bot_bottle/backend/firecracker/infra_artifact.py

@@ -57,24 +57,34 @@ def local_build_requested() -> bool:
     return os.environ.get("BOT_BOTTLE_INFRA_BUILD", "").strip().lower() == "local"
 
 
-def infra_artifact_version(init_script: str) -> str:
+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 infra image `COPY`s it wholesale),
-    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."""
+    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("*.py")):
-        if "__pycache__" in path.parts:
+    pkg = repo_root / "bot_bottle"
+    for path in sorted(pkg.rglob("*")):
+        if not path.is_file():
             continue
-        h.update(str(path.relative_to(_REPO_ROOT)).encode())
+        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:
-        p = _REPO_ROOT / name
         h.update(name.encode())
-        h.update(p.read_bytes())
+        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]

bot_bottle/backend/firecracker/publish_infra.py

@@ -47,8 +47,22 @@ def _sha256(path: Path) -> str:
     return h.hexdigest()
 
 
-def _put(url: str, body: bytes, token: str) -> None:
-    req = urllib.request.Request(url, data=body, method="PUT")
+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")
@@ -64,6 +78,9 @@ def _put(url: str, body: bytes, token: str) -> None:
         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:
@@ -127,8 +144,8 @@ def main(argv: list[str] | None = None) -> int:
         if args.force:
             _delete(gz_url, token)
             _delete(sha_url, token)
-        _put(gz_url, gz.read_bytes(), token)
-        _put(sha_url, sha.read_bytes(), token)
+        _put(gz_url, gz, token)  # streamed from disk (hundreds of MB)
+        _put(sha_url, sha.read_bytes(), token)  # tiny, in-memory is fine
     print(f"published infra rootfs {version}")
     return 0
 

tests/unit/test_infra_artifact.py

@@ -79,6 +79,44 @@ class TestVersion(unittest.TestCase):
             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"

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()