Compare commits

..

1 Commits

Author SHA1 Message Date
didericis fa4d2ce40b Replace die with YamlSubsetError
lint / lint (push) Successful in 1m40s
test / unit (push) Successful in 40s
test / integration (push) Successful in 55s
Update Quality Badges / update-badges (push) Successful in 1m52s
2026-06-08 22:16:35 -04:00
294 changed files with 9601 additions and 30711 deletions
-18
View File
@@ -1,18 +0,0 @@
[run]
branch = True
source = .
[report]
# Coverage policy: see docs/decisions/0004-coverage-policy.md.
#
# `omit` is reserved for genuinely interactive entry-point shells whose
# bodies are `read_tty_line()` / curses prompt loops — there is no
# behaviour to assert that a test wouldn't have to fake wholesale, so a
# test here would inflate the number without buying confidence. This is
# NOT a place to hide subprocess/backend orchestration: that code is
# security-relevant and is measured via the integration suite instead
# (run scripts/coverage.sh for the combined unit+integration number).
omit =
bot_bottle/cli/tui.py
bot_bottle/cli/init.py
tests/*
+1 -1
View File
@@ -26,7 +26,7 @@ jobs:
- name: Run pylint
run: |
# Run pylint on all Python files in the repo
find . -name '*.py' -not -path './.venv/*' -not -path './.git/*' | xargs pylint --fail-under=8.0
find . -name '*.py' -not -path './.venv/*' -not -path './.git/*' | xargs pylint --fail-under=8.0 || true
- name: Run pyright
run: |
+1 -35
View File
@@ -39,14 +39,8 @@ jobs:
with:
python-version: "3.12"
- name: Install dev requirements
run: python3 -m pip install -r requirements-dev.txt
- name: Run unit tests
run: python3 -m coverage run -m unittest discover -t . -s tests/unit -v
- name: Report unit coverage
run: python3 -m coverage report -m
run: python3 -m unittest discover -t . -s tests/unit -v
integration:
runs-on: ubuntu-latest
@@ -70,31 +64,3 @@ jobs:
- name: Run integration tests
run: python3 -m unittest discover -t . -s tests/integration -v
# Combined unit+integration coverage report (informational). See
# docs/decisions/0004-coverage-policy.md.
#
# The hard diff-coverage gate (changed lines >= 90%) is DEFERRED: the
# Firecracker backend's VM/SSH orchestration is covered by the integration
# suite, which needs /dev/kvm + the provisioned TAP/nft pool — a
# container-based runner skips it and those lines read uncovered, so the
# gate can't pass here. Re-enabling it on a self-hosted KVM runner is
# tracked separately (see PRD 0069 / #348 and the ci-runner branch).
coverage:
runs-on: ubuntu-latest
steps:
- name: Checkout
uses: actions/checkout@v4
with:
fetch-depth: 0
- name: Set up Python
uses: actions/setup-python@v5
with:
python-version: "3.12"
- name: Install dev requirements
run: python3 -m pip install -r requirements-dev.txt
- name: Combined coverage report (unit + integration)
run: PYTHON=python3 bash scripts/coverage.sh critical
+24 -26
View File
@@ -6,9 +6,8 @@ on:
- main
paths:
- '**.py'
- '.coveragerc'
# The core-coverage badge reads this list; refresh when it changes.
- 'scripts/critical-modules.txt'
- '.pylintrc'
- 'pyrightconfig.json'
workflow_dispatch:
jobs:
@@ -30,39 +29,38 @@ jobs:
python -m pip install --upgrade pip
pip install -r requirements-dev.txt
- name: Run coverage and extract percentage
id: coverage
- name: Run pylint and extract score
id: pylint
run: |
python -m coverage run -m unittest discover -t . -s tests/unit > /dev/null 2>&1 || true
PERCENT=$(python -m coverage report 2>/dev/null | grep '^TOTAL' | grep -oP '\d+(?=%)' | tail -1)
echo "percent=$PERCENT" >> $GITHUB_OUTPUT
echo "Coverage: $PERCENT%"
PYLINT_OUTPUT=$(python -m pylint bot_bottle/ 2>&1) || true
SCORE=$(echo "$PYLINT_OUTPUT" | grep -oP '(?<=rated at )\d+\.\d+/10' | head -1)
echo "score=$SCORE" >> $GITHUB_OUTPUT
echo "Pylint score: $SCORE"
- name: Extract core (critical-module) coverage percentage
id: core_coverage
- name: Run pyright and check errors
id: pyright
run: |
# Reuses the .coverage data from the previous step. The core list is
# the single source of truth in scripts/critical-modules.txt; every
# core module is unit-tested, so the unit-only run is accurate for it.
INCLUDE=$(grep -vE '^[[:space:]]*(#|$)' scripts/critical-modules.txt | paste -sd, -)
PERCENT=$(python -m coverage report --include="$INCLUDE" 2>/dev/null | grep '^TOTAL' | grep -oP '\d+(?=%)' | tail -1)
echo "percent=$PERCENT" >> $GITHUB_OUTPUT
echo "Core coverage: $PERCENT%"
PYRIGHT_OUTPUT=$(python -m pyright 2>&1) || true
ERRORS=$(echo "$PYRIGHT_OUTPUT" | grep -oP '\d+(?= error)' | head -1)
echo "errors=$ERRORS" >> $GITHUB_OUTPUT
echo "Pyright errors: $ERRORS"
- name: Update badges in README
run: |
COVERAGE_PERCENT="${{ steps.coverage.outputs.percent }}"
CORE_COVERAGE_PERCENT="${{ steps.core_coverage.outputs.percent }}"
PYLINT_SCORE="${{ steps.pylint.outputs.score }}"
PYRIGHT_ERRORS="${{ steps.pyright.outputs.errors }}"
if [ -n "$COVERAGE_PERCENT" ]; then
sed -i "s|/badge/coverage-[^)]*|/badge/coverage-${COVERAGE_PERCENT}%25-brightgreen|" README.md
PYLINT_SCORE_ENCODED=$(echo "$PYLINT_SCORE" | sed 's|/|%2F|g')
if [ -n "$PYLINT_SCORE_ENCODED" ]; then
sed -i "s|/badge/pylint-[^)]*|/badge/pylint-${PYLINT_SCORE_ENCODED}-brightgreen|" README.md
fi
if [ -n "$CORE_COVERAGE_PERCENT" ]; then
sed -i "s|/badge/core%20coverage-[^)]*|/badge/core%20coverage-${CORE_COVERAGE_PERCENT}%25-brightgreen|" README.md
if [ -n "$PYRIGHT_ERRORS" ]; then
sed -i "s|/badge/pyright-[^)]*|/badge/pyright-${PYRIGHT_ERRORS}%20errors-brightgreen|" README.md
fi
echo "Updated badges:"
grep -E "coverage" README.md | head -2
grep -E "pylint|pyright" README.md | head -2
- name: Commit and push badge updates
run: |
@@ -75,7 +73,7 @@ jobs:
else
echo "Badge changes detected, committing..."
git add README.md
MSG="chore: update quality badges"$'\n\n'"- Coverage: ${{ steps.coverage.outputs.percent }}%"$'\n'"- Core coverage: ${{ steps.core_coverage.outputs.percent }}%"$'\n\n'"[skip ci]"
MSG="chore: update quality badges"$'\n\n'"- Pylint: ${{ steps.pylint.outputs.score }}"$'\n'"- Pyright: ${{ steps.pyright.outputs.errors }} errors"$'\n\n'"[skip ci]"
git commit -m "$MSG"
git push
fi
-1
View File
@@ -22,4 +22,3 @@ venv/
.pytest_cache/
.mypy_cache/
.ruff_cache/
.coverage
+6 -13
View File
@@ -2,18 +2,11 @@
## What this is
bot-bottle spins up an isolated backend runtime for running AI coding agents
with a curated set of skills and env vars. The point is to run agents with
broad permissions inside a sandbox, so a misbehaving agent cannot reach the
host. A Python CLI (entry point `cli.py`, package `bot_bottle/`) orchestrates
the runtime lifecycle and the copying of skills and env vars into it.
The default backend on compatible macOS hosts is macos-container:
agents and sidecar bundles run through Apple's `container` CLI without
requiring Docker. On KVM-capable Linux hosts the default is firecracker:
agents run in a Firecracker microVM reached over SSH on a point-to-point
TAP, while the sidecar bundle still uses Docker. The legacy Docker
backend remains available with `BOT_BOTTLE_BACKEND=docker` or
`--backend=docker`.
bot-bottle spins up an isolated container for running AI coding agents with a
curated set of skills and env vars. The point is to run agents with broad
permissions inside a sandbox, so a misbehaving agent cannot reach the host.
A Python CLI (entry point `cli.py`, package `bot_bottle/`) orchestrates
the container lifecycle and the copying of skills and env vars into it.
## Goals
@@ -24,7 +17,7 @@ backend remains available with `BOT_BOTTLE_BACKEND=docker` or
## Non-goals
- Communicating between agents directly
- Removing the Docker backend
- Self hosted VMs (v1 uses local Docker containers, not VMs)
- Advanced agent auditing (lean on git history for auditing)
## Repository layout
@@ -21,7 +21,7 @@ FROM node:22-slim
# to it) works against egress's bumped TLS without the agent needing
# local DNS.
RUN apt-get update \
&& apt-get install -y --no-install-recommends git ca-certificates curl ripgrep iproute2 dnsutils \
&& apt-get install -y --no-install-recommends git ca-certificates curl \
&& rm -rf /var/lib/apt/lists/*
# App-specific deps. Python isn't required by claude-code itself
@@ -36,7 +36,7 @@ RUN apt-get update \
# build (`claude --version` returns 2.1.126). Bump deliberately when
# rolling forward; an unpinned install would mean rebuilds silently pick
# up new behavior.
RUN npm install -g --no-fund --no-audit @anthropic-ai/claude-code@2.1.172 \
RUN npm install -g --no-fund --no-audit @anthropic-ai/claude-code@2.1.126 \
&& npm cache clean --force
# Run as a non-root user. The node image already provides a `node` user
@@ -1,12 +1,12 @@
# bot-bottle Codex provider image.
#
# Mirrors the default Claude image shape: Node LTS, git/network tooling,
# non-root node user, and the provider CLI installed for that user.
# non-root node user, and the provider CLI installed globally.
FROM node:22-slim
RUN apt-get update \
&& apt-get install -y --no-install-recommends git ca-certificates curl procps ripgrep \
&& apt-get install -y --no-install-recommends git ca-certificates curl \
&& rm -rf /var/lib/apt/lists/*
# App-specific deps. Python isn't required by codex itself
@@ -17,15 +17,12 @@ RUN apt-get update \
&& apt-get install -y --no-install-recommends python3 python3-pip python3-venv \
&& rm -rf /var/lib/apt/lists/*
RUN npm install -g --no-fund --no-audit @openai/codex@0.136.0 \
&& npm cache clean --force
USER node
WORKDIR /home/node
ENV PATH="/home/node/.local/bin:${PATH}"
# Remote-control support requires the standalone Codex install layout
# under ~/.codex/packages/standalone/current. The npm package can run
# the TUI, but remote-control commands expect this installer-owned path.
RUN mkdir -p /home/node/.codex \
&& curl -fsSL https://chatgpt.com/codex/install.sh | sh
RUN mkdir -p /home/node/.codex
CMD ["codex"]
+3 -12
View File
@@ -18,13 +18,13 @@
# /git-gate-entrypoint.sh docker-cp'd at start time
# /git-gate/creds/* docker-cp'd at start time
# /git/* bare repos, populated at runtime
# /run/supervise/bot-bottle.db bind-mounted at run time
# /run/supervise/queue/ bind-mounted at run time
# /home/mitmproxy/.mitmproxy/ mitmproxy CA dir
#
# Exposed ports inside the container:
# 9099 egress (mitmproxy, agent-facing HTTPS proxy)
# 9418 git-gate (git-daemon)
# 9420 git-gate smart HTTP (VM-backend agent-facing transport)
# 9420 git-gate smart HTTP (smolmachines agent-facing transport)
# 9100 supervise (MCP HTTP)
# Stage 1: gitleaks binary. The upstream gitleaks image is alpine
@@ -62,18 +62,9 @@ COPY --from=gitleaks-src /usr/bin/gitleaks /usr/bin/gitleaks
# top-level siblings (absolute imports), matching the prior
# Dockerfile.egress / Dockerfile.supervise layout.
COPY bot_bottle/egress_addon_core.py /app/egress_addon_core.py
COPY bot_bottle/egress_dlp_config.py /app/egress_dlp_config.py
COPY bot_bottle/egress_addon.py /app/egress_addon.py
COPY bot_bottle/policy_resolver.py /app/policy_resolver.py
COPY bot_bottle/dlp_detectors.py /app/dlp_detectors.py
COPY bot_bottle/yaml_subset.py /app/yaml_subset.py
COPY bot_bottle/paths.py /app/paths.py
COPY bot_bottle/migrations.py /app/migrations.py
COPY bot_bottle/db_store.py /app/db_store.py
COPY bot_bottle/supervise_types.py /app/supervise_types.py
COPY bot_bottle/queue_store.py /app/queue_store.py
COPY bot_bottle/audit_store.py /app/audit_store.py
COPY bot_bottle/store_manager.py /app/store_manager.py
COPY bot_bottle/supervise.py /app/supervise.py
COPY bot_bottle/supervise_server.py /app/supervise_server.py
COPY bot_bottle/sidecar_init.py /app/sidecar_init.py
@@ -89,7 +80,7 @@ RUN mkdir -p \
/etc/git-gate \
/git-gate/creds \
/git \
/run/supervise \
/run/supervise/queue \
/home/mitmproxy/.mitmproxy
# Documentation only — the compose renderer publishes whichever
+8 -61
View File
@@ -5,8 +5,8 @@
# bot-bottle
[![test](https://gitea.dideric.is/didericis/bot-bottle/actions/workflows/test.yml/badge.svg?branch=main)](https://gitea.dideric.is/didericis/bot-bottle/actions?workflow=test.yml)
[![coverage](https://img.shields.io/badge/coverage-82%25-brightgreen)](https://coverage.readthedocs.io/)
[![core coverage](https://img.shields.io/badge/core%20coverage-95%25-brightgreen)](https://gitea.dideric.is/didericis/bot-bottle/src/branch/main/docs/decisions/0004-coverage-policy.md)
[![pylint](https://img.shields.io/badge/pylint-9.95%2F10-brightgreen)](https://github.com/PyCQA/pylint)
[![pyright](https://img.shields.io/badge/pyright-0%20errors-brightgreen)](https://github.com/microsoft/pyright)
**Problem:** Developer wants to run a coding agent without supervision, but they don't want a prompt injected or misbehaving agent wrecking their environment or exfiltrating sensitive data.
@@ -14,29 +14,20 @@
## Features
- **Per-bottle egress allowlist** — TLS-bumped HTTP/HTTPS chokepoint with a per-manifest host allowlist; per-route path/method/header `matches` filtering; outbound DLP scanning for known tokens and secrets, inbound DLP scanning for prompt-injection attempts; DoH and arbitrary hosts blocked by default.
- **Per-route token-match policy** — each egress route picks what happens when the outbound DLP catches a token via `dlp.outbound_on_match`: `supervise` (default) holds the request and surfaces it in `./cli.py supervise` for approval (an approved value is remembered for the life of the proxy); `redact` scrubs the value and forwards; `block` is a hard `403`. Cuts false-positive friction without weakening default-deny.
- **Per-bottle egress allowlist** — TLS-bumped HTTP/HTTPS chokepoint with a per-manifest host allowlist and request-body DLP scanner; DoH and arbitrary hosts blocked by default.
- **Tokens the agent never sees** — host secrets live in a sidecar; the agent dials `http://sidecar:9099/<path>` and the proxy strips inbound `Authorization` and injects the real token before forwarding. `printenv` in the agent shows proxy URLs only.
- **Gitleaks-scanned push (git-gate)** — `bottle.git` remotes route through a per-bottle `git daemon` that gitleaks-scans incoming refs pre-receive and forwards clean refs upstream over SSH. The agent never holds the upstream credential.
- **Manifest-scoped skills + secrets** — each bottle declares its skills, env, git identity, remotes, and egress routes; unknown keys die at load.
- **Trust boundary at `$HOME`** — bottles (credentials, egress, remotes) live only under `~/.bot-bottle/bottles/`. Repos may ship agents but not bottles, so a cloned repo can't redirect an env var to an attacker host.
- **Composable bottles (`extends:`)** — keep provider/runtime policy in one base bottle (e.g. `claude.md`) and overlay task bottles on top.
- **Parallel, isolated bottles** — each bottle runs in its own backend-owned isolation boundary; bottles don't share state or talk to each other.
- **Parallel, isolated bottles** — each bottle is its own per-agent Docker `--internal` network; bottles don't share state or talk to each other.
- **Provider templates (Claude, Codex)** — `Dockerfile.claude` / `Dockerfile.codex`, or a bottle-supplied Dockerfile. Claude auth via long-lived OAuth token; Codex via opt-in host device-auth forwarding.
- **gVisor auto-detect** — on Linux hosts where `runsc` is registered with Docker, every bottle launches under it for a userspace syscall barrier; no manifest config required.
- **Apple Container backend (macOS default when available)** — runs the agent and sidecar bundle with Apple's `container` CLI, using a host-only agent network plus a separate sidecar egress network.
- **Firecracker backend (Linux default when available)** — runs the agent in a KVM Firecracker microVM reached over SSH on a point-to-point TAP, with the sidecar bundle in Docker. A dedicated, fail-closed `nftables` table isolates the guest, closing the raw DNS/IP exfiltration gap that exists in the legacy Docker backend. Requires KVM (`/dev/kvm`) and a one-time privileged network-pool setup.
- **Legacy Docker backend** — still available for examples, CI, and hosts without Apple Container or KVM via `BOT_BOTTLE_BACKEND=docker` or `--backend=docker`.
- **Smolmachines backend (macOS)** — opt-in `BOT_BOTTLE_BACKEND=smolmachines` runs the agent in a libkrun micro-VM with the sidecar bundle still in Docker.
## Architecture
On the default macOS Apple Container backend, a bottle is an agent container on a host-only internal network plus a sidecar bundle attached to both that internal network and a NAT egress network. The agent gets HTTP(S)_PROXY and CA bundle env vars pointing at the sidecar's internal-network IP, so HTTP/HTTPS traffic flows through the sidecar instead of direct egress. `bottle.git` / git-gate is intentionally deferred on this backend until a safe Apple Container key-delivery path exists.
On the Firecracker backend, a bottle is an agent microVM plus a Docker sidecar bundle for egress, git-gate, and supervise. The VM reaches the sidecars over a per-bottle point-to-point TAP link; a dedicated fail-closed `nftables` table (`inet bot_bottle_fc`) confines the guest to that link, so nothing leaves the box except through the sidecars. The TAP pool and nft table are provisioned once (root); per-launch needs no privilege.
On the legacy Docker backend, the same logical bottle is two containers per agent: an `agent` container and a `sidecars` container. They share a per-agent Docker `--internal` network; the agent has no default route off-box.
The Docker topology looks like this:
A bottle is two containers per agent: an `agent` container, and a `sidecars` container that bundles egress + git-gate + supervise behind a Python init supervisor. They share a per-agent Docker `--internal` network; the agent has no default route off-box.
```
host ( ./cli.py )
@@ -71,24 +62,7 @@ When the agent exits, `cli.py` tears down every sidecar and both networks; nothi
## Quickstart
On compatible macOS hosts, the default backend requires Apple's `container` CLI and does not require Docker. The Firecracker backend (Linux) requires Docker on the host for the sidecar bundle plus the `firecracker` binary and KVM. The legacy Docker backend requires Docker. Claude bottles also need a long-lived Claude Code OAuth token (`claude setup-token`) exported as `BOT_BOTTLE_CLAUDE_OAUTH_TOKEN`.
Use `BOT_BOTTLE_BACKEND=docker ./cli.py start <agent>` on hosts where neither Apple Container nor KVM is available and Docker is the desired backend.
### Firecracker on Linux
On Linux, a KVM-capable host defaults to the Firecracker backend. It needs:
- **`/dev/kvm`** present and accessible. Load `kvm-intel` or `kvm-amd` (and enable virtualization in BIOS/firmware). The invoking user must be in the `kvm` group: `sudo usermod -aG kvm "$USER"` then re-login. bot-bottle preflights this and reports exactly what's missing.
- **`firecracker`** on `PATH`: grab a release from <https://github.com/firecracker-microvm/firecracker/releases>. Start flows print this pointer when the binary is missing.
- **Docker** for the sidecar bundle and image build.
- **A one-time privileged network setup** — the per-bottle TAP pool plus the fail-closed `nftables` isolation table. Run `./cli.py backend setup --backend=firecracker` for the host-appropriate config (a NixOS module, a `sudo` script elsewhere); `./cli.py backend status --backend=firecracker` reports what's present, including whether the pool range collides with an existing route. The pool defaults to `10.243.0.0/16` (an obscure RFC-1918 block that dodges docker/libvirt/LAN and, deliberately, Tailscale's `100.64.0.0/10` CGNAT range); override with `BOT_BOTTLE_FC_IP_BASE` if it clashes on your host.
```sh
BOT_BOTTLE_BACKEND=firecracker ./cli.py start <agent>
```
> **NixOS:** enable `virtualisation.docker`, ensure the KVM module is loaded (`boot.kernelModules = [ "kvm-intel" ];` or `kvm-amd`), and add your user to the `kvm` and `docker` groups. For the network pool, consume the flake module — `imports = [ inputs.bot-bottle.nixosModules.firecracker-netpool ]; services.bot-bottle-firecracker = { enable = true; owner = "you"; };` — then `nixos-rebuild switch` (imperative nft/TAP rules don't survive a rebuild; channel users can `imports = [ <bot-bottle>/nix/firecracker-netpool.nix ]`). `firecracker` isn't in nixpkgs by default as a user binary — install the release binary (pin the version) and put it on `PATH`.
Requires Docker on the host and a long-lived Claude Code OAuth token (`claude setup-token`) exported as `BOT_BOTTLE_CLAUDE_OAUTH_TOKEN`.
```sh
./cli.py start <agent> # builds the image on first run, drops you into claude
@@ -122,15 +96,8 @@ egress:
routes:
- host: gitea.dideric.is
auth:
scheme: token # Bearer | token
scheme: token
token_ref: BOT_BOTTLE_GITEA_TOKEN
matches: # optional — restrict to specific paths/methods/headers
- paths:
- {type: prefix, value: /api/v1/}
methods: [GET, POST, PATCH, DELETE]
dlp: # optional — per-route detector overrides (default: all on)
outbound_detectors: [token_patterns, known_secrets]
inbound_detectors: false # disable response scanning for this host
---
The `gitea-dev` bottle. Provider auth via the inherited Claude route;
@@ -149,26 +116,6 @@ skills:
You help maintain Gitea-hosted projects.
````
**Egress route fields:**
| Field | Required | Description |
|---|---|---|
| `host` | yes | Hostname to allowlist. One entry per host. |
| `role` | no | Reserved for future use. The key is recognised but any value is currently rejected at load. Provider auth routes (e.g. Claude's `api.anthropic.com`) are injected automatically from `agent_provider.auth_token`, not via `role`. |
| `auth.scheme` | when `auth` present | `Bearer` or `token`. Injected by the proxy; the agent never sees the value. |
| `auth.token_ref` | when `auth` present | Env-var name holding the secret on the host. |
| `matches` | no | Array of `{paths, methods, headers}` filters. A request must match at least one entry (if any are given) to be forwarded. |
| `matches[].paths` | no | Array of `{type, value}`. `type` is `prefix` (default), `exact`, or `regex`. |
| `matches[].methods` | no | Array of HTTP method strings, e.g. `[GET, POST]`. |
| `matches[].headers` | no | Array of `{name, value, type}`. `type` is `exact` (default) or `regex`. |
| `dlp` | no | Per-route DLP overrides. Omit to use defaults (all detectors on). |
| `dlp.outbound_detectors` | no | `false` disables outbound scanning; list restricts to named detectors (`token_patterns`, `known_secrets`). |
| `dlp.inbound_detectors` | no | `false` disables inbound scanning; list restricts to named detectors (`naive_injection_detection`). |
| `dlp.outbound_on_match` | no | What to do when an outbound token is detected: `supervise` (default for manifest routes — hold for operator approval), `redact` (scrub the value and forward), or `block` (hard 403). Agent-provider routes (e.g. `api.anthropic.com`) default to `redact`. |
| `git.fetch` | no | `true` permits smart HTTP clone/fetch (`git-upload-pack`) for this host. Push (`git-receive-pack`) remains blocked. |
When an outbound DLP detector matches a token, the route's `dlp.outbound_on_match` policy decides what happens. Under the default `supervise`, the proxy queues an `egress-token-allow` proposal for the operator's `./cli.py supervise` TUI and holds the request open until it is answered (or `EGRESS_TOKEN_ALLOW_TIMEOUT_SECONDS`, default 300s, elapses — after which it fails closed). The operator never sees the raw token, only the host, method, path, and a redacted snippet; approving adds the value to an in-memory safelist for the life of the egress proxy. Under `redact`, the matched value is scrubbed from the body, headers, and path and the request is forwarded (failing closed if a match lands somewhere unredactable, like the hostname). Under `block` it stays a hard `403`. Structural blocks (CRLF injection) and not-in-allowlist host blocks are always hard `403`s regardless of policy.
More examples in `examples/`. Full design lives under `docs/prds/`; the trust-boundary rationale is in `docs/prds/0011-per-file-md-manifest.md`.
## Trademarks
+26 -75
View File
@@ -20,7 +20,6 @@ Per PRD 0050 the per-provider implementations live under
from __future__ import annotations
import importlib.util
import inspect
import os
import shlex
import tempfile
@@ -38,19 +37,13 @@ if TYPE_CHECKING:
PROVIDER_CLAUDE = "claude"
PROVIDER_CODEX = "codex"
PROVIDER_PI = "pi"
PROVIDER_TEMPLATES = frozenset({PROVIDER_CLAUDE, PROVIDER_CODEX, PROVIDER_PI})
PROVIDER_TEMPLATES = frozenset({PROVIDER_CLAUDE, PROVIDER_CODEX})
# Hosts that egress injects the host ChatGPT bearer on when Codex
# forward_host_credentials is enabled. Pipelock must pass these through
# (no TLS MITM) or its header DLP blocks the injected JWT.
CODEX_HOST_CREDENTIAL_HOSTS = ("api.openai.com", "chatgpt.com")
PromptMode = Literal[
"append_file",
"read_prompt_file",
"print_read_prompt_file",
"append_system_prompt",
]
PromptMode = Literal["append_file", "read_prompt_file"]
@dataclass(frozen=True)
@@ -58,9 +51,11 @@ class AgentProviderRuntime:
template: str
command: str
image: str
dockerfile: str
prompt_mode: PromptMode
bypass_args: tuple[str, ...]
resume_args: tuple[str, ...]
remote_control_args: tuple[str, ...]
@dataclass(frozen=True)
@@ -108,12 +103,7 @@ class AgentProvisionPlan:
prompt_mode: PromptMode
image: str
dockerfile: str
guest_home: str
instance_name: str
prompt_file: Path
guest_env: dict[str, str]
has_prompt: bool = False
startup_args: tuple[str, ...] = ()
env_vars: dict[str, str] = field(default_factory=dict)
dirs: tuple[AgentProvisionDir, ...] = ()
files: tuple[AgentProvisionFile, ...] = ()
@@ -137,31 +127,13 @@ class AgentProvider(ABC):
"""The static command / image / prompt-mode table for this
template."""
@property
def guest_home(self) -> str:
"""In-guest home directory for the agent user. Defaults to
`/home/node` to match the Debian-based bot-bottle-* images
(USER node). Override for plugins whose image runs as a
different user."""
return "/home/node"
@property
def dockerfile(self) -> Path:
"""Path to the provider's Dockerfile.
Default: the `Dockerfile` file next to this provider's
`agent_provider.py` module. Override to point at a non-standard
path."""
return Path(inspect.getfile(type(self))).parent / "Dockerfile"
@abstractmethod
def provision_plan(
self,
*,
dockerfile: str,
state_dir: Path,
instance_name: str,
prompt_file: Path,
guest_home: str,
guest_env: dict[str, str] | None = None,
auth_token: str = "",
forward_host_credentials: bool = False,
@@ -169,7 +141,6 @@ class AgentProvider(ABC):
trusted_project_path: str = "",
label: str = "",
color: str = "",
provider_settings: dict[str, object] | None = None,
) -> AgentProvisionPlan:
"""Build the declarative AgentProvisionPlan for one launch.
Backends call this during `prepare` and consume the result as
@@ -209,15 +180,6 @@ class AgentProvider(ABC):
the supervise sidecar is reachable. No-op when
`plan.supervise_plan is None`."""
@abstractmethod
def headless_prompt(self, prompt: str) -> list[str]:
"""Return the agent CLI args that deliver `prompt` as the
initial task in a non-interactive (headless) session.
Called only when ``--prompt`` is passed to
``./cli.py start --headless``; the returned args are appended
after the provider's ``bypass_args`` and ``startup_args``."""
def provision_ca(self, bottle: "Bottle", plan: "BottlePlan") -> None:
"""Install the egress MITM CA into the agent's trust store.
@@ -227,10 +189,6 @@ class AgentProvider(ABC):
from .backend.util import AGENT_CA_PATH, log_ca_fingerprint, select_ca_cert
from .log import die
cert_host_path, label = select_ca_cert(plan.egress_plan)
# Ensure the target directory exists. A backend's rootfs build
# may not preserve the empty /usr/local/share/ca-certificates/
# directory; mkdir -p is idempotent and safe for all backends.
bottle.exec("mkdir -p /usr/local/share/ca-certificates", user="root")
bottle.cp_in(str(cert_host_path), AGENT_CA_PATH)
r = bottle.exec(
f"chmod 644 {AGENT_CA_PATH} && update-ca-certificates",
@@ -247,12 +205,25 @@ class AgentProvider(ABC):
def provision_git(self, bottle: "Bottle", plan: "BottlePlan") -> None:
"""Configure git inside the agent container.
Default: Debian/node — writes the git-gate insteadOf gitconfig
and sets user.name/email as node. Workspace copy runs through
BottleBackend.provision_workspace against the running bottle."""
Default: Debian/node — copies .git when --cwd is set, writes the
git-gate insteadOf gitconfig, sets user.name/email as node.
Override for images that run as a different user or use a
non-standard home directory."""
from .log import info
workspace = plan.workspace_plan
if workspace.enabled and workspace.copy_git and workspace.has_host_git_dir:
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}")
bottle.exec(f"mkdir -p {shlex.quote(workspace.guest_path)}", user="root")
bottle.cp_in(host_git, guest_workspace_git)
bottle.exec(
f"chown -R {shlex.quote(workspace.owner)} "
f"{shlex.quote(guest_workspace_git)}",
user="root",
)
manifest_bottle = plan.manifest.bottle
manifest_bottle = plan.spec.manifest.bottle_for(plan.spec.agent_name)
if manifest_bottle.git:
from .git_gate import GIT_GATE_HOSTNAME, git_gate_render_gitconfig
gate_host = getattr(plan, "git_gate_insteadof_host", GIT_GATE_HOSTNAME)
@@ -339,9 +310,6 @@ def get_provider(template: str) -> AgentProvider:
if template == PROVIDER_CODEX:
from .contrib.codex.agent_provider import CodexAgentProvider
return CodexAgentProvider()
if template == PROVIDER_PI:
from .contrib.pi.agent_provider import PiAgentProvider
return PiAgentProvider()
raise ValueError(f"unknown agent provider template: {template!r}")
@@ -349,13 +317,12 @@ def runtime_for(template: str) -> AgentProviderRuntime:
return get_provider(template).runtime
def build_agent_provision_plan(
def agent_provision_plan(
*,
template: str,
dockerfile: str,
state_dir: Path,
instance_name: str,
prompt_file: Path,
guest_home: str,
guest_env: dict[str, str] | None = None,
auth_token: str = "",
forward_host_credentials: bool = False,
@@ -363,15 +330,13 @@ def build_agent_provision_plan(
trusted_project_path: str = "",
label: str = "",
color: str = "",
provider_settings: dict[str, object] | None = None,
) -> AgentProvisionPlan:
"""Back-compat shim — `prepare` callers stay the same; the work
now lives on the provider plugin."""
return get_provider(template).provision_plan(
dockerfile=dockerfile,
state_dir=state_dir,
instance_name=instance_name,
prompt_file=prompt_file,
guest_home=guest_home,
guest_env=guest_env,
auth_token=auth_token,
forward_host_credentials=forward_host_credentials,
@@ -379,19 +344,9 @@ def build_agent_provision_plan(
trusted_project_path=trusted_project_path,
label=label,
color=color,
provider_settings=provider_settings,
)
def provider_startup_args(
provider_settings: dict[str, object] | None,
) -> tuple[str, ...]:
raw = (provider_settings or {}).get("startup_args", ())
if not isinstance(raw, (list, tuple)):
return ()
return tuple(arg for arg in raw if isinstance(arg, str))
def prompt_args(
prompt_mode: PromptMode,
prompt_path: str | None,
@@ -403,11 +358,7 @@ def prompt_args(
if prompt_mode == "append_file":
return ["--append-system-prompt-file", prompt_path]
if prompt_mode == "read_prompt_file":
if argv and ("resume" in argv or "remote-control" in argv):
if argv and "resume" in argv:
return []
return [f"Read and follow the instructions in {prompt_path}."]
if prompt_mode == "print_read_prompt_file":
return ["-p", f"Read and follow the instructions in {prompt_path}."]
if prompt_mode == "append_system_prompt":
return ["--append-system-prompt", prompt_path]
raise ValueError(f"unknown provider prompt mode: {prompt_mode}")
-93
View File
@@ -1,93 +0,0 @@
"""SQLite-backed audit store for supervise (PRD 0013)."""
from __future__ import annotations
import sqlite3
from pathlib import Path
try:
from .supervise_types import AuditEntry
from .paths import host_db_path
from .db_store import DbStore
from .migrations import TableMigrations
except ImportError:
from supervise_types import AuditEntry # type: ignore[import-not-found] # pylint: disable=import-error,no-name-in-module
from paths import host_db_path # type: ignore[import-not-found] # pylint: disable=import-error,no-name-in-module
from db_store import DbStore # type: ignore[import-not-found] # pylint: disable=import-error,no-name-in-module
from migrations import TableMigrations # type: ignore[import-not-found] # pylint: disable=import-error,no-name-in-module
class AuditStore(DbStore):
"""SQLite-backed persistent store for supervise audit entries."""
def __init__(self, db_path: Path | None = None) -> None:
# One entry per schema version: migrations[0] brings a fresh DB to
# version 1, [1] to version 2, etc. Add new entries at the end; never
# edit existing ones.
migrations = TableMigrations("audit_store", [
# v1 — initial schema
"""
CREATE TABLE IF NOT EXISTS supervise_audit_entries (
id INTEGER PRIMARY KEY AUTOINCREMENT,
timestamp TEXT NOT NULL,
bottle_slug TEXT NOT NULL,
component TEXT NOT NULL,
operator_action TEXT NOT NULL,
operator_notes TEXT NOT NULL,
justification TEXT NOT NULL,
diff TEXT NOT NULL
)
""",
])
super().__init__(db_path or host_db_path(), migrations)
def write_audit_entry(self, entry: AuditEntry) -> Path:
with self._connect() as conn:
conn.execute(
"""
INSERT INTO supervise_audit_entries (
timestamp, bottle_slug, component, operator_action,
operator_notes, justification, diff
) VALUES (?, ?, ?, ?, ?, ?, ?)
""",
(
entry.timestamp,
entry.bottle_slug,
entry.component,
entry.operator_action,
entry.operator_notes,
entry.justification,
entry.diff,
),
)
self._chmod()
return self.db_path
def read_audit_entries(self, component: str, slug: str) -> list[AuditEntry]:
if not self.db_path.is_file():
return []
with self._connect() as conn:
rows = conn.execute(
"""
SELECT * FROM supervise_audit_entries
WHERE component = ? AND bottle_slug = ?
ORDER BY id
""",
(component, slug),
).fetchall()
return [self._row_to_entry(row) for row in rows]
@staticmethod
def _row_to_entry(row: sqlite3.Row) -> AuditEntry:
return AuditEntry(
timestamp=row["timestamp"],
bottle_slug=row["bottle_slug"],
component=row["component"],
operator_action=row["operator_action"],
operator_notes=row["operator_notes"],
justification=row["justification"],
diff=row["diff"],
)
__all__ = ["AuditStore"]
+66 -250
View File
@@ -24,17 +24,14 @@ backend exposes five methods:
enough metadata for callers (CLI `list active`, dashboard
agents pane) to render a row.
Selection is driven by `--backend` on `start` or BOT_BOTTLE_BACKEND
(env var). When neither is set, compatible macOS hosts default to
`macos-container`; Linux hosts with KVM default to `firecracker`;
otherwise `docker`. Per PRD 0003 the manifest does not carry a
backend field; the host picks.
Selection is driven by `--backend` on `start` or
BOT_BOTTLE_BACKEND (env var; default "docker"). Per PRD 0003 the
manifest does not carry a backend field; the host picks.
"""
from __future__ import annotations
import os
import shlex
import sys
from abc import ABC, abstractmethod
from contextlib import AbstractContextManager
@@ -42,15 +39,14 @@ from dataclasses import dataclass
from pathlib import Path
from typing import Any, Generic, Sequence, TypeVar
from ..agent_provider import AgentProvisionPlan, get_provider, build_agent_provision_plan
from ..agent_provider import AgentProvisionPlan, get_provider
from ..egress import EgressPlan
from ..git_gate import GitGatePlan
from ..log import die, info
from ..manifest import Manifest, ManifestIndex
from ..manifest import GitEntry, Manifest
from ..supervise import SupervisePlan
from ..util import expand_tilde
from ..env import resolve_env, ResolvedEnv
from ..workspace import WorkspacePlan, workspace_plan
from ..workspace import WorkspacePlan
from .print_util import print_multi, visible_agent_env_names
from .util import host_skill_dir
@@ -62,7 +58,7 @@ class BottleSpec:
Resolved values (image names, container name, scratch paths, runsc
availability) live on the plan, not the spec."""
manifest: ManifestIndex
manifest: Manifest
agent_name: str
copy_cwd: bool
user_cwd: str
@@ -73,12 +69,6 @@ class BottleSpec:
identity: str = ""
label: str = ""
color: str = ""
# Ordered bottle names selected at launch (issue #269). When non-empty
# they are merged in order and replace the agent's `bottle:` field.
bottle_names: tuple[str, ...] = ()
# True when launched via --headless (no TTY, no interactive prompts).
# The git-gate host-key preflight uses this to error rather than prompt.
headless: bool = False
@dataclass(frozen=True)
@@ -87,41 +77,35 @@ class BottlePlan(ABC):
(e.g. DockerBottlePlan) add backend-specific resolved fields."""
spec: BottleSpec
manifest: Manifest
stage_dir: Path
guest_home: str
git_gate_plan: GitGatePlan
@property
def guest_home(self) -> str:
return self.agent_provision.guest_home
@property
def git_gate_insteadof_host(self) -> str:
"""Host (and optional port) used in git-gate insteadOf URLs.
Docker uses the compose-network DNS alias; VM backends may
override with an IP:port when the guest has no DNS."""
Docker uses the compose-network DNS alias; smolmachines
overrides with a loopback IP:port since TSI has no DNS."""
return "git-gate"
@property
def git_gate_insteadof_scheme(self) -> str:
"""URL scheme for git-gate insteadOf rewrites. 'git' for
Docker (git daemon); VM backends may override (e.g. 'http'
Docker (git daemon); 'http' for smolmachines (HTTP proxy
over a published host port)."""
return "git"
egress_plan: EgressPlan
supervise_plan: SupervisePlan | None
agent_provision: AgentProvisionPlan
workspace_plan: WorkspacePlan
@property
def workspace_plan(self) -> WorkspacePlan:
return workspace_plan(self.spec, guest_home=self.guest_home)
def print(self) -> None:
def print(self, *, remote_control: bool) -> None:
"""Render the y/N preflight summary to stderr."""
del remote_control
spec = self.spec
manifest = self.manifest
agent = manifest.agent
bottle = manifest.bottle
manifest = spec.manifest
agent = manifest.agents[spec.agent_name]
bottle = manifest.bottle_for(spec.agent_name)
env_names = visible_agent_env_names(
sorted(
@@ -136,13 +120,9 @@ class BottlePlan(ABC):
info(f"provider : {self.agent_provision.template}")
print_multi("env ", env_names)
print_multi("skills ", list(agent.skills))
effective_bottles = (
list(spec.bottle_names) if spec.bottle_names
else ([agent.bottle] if agent.bottle else [])
)
print_multi("bottle ", effective_bottles)
info(f"bottle : {agent.bottle}")
identity = manifest.git_identity_summary()
identity = manifest.git_identity_summary(spec.agent_name)
if identity:
info(f" git identity : {identity}")
@@ -183,8 +163,8 @@ class BottleCleanupPlan(ABC):
class ExecResult:
"""Captured result of `Bottle.exec`. Backend-neutral: the Docker
impl populates it from a `subprocess.CompletedProcess`, but a
VM backend could populate it from any source that produces a
returncode + captured streams."""
future fly/smolmachines backend could populate it from any source
that produces a returncode + captured streams."""
returncode: int
stdout: str
@@ -202,7 +182,7 @@ class ActiveAgent:
of sidecar daemons currently up for this bottle (`egress`,
`git-gate`, `supervise`); the dashboard uses it to
gate edit verbs. `backend_name` is the matching key in
`_BACKENDS` (`docker` / `firecracker` / `macos-container`) — used by the active-
`_BACKENDS` (`docker` / `smolmachines`) — used by the active-
list rendering to disambiguate and by the dashboard's
re-attach path."""
@@ -283,108 +263,27 @@ class BottleBackend(ABC, Generic[PlanT, CleanupT]):
name: str
def prepare(self, spec: BottleSpec, stage_dir: Path) -> PlanT:
def prepare(self, spec: BottleSpec, *, stage_dir: Path) -> PlanT:
"""Template method: run cross-backend host-side validation, then
delegate to the subclass's `_resolve_plan` for the
backend-specific resolution (names, scratch files, etc.). The
validation step is enforced here so a future backend cannot
accidentally skip it. No remote/runtime resources are created."""
from .resolve_common import (
merge_provision_env_vars,
mint_slug,
prepare_agent_state_dir,
prepare_egress,
prepare_git_gate,
prepare_supervise,
resolve_manifest_dockerfile,
write_launch_metadata,
)
self._validate(spec)
return self._resolve_plan(spec, stage_dir=stage_dir)
manifest = self._validate(spec)
self._preflight()
from ..git_gate_host_key import preflight_host_keys
manifest = preflight_host_keys(
manifest,
headless=spec.headless,
home_md=spec.manifest.home_md,
)
manifest_bottle = manifest.bottle
manifest_agent_provider = manifest_bottle.agent_provider
agent_provider = get_provider(manifest_agent_provider.template)
resolved_env = resolve_env(manifest)
workspace = workspace_plan(spec, guest_home=agent_provider.guest_home)
slug = mint_slug(spec)
write_launch_metadata(slug, spec, compose_project="", backend=self.name)
# Manifest may override the Dockerfile per-bottle; otherwise fall
# back to the provider plugin's bundled Dockerfile (next to its
# agent_provider.py module).
if manifest_agent_provider.dockerfile:
agent_dockerfile_path = resolve_manifest_dockerfile(
manifest_agent_provider.dockerfile, spec,
)
else:
agent_dockerfile_path = str(agent_provider.dockerfile)
agent_dir, prompt_file = prepare_agent_state_dir(slug, manifest)
agent_provision_plan = build_agent_provision_plan(
template=manifest_agent_provider.template,
dockerfile=agent_dockerfile_path,
state_dir=agent_dir,
instance_name=f"bot-bottle-{slug}",
prompt_file=prompt_file,
guest_env=self._build_guest_env(resolved_env),
forward_host_credentials=manifest_agent_provider.forward_host_credentials,
auth_token=manifest_agent_provider.auth_token,
host_env=dict(os.environ),
trusted_project_path=workspace.workdir,
label=spec.label,
color=spec.color,
provider_settings=manifest_agent_provider.settings,
)
agent_provision_plan = merge_provision_env_vars(agent_provision_plan)
egress_plan = prepare_egress(manifest_bottle, slug, agent_provision_plan)
supervise_plan = prepare_supervise(manifest_bottle, slug)
git_gate_plan = prepare_git_gate(manifest_bottle, slug)
return self._resolve_plan(
spec,
manifest=manifest,
slug=slug,
resolved_env=resolved_env,
agent_provision_plan=agent_provision_plan,
egress_plan=egress_plan,
supervise_plan=supervise_plan,
git_gate_plan=git_gate_plan,
stage_dir=stage_dir,
)
def _build_guest_env(self, resolved_env: ResolvedEnv) -> dict[str, str]:
return {}
def _preflight(self) -> None:
"""
tasks to do before resolving a plan
"""
pass
def _validate(self, spec: BottleSpec) -> Manifest:
"""Cross-backend pre-launch checks. Parses the selected agent and
its bottle (raising ManifestError on invalid content), confirms
skills are present on the host, and every git IdentityFile resolves.
Returns the loaded Manifest for the selected agent. Subclasses with
additional preconditions should override and call
`super()._validate(spec)` first."""
manifest = spec.manifest.load_for_agent(spec.agent_name, spec.bottle_names)
self._validate_skills(manifest.agent.skills)
self._validate_agent_provider_dockerfile(spec, manifest)
return manifest
def _validate(self, spec: BottleSpec) -> None:
"""Cross-backend pre-launch checks. Confirms the agent exists,
the named skills are present on the host, and every git
IdentityFile resolves. Subclasses with additional preconditions
should override and call `super()._validate(spec)` first."""
manifest = spec.manifest
manifest.require_agent(spec.agent_name)
agent = manifest.agents[spec.agent_name]
bottle = manifest.bottle_for(spec.agent_name)
self._validate_skills(agent.skills)
self._validate_git_entries(bottle.git)
self._validate_agent_provider_dockerfile(spec)
def _validate_skills(self, skills: Sequence[str]) -> None:
"""Each named skill must be a directory under the host's
@@ -398,8 +297,18 @@ class BottleBackend(ABC, Generic[PlanT, CleanupT]):
f"Create it under ~/.claude/skills/, then re-run."
)
def _validate_agent_provider_dockerfile(self, spec: BottleSpec, manifest: Manifest) -> None:
bottle = manifest.bottle
def _validate_git_entries(self, entries: Sequence[GitEntry]) -> None:
"""Each entry's IdentityFile must exist on the host (after
expanding leading ~) — the git-gate copies it in at start time
to authenticate the upstream push (PRD 0008). Shape is already
enforced by Manifest validation; this only checks presence."""
for entry in entries:
key = expand_tilde(entry.IdentityFile)
if not os.path.isfile(key):
die(f"git upstream key file not found for '{entry.Name}': {key}")
def _validate_agent_provider_dockerfile(self, spec: BottleSpec) -> None:
bottle = spec.manifest.bottle_for(spec.agent_name)
dockerfile = bottle.agent_provider.dockerfile
if not dockerfile:
return
@@ -407,31 +316,16 @@ class BottleBackend(ABC, Generic[PlanT, CleanupT]):
if not path.is_absolute():
path = Path(spec.user_cwd) / path
if not path.is_file():
effective = (
", ".join(spec.bottle_names) if spec.bottle_names else manifest.agent.bottle
)
die(
f"agent_provider.dockerfile for bottle "
f"'{effective}' not found: {path}"
f"'{spec.manifest.agents[spec.agent_name].bottle}' not found: {path}"
)
@abstractmethod
def _resolve_plan(self,
spec: BottleSpec,
*,
manifest: Manifest,
slug: str,
resolved_env: ResolvedEnv,
agent_provision_plan: AgentProvisionPlan,
egress_plan: EgressPlan,
git_gate_plan: GitGatePlan,
supervise_plan: SupervisePlan | None,
stage_dir: Path) -> PlanT:
def _resolve_plan(self, spec: BottleSpec, *, stage_dir: Path) -> PlanT:
"""Backend-specific plan resolution: image/container names,
env-file, prompt-file, proxy plan, runtime detection. Called by
`prepare` after `_validate` succeeds. Instance name, image,
prompt file, Dockerfile path, and guest home all live on
`agent_provision_plan` — the source of truth."""
`prepare` after `_validate` succeeds."""
@abstractmethod
def launch(self, plan: PlanT) -> AbstractContextManager[Bottle]:
@@ -475,30 +369,9 @@ class BottleBackend(ABC, Generic[PlanT, CleanupT]):
return prompt_path
def provision_workspace(self, plan: PlanT, bottle: "Bottle") -> None:
"""Copy the operator workspace into the running bottle.
This is the only supported workspace-provisioning path: Docker
does not build a derived image containing the current
workspace."""
workspace = plan.workspace_plan
if not (workspace.enabled and workspace.copy_contents):
return
guest_parent = workspace.guest_path.rsplit("/", 1)[0] or "/"
guest_path = shlex.quote(workspace.guest_path)
guest_parent = shlex.quote(guest_parent)
owner = shlex.quote(workspace.owner)
mode = shlex.quote(workspace.mode)
info(f"copying {workspace.host_path} -> {bottle.name}:{workspace.guest_path}")
bottle.exec(
f"rm -rf {guest_path} && mkdir -p {guest_parent}",
user="root",
)
bottle.cp_in(str(workspace.host_path), workspace.guest_path)
bottle.exec(
f"chown -R {owner} {guest_path} && chmod {mode} {guest_path}",
user="root",
)
"""Copy the operator workspace into the running bottle when
the backend cannot bake it into the agent image. Default is
no-op for backends like Docker that handle this before launch."""
def supervise_mcp_url(self, plan: PlanT) -> str:
"""Return the agent-side URL of the per-bottle supervise
@@ -507,7 +380,7 @@ class BottleBackend(ABC, Generic[PlanT, CleanupT]):
MCP entry inside the guest.
Default returns "" so backends without supervise support
don't have to implement it. Docker and firecracker override."""
don't have to implement it. Docker and smolmachines override."""
del plan
return ""
@@ -524,65 +397,26 @@ class BottleBackend(ABC, Generic[PlanT, CleanupT]):
def enumerate_active(self) -> Sequence[ActiveAgent]:
"""Return every currently-running agent on this backend.
Empty when none. Backend-specific: docker queries `docker
compose ls`; firecracker cross-references its running sidecar
containers against per-bottle metadata."""
compose ls`; smolmachines queries `smolvm machine ls --json`
+ cross-references its bundle container."""
@classmethod
@abstractmethod
def is_available(cls) -> bool:
"""Whether this backend's runtime prerequisites are satisfied
on the current host. Docker → `docker` on PATH; firecracker →
Linux + KVM. Used by the cross-backend
on the current host. Docker → `docker` on PATH; smolmachines
→ `smolvm` on PATH. Used by the cross-backend
`enumerate_active_agents` / `cmd_cleanup` to skip backends
the operator hasn't installed, so a docker-only host
doesn't fail when `cli.py list active` walks past
firecracker."""
@classmethod
@abstractmethod
def setup(cls) -> int:
"""Emit this backend's one-time host setup — privileged network
pool, daemon bring-up, install pointers, etc. — as
host-appropriate config or commands. Prints to stdout/stderr and
returns a shell exit code (0 = nothing to report / success). A
backend that needs no host setup prints a short note and returns
0. Invoked generically by `./cli.py backend setup [--backend=…]`
so operators can provision any backend without a
backend-specific command. Classmethod (like `is_available`) —
it's a host query, not per-bottle state."""
@classmethod
@abstractmethod
def status(cls) -> int:
"""Report whether this backend's prerequisites are satisfied on
the host — binaries, daemon reachability, network pool, range
conflicts, etc. Prints a human-readable summary; returns 0 when
the backend is ready to launch and non-zero when something is
missing. Invoked by `./cli.py backend status [--backend=…]`."""
@classmethod
@abstractmethod
def teardown(cls) -> int:
"""Undo `setup()` — the inverse operation, surfaced as
`./cli.py backend teardown [--backend=…]` (uninstall). Symmetric
with setup: where setup is advisory (prints the privileged
commands / declarative config to apply), teardown prints the
commands / config change to remove the host prerequisites. A
backend with no host setup prints a short note and returns 0.
Not called by the launch path or the test suite."""
smolmachines."""
# Import concrete backend classes AFTER the base types are defined, so
# each backend module can pull BottleSpec / BottlePlan / BottleBackend
# via `from . import ...` without hitting a partially-initialized module.
from .docker import DockerBottleBackend # noqa: E402 # pylint: disable=wrong-import-position
from .firecracker import FirecrackerBottleBackend # noqa: E402 # pylint: disable=wrong-import-position
from .macos_container import MacosContainerBottleBackend # noqa: E402 # pylint: disable=wrong-import-position
# Freezer is imported after the backend classes for the same reason:
# Freezer.commit_slug constructs ActiveAgent, which must be fully
# defined first.
from .freeze import CommitCancelled, Freezer, get_freezer # noqa: E402 # pylint: disable=wrong-import-position
from .smolmachines import SmolmachinesBottleBackend # noqa: E402 # pylint: disable=wrong-import-position
# The dict is heterogeneous: each value is a BottleBackend specialized
@@ -591,8 +425,7 @@ from .freeze import CommitCancelled, Freezer, get_freezer # noqa: E402 # pylin
# unparameterized methods (prepare → plan → launch(plan), cleanup, etc.).
_BACKENDS: dict[str, BottleBackend[Any, Any]] = {
"docker": DockerBottleBackend(),
"firecracker": FirecrackerBottleBackend(),
"macos-container": MacosContainerBottleBackend(),
"smolmachines": SmolmachinesBottleBackend(),
}
@@ -604,31 +437,17 @@ def get_bottle_backend(
`name` precedence:
1. explicit arg (CLI `--backend=<name>` passes through here)
2. BOT_BOTTLE_BACKEND env var
3. `macos-container` on compatible macOS hosts
4. `firecracker` on KVM-capable Linux hosts
5. default `docker`
3. default `docker`
Dies with a pointer at the known backends if the chosen name
isn't implemented."""
resolved = name or os.environ.get("BOT_BOTTLE_BACKEND") or _default_backend_name()
resolved = name or os.environ.get("BOT_BOTTLE_BACKEND") or "docker"
if resolved not in _BACKENDS:
known = ", ".join(sorted(_BACKENDS))
die(f"unknown backend {resolved!r}; known backends: {known}")
return _BACKENDS[resolved]
def _default_backend_name() -> str:
if has_backend("macos-container"):
return "macos-container"
# A KVM-capable Linux host defaults to firecracker even when the
# `firecracker` binary isn't installed yet: selecting it here routes
# start through firecracker's preflight, which prints an install
# pointer, instead of silently falling back to docker.
if FirecrackerBottleBackend.is_host_capable():
return "firecracker"
return "docker"
def known_backend_names() -> tuple[str, ...]:
"""Sorted tuple of all backend keys in `_BACKENDS`. Used by
argparse (`--backend` choices) and the dashboard's backend
@@ -640,7 +459,7 @@ def has_backend(name: str) -> bool:
"""Whether the named backend's runtime prerequisites are
available on the current host. Cross-backend callers (list,
cleanup) skip unavailable backends so a docker-only host
doesn't fail when the firecracker backend isn't usable,
doesn't fail when the smolmachines backend isn't installed,
and vice versa.
Returns False for unknown names so callers can pass
@@ -678,12 +497,9 @@ __all__ = [
"BottleCleanupPlan",
"BottlePlan",
"BottleSpec",
"CommitCancelled",
"ExecResult",
"Freezer",
"enumerate_active_agents",
"get_bottle_backend",
"get_freezer",
"has_backend",
"known_backend_names",
]
+8 -57
View File
@@ -2,10 +2,10 @@
This module is a thin façade. The real work lives in four siblings:
- resolve_plan.py — Docker-specific resolution into a DockerBottlePlan
- launch.py — bring-up + teardown context manager
- cleanup.py — orphan enumeration + removal
- enumerate.py — active-agent listing
- prepare.py — host-side resolution into a DockerBottlePlan
- launch.py — bring-up + teardown context manager
- cleanup.py — orphan enumeration + removal
- enumerate.py — active-agent listing
The base class's `prepare` template runs cross-backend host-side
validation before calling `_resolve_plan` here.
@@ -25,23 +25,17 @@ from pathlib import Path
from typing import Generator, Sequence
from ...supervise import SUPERVISE_HOSTNAME, SUPERVISE_PORT
from ...agent_provider import AgentProvisionPlan
from ...egress import EgressPlan
from ...env import ResolvedEnv
from ...git_gate import GitGatePlan
from ...supervise import SupervisePlan
from ...manifest import Manifest
from .. import ActiveAgent, BottleBackend, BottleSpec
from . import cleanup as _cleanup
from . import enumerate as _enumerate
from . import launch as _launch
from . import resolve_plan as _resolve_plan
from . import prepare as _prepare
from .bottle import DockerBottle
from .bottle_cleanup_plan import DockerBottleCleanupPlan
from .bottle_plan import DockerBottlePlan
class DockerBottleBackend(BottleBackend["DockerBottlePlan", "DockerBottleCleanupPlan"]):
"""Docker backend implementation. Selected by BOT_BOTTLE_BACKEND
when set to `docker`; retained as a legacy/example backend."""
(default)."""
name = "docker"
@@ -54,51 +48,8 @@ class DockerBottleBackend(BottleBackend["DockerBottlePlan", "DockerBottleCleanup
launch."""
return shutil.which("docker") is not None
@classmethod
def setup(cls) -> int:
from . import setup as _setup
return _setup.setup()
@classmethod
def status(cls) -> int:
from . import setup as _setup
return _setup.status()
@classmethod
def teardown(cls) -> int:
from . import setup as _setup
return _setup.teardown()
def _preflight(self) -> None:
_resolve_plan.preflight()
def _build_guest_env(self, resolved_env: ResolvedEnv) -> dict[str, str]:
return _resolve_plan.build_guest_env(resolved_env)
def _resolve_plan(
self,
spec: BottleSpec,
*,
manifest: Manifest,
slug: str,
resolved_env: ResolvedEnv,
agent_provision_plan: AgentProvisionPlan,
egress_plan: EgressPlan,
git_gate_plan: GitGatePlan,
supervise_plan: SupervisePlan | None,
stage_dir: Path,
) -> DockerBottlePlan:
return _resolve_plan.resolve_plan(
spec,
manifest=manifest,
slug=slug,
resolved_env=resolved_env,
agent_provision_plan=agent_provision_plan,
egress_plan=egress_plan,
supervise_plan=supervise_plan,
git_gate_plan=git_gate_plan,
stage_dir=stage_dir,
)
def _resolve_plan(self, spec: BottleSpec, *, stage_dir: Path) -> DockerBottlePlan:
return _prepare.resolve_plan(spec, stage_dir=stage_dir)
@contextmanager
def launch(self, plan: DockerBottlePlan) -> Generator[DockerBottle, None, None]:
+6 -16
View File
@@ -9,7 +9,6 @@ from typing import cast
from ...agent_provider import PromptMode, prompt_args
from .. import Bottle, ExecResult
from ..terminal import exec_shell_script
class DockerBottle(Bottle):
@@ -23,20 +22,15 @@ class DockerBottle(Bottle):
*,
agent_command: str = "claude",
agent_prompt_mode: PromptMode = "append_file",
agent_provider_template: str = "claude",
terminal_title: str = "",
terminal_color: str = "",
agent_workdir: str = "/home/node",
):
self.name = container
self._teardown = teardown
self.prompt_path = prompt_path_in_container
self._agent_prompt_mode = agent_prompt_mode
self.agent_command = agent_command
self.terminal_title = terminal_title
self.terminal_color = terminal_color
self.agent_provider_template = agent_provider_template
self.agent_workdir = agent_workdir
self.agent_provider_template = (
"codex" if agent_command == "codex" else "claude"
)
self._closed = False
def agent_argv(
@@ -49,17 +43,13 @@ class DockerBottle(Bottle):
cmd = ["docker", "exec"]
if tty:
cmd.append("-it")
if self.agent_workdir and self.agent_workdir != "/home/node":
cmd.extend(["-w", self.agent_workdir])
cmd.extend([self.name, self.agent_command, *full_argv])
return cmd
def exec_agent(self, argv: list[str], *, tty: bool = True) -> int:
agent_argv = self.agent_argv(argv, tty=tty)
script = exec_shell_script(agent_argv, self.terminal_title, self.terminal_color) if tty else None
if script is None:
return subprocess.run(agent_argv, check=False).returncode
return subprocess.run(["sh", "-lc", script], check=False).returncode
return subprocess.run(
self.agent_argv(argv, tty=tty), check=False,
).returncode
def exec(self, script: str, *, user: str = "node") -> ExecResult:
# Pipe via stdin to `sh -s` so the caller never has to worry
+12 -19
View File
@@ -22,32 +22,25 @@ class DockerBottlePlan(BottlePlan):
`agent_provision` from BottlePlan."""
slug: str
container_name: str
container_name_pinned: bool
image: str
derived_image: str # "" -> no derived image
runtime_image: str # image actually launched (derived or base)
# Absolute path to the Dockerfile that builds `image`. Empty means
# use the repo's default Dockerfile. Populated to a per-bottle
# state file (~/.bot-bottle/state/<slug>/Dockerfile) after a
# capability-block remediation (PRD 0016).
dockerfile_path: str
env_file: Path # docker --env-file: NAME=VALUE literals
# name -> value for vars forwarded into the docker-run child process
# via subprocess env (so values never land on argv or in a file).
# repr=False keeps secret/interpolated/OAuth values out of any
# accidental log of the plan dataclass.
forwarded_env: dict[str, str] = field(repr=False)
prompt_file: Path
use_runsc: bool
@property
def container_name(self) -> str:
return self.agent_provision.instance_name
@property
def image(self) -> str:
return self.agent_provision.image
@property
def dockerfile_path(self) -> str:
"""Absolute path to the Dockerfile that builds `image`. Sourced
from the agent provision plan — the manifest may override per
bottle; otherwise the provider plugin's bundled Dockerfile."""
return self.agent_provision.dockerfile
@property
def prompt_file(self) -> Path:
return self.agent_provision.prompt_file
@property
def agent_command(self) -> str:
return self.agent_provision.command
@@ -1,7 +1,8 @@
"""Per-bottle persistent state.
"""Per-bottle persistent state (PRD 0016).
Holds optional per-bottle Dockerfile overrides, the transcript snapshot
the state-preservation helper saves before teardown, and the launch metadata that lets
Holds the per-bottle Dockerfile override that capability-block
remediation writes, the transcript snapshot the state-preservation
helper saves before teardown, and the launch metadata that lets
`cli.py resume <identity>` reconstruct a bottle's spec. State
lives at:
@@ -36,13 +37,13 @@ from dataclasses import dataclass
from pathlib import Path
from typing import cast
from .paths import bot_bottle_root
from ... import supervise as _supervise
from . import util as docker_mod
# Directory layout: ~/.bot-bottle/state/<identity>/...
_STATE_SUBDIR = "state"
_PER_BOTTLE_DOCKERFILE_NAME = "Dockerfile"
_COMMITTED_IMAGE_NAME = "committed-image"
_TRANSCRIPT_SUBDIR = "transcript"
# Per-sidecar scratch subdirs. PRD 0018 chunk 2: bind-mount sources
# live here so chunk 3's `docker compose up` can find them at stable
@@ -60,7 +61,7 @@ _METADATA_NAME = "metadata.json"
_LIVE_CONFIG_SUBDIR = "live-config"
LIVE_CONFIG_ROUTES_NAME = "routes.yaml"
LIVE_CONFIG_ALLOWLIST_NAME = "allowlist"
# Empty marker file. Session preservation writes it before teardown so
# Empty marker file. capability_apply writes it before teardown so
# cli.py's session-end cleanup knows to preserve the state dir for
# `cli.py resume <identity>`. Absent = clean up.
_PRESERVE_MARKER = ".preserve"
@@ -81,7 +82,6 @@ def bottle_identity(agent_name: str) -> str:
To continue an existing bottle's state, use the recorded
identity from BottleMetadata via `cli.py resume <identity>`,
not this function."""
from .backend.docker import util as docker_mod
slug = docker_mod.slugify(agent_name)
suffix = "".join(secrets.choice(_SUFFIX_ALPHABET) for _ in range(_RANDOM_SUFFIX_LEN))
return f"{slug}-{suffix}"
@@ -105,16 +105,12 @@ class BottleMetadata:
# written before chunk 3 (resume / inspect should fall back to
# deriving from identity in that case).
compose_project: str = ""
# PRD 0040: backend name ("docker", "firecracker", "macos-container").
# Empty string for state dirs written before PRD 0040; callers default
# to "docker" for backward compatibility.
# PRD 0040: backend name ("docker" or "smolmachines"). Empty string
# for state dirs written before PRD 0040; callers default to "docker"
# for backward compatibility.
backend: str = ""
label: str = ""
color: str = ""
# Ordered bottle names selected at launch (issue #269). Empty tuple
# for state dirs written before this change; resume falls back to
# the agent's `bottle:` field in that case.
bottle_names: tuple[str, ...] = ()
def metadata_path(identity: str) -> Path:
@@ -142,10 +138,6 @@ def read_metadata(identity: str) -> BottleMetadata | None:
if not isinstance(raw, dict):
return None
raw_typed = cast(dict[str, object], raw)
raw_bottle_names = raw_typed.get("bottle_names", [])
bottle_names: tuple[str, ...] = ()
if isinstance(raw_bottle_names, list):
bottle_names = tuple(str(n) for n in raw_bottle_names if isinstance(n, str))
return BottleMetadata(
identity=str(raw_typed.get("identity", identity)),
agent_name=str(raw_typed.get("agent_name", "")),
@@ -156,14 +148,13 @@ def read_metadata(identity: str) -> BottleMetadata | None:
backend=str(raw_typed.get("backend", "")),
label=str(raw_typed.get("label", "")),
color=str(raw_typed.get("color", "")),
bottle_names=bottle_names,
)
def bottle_state_dir(identity: str) -> Path:
"""Per-bottle state directory on the host. Created lazily by the
write helpers; readers tolerate its absence."""
return bot_bottle_root() / _STATE_SUBDIR / identity
return _supervise.bot_bottle_root() / _STATE_SUBDIR / identity
def per_bottle_dockerfile_path(identity: str) -> Path:
@@ -172,7 +163,8 @@ def per_bottle_dockerfile_path(identity: str) -> Path:
def per_bottle_dockerfile(identity: str) -> str | None:
"""Return the per-bottle Dockerfile content if present, else
None. None means: use the provider or manifest Dockerfile."""
None. None means: use the repo's Dockerfile (the original
pre-capability-block behavior)."""
p = per_bottle_dockerfile_path(identity)
if p.is_file():
return p.read_text()
@@ -187,32 +179,6 @@ def write_per_bottle_dockerfile(identity: str, content: str) -> Path:
return p
def committed_image_path(identity: str) -> Path:
return bottle_state_dir(identity) / _COMMITTED_IMAGE_NAME
def write_committed_image(identity: str, image_tag: str) -> Path:
"""Persist the committed image tag for `identity`. The next
`cli.py resume <identity>` will boot from this image instead of
rebuilding from the Dockerfile."""
path = committed_image_path(identity)
path.parent.mkdir(parents=True, exist_ok=True)
path.write_text(image_tag.strip() + "\n")
path.chmod(0o644)
return path
def read_committed_image(identity: str) -> str | None:
"""Return the committed image tag for `identity`, or None if no
commit has been recorded. Used by the Docker launch step to skip
the Dockerfile build when a committed snapshot exists."""
path = committed_image_path(identity)
if not path.is_file():
return None
tag = path.read_text().strip()
return tag or None
def per_bottle_image_tag(identity: str) -> str:
"""Image tag for a rebuilt bottle. Distinct from the base
bot-bottle-claude:latest so per-bottle rebuilds don't collide in
@@ -256,7 +222,9 @@ def write_live_config(
def transcript_snapshot_dir(identity: str) -> Path:
"""Where agent session snapshots are kept for resume flows."""
"""Where capability_apply stashes the agent's transcript before
teardown, so the next `cli.py start <agent>` can offer to
resume from it."""
return bottle_state_dir(identity) / _TRANSCRIPT_SUBDIR
@@ -283,9 +251,11 @@ def git_gate_state_dir(identity: str) -> Path:
def supervise_state_dir(identity: str) -> Path:
"""State subdir reserved for supervise sidecar bind-mount sources.
Runtime queue/audit rows live in the host-level bot-bottle SQLite
database, so they survive state-dir cleanup."""
"""State subdir for the supervise sidecar's current-config dir
(bind-mounted into the agent at /etc/bot-bottle/current-config).
The queue dir is intentionally NOT under here it lives at
~/.bot-bottle/queue/<slug>/ alongside the audit logs, so it
survives state-dir cleanup."""
return bottle_state_dir(identity) / _SUPERVISE_SUBDIR
@@ -304,8 +274,9 @@ def preserve_marker_path(identity: str) -> Path:
def mark_preserved(identity: str) -> Path:
"""Mark this bottle's state for preservation across session
teardown so cli.py's session-end cleanup leaves the state dir
intact for a subsequent `cli.py resume`."""
teardown. Written by capability_apply.apply_capability_change so
cli.py's session-end cleanup leaves the state dir intact for a
subsequent `cli.py resume`."""
path = preserve_marker_path(identity)
path.parent.mkdir(parents=True, exist_ok=True)
path.touch()
@@ -318,7 +289,7 @@ def is_preserved(identity: str) -> bool:
def clear_preserve_marker(identity: str) -> None:
"""Idempotent removal. Called at fresh launch (start or resume)
so a marker left from a prior preserved session doesn't keep
so a marker left from a prior capability-block doesn't keep
state alive past the next normal session-end."""
try:
preserve_marker_path(identity).unlink()
@@ -343,7 +314,6 @@ __all__ = [
"bottle_state_dir",
"cleanup_state",
"clear_preserve_marker",
"committed_image_path",
"egress_state_dir",
"git_gate_state_dir",
"is_preserved",
@@ -353,11 +323,9 @@ __all__ = [
"per_bottle_dockerfile_path",
"per_bottle_image_tag",
"preserve_marker_path",
"read_committed_image",
"read_metadata",
"supervise_state_dir",
"transcript_snapshot_dir",
"write_committed_image",
"write_metadata",
"write_per_bottle_dockerfile",
]
@@ -0,0 +1,218 @@
"""capability_apply — host-side orchestrator for capability-block
remediation (PRD 0016).
On approval of a capability-block proposal, the dashboard calls
apply_capability_change(slug, new_dockerfile) which:
1. Snapshots the agent's transcript dir to
~/.bot-bottle/state/<slug>/transcript/ (best-effort).
2. Pushes the agent's working tree via `git push` (best-effort —
no upstream / no commits / no git repo all skip with a log).
3. Writes the new Dockerfile to
~/.bot-bottle/state/<slug>/Dockerfile (PRD 0016 Phase 1
state). The next `cli.py start <agent>` picks it up.
4. Force-removes the agent container + all sidecars + the
per-bottle networks. Idempotent — missing resources are not
errors.
Returns (before, after) Dockerfile contents so the dashboard can
record / render the diff. (capability-block has no audit log per
PRD 0013 — the per-bottle Dockerfile state is its own record.)
This is "fire-and-forget" from the agent's perspective: by the time
the dashboard writes the response file the supervise sidecar is
gone, so the agent's tool call connection drops without ever
receiving the response. The replacement agent (next manual
`cli.py start`) sees the new Dockerfile and starts from there.
v1 does not auto-relaunch — see PRD 0016's capability-block return
semantics open question.
"""
from __future__ import annotations
import shutil
import subprocess
from pathlib import Path
from ...log import info, warn
from .bottle_state import (
mark_preserved,
per_bottle_dockerfile,
transcript_snapshot_dir,
write_per_bottle_dockerfile,
)
from .sidecar_bundle import sidecar_bundle_container_name
# Agent home inside the container (per the repo Dockerfile's
# `USER node` + `WORKDIR /home/node`). Used to locate the transcript
# dir + the workspace dir for git push.
_AGENT_HOME_IN_CONTAINER = "/home/node"
_AGENT_TRANSCRIPT_IN_CONTAINER = f"{_AGENT_HOME_IN_CONTAINER}/.claude"
_AGENT_WORKSPACE_IN_CONTAINER = f"{_AGENT_HOME_IN_CONTAINER}/workspace"
# Per-bottle resource name patterns (mirroring prepare.py).
def _agent_container_name(slug: str) -> str:
return f"bot-bottle-{slug}"
def _per_bottle_container_names(slug: str) -> list[str]:
"""All container names that belong to this bottle. Missing
containers are silently skipped by the teardown helper, so it's
fine to include names that don't exist for a given bottle."""
return [
_agent_container_name(slug),
sidecar_bundle_container_name(slug),
]
def _per_bottle_network_names(slug: str) -> list[str]:
return [
f"bot-bottle-net-{slug}",
f"bot-bottle-egress-{slug}",
]
class CapabilityApplyError(RuntimeError):
"""Raised when the apply fails in a way that should keep the
proposal pending (so the operator can retry). Best-effort
failures (transcript snapshot, git push) do not raise — they
just log and proceed."""
# --- Public helpers --------------------------------------------------------
def fetch_current_dockerfile(slug: str) -> str:
"""Return the Dockerfile content the next `cli.py start <agent>`
would use for this bottle. If a per-bottle override exists, that
one; otherwise the repo's Dockerfile.
Used by the operator-edit verb to show the current source of
truth, and by apply_capability_change for the before-diff."""
override = per_bottle_dockerfile(slug)
if override is not None:
return override
repo_dockerfile = _repo_dockerfile_path()
if repo_dockerfile.is_file():
return repo_dockerfile.read_text()
raise CapabilityApplyError(
f"no per-bottle Dockerfile for {slug} and no repo Dockerfile at "
f"{repo_dockerfile}"
)
def apply_capability_change(slug: str, new_dockerfile: str) -> tuple[str, str]:
"""End-to-end capability-block remediation. See module docstring
for the sequence. Returns (before, after) Dockerfile content."""
if not new_dockerfile.strip():
raise CapabilityApplyError("proposed Dockerfile is empty")
before = fetch_current_dockerfile(slug)
snapshot_transcript(slug)
_push_working_tree(slug)
write_per_bottle_dockerfile(slug, new_dockerfile)
# Set the preserve marker BEFORE teardown so cli.py's session-end
# cleanup sees it and keeps the state dir intact for the
# operator's `cli.py resume <identity>`. Without the marker the
# state dir would be deleted as part of normal session end.
mark_preserved(slug)
_teardown_bottle(slug)
return before, new_dockerfile
# --- Internals -------------------------------------------------------------
def _repo_dockerfile_path() -> Path:
"""Path to the repo's Claude Dockerfile (one dir above this module's
package root). Resolved at call time so the path is correct
regardless of where this module is imported from."""
# bot_bottle/backend/docker/capability_apply.py -> repo root
return Path(__file__).resolve().parent.parent.parent.parent / "Dockerfile.claude"
def snapshot_transcript(slug: str) -> None:
"""`docker cp` /home/node/.claude out of the agent container into
~/.bot-bottle/state/<slug>/transcript/. Best-effort: missing
container, missing dir, or cp error all log a warning and return.
The transcript is what `claude --resume` reads to pick up where
the agent left off.
Called from two places:
- capability-apply, before tearing the bottle down.
- cli.py's session-end path, before the launch context closes,
so a crash or normal exit also leaves a transcript on disk
(deleted along with the state dir on clean exit, kept on
crash or capability-block per the preserve marker)."""
container = _agent_container_name(slug)
dest = transcript_snapshot_dir(slug)
if dest.exists():
# Remove any prior snapshot so the new one is a clean copy.
shutil.rmtree(dest, ignore_errors=True)
dest.parent.mkdir(parents=True, exist_ok=True)
r = subprocess.run(
["docker", "cp", f"{container}:{_AGENT_TRANSCRIPT_IN_CONTAINER}", str(dest)],
capture_output=True, text=True, check=False,
)
if r.returncode != 0:
warn(
f"transcript snapshot skipped "
f"({(r.stderr or '').strip() or 'no transcript dir in container?'})"
)
return
info(f"transcript snapshotted to {dest}")
def _push_working_tree(slug: str) -> None:
"""`docker exec <agent> git push` from /home/node/workspace.
Best-effort: not-a-git-repo, no upstream, nothing-to-push, no
network all log a warning and return. The replacement bottle
will pick up whatever's actually upstream."""
container = _agent_container_name(slug)
r = subprocess.run(
[
"docker", "exec", container, "sh", "-c",
f"cd {_AGENT_WORKSPACE_IN_CONTAINER} && "
f"git rev-parse --is-inside-work-tree >/dev/null 2>&1 && "
f"git push origin HEAD 2>&1 || true",
],
capture_output=True, text=True, check=False,
)
if r.returncode != 0:
warn(
f"capability-apply: git push skipped "
f"({(r.stderr or '').strip() or 'docker exec failed'})"
)
return
output = (r.stdout or "").strip()
if output:
info(f"capability-apply: git push: {output}")
else:
info("capability-apply: git push ran (no output — likely not a git workspace)")
def _teardown_bottle(slug: str) -> None:
"""Force-remove all per-bottle docker resources. Idempotent —
`docker rm -f` / `docker network rm` silently ignore missing
names, so this can be called even mid-rebuild."""
info(f"capability-apply: tearing down bottle {slug}")
for name in _per_bottle_container_names(slug):
subprocess.run(
["docker", "rm", "-f", name],
stdout=subprocess.DEVNULL, stderr=subprocess.DEVNULL, check=False,
)
for net in _per_bottle_network_names(slug):
subprocess.run(
["docker", "network", "rm", net],
stdout=subprocess.DEVNULL, stderr=subprocess.DEVNULL, check=False,
)
__all__ = [
"CapabilityApplyError",
"apply_capability_change",
"fetch_current_dockerfile",
"snapshot_transcript",
]
+8 -7
View File
@@ -18,7 +18,8 @@ scan, just as a fallback bucket alongside the project list.
`cleanup` removes everything in the plan.
Active-agent enumeration lives in `backend/docker/enumerate.py`.
Active-agent enumeration lives in `backend/docker/enumerate.py`
(mirror of `backend/smolmachines/enumerate.py`).
"""
from __future__ import annotations
@@ -26,11 +27,11 @@ from __future__ import annotations
import shutil
import subprocess
from ...paths import bot_bottle_root
from ... import supervise as _supervise
from ...log import info, warn
from . import util as docker_mod
from .bottle_cleanup_plan import DockerBottleCleanupPlan
from ...bottle_state import bottle_state_dir, is_preserved
from .bottle_state import bottle_state_dir, is_preserved
from .compose import COMPOSE_PROJECT_PREFIX, list_compose_projects
@@ -92,9 +93,9 @@ def _list_orphan_state_dirs(
`protected_identities` is the set of slugs that are live in
ANY backend — used so this docker-side check doesn't reap a
running non-docker bottle's state dir (the layout is shared
across backends)."""
state_root = bot_bottle_root() / "state"
running smolmachines bottle's state dir (the layout is shared
across both backends)."""
state_root = _supervise.bot_bottle_root() / "state"
if not state_root.is_dir():
return []
orphans: list[str] = []
@@ -118,7 +119,7 @@ def prepare_cleanup() -> DockerBottleCleanupPlan:
Pulls the union of live identities across backends via
`enumerate_active_agents()` so the orphan-state-dir bucket
doesn't include slugs whose non-docker bottle is still up."""
doesn't include slugs whose smolmachines VM is still up."""
docker_mod.require_docker()
projects = list_compose_projects()
project_set = set(projects)
+21 -10
View File
@@ -28,13 +28,12 @@ from typing import Any
from ...egress import (
EGRESS_HOSTNAME,
EGRESS_ROUTES_IN_CONTAINER,
egress_agent_env_entries,
egress_sidecar_env_entries,
)
from ...git_gate import GIT_GATE_HOSTNAME
from ...log import die, warn
from ...supervise import (
DB_PATH_IN_CONTAINER,
CURRENT_CONFIG_DIR_IN_AGENT,
QUEUE_DIR_IN_CONTAINER,
SUPERVISE_HOSTNAME,
SUPERVISE_PORT,
)
@@ -135,8 +134,9 @@ def _sidecar_bundle_service(plan: DockerBottlePlan) -> dict[str, Any]:
ep = plan.egress_plan
volumes.append(_bind(ep.mitmproxy_ca_host_path, EGRESS_CA_IN_CONTAINER))
if ep.routes:
volumes.append(_bind(ep.routes_path.parent, str(Path(EGRESS_ROUTES_IN_CONTAINER).parent)))
env.extend(egress_sidecar_env_entries(ep))
volumes.append(_bind(ep.routes_path, EGRESS_ROUTES_IN_CONTAINER))
for token_env in sorted(ep.token_env_map.keys()):
env.append(token_env)
# --- git-gate -----------------------------------------------------
gp = plan.git_gate_plan
@@ -163,15 +163,16 @@ def _sidecar_bundle_service(plan: DockerBottlePlan) -> dict[str, Any]:
if sp is not None:
env += [
f"SUPERVISE_BOTTLE_SLUG={plan.slug}",
f"SUPERVISE_DB_PATH={DB_PATH_IN_CONTAINER}",
f"SUPERVISE_QUEUE_DIR={QUEUE_DIR_IN_CONTAINER}",
f"SUPERVISE_PORT={SUPERVISE_PORT}",
]
volumes.append({
"type": "bind",
"source": str(sp.db_path),
"target": DB_PATH_IN_CONTAINER,
"source": str(sp.queue_dir),
"target": QUEUE_DIR_IN_CONTAINER,
"read_only": False,
})
internal_aliases = [EGRESS_HOSTNAME]
if gp.upstreams:
internal_aliases.append(GIT_GATE_HOSTNAME)
@@ -219,10 +220,9 @@ def _agent_service(plan: DockerBottlePlan) -> dict[str, Any]:
# never lands on argv or in the compose file.
for name in sorted(plan.forwarded_env.keys()):
env.append(name)
env.extend(egress_agent_env_entries(plan.egress_plan))
service: dict[str, Any] = {
"image": plan.image,
"image": plan.runtime_image,
"container_name": plan.container_name,
"command": ["sleep", "infinity"],
"networks": {"internal": None},
@@ -230,6 +230,17 @@ def _agent_service(plan: DockerBottlePlan) -> dict[str, Any]:
}
if plan.use_runsc:
service["runtime"] = "runsc"
if plan.env_file and plan.env_file.exists() and plan.env_file.stat().st_size > 0:
service["env_file"] = [str(plan.env_file)]
volumes: list[dict[str, Any]] = []
if plan.supervise_plan is not None:
volumes.append(_bind(
plan.supervise_plan.current_config_dir,
CURRENT_CONFIG_DIR_IN_AGENT,
))
if volumes:
service["volumes"] = volumes
# The init supervisor inside the bundle owns intra-bundle
# daemon ordering, so the agent only waits for the bundle
@@ -1,145 +0,0 @@
"""Consolidated bottle launch sequence for the docker backend (PRD 0070).
Composes the orchestrator primitives into the register/teardown sequence that
replaces the per-bottle sidecar bundle:
1. ensure the orchestrator control plane + shared gateway are up;
2. allocate the bottle a pinned source IP on the gateway network (the
attribution key), skipping the gateway's own address + live bottles;
3. register it (egress policy blob + slug metadata) → bottle id + identity
token;
4. provision its git-gate repos/creds into the running gateway.
It returns a `LaunchContext` with everything the agent container needs to
attach — network, pinned IP, the gateway's address (its proxy target), the
orchestrator URL, and the identity token. The agent `docker run` itself is
the backend's job (it owns provider provisioning); this owns the
orchestrator-facing wiring so that sequence stays testable in isolation.
"""
from __future__ import annotations
from dataclasses import dataclass
from ...docker_cmd import run_docker
from ...egress import EgressPlan
from ...git_gate import GitGatePlan
from ...orchestrator.client import OrchestratorClient
from ...orchestrator.gateway import GATEWAY_NAME, GATEWAY_NETWORK
from ...orchestrator.lifecycle import OrchestratorProcess
from ...orchestrator.registration import registration_inputs
from .gateway_net import next_free_ip
from .gateway_provision import deprovision_git_gate, provision_git_gate
class ConsolidatedLaunchError(RuntimeError):
"""The consolidated register/provision sequence could not complete."""
@dataclass(frozen=True)
class LaunchContext:
"""What the agent container needs to join the shared gateway."""
bottle_id: str
identity_token: str
source_ip: str # the agent's pinned address (attribution key)
network: str # the shared gateway network to attach to
gateway_ip: str # the gateway's address — the agent's proxy target
orchestrator_url: str
def _network_cidr(network: str) -> str:
"""The gateway network's IPv4 subnet, or raise."""
proc = run_docker([
"docker", "network", "inspect",
"--format", "{{range .IPAM.Config}}{{.Subnet}}{{end}}", network,
])
cidr = proc.stdout.strip()
if proc.returncode != 0 or not cidr:
raise ConsolidatedLaunchError(
f"gateway network {network} has no subnet: {proc.stderr.strip()}"
)
return cidr
def _container_ip(name: str, network: str) -> str:
"""A container's IPv4 address on `network`, or raise."""
proc = run_docker([
"docker", "inspect", "--format",
f'{{{{(index .NetworkSettings.Networks "{network}").IPAddress}}}}', name,
])
ip = proc.stdout.strip()
if proc.returncode != 0 or not ip:
raise ConsolidatedLaunchError(
f"gateway {name} has no address on {network}: {proc.stderr.strip()}"
)
return ip
def _taken_ips(client: OrchestratorClient, gateway_ip: str) -> list[str]:
"""Every address already in use on the gateway network: the gateway
container plus every live bottle the registry knows."""
taken = [gateway_ip]
for rec in client.list_bottles():
src = rec.get("source_ip")
if isinstance(src, str) and src:
taken.append(src)
return taken
def launch_consolidated(
egress_plan: EgressPlan,
git_gate_plan: GitGatePlan,
*,
image_ref: str = "",
process: OrchestratorProcess | None = None,
gateway_name: str = GATEWAY_NAME,
network: str = GATEWAY_NETWORK,
) -> LaunchContext:
"""Ensure the orchestrator + gateway are up, allocate + register the
bottle, and provision its git-gate state. Returns the agent's attach
context. Raises `ConsolidatedLaunchError` (or the primitives' own errors)
if any step fails — the caller tears down on failure."""
process = process or OrchestratorProcess()
url = process.ensure_running()
client = OrchestratorClient(url)
cidr = _network_cidr(network)
gateway_ip = _container_ip(gateway_name, network)
source_ip = next_free_ip(cidr, _taken_ips(client, gateway_ip))
inputs = registration_inputs(egress_plan)
reg = client.register_bottle(
source_ip, image_ref=image_ref, policy=inputs.policy, metadata=inputs.metadata,
)
try:
provision_git_gate(gateway_name, reg.bottle_id, git_gate_plan)
except Exception:
# Roll the registration back so a provisioning failure leaves no orphan.
client.teardown_bottle(reg.bottle_id)
raise
return LaunchContext(
bottle_id=reg.bottle_id,
identity_token=reg.identity_token,
source_ip=source_ip,
network=network,
gateway_ip=gateway_ip,
orchestrator_url=url,
)
def teardown_consolidated(
bottle_id: str, *, orchestrator_url: str, gateway_name: str = GATEWAY_NAME,
) -> None:
"""Deregister the bottle and remove its git-gate state from the gateway.
Both steps are idempotent so this is safe from a cleanup trap."""
OrchestratorClient(orchestrator_url).teardown_bottle(bottle_id)
deprovision_git_gate(gateway_name, bottle_id)
__all__ = [
"LaunchContext",
"launch_consolidated",
"teardown_consolidated",
"ConsolidatedLaunchError",
]
+18 -29
View File
@@ -1,21 +1,24 @@
"""Host-side helper for egress sidecar inspection and live updates.
"""Host-side helper for egress sidecar inspection (issue #198).
The approve path uses this module to validate a proposed routes file,
write it to the bottle's live egress state dir, and signal the sidecar
bundle so the mitmproxy addon reloads it.
`_merge_single_route`, `add_route`, and `apply_routes_change` were
removed when the egress-block MCP tool was dropped. The remaining
helpers support runtime inspection and validation of the routes file
without modifying it at runtime.
"""
from __future__ import annotations
import os
import subprocess
from ...egress import EGRESS_ROUTES_IN_CONTAINER
from ...log import warn
from ..egress_apply import EgressApplicator, EgressApplyError
from ...egress_addon_core import load_routes
from .sidecar_bundle import sidecar_bundle_container_name
class EgressApplyError(RuntimeError):
pass
def fetch_current_routes(slug: str) -> str:
container = sidecar_bundle_container_name(slug)
r = subprocess.run(
@@ -30,31 +33,17 @@ def fetch_current_routes(slug: str) -> str:
return r.stdout
class DockerEgressApplicator(EgressApplicator):
def _signal_bundle_reload(self, slug: str) -> None:
container = sidecar_bundle_container_name(slug)
result = subprocess.run(
["docker", "kill", "--signal", "HUP", container],
capture_output=True, text=True, check=False, env=os.environ,
)
if result.returncode != 0:
last_error = (result.stderr or "").strip() or (result.stdout or "").strip()
warn(
f"egress: routes updated on disk for {slug}, but bundle reload failed: "
f"{last_error or 'docker kill failed'}"
)
raise EgressApplyError(
f"could not reload egress bundle {container}: "
f"{last_error or 'docker kill failed'}"
)
applicator = DockerEgressApplicator()
def validate_routes_content(content: str) -> None:
try:
load_routes(content)
except ValueError as e:
raise EgressApplyError(
f"proposed routes.yaml is not valid: {e}"
) from e
__all__ = [
"DockerEgressApplicator",
"EgressApplyError",
"applicator",
"fetch_current_routes",
"validate_routes_content",
]
+3 -2
View File
@@ -1,6 +1,7 @@
"""Active-agent enumeration for the docker backend.
Returns `ActiveAgent` records the CLI `list active` command and the
Mirrors `backend/smolmachines/enumerate.py`: returns
`ActiveAgent` records the CLI `list active` command and the
dashboard agents pane consume. Empty when docker isn't reachable
— gated by `has_backend('docker')` at the cross-backend caller
so this module trusts that docker is available when called.
@@ -14,7 +15,7 @@ from __future__ import annotations
import subprocess
from .. import ActiveAgent
from ...bottle_state import read_metadata
from .bottle_state import read_metadata
from .compose import compose_project_name, list_active_slugs
-23
View File
@@ -1,23 +0,0 @@
"""DockerFreezer — snapshot a Docker bottle via `docker commit`."""
from __future__ import annotations
from .. import ActiveAgent
from ..freeze import Freezer
from .util import commit_container
from ...log import info
class DockerFreezer(Freezer):
"""Freezes a Docker bottle by running `docker commit`."""
backend_name = "docker"
def _freeze(self, agent: ActiveAgent) -> str:
container = f"bot-bottle-{agent.slug}"
image_tag = f"bot-bottle-committed-{agent.slug}:latest"
commit_container(container, image_tag)
return image_tag
def _export_hint(self, slug: str, image_ref: str) -> None:
info(f"to export for migration: docker save {image_ref} -o {slug}.tar")
-47
View File
@@ -1,47 +0,0 @@
"""Shared-gateway source-IP allocation for the consolidated docker backend
(PRD 0070).
In the consolidated model one gateway container serves every bottle over a
single shared docker network, and each agent bottle attaches with a pinned,
deterministic address that the gateway uses as its **attribution key**. This
allocates those addresses from the network's subnet, skipping the reserved
ones — the network address and broadcast (excluded by `hosts()`), docker's
router `.1`, and everything already in use (`taken`: the gateway container
plus every live bottle, which the caller reads from the registry).
Pure `ipaddress` logic — the docker-specific bits (the subnet CIDR, the
gateway container's own address) are gathered by the caller and passed in, so
this stays testable without docker.
"""
from __future__ import annotations
import ipaddress
from collections.abc import Iterable
class NoFreeAddressError(RuntimeError):
"""The shared gateway network's subnet is exhausted — every host address
is reserved or already assigned to a bottle."""
def next_free_ip(cidr: str, taken: Iterable[str]) -> str:
"""The lowest host address in `cidr` not in `taken` and not docker's
router (`.1`). `taken` must include the gateway container's own address
and every live bottle's. Raises `NoFreeAddressError` if the subnet is
full."""
net = ipaddress.ip_network(cidr, strict=False)
reserved = {str(a) for a in taken}
# Docker assigns the network's first host (.1) to the bridge router; a
# bottle must never be handed that address.
reserved.add(str(net.network_address + 1))
for host in net.hosts(): # hosts() already excludes network + broadcast
candidate = str(host)
if candidate not in reserved:
return candidate
raise NoFreeAddressError(
f"no free address in {cidr} ({len(reserved)} reserved/assigned)"
)
__all__ = ["next_free_ip", "NoFreeAddressError"]
@@ -1,94 +0,0 @@
"""Provision one bottle's git-gate state into the running shared gateway
(PRD 0070, docker slice).
The consolidated gateway serves every bottle's repos under `/git/<bottle_id>/`
with per-repo credentials under `/git-gate/creds/<bottle_id>/`. When a bottle
is registered the launcher must place *its* deploy keys + known_hosts into
that per-bottle creds dir and init its bare repos there — so this copies the
credential files into the live gateway container and runs the (namespaced,
init-only) provisioning script produced by `git_gate_render_provision`.
Isolating each bottle's creds dir + repo root by id is what keeps one
bottle's push credentials out of another's repos on the shared gateway.
"""
from __future__ import annotations
import re
from ...docker_cmd import run_docker
from ...git_gate import GitGatePlan, git_gate_render_provision
# bottle ids index the gateway's per-bottle repo + creds dirs; they land in
# `docker cp`/`rm` path arguments, so validate before any path is built (a
# traversal id like "../etc" must never reach the container). Registry ids are
# token_hex — this is defense in depth at the docker boundary.
_SAFE_BOTTLE_ID = re.compile(r"[A-Za-z0-9_-]+")
class GatewayProvisionError(RuntimeError):
"""A git-gate provisioning step against the running gateway failed."""
def _require_safe(bottle_id: str) -> None:
if not _SAFE_BOTTLE_ID.fullmatch(bottle_id):
raise GatewayProvisionError(f"unsafe bottle id {bottle_id!r}")
def _creds_dir(bottle_id: str) -> str:
return f"/git-gate/creds/{bottle_id}"
def _exec(gateway: str, argv: list[str]) -> None:
"""`docker exec` a command in the gateway, raising on non-zero exit."""
proc = run_docker(["docker", "exec", gateway, *argv])
if proc.returncode != 0:
raise GatewayProvisionError(
f"gateway exec {argv!r} failed: {proc.stderr.strip()}"
)
def _cp_into(gateway: str, src: str, dest: str) -> None:
"""`docker cp` a host file into the gateway, raising on non-zero exit."""
proc = run_docker(["docker", "cp", src, f"{gateway}:{dest}"])
if proc.returncode != 0:
raise GatewayProvisionError(
f"gateway cp {src} -> {dest} failed: {proc.stderr.strip()}"
)
def provision_git_gate(gateway: str, bottle_id: str, plan: GitGatePlan) -> None:
"""Place `bottle_id`'s git-gate credentials into the running `gateway`
container and init its bare repos under `/git/<bottle_id>/`.
Copies each upstream's identity key (and known_hosts, when present) into
`/git-gate/creds/<bottle_id>/`, then runs the namespaced provisioning
script. No-op for a bottle with no git upstreams."""
_require_safe(bottle_id)
if not plan.upstreams:
return
creds = _creds_dir(bottle_id)
_exec(gateway, ["mkdir", "-p", creds])
for u in plan.upstreams:
if u.identity_file:
_cp_into(gateway, u.identity_file, f"{creds}/{u.name}-key")
known_hosts = str(u.known_hosts_file)
if known_hosts and known_hosts != ".":
_cp_into(gateway, known_hosts, f"{creds}/{u.name}-known_hosts")
# Init the bare repos + per-repo credential config for this namespace.
script = git_gate_render_provision(bottle_id, plan.upstreams)
_exec(gateway, ["sh", "-c", script])
def deprovision_git_gate(gateway: str, bottle_id: str) -> None:
"""Remove a bottle's repos + creds from the gateway on teardown. Idempotent
— an already-absent namespace is a clean no-op (best effort; a stray dir
can't leak, since attribution is by source IP and the bottle is gone)."""
_require_safe(bottle_id)
run_docker([
"docker", "exec", gateway, "rm", "-rf",
f"/git/{bottle_id}", _creds_dir(bottle_id),
])
__all__ = ["provision_git_gate", "deprovision_git_gate", "GatewayProvisionError"]
+16 -35
View File
@@ -4,8 +4,8 @@ PRD 0018 chunk 3: each instance is one `docker compose` project.
The flow is:
1. Build the agent image from the provider Dockerfile (compose
builds the sidecar images via the `build:` directive on first up).
1. Build the agent's base + derived image (compose builds the
sidecar images via the `build:` directive on first up).
2. Mint the per-bottle egress CA (chunk 2 writes it under
state/<slug>/egress/).
3. Populate the inner plans with launch-time fields so the
@@ -15,8 +15,8 @@ The flow is:
7. `docker compose up -d` (token + OAuth values flow into the
compose subprocess env so `environment: [NAME]` bare-name
entries inherit without rendering values into the file).
8. Provision (CA install, prompt copy, skills, workspace, git,
supervise config) — unchanged, uses `docker exec` / `docker cp`.
8. Provision (CA install, prompt copy, skills, git, supervise
config) — unchanged, uses `docker exec`.
9. Yield a DockerBottle handle. `exec_agent` runs claude via
`docker exec -it` exactly like the pre-compose world.
@@ -37,20 +37,16 @@ from pathlib import Path
from typing import Callable, Generator
from ...egress import egress_resolve_token_values
from ...git_gate import (
provision_git_gate_dynamic_keys,
revoke_git_gate_provisioned_keys,
)
from ...git_gate import revoke_git_gate_provisioned_keys
from ...log import info, warn
from . import network as network_mod
from . import util as docker_mod
from .bottle import DockerBottle
from .bottle_plan import DockerBottlePlan
from ...bottle_state import (
from .bottle_state import (
bottle_state_dir,
egress_state_dir,
git_gate_state_dir,
read_committed_image,
)
from .compose import (
bottle_plan_to_compose,
@@ -79,7 +75,7 @@ def launch(
Teardown on exit."""
stack = ExitStack()
_bottle_for_revoke = plan.manifest.bottle
_bottle_for_revoke = plan.spec.manifest.bottle_for(plan.spec.agent_name)
_git_gate_dir_for_revoke = git_gate_state_dir(plan.slug)
def teardown() -> None:
@@ -95,21 +91,15 @@ def launch(
)
try:
# Step 1: agent image. Use a committed snapshot when one exists
# and is present in the local daemon; otherwise build from the
# Dockerfile. Sidecar images get built lazily by `docker compose
# up` via the renderer's `build:` directives.
committed = read_committed_image(plan.slug)
if committed and docker_mod.image_exists(committed):
info(f"using committed image {committed!r}")
plan = dataclasses.replace(
plan,
agent_provision=dataclasses.replace(plan.agent_provision, image=committed),
)
else:
docker_mod.build_image(
plan.image, _REPO_DIR,
dockerfile=plan.dockerfile_path,
# Step 1: agent image build. Sidecar images get built lazily by
# `docker compose up` via the renderer's `build:` directives.
docker_mod.build_image(
plan.image, _REPO_DIR,
dockerfile=plan.dockerfile_path,
)
if plan.derived_image:
docker_mod.build_image_with_cwd(
plan.derived_image, plan.image, plan.workspace_plan
)
internal_network = network_mod.network_name_for_slug(plan.slug)
@@ -121,11 +111,6 @@ def launch(
git_gate_plan = plan.git_gate_plan
if git_gate_plan.upstreams:
git_gate_plan = provision_git_gate_dynamic_keys(
plan.manifest.bottle,
git_gate_plan,
git_gate_state_dir(plan.slug),
)
git_gate_plan = dataclasses.replace(
git_gate_plan,
internal_network=internal_network,
@@ -194,10 +179,6 @@ def launch(
None,
agent_command=plan.agent_command,
agent_prompt_mode=plan.agent_prompt_mode,
agent_provider_template=plan.agent_provider_template,
terminal_title=f"{plan.spec.label} ({plan.spec.agent_name})" if plan.spec.label else plan.spec.agent_name,
terminal_color=plan.spec.color,
agent_workdir=plan.workspace_plan.workdir,
)
bottle.prompt_path = provision(plan, bottle)
+280
View File
@@ -0,0 +1,280 @@
"""Prepare step for the Docker bottle backend.
`resolve_plan` does all host-side resolution (image and container
names, env-file, prompt-file, proxy plan, runtime detection) and
returns a frozen DockerBottlePlan. No Docker resources are created;
the only side effects are scratch files under `stage_dir` and a probe
of `docker info`. Cross-backend host-side validation has already run
via the base class's `prepare` template before this is called.
"""
from __future__ import annotations
import os
from datetime import datetime, timezone
from dataclasses import replace
from pathlib import Path
from ...agent_provider import PROVIDER_TEMPLATES, agent_provision_plan, runtime_for
from ...egress import Egress
from ...env import ResolvedEnv, resolve_env
from ...git_gate import GitGate
from ...log import die
from ...supervise import Supervise
from ...workspace import workspace_plan as resolve_workspace_plan
from .. import BottleSpec
from . import util as docker_mod
from .bottle_plan import DockerBottlePlan
from .bottle_state import (
BottleMetadata,
agent_state_dir,
bottle_identity,
clear_preserve_marker,
egress_state_dir,
git_gate_state_dir,
per_bottle_dockerfile,
per_bottle_dockerfile_path,
per_bottle_image_tag,
supervise_state_dir,
write_metadata,
)
from .sidecar_bundle import sidecar_bundle_container_name
def resolve_plan(
spec: BottleSpec,
*,
stage_dir: Path,
) -> DockerBottlePlan:
"""Resolve Docker-specific names and write scratch files. Trusts
that the agent and its skills/git-gate keys are present —
validation already ran in the base class."""
docker_mod.require_docker()
git_gate = GitGate()
egress = Egress()
supervise = Supervise()
manifest = spec.manifest
agent = manifest.agents[spec.agent_name]
bottle = manifest.bottle_for(spec.agent_name)
provider = bottle.agent_provider
provider_runtime = runtime_for(provider.template)
guest_home = "/home/node"
workspace_plan = resolve_workspace_plan(spec, guest_home=guest_home)
# PRD 0016 follow-up: identity, not bare slug. A fresh `start`
# mints a random-suffixed identity (so parallel runs of the same
# agent in the same cwd don't collide on container/network
# names); a `resume` passes the recorded identity in via
# spec.identity to continue an existing bottle's state.
slug = spec.identity or bottle_identity(spec.agent_name)
# Record the launch metadata so `cli.py resume <identity>` can
# reconstruct the spec. Idempotent — re-writes on resume with a
# refreshed started_at.
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(),
compose_project=f"bot-bottle-{slug}",
backend="docker",
label=spec.label,
color=spec.color,
))
# Clear any leftover preserve marker from a prior capability-block
# so this fresh launch can be cleaned up at session-end unless
# the agent triggers another capability-block.
clear_preserve_marker(slug)
# PRD 0016 capability-block: if a per-bottle Dockerfile has been
# written (via apply_capability_change), the base image becomes
# per_bottle_image_tag(slug) built from that file. --cwd still
# layers a derived image on top.
dockerfile_path = ""
if per_bottle_dockerfile(slug) is not None:
image_default = per_bottle_image_tag(slug)
dockerfile_path = str(per_bottle_dockerfile_path(slug))
elif provider.dockerfile:
image_default = f"bot-bottle-{provider.template}:{slug}"
dockerfile_path = _resolve_manifest_dockerfile(provider.dockerfile, spec)
elif provider_runtime.dockerfile:
image_default = provider_runtime.image
dockerfile_path = provider_runtime.dockerfile
elif provider.template not in PROVIDER_TEMPLATES:
user_dockerfile = (
Path.home() / ".bot-bottle" / "contrib" / provider.template / "Dockerfile"
)
if user_dockerfile.is_file():
image_default = f"bot-bottle-{provider.template}:{slug}"
dockerfile_path = str(user_dockerfile)
else:
image_default = provider_runtime.image
else:
image_default = provider_runtime.image
image = os.environ.get("BOT_BOTTLE_IMAGE", image_default)
derived_image = ""
runtime_image = image
if spec.copy_cwd:
derived_image = os.environ.get(
"BOT_BOTTLE_DERIVED_IMAGE", f"bot-bottle-cwd:{slug}"
)
runtime_image = derived_image
default_container = f"bot-bottle-{slug}"
pinned_container = os.environ.get("BOT_BOTTLE_CONTAINER", "")
container_name_pinned = bool(pinned_container)
if container_name_pinned:
container_name = pinned_container
if docker_mod.container_exists(container_name):
die(
f"container '{container_name}' already exists "
f"(pinned via BOT_BOTTLE_CONTAINER). "
f"Remove it with 'docker rm -f {container_name}' or unset the override."
)
else:
container_name = ""
for candidate in docker_mod.container_name_candidates(default_container):
if not docker_mod.container_exists(candidate):
container_name = candidate
break
if not container_name:
die(
f"could not find a free container name after "
f"{default_container}-{docker_mod.MAX_CONTAINER_SUFFIX}; "
f"clean up old containers with 'docker rm -f <name>'"
)
# Probe the sidecar-bundle container name for an orphan from a
# previous run. Otherwise a stale bundle surfaces as a
# docker-create conflict deep inside launch() with no actionable
# hint; failing fast here points at the cleanup command.
bundle_name = sidecar_bundle_container_name(slug)
if docker_mod.container_exists(bundle_name):
die(
f"sidecar bundle container '{bundle_name}' already exists. "
f"This is an orphan from a previous run; clean it up with "
f"'./cli.py cleanup' (or 'docker rm -f {bundle_name}') and "
f"retry."
)
# PRD 0018 chunk 2: prepare-time scratch files live under
# ~/.bot-bottle/state/<slug>/<service>/ so chunk 3's compose
# bind-mounts can point at stable paths. The state subdirs are
# cleaned up by start.py's session-end teardown unless something
# explicitly preserves the state dir (capability-block, crash).
agent_dir = agent_state_dir(slug)
agent_dir.mkdir(parents=True, exist_ok=True)
env_file = agent_dir / "agent.env"
prompt_file = agent_dir / "prompt.txt"
prompt_file.write_text("")
prompt_file.chmod(0o600)
git_gate_dir = git_gate_state_dir(slug)
git_gate_dir.mkdir(parents=True, exist_ok=True)
git_gate_plan = git_gate.prepare(bottle, slug, git_gate_dir)
resolved = resolve_env(manifest, spec.agent_name)
# Everything that should reach the bottle by-name (so its value
# never lands on argv or in env_file) goes into one dict. Nothing
# mutates the host os.environ.
forwarded_env: dict[str, str] = dict(resolved.forwarded)
_write_env_file(resolved, env_file)
prompt_file.write_text(agent.prompt)
use_runsc = docker_mod.runsc_available()
agent_provision = agent_provision_plan(
template=provider.template,
dockerfile=dockerfile_path,
state_dir=agent_dir,
guest_home=guest_home,
forward_host_credentials=provider.forward_host_credentials,
auth_token=provider.auth_token,
host_env=dict(os.environ),
trusted_project_path=workspace_plan.workdir,
label=spec.label,
color=spec.color,
)
guest_env = dict(agent_provision.guest_env)
for key, val in agent_provision.env_vars.items():
guest_env.setdefault(key, val)
agent_provision = replace(agent_provision, guest_env=guest_env)
egress_dir = egress_state_dir(slug)
egress_dir.mkdir(parents=True, exist_ok=True)
egress_plan = egress.prepare(
bottle, slug, egress_dir, agent_provision.egress_routes,
)
supervise_plan = None
if bottle.supervise:
# Current Dockerfile for the agent image. Read from the repo
# root; for `--cwd` derived images the base Dockerfile is what
# the agent should propose changes against (the derived layer
# is just a workspace copy).
# (routes.yaml used to land here too but PRD 0017 chunk 3
# moved it behind the `list-egress-routes` MCP tool so the
# agent gets live state rather than a launch-time snapshot.)
supervise_dockerfile_path = (
Path(dockerfile_path)
if dockerfile_path
else Path(__file__).resolve().parent.parent.parent.parent / "Dockerfile.claude"
)
dockerfile_content = (
supervise_dockerfile_path.read_text(encoding="utf-8")
if supervise_dockerfile_path.is_file()
else ""
)
supervise_dir = supervise_state_dir(slug)
supervise_dir.mkdir(parents=True, exist_ok=True)
supervise_plan = supervise.prepare(
slug, supervise_dir,
dockerfile_content=dockerfile_content,
)
return DockerBottlePlan(
spec=spec,
stage_dir=stage_dir,
guest_home=guest_home,
slug=slug,
container_name=container_name,
container_name_pinned=container_name_pinned,
image=image,
derived_image=derived_image,
runtime_image=runtime_image,
dockerfile_path=dockerfile_path,
env_file=env_file,
forwarded_env=forwarded_env,
prompt_file=prompt_file,
git_gate_plan=git_gate_plan,
egress_plan=egress_plan,
supervise_plan=supervise_plan,
use_runsc=use_runsc,
agent_provision=agent_provision,
workspace_plan=workspace_plan,
)
def _write_env_file(resolved: ResolvedEnv, env_file: Path) -> None:
"""Serialize the literal portion of a ResolvedEnv into docker's
`--env-file` syntax (NAME=VALUE per line, mode 600 since the file
may carry verbatim values from the manifest). Forwarded names ride
on the plan as a structured tuple instead."""
env_lines: list[str] = []
for name, value in resolved.literals.items():
if "\n" in value:
die(
f"env entry {name} (literal) contains a newline; "
f"docker --env-file cannot represent multi-line values."
)
env_lines.append(f"{name}={value}")
env_file.write_text("\n".join(env_lines) + ("\n" if env_lines else ""))
env_file.chmod(0o600)
def _resolve_manifest_dockerfile(path_value: str, spec: BottleSpec) -> str:
path = Path(os.path.expanduser(path_value))
if not path.is_absolute():
path = Path(spec.user_cwd) / path
return str(path)
-62
View File
@@ -1,62 +0,0 @@
"""Prepare step for the Docker bottle backend.
`resolve_plan` does all host-side resolution (image and container
names, prompt-file, proxy plan, runtime detection) and returns a
frozen DockerBottlePlan. No Docker resources are created; the only
side effects are scratch files under `stage_dir` and a probe of
`docker info`. Cross-backend host-side validation has already run
via the base class's `prepare` template before this is called.
"""
from __future__ import annotations
from pathlib import Path
from . import util as docker_mod
from .bottle_plan import DockerBottlePlan
from .. import BottleSpec
from ...env import ResolvedEnv
from ...agent_provider import AgentProvisionPlan
from ...egress import EgressPlan
from ...manifest import Manifest
from ...supervise import SupervisePlan
from ...git_gate import GitGatePlan
def preflight() -> None:
docker_mod.require_docker()
def build_guest_env(resolved_env: ResolvedEnv) -> dict[str, str]:
return dict(resolved_env.literals)
def resolve_plan(
spec: BottleSpec,
manifest: Manifest,
slug: str,
resolved_env: ResolvedEnv,
agent_provision_plan: AgentProvisionPlan,
egress_plan: EgressPlan,
supervise_plan: SupervisePlan | None,
git_gate_plan: GitGatePlan,
stage_dir: Path,
) -> DockerBottlePlan:
"""Resolve Docker-specific names and write scratch files. Trusts
that the agent and its skills/git-gate keys are present —
validation already ran in the base class."""
# ==== docker specific setup ====
use_runsc = docker_mod.runsc_available()
return DockerBottlePlan(
spec=spec,
manifest=manifest,
stage_dir=stage_dir,
slug=slug,
forwarded_env=dict(resolved_env.forwarded),
git_gate_plan=git_gate_plan,
egress_plan=egress_plan,
supervise_plan=supervise_plan,
use_runsc=use_runsc,
agent_provision=agent_provision_plan,
)
-89
View File
@@ -1,89 +0,0 @@
"""Host setup + status for the Docker backend.
Unlike Firecracker, the Docker backend needs no privileged one-time
host provisioning (no TAP pool / nft table) — networks and the sidecar
bundle are created per-launch. So `setup()` is mostly an install/daemon
pointer, and `status()` reports whether docker is usable.
This is intentionally minimal; a richer version (daemon config checks,
gVisor/runsc install guidance, rootless-docker hints) is tracked
separately. Reached via `DockerBottleBackend.setup` / `.status`, which
the generic `./cli.py backend {setup,status}` dispatches to.
"""
from __future__ import annotations
import shutil
import subprocess
import sys
from . import util as _util
def _docker_on_path() -> bool:
return shutil.which("docker") is not None
def _daemon_reachable() -> bool:
if not _docker_on_path():
return False
return subprocess.run(
["docker", "info"],
stdout=subprocess.DEVNULL, stderr=subprocess.DEVNULL, check=False,
).returncode == 0
def _print_install_pointer() -> None:
sys.stderr.write("Docker is required but was not found on PATH.\n")
sys.stderr.write(" macOS: Docker Desktop https://docs.docker.com/desktop/install/mac-install/\n")
sys.stderr.write(" Linux: Docker Engine https://docs.docker.com/engine/install/\n")
def setup() -> int:
if not _docker_on_path():
_print_install_pointer()
return 1
sys.stderr.write(
"Docker backend: no privileged host setup required — networks and "
"the sidecar bundle are created per-launch.\n"
)
if not _daemon_reachable():
sys.stderr.write(
"The Docker daemon isn't reachable; start it (e.g. Docker "
"Desktop, or `systemctl start docker`).\n"
)
return 1
if not _util.runsc_available():
sys.stderr.write(
"Optional: register the gVisor (`runsc`) runtime with Docker for "
"a userspace syscall barrier; bottles auto-detect and use it.\n"
)
return 0
def teardown() -> int:
sys.stderr.write(
"Docker backend: nothing to undo — it provisions no privileged host "
"state (networks and the sidecar bundle are per-launch and are "
"removed by `./cli.py cleanup`). Docker itself is left installed.\n"
)
return 0
def status() -> int:
ok = True
if _docker_on_path():
sys.stderr.write("docker on PATH: yes\n")
else:
sys.stderr.write("docker on PATH: NO\n")
ok = False
if ok and _daemon_reachable():
sys.stderr.write("docker daemon: reachable\n")
elif ok:
sys.stderr.write("docker daemon: UNREACHABLE\n")
ok = False
runsc = _docker_on_path() and _util.runsc_available()
sys.stderr.write(f"gVisor runsc runtime: {'registered' if runsc else 'not registered (optional)'}\n")
if not ok:
sys.stderr.write("\nRun: ./cli.py backend setup --backend=docker\n")
return 0 if ok else 1
+63 -47
View File
@@ -7,10 +7,11 @@ from __future__ import annotations
import re
import shutil
import subprocess
import tempfile
from typing import Iterable, Iterator
from ...log import die, info
# from ...workspace import WorkspacePlan
from ...workspace import WorkspacePlan
# Cap on the suffix the container-name conflict logic will try before
@@ -117,54 +118,69 @@ def build_image(ref: str, context: str, *, dockerfile: str = "") -> None:
subprocess.run(args, check=True)
# def build_image_with_cwd(
# derived: str,
# base: str,
# workspace: "WorkspacePlan",
# ) -> None:
# """Build a thin derived image that copies the workspace into
# the plan's guest path and sets the plan's workdir."""
# import os
#
# cwd = str(workspace.host_path)
# if not os.path.isdir(cwd):
# die(f"cwd not found at {cwd}")
# info(f"building image {derived} from {base} with {cwd} -> {workspace.guest_path}")
# with tempfile.TemporaryDirectory(prefix="bot-bottle-cwd.") as tmp:
# context_dir = os.path.join(tmp, "context")
# staged_workspace = os.path.join(context_dir, "workspace")
# shutil.copytree(
# cwd,
# staged_workspace,
# symlinks=True,
# ignore=shutil.ignore_patterns(".git"),
# )
# dockerfile = (
# f"FROM {base}\n"
# f"COPY --chown=node:node workspace/. {workspace.guest_path}\n"
# f"WORKDIR {workspace.workdir}\n"
# )
# subprocess.run(
# ["docker", "build", "-t", derived, "-f", "-", context_dir],
# input=dockerfile,
# text=True,
# check=True,
# )
def build_image_with_cwd(
derived: str,
base: str,
workspace: WorkspacePlan,
) -> None:
"""Build a thin derived image that copies the workspace into
the plan's guest path and sets the plan's workdir."""
import os
def commit_container(container_name: str, image_tag: str) -> None:
"""Run `docker commit <container_name> <image_tag>` to snapshot the
running container's filesystem state as a local Docker image."""
result = subprocess.run(
["docker", "commit", container_name, image_tag],
capture_output=True, text=True, check=False,
)
if result.returncode != 0:
die(
f"docker commit {container_name!r}{image_tag!r} failed: "
f"{(result.stderr or '').strip() or '<no stderr>'}"
cwd = str(workspace.host_path)
if not os.path.isdir(cwd):
die(f"cwd not found at {cwd}")
info(f"building image {derived} from {base} with {cwd} -> {workspace.guest_path}")
with tempfile.TemporaryDirectory(prefix="bot-bottle-cwd.") as tmp:
context_dir = os.path.join(tmp, "context")
staged_workspace = os.path.join(context_dir, "workspace")
shutil.copytree(
cwd,
staged_workspace,
symlinks=True,
ignore=shutil.ignore_patterns(".git"),
)
info(f"committed {container_name!r}{image_tag!r}")
dockerfile = (
f"FROM {base}\n"
f"COPY --chown=node:node workspace/. {workspace.guest_path}\n"
f"WORKDIR {workspace.workdir}\n"
)
subprocess.run(
["docker", "build", "-t", derived, "-f", "-", context_dir],
input=dockerfile,
text=True,
check=True,
)
def image_id(ref: str) -> str:
"""Return the content-addressed image ID (e.g.
`sha256:abcd...`) for `ref`. The smolmachines backend keys its
`.smolmachine` artifact cache on this, so a Dockerfile change
that produces a new image automatically invalidates the cache."""
r = subprocess.run(
["docker", "image", "inspect", "--format", "{{.Id}}", ref],
capture_output=True,
text=True,
check=False,
)
if r.returncode != 0:
die(
f"docker image inspect for {ref!r} failed: "
f"{(r.stderr or '').strip() or '<no stderr>'}"
)
return r.stdout.strip()
def save(ref: str, output: str) -> None:
"""`docker save REF -o OUTPUT`. Writes a tarball of the image
layers + manifest to the host path. Used by smolmachines
prepare to hand the agent image to a containerized crane that
pushes it to the ephemeral registry — bypassing the docker
daemon's `docker push` (which on Docker Desktop can't reach a
host-loopback registry and refuses plain-HTTP pushes to
non-loopback hosts)."""
subprocess.run(["docker", "save", ref, "-o", output], check=True)
def _silent_run(cmd: Iterable[str]) -> int:
-54
View File
@@ -1,54 +0,0 @@
"""Shared base class for host-side egress apply across backends.
Each backend subclasses EgressApplicator and overrides _signal_bundle_reload
with the backend-specific kill command.
"""
from __future__ import annotations
from abc import ABC, abstractmethod
from pathlib import Path
from ..bottle_state import egress_state_dir
from ..egress import EGRESS_ROUTES_FILENAME
from ..egress_addon_core import LOG_OFF, load_config
class EgressApplyError(RuntimeError):
pass
class EgressApplicator(ABC):
def apply_routes_change(self, slug: str, content: str) -> tuple[str, str]:
"""Persist `content` to the live routes file and reload egress."""
self.validate_routes_content(content)
routes_path = self._routes_path(slug)
routes_path.parent.mkdir(parents=True, exist_ok=True)
before = routes_path.read_text(encoding="utf-8") if routes_path.exists() else ""
routes_path.write_text(content, encoding="utf-8")
routes_path.chmod(0o600)
self._signal_bundle_reload(slug)
return before, content
@staticmethod
def validate_routes_content(content: str) -> None:
try:
config = load_config(content)
except ValueError as e:
raise EgressApplyError(
f"proposed routes.yaml is not valid: {e}"
) from e
if config.log != LOG_OFF:
raise EgressApplyError(
"proposed routes.yaml must not change egress logging"
)
@staticmethod
def _routes_path(slug: str) -> Path:
return egress_state_dir(slug) / EGRESS_ROUTES_FILENAME
@abstractmethod
def _signal_bundle_reload(self, slug: str) -> None: ...
__all__ = ["EgressApplicator", "EgressApplyError"]
@@ -1,7 +0,0 @@
"""Firecracker backend: Linux KVM microVM isolation (issue #342)."""
from __future__ import annotations
from .backend import FirecrackerBottleBackend
__all__ = ["FirecrackerBottleBackend"]
-112
View File
@@ -1,112 +0,0 @@
"""FirecrackerBottleBackend — Linux microVM implementation.
Replaces smolmachines on Linux (issue #342): mature KVM-based
isolation via Firecracker, SSH control over a point-to-point TAP, and a
fail-closed nftables egress boundary. Selected by
`BOT_BOTTLE_BACKEND=firecracker` or `--backend=firecracker`.
"""
from __future__ import annotations
from contextlib import contextmanager
from pathlib import Path
from typing import Generator, Sequence
from ...agent_provider import AgentProvisionPlan
from ...egress import EgressPlan
from ...env import ResolvedEnv
from ...git_gate import GitGatePlan
from ...manifest import Manifest
from ...supervise import SupervisePlan
from .. import ActiveAgent, BottleBackend, BottleSpec
from . import cleanup as _cleanup
from . import enumerate as _enumerate
from . import launch as _launch
from . import resolve_plan as _resolve_plan
from . import util as _util
from .bottle import FirecrackerBottle
from .bottle_cleanup_plan import FirecrackerBottleCleanupPlan
from .bottle_plan import FirecrackerBottlePlan
class FirecrackerBottleBackend(
BottleBackend["FirecrackerBottlePlan", "FirecrackerBottleCleanupPlan"]
):
name = "firecracker"
@classmethod
def is_available(cls) -> bool:
return _util.is_available()
@classmethod
def is_host_capable(cls) -> bool:
"""Linux + KVM, regardless of whether the `firecracker` binary
is installed. Drives default-backend selection so a capable host
without the binary still lands on firecracker and gets an
install pointer at launch."""
return _util.is_host_capable()
@classmethod
def setup(cls) -> int:
from . import setup as _setup
return _setup.setup()
@classmethod
def status(cls) -> int:
from . import setup as _setup
return _setup.status()
@classmethod
def teardown(cls) -> int:
from . import setup as _setup
return _setup.teardown()
def _preflight(self) -> None:
_resolve_plan.preflight()
def _build_guest_env(self, resolved_env: ResolvedEnv) -> dict[str, str]:
return _resolve_plan.build_guest_env(resolved_env)
def _resolve_plan(
self,
spec: BottleSpec,
*,
manifest: Manifest,
slug: str,
resolved_env: ResolvedEnv,
agent_provision_plan: AgentProvisionPlan,
egress_plan: EgressPlan,
git_gate_plan: GitGatePlan,
supervise_plan: SupervisePlan | None,
stage_dir: Path,
) -> FirecrackerBottlePlan:
return _resolve_plan.resolve_plan(
spec,
manifest=manifest,
slug=slug,
resolved_env=resolved_env,
agent_provision_plan=agent_provision_plan,
egress_plan=egress_plan,
supervise_plan=supervise_plan,
git_gate_plan=git_gate_plan,
stage_dir=stage_dir,
)
@contextmanager
def launch(
self, plan: FirecrackerBottlePlan
) -> Generator[FirecrackerBottle, None, None]:
with _launch.launch(plan, provision=self.provision) as bottle:
yield bottle
def prepare_cleanup(self) -> FirecrackerBottleCleanupPlan:
return _cleanup.prepare_cleanup()
def cleanup(self, plan: FirecrackerBottleCleanupPlan) -> None:
_cleanup.cleanup(plan)
def enumerate_active(self) -> Sequence[ActiveAgent]:
return _enumerate.enumerate_active()
def supervise_mcp_url(self, plan: FirecrackerBottlePlan) -> str:
return plan.agent_supervise_url
-189
View File
@@ -1,189 +0,0 @@
"""Bottle handle for a Firecracker microVM, over SSH.
Every operation routes through SSH to the guest (dropbear, listening on
the TAP link). `exec` pipes a script over stdin and captures output;
`cp_in` uses scp; `exec_agent` uses `ssh -t` for an interactive PTY
session. `ssh -t` forwards the host terminal's SIGWINCH to the remote
PTY natively, so no separate resize bridge is needed.
Commands run as the image's `node` user via `runuser`, with HOME/USER/
PATH and the bottle env (HTTPS_PROXY at the sidecar, CA paths, …) set
per-invocation through `env` (the VM itself just runs the init; it has
no baked-in process env like a `docker run` container would).
"""
from __future__ import annotations
import os
import shlex
import subprocess
import sys
from pathlib import Path
from typing import Mapping, cast
from ...agent_provider import PromptMode, prompt_args
from .. import Bottle, ExecResult
from ..terminal import exec_shell_script
from . import util
_HOME_FOR = {"node": "/home/node", "root": "/root"}
_DEFAULT_PATH_FOR = {
"node": (
"/home/node/.local/bin:"
"/home/node/.codex/packages/standalone/current/bin:"
"/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin"
),
"root": "/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin",
}
def _env_assignments_for(user: str, env: Mapping[str, str]) -> list[str]:
home = _HOME_FOR.get(user, f"/home/{user}")
out = [f"HOME={home}", f"USER={user}"]
if "PATH" not in env:
out.append(f"PATH={_DEFAULT_PATH_FOR.get(user, _DEFAULT_PATH_FOR['root'])}")
for k, v in env.items():
out.append(f"{k}={v}")
return out
class FirecrackerBottle(Bottle):
def __init__(
self,
name: str,
*,
private_key: Path,
guest_ip: str,
guest_env: Mapping[str, str] | None = None,
prompt_path_in_guest: str | None = None,
agent_command: str = "claude",
agent_prompt_mode: PromptMode = "append_file",
agent_provider_template: str = "claude",
terminal_title: str = "",
terminal_color: str = "",
agent_workdir: str = "/home/node",
) -> None:
self.name = name
self._private_key = private_key
self._guest_ip = guest_ip
self._guest_env = dict(guest_env or {})
self.prompt_path = prompt_path_in_guest
self._agent_prompt_mode = agent_prompt_mode
self.agent_command = agent_command
self.terminal_title = terminal_title
self.terminal_color = terminal_color
self.agent_provider_template = agent_provider_template
self.agent_workdir = agent_workdir
def _ssh(self, *, tty: bool) -> list[str]:
argv = util.ssh_base_argv(self._private_key, self._guest_ip)
if tty:
# -t: allocate a remote PTY and forward window-size changes.
argv.insert(1, "-t")
return argv
def _agent_remote_argv(self, argv: list[str]) -> list[str]:
"""The `runuser … <agent> …` command run inside the guest."""
full_argv = list(argv)
full_argv.extend(
prompt_args(
cast(PromptMode, self._agent_prompt_mode),
self.prompt_path,
argv=full_argv,
)
)
# ALWAYS cd into the workdir before exec'ing the agent. The
# control SSH logs in as root, so the inherited cwd is /root —
# which the agent (running as node) can't even read now that
# /root is root-owned. Run the agent from the node workdir
# (default /home/node) so its cwd is node-accessible; otherwise
# Node's process.cwd(), the shell-snapshot machinery, and
# `/doctor` all fail on the unreadable /root.
# Run the agent from the node workdir (default /home/node), NOT
# the /root cwd inherited from the root SSH login — /root is now
# root-owned and unreadable by node, which breaks Node's
# process.cwd(), the shell-snapshot machinery, and `/doctor`.
# Use `env --chdir` rather than a `sh -c 'cd … && exec "$@"'`
# wrapper: ssh space-joins everything after the host into one
# string for the guest shell, so a quoted script + $@ would be
# re-split and mangled (exec'ing the $0 placeholder). All-simple
# words survive that join.
workdir = self.agent_workdir or _HOME_FOR["node"]
remote = ["runuser", "-u", "node", "--",
"env", f"--chdir={workdir}",
*_env_assignments_for("node", self._guest_env),
self.agent_command, *full_argv]
return remote
def agent_argv(self, argv: list[str], *, tty: bool = True) -> list[str]:
return [*self._ssh(tty=tty), "--", *self._agent_remote_argv(argv)]
def exec_agent(self, argv: list[str], *, tty: bool = True) -> int:
agent_argv = self.agent_argv(argv, tty=tty)
script = (
exec_shell_script(agent_argv, self.terminal_title, self.terminal_color)
if tty else None
)
if script is None:
return subprocess.run(agent_argv, check=False).returncode
return subprocess.run(["sh", "-lc", script], check=False).returncode
def exec(self, script: str, *, user: str = "node") -> ExecResult:
# Pipe the script over stdin (`sh -s`) so nothing needs shell
# quoting through the SSH command line.
remote = ["runuser", "-u", user, "--",
"env", *_env_assignments_for(user, self._guest_env),
"/bin/sh", "-s"]
result = subprocess.run(
[*self._ssh(tty=False), "--", *remote],
input=script, capture_output=True, text=True, check=False,
)
return ExecResult(
returncode=result.returncode,
stdout=result.stdout,
stderr=result.stderr,
)
def cp_in(self, host_path: str, container_path: str) -> None:
# Stream a tar over the SSH exec channel rather than scp: the
# guest runs dropbear, which ships no sftp-server/scp, but every
# agent image has `tar`. Copy so `container_path` becomes a copy
# of `host_path` (docker cp semantics — callers rm -rf the
# destination first).
host_parent = os.path.dirname(host_path.rstrip("/")) or "/"
host_base = os.path.basename(host_path.rstrip("/"))
guest_parent = os.path.dirname(container_path.rstrip("/")) or "/"
guest_base = os.path.basename(container_path.rstrip("/"))
remote = (
f"mkdir -p {shlex.quote(guest_parent)} && "
f"cd {shlex.quote(guest_parent)} && "
f"rm -rf {shlex.quote(guest_base)} && tar -xf - && "
f"{{ [ {shlex.quote(host_base)} = {shlex.quote(guest_base)} ] || "
f"mv {shlex.quote(host_base)} {shlex.quote(guest_base)}; }}"
)
tar = subprocess.Popen(
["tar", "-C", host_parent, "-cf", "-", host_base],
stdout=subprocess.PIPE,
)
# Pass the command as one arg: ssh space-joins everything after
# the host into a single string for the guest's login shell, so a
# `sh -c <remote>` split would drop everything past the first word
# (the guest shell runs `<remote>` directly; stdin carries the
# tar).
ssh = subprocess.run(
[*self._ssh(tty=False), "--", remote],
stdin=tar.stdout, capture_output=True, text=True, check=False,
)
tar.wait()
if tar.returncode != 0 or ssh.returncode != 0:
sys.stderr.write(ssh.stderr)
raise subprocess.CalledProcessError(
ssh.returncode or tar.returncode,
["cp_in", host_path, container_path],
)
def close(self) -> None:
# Real teardown (VM terminate, TAP release) lives on the launch
# ExitStack; this is the idempotent alias the ABC expects.
pass
@@ -1,32 +0,0 @@
"""Cleanup plan for the Firecracker backend."""
from __future__ import annotations
from dataclasses import dataclass
from ...log import info
from .. import BottleCleanupPlan
@dataclass(frozen=True)
class FirecrackerBottleCleanupPlan(BottleCleanupPlan):
# PIDs of orphaned firecracker VMM processes and the sidecar
# containers left behind by previous bottles.
vm_pids: tuple[int, ...] = ()
containers: tuple[str, ...] = ()
run_dirs: tuple[str, ...] = ()
def print(self) -> None:
if self.empty:
info("firecracker cleanup: nothing to remove")
return
for pid in self.vm_pids:
info(f"firecracker VM process: pid {pid}")
for name in self.containers:
info(f"firecracker sidecar container: {name}")
for path in self.run_dirs:
info(f"firecracker run dir: {path}")
@property
def empty(self) -> bool:
return not (self.vm_pids or self.containers or self.run_dirs)
@@ -1,63 +0,0 @@
"""Plan type for the Firecracker backend."""
from __future__ import annotations
from dataclasses import dataclass, field
from pathlib import Path
from ...agent_provider import PromptMode
from .. import BottlePlan
@dataclass(frozen=True)
class FirecrackerBottlePlan(BottlePlan):
slug: str
forwarded_env: dict[str, str] = field(repr=False)
# Stamped by launch once the sidecar is up and its ports are
# published on the host-side TAP IP (empty at prepare time).
agent_proxy_url: str = ""
agent_git_gate_url: str = ""
agent_supervise_url: str = ""
@property
def container_name(self) -> str:
"""Instance name, reused for the sidecar container + VM run dir.
Matches the `bot-bottle-<slug>` convention the other backends
use so cleanup/enumerate discovery-by-prefix keeps working."""
return self.agent_provision.instance_name
@property
def image(self) -> str:
return self.agent_provision.image
@property
def dockerfile_path(self) -> str:
return self.agent_provision.dockerfile
@property
def prompt_file(self) -> Path:
return self.agent_provision.prompt_file
@property
def agent_command(self) -> str:
return self.agent_provision.command
@property
def agent_prompt_mode(self) -> PromptMode:
return self.agent_provision.prompt_mode
@property
def agent_provider_template(self) -> str:
return self.agent_provision.template
@property
def git_gate_insteadof_host(self) -> str:
if self.agent_git_gate_url.startswith("http://"):
return self.agent_git_gate_url.removeprefix("http://").rstrip("/")
return super().git_gate_insteadof_host
@property
def git_gate_insteadof_scheme(self) -> str:
if self.agent_git_gate_url.startswith("http://"):
return "http"
return super().git_gate_insteadof_scheme
-90
View File
@@ -1,90 +0,0 @@
"""Cleanup for the Firecracker backend.
Orphans are: firecracker VMM processes whose config lives under our run
dir, the `bot-bottle-sidecars-*` containers, and the per-bottle run
dirs. TAP slots free themselves (the flock drops when the launcher
exits), so there is nothing to reclaim there.
"""
from __future__ import annotations
import os
import shutil
import signal
import subprocess
from pathlib import Path
from ...log import info
from . import util
from .bottle_cleanup_plan import FirecrackerBottleCleanupPlan
_SIDECAR_PREFIX = "bot-bottle-sidecars-"
def _run_root() -> Path:
return util.cache_dir() / "run"
def _orphan_vm_pids() -> list[int]:
"""firecracker processes whose --config-file is under our run dir."""
run_root = str(_run_root())
result = subprocess.run(
["pgrep", "-a", "firecracker"],
capture_output=True, text=True, check=False,
)
if result.returncode != 0:
return []
pids: list[int] = []
for line in result.stdout.splitlines():
parts = line.split(None, 1)
if len(parts) != 2 or run_root not in parts[1]:
continue
try:
pids.append(int(parts[0]))
except ValueError:
continue
return pids
def _sidecar_containers() -> list[str]:
result = subprocess.run(
["docker", "ps", "-a", "--format", "{{.Names}}",
"--filter", f"name={_SIDECAR_PREFIX}"],
capture_output=True, text=True, check=False,
)
if result.returncode != 0:
return []
return sorted(n.strip() for n in result.stdout.splitlines() if n.strip())
def _run_dirs() -> list[str]:
run_root = _run_root()
if not run_root.is_dir():
return []
return sorted(str(p) for p in run_root.iterdir() if p.is_dir())
def prepare_cleanup() -> FirecrackerBottleCleanupPlan:
return FirecrackerBottleCleanupPlan(
vm_pids=tuple(_orphan_vm_pids()),
containers=tuple(_sidecar_containers()),
run_dirs=tuple(_run_dirs()),
)
def cleanup(plan: FirecrackerBottleCleanupPlan) -> None:
for pid in plan.vm_pids:
info(f"kill firecracker VM pid {pid}")
try:
os.kill(pid, signal.SIGTERM)
except ProcessLookupError:
pass
for name in plan.containers:
info(f"docker rm -f {name}")
subprocess.run(
["docker", "rm", "-f", name],
stdout=subprocess.DEVNULL, stderr=subprocess.DEVNULL, check=False,
)
for path in plan.run_dirs:
info(f"rm -rf {path}")
shutil.rmtree(path, ignore_errors=True)
@@ -1,43 +0,0 @@
"""Active-agent enumeration for the Firecracker backend.
The agent runs in a VM (no container to list), so a live bottle is
identified by its running sidecar container `bot-bottle-sidecars-<slug>`
— the same discovery-by-prefix the other backends use.
"""
from __future__ import annotations
import subprocess
from ...bottle_state import read_metadata
from .. import ActiveAgent
_SIDECAR_PREFIX = "bot-bottle-sidecars-"
def enumerate_active() -> list[ActiveAgent]:
result = subprocess.run(
["docker", "ps", "--format", "{{.Names}}",
"--filter", f"name={_SIDECAR_PREFIX}"],
capture_output=True, text=True, check=False,
)
if result.returncode != 0:
return []
out: list[ActiveAgent] = []
for name in sorted(n.strip() for n in result.stdout.splitlines() if n.strip()):
slug = name[len(_SIDECAR_PREFIX):]
metadata = read_metadata(slug)
if metadata is None or metadata.backend != "firecracker":
# Skip sidecars owned by another backend (docker shares the
# container-name prefix).
continue
out.append(ActiveAgent(
backend_name="firecracker",
slug=slug,
agent_name=metadata.agent_name,
started_at=metadata.started_at,
services=(),
label=metadata.label,
color=metadata.color,
))
return out
@@ -1,173 +0,0 @@
"""Firecracker microVM process lifecycle.
A bottle VM is one `firecracker` process booted from a JSON config
(kernel + writable rootfs ext4 + one TAP network interface). We run it
`--no-api`: all configuration is in the config file, and teardown is a
process signal — the microVM dies with its VMM, which is exactly the
ephemeral-bottle semantics we want. No API socket, no runtime
reconfiguration.
The guest gets its IP from the kernel `ip=` cmdline (kernel-level
autoconfig, no in-guest iproute2) and its SSH pubkey from a `bb_pubkey=`
cmdline arg the init decodes.
"""
from __future__ import annotations
import base64
import json
import signal
import subprocess
import time
from dataclasses import dataclass
from pathlib import Path
from ...log import die, info
from . import util
# Serial console off the critical path but captured to a log for
# debugging boot failures. `reboot=k panic=1 pci=off` are the standard
# Firecracker guest args; `i8042.*` skip the (absent) PS/2 probe to
# shave boot time.
_BASE_BOOT_ARGS = (
"console=ttyS0 reboot=k panic=1 pci=off "
"i8042.noaux i8042.nomux i8042.nopnp i8042.dumbkbd "
"root=/dev/vda rw init=/bb-init"
)
@dataclass
class VmHandle:
"""A running microVM: its VMM process, guest IP, and console log."""
process: subprocess.Popen[bytes]
guest_ip: str
console_log: Path
def is_alive(self) -> bool:
return self.process.poll() is None
def terminate(self) -> None:
"""Stop the VMM (and thus the guest). SIGTERM, then SIGKILL."""
if self.process.poll() is not None:
return
self.process.send_signal(signal.SIGTERM)
try:
self.process.wait(timeout=5)
except subprocess.TimeoutExpired:
self.process.kill()
self.process.wait(timeout=5)
def _boot_args(guest_ip: str, host_ip: str, pubkey: str) -> str:
# ip=<client>::<gw>:<netmask>::<dev>:off — /31 point-to-point link,
# so netmask is 255.255.255.254 and the gateway is the host TAP IP.
ip_arg = f"ip={guest_ip}::{host_ip}:255.255.255.254::eth0:off"
pub_b64 = base64.b64encode(pubkey.encode()).decode()
return f"{_BASE_BOOT_ARGS} {ip_arg} bb_pubkey={pub_b64}"
def _config(
*,
rootfs: Path,
tap: str,
guest_ip: str,
host_ip: str,
pubkey: str,
vcpus: int,
mem_mib: int,
guest_mac: str,
) -> dict[str, object]:
return {
"boot-source": {
"kernel_image_path": str(util.kernel_path()),
"boot_args": _boot_args(guest_ip, host_ip, pubkey),
},
"drives": [
{
"drive_id": "rootfs",
"path_on_host": str(rootfs),
"is_root_device": True,
"is_read_only": False,
}
],
"network-interfaces": [
{
"iface_id": "eth0",
"host_dev_name": tap,
"guest_mac": guest_mac,
}
],
"machine-config": {
"vcpu_count": vcpus,
"mem_size_mib": mem_mib,
},
}
def boot(
*,
name: str,
rootfs: Path,
tap: str,
guest_ip: str,
host_ip: str,
pubkey: str,
run_dir: Path,
vcpus: int = 2,
mem_mib: int = 2048,
guest_mac: str = "06:00:AC:10:00:02",
) -> VmHandle:
"""Write the config and launch the VMM. Returns once the process is
spawned; callers wait for SSH readiness separately."""
run_dir.mkdir(parents=True, exist_ok=True)
config_path = run_dir / "config.json"
console_log = run_dir / "console.log"
config_path.write_text(json.dumps(
_config(
rootfs=rootfs, tap=tap, guest_ip=guest_ip, host_ip=host_ip,
pubkey=pubkey, vcpus=vcpus, mem_mib=mem_mib, guest_mac=guest_mac,
),
indent=2,
))
info(f"booting microVM {name} on {tap} (guest {guest_ip})")
log_fh = console_log.open("wb")
process = subprocess.Popen(
["firecracker", "--no-api", "--config-file", str(config_path)],
stdout=log_fh, stderr=subprocess.STDOUT, stdin=subprocess.DEVNULL,
)
return VmHandle(process=process, guest_ip=guest_ip, console_log=console_log)
def wait_for_ssh(
vm: VmHandle, private_key: Path, *, timeout: float = 30.0,
) -> None:
"""Poll SSH until the guest accepts a command or the deadline
passes. Dies (with the console tail) if the VMM exits early or the
guest never comes up — a boot failure must be loud, not a hang."""
deadline = time.monotonic() + timeout
probe = util.ssh_base_argv(private_key, vm.guest_ip) + ["true"]
while time.monotonic() < deadline:
if not vm.is_alive():
die(f"microVM exited during boot (rc={vm.process.returncode}).\n"
f"{_console_tail(vm.console_log)}")
result = subprocess.run(
probe, stdout=subprocess.DEVNULL, stderr=subprocess.DEVNULL,
check=False,
)
if result.returncode == 0:
return
time.sleep(0.5)
die(f"microVM {vm.guest_ip} did not accept SSH within {timeout:.0f}s.\n"
f"{_console_tail(vm.console_log)}")
def _console_tail(console_log: Path, lines: int = 25) -> str:
try:
text = console_log.read_text(errors="replace").splitlines()
except OSError:
return "(no console log)"
tail = "\n".join(text[-lines:])
return f"--- guest console (last {lines} lines) ---\n{tail}"
-76
View File
@@ -1,76 +0,0 @@
"""FirecrackerFreezer — snapshot a running microVM to a Docker image.
The VM is live and can't be block-copied safely, so — like the macOS
backend — we stream the guest root filesystem out over the control
channel (SSH here) and rebuild an image from it. The bottle keeps
running after the snapshot.
"""
from __future__ import annotations
import json
import os
import subprocess
import tempfile
from pathlib import Path
from ...log import die, info
from .. import ActiveAgent
from ..freeze import Freezer
from . import util
class FirecrackerFreezer(Freezer):
backend_name = "firecracker"
def _freeze(self, agent: ActiveAgent) -> str:
run_dir = util.cache_dir() / "run" / agent.slug
private_key = run_dir / "bottle_id_ed25519"
guest_ip = _guest_ip_from_config(run_dir / "config.json")
if not private_key.is_file() or not guest_ip:
die(f"cannot freeze {agent.slug}: run dir {run_dir} is missing the "
f"SSH key or VM config (is the bottle still running?)")
image_tag = f"bot-bottle-committed-{agent.slug}:latest"
_commit_via_ssh(private_key, guest_ip, image_tag)
info(f"committed {agent.slug} -> {image_tag!r}")
return image_tag
def _export_hint(self, slug: str, image_ref: str) -> None:
info(f"to export for migration: docker image save {image_ref} "
f"-o {slug}.tar")
def _guest_ip_from_config(config_path: Path) -> str:
try:
cfg = json.loads(config_path.read_text())
except (OSError, json.JSONDecodeError):
return ""
boot_args = cfg.get("boot-source", {}).get("boot_args", "")
for token in boot_args.split():
if token.startswith("ip="):
# ip=<client>::<gw>:<mask>::<dev>:off
return token[len("ip="):].split(":", 1)[0]
return ""
def _commit_via_ssh(private_key: Path, guest_ip: str, image_tag: str) -> None:
with tempfile.TemporaryDirectory(prefix="bot-bottle-fc-commit.") as tmp:
rootfs_tar = os.path.join(tmp, "rootfs.tar")
ssh = util.ssh_base_argv(private_key, guest_ip)
with open(rootfs_tar, "wb") as tar_out:
result = subprocess.run(
[*ssh, "--", "tar", "--create", "--one-file-system",
"--exclude=./proc", "--exclude=./sys", "--exclude=./dev",
"--exclude=./run", "--file=-", "--directory=/", "."],
stdout=tar_out, stderr=subprocess.PIPE, check=False,
)
if result.returncode != 0:
die(f"ssh tar for {guest_ip} failed: "
f"{(result.stderr or b'').decode().strip() or '<no stderr>'}")
with open(os.path.join(tmp, "Dockerfile"), "w", encoding="utf-8") as f:
f.write("FROM scratch\nADD rootfs.tar /\nUSER node\nWORKDIR /home/node\n")
build = subprocess.run(
["docker", "build", "-t", image_tag, tmp], check=False,
)
if build.returncode != 0:
die(f"docker build for {image_tag!r} failed")
@@ -1,116 +0,0 @@
"""Empirical, post-boot isolation probe — the authoritative fail-closed
egress-boundary check.
The pre-boot nft check can't be trusted on every host (listing an
nftables table typically needs root; the launcher runs unprivileged).
So before the agent ever runs, we prove the boundary directly: open a
canary TCP listener on a host IP the VM must NOT be able to reach (the
host's primary non-TAP address), then have the guest try to connect. If
the isolation rules are in force the connection is dropped and times
out; if it succeeds, the VM can reach host services it shouldn't — a
sandbox escape — and we refuse to continue.
The listener is load-bearing: without it a "blocked" result could just
be connection-refused. With it, a reachable canary means a real leak
and a timeout means a real drop.
"""
from __future__ import annotations
import socket
import subprocess
import threading
from pathlib import Path
from ...log import die, info, warn
from . import util
def _host_primary_ip() -> str:
"""The source IP the host uses for off-box traffic (its LAN
address) — a canary the VM must not reach. Empty if the host has no
such route (isolated box)."""
result = subprocess.run(
["ip", "-o", "route", "get", "1.1.1.1"],
capture_output=True, text=True, check=False,
)
if result.returncode != 0:
return ""
tokens = result.stdout.split()
# `... src <addr> ...` — the address the host would use as source.
if "src" in tokens:
idx = tokens.index("src")
if idx + 1 < len(tokens):
return tokens[idx + 1]
return ""
# Guest-side connect test: exit 0 = reached the canary (LEAK), 1 =
# blocked (good), 2 = no usable tool (inconclusive -> fail-closed).
_GUEST_PROBE = r"""
h="$1"; p="$2"
if command -v python3 >/dev/null 2>&1; then
python3 - "$h" "$p" <<'PY'
import socket, sys
s = socket.socket(); s.settimeout(3)
sys.exit(0 if s.connect_ex((sys.argv[1], int(sys.argv[2]))) == 0 else 1)
PY
elif command -v bash >/dev/null 2>&1; then
timeout 3 bash -c "exec 3<>/dev/tcp/$h/$p" >/dev/null 2>&1
elif command -v nc >/dev/null 2>&1; then
nc -w3 -z "$h" "$p" >/dev/null 2>&1
else
exit 2
fi
"""
def verify_isolation(private_key: Path, guest_ip: str) -> None:
"""Prove the VM cannot reach the host's primary IP. Dies
(fail-closed) on a confirmed leak or if the guest has no tool to
run the test. Warns (does not fail) when the host has no canary
address to test against."""
canary_ip = _host_primary_ip()
if not canary_ip:
warn("isolation probe skipped: host has no non-TAP route to test "
"against (isolated box).")
return
listener = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
listener.setsockopt(socket.SOL_SOCKET, socket.SO_REUSEADDR, 1)
listener.bind((canary_ip, 0))
listener.listen(1)
listener.settimeout(6)
canary_port = listener.getsockname()[1]
accepted: list[bool] = []
def _accept() -> None:
try:
conn, _ = listener.accept()
accepted.append(True)
conn.close()
except OSError:
pass
thread = threading.Thread(target=_accept, daemon=True)
thread.start()
ssh = util.ssh_base_argv(private_key, guest_ip)
result = subprocess.run(
[*ssh, "--", "sh", "-s", "--", canary_ip, str(canary_port)],
input=_GUEST_PROBE, capture_output=True, text=True, check=False,
)
thread.join(timeout=7)
listener.close()
if result.returncode == 0 or accepted:
die(f"ISOLATION FAILURE: the VM reached the host canary "
f"{canary_ip}:{canary_port}. The egress boundary is not in "
f"force — refusing to run the agent (fail-closed). Verify the "
f"nft table with: ./cli.py backend setup --backend=firecracker")
if result.returncode == 2:
die("isolation probe inconclusive: the guest has no python3/bash/nc "
"to run the connectivity test. Refusing to continue "
"(fail-closed).")
info(f"isolation verified: VM cannot reach host {canary_ip}")
-404
View File
@@ -1,404 +0,0 @@
"""Launch flow for the Firecracker backend.
Per bottle:
1. mint the egress CA, build the agent image (docker), export it to a
cached ext4 rootfs;
2. claim a free TAP pool slot (rootless flock);
3. bring up the Docker sidecar bundle, publishing egress / git-gate /
supervise on the slot's host-side TAP IP at fixed ports;
4. boot the microVM on that TAP; wait for SSH;
5. provision (CA, prompt, skills, workspace, git, supervise) over SSH.
Isolation is enforced by the operator-provisioned nft table (checked
fail-closed in preflight): a VM reaches only its sidecar (DNAT'd from
the host TAP IP) and nothing else. The agent's HTTPS_PROXY therefore
points at `http://<host_tap_ip>:9099`, its only route to the world.
"""
from __future__ import annotations
import dataclasses
import os
import subprocess
from contextlib import ExitStack, contextmanager
from pathlib import Path
from typing import Callable, Generator
from ...bottle_state import (
egress_state_dir,
git_gate_state_dir,
read_committed_image,
)
from ...egress import (
EGRESS_ROUTES_IN_CONTAINER,
egress_agent_env_entries,
egress_resolve_token_values,
egress_sidecar_env_entries,
)
from ...git_gate import (
provision_git_gate_dynamic_keys,
revoke_git_gate_provisioned_keys,
)
from ...log import die, info, warn
from ...supervise import DB_PATH_IN_CONTAINER, SUPERVISE_PORT
from ...util import expand_tilde
from ..docker.egress import (
EGRESS_CA_IN_CONTAINER,
EGRESS_PORT,
egress_tls_init,
)
from ..docker.git_gate import (
GIT_GATE_ACCESS_HOOK_IN_CONTAINER,
GIT_GATE_CREDS_DIR_IN_CONTAINER,
GIT_GATE_ENTRYPOINT_IN_CONTAINER,
GIT_GATE_HOOK_IN_CONTAINER,
)
from ..docker.sidecar_bundle import (
SIDECAR_BUNDLE_DOCKERFILE,
SIDECAR_BUNDLE_IMAGE,
)
from ..util import AGENT_CA_BUNDLE, AGENT_CA_PATH
from . import firecracker_vm, isolation_probe, netpool, util
from .bottle import FirecrackerBottle
from .bottle_plan import FirecrackerBottlePlan
_REPO_DIR = str(Path(__file__).resolve().parent.parent.parent.parent)
_GIT_HTTP_PORT = 9420
_GIT_GATE_READY_FILE = "/run/git-gate/ready"
def sidecar_container_name(slug: str) -> str:
return f"bot-bottle-sidecars-{slug}"
@contextmanager
def launch(
plan: FirecrackerBottlePlan,
*,
provision: Callable[[FirecrackerBottlePlan, "FirecrackerBottle"], str | None],
) -> Generator[FirecrackerBottle, None, None]:
stack = ExitStack()
bottle_for_revoke = plan.manifest.bottle
git_gate_dir_for_revoke = git_gate_state_dir(plan.slug)
def teardown() -> None:
teardown_exc: BaseException | None = None
try:
stack.close()
except BaseException as exc: # noqa: W0718 - teardown must continue
teardown_exc = exc
warn(f"firecracker teardown failed: {exc!r}")
revoke_git_gate_provisioned_keys(bottle_for_revoke, git_gate_dir_for_revoke)
if teardown_exc is not None:
raise teardown_exc
try:
plan = _mint_certs(plan)
plan = _build_agent_image(plan)
# Claim a TAP slot; the flock is held until teardown closes it.
slot, lock = netpool.allocate(plan.slug)
stack.callback(lock.close)
info(f"firecracker slot {slot.iface}: host={slot.host_ip} "
f"guest={slot.guest_ip}")
plan = _provision_git_gate_keys(plan)
sidecar_name = sidecar_container_name(plan.slug)
_force_remove_container(sidecar_name)
_start_sidecar_bundle(plan, sidecar_name, slot.host_ip)
stack.callback(_force_remove_container, sidecar_name)
_stage_git_gate(plan, sidecar_name)
plan = _stamp_agent_urls(plan, slot.host_ip)
# Build the per-bottle rootfs + SSH key, then boot.
base_dir = util.build_base_rootfs_dir(plan.image)
run_dir = util.cache_dir() / "run" / plan.slug
run_dir.mkdir(parents=True, exist_ok=True)
rootfs = run_dir / "rootfs.ext4"
util.build_rootfs_ext4(base_dir, rootfs)
private_key, pubkey = util.generate_keypair(run_dir)
vm = firecracker_vm.boot(
name=plan.container_name,
rootfs=rootfs,
tap=slot.iface,
guest_ip=slot.guest_ip,
host_ip=slot.host_ip,
pubkey=pubkey,
run_dir=run_dir,
)
stack.callback(vm.terminate)
firecracker_vm.wait_for_ssh(vm, private_key)
# Authoritative fail-closed egress-boundary check, before the
# agent runs: prove the VM cannot reach the host directly.
isolation_probe.verify_isolation(private_key, slot.guest_ip)
bottle = FirecrackerBottle(
plan.container_name,
private_key=private_key,
guest_ip=slot.guest_ip,
guest_env=_agent_guest_env(plan, slot.host_ip),
agent_command=plan.agent_command,
agent_prompt_mode=plan.agent_prompt_mode,
agent_provider_template=plan.agent_provider_template,
terminal_title=(
f"{plan.spec.label} ({plan.spec.agent_name})"
if plan.spec.label else plan.spec.agent_name
),
terminal_color=plan.spec.color,
agent_workdir=plan.workspace_plan.workdir,
)
bottle.prompt_path = provision(plan, bottle)
yield bottle
finally:
teardown()
def _mint_certs(plan: FirecrackerBottlePlan) -> FirecrackerBottlePlan:
egress_ca_host, egress_ca_cert_only = egress_tls_init(egress_state_dir(plan.slug))
egress_plan = dataclasses.replace(
plan.egress_plan,
mitmproxy_ca_host_path=egress_ca_host,
mitmproxy_ca_cert_only_host_path=egress_ca_cert_only,
)
return dataclasses.replace(plan, egress_plan=egress_plan)
def _build_agent_image(plan: FirecrackerBottlePlan) -> FirecrackerBottlePlan:
_docker_build(SIDECAR_BUNDLE_IMAGE, _REPO_DIR, dockerfile=SIDECAR_BUNDLE_DOCKERFILE)
committed = read_committed_image(plan.slug)
if committed and _image_exists(committed):
info(f"using committed image {committed!r}")
return dataclasses.replace(
plan,
agent_provision=dataclasses.replace(plan.agent_provision, image=committed),
)
_docker_build(plan.image, _REPO_DIR, dockerfile=plan.dockerfile_path)
return plan
def _provision_git_gate_keys(plan: FirecrackerBottlePlan) -> FirecrackerBottlePlan:
if not plan.git_gate_plan.upstreams:
return plan
git_gate_plan = provision_git_gate_dynamic_keys(
plan.manifest.bottle, plan.git_gate_plan, git_gate_state_dir(plan.slug),
)
return dataclasses.replace(plan, git_gate_plan=git_gate_plan)
def _stamp_agent_urls(
plan: FirecrackerBottlePlan, host_ip: str,
) -> FirecrackerBottlePlan:
proxy_url = f"http://{host_ip}:{EGRESS_PORT}"
supervise_url = (
f"http://{host_ip}:{SUPERVISE_PORT}/" if plan.supervise_plan is not None else ""
)
git_gate_url = (
f"http://{host_ip}:{_GIT_HTTP_PORT}" if plan.git_gate_plan.upstreams else ""
)
return dataclasses.replace(
plan,
agent_proxy_url=proxy_url,
agent_git_gate_url=git_gate_url,
agent_supervise_url=supervise_url,
)
# --- sidecar bundle (Docker) ----------------------------------------
def _start_sidecar_bundle(
plan: FirecrackerBottlePlan, sidecar_name: str, host_ip: str,
) -> None:
argv = ["docker", "run", "--name", sidecar_name, "--detach", "--rm",
"-e", f"BOT_BOTTLE_SIDECAR_DAEMONS={','.join(_sidecar_daemons(plan))}"]
for entry in _sidecar_env_entries(plan):
argv += ["-e", entry]
for host_path, container_path, read_only in _sidecar_mounts(plan):
argv += ["-v", f"{host_path}:{container_path}{':ro' if read_only else ''}"]
# Publish on the slot's host TAP IP at fixed ports — each bottle
# has a distinct host_ip, so fixed ports never collide, and the VM
# reaches them at a stable, well-known address (its only route out).
for port in _sidecar_ports(plan):
argv += ["-p", f"{host_ip}:{port}:{port}"]
argv.append(SIDECAR_BUNDLE_IMAGE)
effective_env = {**dict(os.environ), **plan.agent_provision.provisioned_env}
token_values = egress_resolve_token_values(
plan.egress_plan.token_env_map, effective_env,
)
env = {**os.environ, **token_values}
info(f"docker run sidecar bundle {sidecar_name} (published on {host_ip})")
result = subprocess.run(argv, capture_output=True, text=True, env=env, check=False)
if result.returncode != 0:
die(f"docker run for sidecar bundle {sidecar_name} failed: "
f"{(result.stderr or '').strip() or '<no stderr>'}")
def _sidecar_daemons(plan: FirecrackerBottlePlan) -> tuple[str, ...]:
daemons = ["egress"]
if plan.git_gate_plan.upstreams:
daemons += ["git-gate", "git-http"]
if plan.supervise_plan is not None:
daemons.append("supervise")
return tuple(daemons)
def _sidecar_ports(plan: FirecrackerBottlePlan) -> tuple[int, ...]:
ports = [EGRESS_PORT]
if plan.git_gate_plan.upstreams:
ports.append(_GIT_HTTP_PORT)
if plan.supervise_plan is not None:
ports.append(SUPERVISE_PORT)
return tuple(ports)
def _sidecar_env_entries(plan: FirecrackerBottlePlan) -> tuple[str, ...]:
env: list[str] = list(egress_sidecar_env_entries(plan.egress_plan))
if plan.git_gate_plan.upstreams:
env.append(f"BOT_BOTTLE_GIT_GATE_READY_FILE={_GIT_GATE_READY_FILE}")
if plan.supervise_plan is not None:
env += [
f"SUPERVISE_BOTTLE_SLUG={plan.slug}",
f"SUPERVISE_DB_PATH={DB_PATH_IN_CONTAINER}",
f"SUPERVISE_PORT={SUPERVISE_PORT}",
]
return tuple(env)
def _sidecar_mounts(
plan: FirecrackerBottlePlan,
) -> tuple[tuple[str, str, bool], ...]:
mounts: list[tuple[str, str, bool]] = []
ep = plan.egress_plan
mounts.append((str(ep.mitmproxy_ca_host_path.parent),
str(Path(EGRESS_CA_IN_CONTAINER).parent), False))
if ep.routes:
mounts.append((str(ep.routes_path.parent),
str(Path(EGRESS_ROUTES_IN_CONTAINER).parent), True))
sp = plan.supervise_plan
if sp is not None:
mounts.append((str(sp.db_path.parent),
str(Path(DB_PATH_IN_CONTAINER).parent), False))
return tuple(mounts)
def _stage_git_gate(plan: FirecrackerBottlePlan, sidecar_name: str) -> None:
gp = plan.git_gate_plan
if not gp.upstreams:
return
_docker_exec(sidecar_name, [
"mkdir", "-p",
str(Path(GIT_GATE_HOOK_IN_CONTAINER).parent),
GIT_GATE_CREDS_DIR_IN_CONTAINER, "/git",
str(Path(_GIT_GATE_READY_FILE).parent),
])
for host_path, container_path in _git_gate_files(plan):
_docker_cp(host_path, f"{sidecar_name}:{container_path}")
_docker_exec(sidecar_name, [
"sh", "-c",
f"chmod 755 {GIT_GATE_ENTRYPOINT_IN_CONTAINER} "
f"{GIT_GATE_HOOK_IN_CONTAINER} {GIT_GATE_ACCESS_HOOK_IN_CONTAINER} && "
f"chmod 600 {GIT_GATE_CREDS_DIR_IN_CONTAINER}/* && "
f"touch {_GIT_GATE_READY_FILE}",
])
def _git_gate_files(plan: FirecrackerBottlePlan) -> tuple[tuple[str, str], ...]:
gp = plan.git_gate_plan
files: list[tuple[str, str]] = [
(str(gp.entrypoint_script), GIT_GATE_ENTRYPOINT_IN_CONTAINER),
(str(gp.hook_script), GIT_GATE_HOOK_IN_CONTAINER),
(str(gp.access_hook_script), GIT_GATE_ACCESS_HOOK_IN_CONTAINER),
]
for upstream in gp.upstreams:
files.append((expand_tilde(upstream.identity_file),
f"{GIT_GATE_CREDS_DIR_IN_CONTAINER}/{upstream.name}-key"))
if upstream.known_hosts_file:
files.append((str(upstream.known_hosts_file),
f"{GIT_GATE_CREDS_DIR_IN_CONTAINER}/{upstream.name}-known_hosts"))
return tuple(files)
# --- agent guest env -------------------------------------------------
def _agent_guest_env(plan: FirecrackerBottlePlan, host_ip: str) -> dict[str, str]:
"""Env injected into every agent/exec call over SSH. The VM has no
baked process env (it just runs init), so the proxy/CA/git/supervise
wiring is applied per-invocation."""
proxy_url = f"http://{host_ip}:{EGRESS_PORT}"
no_proxy = f"localhost,127.0.0.1,{host_ip}"
env: dict[str, str] = {
"HTTPS_PROXY": proxy_url, "HTTP_PROXY": proxy_url,
"https_proxy": proxy_url, "http_proxy": proxy_url,
"NO_PROXY": no_proxy, "no_proxy": no_proxy,
"NODE_EXTRA_CA_CERTS": AGENT_CA_PATH,
"SSL_CERT_FILE": AGENT_CA_BUNDLE,
"REQUESTS_CA_BUNDLE": AGENT_CA_BUNDLE,
}
if plan.agent_git_gate_url:
env["GIT_GATE_URL"] = plan.agent_git_gate_url
if plan.agent_supervise_url:
env["MCP_SUPERVISE_URL"] = plan.agent_supervise_url
for entry in egress_agent_env_entries(plan.egress_plan):
key, _, value = entry.partition("=")
env[key] = value
env.update(plan.agent_provision.guest_env)
# Forwarded (bare-name) env: resolve host values now, since the VM
# can't inherit them from a `docker run --env NAME`.
for name in plan.forwarded_env:
value = os.environ.get(name)
if value is not None:
env[name] = value
return env
# --- docker helpers --------------------------------------------------
def _docker_build(ref: str, context: str, *, dockerfile: str = "") -> None:
info(f"docker build {ref}")
args = ["docker", "build", "-t", ref]
if dockerfile:
if not os.path.isabs(dockerfile):
dockerfile = os.path.join(context, dockerfile)
args += ["-f", dockerfile]
args.append(context)
result = subprocess.run(args, check=False)
if result.returncode != 0:
die(f"docker build for {ref!r} failed")
def _image_exists(ref: str) -> bool:
return subprocess.run(
["docker", "image", "inspect", ref],
stdout=subprocess.DEVNULL, stderr=subprocess.DEVNULL, check=False,
).returncode == 0
def _force_remove_container(name: str) -> None:
subprocess.run(
["docker", "rm", "-f", name],
stdout=subprocess.DEVNULL, stderr=subprocess.DEVNULL, check=False,
)
def _docker_exec(name: str, argv: list[str]) -> None:
result = subprocess.run(
["docker", "exec", name, *argv], capture_output=True, text=True, check=False,
)
if result.returncode != 0:
die(f"docker exec in {name} failed: "
f"{(result.stderr or '').strip() or '<no stderr>'}")
def _docker_cp(host_path: str, dest: str) -> None:
result = subprocess.run(
["docker", "cp", host_path, dest], capture_output=True, text=True, check=False,
)
if result.returncode != 0:
die(f"docker cp {host_path} -> {dest} failed: "
f"{(result.stderr or '').strip() or '<no stderr>'}")
@@ -1,17 +0,0 @@
# Firecracker network-pool defaults — the SINGLE source of these values.
#
# Read by every consumer so they can't drift:
# * netpool.py — parses this for the Python defaults (below).
# * scripts/firecracker-netpool.sh — falls back to these when the
# matching BOT_BOTTLE_FC_* env var is unset.
# * nix/firecracker-netpool.nix — readFile-parses this for its option
# defaults, then passes the resolved values back as Environment=.
#
# Plain KEY=VALUE (no quoting, no inline comments, no spaces around `=`)
# so it is bash-sourceable, systemd EnvironmentFile-compatible, and
# trivially parseable from Python and Nix. A real BOT_BOTTLE_FC_* env
# var of the same name always overrides the value here.
BOT_BOTTLE_FC_POOL_SIZE=8
BOT_BOTTLE_FC_IP_BASE=10.243.0.0
BOT_BOTTLE_FC_IFACE_PREFIX=bbfc
BOT_BOTTLE_FC_NFT_TABLE=bot_bottle_fc
-321
View File
@@ -1,321 +0,0 @@
"""Firecracker network pool: constants, IP math, allocation, and the
config renderers (shell command + NixOS module) shown to operators.
The Firecracker backend needs a privileged one-time network setup:
a pool of point-to-point TAP devices (owned by the invoking user, so
`./cli.py start` never needs root) and a dedicated nftables table that
isolates every VM. The pool parameters live in exactly one place —
`netpool.defaults.env`, a plain KEY=VALUE file next to this module —
and every consumer reads *that*: this module (below), the shell script
(`scripts/firecracker-netpool.sh`), and the NixOS module
(`nix/firecracker-netpool.nix`). A `BOT_BOTTLE_FC_*` env var of the
same name always overrides the file, and the backend's fail-closed
preflight derives from these accessors, so nothing can drift.
Topology (per slot i):
* TAP ``bbfc{i}`` — no shared bridge, so no docker0 / virbr0 / cni0
/ br-* collisions.
* a /31 host<->guest link: host = base + 2i (the gateway the VM
routes through), guest = base + 2i + 1 (the VM's address).
* isolation via ``table inet bot_bottle_fc``: a VM reaches only its
own sidecar (DNAT'd from the host TAP IP) and nothing else.
The default IP block is ``10.243.0.0/16`` — an intentionally obscure
corner of RFC-1918 private space. RFC-1918 is the range *designated*
for private links; we pick a high, unusual /16 to steer clear of the
common occupants (Docker's 172.17-31, libvirt's 192.168.122, k8s
10.42/10.244, and typical home LANs on 192.168.0/1.x or 10.0.0.x).
We deliberately avoid ``100.64.0.0/10`` (RFC-6598 CGNAT) because
Tailscale hands out node addresses from exactly that range. No default
is collision-proof, so `overlapping_routes()` is the real guard —
`backend setup`/`status` and the launch preflight call it to catch
a base that clashes with something already on the host.
"""
from __future__ import annotations
import fcntl
import ipaddress
import os
import subprocess
from dataclasses import dataclass
from pathlib import Path
from typing import IO
from ...log import die
# The pool defaults live in one shared file (see module docstring); the
# shell script and NixOS module read the same file, so the values can't
# drift. This is a packaged data file — a missing/broken install is a
# hard error, surfaced here rather than as confusing empty defaults.
DEFAULTS_FILE = Path(__file__).with_name("netpool.defaults.env")
def _load_defaults() -> dict[str, str]:
out: dict[str, str] = {}
for raw in DEFAULTS_FILE.read_text().splitlines():
line = raw.strip()
if not line or line.startswith("#") or "=" not in line:
continue
key, _, value = line.partition("=")
out[key.strip()] = value.strip()
return out
_DEFAULTS = _load_defaults()
def _cfg(key: str) -> str:
"""A `BOT_BOTTLE_FC_*` env var overrides the shared-file default."""
try:
return os.environ.get(key) or _DEFAULTS[key]
except KeyError:
die(f"{key} is missing from {DEFAULTS_FILE.name} (broken install)")
# Interface names are capped at 15 chars (IFNAMSIZ-1); "bbfc" + a small
# index stays well under that and is distinctive enough to grep for.
IFACE_PREFIX = _cfg("BOT_BOTTLE_FC_IFACE_PREFIX")
NFT_TABLE = _cfg("BOT_BOTTLE_FC_NFT_TABLE")
def pool_size() -> int:
return int(_cfg("BOT_BOTTLE_FC_POOL_SIZE"))
def ip_base() -> str:
return _cfg("BOT_BOTTLE_FC_IP_BASE")
# Sidecar ports the VM reaches at its host-side TAP IP. Kept in sync
# with the backend constants (egress 9099, supervise 9100, git-http
# 9420); rendered into the setup output for operator visibility.
SIDECAR_PORTS = (9099, 9100, 9420)
@dataclass(frozen=True)
class Slot:
"""One pool slot: a TAP device and its host/guest /31 addresses."""
index: int
iface: str
host_ip: str
guest_ip: str
@property
def guest_cidr(self) -> str:
"""Guest address with the /31 prefix, for the kernel `ip=` arg."""
return f"{self.guest_ip}/31"
def slot(index: int) -> Slot:
base = int(ipaddress.IPv4Address(ip_base()))
return Slot(
index=index,
iface=f"{IFACE_PREFIX}{index}",
host_ip=str(ipaddress.IPv4Address(base + 2 * index)),
guest_ip=str(ipaddress.IPv4Address(base + 2 * index + 1)),
)
def all_slots() -> list[Slot]:
return [slot(i) for i in range(pool_size())]
# --- fail-closed verification ---------------------------------------
def _run_ok(argv: list[str]) -> bool:
"""Run a probe command, treating a missing binary as failure
(rather than crashing) so callers can stay fail-closed."""
try:
return subprocess.run(
argv, stdout=subprocess.DEVNULL, stderr=subprocess.DEVNULL,
check=False,
).returncode == 0
except FileNotFoundError:
return False
def nft_table_present() -> bool:
"""True iff the isolation table exists in the active nftables
backend. The backend's preflight treats absence as fatal — the VM
must not boot without its egress boundary in place.
Listing may require root; when it can't be confirmed here the
launch path falls back to an empirical post-boot isolation probe.
Returns False (fail-closed) if `nft` is unavailable."""
return _run_ok(["nft", "list", "table", "inet", NFT_TABLE])
def tap_present(iface: str) -> bool:
# `ip link show` is unprivileged, so the TAP-pool check is reliable
# for the non-root launcher.
return _run_ok(["ip", "link", "show", iface])
def missing_taps() -> list[str]:
"""Pool TAPs that the one-time setup has not created yet."""
return [s.iface for s in all_slots() if not tap_present(s.iface)]
@dataclass(frozen=True)
class RouteConflict:
"""An existing host route whose destination overlaps the pool range
but isn't one of our own bbfc TAPs — i.e. the chosen IP base clashes
with something already on the host (a Tailscale CGNAT peer, a
docker/libvirt bridge, the LAN…)."""
dst: str
dev: str
def _pool_span() -> tuple[int, int]:
"""Inclusive [first, last] integer bounds of every address the pool
occupies: base .. base + 2*pool_size - 1."""
base = int(ipaddress.IPv4Address(ip_base()))
return base, base + 2 * pool_size() - 1
def overlapping_routes() -> list[RouteConflict]:
"""Existing routes whose destination overlaps the pool's address
range, excluding our own `bbfc*` TAP routes and the default route.
A non-empty result means `BOT_BOTTLE_FC_IP_BASE` collides with
something already configured on this host, so the pool would shadow
(or be shadowed by) it. Empty on success — or when `ip` is missing
or unparseable, since this is an advisory guard, not the fail-closed
isolation check (that's the nft table + post-boot probe)."""
import json
try:
proc = subprocess.run(
["ip", "-json", "route", "show", "table", "all"],
capture_output=True, text=True, check=False,
)
except FileNotFoundError:
return []
if proc.returncode != 0 or not proc.stdout.strip():
return []
try:
routes = json.loads(proc.stdout)
except json.JSONDecodeError:
return []
lo, hi = _pool_span()
conflicts: list[RouteConflict] = []
for r in routes:
if not isinstance(r, dict):
continue
dst = r.get("dst")
dev = r.get("dev", "")
if not isinstance(dst, str) or dst in ("", "default"):
continue
if isinstance(dev, str) and dev.startswith(IFACE_PREFIX):
continue # our own pool link
try:
net = ipaddress.ip_network(dst, strict=False)
except ValueError:
continue
if net.version != 4:
continue
r_lo = int(net.network_address)
r_hi = int(net.broadcast_address)
if r_lo <= hi and lo <= r_hi: # ranges intersect
conflicts.append(RouteConflict(dst=dst, dev=str(dev)))
return conflicts
# --- allocation ------------------------------------------------------
def _lock_dir() -> Path:
d = Path.home() / ".cache" / "bot-bottle" / "firecracker" / "pool"
d.mkdir(parents=True, exist_ok=True)
return d
def allocate(slug: str) -> tuple[Slot, IO[str]]:
"""Claim a free pool slot for one bottle. Returns the slot and the
held lock file — the caller keeps it open for the VM's lifetime and
closes it on teardown; the flock auto-releases if the launcher
crashes, so a slot is never leaked. Dies when the pool is
exhausted.
A per-slot `flock` (rather than inspecting running processes) makes
allocation race-free across concurrent launches without a central
registry: the first launcher to grab the lock owns the slot."""
del slug # logged by the caller; allocation is purely lock-driven
for s in all_slots():
lock_path = _lock_dir() / f"{s.iface}.lock"
handle = open(lock_path, "w", encoding="utf-8")
try:
fcntl.flock(handle, fcntl.LOCK_EX | fcntl.LOCK_NB)
except OSError:
handle.close()
continue
return s, handle
die(f"Firecracker TAP pool exhausted ({pool_size()} slots, all in "
f"use). Stop a running bottle or raise BOT_BOTTLE_FC_POOL_SIZE "
f"and re-run `./cli.py backend setup --backend=firecracker`.")
raise AssertionError("unreachable")
# --- config renderers (shown by `./cli.py backend setup`) -----------
# The persistent unit is the portable install: the same systemd oneshot
# on every systemd distro (Debian/Ubuntu/Fedora/RHEL/Arch/…).
SYSTEMD_UNIT = "bot-bottle-firecracker-netpool.service"
def render_shell_setup() -> str:
"""The imperative one-shot command — non-persistent fallback for
hosts without systemd (OpenRC/runit/manual)."""
env = _nondefault_env()
prefix = f"{env} " if env else ""
return f"sudo {prefix}./scripts/firecracker-netpool.sh up"
def render_systemd_unit(owner: str, script_path: str) -> str:
"""A portable systemd oneshot unit for the pool — identical across
every systemd distro. ExecStart/ExecStop delegate to the bundled
shell script (the single source of bring-up logic); pool params are
pinned via Environment= so the unit matches the CLI's current
settings and doesn't depend on $SUDO_USER at boot (systemd runs it
as root with no SUDO_USER, which would otherwise own the TAPs as
root and break the rootless launch)."""
return f"""[Unit]
Description=bot-bottle Firecracker TAP pool + nft isolation table
After=network-pre.target
Wants=network-pre.target
[Service]
Type=oneshot
RemainAfterExit=yes
Environment=BOT_BOTTLE_FC_POOL_SIZE={pool_size()}
Environment=BOT_BOTTLE_FC_IP_BASE={ip_base()}
Environment=BOT_BOTTLE_FC_IFACE_PREFIX={IFACE_PREFIX}
Environment=BOT_BOTTLE_FC_OWNER={owner}
ExecStart={script_path} up
ExecStop={script_path} down
[Install]
WantedBy=multi-user.target
"""
# The NixOS setup is a real, importable module (nix/firecracker-netpool.nix,
# exposed as the flake output nixosModules.firecracker-netpool) rather than a
# generated paste — see `backend setup` output.
def _nondefault_env() -> str:
"""Render any non-default pool env overrides so the printed shell
command reproduces the operator's current settings."""
pairs = []
if os.environ.get("BOT_BOTTLE_FC_POOL_SIZE"):
pairs.append(f"BOT_BOTTLE_FC_POOL_SIZE={pool_size()}")
if os.environ.get("BOT_BOTTLE_FC_IP_BASE"):
pairs.append(f"BOT_BOTTLE_FC_IP_BASE={ip_base()}")
if os.environ.get("BOT_BOTTLE_FC_IFACE_PREFIX"):
pairs.append(f"BOT_BOTTLE_FC_IFACE_PREFIX={IFACE_PREFIX}")
return " ".join(pairs)
@@ -1,47 +0,0 @@
"""Prepare step for the Firecracker backend."""
from __future__ import annotations
from pathlib import Path
from ...agent_provider import AgentProvisionPlan
from ...egress import EgressPlan
from ...env import ResolvedEnv
from ...git_gate import GitGatePlan
from ...manifest import Manifest
from ...supervise import SupervisePlan
from .. import BottleSpec
from . import util
from .bottle_plan import FirecrackerBottlePlan
def preflight() -> None:
util.require_firecracker()
def build_guest_env(resolved_env: ResolvedEnv) -> dict[str, str]:
return dict(resolved_env.literals)
def resolve_plan(
spec: BottleSpec,
manifest: Manifest,
slug: str,
resolved_env: ResolvedEnv,
agent_provision_plan: AgentProvisionPlan,
egress_plan: EgressPlan,
supervise_plan: SupervisePlan | None,
git_gate_plan: GitGatePlan,
stage_dir: Path,
) -> FirecrackerBottlePlan:
return FirecrackerBottlePlan(
spec=spec,
manifest=manifest,
stage_dir=stage_dir,
slug=slug,
forwarded_env=dict(resolved_env.forwarded),
git_gate_plan=git_gate_plan,
egress_plan=egress_plan,
supervise_plan=supervise_plan,
agent_provision=agent_provision_plan,
)
-276
View File
@@ -1,276 +0,0 @@
"""Host setup + status for the Firecracker backend.
`setup()` prints the host-appropriate config for the privileged,
one-time network pool (TAP devices + isolation nftables table) the
backend needs. On NixOS it points at the flake module (and prints a
paste-able fallback); elsewhere it prints the sudo command for the
bundled setup script. `status()` reports what's present, including
whether the pool range collides with an existing route.
Called through `FirecrackerBottleBackend.setup` / `.status`, which the
generic `./cli.py backend {setup,status}` command dispatches to.
"""
from __future__ import annotations
import os
import shutil
import subprocess
import sys
from pathlib import Path
from . import netpool
from . import util
_FC_RELEASES = "https://github.com/firecracker-microvm/firecracker/releases"
_UNIT_PATH = Path("/etc/systemd/system") / netpool.SYSTEMD_UNIT
def _owner() -> str:
# Under `sudo`, USER is root but SUDO_USER is the real invoker — the
# TAPs must be owned by them so `./cli.py start` stays rootless.
return os.environ.get("SUDO_USER") or os.environ.get("USER") or "youruser"
def _has_systemd() -> bool:
return Path("/run/systemd/system").is_dir()
def _module_path() -> str:
"""Absolute path to the importable NixOS module in this checkout."""
return str(Path(__file__).resolve().parents[3] / "nix" / "firecracker-netpool.nix")
def _script_path() -> str:
"""Absolute path to the bundled bring-up script in this checkout."""
return str(Path(__file__).resolve().parents[3] / "scripts" / "firecracker-netpool.sh")
def _print_prereqs() -> None:
"""The firecracker binary + KVM + guest artifacts, shown before the
privileged network-pool step so operators see the full picture."""
fc = shutil.which("firecracker")
if fc:
sys.stderr.write(f"1) firecracker binary: found ({fc}).\n")
else:
sys.stderr.write(
"1) firecracker binary: NOT found on PATH. Install a release binary "
"and put it on PATH:\n"
f" {_FC_RELEASES}\n"
" e.g.: download firecracker-vX.Y.Z-$(uname -m).tgz, extract, and\n"
" install -m755 release-*/firecracker-* ~/.local/bin/firecracker\n"
" (NixOS: not packaged as a user binary — fetch the release, pin\n"
" the version, and add it to PATH.)\n"
)
if util.is_host_capable():
sys.stderr.write(" KVM: /dev/kvm present.\n")
else:
sys.stderr.write(
" KVM: /dev/kvm missing/unusable — load kvm-intel/kvm-amd, enable\n"
" virtualization in firmware, and add your user to the `kvm` group.\n"
)
sys.stderr.write(
" Guest artifacts: a kernel (BOT_BOTTLE_FC_KERNEL) and static dropbear\n"
" (BOT_BOTTLE_FC_DROPBEAR) must be cached, and `mke2fs` (e2fsprogs) is\n"
" needed to build the rootfs.\n\n"
)
def _is_nixos() -> bool:
if Path("/etc/NIXOS").exists():
return True
try:
return "ID=nixos" in Path("/etc/os-release").read_text()
except OSError:
return False
def _warn_overlaps() -> None:
"""Warn if the chosen pool range collides with an existing host route
(Tailscale CGNAT peer, a docker/libvirt bridge, the LAN…)."""
conflicts = netpool.overlapping_routes()
if not conflicts:
return
detail = "\n".join(f" {c.dst} dev {c.dev}" for c in conflicts)
sys.stderr.write(
f"WARNING: pool range (base {netpool.ip_base()}, "
f"{netpool.pool_size()} slots) overlaps existing routes:\n"
f"{detail}\n"
"Set BOT_BOTTLE_FC_IP_BASE to a free range before setup, or the "
"pool may shadow / be shadowed by the above.\n\n"
)
def setup() -> int:
sys.stderr.write("Firecracker backend — one-time host setup.\n\n")
_print_prereqs()
slots = netpool.all_slots()
sys.stderr.write(
f"2) network pool: {len(slots)} slots "
f"({slots[0].iface}..{slots[-1].iface}), base {netpool.ip_base()}"
f"TAP devices + nft isolation table, privileged (needs root once).\n\n"
)
_warn_overlaps()
if _is_nixos():
sys.stderr.write(
"Detected NixOS. Import the module — it is NON-INVASIVE: it does "
"not flip networking.nftables.enable or systemd.network.enable, so "
"your existing (iptables) firewall and Docker are untouched. A "
"systemd oneshot brings the pool up alongside them.\n\n"
" # flake users:\n"
" inputs.bot-bottle.url = \"git+ssh://<your-bot-bottle-remote>\";\n"
" imports = [ inputs.bot-bottle.nixosModules.firecracker-netpool ];\n"
" # channel (non-flake) users — import the file directly:\n"
f" imports = [ {_module_path()} ];\n\n"
f" services.bot-bottle-firecracker = {{ enable = true; owner = \"{_owner()}\"; }};\n\n"
"Then `nixos-rebuild switch`.\n"
)
elif _has_systemd():
_setup_systemd()
else:
sys.stderr.write(
"No systemd detected. Run the one-time bring-up as root (and add "
"your own boot persistence — e.g. an OpenRC/runit service):\n\n"
)
sys.stdout.write(netpool.render_shell_setup() + "\n")
return 0
def _setup_systemd() -> None:
"""Install the pool as a persistent systemd unit — the portable path,
identical on every systemd distro. Performs the install directly when
run as root; otherwise prints a self-contained copy-paste block."""
unit = netpool.render_systemd_unit(_owner(), _script_path())
sys.stderr.write(
f"Persistent install (systemd — same on every systemd distro). Needs "
f"`nft` (nftables) and `ip` (iproute2); install via your package "
f"manager if `backend status` reports them missing.\n\n"
)
if os.geteuid() == 0:
_UNIT_PATH.write_text(unit)
subprocess.run(["systemctl", "daemon-reload"], check=False)
rc = subprocess.run(
["systemctl", "enable", "--now", netpool.SYSTEMD_UNIT], check=False,
).returncode
if rc == 0:
sys.stderr.write(
f"Installed and started {netpool.SYSTEMD_UNIT}. Verify with "
f"`./cli.py backend status --backend=firecracker`.\n"
)
else:
sys.stderr.write(
f"Wrote {_UNIT_PATH} but `systemctl enable --now` failed — "
f"check `systemctl status {netpool.SYSTEMD_UNIT}`.\n"
)
return
sys.stderr.write(
"Install the unit (one copy-paste; enables it on boot too):\n\n"
)
sys.stdout.write(
f"sudo tee {_UNIT_PATH} >/dev/null <<'UNIT'\n"
f"{unit}"
f"UNIT\n"
f"sudo systemctl daemon-reload\n"
f"sudo systemctl enable --now {netpool.SYSTEMD_UNIT}\n"
)
sys.stderr.write(
f"\n(Or re-run this as root to install it directly: "
f"sudo ./cli.py backend setup --backend=firecracker)\n"
)
def teardown() -> int:
slots = netpool.all_slots()
sys.stderr.write(
f"Undo the Firecracker network pool ({len(slots)} slots, base "
f"{netpool.ip_base()}) — a privileged operation.\n\n"
)
if _is_nixos():
sys.stderr.write(
"On NixOS: set `services.bot-bottle-firecracker.enable = false;` "
"(or drop the module import) and `nixos-rebuild switch`. The TAP "
"netdevs and nft table are removed declaratively.\n\n"
"To tear down imperatively before a rebuild (does not persist):\n\n"
)
sys.stdout.write("sudo ./scripts/firecracker-netpool.sh down\n")
return 0
if _has_systemd():
if os.geteuid() == 0:
subprocess.run(
["systemctl", "disable", "--now", netpool.SYSTEMD_UNIT],
check=False,
)
_UNIT_PATH.unlink(missing_ok=True)
subprocess.run(["systemctl", "daemon-reload"], check=False)
sys.stderr.write(
f"Stopped, disabled, and removed {netpool.SYSTEMD_UNIT}.\n"
)
else:
sys.stderr.write("Remove the persistent unit (one copy-paste):\n\n")
sys.stdout.write(
f"sudo systemctl disable --now {netpool.SYSTEMD_UNIT}\n"
f"sudo rm -f {_UNIT_PATH}\n"
f"sudo systemctl daemon-reload\n"
)
return 0
sys.stderr.write("Run the teardown as root:\n\n")
sys.stdout.write("sudo ./scripts/firecracker-netpool.sh down\n")
return 0
def status() -> int:
# Readiness == what the launch preflight hard-requires: the TAP pool
# present (unprivileged, authoritative) and no range overlap. Listing
# the nft table usually needs root, so — like the preflight — an
# unconfirmable table is reported but NOT treated as not-ready; the
# post-boot isolation probe is the authoritative check. This keeps an
# unprivileged `backend status` usable as a launch gate.
ok = True
missing = netpool.missing_taps()
total = netpool.pool_size()
if missing:
sys.stderr.write(f"TAP pool: {total - len(missing)}/{total} present "
f"(missing: {', '.join(missing)})\n")
ok = False
else:
sys.stderr.write(f"TAP pool: {total}/{total} present\n")
if shutil.which("nft") is None:
sys.stderr.write(f"nft table inet {netpool.NFT_TABLE}: unverified "
f"(nft not on PATH; enforced + checked post-boot)\n")
elif netpool.nft_table_present():
sys.stderr.write(f"nft table inet {netpool.NFT_TABLE}: present\n")
else:
sys.stderr.write(f"nft table inet {netpool.NFT_TABLE}: not confirmable "
f"unprivileged (listing needs root; verified post-boot)\n")
conflicts = netpool.overlapping_routes()
if conflicts:
detail = ", ".join(f"{c.dst} dev {c.dev}" for c in conflicts)
sys.stderr.write(f"range overlap: base {netpool.ip_base()} CLASHES "
f"with {detail}\n")
ok = False
else:
sys.stderr.write(f"range overlap: none (base {netpool.ip_base()})\n")
_report_persistence()
if not ok:
sys.stderr.write("\nRun: ./cli.py backend setup --backend=firecracker\n")
return 0 if ok else 1
def _report_persistence() -> None:
"""Report whether the pool is installed as the persistent systemd
unit (so it survives reboot) vs brought up imperatively. Advisory —
doesn't affect launch readiness."""
if not _has_systemd():
return
state = subprocess.run(
["systemctl", "is-active", netpool.SYSTEMD_UNIT],
capture_output=True, text=True, check=False,
).stdout.strip() or "unknown"
if state == "active":
sys.stderr.write(f"persistence: {netpool.SYSTEMD_UNIT} active "
f"(survives reboot)\n")
else:
sys.stderr.write(f"persistence: {netpool.SYSTEMD_UNIT} {state} — pool "
f"is not installed as a persistent unit (install with "
f"`backend setup` so it survives reboot)\n")
-323
View File
@@ -1,323 +0,0 @@
"""Host-side primitives for the Firecracker backend.
Covers the pieces that don't need root at launch time: locating the
firecracker binary / guest kernel / injected dropbear, the fail-closed
preflight (KVM + kernel + isolation table + TAP pool must all be
present before a VM boots), the rootless rootfs pipeline
(`docker export` -> `mke2fs -d`, no mount), and per-bottle SSH key
generation.
The privileged network setup (TAP pool + nft table) is a one-time
operator step — see `netpool.py`, `scripts/firecracker-netpool.sh`,
and `./cli.py backend setup --backend=firecracker`.
"""
from __future__ import annotations
import os
import platform
import shutil
import subprocess
from pathlib import Path
from ...log import die, info, warn
from . import netpool
# Guest agent images are Debian-family with USER node; the VM is
# reached over SSH as root (init drops the pubkey into both root's and
# node's authorized_keys) and commands `runuser` down to node.
GUEST_SSH_USER = "root"
# `/dev/kvm` must exist and be openable by the invoking user.
_KVM_DEVICE = "/dev/kvm"
def cache_dir() -> Path:
d = Path(
os.environ.get(
"BOT_BOTTLE_FC_CACHE",
str(Path.home() / ".cache" / "bot-bottle" / "firecracker"),
)
)
d.mkdir(parents=True, exist_ok=True)
return d
def kernel_path() -> Path:
return Path(os.environ.get("BOT_BOTTLE_FC_KERNEL", str(cache_dir() / "vmlinux")))
def dropbear_path() -> Path:
"""The static dropbear injected into every guest rootfs as its SSH
server. Must be statically linked — the guest has none of the
host's shared libraries."""
return Path(
os.environ.get("BOT_BOTTLE_FC_DROPBEAR", str(cache_dir() / "dropbear"))
)
# --- availability + preflight ---------------------------------------
def is_linux() -> bool:
return platform.system() == "Linux"
def is_host_capable() -> bool:
"""Whether this host *could* run firecracker — Linux with KVM —
regardless of whether the `firecracker` binary is installed. Used
for default-backend selection so a KVM Linux host that hasn't
installed firecracker yet still selects it and gets an install
pointer at launch (see `require_firecracker`), rather than silently
falling back to docker."""
return is_linux() and os.path.exists(_KVM_DEVICE)
def is_available() -> bool:
"""Cheap capability probe used by cross-backend enumeration —
firecracker on PATH, on Linux, with KVM. Does not check the
(operator-provisioned) kernel / pool, so an available-but-unset
host still shows up and gets an actionable error at launch."""
return is_host_capable() and shutil.which("firecracker") is not None
def require_firecracker() -> None:
"""Fail-closed preflight. Every check that gates the security
boundary (the isolation table, the TAP pool) errors rather than
booting a VM without it."""
if not is_linux():
die("firecracker backend is only supported on Linux (KVM). "
"On macOS use --backend=macos-container.")
if shutil.which("firecracker") is None:
info("Firecracker is required but was not found on PATH.")
info("Install: https://github.com/firecracker-microvm/firecracker/releases")
die("firecracker not found on PATH")
_require_kvm()
if not kernel_path().is_file():
die(f"guest kernel not found at {kernel_path()}. Set "
"BOT_BOTTLE_FC_KERNEL or place a vmlinux there.")
if not dropbear_path().is_file():
die(f"static dropbear not found at {dropbear_path()}. Set "
"BOT_BOTTLE_FC_DROPBEAR or cache one there.")
if shutil.which("mke2fs") is None:
die("mke2fs (e2fsprogs) not found — required to build guest rootfs")
_require_network_pool()
def _require_kvm() -> None:
if not os.path.exists(_KVM_DEVICE):
die(f"{_KVM_DEVICE} is missing. Enable KVM (load kvm-intel/kvm-amd; "
"confirm virtualization is on in firmware).")
if not os.access(_KVM_DEVICE, os.R_OK | os.W_OK):
die(f"{_KVM_DEVICE} exists but is not accessible. Add your user to "
"the `kvm` group and re-login.")
def _require_network_pool() -> None:
"""Fail-closed on the parts we can check unprivileged; defer the
rest to the post-boot isolation probe.
The TAP pool is verified here (`ip link show` is unprivileged). The
nft table can only be *confirmed present* here when `nft` is
queryable — which usually needs root — so a missing/absent nft is
not treated as fatal at this stage: the authoritative check is the
empirical isolation probe run after boot, before the agent starts
(see isolation_probe.verify_isolation). What we must never do is
boot without the TAP pool."""
conflicts = netpool.overlapping_routes()
if conflicts:
detail = "; ".join(f"{c.dst} dev {c.dev}" for c in conflicts)
warn(f"Firecracker pool range ({netpool.ip_base()}, "
f"{netpool.pool_size()} slots) overlaps existing routes: "
f"{detail}. This can shadow or be shadowed by that route; "
f"set BOT_BOTTLE_FC_IP_BASE to a free range and re-run "
f"./cli.py backend setup --backend=firecracker.")
missing = netpool.missing_taps()
if missing:
die(f"network pool incomplete — missing TAP devices: "
f"{', '.join(missing)}.\n ./cli.py backend setup --backend=firecracker")
if shutil.which("nft") is not None and not netpool.nft_table_present():
# nft is queryable and says the table is absent — that's a
# definite, catchable misconfiguration; fail early.
warn(f"isolation table `inet {netpool.NFT_TABLE}` not found via nft. "
"If this is a permissions issue it will be re-checked "
"empirically after boot; otherwise run: "
"./cli.py backend setup --backend=firecracker")
# --- rootfs pipeline (rootless) -------------------------------------
def docker_image_id(ref: str) -> str:
"""The image's content digest, used as the rootfs cache key."""
result = subprocess.run(
["docker", "image", "inspect", "--format", "{{.Id}}", ref],
capture_output=True, text=True, check=False,
)
if result.returncode != 0 or not result.stdout.strip():
die(f"docker image inspect for {ref!r} failed: "
f"{(result.stderr or '').strip() or '<no output>'}")
return result.stdout.strip().replace("sha256:", "")[:16]
def build_base_rootfs_dir(image_ref: str) -> Path:
"""Export the agent image's filesystem and inject the guest init +
static dropbear. Cached by image digest — the per-bottle bits
(authorized_keys, IP) are passed at boot via the kernel cmdline, so
this tree carries nothing bottle-specific and is safely shared.
Returns the prepared directory (read as the `mke2fs -d` source)."""
digest = docker_image_id(image_ref)
base = cache_dir() / "rootfs" / digest
ready = base / ".bb-ready"
if ready.is_file():
return base
if base.exists():
shutil.rmtree(base, ignore_errors=True)
base.mkdir(parents=True)
info(f"exporting {image_ref} rootfs -> {base}")
cid = subprocess.run(
["docker", "create", image_ref, "sleep", "infinity"],
capture_output=True, text=True, check=False,
)
if cid.returncode != 0 or not cid.stdout.strip():
die(f"docker create {image_ref!r} failed: {cid.stderr.strip()}")
container = cid.stdout.strip()
try:
export = subprocess.Popen(
["docker", "export", container], stdout=subprocess.PIPE,
)
untar = subprocess.run(
["tar", "-x", "-C", str(base)], stdin=export.stdout, check=False,
)
export.wait()
if export.returncode != 0 or untar.returncode != 0:
die(f"exporting rootfs for {image_ref!r} failed")
finally:
subprocess.run(
["docker", "rm", "-f", container],
stdout=subprocess.DEVNULL, stderr=subprocess.DEVNULL, check=False,
)
_inject_guest_boot(base)
ready.write_text("ok\n")
return base
def _inject_guest_boot(rootfs: Path) -> None:
"""Drop the static dropbear and the PID-1 init into the rootfs."""
shutil.copy2(dropbear_path(), rootfs / "bb-dropbear")
os.chmod(rootfs / "bb-dropbear", 0o755)
init = rootfs / "bb-init"
init.write_text(_GUEST_INIT)
os.chmod(init, 0o755)
def build_rootfs_ext4(base_dir: Path, out_path: Path, *, slack_mib: int = 1024) -> None:
"""Build a fresh, writable ext4 for one bottle from the cached base
dir. Rootless: `mke2fs -d` populates the image from a directory
without mounting. Each call produces an independent disk, so the
shared base dir stays untouched and concurrent bottles don't race."""
used_mib = _dir_size_mib(base_dir)
size_mib = used_mib + slack_mib
out_path.parent.mkdir(parents=True, exist_ok=True)
result = subprocess.run(
["mke2fs", "-q", "-t", "ext4", "-d", str(base_dir), "-F",
str(out_path), f"{size_mib}M"],
capture_output=True, text=True, check=False,
)
if result.returncode != 0:
die(f"mke2fs for {out_path} failed: {result.stderr.strip()}")
def _dir_size_mib(path: Path) -> int:
result = subprocess.run(
["du", "-sm", str(path)], capture_output=True, text=True, check=False,
)
try:
return int(result.stdout.split()[0])
except (ValueError, IndexError):
return 2048
# --- per-bottle SSH keys --------------------------------------------
def generate_keypair(dest_dir: Path) -> tuple[Path, str]:
"""Mint a per-bottle ed25519 keypair. Returns (private_key_path,
public_key_line). The public line is injected into the guest via
the boot cmdline; the private key authenticates host->guest SSH."""
dest_dir.mkdir(parents=True, exist_ok=True)
key = dest_dir / "bottle_id_ed25519"
if key.exists():
key.unlink()
(dest_dir / "bottle_id_ed25519.pub").unlink(missing_ok=True)
subprocess.run(
["ssh-keygen", "-t", "ed25519", "-N", "", "-q", "-f", str(key),
"-C", "bot-bottle-firecracker"],
check=True,
)
pub = (dest_dir / "bottle_id_ed25519.pub").read_text().strip()
return key, pub
def ssh_base_argv(private_key: Path, guest_ip: str) -> list[str]:
"""Common SSH options for host->guest control. The VM is ephemeral
and per-bottle, so host-key TOFU is meaningless — pin no known_hosts
and skip the check rather than accumulate churn."""
return [
"ssh",
"-i", str(private_key),
# Only offer the per-bottle key — don't let an agent or the
# operator's ~/.ssh/config inject other identities (newer
# OpenSSH otherwise may not reliably present the -i key).
"-o", "IdentitiesOnly=yes",
"-o", "StrictHostKeyChecking=no",
"-o", "UserKnownHostsFile=/dev/null",
"-o", "LogLevel=ERROR",
"-o", "ConnectTimeout=5",
f"{GUEST_SSH_USER}@{guest_ip}",
]
# PID-1 init injected into every guest. Kept dependency-light: relies
# only on coreutils + a POSIX shell (present in the Debian-family agent
# images). The kernel `ip=` cmdline configures eth0 before init runs,
# so no iproute2 is needed. The per-bottle SSH pubkey arrives base64 on
# the cmdline; dropbear generates ephemeral host keys with -R.
_GUEST_INIT = r"""#!/bin/sh
# bot-bottle Firecracker guest init (PID 1).
mount -t proc proc /proc 2>/dev/null
mount -t sysfs sys /sys 2>/dev/null
mount -t devtmpfs dev /dev 2>/dev/null
mkdir -p /dev/pts && mount -t devpts devpts /dev/pts 2>/dev/null
mount -o remount,rw / 2>/dev/null
# Install the per-bottle SSH pubkey from the kernel cmdline.
KEY=$(sed -n 's/.*bb_pubkey=\([^ ]*\).*/\1/p' /proc/cmdline | base64 -d 2>/dev/null)
if [ -n "$KEY" ]; then
for home in /root /home/node; do
mkdir -p "$home/.ssh"
printf '%s\n' "$KEY" > "$home/.ssh/authorized_keys"
chmod 700 "$home/.ssh"
chmod 600 "$home/.ssh/authorized_keys"
done
chown -R node:node /home/node/.ssh 2>/dev/null || true
fi
# The rootless rootfs build (`docker export | tar` as a non-root user)
# can't preserve uid 0, so every path lands owned by the build uid,
# which maps to `node` (uid 1000) in-guest — including /root. dropbear
# (like OpenSSH) refuses root's authorized_keys unless the home dir is
# owned by root, so restore root's ownership of its own home.
chown -R 0:0 /root 2>/dev/null || true
mkdir -p /etc/dropbear /run
# -R: generate host keys on demand. -E: log auth failures to stderr,
# captured in the host-side console.log for debugging.
/bb-dropbear -R -E -p 22 &
# Reap zombies as PID 1. dropbear is always a child, so `wait` blocks
# rather than busy-looping.
while : ; do wait ; done
"""
-100
View File
@@ -1,100 +0,0 @@
"""Freezer — snapshot a running bottle to a resumable artifact.
Follows the same pattern as BottleBackend: a shared base class with
common post-freeze steps (write committed-image path, mark preserved,
print resume hint) and backend-specific subclasses in their respective
backend directories.
Entry points:
Freezer.commit(agent) — freeze by ActiveAgent
Freezer.commit_slug(slug) — convenience wrapper for cmd_commit
get_freezer(backend_name) — factory
"""
from __future__ import annotations
from abc import ABC, abstractmethod
from . import ActiveAgent
from ..bottle_state import mark_preserved, write_committed_image
from ..log import die, info
class CommitCancelled(Exception):
"""Raised by Freezer._freeze when the user declines a confirmation prompt."""
class Freezer(ABC):
"""Freezes a running bottle to a resumable artifact.
The base class owns the shared post-commit steps:
- write_committed_image — records the artifact path in per-bottle state
- mark_preserved — prevents teardown from removing the state dir
- resume hint — printed to stderr after the snapshot
Subclasses implement _freeze with the backend-specific snapshot
operation and optionally override _export_hint for migration hints.
"""
backend_name: str
def commit(self, agent: ActiveAgent) -> None:
"""Freeze the bottle for `agent` to a resumable artifact.
Calls _freeze for the backend-specific snapshot, then writes the
committed image reference to per-bottle state and marks the bottle
preserved so the next `./cli.py resume` boots from the snapshot.
Raises CommitCancelled if the user declines an interactive
confirmation prompt (e.g. the macos-container stop prompt).
"""
image_ref = self._freeze(agent)
write_committed_image(agent.slug, image_ref)
mark_preserved(agent.slug)
info(f"to resume from this snapshot: ./cli.py resume {agent.slug}")
self._export_hint(agent.slug, image_ref)
@abstractmethod
def _freeze(self, agent: ActiveAgent) -> str:
"""Backend-specific snapshot. Returns the image tag or artifact path
stored by write_committed_image. Raises CommitCancelled if the user
declines a stop-confirmation prompt."""
def _export_hint(self, slug: str, image_ref: str) -> None:
"""Optionally print an export-for-migration hint after committing.
Overridden by backends that provide a meaningful export command."""
def commit_slug(self, slug: str) -> None:
"""Convenience entry for cmd_commit when only a slug is available."""
from ..bottle_state import read_metadata
metadata = read_metadata(slug)
agent = ActiveAgent(
backend_name=self.backend_name,
slug=slug,
agent_name=metadata.agent_name if metadata else "",
started_at=metadata.started_at if metadata else "",
services=(),
)
self.commit(agent)
def get_freezer(backend_name: str) -> Freezer:
"""Return the Freezer for the named backend.
backend_name "" is treated as "docker" for backward compatibility
with state dirs written before the backend field was added."""
resolved = backend_name or "docker"
if resolved == "docker":
from .docker.freezer import DockerFreezer
return DockerFreezer()
if resolved == "macos-container":
from .macos_container.freezer import MacosContainerFreezer
return MacosContainerFreezer()
if resolved == "firecracker":
from .firecracker.freezer import FirecrackerFreezer
return FirecrackerFreezer()
die(
f"commit is only supported for docker, macos-container, and "
f"firecracker; backend {backend_name!r} has no freezer"
)
raise AssertionError("unreachable")
@@ -1,10 +0,0 @@
"""macOS Apple Container backend.
Selectable via `BOT_BOTTLE_BACKEND=macos-container`. This package owns
the Apple `container` CLI integration; launch remains gated until the
sidecar network enforcement shape is implemented.
"""
from .backend import MacosContainerBottleBackend
__all__ = ["MacosContainerBottleBackend"]
@@ -1,102 +0,0 @@
"""MacosContainerBottleBackend — Apple Container implementation."""
from __future__ import annotations
from contextlib import contextmanager
from pathlib import Path
from typing import Generator, Sequence
from ...agent_provider import AgentProvisionPlan
from ...egress import EgressPlan
from ...env import ResolvedEnv
from ...git_gate import GitGatePlan
from ...supervise import SupervisePlan
from ...manifest import Manifest
from .. import ActiveAgent, BottleBackend, BottleSpec
from . import cleanup as _cleanup
from . import enumerate as _enumerate
from . import launch as _launch
from . import resolve_plan as _resolve_plan
from . import util as _container
from .bottle import MacosContainerBottle
from .bottle_cleanup_plan import MacosContainerBottleCleanupPlan
from .bottle_plan import MacosContainerBottlePlan
class MacosContainerBottleBackend(
BottleBackend["MacosContainerBottlePlan", "MacosContainerBottleCleanupPlan"]
):
"""Apple Container backend. Selected by
`BOT_BOTTLE_BACKEND=macos-container` or
`--backend=macos-container`."""
name = "macos-container"
@classmethod
def is_available(cls) -> bool:
return _container.is_available()
@classmethod
def setup(cls) -> int:
from . import setup as _setup
return _setup.setup()
@classmethod
def status(cls) -> int:
from . import setup as _setup
return _setup.status()
@classmethod
def teardown(cls) -> int:
from . import setup as _setup
return _setup.teardown()
def _preflight(self) -> None:
_resolve_plan.preflight()
def _build_guest_env(self, resolved_env: ResolvedEnv) -> dict[str, str]:
return _resolve_plan.build_guest_env(resolved_env)
def _resolve_plan(
self,
spec: BottleSpec,
*,
manifest: Manifest,
slug: str,
resolved_env: ResolvedEnv,
agent_provision_plan: AgentProvisionPlan,
egress_plan: EgressPlan,
git_gate_plan: GitGatePlan,
supervise_plan: SupervisePlan | None,
stage_dir: Path,
) -> MacosContainerBottlePlan:
return _resolve_plan.resolve_plan(
spec,
manifest=manifest,
slug=slug,
resolved_env=resolved_env,
agent_provision_plan=agent_provision_plan,
egress_plan=egress_plan,
supervise_plan=supervise_plan,
git_gate_plan=git_gate_plan,
stage_dir=stage_dir,
)
@contextmanager
def launch(
self, plan: MacosContainerBottlePlan
) -> Generator[MacosContainerBottle, None, None]:
with _launch.launch(plan, provision=self.provision) as bottle:
yield bottle
def prepare_cleanup(self) -> MacosContainerBottleCleanupPlan:
return _cleanup.prepare_cleanup()
def cleanup(self, plan: MacosContainerBottleCleanupPlan) -> None:
_cleanup.cleanup(plan)
def enumerate_active(self) -> Sequence[ActiveAgent]:
return _enumerate.enumerate_active()
def supervise_mcp_url(self, plan: MacosContainerBottlePlan) -> str:
return plan.agent_supervise_url
@@ -1,131 +0,0 @@
"""Bottle handle for Apple's `container` CLI."""
from __future__ import annotations
import os
import subprocess
import sys
from typing import Callable, cast
from ...agent_provider import PromptMode, prompt_args
from .. import Bottle, ExecResult
from ..terminal import exec_shell_script
from . import pty_forward as _pty_forward
_PTY_FORWARD_SCRIPT = _pty_forward.__file__
_TERMINAL_ENV_NAMES = (
"TERM",
"COLORTERM",
"TERM_PROGRAM",
"TERM_PROGRAM_VERSION",
"KITTY_WINDOW_ID",
"KITTY_PID",
"WEZTERM_PANE",
"WEZTERM_UNIX_SOCKET",
"GHOSTTY_BIN_DIR",
"GHOSTTY_RESOURCES_DIR",
"ITERM_SESSION_ID",
"VTE_VERSION",
"KONSOLE_VERSION",
"ALACRITTY_WINDOW_ID",
)
def _terminal_env_names() -> tuple[str, ...]:
return tuple(
name for name in _TERMINAL_ENV_NAMES
if name == "TERM" or os.environ.get(name)
)
class MacosContainerBottle(Bottle):
def __init__(
self,
container: str,
teardown: Callable[[], None],
prompt_path_in_container: str | None,
*,
agent_command: str = "claude",
agent_prompt_mode: PromptMode = "append_file",
agent_provider_template: str = "claude",
terminal_title: str = "",
terminal_color: str = "",
agent_workdir: str = "/home/node",
):
self.name = container
self._teardown = teardown
self.prompt_path = prompt_path_in_container
self._agent_prompt_mode = agent_prompt_mode
self.agent_command = agent_command
self.terminal_title = terminal_title
self.terminal_color = terminal_color
self.agent_provider_template = agent_provider_template
self.agent_workdir = agent_workdir
self._closed = False
def agent_argv(self, argv: list[str], *, tty: bool = True) -> list[str]:
full_argv = list(argv)
full_argv.extend(
prompt_args(
cast(PromptMode, self._agent_prompt_mode),
self.prompt_path,
argv=full_argv,
)
)
container_exec = ["container", "exec"]
if tty:
container_exec.extend(["--interactive", "--tty"])
# Forward terminal capability hints so TUIs can enable modified-key
# protocols. Use bare env names: values stay in the child env, not
# on argv, and pty_forward supplies a TERM fallback when needed.
for name in _terminal_env_names():
container_exec.extend(["--env", name])
if self.agent_workdir and self.agent_workdir != "/home/node":
container_exec.extend(["--workdir", self.agent_workdir])
container_exec.extend([self.name, self.agent_command, *full_argv])
if tty:
# Wrap with the raw-mode forwarder: container exec does not put
# the host terminal into raw mode itself, so the line discipline
# buffers modifier-key sequences until CR. The wrapper sets raw
# mode before exec and restores it on exit.
return [sys.executable, _PTY_FORWARD_SCRIPT, "--", *container_exec]
return container_exec
def exec_agent(self, argv: list[str], *, tty: bool = True) -> int:
agent_argv = self.agent_argv(argv, tty=tty)
script = (
exec_shell_script(agent_argv, self.terminal_title, self.terminal_color)
if tty else None
)
if script is None:
return subprocess.run(agent_argv, check=False).returncode
return subprocess.run(["sh", "-lc", script], check=False).returncode
def exec(self, script: str, *, user: str = "node") -> ExecResult:
result = subprocess.run(
["container", "exec", "--user", user, "--interactive",
self.name, "sh", "-s"],
input=script,
capture_output=True,
text=True,
check=False,
)
return ExecResult(
returncode=result.returncode,
stdout=result.stdout,
stderr=result.stderr,
)
def cp_in(self, host_path: str, container_path: str) -> None:
subprocess.run(
["container", "cp", host_path, f"{self.name}:{container_path}"],
stdout=subprocess.DEVNULL,
check=True,
)
def close(self) -> None:
if self._closed:
return
self._closed = True
self._teardown()
@@ -1,27 +0,0 @@
"""Cleanup plan for the macOS Apple Container backend."""
from __future__ import annotations
from dataclasses import dataclass
from ...log import info
from .. import BottleCleanupPlan
@dataclass(frozen=True)
class MacosContainerBottleCleanupPlan(BottleCleanupPlan):
containers: tuple[str, ...] = ()
networks: tuple[str, ...] = ()
def print(self) -> None:
if not self.containers and not self.networks:
info("macos-container cleanup: nothing to remove")
return
for name in self.containers:
info(f"macos-container container: {name}")
for name in self.networks:
info(f"macos-container network: {name}")
@property
def empty(self) -> bool:
return not self.containers and not self.networks
@@ -1,58 +0,0 @@
"""Plan type for the macOS Apple Container backend."""
from __future__ import annotations
from dataclasses import dataclass, field
from pathlib import Path
from ...agent_provider import PromptMode
from .. import BottlePlan
@dataclass(frozen=True)
class MacosContainerBottlePlan(BottlePlan):
slug: str
forwarded_env: dict[str, str] = field(repr=False)
agent_proxy_url: str = ""
agent_git_gate_url: str = ""
agent_supervise_url: str = ""
@property
def container_name(self) -> str:
return self.agent_provision.instance_name
@property
def image(self) -> str:
return self.agent_provision.image
@property
def dockerfile_path(self) -> str:
return self.agent_provision.dockerfile
@property
def prompt_file(self) -> Path:
return self.agent_provision.prompt_file
@property
def agent_command(self) -> str:
return self.agent_provision.command
@property
def agent_prompt_mode(self) -> PromptMode:
return self.agent_provision.prompt_mode
@property
def agent_provider_template(self) -> str:
return self.agent_provision.template
@property
def git_gate_insteadof_host(self) -> str:
if self.agent_git_gate_url.startswith("http://"):
return self.agent_git_gate_url.removeprefix("http://").rstrip("/")
return super().git_gate_insteadof_host
@property
def git_gate_insteadof_scheme(self) -> str:
if self.agent_git_gate_url.startswith("http://"):
return "http"
return super().git_gate_insteadof_scheme
@@ -1,70 +0,0 @@
"""Cleanup for the macOS Apple Container backend."""
from __future__ import annotations
import subprocess
from ...log import info, warn
from . import util as container_mod
from .bottle_cleanup_plan import MacosContainerBottleCleanupPlan
_PREFIX = "bot-bottle-"
_BUNDLE_PREFIX = "bot-bottle-sidecars-"
def _list_prefixed_containers() -> list[str]:
result = subprocess.run(
["container", "list", "--all", "--quiet"],
capture_output=True,
text=True,
check=False,
)
if result.returncode != 0:
warn(f"container list failed: {result.stderr.strip()}")
return []
return sorted(
name for name in (line.strip() for line in result.stdout.splitlines())
if name.startswith(_PREFIX) or name.startswith(_BUNDLE_PREFIX)
)
def _list_prefixed_networks() -> list[str]:
result = subprocess.run(
["container", "network", "list", "--quiet"],
capture_output=True,
text=True,
check=False,
)
if result.returncode != 0:
return []
return sorted(
name for name in (line.strip() for line in result.stdout.splitlines())
if name.startswith(_PREFIX)
)
def prepare_cleanup() -> MacosContainerBottleCleanupPlan:
container_mod.require_container()
return MacosContainerBottleCleanupPlan(
containers=tuple(_list_prefixed_containers()),
networks=tuple(_list_prefixed_networks()),
)
def cleanup(plan: MacosContainerBottleCleanupPlan) -> None:
for name in plan.containers:
info(f"container delete --force {name}")
subprocess.run(
["container", "delete", "--force", name],
stdout=subprocess.DEVNULL,
stderr=subprocess.DEVNULL,
check=False,
)
for name in plan.networks:
info(f"container network delete {name}")
subprocess.run(
["container", "network", "delete", name],
stdout=subprocess.DEVNULL,
stderr=subprocess.DEVNULL,
check=False,
)
@@ -1,39 +0,0 @@
"""Host-side egress apply for the macos-container backend.
Uses `container kill --signal HUP` (Apple Container framework) instead
of `docker kill` to signal the sidecar bundle.
"""
from __future__ import annotations
import os
import subprocess
from ...log import warn
from ..egress_apply import EgressApplicator, EgressApplyError
from .launch import sidecar_container_name
class MacOSContainerEgressApplicator(EgressApplicator):
def _signal_bundle_reload(self, slug: str) -> None:
container = sidecar_container_name(slug)
result = subprocess.run(
["container", "kill", "--signal", "HUP", container],
capture_output=True, text=True, check=False, env=os.environ,
)
if result.returncode != 0:
last_error = (result.stderr or "").strip() or (result.stdout or "").strip()
warn(
f"egress: routes updated on disk for {slug}, but bundle reload failed: "
f"{last_error or 'container kill failed'}"
)
raise EgressApplyError(
f"could not reload egress bundle {container}: "
f"{last_error or 'container kill failed'}"
)
applicator = MacOSContainerEgressApplicator()
__all__ = ["MacOSContainerEgressApplicator", "EgressApplyError", "applicator"]
@@ -1,40 +0,0 @@
"""Active-agent enumeration for the macOS Apple Container backend."""
from __future__ import annotations
import subprocess
from ...bottle_state import read_metadata
from .. import ActiveAgent
_PREFIX = "bot-bottle-"
_SIDECAR_PREFIX = "bot-bottle-sidecars-"
def enumerate_active() -> list[ActiveAgent]:
result = subprocess.run(
["container", "list", "--quiet"],
capture_output=True,
text=True,
check=False,
)
if result.returncode != 0:
return []
out: list[ActiveAgent] = []
for name in sorted(line.strip() for line in result.stdout.splitlines()):
if not name.startswith(_PREFIX):
continue
if name.startswith(_SIDECAR_PREFIX):
continue
slug = name[len(_PREFIX):]
metadata = read_metadata(slug)
out.append(ActiveAgent(
backend_name="macos-container",
slug=slug,
agent_name=metadata.agent_name if metadata else "?",
started_at=metadata.started_at if metadata else "",
services=(),
label=metadata.label if metadata else "",
color=metadata.color if metadata else "",
))
return out
@@ -1,31 +0,0 @@
"""MacosContainerFreezer — snapshot a macOS container bottle.
Apple Container removes containers when they stop, making stop-then-export
impossible. Instead, commit_container execs into the running container and
streams the root filesystem via tar. The bottle continues running after commit.
"""
from __future__ import annotations
from .. import ActiveAgent
from ..freeze import Freezer
from .util import commit_container
from ...log import info
class MacosContainerFreezer(Freezer):
"""Freezes a macOS-container bottle via exec-tar + image rebuild."""
backend_name = "macos-container"
def _freeze(self, agent: ActiveAgent) -> str:
container = f"bot-bottle-{agent.slug}"
image_tag = f"bot-bottle-committed-{agent.slug}:latest"
commit_container(container, image_tag)
return image_tag
def _export_hint(self, slug: str, image_ref: str) -> None:
info(
f"to export for migration: "
f"container image save {image_ref} -o {slug}.tar"
)
@@ -1,458 +0,0 @@
"""Launch flow for the macOS Apple Container backend.
This backend keeps the explicit proxy-env enforcement model for v1:
the agent container is attached only to a host-only Apple Container
network, while the sidecar bundle is attached to a NAT network first
and the host-only network second. The sidecar's host-only IP is
discovered from `container inspect` and stamped into the agent's
HTTP_PROXY / HTTPS_PROXY env vars.
"""
from __future__ import annotations
import dataclasses
import os
import subprocess
from contextlib import ExitStack, contextmanager
from pathlib import Path
from typing import Callable, Generator
from ...bottle_state import (
egress_state_dir,
git_gate_state_dir,
read_committed_image,
)
from ...egress import (
EGRESS_ROUTES_IN_CONTAINER,
egress_agent_env_entries,
egress_resolve_token_values,
egress_sidecar_env_entries,
)
from ...git_gate import (
provision_git_gate_dynamic_keys,
revoke_git_gate_provisioned_keys,
)
from ...log import die, info, warn
from ...supervise import DB_PATH_IN_CONTAINER, SUPERVISE_PORT
from ...util import expand_tilde
from ..docker.egress import EGRESS_CA_IN_CONTAINER, EGRESS_PORT
from ..docker.git_gate import (
GIT_GATE_ACCESS_HOOK_IN_CONTAINER,
GIT_GATE_CREDS_DIR_IN_CONTAINER,
GIT_GATE_ENTRYPOINT_IN_CONTAINER,
GIT_GATE_HOOK_IN_CONTAINER,
)
from ..docker.sidecar_bundle import (
SIDECAR_BUNDLE_DOCKERFILE,
SIDECAR_BUNDLE_IMAGE,
)
from ..docker.egress import egress_tls_init
from ..util import AGENT_CA_BUNDLE, AGENT_CA_PATH
from . import util as container_mod
from .bottle import MacosContainerBottle
from .bottle_plan import MacosContainerBottlePlan
_REPO_DIR = str(Path(__file__).resolve().parent.parent.parent.parent)
_AGENT_SLEEP_SECONDS = "2147483647"
_GIT_HTTP_PORT = 9420
_GIT_GATE_READY_FILE = "/run/git-gate/ready"
def internal_network_name(slug: str) -> str:
return f"bot-bottle-net-{slug}"
def egress_network_name(slug: str) -> str:
return f"bot-bottle-egress-{slug}"
def sidecar_container_name(slug: str) -> str:
return f"bot-bottle-sidecars-{slug}"
@contextmanager
def launch(
plan: MacosContainerBottlePlan,
*,
provision: Callable[[MacosContainerBottlePlan, "MacosContainerBottle"], str | None],
) -> Generator[MacosContainerBottle, None, None]:
"""Build, run, provision, and yield an Apple Container bottle."""
stack = ExitStack()
bottle_for_revoke = plan.manifest.bottle
git_gate_dir_for_revoke = git_gate_state_dir(plan.slug)
def teardown() -> None:
teardown_exc: BaseException | None = None
try:
stack.close()
except BaseException as exc: # noqa: W0718 - teardown must continue
teardown_exc = exc
warn(f"macos-container teardown failed: {exc!r}")
revoke_git_gate_provisioned_keys(bottle_for_revoke, git_gate_dir_for_revoke)
if teardown_exc is not None:
raise teardown_exc
try:
plan = _mint_certs(plan)
plan = _build_images(plan)
internal_network = internal_network_name(plan.slug)
egress_network = egress_network_name(plan.slug)
_create_networks(internal_network, egress_network, stack)
plan = _provision_git_gate_keys(plan)
sidecar_name = sidecar_container_name(plan.slug)
container_mod.force_remove_container(sidecar_name)
_start_sidecar_bundle(plan, sidecar_name, internal_network, egress_network)
stack.callback(container_mod.force_remove_container, sidecar_name)
_stage_git_gate(plan, sidecar_name)
sidecar_ip = container_mod.container_ipv4_on_network(
sidecar_name, internal_network,
)
plan = _stamp_agent_urls(plan, sidecar_ip)
container_mod.force_remove_container(plan.container_name)
_start_agent(plan, internal_network, sidecar_ip)
stack.callback(container_mod.force_remove_container, plan.container_name)
bottle = MacosContainerBottle(
plan.container_name,
teardown,
None,
agent_command=plan.agent_command,
agent_prompt_mode=plan.agent_prompt_mode,
agent_provider_template=plan.agent_provider_template,
terminal_title=f"{plan.spec.label} ({plan.spec.agent_name})" if plan.spec.label else plan.spec.agent_name,
terminal_color=plan.spec.color,
agent_workdir=plan.workspace_plan.workdir,
)
bottle.prompt_path = provision(plan, bottle)
yield bottle
finally:
teardown()
def _mint_certs(plan: MacosContainerBottlePlan) -> MacosContainerBottlePlan:
egress_ca_host, egress_ca_cert_only = egress_tls_init(
egress_state_dir(plan.slug),
)
egress_plan = dataclasses.replace(
plan.egress_plan,
mitmproxy_ca_host_path=egress_ca_host,
mitmproxy_ca_cert_only_host_path=egress_ca_cert_only,
)
return dataclasses.replace(plan, egress_plan=egress_plan)
def _build_images(plan: MacosContainerBottlePlan) -> MacosContainerBottlePlan:
container_mod.build_image(
SIDECAR_BUNDLE_IMAGE,
_REPO_DIR,
dockerfile=SIDECAR_BUNDLE_DOCKERFILE,
)
committed = read_committed_image(plan.slug)
if committed and container_mod.image_exists(committed):
info(f"using committed image {committed!r}")
return dataclasses.replace(
plan,
agent_provision=dataclasses.replace(
plan.agent_provision,
image=committed,
),
)
container_mod.build_image(
plan.image,
_REPO_DIR,
dockerfile=plan.dockerfile_path,
)
return plan
def _create_networks(
internal_network: str,
egress_network: str,
stack: ExitStack,
) -> None:
container_mod.create_network(internal_network, internal=True)
stack.callback(container_mod.remove_network, internal_network)
container_mod.create_network(egress_network)
stack.callback(container_mod.remove_network, egress_network)
def _start_sidecar_bundle(
plan: MacosContainerBottlePlan,
sidecar_name: str,
internal_network: str,
egress_network: str,
) -> None:
argv = _sidecar_run_argv(plan, sidecar_name, internal_network, egress_network)
effective_env = {**dict(os.environ), **plan.agent_provision.provisioned_env}
token_values = egress_resolve_token_values(
plan.egress_plan.token_env_map, effective_env,
)
env = {**os.environ, **token_values}
info(f"container run sidecar bundle {sidecar_name}")
result = subprocess.run(
argv, capture_output=True, text=True, env=env, check=False,
)
if result.returncode != 0:
die(
f"container run for sidecar bundle {sidecar_name} failed: "
f"{(result.stderr or '').strip() or '<no stderr>'}"
)
def _start_agent(
plan: MacosContainerBottlePlan,
internal_network: str,
sidecar_ip: str,
) -> None:
argv = _agent_run_argv(plan, internal_network, sidecar_ip)
env = {
**os.environ,
**plan.forwarded_env,
}
info(f"container run agent {plan.container_name}")
result = subprocess.run(
argv, capture_output=True, text=True, env=env, check=False,
)
if result.returncode != 0:
die(
f"container run for agent {plan.container_name} failed: "
f"{(result.stderr or '').strip() or '<no stderr>'}"
)
def _stamp_agent_urls(
plan: MacosContainerBottlePlan,
sidecar_ip: str,
) -> MacosContainerBottlePlan:
proxy_url = f"http://{sidecar_ip}:{EGRESS_PORT}"
supervise_url = ""
if plan.supervise_plan is not None:
supervise_url = f"http://{sidecar_ip}:{SUPERVISE_PORT}/"
git_gate_url = ""
if plan.git_gate_plan.upstreams:
git_gate_url = f"http://{sidecar_ip}:{_GIT_HTTP_PORT}"
return dataclasses.replace(
plan,
agent_proxy_url=proxy_url,
agent_git_gate_url=git_gate_url,
agent_supervise_url=supervise_url,
)
def _provision_git_gate_keys(
plan: MacosContainerBottlePlan,
) -> MacosContainerBottlePlan:
if not plan.git_gate_plan.upstreams:
return plan
git_gate_plan = provision_git_gate_dynamic_keys(
plan.manifest.bottle,
plan.git_gate_plan,
git_gate_state_dir(plan.slug),
)
return dataclasses.replace(plan, git_gate_plan=git_gate_plan)
def _stage_git_gate(plan: MacosContainerBottlePlan, sidecar_name: str) -> None:
gp = plan.git_gate_plan
if not gp.upstreams:
return
container_mod.exec_container(
sidecar_name,
[
"mkdir",
"-p",
str(Path(GIT_GATE_HOOK_IN_CONTAINER).parent),
GIT_GATE_CREDS_DIR_IN_CONTAINER,
"/git",
str(Path(_GIT_GATE_READY_FILE).parent),
],
)
for host_path, container_path in _git_gate_files(plan):
container_mod.copy_into_container(
sidecar_name, host_path, container_path,
)
container_mod.exec_container(
sidecar_name,
[
"sh",
"-c",
"chmod 755 "
f"{GIT_GATE_ENTRYPOINT_IN_CONTAINER} "
f"{GIT_GATE_HOOK_IN_CONTAINER} "
f"{GIT_GATE_ACCESS_HOOK_IN_CONTAINER} && "
f"chmod 600 {GIT_GATE_CREDS_DIR_IN_CONTAINER}/* && "
f"touch {_GIT_GATE_READY_FILE}",
],
)
def _git_gate_files(
plan: MacosContainerBottlePlan,
) -> tuple[tuple[str, str], ...]:
gp = plan.git_gate_plan
files: list[tuple[str, str]] = [
(str(gp.entrypoint_script), GIT_GATE_ENTRYPOINT_IN_CONTAINER),
(str(gp.hook_script), GIT_GATE_HOOK_IN_CONTAINER),
(str(gp.access_hook_script), GIT_GATE_ACCESS_HOOK_IN_CONTAINER),
]
for upstream in gp.upstreams:
files.append((
expand_tilde(upstream.identity_file),
f"{GIT_GATE_CREDS_DIR_IN_CONTAINER}/{upstream.name}-key",
))
if upstream.known_hosts_file:
files.append((
str(upstream.known_hosts_file),
f"{GIT_GATE_CREDS_DIR_IN_CONTAINER}/{upstream.name}-known_hosts",
))
return tuple(files)
def _sidecar_run_argv(
plan: MacosContainerBottlePlan,
sidecar_name: str,
internal_network: str,
egress_network: str,
) -> list[str]:
argv = [
"container", "run",
"--name", sidecar_name,
"--detach",
"--rm",
"--network", egress_network,
"--network", internal_network,
"--dns", _sidecar_dns(),
"--env", f"BOT_BOTTLE_SIDECAR_DAEMONS={','.join(_sidecar_daemons(plan))}",
]
for entry in _sidecar_env_entries(plan):
argv += ["--env", entry]
for host_path, container_path, read_only in _sidecar_mounts(plan):
argv += ["--mount", _mount_spec(host_path, container_path, read_only)]
argv.append(SIDECAR_BUNDLE_IMAGE)
return argv
def _agent_run_argv(
plan: MacosContainerBottlePlan,
internal_network: str,
sidecar_ip: str,
) -> list[str]:
argv = [
"container", "run",
"--name", plan.container_name,
"--detach",
"--network", internal_network,
]
for entry in _agent_env_entries(plan, sidecar_ip):
argv += ["--env", entry]
argv += [plan.image, "sleep", _AGENT_SLEEP_SECONDS]
return argv
def _sidecar_dns() -> str:
return container_mod.dns_server()
def _sidecar_daemons(plan: MacosContainerBottlePlan) -> tuple[str, ...]:
daemons = ["egress"]
if plan.git_gate_plan.upstreams:
daemons += ["git-gate", "git-http"]
if plan.supervise_plan is not None:
daemons.append("supervise")
return tuple(daemons)
def _sidecar_env_entries(plan: MacosContainerBottlePlan) -> tuple[str, ...]:
env: list[str] = list(egress_sidecar_env_entries(plan.egress_plan))
if plan.git_gate_plan.upstreams:
env.append(f"BOT_BOTTLE_GIT_GATE_READY_FILE={_GIT_GATE_READY_FILE}")
if plan.supervise_plan is not None:
env += [
f"SUPERVISE_BOTTLE_SLUG={plan.slug}",
f"SUPERVISE_DB_PATH={DB_PATH_IN_CONTAINER}",
f"SUPERVISE_PORT={SUPERVISE_PORT}",
]
return tuple(env)
def _sidecar_mounts(
plan: MacosContainerBottlePlan,
) -> tuple[tuple[str, str, bool], ...]:
mounts: list[tuple[str, str, bool]] = []
ep = plan.egress_plan
mounts.append((
str(ep.mitmproxy_ca_host_path.parent),
str(Path(EGRESS_CA_IN_CONTAINER).parent),
False,
))
if ep.routes:
mounts.append((
str(ep.routes_path.parent),
str(Path(EGRESS_ROUTES_IN_CONTAINER).parent),
True,
))
sp = plan.supervise_plan
if sp is not None:
# `container run --mount type=bind` only accepts directory
# sources (a file source fails with "is not a directory") —
# mount db_path's dedicated parent dir instead of the file
# itself, same as the CA/routes mounts above.
mounts.append((
str(sp.db_path.parent),
str(Path(DB_PATH_IN_CONTAINER).parent),
False,
))
return tuple(mounts)
def _mount_spec(host_path: str, container_path: str, read_only: bool) -> str:
spec = f"type=bind,source={host_path},target={container_path}"
if read_only:
spec += ",readonly"
return spec
def _agent_env_entries(
plan: MacosContainerBottlePlan,
sidecar_ip: str,
) -> tuple[str, ...]:
proxy_url = f"http://{sidecar_ip}:{EGRESS_PORT}"
no_proxy = _agent_no_proxy(plan, sidecar_ip)
env = [
f"HTTPS_PROXY={proxy_url}",
f"HTTP_PROXY={proxy_url}",
f"https_proxy={proxy_url}",
f"http_proxy={proxy_url}",
f"NO_PROXY={no_proxy}",
f"no_proxy={no_proxy}",
f"NODE_EXTRA_CA_CERTS={AGENT_CA_PATH}",
f"SSL_CERT_FILE={AGENT_CA_BUNDLE}",
f"REQUESTS_CA_BUNDLE={AGENT_CA_BUNDLE}",
]
if plan.agent_git_gate_url:
env.append(f"GIT_GATE_URL={plan.agent_git_gate_url}")
if plan.agent_supervise_url:
env.append(f"MCP_SUPERVISE_URL={plan.agent_supervise_url}")
for name, value in sorted(plan.agent_provision.guest_env.items()):
env.append(f"{name}={value}")
for name in sorted(plan.forwarded_env.keys()):
env.append(name)
env.extend(egress_agent_env_entries(plan.egress_plan))
return tuple(env)
def _agent_no_proxy(plan: MacosContainerBottlePlan, sidecar_ip: str) -> str:
hosts = ["localhost", "127.0.0.1", sidecar_ip]
return ",".join(hosts)
@@ -1,70 +0,0 @@
"""Host-side raw-mode wrapper for `container exec --interactive --tty`.
Apple's `container exec --interactive --tty` does not set the host terminal to
raw mode before starting its I/O relay. Without raw mode the kernel line
discipline buffers modifier-key escape sequences (e.g. Shift+Enter in
modifyOtherKeys mode produces \\x1b[13;2~) until a carriage-return arrives, so
they never reach Claude Code inside the container.
This module sets the host terminal to raw mode, spawns the inner argv (the
container exec command), and restores the original terminal attributes on
exit. When stdin is not a TTY (piped invocations, CI) it falls through to a
bare subprocess.run so callers do not need to special-case non-interactive
contexts.
Usage (the `--` separator is the API contract — everything after it is the
inner command):
python pty_forward.py -- container exec --interactive --tty <name> <cmd>
"""
from __future__ import annotations
import os
import subprocess
import sys
import termios
import tty
def _inner_env() -> dict[str, str]:
env = dict(os.environ)
env.setdefault("TERM", "xterm-256color")
return env
def _run_inner(inner: list[str]) -> int:
return subprocess.run(inner, check=False, env=_inner_env()).returncode
def main(argv: list[str]) -> int:
"""Entry point. ``argv`` shape: ``-- <inner-argv...>``."""
if len(argv) < 2 or argv[0] != "--":
sys.stderr.write(
"usage: python pty_forward.py -- <container-exec-argv...>\n"
)
return 2
inner = argv[1:]
try:
fd = sys.stdin.fileno()
except OSError:
return _run_inner(inner)
if not os.isatty(fd):
return _run_inner(inner)
try:
old = termios.tcgetattr(fd)
except termios.error:
return _run_inner(inner)
try:
tty.setraw(fd)
return _run_inner(inner)
finally:
termios.tcsetattr(fd, termios.TCSADRAIN, old)
if __name__ == "__main__":
sys.exit(main(sys.argv[1:]))
@@ -1,47 +0,0 @@
"""Prepare step for the macOS Apple Container backend."""
from __future__ import annotations
from pathlib import Path
from ...agent_provider import AgentProvisionPlan
from ...egress import EgressPlan
from ...env import ResolvedEnv
from ...git_gate import GitGatePlan
from ...supervise import SupervisePlan
from ...manifest import Manifest
from .. import BottleSpec
from . import util as container_mod
from .bottle_plan import MacosContainerBottlePlan
def preflight() -> None:
container_mod.require_container()
def build_guest_env(resolved_env: ResolvedEnv) -> dict[str, str]:
return dict(resolved_env.literals)
def resolve_plan(
spec: BottleSpec,
manifest: Manifest,
slug: str,
resolved_env: ResolvedEnv,
agent_provision_plan: AgentProvisionPlan,
egress_plan: EgressPlan,
supervise_plan: SupervisePlan | None,
git_gate_plan: GitGatePlan,
stage_dir: Path,
) -> MacosContainerBottlePlan:
return MacosContainerBottlePlan(
spec=spec,
manifest=manifest,
stage_dir=stage_dir,
slug=slug,
forwarded_env=dict(resolved_env.forwarded),
git_gate_plan=git_gate_plan,
egress_plan=egress_plan,
supervise_plan=supervise_plan,
agent_provision=agent_provision_plan,
)
@@ -1,79 +0,0 @@
"""Host setup + status for the macOS Apple Container backend.
Like Docker, this backend needs no privileged network-pool provisioning
— it wants Apple's `container` CLI installed and its system service
running. `setup()` points at the install/`container system start` steps;
`status()` reports readiness. Reached via
`MacosContainerBottleBackend.setup` / `.status`, dispatched from the
generic `./cli.py backend {setup,status}`.
"""
from __future__ import annotations
import shutil
import subprocess
import sys
from . import util as _container
def _service_running() -> bool:
if shutil.which("container") is None:
return False
return subprocess.run(
["container", "system", "status"],
stdout=subprocess.DEVNULL, stderr=subprocess.DEVNULL, check=False,
).returncode == 0
def setup() -> int:
if not _container.is_macos():
sys.stderr.write("macos-container backend requires macOS.\n")
return 1
if shutil.which("container") is None:
sys.stderr.write("Apple Container is required but was not found on PATH.\n")
sys.stderr.write("Install: https://github.com/apple/container/releases\n")
return 1
if not _service_running():
sys.stderr.write(
"Apple Container is installed but its system service isn't "
"running. Start it with: container system start\n"
)
return 1
sys.stderr.write(
"macos-container backend: ready — no privileged host setup required.\n"
)
return 0
def teardown() -> int:
sys.stderr.write(
"macos-container backend: nothing to undo — it provisions no "
"privileged host state. The Apple Container CLI and its system "
"service are left as-is (stop the service yourself with "
"`container system stop` if you want).\n"
)
return 0
def status() -> int:
ok = True
if _container.is_macos():
sys.stderr.write("host: macOS\n")
else:
sys.stderr.write("host: NOT macOS (backend unsupported here)\n")
ok = False
if shutil.which("container") is not None:
sys.stderr.write("container CLI on PATH: yes\n")
else:
sys.stderr.write("container CLI on PATH: NO\n")
ok = False
if ok:
sys.stderr.write(
f"container system service: {'running' if _service_running() else 'NOT running'}\n"
)
if not _service_running():
ok = False
if not ok:
sys.stderr.write("\nRun: ./cli.py backend setup --backend=macos-container\n")
return 0 if ok else 1
-471
View File
@@ -1,471 +0,0 @@
"""Host-side primitives for Apple's `container` CLI."""
from __future__ import annotations
import json
import os
import ipaddress
import platform
import shutil
import subprocess
import tempfile
import time
from typing import Iterable
from ...log import die, info
_CONTAINER = "container"
_DEFAULT_DNS = "1.1.1.1"
def is_macos() -> bool:
return platform.system() == "Darwin"
def is_available() -> bool:
return is_macos() and shutil.which(_CONTAINER) is not None
def require_container() -> None:
"""Fail with an install pointer if Apple Container is unavailable."""
if not is_macos():
info("BOT_BOTTLE_BACKEND=macos-container requires macOS.")
die("macos-container backend is only supported on macOS")
if shutil.which(_CONTAINER) is None:
info("Apple Container is required but was not found on PATH.")
info("Install: https://github.com/apple/container/releases")
die("container not found")
_require_container_service()
def _require_container_service() -> None:
result = subprocess.run(
[_CONTAINER, "system", "status"],
stdout=subprocess.DEVNULL,
stderr=subprocess.DEVNULL,
check=False,
)
if result.returncode != 0:
info("Apple Container system service is not running.")
info("Start it with: container system start")
die("container system service not running")
def dns_server() -> str:
override = os.environ.get("BOT_BOTTLE_MACOS_CONTAINER_DNS", "").strip()
if override:
return override
return _host_ipv4_dns() or _DEFAULT_DNS
def build_image(ref: str, context: str, *, dockerfile: str = "") -> None:
"""Build an OCI image with Apple's BuildKit-backed `container build`."""
info(
f"building image {ref} from {context} with Apple Container "
"(layer cache keeps repeat builds fast)"
)
_ensure_builder_dns()
args = [_CONTAINER, "build", "-t", ref, "--dns", dns_server()]
if dockerfile:
# `container build` resolves -f relative to the current working
# directory, not the build context. Anchor a relative Dockerfile to
# the context so builds work from any cwd.
if not os.path.isabs(dockerfile):
dockerfile = os.path.join(context, dockerfile)
args.extend(["-f", dockerfile])
args.append(context)
subprocess.run(args, check=True)
def commit_container(container_name: str, image_tag: str) -> None:
"""Snapshot a running Apple Container as a local image.
`container export` requires a stopped container, but Apple Container
removes containers when they stop, making stop-then-export impossible.
Instead, exec into the running container as root and stream the root
filesystem out via tar, then build a new image from that archive.
The bottle continues running after commit.
"""
with tempfile.TemporaryDirectory(prefix="bot-bottle-container-commit.") as tmp:
rootfs_tar = os.path.join(tmp, "rootfs.tar")
dockerfile = os.path.join(tmp, "Dockerfile")
with open(rootfs_tar, "wb") as tar_out:
result = subprocess.run(
[
_CONTAINER, "exec",
"--user", "root",
container_name,
"tar", "--create",
"--exclude=./proc",
"--exclude=./sys",
"--exclude=./dev",
"--exclude=./run",
"--file=-",
"--directory=/",
".",
],
stdout=tar_out,
stderr=subprocess.PIPE,
check=False,
)
if result.returncode != 0:
die(
f"container exec tar {container_name!r} failed: "
f"{(result.stderr or b'').decode().strip() or '<no stderr>'}"
)
with open(dockerfile, "w", encoding="utf-8") as f:
f.write(
"FROM scratch\n"
"ADD rootfs.tar /\n"
"USER node\n"
"WORKDIR /home/node\n"
)
build_image(image_tag, tmp, dockerfile=dockerfile)
info(f"committed {container_name!r}{image_tag!r}")
def _ensure_builder_dns() -> None:
dns = dns_server()
status = _builder_status()
override = os.environ.get("BOT_BOTTLE_MACOS_CONTAINER_DNS", "").strip()
if _builder_running(status) and _builder_resolves_build_hosts():
if override and not _builder_has_dns(status, dns):
_restart_builder_with_dns(dns)
return
_restart_builder_with_dns(dns)
def _restart_builder_with_dns(dns: str) -> None:
subprocess.run(
[_CONTAINER, "builder", "stop"],
stdout=subprocess.DEVNULL,
stderr=subprocess.DEVNULL,
check=False,
)
subprocess.run(
[_CONTAINER, "builder", "start", "--dns", dns],
check=True,
)
def _host_ipv4_dns() -> str:
if not is_macos():
return ""
result = subprocess.run(
["scutil", "--dns"],
capture_output=True,
text=True,
check=False,
)
if result.returncode != 0:
return ""
blocks: list[list[str]] = []
current: list[str] = []
for line in result.stdout.splitlines():
if line.startswith("resolver #") and current:
blocks.append(current)
current = []
current.append(line)
if current:
blocks.append(current)
for direct_only in (True, False):
for block in blocks:
text = "\n".join(block)
if direct_only and "Directly Reachable Address" not in text:
continue
for line in block:
if "nameserver[" not in line or ":" not in line:
continue
candidate = line.split(":", 1)[1].strip()
if _usable_ipv4(candidate):
return candidate
return ""
def _usable_ipv4(value: str) -> bool:
try:
address = ipaddress.ip_address(value)
except ValueError:
return False
return (
address.version == 4
and not address.is_loopback
and not address.is_link_local
and not address.is_multicast
and not address.is_unspecified
)
def _builder_status() -> list[dict[str, object]]:
result = subprocess.run(
[_CONTAINER, "builder", "status", "--format", "json"],
capture_output=True,
text=True,
check=False,
)
if result.returncode != 0:
return []
try:
data = json.loads(result.stdout or "[]")
except json.JSONDecodeError:
return []
if isinstance(data, list):
return [entry for entry in data if isinstance(entry, dict)]
if isinstance(data, dict):
return [data]
return []
def _builder_running(status: list[dict[str, object]]) -> bool:
for entry in status:
entry_status = entry.get("status")
if isinstance(entry_status, dict) and entry_status.get("state") == "running":
return True
return False
def _builder_dns_nameservers(status: list[dict[str, object]]) -> list[str]:
out: list[str] = []
for entry in status:
config = entry.get("configuration")
config_dns = config.get("dns") if isinstance(config, dict) else None
nameservers = (
config_dns.get("nameservers")
if isinstance(config_dns, dict)
else None
)
if not isinstance(nameservers, list):
continue
out.extend(name for name in nameservers if isinstance(name, str))
return out
def _builder_has_dns(status: list[dict[str, object]], dns: str) -> bool:
return dns in _builder_dns_nameservers(status)
def _builder_resolves_build_hosts() -> bool:
result = subprocess.run(
[_CONTAINER, "exec", "buildkit", "getent", "hosts", "deb.debian.org"],
stdout=subprocess.DEVNULL,
stderr=subprocess.DEVNULL,
check=False,
)
return result.returncode == 0
def image_exists(ref: str) -> bool:
return _silent_run([_CONTAINER, "image", "inspect", ref]) == 0
def container_exists(name: str) -> bool:
result = subprocess.run(
[_CONTAINER, "list", "--all", "--quiet"],
capture_output=True,
text=True,
check=False,
)
if result.returncode != 0:
return False
return name in {line.strip() for line in result.stdout.splitlines()}
def container_is_running(name: str) -> bool:
"""Return True if the named container is currently running.
`container list` without `--all` lists only running containers."""
result = subprocess.run(
[_CONTAINER, "list", "--quiet"],
capture_output=True,
text=True,
check=False,
)
if result.returncode != 0:
return False
return name in {line.strip() for line in result.stdout.splitlines()}
def stop_container(name: str) -> None:
"""Stop the named container without deleting it."""
result = subprocess.run(
[_CONTAINER, "stop", name],
capture_output=True,
text=True,
check=False,
)
if result.returncode != 0:
die(
f"container stop {name!r} failed: "
f"{(result.stderr or '').strip() or '<no stderr>'}"
)
def force_remove_container(name: str) -> None:
if container_exists(name):
subprocess.run(
[_CONTAINER, "delete", "--force", name],
stdout=subprocess.DEVNULL,
stderr=subprocess.DEVNULL,
check=False,
)
def copy_into_container(name: str, host_path: str, container_path: str) -> None:
cmd = [_CONTAINER, "cp", host_path, f"{name}:{container_path}"]
result = _run_container_op(cmd)
if result.returncode != 0:
die(
f"container cp into {name}:{container_path} failed: "
f"{(result.stderr or '').strip() or '<no stderr>'}"
)
def exec_container(name: str, argv: list[str]) -> None:
result = _run_container_op([_CONTAINER, "exec", name, *argv])
if result.returncode != 0:
die(
f"container exec in {name} failed: "
f"{(result.stderr or '').strip() or '<no stderr>'}"
)
def _run_container_op(cmd: list[str]) -> subprocess.CompletedProcess[str]:
result = subprocess.run(
cmd,
capture_output=True,
text=True,
check=False,
)
for _ in range(19):
if result.returncode == 0:
return result
time.sleep(0.1)
result = subprocess.run(
cmd,
capture_output=True,
text=True,
check=False,
)
return result
def create_network(name: str, *, internal: bool = False) -> None:
args = [
_CONTAINER, "network", "create",
"--label", "bot-bottle.backend=macos-container",
]
if internal:
args.append("--internal")
args.append(name)
result = subprocess.run(
args, capture_output=True, text=True, check=False,
)
if result.returncode == 0:
return
if "already exists" in (result.stderr or "").lower():
return
die(
f"container network create {name} failed: "
f"{(result.stderr or '').strip() or '<no stderr>'}"
)
def remove_network(name: str) -> None:
result = subprocess.run(
[_CONTAINER, "network", "delete", name],
stdout=subprocess.DEVNULL,
stderr=subprocess.DEVNULL,
check=False,
)
if result.returncode != 0:
return
def inspect_container(name: str) -> dict[str, object]:
result = subprocess.run(
[_CONTAINER, "inspect", name],
capture_output=True,
text=True,
check=False,
)
if result.returncode != 0:
die(
f"container inspect {name} failed: "
f"{(result.stderr or '').strip() or '<no stderr>'}"
)
try:
data = json.loads(result.stdout or "[]")
except json.JSONDecodeError as exc:
die(f"container inspect {name} returned malformed JSON: {exc}")
if isinstance(data, list) and data and isinstance(data[0], dict):
return data[0]
if isinstance(data, dict):
return data
die(f"container inspect {name} returned an unexpected shape")
raise AssertionError("unreachable")
def container_ipv4_on_network(name: str, network: str) -> str:
data = inspect_container(name)
status = data.get("status")
networks = status.get("networks") if isinstance(status, dict) else None
if not isinstance(networks, list):
die(f"container inspect {name} did not include status.networks")
for entry in networks:
if not isinstance(entry, dict):
continue
if entry.get("network") != network:
continue
raw = entry.get("ipv4Address")
if not isinstance(raw, str) or not raw:
die(f"container {name} has no IPv4 address on {network}")
return raw.split("/", 1)[0]
die(f"container {name} is not attached to network {network}")
raise AssertionError("unreachable")
def image_id(ref: str) -> str:
"""Return the image digest/ID from `container image inspect`.
The command returns JSON on current Apple Container releases. Keep
parsing narrow and fatal so callers do not cache on an empty key.
"""
import json
result = subprocess.run(
[_CONTAINER, "image", "inspect", ref],
capture_output=True,
text=True,
check=False,
)
if result.returncode != 0:
die(
f"container image inspect for {ref!r} failed: "
f"{(result.stderr or '').strip() or '<no stderr>'}"
)
try:
data = json.loads(result.stdout or "{}")
except json.JSONDecodeError as exc:
die(f"container image inspect for {ref!r} returned malformed JSON: {exc}")
if isinstance(data, list) and data:
data = data[0]
if isinstance(data, dict):
value = data.get("id") or data.get("digest") or data.get("ID")
if value:
return str(value)
die(f"container image inspect for {ref!r} did not include an image id")
raise AssertionError("unreachable")
def save(ref: str, output: str) -> None:
subprocess.run([_CONTAINER, "image", "save", ref, "-o", output], check=True)
def _silent_run(cmd: Iterable[str]) -> int:
return subprocess.run(
list(cmd),
stdout=subprocess.DEVNULL,
stderr=subprocess.DEVNULL,
check=False,
).returncode
+4 -3
View File
@@ -1,8 +1,9 @@
"""Shared print helpers for BottlePlan.print implementations.
Lifts the multi-value label printer out of DockerBottlePlan so every
backend (and any future backend) renders the same two-column
scannable preflight without duplicating the indent math."""
Lifts the multi-value label printer out of DockerBottlePlan so the
smolmachines backend (and any future backend) renders the same
two-column scannable preflight without duplicating the indent
math."""
from __future__ import annotations
-132
View File
@@ -1,132 +0,0 @@
"""Shared helpers used across backends' resolve_plan steps.
Each helper owns one well-defined step of the per-bottle plan
resolution so the backends don't repeat the same logic.
Backend-specific steps (container names, env-file, per-bottle
Dockerfile overrides, subnet allocation) stay in the backend's own
resolve_plan.py.
"""
from __future__ import annotations
import os
from dataclasses import replace
from datetime import datetime, timezone
from pathlib import Path
from ..agent_provider import AgentProvisionPlan
from ..bottle_state import (
BottleMetadata,
agent_state_dir,
bottle_identity,
egress_state_dir,
git_gate_state_dir,
supervise_state_dir,
write_metadata,
)
from ..egress import Egress, EgressPlan
from ..git_gate import GitGate, GitGatePlan
from ..manifest import Manifest, ManifestBottle
from ..supervise import Supervise, SupervisePlan
from . import BottleSpec
def mint_slug(spec: BottleSpec) -> str:
"""Return the bottle identity: the recorded identity for a resume,
or a freshly minted one for a new start.
When a label is provided it becomes the full slug (no random suffix),
so two launches with the same label collide by design. When no label
is given the identity is minted with a random suffix to avoid
collisions between anonymous launches of the same agent."""
if spec.identity:
return spec.identity
if spec.label:
from .docker import util as docker_mod
return docker_mod.slugify(spec.label)
return bottle_identity(spec.agent_name)
def write_launch_metadata(
slug: str, spec: BottleSpec, *, compose_project: str, backend: str,
) -> None:
"""Persist launch metadata so `cli.py resume <identity>` can
reconstruct the spec. Idempotent — re-writes on resume with a
refreshed started_at."""
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(),
compose_project=compose_project,
backend=backend,
label=spec.label,
color=spec.color,
bottle_names=spec.bottle_names,
))
def prepare_agent_state_dir(slug: str, manifest: Manifest) -> tuple[Path, Path]:
"""Create the agent state subdir, write the prompt file.
Returns (agent_dir, prompt_file)."""
agent = manifest.agent
agent_dir = agent_state_dir(slug)
agent_dir.mkdir(parents=True, exist_ok=True)
prompt_file = agent_dir / "prompt.txt"
prompt_file.write_text(agent.prompt or "")
prompt_file.chmod(0o600)
return agent_dir, prompt_file
def prepare_git_gate(bottle: ManifestBottle, slug: str) -> GitGatePlan:
git_gate_dir = git_gate_state_dir(slug)
git_gate_dir.mkdir(parents=True, exist_ok=True)
return GitGate().prepare(bottle, slug, git_gate_dir)
def prepare_egress(
bottle: ManifestBottle, slug: str, provision: AgentProvisionPlan,
) -> EgressPlan:
egress_dir = egress_state_dir(slug)
egress_dir.mkdir(parents=True, exist_ok=True)
return Egress().prepare(bottle, slug, egress_dir, provision.egress_routes)
def prepare_supervise(bottle: ManifestBottle, slug: str) -> SupervisePlan | None:
"""Prepare the supervise sidecar state dir. Returns None when
bottle.supervise is falsy."""
if not bottle.supervise:
return None
supervise_dir = supervise_state_dir(slug)
supervise_dir.mkdir(parents=True, exist_ok=True)
return Supervise().prepare(slug, supervise_dir)
def merge_provision_env_vars(provision: AgentProvisionPlan) -> AgentProvisionPlan:
"""Fold provision.env_vars into guest_env (setdefault semantics)
and return a new plan with the merged guest_env."""
merged = dict(provision.guest_env)
for key, val in provision.env_vars.items():
merged.setdefault(key, val)
return replace(provision, guest_env=merged)
def resolve_manifest_dockerfile(path_value: str, spec: BottleSpec) -> str:
"""Resolve a manifest-supplied dockerfile path relative to user_cwd."""
path = Path(os.path.expanduser(path_value))
if not path.is_absolute():
path = Path(spec.user_cwd) / path
return str(path)
__all__ = [
"merge_provision_env_vars",
"mint_slug",
"prepare_agent_state_dir",
"prepare_egress",
"prepare_git_gate",
"prepare_supervise",
"resolve_manifest_dockerfile",
"write_launch_metadata",
]
@@ -0,0 +1,15 @@
"""smolmachines bottle backend (PRD 0023).
Selectable via `BOT_BOTTLE_BACKEND=smolmachines`. Runs each
bottle inside a per-agent microVM (libkrun / Hypervisor.framework
on macOS) with a userspace gvproxy gateway as the egress
primitive. The sidecar bundle (PRD 0024) runs as a host-side
docker container reached only through gvproxy's port-forward list.
Chunk 1 (this commit) ships the backend skeleton + Smolfile +
gvproxy renderers + preflight check. VM lifecycle, sidecar
bringup, and provisioning land in later chunks."""
from .backend import SmolmachinesBottleBackend # noqa: F401
__all__ = ["SmolmachinesBottleBackend"]
@@ -0,0 +1,75 @@
"""SmolmachinesBottleBackend — the smolmachines implementation of
BottleBackend (PRD 0023).
Per PRD 0050 the per-provider provisioning steps (prompt, skills,
the declarative provision-plan apply, supervise MCP registration)
live on the `AgentProvider` plugin under `bot_bottle/contrib/`. The
smolmachines backend only owns the steps that are about backend
infrastructure: CA install (no-op for now), workspace, git copy-in."""
from __future__ import annotations
from contextlib import contextmanager
from pathlib import Path
from typing import Generator, Sequence
from .. import ActiveAgent, Bottle, BottleBackend, BottleSpec
from . import cleanup as _cleanup
from . import enumerate as _enumerate
from . import launch as _launch
from . import prepare as _prepare
from . import smolvm as _smolvm
from .bottle import SmolmachinesBottle
from .bottle_cleanup_plan import SmolmachinesBottleCleanupPlan
from .bottle_plan import SmolmachinesBottlePlan
from .provision import workspace as _workspace
class SmolmachinesBottleBackend(
BottleBackend["SmolmachinesBottlePlan", "SmolmachinesBottleCleanupPlan"]
):
"""smolmachines backend. Selected by
`BOT_BOTTLE_BACKEND=smolmachines`."""
name = "smolmachines"
@classmethod
def is_available(cls) -> bool:
"""`smolvm` on PATH. The backend additionally needs macOS
for libkrun + TSI, but `enumerate_active` / `cleanup` are
host-shell ops that gracefully no-op on Linux too — the
runtime check happens at `prepare`."""
return _smolvm.is_available()
def _resolve_plan(
self, spec: BottleSpec, *, stage_dir: Path
) -> SmolmachinesBottlePlan:
return _prepare.resolve_plan(spec, stage_dir=stage_dir)
@contextmanager
def launch(
self, plan: SmolmachinesBottlePlan
) -> Generator[SmolmachinesBottle, None, None]:
with _launch.launch(plan, provision=self.provision) as bottle:
yield bottle
def provision_workspace(
self, plan: SmolmachinesBottlePlan, bottle: Bottle
) -> None:
_workspace.provision_workspace(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
(`http://<loopback_ip>:<random_port>/`). `agent_supervise_url`
on the plan is "" when the bottle has no sidecar."""
return plan.agent_supervise_url
def prepare_cleanup(self) -> SmolmachinesBottleCleanupPlan:
return _cleanup.prepare_cleanup()
def cleanup(self, plan: SmolmachinesBottleCleanupPlan) -> None:
_cleanup.cleanup(plan)
def enumerate_active(self) -> Sequence[ActiveAgent]:
return _enumerate.enumerate_active()
+183
View File
@@ -0,0 +1,183 @@
"""SmolmachinesBottle — running-instance handle (PRD 0023 chunk 2d).
Routes `exec_agent` / `exec` / `cp_in` through `smolvm machine
exec` / `smolvm machine cp`. The handle is yielded by `launch`
and torn down via the surrounding ExitStack on context exit;
`close` is a no-op idempotent alias so the BottleBackend ABC's
context-manager contract is satisfied.
User context: `smolvm machine exec` runs commands as root in the
VM, but the agent image's USER is `node` and agent CLIs may refuse
to run as root in bypass modes. Both
`exec_agent` and `exec` switch to the requested user (default
`node`) via `runuser -u <user> --` and set `HOME` / `USER`
through `smolvm -e` — avoiding `runuser -l`'s login-shell wiring
(PAM session setup, /etc/profile sourcing) which can hang on a
minimal Debian VM with no PAM session config."""
from __future__ import annotations
import subprocess
import sys
import time
from typing import Mapping, cast
from ...agent_provider import PromptMode, prompt_args
from .. import Bottle, ExecResult
from . import pty_resize as _pty_resize
from . import smolvm as _smolvm
# Absolute path to the pty_resize wrapper. Invoke as
# `python <path>` rather than `python -m <dotted-path>` so the
# wrapper runs regardless of cwd / sys.path — it has no
# bot_bottle.* imports, so it's self-contained.
_PTY_RESIZE_SCRIPT = _pty_resize.__file__
# Per-user env the agent image's USER (node) expects. Some providers
# write session state under the user's home directory;
# bare `runuser -u` inherits root's HOME=/root, which claude
# can't write to. Set HOME / USER explicitly through smolvm -e
# so the child process sees them.
_HOME_FOR = {
"node": "/home/node",
"root": "/root",
}
def _env_assignments_for(user: str, env: Mapping[str, str]) -> list[str]:
home = _HOME_FOR.get(user, f"/home/{user}")
out = [f"HOME={home}", f"USER={user}"]
for k, v in env.items():
out.append(f"{k}={v}")
return out
class SmolmachinesBottle(Bottle):
"""Handle returned by `SmolmachinesBottleBackend.launch`. The
underlying VM lifecycle (create / start / stop / delete) lives
on the launch ExitStack — this class only routes runtime
operations to the right `smolvm machine ...` subcommand."""
def __init__(
self,
machine_name: str,
*,
prompt_path: str | None = None,
guest_env: Mapping[str, str] | None = None,
agent_command: str = "claude",
agent_prompt_mode: PromptMode = "append_file",
) -> None:
self.name = machine_name
# In-VM path to the agent's prompt file. None when the
# agent declared no prompt (file still exists; we just
# don't pass --append-system-prompt-file).
self.prompt_path = prompt_path
# Env vars the agent process needs (HTTPS_PROXY,
# CLAUDE_CODE_OAUTH_TOKEN, manifest-declared bottle env, …).
# Forwarded on every `smolvm machine exec` via `-e K=V`
# because exec doesn't inherit from machine_create's env.
self._guest_env = dict(guest_env or {})
self._agent_prompt_mode = agent_prompt_mode
self.agent_command = agent_command
self.agent_provider_template = (
"codex" if agent_command == "codex" else "claude"
)
def agent_argv(
self, argv: list[str], *, tty: bool = True,
) -> list[str]:
flags = ["smolvm", "machine", "exec", "--name", self.name]
if tty:
flags += ["-i", "-t"]
agent_tail = ["env", *_env_assignments_for("node", self._guest_env),
self.agent_command]
provider_prompt_args = prompt_args(
cast(PromptMode, self._agent_prompt_mode), self.prompt_path, argv=argv,
)
if cast(PromptMode, self._agent_prompt_mode) == "read_prompt_file":
agent_tail += argv
agent_tail += provider_prompt_args
else:
agent_tail += provider_prompt_args
agent_tail += argv
flags += ["--", "runuser", "-u", "node", "--", *agent_tail]
if not tty:
# No PTY allocated — no SIGWINCH to forward, no resize
# bridge needed. Skip the wrapper so non-interactive
# exec paths (e.g., provisioning shell-outs that
# happen to go through this method) stay light.
return flags
return [
sys.executable, _PTY_RESIZE_SCRIPT,
self.name, "--", *flags,
]
def exec_agent(self, argv: list[str], *, tty: bool = True) -> int:
"""Run the selected agent interactively inside the VM as the `node`
user. Inherits the operator's terminal (stdin / stdout /
stderr) so the session feels native. Blocks until the agent
exits; returns the in-VM exit code.
We bypass the captured-output `machine_exec` helper here
because that one wraps stdout/stderr in pipes — fine for
scripted exec, wrong for an interactive shell. Drop down
to `subprocess.run` with the TTY inherited.
UID switches via `runuser -u node --` (not `-l`) so we
avoid login-shell wiring. HOME / USER come from `smolvm
-e` instead, which sets them on the process env."""
return subprocess.run(
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`,
which defaults to the image's USER (also node) — so test
helpers / provision shell-outs run with the same identity
on both backends. Pass `user="root"` for tests that need
root.
`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.
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,
]
r = subprocess.run(
["smolvm", "machine", "exec", "--name", self.name] + argv,
capture_output=True, text=True, check=False,
)
return ExecResult(
returncode=r.returncode,
stdout=r.stdout or "",
stderr=r.stderr or "",
)
def cp_in(self, host_path: str, container_path: str) -> None:
"""Copy a host path into the guest at `container_path`."""
_smolvm.machine_cp(host_path, f"{self.name}:{container_path}")
def close(self) -> None:
# Real teardown lives on the launch ExitStack; this is just
# the idempotent alias the BottleBackend ABC expects.
pass
@@ -0,0 +1,55 @@
"""SmolmachinesBottleCleanupPlan — concrete BottleCleanupPlan (issue #77).
Tracks the resources `SmolmachinesBottleBackend.cleanup` will
remove:
- machines: smolvm machines whose name starts with
`bot-bottle-` (running or stopped). Stopped +
deleted via `smolvm machine stop` + `machine delete -f`.
- bundles: docker containers `bot-bottle-sidecars-<slug>`
left over from a smolmachines bottle (the bundle's
port-forwards stay published on lo0 aliases until
the container is gone). Removed via `docker rm -f`.
- networks: docker networks `bot-bottle-bundle-<slug>`
attached to the bundles. Removed via
`docker network rm`.
Smolmachines state dirs live under the same `~/.bot-bottle/state/`
path the docker backend uses; the docker backend's
`prepare_cleanup` already enumerates orphan state dirs and is the
single source of truth for that bucket (consults
`enumerate_active_bottles()` so it doesn't reap a live
smolmachines bottle's dir)."""
from __future__ import annotations
import sys
from dataclasses import dataclass
from ...log import info
from .. import BottleCleanupPlan
@dataclass(frozen=True)
class SmolmachinesBottleCleanupPlan(BottleCleanupPlan):
"""Resources SmolmachinesBottleBackend.cleanup will remove.
Produced by `prepare_cleanup`; sorted so the y/N output is
stable."""
machines: tuple[str, ...] = ()
bundles: tuple[str, ...] = ()
networks: tuple[str, ...] = ()
@property
def empty(self) -> bool:
return not self.machines and not self.bundles and not self.networks
def print(self) -> None:
print(file=sys.stderr)
for name in self.machines:
info(f"smolvm machine: {name}")
for name in self.bundles:
info(f"bundle container:{name}")
for name in self.networks:
info(f"bundle network: {name}")
print(file=sys.stderr)
@@ -0,0 +1,107 @@
"""SmolmachinesBottlePlan — concrete BottlePlan for the smolmachines
backend (PRD 0023).
Slug + bundle docker subnet / gateway / pinned IP + smolvm
machine name + agent `.smolmachine` artifact + per-bottle guest
env. Provisioning fields (CA cert path, prompt path, etc.) land
in chunk 4."""
from __future__ import annotations
from dataclasses import dataclass
from pathlib import Path
from ...agent_provider import PromptMode
from .. import BottlePlan
@dataclass(frozen=True)
class SmolmachinesBottlePlan(BottlePlan):
"""Resolved fields the launch step needs to bring up the bottle.
Inherits `spec`, `stage_dir`, `git_gate_plan`, `egress_plan`,
`supervise_plan`, and `agent_provision` from BottlePlan."""
slug: str
# Per-bottle docker subnet for the sidecar bundle container.
# The bundle runs at `bundle_ip` (always `.2`); the gateway is
# at `.1`. smolvm's TSI allowlist is set to `bundle_ip/32`.
bundle_subnet: str
bundle_gateway: str
bundle_ip: str
# smolvm machine name + agent image source. machine_create
# boots from a packed `.smolmachine` artifact (pre-baked at
# prepare time via `smolvm pack create`); using `--from`
# instead of `--image` avoids the registry-pull race we hit
# when machine_start tried to fetch on-demand and the libkrun
# agent's network attempt got refused by macOS.
#
# Chunk 2d ships with a public placeholder image (alpine)
# since bot-bottle-claude:latest lives in the operator's local
# docker daemon and smolvm's crane backend can't read from
# there; chunk 4 resolves the agent-image-conversion gap
# (push to a registry first, or smolvm grows a docker-daemon
# transport).
machine_name: str
# Agent image ref (docker tag). `launch` runs the
# build → save → registry push → smolvm pack pipeline against
# this and feeds the resulting `.smolmachine` artifact to
# `machine_create --from`. The pipeline runs at launch time
# (not prepare time) so the docker build output doesn't garble
# the dashboard's preflight modal.
agent_image_ref: str
# In-guest env vars (HTTPS_PROXY etc) — IP-literal URLs since
# the guest has no DNS resolver inside the TSI allowlist.
# Passed to `smolvm machine create` as `-e K=V` flags.
# Smolfile-rendering is gone (smolvm 0.8.0's
# `--smolfile` is mutually exclusive with `--from`, and
# `--from` is the path that avoids the registry-pull race).
guest_env: dict[str, str]
# Path to the agent's prompt file on the host. Always written
# (mode 0o600) so the in-VM path always exists; the file is
# empty when the agent has no prompt — claude-code reads it
# via --append-system-prompt-file only when non-empty.
prompt_file: Path
# Inner Plans for the sidecar bundle daemons. The same shape the
# docker backend uses — same `.prepare()` calls produced
# them — but our launch step doesn't populate the
# docker-specific network fields (internal_network,
# egress_network) because the smolmachines bundle isn't on
# docker's `--internal` + egress bridge topology; it's on a
# per-bottle bridge with a pinned IP. The unused fields stay
# at their dataclass defaults.
# Agent-side endpoints. On Docker Desktop the docker bridge
# IPs aren't reachable from the smolvm guest (TSI uses macOS
# networking; docker container IPs live in the daemon's VM),
# so the agent dials the bundle via host loopback +
# docker-published random ports. Empty at prepare time;
# launch populates these after bundle bringup via
# `dataclasses.replace`. Format: a `host:port` for git-gate
# (insteadOf URL prefix) + full URLs for proxy / supervise.
agent_proxy_url: str = ""
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
@property
def agent_prompt_mode(self) -> PromptMode:
return self.agent_provision.prompt_mode
@property
def agent_provider_template(self) -> str:
return self.agent_provision.template
@property
def agent_dockerfile_path(self) -> str:
return self.agent_provision.dockerfile
+159
View File
@@ -0,0 +1,159 @@
"""Cleanup + active-listing for the smolmachines backend (issue #77).
`prepare_cleanup` enumerates leftover smolmachines resources:
- smolvm machines (`smolvm machine ls --json`) whose name starts
with `bot-bottle-`.
- bundle docker containers (`bot-bottle-sidecars-<slug>`).
- bundle docker networks (`bot-bottle-bundle-<slug>`).
State dirs live under `~/.bot-bottle/state/<identity>/` —
shared layout with the docker backend, which has the single
orphan-state-dir enumerator (it already consults
`enumerate_active_agents()` so a live smolmachines bottle's dir
is preserved).
`cleanup` removes everything in the plan: stop + delete each VM,
force-rm each container, rm each network. Each step is
best-effort — a failure on one resource doesn't block the others."""
from __future__ import annotations
import json
import subprocess
from ...log import info, warn
from . import sidecar_bundle as _bundle
from . import smolvm as _smolvm
from .bottle_cleanup_plan import SmolmachinesBottleCleanupPlan
# Both names start with the same prefix the launcher uses.
_VM_PREFIX = "bot-bottle-"
_BUNDLE_PREFIX = _bundle.bundle_container_name("") # `bot-bottle-sidecars-`
_NETWORK_PREFIX = _bundle.bundle_network_name("") # `bot-bottle-bundle-`
def prepare_cleanup() -> SmolmachinesBottleCleanupPlan:
"""Enumerate every smolmachines-owned resource on the host.
No side effects. Returns an empty plan when smolvm isn't on
PATH (no machines to reap) — `cleanup` is a no-op in that
case too."""
machines = _list_bot_bottle_machines()
bundles = _list_bundle_containers()
networks = _list_bundle_networks()
return SmolmachinesBottleCleanupPlan(
machines=tuple(sorted(machines)),
bundles=tuple(sorted(bundles)),
networks=tuple(sorted(networks)),
)
def cleanup(plan: SmolmachinesBottleCleanupPlan) -> None:
"""Remove everything in the plan. Order matters: stop VMs
first (they hold ports on lo0 aliases via libkrun), then the
bundle containers (which hold the host port-forwards), then
the networks (which docker won't reap until the containers
are gone)."""
for name in plan.machines:
info(f"stopping smolvm machine {name}")
subprocess.run(
["smolvm", "machine", "stop", "--name", name],
stdout=subprocess.DEVNULL, stderr=subprocess.DEVNULL,
check=False,
)
info(f"deleting smolvm machine {name}")
r = subprocess.run(
["smolvm", "machine", "delete", "-f", name],
capture_output=True, text=True, check=False,
)
if r.returncode != 0:
warn(
f"smolvm machine delete -f {name} failed: "
f"{(r.stderr or '').strip()}"
)
for name in plan.bundles:
info(f"removing bundle container {name}")
subprocess.run(
["docker", "rm", "-f", name],
stdout=subprocess.DEVNULL, stderr=subprocess.DEVNULL,
check=False,
)
for name in plan.networks:
info(f"removing bundle network {name}")
r = subprocess.run(
["docker", "network", "rm", name],
capture_output=True, text=True, check=False,
)
if r.returncode != 0 and "no such network" not in (r.stderr or "").lower():
warn(
f"docker network rm {name} failed: "
f"{(r.stderr or '').strip()}"
)
def _list_bot_bottle_machines() -> list[str]:
"""All smolvm machines named `bot-bottle-*`, regardless of
state (running / stopped / created). Empty when smolvm isn't
installed."""
if not _smolvm.is_available():
return []
r = subprocess.run(
["smolvm", "machine", "ls", "--json"],
capture_output=True, text=True, check=False,
)
if r.returncode != 0:
return []
try:
machines = json.loads(r.stdout or "[]")
except json.JSONDecodeError:
return []
return [
m["name"] for m in machines
if isinstance(m, dict)
and m.get("name", "").startswith(_VM_PREFIX)
]
def _list_bundle_containers() -> list[str]:
"""All docker containers named `bot-bottle-sidecars-*`,
running or stopped. Empty when docker isn't installed."""
# Late import: `backend/__init__` imports this module
# transitively via the smolmachines backend.
from .. import has_backend
if not has_backend("docker"):
return []
r = subprocess.run(
["docker", "ps", "-a",
"--filter", f"name=^{_BUNDLE_PREFIX}",
"--format", "{{.Names}}"],
capture_output=True, text=True, check=False,
)
if r.returncode != 0:
return []
return [
line for line in (r.stdout or "").splitlines()
if line and line.startswith(_BUNDLE_PREFIX)
]
def _list_bundle_networks() -> list[str]:
"""All docker networks named `bot-bottle-bundle-*`. Empty
when docker isn't installed."""
from .. import has_backend
if not has_backend("docker"):
return []
r = subprocess.run(
["docker", "network", "ls",
"--filter", f"name={_NETWORK_PREFIX}",
"--format", "{{.Name}}"],
capture_output=True, text=True, check=False,
)
if r.returncode != 0:
return []
return [
line for line in (r.stdout or "").splitlines()
if line and line.startswith(_NETWORK_PREFIX)
]
@@ -0,0 +1,123 @@
"""Active-agent enumeration for the smolmachines backend (PRD
0023 chunk 4 follow-up + issue #77).
Returns a list of `ActiveAgent` records same shape the docker
backend produces so CLI `list active` and the dashboard agents
pane render both backends through one code path.
A smolmachines agent is "active" when its smolvm guest is
running. We cross-reference against the per-bottle sidecar
bundle container to populate the `services` field (which daemons
are up in the bundle); without a bundle we still surface the VM
so the operator can see + clean it up.
The cross-backend caller gates on `has_backend("smolmachines")`
and `has_backend("docker")`, so this module assumes both are
available when called. Both subprocess calls below still
tolerate "command not on PATH" defensively, but the gate is the
intended access pattern."""
from __future__ import annotations
import json
import subprocess
from .. import ActiveAgent
from ..docker.bottle_state import read_metadata
from . import sidecar_bundle as _bundle
# Smolvm VM names produced by prepare are `bot-bottle-<slug>`,
# matching the bundle container name pattern. We use the prefix
# both as a filter and to strip back to the slug.
_VM_NAME_PREFIX = "bot-bottle-"
def enumerate_active() -> list[ActiveAgent]:
"""All currently-running smolmachines-backed agents. Empty
list when no matching VMs are running. Caller is responsible
for gating on `has_backend('smolmachines')` if needed; if
smolvm is missing the `smolvm machine ls` call below returns
nothing silently."""
result = subprocess.run(
["smolvm", "machine", "ls", "--json"],
capture_output=True, text=True, check=False,
)
if result.returncode != 0:
return []
try:
machines = json.loads(result.stdout or "[]")
except json.JSONDecodeError:
return []
services_by_slug = _query_bundle_services()
out: list[ActiveAgent] = []
for m in machines:
name = m.get("name") or ""
state = m.get("state") or ""
if state != "running" or not name.startswith(_VM_NAME_PREFIX):
continue
slug = name[len(_VM_NAME_PREFIX):]
metadata = read_metadata(slug)
out.append(ActiveAgent(
backend_name="smolmachines",
slug=slug,
agent_name=metadata.agent_name if metadata else "?",
started_at=metadata.started_at if metadata else "",
services=services_by_slug.get(slug, ()),
label=metadata.label if metadata else "",
color=metadata.color if metadata else "",
))
return out
def _query_bundle_services() -> dict[str, tuple[str, ...]]:
"""`{slug: ('egress', ...)}` from each running bundle container's
`BOT_BOTTLE_SIDECAR_DAEMONS` env var.
Smolmachines bundles all run the PRD-0024 image with the
same daemon set declared via env, so one inspect per bundle
gets us the picture without exec'ing into the container.
Returns an empty mapping when the docker backend isn't
available the bundle services field on each ActiveAgent
just shows up empty, matching the docker backend's "starting"
state."""
# Late import: `has_backend` lives on the backend package's
# __init__, which imports this module transitively. Pulling
# the name in at call time sidesteps the cycle.
from .. import has_backend
if not has_backend("docker"):
return {}
ps = subprocess.run(
["docker", "ps",
"--filter", "name=" + _bundle.bundle_container_name(""),
"--format", "{{.Names}}"],
capture_output=True, text=True, check=False,
)
if ps.returncode != 0:
return {}
out: dict[str, tuple[str, ...]] = {}
for line in (ps.stdout or "").splitlines():
name = line.strip()
if not name:
continue
slug = name.removeprefix(_bundle.bundle_container_name(""))
if not slug:
continue
inspect = subprocess.run(
["docker", "inspect", name, "--format", "{{json .Config.Env}}"],
capture_output=True, text=True, check=False,
)
if inspect.returncode != 0:
continue
try:
env_list = json.loads(inspect.stdout or "[]")
except json.JSONDecodeError:
continue
for entry in env_list:
key, _, value = entry.partition("=")
if key == "BOT_BOTTLE_SIDECAR_DAEMONS":
out[slug] = tuple(sorted(
d for d in value.split(",") if d
))
break
return out
+428
View File
@@ -0,0 +1,428 @@
"""End-to-end launch flow for the smolmachines backend
(PRD 0023 chunks 2d + 4b).
Brings up the per-bottle docker bridge + sidecar bundle (with
real daemons + their config files), creates + starts the smolvm
guest pointed at the bundle's pinned IP via TSI's
`--allow-cidr <bundle-ip>/32` allowlist, yields a
`SmolmachinesBottle` handle, tears everything down on context
exit.
The bundle's daemons consume the inner Plans the docker backend
already produces: egress reads routes + CAs from the EgressPlan.
Git-gate + supervise plumb through the same plans the docker
backend uses, minus the docker-network fields that don't apply here."""
from __future__ import annotations
import dataclasses
import os
from contextlib import ExitStack, contextmanager
from pathlib import Path
from typing import Callable, Generator
from ...egress import (
EGRESS_ROUTES_IN_CONTAINER,
egress_resolve_token_values,
)
from ...supervise import QUEUE_DIR_IN_CONTAINER, SUPERVISE_PORT
from ...util import expand_tilde
from ..docker import util as docker_mod
from ..docker.egress import (
EGRESS_CA_IN_CONTAINER,
EGRESS_PORT as _EGRESS_PORT,
egress_tls_init,
)
from ..docker.git_gate import (
GIT_GATE_ACCESS_HOOK_IN_CONTAINER,
GIT_GATE_CREDS_DIR_IN_CONTAINER,
GIT_GATE_ENTRYPOINT_IN_CONTAINER,
GIT_GATE_HOOK_IN_CONTAINER,
)
from ...git_gate import revoke_git_gate_provisioned_keys
from ...log import warn
from ..docker.bottle_state import egress_state_dir, git_gate_state_dir
from . import loopback_alias as _loopback
from . import sidecar_bundle as _bundle
from . import smolvm as _smolvm
from .bottle import SmolmachinesBottle
from .bottle_plan import SmolmachinesBottlePlan
from .local_registry import crane_push_tarball, ephemeral_registry
# Repo root, used as the `docker build` context for the agent image.
_REPO_DIR = str(Path(__file__).resolve().parent.parent.parent.parent)
# Per-host cache for `smolvm pack create` outputs. Keyed by the
# docker image ID so a Dockerfile change automatically invalidates
# the cache. `pack create` is idempotent on the smolvm side but
# takes several seconds even on a no-op rebuild.
_SMOLMACHINE_CACHE_DIR = Path.home() / ".cache" / "bot-bottle" / "smolmachines"
# Container-internal listening ports for each bundle daemon. The
# bundle publishes each one on a random host loopback port (see
# `_bundle.start_bundle`), and `_bundle.bundle_host_port` looks
# them up post-start.
_GIT_HTTP_PORT = 9420
_SUPERVISE_PORT = SUPERVISE_PORT
@contextmanager
def launch(
plan: SmolmachinesBottlePlan,
*,
provision: Callable[[SmolmachinesBottlePlan, "SmolmachinesBottle"], str | None],
) -> Generator[SmolmachinesBottle, None, None]:
"""Build + run the bottle and yield a handle; tear everything
down on exit. Errors during bringup unwind any partial state
via the ExitStack."""
stack = ExitStack()
try:
loopback_ip, network = _allocate_resources(plan, stack)
plan = _mint_certs(plan)
plan = _start_bundle(plan, network, loopback_ip, stack)
plan = _discover_urls(plan, loopback_ip)
# Build the agent image and pack it into a `.smolmachine`
# artifact (or hit the per-Dockerfile-digest cache). Runs
# here, not in prepare, so the docker-build output doesn't
# garble the dashboard's preflight modal.
agent_from_path = _ensure_smolmachine(
plan.agent_image_ref,
dockerfile=plan.agent_dockerfile_path,
)
_launch_vm(plan, agent_from_path, loopback_ip, stack)
_init_vm(plan)
bottle = SmolmachinesBottle(
plan.machine_name,
prompt_path=None,
guest_env=plan.guest_env,
agent_command=plan.agent_command,
agent_prompt_mode=plan.agent_prompt_mode,
)
bottle.prompt_path = provision(plan, bottle)
yield bottle
finally:
_teardown_smolmachines(stack, plan)
def _teardown_smolmachines(
stack: ExitStack,
plan: SmolmachinesBottlePlan,
) -> None:
"""Unwind the ExitStack, then revoke any provisioned deploy keys.
ExitStack errors are caught and logged (non-fatal) so that key
revocation always runs. Revocation errors propagate a stranded
deploy key is a security concern the operator must address."""
teardown_exc: BaseException | None = None
try:
stack.close()
except BaseException as exc: # noqa: W0718 — teardown must not fail
teardown_exc = exc
warn(f"smolmachines teardown failed: {exc!r}")
bottle = plan.spec.manifest.bottle_for(plan.spec.agent_name)
revoke_git_gate_provisioned_keys(bottle, git_gate_state_dir(plan.slug))
if teardown_exc is not None:
raise teardown_exc
def _allocate_resources(
plan: SmolmachinesBottlePlan,
stack: ExitStack,
) -> tuple[str, str]:
"""Reserve a loopback alias and create the per-bottle docker bridge.
macOS only routes 127.0.0.1 by default; the per-bottle alias
scopes TSI's allowlist to this bottle's published ports so the
agent can't reach other bottles' or host services' ports on
loopback. No-op on Linux."""
_loopback.ensure_pool()
loopback_ip = _loopback.allocate(plan.slug)
network = _bundle.bundle_network_name(plan.slug)
_bundle.create_bundle_network(network, plan.bundle_subnet, plan.bundle_gateway)
stack.callback(_bundle.remove_bundle_network, network)
return loopback_ip, network
def _mint_certs(plan: SmolmachinesBottlePlan) -> SmolmachinesBottlePlan:
"""Mint the egress MITM CA and return the plan with CA paths filled."""
egress_ca_host, egress_ca_cert_only = egress_tls_init(
egress_state_dir(plan.slug),
)
egress_plan = dataclasses.replace(
plan.egress_plan,
mitmproxy_ca_host_path=egress_ca_host,
mitmproxy_ca_cert_only_host_path=egress_ca_cert_only,
)
return dataclasses.replace(plan, egress_plan=egress_plan)
def _start_bundle(
plan: SmolmachinesBottlePlan,
network: str,
loopback_ip: str,
stack: ExitStack,
) -> SmolmachinesBottlePlan:
"""Build the BundleLaunchSpec, resolve token env, start the
sidecar bundle container, and register teardown."""
bundle_spec = _bundle_launch_spec(plan, network, loopback_ip)
token_env = _resolve_token_env(plan, dict(os.environ))
_bundle.ensure_bundle_image(bundle_spec.image)
_bundle.start_bundle(bundle_spec, env={**os.environ, **token_env})
stack.callback(_bundle.stop_bundle, plan.slug)
return plan
def _discover_urls(
plan: SmolmachinesBottlePlan,
loopback_ip: str,
) -> SmolmachinesBottlePlan:
"""Discover host-side ports for published container ports and
return the plan with URLs + guest_env stamped in.
Docker container IPs (192.168.x.x in the daemon's bridge)
aren't 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.
NO_PROXY includes the per-bottle loopback alias so the
supervise + git-gate URLs bypass HTTPS_PROXY."""
agent_facing_host_port = _bundle.bundle_host_port(
plan.slug, _EGRESS_PORT, host_ip=loopback_ip,
)
agent_proxy_url = f"http://{loopback_ip}:{agent_facing_host_port}"
agent_git_gate_host = ""
if plan.git_gate_plan.upstreams:
git_gate_host_port = _bundle.bundle_host_port(
plan.slug, _GIT_HTTP_PORT, host_ip=loopback_ip,
)
agent_git_gate_host = f"{loopback_ip}:{git_gate_host_port}"
agent_supervise_url = ""
if plan.supervise_plan is not None:
supervise_host_port = _bundle.bundle_host_port(
plan.slug, _SUPERVISE_PORT, host_ip=loopback_ip,
)
agent_supervise_url = f"http://{loopback_ip}:{supervise_host_port}/"
existing_no_proxy = plan.guest_env.get("NO_PROXY", "localhost,127.0.0.1")
guest_env = {
**plan.guest_env,
"HTTPS_PROXY": agent_proxy_url,
"HTTP_PROXY": agent_proxy_url,
"NO_PROXY": f"{existing_no_proxy},{loopback_ip}",
}
if agent_git_gate_host:
guest_env["GIT_GATE_URL"] = f"http://{agent_git_gate_host}"
if agent_supervise_url:
guest_env["MCP_SUPERVISE_URL"] = agent_supervise_url
return dataclasses.replace(
plan,
guest_env=guest_env,
agent_proxy_url=agent_proxy_url,
agent_git_gate_host=agent_git_gate_host,
agent_supervise_url=agent_supervise_url,
)
def _launch_vm(
plan: SmolmachinesBottlePlan,
agent_from_path: Path,
loopback_ip: str,
stack: ExitStack,
) -> None:
"""Create, patch, and start the smolvm VM; register teardown.
--allow-cidr is the per-bottle loopback alias so the guest can
only reach this bottle's bundle ports. force_allowlist patches
smolvm 0.8.0's silent-drop of --allow-cidr when combined with
--from. Smolfile isn't usable here — smolvm 0.8.0 makes --from
and --smolfile mutually exclusive."""
_smolvm.machine_create(
plan.machine_name,
from_path=agent_from_path,
allow_cidrs=[f"{loopback_ip}/32"],
env=plan.guest_env,
)
stack.callback(_smolvm.machine_delete, plan.machine_name)
# Workaround smolvm 0.8.0: `--allow-cidr` is silently dropped
# when combined with `--from`. Patch the persisted state DB
# before start so the booted VM's TSI actually enforces.
_loopback.force_allowlist(plan.machine_name, [f"{loopback_ip}/32"])
_smolvm.machine_start(plan.machine_name)
stack.callback(_smolvm.machine_stop, plan.machine_name)
def _init_vm(plan: SmolmachinesBottlePlan) -> None:
"""Repair filesystem ownership and wait for exec channel readiness.
Ownership repair: smolvm's pack process remaps files to the host
invoker's uid (501 on macOS). /home/node must be node:node so
Claude Code can write ~/.claude.json; /tmp + /var/tmp need root
mode 1777 so non-root processes can create per-uid scratch dirs.
All folded into one sh -c to avoid back-to-back exec calls
immediately after machine_start (libkrun exec-channel race).
wait_exec_ready polls until the exec channel is ready for the
subsequent provision calls, replacing the empirical sleep."""
_smolvm.machine_exec(plan.machine_name, [
"sh", "-c",
"chown -R node:node /home/node && "
"chown root:root /tmp /var/tmp && "
"chmod 1777 /tmp /var/tmp",
])
_smolvm.wait_exec_ready(plan.machine_name)
def _bundle_launch_spec(
plan: SmolmachinesBottlePlan, network: str, loopback_ip: str,
) -> _bundle.BundleLaunchSpec:
"""Build a BundleLaunchSpec from the resolved inner Plans.
Daemons in the CSV:
- egress is always present.
- git-gate + git-http are conditional on plan.git_gate_plan.upstreams.
- supervise is conditional on plan.supervise_plan.
Env + volumes are the union of the sidecar daemons' needs, with
daemon-private values only (HTTPS_PROXY is scoped to the
egress process by egress_entrypoint.sh see PRD 0024's bundle
bind-address PR)."""
daemons: list[str] = ["egress"]
env: list[str] = []
volumes: list[tuple[str, str, bool]] = []
# --- egress -----------------------------------------------
ep = plan.egress_plan
volumes.append((str(ep.mitmproxy_ca_host_path), EGRESS_CA_IN_CONTAINER, True))
if ep.routes:
volumes.append((str(ep.routes_path), EGRESS_ROUTES_IN_CONTAINER, True))
# Bare-name entries for upstream-token slots. Their values
# come from the docker-run subprocess env (inherited from
# the operator's shell), never landing on argv.
for token_env in sorted(ep.token_env_map.keys()):
env.append(token_env)
# --- git-gate ---------------------------------------------
gp = plan.git_gate_plan
if gp.upstreams:
daemons += ["git-gate", "git-http"]
volumes += [
(str(gp.entrypoint_script), GIT_GATE_ENTRYPOINT_IN_CONTAINER, True),
(str(gp.hook_script), GIT_GATE_HOOK_IN_CONTAINER, True),
(str(gp.access_hook_script), GIT_GATE_ACCESS_HOOK_IN_CONTAINER, True),
]
for u in gp.upstreams:
keypath = expand_tilde(u.identity_file)
volumes.append((
keypath,
f"{GIT_GATE_CREDS_DIR_IN_CONTAINER}/{u.name}-key",
True,
))
if u.known_hosts_file:
volumes.append((
str(u.known_hosts_file),
f"{GIT_GATE_CREDS_DIR_IN_CONTAINER}/{u.name}-known_hosts",
True,
))
# --- supervise --------------------------------------------
sp = plan.supervise_plan
if sp is not None:
daemons.append("supervise")
env += [
f"SUPERVISE_BOTTLE_SLUG={plan.slug}",
f"SUPERVISE_QUEUE_DIR={QUEUE_DIR_IN_CONTAINER}",
f"SUPERVISE_PORT={SUPERVISE_PORT}",
]
volumes.append((str(sp.queue_dir), QUEUE_DIR_IN_CONTAINER, False))
# Container ports the agent reaches from the smolvm guest —
# published on host loopback so the guest can dial via TSI +
# macOS networking. Egress is always the agent's HTTP/HTTPS proxy.
ports_to_publish: list[int] = [_EGRESS_PORT]
if gp.upstreams:
ports_to_publish.append(_GIT_HTTP_PORT)
if sp is not None:
ports_to_publish.append(_SUPERVISE_PORT)
return _bundle.BundleLaunchSpec(
slug=plan.slug,
network_name=network,
subnet=plan.bundle_subnet,
gateway=plan.bundle_gateway,
bundle_ip=plan.bundle_ip,
daemons_csv=",".join(daemons),
environment=tuple(env),
volumes=tuple(volumes),
ports_to_publish=tuple(ports_to_publish),
publish_host_ip=loopback_ip,
)
def _resolve_token_env(
plan: SmolmachinesBottlePlan, host_env: dict[str, str],
) -> dict[str, str]:
"""Resolve the egress token env-var values from the host's
environ so they reach the bundle's process env via docker's
`-e NAME` inheritance. Empty when no routes declare auth."""
effective_env = {**host_env, **plan.agent_provision.provisioned_env}
return egress_resolve_token_values(plan.egress_plan.token_env_map, effective_env)
def _ensure_smolmachine(image_ref: str, *, dockerfile: str = "") -> Path:
"""Build the agent docker image and convert it into a
`.smolmachine` artifact, caching the result under
`~/.cache/bot-bottle/smolmachines/` keyed by the docker image
ID (so a Dockerfile change automatically invalidates the cache).
Returns the `.smolmachine.smolmachine` sidecar path that's
the file `machine create --from` consumes (pack create produces
a launcher binary at `.smolmachine` plus the sidecar alongside
it; the sidecar is the actual artifact).
Conversion path: `docker build` (the existing layer cache
makes no-change rebuilds cheap) `docker save` to a tarball
spin up an ephemeral registry on a private docker network
`crane push --insecure` from a one-shot container on the same
network `smolvm pack create --image localhost:<host port>/...`
tear down the registry + network. The crane push detour
sidesteps the Docker-Desktop daemon's HTTPS preference for
non-loopback registries see the `local_registry` module
docstring for the gory details.
Each pack-create costs several seconds even on a hot cache,
so we skip the whole pipeline when the cached sidecar is
already on disk for this image ID."""
_SMOLMACHINE_CACHE_DIR.mkdir(parents=True, exist_ok=True)
docker_mod.build_image(image_ref, _REPO_DIR, dockerfile=dockerfile)
# `sha256:abcd...` -> `abcd...` first 16 chars: short enough to
# keep filenames manageable, long enough to make collisions
# astronomically unlikely.
digest = docker_mod.image_id(image_ref).split(":", 1)[-1][:16]
binary = _SMOLMACHINE_CACHE_DIR / f"{digest}.smolmachine"
sidecar = _SMOLMACHINE_CACHE_DIR / f"{digest}.smolmachine.smolmachine"
if sidecar.is_file():
return sidecar
tarball = _SMOLMACHINE_CACHE_DIR / f"{digest}.image.tar"
docker_mod.save(image_ref, str(tarball))
try:
with ephemeral_registry() as handle:
push_ref = f"{handle.push_endpoint}/bot-bottle:{digest}"
pack_ref = f"{handle.pull_endpoint}/bot-bottle:{digest}"
crane_push_tarball(handle, str(tarball), push_ref)
_smolvm.pack_create(pack_ref, binary)
finally:
# Tarball is ~500MB-1GB for the agent image; reclaim once
# the smolmachine artifact exists. The artifact itself is
# the long-lived cache entry.
tarball.unlink(missing_ok=True)
return sidecar
@@ -0,0 +1,236 @@
"""Ephemeral local OCI registry for the smolmachines agent-image
conversion path (PRD 0023 chunk 4c).
`smolvm pack create --image <ref>` only accepts OCI registry refs
it can't read the local docker daemon's image cache, an OCI
layout directory, or a `docker save` tarball. To convert the
agent's Dockerfile-built image into a `.smolmachine` artifact we
spin up a short-lived `registry:2.8.3` container alongside a
`crane` helper container on a private docker network, push via
`crane push --insecure <tarball> <registry-container>:5000/...`,
and let smolvm pull from the registry's published host port. The
network + both containers are torn down after the pack completes.
Why this two-container dance instead of plain `docker push`:
- Docker Desktop's daemon runs in its own Linux VM, so its
`localhost` is not the host's loopback. A registry bound to
the host's 127.0.0.1 is unreachable from the daemon side.
- `host.docker.internal` is reachable from the daemon but isn't
in Docker's default insecure-registries CIDRs (only `::1/128`
and `127.0.0.0/8` are), so `docker push` to it tries HTTPS,
hits a plain-HTTP registry, and dies with
`http: server gave HTTP response to HTTPS client`. Adding
`host.docker.internal` to daemon.json works but is a one-time
manual step the user has to do in Docker Desktop's UI.
- Going through a docker network sidesteps the host-vs-daemon
loopback mismatch (crane and registry containers see each
other on the network) AND the HTTPS preference (crane has an
`--insecure` flag that forces plain HTTP).
The registry is also published on a random host port so smolvm
a host process can pull from `localhost:<port>` via Docker's
port-forward. smolvm's bundled crane auto-falls-back to HTTP for
localhost addresses, so no insecure-registries config is needed
on that side either."""
from __future__ import annotations
import os
import socket
import subprocess
import time
import uuid
from contextlib import contextmanager
from dataclasses import dataclass
from typing import Generator
from ...log import die
# registry:2.8.3, pinned by digest. Same env-override pattern as the
# sidecar image pin in bot_bottle/backend/docker/sidecar_bundle.py.
REGISTRY_IMAGE = os.environ.get(
"BOT_BOTTLE_REGISTRY_IMAGE",
"registry@sha256:a3d8aaa63ed8681a604f1dea0aa03f100d5895b6a58ace528858a7b332415373",
)
# gcr.io/go-containerregistry/crane:latest, pinned by digest. ~10MB,
# stable upstream from Google; we only invoke `crane push --insecure`
# against a localhost-equivalent registry, so the trust surface is
# narrow.
CRANE_IMAGE = os.environ.get(
"BOT_BOTTLE_CRANE_IMAGE",
(
"gcr.io/go-containerregistry/crane@sha256:"
"0ae17ecb34315aa7cbff28f6eddee3b7adae0b2f90101260d990804db1eb0084"
),
)
# Internal port the registry binds to inside its container — fixed
# by the registry:2 image. The host-side mapping is random.
_REGISTRY_CONTAINER_PORT = "5000"
# How long to wait for the registry's HTTP layer to bind before
# giving up. Two seconds is empirically enough; 10s leaves headroom
# for slow CI runners without making the failure mode chatty.
_READY_TIMEOUT_S = 10.0
@dataclass(frozen=True)
class RegistryHandle:
"""Everything callers need to push to + pull from the ephemeral
registry.
`network` is the per-session docker network a `crane push`
container has to join it to reach the registry by name.
`push_endpoint` is the `<host>:<port>` form to embed in image
refs given to the crane push container (resolves via docker
network DNS). `pull_endpoint` is the `<host>:<port>` form a
host process (smolvm) uses; the registry's host port mapping
backs this."""
network: str
push_endpoint: str
pull_endpoint: str
@contextmanager
def ephemeral_registry() -> Generator[RegistryHandle, None, None]:
"""Bring up a per-session docker network + a `registry:2.8.3`
container on it (published on a random host port), yield a
`RegistryHandle`, force-remove both on exit.
The container is started with `--rm` so a clean exit cleans up
on its own; the `finally` block force-removes on abnormal exit
(the calling process crashes between yield and close)."""
session_id = uuid.uuid4().hex[:12]
network = f"bot-bottle-registry-net-{session_id}"
registry_name = f"bot-bottle-registry-{session_id}"
subprocess.run(
["docker", "network", "create", network],
check=True,
capture_output=True,
)
try:
subprocess.run(
[
"docker", "run", "-d", "--rm",
"--name", registry_name,
"--network", network,
# `-p :5000` (no IP prefix) binds the container's
# port 5000 on a random host port across all
# interfaces. The host side reaches the registry
# via this port — smolvm's `pack create` pulls from
# `localhost:<port>` and the docker port-forward
# routes there.
"-p", _REGISTRY_CONTAINER_PORT,
REGISTRY_IMAGE,
],
check=True,
capture_output=True,
)
try:
port = _host_port(registry_name)
_wait_ready(port)
yield RegistryHandle(
network=network,
push_endpoint=f"{registry_name}:{_REGISTRY_CONTAINER_PORT}",
pull_endpoint=f"localhost:{port}",
)
finally:
subprocess.run(
["docker", "rm", "-f", registry_name],
check=False,
capture_output=True,
)
finally:
subprocess.run(
["docker", "network", "rm", network],
check=False,
capture_output=True,
)
def crane_push_tarball(handle: RegistryHandle, tarball_path: str, ref: str) -> None:
"""Run `crane push --insecure <tarball> <ref>` inside a one-shot
container on the registry's docker network. `ref` should
reference the registry by `handle.push_endpoint` so the crane
container resolves it via docker network DNS.
Doesn't go through `docker push` to avoid the Docker-Desktop
daemon's HTTPS preference for non-loopback hostnames — crane's
`--insecure` flag forces plain HTTP, which is what the
registry container speaks."""
r = subprocess.run(
[
"docker", "run", "--rm",
"--network", handle.network,
"-v", f"{tarball_path}:/img.tar:ro",
CRANE_IMAGE,
"push", "--insecure", "/img.tar", ref,
],
capture_output=True,
text=True,
check=False,
)
if r.returncode != 0:
die(
f"crane push of {tarball_path!r} to {ref!r} failed: "
f"{(r.stderr or r.stdout or '').strip() or '<no output>'}"
)
def _host_port(name: str) -> int:
"""Resolve the host-side port docker mapped to the registry's
container port. `docker port <name> 5000/tcp` returns one or
more `host:port` lines (one per address family) we take the
first."""
r = subprocess.run(
["docker", "port", name, f"{_REGISTRY_CONTAINER_PORT}/tcp"],
capture_output=True,
text=True,
check=False,
)
if r.returncode != 0:
die(
f"docker port {name} {_REGISTRY_CONTAINER_PORT}/tcp failed: "
f"{(r.stderr or '').strip() or '<no stderr>'}"
)
# `0.0.0.0:54321\n[::]:54321\n` — split on the last colon to
# handle either IPv4 or IPv6 host syntax.
line = (r.stdout or "").splitlines()[0].strip()
_, _, port_str = line.rpartition(":")
try:
return int(port_str)
except ValueError:
die(f"unexpected `docker port` output: {line!r}")
def _wait_ready(port: int) -> None:
"""Block until the registry's HTTP layer accepts a TCP
connection on `127.0.0.1:<port>`, or `_READY_TIMEOUT_S`
elapses.
A successful TCP connect is sufficient registry:2.8.3 binds
after it's ready to serve `/v2/` requests, so the push that
follows will land on a working server. We probe loopback
specifically (not via the docker network) because this helper
runs on the host."""
deadline = time.monotonic() + _READY_TIMEOUT_S
last_err: Exception | None = None
while time.monotonic() < deadline:
try:
with socket.create_connection(("127.0.0.1", port), timeout=0.5):
return
except OSError as e:
last_err = e
time.sleep(0.1)
die(
f"local registry on 127.0.0.1:{port} did not accept "
f"connections within {_READY_TIMEOUT_S:.0f}s "
f"(last error: {last_err})"
)
@@ -0,0 +1,272 @@
"""Per-bottle loopback alias allocation + TSI allowlist
enforcement (PRD 0023, follow-up to PR #74).
After the pivot to host-loopback port-forwards, the smolmachines
TSI allowlist was `127.0.0.1/32` which meant the agent VM could
reach **any** service bound to macOS's loopback, not just the
bundle's published ports. Real downgrade from the docker
backend's `--internal` network isolation.
This module narrows the allowlist by allocating each bottle a
unique loopback alias (`127.0.0.16` .. `127.0.0.31`). The
bundle's port-forwards bind to that alias, and the alias's /32
is what TSI allows.
**Smolvm 0.8.0 quirk + workaround.** `smolvm machine create
--from <smolmachine> --net --allow-cidr X/32` silently drops the
flag verified empirically that the agent process's allowlist
ends up `null` in smolvm's persistent state DB (`~/Library/
Application Support/smolvm/server/smolvm.db`, `vms` table,
`data` BLOB), and the booted VM reaches all of `127.0.0.0/8`
regardless of what we passed. Workaround: after machine_create,
open the SQLite DB and patch the row's `allowed_cidrs` field
directly. Smolvm reads the DB at machine_start, so the patched
value takes effect on boot. Tested: enforcement is real the
guest's connect to a non-allowlisted IP fails with `Permission
denied`. Other paths we tried (machine update, stop-edit-
agent.config.json-restart, --smolfile, --image localhost:N/...)
were dead ends.
macOS only configures `127.0.0.1` on `lo0` by default; the
additional aliases require `sudo ifconfig lo0 alias`. We lazily
sudo-add the missing pool on first use per boot the aliases
persist on `lo0` until reboot, so subsequent launches don't
prompt.
Linux native daemons share the host's network namespace; the
whole `127.0.0.0/8` is reachable by default and aliases are
unnecessary. The pool logic detects native-Linux and skips sudo
entirely; the DB patch is also gated on macOS.
Allocation is coordinated by inspecting running bundle
containers' published host IPs — each bottle's bundle owns the
alias appearing in its port bindings. The lowest-numbered free
alias gets handed to a new bottle."""
from __future__ import annotations
import fcntl
import json
import platform
import re
import sqlite3
import subprocess
from pathlib import Path
from typing import Iterable
from ...log import die, info
# smolvm's persistent VM state on macOS — a SQLite DB whose `vms`
# table holds one JSON BLOB per machine. The Linux path is
# different, but smolmachines is macOS-only in v1 (PRD 0023) so
# we hard-code this. If the file moves under us we'll see a
# clear FileNotFoundError; not worth defensive cross-platform
# detection until the backend actually needs Linux.
_SMOLVM_DB_PATH = (
Path.home()
/ "Library"
/ "Application Support"
/ "smolvm"
/ "server"
/ "smolvm.db"
)
# Sixteen aliases by default. Tunable for hosts that want more
# concurrent bottles (each bottle reserves one alias for its
# bundle bringup). The range is chosen to avoid the reserved
# 127.0.0.1/2/3 ports (1 is the default, 2 is sometimes used by
# CUPS, 3 by other macOS services) and stay well clear of
# 127.0.0.53 (systemd-resolved) and 127.0.0.54 (libvirt).
_POOL_START = 16
_POOL_END = 31 # inclusive
# File lock that serialises concurrent allocate() calls so two
# simultaneous launches can't read the same docker state and claim
# the same alias. Narrowed to the allocate() call itself; docker run
# runs after the lock is released. Once the container is running it
# appears in docker state and future allocate() calls will see it.
_ALLOC_LOCK_PATH = Path.home() / ".cache" / "bot-bottle" / "smolmachines.lock"
# Loopback aliases pool: 127.0.0.<start>..127.0.0.<end>.
def _pool_addresses() -> list[str]:
return [f"127.0.0.{i}" for i in range(_POOL_START, _POOL_END + 1)]
def _is_macos() -> bool:
return platform.system() == "Darwin"
def ensure_pool() -> None:
"""Make sure each address in the pool is up on `lo0`. Lazily
runs `sudo ifconfig lo0 alias <ip>/32 up` for missing entries
(sudo prompts once, then the aliases persist on lo0 until
reboot). No-op on non-macOS hosts."""
if not _is_macos():
return
missing = [ip for ip in _pool_addresses() if not _alias_present(ip)]
if not missing:
return
info(
f"smolmachines needs {len(missing)} loopback alias(es) on lo0 "
f"({', '.join(missing[:3])}{', ...' if len(missing) > 3 else ''}) "
f"to scope per-bottle TSI allowlists. sudo will prompt once; "
f"aliases persist until reboot."
)
for ip in missing:
result = subprocess.run(
["sudo", "-p", "bot-bottle (loopback alias): ",
"ifconfig", "lo0", "alias", f"{ip}/32", "up"],
check=False,
)
if result.returncode != 0:
die(
f"sudo ifconfig lo0 alias {ip} failed (exit "
f"{result.returncode}). Re-run with sudo available, "
f"or add manually: sudo ifconfig lo0 alias {ip}/32 up"
)
def force_allowlist(machine_name: str, allowed_cidrs: list[str]) -> None:
"""Patch smolvm's persistent VM-state DB to set the machine's
`allowed_cidrs` to the given list. Workaround for smolvm
0.8.0's silent-drop of `--allow-cidr` when used with `--from`.
Must run AFTER `smolvm machine create` (the row has to
exist) and BEFORE `smolvm machine start` (smolvm reads the
row on start; in-flight VMs don't pick up changes). Once
smolvm honors the CLI flag upstream this whole function is
redundant flag-respecting create + remove this call from
launch.
No-op on non-macOS the DB path differs and the Linux
smolmachines code path isn't exercised in v1."""
if not _is_macos():
return
if not _SMOLVM_DB_PATH.is_file():
die(
f"smolvm state DB not found at {_SMOLVM_DB_PATH}. "
f"smolvm 0.8.0 expected? `smolvm --version` to check."
)
con = sqlite3.connect(str(_SMOLVM_DB_PATH))
try:
cur = con.cursor()
row = cur.execute(
"SELECT data FROM vms WHERE name = ?", (machine_name,),
).fetchone()
if row is None:
die(
f"smolvm DB has no row for machine {machine_name!r}"
f"machine_create must run before force_allowlist."
)
cfg = json.loads(row[0])
cfg["allowed_cidrs"] = list(allowed_cidrs)
# Write as BLOB (the column type smolvm uses) — passing a
# plain str makes sqlite store it as Text and smolvm then
# fails to read it.
cur.execute(
"UPDATE vms SET data = ? WHERE name = ?",
(sqlite3.Binary(json.dumps(cfg).encode()), machine_name),
)
con.commit()
finally:
con.close()
def allocate(_slug: str) -> str:
"""Pick the lowest-numbered alias from the pool not already
in use by a running smolmachines bundle. Bails when the pool
is exhausted the caller should report the limit to the
operator. `_slug` is logged for traceability; not otherwise
used (no on-disk reservation, allocation is purely
docker-state-driven).
On non-macOS the whole `127.0.0.0/8` is loopback by default;
`127.0.0.1` is fine to share and we skip the alias dance.
This still returns a deterministic address so launch.py's
callers don't have to branch on platform.
An exclusive file lock serialises concurrent calls so two
simultaneous launches don't read the same docker state and
claim the same alias."""
if not _is_macos():
return "127.0.0.1"
_ALLOC_LOCK_PATH.parent.mkdir(parents=True, exist_ok=True)
with open(_ALLOC_LOCK_PATH, "w", encoding="utf-8") as lf:
fcntl.flock(lf, fcntl.LOCK_EX)
return _allocate_locked()
def _allocate_locked() -> str:
in_use = _aliases_in_use()
for ip in _pool_addresses():
if ip not in in_use:
return ip
die(
f"smolmachines loopback alias pool exhausted "
f"({_POOL_END - _POOL_START + 1} aliases, all in use). "
f"Stop a running bottle (`smolvm machine ls --json`) or "
f"raise _POOL_END in loopback_alias.py."
)
def _alias_present(ip: str) -> bool:
"""True iff `ifconfig lo0` shows `<ip>` as an inet address.
Exact-match `127.0.0.1` shouldn't match `127.0.0.16`."""
result = subprocess.run(
["/sbin/ifconfig", "lo0"],
capture_output=True, text=True, check=False,
)
if result.returncode != 0:
return False
pattern = re.compile(rf"\binet {re.escape(ip)}\b")
return bool(pattern.search(result.stdout or ""))
def _aliases_in_use() -> set[str]:
"""Aliases already bound by another smolmachines bundle's
published-port mappings. We inspect every container whose
name matches the smolmachines bundle prefix and pull the
`HostIp` out of its port bindings."""
result = subprocess.run(
["docker", "ps", "--format", "{{.Names}}",
"--filter", "name=bot-bottle-sidecars-"],
capture_output=True, text=True, check=False,
)
if result.returncode != 0:
return set()
names = [n.strip() for n in (result.stdout or "").splitlines() if n.strip()]
in_use: set[str] = set()
for name in names:
in_use.update(_host_ips_for_container(name))
return in_use
def _host_ips_for_container(name: str) -> Iterable[str]:
"""Yield the `HostIp` values across all port bindings on
container `name`. A bundle binds three or four ports and
they all share the same HostIp, so callers can take any."""
result = subprocess.run(
["docker", "inspect", name,
"--format", "{{json .HostConfig.PortBindings}}"],
capture_output=True, text=True, check=False,
)
if result.returncode != 0:
return ()
try:
bindings = json.loads(result.stdout or "{}")
except json.JSONDecodeError:
return ()
seen: set[str] = set()
for _port, mappings in (bindings or {}).items():
for m in mappings or []:
host_ip = m.get("HostIp") or ""
if host_ip:
seen.add(host_ip)
return seen
__all__ = ["allocate", "ensure_pool", "force_allowlist"]
+185
View File
@@ -0,0 +1,185 @@
"""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 dataclasses import replace
from pathlib import Path
from ...agent_provider import agent_provision_plan, runtime_for
from ...backend import BottleSpec
from ...backend.docker.bottle_state import (
BottleMetadata,
agent_state_dir,
bottle_identity,
egress_state_dir,
git_gate_state_dir,
supervise_state_dir,
write_metadata,
)
from ...egress import Egress
from ...env import resolve_env
from ...git_gate import GitGate
from ...supervise import Supervise
from ...workspace import workspace_plan as resolve_workspace_plan
from .bottle_plan import SmolmachinesBottlePlan
from .util import smolmachines_bundle_subnet, smolmachines_preflight
# Gateway ports the bundle exposes inside its container — git-gate's
# git-daemon, supervise's MCP. The agent inside the smolvm guest
# dials these on the bundle's pinned IP.
_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)
provider = bottle.agent_provider
provider_runtime = runtime_for(provider.template)
guest_home = "/home/node"
workspace_plan = resolve_workspace_plan(spec, guest_home=guest_home)
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(),
compose_project="",
backend="smolmachines",
label=spec.label,
color=spec.color,
))
subnet, gateway, bundle_ip = smolmachines_bundle_subnet(slug)
# Agent's env: resolve through resolve_env() so ?prompt entries
# are prompted and ${HOST_VAR} entries are interpolated — matching
# the Docker backend's contract. Forwarded (secret/interpolated)
# values still reach the guest as -e K=V smolvm flags because
# smolvm 0.8.0 has no env-file or stdin injection path; this is
# the known argv-exposure gap documented in PRD 0038.
# HTTPS_PROXY / GIT_GATE_URL / MCP_SUPERVISE_URL are populated
# in launch.py after bundle bringup.
resolved = resolve_env(manifest, spec.agent_name)
guest_env: dict[str, str] = {
**resolved.literals,
**resolved.forwarded,
"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",
}
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)
# 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"bot-bottle-{slug}"
# Stash the agent image ref — `launch.launch` runs the
# build → pack pipeline at bringup. Honors BOT_BOTTLE_IMAGE
# to match the docker backend's `resolve_plan` default.
agent_dockerfile_path = ""
if provider.dockerfile:
agent_dockerfile_path = _resolve_manifest_dockerfile(provider.dockerfile, spec)
image_default = f"bot-bottle-{provider.template}:{slug}"
elif provider_runtime.dockerfile:
agent_dockerfile_path = provider_runtime.dockerfile
image_default = provider_runtime.image
else:
image_default = provider_runtime.image
agent_image_ref = os.environ.get("BOT_BOTTLE_IMAGE", image_default)
agent_provision = agent_provision_plan(
template=provider.template,
dockerfile=agent_dockerfile_path,
state_dir=agent_dir,
guest_home=guest_home,
guest_env=guest_env,
forward_host_credentials=provider.forward_host_credentials,
auth_token=provider.auth_token,
host_env=dict(os.environ),
trusted_project_path=workspace_plan.workdir,
label=spec.label,
color=spec.color,
)
merged_guest_env = dict(agent_provision.guest_env)
for key, val in agent_provision.env_vars.items():
merged_guest_env.setdefault(key, val)
agent_provision = replace(agent_provision, guest_env=merged_guest_env)
egress_dir = egress_state_dir(slug)
egress_dir.mkdir(parents=True, exist_ok=True)
egress_plan = Egress().prepare(
bottle, slug, egress_dir, agent_provision.egress_routes,
)
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)
return SmolmachinesBottlePlan(
spec=spec,
stage_dir=stage_dir,
guest_home=guest_home,
slug=slug,
bundle_subnet=subnet,
bundle_gateway=gateway,
bundle_ip=bundle_ip,
machine_name=machine_name,
agent_image_ref=agent_image_ref,
guest_env=agent_provision.guest_env,
prompt_file=prompt_file,
git_gate_plan=git_gate_plan,
egress_plan=egress_plan,
supervise_plan=supervise_plan,
agent_provision=agent_provision,
workspace_plan=workspace_plan,
)
def _resolve_manifest_dockerfile(path_value: str, spec: BottleSpec) -> str:
path = Path(os.path.expanduser(path_value))
if not path.is_absolute():
path = Path(spec.user_cwd) / path
return str(path)
@@ -0,0 +1,13 @@
"""Backend-infrastructure provisioners for the smolmachines backend.
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/`. 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:
- workspace.py copy the operator workspace into the guest
"""
@@ -0,0 +1,32 @@
"""Copy the operator workspace into a smolmachines guest."""
from __future__ import annotations
import shlex
from ....log import info
from ... import Bottle
from ..bottle_plan import SmolmachinesBottlePlan
def provision_workspace(plan: SmolmachinesBottlePlan, bottle: Bottle) -> None:
"""Copy host cwd contents to the planned guest workspace."""
workspace = plan.workspace_plan
if not (workspace.enabled and workspace.copy_contents):
return
guest_parent = workspace.guest_path.rsplit("/", 1)[0] or "/"
guest_path_q = shlex.quote(workspace.guest_path)
guest_parent_q = shlex.quote(guest_parent)
owner_q = shlex.quote(workspace.owner)
mode_q = shlex.quote(workspace.mode)
info(f"copying {workspace.host_path} -> {bottle.name}:{workspace.guest_path}")
bottle.exec(
f"rm -rf {guest_path_q} && mkdir -p {guest_parent_q}",
user="root",
)
bottle.cp_in(str(workspace.host_path), workspace.guest_path)
bottle.exec(
f"chown -R {owner_q} {guest_path_q} && chmod {mode_q} {guest_path_q}",
user="root",
)
@@ -0,0 +1,151 @@
"""Host-side SIGWINCH → in-VM PTY resize bridge (issue #82).
smolvm 0.8.0 `machine exec -t` allocates an in-VM PTY but never
forwards the host terminal's window size (TIOCSWINSZ) to it. The
PTY's initial size is `0 0`, and any host-side resize during the
session goes unnoticed the in-VM claude TUI keeps rendering for
whatever (typically tiny) box it last saw, ignoring the operator's
tmux pane resize. `docker exec -it` does this forwarding
automatically; smolvm doesn't.
This module wraps `smolvm machine exec` with a thin parent
process that:
1. Spawns the original argv as a child (it gets the inherited
TTY, so claude's stdin/stdout/stderr work unchanged).
2. On startup + every host SIGWINCH, reads the host terminal
size via TIOCGWINSZ on stdin (or stderr if stdin isn't a
TTY tmux respawn-pane gives us a TTY on stdout/stderr)
and pushes it into the VM with a side-channel
`smolvm machine exec -- sh -c 'for f in /dev/pts/*; do
stty -F $f cols X rows Y; done'`. The kernel delivers
SIGWINCH to the foreground process group on the slave end
automatically, so claude picks up the new size without
extra signalling.
3. Waits on the child and exits with its returncode.
The dashboard's tmux pane respawn calls `bottle.agent_argv`
which now prepends `[sys.executable, -m, ..., <machine>, --, ...]`
to the smolvm argv. Foreground handoff (curses endwin
subprocess.run) goes through the same path so behavior is
identical.
Removable once smolvm grows native SIGWINCH forwarding (upstream
follow-up tracked separately)."""
from __future__ import annotations
import fcntl
import signal
import struct
import subprocess
import sys
import termios
import threading
from types import FrameType
# How long to wait after the main exec starts before pushing the
# initial size. Concurrent `smolvm machine exec` invocations race
# libkrun's per-exec OCI config write during the main exec's
# bringup window; the side-channel firing immediately corrupts
# `config.json` and the main exec dies with SIGKILL (rc=137) or
# libkrun's "parse error: trailing garbage" depending on
# scheduling. Two seconds is well past the bringup window on a
# warm VM, well under the operator's "this is unresponsive"
# threshold, and short enough that claude's initial render
# almost always fires after the size has been set.
_STARTUP_SYNC_DELAY_SEC = 2.0
def _read_winsize() -> tuple[int, int] | None:
"""Return `(rows, cols)` from whichever of stdin / stdout /
stderr is a TTY, or None if none are. Different invocation
surfaces give us different TTYs:
- foreground handoff (curses endwin subprocess.run): all
three are the operator's terminal.
- tmux respawn-pane: tmux sets all three to the pane's PTY.
- non-TTY (someone piped stdin in tests): none are; the
sync just no-ops, which is the right behavior."""
for stream in (sys.stdin, sys.stdout, sys.stderr):
try:
fd = stream.fileno()
data = fcntl.ioctl(fd, termios.TIOCGWINSZ, b"\x00" * 8)
except OSError:
continue
rows, cols, _, _ = struct.unpack("hhhh", data)
if rows > 0 and cols > 0:
return rows, cols
return None
def _push_size(machine: str, rows: int, cols: int) -> None:
"""Side-channel `smolvm machine exec` that sets the size of
every PTY in the VM. The shell `for` loop covers the case of
multiple concurrent interactive sessions (rare but cheap to
handle); `stty -F` returns silently on PTYs that don't apply.
Best-effort: swallow failures. A failed resize doesn't break
the session it just leaves the in-VM PTY at its old size.
`stdin=DEVNULL` is load-bearing: under tmux, inheriting the
pane PTY here means two concurrent smolvm processes (this one
and the agent session the wrapper is shepherding) share the
PTY's foreground-process-group / input plumbing, and smolvm
bails with an internal config-parse error or SIGKILL within
~100ms of the side-channel firing. Outside tmux the same
pattern survived, presumably because iTerm's PTY plumbing is
more forgiving than tmux's, but the DEVNULL is the right
default either way the side-channel never needs stdin."""
subprocess.run(
["smolvm", "machine", "exec", "--name", machine, "--",
"sh", "-c",
f"for f in /dev/pts/*; do "
f"stty -F \"$f\" cols {cols} rows {rows} 2>/dev/null; "
f"done"],
stdin=subprocess.DEVNULL,
stdout=subprocess.DEVNULL, stderr=subprocess.DEVNULL,
check=False,
)
def main(argv: list[str]) -> int:
"""Entry point. `argv` shape: `<machine> -- <smolvm-argv...>`.
We don't use argparse — the `--` separator is the contract and
everything past it is forwarded verbatim. Keeps the wrapper
transparent for callers building argv programmatically."""
if len(argv) < 3 or argv[1] != "--":
sys.stderr.write(
"usage: python -m bot_bottle.backend.smolmachines.pty_resize "
"<machine> -- <smolvm-argv...>\n"
)
return 2
machine = argv[0]
inner = argv[2:]
def sync(_signum: int | None = None, _frame: FrameType | None = None) -> None:
size = _read_winsize()
if size is None:
return
_push_size(machine, *size)
signal.signal(signal.SIGWINCH, sync) # type: ignore[arg-type]
proc = subprocess.Popen(inner)
# Initial sync is deferred — see _STARTUP_SYNC_DELAY_SEC.
# daemon=True so the timer doesn't block exit when the child
# finishes before the delay elapses.
timer = threading.Timer(_STARTUP_SYNC_DELAY_SEC, sync)
timer.daemon = True
timer.start()
while True:
try:
return proc.wait()
except KeyboardInterrupt:
proc.send_signal(signal.SIGINT)
if __name__ == "__main__":
sys.exit(main(sys.argv[1:]))
@@ -0,0 +1,242 @@
"""Per-bottle sidecar bundle bringup for the smolmachines backend
(PRD 0023).
Two docker resources per bottle live here:
- **A dedicated bridge network**, subnet derived from the slug.
The bundle container gets a pinned IP at `<subnet>.2` so the
smolvm guest's TSI allowlist (`<bundle-ip>/32`) has a stable
target. Without pinning, we'd have to inspect the container's
assigned IP after start and feed it back into the Smolfile
a race we can sidestep with `--ip`.
- **The bundle container itself**, running the PRD 0024 bundle
image (`bot-bottle-sidecars:latest` by default). Same
image, same daemons, same daemon-private env / bind-mounts
as the docker backend.
This module ships the lifecycle primitives only create
network, start bundle, stop bundle, remove network wrapped
around `subprocess.run(["docker", ...])`. Wiring them into the
launch flow + populating the `BundleLaunchSpec` from the inner
Plans (EgressPlan, ) lands in chunk 2d."""
from __future__ import annotations
import subprocess
from dataclasses import dataclass, field
from pathlib import Path
from typing import Sequence
from ...log import die, warn
from ..docker import util as docker_mod
from ..docker.sidecar_bundle import (
SIDECAR_BUNDLE_DOCKERFILE,
SIDECAR_BUNDLE_IMAGE,
)
_REPO_DIR = str(Path(__file__).resolve().parent.parent.parent.parent)
def bundle_network_name(slug: str) -> str:
"""`bot-bottle-bundle-<slug>` — distinct from the docker
backend's `bot-bottle-net-<slug>` so a smolmachines bottle
and a docker bottle for the same agent don't collide on
network name."""
return f"bot-bottle-bundle-{slug}"
def bundle_container_name(slug: str) -> str:
"""`bot-bottle-sidecars-<slug>` — same name shape the docker
backend uses for the bundle (PRD 0024 chunk 5). The dashboard's
prefix-based discovery covers both backends with one filter."""
return f"bot-bottle-sidecars-{slug}"
@dataclass(frozen=True)
class BundleLaunchSpec:
"""Everything `start_bundle` needs to bring up one bundle
container. Populated by chunk-2d's launch flow from the inner
Plans the prepare step already produces."""
slug: str
network_name: str
subnet: str
gateway: str
bundle_ip: str
image: str = SIDECAR_BUNDLE_IMAGE
# Daemon subset CSV for BOT_BOTTLE_SIDECAR_DAEMONS. The
# supervisor inside the bundle reads it to skip
# bottle-irrelevant daemons (e.g. supervise=False bottles).
daemons_csv: str = "egress"
# Plain "KEY=VALUE" strings + "KEY" bare names (the bare-name
# form inherits the value from the docker-run subprocess env,
# matching the docker backend's compose-up secret-forwarding
# pattern).
environment: Sequence[str] = field(default_factory=tuple)
# (host_path, container_path, read_only) bind mounts.
volumes: Sequence[tuple[str, str, bool]] = field(default_factory=tuple)
# Container ports to publish on `publish_host_ip`, random
# host-side port per entry. The smolvm guest's TSI talks via
# macOS networking, so docker container IPs (192.168.x.x in
# the daemon's bridge) aren't directly reachable from the
# guest — host-loopback port-forwards are. Egress's port
# is bundle-internal and never published.
ports_to_publish: Sequence[int] = field(default_factory=tuple)
# Loopback IP to bind published ports against. Per-bottle
# loopback aliases (`127.0.0.16` etc., added via sudo
# ifconfig lo0 alias) narrow the TSI allowlist so a bottle
# can't reach other bottles' (or other host services') ports
# via 127.0.0.1.
publish_host_ip: str = "127.0.0.1"
def ensure_bundle_image(image: str = SIDECAR_BUNDLE_IMAGE) -> None:
"""Build the sidecar bundle image before `docker run`.
The Docker backend gets this for free from compose's `build:`
stanza. smolmachines starts the bundle with plain `docker run`,
so without an explicit build a first launch tries to pull the
local-only `bot-bottle-sidecars:latest` tag from a registry.
"""
docker_mod.build_image(
image,
_REPO_DIR,
dockerfile=SIDECAR_BUNDLE_DOCKERFILE,
)
def create_bundle_network(network_name: str, subnet: str, gateway: str) -> None:
"""`docker network create` with an explicit subnet + gateway
so the bundle's `--ip` lands on the address the Smolfile's
TSI allowlist points at. Idempotent on the caller's side —
`start_bundle` catches the "network exists" error and treats
it as success (chunk-2d teardown is paired with each create).
"""
result = subprocess.run(
["docker", "network", "create",
"--subnet", subnet, "--gateway", gateway,
network_name],
capture_output=True, text=True, check=False,
)
if result.returncode != 0:
# Already-exists is fine on a resume path; everything else
# is fatal — the bundle won't have an addressable network.
if "already exists" in (result.stderr or "").lower():
return
die(
f"docker network create {network_name} failed: "
f"{(result.stderr or '').strip()}"
)
def remove_bundle_network(network_name: str) -> None:
"""Idempotent: a missing network returns success."""
result = subprocess.run(
["docker", "network", "rm", network_name],
capture_output=True, text=True, check=False,
)
if result.returncode == 0:
return
if "no such network" in (result.stderr or "").lower():
return
# Network with attached containers is the common non-fatal
# case during a partial teardown — warn but don't die.
warn(
f"docker network rm {network_name} failed: "
f"{(result.stderr or '').strip()}"
)
def start_bundle(spec: BundleLaunchSpec, *,
env: dict[str, str] | None = None) -> None:
"""Bring the bundle container up on the per-bottle bridge with
the pinned IP. Argv is built deterministically from `spec`;
`env` is the host subprocess env (forwarded values for any
bare-name entries in `spec.environment`)."""
container = bundle_container_name(spec.slug)
argv = [
"docker", "run",
"--name", container,
"--detach",
"--rm",
"--network", spec.network_name,
"--ip", spec.bundle_ip,
"-e", f"BOT_BOTTLE_SIDECAR_DAEMONS={spec.daemons_csv}",
]
for entry in spec.environment:
argv += ["-e", entry]
for host_path, container_path, read_only in spec.volumes:
suffix = ":ro" if read_only else ""
argv += ["-v", f"{host_path}:{container_path}{suffix}"]
# Loopback-only host port-forwards — the smolvm guest's TSI
# uses macOS networking, and macOS loopback is the only host
# surface that round-trips into Docker Desktop's daemon VM.
# Binds to the per-bottle alias so TSI's IP-only allowlist
# narrows reachability to this bottle's bundle only.
for port in spec.ports_to_publish:
argv += ["-p", f"{spec.publish_host_ip}::{port}"]
argv.append(spec.image)
result = subprocess.run(
argv, capture_output=True, text=True,
env=dict(env) if env is not None else None, check=False,
)
if result.returncode != 0:
die(
f"docker run for bundle {container} failed: "
f"{(result.stderr or '').strip()}"
)
def bundle_host_port(
slug: str, container_port: int, *, host_ip: str = "127.0.0.1",
) -> int:
"""`docker port <bundle> <container_port>/tcp` → the random
host-side port docker assigned for the binding on `host_ip`.
Called after `start_bundle` on each container port listed in
`BundleLaunchSpec.ports_to_publish` so the launch step can
build the agent's HTTPS_PROXY / GIT_GATE / SUPERVISE URLs in
`<host_ip>:<host port>` form."""
container = bundle_container_name(slug)
result = subprocess.run(
["docker", "port", container, f"{container_port}/tcp"],
capture_output=True, text=True, check=False,
)
if result.returncode != 0:
die(
f"docker port {container} {container_port}/tcp failed: "
f"{(result.stderr or '').strip() or '<no stderr>'}"
)
# Each line looks like `127.0.0.16:54321` — one per address
# family / host IP. Match on the expected host_ip prefix so
# bottles bound to per-bottle aliases pick the right line.
for raw in (result.stdout or "").splitlines():
line = raw.strip()
if line.startswith(f"{host_ip}:"):
_, _, port_str = line.rpartition(":")
try:
return int(port_str)
except ValueError:
die(f"unexpected `docker port` output: {line!r}")
die(
f"no port mapping on {host_ip} for {container} "
f"{container_port}/tcp; got: {(result.stdout or '').strip()!r}"
)
def stop_bundle(slug: str) -> None:
"""Idempotent: a missing container returns success."""
container = bundle_container_name(slug)
result = subprocess.run(
["docker", "rm", "-f", container],
capture_output=True, text=True, check=False,
)
if result.returncode == 0:
return
if "no such container" in (result.stderr or "").lower():
return
warn(
f"docker rm -f {container} failed: "
f"{(result.stderr or '').strip()}"
)
+247
View File
@@ -0,0 +1,247 @@
"""Thin subprocess wrapper around the `smolvm` CLI (PRD 0023).
One thin Python function per smolvm subcommand the launch flow
needs. Two design choices worth flagging:
- **No daemon, no SDK.** smolvm 0.8.0 ships a `smolvm serve`
HTTP API as the long-term-clean integration target. The
project's stdlib-first ethos + the lower-overhead CLI calls
push v1 to shell out via `subprocess.run`. If a future
smolvm release makes `serve` mandatory (or significantly
faster), revisit.
- **Two return shapes.** `SmolvmRunResult` (returncode + stdout
+ stderr captured) is returned by `machine_exec` because the
caller cares about the in-VM command's exit status, and by
test helpers that introspect output. The other calls
(`machine_start`, `machine_stop`, `pack_create`, etc.) raise
`SmolvmError` on non-zero exit failure to start a VM is
fatal to the launch flow, not something callers want to
branch on.
The wrapper is unit-tested with `subprocess.run` mocked; the
integration smoke test (chunk 2d) exercises against a real
smolvm binary."""
from __future__ import annotations
import shutil
import subprocess
import time
from dataclasses import dataclass
from pathlib import Path
from typing import Mapping, Sequence
_SMOLVM = "smolvm"
@dataclass(frozen=True)
class SmolvmRunResult:
"""Captured result of an in-VM command. Mirrors the structure
`Bottle.exec` returns so callers can hand it straight through."""
returncode: int
stdout: str
stderr: str
class SmolvmError(RuntimeError):
"""Raised when a smolvm subprocess returns non-zero on a path
where the caller has no useful branch to take (start failed,
pack failed, etc.). Carries the captured stderr for the
operator-facing log line."""
def __init__(self, argv: Sequence[str], result: subprocess.CompletedProcess[str]):
self.argv = list(argv)
self.returncode = result.returncode
self.stdout = result.stdout
self.stderr = result.stderr
cmd = " ".join(self.argv)
super().__init__(
f"{cmd!r} failed (exit {result.returncode}): "
f"{(result.stderr or '').strip() or '<no stderr>'}"
)
def _smolvm(*args: str, env: Mapping[str, str] | None = None,
check: bool = True) -> subprocess.CompletedProcess[str]:
"""One subprocess call into the smolvm CLI. `check=True`
raises SmolvmError on non-zero; `check=False` returns the
CompletedProcess for the caller to inspect."""
argv = [_SMOLVM, *args]
result = subprocess.run(
argv,
capture_output=True,
text=True,
env=dict(env) if env is not None else None,
check=False,
)
if check and result.returncode != 0:
raise SmolvmError(argv, result)
return result
# --- Pack ----------------------------------------------------------------
def pack_create(image: str, output: Path) -> None:
"""`smolvm pack create --image <image> -o <output>`. Converts
an OCI image into a self-contained `.smolmachine` artifact
smolvm can boot via `machine create --from`. Idempotent on the
smolvm side re-running with the same image+output rebuilds
from layer cache."""
_smolvm("pack", "create", "--image", image, "-o", str(output))
# --- Machine lifecycle ---------------------------------------------------
def machine_create(
name: str,
*,
image: str | None = None,
from_path: Path | None = None,
allow_cidrs: Sequence[str] = (),
env: Mapping[str, str] | None = None,
) -> None:
"""`smolvm machine create NAME [--image IMG | --from PATH]
[--allow-cidr CIDR ...] [-e K=V ...]`. NAME is positional
(the CLI's exception to the `--name` pattern other
subcommands use).
`image` (registry ref like `alpine:latest`) and `from_path`
(a `.smolmachine` artifact) are mutually exclusive one or
the other tells smolvm what to boot. The wrapper doesn't
enforce exclusivity; smolvm errors clearly enough.
`allow_cidrs` and `env` are passed as CLI flags instead of a
Smolfile because `--from` and `--smolfile` are themselves
mutually exclusive in smolvm 0.8.0 and we want `--from`'s
no-pull-at-start property. The flag form gives the same
result without the Smolfile complication.
`--net` is sent explicitly when `allow_cidrs` is non-empty.
smolvm 0.8.0's docs say `--allow-cidr` implies `--net`, but
empirically the implication only fires when no `--from` is
set `--from PATH --allow-cidr X/32` silently produces a
machine with `network: false` and no routes in the guest, so
the agent can't reach the bundle's pinned IP."""
args: list[str] = ["machine", "create"]
if image is not None:
args += ["--image", image]
if from_path is not None:
args += ["--from", str(from_path)]
if allow_cidrs:
args.append("--net")
for cidr in allow_cidrs:
args += ["--allow-cidr", cidr]
if env:
for k, v in env.items():
args += ["-e", f"{k}={v}"]
args.append(name)
_smolvm(*args)
def machine_start(name: str) -> None:
"""`smolvm machine start --name NAME`."""
_smolvm("machine", "start", "--name", name)
def machine_stop(name: str) -> None:
"""`smolvm machine stop --name NAME`. Idempotent against
already-stopped machines: smolvm prints a notice and exits 0
in that case, so no special handling here."""
_smolvm("machine", "stop", "--name", name)
def machine_delete(name: str) -> None:
"""`smolvm machine delete -f NAME`. NAME is positional. `-f`
skips the interactive confirmation required for
non-interactive teardown."""
_smolvm("machine", "delete", "-f", name)
def machine_exec(
name: str,
argv: Sequence[str],
*,
env: Mapping[str, str] | None = None,
workdir: str | None = None,
timeout: str | None = None,
) -> SmolvmRunResult:
"""`smolvm machine exec --name NAME [-w DIR] [--timeout DUR]
[-e K=V ...] -- ARGV...`. Returns the captured result rather
than raising callers (including `Bottle.exec`) care about
the in-VM command's exit code, not just whether smolvm ran.
`env` here is in-VM env vars (`-e K=V`), not the host
subprocess env smolvm's own argv carries them through the
VMM."""
flags: list[str] = ["machine", "exec", "--name", name]
if workdir is not None:
flags += ["-w", workdir]
if timeout is not None:
flags += ["--timeout", timeout]
if env:
for k, v in env.items():
flags += ["-e", f"{k}={v}"]
# `--` separator before the command. smolvm's CLI requires it
# so its own flag parser doesn't grab argv items that look
# like flags.
flags.append("--")
flags += list(argv)
result = _smolvm(*flags, check=False)
return SmolvmRunResult(
returncode=result.returncode,
stdout=result.stdout or "",
stderr=result.stderr or "",
)
def wait_exec_ready(name: str, *, timeout: float = 5.0) -> None:
"""Poll `machine exec true` until exit 0 or `timeout` elapses.
Replaces `time.sleep(1.5)` after `machine_start`: libkrun's exec
channel needs a brief warm-up before back-to-back exec calls are
safe. Polling exits as soon as the channel is ready and fails
loudly if the VM never responds."""
deadline = time.monotonic() + timeout
delay = 0.1
while time.monotonic() < deadline:
r = machine_exec(name, ["true"])
if r.returncode == 0:
return
remaining = deadline - time.monotonic()
if remaining <= 0:
break
time.sleep(min(delay, remaining))
delay = min(delay * 2, 0.5)
argv = ["smolvm", "machine", "exec", "--name", name, "--", "true"]
raise SmolvmError(
argv,
subprocess.CompletedProcess(
args=argv, returncode=-1, stdout="",
stderr=f"exec channel not ready after {timeout:.0f}s — VM may have failed to boot.",
),
)
def machine_cp(src: str, dst: str) -> None:
"""`smolvm machine cp SRC DST`. Path syntax: `machine:path` to
reference a path inside the VM, bare path for the host. Both
SRC and DST are positional; either side can be machine: or
bare. Empty path is a no-op (returns immediately without
invoking smolvm)."""
if not src or not dst:
return
_smolvm("machine", "cp", src, dst)
# --- Discovery -----------------------------------------------------------
def is_available() -> bool:
"""True iff `smolvm` is on PATH. Used by the integration test
suite's skip-guards."""
return shutil.which(_SMOLVM) is not None
+48
View File
@@ -0,0 +1,48 @@
"""Slug / preflight / subnet helpers for the smolmachines backend
(PRD 0023). Kept in its own module so the renderers can be
unit-tested without importing the docker subprocess paths."""
from __future__ import annotations
import hashlib
import shutil
from ...log import die
def smolmachines_preflight() -> None:
"""Ensure `smolvm` is on PATH before the launch flow runs.
Called from `_resolve_plan`; gives the operator a clear
install pointer rather than a cryptic FileNotFoundError
later. `gvproxy` is no longer required see the PRD's design
pivot section."""
if shutil.which("smolvm") is not None:
return
die(
"BOT_BOTTLE_BACKEND=smolmachines requires `smolvm` on "
"PATH. Install with: "
"curl -sSL https://smolmachines.com/install.sh | sh"
)
def smolmachines_bundle_subnet(slug: str) -> tuple[str, str, str]:
"""Derive a per-bottle docker subnet + gateway IP + bundle IP
from the slug.
Returns `(subnet_cidr, gateway_ip, bundle_ip)`. The third
octet comes from SHA-256 of the slug mod 254 (skipping 17 to
avoid the docker-default bridge), so parallel bottles get
distinct /24s and `resume` reuses the same /24. The bundle
container always lands at `.2`; gateway is `.1`; the smolvm
Smolfile's `allow_cidrs` is `<bundle_ip>/32`."""
digest = hashlib.sha256(slug.encode("utf-8")).digest()
octet = (digest[0] % 254) + 1
# Skip the docker-default bridge to dodge the most common
# collision (operators with `docker0` at 172.17.x.x or a
# 192.168.17.x VPN client).
if octet == 17:
octet = 18
subnet = f"192.168.{octet}.0/24"
gateway = f"192.168.{octet}.1"
bundle_ip = f"192.168.{octet}.2"
return subnet, gateway, bundle_ip
-71
View File
@@ -1,71 +0,0 @@
"""Terminal escape-sequence helpers shared across all bottle backends."""
from __future__ import annotations
import shlex
# color name → (normal_idx, normal_hex, bright_idx, bright_hex, dark_bg_hex)
# OSC 4 sets indexed palette entries (affects syntax-highlighted code and any
# TUI content that uses indexed colors). dark_bg_hex is used for OSC 11
# (default background) — a very dark tint that's visible even when the TUI
# uses true/24-bit colors for its own chrome, which would otherwise bypass
# the palette entirely.
_COLORS: dict[str, tuple[int, str, int, str, str]] = {
"red": (9, "#e74c3c", 1, "#c0392b", "#200808"),
"green": (10, "#2ecc71", 2, "#27ae60", "#082008"),
"yellow": (11, "#f1c40f", 3, "#d4ac0d", "#201808"),
"blue": (12, "#3498db", 4, "#2471a3", "#080820"),
"magenta": (13, "#9b59b6", 5, "#7d3c98", "#160820"),
}
# OSC 104 resets all indexed palette entries; OSC 111 resets default background.
_RESET_PRINTF = "printf '\\033]104\\007\\033]111\\007'"
def palette_printf(color: str) -> str:
"""Shell `printf` command that emits OSC 4 + OSC 11 to tint the terminal
for *color*: sets the normal/bright palette entries AND the default
background to a dark shade of that color. Returns '' if unknown."""
entry = _COLORS.get(color)
if not entry:
return ""
n_idx, n_hex, b_idx, b_hex, bg_hex = entry
seq = (
f"\\033]4;{n_idx};{n_hex}\\007"
f"\\033]4;{b_idx};{b_hex}\\007"
f"\\033]11;{bg_hex}\\007"
)
return f"printf '{seq}'"
def exec_shell_script(
agent_argv: list[str],
terminal_title: str = "",
terminal_color: str = "",
) -> str | None:
"""Build a shell script string that optionally sets the terminal
title and/or palette before running *agent_argv*, and resets the
palette + background on exit. Returns None when no decoration is
needed callers should run *agent_argv* directly in that case."""
title_cmd = (
f"printf '\\033]0;%s\\007' {shlex.quote(terminal_title)}"
if terminal_title else ""
)
pal_cmd = palette_printf(terminal_color)
if not title_cmd and not pal_cmd:
return None
parts: list[str] = []
if title_cmd:
parts.append(title_cmd)
if pal_cmd:
parts.append(pal_cmd)
parts.append(shlex.join(agent_argv))
parts.append(_RESET_PRINTF)
else:
# No palette change — exec so the agent replaces the shell.
parts.append(f"exec {shlex.join(agent_argv)}")
return "; ".join(parts)
+3 -25
View File
@@ -1,21 +1,17 @@
"""Main CLI dispatcher.
Commands: backend, cleanup, commit, edit, info, init, list, resume, start, supervise
Commands: cleanup, edit, info, init, list, resume, start, supervise
"""
from __future__ import annotations
import sys
from ..errors import MissingEnvVarError
from ..log import Die, die, error
from ..manifest import ManifestError
from ..store_manager import StoreManager
from ._common import PROG
from . import list as _list_mod
from .backend import cmd_backend
from .cleanup import cmd_cleanup
from .commit import cmd_commit
from .edit import cmd_edit
from .info import cmd_info
from .init import cmd_init
@@ -26,9 +22,7 @@ from .supervise import cmd_supervise
cmd_list = _list_mod.cmd_list
COMMANDS = {
"backend": cmd_backend,
"cleanup": cmd_cleanup,
"commit": cmd_commit,
"edit": cmd_edit,
"info": cmd_info,
"init": cmd_init,
@@ -42,9 +36,7 @@ COMMANDS = {
def usage() -> None:
sys.stderr.write(f"usage: {PROG} <command> [args...]\n\n")
sys.stderr.write("Commands:\n")
sys.stderr.write(" backend set up / check / undo a backend's host prerequisites (setup|status|teardown)\n")
sys.stderr.write(" cleanup stop and remove all active bot-bottle containers\n")
sys.stderr.write(" commit snapshot a running bottle's container state to a Docker image\n")
sys.stderr.write(" edit open an agent in vim for editing\n")
sys.stderr.write(" info print env, skills, and prompt details for a named agent\n")
sys.stderr.write(" init interactively create a new agent and add it to bot-bottle.json\n")
@@ -79,25 +71,11 @@ def main(argv: list[str] | None = None) -> int:
if handler is None:
usage()
die(f"unknown command: {command}")
mgr = StoreManager.instance()
if not mgr.is_migrated():
sys.stderr.write("bot-bottle: database schema is out of date\n")
sys.stderr.write("Migrate now? [y/N] ")
sys.stderr.flush()
try:
answer = sys.stdin.readline().strip().lower()
except EOFError:
answer = ""
if answer != "y":
error("migration required — re-run and confirm to migrate")
return 1
mgr.migrate()
try:
return handler(rest) or 0
except MissingEnvVarError as e:
error(str(e))
return 1
except ManifestError as e:
# Manifest/config problems surface as a catchable exception;
# print the reason and exit non-zero (same UX die() used to give).
error(str(e))
return 1
except Die as e:
-46
View File
@@ -1,46 +0,0 @@
"""`backend` CLI command — generic host setup/status across backends.
`./cli.py backend setup [--backend=NAME]` provisions (or points at how
to provision) the chosen backend's one-time host prerequisites.
`./cli.py backend status [--backend=NAME]` reports readiness.
`./cli.py backend teardown [--backend=NAME]` undoes setup (uninstall).
All dispatch to the backend's `setup()` / `status()` / `teardown()`
classmethods, so there are no backend-specific commands swapping
backends is just a different `--backend` (or `$BOT_BOTTLE_BACKEND`, or
the host default).
"""
from __future__ import annotations
import argparse
from ..backend import get_bottle_backend, known_backend_names
from ._common import PROG
def cmd_backend(args: list[str]) -> int:
parser = argparse.ArgumentParser(
prog=f"{PROG} backend",
description="Set up or check a backend's host prerequisites.",
)
parser.add_argument(
"action",
choices=("setup", "status", "teardown"),
help="setup: provision/print host prerequisites; status: report "
"readiness; teardown: undo setup (uninstall)",
)
parser.add_argument(
"--backend",
choices=known_backend_names(),
default=None,
help="backend to target (default: $BOT_BOTTLE_BACKEND or the host default)",
)
ns = parser.parse_args(args)
backend = get_bottle_backend(ns.backend)
if ns.action == "setup":
return backend.setup()
if ns.action == "teardown":
return backend.teardown()
return backend.status()
+8 -7
View File
@@ -1,20 +1,21 @@
"""cleanup: stop and remove all orphaned bot-bottle resources.
Walks every registered backend (docker, firecracker, macos-container)
so a single `./cli.py cleanup` reaps every backend's leftovers — a
firecracker bottle's sidecars won't survive a docker-only cleanup pass
(issue addressed alongside #77).
Walks every registered backend (docker + smolmachines) so a single
`./cli.py cleanup` reaps both backends' leftovers — orphaned
smolvm machines won't survive a docker-only cleanup pass (issue
addressed alongside #77).
Each backend's `prepare_cleanup` enumerates its own resources;
docker's `_list_orphan_state_dirs` consults
`enumerate_active_agents()` for the union of live identities so
state dirs of running non-docker bottles aren't reaped. State
state dirs of running smolmachines bottles aren't reaped. State
dirs are shared layout, so docker is the single owner of that
bucket.
State dirs with `.preserve` are intentionally never touched they
hold preserved sessions the operator may want to `resume`. Manual
`rm -rf ~/.bot-bottle/state/<identity>` is the path for those.
hold capability-block rebuilds or crash snapshots the operator may
want to `resume`. Manual `rm -rf ~/.bot-bottle/state/<identity>`
is the path for those.
"""
from __future__ import annotations
-53
View File
@@ -1,53 +0,0 @@
"""commit: freeze a running bottle's state to a resumable artifact.
Docker bottles are committed to a local Docker image. Macos-container
bottles are exported and rebuilt as a local Apple Container image.
Firecracker bottles stream the guest rootfs out over SSH and rebuild a
local Docker image. The resulting reference is stored in per-bottle
state so the next `./cli.py resume <slug>` boots from the snapshot
instead of rebuilding from the Dockerfile.
"""
from __future__ import annotations
import argparse
from ..backend import enumerate_active_agents
from ..backend.freeze import CommitCancelled, get_freezer
from ..bottle_state import read_metadata
from ..log import die
from ._common import PROG
from . import tui
def cmd_commit(argv: list[str]) -> int:
parser = argparse.ArgumentParser(prog=f"{PROG} commit", add_help=True)
parser.add_argument(
"slug",
nargs="?",
default=None,
help=(
"bottle slug from `cli.py list active` "
"(omit to pick interactively)"
),
)
args = parser.parse_args(argv)
slug = args.slug
if slug is None:
active = enumerate_active_agents()
if not active:
die("no active bottles; start one with `./cli.py start`")
choices = [a.slug for a in active]
slug = tui.filter_select(choices, title="Select bottle to commit")
if slug is None:
return 0
metadata = read_metadata(slug)
backend = metadata.backend if metadata else ""
try:
get_freezer(backend).commit_slug(slug)
except CommitCancelled:
return 0
return 0
+6 -7
View File
@@ -5,7 +5,7 @@ from __future__ import annotations
import argparse
from ..log import info
from ..manifest import ManifestIndex
from ..manifest import Manifest
from ._common import PROG, USER_CWD
@@ -14,12 +14,11 @@ def cmd_info(argv: list[str]) -> int:
parser.add_argument("name", help="agent name defined in bot-bottle.json")
args = parser.parse_args(argv)
names = ManifestIndex.resolve(USER_CWD)
names.require_agent(args.name)
manifest = names.load_for_agent(args.name)
manifest = Manifest.resolve(USER_CWD)
manifest.require_agent(args.name)
agent = manifest.agent
bottle = manifest.bottle
agent = manifest.agents[args.name]
bottle = manifest.bottle_for(args.name)
env_names = list(bottle.env.keys())
prompt_first_line = agent.prompt.splitlines()[0] if agent.prompt else ""
@@ -32,7 +31,7 @@ def cmd_info(argv: list[str]) -> int:
f"first line: {prompt_first_line or '(empty)'}"
)
info(f"bottle : {agent.bottle}")
identity = manifest.git_identity_summary()
identity = manifest.git_identity_summary(args.name)
if identity:
info(f" git identity : {identity}")
if bottle.git:
+22 -12
View File
@@ -7,15 +7,26 @@ import os
import sys
from ..backend import enumerate_active_agents
from ..manifest import ManifestIndex
from ..manifest import Manifest
from ._common import PROG, USER_CWD
_ANSI_COLOR_CODES: dict[str, str] = {
"red": "\033[91m",
"green": "\033[92m",
"yellow": "\033[93m",
"blue": "\033[94m",
"magenta": "\033[95m",
"black": "\033[30m",
"red": "\033[31m",
"green": "\033[32m",
"yellow": "\033[33m",
"blue": "\033[34m",
"magenta": "\033[35m",
"cyan": "\033[36m",
"white": "\033[37m",
"bright-black": "\033[90m",
"bright-red": "\033[91m",
"bright-green": "\033[92m",
"bright-yellow": "\033[93m",
"bright-blue": "\033[94m",
"bright-magenta": "\033[95m",
"bright-cyan": "\033[96m",
"bright-white": "\033[97m",
}
_ANSI_RESET = "\033[0m"
@@ -40,14 +51,13 @@ def cmd_list(argv: list[str]) -> int:
args = parser.parse_args(argv)
if args.scope == "available":
manifest = ManifestIndex.resolve(USER_CWD)
for name in manifest.all_agent_names:
manifest = Manifest.resolve(USER_CWD)
for name in manifest.agents.keys():
print(name)
return 0
# `active` enumerates every backend (docker, firecracker,
# macos-container) so non-docker bottles aren't hidden behind
# the env var.
# `active` enumerates every backend (docker + smolmachines)
# so smolmachines bottles aren't hidden behind the env var.
active = enumerate_active_agents()
if not active:
print("no active bot-bottle bottles", file=sys.stderr)
@@ -56,7 +66,7 @@ def cmd_list(argv: list[str]) -> int:
# Tab-separated keeps the format stable for shell pipelines.
for b in active:
services = ",".join(b.services) if b.services else "-"
display_name = f"{b.label} ({b.agent_name})" if b.label else b.agent_name
display_name = b.label if b.label else b.agent_name
colored_name = _ansi_label(display_name, b.color)
print(f"{b.backend_name}\t{b.slug}\t{colored_name}\t{services}")
return 0
+10 -8
View File
@@ -4,12 +4,13 @@ Reads ~/.bot-bottle/state/<identity>/metadata.json to recover the
(agent_name, cwd, copy_cwd) the bottle was originally started with,
then runs the same launch core as `start` but pinned to the
recorded identity so the new bottle picks up any per-bottle Dockerfile
override and transcript snapshot under the same state dir.
(from capability-block apply) and transcript snapshot under the same
state dir.
Use case: an interrupted or preserved bottle needs to be relaunched;
the operator runs
Use case: an agent calls capability-block, the dashboard approves
and tears down the bottle, the operator runs
./cli.py resume <identity>
to bring up the replacement from the recorded state.
to bring up the replacement with the new capabilities baked in.
"""
from __future__ import annotations
@@ -17,9 +18,9 @@ from __future__ import annotations
import argparse
from ..backend import BottleSpec
from ..bottle_state import read_metadata
from ..backend.docker.bottle_state import read_metadata
from ..log import die
from ..manifest import ManifestIndex
from ..manifest import Manifest
from ._common import PROG, USER_CWD
from .start import _launch_bottle
@@ -27,6 +28,7 @@ from .start import _launch_bottle
def cmd_resume(argv: list[str]) -> int:
parser = argparse.ArgumentParser(prog=f"{PROG} resume", add_help=True)
parser.add_argument("--dry-run", action="store_true")
parser.add_argument("--remote-control", action="store_true")
parser.add_argument(
"identity",
help="bottle identity from a prior `start` (see its session-end output)",
@@ -40,7 +42,7 @@ def cmd_resume(argv: list[str]) -> int:
f"check ~/.bot-bottle/state/ or run `cli.py start` to create a new bottle"
)
manifest = ManifestIndex.resolve(USER_CWD)
manifest = Manifest.resolve(USER_CWD)
manifest.require_agent(metadata.agent_name)
spec = BottleSpec(
@@ -49,11 +51,11 @@ def cmd_resume(argv: list[str]) -> int:
copy_cwd=metadata.copy_cwd,
user_cwd=metadata.cwd or USER_CWD,
identity=metadata.identity,
bottle_names=tuple(metadata.bottle_names),
)
backend_name = metadata.backend or None
return _launch_bottle(
spec,
dry_run=args.dry_run,
remote_control=args.remote_control,
backend_name=backend_name,
)
+41 -340
View File
@@ -2,11 +2,6 @@
interactive claude-code session. The container is torn down when the
session ends.
`--headless` selects a non-interactive launch (agent/bottles/label from
flags, no TUI selectors, no y/N prompt) for orchestrators,
CI, and webhook dispatch. The agent still execs on the inherited
stdio/PTY, so an orchestrator that allocates the PTY drives the session.
The launch core is shared with `cli.py resume <identity>` through
the private orchestrator `_launch_bottle`.
"""
@@ -21,23 +16,22 @@ import tempfile
from pathlib import Path
from typing import Callable
from ..agent_provider import get_provider, runtime_for
from ..agent_provider import runtime_for
from ..backend import (
Bottle,
BottleSpec,
enumerate_active_agents,
get_bottle_backend,
known_backend_names,
)
from ..backend.docker import util as docker_mod
from ..backend.docker.bottle_plan import DockerBottlePlan
from ..bottle_state import (
from ..backend.docker.bottle_state import (
cleanup_state,
is_preserved,
mark_preserved,
)
from ..log import info, die
from ..manifest import Manifest, ManifestIndex
from ..backend.docker.capability_apply import snapshot_transcript
from ..log import info
from ..manifest import Manifest
from ._common import PROG, USER_CWD, read_tty_line
from . import tui
@@ -45,49 +39,17 @@ from . import tui
def cmd_start(argv: list[str]) -> int:
parser = argparse.ArgumentParser(prog=f"{PROG} start", add_help=True)
parser.add_argument("--dry-run", action="store_true")
parser.add_argument("--cwd", action="store_true", help="copy host cwd into the running bottle")
parser.add_argument("--cwd", action="store_true", help="copy host cwd into a derived image")
parser.add_argument("--remote-control", action="store_true")
parser.add_argument(
"--backend",
choices=known_backend_names(),
default=None,
help=(
"backend to launch the bottle on (default: $BOT_BOTTLE_BACKEND "
"or host auto-selection). Overrides the env var when set."
"or 'docker'). Overrides the env var when set."
),
)
parser.add_argument(
"--headless",
action="store_true",
help=(
"non-interactive launch: take agent/bottles/label from flags, "
"skip all prompts. For orchestrators, CI, and webhooks."
),
)
parser.add_argument(
"--bottle",
action="append",
default=None,
metavar="NAME",
help=(
"bottle to compose, repeatable (order = merge order). In "
"--headless, defaults to the agent's own bottle when omitted."
),
)
parser.add_argument(
"--label",
default=None,
help="bottle label / terminal title (--headless default: agent name)",
)
parser.add_argument(
"--color",
default=None,
help="bottle color, one of the 16 ANSI color names (--headless default: none)",
)
parser.add_argument(
"--prompt",
default=None,
help="initial task prompt delivered to the agent (required with --headless)",
)
parser.add_argument(
"name",
nargs="?",
@@ -98,49 +60,27 @@ def cmd_start(argv: list[str]) -> int:
dry_run = args.dry_run or os.environ.get("BOT_BOTTLE_DRY_RUN") == "1"
manifest = ManifestIndex.resolve(USER_CWD)
backend_name: str | None = args.backend
if args.headless:
return _start_headless(
manifest, args, dry_run=dry_run, backend_name=backend_name
)
manifest = Manifest.resolve(USER_CWD)
agent_name: str | None = args.name
if agent_name is None:
if not manifest.all_agent_names:
print(
"bot-bottle: no agents defined. "
"Add an agent to ~/.bot-bottle/agents/ or ./bot-bottle/agents/ to get started.",
file=sys.stderr,
)
return 1
agent_name = tui.filter_select(
manifest.all_agent_names,
sorted(manifest.agents.keys()),
title="Select agent",
)
if agent_name is None:
return 0
# Bottle multiselect: always show after agent selection so operators
# can compose bottles at launch time without editing agent manifests.
available_bottles = manifest.all_bottle_names
lineage_map = _bottle_lineage(manifest)
display_labels = [lineage_map.get(n, n) for n in available_bottles]
label_to_name = {lineage_map.get(n, n): n for n in available_bottles}
initial_bottle = _peek_agent_bottle(manifest, agent_name)
initial_labels = [lineage_map.get(initial_bottle, initial_bottle)] if initial_bottle else []
selected_labels = tui.filter_multiselect(
display_labels,
title="Select bottles",
initial=initial_labels,
)
if selected_labels is None:
return 0
bottle_names = tuple(label_to_name.get(lbl, lbl) for lbl in selected_labels)
backend_name: str | None = args.backend
if backend_name is None and "BOT_BOTTLE_BACKEND" not in os.environ:
backend_name = tui.filter_select(
list(known_backend_names()),
title="Select backend",
)
if backend_name is None:
return 0
label, color = tui.name_color_modal(default_label=agent_name)
label, color = _resolve_unique_label(label, color)
spec = BottleSpec(
manifest=manifest,
@@ -149,93 +89,15 @@ def cmd_start(argv: list[str]) -> int:
user_cwd=USER_CWD,
label=label,
color=color,
bottle_names=bottle_names,
)
return _launch_bottle(
spec,
dry_run=dry_run,
remote_control=args.remote_control,
backend_name=backend_name,
)
# --- Headless launch -----------------------------------------------------
def _start_headless(
manifest: ManifestIndex,
args: argparse.Namespace,
*,
dry_run: bool,
backend_name: str | None,
) -> int:
"""Non-interactive launch path for orchestrators / CI / webhooks.
Resolves agent, bottles, label, and color from flags + manifest
defaults instead of the TUI selectors, and auto-confirms the
preflight. Otherwise runs the same launch core as the interactive
path, so the agent still execs on the inherited stdio/PTY an
orchestrator allocates that PTY and relays it to its
desktop/mobile clients."""
agent_name = args.name
if not agent_name:
die("--headless requires an agent name: ./cli.py start <agent> --headless")
manifest.require_agent(agent_name) # raises ManifestError if unknown
prompt = args.prompt
if not prompt:
die(
"--headless requires --prompt: "
"./cli.py start <agent> --headless --prompt 'Do the thing'"
)
if args.bottle:
bottle_names: tuple[str, ...] = tuple(args.bottle)
else:
default_bottle = _peek_agent_bottle(manifest, agent_name)
if not default_bottle:
die(
f"--headless: agent '{agent_name}' has no default bottle; "
f"pass one or more --bottle NAME"
)
bottle_names = (default_bottle,)
label = _uniquify_label_headless(args.label or agent_name)
spec = BottleSpec(
manifest=manifest,
agent_name=agent_name,
copy_cwd=args.cwd,
user_cwd=USER_CWD,
label=label,
color=args.color or "",
bottle_names=bottle_names,
headless=True,
)
return _launch_bottle(
spec,
dry_run=dry_run,
backend_name=backend_name,
assume_yes=True,
headless_prompt_text=prompt,
)
def _uniquify_label_headless(label: str) -> str:
"""Non-interactive analog of `_resolve_unique_label`: if the label's
slug collides with a running bottle, append -2, -3, until free,
logging the chosen label. Orchestrators fire-and-forget many bottles,
so silently picking a free name beats erroring on every collision."""
active_slugs = {a.slug for a in enumerate_active_agents()}
if docker_mod.slugify(label) not in active_slugs:
return label
n = 2
while docker_mod.slugify(f"{label}-{n}") in active_slugs:
n += 1
chosen = f"{label}-{n}"
info(f"label '{label}' already in use; using '{chosen}'")
return chosen
# --- Launch helpers ------------------------------------------------------
@@ -243,7 +105,7 @@ def prepare_with_preflight(
spec: BottleSpec,
*,
stage_dir: Path,
render_preflight: Callable[[DockerBottlePlan, str], None],
render_preflight: Callable[[DockerBottlePlan], None],
prompt_yes: Callable[[], bool],
dry_run: bool = False,
backend_name: str | None = None,
@@ -252,8 +114,8 @@ def prepare_with_preflight(
injected callable, prompt y/N via the injected callable.
`backend_name` selects which backend prepares the plan
(`None` `$BOT_BOTTLE_BACKEND` host auto-selection). The CLI
passes whatever `--backend` resolved to.
(`None` `$BOT_BOTTLE_BACKEND` `docker`). The CLI passes
whatever `--backend` resolved to.
Returns `(plan, identity)`. `plan` is None on dry-run or
operator-N, but `identity` is set as soon as `backend.prepare`
@@ -264,7 +126,7 @@ def prepare_with_preflight(
plan = backend.prepare(spec, stage_dir=stage_dir)
identity = _identity_from_plan(plan)
render_preflight(plan, backend.name)
render_preflight(plan)
if dry_run:
info("dry-run requested; not starting container.")
@@ -276,9 +138,8 @@ def prepare_with_preflight(
def attach_agent(
bottle: Bottle, *, resume: bool = False,
bottle: Bottle, *, remote_control: bool = False, resume: bool = False,
agent_provider_template: str = "claude",
startup_args: tuple[str, ...] = (),
) -> int:
"""Run the selected provider CLI inside `bottle` as an
interactive session. Blocks until the session ends; returns the
@@ -295,7 +156,8 @@ def attach_agent(
"(Ctrl-D or 'exit' to leave; container will be removed)"
)
agent_args = list(runtime.bypass_args)
agent_args.extend(startup_args)
if remote_control:
agent_args.extend(runtime.remote_control_args)
if resume:
agent_args.extend(runtime.resume_args)
return bottle.exec_agent(agent_args, tty=True)
@@ -310,7 +172,7 @@ def capture_claude_session_state(identity: str, exit_code: int) -> None:
# instead of relying on each agent's transcript layout.
if not identity:
return
# snapshot_transcript(identity)
snapshot_transcript(identity)
if exit_code != 0:
mark_preserved(identity)
@@ -334,53 +196,6 @@ def _identity_from_plan(plan: object) -> str:
return getattr(plan, "slug", "")
def _peek_agent_bottle(manifest: ManifestIndex, agent_name: str) -> str:
"""Return the `bottle:` value from the named agent's frontmatter without
fully parsing the agent file, or "" when absent or unreadable.
Used to pre-populate the bottle multiselect with the agent's default
bottle so operators who haven't removed `bottle:` from their manifests
don't need to re-select it every time."""
if manifest.home_md is None:
# Eager mode (from_json_obj): agent is pre-parsed.
if agent_name in manifest.agents:
return manifest.agents[agent_name].bottle
return ""
from ..manifest_loader import scan_agent_names
from ..yaml_subset import YamlSubsetError, parse_frontmatter
home_agents = scan_agent_names(manifest.home_md / "agents")
cwd_agents: dict[str, Path] = {}
if manifest.cwd_md is not None:
cwd_agents = scan_agent_names(manifest.cwd_md / "agents")
merged = {**home_agents, **cwd_agents}
path = merged.get(agent_name)
if path is None:
return ""
try:
fm, _ = parse_frontmatter(path.read_text())
bottle = fm.get("bottle", "")
return str(bottle) if isinstance(bottle, str) else ""
except (OSError, YamlSubsetError):
return ""
def _resolve_unique_label(label: str, color: str) -> tuple[str, str]:
"""Re-prompt with a disclaimer until the label's slug is not already
in use among running bottles. Passes through unchanged when no
collision is found on the first check."""
while True:
slug_candidate = docker_mod.slugify(label)
active_slugs = {a.slug for a in enumerate_active_agents()}
if slug_candidate not in active_slugs:
return label, color
label, color = tui.name_color_modal(
default_label=label,
disclaimer=f'"{label}" is already in use',
)
def _text_prompt_yes() -> bool:
"""Default `prompt_yes` for CLI use: reads y/N from the
controlling tty via stderr prompt + tty-line read."""
@@ -390,141 +205,30 @@ def _text_prompt_yes() -> bool:
return reply in ("y", "Y", "yes", "YES")
def _text_render_preflight():
def _render(plan: DockerBottlePlan, backend_name: str) -> None:
print(file=sys.stderr)
print(f"backend: {backend_name}", file=sys.stderr)
print(_manifest_to_yaml(plan.manifest), file=sys.stderr)
def _text_render_preflight(*, remote_control: bool):
def _render(plan: DockerBottlePlan) -> None:
plan.print(remote_control=remote_control)
return _render
def _bottle_lineage(manifest: ManifestIndex) -> dict[str, str]:
"""Return {bottle_name: lineage_label} for bottles that have an extends chain.
Bottles without a parent are omitted (the caller falls back to the bare name).
Labels show the chain root-first: e.g. 'dev -> bot-bottle-dev -> claude-dev'."""
if manifest.home_md is None:
return {}
bottles_dir = manifest.home_md / "bottles"
if not bottles_dir.is_dir():
return {}
from ..yaml_subset import YamlSubsetError, parse_frontmatter
extends_of: dict[str, str] = {}
for path in bottles_dir.glob("*.md"):
try:
fm, _ = parse_frontmatter(path.read_text())
parent = fm.get("extends", "")
if isinstance(parent, str) and parent:
extends_of[path.stem] = parent
except (OSError, YamlSubsetError):
pass
labels: dict[str, str] = {}
for name in extends_of:
chain = [name]
seen = {name}
cur = name
while cur in extends_of:
par = extends_of[cur]
if par in seen:
break
chain.append(par)
seen.add(par)
cur = par
labels[name] = " -> ".join(reversed(chain))
return labels
def _manifest_to_yaml(manifest: Manifest) -> str:
"""Serialize the resolved Manifest to a YAML string for preflight display."""
lines: list[str] = []
agent = manifest.agent
lines.append("agent:")
if agent.skills:
lines.append(" skills:")
for s in agent.skills:
lines.append(f" - {s}")
if not agent.git_user.is_empty():
lines.append(" git-gate:")
lines.append(" user:")
if agent.git_user.name:
lines.append(f" name: {agent.git_user.name}")
if agent.git_user.email:
lines.append(f" email: {agent.git_user.email}")
bottle = manifest.bottle
lines.append("bottle:")
if bottle.agent_provider.template != "claude" or bottle.agent_provider.dockerfile:
lines.append(" agent_provider:")
lines.append(f" template: {bottle.agent_provider.template}")
if bottle.agent_provider.dockerfile:
lines.append(f" dockerfile: {bottle.agent_provider.dockerfile}")
if bottle.env:
lines.append(" env:")
for k, v in sorted(bottle.env.items()):
lines.append(f" {k}: {v}")
has_git_gate = not bottle.git_user.is_empty() or bottle.git
if has_git_gate:
lines.append(" git-gate:")
if not bottle.git_user.is_empty():
lines.append(" user:")
if bottle.git_user.name:
lines.append(f" name: {bottle.git_user.name}")
if bottle.git_user.email:
lines.append(f" email: {bottle.git_user.email}")
if bottle.git:
lines.append(" repos:")
for entry in bottle.git:
lines.append(f" {entry.Name}:")
lines.append(f" url: {entry.Upstream}")
if bottle.egress.routes:
lines.append(" egress:")
lines.append(" routes:")
for r in bottle.egress.routes:
lines.append(f" - host: {r.Host}")
if r.AuthScheme:
lines.append(f" auth:")
lines.append(f" scheme: {r.AuthScheme}")
lines.append(f" supervise: {'true' if bottle.supervise else 'false'}")
return "\n".join(lines)
def _launch_bottle(
spec: BottleSpec,
*,
dry_run: bool,
remote_control: bool,
backend_name: str | None = None,
assume_yes: bool = False,
headless_prompt_text: str = "",
) -> int:
"""Shared launch core for `start` and `resume`. Builds the plan,
prints / dry-runs / prompts as appropriate, brings the bottle up,
attaches claude, and prints the resume hint on session end.
`assume_yes` skips the interactive y/N confirmation (headless /
orchestrator launches), where there is no human at the prompt.
`headless_prompt_text` is passed to the provider's `headless_prompt`
method and the resulting args are appended to startup_args so the
agent receives the initial task without interactive input."""
attaches claude, and prints the resume hint on session end."""
stage_dir = Path(tempfile.mkdtemp(prefix="bot-bottle-stage."))
identity = ""
try:
plan, identity = prepare_with_preflight(
spec,
stage_dir=stage_dir,
render_preflight=_text_render_preflight(),
prompt_yes=(lambda: True) if assume_yes else _text_prompt_yes,
render_preflight=_text_render_preflight(remote_control=remote_control),
prompt_yes=_text_prompt_yes,
dry_run=dry_run,
backend_name=backend_name,
)
@@ -534,17 +238,10 @@ def _launch_bottle(
backend = get_bottle_backend(backend_name)
with backend.launch(plan) as bottle:
agent_provider_template = getattr(plan, "agent_provider_template", "claude")
extra_args: tuple[str, ...] = ()
if headless_prompt_text:
extra_args = tuple(
get_provider(agent_provider_template).headless_prompt(
headless_prompt_text
)
)
exit_code = attach_agent(
bottle,
remote_control=remote_control,
agent_provider_template=agent_provider_template,
startup_args=plan.agent_provision.startup_args + extra_args,
)
info(
f"session ended (exit {exit_code}); "
@@ -552,8 +249,12 @@ def _launch_bottle(
)
# While the container is still alive: always snapshot the
# transcript and — if the agent exited non-zero — mark
# the state for preservation. This picks up crashes /
# Ctrl-Cs / OOM kills before cleanup removes the state dir.
# the state for preservation. Capability-block already
# did both before triggering teardown from the dashboard;
# this picks up crashes / Ctrl-Cs / OOM kills the same
# way. snapshot_transcript is best-effort so the
# capability-block path's prior snapshot isn't clobbered
# when the container is already gone.
if agent_provider_template == "claude":
capture_claude_session_state(identity, exit_code)
return 0
+55 -89
View File
@@ -2,8 +2,8 @@
act on them (approve / modify / reject).
Curses-based TUI; modify-then-approve shells out to $EDITOR. The
Egress proposals are queued for operator review as full routes.yaml
updates.
approval handler wires to PRD 0016 (capability-block), which rebuilds
the bottle Dockerfile. The egress-block tool was removed in issue #198.
"""
from __future__ import annotations
@@ -19,17 +19,13 @@ from dataclasses import dataclass
from datetime import datetime, timezone
from pathlib import Path
from ..paths import bot_bottle_root
from ..bottle_state import read_metadata
from ..backend.docker.egress_apply import (
EgressApplyError,
applicator as _docker_applicator,
)
from ..backend.macos_container.egress_apply import (
applicator as _macos_applicator,
from .. import supervise as _supervise
from ..backend.docker.bottle_state import read_metadata
from ..backend.docker.capability_apply import (
CapabilityApplyError,
apply_capability_change,
)
from ..log import Die, error, info
from ..supervise import (
COMPONENT_FOR_TOOL,
AuditEntry,
@@ -38,11 +34,9 @@ from ..supervise import (
STATUS_APPROVED,
STATUS_MODIFIED,
STATUS_REJECTED,
TOOL_EGRESS_ALLOW,
TOOL_EGRESS_BLOCK,
TOOL_GITLEAKS_ALLOW,
TOOL_EGRESS_TOKEN_ALLOW,
list_all_pending_proposals,
TOOL_CAPABILITY_BLOCK,
archive_proposal,
list_pending_proposals,
render_diff,
write_audit_entry,
write_response,
@@ -52,39 +46,32 @@ from ._common import PROG
_REFRESH_INTERVAL_MS = 1000
# Proposal tools whose payload is a read-only report, not a file the operator
# edits: modify is unavailable and approval requires a recorded reason for the
# audit trail.
_REPORT_ONLY_TOOLS: tuple[str, ...] = (TOOL_GITLEAKS_ALLOW, TOOL_EGRESS_TOKEN_ALLOW)
@dataclass(frozen=True)
class QueuedProposal:
"""A pending proposal from the supervise queue."""
"""A pending proposal plus the queue dir it was found in."""
proposal: Proposal
queue_dir: Path
# Errors any remediation engine may raise. Caught by the TUI key
# handlers and surfaced in the status line so a failed apply keeps
# the proposal pending rather than crashing curses.
ApplyError = (EgressApplyError,)
def apply_routes_change(slug: str, content: str) -> tuple[str, str]:
meta = read_metadata(slug)
backend = meta.backend if meta is not None else ""
if backend == "macos-container":
return _macos_applicator.apply_routes_change(slug, content)
return _docker_applicator.apply_routes_change(slug, content)
ApplyError = (CapabilityApplyError,)
def discover_pending() -> list[QueuedProposal]:
"""Collect pending proposals across bottles."""
out = [
QueuedProposal(proposal=proposal)
for proposal in list_all_pending_proposals()
]
"""Walk ~/.bot-bottle/queue/* and collect pending proposals."""
queue_root = _supervise.bot_bottle_root() / "queue"
if not queue_root.is_dir():
return []
out: list[QueuedProposal] = []
for slug_dir in sorted(queue_root.iterdir()):
if not slug_dir.is_dir():
continue
for proposal in list_pending_proposals(slug_dir):
out.append(QueuedProposal(proposal=proposal, queue_dir=slug_dir))
out.sort(key=lambda q: q.proposal.arrival_timestamp)
return out
@@ -107,6 +94,7 @@ def _detail_lines(
(f"tool: {p.tool}", 0),
(f"id: {p.id}", 0),
(f"arrived: {p.arrival_timestamp}", 0),
(f"queue: {qp.queue_dir}", 0),
("", 0),
("justification:", 0),
]
@@ -120,10 +108,8 @@ def _detail_lines(
def _suffix_for_tool(tool: str) -> str:
if tool in (TOOL_EGRESS_ALLOW, TOOL_EGRESS_BLOCK):
return ".yaml"
if tool in (TOOL_GITLEAKS_ALLOW, TOOL_EGRESS_TOKEN_ALLOW):
return ".txt"
if tool == TOOL_CAPABILITY_BLOCK:
return ".dockerfile"
return ".txt"
@@ -141,10 +127,16 @@ def approve(
file_to_apply = final_file if final_file is not None else qp.proposal.proposed_file
diff_before, diff_after = "", ""
if qp.proposal.tool in (TOOL_EGRESS_ALLOW, TOOL_EGRESS_BLOCK):
diff_before, diff_after = apply_routes_change(
qp.proposal.bottle_slug,
file_to_apply,
if qp.proposal.tool == TOOL_CAPABILITY_BLOCK:
_meta = read_metadata(qp.proposal.bottle_slug)
if _meta is not None and not _meta.compose_project:
raise CapabilityApplyError(
"capability-block remediation is not supported for smolmachines "
"bottles. Reject this proposal or handle the capability change "
"manually, then restart the bottle."
)
diff_before, diff_after = apply_capability_change(
qp.proposal.bottle_slug, file_to_apply,
)
response = Response(
@@ -153,11 +145,14 @@ def approve(
notes=notes,
final_file=final_file,
)
write_response(qp.proposal.bottle_slug, response)
write_response(qp.queue_dir, response)
_write_audit(
qp, action=status, notes=notes,
diff_before=diff_before, diff_after=diff_after,
)
if qp.proposal.tool == TOOL_CAPABILITY_BLOCK:
archive_proposal(qp.queue_dir, qp.proposal.id)
def reject(qp: QueuedProposal, *, reason: str) -> None:
"""Write a rejection response and an audit entry."""
@@ -167,27 +162,10 @@ def reject(qp: QueuedProposal, *, reason: str) -> None:
notes=reason,
final_file=None,
)
write_response(qp.proposal.bottle_slug, response)
write_response(qp.queue_dir, response)
_write_audit(qp, action=STATUS_REJECTED, notes=reason, diff_before="", diff_after="")
def _approve_from_tui(
stdscr: "curses._CursesWindow", # type: ignore
qp: QueuedProposal,
*,
final_file: str | None = None,
notes: str = "",
) -> str:
"""Approve from curses, prompting for any tool-specific audit note."""
if qp.proposal.tool in _REPORT_ONLY_TOOLS and final_file is None:
notes = _prompt(stdscr, "allow reason (false positive / legitimately needed): ")
if not notes:
return "approve aborted (empty reason)"
approve(qp, final_file=final_file, notes=notes)
verb = "modified+approved" if final_file is not None else "approved"
return _approval_status(qp, verb)
def _write_audit(
qp: QueuedProposal,
*,
@@ -259,10 +237,7 @@ def cmd_supervise(argv: list[str]) -> int:
return e.code if isinstance(e.code, int) else 1
except Exception as e: # noqa: W0718 — catch supervise crash for logging
log_path = _write_crash_log(e)
error(
f"supervise crashed: {type(e).__name__}: {e}",
context={"error_type": type(e).__name__, "crash_log": str(log_path)},
)
error(f"supervise crashed: {type(e).__name__}: {e}")
error(f"full traceback written to {log_path}")
return 1
return 0
@@ -276,7 +251,7 @@ def _write_crash_log(exc: BaseException) -> Path:
)
entry = f"=== supervise crash {stamp} ===\n{body}\n"
try:
log_dir = bot_bottle_root() / "logs"
log_dir = _supervise.bot_bottle_root() / "logs"
log_dir.mkdir(parents=True, exist_ok=True)
path = log_dir / "supervise-crash.log"
with path.open("a", encoding="utf-8") as fh:
@@ -307,7 +282,7 @@ def _list_once() -> int:
return 0
def _try_init_green() -> int: # pragma: no cover
def _try_init_green() -> int:
"""Initialise a green color pair and return its attr, or 0."""
try:
curses.start_color()
@@ -318,7 +293,7 @@ def _try_init_green() -> int: # pragma: no cover
return 0
def _main_loop(stdscr: "curses._CursesWindow") -> None: # type: ignore # pragma: no cover
def _main_loop(stdscr: "curses._CursesWindow") -> None: # type: ignore
curses.curs_set(0)
stdscr.timeout(_REFRESH_INTERVAL_MS)
green_attr = _try_init_green()
@@ -374,22 +349,18 @@ def _main_loop(stdscr: "curses._CursesWindow") -> None: # type: ignore # pragm
_detail_view(stdscr, qp, green_attr=green_attr)
elif key == ord("a"):
try:
status_line = _approve_from_tui(stdscr, qp)
approve(qp)
status_line = _approval_status(qp, "approved")
except ApplyError as e:
status_line = f"apply failed: {e}"
elif key == ord("m"):
if qp.proposal.tool in _REPORT_ONLY_TOOLS:
status_line = f"modify unavailable for {qp.proposal.tool}"
continue
edited = _modify(stdscr, qp)
if edited is None:
status_line = "modify aborted (no change)"
else:
try:
status_line = _approve_from_tui(
stdscr, qp, final_file=edited,
notes="operator modified before approving",
)
approve(qp, final_file=edited, notes="operator modified before approving")
status_line = _approval_status(qp, "modified+approved")
except ApplyError as e:
status_line = f"apply failed: {e}"
elif key == ord("r"):
@@ -408,7 +379,7 @@ def _render(
status_line: str,
*,
green_attr: int = 0, # noqa: F841 — unused, but required by interface
) -> None: # pragma: no cover
) -> None:
stdscr.erase()
h, w = stdscr.getmaxyx()
header = f"bot-bottle supervise ({len(pending)} pending)"
@@ -459,7 +430,7 @@ def _detail_view(
qp: QueuedProposal,
*,
green_attr: int = 0,
) -> None: # pragma: no cover
) -> None:
"""Render the full proposal. Scrollable. Press q to return."""
lines = _detail_lines(qp, green_attr=green_attr)
offset = 0
@@ -487,20 +458,15 @@ def _detail_view(
offset = max(0, len(lines) - 1)
elif key == ord("a"):
try:
_approve_from_tui(stdscr, qp)
approve(qp)
except ApplyError:
pass
return
elif key == ord("m"):
if qp.proposal.tool in _REPORT_ONLY_TOOLS:
return
edited = _modify(stdscr, qp)
if edited is not None:
try:
_approve_from_tui(
stdscr, qp, final_file=edited,
notes="operator modified before approving",
)
approve(qp, final_file=edited, notes="operator modified before approving")
except ApplyError:
pass
return
@@ -511,7 +477,7 @@ def _detail_view(
return
def _modify(stdscr: "curses._CursesWindow", qp: QueuedProposal) -> str | None: # type: ignore # pragma: no cover
def _modify(stdscr: "curses._CursesWindow", qp: QueuedProposal) -> str | None: # type: ignore
"""Suspend curses, open $EDITOR on the proposed file, return edited content."""
suffix = _suffix_for_tool(qp.proposal.tool)
curses.endwin()
@@ -522,7 +488,7 @@ def _modify(stdscr: "curses._CursesWindow", qp: QueuedProposal) -> str | None:
return edited
def _prompt(stdscr: "curses._CursesWindow", label: str) -> str: # type: ignore # pragma: no cover
def _prompt(stdscr: "curses._CursesWindow", label: str) -> str: # type: ignore
"""One-line input at the bottom of the screen."""
curses.curs_set(1)
h, _ = stdscr.getmaxyx()
+19 -319
View File
@@ -17,43 +17,6 @@ import sys
from typing import Any, Optional
def filter_multiselect(
items: list[str],
*,
title: str = "",
initial: Optional[list[str]] = None,
tty_path: str = "/dev/tty",
) -> Optional[list[str]]:
"""Render a multi-select picker over *items*.
Returns the ordered list of selected items, or ``None`` if the user
cancelled (Esc / ``q`` / Ctrl-C / Ctrl-D with no items).
Press Space to toggle the item under the cursor.
Press Enter to confirm the current selection.
Press Ctrl-D to confirm the current selection (returns even if empty).
Press Esc/q to cancel (returns None).
*initial* pre-populates the selection in insertion order. Items
added are appended; removed items leave the remaining order unchanged.
"""
if not items:
return []
try:
tty_fd = open(tty_path, "r+b", buffering=0)
except OSError:
return None
try:
fd_dup = os.dup(tty_fd.fileno())
return _run_multiselect(
items, title=title, initial=list(initial or []), tty_fd=fd_dup
)
finally:
tty_fd.close()
def filter_select(
items: list[str],
*,
@@ -258,283 +221,25 @@ def _addstr_safe(screen: Any, row: int, col: int, text: str, attr: int = curses.
pass
# ---------------------------------------------------------------------------
# filter_multiselect internals
# ---------------------------------------------------------------------------
_KEY_SPACE = 32
def _run_multiselect(
items: list[str], *, title: str, initial: list[str], tty_fd: int
) -> Optional[list[str]]:
"""Drive a curses multi-select session on *tty_fd*."""
os.environ.setdefault("TERM", "xterm-256color")
orig_stdin = sys.__stdin__
orig_stdout = sys.__stdout__
try:
import io
tty_text = io.TextIOWrapper(io.FileIO(tty_fd, mode='r+'), write_through=True)
sys.__stdin__ = tty_text # type: ignore[assignment]
sys.__stdout__ = tty_text # type: ignore[assignment]
screen = curses.initscr()
curses.noecho()
curses.cbreak()
screen.keypad(True)
try:
result = _multiselect_loop(screen, items, title=title, initial=initial)
finally:
screen.keypad(False)
curses.nocbreak()
curses.echo()
curses.endwin()
except Exception: # noqa: W0718
return None
finally:
sys.__stdin__ = orig_stdin # type: ignore[assignment]
sys.__stdout__ = orig_stdout # type: ignore[assignment]
return result
def _toggle_membership(items: list[str], item: str) -> None:
"""Add `item` if absent, remove it if present (in place)."""
if item in items:
items.remove(item)
else:
items.append(item)
def _handle_order_key(key: int, selected: list[str], order_cursor: int) -> int:
"""Apply a keypress in 'order' focus: navigate, reorder, or remove the
item at `order_cursor`. Mutates `selected` in place and returns the new
order cursor."""
if key in (curses.KEY_UP, ord("k")):
if order_cursor > 0:
order_cursor -= 1
elif key in (curses.KEY_DOWN, ord("j")):
if order_cursor < len(selected) - 1:
order_cursor += 1
elif key == ord("K"):
# Move selected item up (earlier in order).
if order_cursor > 0:
i = order_cursor
selected[i - 1], selected[i] = selected[i], selected[i - 1]
order_cursor -= 1
elif key == ord("J"):
# Move selected item down (later in order).
if order_cursor < len(selected) - 1:
i = order_cursor
selected[i], selected[i + 1] = selected[i + 1], selected[i]
order_cursor += 1
elif key in (curses.KEY_ENTER, _KEY_ENTER_ALT, ord("\r"), _KEY_SPACE):
# Remove item from selection while in order mode.
del selected[order_cursor]
if order_cursor >= len(selected) and order_cursor > 0:
order_cursor -= 1
return order_cursor
def _multiselect_loop(
screen: Any, items: list[str], *, title: str, initial: list[str]
) -> Optional[list[str]]:
query = ""
cursor = 0
selected: list[str] = [s for s in initial if s in items]
# focus = "filter": navigate + toggle items in the filterable list
# focus = "order": navigate + reorder items in the selected list
focus = "filter"
order_cursor = 0
while True:
filtered = _filter_items(items, query)
if not filtered:
cursor = 0
elif cursor >= len(filtered):
cursor = len(filtered) - 1
if not selected:
order_cursor = 0
if focus == "order":
focus = "filter"
elif order_cursor >= len(selected):
order_cursor = len(selected) - 1
try:
_render_multiselect(
screen, filtered, cursor,
query=query, title=title, selected=selected,
focus=focus, order_cursor=order_cursor,
)
except curses.error:
return None
try:
key = screen.getch()
except KeyboardInterrupt:
return None
if key in (_KEY_ESC, _KEY_CTRL_C, ord("q")):
return None
if key == _KEY_CTRL_D:
return list(selected)
# Tab toggles between filter and order focus.
if key == ord("\t"):
if focus == "filter" and selected:
focus = "order"
order_cursor = 0
else:
focus = "filter"
continue
if focus == "filter":
if key in (curses.KEY_ENTER, _KEY_ENTER_ALT, ord("\r")):
return list(selected)
elif key == _KEY_SPACE:
if filtered:
_toggle_membership(selected, filtered[cursor])
elif key in (curses.KEY_UP, ord("k")):
if cursor > 0:
cursor -= 1
elif key in (curses.KEY_DOWN, ord("j")):
if cursor < len(filtered) - 1:
cursor += 1
elif key in (curses.KEY_BACKSPACE, _KEY_BACKSPACE_WIN, 127):
query = query[:-1]
new_filtered = _filter_items(items, query)
if cursor >= len(new_filtered):
cursor = max(0, len(new_filtered) - 1)
elif 32 <= key <= 126 and key != _KEY_SPACE:
query += chr(key)
cursor = 0
else: # focus == "order"
order_cursor = _handle_order_key(key, selected, order_cursor)
def _render_multiselect(
screen: Any,
filtered: list[str],
cursor: int,
*,
query: str,
title: str,
selected: list[str],
focus: str = "filter",
order_cursor: int = 0,
) -> None:
screen.erase()
rows, cols = screen.getmaxyx()
min_rows = 7
if rows < min_rows:
raise curses.error("terminal too small")
sep = "" * min(cols - 1, 40)
row = 0
if title and row < rows - 1:
_addstr_safe(screen, row, 0, title[:cols - 1], curses.A_BOLD)
row += 1
# Filter line — dim when focus is on the order panel.
filter_label = f"Filter: {query}"
filter_hint = " [Tab: reorder]" if focus == "filter" and selected else ""
filter_attr = curses.A_DIM if focus == "order" else curses.A_NORMAL
if row < rows - 1:
_addstr_safe(screen, row, 0, (filter_label + filter_hint)[:cols - 1], filter_attr)
row += 1
if row < rows - 1:
_addstr_safe(screen, row, 0, sep)
row += 1
# Compute how many rows the bottom order panel needs.
# Cap the visible selected list to keep the filter list legible.
order_rows = min(len(selected), max(1, (rows - row) // 3)) if selected else 0
# Bottom reserved: sep + order_rows + sep + help = order_rows + 3
bottom_reserved = order_rows + 3
list_start = row
list_rows = rows - list_start - bottom_reserved
if list_rows < 1:
list_rows = 1
selected_set = set(selected)
filter_dim = focus == "order"
scroll = max(0, cursor - list_rows + 1)
visible = filtered[scroll: scroll + list_rows]
for idx, item in enumerate(visible):
abs_idx = scroll + idx
mark = "[*]" if item in selected_set else "[ ]"
prefix = "> " if (abs_idx == cursor and focus == "filter") else " "
line = (prefix + mark + " " + item)[:cols - 1]
item_attr = curses.A_DIM if filter_dim else (
curses.A_REVERSE if abs_idx == cursor else curses.A_NORMAL
)
if row < rows - bottom_reserved:
_addstr_safe(screen, row, 0, line, item_attr)
row += 1
# Separator before the order panel.
if row < rows - (order_rows + 2):
_addstr_safe(screen, row, 0, sep)
row += 1
# Order panel.
order_scroll = max(0, order_cursor - order_rows + 1)
order_visible = selected[order_scroll: order_scroll + order_rows]
for idx, item in enumerate(order_visible):
abs_idx = order_scroll + idx
is_active = focus == "order" and abs_idx == order_cursor
prefix = "> " if is_active else " "
line = (prefix + item)[:cols - 1]
attr = curses.A_REVERSE if is_active else curses.A_NORMAL
if row < rows - 2:
_addstr_safe(screen, row, 0, line, attr)
row += 1
if row < rows - 1:
_addstr_safe(screen, row, 0, sep)
row += 1
if focus == "filter":
help_line = "[↑↓/jk] move [Space] toggle [Enter] confirm [Tab] reorder [Esc/q] cancel"
else:
help_line = "[↑↓/jk] cursor [K/J] reorder [Space/Enter] remove [Tab] back [Ctrl-D] done"
if row < rows:
_addstr_safe(screen, min(rows - 1, row), 0, help_line[:cols - 1])
screen.refresh()
# ---------------------------------------------------------------------------
# name_color_modal — two-step label + color picker
# ---------------------------------------------------------------------------
_ANSI_COLORS = [
"red", "green", "yellow", "blue", "magenta",
"red", "green", "blue", "yellow", "magenta", "cyan", "white", "black",
"bright-red", "bright-green", "bright-blue", "bright-yellow",
"bright-magenta", "bright-cyan", "bright-white", "bright-black",
]
_CURSES_COLOR_MAP: dict[str, int] = {
"black": curses.COLOR_BLACK,
"red": curses.COLOR_RED,
"green": curses.COLOR_GREEN,
"yellow": curses.COLOR_YELLOW,
"blue": curses.COLOR_BLUE,
"magenta": curses.COLOR_MAGENTA,
"cyan": curses.COLOR_CYAN,
"white": curses.COLOR_WHITE,
}
_COLOR_NONE = "(none)"
@@ -543,15 +248,11 @@ _COLOR_NONE = "(none)"
def name_color_modal(
default_label: str,
*,
disclaimer: str = "",
tty_path: str = "/dev/tty",
) -> tuple[str, str]:
"""Present a two-step curses modal: first edit the agent label,
then optionally pick a color.
``disclaimer`` is shown below the input field use it to surface
an error from a previous attempt (e.g. name already in use).
Returns ``(label, color)`` where ``color`` is one of the 16 ANSI
color name strings or ``""`` for no color. Falls back to
``(default_label, "")`` on any error (terminal too small, not a tty).
@@ -563,14 +264,14 @@ def name_color_modal(
try:
fd_dup = os.dup(tty_fd.fileno())
return _run_name_color(default_label, tty_fd=fd_dup, disclaimer=disclaimer)
return _run_name_color(default_label, tty_fd=fd_dup)
except Exception: # noqa: BLE001 # pylint: disable=broad-exception-caught
return default_label, ""
finally:
tty_fd.close()
def _run_name_color(default_label: str, *, tty_fd: int, disclaimer: str = "") -> tuple[str, str]:
def _run_name_color(default_label: str, *, tty_fd: int) -> tuple[str, str]:
import io
orig_stdin = sys.__stdin__
orig_stdout = sys.__stdout__
@@ -585,7 +286,7 @@ def _run_name_color(default_label: str, *, tty_fd: int, disclaimer: str = "") ->
curses.cbreak()
screen.keypad(True)
try:
label = _label_step(screen, default_label, disclaimer=disclaimer)
label = _label_step(screen, default_label)
color = _color_step(screen, label)
finally:
screen.keypad(False)
@@ -598,14 +299,14 @@ def _run_name_color(default_label: str, *, tty_fd: int, disclaimer: str = "") ->
return label, color
def _label_step(screen: Any, default_label: str, *, disclaimer: str = "") -> str:
def _label_step(screen: Any, default_label: str) -> str:
"""Step 1: edit the label. First printable key replaces the
pre-fill; subsequent keys append. Enter confirms."""
text = default_label
replaced = False # True once the user has typed their first char
while True:
_render_label(screen, text, disclaimer=disclaimer)
_render_label(screen, text)
try:
key = screen.getch()
except KeyboardInterrupt:
@@ -629,7 +330,7 @@ def _label_step(screen: Any, default_label: str, *, disclaimer: str = "") -> str
text += chr(key)
def _render_label(screen: Any, text: str, *, disclaimer: str = "") -> None:
def _render_label(screen: Any, text: str) -> None:
screen.erase()
rows, cols = screen.getmaxyx()
sep = "" * min(cols - 1, 40)
@@ -637,12 +338,8 @@ def _render_label(screen: Any, text: str, *, disclaimer: str = "") -> None:
_addstr_safe(screen, 1, 0, sep)
_addstr_safe(screen, 2, 0, text[:cols - 1], curses.A_REVERSE)
_addstr_safe(screen, 3, 0, sep)
row = 4
if disclaimer and rows > row + 1:
_addstr_safe(screen, row, 0, disclaimer[:cols - 1], curses.A_BOLD)
row += 1
if rows > row + 1:
_addstr_safe(screen, row, 0, "[any key] edit [Enter] confirm", curses.A_DIM)
if rows > 5:
_addstr_safe(screen, 5, 0, "[any key] edit [Enter] confirm", curses.A_DIM)
screen.refresh()
@@ -682,10 +379,13 @@ def _init_color_pairs() -> dict[str, int]:
curses.use_default_colors()
pair_idx = 2 # pair 1 reserved for other uses
for name in _ANSI_COLORS:
fg = _CURSES_COLOR_MAP.get(name, curses.COLOR_WHITE)
base = name.replace("bright-", "")
fg = _CURSES_COLOR_MAP.get(base, curses.COLOR_WHITE)
try:
curses.init_pair(pair_idx, fg, -1)
attr = curses.color_pair(pair_idx) | curses.A_BOLD
attr = curses.color_pair(pair_idx)
if name.startswith("bright-"):
attr |= curses.A_BOLD
attrs[name] = attr
pair_idx += 1
except curses.error:
+19 -113
View File
@@ -17,12 +17,9 @@ from typing import TYPE_CHECKING
from ...agent_provider import (
AgentProvider,
AgentProviderRuntime,
AgentProvisionDir,
AgentProvisionFile,
AgentProvisionPlan,
provider_startup_args,
)
from ...backend.docker import util as docker_mod
from ...egress import EgressRoute
from ...log import die, info, warn
@@ -31,6 +28,8 @@ if TYPE_CHECKING:
from ...backend import Bottle, BottlePlan
_REPO_ROOT = Path(__file__).resolve().parents[3]
_SUPERVISE_MCP_NAME = "supervise"
@@ -41,56 +40,15 @@ def _skills_dir(guest_home: str) -> str:
def _prompt_path(guest_home: str) -> str:
return f"{guest_home}/.bot-bottle-prompt.txt"
_STATUS_LINE_COLORS = {
"red": "\033[91m",
"green": "\033[92m",
"yellow": "\033[93m",
"blue": "\033[94m",
"magenta": "\033[95m",
}
_CLAUDE_THEME_COLORS = {
"red": "redBright",
"green": "greenBright",
"yellow": "yellowBright",
"blue": "blueBright",
"magenta": "magentaBright",
}
def _status_line_script(label: str, color: str) -> str:
if not label:
return "#!/bin/sh\nprintf '\\n'\n"
label_q = shlex.quote(label)
if color and color in _STATUS_LINE_COLORS:
return (
"#!/bin/sh\n"
f"printf '%b%s%b\\n' '{_STATUS_LINE_COLORS[color]}' {label_q} '\\033[0m'\n"
)
return f"#!/bin/sh\nprintf '%s\\n' {label_q}\n"
def _custom_theme_payload(color: str) -> dict[str, object] | None:
theme_color = _CLAUDE_THEME_COLORS.get(color)
if not theme_color:
return None
return {
"name": f"Bot-bottle {color}",
"base": "dark",
"overrides": {
"claude": f"ansi:{theme_color}",
},
}
_RUNTIME = AgentProviderRuntime(
template="claude",
command="claude",
image="bot-bottle-claude:latest",
dockerfile=str(_REPO_ROOT / "Dockerfile.claude"),
prompt_mode="append_file",
bypass_args=("--dangerously-skip-permissions",),
resume_args=("--continue",),
remote_control_args=("--remote-control",),
)
@@ -104,8 +62,7 @@ class ClaudeAgentProvider(AgentProvider):
*,
dockerfile: str,
state_dir: Path,
instance_name: str,
prompt_file: Path,
guest_home: str,
guest_env: dict[str, str] | None = None,
auth_token: str = "",
forward_host_credentials: bool = False,
@@ -113,22 +70,15 @@ class ClaudeAgentProvider(AgentProvider):
trusted_project_path: str = "",
label: str = "",
color: str = "",
provider_settings: dict[str, object] | None = None,
) -> AgentProvisionPlan:
del forward_host_credentials, host_env
del forward_host_credentials, host_env # Codex-only knobs
resolved_guest_env = dict(guest_env or {})
startup_args = provider_startup_args(provider_settings)
guest_home = self.guest_home
trusted_path = trusted_project_path or guest_home
env_vars: dict[str, str] = {
"CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC": "1",
"DISABLE_ERROR_REPORTING": "1",
}
dirs = (
AgentProvisionDir(f"{guest_home}/.claude"),
AgentProvisionDir(f"{guest_home}/.claude/themes"),
)
claude_config = state_dir / "claude.json"
claude_projects = {guest_home: {"hasTrustDialogAccepted": True}}
claude_projects[trusted_path] = {"hasTrustDialogAccepted": True}
@@ -138,45 +88,15 @@ class ClaudeAgentProvider(AgentProvider):
"bypassPermissionsModeAccepted": True,
"projects": claude_projects,
}
if label:
payload["name"] = label
if color:
payload["color"] = color
claude_config.write_text(json.dumps(payload, indent=2) + "\n")
claude_config.chmod(0o600)
files = [
files = (
AgentProvisionFile(claude_config, f"{guest_home}/.claude.json"),
]
claude_settings = state_dir / "claude-settings.json"
claude_settings_payload: dict[str, object] = {}
if label or color:
statusline_script = state_dir / "claude-statusline.sh"
statusline_script.write_text(_status_line_script(label, color))
statusline_script.chmod(0o755)
files.append(AgentProvisionFile(
statusline_script,
f"{guest_home}/.claude/statusline.sh",
mode="755",
))
claude_settings_payload["statusLine"] = {
"type": "command",
"command": "~/.claude/statusline.sh",
}
theme_payload = _custom_theme_payload(color)
if theme_payload is not None:
theme_name = f"bot-bottle-{docker_mod.slugify(label or color)}"
theme_file = state_dir / f"{theme_name}.json"
theme_file.write_text(json.dumps(theme_payload, indent=2) + "\n")
theme_file.chmod(0o644)
files.append(AgentProvisionFile(
theme_file,
f"{guest_home}/.claude/themes/{theme_name}.json",
))
claude_settings_payload["theme"] = f"custom:{theme_name}"
if claude_settings_payload:
claude_settings.write_text(json.dumps(claude_settings_payload, indent=2) + "\n")
claude_settings.chmod(0o600)
files.append(AgentProvisionFile(
claude_settings,
f"{guest_home}/.claude/settings.json",
))
)
egress_routes = (EgressRoute(
host="api.anthropic.com",
auth_scheme="Bearer" if auth_token else "",
@@ -187,22 +107,15 @@ class ClaudeAgentProvider(AgentProvider):
env_vars["CLAUDE_CODE_OAUTH_TOKEN"] = "egress-placeholder"
hidden_env_names = frozenset({"CLAUDE_CODE_OAUTH_TOKEN"})
has_prompt = prompt_file.exists() and bool(prompt_file.read_text())
return AgentProvisionPlan(
template=_RUNTIME.template,
command=_RUNTIME.command,
prompt_mode=_RUNTIME.prompt_mode,
image=_RUNTIME.image,
dockerfile=dockerfile,
guest_home=guest_home,
instance_name=instance_name,
prompt_file=prompt_file,
env_vars=env_vars,
guest_env=resolved_guest_env,
has_prompt=has_prompt,
startup_args=startup_args,
dirs=dirs,
files=tuple(files),
files=files,
egress_routes=egress_routes,
hidden_env_names=hidden_env_names,
)
@@ -213,11 +126,11 @@ class ClaudeAgentProvider(AgentProvider):
when the agent has no skills."""
from ...backend.util import host_skill_dir
agent = plan.manifest.agent
agent = plan.spec.manifest.agents[plan.spec.agent_name]
if not agent.skills:
return
skills_dir = _skills_dir(plan.guest_home)
bottle.exec(f"mkdir -p {shlex.quote(skills_dir)}", user="root")
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):
@@ -227,13 +140,9 @@ class ClaudeAgentProvider(AgentProvider):
)
dst = f"{skills_dir}/{name}"
info(f"copying skill {name} into {bottle.name}:{dst}")
# Defense in depth: skill names are validated kebab-case at
# manifest load, but quote the path so a future unvalidated
# field can't inject shell metacharacters here either.
dst_q = shlex.quote(dst)
bottle.exec(f"rm -rf {dst_q} && mkdir -p {dst_q}", user="root")
bottle.exec(f"rm -rf {dst} && mkdir -p {dst}", user="root")
bottle.cp_in(f"{src}/.", f"{dst}/")
bottle.exec(f"chown -R node:node {dst_q}", user="root")
bottle.exec(f"chown -R node:node {dst}", user="root")
def provision_prompt(self, plan: "BottlePlan", bottle: "Bottle") -> str | None:
"""Copy the prompt file into the guest, fix ownership/mode.
@@ -246,8 +155,8 @@ class ClaudeAgentProvider(AgentProvider):
f"chown node:node {prompt_path} && chmod 600 {prompt_path}",
user="root",
)
agent = plan.manifest.agent
return prompt_path if plan.agent_provision.has_prompt or agent.prompt else None
agent = plan.spec.manifest.agents[plan.spec.agent_name]
return prompt_path if agent.prompt else None
def provision(self, plan: "BottlePlan", bottle: "Bottle") -> None:
"""Apply the claude-side declarative provision steps from
@@ -313,9 +222,6 @@ class ClaudeAgentProvider(AgentProvider):
f"claude mcp add --scope user --transport http supervise {supervise_url}"
)
def headless_prompt(self, prompt: str) -> list[str]:
return ["-p", prompt]
def _exec(bottle: "Bottle", script: str, error: str) -> None:
result = bottle.exec(script, user="root")
+18 -45
View File
@@ -18,11 +18,10 @@ from ...agent_provider import (
CODEX_HOST_CREDENTIAL_HOSTS,
AgentProvider,
AgentProviderRuntime,
AgentProvisionDir,
AgentProvisionCommand,
AgentProvisionDir,
AgentProvisionFile,
AgentProvisionPlan,
provider_startup_args,
)
from .codex_auth import codex_host_access_token, write_codex_dummy_auth_file
from ...egress import CODEX_HOST_CREDENTIAL_TOKEN_REF, EgressRoute
@@ -33,13 +32,9 @@ if TYPE_CHECKING:
from ...backend import Bottle, BottlePlan
_REPO_ROOT = Path(__file__).resolve().parents[3]
_SUPERVISE_MCP_NAME = "supervise"
_CODEX_CLI = "/home/node/.codex/packages/standalone/current/bin/codex"
_CODEX_CLI_PATH = (
"/home/node/.local/bin:"
"/home/node/.codex/packages/standalone/current/bin:"
"/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin"
)
def _skills_dir(guest_home: str) -> str:
@@ -53,14 +48,15 @@ def _skills_dir(guest_home: str) -> str:
def _prompt_path(guest_home: str) -> str:
return f"{guest_home}/.bot-bottle-prompt.txt"
_RUNTIME = AgentProviderRuntime(
template="codex",
command=_CODEX_CLI,
command="codex",
image="bot-bottle-codex:latest",
dockerfile=str(_REPO_ROOT / "Dockerfile.codex"),
prompt_mode="read_prompt_file",
bypass_args=("--dangerously-bypass-approvals-and-sandbox",),
resume_args=("resume", "--last"),
remote_control_args=(),
)
@@ -74,8 +70,7 @@ class CodexAgentProvider(AgentProvider):
*,
dockerfile: str,
state_dir: Path,
instance_name: str,
prompt_file: Path,
guest_home: str,
guest_env: dict[str, str] | None = None,
auth_token: str = "",
forward_host_credentials: bool = False,
@@ -83,12 +78,9 @@ class CodexAgentProvider(AgentProvider):
trusted_project_path: str = "",
label: str = "",
color: str = "",
provider_settings: dict[str, object] | None = None,
) -> AgentProvisionPlan:
del auth_token, label, color
del auth_token, label, color # Claude-only knobs
resolved_guest_env = dict(guest_env or {})
startup_args = provider_startup_args(provider_settings)
guest_home = self.guest_home
trusted_path = trusted_project_path or guest_home
env_vars: dict[str, str] = {
@@ -110,11 +102,6 @@ class CodexAgentProvider(AgentProvider):
config_file.write_text(
f'[projects."{toml_path}"]\n'
'trust_level = "trusted"\n'
"\n"
"[tui]\n"
'status_line = ["model-with-reasoning"]\n'
'terminal_title = ["spinner", "project"]\n'
'theme = "ansi"\n'
)
config_file.chmod(0o600)
files.append(AgentProvisionFile(config_file, config_path))
@@ -151,27 +138,20 @@ class CodexAgentProvider(AgentProvider):
"env",
f"HOME={guest_home}",
f"CODEX_HOME={auth_dir}",
f"PATH={_CODEX_CLI_PATH}",
_CODEX_CLI, "login", "status",
"codex", "login", "status",
), (
"codex host credentials: dummy auth was copied into the "
"guest, but Codex did not accept it"
)))
has_prompt = prompt_file.exists() and bool(prompt_file.read_text())
return AgentProvisionPlan(
template=_RUNTIME.template,
command=_RUNTIME.command,
prompt_mode=_RUNTIME.prompt_mode,
image=_RUNTIME.image,
dockerfile=dockerfile,
guest_home=guest_home,
instance_name=instance_name,
prompt_file=prompt_file,
env_vars=env_vars,
guest_env=resolved_guest_env,
has_prompt=has_prompt,
startup_args=startup_args,
dirs=tuple(dirs),
files=tuple(files),
pre_copy=tuple(pre_copy),
@@ -186,11 +166,11 @@ class CodexAgentProvider(AgentProvider):
skills."""
from ...backend.util import host_skill_dir
agent = plan.manifest.agent
agent = plan.spec.manifest.agents[plan.spec.agent_name]
if not agent.skills:
return
skills_dir = _skills_dir(plan.guest_home)
bottle.exec(f"mkdir -p {shlex.quote(skills_dir)}", user="root")
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):
@@ -200,13 +180,9 @@ class CodexAgentProvider(AgentProvider):
)
dst = f"{skills_dir}/{name}"
info(f"copying skill {name} into {bottle.name}:{dst}")
# Defense in depth: skill names are validated kebab-case at
# manifest load, but quote the path so a future unvalidated
# field can't inject shell metacharacters here either.
dst_q = shlex.quote(dst)
bottle.exec(f"rm -rf {dst_q} && mkdir -p {dst_q}", user="root")
bottle.exec(f"rm -rf {dst} && mkdir -p {dst}", user="root")
bottle.cp_in(f"{src}/.", f"{dst}/")
bottle.exec(f"chown -R node:node {dst_q}", user="root")
bottle.exec(f"chown -R node:node {dst}", user="root")
def provision_prompt(self, plan: "BottlePlan", bottle: "Bottle") -> str | None:
"""Copy the prompt file into the guest, fix ownership/mode.
@@ -219,8 +195,8 @@ class CodexAgentProvider(AgentProvider):
f"chown node:node {prompt_path} && chmod 600 {prompt_path}",
user="root",
)
agent = plan.manifest.agent
return prompt_path if plan.agent_provision.has_prompt or agent.prompt else None
agent = plan.spec.manifest.agents[plan.spec.agent_name]
return prompt_path if agent.prompt else None
def provision(self, plan: "BottlePlan", bottle: "Bottle") -> None:
"""Apply the codex-side declarative provision steps from
@@ -274,8 +250,8 @@ class CodexAgentProvider(AgentProvider):
return
info(f"registering supervise MCP server in agent codex config → {supervise_url}")
r = bottle.exec(
f"{shlex.quote(_CODEX_CLI)} mcp add {_SUPERVISE_MCP_NAME} --url "
f"{shlex.quote(supervise_url)}",
f"codex mcp add --transport http "
f"{_SUPERVISE_MCP_NAME} {supervise_url}",
user="node",
)
if r.returncode != 0:
@@ -283,12 +259,9 @@ class CodexAgentProvider(AgentProvider):
f"`codex mcp add supervise` failed (exit {r.returncode}): "
f"{(r.stderr or r.stdout or '').strip()}. Inside the bottle, "
f"register manually with: "
f"codex mcp add supervise --url {shlex.quote(supervise_url)}"
f"codex mcp add --transport http supervise {supervise_url}"
)
def headless_prompt(self, prompt: str) -> list[str]:
return [prompt]
def _exec(bottle: "Bottle", script: str, error: str) -> None:
result = bottle.exec(script, user="root")
@@ -2,13 +2,7 @@
Generates ed25519 keypairs via `ssh-keygen` and registers / deletes
them using the Gitea deploy-key HTTP API. No new Python dependencies
only stdlib `urllib.request` and `subprocess`.
Required token permissions (Gitea "Applications" "Generate Token"):
- Repository: Read & Write
Grants POST /api/v1/repos/{owner}/{repo}/keys (create deploy key)
and DELETE /api/v1/repos/{owner}/{repo}/keys/{id} (revoke deploy key).
No other scopes are needed."""
only stdlib `urllib.request` and `subprocess`."""
from __future__ import annotations
@@ -19,12 +13,7 @@ import urllib.error
import urllib.request
from pathlib import Path
from ...deploy_key_provisioner import DeployKeyCollisionError, DeployKeyProvisioner
# Timeout for ssh-keygen and Gitea API HTTP calls. A hung Gitea instance at
# prepare time would stall bottle launch indefinitely without this bound.
_API_TIMEOUT_SECS = 30
_KEYGEN_TIMEOUT_SECS = 10
from ...deploy_key_provisioner import DeployKeyProvisioner
class GiteaDeployKeyProvisioner(DeployKeyProvisioner):
@@ -51,7 +40,6 @@ class GiteaDeployKeyProvisioner(DeployKeyProvisioner):
check=True,
stdout=subprocess.DEVNULL,
stderr=subprocess.DEVNULL,
timeout=_KEYGEN_TIMEOUT_SECS,
)
private_key = key_path.read_bytes()
public_key = key_path.with_suffix(".pub").read_text().strip()
@@ -73,15 +61,10 @@ class GiteaDeployKeyProvisioner(DeployKeyProvisioner):
method="POST",
)
try:
with urllib.request.urlopen(req, timeout=_API_TIMEOUT_SECS) as resp:
with urllib.request.urlopen(req) as resp:
body = json.loads(resp.read())
except urllib.error.HTTPError as exc:
_body = _read_error_body(exc)
if exc.code == 422:
raise DeployKeyCollisionError(
f"deploy key collision for {owner_repo!r} "
f"(title={title!r}): key title or content already registered — {_body}"
) from exc
raise RuntimeError(
f"failed to create deploy key for {owner_repo}: "
f"HTTP {exc.code}{_body}"
@@ -104,7 +87,7 @@ class GiteaDeployKeyProvisioner(DeployKeyProvisioner):
method="DELETE",
)
try:
with urllib.request.urlopen(req, timeout=_API_TIMEOUT_SECS):
with urllib.request.urlopen(req):
pass
except urllib.error.HTTPError as exc:
if exc.code == 404:
-41
View File
@@ -1,41 +0,0 @@
# bot-bottle Pi provider image.
#
# Node LTS, git/network tooling, and the Pi coding-agent CLI installed globally.
FROM node:22-slim
RUN apt-get update \
&& apt-get install -y --no-install-recommends \
git \
ca-certificates \
curl \
fd-find \
ripgrep \
&& ln -s /usr/bin/fdfind /usr/local/bin/fd \
&& rm -rf /var/lib/apt/lists/*
RUN apt-get update \
&& apt-get install -y --no-install-recommends python3 python3-pip python3-venv \
&& rm -rf /var/lib/apt/lists/*
RUN npm install -g --ignore-scripts --no-fund --no-audit @earendil-works/pi-coding-agent \
&& npm cache clean --force
RUN mkdir -p /home/node/.pi/agent \
/home/node/.pi/context-mode/sessions \
/tmp/pi-subagents-uid-1000 \
&& chown -R node:node /home/node/.pi /tmp \
&& chmod -R u+rwX /tmp \
&& chown root:root /tmp /var/tmp \
&& chmod 1777 /tmp /var/tmp
USER node
WORKDIR /home/node
RUN pi install npm:@harms-haus/pi-cwd \
&& pi install npm:pi-web-access \
&& pi install npm:context-mode \
&& pi install npm:pi-subagents \
&& pi install npm:pi-mcp-adapter
CMD ["pi"]
-1
View File
@@ -1 +0,0 @@
"""Pi agent provider package."""
-328
View File
@@ -1,328 +0,0 @@
"""Pi agent provider plugin (PRD 0058, contrib).
Pi uses ~/.pi/agent/models.json for custom provider/model settings.
This provider writes an Ollama-compatible default configuration and
lets bottles override the model endpoint and model ids via
agent_provider.settings.
"""
from __future__ import annotations
import json
import os
import shlex
from pathlib import Path
from typing import TYPE_CHECKING
from urllib.parse import urlparse
from ...agent_provider import (
AgentProvider,
AgentProviderRuntime,
AgentProvisionDir,
AgentProvisionFile,
AgentProvisionPlan,
provider_startup_args,
)
from ...egress import EgressRoute
from ...log import die, info
if TYPE_CHECKING:
from ...backend import Bottle, BottlePlan
_DEFAULT_BASE_URL = "http://ollama:11434/v1"
_DEFAULT_MODEL = "qwen2.5-coder:7b"
_DEFAULT_PROVIDER_NAME = "ollama"
_DEFAULT_CONTEXT_WINDOW = 4096
_DEFAULT_MAX_TOKENS = 1024
def _skills_dir(guest_home: str) -> str:
return f"{guest_home}/.pi/agent/skills"
def _prompt_path(guest_home: str) -> str:
return f"{guest_home}/.bot-bottle-prompt.txt"
def _append_system_path(guest_home: str) -> str:
return f"{guest_home}/.pi/agent/APPEND_SYSTEM.md"
def _models_path(guest_home: str) -> str:
return f"{guest_home}/.pi/agent/models.json"
def _runtime_state_repair_script(guest_home: str) -> str:
home = shlex.quote(guest_home)
pi_home = shlex.quote(f"{guest_home}/.pi")
context_sessions = shlex.quote(f"{guest_home}/.pi/context-mode/sessions")
return (
f"mkdir -p {context_sessions} /tmp/pi-subagents-uid-1000 && "
f"chown node:node {home} && "
f"chown -R node:node {pi_home} /tmp && "
"chmod -R u+rwX /tmp && "
f"chmod 755 {home} && "
"chown root:root /tmp /var/tmp && "
"chmod 1777 /tmp /var/tmp"
)
def _settings_value(
settings: dict[str, object],
key: str,
default: object,
) -> object:
value = settings.get(key)
return default if value is None else value
def _settings_int(
settings: dict[str, object],
key: str,
default: int,
) -> int:
value = _settings_value(settings, key, default)
if isinstance(value, bool):
return default
if isinstance(value, (int, str)):
return int(value)
return default
def _pi_models_json(
settings: dict[str, object],
) -> tuple[dict[str, object], str, str, list[str], str]:
provider_name = str(
_settings_value(settings, "provider", _DEFAULT_PROVIDER_NAME)
)
base_url = str(_settings_value(settings, "base_url", _DEFAULT_BASE_URL))
api = str(_settings_value(settings, "api", "openai-completions"))
api_key = settings.get("api_key")
api_key_env = str(settings.get("api_key_env", ""))
models_raw = _settings_value(settings, "models", [_DEFAULT_MODEL])
models = [str(model) for model in models_raw] # type: ignore[union-attr]
supports_developer_role = bool(
_settings_value(settings, "supports_developer_role", False)
)
supports_reasoning_effort = bool(
_settings_value(settings, "supports_reasoning_effort", False)
)
max_tokens_field = str(
_settings_value(settings, "max_tokens_field", "max_tokens")
)
context_window = _settings_int(
settings, "context_window", _DEFAULT_CONTEXT_WINDOW,
)
max_tokens = _settings_int(settings, "max_tokens", _DEFAULT_MAX_TOKENS)
input_context_window = max(1, context_window - max_tokens)
provider: dict[str, object] = {
"baseUrl": base_url,
"api": api,
"compat": {
"supportsDeveloperRole": supports_developer_role,
"supportsReasoningEffort": supports_reasoning_effort,
"maxTokensField": max_tokens_field,
},
"models": [
{
"id": model,
"name": model,
"contextWindow": input_context_window,
"maxTokens": max_tokens,
}
for model in models
],
}
if api_key is not None:
provider["apiKey"] = str(api_key)
elif api_key_env:
provider["apiKey"] = "egress-placeholder"
elif provider_name == _DEFAULT_PROVIDER_NAME:
provider["apiKey"] = "ollama"
payload: dict[str, object] = {
"providers": {
provider_name: provider,
}
}
return payload, base_url, api_key_env, models, provider_name
def _route_host(base_url: str) -> str:
parsed = urlparse(base_url)
if not parsed.scheme or not parsed.hostname:
die(
"agent provider provisioning: pi settings base_url must be an "
f"absolute URL (was {base_url!r})"
)
return parsed.hostname
_RUNTIME = AgentProviderRuntime(
template="pi",
command="pi",
image="bot-bottle-pi:latest",
prompt_mode="append_system_prompt",
bypass_args=(),
resume_args=(),
)
class PiAgentProvider(AgentProvider):
@property
def runtime(self) -> AgentProviderRuntime:
return _RUNTIME
def provision_plan(
self,
*,
dockerfile: str,
state_dir: Path,
instance_name: str,
prompt_file: Path,
guest_env: dict[str, str] | None = None,
auth_token: str = "",
forward_host_credentials: bool = False,
host_env: dict[str, str] | None = None,
trusted_project_path: str = "",
label: str = "",
color: str = "",
provider_settings: dict[str, object] | None = None,
) -> AgentProvisionPlan:
del auth_token, forward_host_credentials, host_env, trusted_project_path
del label, color
resolved_guest_env = dict(guest_env or {})
guest_home = self.guest_home
settings = dict(provider_settings or {})
models_payload, base_url, api_key_env, models, provider_name = (
_pi_models_json(settings)
)
extra_startup_args = provider_startup_args(provider_settings)
models_file = state_dir / "pi-models.json"
models_file.write_text(json.dumps(models_payload, indent=2) + "\n")
models_file.chmod(0o600)
has_prompt = prompt_file.exists() and bool(prompt_file.read_text())
auth_scheme = "Bearer" if api_key_env else ""
return AgentProvisionPlan(
template=_RUNTIME.template,
command=_RUNTIME.command,
prompt_mode=_RUNTIME.prompt_mode,
image=_RUNTIME.image,
dockerfile=dockerfile,
guest_home=guest_home,
instance_name=instance_name,
prompt_file=prompt_file,
guest_env=resolved_guest_env,
has_prompt=has_prompt,
startup_args=(
"--models",
",".join(f"{provider_name}/{model}" for model in models),
*extra_startup_args,
),
dirs=(AgentProvisionDir(f"{guest_home}/.pi/agent"),),
files=(AgentProvisionFile(models_file, _models_path(guest_home)),),
egress_routes=(EgressRoute(
host=_route_host(base_url),
auth_scheme=auth_scheme,
token_ref=api_key_env,
),),
)
def provision_skills(self, plan: "BottlePlan", bottle: "Bottle") -> None:
from ...backend.util import host_skill_dir
agent = plan.manifest.agent
if not agent.skills:
return
skills_dir = _skills_dir(plan.guest_home)
bottle.exec(f"mkdir -p {shlex.quote(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}")
# Defense in depth: skill names are validated kebab-case at
# manifest load, but quote the path so a future unvalidated
# field can't inject shell metacharacters here either.
dst_q = shlex.quote(dst)
bottle.exec(f"rm -rf {dst_q} && mkdir -p {dst_q}", user="root")
bottle.cp_in(f"{src}/.", f"{dst}/")
bottle.exec(f"chown -R node:node {dst_q}", user="root")
def provision_prompt(self, plan: "BottlePlan", bottle: "Bottle") -> str | None:
prompt_path = _prompt_path(plan.guest_home)
append_system_path = _append_system_path(plan.guest_home)
bottle.cp_in(str(plan.prompt_file), prompt_path) # type: ignore
bottle.exec(
f"mkdir -p {shlex.quote(plan.guest_home)}/.pi/agent && "
f"cp {shlex.quote(prompt_path)} {shlex.quote(append_system_path)} && "
f"chown node:node {shlex.quote(prompt_path)} "
f"{shlex.quote(append_system_path)} && "
f"chmod 600 {shlex.quote(prompt_path)} "
f"{shlex.quote(append_system_path)}",
user="root",
)
# Pi's `--append-system-prompt` takes literal text, not a file path.
# Use its documented APPEND_SYSTEM.md discovery path instead.
return None
def provision(self, plan: "BottlePlan", bottle: "Bottle") -> None:
provision = plan.agent_provision
_exec(
bottle,
_runtime_state_repair_script(plan.guest_home),
"could not prepare pi runtime state",
)
for d in provision.dirs:
path = shlex.quote(d.guest_path)
_exec(bottle, f"mkdir -p {path}", f"could not create {d.guest_path}")
_exec(
bottle,
f"chown {shlex.quote(d.owner)} {path}",
f"could not chown {d.guest_path}",
)
_exec(
bottle,
f"chmod {shlex.quote(d.mode)} {path}",
f"could not chmod {d.guest_path}",
)
for f in provision.files:
bottle.cp_in(str(f.host_path), f.guest_path)
path = shlex.quote(f.guest_path)
_exec(
bottle,
f"chown {shlex.quote(f.owner)} {path}",
f"could not chown {f.guest_path}",
)
_exec(
bottle,
f"chmod {shlex.quote(f.mode)} {path}",
f"could not chmod {f.guest_path}",
)
def provision_supervise_mcp(
self,
plan: "BottlePlan",
bottle: "Bottle",
supervise_url: str,
) -> None:
del plan, bottle, supervise_url
def headless_prompt(self, prompt: str) -> list[str]:
return ["-p", prompt]
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}")
-59
View File
@@ -1,59 +0,0 @@
"""Shared SQLite-backed store base class for bot-bottle (PRD 0013)."""
from __future__ import annotations
import sqlite3
from pathlib import Path
try:
from .migrations import TableMigrations
except ImportError:
from migrations import TableMigrations # type: ignore[import-not-found] # pylint: disable=import-error,no-name-in-module
class DbVersionError(Exception):
"""Raised when the on-disk schema is behind the current migration list."""
class DbStore:
"""Base for SQLite-backed stores. Subclasses resolve db_path then call super().__init__."""
def __init__(self, db_path: Path, migrations: TableMigrations) -> None:
self.db_path = db_path
self._migrations = migrations
self.db_path.parent.mkdir(parents=True, exist_ok=True)
def _connect(self) -> sqlite3.Connection:
conn = sqlite3.connect(self.db_path)
conn.row_factory = sqlite3.Row
return conn
def is_migrated(self) -> bool:
"""Return True if the DB is fully up-to-date, False if migration is needed."""
if not self.db_path.exists():
return False
try:
with self._connect() as conn:
row = conn.execute(
"SELECT version FROM schema_versions WHERE module = ?",
(self._migrations.schema_key,),
).fetchone()
except sqlite3.OperationalError:
return False
version = row[0] if row else 0
return version == len(self._migrations.migrations)
def migrate(self) -> None:
"""Apply any pending migrations and set permissions on the DB file."""
with self._connect() as conn:
self._migrations.apply(conn)
self._chmod()
def _chmod(self) -> None:
try:
self.db_path.chmod(0o600)
except OSError:
pass
__all__ = ["DbStore", "DbVersionError"]

Some files were not shown because too many files have changed in this diff Show More