fix(orchestrator): only recreate the orchestrator on a real source change
test / unit (pull_request) Successful in 1m7s
test / integration (pull_request) Successful in 20s
test / coverage (pull_request) Successful in 1m19s
lint / lint (push) Successful in 2m7s
test / unit (push) Successful in 1m11s
test / integration (push) Successful in 28s
test / coverage (push) Successful in 1m18s
Update Quality Badges / update-badges (push) Successful in 1m9s
test / unit (pull_request) Successful in 1m7s
test / integration (pull_request) Successful in 20s
test / coverage (pull_request) Successful in 1m19s
lint / lint (push) Successful in 2m7s
test / unit (push) Successful in 1m11s
test / integration (push) Successful in 28s
test / coverage (push) Successful in 1m18s
Update Quality Badges / update-badges (push) Successful in 1m9s
ensure_running() unconditionally recreated the bot-bottle-orchestrator container on every bottle launch, added so bind-mounted code changes take effect (the process never reloads). But the orchestrator's per-bottle egress auth tokens live only in its process memory (Orchestrator._tokens), by design never persisted to disk. So starting a second bottle recreated the container and silently dropped the FIRST bottle's already-injected token -- its next authed egress call 403s with "env var EGRESS_TOKEN_0 is unset", and it needs a full restart to recover. Now the orchestrator container is labeled with a content hash of its bind-mounted bot_bottle source, mirroring the gateway's existing image-staleness check. ensure_running only recreates on a hash mismatch (a real code change), so a bottle launch that isn't accompanied by a code change leaves a healthy orchestrator -- and every other active bottle's in-memory tokens -- alone. Fixes #381. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
This commit was merged in pull request #382.
This commit is contained in:
@@ -16,6 +16,7 @@ names + the published port).
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import hashlib
|
||||
import time
|
||||
import urllib.error
|
||||
import urllib.request
|
||||
@@ -29,6 +30,10 @@ from .gateway import GATEWAY_IMAGE, GATEWAY_NETWORK, DockerGateway
|
||||
DEFAULT_PORT = 8099
|
||||
ORCHESTRATOR_NAME = "bot-bottle-orchestrator"
|
||||
ORCHESTRATOR_LABEL = "bot-bottle-orchestrator=1"
|
||||
# Baked onto the container as a label so `ensure_running` can tell whether the
|
||||
# running process is executing the *current* bind-mounted source — see
|
||||
# `_source_hash`.
|
||||
ORCHESTRATOR_SOURCE_HASH_LABEL = "bot-bottle-orchestrator-source-hash"
|
||||
|
||||
# The repo root is bind-mounted into the control-plane container so
|
||||
# `python -m bot_bottle.orchestrator` resolves the package (the orchestrator
|
||||
@@ -46,6 +51,22 @@ class OrchestratorStartError(RuntimeError):
|
||||
"""The orchestrator container did not become healthy within the timeout."""
|
||||
|
||||
|
||||
def _source_hash(repo_root: Path) -> str:
|
||||
"""Content hash of the orchestrator's bind-mounted Python source (the
|
||||
`bot_bottle` package the control-plane process imports). This only
|
||||
changes when the code that would actually run inside the container
|
||||
changes — `ensure_running` recreates the container on a mismatch and
|
||||
otherwise leaves a healthy one alone, so a bottle launch that isn't
|
||||
accompanied by a code change doesn't restart the process and drop every
|
||||
*other* active bottle's in-memory egress tokens (`Orchestrator._tokens`
|
||||
in `service.py`, never persisted to disk by design)."""
|
||||
h = hashlib.sha256()
|
||||
for path in sorted((repo_root / "bot_bottle").rglob("*.py")):
|
||||
h.update(str(path.relative_to(repo_root)).encode())
|
||||
h.update(path.read_bytes())
|
||||
return h.hexdigest()
|
||||
|
||||
|
||||
class OrchestratorService:
|
||||
"""Manages the orchestrator control-plane container + the shared gateway.
|
||||
Callers only need `ensure_running()` + `url`."""
|
||||
@@ -88,14 +109,17 @@ class OrchestratorService:
|
||||
proc = run_docker(["docker", "ps", "--filter", f"name=^/{name}$", "--format", "{{.Names}}"])
|
||||
return name in proc.stdout.split()
|
||||
|
||||
def _run_orchestrator_container(self) -> None:
|
||||
def _run_orchestrator_container(self, source_hash: str) -> None:
|
||||
"""Start the control-plane container (idempotent: clears a stale
|
||||
fixed-name container first). Register-only broker → no docker socket."""
|
||||
fixed-name container first). Register-only broker → no docker socket.
|
||||
Labels the container with `source_hash` so a later `ensure_running`
|
||||
can detect a real code change (see `_source_hash`)."""
|
||||
run_docker(["docker", "rm", "--force", ORCHESTRATOR_NAME])
|
||||
proc = run_docker([
|
||||
"docker", "run", "--detach",
|
||||
"--name", ORCHESTRATOR_NAME,
|
||||
"--label", ORCHESTRATOR_LABEL,
|
||||
"--label", f"{ORCHESTRATOR_SOURCE_HASH_LABEL}={source_hash}",
|
||||
"--network", self.network,
|
||||
# Host CLI reaches the control plane here; bound to loopback so it
|
||||
# is not exposed on the host's external interfaces.
|
||||
@@ -119,26 +143,46 @@ class OrchestratorService:
|
||||
def _gateway(self) -> DockerGateway:
|
||||
return DockerGateway(self.image, network=self.network, orchestrator_url=self.internal_url)
|
||||
|
||||
def _orchestrator_source_current(self, current_hash: str) -> bool:
|
||||
"""True iff the running orchestrator container was created from the
|
||||
*current* bind-mounted source. Mirrors `DockerGateway`'s
|
||||
image-staleness check, but by content hash rather than image id since
|
||||
the orchestrator runs bind-mounted source, not a built image."""
|
||||
if not self._container_running(ORCHESTRATOR_NAME):
|
||||
return False
|
||||
proc = run_docker([
|
||||
"docker", "inspect", "--format",
|
||||
"{{ index .Config.Labels \"" + ORCHESTRATOR_SOURCE_HASH_LABEL + "\" }}",
|
||||
ORCHESTRATOR_NAME,
|
||||
])
|
||||
if proc.returncode != 0:
|
||||
return True # can't compare -> don't churn a working container
|
||||
return proc.stdout.strip() == current_hash
|
||||
|
||||
def ensure_running(
|
||||
self, *, startup_timeout: float = DEFAULT_STARTUP_TIMEOUT_SECONDS,
|
||||
) -> str:
|
||||
"""Ensure the control plane + shared gateway are up; return the host
|
||||
control-plane URL. Idempotent — a healthy control plane and a running
|
||||
gateway are left untouched. Raises `OrchestratorStartError` on
|
||||
timeout."""
|
||||
control-plane URL. Idempotent — a healthy control plane running
|
||||
current code and a running gateway are left untouched. Raises
|
||||
`OrchestratorStartError` on timeout."""
|
||||
gateway = self._gateway()
|
||||
gateway.ensure_built() # rebuild the bundle image on a source change
|
||||
gateway.ensure_running() # creates the shared network + (re)starts gateway
|
||||
|
||||
# Always (re)create the orchestrator container. It runs the repo's code
|
||||
# bind-mounted, but the Python process loaded that code at startup and
|
||||
# won't reload — so reusing a healthy-but-stale container would keep
|
||||
# running OLD control-plane code (e.g. dropping the tokens field). Cheap
|
||||
# (~seconds); the registry DB persists and the current launch
|
||||
# re-registers its own in-memory state. (The dedicated orchestrator
|
||||
# image follow-up replaces this with image-staleness detection.)
|
||||
# Recreate the orchestrator container only when its bind-mounted
|
||||
# source has actually changed since it started — its Python process
|
||||
# loaded that code at startup and won't reload, so a stale container
|
||||
# would keep running OLD control-plane code. Recreating on *every*
|
||||
# launch (the prior behaviour) would drop every other active
|
||||
# bottle's in-memory egress tokens each time a new bottle starts,
|
||||
# since the orchestrator process holds them only in memory (#381).
|
||||
current_hash = _source_hash(self._repo_root)
|
||||
if self.is_healthy() and self._orchestrator_source_current(current_hash):
|
||||
return self.url
|
||||
|
||||
log.info("starting orchestrator container", context={"name": ORCHESTRATOR_NAME})
|
||||
self._run_orchestrator_container()
|
||||
self._run_orchestrator_container(current_hash)
|
||||
|
||||
deadline = time.monotonic() + startup_timeout
|
||||
while time.monotonic() < deadline:
|
||||
|
||||
Reference in New Issue
Block a user