refactor(backend): move per-provider provisioning onto AgentProvider

BottleBackend.provision now resolves the provider plugin from the
plan and dispatches prompt / skills / declarative-apply /
supervise-mcp through it. The four hooks the docker + smolmachines
backends used to override (provision_skills, provision_prompt,
provision_provider_auth, provision_supervise) are gone — the
duplicated 50-line implementations under
backend/{docker,smolmachines}/provision/{skills,prompt,
provider_auth,supervise}.py are deleted.

Each backend gains a small supervise_mcp_url(plan) override so the
provider plugin can run `claude mcp add` / `codex mcp add`
against the right URL: docker returns
http://{SUPERVISE_HOSTNAME}:{SUPERVISE_PORT}/ on the compose
network alias; smolmachines returns plan.agent_supervise_url which
launch.py already pins to a host-loopback port.

Removes tests/unit/test_provision_supervise.py — the URL it
asserted on now lives on the backend, with no equivalent
standalone surface to test against (it's covered by the broader
plan / launch integration tests).
This commit is contained in:
2026-06-03 21:21:42 +00:00
committed by didericis
parent 1443376268
commit 8c45016aa2
14 changed files with 75 additions and 491 deletions
@@ -1,14 +1,12 @@
"""Provisioning helpers for the smolmachines backend (PRD 0023
chunk 4).
"""Backend-infrastructure provisioners for the smolmachines backend.
Each method maps onto one of `BottleBackend`'s `provision_*`
overrides. They run after the VM is up + the bundle is reachable
and copy host-side state (prompt, skills, .git, CA cert,
supervise MCP config) into the guest via `smolvm machine cp` /
`smolvm machine exec`.
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:
Chunk 4a ships `provision_prompt` and `provision_skills` — the
two that don't depend on agent-image tooling (claude-code,
update-ca-certificates) beyond `cp` and `mkdir`. provision_ca /
provision_git / provision_supervise land once the agent-image
gap is solved."""
- 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
"""
@@ -1,44 +0,0 @@
"""Copy the agent prompt into a running smolmachines bottle.
The prompt file is always copied (so the in-guest path always
exists) but `--append-system-prompt-file` only fires when the
agent actually has a prompt — the return value signals which
case, mirroring the docker backend's contract.
cp_in lands files as root inside the VM; the claude
process runs as `node`, so we chown + chmod the prompt after the
copy. Same flow as the docker backend's provision_prompt."""
from __future__ import annotations
import os
from ... import Bottle
from ..bottle_plan import SmolmachinesBottlePlan
# `node` is the agent user from the repo Dockerfile.
# BOT_BOTTLE_GUEST_HOME mirrors the docker backend's
# BOT_BOTTLE_CONTAINER_HOME knob.
_DEFAULT_GUEST_HOME = "/home/node"
def provision_prompt(plan: SmolmachinesBottlePlan, bottle: Bottle) -> str | None:
"""Copy the prompt file into the running smolvm guest, fix
ownership/mode. Returns the in-guest path if the agent has a
non-empty prompt (drives --append-system-prompt-file), else
None. The file is copied either way so the path always
exists — mirrors the docker backend's behavior."""
guest_home = os.environ.get("BOT_BOTTLE_GUEST_HOME", _DEFAULT_GUEST_HOME)
in_guest_prompt_path = f"{guest_home}/.bot-bottle-prompt.txt"
bottle.cp_in(str(plan.prompt_file), in_guest_prompt_path)
# cp_in lands as root, source's 0o600 mode is preserved —
# node can't read its own prompt without these two.
bottle.exec(
f"chown node:node {in_guest_prompt_path} && chmod 600 {in_guest_prompt_path}",
user="root",
)
agent = plan.spec.manifest.agents[plan.spec.agent_name]
return in_guest_prompt_path if agent.prompt else None
@@ -1,35 +0,0 @@
"""Provision non-secret provider auth markers into a smolmachines bottle."""
from __future__ import annotations
import shlex
from ....log import die
from ... import Bottle
from ..bottle_plan import SmolmachinesBottlePlan
def provision_provider_auth(plan: SmolmachinesBottlePlan, bottle: Bottle) -> None:
"""Apply provider-owned guest setup through the bottle's exec / cp_in."""
provision = plan.agent_provision
for d in provision.dirs:
_exec(bottle, f"mkdir -p {shlex.quote(d.guest_path)}", f"could not create {d.guest_path}")
_exec(bottle, f"chown {shlex.quote(d.owner)} {shlex.quote(d.guest_path)}", f"could not chown {d.guest_path}")
_exec(bottle, f"chmod {shlex.quote(d.mode)} {shlex.quote(d.guest_path)}", f"could not chmod {d.guest_path}")
for command in provision.pre_copy:
_exec(bottle, shlex.join(command.argv), command.error)
for f in provision.files:
bottle.cp_in(str(f.host_path), f.guest_path)
_exec(bottle, f"chown {shlex.quote(f.owner)} {shlex.quote(f.guest_path)}", f"could not chown {f.guest_path}")
_exec(bottle, f"chmod {shlex.quote(f.mode)} {shlex.quote(f.guest_path)}", f"could not chmod {f.guest_path}")
for command in provision.verify:
_exec(bottle, shlex.join(command.argv), command.error)
def _exec(bottle: Bottle, script: str, error: str) -> None:
result = bottle.exec(script, user="root")
if result.returncode != 0:
detail = (result.stderr or result.stdout).strip()
if detail:
detail = f": {detail}"
die(f"agent provider provisioning: {error}{detail}")
@@ -1,63 +0,0 @@
"""Copy host-side skill directories into a running smolmachines
bottle.
Skills are validated on the host before launch by
`BottleBackend._validate_skills`; this module assumes that
validation has already run. A skill that disappears between
validation and copy still dies loudly rather than silently
producing a partial guest."""
from __future__ import annotations
import os
from ....log import die, info
from ...util import host_skill_dir
from ... import Bottle
from ..bottle_plan import SmolmachinesBottlePlan
# In-guest path mirrors the docker backend's claude-skills
# convention (~/.claude/skills/<name>/) under the node user's
# home — same path as the real bot-bottle image's
# /home/node/.claude/skills (pre-created in the Dockerfile).
_DEFAULT_SKILLS_DIR = "/home/node/.claude/skills"
def provision_skills(plan: SmolmachinesBottlePlan, bottle: Bottle) -> None:
"""Copy each of the agent's named skills from the host's
~/.claude/skills/<name>/ into the guest's equivalent path.
For each skill: `mkdir -p` the destination, cp_in the host
source dir over, then chown the result to node:node so the
agent can read it. No-op when the agent has no skills.
cp_in on a directory copies recursively; unlike docker cp's
trailing-slash convention, smolvm doesn't need the `/.` suffix
dance.
cp_in lands files as root inside the VM, so we chown each
skill tree over to node:node after the copy — same pattern as
the docker backend's provision_prompt."""
agent = plan.spec.manifest.agents[plan.spec.agent_name]
if not agent.skills:
return
skills_dir = os.environ.get(
"BOT_BOTTLE_GUEST_SKILLS_DIR", _DEFAULT_SKILLS_DIR,
)
bottle.exec(f"mkdir -p {skills_dir}", user="root")
for name in agent.skills:
src = host_skill_dir(name)
if not os.path.isdir(src):
die(
f"skill {name!r} disappeared from host between "
f"validation and copy at {src}."
)
dst = f"{skills_dir}/{name}"
info(f"copying skill {name} into {bottle.name}:{dst}")
# Wipe any prior copy so re-runs don't accumulate.
bottle.exec(f"rm -rf {dst}", user="root")
bottle.cp_in(src, dst)
bottle.exec(f"chown -R node:node {dst}", user="root")
@@ -1,58 +0,0 @@
"""Supervise sidecar provisioning inside a running smolmachines
bottle (PRD 0023 chunk 4d; PRD 0013 supervise plane).
Registers the per-bottle supervise sidecar as an HTTP MCP server
in the agent's claude-code config so the agent discovers the
stuck-recovery MCP tools (pipelock-block, capability-block) at
startup.
Mirrors `backend.docker.provision.supervise` — same `claude mcp
add` call, just dispatched via bottle.exec instead of
`docker exec`, and against `<bundle_ip>:<port>` instead of the
short `supervise` alias (no DNS in the TSI-allowlisted guest)."""
from __future__ import annotations
from ....log import info, warn
from ... import Bottle
from ..bottle_plan import SmolmachinesBottlePlan
_SUPERVISE_MCP_NAME = "supervise"
def provision_supervise(plan: SmolmachinesBottlePlan, bottle: Bottle) -> None:
"""Run `claude mcp add` inside the guest to register the
supervise sidecar in claude-code's user config. No-op when
bottle.supervise is False.
The URL is the agent-side endpoint launch.py populated after
bundle bringup — `http://127.0.0.1:<host port>/` rather than
the bundle's docker bridge IP, because that bridge isn't
reachable from the smolvm guest on macOS.
Failure is logged but not fatal: the bottle still works (you
just can't call supervise tools from the agent until the entry
is added manually). The operator sees the warning at launch."""
if plan.supervise_plan is None:
return
url = plan.agent_supervise_url
info(f"registering supervise MCP server in agent claude config → {url}")
# `claude mcp add --scope user` writes to ~/.claude.json. Run
# as node so the config lands in /home/node/.claude.json.
# SmolmachinesBottle.exec sets HOME and USER automatically
# for the requested user.
r = bottle.exec(
f"claude mcp add --scope user --transport http {_SUPERVISE_MCP_NAME} {url}",
user="node",
)
if r.returncode != 0:
warn(
f"`claude mcp add supervise` failed (exit {r.returncode}): "
f"{(r.stderr or r.stdout or '').strip()}. Inside the bottle, "
f"register manually with: "
f"claude mcp add --scope user --transport http supervise {url}"
)
__all__ = ["provision_supervise"]