Files
bot-bottle/claude_bottle/backend/smolmachines/prepare.py
T
didericis-claude 5e0130b56f
test / unit (push) Successful in 26s
test / integration (push) Successful in 43s
fix(smolmachines): build agent image in launch, not prepare
When starting a smolmachines agent from the dashboard the
docker-build output rendered on top of the curses preflight
modal — the build was kicked off before the operator had
confirmed launch. The docker backend's `prepare` is pure
resolution (no docker calls); smolmachines was inconsistent
because `prepare` called `_ensure_smolmachine` which ran
`docker build` → `docker save` → `crane push` → `smolvm pack
create`, several seconds of stderr noise rendered before the
y/N prompt.

Move the pipeline:

- `_ensure_smolmachine` (+ `_SMOLMACHINE_CACHE_DIR` + `_REPO_DIR`
  + the local-registry / smolvm imports) moves from
  `backend/smolmachines/prepare.py` to
  `backend/smolmachines/launch.py`. Called right before
  `_smolvm.machine_create` so the resulting `.smolmachine`
  sidecar path lands as a local in `launch`, not on the plan.

- `SmolmachinesBottlePlan.agent_from_path: Path` becomes
  `agent_image_ref: str`. `prepare` stashes only the docker tag
  (`$CLAUDE_BOTTLE_IMAGE` || `claude-bottle:latest`); `launch`
  resolves it into the artifact at bringup.

This puts smolmachines on the same prepare-vs-launch boundary
the docker backend uses: the preflight summary in the dashboard
prints, the operator confirms, then `launch` runs — and its
stderr is routed via `_route_op_to_right_pane` (in tmux) or via
`curses.endwin` (foreground handoff) so the build output lands
cleanly.

Tests:
- `tests/unit/test_smolmachines_prepare_image.py` →
  `tests/unit/test_smolmachines_launch_image.py`, updated to
  import `_ensure_smolmachine` from `launch` rather than
  `prepare`.
- `test_smolmachines_provision.py`: plan fixture switches
  `agent_from_path` → `agent_image_ref`.

593 unit tests pass.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
2026-05-27 19:44:53 -04:00

168 lines
6.5 KiB
Python

"""smolmachines `_resolve_plan` (PRD 0023 chunks 2d + 4c).
Resolves the per-bottle docker subnet + bundle IP and assembles
the guest env. The agent's docker image build → smolmachine
pack pipeline runs in `launch.launch`, not here, so the
dashboard's preflight modal isn't garbled by docker-build output
before the operator has confirmed.
No VM bringup — that's `launch.launch`'s job."""
from __future__ import annotations
import os
from datetime import datetime, timezone
from pathlib import Path
from ...backend import BottleSpec
from ...backend.docker.bottle_state import (
BottleMetadata,
agent_state_dir,
bottle_identity,
egress_state_dir,
git_gate_state_dir,
pipelock_state_dir,
supervise_state_dir,
write_metadata,
)
from ...egress import Egress
from ...git_gate import GitGate
from ...pipelock import PipelockProxy
from ...supervise import Supervise
from .bottle_plan import SmolmachinesBottlePlan
from .util import smolmachines_bundle_subnet, smolmachines_preflight
# Gateway ports the bundle exposes inside its container — pipelock
# HTTPS proxy, git-gate's git-daemon, supervise's MCP. The agent
# inside the smolvm guest dials these on the bundle's pinned IP.
_BUNDLE_PIPELOCK_PORT = 8888
_BUNDLE_GIT_GATE_PORT = 9418
_BUNDLE_SUPERVISE_PORT = 9100
def resolve_plan(
spec: BottleSpec, *, stage_dir: Path
) -> SmolmachinesBottlePlan:
"""Materialize the smolmachines plan. The bundle's docker
subnet + pinned IP are derived from the slug; the agent's
`.smolmachine` artifact is built (or cache-hit) here so
launch's `machine create --from` boots without a registry
pull. Per-bottle guest env + the TSI allow_cidrs land on the
plan for launch to pass straight through to
`machine create` flags."""
smolmachines_preflight()
manifest = spec.manifest
bottle = manifest.bottle_for(spec.agent_name)
slug = spec.identity or bottle_identity(spec.agent_name)
# Record minimal metadata so `cli.py resume` can recover the
# slug. Same schema as the docker backend.
write_metadata(BottleMetadata(
identity=slug,
agent_name=spec.agent_name,
cwd=spec.user_cwd if spec.copy_cwd else "",
copy_cwd=spec.copy_cwd,
started_at=datetime.now(timezone.utc).isoformat(),
# No compose project for smolmachines bottles; chunk 4
# will give dashboard discovery a backend-specific path.
compose_project="",
))
subnet, gateway, bundle_ip = smolmachines_bundle_subnet(slug)
# Agent's env: the prepare-time view doesn't yet know the
# host loopback ports the bundle's daemons get published on
# (those come from docker AFTER `docker run` returns), so
# HTTPS_PROXY / GIT_GATE_URL / MCP_SUPERVISE_URL are
# populated in launch.py and stamped onto guest_env there.
# What we set here is the part that doesn't depend on
# bundle bringup — bottle.env literals, the empty-NO_PROXY
# safe default, and the TLS trust env trio
# (NODE_EXTRA_CA_CERTS / SSL_CERT_FILE / REQUESTS_CA_BUNDLE)
# pointing at Debian's update-ca-certificates output bundle.
guest_env: dict[str, str] = {
**bottle.env,
"NO_PROXY": "localhost,127.0.0.1",
"NODE_EXTRA_CA_CERTS": "/etc/ssl/certs/ca-certificates.crt",
"SSL_CERT_FILE": "/etc/ssl/certs/ca-certificates.crt",
"REQUESTS_CA_BUNDLE": "/etc/ssl/certs/ca-certificates.crt",
}
# Inner Plans for the four bundle daemons. The ABCs are
# platform-neutral — `.prepare()` writes config files + returns
# a Plan dataclass with no backend-specific assumptions. State
# dirs are still keyed by slug under the docker backend's
# bottle_state layout (shared on-host convention; not a docker
# dependency).
pipelock_dir = pipelock_state_dir(slug)
pipelock_dir.mkdir(parents=True, exist_ok=True)
proxy_plan = PipelockProxy().prepare(bottle, slug, pipelock_dir)
git_gate_dir = git_gate_state_dir(slug)
git_gate_dir.mkdir(parents=True, exist_ok=True)
git_gate_plan = GitGate().prepare(bottle, slug, git_gate_dir)
egress_dir = egress_state_dir(slug)
egress_dir.mkdir(parents=True, exist_ok=True)
egress_plan = Egress().prepare(bottle, slug, egress_dir)
# Claude-code refuses to start without *something* it
# recognises as a credential. When the bottle has an egress
# route carrying the `claude_code_oauth` role marker, egress
# strips + re-injects the real Authorization header on the
# outbound leg using a token held in egress's own environ — so
# the agent gets a non-secret placeholder here (matches the
# docker backend's forwarded_env logic in
# claude_bottle/backend/docker/prepare.py).
if any("claude_code_oauth" in r.roles for r in egress_plan.routes):
guest_env["CLAUDE_CODE_OAUTH_TOKEN"] = "egress-placeholder"
guest_env.setdefault("CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC", "1")
guest_env.setdefault("DISABLE_ERROR_REPORTING", "1")
supervise_plan = None
if bottle.supervise:
supervise_dir = supervise_state_dir(slug)
supervise_dir.mkdir(parents=True, exist_ok=True)
supervise_plan = Supervise().prepare(slug, supervise_dir)
# Prompt file is always written (mode 0o600) so the in-VM
# path always exists. Content is the agent's `prompt`
# field (markdown body) — empty for agents with no prompt.
# claude-code reads it via --append-system-prompt-file only
# when non-empty, but the file must exist either way to
# match the docker backend's contract.
agent_dir = agent_state_dir(slug)
agent_dir.mkdir(parents=True, exist_ok=True)
prompt_file = agent_dir / "prompt.txt"
agent = manifest.agents[spec.agent_name]
prompt_file.write_text(agent.prompt or "")
prompt_file.chmod(0o600)
machine_name = f"claude-bottle-{slug}"
# Stash the agent image ref — `launch.launch` runs the
# build → pack pipeline at bringup. Honors CLAUDE_BOTTLE_IMAGE
# to match the docker backend's `resolve_plan` default.
agent_image_ref = os.environ.get(
"CLAUDE_BOTTLE_IMAGE", "claude-bottle:latest"
)
return SmolmachinesBottlePlan(
spec=spec,
stage_dir=stage_dir,
slug=slug,
bundle_subnet=subnet,
bundle_gateway=gateway,
bundle_ip=bundle_ip,
machine_name=machine_name,
agent_image_ref=agent_image_ref,
guest_env=guest_env,
prompt_file=prompt_file,
proxy_plan=proxy_plan,
git_gate_plan=git_gate_plan,
egress_plan=egress_plan,
supervise_plan=supervise_plan,
)