory tool, and the standalone rigmini.sh is generated from this file.
+
+There are two numbers and they are rarely the same. `status` reports what the machine ADVERTISES and what is quietly capping it. `push` finds what it will SURVIVE, by allocating until it stops. `all` does both and weighs the result against what this profile's cluster needs.
+
+The gap between them is the whole reason this exists. Under WSL the cap lives in .wslconfig; in a container or a managed workspace it is a cgroup limit, and there /proc/meminfo reports the HOST's memory while the kernel kills you at a fraction of it. A script that only read MemTotal would confidently report 32 GB on a box that OOMs at 2.
+
+Runs on native Linux and under WSL. On WSL the memory you see is a VM allocation that can be raised, and the commonest failure is raising it without restarting, so status compares what .wslconfig says with what actually booted.
+
+It reports and instructs. It never raises a limit, frees anything or installs a package. The one write it can make is `backup`, which copies .wslconfig beside itself, so that `restore` has something to put back after a hand edit.
+
+Usage:
+
+```
+mem.sh status                                  what it has, what caps it
+mem.sh push [--to GB] [--to-oom]               climb until it stops
+mem.sh all  [--budget GB]                      both, then the verdict
+mem.sh backup | restore                        .wslconfig, WSL only
+```
+
+## require_linux
+
+Windows outside WSL (Git Bash, MSYS, Cygwin) looks close enough to work and then fails in a pile of confusing ways: no /proc, no docker socket, none of the tooling. It is detectable, so name it instead.
+
+## CG_MAX_FILE / CG_CUR_FILE
+
+Where a cgroup records this cgroup's own limit and usage. Set once by find_cgroup, because every later reading needs both, and hunting for the files on each call would be the slow part of the poll loop.
+
+## find_cgroup
+
+Inside a container the cgroup namespace makes the top of the tree BE the container's own cgroup, so the unqualified path is already the right one. On a host it is the root cgroup, which is never limited; hence the second attempt via /proc/self/cgroup, which names the slice this shell is in.
+
+## cgroup_cap_mb
+
+Returns the cap in MB, or "" when there is none worth reporting. cgroup v2 spells unlimited "max"; v1 spells it as a number near 2^63, which is why this compares against MemTotal rather than testing for a magic value. A "limit" above the machine's own memory is not a limit, however it is written.
+
+## headroom_mb
+
+How much room is left RIGHT NOW, from whichever accounting actually governs. In a capped container /proc/meminfo describes the host and is worse than useless for this: it would report tens of gigabytes free on a box that is one allocation from being killed.
+
+## wslconfig_path
+
+/mnt/c/Users can hold several real accounts (a renamed login leaves the old directory behind), so picking the first alphabetically is a coin toss. Ask Windows, then fall back to whichever profile actually owns a config.
+
+## status: overcommit
+
+overcommit_memory=0 is the default heuristic: a large allocation is granted on a guess, and the reckoning arrives later as an OOM kill rather than as a failed malloc. It is why `push` touches every page it asks for.
+
+## status: WSL
+
+WSL keeps its cap on the Windows side, in a file this shell can read but not usefully apply: the change costs a full VM restart. Report it, and report the commonest mistake, which is editing it and not restarting.
+
+## backup
+
+Backups are timestamped and never overwritten: a backup that can destroy itself on a second run is not a backup.
+
+## restore
+
+Newest is the right default (undo the last edit), but if you backed up *after* editing, the state you want is older. The rest are shown so a no-op restore is obviously a no-op rather than a mystery.
+
+## allocator
+
+The child allocates and stops itself; the parent only watches. That split is the point: under --to-oom the allocating process is expected to be killed, and something has to survive to say how far it got.
+
+### OOM score
+
+The child raises its own OOM score to the maximum so the kernel picks THIS process first. Raising needs no privilege (only lowering does). Without it, the kernel is free to choose your shell, your ssh session or dockerd; on a box you are still using, that is not an acceptable coin toss.
+
+### Writing straight into the array element
+
+Each chunk is written STRAIGHT INTO the array element (`printf -v "arr[$i]"`). The obvious spelling, building one chunk and `arr+=("$chunk")`, costs three copies per step, not one: the template stays resident, expanding "$chunk" makes a temporary word, and the append makes the element. A 128 MB step then needs 384 MB transiently, and on a small box it is killed on the first append while reporting a third of the true ceiling.
+
+printf -v into a subscript also means every page is written, so it is resident rather than merely promised: the only kind of allocation that measures anything under heuristic overcommit.
+
+### First swap
+
+Worth calling out separately from the ceiling: this is where the box stops being fast and starts being unusable, which for a scheduler is a different and earlier problem than being killed.
+
+## push: step size
+
+A step is worth about a sixty-fourth of the ceiling: enough resolution to find the edge, few enough lines to read, and small enough that the transient cost of one allocation never dominates a small box. A fixed size cannot do all three: 128 MB is fine on 16 GB and absurd on 512 MB.
+
+## push: floor
+
+Stop with a cushion rather than riding it to the kill. How big a cushion depends on what it is protecting. Under a cgroup cap, running out kills only this container's own processes, so it need cover no more than the shell that prints the result, and a 512 MB cushion on a 1 GB box would halve the answer. On a host there is everything else to protect, and the OOM killer does not promise to pick the process that caused the problem.
+
+## push: Ctrl-C
+
+INT kills the child and lets the summary print anyway, so an impatient Ctrl-C still tells you how far it got and, more importantly, still gives the memory back.
+
+## push: claimed vs. measured
+
+The gap between the claim and the measurement is the finding, but only when the BOX chose where to stop. An empty $stop means the child was ended rather than deciding to end; anything else (--to, the floor) is a stop we asked for, and flagging those as short of the ceiling would put a warning on every deliberately small run.

rig/docs/notes/ports.md

@@ -0,0 +1,32 @@
+# ctrl/ports.sh
+
+## Why each environment gets a port block
+
+New versions of a system mean new clusters on ONE machine, not new machines. Cluster name, kubectl context, registry container and image tag already derive from the directory name, so two copies never collide there, but host ports are a single shared namespace and would.
+
+The block is derived from the directory name: stateless, stable, and requiring no coordination between copies that know nothing about each other.
+
+```
+base = 20000 + (hash(slug) % 200) * 10
+  +0 HTTP   +1 HTTPS   +2 TILT   +3 REGISTRY   (+4..9 reserved)
+```
+
+20000+ deliberately avoids the ports something is already likely to hold: 80, 443, 3000, 5432, 8000, 8080.
+
+Derivation is a default, not a decision. On first use the resolved block is written into ctrl/.env, so it becomes pinned, visible and editable rather than a number that appears from nowhere. Anything already in ctrl/.env wins.
+
+## active
+
+The resolved facts a consumer outside bash needs, machine-readable:
+
+```
+CLUSTER KUBECONTEXT HTTP HTTPS TILT REGISTRY MANIFESTS_DIR
+```
+
+Identity and ports together, because they are one fact set: both derive from the directory name so that copies never collide. A consumer needs all of them or none, and fetching them separately is how two end up disagreeing. MANIFESTS_DIR rides along because the one consumer that needs the addressing is the one that needs to know what to deploy.
+
+Space-separated, so MANIFESTS_DIR must not contain spaces. Everything else in rig already assumes that of paths; kind, docker and kubectl all do.
+
+`derive` answers a DIFFERENT question (what the directory name alone implies) and deliberately ignores ctrl/.env. Configuring anything from it would silently contradict the rule that "anything already in ctrl/.env wins". `active` is what anything downstream should read.
+
+Why this exists at all: the cluster name is not the bare directory name. default_cluster_name() lowercases it and replaces every character outside [a-z0-9-], because it has to be a DNS label. Re-deriving that in another language is how a copy in `My_Project/` ends up guarding the wrong context.

rig/docs/notes/registry.md

@@ -0,0 +1,41 @@
+# ctrl/registry.sh
+
+## Registry modes
+
+Registry plumbing. This is the seam — not a tool. Four modes, selected by
+`REGISTRY_MODE` in the active profile:
+
+- **none** — Tilt builds straight into the node. No registry at all, and so no
+  guard against an outward push: an unqualified image name means
+  `docker.io/library/<name>`, and only Tilt's kind detection stands between that
+  and a real push. Throwaway use only; every profile here now defaults to `local`
+  instead.
+- **local** — a `registry:2` container wired into the cluster.
+- **mirror** — the same container, but configured as a pull-through cache of the
+  corporate registry. This is what a locked-down client actually looks like:
+  images originate from corp, you don't hammer it, and you keep working when the
+  VPN drops.
+- **remote** — no local container; pull straight from the corporate registry
+  using an imagePullSecret.
+
+## Why a script rather than ctlptl
+
+Deliberately a script rather than a tool. ctlptl collapses the `local` wiring
+into one line, but its Registry spec only accepts name/port/image/listenAddress —
+there is no way to set `REGISTRY_PROXY_REMOTEURL`, so it cannot express `mirror`
+at all. Keeping the seam here is what keeps the corporate registry swappable.
+
+## CA trust (install_ca_into_nodes)
+
+A corporate registry is almost always fronted by an internal CA, and trust has to
+reach three separate places. Nothing does this for you, and the symptom when it's
+missing is an opaque:
+
+    x509: certificate signed by unknown authority
+
+1. the host docker daemon — `/etc/docker/certs.d/<host>/ca.crt` (needs root)
+2. every kind node's containerd — nodes do NOT inherit host trust
+3. anything doing HTTPS from inside the cluster, in its own trust store
+
+`registry.sh` handles (2) because it's ours to handle. (1) is reported by
+`check.sh` since it needs root. (3) belongs to the workload.

rig/docs/notes/selftest.md

@@ -0,0 +1,67 @@
+# ctrl/selftest.sh
+
+## Purpose
+
+What rig has settled, written down as assertions.
+
+These are documentation that runs. Each check is ONE decision that has already been made, with the reason above it: not coverage, and deliberately not an exhaustive sweep of use cases. rig's own index says a rule without its reason gets overridden the first time it is inconvenient; a rule nobody can restate is worse. So the test says what was decided, and failing it should read as "you are about to undo this" rather than "something broke".
+
+Scope, on purpose:
+
+- No cluster, no docker, no network. It must be cheap enough to actually run.
+- It asserts about RIG. `make check` asserts about the MACHINE and never fails; this exits 1, the way `make standalone check` does.
+- What actually deploys is not testable here. `tilt ci` stays a manual step.
+
+## rig needs no profile
+
+rig assumes no configuration. A profile is an overlay on built-in defaults, so a rig with no `env.d/` at all must resolve, report, and still generate a kit. Naming a profile that does not exist must still be an error, because a typo that silently fell back to the defaults would be worse than a failure.
+
+## the ports.sh active contract
+
+`ports.sh active` is read POSITIONALLY by two other files: the Makefile takes `$(word 2)` and `$(word 5)`, the Tiltfile takes `_facts[0]..[6]`. Insert a field in the middle and nothing errors: Tilt simply guards on the wrong context or binds the wrong port. The field count and order are the contract, so they are pinned here rather than left to whoever edits `ports.sh` next.
+
+## the caller's env beats the files
+
+`lib/config.sh` states one precedence rule: `versions.env` < `env.d/<profile>` < `ctrl/.env` < the caller's env. It is enforced by `CONFIG_OVERRIDABLE`, a hand-maintained list, and a key missing from it loses to the file SILENTLY. `REGISTRY_PORT` and `MANIFESTS_DIR` were both missing on 2026-09-13 and were found by accident.
+
+So the loop is generated FROM the list: add a key to `CONFIG_OVERRIDABLE` and the test starts asking about it without anyone remembering to come here. Three keys name something that must exist and are validated at load, so they get a real alternative rather than a sentinel.
+
+## one derivation, not three
+
+The Makefile used to compute the cluster name itself and sed `TILT_PORT` out of `ctrl/.env`: a second derivation of values `lib/config.sh` already owns, which could disagree with it after `ports.sh persist`. It now reads `ports.sh active`. Nothing structurally prevents the sed coming back, so the agreement is asserted against the real `make -n` output rather than against the source.
+
+`--no-print-directory` and a grep, not `tail -1`: run from `make selftest` this is a RECURSIVE make, and the "Entering/Leaving directory" lines go to STDOUT. `tail -1` then reads "make[1]: Leaving directory ..." and both checks fail, but only when invoked through make, never when the script is run directly. A test that passes one way and fails the other is worse than no test.
+
+## identity follows the folder, safely
+
+The cluster name is NOT the bare directory name: kind needs a DNS label, so `default_cluster_name` lowercases it and replaces everything outside `[a-z0-9-]`. Re-deriving that anywhere else is how a copy ends up guarding the wrong context, which is exactly why the Tiltfile asks instead of computing.
+
+## ports are stable across versions
+
+Not a change-detector. The block is derived, never stored, so if the derivation shifts then every EXISTING environment's ports move underneath it: a running cluster keeps its old ports while rig starts reporting new ones, and `ports.sh show` stops describing reality. Anchored to three known names.
+
+## rig stays standalone
+
+rig sits inside a host project's tree but must be copyable straight out of it: no imports, no paths, no assumption the host is there. This grep is the whole test of that claim, and until it was added it lived only in prose and in whoever remembered to run it.
+
+The pattern is assembled from fragments so the file does not match ITSELF. Writing it literally would fail forever; excluding the file instead would put a blind spot in the one check that guards the boundary.
+
+## the Tiltfile hardcodes nothing
+
+Every other Tiltfile on this machine writes its slug in five or six times by hand, so a copied project deploys into the original's cluster until someone edits all of them. rig's asks `ports.sh`. A literal `kind-<name>` in it would mean that has been undone.
+
+## standalone kits are generated and current
+
+The kits under `standalone/<profile>/` are rig flattened into single files, one per profile. A kit left behind by a change to rig is exactly the drift they replaced (`rigmini.sh` once said 2 GB per node long after rig measured 800 MB), so a stale kit fails here rather than waiting to be noticed on another machine.
+
+## kit Makefiles call only real verbs
+
+Each kit's Makefile exists so nothing wrapping these scripts has to GUESS how to call them. A generated Makefile once did guess: `rigmini.sh on`, not a verb, and a bare `rigdeps.sh` for "check and report", which installs. So every target's default verb must be one its script's own dispatch accepts, read from that dispatch, not from a list that could drift from it.
+
+## export carries choices, not credentials
+
+An export is "take the setup I have here somewhere else", so it carries this machine's CHOICES (profile, ports, manifest dir) and never its credentials: `ctrl/.env` can hold registry and mirror logins next to those choices. The committed per-profile kits carry neither, since they must be the same on any machine. Proven with sentinel values in a scratch copy, because the real `ctrl/.env` may have those keys empty, and an empty value proves nothing.
+
+## optional: Tiltfile evaluates
+
+Parsing the Tiltfile for real is the only way to know it still evaluates, but Tilt snapshots a kubectl context before parsing, so it cannot run without a cluster. Skipped rather than failed when there is none, the same way docgen skips its graphgen section.

rig/docs/notes/standalone.md

@@ -0,0 +1,31 @@
+# ctrl/standalone.sh
+
+## Purpose
+
+Generates the standalone kits: single-file versions of rig's own tools, one folder per profile, for machines the full rig is not going to.
+
+A kit is a pure function of rig as it is right now. It gains nothing rig lacks and loses nothing rig has: improve rig, regenerate, and every kit follows. Nothing in `standalone/<profile>/` is ever edited by hand.
+
+## The contract
+
+What this file does NOT know, on purpose: which tools rig has, what they are called, how its libraries are split, where configuration lives or what it contains. Rig will change shape (scripts get split, renamed and grow new libraries), and a generator that encoded today's layout would quietly produce a wrong kit the first time it did. So it works from a contract a script opts into, and from nothing else:
+
+1. A marker comment, alone on a line near the top, declares an entry point: `(hash) rig:standalone <kit-name> <default-verb>`. The default verb must only REPORT: it is run as a smoke test.
+2. Every `source` an entry point makes names a `.sh` file by a path that resolves relative to the entry point. Libraries may source further libraries however they like; bash follows those itself.
+3. Configuration enters through `load_config`, and the libraries provide `config_profiles`, `config_freeze <profile|--current>` (which prints a replacement `load_config` with that resolution frozen in) and, for an export, `config_current_profile` and `config_left_out`. How config is layered, stored, derived or frozen is rig's business; the generator only asks, and embeds the answer without interpreting it.
+
+## Bash does the resolving
+
+Bash does the resolving, not a parser in the generator. Libraries are sourced in a clean shell and read back with `declare -f` and `declare -p`, so any structure bash can load, this can flatten.
+
+## Every kit is proven before it is written
+
+Every kit is PROVEN to stand alone before it is written: no `source` left, no path into rig's tree in its code, `bash -n` clean, and its default verb run in an empty directory with nothing from rig present. A shape the generator has never seen either passes that, or generation stops and names the kit, the file, the line and what is wrong. It never writes a kit that only looks finished.
+
+## Usage: write, check, export
+
+- `standalone.sh write`: generate every kit into `standalone/<profile>/`.
+- `standalone.sh check`: generate into a scratch dir and fail if any kit differs.
+- `standalone.sh export DIR`: ONE kit for the configuration this machine runs (its profile plus the choices in its local config, WITHOUT its credentials), written outside the repo.
+
+`write` and `check` are what gets committed: one kit per profile, identical on any machine. `export` answers the other question, "take the setup I have here somewhere else", so it reflects this machine, and for exactly that reason it never lands in the repository.

rig/docs/notes/versions.md

@@ -0,0 +1,41 @@
+# ctrl/versions.env
+
+## Pinned toolchain
+
+The single manifest `ctrl/deps.sh` installs from. Every entry is a single binary; none of them needs an apt repo.
+
+- kubectl — fully static
+- kind — libc only
+- tilt — libc + libstdc++ + libgcc (present in base Debian)
+- jq — upstream static build (Debian's is linked against libjq/libonig)
+
+Checksums are the upstream-published SHA256 of the linux/amd64 artifact.
+
+## Bumping a pin
+
+Change the version, then take the checksum from the release's own published list — never hand-edit or hand-copy one from a download you did. For anything hosted on GitHub releases that is:
+
+```
+curl -sSL https://github.com/<org>/<repo>/releases/download/<tag>/checksums.txt \
+  | grep linux.x86_64
+```
+
+(kubectl publishes its own instead: `<KUBECTL_URL>.sha256`.)
+
+There was a `ctrl/versions-refresh.sh` named here that has never existed. If bumping stops being rare enough to do by hand, write it — but a comment pointing at a missing script is worse than no comment.
+
+## ctlptl
+
+Creates a kind cluster WITH a local registry wired in, which is what keeps images off docker.io (an unqualified name means `docker.io/library/<name>`). Same publisher and same archive shape as tilt: binary at the archive root, so `fetch_tgz` handles it with strip=0 and no special case.
+
+## docker compose
+
+The distro docker packages ship the daemon and the CLI but frequently not this, so `docker compose up` fails with "unknown command" on an otherwise working Docker. It is a CLI plugin, found by NAME in a plugin directory, so a copy in the bin dir alone only gives you the retired `docker-compose` v1 spelling; deps.sh links it into `~/.docker/cli-plugins`.
+
+## Node images
+
+Node images shipped with `KIND_VERSION`, pinned by digest so a kind upgrade can never silently move the k8s version. Profiles select one via `K8S_VERSION`. Older entries are kept deliberately: running a trailing-edge control plane is part of simulating a legacy estate.
+
+## Cabinets
+
+Public services dropped in as-is, the upstream image unmodified. The same declaration installs on compose or in the cluster, so a dependency is named once and works either way. Pinned by tag rather than digest because they are ordinary upstream images with no supply chain claim attached — bump freely, and preload them for the offline profile.

rig/docs/viewer.html

@@ -0,0 +1,101 @@
+<!DOCTYPE html>
+<html>
+<head>
+<meta charset="UTF-8">
+<title>Graph Viewer</title>
+<style>
+  * { margin: 0; padding: 0; }
+  body {
+    background: #0a0e17;
+    overflow: hidden;
+    width: 100vw;
+    height: 100vh;
+  }
+  #container {
+    width: 100vw;
+    height: 100vh;
+    overflow: hidden;
+    cursor: grab;
+  }
+  #container.dragging { cursor: grabbing; }
+  img {
+    transform-origin: 0 0;
+    user-select: none;
+    -webkit-user-drag: none;
+  }
+</style>
+</head>
+<body>
+<div id="container">
+  <img id="img" />
+</div>
+<script>
+var src = new URLSearchParams(location.search).get('src');
+var img = document.getElementById('img');
+var container = document.getElementById('container');
+
+img.src = src;
+
+var scale = 1;
+var x = 0, y = 0;
+var dragging = false;
+var startX, startY, startPanX, startPanY;
+
+function apply() {
+  img.style.transform = 'translate(' + x + 'px,' + y + 'px) scale(' + scale + ')';
+}
+
+// Fit to screen on load
+img.onload = function() {
+  var sw = window.innerWidth / img.naturalWidth;
+  var sh = window.innerHeight / img.naturalHeight;
+  scale = Math.min(sw, sh) * 0.95;
+  x = (window.innerWidth - img.naturalWidth * scale) / 2;
+  y = (window.innerHeight - img.naturalHeight * scale) / 2;
+  apply();
+};
+
+// Wheel zoom toward cursor
+container.addEventListener('wheel', function(e) {
+  e.preventDefault();
+  var factor = e.deltaY < 0 ? 1.12 : 0.89;
+  var rect = container.getBoundingClientRect();
+  var mx = e.clientX - rect.left;
+  var my = e.clientY - rect.top;
+  x = mx - (mx - x) * factor;
+  y = my - (my - y) * factor;
+  scale *= factor;
+  apply();
+}, { passive: false });
+
+// Pan
+container.addEventListener('mousedown', function(e) {
+  if (e.button !== 0) return;
+  dragging = true;
+  startX = e.clientX;
+  startY = e.clientY;
+  startPanX = x;
+  startPanY = y;
+  container.classList.add('dragging');
+  e.preventDefault();
+});
+
+window.addEventListener('mousemove', function(e) {
+  if (!dragging) return;
+  x = startPanX + (e.clientX - startX);
+  y = startPanY + (e.clientY - startY);
+  apply();
+});
+
+window.addEventListener('mouseup', function() {
+  dragging = false;
+  container.classList.remove('dragging');
+});
+
+// Double-click to reset
+container.addEventListener('dblclick', function() {
+  img.onload();
+});
+</script>
+</body>
+</html>