bot_bottle/backend/firecracker/infra_artifact.py

@@ -0,0 +1,199 @@
+"""Prebuilt infra-VM rootfs, pulled as an artifact (PRD 0069 Stage 2).
+
+The Firecracker infra VM boots a fixed rootfs (orchestrator control plane +
+gateway + buildah, control-plane init as PID 1) that does not vary per launch —
+the per-boot bits (authorized_keys, guest IP) ride the kernel cmdline, so one
+rootfs boots on any host. Instead of building that rootfs on the launch host
+with Docker, we build it **off-host** and publish it as a versioned, ready-to-
+boot ext4 (gzip-compressed) to a Gitea **generic package**; the launch host
+downloads + verifies + boots it. No Docker, no image tooling on the launch
+host — just an HTTP fetch and gunzip.
+
+  publish (off-host, see publish_infra.py):
+    docker build -> rootfs dir -> mke2fs -> gzip -> PUT generic package
+  pull (this module, launch host):
+    GET .../rootfs.ext4.gz (+ .sha256) -> verify -> gunzip -> boot
+
+The artifact **version** is a content hash of everything baked into the rootfs
+(the shipped bot_bottle package, the three Dockerfiles, and the init), so a
+launch host always pulls the artifact matching its code and a content change
+can't silently boot a stale rootfs. A checksum mismatch fails closed.
+
+Set `BOT_BOTTLE_INFRA_BUILD=local` to skip the pull and build the rootfs
+locally with Docker (dev iteration on the Dockerfiles) — see `infra_vm`.
+"""
+
+from __future__ import annotations
+
+import gzip
+import hashlib
+import os
+import shutil
+import urllib.error
+import urllib.request
+from pathlib import Path
+
+from ...log import die, info
+from . import util
+
+# Bump if the on-disk artifact *format* changes (compression, layout) so a new
+# scheme can't collide with a cached/published artifact of the old one.
+_ARTIFACT_FORMAT = "1"
+
+_REPO_ROOT = Path(__file__).resolve().parents[3]
+_DOCKERFILES = ("Dockerfile.orchestrator", "Dockerfile.gateway", "Dockerfile.infra")
+
+_DEFAULT_BASE = "https://gitea.dideric.is"
+_DEFAULT_OWNER = "didericis"
+_PACKAGE = "bot-bottle-firecracker-infra"
+
+# Streaming copy chunk for the (hundreds-of-MB) download.
+_CHUNK = 1 << 20
+
+
+def local_build_requested() -> bool:
+    """True when the operator opted into the dev Docker-build path instead of
+    pulling the published artifact (`BOT_BOTTLE_INFRA_BUILD=local`)."""
+    return os.environ.get("BOT_BOTTLE_INFRA_BUILD", "").strip().lower() == "local"
+
+
+def infra_artifact_version(init_script: str, *, repo_root: Path = _REPO_ROOT) -> str:
+    """Content hash (16 hex) of everything baked into the infra rootfs: the
+    whole shipped `bot_bottle` package, the three fixed Dockerfiles, and the
+    guest init. Deterministic across the publish host and the launch host when
+    both run the same checkout, so the tag the launch host pulls is exactly the
+    tag publish produced.
+
+    The package is `COPY bot_bottle /app/bot_bottle`'d wholesale into the image,
+    so hash *every* regular file under it — not just `*.py`. Non-Python inputs
+    (e.g. `egress_entrypoint.sh`, `netpool.defaults.env`) are baked in too, and
+    a change to one must bump the version or a launch host could boot a stale
+    rootfs whose code differs from its checkout. `__pycache__`/`.pyc` are the
+    only exclusions — build artifacts, never copied."""
+    h = hashlib.sha256()
+    h.update(f"format={_ARTIFACT_FORMAT}\n".encode())
+    pkg = repo_root / "bot_bottle"
+    for path in sorted(pkg.rglob("*")):
+        if not path.is_file():
+            continue
+        if "__pycache__" in path.parts or path.suffix == ".pyc":
+            continue
+        h.update(str(path.relative_to(repo_root)).encode())
+        h.update(b"\0")
+        h.update(path.read_bytes())
+    for name in _DOCKERFILES:
+        h.update(name.encode())
+        h.update(b"\0")
+        h.update((repo_root / name).read_bytes())
+    h.update(b"init\0")
+    h.update(init_script.encode())
+    return h.hexdigest()[:16]
+
+
+def _config() -> tuple[str, str, str]:
+    """(base_url, owner, token) for the generic-package endpoint. Base + owner
+    are overridable for other deployments / mirrors; the token comes solely from
+    `BOT_BOTTLE_INFRA_ARTIFACT_TOKEN` (a dedicated package-scoped token, kept
+    separate from the general-purpose Gitea token) and is optional — a public
+    package needs none to pull."""
+    base = os.environ.get("BOT_BOTTLE_INFRA_ARTIFACT_BASE", _DEFAULT_BASE).rstrip("/")
+    owner = os.environ.get("BOT_BOTTLE_INFRA_ARTIFACT_OWNER", _DEFAULT_OWNER)
+    token = os.environ.get("BOT_BOTTLE_INFRA_ARTIFACT_TOKEN", "")
+    return base, owner, token
+
+
+def artifact_url(version: str, filename: str) -> str:
+    """The generic-package download URL for one file of this version's
+    artifact (`rootfs.ext4.gz` / `rootfs.ext4.gz.sha256`)."""
+    base, owner, _ = _config()
+    return f"{base}/api/packages/{owner}/generic/{_PACKAGE}/{version}/{filename}"
+
+
+_GZ_NAME = "rootfs.ext4.gz"
+_SHA_NAME = "rootfs.ext4.gz.sha256"
+
+
+def _cache_root(version: str) -> Path:
+    return util.cache_dir() / "infra-artifact" / version
+
+
+def _open(url: str) -> urllib.request.Request:
+    _, _, token = _config()
+    req = urllib.request.Request(url)
+    if token:
+        req.add_header("Authorization", f"token {token}")
+    return req
+
+
+def _download(url: str, dest: Path) -> None:
+    """Stream `url` to `dest` (atomic via a `.part` sibling)."""
+    tmp = dest.with_suffix(dest.suffix + ".part")
+    try:
+        with urllib.request.urlopen(_open(url)) as resp, open(tmp, "wb") as out:
+            shutil.copyfileobj(resp, out, _CHUNK)
+    except urllib.error.HTTPError as e:
+        tmp.unlink(missing_ok=True)
+        if e.code == 404:
+            die(
+                f"infra artifact not published for this code version.\n"
+                f"    missing: {url}\n"
+                f"    publish it from a build host (Docker):\n"
+                f"        python3 -m bot_bottle.backend.firecracker.publish_infra\n"
+                f"    or build the rootfs locally: BOT_BOTTLE_INFRA_BUILD=local"
+            )
+        die(f"downloading infra artifact failed (HTTP {e.code}): {url}")
+    except urllib.error.URLError as e:
+        tmp.unlink(missing_ok=True)
+        die(f"infra artifact registry unreachable: {url} ({e.reason})")
+    tmp.replace(dest)
+
+
+def _sha256_file(path: Path) -> str:
+    h = hashlib.sha256()
+    with open(path, "rb") as fh:
+        for chunk in iter(lambda: fh.read(_CHUNK), b""):
+            h.update(chunk)
+    return h.hexdigest()
+
+
+def ensure_artifact_gz(version: str) -> Path:
+    """The verified, cached `rootfs.ext4.gz` for `version` — downloading it (and
+    its `.sha256`) once, then reusing it. Fail-closed on a checksum mismatch:
+    the partial is removed and we die rather than boot an unverified rootfs."""
+    root = _cache_root(version)
+    root.mkdir(parents=True, exist_ok=True)
+    gz = root / _GZ_NAME
+    ok = root / ".verified"
+    if gz.is_file() and ok.is_file():
+        return gz
+
+    info(f"pulling infra rootfs artifact {_PACKAGE}/{version}")
+    _download(artifact_url(version, _GZ_NAME), gz)
+    sha = root / _SHA_NAME
+    _download(artifact_url(version, _SHA_NAME), sha)
+
+    expected = sha.read_text().split()[0].strip().lower()
+    actual = _sha256_file(gz)
+    if actual != expected:
+        gz.unlink(missing_ok=True)
+        sha.unlink(missing_ok=True)
+        die(
+            f"infra artifact checksum mismatch for {version}:\n"
+            f"    expected {expected}\n"
+            f"    actual   {actual}\n"
+            f"    refusing to boot an unverified rootfs."
+        )
+    ok.write_text("ok\n")
+    return gz
+
+
+def materialize_ext4(version: str, dest: Path) -> None:
+    """Ensure the verified artifact is cached, then gunzip it to `dest` — a
+    fresh, writable per-boot rootfs (the VM mutates it; the cached `.gz` stays
+    pristine). Atomic via a `.part` sibling."""
+    gz = ensure_artifact_gz(version)
+    tmp = dest.with_suffix(dest.suffix + ".part")
+    info(f"expanding infra rootfs -> {dest}")
+    with gzip.open(gz, "rb") as src, open(tmp, "wb") as out:
+        shutil.copyfileobj(src, out, _CHUNK)
+    tmp.replace(dest)

bot_bottle/backend/firecracker/infra_vm.py

@@ -35,7 +35,7 @@ from typing import Generator
 from ...log import die, info
 from ..docker import util as docker_mod
 from ..docker.gateway_provision import GatewayProvisionError
-from . import firecracker_vm, netpool, util
+from . import firecracker_vm, infra_artifact, netpool, util
 
 # The single infra-VM image: gateway data plane + baked control-plane source
 # (Dockerfile.infra FROM the gateway image). Built from source by default;
@@ -109,10 +109,26 @@ class InfraVm:
 
 
 def ensure_built() -> None:
-    """Build the infra image from source (bootstrap via host docker). The
+    """Ensure the infra rootfs is available before boot.
-    infra image `COPY --from`s the orchestrator image and is `FROM` the
+
-    gateway image, so both must exist first. A pull-from-registry mode
+    Default (docker-free, PRD 0069 Stage 2): download + verify the prebuilt
-    replaces this later."""
+    rootfs artifact matching this code version (see `infra_artifact`); the
+    launch host needs no Docker. `BOT_BOTTLE_INFRA_BUILD=local` instead builds
+    the three fixed images from source with host Docker — the infra image
+    `COPY --from`s the orchestrator image and is `FROM` the gateway image, so
+    both must exist first — for iterating on the Dockerfiles."""
+    if infra_artifact.local_build_requested():
+        build_infra_images_with_docker()
+        return
+    infra_artifact.ensure_artifact_gz(
+        infra_artifact.infra_artifact_version(_infra_init()))
+
+
+def build_infra_images_with_docker() -> None:
+    """Build the three fixed images from source with host Docker: orchestrator,
+    gateway, then the combined infra image (`COPY --from` orchestrator, `FROM`
+    gateway). The launch host uses this only in `BOT_BOTTLE_INFRA_BUILD=local`
+    mode; `publish_infra` uses it off-host to produce the published artifact."""
     docker_mod.build_image(
         _ORCHESTRATOR_IMAGE, str(_REPO_ROOT), dockerfile="Dockerfile.orchestrator")
     docker_mod.build_image(
@@ -190,10 +206,15 @@ def boot() -> InfraVm:
         die(f"orchestrator link {slot.iface} not present.\n"
             f"    ./cli.py backend setup --backend=firecracker")
 
-    base = build_infra_rootfs_dir()
     run_dir = _infra_dir()
     rootfs = run_dir / "rootfs.ext4"
-    util.build_rootfs_ext4(base, rootfs, slack_mib=8192)
+    if infra_artifact.local_build_requested():
+        util.build_rootfs_ext4(build_infra_rootfs_dir(), rootfs, slack_mib=8192)
+    else:
+        # Prebuilt artifact already carries the buildah build slack; expand it
+        # to a fresh writable rootfs for this boot.
+        infra_artifact.materialize_ext4(
+            infra_artifact.infra_artifact_version(_infra_init()), rootfs)
     private_key, pubkey = _stable_keypair()
 
     info(f"booting infra VM on {slot.iface} (guest {slot.guest_ip})")

bot_bottle/backend/firecracker/publish_infra.py

@@ -0,0 +1,169 @@
+"""Build the infra rootfs and publish it as a Gitea generic package.
+
+The off-host (build / CI) half of PRD 0069 Stage 2: this DOES use Docker, but
+never on the launch host. It runs the same pipeline the launch host used to run
+locally — `docker build` the three fixed images, export to a rootfs dir, inject
+the guest boot, `mke2fs` to an ext4 with the buildah build slack — then gzips
+the ext4 and PUTs it (plus a `.sha256`) to
+`…/api/packages/<owner>/generic/bot-bottle-firecracker-infra/<version>/`.
+
+The `<version>` is `infra_artifact.infra_artifact_version(...)`, the content
+hash of the rootfs inputs, so a launch host at the same code checkout resolves
+the exact artifact this produced.
+
+  python3 -m bot_bottle.backend.firecracker.publish_infra [--dry-run] [--force]
+
+Auth: a token with `write:package` on the target owner, from
+`BOT_BOTTLE_INFRA_ARTIFACT_TOKEN`.
+"""
+
+from __future__ import annotations
+
+import argparse
+import gzip
+import hashlib
+import shutil
+import sys
+import tempfile
+import urllib.error
+import urllib.request
+from pathlib import Path
+
+from . import infra_artifact, infra_vm, util
+
+_CHUNK = 1 << 20
+
+# A human-readable description shipped alongside the artifact — generic packages
+# have no description field, so this file *is* the description on the package
+# page. Uploaded on every publish so it never goes stale.
+_ABOUT_NAME = "about.txt"
+_ABOUT_TEXT = (
+    "bot-bottle infra rootfs for the Firecracker backend (PRD 0069 Stage 2, "
+    "#348): the per-host infra VM (orchestrator control plane + gateway + "
+    "buildah). Prebuilt off-host, gzip ext4; the launch host downloads + "
+    "sha256-verifies + boots it, no host Docker. The version tag is a content "
+    "hash of the rootfs inputs. Files: rootfs.ext4.gz + rootfs.ext4.gz.sha256.\n"
+)
+
+
+def _gzip(src: Path, dest: Path) -> None:
+    with open(src, "rb") as fh, gzip.open(dest, "wb") as out:
+        shutil.copyfileobj(fh, out, _CHUNK)
+
+
+def _sha256(path: Path) -> str:
+    h = hashlib.sha256()
+    with open(path, "rb") as fh:
+        for chunk in iter(lambda: fh.read(_CHUNK), b""):
+            h.update(chunk)
+    return h.hexdigest()
+
+
+def _put(url: str, body: "bytes | Path", token: str) -> None:
+    """PUT `body` (raw bytes, or a Path streamed from disk) to `url`. The rootfs
+    is hundreds of MB, so it is passed as a Path and streamed — `urlopen` reads
+    the open file in blocks rather than materializing it in memory (with an
+    explicit Content-Length, which Gitea requires and which also stops urllib
+    from `len()`-ing a non-bytes body)."""
+    handle = None
+    if isinstance(body, Path):
+        length = body.stat().st_size
+        handle = open(body, "rb")
+        data: object = handle
+    else:
+        length = len(body)
+        data = body
+    req = urllib.request.Request(url, data=data, method="PUT")  # type: ignore[arg-type]
+    req.add_header("Content-Length", str(length))
+    if token:
+        req.add_header("Authorization", f"token {token}")
+    req.add_header("Content-Type", "application/octet-stream")
+    try:
+        with urllib.request.urlopen(req) as resp:
+            print(f"  uploaded {url} (HTTP {resp.status})")
+    except urllib.error.HTTPError as e:
+        if e.code == 409:
+            raise SystemExit(
+                f"artifact already published at {url} (HTTP 409); "
+                f"bump the code version or pass --force to overwrite"
+            )
+        raise SystemExit(f"upload failed (HTTP {e.code}): {url}\n{e.read().decode(errors='replace')}")
+    except urllib.error.URLError as e:
+        raise SystemExit(f"registry unreachable: {url} ({e.reason})")
+    finally:
+        if handle is not None:
+            handle.close()
+
+
+def _delete(url: str, token: str) -> None:
+    req = urllib.request.Request(url, method="DELETE")
+    if token:
+        req.add_header("Authorization", f"token {token}")
+    try:
+        with urllib.request.urlopen(req):
+            pass
+    except urllib.error.HTTPError as e:
+        if e.code != 404:
+            raise SystemExit(f"could not overwrite existing artifact (HTTP {e.code}): {url}")
+    except urllib.error.URLError as e:
+        raise SystemExit(f"registry unreachable: {url} ({e.reason})")
+
+
+def build_artifact(out_dir: Path) -> tuple[str, Path, Path]:
+    """Build the infra rootfs ext4, gzip it, and write the checksum. Returns
+    `(version, gz_path, sha_path)`. Uses host Docker (off-host / CI)."""
+    version = infra_artifact.infra_artifact_version(infra_vm._infra_init())
+    print(f"building infra rootfs artifact {version} (docker)")
+    infra_vm.build_infra_images_with_docker()
+    base = infra_vm.build_infra_rootfs_dir()
+
+    ext4 = out_dir / "rootfs.ext4"
+    util.build_rootfs_ext4(base, ext4, slack_mib=8192)
+    gz = out_dir / "rootfs.ext4.gz"
+    print("compressing rootfs")
+    _gzip(ext4, gz)
+    ext4.unlink(missing_ok=True)
+
+    sha = out_dir / "rootfs.ext4.gz.sha256"
+    digest = _sha256(gz)
+    sha.write_text(f"{digest}  rootfs.ext4.gz\n")
+    print(f"  {gz.name}: {gz.stat().st_size / 1e6:.0f} MB  sha256={digest}")
+    return version, gz, sha
+
+
+def main(argv: list[str] | None = None) -> int:
+    parser = argparse.ArgumentParser(
+        prog="publish_infra", description="Build + publish the infra rootfs artifact.")
+    parser.add_argument("--dry-run", action="store_true",
+                        help="build the artifact but do not upload")
+    parser.add_argument("--force", action="store_true",
+                        help="overwrite an already-published artifact of this version")
+    args = parser.parse_args(argv)
+
+    _, _, token = infra_artifact._config()
+    if not args.dry_run and not token:
+        raise SystemExit(
+            "no publish token: set BOT_BOTTLE_INFRA_ARTIFACT_TOKEN to a token "
+            "with write:package")
+
+    with tempfile.TemporaryDirectory(prefix="bb-publish-infra.") as tmp:
+        version, gz, sha = build_artifact(Path(tmp))
+        gz_url = infra_artifact.artifact_url(version, gz.name)
+        sha_url = infra_artifact.artifact_url(version, sha.name)
+        about_url = infra_artifact.artifact_url(version, _ABOUT_NAME)
+        if args.dry_run:
+            print(f"dry-run: would upload -> {gz_url}")
+            return 0
+        if args.force:
+            _delete(gz_url, token)
+            _delete(sha_url, token)
+            _delete(about_url, token)
+        _put(gz_url, gz, token)  # streamed from disk (hundreds of MB)
+        _put(sha_url, sha.read_bytes(), token)  # tiny, in-memory is fine
+        _put(about_url, _ABOUT_TEXT.encode(), token)  # package description
+    print(f"published infra rootfs {version}")
+    return 0
+
+
+if __name__ == "__main__":
+    sys.exit(main())

docs/prds/0069-firecracker-native-docker-free.md

@@ -8,16 +8,20 @@
 > **Superseded in part by [PRD 0070](0070-per-host-orchestrator.md) (#351):**
 > the sidecar-consolidation framing here (Stage 1, per-host sidecar; Stage 4,
 > sidecar-as-VM) is taken over by 0070's per-host orchestrator. This PRD still
-> owns the docker-free **image-building** work — Stage 2 (nix-built fixed
+> owns the docker-free **image-provisioning** work — Stage 2 (pull the fixed
-> images, a dependency of 0070) and Stage 3 (in-VM Dockerfile builder).
+> images from an OCI registry instead of building them with host Docker, a
+> dependency of 0070) and Stage 3 (in-VM Dockerfile builder).
 
 ## Summary
 
 Make the Firecracker backend depend on **firecracker + KVM only**, removing
 Docker from the host. Two moves get us there: run the **sidecar bundle as a
 persistent, per-host service** (eventually a Firecracker VM) instead of a
-per-bottle container, and **build agent rootfs images without a host Docker
+per-bottle container, and **provision rootfs images without a host Docker
-daemon** (nix for the fixed images; an in-VM builder for user Dockerfiles).
+daemon** — pull the fixed images (orchestrator/gateway/infra) from an OCI
+registry and unpack them daemonlessly, and build user Dockerfiles in an in-VM
+builder. The images are still *built* with Docker, but off the launch host
+(CI / a publish step) and pushed to the registry; the launch host only pulls.
 
 ## Motivation
 
@@ -93,13 +97,51 @@ torn down at exit."
 Can ship as a container first (quick resource/ops win) and become a VM in
 Stage 4.
 
-### Stage 2 — Fixed images built with nix (no Docker)
+### Stage 2 — Fixed rootfs prebuilt + pulled as an artifact (no host Docker)
 
-The images bot-bottle *ships* — the sidecar, the agent base, and the builder
+The one fixed image the Firecracker backend needs at launch — the combined
-(Stage 3) — are built declaratively with nix (`nixos-generators` /
+**infra** rootfs the infra VM boots (orchestrator control plane + gateway +
-`make-ext4-fs` / `pkgs.dockerTools` for the rootfs), producing an ext4 or
+buildah, with the control-plane init as PID 1) — is **prebuilt end-to-end off
-tar with correct ownership. Removes Docker for everything we own and gives
+the launch host and published as a versioned, ready-to-boot ext4 artifact**.
-the rootless-rootfs correctness (#347) for free on these images.
+The launch host **downloads the `.ext4` and boots it directly** — no
+`docker build`, no `docker export`, no `mke2fs`, no image tooling at all.
+
+This is possible because the infra rootfs is already **host- and
+bottle-agnostic**: the per-boot bits (authorized_keys, guest IP) arrive on the
+**kernel cmdline**, not in the rootfs (see `build_base_rootfs_dir`). So one
+published ext4 boots on any launch host.
+
+- **Artifact.** `rootfs.ext4` + a `rootfs.ext4.sha256`, published as a Gitea
+  **generic package** (`bot-bottle-firecracker-infra/<tag>`) — generic packages take
+  arbitrary large binaries (no attachment size cap / file-type allowlist that
+  release attachments impose). The matching `vmlinux` kernel can ship the same
+  way, so the whole VM is fetchable.
+- **Pull.** The launch host `GET`s
+  `…/api/packages/<owner>/generic/bot-bottle-firecracker-infra/<tag>/rootfs.ext4` (+
+  `.sha256`) for its pinned tag, verifies the checksum, caches it under the
+  tag, and attaches it as the infra VM's root disk. Host prerequisite is an
+  HTTP client — nothing else. Public packages need no auth to pull; a token
+  with `read:package` covers a private instance.
+- **Registry.** The artifact base URL + owner are configurable, defaulting to
+  this deployment's Gitea (`https://gitea.dideric.is` / `didericis`);
+  overridable via env for other deployments / air-gapped mirrors.
+- **Versioning.** A pinned tag bumped when the infra rootfs contents change
+  (bot_bottle's shipped files, the base deps, or the init), so a launch host
+  pulls the artifact matching its code and a content change can't silently
+  boot a stale rootfs. A checksum mismatch fails closed.
+- **Publish.** A `publish` step (CLI subcommand / CI job) runs the full
+  pipeline **on a build/CI host** — `docker build` the three Dockerfiles →
+  export → inject guest boot → `mke2fs` → upload the `.ext4` + `.sha256`.
+  Building still uses Docker, but never on the launch/runner host, which is
+  the one #348 needs unprivileged.
+- **Dev escape hatch.** An explicit opt-in still builds the rootfs locally
+  with Docker (for iterating on the Dockerfiles without a publish
+  round-trip); it is never the default path.
+
+Removes Docker from the launch host entirely for the fixed image, and the
+launch host needs no OCI/rootfs tooling — just fetch + boot. The build-time
+cache / build-time-egress open problems a from-scratch build would face don't
+arise: the launch host never builds, it downloads a finished disk.
 
 ### Stage 3 — User Dockerfiles built in a builder VM (the unlock)
 

tests/unit/test_firecracker_infra_vm.py

@@ -7,6 +7,7 @@ decisions that must hold without a VM.
 
 from __future__ import annotations
 
+import os
 import unittest
 from pathlib import Path
 from unittest.mock import MagicMock, patch
@@ -95,8 +96,17 @@ class TestRegistryVolume(unittest.TestCase):
 
 
 class TestEnsureBuilt(unittest.TestCase):
-    def test_builds_deps_before_infra(self):
+    def test_default_pulls_artifact_without_docker(self):
-        with patch.object(infra_vm.docker_mod, "build_image") as build:
+        # PRD 0069 Stage 2: the launch host pulls the prebuilt rootfs; no Docker.
+        with patch.object(infra_vm.docker_mod, "build_image") as build, \
+                patch.object(infra_vm.infra_artifact, "ensure_artifact_gz") as pull:
+            infra_vm.ensure_built()
+        build.assert_not_called()
+        pull.assert_called_once()
+
+    def test_local_mode_builds_deps_before_infra(self):
+        with patch.dict(os.environ, {"BOT_BOTTLE_INFRA_BUILD": "local"}), \
+                patch.object(infra_vm.docker_mod, "build_image") as build:
             infra_vm.ensure_built()
         tags = [c.args[0] for c in build.call_args_list]
         # infra is FROM gateway and COPY --from orchestrator, so both first.

tests/unit/test_infra_artifact.py

@@ -0,0 +1,182 @@
+"""Unit: the prebuilt infra-rootfs artifact pull (PRD 0069 Stage 2).
+
+The launch-host half — version hashing and download/verify/decompress — is
+what keeps a docker-free host from booting a stale or corrupted rootfs, so the
+checksum + fail-closed paths are locked here. Network is mocked; no Docker.
+"""
+
+from __future__ import annotations
+
+import gzip
+import hashlib
+import io
+import os
+import tempfile
+import unittest
+import urllib.error
+import urllib.request
+from pathlib import Path
+from unittest import mock
+
+from bot_bottle.backend.firecracker import infra_artifact as ia
+from bot_bottle.log import Die
+
+
+def _gz(data: bytes) -> bytes:
+    return gzip.compress(data)
+
+
+class _FakeNet:
+    """Map artifact URLs to bytes (or an HTTPError) for urlopen."""
+
+    def __init__(self, responses: "dict[str, bytes | Exception]") -> None:
+        self._responses = responses
+        self.calls: list[str] = []
+
+    def urlopen(self, req: urllib.request.Request, *a: object, **k: object) -> io.BytesIO:
+        url = req.full_url
+        self.calls.append(url)
+        val = self._responses.get(url)
+        if isinstance(val, Exception):
+            raise val
+        if val is None:
+            raise urllib.error.HTTPError(url, 404, "not found", {}, None)  # type: ignore[arg-type]
+        return io.BytesIO(val)
+
+
+class _CacheMixin(unittest.TestCase):
+    def setUp(self) -> None:
+        self._tmp = tempfile.TemporaryDirectory()
+        self._env = mock.patch.dict(
+            os.environ,
+            {"BOT_BOTTLE_FC_CACHE": self._tmp.name,
+             "BOT_BOTTLE_INFRA_ARTIFACT_TOKEN": ""},
+            clear=False,
+        )
+        self._env.start()
+        self.addCleanup(self._env.stop)
+        self.addCleanup(self._tmp.cleanup)
+
+    def _serve(self, version: str, gz_bytes: bytes, sha_text: str | None = None):
+        if sha_text is None:
+            sha_text = f"{hashlib.sha256(gz_bytes).hexdigest()}  rootfs.ext4.gz\n"
+        net = _FakeNet({
+            ia.artifact_url(version, "rootfs.ext4.gz"): gz_bytes,
+            ia.artifact_url(version, "rootfs.ext4.gz.sha256"): sha_text.encode(),
+        })
+        return mock.patch.object(ia.urllib.request, "urlopen", net.urlopen), net
+
+
+class TestVersion(unittest.TestCase):
+    def test_deterministic_16_hex(self) -> None:
+        v = ia.infra_artifact_version("#!/bin/sh\ntrue\n")
+        self.assertEqual(v, ia.infra_artifact_version("#!/bin/sh\ntrue\n"))
+        self.assertEqual(16, len(v))
+        int(v, 16)  # hex
+
+    def test_init_change_bumps_version(self) -> None:
+        self.assertNotEqual(
+            ia.infra_artifact_version("a"), ia.infra_artifact_version("b"))
+
+
+class TestVersionInputs(unittest.TestCase):
+    """The hash must cover *every* file baked into the rootfs, not just `*.py`
+    (`COPY bot_bottle` is wholesale) — else a non-Python change (e.g. the egress
+    entrypoint shell script) leaves the version unchanged and a launch host
+    boots a rootfs whose code differs from its checkout."""
+
+    def _fake_repo(self, root: Path) -> None:
+        pkg = root / "bot_bottle"
+        pkg.mkdir()
+        (pkg / "app.py").write_text("print('hi')\n")
+        (pkg / "egress_entrypoint.sh").write_text("#!/bin/sh\nexec mitmdump\n")
+        (pkg / "netpool.defaults.env").write_text("FOO=1\n")
+        for name in ("Dockerfile.orchestrator", "Dockerfile.gateway", "Dockerfile.infra"):
+            (root / name).write_text(f"FROM scratch  # {name}\n")
+
+    def test_non_python_file_change_bumps_version(self) -> None:
+        with tempfile.TemporaryDirectory() as d:
+            root = Path(d)
+            self._fake_repo(root)
+            before = ia.infra_artifact_version("init", repo_root=root)
+            (root / "bot_bottle" / "egress_entrypoint.sh").write_text(
+                "#!/bin/sh\nexec mitmdump --different\n")
+            after = ia.infra_artifact_version("init", repo_root=root)
+        self.assertNotEqual(before, after)
+
+    def test_pyc_and_pycache_ignored(self) -> None:
+        with tempfile.TemporaryDirectory() as d:
+            root = Path(d)
+            self._fake_repo(root)
+            before = ia.infra_artifact_version("init", repo_root=root)
+            cache = root / "bot_bottle" / "__pycache__"
+            cache.mkdir()
+            (cache / "app.cpython-312.pyc").write_bytes(b"\x00bytecode")
+            (root / "bot_bottle" / "app.pyc").write_bytes(b"\x00bytecode")
+            after = ia.infra_artifact_version("init", repo_root=root)
+        self.assertEqual(before, after)
+
+
+class TestEnsureArtifact(_CacheMixin):
+    def test_downloads_verifies_and_caches(self) -> None:
+        version = "deadbeef00000000"
+        gz = _gz(b"fake ext4 bytes")
+        patcher, net = self._serve(version, gz)
+        with patcher:
+            path = ia.ensure_artifact_gz(version)
+            self.assertTrue(path.is_file())
+            self.assertEqual(gz, path.read_bytes())
+            first_calls = len(net.calls)
+            # Second call is a cache hit — no further network.
+            ia.ensure_artifact_gz(version)
+            self.assertEqual(first_calls, len(net.calls))
+
+    def test_checksum_mismatch_fails_closed(self) -> None:
+        version = "beefbeefbeefbeef"
+        gz = _gz(b"payload")
+        patcher, _ = self._serve(version, gz, sha_text="0" * 64 + "  rootfs.ext4.gz\n")
+        with patcher:
+            with self.assertRaises(Die) as ctx:
+                ia.ensure_artifact_gz(version)
+        self.assertIn("checksum mismatch", str(ctx.exception.message))
+        # nothing left cached to accidentally boot
+        self.assertFalse((ia._cache_root(version) / "rootfs.ext4.gz").exists())
+
+    def test_missing_artifact_points_at_publish(self) -> None:
+        version = "0000000000000000"
+        net = _FakeNet({})  # everything 404s
+        with mock.patch.object(ia.urllib.request, "urlopen", net.urlopen):
+            with self.assertRaises(Die) as ctx:
+                ia.ensure_artifact_gz(version)
+        self.assertIn("publish_infra", str(ctx.exception.message))
+
+    def test_materialize_gunzips_to_dest(self) -> None:
+        version = "1234123412341234"
+        raw = b"the real rootfs contents" * 100
+        patcher, _ = self._serve(version, _gz(raw))
+        with patcher, tempfile.TemporaryDirectory() as d:
+            dest = Path(d) / "rootfs.ext4"
+            ia.materialize_ext4(version, dest)
+            self.assertEqual(raw, dest.read_bytes())
+
+
+class TestConfig(unittest.TestCase):
+    def test_base_and_owner_overridable(self) -> None:
+        with mock.patch.dict(os.environ, {
+            "BOT_BOTTLE_INFRA_ARTIFACT_BASE": "https://mirror.example/",
+            "BOT_BOTTLE_INFRA_ARTIFACT_OWNER": "acme",
+        }):
+            url = ia.artifact_url("v1", "rootfs.ext4.gz")
+        self.assertEqual(
+            "https://mirror.example/api/packages/acme/generic/"
+            "bot-bottle-firecracker-infra/v1/rootfs.ext4.gz", url)
+
+    def test_local_build_flag(self) -> None:
+        with mock.patch.dict(os.environ, {"BOT_BOTTLE_INFRA_BUILD": "local"}):
+            self.assertTrue(ia.local_build_requested())
+        with mock.patch.dict(os.environ, {"BOT_BOTTLE_INFRA_BUILD": ""}):
+            self.assertFalse(ia.local_build_requested())
+
+
+if __name__ == "__main__":
+    unittest.main()

tests/unit/test_publish_infra.py

@@ -0,0 +1,62 @@
+"""Unit: the infra-artifact publisher's upload path (PRD 0069 Stage 2).
+
+The rootfs is hundreds of MB, so `_put` must stream it from disk rather than
+read it into memory. Network is mocked; no Docker, no real build.
+"""
+
+from __future__ import annotations
+
+import tempfile
+import unittest
+import urllib.request
+from pathlib import Path
+from unittest import mock
+
+from bot_bottle.backend.firecracker import publish_infra as pub
+
+
+class _Resp:
+    status = 201
+
+    def __enter__(self) -> "_Resp":
+        return self
+
+    def __exit__(self, *a: object) -> bool:
+        return False
+
+
+class TestPut(unittest.TestCase):
+    def test_streams_file_body_with_content_length(self) -> None:
+        captured: list[urllib.request.Request] = []
+
+        def fake_urlopen(req: urllib.request.Request, *a: object, **k: object) -> _Resp:
+            captured.append(req)
+            return _Resp()
+
+        with tempfile.TemporaryDirectory() as d:
+            f = Path(d) / "rootfs.ext4.gz"
+            payload = b"x" * 4096
+            f.write_bytes(payload)
+            with mock.patch.object(pub.urllib.request, "urlopen", fake_urlopen):
+                pub._put("https://reg/pkg", f, token="t")
+
+        req = captured[0]
+        # Body is the open file object (streamed), never the bytes in memory.
+        self.assertTrue(hasattr(req.data, "read"))
+        self.assertNotIsInstance(req.data, (bytes, bytearray))
+        self.assertEqual(str(len(payload)), req.get_header("Content-length"))
+
+    def test_small_bytes_body_still_works(self) -> None:
+        captured: list[urllib.request.Request] = []
+
+        def fake_urlopen(req: urllib.request.Request, *a: object, **k: object) -> _Resp:
+            captured.append(req)
+            return _Resp()
+
+        with mock.patch.object(pub.urllib.request, "urlopen", fake_urlopen):
+            pub._put("https://reg/sha", b"abc123  rootfs\n", token="")
+        self.assertEqual(b"abc123  rootfs\n", captured[0].data)
+
+
+if __name__ == "__main__":
+    unittest.main()