claude_bottle/backend/smolmachines/launch.py

@@ -21,6 +21,7 @@ from __future__ import annotations
 
 import dataclasses
 import os
+import time
 from contextlib import ExitStack, contextmanager
 from typing import Callable, Generator
 
@@ -34,6 +35,7 @@ from ...util import expand_tilde
 from ..docker.egress import (
     EGRESS_CA_IN_CONTAINER,
     EGRESS_PIPELOCK_CA_IN_CONTAINER,
+    EGRESS_PORT as _EGRESS_PORT,
     egress_tls_init,
 )
 from ..docker.git_gate import (
@@ -125,8 +127,22 @@ def launch(
         # reachable from the smolvm guest on macOS — TSI uses
         # macOS networking, and macOS sees the daemon's bridge
         # via the published-port loopback forward only.
-        pipelock_host_port = _bundle.bundle_host_port(plan.slug, _PIPELOCK_PORT)
+        #
-        agent_proxy_url = f"http://127.0.0.1:{pipelock_host_port}"
+        # Proxy hop order matches the docker backend: when the
+        # bottle declares egress routes, the agent's first hop is
+        # egress (for token injection), then pipelock. Without
+        # routes, the agent dials pipelock directly. Whichever
+        # one is "agent-facing" is the daemon whose port we
+        # publish on host loopback; the other stays bundle-
+        # internal as the upstream proxy.
+        if plan.egress_plan.routes:
+            agent_facing_port = _EGRESS_PORT
+        else:
+            agent_facing_port = _PIPELOCK_PORT
+        agent_facing_host_port = _bundle.bundle_host_port(
+            plan.slug, agent_facing_port,
+        )
+        agent_proxy_url = f"http://127.0.0.1:{agent_facing_host_port}"
         agent_git_gate_host = ""
         if plan.git_gate_plan.upstreams:
             git_gate_host_port = _bundle.bundle_host_port(
@@ -189,6 +205,14 @@ def launch(
             ["chown", "-R", "node:node", "/home/node"],
         )
 
+        # Wait briefly for the VM to settle. Back-to-back smolvm
+        # machine_exec calls immediately after machine_start
+        # occasionally SIGKILL the in-VM child at ~100ms (looks
+        # like a VM warm-up race in libkrun's exec channel).
+        # 1.5s is empirically enough to dodge it; provisioning
+        # already takes seconds so the wait is amortized.
+        time.sleep(1.5)
+
         # 7. Provision (CA / prompt / skills / git / supervise).
         prompt_path = provision(plan, plan.machine_name)
 
@@ -220,9 +244,14 @@ def _bundle_launch_spec(
     env: list[str] = []
     volumes: list[tuple[str, str, bool]] = []
 
-    # PRD 0023 chunk 3: egress binds 127.0.0.1 inside the bundle
+    # In this Docker-Desktop-compatible topology, whichever daemon
-    # so TSI's IP-only allowlist can't bypass pipelock.
+    # is "agent-facing" gets its port published on the host
-    env.append("EGRESS_LISTEN_HOST=127.0.0.1")
+    # loopback (see `_ensure_smolmachine`'s discovery loop) and the
+    # other stays bundle-internal. The bundle is NOT reachable by
+    # bridge IP from the smolvm guest, so the
+    # PRD-0023-chunk-3 EGRESS_LISTEN_HOST=127.0.0.1 mitigation
+    # isn't needed: the agent can only dial whatever daemon's
+    # host port we publish, period.
 
     # --- pipelock ---------------------------------------------
     pp = plan.proxy_plan
@@ -279,9 +308,14 @@ def _bundle_launch_spec(
 
     # Container ports the agent reaches from the smolvm guest —
     # published on host loopback so the guest can dial via TSI +
-    # macOS networking. Egress is bundle-internal and never
+    # macOS networking. The HTTP/HTTPS chokepoint is whichever
-    # published.
+    # daemon's port we publish: egress when routes are declared
-    ports_to_publish: list[int] = [_PIPELOCK_PORT]
+    # (token injection first, then forwards to bundle-internal
+    # pipelock), pipelock otherwise.
+    if ep.routes:
+        ports_to_publish: list[int] = [_EGRESS_PORT]
+    else:
+        ports_to_publish = [_PIPELOCK_PORT]
     if gp.upstreams:
         ports_to_publish.append(_GIT_GATE_PORT)
     if sp is not None:

claude_bottle/backend/smolmachines/provision/ca.py

@@ -66,8 +66,29 @@ def provision_ca(plan: SmolmachinesBottlePlan, target: str) -> None:
     # default. The env trio (NODE_EXTRA_CA_CERTS / SSL_CERT_FILE /
     # REQUESTS_CA_BUNDLE) on the guest_env covers Node + Python
     # `requests` / libraries that don't load the system bundle.
-    _smolvm.machine_exec(target, ["chmod", "644", AGENT_CA_PATH])
+    #
-    _smolvm.machine_exec(target, ["update-ca-certificates"])
+    # chown + chmod + update-ca-certificates run in one
+    # `sh -c` so we only pay one machine_exec round trip; the
+    # `&&` chaining surfaces the first failure as the return
+    # code.
+    r = _smolvm.machine_exec(target, [
+        "sh", "-c",
+        f"chown root:root {AGENT_CA_PATH} && "
+        f"chmod 644 {AGENT_CA_PATH} && "
+        f"update-ca-certificates",
+    ])
+    if r.returncode != 0 or "1 added" not in (r.stdout or ""):
+        # update-ca-certificates not adding our cert is fatal —
+        # claude-code's TLS handshake against the egress-MITM'd
+        # api.anthropic.com would fail downstream. Bail early
+        # with what we can see (output is captured by smolvm so
+        # we can surface it).
+        die(
+            f"update-ca-certificates didn't add the agent CA "
+            f"(exit {r.returncode}): "
+            f"stdout={(r.stdout or '').strip()!r} "
+            f"stderr={(r.stderr or '').strip()!r}"
+        )
 
     # Stdlib SHA-256 of the cert's DER bytes — the standard
     # fingerprint form. Never the private key.

tests/unit/test_smolmachines_provision.py

@@ -307,21 +307,38 @@ class TestProvisionCA(unittest.TestCase):
     def tearDown(self):
         self._tmp.cleanup()
 
+    # provision_ca dies hard if update-ca-certificates' stdout
+    # doesn't include "1 added"; supply a stock success return
+    # so the bulk of the tests below exercise the happy path.
+    _UPDATE_OK = SmolvmRunResult(
+        returncode=0,
+        stdout="Updating certificates in /etc/ssl/certs...\n1 added, 0 removed; done.\n",
+        stderr="",
+    )
+
     def test_pipelock_path_when_no_routes(self):
         plan = _plan(pipelock_ca_path=self.pipelock_ca)
         with patch(
             "claude_bottle.backend.smolmachines.provision.ca._smolvm.machine_cp"
         ) as cp, patch(
-            "claude_bottle.backend.smolmachines.provision.ca._smolvm.machine_exec"
+            "claude_bottle.backend.smolmachines.provision.ca._smolvm.machine_exec",
+            return_value=self._UPDATE_OK,
         ) as ex:
             _ca.provision_ca(plan, "claude-bottle-demo-abc12")
         cp.assert_called_once_with(
             str(self.pipelock_ca),
             "claude-bottle-demo-abc12:" + _ca.AGENT_CA_PATH,
         )
-        argvs = [c.args[1] for c in ex.call_args_list]
+        # chmod + chown + update-ca-certificates are now folded
-        self.assertIn(["chmod", "644", _ca.AGENT_CA_PATH], argvs)
+        # into one `sh -c` invocation (working around a smolvm
-        self.assertIn(["update-ca-certificates"], argvs)
+        # exec warm-up SIGKILL race), so we look at the single
+        # exec's argv rather than expecting separate calls.
+        ex.assert_called_once()
+        argv = ex.call_args.args[1]
+        self.assertEqual("sh", argv[0])
+        self.assertEqual("-c", argv[1])
+        self.assertIn("chmod 644", argv[2])
+        self.assertIn("update-ca-certificates", argv[2])
 
     def test_egress_path_when_routes_declared(self):
         plan = _plan(
@@ -332,7 +349,8 @@ class TestProvisionCA(unittest.TestCase):
         with patch(
             "claude_bottle.backend.smolmachines.provision.ca._smolvm.machine_cp"
         ) as cp, patch(
-            "claude_bottle.backend.smolmachines.provision.ca._smolvm.machine_exec"
+            "claude_bottle.backend.smolmachines.provision.ca._smolvm.machine_exec",
+            return_value=self._UPDATE_OK,
         ):
             _ca.provision_ca(plan, "claude-bottle-demo-abc12")
         # When routes are declared, egress is the agent's first hop,