Diffusion: turning it on catches a consumer up 3776b70d9b17

    // Turned on: bumped at once to where its upstreams are (#148).

    if rule.follow != crate::diffusion::Follow::Off {

        let (app, row) = (app.clone(), row.clone());

        tokio::spawn(async move { crate::diffusion::catch_up(&app, &row).await });

    }

    propagate_to(app, upstream, heads, green, None).await

}

/// `propagate`, to one consumer only when `only` names it.

async fn propagate_to(app: &Shared, upstream: &RepoRow, heads: Vec<ChangeHash>, green: bool, only: Option<i64>) {

        if only.is_some_and(|o| o != consumer_id) {

            continue;

        }

        }

    }

}

/// The repository on this hub with Oxygen id `id` (hex).

async fn repo_by_oxy_id(app: &Shared, id: &str) -> Option<RepoRow> {

    for row in db::repos::list(&app.db).await.ok()? {

        let Some(name) = RepoName::new(&row.owner, &row.name) else { continue };

        if app.repos.read(&name, |r, _| Ok(r.id()?)).await.ok().map(hex::encode).as_deref() == Some(id) {

            return Some(row);

        }

    }

    None

}

/// The newest state of `upstream`'s default bookmark whose run passed.

async fn last_green(app: &Shared, upstream: &RepoRow) -> Option<Vec<ChangeHash>> {

    let heads: String =

        sqlx::query_scalar("SELECT heads FROM flow_runs WHERE repo_id = ? AND bookmark = ? AND status = 'passed' ORDER BY id DESC LIMIT 1")

            .bind(upstream.id)

            .bind(&upstream.default_bookmark)

            .fetch_optional(&app.db)

            .await

            .ok()

            .flatten()?;

    let h: Vec<ChangeHash> = heads.split('+').filter_map(ChangeHash::from_hex).collect();

    (!h.is_empty()).then_some(h)

}

/// Bring `consumer` up to date with the upstreams it pins, at once: when

/// it turns Diffusion on, it is bumped to each upstream's newest state

/// that passed (or simply its newest, when it follows every move).

pub async fn catch_up(app: &Shared, consumer: &RepoRow) {

    let upstreams: Vec<String> = sqlx::query_scalar("SELECT DISTINCT upstream FROM diffusion_pins WHERE consumer_id = ?")

        .bind(consumer.id)

        .fetch_all(&app.db)

        .await

        .unwrap_or_default();

    for id in upstreams {

        let Some(upstream) = repo_by_oxy_id(app, &id).await else { continue };

        if let Some(h) = last_green(app, &upstream).await {

            propagate_to(app, &upstream, h, true, Some(consumer.id)).await;

        }

        let Some(name) = RepoName::new(&upstream.owner, &upstream.name) else { continue };

        let b = upstream.default_bookmark.clone();

        if let Ok(h) = app.repos.read(&name, move |r, _| heads_of(r, &b)).await {

            propagate_to(app, &upstream, h, false, Some(consumer.id)).await;

    if crate::diffusion::rule(&app.config.diffusion.follow, &row, None, "").follow != crate::diffusion::Follow::Off {

        let (app, row) = (app.clone(), row.clone());

        tokio::spawn(async move { crate::diffusion::catch_up(&app, &row).await });

    }

    // Turned on to follow every move: bumped at once to where the upstream

    // is (v2), by the diffusion account; the next push updates it.

    let first = bump().await.expect("caught up when turned on");

    assert!(first.title.contains("1 change") && first.body.contains("api v2: faster sprites"), "{:?}", first.title);

    let mut p = first.clone();

    for _ in 0..100 {

        p = bump().await.unwrap();

        if p.body.contains("api v3") {

            break;

        }

        tokio::time::sleep(std::time::Duration::from_millis(50)).await;

    }

    assert_eq!(p.number, first.number, "the same proposal");

    // A consumer turning Diffusion on is bumped at once to the upstream's

    // newest passing state, without waiting for it to move again.

    create(&h.app, "andy", "game2").await;

    let g2_work = tempfile::tempdir().unwrap();

    let g2 = client(&format!("{}/andy/game2", h.base), g2_work.path());

    g2.submodule_add(&format!("{}/andy/api", h.base), "deps/api", Some("main")).unwrap();

    g2.snapshot("t").unwrap();

    g2.commit("game2 on api", &[]).unwrap();

    assert!(g2.push("origin", false).unwrap().iter().all(|r| r.ok));

    // Its pin is api's newest state already: move api on, pass the run.

    write(api_work.path(), "a5.c", "v5\n");

    api.snapshot("t").unwrap();

    api.commit("api v5", &[]).unwrap();

    assert!(api.push("origin", false).unwrap().iter().all(|r| r.ok));

    pass_all().await;

    let g2_row = db::repos::get(&h.app.db, "andy", "game2").await.unwrap().unwrap();

    for _ in 0..100 {

        if sqlx::query_scalar::<_, i64>("SELECT COUNT(*) FROM diffusion_pins WHERE consumer_id = ?")

            .bind(g2_row.id)

            .fetch_one(&h.app.db)

            .await

            .unwrap()

            > 0

        {

            break;

        }

        tokio::time::sleep(std::time::Duration::from_millis(30)).await;

    }

    assert!(db::proposals::list(&h.app.db, g2_row.id, &[]).await.unwrap().is_empty(), "off until turned on");

    let (st, _) = call(&h.app, "PUT", "/api/v1/repos/andy/game2/diffusion", Some("site"), Some(r#"{"follow":"green"}"#.into())).await;

    assert_eq!(st, StatusCode::OK);

    let mut caught = None;

    for _ in 0..100 {

        if let Some(p) = db::proposals::list(&h.app.db, g2_row.id, &["open"]).await.unwrap().into_iter().next() {

            caught = Some(p);

            break;

        }

        tokio::time::sleep(std::time::Duration::from_millis(50)).await;

    }

    let caught = caught.expect("bumped as soon as it was turned on");

    assert!(caught.body.contains("api v5") && caught.title.contains("1 change"), "{:?} {:?}", caught.title, caught.body);

- **Architecture** (OxygenFlow spec §11.2–§11.3, oxygenflow#36): a runner reports each image's architecture on its claims (`image_archs`), kept in `flow_images`; a job is offered only to a runner whose architecture matches its sandbox's `arch`, else its image's as known; unknown matches, as before. The queue says which architecture a waiting job asks for. **Images by hash** (oxygenflow#39, Jetstream): `flow rootfs push HASH` sends a rootfs image as the FastCDC chunks the hub lacks (`POST /flow/images/missing`, `PUT /flow/images/chunks/{hash}`, by a token that may write repositories) and then its manifest (`PUT /flow/images/{hash}`), which the hub accepts only when every chunk is held and they make an image with that hash; chunks are kept zstd-compressed under `<data>/images`, shared by every image, and `jet_images` lists what is held. Runners and accounts fetch with `GET /flow/images/{hash}` and `GET /flow/images/chunks/{hash}`. A runner whose claims say `fetches_images` is offered jobs whose image only the hub holds, and fetches it before its preflight. Each claim also carries the runner's `facts` (OxygenFlow spec §11.1, oxygenflow#40): free disk, load, speed score and class, kernel; the hub keeps the latest on the runner, shows them on Admin › Runners and in `GET /runners`. A job's finish carries the most disk and memory it took (`peak_disk_mib`, `peak_memory_mib`, oxygenflow#41); a new job's `need_disk_mib` is the most its last five runs of the same repository and name took, plus a quarter and 64 MiB, and it is offered only to a runner whose claim reports at least that much free disk; the waiting reason says so. **Ranking** (oxygenflow#42): a job that another free runner which polled in the last 10 s would do better (it holds the job's image while the claimant would fetch it, or has a higher speed class) is held from the claimant for up to 15 s, then any runner that fits takes it; each job records why it ran where it did (`placed`: "holds the image, idle, speed 100 (class 3)", with "after N s held for a better runner" when it was), shown on the run page, in the API and by `oh run view`. A run whose jobs pin an image held by neither the hub nor a runner sets a failing `pipeline/images` check on its state (#137), naming the images and how to send them (`flow rootfs push`), so a proposal pinning a new image shows it before it lands; a later run of the state turns it to passed once every image is held. A placement pass every 15 seconds works out why each ready queued job no runner can take waits, from what each online runner offered at its last claim (scope, tier, architecture, image held, labels, memory and CPUs, a recent decline), and shows it on the job (API `waiting`, `oh run view` and `oh run watch`, its panel open on the run page) and in its check's summary, so a proposal says why its check is stuck (#28). **Diffusion** (#148, `docs/diffusion.md`): a push that moves a repository's default bookmark, or the bookmark its work lands on (the most common target of its proposals landed in the last 90 days), records each Oxygen subrepo pin in the new state (`diffusion_pins`: consumer, bookmark, path, the upstream's Oxygen repository id, the pinned heads); a hub that had no index fills it at start. `GET /repos/{owner}/{name}/consumers` lists the consumers the caller may read, each with its pin and how many changes of this repository's default bookmark it lacks (`behind`, null when the pin names changes this repository does not hold), and the overview shows them as Used by. A consumer follows a subrepo's upstream as its `.oxymodules` entry says (`follow = off | green | any`, `land = propose | auto`, `target` naming the bookmark to bump, `watch` listing paths whose upstream changes are flagged), else as its repository setting says (Settings › Diffusion, or `PUT /repos/{owner}/{name}/diffusion {"follow": ...}` by its owners and admins; migration 0058), else as `[diffusion] follow` in hub.toml says (default `off`). A **bump** moves a consumer's pin at a path to a newer upstream state: one change on the target bookmark's heads that replaces only the pin (oxy-core `build_pin_change`), signed with the hub's key, on the bookmark `diffusion/<path>`, which the hub owns and rebuilds on the target each time (a forced update). It is skipped when the pin already holds the state, when the bump bookmark already moves it there, or when the state lacks changes the pin has (consumers only move forward). A bump is **proposed** once per bump bookmark, by the hub's `diffusion` account (made on first use, never able to sign in), into the target, labelled `dependencies`, its body the upstream changes the pin lacks (newest first, linking to the upstream's change pages); a later bump edits the same open proposal. It is triggered when a push moves the upstream's default bookmark (for consumers following `any`) or when a run of that bookmark passes (for `green`). Diffusion never lands a proposal. Turning Diffusion on for a consumer (the setting or the API) catches it up at once: it is bumped to each upstream's newest state whose default-bookmark run passed, or to its newest state when it follows every move. **Images page** (#146): Admin › Runners › Images lists every rootfs image a runner holds, the hub keeps, or a job ran on in the last 90 days (from each job's sandbox), newest use first: its size and architecture, where it is (the hub, each runner holding it, each runner fetching it from the swarm now), the repositories whose jobs used it, and who sent it; an image held nowhere is marked. **The swarm** (#144, oxygenflow docs/jetstream.md §8.1): a runner in an image swarm reports its peer address, its site and the BLAKE3 of its TLS certificate with each claim (`swarm`; without a certificate it is not in the swarm), kept in memory and shown on Admin › Runners. `POST /flow/swarm/announce {image, state}` (by a runner; `fetching`, `done` or `stopped`) returns the online runners in its site that hold the image or announced fetching it in the last 45 seconds, each with its certificate's fingerprint, which the fetcher pins its TLS connection to, and a ticket signed with the hub key (JSON naming the runner, its site and an expiry 15 minutes on, hex, then the signature) that peers check against `/.well-known/oxyhub-key` before serving chunks; a runner that has not reported an address is told to add `[runner.swarm]` (409).