fix(firecracker): hash all baked-in files + stream the artifact upload
lint / lint (push) Successful in 2m26s
test / unit (pull_request) Successful in 1m44s
test / integration (pull_request) Successful in 40s
test / coverage (pull_request) Successful in 1m32s

Address PR #395 review (two P1s):

- Version hash covered only `bot_bottle/**.py`, but the image `COPY`s the
  whole package — non-Python inputs baked in (egress_entrypoint.sh,
  netpool.defaults.env) didn't change the version, so a launch host could
  boot a stale rootfs whose code differs from its checkout. Hash every
  regular file under bot_bottle/ (excluding __pycache__/.pyc). Regression
  tests: a shell-script change bumps the version; .pyc/__pycache__ don't.

- publish_infra `_put` read the whole (hundreds-of-MB) gz into memory via
  read_bytes(). Stream it from disk with an explicit Content-Length; the
  tiny .sha256 stays in-memory. Test asserts the body is the file object,
  not bytes.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01UoEZHDjv84ChoZbozQERhJ
This commit is contained in:
2026-07-16 23:46:23 -04:00
parent 8d8a88aeeb
commit f2891a1634
4 changed files with 142 additions and 15 deletions
@@ -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