Compare commits
117 Commits
7ab85e9ea6
..
main
| Author | SHA1 | Date | |
|---|---|---|---|
| dee0121e8d | |||
| 6f997bf118 | |||
| 2fb08fc976 | |||
| 509eb73497 | |||
| df9c4ca59b | |||
| 6ffa8d8843 | |||
| e3d17dbc07 | |||
| 1b86847f0d | |||
| 9dee92406e | |||
| 309ec34f29 | |||
| 9eab5be2c4 | |||
| b3834ebf66 | |||
| e2857f1eeb | |||
| fd529a98b5 | |||
| 49b407437c | |||
| 8315e4192a | |||
| 938df8513f | |||
| ec38458c94 | |||
| f6df85a8cd | |||
| 9bf2961d13 | |||
| 6385752040 | |||
| 496608fc25 | |||
| 218f29cb05 | |||
| 1518f73de5 | |||
| 9d82535390 | |||
| c89847b626 | |||
| cd9f023f3d | |||
| 5c499d290b | |||
| 0500ae5f4c | |||
| 5614a56ccd | |||
| 71c0f8ed88 | |||
| 556217ae7b | |||
| 7461802b62 | |||
| 5c12c6bf4e | |||
| 4096409495 | |||
| 8d0782d1c7 | |||
| 6793a09e2b | |||
| af293d7036 | |||
| d415581adc | |||
| 27b9ba5247 | |||
| 420184b874 | |||
| 7938b90d19 | |||
| d879258f62 | |||
| 78d3b43061 | |||
| cdc5c8203d | |||
| d04bbf1454 | |||
| c00097d998 | |||
| 6630a1f701 | |||
| a7ad82f03a | |||
| 9b8f126b8f | |||
| d167c03215 | |||
| 479b93bd0b | |||
| 2de61eeb17 | |||
| a4bc5d4508 | |||
| 7ebd067d2c | |||
| be50354100 | |||
| e1163184c9 | |||
| 70f6a9be20 | |||
| aa43fd032f | |||
| be5c803e8e | |||
| 38ff4a5e88 | |||
| 8df76f6126 | |||
| b63c41db9c | |||
| 6c52686069 | |||
| a52245af95 | |||
| d4e48a4169 | |||
| 53cc3ca492 | |||
| bafb73fdb9 | |||
| b0f317c499 | |||
| 57eb4394dc | |||
| 82e1a353bd | |||
| a6e1aebda1 | |||
| 74ec9843f0 | |||
| ed9fc76f97 | |||
| bd8a146a46 | |||
| 85fb6b0c98 | |||
| 902286dbc0 | |||
| 73c566f3ff | |||
| 33b7bcd082 | |||
| 9e83ff1992 | |||
| 1d10595e5c | |||
| 364cad7e56 | |||
| ff355f81de | |||
| cf97a49eac | |||
| e607af73ab | |||
| 998b7c5dd7 | |||
| 9a4899d4e1 | |||
| 5083b45f42 | |||
| 24aeba9676 | |||
| ff36b73ff1 | |||
| 10d295eaf6 | |||
| 69c4c85cd5 | |||
| 52e1249c2f | |||
| bd4f384038 | |||
| 0500e71383 | |||
| 72165b5db5 | |||
| 0edd46d56d | |||
| 4682dd441f | |||
| 1827593b89 | |||
| 73e70e326c | |||
| d744bec7b1 | |||
| f3fbfb3cc3 | |||
| b2245ae1f3 | |||
| f0fe33b1d0 | |||
| d4889663d1 | |||
| 1022247ce5 | |||
| 671d91070e | |||
| 1c6d30ffd8 | |||
| 583ff98b27 | |||
| fafb828bb7 | |||
| f9ad6c85aa | |||
| 7488110e71 | |||
| 22dde95561 | |||
| e29b79d517 | |||
| 1d85acfd99 | |||
| 90defdc9cd | |||
| 2039ef635f |
@@ -2,7 +2,7 @@
|
||||
# digest, etc.) without coupling every dev push to upstream registry
|
||||
# availability.
|
||||
#
|
||||
# Opt-in via CLAUDE_BOTTLE_RUN_CANARIES=1 so the same files can be run
|
||||
# Opt-in via BOT_BOTTLE_RUN_CANARIES=1 so the same files can be run
|
||||
# locally with the same gating.
|
||||
|
||||
name: canaries
|
||||
@@ -17,7 +17,7 @@ jobs:
|
||||
canaries:
|
||||
runs-on: ubuntu-latest
|
||||
env:
|
||||
CLAUDE_BOTTLE_RUN_CANARIES: "1"
|
||||
BOT_BOTTLE_RUN_CANARIES: "1"
|
||||
steps:
|
||||
- name: Checkout
|
||||
uses: actions/checkout@v4
|
||||
@@ -25,4 +25,7 @@ jobs:
|
||||
# No actions/setup-python: canaries are stdlib unittest on the image's
|
||||
# system Python 3.12 (older act_runner mishandles setup-python's PATH).
|
||||
- name: Run canaries
|
||||
run: python3 -m unittest discover -t . -s tests/canaries -v
|
||||
run: |
|
||||
python3 -m scripts.unittest_gate \
|
||||
-t . -s tests/canaries -v \
|
||||
--minimum-executed 1 --fail-on-skip
|
||||
|
||||
@@ -4,6 +4,13 @@ on:
|
||||
push:
|
||||
paths:
|
||||
- "**.py"
|
||||
- "Dockerfile*"
|
||||
- "bot_bottle/contrib/*/Dockerfile"
|
||||
- "bot_bottle/contrib/*/package.json"
|
||||
- "bot_bottle/contrib/*/package-lock.json"
|
||||
- "bot_bottle/contrib/codex/codex-package_SHA256SUMS"
|
||||
- "requirements.gateway.*"
|
||||
- "image-build-args.json"
|
||||
- ".pylintrc"
|
||||
- ".gitea/workflows/lint.yml"
|
||||
|
||||
@@ -13,6 +20,9 @@ jobs:
|
||||
steps:
|
||||
- uses: actions/checkout@v3
|
||||
|
||||
- name: Enforce immutable image inputs
|
||||
run: python3 scripts/check_image_inputs.py
|
||||
|
||||
# No actions/setup-python: the runner image already ships Python 3.12,
|
||||
# and older act_runner engines mishandle setup-python's PATH. Install
|
||||
# into the ephemeral job container's system Python — the pylint/pyright
|
||||
|
||||
@@ -3,6 +3,7 @@ name: prd-number-check
|
||||
on:
|
||||
pull_request:
|
||||
types: [opened, reopened, synchronize]
|
||||
branches: [main]
|
||||
|
||||
jobs:
|
||||
require-numbered-prds:
|
||||
|
||||
@@ -60,6 +60,9 @@ jobs:
|
||||
|
||||
integration-docker:
|
||||
runs-on: ubuntu-latest
|
||||
concurrency:
|
||||
group: integration-docker-infra
|
||||
cancel-in-progress: false
|
||||
steps:
|
||||
- name: Checkout
|
||||
uses: actions/checkout@v4
|
||||
@@ -84,7 +87,30 @@ jobs:
|
||||
env:
|
||||
BOT_BOTTLE_BACKEND: docker
|
||||
COVERAGE_FILE: ${{ github.workspace }}/.coverage.docker
|
||||
run: python3 -m coverage run -m unittest discover -t . -s tests/integration -v
|
||||
run: |
|
||||
set -euo pipefail
|
||||
DOCKER_CLIENT_NETWORK=$(
|
||||
docker inspect "$(hostname)" |
|
||||
python3 -c 'import json,sys; n=json.load(sys.stdin)[0]["NetworkSettings"]["Networks"]; print(next(iter(n)))'
|
||||
)
|
||||
test -n "$DOCKER_CLIENT_NETWORK"
|
||||
RUN_KEY="${GITHUB_RUN_ID:-${GITHUB_RUN_NUMBER:-0}}"
|
||||
export NO_PROXY="*"
|
||||
export no_proxy="*"
|
||||
export BOT_BOTTLE_DOCKER_CLIENT_NETWORK="$DOCKER_CLIENT_NETWORK"
|
||||
export BOT_BOTTLE_DOCKER_ROOT_MOUNT="bot-bottle-ci-root-$RUN_KEY"
|
||||
export BOT_BOTTLE_DOCKER_CA_MOUNT="bot-bottle-ci-ca-$RUN_KEY"
|
||||
python3 -m coverage run -m scripts.unittest_gate \
|
||||
-t . -s tests/integration -v \
|
||||
--minimum-executed 22 --fail-on-skip
|
||||
|
||||
- name: Clean Docker integration volumes
|
||||
if: always()
|
||||
run: |
|
||||
RUN_KEY="${GITHUB_RUN_ID:-${GITHUB_RUN_NUMBER:-0}}"
|
||||
docker volume rm --force \
|
||||
"bot-bottle-ci-root-$RUN_KEY" \
|
||||
"bot-bottle-ci-ca-$RUN_KEY" 2>/dev/null || true
|
||||
|
||||
# Non-dot name so upload-artifact's dotfile-skipping glob picks it up.
|
||||
- name: Stage docker coverage for upload
|
||||
|
||||
@@ -0,0 +1,97 @@
|
||||
# Manually refresh the committed package locks and the pinned Codex installer
|
||||
# checksum after deliberately changing a direct version in the source files.
|
||||
#
|
||||
# The job uploads the generated files for review; it never commits or pushes.
|
||||
|
||||
name: refresh-image-locks
|
||||
|
||||
on:
|
||||
workflow_dispatch:
|
||||
push:
|
||||
paths:
|
||||
- 'requirements.gateway.in'
|
||||
- 'bot_bottle/contrib/claude/package.json'
|
||||
- 'bot_bottle/contrib/pi/package.json'
|
||||
- 'bot_bottle/contrib/codex/Dockerfile'
|
||||
- 'image-build-args.json'
|
||||
- '.gitea/workflows/refresh-image-locks.yml'
|
||||
|
||||
permissions:
|
||||
code: read
|
||||
|
||||
jobs:
|
||||
refresh:
|
||||
runs-on: ubuntu-latest
|
||||
steps:
|
||||
- name: Checkout
|
||||
uses: actions/checkout@v4
|
||||
|
||||
- name: Resolve image runtime versions
|
||||
id: runtimes
|
||||
run: |
|
||||
python3 - <<'PY' >> "$GITHUB_OUTPUT"
|
||||
import json
|
||||
import re
|
||||
inputs = json.load(open("image-build-args.json"))
|
||||
for output, name in (
|
||||
("python-version", "PYTHON_BASE_IMAGE"),
|
||||
("node-version", "NODE_BASE_IMAGE"),
|
||||
):
|
||||
match = re.search(r":(\d+\.\d+\.\d+)-", inputs[name])
|
||||
if match is None:
|
||||
raise SystemExit(f"cannot resolve runtime version from {name}")
|
||||
print(f"{output}={match.group(1)}")
|
||||
PY
|
||||
|
||||
- name: Use the image Python version
|
||||
uses: actions/setup-python@v5
|
||||
with:
|
||||
python-version: '${{ steps.runtimes.outputs.python-version }}'
|
||||
|
||||
- name: Use the image Node version
|
||||
uses: actions/setup-node@v4
|
||||
with:
|
||||
node-version: '${{ steps.runtimes.outputs.node-version }}'
|
||||
|
||||
- name: Compile gateway Python lock
|
||||
run: |
|
||||
python3 -m venv /tmp/image-lock-tools
|
||||
/tmp/image-lock-tools/bin/python -m pip install \
|
||||
pip==25.2 \
|
||||
pip-tools==7.5.1
|
||||
/tmp/image-lock-tools/bin/python -m piptools compile \
|
||||
--generate-hashes \
|
||||
--output-file requirements.gateway.lock \
|
||||
requirements.gateway.in
|
||||
|
||||
- name: Resolve provider npm locks
|
||||
run: |
|
||||
for provider in claude pi; do
|
||||
(
|
||||
cd "bot_bottle/contrib/$provider"
|
||||
npm install --package-lock-only --ignore-scripts --no-audit --no-fund
|
||||
)
|
||||
done
|
||||
python3 scripts/complete_npm_lock_integrity.py \
|
||||
bot_bottle/contrib/claude/package-lock.json \
|
||||
bot_bottle/contrib/pi/package-lock.json
|
||||
|
||||
- name: Refresh pinned Codex archive checksums
|
||||
run: |
|
||||
CODEX_VERSION=$(
|
||||
sed -n 's/^ARG CODEX_VERSION=//p' bot_bottle/contrib/codex/Dockerfile
|
||||
)
|
||||
test -n "$CODEX_VERSION"
|
||||
curl -fsSL \
|
||||
"https://github.com/openai/codex/releases/download/rust-v${CODEX_VERSION}/codex-package_SHA256SUMS" \
|
||||
-o bot_bottle/contrib/codex/codex-package_SHA256SUMS
|
||||
|
||||
- name: Upload refreshed inputs
|
||||
uses: actions/upload-artifact@v3
|
||||
with:
|
||||
name: image-input-locks
|
||||
path: |
|
||||
requirements.gateway.lock
|
||||
bot_bottle/contrib/claude/package-lock.json
|
||||
bot_bottle/contrib/pi/package-lock.json
|
||||
bot_bottle/contrib/codex/codex-package_SHA256SUMS
|
||||
+174
-7
@@ -12,33 +12,49 @@ on:
|
||||
- 'bot_bottle/**'
|
||||
- 'tests/**/*.py'
|
||||
- 'cli.py'
|
||||
- 'install.sh'
|
||||
- 'setup.py'
|
||||
- 'MANIFEST.in'
|
||||
- 'flake.nix'
|
||||
- 'nix/firecracker-netpool.nix'
|
||||
- 'scripts/coverage.sh'
|
||||
- 'scripts/critical-modules.txt'
|
||||
- 'scripts/diff_coverage.py'
|
||||
- 'scripts/tracker_policy.py'
|
||||
- 'scripts/**/*.py'
|
||||
- 'scripts/firecracker-netpool.sh'
|
||||
- 'Dockerfile*'
|
||||
- 'image-build-args.json'
|
||||
- 'pyproject.toml'
|
||||
- 'requirements-dev.txt'
|
||||
- 'requirements.gateway.*'
|
||||
- '.coveragerc'
|
||||
- '.dockerignore'
|
||||
- '.gitea/workflows/test.yml'
|
||||
- '.gitea/workflows/refresh-image-locks.yml'
|
||||
- '.gitea/workflows/pre-release-test.yml'
|
||||
pull_request:
|
||||
paths:
|
||||
- 'bot_bottle/**'
|
||||
- 'tests/**/*.py'
|
||||
- 'cli.py'
|
||||
- 'install.sh'
|
||||
- 'setup.py'
|
||||
- 'MANIFEST.in'
|
||||
- 'flake.nix'
|
||||
- 'nix/firecracker-netpool.nix'
|
||||
- 'scripts/coverage.sh'
|
||||
- 'scripts/critical-modules.txt'
|
||||
- 'scripts/diff_coverage.py'
|
||||
- 'scripts/tracker_policy.py'
|
||||
- 'scripts/**/*.py'
|
||||
- 'scripts/firecracker-netpool.sh'
|
||||
- 'Dockerfile*'
|
||||
- 'image-build-args.json'
|
||||
- 'pyproject.toml'
|
||||
- 'requirements-dev.txt'
|
||||
- 'requirements.gateway.*'
|
||||
- '.coveragerc'
|
||||
- '.dockerignore'
|
||||
- '.gitea/workflows/test.yml'
|
||||
- '.gitea/workflows/refresh-image-locks.yml'
|
||||
- '.gitea/workflows/pre-release-test.yml'
|
||||
|
||||
jobs:
|
||||
unit:
|
||||
@@ -71,6 +87,9 @@ jobs:
|
||||
|
||||
integration-docker:
|
||||
runs-on: ubuntu-latest
|
||||
concurrency:
|
||||
group: integration-docker-infra
|
||||
cancel-in-progress: false
|
||||
steps:
|
||||
- name: Checkout
|
||||
uses: actions/checkout@v4
|
||||
@@ -83,11 +102,51 @@ jobs:
|
||||
python3 --version
|
||||
python3 cli.py backend status --backend=docker
|
||||
|
||||
- name: Preflight — clear any leftover poisoned gateway network
|
||||
run: |
|
||||
# The gateway network has a fixed name and persists across jobs on
|
||||
# this shared runner. A pre-fix or concurrent launch can leave it with
|
||||
# a malformed IPv6 subnet that trips docker's own ParseAddr in
|
||||
# `network inspect` (see PR #515); the code now self-heals it, but the
|
||||
# heal can't run if `network inspect` is what's broken on some daemon
|
||||
# versions. Drop the network here so this run recreates it IPv4-only.
|
||||
# Remove the attached gateway container first (else `network rm` fails
|
||||
# on active endpoints); both are recreated by ensure_running. Harmless
|
||||
# when absent.
|
||||
docker rm --force bot-bottle-orch-gateway 2>/dev/null || true
|
||||
docker network rm bot-bottle-gateway 2>/dev/null || true
|
||||
|
||||
- name: Run integration tests (docker) with coverage
|
||||
env:
|
||||
BOT_BOTTLE_BACKEND: docker
|
||||
COVERAGE_FILE: ${{ github.workspace }}/.coverage.docker
|
||||
run: python3 -m coverage run -m unittest discover -t . -s tests/integration -v
|
||||
run: |
|
||||
set -euo pipefail
|
||||
# act_runner executes this job in a container while sharing the host
|
||||
# Docker socket. Attach control-plane siblings to the job's network,
|
||||
# and use named volumes for state the host daemon must mount.
|
||||
DOCKER_CLIENT_NETWORK=$(
|
||||
docker inspect "$(hostname)" |
|
||||
python3 -c 'import json,sys; n=json.load(sys.stdin)[0]["NetworkSettings"]["Networks"]; print(next(iter(n)))'
|
||||
)
|
||||
test -n "$DOCKER_CLIENT_NETWORK"
|
||||
RUN_KEY="${GITHUB_RUN_ID:-${GITHUB_RUN_NUMBER:-0}}"
|
||||
export NO_PROXY="*"
|
||||
export no_proxy="*"
|
||||
export BOT_BOTTLE_DOCKER_CLIENT_NETWORK="$DOCKER_CLIENT_NETWORK"
|
||||
export BOT_BOTTLE_DOCKER_ROOT_MOUNT="bot-bottle-ci-root-$RUN_KEY"
|
||||
export BOT_BOTTLE_DOCKER_CA_MOUNT="bot-bottle-ci-ca-$RUN_KEY"
|
||||
python3 -m coverage run -m scripts.unittest_gate \
|
||||
-t . -s tests/integration -v \
|
||||
--minimum-executed 22 --fail-on-skip
|
||||
|
||||
- name: Clean Docker integration volumes
|
||||
if: always()
|
||||
run: |
|
||||
RUN_KEY="${GITHUB_RUN_ID:-${GITHUB_RUN_NUMBER:-0}}"
|
||||
docker volume rm --force \
|
||||
"bot-bottle-ci-root-$RUN_KEY" \
|
||||
"bot-bottle-ci-ca-$RUN_KEY" 2>/dev/null || true
|
||||
|
||||
- name: Stage docker coverage for upload
|
||||
run: cp .coverage.docker coverage-docker.dat
|
||||
@@ -98,6 +157,114 @@ jobs:
|
||||
name: coverage-docker
|
||||
path: coverage-docker.dat
|
||||
|
||||
image-input-builds:
|
||||
runs-on: ubuntu-latest
|
||||
steps:
|
||||
- name: Checkout
|
||||
uses: actions/checkout@v4
|
||||
|
||||
- name: Verify shared bases cover supported architectures
|
||||
run: |
|
||||
set -euo pipefail
|
||||
python_ref=$(python3 -c \
|
||||
'import json; print(json.load(open("image-build-args.json"))["PYTHON_BASE_IMAGE"])')
|
||||
node_ref=$(python3 -c \
|
||||
'import json; print(json.load(open("image-build-args.json"))["NODE_BASE_IMAGE"])')
|
||||
docker_cli_ref=$(python3 -c \
|
||||
'import json; print(json.load(open("image-build-args.json"))["DOCKER_CLI_BASE_IMAGE"])')
|
||||
test -n "$python_ref"
|
||||
test -n "$node_ref"
|
||||
test -n "$docker_cli_ref"
|
||||
for ref in "$python_ref" "$node_ref" "$docker_cli_ref"; do
|
||||
docker buildx imagetools inspect --raw "$ref" |
|
||||
python3 -c '
|
||||
import json
|
||||
import sys
|
||||
manifest = json.load(sys.stdin)
|
||||
platforms = {
|
||||
(item["platform"]["os"], item["platform"]["architecture"])
|
||||
for item in manifest["manifests"]
|
||||
if item.get("platform", {}).get("os") != "unknown"
|
||||
}
|
||||
required = {("linux", "amd64"), ("linux", "arm64")}
|
||||
missing = required - platforms
|
||||
if missing:
|
||||
raise SystemExit(f"base manifest lacks supported platforms: {missing}")
|
||||
'
|
||||
done
|
||||
|
||||
- name: Verify Codex archives for all supported architectures
|
||||
run: |
|
||||
set -euo pipefail
|
||||
codex_version=$(
|
||||
sed -n 's/^ARG CODEX_VERSION=//p' bot_bottle/contrib/codex/Dockerfile
|
||||
)
|
||||
test -n "$codex_version"
|
||||
tmp=$(mktemp -d)
|
||||
trap 'rm -rf "$tmp"' EXIT
|
||||
for target in \
|
||||
aarch64-unknown-linux-musl \
|
||||
x86_64-unknown-linux-musl
|
||||
do
|
||||
asset="codex-package-${target}.tar.gz"
|
||||
expected=$(
|
||||
awk -v asset="$asset" '$2 == asset { print $1 }' \
|
||||
bot_bottle/contrib/codex/codex-package_SHA256SUMS
|
||||
)
|
||||
test -n "$expected"
|
||||
curl -fsSL \
|
||||
"https://github.com/openai/codex/releases/download/rust-v${codex_version}/${asset}" \
|
||||
-o "$tmp/$asset"
|
||||
echo "$expected $tmp/$asset" | sha256sum -c -
|
||||
tar -tzf "$tmp/$asset" > "$tmp/$asset.contents"
|
||||
grep -Fx 'bin/codex' "$tmp/$asset.contents"
|
||||
grep -Fx 'bin/codex-code-mode-host' "$tmp/$asset.contents"
|
||||
grep -Fx 'codex-package.json' "$tmp/$asset.contents"
|
||||
done
|
||||
|
||||
- name: Build and smoke-test all supported images
|
||||
run: |
|
||||
set -euo pipefail
|
||||
suffix="${GITHUB_RUN_ID:-${GITHUB_RUN_NUMBER:-image-inputs}}"
|
||||
orchestrator="bot-bottle-orchestrator-inputs:${suffix}"
|
||||
gateway="bot-bottle-gateway-inputs:${suffix}"
|
||||
orchestrator_fc="bot-bottle-orchestrator-fc-inputs:${suffix}"
|
||||
claude="bot-bottle-claude-inputs:${suffix}"
|
||||
codex="bot-bottle-codex-inputs:${suffix}"
|
||||
pi="bot-bottle-pi-inputs:${suffix}"
|
||||
python_base=$(python3 -c \
|
||||
'import json; print(json.load(open("image-build-args.json"))["PYTHON_BASE_IMAGE"])')
|
||||
node_base=$(python3 -c \
|
||||
'import json; print(json.load(open("image-build-args.json"))["NODE_BASE_IMAGE"])')
|
||||
|
||||
docker build --build-arg "PYTHON_BASE_IMAGE=$python_base" \
|
||||
-t "$orchestrator" -f Dockerfile.orchestrator .
|
||||
orchestrator_id=$(docker image inspect --format '{{.Id}}' "$orchestrator")
|
||||
case "$orchestrator_id" in sha256:*) ;; *) exit 1 ;; esac
|
||||
orchestrator_base="bot-bottle-orchestrator-inputs:sha256-${orchestrator_id#sha256:}"
|
||||
docker image tag "$orchestrator_id" "$orchestrator_base"
|
||||
test "$(
|
||||
docker image inspect --format '{{.Id}}' "$orchestrator_base"
|
||||
)" = "$orchestrator_id"
|
||||
docker build --build-arg "PYTHON_BASE_IMAGE=$python_base" \
|
||||
-t "$gateway" -f Dockerfile.gateway .
|
||||
docker build \
|
||||
--build-arg "ORCHESTRATOR_BASE_IMAGE=$orchestrator_base" \
|
||||
-t "$orchestrator_fc" -f Dockerfile.orchestrator.fc .
|
||||
docker build --build-arg "NODE_BASE_IMAGE=$node_base" \
|
||||
-t "$claude" -f bot_bottle/contrib/claude/Dockerfile .
|
||||
docker build --build-arg "NODE_BASE_IMAGE=$node_base" \
|
||||
-t "$codex" -f bot_bottle/contrib/codex/Dockerfile .
|
||||
docker build --build-arg "NODE_BASE_IMAGE=$node_base" \
|
||||
-t "$pi" -f bot_bottle/contrib/pi/Dockerfile .
|
||||
|
||||
docker run --rm --entrypoint python3 "$orchestrator" -c \
|
||||
'import bot_bottle.orchestrator'
|
||||
docker run --rm --entrypoint mitmdump "$gateway" --version
|
||||
docker run --rm "$claude" claude --version
|
||||
docker run --rm "$codex" codex --version
|
||||
docker run --rm "$pi" pi --version
|
||||
|
||||
coverage:
|
||||
needs: [unit, integration-docker]
|
||||
timeout-minutes: 15
|
||||
@@ -131,7 +298,7 @@ jobs:
|
||||
- name: Combined coverage (unit + docker integration)
|
||||
run: PYTHON=python3 bash scripts/coverage.sh aggregate critical
|
||||
|
||||
- name: Diff-coverage gate (changed lines >= 90%)
|
||||
- name: Diff-coverage gate (changed lines >= 80%)
|
||||
run: |
|
||||
git fetch --no-tags origin main:refs/remotes/origin/main
|
||||
python3 scripts/diff_coverage.py --base origin/main --min 90
|
||||
python3 scripts/diff_coverage.py --base origin/main --min 80
|
||||
|
||||
@@ -33,19 +33,28 @@ jobs:
|
||||
- name: Run coverage and extract percentage
|
||||
id: coverage
|
||||
run: |
|
||||
python3 -m coverage run -m unittest discover -t . -s tests/unit > /dev/null 2>&1 || true
|
||||
PERCENT=$(python3 -m coverage report 2>/dev/null | grep '^TOTAL' | grep -oP '\d+(?=%)' | tail -1)
|
||||
set -euo pipefail
|
||||
# Never publish a badge from a failed or partial test run.
|
||||
python3 -m coverage run -m unittest discover -t . -s tests/unit
|
||||
REPORT=$(python3 -m coverage report)
|
||||
printf '%s\n' "$REPORT"
|
||||
PERCENT=$(printf '%s\n' "$REPORT" | awk '$1 == "TOTAL" {gsub("%", "", $NF); print $NF}')
|
||||
test -n "$PERCENT"
|
||||
echo "percent=$PERCENT" >> $GITHUB_OUTPUT
|
||||
echo "Coverage: $PERCENT%"
|
||||
|
||||
- name: Extract core (critical-module) coverage percentage
|
||||
id: core_coverage
|
||||
run: |
|
||||
set -euo pipefail
|
||||
# Reuses the .coverage data from the previous step. The core list is
|
||||
# the single source of truth in scripts/critical-modules.txt; every
|
||||
# core module is unit-tested, so the unit-only run is accurate for it.
|
||||
INCLUDE=$(grep -vE '^[[:space:]]*(#|$)' scripts/critical-modules.txt | paste -sd, -)
|
||||
PERCENT=$(python3 -m coverage report --include="$INCLUDE" 2>/dev/null | grep '^TOTAL' | grep -oP '\d+(?=%)' | tail -1)
|
||||
# validated single source of truth. Fail if a listed path disappeared
|
||||
# or if the measured core falls below ADR 0004's 90% minimum.
|
||||
INCLUDE=$(python3 scripts/critical_modules.py)
|
||||
REPORT=$(python3 -m coverage report --include="$INCLUDE" --fail-under=90)
|
||||
printf '%s\n' "$REPORT"
|
||||
PERCENT=$(printf '%s\n' "$REPORT" | awk '$1 == "TOTAL" {gsub("%", "", $NF); print $NF}')
|
||||
test -n "$PERCENT"
|
||||
echo "percent=$PERCENT" >> $GITHUB_OUTPUT
|
||||
echo "Core coverage: $PERCENT%"
|
||||
|
||||
|
||||
+21
-6
@@ -36,11 +36,23 @@
|
||||
# 9420 git-gate smart HTTP (VM-backend agent-facing transport)
|
||||
# 9100 supervise (MCP HTTP)
|
||||
|
||||
# Based on `python:3.12-slim` (Debian trixie) rather than the
|
||||
# Based on an exact `python:3.12.13-slim-trixie` multi-architecture manifest
|
||||
# rather than the
|
||||
# `mitmproxy/mitmproxy` image (Debian bookworm), matching the trixie base the
|
||||
# orchestrator image needs for buildah (Dockerfile.orchestrator.fc). mitmproxy
|
||||
# is pip-installed to the same effect as the upstream image.
|
||||
FROM python:3.12-slim
|
||||
ARG PYTHON_BASE_IMAGE
|
||||
FROM ${PYTHON_BASE_IMAGE}
|
||||
|
||||
# Freeze apt's package universe as well as the base filesystem. Without a
|
||||
# snapshot, the same Dockerfile resolves different package versions over time.
|
||||
ARG DEBIAN_SNAPSHOT=20260724T000000Z
|
||||
RUN sed -i \
|
||||
-e "s|http://deb.debian.org/debian-security|http://snapshot.debian.org/archive/debian-security/${DEBIAN_SNAPSHOT}|g" \
|
||||
-e "s|https://deb.debian.org/debian-security|http://snapshot.debian.org/archive/debian-security/${DEBIAN_SNAPSHOT}|g" \
|
||||
-e "s|http://deb.debian.org/debian|http://snapshot.debian.org/archive/debian/${DEBIAN_SNAPSHOT}|g" \
|
||||
-e "s|https://deb.debian.org/debian|http://snapshot.debian.org/archive/debian/${DEBIAN_SNAPSHOT}|g" \
|
||||
/etc/apt/sources.list.d/debian.sources
|
||||
|
||||
# Runtime system deps:
|
||||
# git supplies the `git daemon` subcommand (no separate package)
|
||||
@@ -48,16 +60,19 @@ FROM python:3.12-slim
|
||||
# openssh-client supplies the upstream SSH transport the
|
||||
# pre-receive hook uses to forward accepted refs.
|
||||
# ca-certificates is needed for mitmdump upstream TLS.
|
||||
RUN apt-get update \
|
||||
RUN apt-get -o Acquire::Check-Valid-Until=false update \
|
||||
&& apt-get install -y --no-install-recommends \
|
||||
git openssh-client ca-certificates \
|
||||
&& rm -rf /var/lib/apt/lists/*
|
||||
|
||||
# mitmdump (the egress data plane). The upstream mitmproxy image baked
|
||||
# this in; on the plain python base we pip-install the same pinned
|
||||
# version. Its CA dir is set explicitly via `--set confdir=` in
|
||||
# this in; on the plain python base we install a fully resolved lock whose
|
||||
# distributions are all hash-verified. Its CA dir is set explicitly via
|
||||
# `--set confdir=` in
|
||||
# egress-entrypoint.sh, so it doesn't depend on a `mitmproxy` home user.
|
||||
RUN pip install --no-cache-dir mitmproxy==11.1.3
|
||||
COPY requirements.gateway.lock /tmp/requirements.gateway.lock
|
||||
RUN pip install --no-cache-dir --require-hashes \
|
||||
-r /tmp/requirements.gateway.lock
|
||||
|
||||
# gitleaks (the pre-receive hook's secret scanner). Installed from its
|
||||
# official release, pinned by version + SHA256 and verified — rather than
|
||||
|
||||
+13
-8
@@ -9,19 +9,24 @@
|
||||
# Keeping the content in one place means future orchestrator deps (e.g.
|
||||
# iroh) are added here once, not duplicated per backend.
|
||||
#
|
||||
# It stays deliberately lean: the control plane is **stdlib-only** today, so
|
||||
# no third-party payload — none of the gateway's mitmproxy/git/gitleaks
|
||||
# (that's Dockerfile.gateway) and no buildah (that's the firecracker
|
||||
# builder, and lives only in Dockerfile.orchestrator.fc). Keeping the
|
||||
# secret-dense control plane on a minimal dependency surface is the point
|
||||
# (PRD 0070's "secret concentration").
|
||||
# It stays deliberately lean: only the pinned FastAPI/Uvicorn control-plane
|
||||
# stack is installed here — none of the gateway's mitmproxy/git/gitleaks
|
||||
# (that's Dockerfile.gateway) and no buildah (that's firecracker-only).
|
||||
#
|
||||
# Shares the trixie `python:3.12-slim` base with the gateway image.
|
||||
# Shares an exact multi-architecture Python/trixie manifest with the gateway
|
||||
# image. The version-qualified tag keeps the human-readable upstream version;
|
||||
# the digest makes the bytes immutable.
|
||||
|
||||
FROM python:3.12-slim
|
||||
ARG PYTHON_BASE_IMAGE
|
||||
FROM ${PYTHON_BASE_IMAGE}
|
||||
|
||||
WORKDIR /app
|
||||
|
||||
COPY requirements.orchestrator.lock /tmp/requirements.orchestrator.lock
|
||||
RUN pip install --no-cache-dir --require-hashes \
|
||||
-r /tmp/requirements.orchestrator.lock \
|
||||
&& rm /tmp/requirements.orchestrator.lock
|
||||
|
||||
# The orchestrator content. Baked so the image is self-contained (runs from
|
||||
# a built image, no runtime bind-mount); the docker backend may still
|
||||
# bind-mount /app for dev live-reload, which simply overlays this copy.
|
||||
|
||||
@@ -12,10 +12,21 @@
|
||||
# bare microVM (no fuse-overlayfs / overlay module / subuid maps). The trixie
|
||||
# base (from Dockerfile.orchestrator's python:3.12-slim) carries buildah 1.39,
|
||||
# which parses the Dockerfile heredocs agent images use (bookworm's 1.28 can't).
|
||||
# Matches image_builder.
|
||||
FROM bot-bottle-orchestrator:latest
|
||||
# Matches image_builder. There is deliberately no default: the build coordinator
|
||||
# passes the exact local image ID returned by `docker image inspect`, so this
|
||||
# stage cannot silently resolve a stale `:latest` tag.
|
||||
ARG ORCHESTRATOR_BASE_IMAGE
|
||||
FROM ${ORCHESTRATOR_BASE_IMAGE}
|
||||
|
||||
RUN apt-get update \
|
||||
ARG DEBIAN_SNAPSHOT=20260724T000000Z
|
||||
RUN sed -i \
|
||||
-e "s|http://deb.debian.org/debian-security|http://snapshot.debian.org/archive/debian-security/${DEBIAN_SNAPSHOT}|g" \
|
||||
-e "s|https://deb.debian.org/debian-security|http://snapshot.debian.org/archive/debian-security/${DEBIAN_SNAPSHOT}|g" \
|
||||
-e "s|http://deb.debian.org/debian|http://snapshot.debian.org/archive/debian/${DEBIAN_SNAPSHOT}|g" \
|
||||
-e "s|https://deb.debian.org/debian|http://snapshot.debian.org/archive/debian/${DEBIAN_SNAPSHOT}|g" \
|
||||
/etc/apt/sources.list.d/debian.sources
|
||||
|
||||
RUN apt-get -o Acquire::Check-Valid-Until=false update \
|
||||
&& apt-get install -y --no-install-recommends \
|
||||
buildah crun netavark aardvark-dns \
|
||||
&& rm -rf /var/lib/apt/lists/*
|
||||
|
||||
@@ -4,5 +4,8 @@
|
||||
include Dockerfile.gateway
|
||||
include Dockerfile.orchestrator
|
||||
include Dockerfile.orchestrator.fc
|
||||
include image-build-args.json
|
||||
include requirements.gateway.in
|
||||
include requirements.gateway.lock
|
||||
include nix/firecracker-netpool.nix
|
||||
include scripts/firecracker-netpool.sh
|
||||
|
||||
@@ -5,7 +5,7 @@
|
||||
# bot-bottle
|
||||
|
||||
[](https://gitea.dideric.is/didericis/bot-bottle/actions?workflow=test.yml)
|
||||
[](https://coverage.readthedocs.io/)
|
||||
[](https://coverage.readthedocs.io/)
|
||||
[](https://gitea.dideric.is/didericis/bot-bottle/src/branch/main/docs/decisions/0004-coverage-policy.md)
|
||||
|
||||
**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.
|
||||
@@ -15,7 +15,7 @@
|
||||
## 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-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 `bot-bottle 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.
|
||||
- **Tokens the agent never sees** — host secrets live in a gateway; the agent dials `http://gateway: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.
|
||||
@@ -39,7 +39,7 @@ On the legacy Docker backend, the same logical bottle is two containers per agen
|
||||
The Docker topology looks like this:
|
||||
|
||||
```
|
||||
host ( ./cli.py )
|
||||
host ( bot-bottle )
|
||||
│
|
||||
starts │ stops
|
||||
▼
|
||||
@@ -71,11 +71,25 @@ When the agent exits, `cli.py` tears down every gateway 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 gateway 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`.
|
||||
```sh
|
||||
curl -fsSL https://gitea.dideric.is/didericis/bot-bottle/raw/branch/main/install.sh | sh
|
||||
```
|
||||
|
||||
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.
|
||||
The installer is a bootstrapper: it finds a suitable Python, installs bot-bottle with `pipx` (falling back to `pip --user`), creates `~/.bot-bottle`, and runs `bot-bottle doctor`. It is idempotent and never uses `sudo`. Python-native users can skip it entirely with `pipx install bot-bottle` or `uv tool install bot-bottle`.
|
||||
|
||||
> **CI (macOS Apple Container):** the `integration-macos` job (`.gitea/workflows/test.yml`) runs the integration suite against `BOT_BOTTLE_BACKEND=macos-container` on a self-hosted macOS runner labelled `macos`, because Apple Container needs the host virtualization framework and cannot run in a Linux container (so it can't reuse the `kvm` runner). Provision an Apple Silicon host with the `container` CLI on `PATH` and `container system status` running, then register the runner in **host mode** (not docker mode) with the `macos` label — `brew install gitea-runner` (the `act_runner` rename). Give it a Python ≥ 3.11 with `coverage` importable on the launchd service's `PATH` (a launchd service doesn't inherit your shell profile, so pin `node` and the Python env explicitly). The job is **advisory** — `workflow_dispatch` (manual) only, never triggered by push or PR — since a single laptop that sleeps/roams must not block merges or churn on every push to main; its coverage doesn't feed the gate. The infra container is a singleton (`bot-bottle-mac-infra`), so keep runner concurrency at 1.
|
||||
### Requirements
|
||||
|
||||
**Python ≥ 3.11**, and this is the one that trips people up on macOS: the `python3` Apple ships at `/usr/bin/python3` is **3.9.6**, which is too old. Bare `python3` resolves to that stub far more often than people expect. `path_helper` builds a login shell's `PATH` from `/etc/paths` and then appends `/etc/paths.d/*`, and `/usr/bin` sits in the former — so even when `/opt/homebrew/bin` *is* on the `PATH` (via `/etc/paths.d/homebrew`), it comes after `/usr/bin` and loses. Prepending a newer Python is something your shell profile does, and a fresh account, a launchd job, or a CI runner has no such profile. So the installer looks past bare `python3` before giving up: it tries `python3`, then the versioned `python3.11`–`python3.14` names, then `/opt/homebrew/bin`, `/usr/local/bin`, `~/.local/bin`, and python.org framework builds — and tells you which one it picked when it isn't the obvious one. Point it somewhere specific with `BOT_BOTTLE_PYTHON=/path/to/python3`.
|
||||
|
||||
**No `pipx` required.** If `pipx` is present the installer uses it and stays out of the way. If it isn't, bot-bottle installs into a private venv at `~/.bot-bottle/venv` (override with `BOT_BOTTLE_VENV`) and symlinks the entry point into `~/.local/bin`. There is deliberately no `pip install --user` path: Homebrew, python.org and Debian/Ubuntu interpreters are all externally managed (PEP 668), which blocks `--user` outright — so on a Mac it is never the fallback it appears to be. A venv is exempt from PEP 668, and `venv` is stdlib, so unlike `pipx` there is nothing to bootstrap first.
|
||||
|
||||
**`git`**, because the default install spec is a `git+` URL. Set `BOT_BOTTLE_INSTALL_SPEC` to a wheel path or index name to avoid it.
|
||||
|
||||
**A backend**, which the installer deliberately does *not* install for you — `doctor` reports what's missing afterwards. 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 gateway 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 bot-bottle start <agent>` on hosts where neither Apple Container nor KVM is available and Docker is the desired backend.
|
||||
|
||||
> **CI (macOS Apple Container):** the advisory `integration-macos` job in `.gitea/workflows/pre-release-test.yml` runs only on manual dispatch. It targets a self-hosted host-mode runner labelled `macos`; Apple Container cannot run inside the Linux pull-request runner. Provision an Apple Silicon host with the `container` CLI running and Python ≥ 3.11 plus `coverage` on the launchd service's explicit `PATH`. The infra container is a singleton (`bot-bottle-mac-infra`), so keep runner concurrency at 1. Its coverage is reported separately and never feeds the required pull-request gate.
|
||||
|
||||
### Containers inside a bottle
|
||||
|
||||
@@ -166,18 +180,18 @@ 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 gateway 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.
|
||||
- **A one-time privileged network setup** — the per-bottle TAP pool plus the fail-closed `nftables` isolation table. Run `bot-bottle backend setup --backend=firecracker` for the host-appropriate config (a NixOS module, a `sudo` script elsewhere); `bot-bottle 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>
|
||||
BOT_BOTTLE_BACKEND=firecracker bot-bottle 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`.
|
||||
|
||||
> **CI:** the coverage gate (`.gitea/workflows/test.yml` → `coverage` job) runs on a self-hosted runner labelled `kvm`, because the Firecracker backend's VM/SSH orchestration is exercised only by the integration suite, which needs `/dev/kvm` + the provisioned pool (a container runner would skip it and read as uncovered). Provision that runner exactly like a normal Firecracker host — `firecracker` on `PATH`, `/dev/kvm`, the cached guest kernel + static dropbear, and the pool installed as the persistent systemd unit — then register it with the `kvm` label. A Docker-capable hosted job builds the candidate once; KVM tests boot those exact bytes, and a successful main run publishes them. The unit/lint jobs still run on `ubuntu-latest`.
|
||||
> **CI:** Firecracker integration runs in the manually dispatched `.gitea/workflows/pre-release-test.yml` on a self-hosted runner labelled `kvm`; privileged KVM hosts never execute unreviewed PR code automatically. Provision it like a normal Firecracker host: `firecracker` on `PATH`, `/dev/kvm`, the cached guest kernel and static dropbear, and the persistent TAP/nft pool. The required pull-request workflow runs unit plus the complete Docker integration suite on `ubuntu-latest`; see `docs/ci.md`.
|
||||
|
||||
```sh
|
||||
./cli.py start <agent> # builds the image on first run, drops you into claude
|
||||
bot-bottle start <agent> # builds the image on first run, drops you into claude
|
||||
```
|
||||
|
||||
## Manifest
|
||||
@@ -253,7 +267,7 @@ You help maintain Gitea-hosted projects.
|
||||
| `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.
|
||||
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 `bot-bottle 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`.
|
||||
|
||||
|
||||
@@ -226,7 +226,7 @@ class AgentProvider(ABC):
|
||||
initial task in a non-interactive (headless) session.
|
||||
|
||||
Called only when ``--prompt`` is passed to
|
||||
``./cli.py start --headless``; the returned args are appended
|
||||
``bot-bottle 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:
|
||||
|
||||
@@ -30,6 +30,7 @@ if TYPE_CHECKING:
|
||||
BottleImages,
|
||||
BottlePlan,
|
||||
BottleSpec,
|
||||
EnumerationError,
|
||||
ExecResult,
|
||||
)
|
||||
from .selection import (
|
||||
@@ -59,6 +60,7 @@ _LAZY_MODULES: dict[str, str] = {
|
||||
"BottleImages": "base",
|
||||
"BottleBackend": "base",
|
||||
"BackendStatus": "base",
|
||||
"EnumerationError": "base",
|
||||
"get_bottle_backend": "selection",
|
||||
"known_backend_names": "selection",
|
||||
"has_backend": "selection",
|
||||
@@ -100,6 +102,7 @@ __all__ = [
|
||||
"BottlePlan",
|
||||
"BottleSpec",
|
||||
"ExecResult",
|
||||
"EnumerationError",
|
||||
"CommitCancelled",
|
||||
"Freezer",
|
||||
"get_freezer",
|
||||
|
||||
+36
-78
@@ -23,14 +23,14 @@ from dataclasses import dataclass
|
||||
from pathlib import Path
|
||||
from typing import Generator, 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 ..util import expand_tilde
|
||||
from ..manifest import Manifest, ManifestIndex
|
||||
from ..supervisor.plan import SupervisePlan
|
||||
from ..env import resolve_env, ResolvedEnv
|
||||
from ..env import ResolvedEnv
|
||||
from ..workspace import WorkspacePlan, workspace_plan
|
||||
from .print_util import print_multi, visible_agent_env_names
|
||||
from .util import host_skill_dir
|
||||
@@ -42,6 +42,10 @@ class BackendStatus(enum.IntEnum):
|
||||
READY = 0
|
||||
|
||||
|
||||
class EnumerationError(RuntimeError):
|
||||
"""A backend could not produce an authoritative live-resource snapshot."""
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class BottleSpec:
|
||||
"""CLI-supplied intent. Backend-agnostic — each backend's prepare
|
||||
@@ -168,6 +172,10 @@ class BottleCleanupPlan(ABC):
|
||||
"""True iff there is nothing to clean up; the CLI uses this to
|
||||
short-circuit before showing the y/N."""
|
||||
|
||||
@abstractmethod
|
||||
def intersect(self, current: "BottleCleanupPlan") -> "BottleCleanupPlan":
|
||||
"""Resources both displayed to the operator and currently removable."""
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class ExecResult:
|
||||
@@ -296,82 +304,18 @@ class BottleBackend(ABC, Generic[PlanT, CleanupT]):
|
||||
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,
|
||||
reject_nested_containers,
|
||||
resolve_manifest_dockerfile,
|
||||
write_launch_metadata,
|
||||
)
|
||||
|
||||
manifest = self._validate(spec)
|
||||
|
||||
if not self.supports_nested_containers:
|
||||
reject_nested_containers(self.name, manifest)
|
||||
|
||||
self._preflight()
|
||||
|
||||
from ..git_gate import GitGate
|
||||
manifest = GitGate().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)
|
||||
from .preparation import BottlePreparationPlanner
|
||||
prepared = BottlePreparationPlanner(self).prepare(spec)
|
||||
|
||||
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,
|
||||
manifest=prepared.manifest,
|
||||
slug=prepared.slug,
|
||||
resolved_env=prepared.resolved_env,
|
||||
agent_provision_plan=prepared.agent_provision_plan,
|
||||
egress_plan=prepared.egress_plan,
|
||||
supervise_plan=prepared.supervise_plan,
|
||||
git_gate_plan=prepared.git_gate_plan,
|
||||
stage_dir=stage_dir,
|
||||
)
|
||||
|
||||
@@ -552,6 +496,20 @@ class BottleBackend(ABC, Generic[PlanT, CleanupT]):
|
||||
(macos-container) die with a pointer — the default here."""
|
||||
die(f"backend {self.name!r} has no orchestrator control plane")
|
||||
|
||||
def attach_bottled_agents_to_gateway(self) -> None:
|
||||
"""Reconcile all running bottles against the current gateway.
|
||||
|
||||
Called when the gateway is (re)brought up (cold-boot path) to restore
|
||||
the three gateway-dependent services for every live bottle: CA trust,
|
||||
git-gate repos/creds, and egress tokens. Per-bottle failures must be
|
||||
logged and skipped — one unreachable agent must not block the rest.
|
||||
|
||||
Default: no-op. Backends that run a gateway (Firecracker, docker,
|
||||
macOS) override this with a backend-native implementation that reaches
|
||||
running agents via their transport (SSH for Firecracker, exec/cp for
|
||||
docker and macOS). PRD 0081."""
|
||||
return
|
||||
|
||||
@abstractmethod
|
||||
def prepare_cleanup(self) -> CleanupT:
|
||||
"""Enumerate orphaned resources from previous bottles. No side
|
||||
@@ -587,7 +545,7 @@ class BottleBackend(ABC, Generic[PlanT, CleanupT]):
|
||||
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=…]`
|
||||
0. Invoked generically by `bot-bottle 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."""
|
||||
@@ -604,14 +562,14 @@ class BottleBackend(ABC, Generic[PlanT, CleanupT]):
|
||||
stderr. When quiet=True returns the status code silently —
|
||||
useful for cheap programmatic checks.
|
||||
|
||||
Invoked by `./cli.py backend status [--backend=…]` (quiet=False)
|
||||
Invoked by `bot-bottle backend status [--backend=…]` (quiet=False)
|
||||
and by is_backend_ready() (caller-controlled)."""
|
||||
|
||||
@classmethod
|
||||
@abstractmethod
|
||||
def teardown(cls) -> int:
|
||||
"""Undo `setup()` — the inverse operation, surfaced as
|
||||
`./cli.py backend teardown [--backend=…]` (uninstall). Symmetric
|
||||
`bot-bottle 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
|
||||
|
||||
@@ -0,0 +1,60 @@
|
||||
"""Shared destructive-cleanup execution and failure accounting."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import os
|
||||
import shutil
|
||||
import subprocess
|
||||
from collections.abc import Sequence
|
||||
from pathlib import Path
|
||||
|
||||
|
||||
class CleanupError(RuntimeError):
|
||||
"""One or more approved cleanup mutations did not complete."""
|
||||
|
||||
|
||||
class CleanupFailures:
|
||||
"""Attempt every approved mutation, then fail with complete diagnostics."""
|
||||
|
||||
def __init__(self) -> None:
|
||||
self._messages: list[str] = []
|
||||
|
||||
def run(self, argv: Sequence[str], description: str) -> None:
|
||||
raw_timeout = os.environ.get(
|
||||
"BOT_BOTTLE_CLEANUP_COMMAND_TIMEOUT_SECONDS", "120",
|
||||
)
|
||||
try:
|
||||
timeout = float(raw_timeout)
|
||||
except ValueError:
|
||||
timeout = 120.0
|
||||
try:
|
||||
result = subprocess.run(
|
||||
list(argv), capture_output=True, text=True, check=False,
|
||||
timeout=max(timeout, 1.0),
|
||||
)
|
||||
except (OSError, subprocess.SubprocessError) as exc:
|
||||
self._messages.append(f"{description}: {exc}")
|
||||
return
|
||||
if result.returncode != 0:
|
||||
detail = (result.stderr or result.stdout).strip()
|
||||
self._messages.append(
|
||||
f"{description}: {detail or f'exit {result.returncode}'}"
|
||||
)
|
||||
|
||||
def remove_tree(self, path: Path, description: str) -> None:
|
||||
try:
|
||||
shutil.rmtree(path)
|
||||
except FileNotFoundError:
|
||||
return
|
||||
except OSError as exc:
|
||||
self._messages.append(f"{description}: {exc}")
|
||||
|
||||
def record(self, message: str) -> None:
|
||||
self._messages.append(message)
|
||||
|
||||
def raise_if_any(self) -> None:
|
||||
if self._messages:
|
||||
raise CleanupError("; ".join(self._messages))
|
||||
|
||||
|
||||
__all__ = ["CleanupError", "CleanupFailures"]
|
||||
@@ -46,6 +46,22 @@ class DockerBottleCleanupPlan(BottleCleanupPlan):
|
||||
and not self.orphan_state_dirs
|
||||
)
|
||||
|
||||
def intersect(self, current: BottleCleanupPlan) -> "DockerBottleCleanupPlan":
|
||||
if not isinstance(current, DockerBottleCleanupPlan):
|
||||
raise TypeError("cleanup plans must have the same backend type")
|
||||
return DockerBottleCleanupPlan(
|
||||
projects=tuple(x for x in self.projects if x in current.projects),
|
||||
stray_containers=tuple(
|
||||
x for x in self.stray_containers if x in current.stray_containers
|
||||
),
|
||||
stray_networks=tuple(
|
||||
x for x in self.stray_networks if x in current.stray_networks
|
||||
),
|
||||
orphan_state_dirs=tuple(
|
||||
x for x in self.orphan_state_dirs if x in current.orphan_state_dirs
|
||||
),
|
||||
)
|
||||
|
||||
def print(self) -> None:
|
||||
print(file=sys.stderr)
|
||||
for name in self.projects:
|
||||
|
||||
@@ -23,11 +23,12 @@ Active-agent enumeration lives in `backend/docker/enumerate.py`.
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import shutil
|
||||
import subprocess
|
||||
|
||||
from ...paths import bot_bottle_root
|
||||
from ...log import info, warn
|
||||
from ...log import info
|
||||
from .. import EnumerationError
|
||||
from ..cleanup_control import CleanupFailures
|
||||
from . import util as docker_mod
|
||||
from .bottle_cleanup_plan import DockerBottleCleanupPlan
|
||||
from ...bottle_state import bottle_state_dir, is_preserved
|
||||
@@ -36,15 +37,17 @@ from .compose import COMPOSE_PROJECT_PREFIX, list_compose_projects
|
||||
|
||||
def _list_prefixed_containers() -> list[str]:
|
||||
"""All bot-bottle-prefixed containers, running or stopped."""
|
||||
result = subprocess.run(
|
||||
["docker", "ps", "-a",
|
||||
"--filter", f"name=^{COMPOSE_PROJECT_PREFIX}",
|
||||
"--format", "{{.Names}}\t{{.Label \"com.docker.compose.project\"}}"],
|
||||
capture_output=True, text=True, check=False,
|
||||
)
|
||||
try:
|
||||
result = subprocess.run(
|
||||
["docker", "ps", "-a",
|
||||
"--filter", f"name=^{COMPOSE_PROJECT_PREFIX}",
|
||||
"--format", "{{.Names}}\t{{.Label \"com.docker.compose.project\"}}"],
|
||||
capture_output=True, text=True, check=False,
|
||||
)
|
||||
except OSError as exc:
|
||||
raise EnumerationError(f"docker ps failed: {exc}") from exc
|
||||
if result.returncode != 0:
|
||||
warn(f"docker ps failed: {result.stderr.strip()}")
|
||||
return []
|
||||
raise EnumerationError(f"docker ps failed: {result.stderr.strip()}")
|
||||
out: list[str] = []
|
||||
for line in (result.stdout or "").splitlines():
|
||||
if not line:
|
||||
@@ -63,15 +66,19 @@ def _list_prefixed_networks() -> list[str]:
|
||||
to a compose project. Compose-managed networks have a
|
||||
`com.docker.compose.project` label; bare ones (from pre-compose
|
||||
code paths) don't."""
|
||||
result = subprocess.run(
|
||||
["docker", "network", "ls",
|
||||
"--filter", f"name={COMPOSE_PROJECT_PREFIX}",
|
||||
"--format", "{{.Name}}\t{{.Label \"com.docker.compose.project\"}}"],
|
||||
capture_output=True, text=True, check=False,
|
||||
)
|
||||
try:
|
||||
result = subprocess.run(
|
||||
["docker", "network", "ls",
|
||||
"--filter", f"name={COMPOSE_PROJECT_PREFIX}",
|
||||
"--format", "{{.Name}}\t{{.Label \"com.docker.compose.project\"}}"],
|
||||
capture_output=True, text=True, check=False,
|
||||
)
|
||||
except OSError as exc:
|
||||
raise EnumerationError(f"docker network ls failed: {exc}") from exc
|
||||
if result.returncode != 0:
|
||||
warn(f"docker network ls failed: {result.stderr.strip()}")
|
||||
return []
|
||||
raise EnumerationError(
|
||||
f"docker network ls failed: {result.stderr.strip()}"
|
||||
)
|
||||
out: list[str] = []
|
||||
for line in (result.stdout or "").splitlines():
|
||||
if not line:
|
||||
@@ -120,7 +127,10 @@ def prepare_cleanup() -> DockerBottleCleanupPlan:
|
||||
`enumerate_active_agents()` so the orphan-state-dir bucket
|
||||
doesn't include slugs whose non-docker bottle is still up."""
|
||||
docker_mod.require_docker()
|
||||
projects = list_compose_projects()
|
||||
projects = list_compose_projects(
|
||||
warn_on_error=False,
|
||||
raise_on_error=True,
|
||||
)
|
||||
project_set = set(projects)
|
||||
# Late import to avoid a circular at module-load time —
|
||||
# the backend package's __init__ imports this module.
|
||||
@@ -140,40 +150,30 @@ def cleanup(plan: DockerBottleCleanupPlan) -> None:
|
||||
"""Remove everything in the plan. Projects first (whose `compose
|
||||
down` reaps their containers + networks atomically), then stray
|
||||
legacy resources, then orphan state dirs."""
|
||||
failures = CleanupFailures()
|
||||
for project in plan.projects:
|
||||
info(f"docker compose down ({project})")
|
||||
result = subprocess.run(
|
||||
failures.run(
|
||||
["docker", "compose", "-p", project, "down", "--volumes"],
|
||||
capture_output=True, text=True, check=False,
|
||||
f"docker compose down failed for {project}",
|
||||
)
|
||||
if result.returncode != 0:
|
||||
warn(
|
||||
f"compose down failed for {project}: "
|
||||
f"{result.stderr.strip()}"
|
||||
)
|
||||
|
||||
for name in plan.stray_containers:
|
||||
info(f"removing stray container {name}")
|
||||
subprocess.run(
|
||||
failures.run(
|
||||
["docker", "rm", "-f", name],
|
||||
stdout=subprocess.DEVNULL,
|
||||
stderr=subprocess.DEVNULL,
|
||||
check=False,
|
||||
f"removing stray container {name}",
|
||||
)
|
||||
|
||||
for name in plan.stray_networks:
|
||||
info(f"removing stray network {name}")
|
||||
subprocess.run(
|
||||
failures.run(
|
||||
["docker", "network", "rm", name],
|
||||
stdout=subprocess.DEVNULL,
|
||||
stderr=subprocess.DEVNULL,
|
||||
check=False,
|
||||
f"removing stray network {name}",
|
||||
)
|
||||
|
||||
for identity in plan.orphan_state_dirs:
|
||||
path = bottle_state_dir(identity)
|
||||
info(f"removing orphan state dir {path}")
|
||||
try:
|
||||
shutil.rmtree(path, ignore_errors=True)
|
||||
except OSError as e:
|
||||
warn(f"failed to remove {path}: {e}")
|
||||
failures.remove_tree(path, f"removing orphan state dir {path}")
|
||||
failures.raise_if_any()
|
||||
|
||||
@@ -16,6 +16,7 @@ from pathlib import Path
|
||||
from typing import Any
|
||||
|
||||
from ...log import die, warn
|
||||
from ..base import EnumerationError
|
||||
|
||||
|
||||
# --- Lifecycle helpers (PRD 0018 chunk 3) ----------------------------------
|
||||
@@ -52,19 +53,20 @@ def slug_from_compose_project(project: str) -> str:
|
||||
|
||||
|
||||
def list_compose_projects(
|
||||
*, include_stopped: bool = True, warn_on_error: bool = True,
|
||||
*,
|
||||
include_stopped: bool = True,
|
||||
warn_on_error: bool = True,
|
||||
raise_on_error: bool = False,
|
||||
) -> list[str]:
|
||||
"""All compose project names starting with `bot-bottle-`.
|
||||
`include_stopped=True` (default) runs `docker compose ls --all`
|
||||
so exited projects appear too; pass False to get only projects
|
||||
with at least one running container.
|
||||
|
||||
Returns [] on docker daemon errors or malformed output rather
|
||||
than raising — callers should treat the empty list as "no
|
||||
projects discoverable", not "no projects exist". `warn_on_error`
|
||||
stays true for explicit operator commands like cleanup, but active
|
||||
discovery paths set it false so dashboard refreshes don't spam
|
||||
stderr while Docker Desktop is stopped."""
|
||||
Best-effort callers get ``[]`` on Docker errors or malformed output.
|
||||
Enumeration callers pass ``raise_on_error=True`` so a failed query is not
|
||||
reported as an authoritative empty result.
|
||||
"""
|
||||
argv = ["docker", "compose", "ls", "--format", "json"]
|
||||
if include_stopped:
|
||||
argv.insert(3, "--all")
|
||||
@@ -72,19 +74,30 @@ def list_compose_projects(
|
||||
result = subprocess.run(
|
||||
argv, capture_output=True, text=True, check=False,
|
||||
)
|
||||
except FileNotFoundError:
|
||||
# docker binary not on PATH — same shape as a daemon-down
|
||||
# error from the caller's POV: no projects discoverable.
|
||||
except OSError as exc:
|
||||
# Not only "not found": docker on PATH but not executable by this
|
||||
# user raises PermissionError. Either way the query never ran, so an
|
||||
# enumeration caller must not read the empty result as authoritative.
|
||||
if raise_on_error:
|
||||
raise EnumerationError(
|
||||
f"docker compose ls failed: docker unavailable ({exc})"
|
||||
) from exc
|
||||
return []
|
||||
if result.returncode != 0:
|
||||
message = f"docker compose ls failed: {result.stderr.strip()}"
|
||||
if raise_on_error:
|
||||
raise EnumerationError(message)
|
||||
if warn_on_error:
|
||||
warn(f"docker compose ls failed: {result.stderr.strip()}")
|
||||
warn(message)
|
||||
return []
|
||||
try:
|
||||
projects = json.loads(result.stdout or "[]")
|
||||
except json.JSONDecodeError as e:
|
||||
message = f"docker compose ls returned malformed JSON: {e}"
|
||||
if raise_on_error:
|
||||
raise EnumerationError(message) from e
|
||||
if warn_on_error:
|
||||
warn(f"docker compose ls returned malformed JSON: {e}")
|
||||
warn(message)
|
||||
return []
|
||||
names: list[str] = []
|
||||
for p in projects:
|
||||
@@ -97,7 +110,10 @@ def list_compose_projects(
|
||||
|
||||
|
||||
def list_active_slugs(
|
||||
*, include_stopped: bool = False, warn_on_error: bool = True,
|
||||
*,
|
||||
include_stopped: bool = False,
|
||||
warn_on_error: bool = True,
|
||||
raise_on_error: bool = False,
|
||||
) -> list[str]:
|
||||
"""Slugs (project name minus prefix) of currently-running
|
||||
bottles. Used by the dashboard's operator-edit verbs to choose
|
||||
@@ -108,6 +124,7 @@ def list_active_slugs(
|
||||
for p in list_compose_projects(
|
||||
include_stopped=include_stopped,
|
||||
warn_on_error=warn_on_error,
|
||||
raise_on_error=raise_on_error,
|
||||
)
|
||||
) if slug
|
||||
)
|
||||
|
||||
@@ -68,6 +68,11 @@ def _network_container_ips(network: str) -> list[str]:
|
||||
"docker", "network", "inspect", "--format",
|
||||
"{{range .Containers}}{{.IPv4Address}} {{end}}", network,
|
||||
])
|
||||
if proc.returncode != 0:
|
||||
detail = proc.stderr.strip() or f"exit {proc.returncode}"
|
||||
raise ConsolidatedLaunchError(
|
||||
f"could not inspect addresses on gateway network {network}: {detail}"
|
||||
)
|
||||
ips: list[str] = []
|
||||
for entry in proc.stdout.split():
|
||||
ips.append(entry.split("/", 1)[0])
|
||||
|
||||
@@ -1,9 +1,8 @@
|
||||
"""Active-agent enumeration for the docker backend.
|
||||
|
||||
Returns `ActiveAgent` records the CLI `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.
|
||||
dashboard agents pane consume. Docker query failures raise rather
|
||||
than masquerading as an authoritative empty result.
|
||||
|
||||
The parser (`_parse_services_by_project`) is exposed for direct
|
||||
unit testing; the docker `docker ps` invocation is in
|
||||
@@ -13,17 +12,18 @@ from __future__ import annotations
|
||||
|
||||
import subprocess
|
||||
|
||||
from .. import ActiveAgent
|
||||
from .. import ActiveAgent, EnumerationError
|
||||
from ...bottle_state import read_metadata
|
||||
from .compose import compose_project_name, list_active_slugs
|
||||
|
||||
|
||||
def enumerate_active() -> list[ActiveAgent]:
|
||||
"""All currently-running docker-backed agents. Caller is
|
||||
responsible for gating on `has_backend('docker')` if it
|
||||
matters; if docker is missing the `docker ps` call below
|
||||
returns an empty list silently."""
|
||||
slugs = list_active_slugs(include_stopped=False, warn_on_error=False)
|
||||
"""All currently-running docker-backed agents."""
|
||||
slugs = list_active_slugs(
|
||||
include_stopped=False,
|
||||
warn_on_error=False,
|
||||
raise_on_error=True,
|
||||
)
|
||||
if not slugs:
|
||||
return []
|
||||
services_by_project = _query_services_by_project()
|
||||
@@ -74,8 +74,9 @@ def _query_services_by_project() -> dict[str, set[str]]:
|
||||
],
|
||||
capture_output=True, text=True, check=False,
|
||||
)
|
||||
except FileNotFoundError:
|
||||
return {}
|
||||
except OSError as exc:
|
||||
# Missing, or on PATH but not executable by this user (PermissionError).
|
||||
raise EnumerationError(f"docker ps failed: docker unavailable ({exc})") from exc
|
||||
if r.returncode != 0:
|
||||
return {}
|
||||
raise EnumerationError(f"docker ps failed: {r.stderr.strip()}")
|
||||
return _parse_services_by_project(r.stdout or "")
|
||||
|
||||
@@ -17,6 +17,10 @@ from ...gateway import (
|
||||
DEFAULT_CA_TIMEOUT_SECONDS, CA_POLL_SECONDS, GATEWAY_CA_CERT, GatewayError
|
||||
)
|
||||
|
||||
DEFAULT_GATEWAY_SUBNET = "10.242.255.0/24"
|
||||
_GATEWAY_SUBNET_LABEL = "bot-bottle.gateway-subnet"
|
||||
|
||||
|
||||
class DockerGateway(Gateway):
|
||||
"""The consolidated gateway as a single, fixed-name Docker container.
|
||||
|
||||
@@ -35,6 +39,8 @@ class DockerGateway(Gateway):
|
||||
build_context: Path | None = None,
|
||||
dockerfile: str | None = GATEWAY_DOCKERFILE,
|
||||
host_port_bindings: tuple[int, ...] = (),
|
||||
ca_mount_source: str | Path | None = None,
|
||||
subnet: str | None = None,
|
||||
) -> None:
|
||||
self.image_ref = image_ref
|
||||
self.name = name
|
||||
@@ -59,6 +65,15 @@ class DockerGateway(Gateway):
|
||||
# backend's dev-harness gateway so VMs can reach it via their TAP link;
|
||||
# Docker's DNAT + the nft `ct status dnat accept` rule handle the rest.
|
||||
self._host_port_bindings = host_port_bindings
|
||||
self._subnet = (
|
||||
subnet
|
||||
or os.environ.get("BOT_BOTTLE_DOCKER_GATEWAY_SUBNET", "").strip()
|
||||
or DEFAULT_GATEWAY_SUBNET
|
||||
)
|
||||
configured_ca = os.environ.get("BOT_BOTTLE_DOCKER_CA_MOUNT", "").strip()
|
||||
self._ca_mount_source = str(
|
||||
ca_mount_source or configured_ca or host_gateway_ca_dir()
|
||||
)
|
||||
|
||||
def image_exists(self) -> bool:
|
||||
return run_docker(["docker", "image", "inspect", self.image_ref]).returncode == 0
|
||||
@@ -81,6 +96,11 @@ class DockerGateway(Gateway):
|
||||
str(context)]
|
||||
if os.environ.get("BOT_BOTTLE_NO_CACHE"):
|
||||
argv.insert(2, "--no-cache")
|
||||
for name, value in resources.image_build_args(
|
||||
self._dockerfile,
|
||||
context=context,
|
||||
).items():
|
||||
argv[-1:-1] = ["--build-arg", f"{name}={value}"]
|
||||
proc = run_docker(argv)
|
||||
if proc.returncode != 0:
|
||||
raise GatewayError(f"gateway image build failed: {proc.stderr.strip()}")
|
||||
@@ -109,10 +129,72 @@ class DockerGateway(Gateway):
|
||||
def _ensure_network(self) -> None:
|
||||
"""Create the shared gateway network if it doesn't exist. Idempotent —
|
||||
a concurrent create loses harmlessly (the loser sees 'already exists').
|
||||
Docker picks the subnet; the launcher reads it back to allocate IPs."""
|
||||
if run_docker(["docker", "network", "inspect", self.network]).returncode == 0:
|
||||
return
|
||||
proc = run_docker(["docker", "network", "create", self.network])
|
||||
The explicit subnet is required because bottle attribution pins source
|
||||
IPs; Docker rejects static endpoint addresses on an auto-IPAM network."""
|
||||
inspected = run_docker([
|
||||
"docker", "network", "inspect",
|
||||
"--format", f'{{{{index .Labels "{_GATEWAY_SUBNET_LABEL}"}}}}',
|
||||
self.network,
|
||||
])
|
||||
if inspected.returncode == 0:
|
||||
marker = inspected.stdout.strip()
|
||||
if marker in {"", self._subnet}:
|
||||
return
|
||||
# Inspectable but mislabelled: the stale auto-IPAM network created
|
||||
# by older releases. Replace it below.
|
||||
stale = True
|
||||
else:
|
||||
# inspect failed. Classify by stderr — do NOT assume "not absent"
|
||||
# implies "poisoned": a transient daemon/API error, permission
|
||||
# failure, timeout, or bad context also fails here, and destroying
|
||||
# the shared gateway on that guess would tear the network out from
|
||||
# under every live bottle.
|
||||
err = inspected.stderr.lower()
|
||||
if "no such network" in err or "not found" in err:
|
||||
# Absent: nothing to replace — create it below.
|
||||
stale = False
|
||||
elif "parseaddr" in err:
|
||||
# Present but poisoned. A daemon that default-enables IPv6
|
||||
# attaches an fdd0::/64 subnet whose `::1/64` gateway trips
|
||||
# docker's own netip.ParseAddr in `network inspect`/`ls`, so the
|
||||
# command exits non-zero with that signature. A fixed release
|
||||
# never *creates* such a network, but one can survive on a
|
||||
# shared host from an older or concurrent launch — and
|
||||
# `--ipv6=false` alone can't heal it, since the create below only
|
||||
# no-ops on "already exists". Force-replace it so later reads
|
||||
# (e.g. `_network_cidr` pinning a source IP) stop failing.
|
||||
stale = True
|
||||
else:
|
||||
# Unrecognized failure: no evidence the network is malformed.
|
||||
# Surface it rather than mutate shared state on a guess.
|
||||
raise GatewayError(
|
||||
f"gateway network {self.network} could not be inspected: "
|
||||
f"{inspected.stderr.strip()}"
|
||||
)
|
||||
if stale:
|
||||
# Migrate the stale/poisoned network. Removing the fixed gateway is
|
||||
# safe here: this launch recreates it.
|
||||
run_docker(["docker", "rm", "--force", self.name])
|
||||
removed = run_docker(["docker", "network", "rm", self.network])
|
||||
if removed.returncode != 0 and "no such network" not in removed.stderr.lower():
|
||||
raise GatewayError(
|
||||
f"gateway network {self.network} needs explicit subnet "
|
||||
f"{self._subnet} but could not be replaced: "
|
||||
f"{removed.stderr.strip()}"
|
||||
)
|
||||
proc = run_docker([
|
||||
"docker", "network", "create",
|
||||
# bot-bottle attribution pins IPv4 source IPs; it has no IPv6
|
||||
# support. Disable IPv6 explicitly so a daemon that default-enables
|
||||
# it (default-address-pools) can't attach an fdd0::/64 subnet — a
|
||||
# malformed `::1/64` gateway address then trips docker's own
|
||||
# ParseAddr in `network inspect`/`ls`, which poisons every launch
|
||||
# that reads this network's subnet.
|
||||
"--ipv6=false",
|
||||
"--subnet", self._subnet,
|
||||
"--label", f"{_GATEWAY_SUBNET_LABEL}={self._subnet}",
|
||||
self.network,
|
||||
])
|
||||
if proc.returncode != 0 and "already exists" not in proc.stderr:
|
||||
raise GatewayError(
|
||||
f"gateway network {self.network} failed to create: {proc.stderr.strip()}"
|
||||
@@ -143,9 +225,9 @@ class DockerGateway(Gateway):
|
||||
# Recreate when the running container's image is stale (a rebuild),
|
||||
# so source changes to the gateway's flat daemons take effect — not
|
||||
# just when the container is absent.
|
||||
self._ensure_network()
|
||||
if self.is_running() and self._running_image_is_current():
|
||||
return
|
||||
self._ensure_network()
|
||||
# Clear any stale (stopped OR outdated-image) container holding the
|
||||
# fixed name, then start fresh. `rm --force` on an absent name is a
|
||||
# tolerated no-op.
|
||||
@@ -158,7 +240,7 @@ class DockerGateway(Gateway):
|
||||
# Persist the self-generated CA on the host so it survives both
|
||||
# container recreation AND docker volume pruning (agents trust it)
|
||||
# — see host_gateway_ca_dir / issue #450.
|
||||
"--volume", f"{host_gateway_ca_dir()}:{MITMPROXY_HOME}",
|
||||
"--volume", f"{self._ca_mount_source}:{MITMPROXY_HOME}",
|
||||
# No DB mount: the data plane (egress / supervise / git-gate) reaches
|
||||
# the supervise queue over the control-plane RPC and never opens
|
||||
# bot-bottle.db, so the gateway container gets no file handle on it
|
||||
@@ -253,4 +335,4 @@ class DockerGateway(Gateway):
|
||||
def provisioning_transport(self) -> GatewayTransport:
|
||||
"""The exec/cp transport git-gate provisioning stages per-bottle repos +
|
||||
deploy keys through (over the docker socket)."""
|
||||
return DockerGatewayTransport(self.name)
|
||||
return DockerGatewayTransport(self.name)
|
||||
|
||||
@@ -33,7 +33,6 @@ from .orchestrator import (
|
||||
ORCHESTRATOR_NAME,
|
||||
ORCHESTRATOR_NETWORK,
|
||||
)
|
||||
from ...paths import bot_bottle_root
|
||||
from ... import resources
|
||||
from ...gateway import (
|
||||
GATEWAY_IMAGE,
|
||||
@@ -69,6 +68,8 @@ class DockerInfraService(InfraService):
|
||||
gateway_image: str = GATEWAY_IMAGE,
|
||||
repo_root: Path | None = None,
|
||||
host_root: Path | None = None,
|
||||
root_mount_source: str | Path | None = None,
|
||||
gateway_ca_mount_source: str | Path | None = None,
|
||||
orchestrator_name: str = ORCHESTRATOR_NAME,
|
||||
orchestrator_label: str = ORCHESTRATOR_LABEL,
|
||||
gateway_name: str = GATEWAY_NAME,
|
||||
@@ -78,10 +79,14 @@ class DockerInfraService(InfraService):
|
||||
self.control_network = control_network
|
||||
self.orchestrator_image = orchestrator_image
|
||||
self.gateway_image = gateway_image
|
||||
# Build context / bind-mount source: the repo root in a checkout, a
|
||||
# staged copy from the installed wheel otherwise (bot_bottle.resources).
|
||||
# Build context: the repo root in a checkout, a staged copy from the
|
||||
# installed wheel otherwise (bot_bottle.resources).
|
||||
self._repo_root = repo_root if repo_root is not None else resources.build_root()
|
||||
self._host_root = host_root or bot_bottle_root()
|
||||
if host_root is not None and root_mount_source is not None:
|
||||
raise ValueError("pass host_root or root_mount_source, not both")
|
||||
self._host_root = host_root
|
||||
self._root_mount_source = root_mount_source
|
||||
self._gateway_ca_mount_source = gateway_ca_mount_source
|
||||
self._orchestrator_name = orchestrator_name
|
||||
self._orchestrator_label = orchestrator_label
|
||||
self._gateway_name = gateway_name
|
||||
@@ -98,6 +103,7 @@ class DockerInfraService(InfraService):
|
||||
control_network=self.control_network,
|
||||
repo_root=self._repo_root,
|
||||
host_root=self._host_root,
|
||||
root_mount_source=self._root_mount_source,
|
||||
)
|
||||
|
||||
def gateway(self) -> DockerGateway:
|
||||
@@ -112,6 +118,7 @@ class DockerInfraService(InfraService):
|
||||
network=self.network,
|
||||
control_network=self.control_network,
|
||||
build_context=self._repo_root,
|
||||
ca_mount_source=self._gateway_ca_mount_source,
|
||||
)
|
||||
|
||||
def ensure_running(
|
||||
|
||||
@@ -42,13 +42,9 @@ ORCHESTRATOR_IMAGE = os.environ.get(
|
||||
)
|
||||
ORCHESTRATOR_DOCKERFILE = "Dockerfile.orchestrator"
|
||||
# Baked as a container label so `ensure_running` can detect whether the running
|
||||
# orchestrator is executing the current bind-mounted source.
|
||||
# orchestrator image was built from the current source.
|
||||
ORCHESTRATOR_SOURCE_HASH_LABEL = "bot-bottle-orchestrator-source-hash"
|
||||
|
||||
# The bind-mount path for the live control-plane source inside the container.
|
||||
# PYTHONPATH points here so a code change takes effect on the next launch
|
||||
# without an image rebuild.
|
||||
_SRC_IN_CONTAINER = "/bot-bottle-src"
|
||||
# Bot-bottle host-root bind-mount (DB + state) inside the orchestrator. The
|
||||
# control plane opens bot-bottle.db under here (via BOT_BOTTLE_ROOT ->
|
||||
# host_db_path()); it is the ONLY container with a handle on it (issue #469).
|
||||
@@ -72,23 +68,51 @@ class DockerOrchestrator(Orchestrator):
|
||||
control_network: str = ORCHESTRATOR_NETWORK,
|
||||
repo_root: Path | None = None,
|
||||
host_root: Path | None = None,
|
||||
root_mount_source: str | Path | None = None,
|
||||
client_host: str | None = None,
|
||||
client_network: str | None = None,
|
||||
bind_host: str | None = None,
|
||||
dockerfile: str | None = ORCHESTRATOR_DOCKERFILE,
|
||||
) -> None:
|
||||
if host_root is not None and root_mount_source is not None:
|
||||
raise ValueError("pass host_root or root_mount_source, not both")
|
||||
self.image_ref = image_ref
|
||||
self.name = name
|
||||
self.label = label
|
||||
self.port = port
|
||||
self.control_network = control_network
|
||||
# Build context / bind-mount source: the repo root in a checkout, a
|
||||
# staged copy from the installed wheel otherwise (bot_bottle.resources).
|
||||
# Build context: the repo root in a checkout, a staged copy from the
|
||||
# installed wheel otherwise (bot_bottle.resources).
|
||||
self._repo_root = repo_root if repo_root is not None else resources.build_root()
|
||||
self._host_root = host_root or bot_bottle_root()
|
||||
configured_root = os.environ.get("BOT_BOTTLE_DOCKER_ROOT_MOUNT", "").strip()
|
||||
self._root_mount_source = str(
|
||||
root_mount_source or configured_root or host_root or bot_bottle_root()
|
||||
)
|
||||
configured_network = os.environ.get(
|
||||
"BOT_BOTTLE_DOCKER_CLIENT_NETWORK", ""
|
||||
).strip()
|
||||
self._client_network = client_network or configured_network or None
|
||||
configured_host = os.environ.get(
|
||||
"BOT_BOTTLE_DOCKER_HOST_ADDRESS", ""
|
||||
).strip()
|
||||
self._client_host = (
|
||||
client_host or configured_host
|
||||
or (self.name if self._client_network else "127.0.0.1")
|
||||
)
|
||||
# A socket-shared CI runner reaches published ports through its Docker
|
||||
# network rather than its own loopback. Production stays bound to host
|
||||
# loopback unless a caller explicitly selects another client.
|
||||
self._bind_host = bind_host or (
|
||||
"0.0.0.0"
|
||||
if not self._client_network and self._client_host != "127.0.0.1"
|
||||
else "127.0.0.1"
|
||||
)
|
||||
self._dockerfile = dockerfile
|
||||
|
||||
def url(self) -> str:
|
||||
"""Host-side control-plane URL — the orchestrator's published loopback,
|
||||
which the CLI reaches."""
|
||||
return f"http://127.0.0.1:{self.port}"
|
||||
"""Control-plane URL reachable by this Docker client."""
|
||||
port = DEFAULT_PORT if self._client_network else self.port
|
||||
return f"http://{self._client_host}:{port}"
|
||||
|
||||
def gateway_url(self) -> str:
|
||||
"""The URL the gateway's data plane resolves policy against — the
|
||||
@@ -107,6 +131,11 @@ class DockerOrchestrator(Orchestrator):
|
||||
str(self._repo_root)]
|
||||
if os.environ.get("BOT_BOTTLE_NO_CACHE"):
|
||||
argv.insert(2, "--no-cache")
|
||||
for name, value in resources.image_build_args(
|
||||
self._dockerfile,
|
||||
context=self._repo_root,
|
||||
).items():
|
||||
argv[-1:-1] = ["--build-arg", f"{name}={value}"]
|
||||
proc = run_docker(argv)
|
||||
if proc.returncode != 0:
|
||||
raise GatewayError(
|
||||
@@ -119,8 +148,7 @@ class DockerOrchestrator(Orchestrator):
|
||||
return self.name in proc.stdout.split()
|
||||
|
||||
def _source_current(self, current_hash: str) -> bool:
|
||||
"""True iff the running orchestrator was started from the current
|
||||
bind-mounted source."""
|
||||
"""True iff the running orchestrator image matches current source."""
|
||||
if not self.is_running():
|
||||
return False
|
||||
proc = run_docker([
|
||||
@@ -182,15 +210,19 @@ class DockerOrchestrator(Orchestrator):
|
||||
# Control network only — agents are never on it, so they have no
|
||||
# route to the control plane (the L3 block, not just the JWT).
|
||||
"--network", self.control_network,
|
||||
# Host CLI reaches the control plane here (loopback only). The
|
||||
# Host CLI reaches the control plane here (loopback by default).
|
||||
# Socket-shared CI joins the container directly to the job network;
|
||||
# the host-side mapping remains loopback-only in that topology. The
|
||||
# orchestrator listens on the fixed DEFAULT_PORT inside the
|
||||
# container; self.port is the host-side published port.
|
||||
"--publish", f"127.0.0.1:{self.port}:{DEFAULT_PORT}",
|
||||
# Live control-plane source (code changes without an image rebuild).
|
||||
"--volume", f"{self._repo_root}:{_SRC_IN_CONTAINER}:ro",
|
||||
"--env", f"PYTHONPATH={_SRC_IN_CONTAINER}",
|
||||
"--publish", f"{self._bind_host}:{self.port}:{DEFAULT_PORT}",
|
||||
# The image was rebuilt from `_repo_root` immediately before this
|
||||
# launch. Running its baked package avoids a host-path bind mount,
|
||||
# which is both more production-like and works with socket-shared
|
||||
# CI where the daemon cannot see the job container's workspace.
|
||||
# Orchestrator registry DB on the host (sole writer: control plane).
|
||||
"--volume", f"{self._host_root}:{_ROOT_IN_CONTAINER}",
|
||||
# `root_mount_source` may be a host path or a named Docker volume.
|
||||
"--volume", f"{self._root_mount_source}:{_ROOT_IN_CONTAINER}",
|
||||
"--env", f"BOT_BOTTLE_ROOT={_ROOT_IN_CONTAINER}",
|
||||
# The signing key — held ONLY by the orchestrator (it verifies
|
||||
# tokens); the gateway gets the pre-minted `gateway` JWT, never the
|
||||
@@ -205,6 +237,15 @@ class DockerOrchestrator(Orchestrator):
|
||||
raise OrchestratorStartError(
|
||||
f"orchestrator container failed to start: {proc.stderr.strip()}"
|
||||
)
|
||||
if self._client_network:
|
||||
proc = run_docker([
|
||||
"docker", "network", "connect", self._client_network, self.name,
|
||||
])
|
||||
if proc.returncode != 0:
|
||||
raise OrchestratorStartError(
|
||||
f"orchestrator container failed to join client network "
|
||||
f"{self._client_network}: {proc.stderr.strip()}"
|
||||
)
|
||||
|
||||
def stop(self) -> None:
|
||||
"""Remove the control-plane container (idempotent)."""
|
||||
|
||||
@@ -8,7 +8,7 @@ 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.
|
||||
the generic `bot-bottle backend {setup,status}` dispatches to.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
@@ -69,7 +69,7 @@ def teardown() -> int:
|
||||
sys.stderr.write(
|
||||
"Docker backend: nothing to undo — it provisions no privileged host "
|
||||
"state (networks and the gateway are per-launch and are "
|
||||
"removed by `./cli.py cleanup`). Docker itself is left installed.\n"
|
||||
"removed by `bot-bottle cleanup`). Docker itself is left installed.\n"
|
||||
)
|
||||
return 0
|
||||
|
||||
@@ -89,5 +89,5 @@ def status() -> int:
|
||||
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")
|
||||
sys.stderr.write("\nRun: bot-bottle backend setup --backend=docker\n")
|
||||
return 0 if ok else 1
|
||||
|
||||
@@ -6,12 +6,18 @@ from __future__ import annotations
|
||||
|
||||
import os
|
||||
from datetime import datetime, timezone
|
||||
import re
|
||||
import shutil
|
||||
import subprocess
|
||||
from typing import Iterator
|
||||
|
||||
from ... import resources
|
||||
from ...log import die, info
|
||||
from ...util import slugify as _slugify
|
||||
|
||||
|
||||
def slugify(name: str) -> str:
|
||||
"""Compatibility wrapper; new generic callers import ``bot_bottle.util``."""
|
||||
return _slugify(name)
|
||||
|
||||
|
||||
def run_docker(
|
||||
@@ -114,20 +120,13 @@ def docker_cp(src: str, dest: str) -> None:
|
||||
f"{(result.stderr or '').strip() or '<no stderr>'}")
|
||||
|
||||
|
||||
_SLUG_RE = re.compile(r"[^a-z0-9]+")
|
||||
|
||||
|
||||
def slugify(name: str) -> str:
|
||||
"""Lowercase, non-alnum runs → '-', trimmed. Dies on empty result."""
|
||||
if not name:
|
||||
die("slugify: missing name")
|
||||
slug = _SLUG_RE.sub("-", name.lower()).strip("-")
|
||||
if not slug:
|
||||
die(f"name '{name}' produced an empty slug; use alphanumeric characters")
|
||||
return slug
|
||||
|
||||
|
||||
def build_image(ref: str, context: str, *, dockerfile: str = "") -> None:
|
||||
def build_image(
|
||||
ref: str,
|
||||
context: str,
|
||||
*,
|
||||
dockerfile: str = "",
|
||||
build_args: dict[str, str] | None = None,
|
||||
) -> None:
|
||||
"""Invokes `docker build` every call. Layer cache makes no-change
|
||||
rebuilds cheap; running every time means Dockerfile edits land
|
||||
without manual `docker rmi`.
|
||||
@@ -147,10 +146,61 @@ def build_image(ref: str, context: str, *, dockerfile: str = "") -> None:
|
||||
args.append("--no-cache")
|
||||
if dockerfile:
|
||||
args.extend(["-f", dockerfile])
|
||||
effective_build_args = resources.image_build_args(
|
||||
dockerfile,
|
||||
context=context,
|
||||
) if dockerfile else {}
|
||||
effective_build_args.update(build_args or {})
|
||||
for name, value in effective_build_args.items():
|
||||
args.extend(["--build-arg", f"{name}={value}"])
|
||||
args.append(context)
|
||||
subprocess.run(args, check=True)
|
||||
|
||||
|
||||
def image_id(ref: str) -> str:
|
||||
"""Return the exact content-addressed ID for a local image.
|
||||
|
||||
This is used when one locally built image is another Dockerfile's base:
|
||||
passing the ID prevents a mutable tag from being resolved between builds.
|
||||
"""
|
||||
result = run_docker(["docker", "image", "inspect", "--format", "{{.Id}}", ref])
|
||||
image = result.stdout.strip()
|
||||
if result.returncode != 0 or not image.startswith("sha256:"):
|
||||
detail = (result.stderr or result.stdout or "").strip()
|
||||
die(f"could not resolve exact image ID for {ref!r}: {detail or '<no detail>'}")
|
||||
return image
|
||||
|
||||
|
||||
def pinned_local_image_ref(ref: str) -> str:
|
||||
"""Give a local image a content-derived tag and verify the tag resolves
|
||||
back to the same image ID.
|
||||
|
||||
BuildKit treats a bare ``sha256:...`` ID in ``FROM`` as a registry
|
||||
repository name. A tag whose complete suffix is the local image ID remains
|
||||
resolvable by BuildKit, while the post-tag inspection keeps the handoff
|
||||
fail-closed.
|
||||
"""
|
||||
image = image_id(ref)
|
||||
digest = image.removeprefix("sha256:")
|
||||
if len(digest) != 64 or any(char not in "0123456789abcdef" for char in digest):
|
||||
die(f"could not derive a local base tag from invalid image ID {image!r}")
|
||||
|
||||
repository = ref.split("@", 1)[0]
|
||||
last_slash = repository.rfind("/")
|
||||
last_colon = repository.rfind(":")
|
||||
if last_colon > last_slash:
|
||||
repository = repository[:last_colon]
|
||||
pinned_ref = f"{repository}:sha256-{digest}"
|
||||
|
||||
result = run_docker(["docker", "image", "tag", image, pinned_ref])
|
||||
if result.returncode != 0:
|
||||
detail = (result.stderr or result.stdout or "").strip()
|
||||
die(f"could not tag exact local image {image}: {detail or '<no detail>'}")
|
||||
if image_id(pinned_ref) != image:
|
||||
die(f"content-derived local tag {pinned_ref!r} did not resolve to {image}")
|
||||
return pinned_ref
|
||||
|
||||
|
||||
def verify_agent_image(image: str, argv: tuple[str, ...]) -> None:
|
||||
"""Run `argv` inside a throwaway container of a freshly built agent
|
||||
image and die loudly if it fails, instead of shipping an image
|
||||
|
||||
@@ -11,7 +11,8 @@ from pathlib import Path
|
||||
|
||||
from ..bottle_state import egress_state_dir
|
||||
from ..egress import EGRESS_ROUTES_FILENAME
|
||||
from ..gateway.egress.addon_core import LOG_OFF, load_config
|
||||
from ..gateway.egress.schema import load_config
|
||||
from ..gateway.egress.types import LOG_OFF
|
||||
|
||||
|
||||
class EgressApplyError(RuntimeError):
|
||||
|
||||
@@ -27,3 +27,11 @@ class FirecrackerBottleCleanupPlan(BottleCleanupPlan):
|
||||
@property
|
||||
def empty(self) -> bool:
|
||||
return not (self.vm_pids or self.run_dirs)
|
||||
|
||||
def intersect(self, current: BottleCleanupPlan) -> "FirecrackerBottleCleanupPlan":
|
||||
if not isinstance(current, FirecrackerBottleCleanupPlan):
|
||||
raise TypeError("cleanup plans must have the same backend type")
|
||||
return FirecrackerBottleCleanupPlan(
|
||||
vm_pids=tuple(x for x in self.vm_pids if x in current.vm_pids),
|
||||
run_dirs=tuple(x for x in self.run_dirs if x in current.run_dirs),
|
||||
)
|
||||
|
||||
@@ -11,10 +11,9 @@ Reaps *orphans* only — resources with no live VM behind them:
|
||||
— a VMM left lingering after its dir was removed.
|
||||
|
||||
A run dir with a *live* firecracker process is a running bottle and is
|
||||
left strictly alone: it is neither killed nor removed. (The backend's
|
||||
`enumerate_active` registry is still a stub — #354 — so a live process
|
||||
is the only reliable "this bottle is in use" signal we have. Once the
|
||||
registry lands, registry-orphaned-but-running VMs can be reaped too.)
|
||||
left strictly alone: it is neither killed nor removed. Active-agent
|
||||
enumeration uses this same process snapshot, so cleanup and generic
|
||||
backend consumers agree about which bottles are running.
|
||||
|
||||
TAP slots free themselves (the flock drops when the launcher exits), so
|
||||
there is nothing to reclaim there.
|
||||
@@ -22,14 +21,16 @@ there is nothing to reclaim there.
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
from collections.abc import Sequence
|
||||
import os
|
||||
import shutil
|
||||
import signal
|
||||
import subprocess
|
||||
from pathlib import Path
|
||||
|
||||
from ...log import info
|
||||
from . import util
|
||||
from .. import EnumerationError
|
||||
from ..cleanup_control import CleanupError, CleanupFailures
|
||||
from . import lifecycle_lock, util
|
||||
from .bottle_cleanup_plan import FirecrackerBottleCleanupPlan
|
||||
|
||||
|
||||
@@ -37,7 +38,7 @@ def _run_root() -> Path:
|
||||
return util.cache_dir() / "run"
|
||||
|
||||
|
||||
def _run_dir_of(cmd: str, run_root: Path) -> Path | None:
|
||||
def _run_dir_of(args: Sequence[str], run_root: Path) -> Path | None:
|
||||
"""The bottle run dir a firecracker cmdline belongs to, or None.
|
||||
|
||||
A bottle VM is launched with `--config-file <run_root>/<slug>/config.json`,
|
||||
@@ -45,15 +46,35 @@ def _run_dir_of(cmd: str, run_root: Path) -> Path | None:
|
||||
the run root. Anything else (a builder VM, the infra VM elsewhere) is
|
||||
not ours to reap here.
|
||||
"""
|
||||
toks = cmd.split()
|
||||
for i, tok in enumerate(toks):
|
||||
if tok == "--config-file" and i + 1 < len(toks):
|
||||
parent = Path(toks[i + 1]).parent
|
||||
for i, arg in enumerate(args):
|
||||
if arg == "--config-file" and i + 1 < len(args):
|
||||
parent = Path(args[i + 1]).parent
|
||||
if parent.parent == run_root:
|
||||
return parent
|
||||
return None
|
||||
|
||||
|
||||
def _decode_cmdline(raw: bytes) -> tuple[str, ...]:
|
||||
"""Decode Linux's NUL-delimited argv without losing embedded spaces."""
|
||||
return tuple(
|
||||
value.decode(errors="surrogateescape")
|
||||
for value in raw.split(b"\0") if value
|
||||
)
|
||||
|
||||
|
||||
def _process_args(pid: int) -> tuple[str, ...] | None:
|
||||
"""Read one process's lossless argv, or None when it exited meanwhile."""
|
||||
try:
|
||||
raw = Path(f"/proc/{pid}/cmdline").read_bytes()
|
||||
except FileNotFoundError:
|
||||
return None
|
||||
except OSError as exc:
|
||||
raise EnumerationError(
|
||||
f"could not inspect Firecracker pid {pid}: {exc}"
|
||||
) from exc
|
||||
return _decode_cmdline(raw)
|
||||
|
||||
|
||||
def _scan_processes(run_root: Path) -> tuple[set[str], list[int]]:
|
||||
"""Inspect running firecracker VMs under ``run_root``.
|
||||
|
||||
@@ -62,23 +83,34 @@ def _scan_processes(run_root: Path) -> tuple[set[str], list[int]]:
|
||||
* ``orphan_pids`` — firecracker pids whose run dir no longer exists
|
||||
(a lingering VMM to kill).
|
||||
"""
|
||||
result = subprocess.run(
|
||||
["pgrep", "-a", "firecracker"],
|
||||
capture_output=True, text=True, check=False,
|
||||
)
|
||||
if result.returncode != 0:
|
||||
try:
|
||||
result = subprocess.run(
|
||||
["pgrep", "firecracker"],
|
||||
capture_output=True, text=True, check=False,
|
||||
)
|
||||
except OSError as exc:
|
||||
raise EnumerationError(
|
||||
f"could not enumerate Firecracker processes: {exc}"
|
||||
) from exc
|
||||
if result.returncode == 1:
|
||||
# pgrep's documented "no processes matched" result.
|
||||
return set(), []
|
||||
if result.returncode != 0:
|
||||
detail = (result.stderr or "").strip() or f"exit {result.returncode}"
|
||||
raise EnumerationError(
|
||||
f"could not enumerate Firecracker processes: {detail}"
|
||||
)
|
||||
live: set[str] = set()
|
||||
orphan_pids: list[int] = []
|
||||
for line in result.stdout.splitlines():
|
||||
parts = line.split(None, 1)
|
||||
if len(parts) != 2:
|
||||
continue
|
||||
try:
|
||||
pid = int(parts[0])
|
||||
pid = int(line.strip())
|
||||
except ValueError:
|
||||
continue
|
||||
run_dir = _run_dir_of(parts[1], run_root)
|
||||
args = _process_args(pid)
|
||||
if args is None:
|
||||
continue
|
||||
run_dir = _run_dir_of(args, run_root)
|
||||
if run_dir is None:
|
||||
continue
|
||||
if run_dir.is_dir():
|
||||
@@ -114,12 +146,54 @@ def prepare_cleanup() -> FirecrackerBottleCleanupPlan:
|
||||
|
||||
|
||||
def cleanup(plan: FirecrackerBottleCleanupPlan) -> None:
|
||||
for pid in plan.vm_pids:
|
||||
"""Revalidate the preview under the launch lock, then remove its survivors."""
|
||||
with lifecycle_lock.hold():
|
||||
fresh = prepare_cleanup()
|
||||
approved_pids = set(plan.vm_pids).intersection(fresh.vm_pids)
|
||||
approved_dirs = set(plan.run_dirs).intersection(fresh.run_dirs)
|
||||
failures = CleanupFailures()
|
||||
for pid in sorted(approved_pids):
|
||||
try:
|
||||
_terminate_orphan(pid, _run_root())
|
||||
except CleanupError as exc:
|
||||
failures.record(str(exc))
|
||||
for path in sorted(approved_dirs):
|
||||
info(f"rm -rf {path}")
|
||||
failures.remove_tree(Path(path), f"removing Firecracker run dir {path}")
|
||||
failures.raise_if_any()
|
||||
|
||||
|
||||
def _terminate_orphan(pid: int, run_root: Path) -> None:
|
||||
"""Signal exactly the process identity that still owns an orphan config."""
|
||||
try:
|
||||
pidfd = os.pidfd_open(pid)
|
||||
except ProcessLookupError:
|
||||
return
|
||||
except OSError as exc:
|
||||
raise EnumerationError(
|
||||
f"could not pin Firecracker pid {pid} for cleanup: {exc}"
|
||||
) from exc
|
||||
try:
|
||||
try:
|
||||
raw = Path(f"/proc/{pid}/cmdline").read_bytes()
|
||||
except FileNotFoundError:
|
||||
return
|
||||
except OSError as exc:
|
||||
raise EnumerationError(
|
||||
f"could not revalidate Firecracker pid {pid}: {exc}"
|
||||
) from exc
|
||||
args = _decode_cmdline(raw)
|
||||
run_dir = _run_dir_of(args, run_root)
|
||||
if run_dir is None or run_dir.is_dir():
|
||||
return
|
||||
info(f"kill firecracker VM pid {pid}")
|
||||
try:
|
||||
os.kill(pid, signal.SIGTERM)
|
||||
signal.pidfd_send_signal(pidfd, signal.SIGTERM)
|
||||
except ProcessLookupError:
|
||||
pass
|
||||
for path in plan.run_dirs:
|
||||
info(f"rm -rf {path}")
|
||||
shutil.rmtree(path, ignore_errors=True)
|
||||
return
|
||||
except OSError as exc:
|
||||
raise CleanupError(
|
||||
f"could not signal Firecracker pid {pid}: {exc}"
|
||||
) from exc
|
||||
finally:
|
||||
os.close(pidfd)
|
||||
|
||||
@@ -26,22 +26,19 @@ The TAP slot allocation, rootfs build, and VM boot are the caller's job.
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import json
|
||||
import subprocess
|
||||
from dataclasses import dataclass
|
||||
from pathlib import Path
|
||||
|
||||
from ...egress import EgressPlan
|
||||
from ...git_gate import GitGatePlan
|
||||
from ...log import info
|
||||
from ...orchestrator.client import OrchestratorClient, OrchestratorClientError
|
||||
from ...orchestrator.client import OrchestratorClient
|
||||
from ...orchestrator.lifecycle import (
|
||||
OrchestratorStartError, # re-exported so callers can catch it
|
||||
)
|
||||
from ...orchestrator.reprovision import reprovision_bottles
|
||||
from ...orchestrator.store.secret_store import ENV_VAR_SECRET_NAME
|
||||
from ..provision_bottle import deprovision_bottle, provision_bottle
|
||||
from . import cleanup, util
|
||||
from . import util
|
||||
from .gateway import FirecrackerGateway
|
||||
from .infra import FirecrackerInfraService
|
||||
|
||||
@@ -64,17 +61,6 @@ class LaunchContext:
|
||||
env_var_secret: str = "" # encryption key injected into the agent's env
|
||||
|
||||
|
||||
def _guest_ip_from_config(config_path: Path) -> str:
|
||||
"""Read the kernel's configured guest IP from a Firecracker config."""
|
||||
try:
|
||||
config = json.loads(config_path.read_text())
|
||||
args = config["boot-source"]["boot_args"]
|
||||
ip_arg = next(part for part in args.split() if part.startswith("ip="))
|
||||
return ip_arg.removeprefix("ip=").split(":", 1)[0]
|
||||
except (OSError, ValueError, KeyError, TypeError, StopIteration):
|
||||
return ""
|
||||
|
||||
|
||||
def persist_env_var_secret(private_key: Path, guest_ip: str, secret: str) -> None:
|
||||
"""Mirror the exec-time key into guest tmpfs for restart recovery."""
|
||||
proc = subprocess.run(
|
||||
@@ -89,29 +75,6 @@ def persist_env_var_secret(private_key: Path, guest_ip: str, secret: str) -> Non
|
||||
)
|
||||
|
||||
|
||||
def _reprovision_running_bottles(client: OrchestratorClient) -> None:
|
||||
"""Read keys from live agent VMs and restore the restarted gateway."""
|
||||
try:
|
||||
secrets_by_ip: dict[str, str] = {}
|
||||
for run_dir in cleanup.live_run_dirs():
|
||||
guest_ip = _guest_ip_from_config(run_dir / "config.json")
|
||||
private_key = run_dir / "bottle_id_ed25519"
|
||||
if not guest_ip or not private_key.is_file():
|
||||
continue
|
||||
proc = subprocess.run(
|
||||
util.ssh_base_argv(private_key, guest_ip)
|
||||
+ [f"cat {_ENV_VAR_SECRET_PATH}"],
|
||||
capture_output=True, text=True, check=False,
|
||||
)
|
||||
if proc.returncode == 0 and proc.stdout.strip():
|
||||
secrets_by_ip[guest_ip] = proc.stdout.strip()
|
||||
count = reprovision_bottles(client, secrets_by_ip)
|
||||
if count:
|
||||
info(f"reprovisioned egress tokens for {count} Firecracker bottle(s)")
|
||||
except (OSError, OrchestratorClientError) as exc:
|
||||
info(f"egress token reprovision skipped: {exc}")
|
||||
|
||||
|
||||
def launch_consolidated(
|
||||
egress_plan: EgressPlan,
|
||||
git_gate_plan: GitGatePlan,
|
||||
@@ -126,7 +89,6 @@ def launch_consolidated(
|
||||
service = FirecrackerInfraService()
|
||||
url = service.ensure_running()
|
||||
client = OrchestratorClient(url)
|
||||
_reprovision_running_bottles(client)
|
||||
|
||||
# Read the gateway's provisioning transport + CA off the Gateway service.
|
||||
gateway = service.gateway()
|
||||
|
||||
@@ -1,14 +1,32 @@
|
||||
"""Active-agent enumeration for the Firecracker backend.
|
||||
|
||||
The backend is disabled during the companion-container removal (#385) — it can't
|
||||
launch bottles, so there are none to enumerate. Real enumeration returns
|
||||
with the backend's consolidated relaunch (#354).
|
||||
Running bottles are the Firecracker processes whose ``--config-file`` points
|
||||
at an existing per-bottle run directory. The same authoritative process scan
|
||||
protects cleanup from deleting live VMs; operational scan failures propagate
|
||||
as ``EnumerationError`` instead of masquerading as an empty host.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
from ...bottle_state import read_metadata
|
||||
from .. import ActiveAgent
|
||||
from .cleanup import live_run_dirs
|
||||
|
||||
|
||||
def enumerate_active() -> list[ActiveAgent]:
|
||||
return []
|
||||
out: list[ActiveAgent] = []
|
||||
for run_dir in live_run_dirs():
|
||||
slug = run_dir.name
|
||||
metadata = read_metadata(slug)
|
||||
out.append(ActiveAgent(
|
||||
backend_name="firecracker",
|
||||
slug=slug,
|
||||
agent_name=metadata.agent_name if metadata else "?",
|
||||
started_at=metadata.started_at if metadata else "",
|
||||
# Firecracker uses the shared gateway, so there are no
|
||||
# per-bottle gateway service containers to report.
|
||||
services=(),
|
||||
label=metadata.label if metadata else "",
|
||||
color=metadata.color if metadata else "",
|
||||
))
|
||||
return out
|
||||
|
||||
@@ -19,12 +19,14 @@ from __future__ import annotations
|
||||
import fcntl
|
||||
import hashlib
|
||||
import os
|
||||
import shlex
|
||||
import shutil
|
||||
import subprocess
|
||||
from contextlib import contextmanager
|
||||
from pathlib import Path
|
||||
from typing import Generator
|
||||
|
||||
from ... import resources
|
||||
from ...log import die, info
|
||||
from . import util
|
||||
from .infra import FirecrackerInfraService
|
||||
@@ -55,6 +57,11 @@ def _rootfs_digest(dockerfile: Path) -> str:
|
||||
h = hashlib.sha256()
|
||||
h.update(_dockerfile_hash(dockerfile).encode())
|
||||
h.update(b"\0")
|
||||
for name, value in resources.image_build_args(dockerfile).items():
|
||||
h.update(name.encode())
|
||||
h.update(b"=")
|
||||
h.update(value.encode())
|
||||
h.update(b"\0")
|
||||
h.update(util._GUEST_INIT.encode())
|
||||
return h.hexdigest()[:16]
|
||||
|
||||
@@ -147,7 +154,13 @@ def _build_in_infra(
|
||||
if prep.returncode != 0:
|
||||
die(f"preparing build dir in the infra VM failed: {prep.stderr.strip()}")
|
||||
_send_dockerfile(key, ip, dockerfile, ctx)
|
||||
_buildah_build(key, ip, ctx, tag)
|
||||
_buildah_build(
|
||||
key,
|
||||
ip,
|
||||
ctx,
|
||||
tag,
|
||||
resources.image_build_args(dockerfile),
|
||||
)
|
||||
_smoke_test(key, ip, tag, smoke_ctr, smoke_test)
|
||||
_stream_rootfs(key, ip, tag, export_ctr, base)
|
||||
finally:
|
||||
@@ -184,15 +197,26 @@ def _send_dockerfile(private_key: Path, guest_ip: str, dockerfile: Path, ctx: st
|
||||
f"{proc.stderr.decode(errors='replace').strip()}")
|
||||
|
||||
|
||||
def _buildah_build(private_key: Path, guest_ip: str, ctx: str, tag: str) -> None:
|
||||
def _buildah_build(
|
||||
private_key: Path,
|
||||
guest_ip: str,
|
||||
ctx: str,
|
||||
tag: str,
|
||||
build_args: dict[str, str],
|
||||
) -> None:
|
||||
# Stream buildah's step-by-step output straight to our stderr (like the
|
||||
# docker backend's `docker build`), so a long first build (base pull +
|
||||
# apt/npm installs) shows live progress instead of a silent wait. The
|
||||
# remote stderr is where buildah writes its `STEP i/n` lines.
|
||||
info(f"buildah build {tag} in the infra VM (streaming output)")
|
||||
arg_flags = " ".join(
|
||||
f"--build-arg {shlex.quote(f'{name}={value}')}"
|
||||
for name, value in build_args.items()
|
||||
)
|
||||
rc = _ssh_streamed(
|
||||
private_key, guest_ip,
|
||||
f"buildah build {_BUILD_FLAGS} -t {tag} -f {ctx}/Dockerfile {ctx}/ctx",
|
||||
f"buildah build {_BUILD_FLAGS} {arg_flags} "
|
||||
f"-t {tag} -f {ctx}/Dockerfile {ctx}/ctx",
|
||||
timeout=_BUILD_TIMEOUT_SECONDS,
|
||||
)
|
||||
if rc != 0:
|
||||
|
||||
@@ -17,6 +17,7 @@ from ...orchestrator.lifecycle import DEFAULT_STARTUP_TIMEOUT_SECONDS
|
||||
from . import infra_vm
|
||||
from .gateway import FirecrackerGateway
|
||||
from .orchestrator import FirecrackerOrchestrator
|
||||
from .reconcile import attach_bottled_agents_to_gateway
|
||||
|
||||
|
||||
class FirecrackerInfraService(InfraService):
|
||||
@@ -67,9 +68,11 @@ class FirecrackerInfraService(InfraService):
|
||||
# holds the signing key) mints the role-scoped `gateway` JWT for the
|
||||
# gateway, which never sees the key (#469).
|
||||
orchestrator.ensure_running(startup_timeout=startup_timeout)
|
||||
self.gateway().connect_to_orchestrator(
|
||||
gateway = self.gateway()
|
||||
gateway.connect_to_orchestrator(
|
||||
orchestrator.gateway_url(), orchestrator.mint_gateway_token())
|
||||
infra_vm.record_booted_version(want)
|
||||
attach_bottled_agents_to_gateway(url, gateway)
|
||||
return url
|
||||
|
||||
def stop(self) -> None:
|
||||
|
||||
@@ -41,6 +41,8 @@ from ... import resources
|
||||
from ...log import die, info
|
||||
from . import util
|
||||
|
||||
ARTIFACT_HTTP_TIMEOUT_SECONDS = 30.0
|
||||
|
||||
# Bump if the on-disk artifact *format* changes (compression, layout) so a new
|
||||
# scheme can't collide with a cached/published artifact of the old one.
|
||||
_ARTIFACT_FORMAT = "1"
|
||||
@@ -49,9 +51,18 @@ _ARTIFACT_FORMAT = "1"
|
||||
# from its own generic package; the Dockerfiles baked into each differ (only the
|
||||
# orchestrator rootfs carries buildah), so the versions are hashed separately.
|
||||
ROLES = ("orchestrator", "gateway")
|
||||
_DOCKERFILES = {
|
||||
"orchestrator": ("Dockerfile.orchestrator", "Dockerfile.orchestrator.fc"),
|
||||
"gateway": ("Dockerfile.gateway",),
|
||||
_BUILD_INPUTS = {
|
||||
"orchestrator": (
|
||||
"image-build-args.json",
|
||||
"Dockerfile.orchestrator",
|
||||
"Dockerfile.orchestrator.fc",
|
||||
"requirements.orchestrator.lock",
|
||||
),
|
||||
"gateway": (
|
||||
"image-build-args.json",
|
||||
"Dockerfile.gateway",
|
||||
"requirements.gateway.lock",
|
||||
),
|
||||
}
|
||||
|
||||
_DEFAULT_BASE = "https://gitea.dideric.is"
|
||||
@@ -101,7 +112,7 @@ def infra_artifact_version(
|
||||
h.update(str(path.relative_to(repo_root)).encode())
|
||||
h.update(b"\0")
|
||||
h.update(path.read_bytes())
|
||||
for name in _DOCKERFILES[role]:
|
||||
for name in _BUILD_INPUTS[role]:
|
||||
h.update(name.encode())
|
||||
h.update(b"\0")
|
||||
h.update((repo_root / name).read_bytes())
|
||||
@@ -155,7 +166,9 @@ def _download(url: str, dest: Path) -> None:
|
||||
"""Stream `url` to `dest` (atomic via a `.part` sibling)."""
|
||||
tmp = dest.with_suffix(dest.suffix + ".part")
|
||||
try:
|
||||
with urllib.request.urlopen(_open(url)) as resp, open(tmp, "wb") as out:
|
||||
with urllib.request.urlopen(
|
||||
_open(url), timeout=ARTIFACT_HTTP_TIMEOUT_SECONDS,
|
||||
) as resp, open(tmp, "wb") as out:
|
||||
shutil.copyfileobj(resp, out, _CHUNK)
|
||||
except urllib.error.HTTPError as e:
|
||||
tmp.unlink(missing_ok=True)
|
||||
|
||||
@@ -133,10 +133,15 @@ def build_infra_images_with_docker() -> None:
|
||||
root = str(resources.build_root())
|
||||
docker_mod.build_image(
|
||||
_ORCHESTRATOR_IMAGE, root, dockerfile="Dockerfile.orchestrator")
|
||||
orchestrator_base = docker_mod.pinned_local_image_ref(_ORCHESTRATOR_IMAGE)
|
||||
docker_mod.build_image(
|
||||
_GATEWAY_IMAGE, root, dockerfile="Dockerfile.gateway")
|
||||
docker_mod.build_image(
|
||||
_ORCHESTRATOR_FC_IMAGE, root, dockerfile="Dockerfile.orchestrator.fc")
|
||||
_ORCHESTRATOR_FC_IMAGE,
|
||||
root,
|
||||
dockerfile="Dockerfile.orchestrator.fc",
|
||||
build_args={"ORCHESTRATOR_BASE_IMAGE": orchestrator_base},
|
||||
)
|
||||
|
||||
|
||||
def build_rootfs_dir(role: str) -> Path:
|
||||
@@ -199,7 +204,7 @@ def boot_vm(
|
||||
Records the PID."""
|
||||
if not netpool.tap_present(slot.iface):
|
||||
die(f"infra link {slot.iface} not present.\n"
|
||||
f" ./cli.py backend setup --backend=firecracker")
|
||||
f" bot-bottle backend setup --backend=firecracker")
|
||||
|
||||
run_dir.mkdir(parents=True, exist_ok=True)
|
||||
rootfs = run_dir / "rootfs.ext4"
|
||||
|
||||
@@ -108,7 +108,7 @@ def verify_isolation(private_key: Path, guest_ip: str) -> None:
|
||||
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")
|
||||
f"nft table with: bot-bottle 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 "
|
||||
|
||||
@@ -46,7 +46,7 @@ from ...log import die, info, warn
|
||||
from ...supervisor.types import SUPERVISE_PORT
|
||||
from ..docker.egress import EGRESS_PORT
|
||||
from ..util import AGENT_CA_BUNDLE, AGENT_CA_PATH
|
||||
from . import firecracker_vm, image_builder, isolation_probe, netpool, util
|
||||
from . import firecracker_vm, image_builder, isolation_probe, lifecycle_lock, netpool, util
|
||||
from .bottle import FirecrackerBottle
|
||||
from .bottle_plan import FirecrackerBottlePlan
|
||||
from ...orchestrator.store.config_store import resolve_teardown_timeout
|
||||
@@ -164,25 +164,29 @@ def launch(
|
||||
)
|
||||
|
||||
# Step 6: build the per-bottle rootfs + SSH key, then boot.
|
||||
run_dir = util.cache_dir() / "run" / plan.slug
|
||||
run_dir.mkdir(parents=True, exist_ok=True)
|
||||
# Remove the run dir on teardown so the per-bottle rootfs.ext4 (~1G)
|
||||
# doesn't leak. Registered before vm.terminate below so it runs *after*
|
||||
# it (ExitStack is LIFO): the VM is gone before we rm its rootfs.
|
||||
stack.callback(lambda: shutil.rmtree(run_dir, ignore_errors=True))
|
||||
rootfs = run_dir / "rootfs.ext4"
|
||||
util.build_rootfs_ext4(agent_base, rootfs)
|
||||
private_key, pubkey = util.generate_keypair(run_dir)
|
||||
# Cleanup takes the same lock while refreshing its process snapshot.
|
||||
# Hold it until the VMM exists so a newly-created run dir can never be
|
||||
# mistaken for an orphan in the build-before-boot window.
|
||||
with lifecycle_lock.hold():
|
||||
run_dir = util.cache_dir() / "run" / plan.slug
|
||||
run_dir.mkdir(parents=True, exist_ok=True)
|
||||
# Remove the run dir on teardown so the per-bottle rootfs.ext4 (~1G)
|
||||
# doesn't leak. Registered before vm.terminate below so it runs
|
||||
# *after* it (ExitStack is LIFO).
|
||||
stack.callback(lambda: shutil.rmtree(run_dir, ignore_errors=True))
|
||||
rootfs = run_dir / "rootfs.ext4"
|
||||
util.build_rootfs_ext4(agent_base, 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,
|
||||
)
|
||||
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)
|
||||
persist_env_var_secret(private_key, slot.guest_ip, ctx.env_var_secret)
|
||||
|
||||
@@ -0,0 +1,30 @@
|
||||
"""Serialize Firecracker run-directory creation with orphan cleanup."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import fcntl
|
||||
from contextlib import contextmanager
|
||||
from pathlib import Path
|
||||
from typing import Generator
|
||||
|
||||
from . import util
|
||||
|
||||
|
||||
def _lock_path() -> Path:
|
||||
return util.cache_dir() / "run.lifecycle.lock"
|
||||
|
||||
|
||||
@contextmanager
|
||||
def hold() -> Generator[None]:
|
||||
"""Exclude cleanup while a launch directory lacks a visible VMM."""
|
||||
path = _lock_path()
|
||||
path.parent.mkdir(parents=True, exist_ok=True)
|
||||
with path.open("a", encoding="utf-8") as handle:
|
||||
fcntl.flock(handle, fcntl.LOCK_EX)
|
||||
try:
|
||||
yield
|
||||
finally:
|
||||
fcntl.flock(handle, fcntl.LOCK_UN)
|
||||
|
||||
|
||||
__all__ = ["hold"]
|
||||
@@ -3,7 +3,7 @@ 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
|
||||
`bot-bottle 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
|
||||
@@ -177,14 +177,20 @@ def gw_slot() -> Slot:
|
||||
# --- fail-closed verification ---------------------------------------
|
||||
|
||||
def _run_ok(argv: list[str]) -> bool:
|
||||
"""Run a probe command, treating a missing binary as failure
|
||||
"""Run a probe command, treating an unavailable 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:
|
||||
except OSError:
|
||||
# Not only "missing". A name on PATH that isn't executable by this
|
||||
# user raises PermissionError, and CPython reports that EACCES in
|
||||
# preference to the ENOENT from the other PATH entries — which is
|
||||
# how `doctor` came to die with a traceback on a fresh macOS
|
||||
# account. Any OSError means the probe couldn't run, which for a
|
||||
# fail-closed check is indistinguishable from "not present".
|
||||
return False
|
||||
|
||||
|
||||
@@ -244,7 +250,9 @@ def overlapping_routes() -> list[RouteConflict]:
|
||||
["ip", "-json", "route", "show", "table", "all"],
|
||||
capture_output=True, text=True, check=False,
|
||||
)
|
||||
except FileNotFoundError:
|
||||
except OSError:
|
||||
# Missing, or present-but-not-executable for this user; either way
|
||||
# there are no routes we can enumerate. See _run_ok.
|
||||
return []
|
||||
if proc.returncode != 0 or not proc.stdout.strip():
|
||||
return []
|
||||
@@ -307,11 +315,11 @@ def allocate(slug: str) -> tuple[Slot, IO[str]]:
|
||||
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`.")
|
||||
f"and re-run `bot-bottle backend setup --backend=firecracker`.")
|
||||
raise AssertionError("unreachable")
|
||||
|
||||
|
||||
# --- config renderers (shown by `./cli.py backend setup`) -----------
|
||||
# --- config renderers (shown by `bot-bottle backend setup`) -----------
|
||||
|
||||
# The persistent unit is the portable install: the same systemd oneshot
|
||||
# on every systemd distro (Debian/Ubuntu/Fedora/RHEL/Arch/…).
|
||||
|
||||
@@ -34,6 +34,7 @@ from pathlib import Path
|
||||
from . import infra_artifact, infra_vm, util
|
||||
|
||||
_CHUNK = 1 << 20
|
||||
_REGISTRY_HTTP_TIMEOUT_SECONDS = 30.0
|
||||
|
||||
_GZ_NAME = "rootfs.ext4.gz"
|
||||
_SHA_NAME = "rootfs.ext4.gz.sha256"
|
||||
@@ -91,7 +92,9 @@ def _put(url: str, body: "bytes | Path", token: str) -> None:
|
||||
req.add_header("Authorization", f"token {token}")
|
||||
req.add_header("Content-Type", "application/octet-stream")
|
||||
try:
|
||||
with urllib.request.urlopen(req) as resp:
|
||||
with urllib.request.urlopen(
|
||||
req, timeout=_REGISTRY_HTTP_TIMEOUT_SECONDS,
|
||||
) as resp:
|
||||
print(f" uploaded {url} (HTTP {resp.status})")
|
||||
except urllib.error.HTTPError as e:
|
||||
if e.code == 409:
|
||||
@@ -112,7 +115,9 @@ def _delete(url: str, token: str) -> None:
|
||||
if token:
|
||||
req.add_header("Authorization", f"token {token}")
|
||||
try:
|
||||
with urllib.request.urlopen(req):
|
||||
with urllib.request.urlopen(
|
||||
req, timeout=_REGISTRY_HTTP_TIMEOUT_SECONDS,
|
||||
):
|
||||
pass
|
||||
except urllib.error.HTTPError as e:
|
||||
if e.code != 404:
|
||||
@@ -151,7 +156,10 @@ def _try_download_published(role: str, role_dir: Path) -> str | None:
|
||||
version = _role_version(role)
|
||||
sha_url = infra_artifact.artifact_url(version, _SHA_NAME, role=role)
|
||||
try:
|
||||
with urllib.request.urlopen(infra_artifact._open(sha_url)):
|
||||
with urllib.request.urlopen(
|
||||
infra_artifact._open(sha_url),
|
||||
timeout=_REGISTRY_HTTP_TIMEOUT_SECONDS,
|
||||
):
|
||||
pass
|
||||
except urllib.error.HTTPError as e:
|
||||
if e.code == 404:
|
||||
@@ -195,7 +203,10 @@ def _publish_bundle(role: str, role_dir: Path, token: str) -> str:
|
||||
# present, a re-publish is a no-op. Otherwise clear any partial upload left
|
||||
# by an interrupted prior attempt and upload the complete set.
|
||||
try:
|
||||
with urllib.request.urlopen(infra_artifact._open(sha_url)) as resp:
|
||||
with urllib.request.urlopen(
|
||||
infra_artifact._open(sha_url),
|
||||
timeout=_REGISTRY_HTTP_TIMEOUT_SECONDS,
|
||||
) as resp:
|
||||
remote_sha = resp.read().decode("utf-8").split()[0].strip().lower()
|
||||
except urllib.error.HTTPError as e:
|
||||
if e.code != 404:
|
||||
|
||||
@@ -0,0 +1,199 @@
|
||||
"""Bring-up reconcile: re-attach all running agent VMs to a freshly-booted gateway.
|
||||
|
||||
Called from the cold-boot branch of `FirecrackerInfraService.ensure_running()`
|
||||
after `gateway.connect_to_orchestrator()` completes. Restores the three
|
||||
gateway-dependent services for every live bottle:
|
||||
|
||||
- **CA** — push the current (freshly-minted) gateway CA to each agent's
|
||||
trust store and run `update-ca-certificates`, so the agent trusts the
|
||||
new CA on its next egress call.
|
||||
- **git-gate** — re-provision each bottle's bare repos and per-repo creds
|
||||
in the gateway, rebuilt from the persisted host-side state dir.
|
||||
- **egress tokens** — read the agent's `ENV_VAR_SECRET` and feed
|
||||
`reprovision_bottles` to restore the orchestrator's in-memory tokens.
|
||||
|
||||
Per-bottle failures are caught, logged, and skipped so one unreachable VM
|
||||
does not block the others or the gateway coming up (PRD 0081).
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import json
|
||||
import subprocess
|
||||
from pathlib import Path
|
||||
|
||||
from ...bottle_state import git_gate_state_dir
|
||||
from ...gateway import GatewayError
|
||||
from ...gateway.git_gate.render import GitGateUpstream
|
||||
from ...git_gate.plan import GitGatePlan
|
||||
from ...log import info
|
||||
from ...orchestrator.client import OrchestratorClient, OrchestratorClientError
|
||||
from ...orchestrator.reprovision import reprovision_bottles
|
||||
from ..provision_gateway import provision_git_gate
|
||||
from ..util import AGENT_CA_PATH
|
||||
from . import cleanup, util
|
||||
from .gateway import FirecrackerGateway
|
||||
|
||||
# Where persist_env_var_secret writes the key on the agent VM (matches
|
||||
# consolidated_launch._ENV_VAR_SECRET_PATH — duplicated to avoid a
|
||||
# circular import through infra.py).
|
||||
_ENV_VAR_SECRET_PATH = "/run/bot-bottle/env-var-secret"
|
||||
|
||||
|
||||
def _guest_ip_from_config(config_path: Path) -> str:
|
||||
"""Read the agent VM's guest IP from its Firecracker config file."""
|
||||
try:
|
||||
config = json.loads(config_path.read_text())
|
||||
args = config["boot-source"]["boot_args"]
|
||||
ip_arg = next(p for p in args.split() if p.startswith("ip="))
|
||||
return ip_arg.removeprefix("ip=").split(":", 1)[0]
|
||||
except (OSError, ValueError, KeyError, TypeError, StopIteration):
|
||||
return ""
|
||||
|
||||
|
||||
def attach_bottled_agents_to_gateway(
|
||||
orchestrator_url: str, gateway: FirecrackerGateway,
|
||||
) -> None:
|
||||
"""Reconcile all live agent VMs against the freshly-booted gateway.
|
||||
|
||||
Fetches the new CA, lists registered bottles, then for each live run dir
|
||||
pushes the CA, re-provisions git-gate, and restores egress tokens. Each
|
||||
per-bottle step is wrapped so a failure is logged and skipped."""
|
||||
try:
|
||||
ca_pem = gateway.ca_cert_pem()
|
||||
except GatewayError as exc:
|
||||
info(f"bring-up reconcile: could not fetch gateway CA, skipping: {exc}")
|
||||
return
|
||||
|
||||
client = OrchestratorClient(orchestrator_url)
|
||||
try:
|
||||
bottles = client.list_bottles()
|
||||
except OrchestratorClientError as exc:
|
||||
info(f"bring-up reconcile: could not list bottles, skipping: {exc}")
|
||||
return
|
||||
|
||||
source_ip_to_bottle_id: dict[str, str] = {}
|
||||
for b in bottles:
|
||||
source_ip = b.get("source_ip")
|
||||
bottle_id = b.get("bottle_id")
|
||||
if isinstance(source_ip, str) and isinstance(bottle_id, str):
|
||||
source_ip_to_bottle_id[source_ip] = bottle_id
|
||||
|
||||
transport = gateway.provisioning_transport()
|
||||
secrets_by_ip: dict[str, str] = {}
|
||||
|
||||
for run_dir in cleanup.live_run_dirs():
|
||||
slug = run_dir.name
|
||||
guest_ip = _guest_ip_from_config(run_dir / "config.json")
|
||||
private_key = run_dir / "bottle_id_ed25519"
|
||||
if not guest_ip or not private_key.is_file():
|
||||
continue
|
||||
|
||||
# CA: push the gateway's current certificate to the agent's trust store.
|
||||
try:
|
||||
_push_ca(private_key, guest_ip, ca_pem)
|
||||
except Exception as exc:
|
||||
info(f"bring-up reconcile: CA push to {slug!r} failed: {exc}")
|
||||
|
||||
# git-gate: re-provision repos + creds from the persisted state dir.
|
||||
bottle_id = source_ip_to_bottle_id.get(guest_ip)
|
||||
if bottle_id:
|
||||
try:
|
||||
_reprovision_git_gate(transport, bottle_id, slug)
|
||||
except Exception as exc:
|
||||
info(f"bring-up reconcile: git-gate for {slug!r} failed: {exc}")
|
||||
|
||||
# egress tokens: read ENV_VAR_SECRET from the agent's tmpfs.
|
||||
proc = subprocess.run(
|
||||
util.ssh_base_argv(private_key, guest_ip) + [f"cat {_ENV_VAR_SECRET_PATH}"],
|
||||
capture_output=True, text=True, check=False,
|
||||
)
|
||||
if proc.returncode == 0 and proc.stdout.strip():
|
||||
secrets_by_ip[guest_ip] = proc.stdout.strip()
|
||||
|
||||
# Restore in-memory egress tokens for all bottles that exposed a key.
|
||||
if secrets_by_ip:
|
||||
try:
|
||||
count = reprovision_bottles(client, secrets_by_ip)
|
||||
if count:
|
||||
info(
|
||||
f"bring-up reconcile: restored egress tokens for {count} bottle(s)"
|
||||
)
|
||||
except OrchestratorClientError as exc:
|
||||
info(f"bring-up reconcile: egress token restore failed: {exc}")
|
||||
|
||||
|
||||
def _push_ca(private_key: Path, guest_ip: str, ca_pem: str) -> None:
|
||||
"""SSH the gateway CA PEM into the agent VM and update its trust store.
|
||||
|
||||
Runs as the SSH root user (the agent VM's dropbear accepts root). Each
|
||||
step uses check=True so a failure raises and the caller's except clause
|
||||
logs and continues."""
|
||||
ssh = util.ssh_base_argv(private_key, guest_ip)
|
||||
# mkdir is idempotent; rootfs builds may not preserve the target dir.
|
||||
subprocess.run(
|
||||
ssh + ["mkdir -p /usr/local/share/ca-certificates"],
|
||||
capture_output=True, check=True,
|
||||
)
|
||||
subprocess.run(
|
||||
ssh + [f"cat > {AGENT_CA_PATH}"],
|
||||
input=ca_pem, text=True, capture_output=True, check=True,
|
||||
)
|
||||
subprocess.run(
|
||||
ssh + [f"chmod 644 {AGENT_CA_PATH} && update-ca-certificates"],
|
||||
capture_output=True, check=True,
|
||||
)
|
||||
|
||||
|
||||
def _reprovision_git_gate(
|
||||
transport: object, bottle_id: str, slug: str,
|
||||
) -> None:
|
||||
"""Re-provision one bottle's git-gate repos and creds from its state dir.
|
||||
|
||||
Reads `upstreams.json` (written by `provision_git_gate_dynamic_keys` at
|
||||
launch) to reconstruct the GitGateUpstream table, then calls
|
||||
`provision_git_gate` which places the credential files and inits the bare
|
||||
repos in the gateway. No-op when there is no `upstreams.json` (the bottle
|
||||
has no git upstreams)."""
|
||||
state_dir = git_gate_state_dir(slug)
|
||||
upstreams_file = state_dir / "upstreams.json"
|
||||
if not upstreams_file.exists():
|
||||
return
|
||||
|
||||
raw = json.loads(upstreams_file.read_text())
|
||||
upstreams: list[GitGateUpstream] = []
|
||||
for u in raw:
|
||||
name = u["name"]
|
||||
# The key in the state dir is preferred: gitea deploy keys are written
|
||||
# there by provision_git_gate_dynamic_keys; static keys keep their
|
||||
# original manifest path.
|
||||
key_in_state = state_dir / f"{name}-key"
|
||||
identity_file = (
|
||||
str(key_in_state) if key_in_state.is_file()
|
||||
else u.get("identity_file", "")
|
||||
)
|
||||
known_hosts = state_dir / f"{name}-known_hosts"
|
||||
upstreams.append(GitGateUpstream(
|
||||
name=name,
|
||||
upstream_url=u["upstream_url"],
|
||||
upstream_host=u.get("upstream_host", ""),
|
||||
upstream_port=u.get("upstream_port", ""),
|
||||
identity_file=identity_file,
|
||||
known_host_key=u.get("known_host_key", ""),
|
||||
known_hosts_file=known_hosts if known_hosts.is_file() else Path(),
|
||||
))
|
||||
|
||||
if not upstreams:
|
||||
return
|
||||
|
||||
plan = GitGatePlan(
|
||||
slug=slug,
|
||||
entrypoint_script=state_dir / "git_gate_entrypoint.sh",
|
||||
hook_script=state_dir / "git_gate_pre_receive.sh",
|
||||
access_hook_script=state_dir / "git_gate_access_hook.sh",
|
||||
upstreams=tuple(upstreams),
|
||||
)
|
||||
provision_git_gate(transport, bottle_id, plan) # type: ignore[arg-type]
|
||||
|
||||
|
||||
__all__ = ["attach_bottled_agents_to_gateway"]
|
||||
@@ -8,7 +8,7 @@ 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.
|
||||
generic `bot-bottle backend {setup,status}` command dispatches to.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
@@ -34,7 +34,7 @@ _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.
|
||||
# TAPs must be owned by them so `bot-bottle start` stays rootless.
|
||||
return os.environ.get("SUDO_USER") or os.environ.get("USER") or "youruser"
|
||||
|
||||
|
||||
@@ -161,7 +161,7 @@ def _setup_systemd() -> None:
|
||||
if rc == 0:
|
||||
sys.stderr.write(
|
||||
f"Installed and started {netpool.SYSTEMD_UNIT}. Verify with "
|
||||
f"`./cli.py backend status --backend=firecracker`.\n"
|
||||
f"`bot-bottle backend status --backend=firecracker`.\n"
|
||||
)
|
||||
else:
|
||||
sys.stderr.write(
|
||||
@@ -181,7 +181,7 @@ def _setup_systemd() -> None:
|
||||
)
|
||||
sys.stderr.write(
|
||||
f"\n(Or re-run this as root to install it directly: "
|
||||
f"sudo ./cli.py backend setup --backend=firecracker)\n"
|
||||
f"sudo bot-bottle backend setup --backend=firecracker)\n"
|
||||
)
|
||||
|
||||
|
||||
@@ -334,7 +334,7 @@ def status() -> int:
|
||||
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")
|
||||
sys.stderr.write("\nRun: bot-bottle backend setup --backend=firecracker\n")
|
||||
return 0 if ok else 1
|
||||
|
||||
|
||||
|
||||
@@ -9,7 +9,7 @@ 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`.
|
||||
and `bot-bottle backend setup --backend=firecracker`.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
@@ -132,18 +132,18 @@ def _require_network_pool() -> None:
|
||||
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.")
|
||||
f"bot-bottle 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")
|
||||
f"{', '.join(missing)}.\n bot-bottle 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")
|
||||
"bot-bottle backend setup --backend=firecracker")
|
||||
|
||||
|
||||
# --- rootfs pipeline (rootless) -------------------------------------
|
||||
|
||||
@@ -43,7 +43,7 @@ class Freezer(ABC):
|
||||
|
||||
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.
|
||||
preserved so the next `bot-bottle resume` boots from the snapshot.
|
||||
|
||||
Raises CommitCancelled if the user declines an interactive
|
||||
confirmation prompt (e.g. the macos-container stop prompt).
|
||||
@@ -51,7 +51,7 @@ class Freezer(ABC):
|
||||
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}")
|
||||
info(f"to resume from this snapshot: bot-bottle resume {agent.slug}")
|
||||
self._export_hint(agent.slug, image_ref)
|
||||
|
||||
@abstractmethod
|
||||
|
||||
@@ -25,3 +25,11 @@ class MacosContainerBottleCleanupPlan(BottleCleanupPlan):
|
||||
@property
|
||||
def empty(self) -> bool:
|
||||
return not self.containers and not self.networks
|
||||
|
||||
def intersect(self, current: BottleCleanupPlan) -> "MacosContainerBottleCleanupPlan":
|
||||
if not isinstance(current, MacosContainerBottleCleanupPlan):
|
||||
raise TypeError("cleanup plans must have the same backend type")
|
||||
return MacosContainerBottleCleanupPlan(
|
||||
containers=tuple(x for x in self.containers if x in current.containers),
|
||||
networks=tuple(x for x in self.networks if x in current.networks),
|
||||
)
|
||||
|
||||
@@ -4,7 +4,9 @@ from __future__ import annotations
|
||||
|
||||
import subprocess
|
||||
|
||||
from ...log import info, warn
|
||||
from .. import EnumerationError
|
||||
from ..cleanup_control import CleanupFailures
|
||||
from ...log import info
|
||||
from . import util as container_mod
|
||||
from .bottle_cleanup_plan import MacosContainerBottleCleanupPlan
|
||||
|
||||
@@ -19,8 +21,8 @@ def _list_prefixed_containers() -> list[str]:
|
||||
check=False,
|
||||
)
|
||||
if result.returncode != 0:
|
||||
warn(f"container list failed: {result.stderr.strip()}")
|
||||
return []
|
||||
detail = result.stderr.strip() or f"exit {result.returncode}"
|
||||
raise EnumerationError(f"container list failed: {detail}")
|
||||
return sorted(
|
||||
name for name in (line.strip() for line in result.stdout.splitlines())
|
||||
if name.startswith(_PREFIX)
|
||||
@@ -35,7 +37,8 @@ def _list_prefixed_networks() -> list[str]:
|
||||
check=False,
|
||||
)
|
||||
if result.returncode != 0:
|
||||
return []
|
||||
detail = result.stderr.strip() or f"exit {result.returncode}"
|
||||
raise EnumerationError(f"container network list failed: {detail}")
|
||||
return sorted(
|
||||
name for name in (line.strip() for line in result.stdout.splitlines())
|
||||
if name.startswith(_PREFIX)
|
||||
@@ -51,19 +54,17 @@ def prepare_cleanup() -> MacosContainerBottleCleanupPlan:
|
||||
|
||||
|
||||
def cleanup(plan: MacosContainerBottleCleanupPlan) -> None:
|
||||
failures = CleanupFailures()
|
||||
for name in plan.containers:
|
||||
info(f"container delete --force {name}")
|
||||
subprocess.run(
|
||||
failures.run(
|
||||
["container", "delete", "--force", name],
|
||||
stdout=subprocess.DEVNULL,
|
||||
stderr=subprocess.DEVNULL,
|
||||
check=False,
|
||||
f"deleting container {name}",
|
||||
)
|
||||
for name in plan.networks:
|
||||
info(f"container network delete {name}")
|
||||
subprocess.run(
|
||||
failures.run(
|
||||
["container", "network", "delete", name],
|
||||
stdout=subprocess.DEVNULL,
|
||||
stderr=subprocess.DEVNULL,
|
||||
check=False,
|
||||
f"deleting network {name}",
|
||||
)
|
||||
failures.raise_if_any()
|
||||
|
||||
@@ -5,7 +5,7 @@ from __future__ import annotations
|
||||
import subprocess
|
||||
|
||||
from ...bottle_state import read_metadata
|
||||
from .. import ActiveAgent
|
||||
from .. import ActiveAgent, EnumerationError
|
||||
from .infra import INFRA_NAME, ORCHESTRATOR_NAME
|
||||
|
||||
# The name every agent container carries: `bot-bottle-<slug>`. Exported
|
||||
@@ -20,17 +20,18 @@ CONTAINER_NAME_PREFIX = "bot-bottle-"
|
||||
_INFRA_NAMES = frozenset({INFRA_NAME, ORCHESTRATOR_NAME})
|
||||
|
||||
|
||||
class EnumerationError(RuntimeError):
|
||||
"""container list failed; the resulting live set is not authoritative."""
|
||||
|
||||
|
||||
def enumerate_active() -> list[ActiveAgent]:
|
||||
result = subprocess.run(
|
||||
["container", "list", "--quiet"],
|
||||
capture_output=True,
|
||||
text=True,
|
||||
check=False,
|
||||
)
|
||||
try:
|
||||
result = subprocess.run(
|
||||
["container", "list", "--quiet"],
|
||||
capture_output=True,
|
||||
text=True,
|
||||
check=False,
|
||||
)
|
||||
except FileNotFoundError as exc:
|
||||
raise EnumerationError(
|
||||
"container list failed: container CLI not found"
|
||||
) from exc
|
||||
if result.returncode != 0:
|
||||
raise EnumerationError(
|
||||
f"container list failed: "
|
||||
|
||||
@@ -107,7 +107,8 @@ def _layer_nested_containers(
|
||||
"""
|
||||
if not plan.nested_containers:
|
||||
return agent_image
|
||||
derived = f"{agent_image}{nested_containers_mod.IMAGE_SUFFIX}"
|
||||
pinned_base = container_mod.pinned_local_image_ref(agent_image)
|
||||
derived = f"{pinned_base}{nested_containers_mod.IMAGE_SUFFIX}"
|
||||
if plan.spec.image_policy == "cached":
|
||||
if not container_mod.image_exists(derived):
|
||||
die(
|
||||
@@ -116,7 +117,10 @@ def _layer_nested_containers(
|
||||
)
|
||||
info(f"using cached nested-container image {derived!r}")
|
||||
return derived
|
||||
return nested_containers_mod.build_image(agent_image, container_mod.build_image)
|
||||
return nested_containers_mod.build_image(
|
||||
pinned_base,
|
||||
container_mod.build_image,
|
||||
)
|
||||
|
||||
|
||||
@contextmanager
|
||||
|
||||
@@ -55,7 +55,7 @@ _GUEST_DEVICES = ("/dev/fuse", "/dev/net/tun")
|
||||
|
||||
|
||||
def build_image(
|
||||
base_image: str,
|
||||
pinned_base: str,
|
||||
build: Callable[..., None],
|
||||
) -> str:
|
||||
"""Layer the nested-container tooling onto an already-built agent image.
|
||||
@@ -66,14 +66,15 @@ def build_image(
|
||||
# TODO(#394): replace this hand-rolled Dockerfile with a docker-layer
|
||||
# abstraction once that infrastructure exists.
|
||||
"""
|
||||
image = f"{base_image}{IMAGE_SUFFIX}"
|
||||
image = f"{pinned_base}{IMAGE_SUFFIX}"
|
||||
init_script = Path(__file__).with_name("nested-containers-init.sh")
|
||||
with tempfile.TemporaryDirectory(prefix="bot-bottle-nested-containers.") as tmp:
|
||||
context = Path(tmp)
|
||||
shutil.copy2(init_script, context / "nested-containers-init.sh")
|
||||
(context / "Dockerfile").write_text(
|
||||
"FROM docker:28-cli AS docker_cli\n"
|
||||
f"FROM {base_image}\n"
|
||||
"ARG DOCKER_CLI_BASE_IMAGE\n"
|
||||
"FROM ${DOCKER_CLI_BASE_IMAGE} AS docker_cli\n"
|
||||
f"FROM {pinned_base}\n"
|
||||
"USER root\n"
|
||||
"COPY --from=docker_cli /usr/local/bin/docker /usr/local/bin/docker\n"
|
||||
"COPY --from=docker_cli /usr/local/libexec/docker/cli-plugins/"
|
||||
|
||||
@@ -5,7 +5,7 @@ Like Docker, this backend needs no privileged network-pool provisioning
|
||||
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}`.
|
||||
generic `bot-bottle backend {setup,status}`.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
@@ -75,5 +75,5 @@ def status() -> int:
|
||||
if not _service_running():
|
||||
ok = False
|
||||
if not ok:
|
||||
sys.stderr.write("\nRun: ./cli.py backend setup --backend=macos-container\n")
|
||||
sys.stderr.write("\nRun: bot-bottle backend setup --backend=macos-container\n")
|
||||
return 0 if ok else 1
|
||||
|
||||
@@ -13,6 +13,7 @@ import time
|
||||
from datetime import datetime, timezone
|
||||
from typing import Iterable
|
||||
|
||||
from ... import resources
|
||||
from ...log import die, info
|
||||
|
||||
|
||||
@@ -60,7 +61,13 @@ def dns_server() -> str:
|
||||
return _host_ipv4_dns() or _DEFAULT_DNS
|
||||
|
||||
|
||||
def build_image(ref: str, context: str, *, dockerfile: str = "") -> None:
|
||||
def build_image(
|
||||
ref: str,
|
||||
context: str,
|
||||
*,
|
||||
dockerfile: str = "",
|
||||
build_args: dict[str, str] | None = None,
|
||||
) -> None:
|
||||
"""Build an OCI image with Apple's BuildKit-backed `container build`.
|
||||
|
||||
Set `BOT_BOTTLE_NO_CACHE=1` (the `start --no-cache` flag) to force
|
||||
@@ -83,6 +90,13 @@ def build_image(ref: str, context: str, *, dockerfile: str = "") -> None:
|
||||
if not os.path.isabs(dockerfile):
|
||||
dockerfile = os.path.join(context, dockerfile)
|
||||
args.extend(["-f", dockerfile])
|
||||
effective_build_args = resources.image_build_args(
|
||||
dockerfile,
|
||||
context=context,
|
||||
) if dockerfile else {}
|
||||
effective_build_args.update(build_args or {})
|
||||
for name, value in effective_build_args.items():
|
||||
args.extend(["--build-arg", f"{name}={value}"])
|
||||
args.append(context)
|
||||
subprocess.run(args, check=True)
|
||||
|
||||
@@ -668,6 +682,47 @@ def image_id(ref: str) -> str:
|
||||
raise AssertionError("unreachable")
|
||||
|
||||
|
||||
def pinned_local_image_ref(ref: str) -> str:
|
||||
"""Tag a local image with its complete content ID for a stable ``FROM``.
|
||||
|
||||
Agent images are immediately used as bases for the optional
|
||||
nested-containers layer. A content-derived tag prevents another concurrent
|
||||
build from moving the provider's ordinary ``:latest`` tag between those
|
||||
two builds.
|
||||
|
||||
Unlike Docker, `container image tag` only accepts ``image-name[:tag]`` as
|
||||
its source and rejects a bare image ID ("cannot specify 64 byte hex string
|
||||
as reference"), so the mutable ``ref`` is what gets tagged here. The
|
||||
post-tag inspection below is what keeps that fail-closed: if ``ref`` moved
|
||||
between the two commands, the new tag will not resolve to the ID this call
|
||||
derived its name from.
|
||||
"""
|
||||
image = image_id(ref)
|
||||
digest = image.removeprefix("sha256:")
|
||||
if len(digest) != 64 or any(char not in "0123456789abcdef" for char in digest):
|
||||
die(f"could not derive a local base tag from invalid image ID {image!r}")
|
||||
repository = ref.split("@", 1)[0]
|
||||
last_slash = repository.rfind("/")
|
||||
last_colon = repository.rfind(":")
|
||||
if last_colon > last_slash:
|
||||
repository = repository[:last_colon]
|
||||
pinned_ref = f"{repository}:sha256-{digest}"
|
||||
result = subprocess.run(
|
||||
[_CONTAINER, "image", "tag", ref, pinned_ref],
|
||||
capture_output=True,
|
||||
text=True,
|
||||
check=False,
|
||||
)
|
||||
if result.returncode != 0:
|
||||
die(
|
||||
f"could not tag exact local image {image} via {ref!r}: "
|
||||
f"{(result.stderr or result.stdout or '').strip() or '<no detail>'}"
|
||||
)
|
||||
if image_id(pinned_ref) != image:
|
||||
die(f"content-derived local tag {pinned_ref!r} did not resolve to {image}")
|
||||
return pinned_ref
|
||||
|
||||
|
||||
def image_created_at(ref: str) -> datetime | None:
|
||||
"""Return the image creation timestamp as an aware UTC datetime, or None
|
||||
when the field is absent or unparseable (e.g. FROM-scratch images, images
|
||||
|
||||
@@ -0,0 +1,124 @@
|
||||
"""Backend-neutral preparation planner.
|
||||
|
||||
This module owns the shared transformation from a CLI ``BottleSpec`` to the
|
||||
typed inputs consumed by a concrete backend's ``_resolve_plan``. Backend
|
||||
classes retain only their validation/preflight/env hooks and their
|
||||
backend-specific final resolution.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import os
|
||||
from dataclasses import dataclass
|
||||
from typing import TYPE_CHECKING, Protocol
|
||||
|
||||
from ..agent_provider import AgentProvisionPlan, build_agent_provision_plan, get_provider
|
||||
from ..egress import EgressPlan
|
||||
from ..env import ResolvedEnv, resolve_env
|
||||
from ..git_gate import GitGate, GitGatePlan
|
||||
from ..manifest import Manifest
|
||||
from ..supervisor.plan import SupervisePlan
|
||||
from ..workspace import workspace_plan
|
||||
from .resolve_common import (
|
||||
merge_provision_env_vars,
|
||||
mint_slug,
|
||||
prepare_agent_state_dir,
|
||||
prepare_egress,
|
||||
prepare_git_gate,
|
||||
prepare_supervise,
|
||||
reject_nested_containers,
|
||||
resolve_manifest_dockerfile,
|
||||
write_launch_metadata,
|
||||
)
|
||||
|
||||
if TYPE_CHECKING:
|
||||
from .base import BottleSpec
|
||||
|
||||
|
||||
class PreparationBackend(Protocol):
|
||||
"""Backend hooks needed by the shared planner."""
|
||||
|
||||
name: str
|
||||
supports_nested_containers: bool
|
||||
|
||||
def _validate(self, spec: BottleSpec) -> Manifest: ...
|
||||
def _preflight(self) -> None: ...
|
||||
def _build_guest_env(self, resolved_env: ResolvedEnv) -> dict[str, str]: ...
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class PreparedBottle:
|
||||
"""Typed, backend-neutral result of shared launch preparation."""
|
||||
|
||||
manifest: Manifest
|
||||
slug: str
|
||||
resolved_env: ResolvedEnv
|
||||
agent_provision_plan: AgentProvisionPlan
|
||||
egress_plan: EgressPlan
|
||||
git_gate_plan: GitGatePlan
|
||||
supervise_plan: SupervisePlan | None
|
||||
|
||||
|
||||
class BottlePreparationPlanner:
|
||||
"""Run the common, side-effect-limited part of bottle preparation."""
|
||||
|
||||
def __init__(self, backend: PreparationBackend) -> None:
|
||||
self._backend = backend
|
||||
|
||||
def prepare(self, spec: BottleSpec) -> PreparedBottle:
|
||||
backend = self._backend
|
||||
# These are deliberately protected backend hooks: only this shared
|
||||
# planner orchestrates them, while concrete backends provide the
|
||||
# implementation.
|
||||
manifest = backend._validate(spec) # pylint: disable=protected-access
|
||||
if not backend.supports_nested_containers:
|
||||
reject_nested_containers(backend.name, manifest)
|
||||
|
||||
backend._preflight() # pylint: disable=protected-access
|
||||
manifest = GitGate().preflight_host_keys(
|
||||
manifest,
|
||||
headless=spec.headless,
|
||||
home_md=spec.manifest.home_md,
|
||||
)
|
||||
|
||||
bottle = manifest.bottle
|
||||
provider_config = bottle.agent_provider
|
||||
provider = get_provider(provider_config.template)
|
||||
resolved_env = resolve_env(manifest)
|
||||
workspace = workspace_plan(spec, guest_home=provider.guest_home)
|
||||
slug = mint_slug(spec)
|
||||
write_launch_metadata(slug, spec, compose_project="", backend=backend.name)
|
||||
|
||||
dockerfile = (
|
||||
resolve_manifest_dockerfile(provider_config.dockerfile, spec)
|
||||
if provider_config.dockerfile
|
||||
else str(provider.dockerfile)
|
||||
)
|
||||
agent_dir, prompt_file = prepare_agent_state_dir(slug, manifest)
|
||||
provision = build_agent_provision_plan(
|
||||
template=provider_config.template,
|
||||
dockerfile=dockerfile,
|
||||
state_dir=agent_dir,
|
||||
instance_name=f"bot-bottle-{slug}",
|
||||
prompt_file=prompt_file,
|
||||
guest_env=backend._build_guest_env( # pylint: disable=protected-access
|
||||
resolved_env
|
||||
),
|
||||
forward_host_credentials=provider_config.forward_host_credentials,
|
||||
auth_token=provider_config.auth_token,
|
||||
host_env=dict(os.environ),
|
||||
trusted_project_path=workspace.workdir,
|
||||
label=spec.label,
|
||||
color=spec.color,
|
||||
provider_settings=provider_config.settings,
|
||||
)
|
||||
provision = merge_provision_env_vars(provision)
|
||||
return PreparedBottle(
|
||||
manifest=manifest,
|
||||
slug=slug,
|
||||
resolved_env=resolved_env,
|
||||
agent_provision_plan=provision,
|
||||
egress_plan=prepare_egress(bottle, slug, provision),
|
||||
git_gate_plan=prepare_git_gate(bottle, slug),
|
||||
supervise_plan=prepare_supervise(bottle, slug),
|
||||
)
|
||||
@@ -63,12 +63,23 @@ def provision_git_gate(
|
||||
transport.exec(["chmod", "+x", "/etc/git-gate/access-hook"])
|
||||
creds = _creds_dir(bottle_id)
|
||||
transport.exec(["mkdir", "-p", creds])
|
||||
transport.exec(["chmod", "700", creds])
|
||||
credential_paths: list[str] = []
|
||||
for u in plan.upstreams:
|
||||
if u.identity_file:
|
||||
transport.cp_into(u.identity_file, f"{creds}/{u.name}-key")
|
||||
key_path = f"{creds}/{u.name}-key"
|
||||
transport.cp_into(u.identity_file, key_path)
|
||||
credential_paths.append(key_path)
|
||||
known_hosts = str(u.known_hosts_file)
|
||||
if known_hosts and known_hosts != ".":
|
||||
transport.cp_into(known_hosts, f"{creds}/{u.name}-known_hosts")
|
||||
known_hosts_path = f"{creds}/{u.name}-known_hosts"
|
||||
transport.cp_into(known_hosts, known_hosts_path)
|
||||
credential_paths.append(known_hosts_path)
|
||||
# Copy-mode behavior differs across Docker, Apple Container, and SSH.
|
||||
# Apply the security contract inside the gateway so every backend produces
|
||||
# the same private credential namespace.
|
||||
if credential_paths:
|
||||
transport.exec(["chmod", "600", *credential_paths])
|
||||
# Init the bare repos + per-repo credential config for this namespace.
|
||||
script = git_gate_render_provision(bottle_id, plan.upstreams)
|
||||
transport.exec(["sh", "-c", script])
|
||||
|
||||
@@ -30,6 +30,7 @@ from ..log import die
|
||||
from ..manifest import Manifest, ManifestBottle
|
||||
from ..supervisor.plan import SupervisePlan
|
||||
from ..orchestrator.supervisor import Supervisor
|
||||
from ..util import slugify
|
||||
from . import BottleSpec
|
||||
|
||||
|
||||
@@ -44,8 +45,7 @@ def mint_slug(spec: BottleSpec) -> str:
|
||||
if spec.identity:
|
||||
return spec.identity
|
||||
if spec.label:
|
||||
from .docker import util as docker_mod
|
||||
return docker_mod.slugify(spec.label)
|
||||
return slugify(spec.label)
|
||||
return bottle_identity(spec.agent_name)
|
||||
|
||||
|
||||
|
||||
@@ -86,7 +86,7 @@ def _print_vm_install_instructions() -> None:
|
||||
info("Then start the service: container system start")
|
||||
else:
|
||||
info("Install Firecracker: https://github.com/firecracker-microvm/firecracker/releases")
|
||||
info("Configure the host: ./cli.py backend setup")
|
||||
info("Configure the host: bot-bottle backend setup")
|
||||
|
||||
|
||||
def _auto_select_backend(prompt: bool = True) -> str:
|
||||
|
||||
@@ -1,9 +1,9 @@
|
||||
"""`backend` CLI command — generic host setup/status across backends.
|
||||
|
||||
`./cli.py backend setup [--backend=NAME]` provisions (or points at how
|
||||
`bot-bottle 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).
|
||||
`bot-bottle backend status [--backend=NAME]` reports readiness.
|
||||
`bot-bottle 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
|
||||
|
||||
@@ -1,7 +1,7 @@
|
||||
"""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
|
||||
so a single `bot-bottle cleanup` reaps every backend's leftovers — a
|
||||
firecracker bottle's VM processes and run dirs won't survive a
|
||||
docker-only cleanup pass (issue addressed alongside #77).
|
||||
|
||||
@@ -22,6 +22,7 @@ from __future__ import annotations
|
||||
import sys
|
||||
|
||||
from ...backend import get_bottle_backend, has_backend, known_backend_names
|
||||
from ...backend.cleanup_control import CleanupError
|
||||
from ...log import info
|
||||
from ...util import read_tty_line
|
||||
|
||||
@@ -52,10 +53,20 @@ def cmd_cleanup(_argv: list[str]) -> int:
|
||||
info("cleanup: skipped")
|
||||
return 0
|
||||
|
||||
for name, backend, plan in prepared:
|
||||
if plan.empty:
|
||||
# Confirmation authorizes a fresh authoritative snapshot, not blind use of
|
||||
# identities that may have changed while the operator reviewed the preview.
|
||||
failures: list[str] = []
|
||||
for name, backend, displayed in prepared:
|
||||
current = backend.prepare_cleanup()
|
||||
approved = displayed.intersect(current)
|
||||
if approved.empty:
|
||||
continue
|
||||
backend.cleanup(plan)
|
||||
try:
|
||||
backend.cleanup(approved)
|
||||
except CleanupError as exc:
|
||||
failures.append(f"{name}: {exc}")
|
||||
if failures:
|
||||
raise CleanupError("cleanup incomplete: " + "; ".join(failures))
|
||||
info("cleanup: done")
|
||||
return 0
|
||||
|
||||
|
||||
@@ -4,7 +4,7 @@ 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
|
||||
state so the next `bot-bottle resume <slug>` boots from the snapshot
|
||||
instead of rebuilding from the Dockerfile.
|
||||
"""
|
||||
|
||||
@@ -37,7 +37,7 @@ def cmd_commit(argv: list[str]) -> int:
|
||||
if slug is None:
|
||||
active = enumerate_active_agents()
|
||||
if not active:
|
||||
die("no active bottles; start one with `./cli.py start`")
|
||||
die("no active bottles; start one with `bot-bottle start`")
|
||||
choices = [a.slug for a in active]
|
||||
slug = tui.filter_select(choices, title="Select bottle to commit")
|
||||
if slug is None:
|
||||
|
||||
@@ -8,7 +8,7 @@ override and transcript snapshot under the same state dir.
|
||||
|
||||
Use case: an interrupted or preserved bottle needs to be relaunched;
|
||||
the operator runs
|
||||
./cli.py resume <identity>
|
||||
bot-bottle resume <identity>
|
||||
to bring up the replacement from the recorded state.
|
||||
"""
|
||||
|
||||
|
||||
@@ -25,12 +25,11 @@ from typing import Callable
|
||||
from ...agent_provider import get_provider, runtime_for
|
||||
from ...backend import (
|
||||
Bottle,
|
||||
BottlePlan,
|
||||
BottleSpec,
|
||||
enumerate_active_agents,
|
||||
get_bottle_backend,
|
||||
)
|
||||
from ...backend.docker import util as docker_mod
|
||||
from ...backend.docker.bottle_plan import DockerBottlePlan
|
||||
from ...bottle_state import (
|
||||
cleanup_state,
|
||||
is_preserved,
|
||||
@@ -40,7 +39,7 @@ from ...image_cache import StaleImageError
|
||||
from ...log import info, die
|
||||
from ...manifest import Manifest, ManifestIndex
|
||||
from ..constants import PROG
|
||||
from ...util import read_tty_line
|
||||
from ...util import read_tty_line, slugify
|
||||
from .. import tui
|
||||
|
||||
|
||||
@@ -204,19 +203,19 @@ def _start_headless(
|
||||
if not os.isatty(stdin_fd):
|
||||
die(
|
||||
"--headless requires a PTY on stdin; run via:\n"
|
||||
" script -q /dev/null ./cli.py start ..."
|
||||
" script -q /dev/null bot-bottle start ..."
|
||||
)
|
||||
|
||||
agent_name = args.name
|
||||
if not agent_name:
|
||||
die("--headless requires an agent name: ./cli.py start <agent> --headless")
|
||||
die("--headless requires an agent name: bot-bottle 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'"
|
||||
"bot-bottle start <agent> --headless --prompt 'Do the thing'"
|
||||
)
|
||||
|
||||
if args.bottle:
|
||||
@@ -257,10 +256,10 @@ def _uniquify_label_headless(label: str) -> str:
|
||||
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:
|
||||
if slugify(label) not in active_slugs:
|
||||
return label
|
||||
n = 2
|
||||
while docker_mod.slugify(f"{label}-{n}") in active_slugs:
|
||||
while slugify(f"{label}-{n}") in active_slugs:
|
||||
n += 1
|
||||
chosen = f"{label}-{n}"
|
||||
info(f"label '{label}' already in use; using '{chosen}'")
|
||||
@@ -274,11 +273,11 @@ def prepare_with_preflight(
|
||||
spec: BottleSpec,
|
||||
*,
|
||||
stage_dir: Path,
|
||||
render_preflight: Callable[[DockerBottlePlan, str], None],
|
||||
render_preflight: Callable[[BottlePlan, str], None],
|
||||
prompt_yes: Callable[[], bool],
|
||||
dry_run: bool = False,
|
||||
backend_name: str | None = None,
|
||||
) -> tuple[DockerBottlePlan | None, str]:
|
||||
) -> tuple[BottlePlan | None, str]:
|
||||
"""Run `backend.prepare`, render the preflight summary via the
|
||||
injected callable, prompt y/N via the injected callable.
|
||||
|
||||
@@ -320,9 +319,9 @@ def attach_agent(
|
||||
|
||||
`resume=True` adds `--continue` so claude picks up its most
|
||||
recent session non-interactively (no session-picker prompt).
|
||||
First-attach paths (`./cli.py start`) leave it False.
|
||||
First-attach paths (`bot-bottle start`) leave it False.
|
||||
|
||||
Used as the inner step of `./cli.py start`."""
|
||||
Used as the inner step of `bot-bottle start`."""
|
||||
runtime = runtime_for(agent_provider_template)
|
||||
info(
|
||||
f"attaching interactive {agent_provider_template} session "
|
||||
@@ -355,7 +354,7 @@ def settle_state(identity: str) -> None:
|
||||
if not identity:
|
||||
return
|
||||
if is_preserved(identity):
|
||||
info(f"to resume this bottle: ./cli.py resume {identity}")
|
||||
info(f"to resume this bottle: bot-bottle resume {identity}")
|
||||
return
|
||||
cleanup_state(identity)
|
||||
|
||||
@@ -405,7 +404,7 @@ def _resolve_unique_label(label: str, color: str) -> tuple[str, str]:
|
||||
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)
|
||||
slug_candidate = slugify(label)
|
||||
active_slugs = {a.slug for a in enumerate_active_agents()}
|
||||
if slug_candidate not in active_slugs:
|
||||
return label, color
|
||||
@@ -432,7 +431,7 @@ def _select_image_policy() -> str | None:
|
||||
|
||||
|
||||
def _text_render_preflight():
|
||||
def _render(plan: DockerBottlePlan, backend_name: str) -> None:
|
||||
def _render(plan: BottlePlan, 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)
|
||||
|
||||
@@ -110,7 +110,7 @@ def discover_pending() -> list[QueuedProposal]:
|
||||
def _approval_status(qp: QueuedProposal, verb: str) -> str:
|
||||
"""Status-line text after a successful approval."""
|
||||
base = f"{verb} {qp.proposal.tool} for [{qp.label}]"
|
||||
return f"{base}; resume: ./cli.py resume {qp.label}"
|
||||
return f"{base}; resume: bot-bottle resume {qp.label}"
|
||||
|
||||
|
||||
def _detail_lines(
|
||||
@@ -368,7 +368,7 @@ def _main_loop(stdscr: "curses._CursesWindow") -> None: # type: ignore # pragm
|
||||
elif key in (curses.KEY_UP, ord("k")):
|
||||
selected = max(selected - 1, 0)
|
||||
elif key in (curses.KEY_ENTER, 10, 13):
|
||||
_detail_view(stdscr, qp, green_attr=green_attr)
|
||||
status_line = _detail_view(stdscr, qp, green_attr=green_attr)
|
||||
elif key == ord("a"):
|
||||
try:
|
||||
status_line = _approve_from_tui(stdscr, qp)
|
||||
@@ -456,7 +456,7 @@ def _detail_view(
|
||||
qp: QueuedProposal,
|
||||
*,
|
||||
green_attr: int = 0,
|
||||
) -> None: # pragma: no cover
|
||||
) -> str: # pragma: no cover
|
||||
"""Render the full proposal. Scrollable. Press q to return."""
|
||||
lines = _detail_lines(qp, green_attr=green_attr)
|
||||
offset = 0
|
||||
@@ -473,7 +473,7 @@ def _detail_view(
|
||||
stdscr.refresh()
|
||||
key = stdscr.getch()
|
||||
if key in (ord("q"), 27):
|
||||
return
|
||||
return ""
|
||||
if key in (curses.KEY_DOWN, ord("j")):
|
||||
offset = min(offset + 1, max(0, len(lines) - 1))
|
||||
elif key in (curses.KEY_UP, ord("k")):
|
||||
@@ -484,31 +484,34 @@ def _detail_view(
|
||||
offset = max(0, len(lines) - 1)
|
||||
elif key == ord("a"):
|
||||
try:
|
||||
_approve_from_tui(stdscr, qp)
|
||||
except ApplyError:
|
||||
pass
|
||||
return
|
||||
return _approve_from_tui(stdscr, qp)
|
||||
except ApplyError as exc:
|
||||
return f"apply failed: {exc}"
|
||||
elif key == ord("m"):
|
||||
if qp.proposal.tool in _REPORT_ONLY_TOOLS:
|
||||
return
|
||||
return f"modify unavailable for {qp.proposal.tool}"
|
||||
edited = _modify(stdscr, qp)
|
||||
if edited is not None:
|
||||
try:
|
||||
_approve_from_tui(
|
||||
stdscr, qp, final_file=edited,
|
||||
notes="operator modified before approving",
|
||||
)
|
||||
except ApplyError:
|
||||
pass
|
||||
return
|
||||
if edited is None:
|
||||
return "modify aborted (no change)"
|
||||
try:
|
||||
return _approve_from_tui(
|
||||
stdscr, qp, final_file=edited,
|
||||
notes="operator modified before approving",
|
||||
)
|
||||
except ApplyError as exc:
|
||||
return f"apply failed: {exc}"
|
||||
elif key == ord("r"):
|
||||
reason = _prompt(stdscr, "reject reason: ")
|
||||
if reason:
|
||||
reject(qp, reason=reason)
|
||||
return
|
||||
return f"rejected {qp.proposal.tool} for [{qp.label}]"
|
||||
return "reject aborted (empty reason)"
|
||||
|
||||
|
||||
def _modify(stdscr: "curses._CursesWindow", qp: QueuedProposal) -> str | None: # type: ignore # pragma: no cover
|
||||
def _modify(
|
||||
stdscr: "curses._CursesWindow", # type: ignore
|
||||
qp: QueuedProposal,
|
||||
) -> str | None: # pragma: no cover
|
||||
"""Suspend curses, open $EDITOR on the proposed file, return edited content."""
|
||||
suffix = _suffix_for_tool(qp.proposal.tool)
|
||||
curses.endwin()
|
||||
|
||||
+32
-6
@@ -16,6 +16,8 @@ import os
|
||||
import sys
|
||||
from typing import Any, Optional
|
||||
|
||||
from ..log import debug
|
||||
|
||||
|
||||
def filter_multiselect(
|
||||
items: list[str],
|
||||
@@ -42,7 +44,11 @@ def filter_multiselect(
|
||||
|
||||
try:
|
||||
tty_fd = open(tty_path, "r+b", buffering=0)
|
||||
except OSError:
|
||||
except OSError as exc:
|
||||
debug(
|
||||
"multi-select unavailable; treating it as cancellation",
|
||||
context={"error_type": type(exc).__name__, "tty": tty_path},
|
||||
)
|
||||
return None
|
||||
|
||||
try:
|
||||
@@ -73,7 +79,11 @@ def filter_select(
|
||||
|
||||
try:
|
||||
tty_fd = open(tty_path, "r+b", buffering=0)
|
||||
except OSError:
|
||||
except OSError as exc:
|
||||
debug(
|
||||
"filter-select unavailable; treating it as cancellation",
|
||||
context={"error_type": type(exc).__name__, "tty": tty_path},
|
||||
)
|
||||
return None
|
||||
|
||||
try:
|
||||
@@ -129,7 +139,11 @@ def _run_picker(items: list[str], *, title: str, tty_fd: int) -> Optional[str]:
|
||||
curses.nocbreak()
|
||||
curses.echo()
|
||||
curses.endwin()
|
||||
except Exception: # noqa: W0718 — curses can raise many error types
|
||||
except Exception as exc: # noqa: W0718 — curses can raise many error types
|
||||
debug(
|
||||
"filter-select display failed; treating it as cancellation",
|
||||
context={"error_type": type(exc).__name__},
|
||||
)
|
||||
return None
|
||||
finally:
|
||||
sys.__stdin__ = orig_stdin # type: ignore[assignment]
|
||||
@@ -292,7 +306,11 @@ def _run_multiselect(
|
||||
curses.nocbreak()
|
||||
curses.echo()
|
||||
curses.endwin()
|
||||
except Exception: # noqa: W0718
|
||||
except Exception as exc: # noqa: W0718
|
||||
debug(
|
||||
"multi-select display failed; treating it as cancellation",
|
||||
context={"error_type": type(exc).__name__},
|
||||
)
|
||||
return None
|
||||
finally:
|
||||
sys.__stdin__ = orig_stdin # type: ignore[assignment]
|
||||
@@ -558,13 +576,21 @@ def name_color_modal(
|
||||
"""
|
||||
try:
|
||||
tty_fd = open(tty_path, "r+b", buffering=0) # pylint: disable=consider-using-with
|
||||
except OSError:
|
||||
except OSError as exc:
|
||||
debug(
|
||||
"name/color picker unavailable; using defaults",
|
||||
context={"error_type": type(exc).__name__, "tty": tty_path},
|
||||
)
|
||||
return default_label, ""
|
||||
|
||||
try:
|
||||
fd_dup = os.dup(tty_fd.fileno())
|
||||
return _run_name_color(default_label, tty_fd=fd_dup, disclaimer=disclaimer)
|
||||
except Exception: # noqa: BLE001 # pylint: disable=broad-exception-caught
|
||||
except Exception as exc: # noqa: BLE001 # pylint: disable=broad-exception-caught
|
||||
debug(
|
||||
"name/color picker failed; using defaults",
|
||||
context={"error_type": type(exc).__name__},
|
||||
)
|
||||
return default_label, ""
|
||||
finally:
|
||||
tty_fd.close()
|
||||
|
||||
@@ -8,9 +8,17 @@
|
||||
# Layer ordering is deliberate: the npm install lives in its own layer so
|
||||
# changes to the rest of the repo (or to the CMD) don't bust it.
|
||||
|
||||
# Current Node LTS; slim variant keeps the image small while still
|
||||
# providing apt-get for any future additions.
|
||||
FROM node:22-trixie-slim
|
||||
# Version-qualified Node LTS, pinned to its multi-architecture manifest.
|
||||
ARG NODE_BASE_IMAGE
|
||||
FROM ${NODE_BASE_IMAGE}
|
||||
|
||||
ARG DEBIAN_SNAPSHOT=20260724T000000Z
|
||||
RUN sed -i \
|
||||
-e "s|http://deb.debian.org/debian-security|http://snapshot.debian.org/archive/debian-security/${DEBIAN_SNAPSHOT}|g" \
|
||||
-e "s|https://deb.debian.org/debian-security|http://snapshot.debian.org/archive/debian-security/${DEBIAN_SNAPSHOT}|g" \
|
||||
-e "s|http://deb.debian.org/debian|http://snapshot.debian.org/archive/debian/${DEBIAN_SNAPSHOT}|g" \
|
||||
-e "s|https://deb.debian.org/debian|http://snapshot.debian.org/archive/debian/${DEBIAN_SNAPSHOT}|g" \
|
||||
/etc/apt/sources.list.d/debian.sources
|
||||
|
||||
# Install runtime system deps. claude-code shells out to git for several
|
||||
# features (status checks, commits, PR creation) — without git in the
|
||||
@@ -20,7 +28,7 @@ FROM node:22-trixie-slim
|
||||
# HTTPS_PROXY-aware tool (curl itself, plus anything that shells out
|
||||
# to it) works against egress's bumped TLS without the agent needing
|
||||
# local DNS.
|
||||
RUN apt-get update \
|
||||
RUN apt-get -o Acquire::Check-Valid-Until=false update \
|
||||
&& apt-get install -y --no-install-recommends \
|
||||
git \
|
||||
ca-certificates \
|
||||
@@ -35,15 +43,17 @@ RUN apt-get update \
|
||||
# (claude-code is a Node CLI), but is convenient for the agent to
|
||||
# shell out to for ad-hoc scripts. Kept on its own layer so it can
|
||||
# be moved to a downstream image if the base ever needs to shrink.
|
||||
RUN apt-get update \
|
||||
RUN apt-get -o Acquire::Check-Valid-Until=false update \
|
||||
&& apt-get install -y --no-install-recommends python3 python3-pip python3-venv \
|
||||
&& rm -rf /var/lib/apt/lists/*
|
||||
|
||||
# Install claude-code globally. Pinned to the version verified in the v1
|
||||
# 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 \
|
||||
# Install from the committed npm lock. `npm ci` verifies every registry
|
||||
# artifact against its lockfile integrity and refuses dependency drift.
|
||||
COPY bot_bottle/contrib/claude/package.json \
|
||||
bot_bottle/contrib/claude/package-lock.json /opt/claude/
|
||||
RUN cd /opt/claude \
|
||||
&& npm ci --omit=dev --no-fund --no-audit \
|
||||
&& ln -s /opt/claude/node_modules/.bin/claude /usr/local/bin/claude \
|
||||
&& npm cache clean --force
|
||||
|
||||
# Git reads both ~/.gitconfig and ~/.config/git/config. Keep its XDG config
|
||||
|
||||
+140
@@ -0,0 +1,140 @@
|
||||
{
|
||||
"name": "bot-bottle-claude-image",
|
||||
"lockfileVersion": 3,
|
||||
"requires": true,
|
||||
"packages": {
|
||||
"": {
|
||||
"name": "bot-bottle-claude-image",
|
||||
"dependencies": {
|
||||
"@anthropic-ai/claude-code": "2.1.172"
|
||||
}
|
||||
},
|
||||
"node_modules/@anthropic-ai/claude-code": {
|
||||
"version": "2.1.172",
|
||||
"resolved": "https://registry.npmjs.org/@anthropic-ai/claude-code/-/claude-code-2.1.172.tgz",
|
||||
"integrity": "sha512-SfwC+5fQcmNbvvm+1vLiZbfUxt0PQz9lbXapj9+FI+XY/2e+3zgteBM4JFEXBjULZj1DtZXHmKtAROUrMM9GZg==",
|
||||
"hasInstallScript": true,
|
||||
"license": "SEE LICENSE IN README.md",
|
||||
"bin": {
|
||||
"claude": "bin/claude.exe"
|
||||
},
|
||||
"engines": {
|
||||
"node": ">=18.0.0"
|
||||
},
|
||||
"optionalDependencies": {
|
||||
"@anthropic-ai/claude-code-darwin-arm64": "2.1.172",
|
||||
"@anthropic-ai/claude-code-darwin-x64": "2.1.172",
|
||||
"@anthropic-ai/claude-code-linux-arm64": "2.1.172",
|
||||
"@anthropic-ai/claude-code-linux-arm64-musl": "2.1.172",
|
||||
"@anthropic-ai/claude-code-linux-x64": "2.1.172",
|
||||
"@anthropic-ai/claude-code-linux-x64-musl": "2.1.172",
|
||||
"@anthropic-ai/claude-code-win32-arm64": "2.1.172",
|
||||
"@anthropic-ai/claude-code-win32-x64": "2.1.172"
|
||||
}
|
||||
},
|
||||
"node_modules/@anthropic-ai/claude-code-darwin-arm64": {
|
||||
"version": "2.1.172",
|
||||
"resolved": "https://registry.npmjs.org/@anthropic-ai/claude-code-darwin-arm64/-/claude-code-darwin-arm64-2.1.172.tgz",
|
||||
"integrity": "sha512-pBRgDo8PAgbt2aE4oc6ZrKdOa/Ax36RAduhLCaI8NWD3a0RDb5mETzQciQLwnuenk0bs27vIRh9Yg1jAYG/0+A==",
|
||||
"cpu": [
|
||||
"arm64"
|
||||
],
|
||||
"license": "SEE LICENSE IN LICENSE.md",
|
||||
"optional": true,
|
||||
"os": [
|
||||
"darwin"
|
||||
]
|
||||
},
|
||||
"node_modules/@anthropic-ai/claude-code-darwin-x64": {
|
||||
"version": "2.1.172",
|
||||
"resolved": "https://registry.npmjs.org/@anthropic-ai/claude-code-darwin-x64/-/claude-code-darwin-x64-2.1.172.tgz",
|
||||
"integrity": "sha512-vSgibgeCyvCFiLJSXu/sgcd3L/tUjSiS/tfS9rJLXUjElw8satMJhA5pqPUiBmKMflOWKMufbZgzXvLx+OhvFw==",
|
||||
"cpu": [
|
||||
"x64"
|
||||
],
|
||||
"license": "SEE LICENSE IN LICENSE.md",
|
||||
"optional": true,
|
||||
"os": [
|
||||
"darwin"
|
||||
]
|
||||
},
|
||||
"node_modules/@anthropic-ai/claude-code-linux-arm64": {
|
||||
"version": "2.1.172",
|
||||
"resolved": "https://registry.npmjs.org/@anthropic-ai/claude-code-linux-arm64/-/claude-code-linux-arm64-2.1.172.tgz",
|
||||
"integrity": "sha512-Ql7AbyaXnlA6NwDUaQGO7ZZis21rMjYjbKzpksMCvY35CmsJqanYgbYSn/rE83u/tZpKo+NqOv+bWEDSzsZ02w==",
|
||||
"cpu": [
|
||||
"arm64"
|
||||
],
|
||||
"license": "SEE LICENSE IN LICENSE.md",
|
||||
"optional": true,
|
||||
"os": [
|
||||
"linux"
|
||||
]
|
||||
},
|
||||
"node_modules/@anthropic-ai/claude-code-linux-arm64-musl": {
|
||||
"version": "2.1.172",
|
||||
"resolved": "https://registry.npmjs.org/@anthropic-ai/claude-code-linux-arm64-musl/-/claude-code-linux-arm64-musl-2.1.172.tgz",
|
||||
"integrity": "sha512-Pa9mGGmp8QCRC2j1cgcWRRkwsK1x4bPsS3CcLRd936Op0k5et62tD3qIYhUPQOIxeuxe9Tt/y7lX1cx7JTDxyA==",
|
||||
"cpu": [
|
||||
"arm64"
|
||||
],
|
||||
"license": "SEE LICENSE IN LICENSE.md",
|
||||
"optional": true,
|
||||
"os": [
|
||||
"linux"
|
||||
]
|
||||
},
|
||||
"node_modules/@anthropic-ai/claude-code-linux-x64": {
|
||||
"version": "2.1.172",
|
||||
"resolved": "https://registry.npmjs.org/@anthropic-ai/claude-code-linux-x64/-/claude-code-linux-x64-2.1.172.tgz",
|
||||
"integrity": "sha512-RYCY9EHkmtoAlwBKcWRzGIhuus+GM2CIVCfU81cTQAwDcCHunoBeFn3NqAcFV1VKb4dk9TRarAmQcWMKJrpPig==",
|
||||
"cpu": [
|
||||
"x64"
|
||||
],
|
||||
"license": "SEE LICENSE IN LICENSE.md",
|
||||
"optional": true,
|
||||
"os": [
|
||||
"linux"
|
||||
]
|
||||
},
|
||||
"node_modules/@anthropic-ai/claude-code-linux-x64-musl": {
|
||||
"version": "2.1.172",
|
||||
"resolved": "https://registry.npmjs.org/@anthropic-ai/claude-code-linux-x64-musl/-/claude-code-linux-x64-musl-2.1.172.tgz",
|
||||
"integrity": "sha512-1NflAnV/MqIlD4rzlGDVsJgGK2xJ2ldVd5pkcbu7PsDJBW5dzKYVa4PmD0715K8Yiji8jQovh/nhIo6gYyTfVQ==",
|
||||
"cpu": [
|
||||
"x64"
|
||||
],
|
||||
"license": "SEE LICENSE IN LICENSE.md",
|
||||
"optional": true,
|
||||
"os": [
|
||||
"linux"
|
||||
]
|
||||
},
|
||||
"node_modules/@anthropic-ai/claude-code-win32-arm64": {
|
||||
"version": "2.1.172",
|
||||
"resolved": "https://registry.npmjs.org/@anthropic-ai/claude-code-win32-arm64/-/claude-code-win32-arm64-2.1.172.tgz",
|
||||
"integrity": "sha512-Gj8mIbHDDSGWnoriqB1Jt1uH6cvNBFDQBtIYarCcv0fs+QGCEP6qm2GIaKqxAbwkUaLT0sCW/7+ukvkNdSltuQ==",
|
||||
"cpu": [
|
||||
"arm64"
|
||||
],
|
||||
"license": "SEE LICENSE IN LICENSE.md",
|
||||
"optional": true,
|
||||
"os": [
|
||||
"win32"
|
||||
]
|
||||
},
|
||||
"node_modules/@anthropic-ai/claude-code-win32-x64": {
|
||||
"version": "2.1.172",
|
||||
"resolved": "https://registry.npmjs.org/@anthropic-ai/claude-code-win32-x64/-/claude-code-win32-x64-2.1.172.tgz",
|
||||
"integrity": "sha512-OkheFwagiCEKaO2Sb0j3JTO1NrcR3zTlFik/AN+yQPefhUIGP6vHQDbBG5ksuFe+Dyd9s+P95OUh8WDhccb+Ng==",
|
||||
"cpu": [
|
||||
"x64"
|
||||
],
|
||||
"license": "SEE LICENSE IN LICENSE.md",
|
||||
"optional": true,
|
||||
"os": [
|
||||
"win32"
|
||||
]
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,7 @@
|
||||
{
|
||||
"name": "bot-bottle-claude-image",
|
||||
"private": true,
|
||||
"dependencies": {
|
||||
"@anthropic-ai/claude-code": "2.1.172"
|
||||
}
|
||||
}
|
||||
@@ -3,9 +3,22 @@
|
||||
# Mirrors the default Claude image shape: Node LTS, git/network tooling,
|
||||
# non-root node user, and the provider CLI installed for that user.
|
||||
|
||||
FROM node:22-trixie-slim
|
||||
ARG NODE_BASE_IMAGE
|
||||
FROM ${NODE_BASE_IMAGE}
|
||||
|
||||
RUN apt-get update \
|
||||
# Remote-control requires the standalone package layout. Keep this exact release
|
||||
# in sync with the committed upstream archive checksums.
|
||||
ARG CODEX_VERSION=0.145.0
|
||||
|
||||
ARG DEBIAN_SNAPSHOT=20260724T000000Z
|
||||
RUN sed -i \
|
||||
-e "s|http://deb.debian.org/debian-security|http://snapshot.debian.org/archive/debian-security/${DEBIAN_SNAPSHOT}|g" \
|
||||
-e "s|https://deb.debian.org/debian-security|http://snapshot.debian.org/archive/debian-security/${DEBIAN_SNAPSHOT}|g" \
|
||||
-e "s|http://deb.debian.org/debian|http://snapshot.debian.org/archive/debian/${DEBIAN_SNAPSHOT}|g" \
|
||||
-e "s|https://deb.debian.org/debian|http://snapshot.debian.org/archive/debian/${DEBIAN_SNAPSHOT}|g" \
|
||||
/etc/apt/sources.list.d/debian.sources
|
||||
|
||||
RUN apt-get -o Acquire::Check-Valid-Until=false update \
|
||||
&& apt-get install -y --no-install-recommends \
|
||||
git \
|
||||
ca-certificates \
|
||||
@@ -19,7 +32,7 @@ RUN apt-get update \
|
||||
# (codex is a Node CLI), but is convenient for the agent to shell
|
||||
# out to for ad-hoc scripts. Kept on its own layer so it can be
|
||||
# moved to a downstream image if the base ever needs to shrink.
|
||||
RUN apt-get update \
|
||||
RUN apt-get -o Acquire::Check-Valid-Until=false update \
|
||||
&& apt-get install -y --no-install-recommends python3 python3-pip python3-venv \
|
||||
&& rm -rf /var/lib/apt/lists/*
|
||||
|
||||
@@ -30,10 +43,29 @@ WORKDIR /home/node
|
||||
|
||||
ENV PATH="/home/node/.local/bin:${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
|
||||
# Install the exact standalone release archive selected by the target
|
||||
# architecture. The checksum list is copied from the immutable upstream release
|
||||
# and committed so a rebuild cannot silently accept changed release bytes.
|
||||
COPY --chown=node:node bot_bottle/contrib/codex/codex-package_SHA256SUMS /tmp/codex-package_SHA256SUMS
|
||||
RUN case "$(dpkg --print-architecture)" in \
|
||||
amd64) codex_target=x86_64-unknown-linux-musl ;; \
|
||||
arm64) codex_target=aarch64-unknown-linux-musl ;; \
|
||||
*) echo "unsupported Codex architecture: $(dpkg --print-architecture)" >&2; exit 1 ;; \
|
||||
esac \
|
||||
&& codex_asset="codex-package-${codex_target}.tar.gz" \
|
||||
&& codex_sha256="$(awk -v asset="${codex_asset}" '$2 == asset { print $1 }' /tmp/codex-package_SHA256SUMS)" \
|
||||
&& test -n "${codex_sha256}" \
|
||||
&& curl -fsSL \
|
||||
"https://github.com/openai/codex/releases/download/rust-v${CODEX_VERSION}/${codex_asset}" \
|
||||
-o "/tmp/${codex_asset}" \
|
||||
&& echo "${codex_sha256} /tmp/${codex_asset}" | sha256sum -c - \
|
||||
&& codex_release="/home/node/.codex/packages/standalone/releases/${CODEX_VERSION}-${codex_target}" \
|
||||
&& mkdir -p "${codex_release}" /home/node/.local/bin \
|
||||
&& tar -xzf "/tmp/${codex_asset}" -C "${codex_release}" \
|
||||
&& ln -s bin/codex "${codex_release}/codex" \
|
||||
&& ln -s "${codex_release}" /home/node/.codex/packages/standalone/current \
|
||||
&& ln -s /home/node/.codex/packages/standalone/current/bin/codex /home/node/.local/bin/codex \
|
||||
&& rm "/tmp/${codex_asset}" \
|
||||
&& test "$(codex --version)" = "codex-cli ${CODEX_VERSION}"
|
||||
|
||||
CMD ["codex"]
|
||||
|
||||
@@ -0,0 +1,2 @@
|
||||
54f79a05aba6f9abf8ef988abcae8bf2fcefba20beb549b4ff2b3acdb2cb6f54 codex-package-aarch64-unknown-linux-musl.tar.gz
|
||||
71a28d362c96ac9829bf8203a2c71be451aeb726adb843167fdaf0eae8fe7dd9 codex-package-x86_64-unknown-linux-musl.tar.gz
|
||||
@@ -2,9 +2,18 @@
|
||||
#
|
||||
# Node LTS, git/network tooling, and the Pi coding-agent CLI installed globally.
|
||||
|
||||
FROM node:22-trixie-slim
|
||||
ARG NODE_BASE_IMAGE
|
||||
FROM ${NODE_BASE_IMAGE}
|
||||
|
||||
RUN apt-get update \
|
||||
ARG DEBIAN_SNAPSHOT=20260724T000000Z
|
||||
RUN sed -i \
|
||||
-e "s|http://deb.debian.org/debian-security|http://snapshot.debian.org/archive/debian-security/${DEBIAN_SNAPSHOT}|g" \
|
||||
-e "s|https://deb.debian.org/debian-security|http://snapshot.debian.org/archive/debian-security/${DEBIAN_SNAPSHOT}|g" \
|
||||
-e "s|http://deb.debian.org/debian|http://snapshot.debian.org/archive/debian/${DEBIAN_SNAPSHOT}|g" \
|
||||
-e "s|https://deb.debian.org/debian|http://snapshot.debian.org/archive/debian/${DEBIAN_SNAPSHOT}|g" \
|
||||
/etc/apt/sources.list.d/debian.sources
|
||||
|
||||
RUN apt-get -o Acquire::Check-Valid-Until=false update \
|
||||
&& apt-get install -y --no-install-recommends \
|
||||
git \
|
||||
ca-certificates \
|
||||
@@ -15,13 +24,10 @@ RUN apt-get update \
|
||||
&& ln -s /usr/bin/fdfind /usr/local/bin/fd \
|
||||
&& rm -rf /var/lib/apt/lists/*
|
||||
|
||||
RUN apt-get update \
|
||||
RUN apt-get -o Acquire::Check-Valid-Until=false update \
|
||||
&& apt-get install -y --no-install-recommends python3 python3-pip python3-venv \
|
||||
&& rm -rf /var/lib/apt/lists/*
|
||||
|
||||
RUN npm install -g --ignore-scripts --no-fund --no-audit @earendil-works/pi-coding-agent \
|
||||
&& npm cache clean --force
|
||||
|
||||
RUN install -d -o node -g node -m 755 /home/node/.config /home/node/.config/git \
|
||||
&& mkdir -p /home/node/.pi/agent \
|
||||
/home/node/.pi/context-mode/sessions \
|
||||
@@ -34,10 +40,15 @@ RUN install -d -o node -g node -m 755 /home/node/.config /home/node/.config/git
|
||||
USER node
|
||||
WORKDIR /home/node
|
||||
|
||||
RUN pi install npm:@harms-haus/pi-cwd \
|
||||
&& pi install npm:pi-web-access \
|
||||
&& pi install npm:context-mode \
|
||||
&& pi install npm:pi-subagents \
|
||||
&& pi install npm:pi-mcp-adapter
|
||||
# Pi discovers npm packages from its agent directory. Installing the CLI and
|
||||
# extensions together from the committed lock makes all direct and transitive
|
||||
# package versions deterministic, with npm integrity verification.
|
||||
COPY --chown=node:node bot_bottle/contrib/pi/package.json \
|
||||
bot_bottle/contrib/pi/package-lock.json /home/node/.pi/agent/
|
||||
RUN cd /home/node/.pi/agent \
|
||||
&& npm ci --omit=dev --no-fund --no-audit \
|
||||
&& npm cache clean --force
|
||||
|
||||
ENV PATH="/home/node/.pi/agent/node_modules/.bin:${PATH}"
|
||||
|
||||
CMD ["pi"]
|
||||
|
||||
Generated
+5448
File diff suppressed because it is too large
Load Diff
@@ -0,0 +1,15 @@
|
||||
{
|
||||
"name": "bot-bottle-pi-image",
|
||||
"private": true,
|
||||
"dependencies": {
|
||||
"@earendil-works/pi-coding-agent": "0.81.1",
|
||||
"@earendil-works/pi-agent-core": "0.81.1",
|
||||
"@earendil-works/pi-ai": "0.81.1",
|
||||
"@earendil-works/pi-tui": "0.81.1",
|
||||
"@harms-haus/pi-cwd": "1.0.0",
|
||||
"context-mode": "1.0.169",
|
||||
"pi-mcp-adapter": "2.11.0",
|
||||
"pi-subagents": "0.35.1",
|
||||
"pi-web-access": "0.13.0"
|
||||
}
|
||||
}
|
||||
@@ -11,7 +11,7 @@ from __future__ import annotations
|
||||
from dataclasses import dataclass
|
||||
from pathlib import Path
|
||||
|
||||
from ..gateway.egress.addon_core import Route
|
||||
from ..gateway.egress.types import Route
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
@@ -19,7 +19,7 @@ class EgressRoute(Route):
|
||||
"""Host-side extension of the addon's `Route`.
|
||||
|
||||
Inherits `host`, `matches`, `auth_scheme`, and `token_env`
|
||||
from `egress_addon_core.Route` — those are the fields that cross the
|
||||
from the gateway's wire `Route` — those are the fields that cross the
|
||||
YAML wire into the gateway. The fields below are host-only and
|
||||
are never serialised to the addon.
|
||||
|
||||
|
||||
@@ -14,8 +14,8 @@ import secrets
|
||||
from pathlib import Path
|
||||
from typing import TYPE_CHECKING
|
||||
|
||||
from ..gateway.egress.addon_core import (
|
||||
ON_MATCH_REDACT,
|
||||
from ..gateway.egress.dlp_config import ON_MATCH_REDACT
|
||||
from ..gateway.egress.types import (
|
||||
HeaderMatch as CoreHeaderMatch,
|
||||
MatchEntry as CoreMatchEntry,
|
||||
PathMatch as CorePathMatch,
|
||||
|
||||
@@ -136,10 +136,18 @@ def _pump(name: str, stream: IO[bytes]) -> None:
|
||||
"""Read lines from `stream`, prefix with `[name]`, write to
|
||||
stdout. Runs in its own thread per child; daemon=True so a
|
||||
blocked read doesn't keep the process alive after main exits."""
|
||||
for raw in iter(stream.readline, b""):
|
||||
line = raw.decode("utf-8", errors="replace").rstrip("\n")
|
||||
sys.stdout.write(f"[{name}] {line}\n")
|
||||
sys.stdout.flush()
|
||||
try:
|
||||
for raw in iter(stream.readline, b""):
|
||||
line = raw.decode("utf-8", errors="replace").rstrip("\n")
|
||||
sys.stdout.write(f"[{name}] {line}\n")
|
||||
sys.stdout.flush()
|
||||
except (OSError, ValueError) as exc:
|
||||
# The manager closes a dead child's pipe after wait() and before a
|
||||
# restart. A pump can be between readline calls at that exact moment;
|
||||
# closed-stream errors are normal completion, not uncaught thread
|
||||
# failures. Preserve genuinely unexpected I/O diagnostics.
|
||||
if not stream.closed:
|
||||
_log(f"{name} output pump stopped: {type(exc).__name__}: {exc}")
|
||||
|
||||
|
||||
def _spawn(spec: _DaemonSpec) -> subprocess.Popen[bytes]:
|
||||
|
||||
@@ -0,0 +1,137 @@
|
||||
"""Shared resource boundaries for gateway stdlib HTTP services."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import http.server
|
||||
import io
|
||||
import socket
|
||||
import threading
|
||||
import time
|
||||
from dataclasses import dataclass
|
||||
from typing import Any, Protocol
|
||||
|
||||
|
||||
class Readable(Protocol):
|
||||
def read(self, size: int = -1, /) -> bytes: ...
|
||||
|
||||
|
||||
class Writable(Protocol):
|
||||
def write(self, data: bytes, /) -> object: ...
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class BodyReadError(Exception):
|
||||
status: int
|
||||
message: str
|
||||
|
||||
|
||||
def read_declared_body(
|
||||
stream: Readable,
|
||||
connection: socket.socket,
|
||||
raw_length: str | None,
|
||||
*,
|
||||
maximum: int,
|
||||
timeout_seconds: float,
|
||||
require_length: bool,
|
||||
) -> bytes:
|
||||
"""Validate and read exactly one declared body under a read deadline."""
|
||||
output = io.BytesIO()
|
||||
copy_declared_body(
|
||||
stream, output, connection, raw_length, maximum=maximum,
|
||||
timeout_seconds=timeout_seconds, require_length=require_length,
|
||||
)
|
||||
return output.getvalue()
|
||||
|
||||
|
||||
def copy_declared_body(
|
||||
stream: Readable,
|
||||
output: Writable,
|
||||
connection: socket.socket,
|
||||
raw_length: str | None,
|
||||
*,
|
||||
maximum: int,
|
||||
timeout_seconds: float,
|
||||
require_length: bool,
|
||||
) -> int:
|
||||
"""Copy one declared body to a sink without retaining it in memory."""
|
||||
if raw_length is None:
|
||||
if require_length:
|
||||
raise BodyReadError(411, "Content-Length required")
|
||||
raw_length = "0"
|
||||
try:
|
||||
length = int(raw_length)
|
||||
except ValueError as exc:
|
||||
raise BodyReadError(400, "invalid Content-Length") from exc
|
||||
if length < 0:
|
||||
raise BodyReadError(400, "invalid Content-Length")
|
||||
if length > maximum:
|
||||
raise BodyReadError(413, "request body too large")
|
||||
previous_timeout = connection.gettimeout()
|
||||
deadline = time.monotonic() + timeout_seconds
|
||||
remaining = length
|
||||
try:
|
||||
while remaining:
|
||||
timeout = deadline - time.monotonic()
|
||||
if timeout <= 0:
|
||||
raise BodyReadError(408, "request body read timed out")
|
||||
connection.settimeout(timeout)
|
||||
chunk = stream.read(min(remaining, 64 * 1024))
|
||||
if not chunk:
|
||||
raise BodyReadError(400, "incomplete request body")
|
||||
output.write(chunk)
|
||||
remaining -= len(chunk)
|
||||
except TimeoutError as exc:
|
||||
raise BodyReadError(408, "request body read timed out") from exc
|
||||
finally:
|
||||
connection.settimeout(previous_timeout)
|
||||
return length
|
||||
|
||||
|
||||
class BoundedThreadingHTTPServer(http.server.ThreadingHTTPServer):
|
||||
"""ThreadingHTTPServer with a hard cap on in-flight request threads."""
|
||||
|
||||
daemon_threads = True
|
||||
|
||||
def __init__( # pylint: disable=consider-using-with
|
||||
self, *args, max_workers: int = 32, **kwargs, # type: ignore[no-untyped-def]
|
||||
):
|
||||
if max_workers < 1:
|
||||
raise ValueError("max_workers must be positive")
|
||||
self._request_slots = threading.BoundedSemaphore(max_workers)
|
||||
super().__init__(*args, **kwargs)
|
||||
|
||||
def process_request(
|
||||
self, request: Any, client_address: Any,
|
||||
) -> None:
|
||||
if not self._request_slots.acquire( # pylint: disable=consider-using-with
|
||||
blocking=False,
|
||||
):
|
||||
try:
|
||||
request.sendall(
|
||||
b"HTTP/1.1 503 Service Unavailable\r\n"
|
||||
b"Content-Length: 0\r\nConnection: close\r\n\r\n"
|
||||
)
|
||||
finally:
|
||||
self.shutdown_request(request)
|
||||
return
|
||||
try:
|
||||
super().process_request(request, client_address)
|
||||
except BaseException:
|
||||
self._request_slots.release()
|
||||
raise
|
||||
|
||||
def process_request_thread(
|
||||
self, request: Any, client_address: Any,
|
||||
) -> None:
|
||||
try:
|
||||
super().process_request_thread(request, client_address)
|
||||
finally:
|
||||
self._request_slots.release()
|
||||
|
||||
|
||||
__all__ = [
|
||||
"BodyReadError",
|
||||
"BoundedThreadingHTTPServer",
|
||||
"copy_declared_body",
|
||||
"read_declared_body",
|
||||
]
|
||||
@@ -16,29 +16,35 @@ import typing
|
||||
from mitmproxy import http # type: ignore[import-not-found] # pylint: disable=import-error
|
||||
|
||||
from bot_bottle.constants import IDENTITY_HEADER
|
||||
from bot_bottle.gateway.egress.dlp_detectors import redact_tokens, strip_crlf
|
||||
from bot_bottle.gateway.egress.addon_core import (
|
||||
LOG_BLOCKS,
|
||||
LOG_FULL,
|
||||
from bot_bottle.gateway.egress.dlp_detectors import redact_tokens
|
||||
from bot_bottle.gateway.egress.dlp_config import (
|
||||
DEFAULT_OUTBOUND_ON_MATCH,
|
||||
ON_MATCH_BLOCK,
|
||||
ON_MATCH_REDACT,
|
||||
)
|
||||
from bot_bottle.gateway.egress.context import resolve_client_context
|
||||
from bot_bottle.gateway.egress.dlp import (
|
||||
build_inbound_scan_text,
|
||||
build_token_allow_payload,
|
||||
scan_inbound,
|
||||
scan_outbound,
|
||||
)
|
||||
from bot_bottle.gateway.egress.outbound_pipeline import redact_request, scan_request
|
||||
from bot_bottle.gateway.egress.matching import (
|
||||
decide,
|
||||
match_route,
|
||||
)
|
||||
from bot_bottle.gateway.egress.request_pipeline import (
|
||||
evaluate_route_policy,
|
||||
git_block_reason,
|
||||
)
|
||||
from bot_bottle.gateway.egress.schema import route_to_yaml_dict
|
||||
from bot_bottle.gateway.egress.types import (
|
||||
LOG_BLOCKS,
|
||||
LOG_FULL,
|
||||
Config,
|
||||
Route,
|
||||
ScanResult,
|
||||
build_inbound_scan_text,
|
||||
build_outbound_scan_text,
|
||||
build_token_allow_payload,
|
||||
decide,
|
||||
decide_git_fetch,
|
||||
is_git_fetch_request,
|
||||
is_git_push_request,
|
||||
match_route,
|
||||
resolve_client_context,
|
||||
outbound_scan_headers,
|
||||
route_to_yaml_dict,
|
||||
scan_inbound,
|
||||
scan_outbound,
|
||||
)
|
||||
from bot_bottle.gateway.policy_resolver import PolicyResolveError, PolicyResolver
|
||||
from bot_bottle.supervisor.types import (
|
||||
@@ -383,19 +389,9 @@ class EgressAddon:
|
||||
self._passthrough_conns.discard(conn_id)
|
||||
|
||||
async def request(self, flow: http.HTTPFlow) -> None:
|
||||
config, slug, env = self._request_context(flow)
|
||||
request_path, _, query = flow.request.path.partition("?")
|
||||
|
||||
# Reuse the context stashed by http_connect for HTTPS flows (one
|
||||
# orchestrator round-trip per connection). Plain-HTTP flows have no
|
||||
# prior CONNECT stash, so resolve now and stash for response/websocket.
|
||||
meta = getattr(flow, "metadata", None)
|
||||
if isinstance(meta, dict) and _FLOW_CTX_KEY in meta:
|
||||
config, slug, env = meta[_FLOW_CTX_KEY]
|
||||
self._request_token(flow) # strip identity headers; token already resolved
|
||||
else:
|
||||
config, slug, env = self._resolve_flow(flow)
|
||||
self._stash_flow_ctx(flow, config, slug, env)
|
||||
|
||||
# Introspection ("_egress.local/allowlist") reports the calling bottle's
|
||||
# own resolved routes — served after resolution so it reflects this
|
||||
# bottle's policy, not a stale global.
|
||||
@@ -416,56 +412,66 @@ class EgressAddon:
|
||||
# the path/query the git checks below rely on.
|
||||
request_path, _, query = flow.request.path.partition("?")
|
||||
|
||||
if is_git_push_request(request_path, query):
|
||||
self._block(
|
||||
flow,
|
||||
"egress: git push over HTTPS is not supported; "
|
||||
"use the bottle.git SSH path (gitleaks-scanned by "
|
||||
"git-gate's pre-receive hook).",
|
||||
ctx=self._req_ctx(flow),
|
||||
)
|
||||
if not self._allow_git_request(flow, config, request_path, query):
|
||||
return
|
||||
|
||||
if is_git_fetch_request(request_path, query):
|
||||
git_decision = decide_git_fetch(
|
||||
config.routes, flow.request.pretty_host,
|
||||
)
|
||||
if git_decision.action == "block":
|
||||
self._block(
|
||||
flow,
|
||||
git_decision.reason,
|
||||
ctx=self._req_ctx(flow),
|
||||
)
|
||||
return
|
||||
self._apply_route_policy(flow, config, route, request_path, env)
|
||||
|
||||
def _request_context(
|
||||
self, flow: http.HTTPFlow,
|
||||
) -> tuple[Config, str, "typing.Mapping[str, str]"]:
|
||||
"""Resolve one bottle context, reusing the HTTPS CONNECT snapshot."""
|
||||
meta = getattr(flow, "metadata", None)
|
||||
if isinstance(meta, dict) and _FLOW_CTX_KEY in meta:
|
||||
config, slug, env = meta[_FLOW_CTX_KEY]
|
||||
self._request_token(flow)
|
||||
return config, slug, env
|
||||
config, slug, env = self._resolve_flow(flow)
|
||||
self._stash_flow_ctx(flow, config, slug, env)
|
||||
return config, slug, env
|
||||
|
||||
def _allow_git_request(
|
||||
self, flow: http.HTTPFlow, config: Config,
|
||||
request_path: str, query: str,
|
||||
) -> bool:
|
||||
"""Apply the HTTPS Git push/fetch boundary before general routing."""
|
||||
reason = git_block_reason(
|
||||
config.routes, flow.request.pretty_host, request_path, query,
|
||||
)
|
||||
if not reason:
|
||||
return True
|
||||
self._block(flow, reason, ctx=self._req_ctx(flow))
|
||||
return False
|
||||
|
||||
def _apply_route_policy(
|
||||
self, flow: http.HTTPFlow, config: Config, route: Route | None,
|
||||
request_path: str, env: "typing.Mapping[str, str]",
|
||||
) -> None:
|
||||
"""Strip agent auth, evaluate the route, then inject gateway auth."""
|
||||
# Strip agent-set Authorization after DLP scan so smuggled tokens
|
||||
# are caught above; the route may inject gateway-owned auth below.
|
||||
# Routes with preserve_auth=True pass the header through as-is so the
|
||||
# agent's own credentials (e.g. registry bearer tokens) reach the upstream.
|
||||
if route is None or not route.preserve_auth:
|
||||
result = evaluate_route_policy(
|
||||
config,
|
||||
route,
|
||||
host=flow.request.pretty_host,
|
||||
request_path=request_path,
|
||||
method=flow.request.method,
|
||||
headers=dict(flow.request.headers),
|
||||
env=env,
|
||||
)
|
||||
if result.strip_authorization:
|
||||
flow.request.headers.pop("authorization", None)
|
||||
|
||||
# Build headers mapping for match evaluation
|
||||
req_headers = {k.lower(): v for k, v in flow.request.headers.items()}
|
||||
|
||||
decision = decide(
|
||||
config.routes,
|
||||
flow.request.pretty_host,
|
||||
request_path,
|
||||
env,
|
||||
request_method=flow.request.method,
|
||||
request_headers=req_headers,
|
||||
deny_reason=config.deny_reason,
|
||||
)
|
||||
|
||||
if decision.action == "block":
|
||||
self._block(flow, decision.reason, ctx=self._req_ctx(flow))
|
||||
if result.block_reason:
|
||||
self._block(flow, result.block_reason, ctx=self._req_ctx(flow))
|
||||
return
|
||||
|
||||
if decision.inject_authorization is not None:
|
||||
flow.request.headers["authorization"] = decision.inject_authorization
|
||||
if result.inject_authorization is not None:
|
||||
flow.request.headers["authorization"] = result.inject_authorization
|
||||
|
||||
if config.log >= LOG_FULL:
|
||||
if result.log_request:
|
||||
self._log_request(flow, env)
|
||||
|
||||
def _block_dlp(self, flow: http.HTTPFlow, result: ScanResult) -> None:
|
||||
@@ -489,20 +495,12 @@ class EgressAddon:
|
||||
Loops so the supervise policy can re-scan after each approval — a
|
||||
second, un-approved token in the same request is still caught."""
|
||||
while True:
|
||||
request_path, _, query = flow.request.path.partition("?")
|
||||
body = flow.request.get_text(strict=False) or ""
|
||||
headers = outbound_scan_headers(route, dict(flow.request.headers))
|
||||
scan_text = build_outbound_scan_text(
|
||||
flow.request.pretty_host, request_path, query, headers, body,
|
||||
)
|
||||
# CRLF is scanned only over the request line + headers, never the
|
||||
# body (see scan_outbound) — a body is not an injection vector.
|
||||
crlf_text = build_outbound_scan_text(
|
||||
flow.request.pretty_host, request_path, query, headers, "",
|
||||
)
|
||||
result = scan_outbound(
|
||||
route, scan_text, env,
|
||||
safe_tokens=self._safe_tokens_for(slug), crlf_text=crlf_text,
|
||||
request_path, _, _ = flow.request.path.partition("?")
|
||||
result = scan_request(
|
||||
flow.request,
|
||||
route,
|
||||
env,
|
||||
safe_tokens=self._safe_tokens_for(slug),
|
||||
)
|
||||
if result is None or result.severity != "block":
|
||||
return True
|
||||
@@ -512,7 +510,7 @@ class EgressAddon:
|
||||
# redact scrubs every detection (tokens and structural CRLF) and
|
||||
# forwards; it fails closed only if a match survives the scrub.
|
||||
if policy == ON_MATCH_REDACT:
|
||||
if self._redact_outbound(flow, route, env):
|
||||
if redact_request(flow.request, route, env):
|
||||
if self._flow_log(flow) >= LOG_BLOCKS:
|
||||
sys.stderr.write(json.dumps({
|
||||
"event": "egress_redacted",
|
||||
@@ -545,41 +543,6 @@ class EgressAddon:
|
||||
return False # _supervise_token_block wrote the 403 response
|
||||
# loop: the approved value is now in safe_tokens; re-scan.
|
||||
|
||||
def _redact_outbound(
|
||||
self, flow: http.HTTPFlow, route: Route, env: "typing.Mapping[str, str]",
|
||||
) -> bool:
|
||||
"""Scrub detected tokens (and CRLF injection sequences) from the mutable
|
||||
request surfaces (body, headers, path/query) and re-scan. `env` is the
|
||||
per-bottle env overlay. Returns True if the request is now clean; False
|
||||
if a block-severity match remains on a surface redaction cannot rewrite
|
||||
(the hostname) so the caller fails closed."""
|
||||
body = flow.request.get_text(strict=False)
|
||||
if body:
|
||||
redacted_body = redact_tokens(body, env=env)
|
||||
if redacted_body != body:
|
||||
flow.request.text = redacted_body
|
||||
for name, value in list(flow.request.headers.items()):
|
||||
if name.lower() == "host":
|
||||
continue # routing-critical; never a legitimate token
|
||||
redacted = strip_crlf(redact_tokens(value, env=env))
|
||||
if redacted != value:
|
||||
flow.request.headers[name] = redacted
|
||||
redacted_path = strip_crlf(redact_tokens(flow.request.path, env=env))
|
||||
if redacted_path != flow.request.path:
|
||||
flow.request.path = redacted_path
|
||||
|
||||
request_path, _, query = flow.request.path.partition("?")
|
||||
new_body = flow.request.get_text(strict=False) or ""
|
||||
headers = outbound_scan_headers(route, dict(flow.request.headers))
|
||||
scan_text = build_outbound_scan_text(
|
||||
flow.request.pretty_host, request_path, query, headers, new_body,
|
||||
)
|
||||
crlf_text = build_outbound_scan_text(
|
||||
flow.request.pretty_host, request_path, query, headers, "",
|
||||
)
|
||||
result = scan_outbound(route, scan_text, env, crlf_text=crlf_text)
|
||||
return result is None or result.severity != "block"
|
||||
|
||||
async def _supervise_token_block(
|
||||
self,
|
||||
flow: http.HTTPFlow,
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
@@ -0,0 +1,77 @@
|
||||
"""Fail-closed resolution of a client's policy and egress credentials."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import typing
|
||||
|
||||
from ...log import debug
|
||||
from .types import Config
|
||||
|
||||
|
||||
DENY_UNATTRIBUTED = (
|
||||
"egress: this request was not attributed to any bottle, so no egress policy "
|
||||
"applies and every host is denied. Either the bottle's registry row is "
|
||||
"missing/ambiguous (torn down, or another bottle claimed its source IP), or "
|
||||
"the request carried no matching identity token — check that the caller's "
|
||||
"proxy URL includes it. This is not an allowlist problem."
|
||||
)
|
||||
DENY_UNPARSEABLE = (
|
||||
"egress: this bottle's egress policy could not be parsed, so it is being "
|
||||
"treated as deny-all. Fix the bottle's egress.routes; every host is denied "
|
||||
"until it loads."
|
||||
)
|
||||
DENY_RESOLVER_ERROR = (
|
||||
"egress: the orchestrator could not be reached to resolve this bottle's "
|
||||
"egress policy, so every host is denied (fail-closed). Check that the "
|
||||
"control plane is up; this is not an allowlist problem."
|
||||
)
|
||||
|
||||
|
||||
class PolicyResolverLike(typing.Protocol):
|
||||
def resolve(self, source_ip: str, identity_token: str = ...) -> str | None: ...
|
||||
|
||||
|
||||
class ContextResolverLike(typing.Protocol):
|
||||
def resolve_policy_and_bottle_id(
|
||||
self, source_ip: str, identity_token: str = ...,
|
||||
) -> tuple[str | None, str | None, dict[str, str]]: ...
|
||||
|
||||
|
||||
def _config_from_policy(policy: str | None) -> Config:
|
||||
# Local import keeps schema parsing independent of resolver protocols.
|
||||
from .schema import load_config
|
||||
if not policy:
|
||||
return Config(routes=(), deny_reason=DENY_UNATTRIBUTED)
|
||||
try:
|
||||
return load_config(policy)
|
||||
except ValueError:
|
||||
return Config(routes=(), deny_reason=DENY_UNPARSEABLE)
|
||||
|
||||
|
||||
def resolve_client_config(
|
||||
resolver: PolicyResolverLike, client_ip: str, identity_token: str = "",
|
||||
) -> Config:
|
||||
try:
|
||||
policy = resolver.resolve(client_ip, identity_token)
|
||||
except Exception as exc: # noqa: BLE001 - a policy lookup failure must deny
|
||||
debug(
|
||||
"egress policy resolution failed; applying deny-all",
|
||||
context={"error_type": type(exc).__name__},
|
||||
)
|
||||
return Config(routes=(), deny_reason=DENY_RESOLVER_ERROR)
|
||||
return _config_from_policy(policy)
|
||||
|
||||
|
||||
def resolve_client_context(
|
||||
resolver: ContextResolverLike, client_ip: str, identity_token: str = "",
|
||||
) -> tuple[Config, str, dict[str, str]]:
|
||||
try:
|
||||
policy, bottle_id, tokens = resolver.resolve_policy_and_bottle_id(
|
||||
client_ip, identity_token)
|
||||
except Exception as exc: # noqa: BLE001 - a policy lookup failure must deny
|
||||
debug(
|
||||
"egress context resolution failed; applying deny-all",
|
||||
context={"error_type": type(exc).__name__},
|
||||
)
|
||||
return Config(routes=(), deny_reason=DENY_RESOLVER_ERROR), "", {}
|
||||
return _config_from_policy(policy), (bottle_id or ""), tokens
|
||||
@@ -0,0 +1,99 @@
|
||||
"""DLP scan dispatch and safe proposal rendering for egress requests."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import typing
|
||||
|
||||
from .types import Route, ScanResult
|
||||
|
||||
|
||||
def build_outbound_scan_text(host: str, path: str, query: str,
|
||||
headers: typing.Mapping[str, str], body: str) -> str:
|
||||
parts = [host, path]
|
||||
if query:
|
||||
parts.append(query)
|
||||
parts.extend(f"{name}: {value}" for name, value in headers.items())
|
||||
if body:
|
||||
parts.append(body)
|
||||
return "\n".join(parts)
|
||||
|
||||
|
||||
def outbound_scan_headers(route: Route, headers: typing.Mapping[str, str]) -> dict[str, str]:
|
||||
"""Drop agent Authorization when the route injects gateway-owned auth."""
|
||||
skip_auth = bool(route.auth_scheme and route.token_env)
|
||||
return {name: value for name, value in headers.items()
|
||||
if not (skip_auth and name.lower() == "authorization")}
|
||||
|
||||
|
||||
def build_inbound_scan_text(headers: typing.Mapping[str, str], body: str) -> str:
|
||||
parts = [f"{name}: {value}" for name, value in headers.items()]
|
||||
if body:
|
||||
parts.append(body)
|
||||
return "\n".join(parts)
|
||||
|
||||
|
||||
def _enabled(configured: tuple[str, ...] | None, name: str) -> bool:
|
||||
return configured is None or name in configured
|
||||
|
||||
|
||||
def scan_outbound(route: Route, body: str | bytes, environ: typing.Mapping[str, str], *,
|
||||
safe_tokens: typing.AbstractSet[str] | None = None,
|
||||
crlf_text: str | None = None) -> ScanResult | None:
|
||||
if not route.inspect:
|
||||
return None
|
||||
try:
|
||||
from dlp_detectors import ( # type: ignore[import-not-found]
|
||||
scan_crlf_injection, scan_entropy, scan_known_secrets, scan_token_patterns)
|
||||
except ImportError: # pragma: no cover - gateway's flat module path
|
||||
from .dlp_detectors import (
|
||||
scan_crlf_injection, scan_entropy, scan_known_secrets, scan_token_patterns)
|
||||
if isinstance(body, bytes):
|
||||
try:
|
||||
text = body.decode("utf-8")
|
||||
except UnicodeDecodeError:
|
||||
text = body.decode("latin-1")
|
||||
else:
|
||||
text = body
|
||||
result = scan_crlf_injection(text if crlf_text is None else crlf_text)
|
||||
if result is not None:
|
||||
return result
|
||||
if _enabled(route.outbound_detectors, "token_patterns"):
|
||||
result = scan_token_patterns(text, location="body", safe_tokens=safe_tokens)
|
||||
if result is not None:
|
||||
return result
|
||||
if _enabled(route.outbound_detectors, "known_secrets"):
|
||||
extra = tuple(prefix for prefix in environ.get(
|
||||
"BOT_BOTTLE_SENSITIVE_PREFIXES", "").split(",") if prefix)
|
||||
result = scan_known_secrets(text, location="body", env=environ,
|
||||
sensitive_prefixes=("EGRESS_TOKEN_",) + extra,
|
||||
safe_tokens=safe_tokens)
|
||||
if result is not None:
|
||||
return result
|
||||
if route.outbound_detectors is not None and "entropy" in route.outbound_detectors:
|
||||
return scan_entropy(text, location="body")
|
||||
return None
|
||||
|
||||
|
||||
def build_token_allow_payload(host: str, method: str, path: str, result: ScanResult) -> str:
|
||||
"""Render redacted operator context; the raw matched secret is excluded."""
|
||||
lines = [
|
||||
"egress blocked an outbound request carrying a detected token",
|
||||
f"host: {host}", f"method: {method}", f"path: {path}",
|
||||
f"detector: {result.reason}",
|
||||
]
|
||||
if result.context:
|
||||
lines.append(f"context: {result.context}")
|
||||
return "\n".join(lines) + "\n"
|
||||
|
||||
|
||||
def scan_inbound(route: Route, body: str | bytes) -> ScanResult | None:
|
||||
if not route.inspect:
|
||||
return None
|
||||
try:
|
||||
from dlp_detectors import scan_naive_injection # type: ignore[import-not-found]
|
||||
except ImportError: # pragma: no cover - gateway's flat module path
|
||||
from .dlp_detectors import scan_naive_injection
|
||||
text = body if isinstance(body, str) else body.decode("utf-8", errors="replace")
|
||||
if _enabled(route.inbound_detectors, "naive_injection_detection"):
|
||||
return scan_naive_injection(text)
|
||||
return None
|
||||
@@ -19,7 +19,7 @@ from math import log2
|
||||
from collections import Counter
|
||||
from urllib.parse import quote as url_quote
|
||||
|
||||
from .addon_core import ScanResult
|
||||
from .types import ScanResult
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
@@ -0,0 +1,112 @@
|
||||
"""Route matching and request-policy decisions for the egress gateway."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import typing
|
||||
|
||||
from .types import Decision, MatchEntry, PathMatch, Route
|
||||
|
||||
|
||||
def _path_matches(pm: PathMatch, request_path: str) -> bool:
|
||||
if pm.type == "exact":
|
||||
return request_path == pm.value
|
||||
if pm.type == "prefix":
|
||||
if request_path == pm.value:
|
||||
return True
|
||||
if not pm.value.endswith("/"):
|
||||
return request_path.startswith(pm.value + "/")
|
||||
return request_path.startswith(pm.value)
|
||||
return (
|
||||
pm.type == "regex"
|
||||
and pm.compiled is not None
|
||||
and pm.compiled.search(request_path) is not None
|
||||
)
|
||||
|
||||
|
||||
def _entry_matches(
|
||||
entry: MatchEntry, request_path: str, request_method: str,
|
||||
request_headers: typing.Mapping[str, str],
|
||||
) -> bool:
|
||||
if entry.paths and not any(_path_matches(pm, request_path) for pm in entry.paths):
|
||||
return False
|
||||
if entry.methods and request_method.upper() not in entry.methods:
|
||||
return False
|
||||
for match in entry.headers:
|
||||
value = request_headers.get(match.name.lower())
|
||||
if value is None:
|
||||
return False
|
||||
if match.type == "exact" and value != match.value:
|
||||
return False
|
||||
if match.type == "regex" and (
|
||||
match.compiled is None or match.compiled.search(value) is None
|
||||
):
|
||||
return False
|
||||
return True
|
||||
|
||||
|
||||
def evaluate_matches(
|
||||
route: Route, request_path: str, request_method: str = "GET",
|
||||
request_headers: typing.Mapping[str, str] | None = None,
|
||||
) -> bool:
|
||||
"""Return whether a request satisfies a route's optional match entries."""
|
||||
if not route.matches:
|
||||
return True
|
||||
return any(_entry_matches(entry, request_path, request_method, request_headers or {})
|
||||
for entry in route.matches)
|
||||
|
||||
|
||||
def is_git_push_request(path: str, query: str) -> bool:
|
||||
return path.endswith("/git-receive-pack") or (
|
||||
path.endswith("/info/refs") and any(
|
||||
pair.partition("=") == ("service", "=", "git-receive-pack")
|
||||
for pair in query.split("&")
|
||||
)
|
||||
)
|
||||
|
||||
|
||||
def is_git_fetch_request(path: str, query: str) -> bool:
|
||||
return path.endswith("/git-upload-pack") or (
|
||||
path.endswith("/info/refs") and any(
|
||||
pair.partition("=") == ("service", "=", "git-upload-pack")
|
||||
for pair in query.split("&")
|
||||
)
|
||||
)
|
||||
|
||||
|
||||
def match_route(routes: typing.Sequence[Route], request_host: str) -> Route | None:
|
||||
target = request_host.lower()
|
||||
return next((route for route in routes if route.host.lower() == target), None)
|
||||
|
||||
|
||||
def decide(
|
||||
routes: typing.Sequence[Route], request_host: str, request_path: str,
|
||||
environ: typing.Mapping[str, str], *, request_method: str = "GET",
|
||||
request_headers: typing.Mapping[str, str] | None = None, deny_reason: str = "",
|
||||
) -> Decision:
|
||||
route = match_route(routes, request_host)
|
||||
if route is None:
|
||||
return Decision("block", deny_reason or (
|
||||
f"egress: host {request_host!r} is not in the bottle's egress.routes "
|
||||
"allowlist. Declare a route for it or remove the request."))
|
||||
if not evaluate_matches(route, request_path, request_method, request_headers):
|
||||
return Decision("block", (
|
||||
f"egress: request {request_method} {request_path!r} does not match any "
|
||||
f"entry in matches for {route.host!r}"))
|
||||
if route.auth_scheme and route.token_env:
|
||||
token = environ.get(route.token_env, "")
|
||||
if not token:
|
||||
return Decision("block", (
|
||||
f"egress: route for {route.host!r} declared auth but env var "
|
||||
f"{route.token_env!r} is unset"))
|
||||
return Decision("forward", inject_authorization=f"{route.auth_scheme} {token}")
|
||||
return Decision("forward")
|
||||
|
||||
|
||||
def decide_git_fetch(routes: typing.Sequence[Route], request_host: str) -> Decision:
|
||||
route = match_route(routes, request_host)
|
||||
if route is not None and route.git_fetch:
|
||||
return Decision("forward")
|
||||
return Decision("block", (
|
||||
"egress: git fetch/clone over HTTPS is not allowed by default; use git-gate "
|
||||
"for declared repos or set egress.routes[].git.fetch=true for explicit "
|
||||
"read-only HTTPS Git access."))
|
||||
@@ -0,0 +1,83 @@
|
||||
"""Outbound DLP request scanning and redaction for the egress pipeline."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
from typing import ItemsView, Mapping, Protocol
|
||||
|
||||
from .dlp import (
|
||||
build_outbound_scan_text,
|
||||
outbound_scan_headers,
|
||||
scan_outbound,
|
||||
)
|
||||
from .dlp_detectors import redact_tokens, strip_crlf
|
||||
from .types import Route, ScanResult
|
||||
|
||||
|
||||
class MutableHeaders(Protocol):
|
||||
def items(self) -> ItemsView[str, str]: ...
|
||||
def __getitem__(self, name: str, /) -> str: ...
|
||||
def __setitem__(self, name: str, value: str, /) -> None: ...
|
||||
|
||||
|
||||
class MutableRequest(Protocol):
|
||||
pretty_host: str
|
||||
path: str
|
||||
headers: MutableHeaders
|
||||
text: str
|
||||
|
||||
def get_text(self, strict: bool = False) -> str | None: ...
|
||||
|
||||
|
||||
def scan_request(
|
||||
request: MutableRequest,
|
||||
route: Route,
|
||||
env: Mapping[str, str],
|
||||
*,
|
||||
safe_tokens: set[str] | None = None,
|
||||
) -> ScanResult | None:
|
||||
"""Scan all mutable outbound request surfaces in their canonical order."""
|
||||
request_path, _, query = request.path.partition("?")
|
||||
headers = outbound_scan_headers(route, dict(request.headers.items()))
|
||||
body = request.get_text(strict=False) or ""
|
||||
scan_text = build_outbound_scan_text(
|
||||
request.pretty_host, request_path, query, headers, body,
|
||||
)
|
||||
# Bodies cannot alter HTTP framing, so CRLF detection is deliberately
|
||||
# restricted to the request line and headers.
|
||||
crlf_text = build_outbound_scan_text(
|
||||
request.pretty_host, request_path, query, headers, "",
|
||||
)
|
||||
return scan_outbound(
|
||||
route,
|
||||
scan_text,
|
||||
env,
|
||||
safe_tokens=safe_tokens,
|
||||
crlf_text=crlf_text,
|
||||
)
|
||||
|
||||
|
||||
def redact_request(
|
||||
request: MutableRequest,
|
||||
route: Route,
|
||||
env: Mapping[str, str],
|
||||
) -> bool:
|
||||
"""Redact mutable request surfaces and return whether the result is clean."""
|
||||
body = request.get_text(strict=False)
|
||||
if body:
|
||||
redacted_body = redact_tokens(body, env=env)
|
||||
if redacted_body != body:
|
||||
request.text = redacted_body
|
||||
for name, value in list(request.headers.items()):
|
||||
if name.lower() == "host":
|
||||
continue
|
||||
redacted = strip_crlf(redact_tokens(value, env=env))
|
||||
if redacted != value:
|
||||
request.headers[name] = redacted
|
||||
redacted_path = strip_crlf(redact_tokens(request.path, env=env))
|
||||
if redacted_path != request.path:
|
||||
request.path = redacted_path
|
||||
result = scan_request(request, route, env)
|
||||
return result is None or result.severity != "block"
|
||||
|
||||
|
||||
__all__ = ["MutableRequest", "redact_request", "scan_request"]
|
||||
@@ -0,0 +1,92 @@
|
||||
"""Framework-neutral request policy stages for the egress adapter.
|
||||
|
||||
The mitmproxy addon owns flow mutation and response construction. This module
|
||||
owns the ordered Git and route-policy decisions so those rules remain directly
|
||||
testable without a live proxy flow.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
from dataclasses import dataclass
|
||||
from typing import Mapping, Sequence
|
||||
|
||||
from .matching import (
|
||||
decide,
|
||||
decide_git_fetch,
|
||||
is_git_fetch_request,
|
||||
is_git_push_request,
|
||||
)
|
||||
from .types import LOG_FULL, Config, Route
|
||||
|
||||
GIT_PUSH_BLOCK_REASON = (
|
||||
"egress: git push over HTTPS is not supported; "
|
||||
"use the bottle.git SSH path (gitleaks-scanned by "
|
||||
"git-gate's pre-receive hook)."
|
||||
)
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class RoutePolicyResult:
|
||||
"""The flow mutations and outcome produced by general route policy."""
|
||||
|
||||
block_reason: str = ""
|
||||
strip_authorization: bool = False
|
||||
inject_authorization: str | None = None
|
||||
log_request: bool = False
|
||||
|
||||
|
||||
def git_block_reason(
|
||||
routes: Sequence[Route],
|
||||
host: str,
|
||||
request_path: str,
|
||||
query: str,
|
||||
) -> str:
|
||||
"""Return the HTTPS Git policy denial, or ``""`` when allowed."""
|
||||
if is_git_push_request(request_path, query):
|
||||
return GIT_PUSH_BLOCK_REASON
|
||||
if not is_git_fetch_request(request_path, query):
|
||||
return ""
|
||||
decision = decide_git_fetch(routes, host)
|
||||
return decision.reason if decision.action == "block" else ""
|
||||
|
||||
|
||||
def evaluate_route_policy(
|
||||
config: Config,
|
||||
route: Route | None,
|
||||
*,
|
||||
host: str,
|
||||
request_path: str,
|
||||
method: str,
|
||||
headers: Mapping[str, str],
|
||||
env: Mapping[str, str],
|
||||
) -> RoutePolicyResult:
|
||||
"""Evaluate authorization stripping, matching, injection, and logging."""
|
||||
strip_authorization = route is None or not route.preserve_auth
|
||||
effective_headers = {
|
||||
name.lower(): value
|
||||
for name, value in headers.items()
|
||||
if not (strip_authorization and name.lower() == "authorization")
|
||||
}
|
||||
decision = decide(
|
||||
config.routes,
|
||||
host,
|
||||
request_path,
|
||||
env,
|
||||
request_method=method,
|
||||
request_headers=effective_headers,
|
||||
deny_reason=config.deny_reason,
|
||||
)
|
||||
return RoutePolicyResult(
|
||||
block_reason=decision.reason if decision.action == "block" else "",
|
||||
strip_authorization=strip_authorization,
|
||||
inject_authorization=decision.inject_authorization,
|
||||
log_request=config.log >= LOG_FULL,
|
||||
)
|
||||
|
||||
|
||||
__all__ = [
|
||||
"GIT_PUSH_BLOCK_REASON",
|
||||
"RoutePolicyResult",
|
||||
"evaluate_route_policy",
|
||||
"git_block_reason",
|
||||
]
|
||||
@@ -0,0 +1,349 @@
|
||||
"""Egress policy schema parsing and serialization (PRD 0017 / 0053)."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import re
|
||||
import typing
|
||||
|
||||
from ...yaml_subset import YamlSubsetError, parse_yaml_subset
|
||||
from .dlp_config import parse_inspect_block
|
||||
from .types import (
|
||||
HEADER_MATCH_TYPES,
|
||||
LOG_BLOCKS,
|
||||
LOG_FULL,
|
||||
LOG_OFF,
|
||||
PATH_MATCH_TYPES,
|
||||
VALID_METHODS,
|
||||
Config,
|
||||
HeaderMatch,
|
||||
MatchEntry,
|
||||
PathMatch,
|
||||
Route,
|
||||
)
|
||||
|
||||
# Parsing
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
def _parse_path_match(idx: int, j: int, raw: object) -> PathMatch:
|
||||
label = f"route[{idx}] matches paths[{j}]"
|
||||
if not isinstance(raw, dict):
|
||||
raise ValueError(f"{label}: must be an object")
|
||||
raw_dict: dict[str, object] = typing.cast(dict[str, object], raw)
|
||||
ptype = raw_dict.get("type", "prefix")
|
||||
if not isinstance(ptype, str) or ptype not in PATH_MATCH_TYPES:
|
||||
raise ValueError(
|
||||
f"{label}: 'type' must be one of {', '.join(PATH_MATCH_TYPES)} "
|
||||
f"(got {ptype!r})"
|
||||
)
|
||||
value = raw_dict.get("value")
|
||||
if not isinstance(value, str) or not value:
|
||||
raise ValueError(f"{label}: 'value' must be a non-empty string")
|
||||
if ptype in ("exact", "prefix") and not value.startswith("/"):
|
||||
raise ValueError(
|
||||
f"{label}: value {value!r} must start with '/' for "
|
||||
f"type {ptype!r}"
|
||||
)
|
||||
compiled: re.Pattern[str] | None = None
|
||||
if ptype == "regex":
|
||||
try:
|
||||
compiled = re.compile(value)
|
||||
except re.error as e:
|
||||
raise ValueError(
|
||||
f"{label}: regex {value!r} failed to compile: {e}"
|
||||
) from e
|
||||
for k in raw_dict:
|
||||
if k not in ("type", "value"):
|
||||
raise ValueError(f"{label}: unknown key {k!r}")
|
||||
return PathMatch(type=ptype, value=value, compiled=compiled)
|
||||
|
||||
|
||||
def _parse_header_match(idx: int, j: int, raw: object) -> HeaderMatch:
|
||||
label = f"route[{idx}] matches headers[{j}]"
|
||||
if not isinstance(raw, dict):
|
||||
raise ValueError(f"{label}: must be an object")
|
||||
raw_dict: dict[str, object] = typing.cast(dict[str, object], raw)
|
||||
name = raw_dict.get("name")
|
||||
if not isinstance(name, str) or not name:
|
||||
raise ValueError(f"{label}: 'name' must be a non-empty string")
|
||||
value = raw_dict.get("value")
|
||||
if not isinstance(value, str):
|
||||
raise ValueError(f"{label}: 'value' must be a string")
|
||||
htype = raw_dict.get("type", "exact")
|
||||
if not isinstance(htype, str) or htype not in HEADER_MATCH_TYPES:
|
||||
raise ValueError(
|
||||
f"{label}: 'type' must be one of {', '.join(HEADER_MATCH_TYPES)} "
|
||||
f"(got {htype!r})"
|
||||
)
|
||||
compiled: re.Pattern[str] | None = None
|
||||
if htype == "regex":
|
||||
try:
|
||||
compiled = re.compile(value)
|
||||
except re.error as e:
|
||||
raise ValueError(
|
||||
f"{label}: regex {value!r} failed to compile: {e}"
|
||||
) from e
|
||||
for k in raw_dict:
|
||||
if k not in ("name", "value", "type"):
|
||||
raise ValueError(f"{label}: unknown key {k!r}")
|
||||
return HeaderMatch(name=name, value=value, type=htype, compiled=compiled)
|
||||
|
||||
|
||||
def _parse_match_entry(idx: int, k: int, raw: object) -> MatchEntry:
|
||||
label = f"route[{idx}] matches[{k}]"
|
||||
if not isinstance(raw, dict):
|
||||
raise ValueError(f"{label}: must be an object")
|
||||
raw_dict: dict[str, object] = typing.cast(dict[str, object], raw)
|
||||
|
||||
paths: tuple[PathMatch, ...] = ()
|
||||
paths_raw = raw_dict.get("paths")
|
||||
if paths_raw is not None:
|
||||
if not isinstance(paths_raw, list):
|
||||
raise ValueError(f"{label}: 'paths' must be a list")
|
||||
paths_list = typing.cast(list[object], paths_raw)
|
||||
paths = tuple(_parse_path_match(idx, j, p) for j, p in enumerate(paths_list))
|
||||
|
||||
methods: tuple[str, ...] = ()
|
||||
methods_raw = raw_dict.get("methods")
|
||||
if methods_raw is not None:
|
||||
if not isinstance(methods_raw, list):
|
||||
raise ValueError(f"{label}: 'methods' must be a list")
|
||||
methods_list = typing.cast(list[object], methods_raw)
|
||||
normalised: list[str] = []
|
||||
for j, m in enumerate(methods_list):
|
||||
if not isinstance(m, str):
|
||||
raise ValueError(f"{label}: methods[{j}] must be a string")
|
||||
upper = m.upper()
|
||||
if upper not in VALID_METHODS:
|
||||
raise ValueError(
|
||||
f"{label}: methods[{j}] {m!r} is not a valid HTTP method"
|
||||
)
|
||||
normalised.append(upper)
|
||||
methods = tuple(normalised)
|
||||
|
||||
headers: tuple[HeaderMatch, ...] = ()
|
||||
headers_raw = raw_dict.get("headers")
|
||||
if headers_raw is not None:
|
||||
if not isinstance(headers_raw, list):
|
||||
raise ValueError(f"{label}: 'headers' must be a list")
|
||||
headers_list = typing.cast(list[object], headers_raw)
|
||||
headers = tuple(
|
||||
_parse_header_match(idx, j, h) for j, h in enumerate(headers_list)
|
||||
)
|
||||
|
||||
for key in raw_dict:
|
||||
if key not in ("paths", "methods", "headers"):
|
||||
raise ValueError(f"{label}: unknown key {key!r}")
|
||||
|
||||
return MatchEntry(paths=paths, methods=methods, headers=headers)
|
||||
|
||||
|
||||
def parse_routes(payload: object) -> tuple[Route, ...]:
|
||||
if not isinstance(payload, dict):
|
||||
raise ValueError("routes payload: top-level must be an object")
|
||||
payload_dict: dict[str, object] = typing.cast(dict[str, object], payload)
|
||||
raw: object = payload_dict.get("routes")
|
||||
if not isinstance(raw, list):
|
||||
raise ValueError("routes payload: 'routes' must be a list")
|
||||
raw_list: list[object] = typing.cast(list[object], raw)
|
||||
out: list[Route] = []
|
||||
for i, r in enumerate(raw_list):
|
||||
out.append(_parse_one(i, r))
|
||||
return tuple(out)
|
||||
|
||||
|
||||
def _parse_one(idx: int, raw: object) -> Route:
|
||||
label = f"route[{idx}]"
|
||||
if not isinstance(raw, dict):
|
||||
raise ValueError(f"{label}: must be an object (got {type(raw).__name__})")
|
||||
raw_dict: dict[str, object] = typing.cast(dict[str, object], raw)
|
||||
host: object = raw_dict.get("host")
|
||||
if not isinstance(host, str) or not host:
|
||||
raise ValueError(f"{label}: 'host' must be a non-empty string")
|
||||
legacy_flat = "inspect" not in raw_dict
|
||||
inspect_raw = raw_dict.get("inspect", {})
|
||||
if inspect_raw is False:
|
||||
inspect = False
|
||||
settings: dict[str, object] = {}
|
||||
elif isinstance(inspect_raw, dict):
|
||||
inspect = True
|
||||
settings = (
|
||||
{k: v for k, v in raw_dict.items() if k != "host"}
|
||||
if legacy_flat
|
||||
else typing.cast(dict[str, object], inspect_raw)
|
||||
)
|
||||
legacy_dlp = settings.pop("dlp", None)
|
||||
if isinstance(legacy_dlp, dict):
|
||||
settings.update(typing.cast(dict[str, object], legacy_dlp))
|
||||
elif legacy_dlp is not None:
|
||||
raise ValueError(
|
||||
f"{label} ({host}): legacy 'dlp' must be an object"
|
||||
)
|
||||
else:
|
||||
raise ValueError(f"{label} ({host}): 'inspect' must be false or an object")
|
||||
|
||||
# matches
|
||||
matches: tuple[MatchEntry, ...] = ()
|
||||
matches_raw = settings.get("matches")
|
||||
if matches_raw is not None:
|
||||
if not isinstance(matches_raw, list):
|
||||
raise ValueError(f"{label} ({host}): 'matches' must be a list")
|
||||
matches_list = typing.cast(list[object], matches_raw)
|
||||
matches = tuple(
|
||||
_parse_match_entry(idx, k, m) for k, m in enumerate(matches_list)
|
||||
)
|
||||
|
||||
# auth (unchanged wire format)
|
||||
auth_scheme: object = settings.get("auth_scheme", "")
|
||||
token_env: object = settings.get("token_env", "")
|
||||
if not isinstance(auth_scheme, str):
|
||||
raise ValueError(f"{label} ({host}): 'auth_scheme' must be a string")
|
||||
if not isinstance(token_env, str):
|
||||
raise ValueError(f"{label} ({host}): 'token_env' must be a string")
|
||||
if bool(auth_scheme) != bool(token_env):
|
||||
raise ValueError(
|
||||
f"{label} ({host}): 'auth_scheme' and 'token_env' must be both "
|
||||
f"set or both empty (got auth_scheme={auth_scheme!r}, "
|
||||
f"token_env={token_env!r})"
|
||||
)
|
||||
|
||||
# git-over-HTTPS policy
|
||||
git_fetch = False
|
||||
git_raw = settings.get("git")
|
||||
if git_raw is not None:
|
||||
if not isinstance(git_raw, dict):
|
||||
raise ValueError(f"{label} ({host}): 'git' must be an object")
|
||||
git_dict: dict[str, object] = typing.cast(dict[str, object], git_raw)
|
||||
fetch_raw = git_dict.get("fetch", False)
|
||||
if fetch_raw is True or fetch_raw is False:
|
||||
git_fetch = fetch_raw
|
||||
else:
|
||||
raise ValueError(f"{label} ({host}): 'git.fetch' must be a boolean")
|
||||
for k in git_dict:
|
||||
if k != "fetch":
|
||||
raise ValueError(
|
||||
f"{label} ({host}): git has unknown key {k!r}; "
|
||||
"accepted key is 'fetch'"
|
||||
)
|
||||
|
||||
# dlp detectors
|
||||
outbound_detectors, inbound_detectors, outbound_on_match = parse_inspect_block(
|
||||
idx, host, settings,
|
||||
)
|
||||
|
||||
preserve_auth_raw = settings.get("preserve_auth", False)
|
||||
if preserve_auth_raw is not True and preserve_auth_raw is not False:
|
||||
raise ValueError(
|
||||
f"{label} ({host}): 'preserve_auth' must be a boolean"
|
||||
)
|
||||
preserve_auth: bool = preserve_auth_raw
|
||||
|
||||
for k in settings:
|
||||
if k not in (
|
||||
"matches", "auth_scheme", "token_env", "git", "preserve_auth",
|
||||
"outbound_detectors", "inbound_detectors", "outbound_on_match",
|
||||
):
|
||||
raise ValueError(
|
||||
f"{label} ({host}): inspect has unknown key {k!r}"
|
||||
)
|
||||
for k in raw_dict:
|
||||
if not legacy_flat and k not in ("host", "inspect"):
|
||||
raise ValueError(
|
||||
f"{label} ({host}): unknown key {k!r}; accepted keys "
|
||||
f"are 'host' and 'inspect'"
|
||||
)
|
||||
|
||||
return Route(
|
||||
host=host,
|
||||
matches=matches,
|
||||
auth_scheme=auth_scheme,
|
||||
token_env=token_env,
|
||||
git_fetch=git_fetch,
|
||||
outbound_detectors=outbound_detectors,
|
||||
inbound_detectors=inbound_detectors,
|
||||
outbound_on_match=outbound_on_match,
|
||||
preserve_auth=preserve_auth,
|
||||
inspect=inspect,
|
||||
)
|
||||
|
||||
|
||||
def _path_match_to_dict(pm: PathMatch) -> dict[str, object]:
|
||||
d: dict[str, object] = {"value": pm.value}
|
||||
if pm.type != "prefix":
|
||||
d["type"] = pm.type
|
||||
return d
|
||||
|
||||
|
||||
def _header_match_to_dict(hm: HeaderMatch) -> dict[str, object]:
|
||||
d: dict[str, object] = {"name": hm.name, "value": hm.value}
|
||||
if hm.type != "exact":
|
||||
d["type"] = hm.type
|
||||
return d
|
||||
|
||||
|
||||
def _match_entry_to_dict(me: MatchEntry) -> dict[str, object]:
|
||||
d: dict[str, object] = {}
|
||||
if me.paths:
|
||||
d["paths"] = [_path_match_to_dict(p) for p in me.paths]
|
||||
if me.methods:
|
||||
d["methods"] = list(me.methods)
|
||||
if me.headers:
|
||||
d["headers"] = [_header_match_to_dict(h) for h in me.headers]
|
||||
return d
|
||||
|
||||
|
||||
def route_to_yaml_dict(r: Route) -> dict[str, object]:
|
||||
"""Serialize a Route to YAML-schema-compatible dict.
|
||||
|
||||
Uses the same field names the YAML parser accepts, so the output
|
||||
can be round-tripped directly into an `allow` or `egress-block`
|
||||
proposal without translation. Fields that are empty/default are
|
||||
omitted so the agent doesn't copy irrelevant keys."""
|
||||
d: dict[str, object] = {"host": r.host}
|
||||
if not r.inspect:
|
||||
d["inspect"] = False
|
||||
return d
|
||||
inspected: dict[str, object] = {}
|
||||
if r.auth_scheme:
|
||||
inspected["auth_scheme"] = r.auth_scheme
|
||||
inspected["token_env"] = r.token_env
|
||||
if r.matches:
|
||||
inspected["matches"] = [_match_entry_to_dict(m) for m in r.matches]
|
||||
if r.git_fetch:
|
||||
inspected["git"] = {"fetch": True}
|
||||
if r.outbound_detectors is not None:
|
||||
inspected["outbound_detectors"] = list(r.outbound_detectors)
|
||||
if r.inbound_detectors is not None:
|
||||
inspected["inbound_detectors"] = list(r.inbound_detectors)
|
||||
if r.outbound_on_match:
|
||||
inspected["outbound_on_match"] = r.outbound_on_match
|
||||
if r.preserve_auth:
|
||||
inspected["preserve_auth"] = True
|
||||
if inspected:
|
||||
d["inspect"] = inspected
|
||||
return d
|
||||
|
||||
|
||||
def parse_config(payload: object) -> "Config":
|
||||
"""Parse a full egress config payload (top-level log level + routes)."""
|
||||
if not isinstance(payload, dict):
|
||||
raise ValueError("routes payload: top-level must be an object")
|
||||
payload_dict: dict[str, object] = typing.cast(dict[str, object], payload)
|
||||
|
||||
log_raw: object = payload_dict.get("log", LOG_OFF)
|
||||
if log_raw is True or log_raw is False or not isinstance(log_raw, int) \
|
||||
or log_raw not in (LOG_OFF, LOG_BLOCKS, LOG_FULL):
|
||||
raise ValueError(
|
||||
f"routes payload: 'log' must be {LOG_OFF}, {LOG_BLOCKS}, or {LOG_FULL}"
|
||||
)
|
||||
|
||||
routes = parse_routes(payload)
|
||||
return Config(routes=routes, log=log_raw)
|
||||
|
||||
|
||||
def load_config(text: str) -> "Config":
|
||||
"""Parse YAML text → Config (routes + log flag)."""
|
||||
try:
|
||||
payload = parse_yaml_subset(text)
|
||||
except YamlSubsetError as e:
|
||||
raise ValueError(f"routes payload: invalid YAML: {e}") from e
|
||||
return parse_config(payload)
|
||||
@@ -0,0 +1,81 @@
|
||||
"""Shared egress policy value objects.
|
||||
|
||||
Kept dependency-free so the schema parser, matcher, DLP scanner, and addon
|
||||
adapter can use the same immutable public shapes without importing each other.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import re
|
||||
from dataclasses import dataclass
|
||||
|
||||
|
||||
PATH_MATCH_TYPES = ("exact", "prefix", "regex")
|
||||
HEADER_MATCH_TYPES = ("exact", "regex")
|
||||
VALID_METHODS = frozenset({
|
||||
"GET", "HEAD", "POST", "PUT", "DELETE", "PATCH", "OPTIONS", "TRACE",
|
||||
"CONNECT",
|
||||
})
|
||||
|
||||
LOG_OFF = 0
|
||||
LOG_BLOCKS = 1
|
||||
LOG_FULL = 2
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class PathMatch:
|
||||
type: str
|
||||
value: str
|
||||
compiled: re.Pattern[str] | None = None
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class HeaderMatch:
|
||||
name: str
|
||||
value: str
|
||||
type: str = "exact"
|
||||
compiled: re.Pattern[str] | None = None
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class MatchEntry:
|
||||
paths: tuple[PathMatch, ...] = ()
|
||||
methods: tuple[str, ...] = ()
|
||||
headers: tuple[HeaderMatch, ...] = ()
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class Route:
|
||||
host: str
|
||||
matches: tuple[MatchEntry, ...] = ()
|
||||
auth_scheme: str = ""
|
||||
token_env: str = ""
|
||||
git_fetch: bool = False
|
||||
outbound_detectors: tuple[str, ...] | None = None
|
||||
inbound_detectors: tuple[str, ...] | None = None
|
||||
outbound_on_match: str = ""
|
||||
preserve_auth: bool = False
|
||||
inspect: bool = True
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class Config:
|
||||
routes: tuple[Route, ...]
|
||||
log: int = LOG_OFF
|
||||
deny_reason: str = ""
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class Decision:
|
||||
action: str
|
||||
reason: str = ""
|
||||
inject_authorization: str | None = None
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class ScanResult:
|
||||
severity: str
|
||||
reason: str
|
||||
location: str = ""
|
||||
context: str = ""
|
||||
matched: str = ""
|
||||
@@ -21,12 +21,19 @@ from __future__ import annotations
|
||||
import os
|
||||
import subprocess
|
||||
import sys
|
||||
import tempfile
|
||||
import threading
|
||||
import typing
|
||||
from http.server import BaseHTTPRequestHandler, ThreadingHTTPServer
|
||||
from http.server import BaseHTTPRequestHandler
|
||||
from pathlib import Path
|
||||
from urllib.parse import urlsplit
|
||||
|
||||
from bot_bottle.constants import GIT_GATE_TIMEOUT_SECS, IDENTITY_HEADER
|
||||
from bot_bottle.gateway.bounded_http import (
|
||||
BodyReadError,
|
||||
BoundedThreadingHTTPServer,
|
||||
copy_declared_body,
|
||||
)
|
||||
from bot_bottle.gateway.policy_resolver import PolicyResolveError, PolicyResolver
|
||||
|
||||
|
||||
@@ -77,6 +84,10 @@ def resolve_sandbox_root(
|
||||
|
||||
# Bound memory use while still allowing ordinary git push packfiles.
|
||||
MAX_BODY_BYTES = 100 * 1024 * 1024
|
||||
REQUEST_BODY_TIMEOUT_SECONDS = 30.0
|
||||
MAX_REQUEST_WORKERS = 16
|
||||
MAX_BODY_WORKERS = 2
|
||||
_BODY_WORK_SLOTS = threading.BoundedSemaphore(MAX_BODY_WORKERS)
|
||||
|
||||
|
||||
class GitHttpHandler(BaseHTTPRequestHandler):
|
||||
@@ -184,27 +195,40 @@ class GitHttpHandler(BaseHTTPRequestHandler):
|
||||
value = self.headers.get(header)
|
||||
if value:
|
||||
env[variable] = value
|
||||
raw_length = self.headers.get("content-length", "0") or "0"
|
||||
if not _BODY_WORK_SLOTS.acquire(blocking=False):
|
||||
self.send_error(503, "git request capacity exhausted")
|
||||
return
|
||||
try:
|
||||
length = int(raw_length)
|
||||
except ValueError:
|
||||
self.send_error(400, "Bad Content-Length")
|
||||
return
|
||||
if length < 0:
|
||||
self.send_error(400, "Negative Content-Length")
|
||||
return
|
||||
if length > MAX_BODY_BYTES:
|
||||
self.send_error(413, "Request body too large")
|
||||
return
|
||||
body = self.rfile.read(length) if length else b""
|
||||
proc = subprocess.run(
|
||||
["git", "http-backend"],
|
||||
input=body,
|
||||
env=env,
|
||||
capture_output=True,
|
||||
check=False,
|
||||
timeout=GIT_GATE_TIMEOUT_SECS,
|
||||
)
|
||||
with tempfile.TemporaryFile() as body:
|
||||
try:
|
||||
copy_declared_body(
|
||||
self.rfile,
|
||||
body,
|
||||
self.connection,
|
||||
self.headers.get("content-length"),
|
||||
maximum=MAX_BODY_BYTES,
|
||||
timeout_seconds=REQUEST_BODY_TIMEOUT_SECONDS,
|
||||
require_length=False,
|
||||
)
|
||||
except BodyReadError as exc:
|
||||
self.send_error(exc.status, exc.message)
|
||||
return
|
||||
body.seek(0)
|
||||
try:
|
||||
proc = subprocess.run(
|
||||
["git", "http-backend"],
|
||||
stdin=body,
|
||||
env=env,
|
||||
capture_output=True,
|
||||
check=False,
|
||||
timeout=GIT_GATE_TIMEOUT_SECS,
|
||||
)
|
||||
except (OSError, subprocess.SubprocessError) as exc:
|
||||
self.log_message("git http-backend unavailable: %s", exc)
|
||||
self.send_error(503, "git backend unavailable")
|
||||
return
|
||||
finally:
|
||||
_BODY_WORK_SLOTS.release()
|
||||
self._write_cgi_response(proc.stdout)
|
||||
|
||||
def _repo_dir(self, sandbox_root: Path, path: str) -> Path | None:
|
||||
@@ -273,7 +297,9 @@ def main() -> int:
|
||||
"(no single-tenant flat-root fallback)\n"
|
||||
)
|
||||
return 1
|
||||
server = ThreadingHTTPServer(("0.0.0.0", port), GitHttpHandler)
|
||||
server = BoundedThreadingHTTPServer(
|
||||
("0.0.0.0", port), GitHttpHandler, max_workers=MAX_REQUEST_WORKERS,
|
||||
)
|
||||
# Resolve each request's sandbox namespace by source IP against the
|
||||
# orchestrator control plane.
|
||||
server.policy_resolver = PolicyResolver(orch_url) # type: ignore[attr-defined]
|
||||
|
||||
@@ -252,6 +252,27 @@ cat > "$refs_file"
|
||||
|
||||
zero=0000000000000000000000000000000000000000
|
||||
|
||||
# Phase 0: reject Gitea AGit review refs before scanning or forwarding.
|
||||
# A push to refs/for/*, refs/draft/*, or refs/for-review/* asks Gitea to
|
||||
# open a pull request backed by a server-managed refs/pull/<n>/head rather
|
||||
# than an ordinary refs/heads/* branch. That breaks the git-gate workflow:
|
||||
# follow-up commits can't be pushed back through the branch, and Gitea
|
||||
# rejects later direct updates to the generated review ref. Fail the whole
|
||||
# push here (before any gitleaks scan or upstream forward) so the caller
|
||||
# pushes a real branch and opens the PR against it instead. Deletions
|
||||
# (new == zero) stay allowed so stale AGit refs can still be cleaned up.
|
||||
while IFS=' ' read -r old new ref; do
|
||||
[ -z "$ref" ] && continue
|
||||
[ "$new" = "$zero" ] && continue
|
||||
case "$ref" in
|
||||
refs/for/*|refs/draft/*|refs/for-review/*)
|
||||
echo "git-gate: refusing AGit review ref $ref" >&2
|
||||
echo "git-gate: push to refs/heads/<branch> and open a branch-backed pull request instead" >&2
|
||||
exit 1
|
||||
;;
|
||||
esac
|
||||
done < "$refs_file"
|
||||
|
||||
supervise_gitleaks_allow() {
|
||||
log_opts=$1
|
||||
ref=$2
|
||||
@@ -364,7 +385,7 @@ PY
|
||||
;;
|
||||
esac
|
||||
echo "git-gate: queued # gitleaks:allow supervisor approval $proposal_id" >&2
|
||||
echo "git-gate: approve with './cli.py supervise' to continue this push" >&2
|
||||
echo "git-gate: approve with 'bot-bottle supervise' to continue this push" >&2
|
||||
waited=0
|
||||
while [ "$waited" -lt "$timeout" ]; do
|
||||
status=$(PYTHONPATH="/app${PYTHONPATH:+:$PYTHONPATH}" python3 - "$proposal_id" <<'PY'
|
||||
|
||||
@@ -0,0 +1,92 @@
|
||||
"""Framework-neutral MCP method and tool dispatch."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import json
|
||||
from dataclasses import dataclass
|
||||
from typing import Callable, Protocol
|
||||
|
||||
from bot_bottle.gateway.egress.schema import load_config, route_to_yaml_dict
|
||||
from bot_bottle.gateway.policy_resolver import PolicyResolveError, PolicyResolver
|
||||
from bot_bottle.supervisor import types as _sv
|
||||
|
||||
|
||||
class Request(Protocol):
|
||||
@property
|
||||
def method(self) -> str: ...
|
||||
|
||||
@property
|
||||
def params(self) -> dict[str, object]: ...
|
||||
|
||||
|
||||
class MethodNotFoundError(Exception):
|
||||
"""Raised when a JSON-RPC method has no MCP handler."""
|
||||
|
||||
|
||||
class RouteResolutionError(Exception):
|
||||
"""The caller's live route table could not be resolved authoritatively."""
|
||||
|
||||
|
||||
Handler = Callable[[dict[str, object]], object]
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class Handlers:
|
||||
initialize: Handler
|
||||
tools_list: Handler
|
||||
list_routes: Handler
|
||||
check_proposal: Handler
|
||||
propose: Handler
|
||||
|
||||
|
||||
def dispatch(request: Request, handlers: Handlers) -> object:
|
||||
"""Route one parsed request without depending on the HTTP server."""
|
||||
if request.method == "initialize":
|
||||
return handlers.initialize(request.params)
|
||||
if request.method == "notifications/initialized":
|
||||
return None
|
||||
if request.method == "tools/list":
|
||||
return handlers.tools_list(request.params)
|
||||
if request.method != "tools/call":
|
||||
raise MethodNotFoundError(request.method)
|
||||
|
||||
tool = request.params.get("name")
|
||||
if tool == _sv.TOOL_LIST_EGRESS_ROUTES:
|
||||
return handlers.list_routes(request.params)
|
||||
if tool == _sv.TOOL_CHECK_PROPOSAL:
|
||||
return handlers.check_proposal(request.params)
|
||||
return handlers.propose(request.params)
|
||||
|
||||
|
||||
def resolved_routes_payload(
|
||||
resolver: PolicyResolver,
|
||||
source_ip: str,
|
||||
identity_token: str,
|
||||
) -> dict[str, object]:
|
||||
"""Render an authoritatively resolved route table for the calling bottle."""
|
||||
try:
|
||||
policy, bottle_id, _tokens = resolver.resolve_policy_and_bottle_id(
|
||||
source_ip, identity_token,
|
||||
)
|
||||
except PolicyResolveError as exc:
|
||||
raise RouteResolutionError("orchestrator unavailable") from exc
|
||||
if not bottle_id:
|
||||
raise RouteResolutionError("request source is not attributed to a bottle")
|
||||
try:
|
||||
config = load_config(policy or "")
|
||||
except ValueError as exc:
|
||||
raise RouteResolutionError("resolved policy is invalid") from exc
|
||||
body = json.dumps(
|
||||
{"routes": [route_to_yaml_dict(route) for route in config.routes]},
|
||||
indent=2,
|
||||
)
|
||||
return {"content": [{"type": "text", "text": body}], "isError": False}
|
||||
|
||||
|
||||
__all__ = [
|
||||
"Handlers",
|
||||
"MethodNotFoundError",
|
||||
"RouteResolutionError",
|
||||
"dispatch",
|
||||
"resolved_routes_payload",
|
||||
]
|
||||
@@ -51,17 +51,27 @@ from __future__ import annotations
|
||||
import http.server
|
||||
import json
|
||||
import os
|
||||
import socketserver
|
||||
import sys
|
||||
import time
|
||||
import typing
|
||||
from dataclasses import dataclass
|
||||
|
||||
from bot_bottle.constants import IDENTITY_HEADER
|
||||
from bot_bottle.gateway.egress.addon_core import (
|
||||
LOG_OFF, load_config, resolve_client_context, route_to_yaml_dict,
|
||||
from bot_bottle.gateway.bounded_http import (
|
||||
BodyReadError,
|
||||
BoundedThreadingHTTPServer,
|
||||
read_declared_body,
|
||||
)
|
||||
from bot_bottle.gateway.egress.schema import load_config
|
||||
from bot_bottle.gateway.egress.types import LOG_OFF
|
||||
from bot_bottle.gateway.policy_resolver import PolicyResolveError, PolicyResolver
|
||||
from bot_bottle.gateway.supervisor.mcp_dispatch import (
|
||||
Handlers as DispatchHandlers,
|
||||
MethodNotFoundError,
|
||||
RouteResolutionError,
|
||||
dispatch,
|
||||
resolved_routes_payload,
|
||||
)
|
||||
from bot_bottle.supervisor import types as _sv
|
||||
|
||||
|
||||
@@ -565,6 +575,8 @@ def format_unknown_proposal_text(proposal_id: str) -> str:
|
||||
# Max request body the server accepts. 1 MB is well above any realistic
|
||||
# routes.yaml proposal.
|
||||
MAX_BODY_BYTES = 1 * 1024 * 1024
|
||||
REQUEST_BODY_TIMEOUT_SECONDS = 10.0
|
||||
MAX_REQUEST_WORKERS = 32
|
||||
|
||||
|
||||
class MCPHandler(http.server.BaseHTTPRequestHandler):
|
||||
@@ -587,19 +599,18 @@ class MCPHandler(http.server.BaseHTTPRequestHandler):
|
||||
self._write_text(405, "use POST for MCP requests\n")
|
||||
|
||||
def do_POST(self) -> None:
|
||||
length_header = self.headers.get("Content-Length")
|
||||
if length_header is None:
|
||||
self._write_text(411, "Content-Length required\n")
|
||||
return
|
||||
try:
|
||||
length = int(length_header)
|
||||
except ValueError:
|
||||
self._write_text(400, "invalid Content-Length\n")
|
||||
body = read_declared_body(
|
||||
self.rfile,
|
||||
self.connection,
|
||||
self.headers.get("Content-Length"),
|
||||
maximum=MAX_BODY_BYTES,
|
||||
timeout_seconds=REQUEST_BODY_TIMEOUT_SECONDS,
|
||||
require_length=True,
|
||||
)
|
||||
except BodyReadError as exc:
|
||||
self._write_text(exc.status, exc.message + "\n")
|
||||
return
|
||||
if length < 0 or length > MAX_BODY_BYTES:
|
||||
self._write_text(413, "request body too large\n")
|
||||
return
|
||||
body = self.rfile.read(length)
|
||||
|
||||
try:
|
||||
req = parse_jsonrpc(body)
|
||||
@@ -611,6 +622,11 @@ class MCPHandler(http.server.BaseHTTPRequestHandler):
|
||||
|
||||
try:
|
||||
result = self._dispatch(req, config)
|
||||
except MethodNotFoundError as e:
|
||||
self._write_jsonrpc(
|
||||
jsonrpc_error(req.id, ERR_METHOD_NOT_FOUND, f"method not found: {e}"),
|
||||
)
|
||||
return
|
||||
except _RpcClientError as e:
|
||||
self._write_jsonrpc(jsonrpc_error(req.id, e.code, e.message))
|
||||
return
|
||||
@@ -633,41 +649,42 @@ class MCPHandler(http.server.BaseHTTPRequestHandler):
|
||||
self._write_jsonrpc(jsonrpc_result(req.id, result))
|
||||
|
||||
def _dispatch(self, req: JsonRpcRequest, config: ServerConfig) -> object:
|
||||
method = req.method
|
||||
if method == "initialize":
|
||||
return handle_initialize(req.params)
|
||||
if method == "notifications/initialized":
|
||||
return None # ack-only
|
||||
if method == "tools/list":
|
||||
return handle_tools_list(req.params)
|
||||
if method == "tools/call":
|
||||
# `list-egress-routes` is read-only introspection. The shared gateway
|
||||
# has no static route table (routes are resolved per request by
|
||||
# source IP), so answer it from the calling bottle's resolved policy.
|
||||
# Otherwise the agent sees an empty allowlist and composes an egress
|
||||
# proposal that *replaces* the live routes instead of extending them
|
||||
# — silently dropping base routes like api.anthropic.com on approval.
|
||||
if req.params.get("name") == _sv.TOOL_LIST_EGRESS_ROUTES:
|
||||
return self._resolved_routes_payload()
|
||||
resolver = self._resolver_or_fail()
|
||||
source_ip = self.client_address[0]
|
||||
token = self._identity_token()
|
||||
# `check-proposal` is a non-blocking read of the calling bottle's
|
||||
# own queue — attributed by (source_ip, identity_token) like a
|
||||
# proposal, but it never queues or blocks.
|
||||
if req.params.get("name") == _sv.TOOL_CHECK_PROPOSAL:
|
||||
return handle_check_proposal(
|
||||
req.params, resolver=resolver,
|
||||
source_ip=source_ip, identity_token=token,
|
||||
)
|
||||
# The control plane attributes the proposal to the source-IP + token
|
||||
# resolved bottle, so the one shared queue holds each bottle's
|
||||
# proposal under its own id — no slug is asserted by this daemon.
|
||||
return handle_tools_call(
|
||||
req.params, config, resolver=resolver,
|
||||
source_ip=source_ip, identity_token=token,
|
||||
def check(params: dict[str, object]) -> object:
|
||||
return handle_check_proposal(
|
||||
params,
|
||||
resolver=self._resolver_or_fail(),
|
||||
source_ip=self.client_address[0],
|
||||
identity_token=self._identity_token(),
|
||||
)
|
||||
raise _RpcClientError(ERR_METHOD_NOT_FOUND, f"method not found: {method}")
|
||||
|
||||
def propose(params: dict[str, object]) -> object:
|
||||
return handle_tools_call(
|
||||
params,
|
||||
config,
|
||||
resolver=self._resolver_or_fail(),
|
||||
source_ip=self.client_address[0],
|
||||
identity_token=self._identity_token(),
|
||||
)
|
||||
|
||||
def list_routes(_params: dict[str, object]) -> object:
|
||||
try:
|
||||
return resolved_routes_payload(
|
||||
self._resolver_or_fail(),
|
||||
self.client_address[0],
|
||||
self._identity_token(),
|
||||
)
|
||||
except RouteResolutionError as exc:
|
||||
raise _RpcInternalError(
|
||||
f"could not resolve live egress routes: {exc}"
|
||||
) from exc
|
||||
|
||||
return dispatch(req, DispatchHandlers(
|
||||
initialize=handle_initialize,
|
||||
tools_list=handle_tools_list,
|
||||
list_routes=list_routes,
|
||||
check_proposal=check,
|
||||
propose=propose,
|
||||
))
|
||||
|
||||
def _identity_token(self) -> str:
|
||||
"""The agent's per-bottle identity token from the request header (the
|
||||
@@ -686,20 +703,6 @@ class MCPHandler(http.server.BaseHTTPRequestHandler):
|
||||
raise _RpcInternalError("supervise server has no policy resolver")
|
||||
return resolver
|
||||
|
||||
def _resolved_routes_payload(self) -> dict[str, object]:
|
||||
"""The calling bottle's live egress routes as the `list-egress-routes`
|
||||
JSON payload, resolved by (source_ip, identity token). Fail-closed: an
|
||||
unattributed source or an unreachable orchestrator yields an empty route
|
||||
list (never another bottle's), courtesy of `resolve_client_context`."""
|
||||
resolver = self._resolver_or_fail()
|
||||
conf, _slug, _tokens = resolve_client_context(
|
||||
resolver, self.client_address[0], self._identity_token(),
|
||||
)
|
||||
body = json.dumps(
|
||||
{"routes": [route_to_yaml_dict(r) for r in conf.routes]}, indent=2,
|
||||
)
|
||||
return {"content": [{"type": "text", "text": body}], "isError": False}
|
||||
|
||||
def _write_jsonrpc(self, body: bytes) -> None:
|
||||
self.send_response(200)
|
||||
self.send_header("Content-Type", "application/json")
|
||||
@@ -719,7 +722,7 @@ class MCPHandler(http.server.BaseHTTPRequestHandler):
|
||||
self.wfile.write(encoded)
|
||||
|
||||
|
||||
class MCPServer(socketserver.ThreadingMixIn, http.server.HTTPServer):
|
||||
class MCPServer(BoundedThreadingHTTPServer):
|
||||
allow_reuse_address = True
|
||||
daemon_threads = True
|
||||
config: ServerConfig = ServerConfig()
|
||||
@@ -728,6 +731,9 @@ class MCPServer(socketserver.ThreadingMixIn, http.server.HTTPServer):
|
||||
# closed per request (see `_resolver_or_fail`).
|
||||
policy_resolver: "PolicyResolver | None" = None
|
||||
|
||||
def __init__(self, *args, **kwargs): # type: ignore[no-untyped-def]
|
||||
super().__init__(*args, max_workers=MAX_REQUEST_WORKERS, **kwargs)
|
||||
|
||||
|
||||
# --- Entry point -----------------------------------------------------------
|
||||
|
||||
|
||||
@@ -8,6 +8,7 @@ imported (`deploy_key_provisioner`) to keep its cost off the host path.
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import json
|
||||
import os
|
||||
import dataclasses
|
||||
from pathlib import Path
|
||||
@@ -138,7 +139,32 @@ def provision_git_gate_dynamic_keys(
|
||||
if upstream.name not in updated_names:
|
||||
updated.append(upstream)
|
||||
|
||||
return dataclasses.replace(plan, upstreams=tuple(updated))
|
||||
final_plan = dataclasses.replace(plan, upstreams=tuple(updated))
|
||||
_write_upstreams_snapshot(stage_dir, final_plan.upstreams)
|
||||
return final_plan
|
||||
|
||||
|
||||
def _write_upstreams_snapshot(
|
||||
stage_dir: Path, upstreams: tuple[GitGateUpstream, ...]
|
||||
) -> None:
|
||||
"""Persist the fully-resolved upstream table to `upstreams.json` in
|
||||
`stage_dir` so the bring-up reconcile can re-provision git-gate without
|
||||
the manifest. Written after dynamic keys are provisioned so every
|
||||
identity_file is set."""
|
||||
data = [
|
||||
{
|
||||
"name": u.name,
|
||||
"upstream_url": u.upstream_url,
|
||||
"upstream_host": u.upstream_host,
|
||||
"upstream_port": u.upstream_port,
|
||||
"identity_file": u.identity_file,
|
||||
"known_host_key": u.known_host_key,
|
||||
}
|
||||
for u in upstreams
|
||||
]
|
||||
snapshot = stage_dir / "upstreams.json"
|
||||
snapshot.write_text(json.dumps(data, indent=2))
|
||||
snapshot.chmod(0o600)
|
||||
|
||||
|
||||
__all__ = [
|
||||
|
||||
@@ -44,7 +44,7 @@ if TYPE_CHECKING:
|
||||
from ..gateway import Gateway, GatewayError
|
||||
from .lifecycle import Orchestrator
|
||||
from .service import OrchestratorCore
|
||||
from .server import OrchestratorServer, dispatch, make_server
|
||||
from .server import OrchestratorServer, create_app, make_server
|
||||
|
||||
|
||||
# Facade name -> submodule that defines it. Lazy so importing a leaf (or the
|
||||
@@ -67,8 +67,8 @@ _LAZY: dict[str, str] = {
|
||||
"GatewayError": "..gateway",
|
||||
"Orchestrator": ".lifecycle",
|
||||
"OrchestratorCore": ".service",
|
||||
"create_app": ".server",
|
||||
"OrchestratorServer": ".server",
|
||||
"dispatch": ".server",
|
||||
"make_server": ".server",
|
||||
}
|
||||
|
||||
@@ -100,7 +100,7 @@ __all__ = [
|
||||
"GatewayError",
|
||||
"Orchestrator",
|
||||
"OrchestratorCore",
|
||||
"create_app",
|
||||
"OrchestratorServer",
|
||||
"dispatch",
|
||||
"make_server",
|
||||
]
|
||||
|
||||
@@ -1,6 +1,7 @@
|
||||
"""Run the orchestrator control plane as a plain process (PRD 0070 dev-harness).
|
||||
|
||||
python -m bot_bottle.orchestrator [--host H] [--port P] [--db PATH]
|
||||
BOT_BOTTLE_ORCHESTRATOR_TOKEN=<signing-key> \
|
||||
python -m bot_bottle.orchestrator [--host H] [--port P] [--db PATH]
|
||||
|
||||
The PRD sequences the orchestrator as a plain-process dev-harness first, so
|
||||
the consolidation core (registry + attribution + HTTP control plane + live
|
||||
@@ -16,14 +17,13 @@ import secrets
|
||||
from pathlib import Path
|
||||
|
||||
from .. import log
|
||||
from .store.store_manager import StoreManager
|
||||
from .broker import StubBroker, SubmitBroker
|
||||
from .broker_client import BrokerClient
|
||||
from .host_server import BROKER_SECRET_ENV, DEFAULT_PORT, broker_secret_from_env
|
||||
from .server import make_server
|
||||
from ..trust_domain import CONTROL_PLANE
|
||||
from .broker import LaunchBroker, StubBroker
|
||||
from .docker_broker import DockerBroker
|
||||
from .store.registry_store import RegistryStore, default_db_path
|
||||
from .server import make_server
|
||||
from .service import OrchestratorCore
|
||||
from .store.store_manager import StoreManager
|
||||
from .store.registry_store import RegistryStore, default_db_path
|
||||
|
||||
|
||||
def main(argv: list[str] | None = None) -> int:
|
||||
@@ -36,15 +36,15 @@ def main(argv: list[str] | None = None) -> int:
|
||||
help=f"registry DB path (default: {default_db_path()})",
|
||||
)
|
||||
parser.add_argument(
|
||||
"--broker", choices=("stub", "docker", "http"), default="stub",
|
||||
help="launch broker: 'stub' records requests; 'docker' runs containers "
|
||||
"in-process; 'http' relays signed requests to a host control server",
|
||||
)
|
||||
parser.add_argument(
|
||||
"--host-controller-url", default=f"http://127.0.0.1:{DEFAULT_PORT}",
|
||||
help="host control server URL (used only with --broker http)",
|
||||
"--broker", choices=("stub", "docker"), default="stub",
|
||||
help="launch broker: 'stub' records requests; 'docker' runs containers",
|
||||
)
|
||||
args = parser.parse_args(argv)
|
||||
if not CONTROL_PLANE.key_from_env():
|
||||
log.die(
|
||||
f"{CONTROL_PLANE.key_env} is required; refusing to start the "
|
||||
"orchestrator without caller authentication"
|
||||
)
|
||||
|
||||
registry = RegistryStore(args.db)
|
||||
registry.migrate()
|
||||
@@ -54,39 +54,22 @@ def main(argv: list[str] | None = None) -> int:
|
||||
# operator reaches it over HTTP (never a second, disconnected DB).
|
||||
StoreManager(registry.db_path).migrate()
|
||||
|
||||
# A signing secret ties the orchestrator (signer) to its broker (verifier).
|
||||
# 'stub' records launches instead of starting anything; 'docker' runs real
|
||||
# containers in-process; 'http' relays signed requests to a separate host
|
||||
# control server, which verifies and launches. For 'stub'/'docker' the
|
||||
# secret is ephemeral (signer and verifier share this process); for 'http'
|
||||
# it must be the SAME secret the host controller holds, so it is read from
|
||||
# the shared env var (the chunk-1 stand-in for out-of-band provisioning).
|
||||
broker: SubmitBroker
|
||||
if args.broker == "http":
|
||||
secret = broker_secret_from_env()
|
||||
if secret is None:
|
||||
parser.error(
|
||||
f"--broker http requires a shared signing secret in "
|
||||
f"${BROKER_SECRET_ENV} (hex), matching the host control server"
|
||||
)
|
||||
broker = BrokerClient(args.host_controller_url)
|
||||
else:
|
||||
secret = secrets.token_bytes(32)
|
||||
broker = DockerBroker(secret) if args.broker == "docker" else StubBroker(secret)
|
||||
# An ephemeral signing secret ties the orchestrator (signer) to its
|
||||
# broker (verifier). 'stub' records launches instead of starting
|
||||
# anything; 'docker' runs real containers (firecracker drops in later).
|
||||
secret = secrets.token_bytes(32)
|
||||
broker: LaunchBroker = DockerBroker(secret) if args.broker == "docker" else StubBroker(secret)
|
||||
orchestrator = OrchestratorCore(registry, broker, secret)
|
||||
|
||||
server = make_server(orchestrator, host=args.host, port=args.port)
|
||||
bound_host, bound_port = server.server_address[0], server.server_address[1]
|
||||
log.info(
|
||||
"orchestrator control plane listening",
|
||||
context={"host": bound_host, "port": bound_port, "db": str(registry.db_path)},
|
||||
context={"host": args.host, "port": args.port, "db": str(registry.db_path)},
|
||||
)
|
||||
try:
|
||||
server.serve_forever()
|
||||
server.run()
|
||||
except KeyboardInterrupt:
|
||||
log.info("orchestrator shutting down")
|
||||
finally:
|
||||
server.server_close()
|
||||
return 0
|
||||
|
||||
|
||||
|
||||
@@ -0,0 +1,374 @@
|
||||
"""FastAPI control-plane routes for the orchestrator."""
|
||||
# pyright: reportUnusedFunction=false
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import asyncio
|
||||
import math
|
||||
import sys
|
||||
from fastapi import FastAPI, HTTPException
|
||||
from fastapi.exceptions import RequestValidationError
|
||||
from fastapi.responses import JSONResponse
|
||||
from pydantic import BaseModel, ConfigDict, StrictStr
|
||||
from starlette.types import ASGIApp, Message, Receive, Scope, Send
|
||||
|
||||
from ..orchestrator_auth import ROLE_CLI, ROLES
|
||||
from ..supervisor.types import TOOLS
|
||||
from ..trust_domain import CONTROL_PLANE
|
||||
from .http_contract import (
|
||||
MAX_BODY_BYTES,
|
||||
ORCHESTRATOR_AUTH_HEADER,
|
||||
REQUEST_BODY_TIMEOUT_SECONDS,
|
||||
)
|
||||
from .service import OrchestratorCore
|
||||
|
||||
_GATEWAY_ROUTES = frozenset({
|
||||
("POST", "/resolve"),
|
||||
("POST", "/supervise/propose"),
|
||||
("POST", "/supervise/poll"),
|
||||
})
|
||||
|
||||
|
||||
class _StrictModel(BaseModel):
|
||||
model_config = ConfigDict(extra="ignore", strict=True)
|
||||
|
||||
|
||||
class LaunchBody(_StrictModel):
|
||||
source_ip: StrictStr
|
||||
image_ref: StrictStr = ""
|
||||
metadata: StrictStr = ""
|
||||
policy: StrictStr = ""
|
||||
tokens: dict[StrictStr, StrictStr] = {}
|
||||
env_var_secret: StrictStr = ""
|
||||
|
||||
|
||||
class PolicyBody(_StrictModel):
|
||||
policy: StrictStr
|
||||
|
||||
|
||||
class ReprovisionBody(_StrictModel):
|
||||
env_var_secret: StrictStr
|
||||
|
||||
|
||||
class SecretBody(_StrictModel):
|
||||
name: StrictStr
|
||||
value: StrictStr
|
||||
env_var_secret: StrictStr
|
||||
|
||||
|
||||
class ReconcileBody(_StrictModel):
|
||||
live_source_ips: list[StrictStr]
|
||||
grace_seconds: float | None = None
|
||||
|
||||
|
||||
class IdentityBody(_StrictModel):
|
||||
source_ip: StrictStr
|
||||
identity_token: StrictStr = ""
|
||||
|
||||
|
||||
class AttributeBody(_StrictModel):
|
||||
source_ip: StrictStr
|
||||
identity_token: StrictStr
|
||||
|
||||
|
||||
class RespondBody(_StrictModel):
|
||||
proposal_id: StrictStr
|
||||
bottle_slug: StrictStr
|
||||
decision: StrictStr
|
||||
notes: StrictStr = ""
|
||||
final_file: StrictStr | None = None
|
||||
|
||||
|
||||
class ProposeBody(IdentityBody):
|
||||
tool: StrictStr
|
||||
proposed_file: StrictStr
|
||||
justification: StrictStr
|
||||
|
||||
|
||||
class PollBody(IdentityBody):
|
||||
proposal_id: StrictStr
|
||||
|
||||
|
||||
class ControlPlaneBoundary:
|
||||
"""Reject unauthenticated and oversized requests before reading a body."""
|
||||
|
||||
def __init__(self, app: ASGIApp, signing_key: str) -> None:
|
||||
self.app = app
|
||||
self.signing_key = signing_key
|
||||
|
||||
async def __call__(self, scope: Scope, receive: Receive, send: Send) -> None:
|
||||
if scope["type"] != "http":
|
||||
await self.app(scope, receive, send)
|
||||
return
|
||||
method = scope["method"]
|
||||
route = scope["path"].rstrip("/") or "/"
|
||||
if not (method == "GET" and route == "/health"):
|
||||
headers = dict(scope["headers"])
|
||||
presented = headers.get(
|
||||
ORCHESTRATOR_AUTH_HEADER.encode(), b"",
|
||||
).decode(errors="ignore")
|
||||
role = CONTROL_PLANE.verify(presented, self.signing_key)
|
||||
if role is None:
|
||||
await self._reject(
|
||||
scope, send, 401, "control-plane authentication required",
|
||||
)
|
||||
return
|
||||
allowed = ROLES if (method, route) in _GATEWAY_ROUTES else {ROLE_CLI}
|
||||
if role not in allowed:
|
||||
await self._reject(scope, send, 403, "insufficient role for this route")
|
||||
return
|
||||
scope.setdefault("state", {})["role"] = role
|
||||
raw_length = dict(scope["headers"]).get(b"content-length")
|
||||
if raw_length is not None:
|
||||
try:
|
||||
length = int(raw_length)
|
||||
except ValueError:
|
||||
await self._reject(scope, send, 400, "invalid Content-Length")
|
||||
return
|
||||
if length < 0:
|
||||
await self._reject(scope, send, 400, "invalid Content-Length")
|
||||
return
|
||||
if length > MAX_BODY_BYTES:
|
||||
await self._reject(scope, send, 413, "request body too large")
|
||||
return
|
||||
try:
|
||||
body = await self._read_body(receive)
|
||||
except _BodyTooLarge:
|
||||
await self._reject(scope, send, 413, "request body too large")
|
||||
return
|
||||
except TimeoutError:
|
||||
await self._reject(scope, send, 408, "request body read timed out")
|
||||
return
|
||||
try:
|
||||
await self.app(scope, self._replay_body(body), send)
|
||||
except Exception as exc: # noqa: BLE001 - redact control-plane failures
|
||||
sys.stderr.write(
|
||||
f"orchestrator: {method} {route} failed "
|
||||
f"[error_type={type(exc).__name__}]\n"
|
||||
)
|
||||
sys.stderr.flush()
|
||||
await self._reject(scope, send, 500, "internal error")
|
||||
|
||||
@staticmethod
|
||||
async def _reject(
|
||||
scope: Scope, send: Send, status: int, error: str,
|
||||
) -> None:
|
||||
response = JSONResponse({"error": error}, status_code=status)
|
||||
await response(scope, ControlPlaneBoundary._empty_receive, send)
|
||||
|
||||
@staticmethod
|
||||
async def _empty_receive() -> Message:
|
||||
return {"type": "http.disconnect"}
|
||||
|
||||
@staticmethod
|
||||
async def _read_body(receive: Receive) -> bytes:
|
||||
body = bytearray()
|
||||
async with asyncio.timeout(REQUEST_BODY_TIMEOUT_SECONDS):
|
||||
while True:
|
||||
message = await receive()
|
||||
if message["type"] != "http.request":
|
||||
break
|
||||
body.extend(message.get("body", b""))
|
||||
if len(body) > MAX_BODY_BYTES:
|
||||
raise _BodyTooLarge
|
||||
if not message.get("more_body", False):
|
||||
break
|
||||
return bytes(body)
|
||||
|
||||
@staticmethod
|
||||
def _replay_body(body: bytes) -> Receive:
|
||||
sent = False
|
||||
|
||||
async def replay() -> Message:
|
||||
nonlocal sent
|
||||
if sent:
|
||||
return {"type": "http.disconnect"}
|
||||
sent = True
|
||||
return {"type": "http.request", "body": body, "more_body": False}
|
||||
|
||||
return replay
|
||||
|
||||
|
||||
class _BodyTooLarge(Exception):
|
||||
"""The streamed request exceeded the control-plane body limit."""
|
||||
|
||||
|
||||
def _required(value: str, name: str) -> str:
|
||||
if not value:
|
||||
raise HTTPException(400, f"{name} (string) is required")
|
||||
return value
|
||||
|
||||
|
||||
def create_app(orch: OrchestratorCore, *, signing_key: str) -> FastAPI:
|
||||
"""Build the authenticated orchestrator ASGI application."""
|
||||
key = signing_key.strip()
|
||||
if not key:
|
||||
raise ValueError(
|
||||
"orchestrator control-plane signing key is required; "
|
||||
"refusing to start without caller authentication"
|
||||
)
|
||||
app = FastAPI(
|
||||
title="bot-bottle orchestrator",
|
||||
docs_url=None,
|
||||
redoc_url=None,
|
||||
openapi_url=None,
|
||||
)
|
||||
app.add_middleware(ControlPlaneBoundary, signing_key=key)
|
||||
|
||||
@app.exception_handler(RequestValidationError)
|
||||
async def invalid_request(
|
||||
_request: object, exc: RequestValidationError,
|
||||
) -> JSONResponse:
|
||||
errors = exc.errors()
|
||||
location = errors[0].get("loc", ()) if errors else ()
|
||||
field = str(location[1]) if len(location) > 1 else ""
|
||||
suffix = f": {field}" if field else ""
|
||||
return JSONResponse(
|
||||
{"error": f"invalid request body{suffix}"},
|
||||
status_code=400,
|
||||
)
|
||||
|
||||
@app.get("/health")
|
||||
def health() -> dict[str, str]:
|
||||
return {"status": "ok"}
|
||||
|
||||
@app.get("/gateway")
|
||||
def gateway() -> dict[str, object]:
|
||||
return orch.gateway_status()
|
||||
|
||||
@app.get("/bottles")
|
||||
def bottles() -> dict[str, object]:
|
||||
return {"bottles": [record.redacted() for record in orch.registry.all()]}
|
||||
|
||||
@app.post("/bottles", status_code=201)
|
||||
def launch(body: LaunchBody) -> dict[str, str]:
|
||||
rec = orch.launch_bottle(
|
||||
_required(body.source_ip, "source_ip"),
|
||||
image_ref=body.image_ref,
|
||||
metadata=body.metadata,
|
||||
policy=body.policy,
|
||||
tokens=dict(body.tokens),
|
||||
env_var_secret=body.env_var_secret,
|
||||
)
|
||||
return {"bottle_id": rec.bottle_id, "identity_token": rec.identity_token}
|
||||
|
||||
@app.put("/bottles/{bottle_id}/policy")
|
||||
def set_policy(bottle_id: str, body: PolicyBody) -> dict[str, object]:
|
||||
if orch.set_policy(bottle_id, body.policy):
|
||||
return {"updated": True}
|
||||
raise HTTPException(404, "no such bottle")
|
||||
|
||||
@app.post("/bottles/{bottle_id}/reprovision_gateway")
|
||||
def reprovision(bottle_id: str, body: ReprovisionBody) -> dict[str, object]:
|
||||
secret = _required(body.env_var_secret, "env_var_secret")
|
||||
if orch.reprovision_from_secret(bottle_id, secret):
|
||||
return {"reprovisioned": True}
|
||||
raise HTTPException(404, "no stored secrets for this bottle")
|
||||
|
||||
@app.post("/bottles/{bottle_id}/secret")
|
||||
def update_secret(bottle_id: str, body: SecretBody) -> dict[str, object]:
|
||||
# Update ONE egress token for a running bottle in place — the
|
||||
# single-secret form of reprovision, for refreshing a short-lived host
|
||||
# credential (e.g. the Codex access token) without a relaunch. cli-only
|
||||
# (not in _GATEWAY_ROUTES): a bottle must never set its own tokens.
|
||||
if orch.update_agent_secret(
|
||||
bottle_id,
|
||||
_required(body.name, "name"),
|
||||
_required(body.value, "value"),
|
||||
_required(body.env_var_secret, "env_var_secret"),
|
||||
):
|
||||
return {"updated": True}
|
||||
raise HTTPException(404, "no such bottle")
|
||||
|
||||
@app.delete("/bottles/{bottle_id}")
|
||||
def teardown(bottle_id: str) -> dict[str, object]:
|
||||
if orch.teardown_bottle(bottle_id):
|
||||
return {"torn_down": True}
|
||||
raise HTTPException(404, "no such bottle")
|
||||
|
||||
@app.post("/reconcile")
|
||||
def reconcile(body: ReconcileBody) -> dict[str, object]:
|
||||
if any(not ip for ip in body.live_source_ips):
|
||||
raise HTTPException(400, "live_source_ips must contain non-empty strings")
|
||||
kwargs: dict[str, float] = {}
|
||||
if body.grace_seconds is not None:
|
||||
if not math.isfinite(body.grace_seconds) or body.grace_seconds < 0:
|
||||
raise HTTPException(
|
||||
400, "grace_seconds must be a non-negative finite number",
|
||||
)
|
||||
kwargs["grace_seconds"] = body.grace_seconds
|
||||
return {"reaped": orch.reconcile(body.live_source_ips, **kwargs)}
|
||||
|
||||
@app.post("/attribute")
|
||||
def attribute(body: AttributeBody) -> dict[str, str]:
|
||||
rec = orch.attribute(body.source_ip, body.identity_token)
|
||||
if rec is None:
|
||||
raise HTTPException(403, "unattributed")
|
||||
return {"bottle_id": rec.bottle_id}
|
||||
|
||||
@app.get("/supervise/proposals")
|
||||
def proposals() -> dict[str, object]:
|
||||
return {"proposals": orch.supervise_pending()}
|
||||
|
||||
@app.post("/supervise/respond")
|
||||
def respond(body: RespondBody) -> dict[str, object]:
|
||||
ok, error = orch.supervise_respond(
|
||||
_required(body.proposal_id, "proposal_id"),
|
||||
bottle_slug=_required(body.bottle_slug, "bottle_slug"),
|
||||
decision=_required(body.decision, "decision"),
|
||||
notes=body.notes,
|
||||
final_file=body.final_file,
|
||||
)
|
||||
if not ok:
|
||||
raise HTTPException(409, error)
|
||||
return {"responded": True}
|
||||
|
||||
@app.post("/supervise/propose", status_code=201)
|
||||
def propose(body: ProposeBody) -> dict[str, str]:
|
||||
source_ip = _required(body.source_ip, "source_ip")
|
||||
if body.tool not in TOOLS:
|
||||
raise HTTPException(400, f"tool (string) must be one of {TOOLS}")
|
||||
rec = orch.resolve(source_ip, body.identity_token)
|
||||
if rec is None:
|
||||
raise HTTPException(403, "unattributed")
|
||||
proposal_id = orch.supervise_queue_proposal(
|
||||
rec.bottle_id,
|
||||
tool=body.tool,
|
||||
proposed_file=_required(body.proposed_file, "proposed_file"),
|
||||
justification=_required(body.justification, "justification"),
|
||||
)
|
||||
return {"proposal_id": proposal_id}
|
||||
|
||||
@app.post("/supervise/poll")
|
||||
def poll(body: PollBody) -> dict[str, object]:
|
||||
rec = orch.resolve(
|
||||
_required(body.source_ip, "source_ip"), body.identity_token,
|
||||
)
|
||||
if rec is None:
|
||||
raise HTTPException(403, "unattributed")
|
||||
return orch.supervise_poll_response(
|
||||
rec.bottle_id, _required(body.proposal_id, "proposal_id"),
|
||||
)
|
||||
|
||||
@app.post("/resolve")
|
||||
def resolve(body: IdentityBody) -> dict[str, object]:
|
||||
rec = orch.resolve(
|
||||
_required(body.source_ip, "source_ip"), body.identity_token,
|
||||
)
|
||||
if rec is None:
|
||||
raise HTTPException(403, "unattributed")
|
||||
return {
|
||||
"bottle_id": rec.bottle_id,
|
||||
"policy": rec.policy,
|
||||
"tokens": orch.tokens_for(rec.bottle_id),
|
||||
}
|
||||
|
||||
return app
|
||||
|
||||
|
||||
__all__ = [
|
||||
"ControlPlaneBoundary",
|
||||
"MAX_BODY_BYTES",
|
||||
"ORCHESTRATOR_AUTH_HEADER",
|
||||
"create_app",
|
||||
]
|
||||
@@ -29,7 +29,6 @@ import json
|
||||
import secrets
|
||||
import time
|
||||
from dataclasses import dataclass
|
||||
from typing import Protocol
|
||||
|
||||
_JWT_HEADER = {"alg": "HS256", "typ": "JWT"}
|
||||
_ALLOWED_OPS = ("launch", "teardown")
|
||||
@@ -38,21 +37,7 @@ _ALLOWED_OPS = ("launch", "teardown")
|
||||
class BrokerAuthError(Exception):
|
||||
"""A broker request failed provenance or schema verification —
|
||||
bad/absent signature, malformed token, or a payload that doesn't match
|
||||
the fixed launch-request shape. Fail-closed: the broker must not act.
|
||||
|
||||
A **definite** negative: nothing was launched, so a caller may safely roll
|
||||
back as if the op never happened."""
|
||||
|
||||
|
||||
class BrokerUnavailableError(Exception):
|
||||
"""A brokered request could not be carried to a verdict: the broker (or the
|
||||
wire to it) was unreachable, timed out, or dropped the response.
|
||||
|
||||
Crucially **ambiguous** — unlike `BrokerAuthError`, the op MAY already have
|
||||
taken effect on the backend before the response was lost, so a caller must
|
||||
NOT assume it did nothing (e.g. must not roll a registry row back as if no
|
||||
launch happened, which would orphan a running container). Only the in-process
|
||||
brokers never raise this; the out-of-process `BrokerClient` does."""
|
||||
the fixed launch-request shape. Fail-closed: the broker must not act."""
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
@@ -138,16 +123,6 @@ def verify_request(token: str, secret: bytes) -> LaunchRequest:
|
||||
|
||||
# --- the broker itself ------------------------------------------------------
|
||||
|
||||
class SubmitBroker(Protocol):
|
||||
"""The single method `OrchestratorCore` depends on: verify a signed token and
|
||||
perform its op, returning the verified request. Both the in-process
|
||||
`LaunchBroker` and the out-of-process `BrokerClient` (which relays the token
|
||||
to the host control server) satisfy it structurally, so the core is unchanged
|
||||
whether the backend is local or a real host service."""
|
||||
|
||||
def submit(self, token: str) -> LaunchRequest: ...
|
||||
|
||||
|
||||
class LaunchBroker(abc.ABC):
|
||||
"""Verifies a signed request came from the orchestrator, then performs
|
||||
the backend-native launch/teardown. Subclasses implement `_launch` /
|
||||
@@ -193,9 +168,7 @@ class StubBroker(LaunchBroker):
|
||||
|
||||
__all__ = [
|
||||
"BrokerAuthError",
|
||||
"BrokerUnavailableError",
|
||||
"LaunchRequest",
|
||||
"SubmitBroker",
|
||||
"LaunchBroker",
|
||||
"StubBroker",
|
||||
"sign_request",
|
||||
|
||||
@@ -1,126 +0,0 @@
|
||||
"""Orchestrator-side broker transport (issue #468, chunk 1).
|
||||
|
||||
The signer's half of the launch-broker transport gap. `BrokerClient` satisfies
|
||||
the exact `submit(token)` contract `OrchestratorCore` already depends on (see
|
||||
`broker.SubmitBroker`), but instead of verifying and launching in-process it POSTs
|
||||
the signed token to the host control server over HTTP (stdlib `urllib`, like
|
||||
`orchestrator/client.py`). Because it is drop-in for that interface, wiring a real
|
||||
out-of-process backend does not change the core: it still signs a request and
|
||||
calls `submit()`; only the wire is new.
|
||||
|
||||
A provenance/schema rejection from the host controller (HTTP 401) is re-raised as
|
||||
the same `BrokerAuthError` the in-process broker raises, so the launch path's
|
||||
rollback-on-failure (`OrchestratorCore.launch_bottle`) behaves identically whether
|
||||
the broker is local or remote.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import json
|
||||
import urllib.error
|
||||
import urllib.request
|
||||
|
||||
from .broker import BrokerAuthError, BrokerUnavailableError, LaunchRequest
|
||||
|
||||
DEFAULT_TIMEOUT_SECONDS = 5.0
|
||||
|
||||
|
||||
class BrokerClientError(RuntimeError):
|
||||
"""The host control server *responded*, but with an unexpected status other
|
||||
than the fail-closed 401 (which surfaces as `BrokerAuthError`) — e.g. a 502
|
||||
backend failure or a malformed body. A definite negative: the host processed
|
||||
the request and it did not launch. (A *no-response* failure — unreachable /
|
||||
timeout / dropped — is the ambiguous `BrokerUnavailableError` instead.)"""
|
||||
|
||||
|
||||
class BrokerClient:
|
||||
"""Drop-in `submit(token)` that relays a signed request to the host control
|
||||
server. Holds no secret — provenance rides entirely in the signed token, so a
|
||||
caller that can reach this client still cannot forge a launch."""
|
||||
|
||||
def __init__(self, base_url: str, *, timeout: float = DEFAULT_TIMEOUT_SECONDS) -> None:
|
||||
self._base = base_url.rstrip("/")
|
||||
self._timeout = timeout
|
||||
|
||||
def submit(self, token: str) -> LaunchRequest:
|
||||
"""POST the signed token to the host controller and return the request it
|
||||
verified and acted on.
|
||||
|
||||
Raises `BrokerAuthError` on a fail-closed 401 (bad provenance/schema —
|
||||
the same exception the in-process broker raises); `BrokerClientError` if
|
||||
the host *responds* with any other non-success status or a malformed
|
||||
body (a definite negative); or `BrokerUnavailableError` if no response is
|
||||
obtained (unreachable / timeout / dropped) — the **ambiguous** case, where
|
||||
the host may already have acted, so the caller must not roll back."""
|
||||
data = json.dumps({"token": token}).encode()
|
||||
req = urllib.request.Request(
|
||||
f"{self._base}/broker", data=data, method="POST",
|
||||
headers={"Content-Type": "application/json"},
|
||||
)
|
||||
try:
|
||||
with urllib.request.urlopen(req, timeout=self._timeout) as resp:
|
||||
return _request_from(_json_object(resp.read()))
|
||||
except urllib.error.HTTPError as e:
|
||||
detail = _error_detail(e)
|
||||
if e.code == 401:
|
||||
raise BrokerAuthError(
|
||||
detail or "host controller rejected the request"
|
||||
) from e
|
||||
raise BrokerClientError(
|
||||
f"POST /broker: HTTP {e.code} {detail}".rstrip()
|
||||
) from e
|
||||
except (urllib.error.URLError, TimeoutError, OSError) as e:
|
||||
# No usable response — unreachable, timed out, or the connection
|
||||
# dropped mid-exchange. Ambiguous: the request may already have
|
||||
# launched the bottle, so this is NOT a definite failure.
|
||||
raise BrokerUnavailableError(f"POST /broker: {e}") from e
|
||||
|
||||
|
||||
def _json_object(raw: bytes) -> dict[str, object]:
|
||||
"""Parse a JSON object, tolerating an empty or malformed body (→ {}), like
|
||||
the orchestrator client — a bad body becomes a clean 'missing field' error
|
||||
downstream rather than an opaque JSON crash."""
|
||||
if not raw:
|
||||
return {}
|
||||
try:
|
||||
obj = json.loads(raw)
|
||||
except ValueError:
|
||||
return {}
|
||||
return obj if isinstance(obj, dict) else {}
|
||||
|
||||
|
||||
def _error_detail(e: urllib.error.HTTPError) -> str:
|
||||
"""The `error` string from a structured error response, best-effort — an
|
||||
error body may be absent or unreadable, in which case there is no detail."""
|
||||
try:
|
||||
detail = _json_object(e.read()).get("error", "")
|
||||
except Exception: # noqa: BLE001 — the error body is advisory only
|
||||
return ""
|
||||
return detail if isinstance(detail, str) else ""
|
||||
|
||||
|
||||
def _request_from(payload: dict[str, object]) -> LaunchRequest:
|
||||
"""Reconstruct the verified `LaunchRequest` the controller echoed, so the
|
||||
returned value matches the in-process broker's (which returns the request it
|
||||
acted on). A missing op/bottle_id means a malformed response."""
|
||||
op = payload.get("op")
|
||||
bottle_id = payload.get("bottle_id")
|
||||
if not isinstance(op, str) or not isinstance(bottle_id, str) or not bottle_id:
|
||||
raise BrokerClientError("host controller response missing op/bottle_id")
|
||||
source_ip = payload.get("source_ip")
|
||||
image_ref = payload.get("image_ref")
|
||||
slot = payload.get("slot")
|
||||
return LaunchRequest(
|
||||
op=op,
|
||||
bottle_id=bottle_id,
|
||||
source_ip=source_ip if isinstance(source_ip, str) else "",
|
||||
image_ref=image_ref if isinstance(image_ref, str) else "",
|
||||
slot=slot if isinstance(slot, int) and not isinstance(slot, bool) else None,
|
||||
)
|
||||
|
||||
|
||||
__all__ = [
|
||||
"BrokerClient",
|
||||
"BrokerClientError",
|
||||
"DEFAULT_TIMEOUT_SECONDS",
|
||||
]
|
||||
@@ -18,9 +18,10 @@ import urllib.request
|
||||
from collections.abc import Iterable
|
||||
from dataclasses import dataclass
|
||||
|
||||
from ..log import debug
|
||||
from ..orchestrator_auth import ROLE_CLI
|
||||
from ..trust_domain import CONTROL_PLANE
|
||||
from .server import ORCHESTRATOR_AUTH_HEADER
|
||||
from .http_contract import ORCHESTRATOR_AUTH_HEADER
|
||||
|
||||
DEFAULT_TIMEOUT_SECONDS = 5.0
|
||||
|
||||
@@ -53,6 +54,23 @@ class RegisteredBottle:
|
||||
env_var_secret: str = ""
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class BackendProbeFailure:
|
||||
"""Safe diagnostic for an optional backend discovery probe."""
|
||||
|
||||
backend: str
|
||||
error_type: str
|
||||
|
||||
|
||||
def _probe_failure(backend: str, exc: BaseException) -> BackendProbeFailure:
|
||||
failure = BackendProbeFailure(backend, type(exc).__name__)
|
||||
debug(
|
||||
"orchestrator discovery probe unavailable",
|
||||
context={"backend": failure.backend, "error_type": failure.error_type},
|
||||
)
|
||||
return failure
|
||||
|
||||
|
||||
class OrchestratorClient:
|
||||
"""Trusted host-side client for the orchestrator control plane.
|
||||
|
||||
@@ -166,6 +184,27 @@ class OrchestratorClient:
|
||||
)
|
||||
return True
|
||||
|
||||
def update_agent_secret(
|
||||
self, bottle_id: str, name: str, value: str, env_var_secret: str,
|
||||
) -> bool:
|
||||
"""Update ONE egress token for a running bottle in place
|
||||
(`POST /bottles/<id>/secret`) — the single-secret form of
|
||||
`reprovision_gateway`, for pushing a freshly-refreshed host credential
|
||||
into a bottle without a relaunch. Returns True on success, False when the
|
||||
orchestrator doesn't know the bottle (404)."""
|
||||
status, _ = self._request(
|
||||
"POST",
|
||||
f"/bottles/{bottle_id}/secret",
|
||||
{"name": name, "value": value, "env_var_secret": env_var_secret},
|
||||
)
|
||||
if status == 404:
|
||||
return False
|
||||
if not 200 <= status < 300:
|
||||
raise OrchestratorClientError(
|
||||
f"update_agent_secret {bottle_id}: HTTP {status}"
|
||||
)
|
||||
return True
|
||||
|
||||
def teardown_bottle(self, bottle_id: str) -> bool:
|
||||
"""Tear a bottle down (`DELETE /bottles/<id>`). False if the
|
||||
orchestrator didn't know it (404) — idempotent for cleanup paths."""
|
||||
@@ -245,32 +284,41 @@ def discover_orchestrator_url(*, timeout: float = 2.0) -> str:
|
||||
orchestrator TAP. Returns the first that answers `/health`; raises if none
|
||||
do (no orchestrator up — launch a bottle first)."""
|
||||
candidates: list[str] = []
|
||||
failures: list[BackendProbeFailure] = []
|
||||
try: # docker: loopback-published control plane
|
||||
from .lifecycle import DEFAULT_PORT as _DOCKER_PORT
|
||||
candidates.append(f"http://127.0.0.1:{_DOCKER_PORT}")
|
||||
except Exception: # noqa: BLE001 — backend optional
|
||||
except Exception as exc: # noqa: BLE001 — backend optional
|
||||
failures.append(_probe_failure("docker", exc))
|
||||
candidates.append("http://127.0.0.1:8099")
|
||||
try: # firecracker: infra VM control plane on the orchestrator TAP
|
||||
from ..backend.firecracker import netpool
|
||||
from ..backend.firecracker.infra_vm import ORCHESTRATOR_PORT
|
||||
candidates.append(
|
||||
f"http://{netpool.orch_slot().guest_ip}:{ORCHESTRATOR_PORT}")
|
||||
except Exception: # noqa: BLE001 — backend optional / not firecracker
|
||||
pass
|
||||
except Exception as exc: # noqa: BLE001 — backend optional / not firecracker
|
||||
failures.append(_probe_failure("firecracker", exc))
|
||||
try: # macOS: orchestrator container on its host-only address
|
||||
from ..backend.macos_container.infra import probe_orchestrator_url
|
||||
url = probe_orchestrator_url()
|
||||
if url:
|
||||
candidates.append(url)
|
||||
except Exception: # noqa: BLE001 — backend optional / not macOS
|
||||
pass
|
||||
except Exception as exc: # noqa: BLE001 — backend optional / not macOS
|
||||
failures.append(_probe_failure("macos-container", exc))
|
||||
for url in candidates:
|
||||
if OrchestratorClient(url, timeout=timeout).health():
|
||||
return url
|
||||
detail = ""
|
||||
if failures:
|
||||
detail = "; optional probes unavailable: " + ", ".join(
|
||||
f"{failure.backend} ({failure.error_type})" for failure in failures
|
||||
)
|
||||
raise OrchestratorClientError(
|
||||
"no running orchestrator control plane found (tried "
|
||||
+ ", ".join(candidates)
|
||||
+ "); launch a bottle first"
|
||||
+ ")"
|
||||
+ detail
|
||||
+ "; launch a bottle first"
|
||||
)
|
||||
|
||||
|
||||
|
||||
@@ -1,270 +0,0 @@
|
||||
"""Host control server (issue #468) — the launch broker as a real host service.
|
||||
|
||||
Chunk 1 of the host-control-server stack closes the **transport** gap the PRD
|
||||
opens with: today `LaunchBroker.submit(token)` is an in-process method call from
|
||||
`OrchestratorCore`, and a real host service needs it reachable over the wire.
|
||||
This module is that service — the single privileged host component — reached over
|
||||
**HTTP** (the universal transport 0070 chose), mirroring the orchestrator control
|
||||
plane's shape (`orchestrator/server.py`): a pure `dispatch()` for socket-free
|
||||
testing, wrapped by a thin stdlib `http.server` adapter.
|
||||
|
||||
GET /health -> 200 {"status": "ok"}
|
||||
POST /broker -> 200 {"op", "bottle_id", "source_ip", "image_ref", "slot"}
|
||||
400 (bad body) | 401 (bad provenance/schema) | 502 (backend)
|
||||
body: {"token": "<signed launch/teardown JWT>"}
|
||||
|
||||
Only the **signed token** crosses the wire; the server holds the shared HS256
|
||||
secret and a real `LaunchBroker` (e.g. `DockerBroker`) and runs the existing
|
||||
`verify_request` + `_launch`/`_teardown` path behind the endpoint, so nothing
|
||||
free-form ever reaches it. Provenance/schema failures are fail-closed 401s that
|
||||
never touch the backend (`LaunchBroker.submit` verifies before acting), and a
|
||||
backend launch failure is a 502 the caller must surface — neither takes the
|
||||
controller down.
|
||||
|
||||
The signed launch token *is* the endpoint's authentication (its provenance is the
|
||||
whole point of the JWS), so `/broker` needs no separate caller credential; the
|
||||
host controller's own lifecycle endpoints, which do, arrive with the durable
|
||||
`TrustDomain` key in a later chunk.
|
||||
|
||||
The shared signing secret is read from `$BOT_BOTTLE_BROKER_SECRET` (hex). That is
|
||||
a **chunk-1 stopgap**: it must be provisioned to signer and verifier out of band,
|
||||
which is exactly what the durable `TrustDomain` key in chunk 2 (#476) replaces.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import argparse
|
||||
import http.server
|
||||
import json
|
||||
import os
|
||||
import socketserver
|
||||
import sys
|
||||
import typing
|
||||
from urllib.parse import urlsplit
|
||||
|
||||
from .. import log
|
||||
from .broker import BrokerAuthError, LaunchBroker
|
||||
from .docker_broker import DockerBroker
|
||||
|
||||
# JSON body payload type (parsed request / rendered response).
|
||||
Json = dict[str, object]
|
||||
|
||||
# The hex-encoded HS256 secret shared with the request signer (the orchestrator).
|
||||
# Chunk-1 stopgap for the durable, out-of-band `TrustDomain` key of chunk 2.
|
||||
BROKER_SECRET_ENV = "BOT_BOTTLE_BROKER_SECRET"
|
||||
|
||||
# Default host-controller port. Distinct from the orchestrator control plane
|
||||
# (8099) — a separate privileged component listening on its own socket.
|
||||
DEFAULT_PORT = 8091
|
||||
|
||||
# Cap on the request body. A signed broker request is tiny, so rejecting anything
|
||||
# larger *before reading it* keeps a caller that can merely reach the socket (no
|
||||
# signed token needed) from exhausting memory or a handler thread with a huge
|
||||
# Content-Length — the signed token, not mere reachability, is the authority.
|
||||
MAX_BODY_BYTES = 64 * 1024
|
||||
|
||||
# Per-request socket timeout, bounding how long a stalled / slow-loris caller can
|
||||
# hold a handler thread on this privileged listener.
|
||||
REQUEST_TIMEOUT_SECONDS = 15
|
||||
|
||||
|
||||
def _parse_json_object(body: bytes) -> Json:
|
||||
"""Parse a JSON object body. Raises ValueError for non-objects / bad JSON."""
|
||||
if not body:
|
||||
return {}
|
||||
obj = json.loads(body) # raises json.JSONDecodeError (a ValueError)
|
||||
if not isinstance(obj, dict):
|
||||
raise ValueError("request body must be a JSON object")
|
||||
return obj
|
||||
|
||||
|
||||
def broker_secret_from_env(environ: typing.Mapping[str, str] | None = None) -> bytes | None:
|
||||
"""The shared HS256 secret from `$BOT_BOTTLE_BROKER_SECRET` (hex), or None
|
||||
when unset or not valid hex. The signer (orchestrator, `--broker http`) and
|
||||
the verifier (this server) read the same env var so both hold the same key —
|
||||
the chunk-1 stand-in for out-of-band provisioning."""
|
||||
env = os.environ if environ is None else environ
|
||||
raw = env.get(BROKER_SECRET_ENV, "").strip()
|
||||
if not raw:
|
||||
return None
|
||||
try:
|
||||
return bytes.fromhex(raw)
|
||||
except ValueError:
|
||||
return None
|
||||
|
||||
|
||||
def dispatch( # pylint: disable=too-many-return-statements
|
||||
broker: LaunchBroker, method: str, path: str, body: bytes,
|
||||
) -> tuple[int, Json]:
|
||||
"""Route one host-control request to a (status, payload) pair. Pure — the
|
||||
only side effect is the broker's own backend launch — so routing is testable
|
||||
without a socket.
|
||||
|
||||
Total by design: a provenance/schema failure becomes 401 and a backend launch
|
||||
failure becomes 502 rather than raising, so one bad request can neither act
|
||||
on the backend nor take the controller down for the next caller."""
|
||||
route = urlsplit(path).path.rstrip("/") or "/"
|
||||
|
||||
if method == "GET" and route == "/health":
|
||||
return 200, {"status": "ok"}
|
||||
|
||||
if method == "POST" and route == "/broker":
|
||||
try:
|
||||
data = _parse_json_object(body)
|
||||
except ValueError as e:
|
||||
return 400, {"error": f"invalid JSON: {e}"}
|
||||
token = data.get("token")
|
||||
if not isinstance(token, str) or not token:
|
||||
return 400, {"error": "token (string) is required"}
|
||||
try:
|
||||
req = broker.submit(token)
|
||||
except BrokerAuthError as e:
|
||||
# Fail-closed: bad signature, malformed token, or off-schema payload.
|
||||
# `submit` verifies before acting, so nothing was launched.
|
||||
return 401, {"error": f"broker auth failed: {e}"}
|
||||
except Exception as e: # noqa: BLE001 — a backend launch failure (docker
|
||||
# down, image gone) is operational, not a control-plane bug; the
|
||||
# caller must see it as a distinct 502, and the server must stay up.
|
||||
return 502, {"error": f"backend launch failed: {e}"}
|
||||
return 200, {
|
||||
"op": req.op,
|
||||
"bottle_id": req.bottle_id,
|
||||
"source_ip": req.source_ip,
|
||||
"image_ref": req.image_ref,
|
||||
"slot": req.slot,
|
||||
}
|
||||
|
||||
return 404, {"error": "not found"}
|
||||
|
||||
|
||||
class Handler(http.server.BaseHTTPRequestHandler):
|
||||
"""Thin stdlib adapter: read the body, call `dispatch`, write JSON."""
|
||||
|
||||
# Socket timeout per request (applied by StreamRequestHandler.setup) so a
|
||||
# stalled caller can't pin a handler thread on this privileged listener.
|
||||
timeout = REQUEST_TIMEOUT_SECONDS
|
||||
|
||||
# Quiet by default; opt back into stdlib access logging with
|
||||
# BOT_BOTTLE_HOST_CONTROLLER_DEBUG (the controller has its own logging).
|
||||
def log_message(self, format: str, *args: typing.Any) -> None: # noqa: A002
|
||||
if os.environ.get("BOT_BOTTLE_HOST_CONTROLLER_DEBUG"):
|
||||
super().log_message(format, *args)
|
||||
|
||||
def _serve(self, method: str) -> None:
|
||||
"""Read the request body (bounded), dispatch it, and write the JSON
|
||||
reply. A dispatch that raises (it shouldn't — dispatch is total) still
|
||||
returns a 500 rather than dropping the connection."""
|
||||
server = self.server
|
||||
assert isinstance(server, HostControlServer)
|
||||
try:
|
||||
length = int(self.headers.get("Content-Length") or 0)
|
||||
except ValueError:
|
||||
self._reply(400, {"error": "invalid Content-Length"})
|
||||
return
|
||||
if length < 0 or length > MAX_BODY_BYTES:
|
||||
# Reject before reading: nothing legitimate is this big, so an
|
||||
# oversized declared length is a bug or a resource-exhaustion attempt.
|
||||
self._reply(413, {"error": "request body too large"})
|
||||
return
|
||||
body = self.rfile.read(length) if length > 0 else b""
|
||||
try:
|
||||
status, payload = dispatch(server.broker, method, self.path, body)
|
||||
except Exception as e: # noqa: BLE001 — the controller must stay up
|
||||
sys.stderr.write(f"host controller: {method} {self.path} failed: {e!r}\n")
|
||||
sys.stderr.flush()
|
||||
status, payload = 500, {"error": f"internal error: {e}"}
|
||||
self._reply(status, payload)
|
||||
|
||||
def _reply(self, status: int, payload: typing.Mapping[str, object]) -> None:
|
||||
"""Write one JSON response with an explicit Content-Length."""
|
||||
data = json.dumps(payload).encode()
|
||||
self.send_response(status)
|
||||
self.send_header("Content-Type", "application/json")
|
||||
self.send_header("Content-Length", str(len(data)))
|
||||
self.end_headers()
|
||||
self.wfile.write(data)
|
||||
|
||||
def do_GET(self) -> None:
|
||||
self._serve("GET")
|
||||
|
||||
def do_POST(self) -> None:
|
||||
self._serve("POST")
|
||||
|
||||
|
||||
class HostControlServer(socketserver.ThreadingMixIn, http.server.HTTPServer):
|
||||
"""Threading HTTP server that carries the launch broker for its handlers.
|
||||
|
||||
The broker holds the shared signing secret and performs the backend-native
|
||||
launch/teardown; the server itself keeps no secret of its own — provenance
|
||||
rides entirely in each request's signed token."""
|
||||
|
||||
daemon_threads = True
|
||||
allow_reuse_address = True
|
||||
|
||||
def __init__(self, address: tuple[str, int], broker: LaunchBroker) -> None:
|
||||
self.broker = broker
|
||||
super().__init__(address, Handler)
|
||||
|
||||
|
||||
def make_host_server(
|
||||
broker: LaunchBroker, host: str = "127.0.0.1", port: int = DEFAULT_PORT
|
||||
) -> HostControlServer:
|
||||
"""Build (but do not start) a host control server. `port=0` binds an
|
||||
ephemeral port — read `server.server_address` for the actual one."""
|
||||
return HostControlServer((host, port), broker)
|
||||
|
||||
|
||||
def main(argv: list[str] | None = None) -> int:
|
||||
"""Run the host control server as a plain process (dev-harness).
|
||||
|
||||
python -m bot_bottle.orchestrator.host_server [--host H] [--port P]
|
||||
|
||||
Fail-closed: without a shared `$BOT_BOTTLE_BROKER_SECRET` the server can
|
||||
verify no request's provenance, so it refuses to start rather than run a
|
||||
launcher that accepts unsigned input."""
|
||||
parser = argparse.ArgumentParser(prog="bot_bottle.orchestrator.host_server")
|
||||
parser.add_argument("--host", default="127.0.0.1", help="bind address")
|
||||
parser.add_argument("--port", type=int, default=DEFAULT_PORT, help="bind port (0 = ephemeral)")
|
||||
args = parser.parse_args(argv)
|
||||
|
||||
secret = broker_secret_from_env()
|
||||
if secret is None:
|
||||
sys.stderr.write(
|
||||
f"host controller: refusing to start without a shared signing secret "
|
||||
f"(${BROKER_SECRET_ENV}, hex) — it could verify no request's "
|
||||
"provenance and would relay unsigned launches to the backend\n"
|
||||
)
|
||||
sys.stderr.flush()
|
||||
return 2
|
||||
|
||||
broker = DockerBroker(secret)
|
||||
server = make_host_server(broker, host=args.host, port=args.port)
|
||||
bound_host, bound_port = server.server_address[0], server.server_address[1]
|
||||
log.info(
|
||||
"host control server listening",
|
||||
context={"host": bound_host, "port": bound_port},
|
||||
)
|
||||
try:
|
||||
server.serve_forever()
|
||||
except KeyboardInterrupt:
|
||||
log.info("host controller shutting down")
|
||||
finally:
|
||||
server.server_close()
|
||||
return 0
|
||||
|
||||
|
||||
__all__ = [
|
||||
"dispatch",
|
||||
"Handler",
|
||||
"HostControlServer",
|
||||
"make_host_server",
|
||||
"broker_secret_from_env",
|
||||
"main",
|
||||
"Json",
|
||||
"BROKER_SECRET_ENV",
|
||||
"DEFAULT_PORT",
|
||||
]
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
raise SystemExit(main())
|
||||
@@ -0,0 +1,11 @@
|
||||
"""Dependency-free constants shared by orchestrator HTTP clients and server."""
|
||||
|
||||
ORCHESTRATOR_AUTH_HEADER = "x-bot-bottle-orchestrator-auth"
|
||||
MAX_BODY_BYTES = 1 * 1024 * 1024
|
||||
REQUEST_BODY_TIMEOUT_SECONDS = 10.0
|
||||
|
||||
__all__ = [
|
||||
"MAX_BODY_BYTES",
|
||||
"ORCHESTRATOR_AUTH_HEADER",
|
||||
"REQUEST_BODY_TIMEOUT_SECONDS",
|
||||
]
|
||||
@@ -2,6 +2,7 @@
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
from ..log import debug
|
||||
from .client import OrchestratorClient, OrchestratorClientError
|
||||
|
||||
|
||||
@@ -27,7 +28,14 @@ def reprovision_bottles(
|
||||
try:
|
||||
if client.reprovision_gateway(bottle_id, secret):
|
||||
restored += 1
|
||||
except OrchestratorClientError:
|
||||
except OrchestratorClientError as exc:
|
||||
debug(
|
||||
"gateway secret reprovision failed; continuing with other bottles",
|
||||
context={
|
||||
"bottle_id": bottle_id,
|
||||
"error_type": type(exc).__name__,
|
||||
},
|
||||
)
|
||||
continue
|
||||
return restored
|
||||
|
||||
|
||||
@@ -1,452 +1,80 @@
|
||||
"""Orchestrator HTTP control plane (PRD 0070).
|
||||
|
||||
The backend-agnostic control-plane RPC (CLI / console -> orchestrator) over
|
||||
**HTTP** — the universal transport chosen in 0070 (works on every host; no
|
||||
vsock / unix-socket portability caveats):
|
||||
|
||||
GET /health -> 200 {"status": "ok"}
|
||||
GET /gateway -> 200 {"configured", ["name","running"]}
|
||||
GET /bottles -> 200 {"bottles": [ <redacted record>, ...]}
|
||||
POST /bottles -> 201 {"bottle_id","identity_token"} (launch)
|
||||
body: {"source_ip", ["image_ref"],
|
||||
["metadata"], ["policy"],
|
||||
["tokens"], ["env_var_secret"]}
|
||||
PUT /bottles/<bottle_id>/policy -> 200 {"updated": true} | 404 (live reload)
|
||||
body: {"policy"}
|
||||
POST /bottles/<bottle_id>/reprovision_gateway
|
||||
-> 200 {"reprovisioned": true} | 404
|
||||
body: {"env_var_secret"}
|
||||
DELETE /bottles/<bottle_id> -> 200 {"torn_down": true} | 404 (teardown)
|
||||
POST /reconcile -> 200 {"reaped": [bottle_id, ...]}
|
||||
body: {"live_source_ips": [...],
|
||||
["grace_seconds"]}
|
||||
POST /attribute -> 200 {"bottle_id"} | 403
|
||||
POST /resolve -> 200 {"bottle_id","policy"} | 403
|
||||
body: {"source_ip","identity_token"}
|
||||
GET /supervise/proposals -> 200 {"proposals": [ <proposal>, ...]}
|
||||
POST /supervise/respond -> 200 {"responded": true} | 409 (operator)
|
||||
body: {"proposal_id","bottle_slug",
|
||||
"decision", ["notes"],["final_file"]}
|
||||
POST /supervise/propose -> 201 {"proposal_id"} | 403 (agent)
|
||||
body: {"source_ip","identity_token",
|
||||
"tool","proposed_file","justification"}
|
||||
POST /supervise/poll -> 200 {"status", ["notes"],["final_file"]} | 403
|
||||
body: {"source_ip","identity_token",
|
||||
"proposal_id"}
|
||||
|
||||
The `/supervise/propose` + `/supervise/poll` pair is the **agent** half of the
|
||||
supervise flow: the data plane (supervise / egress / git-gate) queues a proposal
|
||||
and polls for its response over RPC instead of opening `bot-bottle.db` directly.
|
||||
`poll` is idempotent — it never archives, so a dropped connection can't lose an
|
||||
operator decision (the row is reaped when the bottle is torn down / reconciled).
|
||||
Both attribute the caller by `(source_ip, identity_token)` exactly like
|
||||
`/resolve`, so a bottle can only ever queue or read its own proposals.
|
||||
|
||||
`POST /bottles` / `DELETE` drive the full launch lifecycle: they mint (or
|
||||
tear down) the bottle in the registry AND broker the backend-native launch
|
||||
via the orchestrator. Register/deregister without a launch are internal to
|
||||
`OrchestratorCore`, not exposed here.
|
||||
|
||||
Routing/handling is the pure function `dispatch()` so it is unit-testable
|
||||
without a socket; `Handler` / `OrchestratorServer` / `make_server` are a
|
||||
thin stdlib adapter around it. Listing redacts identity tokens — they are
|
||||
returned only once, to the caller that launches the bottle.
|
||||
"""
|
||||
"""Uvicorn transport for the FastAPI orchestrator control plane."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import http.server
|
||||
import json
|
||||
import os
|
||||
import socketserver
|
||||
import sys
|
||||
import typing
|
||||
from urllib.parse import urlsplit
|
||||
import socket
|
||||
import threading
|
||||
|
||||
import uvicorn
|
||||
|
||||
from ..orchestrator_auth import ROLE_CLI, ROLES
|
||||
from ..trust_domain import CONTROL_PLANE
|
||||
from ..supervisor.types import TOOLS
|
||||
from .api import create_app
|
||||
from .http_contract import MAX_BODY_BYTES, ORCHESTRATOR_AUTH_HEADER
|
||||
from .service import OrchestratorCore
|
||||
|
||||
# JSON body payload type (parsed request / rendered response).
|
||||
Json = dict[str, object]
|
||||
|
||||
# The request header carrying the caller's role-scoped control-plane token (a
|
||||
# signed JWT naming the caller's role — see orchestrator_auth). The role gates which
|
||||
# routes the caller may reach: the data plane holds a `gateway` token good only
|
||||
# for the agent-facing lookups; the host CLI holds a `cli` token for the
|
||||
# operator/mutating routes. An agent that can merely *reach* the port holds no
|
||||
# token at all, and a compromised gateway holds only `gateway` — neither can
|
||||
# drive the operator routes (approve proposals, rewrite policy, read tokens).
|
||||
ORCHESTRATOR_AUTH_HEADER = "x-bot-bottle-orchestrator-auth"
|
||||
|
||||
# The routes the data plane (role `gateway`) is allowed to reach — exactly the
|
||||
# per-request lookups PolicyResolver makes. Every other authenticated route is
|
||||
# operator-only. `cli` is a superset role: it may reach any route.
|
||||
_GATEWAY_ROUTES: frozenset[tuple[str, str]] = frozenset({
|
||||
("POST", "/resolve"),
|
||||
("POST", "/supervise/propose"),
|
||||
("POST", "/supervise/poll"),
|
||||
})
|
||||
MAX_REQUESTS = 32
|
||||
KEEP_ALIVE_TIMEOUT_SECONDS = 10
|
||||
|
||||
|
||||
def _allowed_roles(method: str, route: str) -> frozenset[str]:
|
||||
"""The roles permitted on `(method, route)`: `gateway` or `cli` on the
|
||||
data-plane routes, `cli`-only everywhere else."""
|
||||
if (method, route) in _GATEWAY_ROUTES:
|
||||
return ROLES
|
||||
return frozenset({ROLE_CLI})
|
||||
class OrchestratorServer:
|
||||
"""Small lifecycle wrapper around Uvicorn with an eagerly bound socket."""
|
||||
|
||||
def __init__(self, config: uvicorn.Config) -> None:
|
||||
self._server = uvicorn.Server(config)
|
||||
self._stopped = threading.Event()
|
||||
self._socket = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
|
||||
self._socket.setsockopt(socket.SOL_SOCKET, socket.SO_REUSEADDR, 1)
|
||||
self._socket.bind((config.host, config.port))
|
||||
self._socket.listen(config.backlog)
|
||||
self.server_address = self._socket.getsockname()
|
||||
|
||||
def _parse_json_object(body: bytes) -> Json:
|
||||
"""Parse a JSON object body. Raises ValueError for non-objects / bad JSON."""
|
||||
if not body:
|
||||
return {}
|
||||
obj = json.loads(body) # raises json.JSONDecodeError (a ValueError)
|
||||
if not isinstance(obj, dict):
|
||||
raise ValueError("request body must be a JSON object")
|
||||
return obj
|
||||
|
||||
|
||||
def dispatch( # pylint: disable=too-many-return-statements,too-many-branches
|
||||
orch: OrchestratorCore, method: str, path: str, body: bytes, *, role: str | None = ROLE_CLI,
|
||||
) -> tuple[int, Json]:
|
||||
"""Route one control-plane request to a (status, payload) pair. Pure —
|
||||
no I/O beyond the orchestrator — so it is fully testable without a socket.
|
||||
|
||||
`role` is the caller's verified control-plane role (`gateway` or `cli`), or
|
||||
None for an unauthenticated request; an open-mode server (no signing key
|
||||
configured — see `OrchestratorServer`) passes `cli`. Every route except
|
||||
`GET /health` requires a role: a missing role is 401, and a role that
|
||||
doesn't cover the route is 403 — so a `gateway` data-plane token can reach
|
||||
`/resolve` + `/supervise/{propose,poll}` but not the operator routes
|
||||
(rewrite policy, read injected tokens, approve its own supervise proposals).
|
||||
The source-IP + identity-token checks inside `/resolve` and `/attribute`
|
||||
authenticate the *bottle* a request is about, not the *caller*, so this role
|
||||
gate is what protects the caller-privileged routes. Defaults `cli` so unit
|
||||
tests of the routing logic don't have to thread it through."""
|
||||
route = urlsplit(path).path.rstrip("/") or "/"
|
||||
|
||||
if method == "GET" and route == "/health":
|
||||
return 200, {"status": "ok"}
|
||||
|
||||
# Role gate — every route below is a trusted-caller operation. Deny before
|
||||
# touching the registry / broker / supervise store.
|
||||
if role is None:
|
||||
return 401, {"error": "control-plane authentication required"}
|
||||
if role not in _allowed_roles(method, route):
|
||||
return 403, {"error": "insufficient role for this route"}
|
||||
|
||||
if method == "GET" and route == "/gateway":
|
||||
return 200, orch.gateway_status()
|
||||
|
||||
if method == "GET" and route == "/bottles":
|
||||
return 200, {"bottles": [r.redacted() for r in orch.registry.all()]}
|
||||
|
||||
if method == "POST" and route == "/bottles":
|
||||
def run(self) -> None:
|
||||
try:
|
||||
data = _parse_json_object(body)
|
||||
except ValueError as e:
|
||||
return 400, {"error": f"invalid JSON: {e}"}
|
||||
source_ip = data.get("source_ip")
|
||||
if not isinstance(source_ip, str) or not source_ip:
|
||||
return 400, {"error": "source_ip (string) is required"}
|
||||
image_ref = data.get("image_ref")
|
||||
metadata = data.get("metadata")
|
||||
policy = data.get("policy")
|
||||
raw_tokens = data.get("tokens")
|
||||
tokens = {
|
||||
k: v for k, v in raw_tokens.items() if isinstance(k, str) and isinstance(v, str)
|
||||
} if isinstance(raw_tokens, dict) else {}
|
||||
env_var_secret = data.get("env_var_secret", "")
|
||||
rec = orch.launch_bottle(
|
||||
source_ip,
|
||||
image_ref=image_ref if isinstance(image_ref, str) else "",
|
||||
metadata=metadata if isinstance(metadata, str) else "",
|
||||
policy=policy if isinstance(policy, str) else "",
|
||||
tokens=tokens,
|
||||
env_var_secret=env_var_secret if isinstance(env_var_secret, str) else "",
|
||||
)
|
||||
return 201, {"bottle_id": rec.bottle_id, "identity_token": rec.identity_token}
|
||||
self._server.run(sockets=[self._socket])
|
||||
finally:
|
||||
self._stopped.set()
|
||||
|
||||
if method == "PUT" and route.startswith("/bottles/") and route.endswith("/policy"):
|
||||
bottle_id = route[len("/bottles/"):-len("/policy")]
|
||||
try:
|
||||
data = _parse_json_object(body)
|
||||
except ValueError as e:
|
||||
return 400, {"error": f"invalid JSON: {e}"}
|
||||
policy = data.get("policy")
|
||||
if not isinstance(policy, str):
|
||||
return 400, {"error": "policy (string) is required"}
|
||||
if orch.set_policy(bottle_id, policy):
|
||||
return 200, {"updated": True}
|
||||
return 404, {"error": "no such bottle"}
|
||||
def serve_forever(self) -> None:
|
||||
self.run()
|
||||
|
||||
if (
|
||||
method == "POST"
|
||||
and route.startswith("/bottles/")
|
||||
and route.endswith("/reprovision_gateway")
|
||||
):
|
||||
bottle_id = route[len("/bottles/") : -len("/reprovision_gateway")]
|
||||
try:
|
||||
data = _parse_json_object(body)
|
||||
except ValueError as e:
|
||||
return 400, {"error": f"invalid JSON: {e}"}
|
||||
env_var_secret = data.get("env_var_secret")
|
||||
if not isinstance(env_var_secret, str) or not env_var_secret:
|
||||
return 400, {"error": "env_var_secret (string) is required"}
|
||||
if orch.reprovision_from_secret(bottle_id, env_var_secret):
|
||||
return 200, {"reprovisioned": True}
|
||||
return 404, {"error": "no stored secrets for this bottle"}
|
||||
def shutdown(self) -> None:
|
||||
self._server.should_exit = True
|
||||
self._stopped.wait(timeout=5)
|
||||
|
||||
if method == "DELETE" and route.startswith("/bottles/"):
|
||||
bottle_id = route[len("/bottles/"):]
|
||||
if orch.teardown_bottle(bottle_id):
|
||||
return 200, {"torn_down": True}
|
||||
return 404, {"error": "no such bottle"}
|
||||
|
||||
if method == "POST" and route == "/reconcile":
|
||||
# Host-driven self-heal: the caller enumerates its live bottles (only
|
||||
# the host can see the backend) and the orchestrator drops rows for
|
||||
# every other active bottle. Trusted-caller only — an agent that could
|
||||
# reach this would be able to unregister its neighbours.
|
||||
try:
|
||||
data = _parse_json_object(body)
|
||||
except ValueError as e:
|
||||
return 400, {"error": f"invalid JSON: {e}"}
|
||||
raw_ips = data.get("live_source_ips")
|
||||
if not isinstance(raw_ips, list):
|
||||
return 400, {"error": "live_source_ips (list of strings) is required"}
|
||||
live = [ip for ip in raw_ips if isinstance(ip, str) and ip]
|
||||
grace = data.get("grace_seconds")
|
||||
kwargs = (
|
||||
{"grace_seconds": float(grace)}
|
||||
if isinstance(grace, (int, float)) and not isinstance(grace, bool)
|
||||
else {}
|
||||
)
|
||||
return 200, {"reaped": orch.reconcile(live, **kwargs)}
|
||||
|
||||
if method == "POST" and route == "/attribute":
|
||||
try:
|
||||
data = _parse_json_object(body)
|
||||
except ValueError as e:
|
||||
return 400, {"error": f"invalid JSON: {e}"}
|
||||
source_ip = data.get("source_ip")
|
||||
token = data.get("identity_token")
|
||||
if not isinstance(source_ip, str) or not isinstance(token, str):
|
||||
return 400, {"error": "source_ip and identity_token (strings) required"}
|
||||
rec = orch.attribute(source_ip, token)
|
||||
if rec is None:
|
||||
return 403, {"error": "unattributed"}
|
||||
return 200, {"bottle_id": rec.bottle_id}
|
||||
|
||||
if method == "GET" and route == "/supervise/proposals":
|
||||
# Operator TUI: pending supervise proposals across all bottles.
|
||||
return 200, {"proposals": orch.supervise_pending()}
|
||||
|
||||
if method == "POST" and route == "/supervise/respond":
|
||||
# Operator decision: apply (approve/modify rewrites egress policy),
|
||||
# write the queued response, audit — all server-side on the one DB.
|
||||
try:
|
||||
data = _parse_json_object(body)
|
||||
except ValueError as e:
|
||||
return 400, {"error": f"invalid JSON: {e}"}
|
||||
proposal_id = data.get("proposal_id")
|
||||
bottle_slug = data.get("bottle_slug")
|
||||
decision = data.get("decision")
|
||||
if not (isinstance(proposal_id, str) and proposal_id):
|
||||
return 400, {"error": "proposal_id (string) is required"}
|
||||
if not (isinstance(bottle_slug, str) and bottle_slug):
|
||||
return 400, {"error": "bottle_slug (string) is required"}
|
||||
if not (isinstance(decision, str) and decision):
|
||||
return 400, {"error": "decision (string) is required"}
|
||||
notes = data.get("notes")
|
||||
final_file = data.get("final_file")
|
||||
ok, err = orch.supervise_respond(
|
||||
proposal_id,
|
||||
bottle_slug=bottle_slug,
|
||||
decision=decision,
|
||||
notes=notes if isinstance(notes, str) else "",
|
||||
final_file=final_file if isinstance(final_file, str) else None,
|
||||
)
|
||||
if ok:
|
||||
return 200, {"responded": True}
|
||||
return 409, {"error": err}
|
||||
|
||||
if method == "POST" and route == "/supervise/propose":
|
||||
# Agent half: queue a proposal, attributed to the caller resolved from
|
||||
# (source_ip, identity_token) — never a caller-supplied slug — so the
|
||||
# data plane can't forge attribution. Fail-closed 403 when unattributed.
|
||||
try:
|
||||
data = _parse_json_object(body)
|
||||
except ValueError as e:
|
||||
return 400, {"error": f"invalid JSON: {e}"}
|
||||
source_ip = data.get("source_ip")
|
||||
token = data.get("identity_token")
|
||||
tool = data.get("tool")
|
||||
proposed_file = data.get("proposed_file")
|
||||
justification = data.get("justification")
|
||||
if not isinstance(source_ip, str) or not source_ip:
|
||||
return 400, {"error": "source_ip (string) is required"}
|
||||
if not isinstance(tool, str) or tool not in TOOLS:
|
||||
return 400, {"error": f"tool (string) must be one of {TOOLS}"}
|
||||
if not isinstance(proposed_file, str) or not proposed_file:
|
||||
return 400, {"error": "proposed_file (string) is required"}
|
||||
if not isinstance(justification, str) or not justification:
|
||||
return 400, {"error": "justification (string) is required"}
|
||||
rec = orch.resolve(source_ip, token if isinstance(token, str) else "")
|
||||
if rec is None:
|
||||
return 403, {"error": "unattributed"}
|
||||
proposal_id = orch.supervise_queue_proposal(
|
||||
rec.bottle_id, tool=tool, proposed_file=proposed_file,
|
||||
justification=justification,
|
||||
)
|
||||
return 201, {"proposal_id": proposal_id}
|
||||
|
||||
if method == "POST" and route == "/supervise/poll":
|
||||
# Agent half: non-blocking read of the caller's own proposal decision.
|
||||
# Attributed like /propose, and scoped to the resolved bottle id, so a
|
||||
# guessed proposal_id can never read another bottle's response.
|
||||
try:
|
||||
data = _parse_json_object(body)
|
||||
except ValueError as e:
|
||||
return 400, {"error": f"invalid JSON: {e}"}
|
||||
source_ip = data.get("source_ip")
|
||||
token = data.get("identity_token")
|
||||
proposal_id = data.get("proposal_id")
|
||||
if not isinstance(source_ip, str) or not source_ip:
|
||||
return 400, {"error": "source_ip (string) is required"}
|
||||
if not isinstance(proposal_id, str) or not proposal_id:
|
||||
return 400, {"error": "proposal_id (string) is required"}
|
||||
rec = orch.resolve(source_ip, token if isinstance(token, str) else "")
|
||||
if rec is None:
|
||||
return 403, {"error": "unattributed"}
|
||||
return 200, orch.supervise_poll_response(rec.bottle_id, proposal_id)
|
||||
|
||||
if method == "POST" and route == "/resolve":
|
||||
# The per-request lookup the multi-tenant gateway makes: returns the
|
||||
# bottle's policy. Requires a matching (source_ip, identity_token)
|
||||
# pair — a missing/empty/mismatched token fail-closes (403), no
|
||||
# source-IP-only fallback.
|
||||
try:
|
||||
data = _parse_json_object(body)
|
||||
except ValueError as e:
|
||||
return 400, {"error": f"invalid JSON: {e}"}
|
||||
source_ip = data.get("source_ip")
|
||||
token = data.get("identity_token")
|
||||
if not isinstance(source_ip, str) or not source_ip:
|
||||
return 400, {"error": "source_ip (string) is required"}
|
||||
rec = orch.resolve(source_ip, token if isinstance(token, str) else "")
|
||||
if rec is None:
|
||||
return 403, {"error": "unattributed"}
|
||||
# tokens are the in-memory per-bottle egress auth values the gateway
|
||||
# injects; served here, never persisted.
|
||||
return 200, {
|
||||
"bottle_id": rec.bottle_id,
|
||||
"policy": rec.policy,
|
||||
"tokens": orch.tokens_for(rec.bottle_id),
|
||||
}
|
||||
|
||||
return 404, {"error": "not found"}
|
||||
|
||||
|
||||
class Handler(http.server.BaseHTTPRequestHandler):
|
||||
"""Thin stdlib adapter: read the body, call `dispatch`, write JSON."""
|
||||
|
||||
# Quiet by default (the orchestrator has its own logging); opt back into
|
||||
# stdlib access logging with BOT_BOTTLE_ORCHESTRATOR_DEBUG.
|
||||
def log_message(self, format: str, *args: typing.Any) -> None: # noqa: A002
|
||||
if os.environ.get("BOT_BOTTLE_ORCHESTRATOR_DEBUG"):
|
||||
super().log_message(format, *args)
|
||||
|
||||
def _serve(self, method: str) -> None:
|
||||
"""Read the request body, dispatch it, and write the JSON reply. A
|
||||
dispatch failure (e.g. a broker error) returns a 500 rather than
|
||||
crashing the connection, so one bad request can't take the control
|
||||
plane down for the caller."""
|
||||
server = self.server
|
||||
assert isinstance(server, OrchestratorServer)
|
||||
length = int(self.headers.get("Content-Length") or 0)
|
||||
body = self.rfile.read(length) if length > 0 else b""
|
||||
role = server.role_for(self.headers.get(ORCHESTRATOR_AUTH_HEADER, ""))
|
||||
try:
|
||||
status, payload = dispatch(
|
||||
server.orchestrator, method, self.path, body, role=role)
|
||||
except Exception as e: # noqa: BLE001 — the control plane must stay up
|
||||
sys.stderr.write(f"orchestrator: {method} {self.path} failed: {e!r}\n")
|
||||
sys.stderr.flush()
|
||||
status, payload = 500, {"error": f"internal error: {e}"}
|
||||
data = json.dumps(payload).encode()
|
||||
self.send_response(status)
|
||||
self.send_header("Content-Type", "application/json")
|
||||
self.send_header("Content-Length", str(len(data)))
|
||||
self.end_headers()
|
||||
self.wfile.write(data)
|
||||
|
||||
def do_GET(self) -> None:
|
||||
self._serve("GET")
|
||||
|
||||
def do_POST(self) -> None:
|
||||
self._serve("POST")
|
||||
|
||||
def do_PUT(self) -> None:
|
||||
self._serve("PUT")
|
||||
|
||||
def do_DELETE(self) -> None:
|
||||
self._serve("DELETE")
|
||||
|
||||
|
||||
class OrchestratorServer(socketserver.ThreadingMixIn, http.server.HTTPServer):
|
||||
"""Threading HTTP server that carries the orchestrator for its handlers.
|
||||
|
||||
Holds the per-host control-plane *signing key* (from
|
||||
`$BOT_BOTTLE_ORCHESTRATOR_TOKEN`, injected by the launcher into the
|
||||
orchestrator process only) and verifies each request's role-scoped token
|
||||
against it. When a key is set, every route but `/health` requires a valid
|
||||
token whose role covers the route; when it is unset the server runs **open**
|
||||
(full `cli` access) and says so loudly at startup — a fail-visible fallback
|
||||
for tests and any backend that hasn't wired the key yet (e.g. Firecracker,
|
||||
whose nft boundary already blocks agents from the control-plane port)."""
|
||||
|
||||
daemon_threads = True
|
||||
allow_reuse_address = True
|
||||
|
||||
def __init__(self, address: tuple[str, int], orchestrator: OrchestratorCore) -> None:
|
||||
self.orchestrator = orchestrator
|
||||
# The control-plane trust domain's signing key, as injected into THIS
|
||||
# (the owning) process by the launcher (#476). Unset → open mode below.
|
||||
self._signing_key = CONTROL_PLANE.key_from_env()
|
||||
if not self._signing_key:
|
||||
sys.stderr.write(
|
||||
"orchestrator: WARNING — no control-plane signing key "
|
||||
f"(${CONTROL_PLANE.key_env}); running WITHOUT caller "
|
||||
"authentication. Any client that can reach this port can drive "
|
||||
"it. Backends that put the control plane on an agent-reachable "
|
||||
"network MUST set this.\n"
|
||||
)
|
||||
sys.stderr.flush()
|
||||
super().__init__(address, Handler)
|
||||
|
||||
def role_for(self, presented: str) -> str | None:
|
||||
"""The role the request is authorized as, or None if unauthenticated.
|
||||
Open mode (no signing key) grants full `cli` access — the fail-visible
|
||||
fallback. Otherwise verify the presented signed token; a missing/invalid
|
||||
token yields None (→ 401), a valid one yields its `gateway`/`cli`
|
||||
role (→ per-route 401/403 in `dispatch`)."""
|
||||
if not self._signing_key:
|
||||
return ROLE_CLI
|
||||
return CONTROL_PLANE.verify(presented, self._signing_key)
|
||||
def server_close(self) -> None:
|
||||
self._socket.close()
|
||||
|
||||
|
||||
def make_server(
|
||||
orchestrator: OrchestratorCore, host: str = "127.0.0.1", port: int = 0
|
||||
orchestrator: OrchestratorCore,
|
||||
host: str = "127.0.0.1",
|
||||
port: int = 0,
|
||||
*,
|
||||
signing_key: str | None = None,
|
||||
) -> OrchestratorServer:
|
||||
"""Build (but do not start) a control-plane server. `port=0` binds an
|
||||
ephemeral port — read `server.server_address` for the actual one."""
|
||||
return OrchestratorServer((host, port), orchestrator)
|
||||
"""Build a bounded Uvicorn server around the orchestrator application."""
|
||||
key = CONTROL_PLANE.key_from_env() if signing_key is None else signing_key
|
||||
app = create_app(orchestrator, signing_key=key)
|
||||
config = uvicorn.Config(
|
||||
app,
|
||||
host=host,
|
||||
port=port,
|
||||
access_log=bool(os.environ.get("BOT_BOTTLE_ORCHESTRATOR_DEBUG")),
|
||||
log_level="info",
|
||||
limit_concurrency=MAX_REQUESTS,
|
||||
timeout_keep_alive=KEEP_ALIVE_TIMEOUT_SECONDS,
|
||||
server_header=False,
|
||||
)
|
||||
return OrchestratorServer(config)
|
||||
|
||||
|
||||
__all__ = [
|
||||
"dispatch", "Handler", "OrchestratorServer", "make_server", "Json",
|
||||
"KEEP_ALIVE_TIMEOUT_SECONDS",
|
||||
"MAX_BODY_BYTES",
|
||||
"MAX_REQUESTS",
|
||||
"ORCHESTRATOR_AUTH_HEADER",
|
||||
"OrchestratorServer",
|
||||
"create_app",
|
||||
"make_server",
|
||||
]
|
||||
|
||||
@@ -25,7 +25,7 @@ import json
|
||||
from collections.abc import Iterable
|
||||
from datetime import datetime, timezone
|
||||
|
||||
from .broker import BrokerUnavailableError, LaunchRequest, SubmitBroker, sign_request
|
||||
from .broker import LaunchBroker, LaunchRequest, sign_request
|
||||
from .store.registry_store import DEFAULT_REAP_GRACE_SECONDS, BottleRecord, RegistryStore
|
||||
from .supervisor import (
|
||||
AuditEntry,
|
||||
@@ -62,7 +62,7 @@ class OrchestratorCore:
|
||||
def __init__(
|
||||
self,
|
||||
registry: RegistryStore,
|
||||
broker: SubmitBroker,
|
||||
broker: LaunchBroker,
|
||||
sign_secret: bytes,
|
||||
supervisor: Supervisor | None = None,
|
||||
) -> None:
|
||||
@@ -111,23 +111,14 @@ class OrchestratorCore:
|
||||
image_ref=image_ref,
|
||||
slot=slot,
|
||||
)
|
||||
launched = False
|
||||
try:
|
||||
self._broker.submit(sign_request(req, self._secret))
|
||||
except BrokerUnavailableError:
|
||||
# Ambiguous delivery failure (timeout / dropped response): the broker
|
||||
# may already have launched the bottle before the response was lost.
|
||||
# Do NOT deregister — that would orphan a running container with no
|
||||
# registry row (reconcile reaps rows, never containers). Keep the row
|
||||
# so reconcile reaps it iff the bottle is not actually live; surface
|
||||
# the error so the caller knows the launch is unconfirmed.
|
||||
raise
|
||||
except Exception:
|
||||
# A definite failure — a fail-closed rejection, a backend launch
|
||||
# error, or the host reporting it did not launch: nothing is running,
|
||||
# so roll the registry entry back to leave no orphan.
|
||||
self.registry.deregister(rec.bottle_id)
|
||||
self._tokens.pop(rec.bottle_id, None)
|
||||
raise
|
||||
launched = True
|
||||
finally:
|
||||
if not launched:
|
||||
self.registry.deregister(rec.bottle_id)
|
||||
self._tokens.pop(rec.bottle_id, None)
|
||||
return rec
|
||||
|
||||
def teardown_bottle(self, bottle_id: str) -> bool:
|
||||
@@ -380,10 +371,36 @@ class OrchestratorCore:
|
||||
if not encrypted:
|
||||
return False
|
||||
try:
|
||||
self._tokens[bottle_id] = {k: decrypt_value(env_var_secret, v)
|
||||
for k, v in encrypted.items()}
|
||||
decrypted = {
|
||||
k: decrypt_value(env_var_secret, v) for k, v in encrypted.items()
|
||||
}
|
||||
except ValueError:
|
||||
return False
|
||||
self._tokens[bottle_id] = decrypted
|
||||
return True
|
||||
|
||||
def update_agent_secret(
|
||||
self, bottle_id: str, name: str, value: str, env_var_secret: str,
|
||||
) -> bool:
|
||||
"""Update ONE egress token for a known bottle in place — the
|
||||
single-secret form of ``reprovision_from_secret``.
|
||||
|
||||
Sets the in-memory token AND upserts the single re-encrypted row under
|
||||
*env_var_secret* (the same key the rest of the rows are encrypted with, so
|
||||
the whole set stays decryptable by a later ``reprovision_from_secret``),
|
||||
leaving every other token untouched. Returns False if the bottle is
|
||||
unknown.
|
||||
|
||||
Unlike ``reprovision_from_secret`` (which restores the values captured at
|
||||
launch), this pushes a *caller-supplied* value — used to refresh a
|
||||
short-lived host credential (e.g. the Codex access token) into a
|
||||
still-running bottle without a relaunch."""
|
||||
from .store.secret_store import encrypt_value
|
||||
if self.registry.get(bottle_id) is None:
|
||||
return False
|
||||
self._tokens.setdefault(bottle_id, {})[name] = value
|
||||
self.registry.store_agent_secret(
|
||||
bottle_id, name, encrypt_value(env_var_secret, value))
|
||||
return True
|
||||
|
||||
# --- consolidated gateway ----------------------------------------------
|
||||
|
||||
Some files were not shown because too many files have changed in this diff Show More
Reference in New Issue
Block a user