fix(backend): extract poll_ca_cert helper and fix PRD port docs

Extract the shared CA cert polling loop into `backend/util.poll_ca_cert`
(firecracker and macos backends were duplicating deadline/sleep/raise logic).
Each caller now wraps a fetch lambda and converts TimeoutError to its own
error type. Also corrects the PRD port publication line from {port}:{port}
to {host_port}:8099.

bot_bottle/backend/firecracker/infra_vm.py

@@ -33,6 +33,7 @@ from pathlib import Path
 from typing import Generator
 
 from ...log import die, info
+from .. import util as backend_util
 from ..docker import util as docker_mod
 from ..docker.gateway_provision import GatewayProvisionError
 from . import firecracker_vm, infra_artifact, netpool, util
@@ -93,19 +94,18 @@ class InfraVm:
         """The gateway's mitmproxy CA (PEM) that agents install to trust its
         TLS interception. Generated a moment after boot, so this polls over
         SSH until it appears (mirrors DockerGateway.ca_cert_pem)."""
-        deadline = time.monotonic() + timeout
+        def _fetch() -> str | None:
-        while True:
             proc = subprocess.run(
                 util.ssh_base_argv(self.private_key, self.guest_ip)
                 + [f"cat {_GATEWAY_CA_PATH}"],
                 capture_output=True, text=True, timeout=15, check=False,
             )
-            if proc.returncode == 0 and "BEGIN CERTIFICATE" in proc.stdout:
+            ok = proc.returncode == 0 and "BEGIN CERTIFICATE" in proc.stdout
-                return proc.stdout
+            return proc.stdout if ok else None
-            if time.monotonic() >= deadline:
+        try:
-                die(f"gateway CA not available after {timeout:g}s: "
+            return backend_util.poll_ca_cert(_fetch, timeout=timeout)
-                    f"{proc.stderr.strip() or 'empty'}")
+        except TimeoutError as exc:
-            time.sleep(_HEALTH_POLL_SECONDS)
+            die(str(exc))
 
 
 def ensure_built() -> None:

bot_bottle/backend/macos_container/infra.py

@@ -53,6 +53,7 @@ from ...paths import (
     HOST_DB_FILENAME,
     host_control_plane_token,
 )
+from .. import util as backend_util
 from . import util as container_mod
 from .gateway import (
     DEFAULT_CA_TIMEOUT_SECONDS,
@@ -263,18 +264,16 @@ class MacosInfraService:
         interception. Read out of the container (the CA lives on a
         container-internal path, not a host mount); polls because mitmproxy
         writes it a beat after start."""
-        deadline = time.monotonic() + timeout
+        def _fetch() -> str | None:
-        while True:
             result = container_mod.run_container_argv(
                 ["container", "exec", self._name, "cat", GATEWAY_CA_CERT])
-            if result.returncode == 0 and result.stdout.strip():
+            return result.stdout if result.returncode == 0 and result.stdout.strip() else None
-                return result.stdout
+        try:
-            if time.monotonic() >= deadline:
+            return backend_util.poll_ca_cert(_fetch, timeout=timeout)
-                raise GatewayError(
+        except TimeoutError as exc:
-                    f"gateway CA not available in {self._name} after {timeout:g}s: "
+            raise GatewayError(
-                    f"{(result.stderr or '').strip() or 'empty'}"
+                f"gateway CA not available in {self._name} after {timeout:g}s"
-                )
+            ) from exc
-            time.sleep(_CA_POLL_SECONDS)
 
     def stop(self) -> None:
         """Remove the infra container (idempotent). The DB volume persists."""

bot_bottle/backend/util.py

@@ -7,6 +7,8 @@ from __future__ import annotations
 import hashlib
 import os
 import ssl
+import time
+from collections.abc import Callable
 from pathlib import Path
 from typing import TYPE_CHECKING
 
@@ -15,6 +17,24 @@ from ..log import die, info
 if TYPE_CHECKING:
     from ..egress import EgressPlan
 
+_CA_POLL_INTERVAL = 0.5
+
+
+def poll_ca_cert(fetch: Callable[[], str | None], *, timeout: float) -> str:
+    """Poll `fetch` until it returns a non-empty PEM string or `timeout` expires.
+
+    `fetch` should return the PEM on success and `None` (or empty string) when
+    the cert is not yet available. Raises `TimeoutError` if the cert never
+    appears within `timeout` seconds."""
+    deadline = time.monotonic() + timeout
+    while True:
+        result = fetch()
+        if result:
+            return result
+        if time.monotonic() >= deadline:
+            raise TimeoutError(f"CA cert not available after {timeout:g}s")
+        time.sleep(_CA_POLL_INTERVAL)
+
 
 # Debian-family CA layout, shared by every backend (all guest images
 # are Debian-family). AGENT_CA_PATH is the source path that

docs/prds/prd-new-consolidate-docker-infra-backend.md

@@ -90,8 +90,9 @@ first (`DockerGateway.ensure_running`), then orchestrator. After this PRD:
 - Single `docker run` of `bot-bottle-infra:latest`
 - Container name: `bot-bottle-infra` (replaces `bot-bottle-orch-gateway` +
   `bot-bottle-orchestrator`)
-- Published ports: `127.0.0.1:{port}:{port}` for the control plane (same as
+- Published ports: `127.0.0.1:{host_port}:8099` for the control plane
-  today)
+  (`gateway_init` listens on a fixed internal port 8099; the caller-chosen
+  host port maps to it)
 - Bind mounts: repo root + host root (same as today)
 - `DockerGateway` becomes an implementation detail of `OrchestratorService`
   rather than a separately started container; the gateway image name