d75d5f3e48
apply_routes_change wrote the proposed routes via
`tempfile.mkstemp` (default mode 0600) then `docker cp`'d into the
egress-proxy container. docker cp preserves mode + host uid, so
the file landed inside the container as 0600 owned by the host
user's uid — which is not the mitmproxy user (uid 1000) the
addon runs as. The SIGHUP-triggered reload then failed with
PermissionError on the re-read, the old routes table stayed in
memory, and the operator-approved route never took effect.
Symptoms reported:
- Operator approves egress-proxy-block proposal that adds
google.com to routes.
- Agent retries `curl https://google.com` and still gets 403
"egress-proxy: host 'google.com' is not in the bottle's
egress_proxy.routes allowlist."
- `docker exec <egress-proxy> cat /etc/egress-proxy/routes.yaml`
returns "Permission denied" (mitmproxy user can't read it,
so the reload couldn't either).
Fix: chmod 0644 on the host tmp file before docker cp. Mirrors
the same pattern in DockerEgressProxy.start which already chmods
the original routes.yaml + the CAs before cp. The proposed routes
content carries no secrets (tokens live in the egress-proxy
container's environ, not the routes file), so 0644 in /tmp for
the brief window between write and cp is safe.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
128 lines
4.8 KiB
Python
128 lines
4.8 KiB
Python
"""Host-side helper to apply a routes.yaml change to a running
|
|
egress-proxy sidecar (PRD 0014 retargeted by PRD 0017 chunk 3).
|
|
|
|
Used by the supervise dashboard when the operator approves an
|
|
egress-proxy-block proposal (or runs the operator-initiated
|
|
`routes edit <bottle>` verb). Fetches the current routes.yaml via
|
|
`docker exec cat`, validates the new content, writes it into the
|
|
sidecar via `docker cp`, then `docker kill --signal HUP` to make
|
|
the addon reload without dropping connections.
|
|
|
|
Raises EgressProxyApplyError on any failure — the dashboard
|
|
surfaces the message and keeps the proposal pending so the
|
|
operator can retry.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import os
|
|
import subprocess
|
|
import tempfile
|
|
from pathlib import Path
|
|
|
|
from ...egress_proxy import EGRESS_PROXY_ROUTES_IN_CONTAINER
|
|
from ...egress_proxy_addon_core import load_routes
|
|
from .egress_proxy import egress_proxy_container_name
|
|
|
|
|
|
class EgressProxyApplyError(RuntimeError):
|
|
"""Raised when fetch / apply fails. Caller renders to the
|
|
operator; does not crash the dashboard."""
|
|
|
|
|
|
def fetch_current_routes(slug: str) -> str:
|
|
"""Read the live routes.yaml from the running egress-proxy sidecar
|
|
for `slug`. Returns the file content as a string. Raises
|
|
EgressProxyApplyError if the sidecar isn't reachable or the read
|
|
fails."""
|
|
container = egress_proxy_container_name(slug)
|
|
r = subprocess.run(
|
|
["docker", "exec", container, "cat", EGRESS_PROXY_ROUTES_IN_CONTAINER],
|
|
capture_output=True, text=True, check=False,
|
|
)
|
|
if r.returncode != 0:
|
|
raise EgressProxyApplyError(
|
|
f"could not read routes.yaml from {container}: "
|
|
f"{(r.stderr or '').strip() or 'container not running?'}"
|
|
)
|
|
return r.stdout
|
|
|
|
|
|
def validate_routes_content(content: str) -> None:
|
|
"""Syntactic check before SIGHUP — the addon's reload also
|
|
validates, but failing here keeps the old routes live and gives
|
|
the operator a clearer error than the addon's stderr line."""
|
|
try:
|
|
load_routes(content)
|
|
except ValueError as e:
|
|
raise EgressProxyApplyError(
|
|
f"proposed routes.yaml is not valid: {e}"
|
|
) from e
|
|
|
|
|
|
def apply_routes_change(slug: str, new_content: str) -> tuple[str, str]:
|
|
"""Apply `new_content` to the egress-proxy sidecar for `slug`:
|
|
1. Fetch current routes.yaml (for the before-diff).
|
|
2. Validate the new content via the addon's own parser.
|
|
3. Write to a temp file, `docker cp` into the sidecar.
|
|
4. `docker kill --signal HUP` so the addon reloads.
|
|
|
|
Returns (before, after) where `after` == `new_content`. Raises
|
|
EgressProxyApplyError on any step; the existing routes in the
|
|
sidecar are unchanged if the failure is before docker cp, and
|
|
are reverted in spirit if SIGHUP fails (cp landed but reload
|
|
didn't fire — caller's next attempt will SIGHUP again)."""
|
|
container = egress_proxy_container_name(slug)
|
|
before = fetch_current_routes(slug)
|
|
validate_routes_content(new_content)
|
|
|
|
fd, tmp_path = tempfile.mkstemp(prefix="cb-routes.", suffix=".yaml")
|
|
try:
|
|
with os.fdopen(fd, "w") as f:
|
|
f.write(new_content)
|
|
# mkstemp creates the file with mode 0600. `docker cp`
|
|
# preserves mode + host uid into the container, so without
|
|
# chmod the file lands as 0600 owned by the host user's uid,
|
|
# which inside the container is not mitmproxy (uid 1000) —
|
|
# the addon's reload then fails with PermissionError on the
|
|
# SIGHUP-triggered re-read and the old routes table stays in
|
|
# memory. Bump to 0644 so mitmproxy can read it post-cp;
|
|
# the host stage_dir doesn't apply to this tmp file but the
|
|
# content isn't secret (no tokens — those live in the
|
|
# container's environ), so 0644 in /tmp is fine.
|
|
os.chmod(tmp_path, 0o644)
|
|
cp = subprocess.run(
|
|
["docker", "cp", tmp_path,
|
|
f"{container}:{EGRESS_PROXY_ROUTES_IN_CONTAINER}"],
|
|
capture_output=True, text=True, check=False,
|
|
)
|
|
if cp.returncode != 0:
|
|
raise EgressProxyApplyError(
|
|
f"failed to copy routes.yaml into {container}: "
|
|
f"{(cp.stderr or '').strip()}"
|
|
)
|
|
sig = subprocess.run(
|
|
["docker", "kill", "--signal", "HUP", container],
|
|
capture_output=True, text=True, check=False,
|
|
)
|
|
if sig.returncode != 0:
|
|
raise EgressProxyApplyError(
|
|
f"failed to SIGHUP {container}: "
|
|
f"{(sig.stderr or '').strip()}"
|
|
)
|
|
finally:
|
|
try:
|
|
Path(tmp_path).unlink()
|
|
except OSError:
|
|
pass
|
|
|
|
return before, new_content
|
|
|
|
|
|
__all__ = [
|
|
"EgressProxyApplyError",
|
|
"apply_routes_change",
|
|
"fetch_current_routes",
|
|
"validate_routes_content",
|
|
]
|