feat(agent-provider): user plugin discovery, Dockerfile cascade, and provider-owned ca/git provisioning

- Add _load_user_plugin: loads AgentProvider subclass from
  ~/.bot-bottle/contrib/<name>/agent_provider.py; get_provider()
  checks there first before falling back to built-ins
- Add Dockerfile cascade to docker prepare: per-bottle override →
  manifest dockerfile → user plugin Dockerfile → provider default
- Move provision_ca and provision_git from backend-specific
  provision/ modules to AgentProvider ABC as overridable defaults;
  delete docker/provision/ca.py, docker/provision/git.py,
  smolmachines/provision/ca.py, smolmachines/provision/git.py
- Add git_gate_insteadof_host/scheme properties to BottlePlan base;
  SmolmachinesBottlePlan overrides them to return agent_git_gate_host
  and "http" so provision_git works correctly on both backends
- Move SIGKILL retry from smolmachines provision/ca.py into
  SmolmachinesBottle.exec via _exec_raw helper — all exec calls
  on smolmachines now transparently retry once on exit 137
- Relax manifest_agent template validation to allow user-defined
  template names; keep auth_token/forward_host_credentials guards
  for built-in-only features
- Update tests: rewrite test_docker_provision_git_user and
  test_smolmachines_provision to call provider methods directly;
  add TestSmolmachinesBottleExec for SIGKILL retry coverage

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
2026-06-07 10:39:58 -04:00
parent 65746af720
commit efb3af4a93
16 changed files with 320 additions and 477 deletions
@@ -22,8 +22,6 @@ from . import smolvm as _smolvm
from .bottle import SmolmachinesBottle
from .bottle_cleanup_plan import SmolmachinesBottleCleanupPlan
from .bottle_plan import SmolmachinesBottlePlan
from .provision import ca as _ca
from .provision import git as _git
from .provision import workspace as _workspace
@@ -55,21 +53,11 @@ class SmolmachinesBottleBackend(
with _launch.launch(plan, provision=self.provision) as bottle:
yield bottle
def provision_ca(
self, plan: SmolmachinesBottlePlan, bottle: Bottle
) -> None:
_ca.provision_ca(plan, bottle)
def provision_workspace(
self, plan: SmolmachinesBottlePlan, bottle: Bottle
) -> None:
_workspace.provision_workspace(plan, bottle)
def provision_git(
self, plan: SmolmachinesBottlePlan, bottle: Bottle
) -> None:
_git.provision_git(plan, bottle)
def supervise_mcp_url(self, plan: SmolmachinesBottlePlan) -> str:
"""The smolmachines guest reaches the supervise sidecar via a
host-published random port the launch step pinned earlier
+17 -3
View File
@@ -19,6 +19,7 @@ from __future__ import annotations
import subprocess
import sys
import time
from typing import Mapping, cast
from ...agent_provider import PromptMode, prompt_args
@@ -131,6 +132,11 @@ class SmolmachinesBottle(Bottle):
self.agent_argv(argv, tty=tty), check=False,
).returncode
# smolvm/libkrun can SIGKILL an otherwise-normal exec during
# early-VM provisioning. Retry once after a short settle so
# callers (provision_ca, etc.) don't have to handle it themselves.
_SIGKILL_EXIT = 128 + 9
def exec(self, script: str, *, user: str = "node") -> ExecResult:
"""Run a POSIX shell script as `user` (default `node`) and
capture the result. Matches the docker backend's `exec`,
@@ -141,14 +147,22 @@ class SmolmachinesBottle(Bottle):
`runuser -u <user> -- env ... /bin/sh -c <script>` switches UID
without invoking a login shell, then sets HOME / USER and the
bottle env in the child process."""
bottle env in the child process.
Retries once on SIGKILL (exit 137) — libkrun occasionally
kills short-lived execs during VM bring-up."""
r = self._exec_raw(script, user=user)
if r.returncode == self._SIGKILL_EXIT:
time.sleep(1.0)
r = self._exec_raw(script, user=user)
return r
def _exec_raw(self, script: str, *, user: str = "node") -> ExecResult:
argv = [
"--", "runuser", "-u", user, "--",
"env", *_env_assignments_for(user, self._guest_env),
"/bin/sh", "-c", script,
]
# Call smolvm directly because this path needs the host-side
# subprocess capture shape used by the Docker backend.
r = subprocess.run(
["smolvm", "machine", "exec", "--name", self.name] + argv,
capture_output=True, text=True, check=False,
@@ -82,6 +82,14 @@ class SmolmachinesBottlePlan(BottlePlan):
agent_git_gate_host: str = ""
agent_supervise_url: str = ""
@property
def git_gate_insteadof_host(self) -> str:
return self.agent_git_gate_host
@property
def git_gate_insteadof_scheme(self) -> str:
return "http"
@property
def agent_command(self) -> str:
return self.agent_provision.command
@@ -2,11 +2,12 @@
Per PRD 0050 the per-provider provisioning steps (prompt, skills,
declarative provision-plan apply, supervise MCP registration) live on
the `AgentProvider` plugin under `bot_bottle/contrib/`. The modules
left in this subpackage handle only the steps that are
backend-specific:
the `AgentProvider` plugin under `bot_bottle/contrib/`. CA and git
provisioning also moved to the AgentProvider ABC (with Debian/node
defaults); user plugins override them for non-standard images.
The module left in this subpackage handles the remaining backend-
specific step:
- ca.py — install per-bottle CA bundle into the guest trust store
- git.py — copy host cwd `.git` into the guest when --cwd is used
- workspace.py — copy the operator workspace into the guest
"""
@@ -1,90 +0,0 @@
"""Install the per-bottle egress MITM CA into the smolmachines
guest's trust store (PRD 0023 chunk 4d).
Mirrors `backend.docker.provision.ca`: copy the egress CA to
Debian's `/usr/local/share/ca-certificates/` path,
`update-ca-certificates` to rebuild the trust bundle, and log the
fingerprint once.
`smolvm machine exec` runs commands as root in the VM (no `-u`
flag exists; the VM init is root), so we don't need the explicit
`-u 0` the docker backend uses on its `docker exec` calls."""
from __future__ import annotations
import time
from ....log import die
from ...util import (
AGENT_CA_BUNDLE,
AGENT_CA_PATH,
log_ca_fingerprint,
select_ca_cert,
)
from ... import Bottle, ExecResult
from ..bottle_plan import SmolmachinesBottlePlan
_SIGKILL_EXIT = 128 + 9
def provision_ca(plan: SmolmachinesBottlePlan, bottle: Bottle) -> None:
"""Copy the agent-facing CA cert into the guest, rebuild the
trust bundle, emit a one-line fingerprint log. Called from
`BottleBackend.provision` after the smolvm guest is up."""
cert_host_path, label = select_ca_cert(plan.egress_plan)
bottle.cp_in(str(cert_host_path), AGENT_CA_PATH)
# Mode 0644 — readable to non-root tools in the guest.
# update-ca-certificates rebuilds the bundle at AGENT_CA_BUNDLE,
# which is what curl / Python ssl / OpenSSL-based tools read by
# 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.
#
r = _install_ca(bottle)
if r.returncode == _SIGKILL_EXIT:
# smolvm/libkrun can SIGKILL an otherwise-normal exec
# during early-VM provisioning. `update-ca-certificates`
# is idempotent, so retry the same install once after a
# short settle delay before treating it as fatal.
time.sleep(1.0)
r = _install_ca(bottle)
if r.returncode != 0:
# 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 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}"
)
log_ca_fingerprint(cert_host_path, label)
def _install_ca(bottle: Bottle) -> ExecResult:
# chown + chmod + update-ca-certificates + bundle
# verification run in one exec so we only pay one
# round trip; the `&&` chaining surfaces the first failure
# as the return code. The verify check is more stable than
# requiring "1 added" in stdout: a retry after a
# partially-completed first run may legitimately report "0
# added" while the cert is already installed.
return bottle.exec(
f"chown root:root {AGENT_CA_PATH} && "
f"chmod 644 {AGENT_CA_PATH} && "
f"update-ca-certificates && "
f"openssl verify -CAfile {AGENT_CA_BUNDLE} {AGENT_CA_PATH}",
user="root",
)
# Re-exported for the launch/provision_ca caller + tests. The path
# constants live in the shared `backend.util` (Debian's
# `update-ca-certificates` layout is the same in both backends).
__all__ = ["AGENT_CA_BUNDLE", "AGENT_CA_PATH", "provision_ca"]
@@ -1,133 +0,0 @@
"""Git provisioning inside a running smolmachines bottle
(PRD 0023 chunk 4d).
Three concerns, all about git in the agent:
1. If --cwd was passed AND the host cwd has a .git, copy that
.git into the planned guest workspace so the agent operates on
the user's repo.
2. If the bottle declares `git` entries (PRD 0008), write a
~/.gitconfig with insteadOf rules so every git operation
against a declared upstream transparently hits the per-bottle
git-gate. The gate mirrors the upstream in both directions,
so URL rewriting is symmetric.
3. If the bottle declares `git.user` (issue #86), set
`git config --global user.{name,email}` inside the guest so
the agent's commits are attributed to that identity.
Differs from `backend.docker.provision.git` in one address detail:
the TSI-allowlisted guest can only reach the bundle's pinned IP
(no DNS resolver in the /32 allowlist), so the insteadOf URLs
are `http://<bundle_ip>:<port>/<name>.git` rather than the
docker backend's `git://git-gate/<name>.git`. The render itself
is the shared `git_gate_render_gitconfig` on the platform-neutral
git_gate module."""
from __future__ import annotations
import os
import shlex
import tempfile
from pathlib import Path
from ....git_gate import git_gate_render_gitconfig
from ....log import info
from ... import Bottle
from ..bottle_plan import SmolmachinesBottlePlan
def provision_git(plan: SmolmachinesBottlePlan, bottle: Bottle) -> None:
"""Set up git inside the guest. Runs all three subcases; each
no-ops when its condition isn't met."""
_provision_cwd_git(plan, bottle)
_provision_git_gate_config(plan, bottle)
_provision_git_user(plan, bottle)
def _provision_cwd_git(plan: SmolmachinesBottlePlan, bottle: Bottle) -> None:
"""If --cwd was set and the host cwd has a .git directory, copy
it into <guest_home>/workspace/.git and fix ownership. No-op
otherwise."""
workspace = plan.workspace_plan
if not (workspace.enabled and workspace.copy_git and workspace.has_host_git_dir):
return
guest_workspace_git = f"{workspace.guest_path}/.git"
host_git = str(workspace.host_path / ".git")
info(f"copying {host_git} -> {bottle.name}:{guest_workspace_git}")
# mkdir -p the workspace dir so cp_in lands the .git
# directly there even on first-time bottles.
bottle.exec(f"mkdir -p {shlex.quote(workspace.guest_path)}", user="root")
bottle.cp_in(host_git, guest_workspace_git)
# cp_in lands files as root; the agent runs as node so
# the workspace tree must be chowned over.
bottle.exec(
f"chown -R {shlex.quote(workspace.owner)} {shlex.quote(guest_workspace_git)}",
user="root",
)
def _provision_git_gate_config(
plan: SmolmachinesBottlePlan, bottle: Bottle
) -> None:
"""Write ~/.gitconfig in the guest with the git-gate insteadOf
rules. No-op when the bottle has no `git` entries."""
manifest_bottle = plan.spec.manifest.bottle_for(plan.spec.agent_name)
if not manifest_bottle.git:
return
# `<loopback alias>:<host port>` form: the bundle's git-gate
# HTTP port is published on host loopback at launch time so
# the smolvm guest (which can only reach macOS networking via
# TSI, not the docker bridge IP) can dial it. launch.py
# populates `plan.agent_git_gate_host` after bundle bringup.
content = git_gate_render_gitconfig(
manifest_bottle.git, plan.agent_git_gate_host, scheme="http",
)
guest_gitconfig = f"{plan.guest_home}/.gitconfig"
# Stage the file under the plan's stage_dir so cp_in
# has a stable host path. The plan's stage_dir is cleaned up
# by start.py's session-end teardown.
with tempfile.NamedTemporaryFile(
"w", dir=str(plan.stage_dir), prefix="gitconfig.",
delete=False,
) as f:
f.write(content)
config_file = Path(f.name)
os.chmod(config_file, 0o600)
info(f"writing {guest_gitconfig} with {len(manifest_bottle.git)} insteadOf rule(s)")
bottle.cp_in(str(config_file), guest_gitconfig)
bottle.exec(
f"chown node:node {shlex.quote(guest_gitconfig)} && "
f"chmod 644 {shlex.quote(guest_gitconfig)}",
user="root",
)
def _provision_git_user(
plan: SmolmachinesBottlePlan, bottle: Bottle,
) -> None:
"""Apply `git config --global user.{name,email}` inside the
guest as the node user so --global lands in the same
`/home/node/.gitconfig` that `_provision_git_gate_config`
writes to. No-op when the bottle didn't declare `git.user`.
SmolmachinesBottle.exec(user="node") automatically sets
HOME=/home/node so --global writes to /home/node/.gitconfig."""
manifest_bottle = plan.spec.manifest.bottle_for(plan.spec.agent_name)
gu = manifest_bottle.git_user
if gu.is_empty():
return
if gu.name:
info(f"git config --global user.name = {gu.name!r}")
bottle.exec(
f"git config --global user.name {shlex.quote(gu.name)}",
user="node",
)
if gu.email:
info(f"git config --global user.email = {gu.email!r}")
bottle.exec(
f"git config --global user.email {shlex.quote(gu.email)}",
user="node",
)