Compare commits
97 Commits
c3ad2264fa
..
main
| Author | SHA1 | Date | |
|---|---|---|---|
| 0fb9b04c01 | |||
| 26d0f5e3b2 | |||
| bc4e559775 | |||
| 854f6b5696 | |||
| 28953bfe0b | |||
| 1ffc553ade | |||
| 9014c07b86 | |||
| 8e2465e241 | |||
| a8043be394 | |||
| 7d401a68c5 | |||
| ce7a7c9915 | |||
| 83aa6768fc | |||
| 6fea44067f | |||
| bf8ff91b31 | |||
| 315ed04979 | |||
| 9a04ab262b | |||
| cc094765fd | |||
| 0ba25352b9 | |||
| dba48706de | |||
| 854a8956ad | |||
| 7a9628fc03 | |||
| ca8b2a9f2c | |||
| 96f5be48a6 | |||
| 82cf9bab5a | |||
| 3c92e79775 | |||
| 220620bfcc | |||
| b0f012b8e6 | |||
| fa9fed4194 | |||
| d0b595828f | |||
| 182a28d724 | |||
| cfb2284b99 | |||
| 2cd06814e6 | |||
| 8fed02fd1e | |||
| a7b2befc06 | |||
| 6fdf090469 | |||
| d32e9cc3c3 | |||
| ef89ed084f | |||
| ccd987a501 | |||
| 2cd44cf79a | |||
| 8a1b833aaa | |||
| 3b5c55bc8e | |||
| 95220b4808 | |||
| b032562d74 | |||
| 1d925172ec | |||
| f6ae485b68 | |||
| e3258d0683 | |||
| 0ff11d8ed7 | |||
| a970f974a2 | |||
| c845d3fed4 | |||
| c6a9419b95 | |||
| 36fb019007 | |||
| adc033a902 | |||
| 21b253c7eb | |||
| d4e2bc5f93 | |||
| 4998a5ec6a | |||
| efd413c1ba | |||
| d3d468532f | |||
| ad2927b3b1 | |||
| 2582373490 | |||
| 17ac1be93b | |||
| c53254e9d5 | |||
| 58ecd8cb90 | |||
| 310b36196d | |||
| c473e5e5d8 | |||
| 137426d9ac | |||
| 2a3a7dfb5c | |||
| 16c12177d2 | |||
| 0f1734b823 | |||
| 2bf28e03f4 | |||
| d3428b8c14 | |||
| 4199de5e3e | |||
| 8348714e3e | |||
| 26002b75ca | |||
| 0c91c75a05 | |||
| 8ce8a8cc62 | |||
| 3fba385513 | |||
| b25cd72fc3 | |||
| 8e43c26ab4 | |||
| 14ff4fe186 | |||
| cae1215f63 | |||
| 28766d7733 | |||
| 819f967844 | |||
| 2f45f5afec | |||
| 31a5ec2fc8 | |||
| 1f192d785a | |||
| 853b6d1678 | |||
| cf9a53d582 | |||
| 0b36c3eb48 | |||
| 28fcc3f2d2 | |||
| 571030b8e8 | |||
| 288b205a44 | |||
| 0c1d27b605 | |||
| 69361114d1 | |||
| e4d53fd360 | |||
| 5e01c28016 | |||
| 2f8539c2c7 | |||
| ad100b8a84 |
@@ -1,6 +1,10 @@
|
||||
[run]
|
||||
branch = True
|
||||
source = .
|
||||
# Store paths relative to the project root so .coverage.* files produced on
|
||||
# different runners (ubuntu-latest vs self-hosted KVM) can be combined by the
|
||||
# coverage job without a [paths] remapping section.
|
||||
relative_files = True
|
||||
|
||||
[report]
|
||||
# Coverage policy: see docs/decisions/0004-coverage-policy.md.
|
||||
|
||||
+152
-121
@@ -1,4 +1,5 @@
|
||||
# Run the project's test suite on every PR push and on push to main.
|
||||
# Run the project's test suite when package or runtime inputs change on a PR
|
||||
# or on push to main.
|
||||
#
|
||||
# The suite uses stdlib `unittest` discovery — no external Python
|
||||
# dependencies are required to execute it. Tests are split by directory:
|
||||
@@ -9,10 +10,12 @@
|
||||
# tests/canaries/ — upstream regression canaries; run on a separate
|
||||
# schedule (see canaries.yml), not here
|
||||
#
|
||||
# Integration tests run once per backend in separate jobs. Each job sets
|
||||
# BOT_BOTTLE_BACKEND explicitly so the test suite uses the right backend.
|
||||
# Backends that aren't available on the runner fail the preflight step
|
||||
# rather than silently skipping inside the test output.
|
||||
# Each test job runs once under coverage and uploads a small .coverage.*
|
||||
# artifact. The `coverage` job combines them — no test reruns, no KVM
|
||||
# dependency on that job. For main-branch pushes only, the tested rootfs
|
||||
# and matching dropbear are uploaded so `publish-infra` can publish the
|
||||
# byte-identical artifact that was tested. PRs avoid the ~194 MB rootfs
|
||||
# transfer entirely.
|
||||
|
||||
name: test
|
||||
|
||||
@@ -21,72 +24,37 @@ on:
|
||||
branches:
|
||||
- main
|
||||
paths:
|
||||
- '**.py'
|
||||
- '.gitea/workflows/**.yml'
|
||||
- 'scripts/**'
|
||||
- 'README.md'
|
||||
# Dockerfiles and pyproject.toml are baked into the infra rootfs; a
|
||||
# change here alters what the integration/coverage jobs build locally.
|
||||
- 'bot_bottle/**'
|
||||
- 'tests/**/*.py'
|
||||
- 'cli.py'
|
||||
- 'scripts/coverage.sh'
|
||||
- 'scripts/critical-modules.txt'
|
||||
- 'scripts/diff_coverage.py'
|
||||
- 'scripts/tracker_policy.py'
|
||||
- 'scripts/firecracker-netpool.sh'
|
||||
- 'Dockerfile*'
|
||||
- 'pyproject.toml'
|
||||
- 'requirements-dev.txt'
|
||||
- '.coveragerc'
|
||||
- '.dockerignore'
|
||||
pull_request:
|
||||
paths:
|
||||
- '**.py'
|
||||
- '.gitea/workflows/**.yml'
|
||||
- 'scripts/**'
|
||||
- 'README.md'
|
||||
- 'bot_bottle/**'
|
||||
- 'tests/**/*.py'
|
||||
- 'cli.py'
|
||||
- 'scripts/coverage.sh'
|
||||
- 'scripts/critical-modules.txt'
|
||||
- 'scripts/diff_coverage.py'
|
||||
- 'scripts/tracker_policy.py'
|
||||
- 'scripts/firecracker-netpool.sh'
|
||||
- 'Dockerfile*'
|
||||
- 'pyproject.toml'
|
||||
- 'requirements-dev.txt'
|
||||
- '.coveragerc'
|
||||
- '.dockerignore'
|
||||
workflow_dispatch:
|
||||
|
||||
jobs:
|
||||
stage-firecracker-inputs:
|
||||
runs-on: [self-hosted, kvm]
|
||||
# Same guard as the other KVM-runner jobs: don't spin the privileged
|
||||
# runner for fork PRs (this only copies a non-secret static binary, but
|
||||
# keep the posture consistent — build-infra/integration/coverage all
|
||||
# depend on it, so gating here gates the whole Firecracker chain).
|
||||
if: >-
|
||||
github.event_name == 'push' ||
|
||||
github.event_name == 'workflow_dispatch' ||
|
||||
(github.event_name == 'pull_request' &&
|
||||
github.event.pull_request.head.repo.full_name == github.repository)
|
||||
steps:
|
||||
- name: Stage the provisioned static dropbear
|
||||
run: |
|
||||
mkdir -p firecracker-inputs
|
||||
cp /var/cache/bot-bottle-fc/dropbear firecracker-inputs/dropbear
|
||||
|
||||
- name: Upload Firecracker build inputs
|
||||
uses: actions/upload-artifact@v3
|
||||
with:
|
||||
name: firecracker-inputs
|
||||
path: firecracker-inputs/
|
||||
|
||||
build-infra:
|
||||
needs: stage-firecracker-inputs
|
||||
runs-on: ubuntu-latest
|
||||
steps:
|
||||
- name: Checkout
|
||||
uses: actions/checkout@v4
|
||||
|
||||
- name: Download Firecracker build inputs
|
||||
uses: actions/download-artifact@v3
|
||||
with:
|
||||
name: firecracker-inputs
|
||||
path: firecracker-inputs
|
||||
|
||||
- name: Build infra candidate from this checkout
|
||||
env:
|
||||
BOT_BOTTLE_FC_DROPBEAR: ${{ github.workspace }}/firecracker-inputs/dropbear
|
||||
run: python3 -m bot_bottle.backend.firecracker.publish_infra --output infra-candidate
|
||||
|
||||
- name: Upload infra candidate
|
||||
uses: actions/upload-artifact@v3
|
||||
with:
|
||||
name: infra-candidate
|
||||
path: infra-candidate/
|
||||
|
||||
unit:
|
||||
runs-on: ubuntu-latest
|
||||
steps:
|
||||
@@ -101,12 +69,29 @@ jobs:
|
||||
- name: Install dev requirements
|
||||
run: python3 -m pip install --break-system-packages -r requirements-dev.txt
|
||||
|
||||
- name: Run unit tests
|
||||
- name: Run unit tests with coverage
|
||||
env:
|
||||
COVERAGE_FILE: ${{ github.workspace }}/.coverage.unit
|
||||
run: python3 -m coverage run -m unittest discover -t . -s tests/unit -v
|
||||
|
||||
- name: Report unit coverage
|
||||
env:
|
||||
COVERAGE_FILE: ${{ github.workspace }}/.coverage.unit
|
||||
run: python3 -m coverage report -m
|
||||
|
||||
# upload-artifact@v3's glob skips dotfiles, so a bare `.coverage.unit`
|
||||
# silently uploads nothing ("No files were found"). Stage it under a
|
||||
# non-dot name; the coverage job renames it back before `coverage
|
||||
# combine`. `cp` also fails loudly if coverage never wrote the file.
|
||||
- name: Stage unit coverage for upload
|
||||
run: cp .coverage.unit coverage-unit.dat
|
||||
|
||||
- name: Upload unit coverage artifact
|
||||
uses: actions/upload-artifact@v3
|
||||
with:
|
||||
name: coverage-unit
|
||||
path: coverage-unit.dat
|
||||
|
||||
integration-docker:
|
||||
runs-on: ubuntu-latest
|
||||
steps:
|
||||
@@ -115,6 +100,9 @@ jobs:
|
||||
|
||||
# No actions/setup-python (see the note in the `unit` job); the
|
||||
# container's system Python 3.12 runs the stdlib test suite directly.
|
||||
- name: Install coverage
|
||||
run: python3 -m pip install --break-system-packages coverage
|
||||
|
||||
- name: Show environment
|
||||
run: |
|
||||
python3 --version
|
||||
@@ -124,10 +112,21 @@ jobs:
|
||||
echo "docker not on PATH — integration tests will skip"
|
||||
fi
|
||||
|
||||
- name: Run integration tests (docker)
|
||||
- name: Run integration tests (docker) with coverage
|
||||
env:
|
||||
BOT_BOTTLE_BACKEND: docker
|
||||
run: python3 -m unittest discover -t . -s tests/integration -v
|
||||
COVERAGE_FILE: ${{ github.workspace }}/.coverage.docker
|
||||
run: python3 -m coverage run -m unittest discover -t . -s tests/integration -v
|
||||
|
||||
# Non-dot name so upload-artifact's dotfile-skipping glob picks it up.
|
||||
- name: Stage docker coverage for upload
|
||||
run: cp .coverage.docker coverage-docker.dat
|
||||
|
||||
- name: Upload docker coverage artifact
|
||||
uses: actions/upload-artifact@v3
|
||||
with:
|
||||
name: coverage-docker
|
||||
path: coverage-docker.dat
|
||||
|
||||
# Integration tests against the Firecracker backend. Runs on a self-hosted
|
||||
# KVM runner (label `kvm`) where /dev/kvm and the TAP/nft pool are available.
|
||||
@@ -137,9 +136,16 @@ jobs:
|
||||
#
|
||||
# Runner prerequisites (provision once; see README "Firecracker on Linux"):
|
||||
# `firecracker` on PATH, `/dev/kvm` accessible, cached kernel +
|
||||
# static dropbear, and the pool as a persistent systemd unit.
|
||||
# static dropbear at /var/cache/bot-bottle-fc/dropbear, and the pool as a
|
||||
# persistent systemd unit.
|
||||
#
|
||||
# The infra candidate is built here directly (no artifact download) to
|
||||
# eliminate the ~70 s ubuntu-latest upload + ~83 s combined download that
|
||||
# the old build-infra → integration-firecracker + coverage chain incurred.
|
||||
# For main-branch pushes the tested rootfs and matching dropbear are
|
||||
# uploaded so publish-infra can publish the byte-identical artifact; PRs
|
||||
# skip those uploads entirely.
|
||||
integration-firecracker:
|
||||
needs: build-infra
|
||||
runs-on: [self-hosted, kvm]
|
||||
if: >-
|
||||
github.event_name == 'push' ||
|
||||
@@ -159,49 +165,65 @@ jobs:
|
||||
# range overlap; it prints the exact `backend setup` fix.
|
||||
python3 cli.py backend status --backend=firecracker
|
||||
|
||||
- name: Download the candidate built from this checkout
|
||||
uses: actions/download-artifact@v3
|
||||
with:
|
||||
name: infra-candidate
|
||||
path: infra-candidate
|
||||
- name: Build infra candidate from this checkout
|
||||
env:
|
||||
BOT_BOTTLE_FC_DROPBEAR: /var/cache/bot-bottle-fc/dropbear
|
||||
run: python3 -m bot_bottle.backend.firecracker.publish_infra --output infra-candidate --reuse-published
|
||||
|
||||
- name: Replace the persistent infra VM with the candidate
|
||||
run: python3 -c 'from bot_bottle.backend.firecracker import infra_vm; infra_vm.stop()'
|
||||
|
||||
# No dev-requirements install: the integration suite runs on stdlib
|
||||
# `unittest` (pylint/pyright are lint.yml's concern, not this job's),
|
||||
# and the self-hosted runner's Nix python env has no `pip` module
|
||||
# (`python3 -m pip` → "No module named pip"). Nothing to install.
|
||||
- name: Run integration tests (firecracker)
|
||||
# No dev-requirements install: `coverage` is already provided by the
|
||||
# self-hosted runner's Nix python env, and that env has no `pip`
|
||||
# module to install into anyway.
|
||||
- name: Run integration tests (firecracker) with coverage
|
||||
env:
|
||||
BOT_BOTTLE_BACKEND: firecracker
|
||||
BOT_BOTTLE_INFRA_ARTIFACT_DIR: ${{ github.workspace }}/infra-candidate
|
||||
run: python3 -m unittest discover -t . -s tests/integration -v
|
||||
COVERAGE_FILE: ${{ github.workspace }}/.coverage.firecracker
|
||||
run: python3 -m coverage run -m unittest discover -t . -s tests/integration -v
|
||||
|
||||
# Combined unit+integration coverage + the diff-coverage gate (the hard
|
||||
# gate: new/changed lines >= 90%). See docs/decisions/0004-coverage-policy.md.
|
||||
# Non-dot name so upload-artifact's dotfile-skipping glob picks it up.
|
||||
- name: Stage firecracker coverage for upload
|
||||
run: cp .coverage.firecracker coverage-firecracker.dat
|
||||
|
||||
- name: Upload firecracker coverage artifact
|
||||
uses: actions/upload-artifact@v3
|
||||
with:
|
||||
name: coverage-firecracker
|
||||
path: coverage-firecracker.dat
|
||||
|
||||
# Only upload the large rootfs artifact on main-branch pushes;
|
||||
# PRs avoid the ~194 MB transfer. publish-infra only runs on main
|
||||
# and downloads these to publish the byte-identical tested rootfs.
|
||||
- name: Upload tested rootfs (main branch only)
|
||||
if: github.event_name == 'push' && github.ref == 'refs/heads/main'
|
||||
uses: actions/upload-artifact@v3
|
||||
with:
|
||||
name: infra-candidate
|
||||
path: infra-candidate/
|
||||
|
||||
- name: Upload dropbear for publish verification (main branch only)
|
||||
if: github.event_name == 'push' && github.ref == 'refs/heads/main'
|
||||
uses: actions/upload-artifact@v3
|
||||
with:
|
||||
name: firecracker-inputs
|
||||
path: /var/cache/bot-bottle-fc/dropbear
|
||||
|
||||
# Combined coverage gate: aggregates .coverage.* artifacts uploaded by each
|
||||
# test job, then runs the diff-coverage gate (new/changed lines >= 90%).
|
||||
#
|
||||
# This runs on a self-hosted KVM runner (label `kvm`), NOT ubuntu-latest,
|
||||
# because the Firecracker backend's subprocess/VM orchestration
|
||||
# (launch/boot/SSH/isolation-probe) is covered by the integration suite,
|
||||
# and that suite needs `/dev/kvm` + the provisioned TAP/nft pool — which a
|
||||
# container-based runner doesn't have. On such a runner the firecracker
|
||||
# integration test skips and its ~230 orchestration lines read as
|
||||
# uncovered, so the gate can't pass there.
|
||||
# Runs on ubuntu-latest — no KVM needed, no test reruns. Coverage files use
|
||||
# relative_files = True (.coveragerc) so they combine cleanly across runners.
|
||||
# Each test job sets COVERAGE_FILE to an absolute path so coverage.py writes
|
||||
# to a known location that upload-artifact can find regardless of runner env.
|
||||
#
|
||||
# Restricted to the same events as integration-firecracker (same-repo PRs,
|
||||
# push, workflow_dispatch) for the same security reason.
|
||||
#
|
||||
# See #414 for the planned follow-up: artifact-based coverage combination
|
||||
# (run tests once in their respective jobs, combine .coverage files here).
|
||||
#
|
||||
# build-infra creates one candidate from the checkout. This job boots that
|
||||
# same candidate after integration-firecracker has exercised it; the main
|
||||
# push path publishes the identical bytes only after every required job.
|
||||
# Restricted to the same events as integration-firecracker: it depends on
|
||||
# that job's coverage artifact and skips for fork PRs alongside it.
|
||||
coverage:
|
||||
needs: [build-infra, integration-firecracker]
|
||||
needs: [unit, integration-docker, integration-firecracker]
|
||||
timeout-minutes: 15
|
||||
runs-on: [self-hosted, kvm]
|
||||
runs-on: ubuntu-latest
|
||||
if: >-
|
||||
github.event_name == 'push' ||
|
||||
github.event_name == 'workflow_dispatch' ||
|
||||
@@ -213,29 +235,37 @@ jobs:
|
||||
with:
|
||||
fetch-depth: 0
|
||||
|
||||
- name: Preflight — Firecracker host is ready
|
||||
run: |
|
||||
command -v firecracker >/dev/null || {
|
||||
echo "firecracker not on PATH — provision the runner (README: Firecracker on Linux)"; exit 1; }
|
||||
test -e /dev/kvm || { echo "/dev/kvm missing — KVM not available on this runner"; exit 1; }
|
||||
# `backend status` exits non-zero unless the TAP pool is up + no
|
||||
# range overlap; it prints the exact `backend setup` fix.
|
||||
python3 cli.py backend status --backend=firecracker
|
||||
- name: Install coverage
|
||||
run: python3 -m pip install --break-system-packages coverage
|
||||
|
||||
- name: Download the candidate already exercised by integration
|
||||
- name: Download unit coverage artifact
|
||||
uses: actions/download-artifact@v3
|
||||
with:
|
||||
name: infra-candidate
|
||||
path: infra-candidate
|
||||
name: coverage-unit
|
||||
path: ${{ github.workspace }}
|
||||
|
||||
- name: Download docker coverage artifact
|
||||
uses: actions/download-artifact@v3
|
||||
with:
|
||||
name: coverage-docker
|
||||
path: ${{ github.workspace }}
|
||||
|
||||
- name: Download firecracker coverage artifact
|
||||
uses: actions/download-artifact@v3
|
||||
with:
|
||||
name: coverage-firecracker
|
||||
path: ${{ github.workspace }}
|
||||
|
||||
# Rename the non-dot upload names back to the .coverage.* files that
|
||||
# `coverage combine` discovers (see the staging steps in each test job).
|
||||
- name: Reassemble coverage data files
|
||||
run: |
|
||||
mv coverage-unit.dat .coverage.unit
|
||||
mv coverage-docker.dat .coverage.docker
|
||||
mv coverage-firecracker.dat .coverage.firecracker
|
||||
|
||||
# No dev-requirements install: `coverage` is already provided by the
|
||||
# self-hosted runner's Nix python env, and that env has no `pip`
|
||||
# module to install into anyway. `scripts/coverage.sh` +
|
||||
# `diff_coverage.py` need only `coverage` (not pylint/pyright).
|
||||
- name: Combined coverage (unit + integration, incl. firecracker)
|
||||
env:
|
||||
BOT_BOTTLE_CI_INFRA_ARTIFACT_DIR: ${{ github.workspace }}/infra-candidate
|
||||
run: PYTHON=python3 bash scripts/coverage.sh critical
|
||||
run: PYTHON=python3 bash scripts/coverage.sh aggregate critical
|
||||
|
||||
- name: Diff-coverage gate (changed lines >= 90%)
|
||||
run: |
|
||||
@@ -243,14 +273,14 @@ jobs:
|
||||
python3 scripts/diff_coverage.py --base origin/main --min 90
|
||||
|
||||
publish-infra:
|
||||
needs: [stage-firecracker-inputs, build-infra, unit, integration-docker, integration-firecracker, coverage]
|
||||
needs: [unit, integration-docker, integration-firecracker, coverage]
|
||||
runs-on: ubuntu-latest
|
||||
if: github.event_name == 'push' && github.ref == 'refs/heads/main'
|
||||
steps:
|
||||
- name: Checkout the tested revision
|
||||
uses: actions/checkout@v4
|
||||
|
||||
- name: Download the tested candidate
|
||||
- name: Download the tested rootfs
|
||||
uses: actions/download-artifact@v3
|
||||
with:
|
||||
name: infra-candidate
|
||||
@@ -258,9 +288,10 @@ jobs:
|
||||
|
||||
# publish_infra re-derives the version from the checkout to confirm the
|
||||
# bundle matches before uploading, and the version hashes the dropbear
|
||||
# bytes. Stage the SAME dropbear build-infra used, or the recheck
|
||||
# computes a "<missing>"-dropbear version and rejects the candidate.
|
||||
- name: Download the staged dropbear (matches build-infra's version)
|
||||
# bytes. Download the SAME dropbear integration-firecracker used, or
|
||||
# the recheck computes a "<missing>"-dropbear version and rejects the
|
||||
# candidate.
|
||||
- name: Download the staged dropbear (matches build's version)
|
||||
uses: actions/download-artifact@v3
|
||||
with:
|
||||
name: firecracker-inputs
|
||||
|
||||
@@ -14,11 +14,14 @@ on:
|
||||
jobs:
|
||||
update-badges:
|
||||
runs-on: ubuntu-latest
|
||||
permissions:
|
||||
contents: write
|
||||
|
||||
steps:
|
||||
- uses: actions/checkout@v3
|
||||
with:
|
||||
fetch-depth: 0
|
||||
token: ${{ secrets.GITHUB_TOKEN }}
|
||||
token: ${{ secrets.BADGE_PUSH_TOKEN }}
|
||||
|
||||
# No actions/setup-python: the runner image ships Python 3.12 and older
|
||||
# act_runner engines mishandle setup-python's PATH. Install into the
|
||||
|
||||
@@ -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.
|
||||
@@ -75,6 +75,88 @@ On compatible macOS hosts, the default backend requires Apple's `container` CLI
|
||||
|
||||
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.
|
||||
|
||||
### Containers inside a bottle
|
||||
|
||||
A bottle may set `nested_containers: true`. On the macOS backend this starts a
|
||||
guest-local, rootless **podman** service after the bottle is registered and
|
||||
exposes its Docker-compatible API socket, so the agent still runs `docker` and
|
||||
`docker compose`. Nothing is mounted from the host: Docker Desktop's socket
|
||||
stays out of the bottle and the guest gains no outer VM capabilities. Backends
|
||||
that cannot do this (`docker`, `firecracker`) reject the flag rather than
|
||||
silently ignore it.
|
||||
|
||||
Rootless Docker was tried first and does not work here at all: Apple
|
||||
Container's capability bounding set omits `CAP_SYS_ADMIN`, which the kernel
|
||||
requires to write a multi-range `uid_map`. See
|
||||
[`docs/research/rootless-docker-in-apple-container-spike.md`](docs/research/rootless-docker-in-apple-container-spike.md).
|
||||
|
||||
The tradeoff to understand before enabling it: podman avoids that requirement
|
||||
by falling back to a single-UID mapping, so nested containers provide **no
|
||||
isolation from the agent itself** — `root` inside a nested container is the
|
||||
agent user outside it. Nested containers are a build/test convenience, not a
|
||||
security boundary. The bottle remains the boundary.
|
||||
|
||||
Pulling images goes through the bottle's egress proxy like every other
|
||||
request, so each registry needs a route — **and so does the CDN it redirects
|
||||
layer blobs to**, which is a different host. Without the CDN route the pull
|
||||
authenticates, fetches the manifest, then 403s partway through.
|
||||
|
||||
Docker Hub and GHCR additionally need `preserve_auth: true`: their token dance
|
||||
uses a client-fetched per-scope bearer token that the proxy would otherwise
|
||||
strip. Turn DLP off on every registry and CDN route — the bodies are
|
||||
compressed layer blobs that no detector can read, and buffering them is what
|
||||
triggers the shared-proxy OOM in #455.
|
||||
|
||||
```yaml
|
||||
nested_containers: true
|
||||
egress:
|
||||
routes:
|
||||
# Docker Hub: registry, token endpoint, blob CDN.
|
||||
- host: registry-1.docker.io
|
||||
preserve_auth: true
|
||||
dlp: { outbound_detectors: false, inbound_detectors: false }
|
||||
- host: auth.docker.io
|
||||
preserve_auth: true
|
||||
dlp: { outbound_detectors: false, inbound_detectors: false }
|
||||
- host: production.cloudfront.docker.com
|
||||
dlp: { outbound_detectors: false, inbound_detectors: false }
|
||||
# GHCR: registry + blob CDN.
|
||||
- host: ghcr.io
|
||||
preserve_auth: true
|
||||
dlp: { outbound_detectors: false, inbound_detectors: false }
|
||||
- host: pkg-containers.githubusercontent.com
|
||||
dlp: { outbound_detectors: false, inbound_detectors: false }
|
||||
# quay.io: registry + blob CDNs. No preserve_auth needed for public pulls.
|
||||
- host: quay.io
|
||||
dlp: { outbound_detectors: false, inbound_detectors: false }
|
||||
- host: cdn01.quay.io
|
||||
dlp: { outbound_detectors: false, inbound_detectors: false }
|
||||
- host: cdn02.quay.io
|
||||
dlp: { outbound_detectors: false, inbound_detectors: false }
|
||||
- host: cdn03.quay.io
|
||||
dlp: { outbound_detectors: false, inbound_detectors: false }
|
||||
```
|
||||
|
||||
`mcr.microsoft.com` and `registry.k8s.io` follow the same shape and also
|
||||
redirect blobs elsewhere (`*.data.mcr.microsoft.com` and
|
||||
`us-*-docker.pkg.dev` respectively); route whichever host the 403 names.
|
||||
|
||||
Inside a nested container the same allowlist applies: an allowlisted host
|
||||
returns 200 and anything else gets a 403 straight from the proxy. The
|
||||
gateway's CA bundle and proxy settings are wired in automatically, so
|
||||
`docker run … curl https://…` works with no extra flags — no `--add-host`,
|
||||
`-e`, or `-v`.
|
||||
|
||||
Two things worth knowing when testing that:
|
||||
|
||||
- Public DNS inside a nested container fails **by design**. Everything
|
||||
egresses through the proxy, so `nslookup` failing is expected and is not
|
||||
evidence of a problem.
|
||||
- Alpine's BusyBox `wget` drops the connection after the proxy's TLS
|
||||
interception and reports `error getting response`, even though the proxy
|
||||
logs the decrypted request and returns a response. Use `curl` to test
|
||||
egress; BusyBox `wget` will lie to you.
|
||||
|
||||
### Firecracker on Linux
|
||||
|
||||
On Linux, a KVM-capable host defaults to the Firecracker backend. It needs:
|
||||
@@ -123,14 +205,14 @@ git:
|
||||
egress:
|
||||
routes:
|
||||
- host: gitea.dideric.is
|
||||
auth:
|
||||
scheme: token # Bearer | token
|
||||
token_ref: BOT_BOTTLE_GITEA_TOKEN
|
||||
matches: # optional — restrict to specific paths/methods/headers
|
||||
- paths:
|
||||
- {type: prefix, value: /api/v1/}
|
||||
methods: [GET, POST, PATCH, DELETE]
|
||||
dlp: # optional — per-route detector overrides (default: all on)
|
||||
inspect:
|
||||
auth:
|
||||
scheme: token # Bearer | token
|
||||
token_ref: BOT_BOTTLE_GITEA_TOKEN
|
||||
matches: # optional — restrict to specific paths/methods/headers
|
||||
- paths:
|
||||
- {type: prefix, value: /api/v1/}
|
||||
methods: [GET, POST, PATCH, DELETE]
|
||||
outbound_detectors: [token_patterns, known_secrets]
|
||||
inbound_detectors: false # disable response scanning for this host
|
||||
---
|
||||
|
||||
@@ -45,6 +45,10 @@ PROVIDER_TEMPLATES = frozenset({PROVIDER_CLAUDE, PROVIDER_CODEX, PROVIDER_PI})
|
||||
# forward_host_credentials is enabled. Pipelock must pass these through
|
||||
# (no TLS MITM) or its header DLP blocks the injected JWT.
|
||||
CODEX_HOST_CREDENTIAL_HOSTS = ("api.openai.com", "chatgpt.com")
|
||||
|
||||
# Host that egress injects the host Claude bearer on when Claude
|
||||
# forward_host_credentials is enabled.
|
||||
CLAUDE_HOST_CREDENTIAL_HOSTS = ("api.anthropic.com",)
|
||||
PromptMode = Literal[
|
||||
"append_file",
|
||||
"read_prompt_file",
|
||||
@@ -257,7 +261,28 @@ class AgentProvider(ABC):
|
||||
Default: Debian/node — writes the git-gate insteadOf gitconfig
|
||||
and sets user.name/email as node. Workspace copy runs through
|
||||
BottleBackend.provision_workspace against the running bottle."""
|
||||
from .log import info
|
||||
from .log import die, info
|
||||
|
||||
# Firecracker exports image rootfs files through an unprivileged host
|
||||
# tar extraction, so image-time ownership of XDG directories is not
|
||||
# preserved. Git consults ~/.config/git even when the actual config
|
||||
# is ~/.gitconfig; an unreadable directory there can prevent the
|
||||
# git-gate insteadOf rules below from taking effect. Repair this at
|
||||
# runtime, after every backend's copy/export path has completed.
|
||||
git_xdg_dir = f"{plan.guest_home}/.config/git"
|
||||
repair = bottle.exec(
|
||||
f"chown node:node {shlex.quote(plan.guest_home)} && "
|
||||
f"chmod 755 {shlex.quote(plan.guest_home)} && "
|
||||
f"mkdir -p {shlex.quote(git_xdg_dir)} && "
|
||||
f"chown -R node:node {shlex.quote(f'{plan.guest_home}/.config')} && "
|
||||
f"chmod -R u+rwX,go+rX {shlex.quote(f'{plan.guest_home}/.config')}",
|
||||
user="root",
|
||||
)
|
||||
if repair.returncode != 0:
|
||||
die(
|
||||
"git provisioning: could not make the runtime Git config "
|
||||
f"directory readable: {(repair.stderr or repair.stdout).strip()}"
|
||||
)
|
||||
|
||||
manifest_bottle = plan.manifest.bottle
|
||||
if manifest_bottle.git:
|
||||
@@ -280,11 +305,27 @@ class AgentProvider(ABC):
|
||||
f"{len(manifest_bottle.git)} insteadOf rule(s)"
|
||||
)
|
||||
bottle.cp_in(str(config_file), guest_gitconfig)
|
||||
bottle.exec(
|
||||
permissions = bottle.exec(
|
||||
f"chown node:node {shlex.quote(guest_gitconfig)} && "
|
||||
f"chmod 644 {shlex.quote(guest_gitconfig)}",
|
||||
user="root",
|
||||
)
|
||||
if permissions.returncode != 0:
|
||||
die(
|
||||
"git provisioning: could not set ownership on "
|
||||
f"{guest_gitconfig}: "
|
||||
f"{(permissions.stderr or permissions.stdout).strip()}"
|
||||
)
|
||||
configured = bottle.exec(
|
||||
"git config --global --get-regexp '^url\\..*\\.insteadof$'",
|
||||
user="node",
|
||||
)
|
||||
if configured.returncode != 0:
|
||||
die(
|
||||
"git provisioning: the runtime user cannot read the "
|
||||
f"git-gate insteadOf rules from {guest_gitconfig}: "
|
||||
f"{(configured.stderr or configured.stdout).strip()}"
|
||||
)
|
||||
|
||||
gu = manifest_bottle.git_user
|
||||
if not gu.is_empty():
|
||||
|
||||
@@ -37,10 +37,10 @@ import os
|
||||
import shlex
|
||||
import sys
|
||||
from abc import ABC, abstractmethod
|
||||
from contextlib import AbstractContextManager
|
||||
from contextlib import AbstractContextManager, contextmanager
|
||||
from dataclasses import dataclass
|
||||
from pathlib import Path
|
||||
from typing import TYPE_CHECKING, Any, Generic, Sequence, TypeVar
|
||||
from typing import TYPE_CHECKING, Any, Generator, Generic, Sequence, TypeVar
|
||||
|
||||
from ..agent_provider import AgentProvisionPlan, get_provider, build_agent_provision_plan
|
||||
from ..egress import EgressPlan
|
||||
@@ -83,6 +83,9 @@ class BottleSpec:
|
||||
# True when launched via --headless (no TTY, no interactive prompts).
|
||||
# The git-gate host-key preflight uses this to error rather than prompt.
|
||||
headless: bool = False
|
||||
# Image startup policy. "fresh" preserves the normal build path;
|
||||
# "cached" reuses the current local image/artifact without rebuilding.
|
||||
image_policy: str = "fresh"
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
@@ -278,6 +281,18 @@ PlanT = TypeVar("PlanT", bound=BottlePlan)
|
||||
CleanupT = TypeVar("CleanupT", bound=BottleCleanupPlan)
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class BottleImages:
|
||||
"""Resolved image references (or artifact paths) for a bottle launch.
|
||||
|
||||
For Docker/macOS-container backends, `agent` and `sidecar` are string
|
||||
image refs. For the smolmachines backend they are Path objects pointing
|
||||
to pre-built `.smolmachine` artifacts."""
|
||||
|
||||
agent: str | Path
|
||||
sidecar: str | Path = ""
|
||||
|
||||
|
||||
class BottleBackend(ABC, Generic[PlanT, CleanupT]):
|
||||
"""Abstract base for selectable bottle backends. Concrete subclasses
|
||||
(e.g. DockerBottleBackend) own their own prepare/launch impls.
|
||||
@@ -287,6 +302,11 @@ class BottleBackend(ABC, Generic[PlanT, CleanupT]):
|
||||
|
||||
name: str
|
||||
|
||||
# Whether this backend can run a container engine *inside* the bottle.
|
||||
# Backends that cannot must reject `nested_containers: true` rather than
|
||||
# reach for a host daemon socket (issue #392).
|
||||
supports_nested_containers: bool = False
|
||||
|
||||
def prepare(self, spec: BottleSpec, stage_dir: Path) -> PlanT:
|
||||
"""Template method: run cross-backend host-side validation, then
|
||||
delegate to the subclass's `_resolve_plan` for the
|
||||
@@ -300,12 +320,16 @@ class BottleBackend(ABC, Generic[PlanT, CleanupT]):
|
||||
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_host_key import preflight_host_keys
|
||||
@@ -437,9 +461,27 @@ class BottleBackend(ABC, Generic[PlanT, CleanupT]):
|
||||
prompt file, Dockerfile path, and guest home all live on
|
||||
`agent_provision_plan` — the source of truth."""
|
||||
|
||||
def prelaunch_checks(self, plan: PlanT) -> None:
|
||||
"""Raise StaleImageError if any cached image used by this plan is stale.
|
||||
No-op default; backends override to call the shared check_stale*
|
||||
helpers on their image/artifact timestamps. Called by the CLI before
|
||||
launch so the operator can be prompted outside the launch context."""
|
||||
|
||||
@contextmanager
|
||||
def launch(self, plan: PlanT) -> Generator[Bottle, None, None]:
|
||||
"""Template: build or load images, then delegate to _launch_impl."""
|
||||
images = self._build_or_load_images(plan)
|
||||
with self._launch_impl(plan, images) as bottle:
|
||||
yield bottle
|
||||
|
||||
@abstractmethod
|
||||
def launch(self, plan: PlanT) -> AbstractContextManager[Bottle]:
|
||||
"""Build/run the bottle and yield a handle; tear down on exit."""
|
||||
def _build_or_load_images(self, plan: PlanT) -> BottleImages:
|
||||
"""Return the agent and sidecar image references (or artifact paths)
|
||||
for this plan, building fresh images when the policy requires it."""
|
||||
|
||||
@abstractmethod
|
||||
def _launch_impl(self, plan: PlanT, images: BottleImages) -> AbstractContextManager[Bottle]:
|
||||
"""Bring up the bottle using pre-resolved images; yield a handle; tear down on exit."""
|
||||
|
||||
def provision(self, plan: PlanT, bottle: "Bottle") -> str | None:
|
||||
"""Copy host-side files (CA cert, prompt, skills, .git) into
|
||||
|
||||
@@ -7,10 +7,13 @@ imports it rather than re-implementing it.
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import dataclasses
|
||||
|
||||
from ..egress import EgressPlan
|
||||
from ..git_gate import GitGatePlan
|
||||
from ..orchestrator.client import OrchestratorClient
|
||||
from ..orchestrator.client import OrchestratorClient, RegisteredBottle
|
||||
from ..orchestrator.registration import registration_inputs
|
||||
from ..orchestrator.secret_store import new_env_var_secret
|
||||
from .docker.gateway_provision import GatewayTransport, deprovision_git_gate, provision_git_gate
|
||||
|
||||
|
||||
@@ -23,21 +26,27 @@ def provision_bottle(
|
||||
*,
|
||||
image_ref: str = "",
|
||||
tokens: dict[str, str] | None = None,
|
||||
):
|
||||
env_var_secret: str | None = None,
|
||||
) -> RegisteredBottle:
|
||||
"""Register the bottle and provision its git-gate state. Rolls back the
|
||||
registration if provisioning fails so no orphan is left. Returns the
|
||||
`RegisteredBottle` from the orchestrator."""
|
||||
registration if provisioning fails so no orphan is left.
|
||||
|
||||
Generates a fresh ENV_VAR_SECRET, passes it to the orchestrator so it can
|
||||
encrypt the token values at rest, and stamps the secret onto the returned
|
||||
``RegisteredBottle`` so callers can inject it into the agent container's
|
||||
environment."""
|
||||
inputs = registration_inputs(egress_plan)
|
||||
env_var_secret = env_var_secret or new_env_var_secret()
|
||||
reg = client.register_bottle(
|
||||
source_ip, image_ref=image_ref, policy=inputs.policy,
|
||||
metadata=inputs.metadata, tokens=tokens,
|
||||
metadata=inputs.metadata, tokens=tokens, env_var_secret=env_var_secret,
|
||||
)
|
||||
try:
|
||||
provision_git_gate(transport, reg.bottle_id, git_gate_plan)
|
||||
except Exception:
|
||||
client.teardown_bottle(reg.bottle_id)
|
||||
raise
|
||||
return reg
|
||||
return dataclasses.replace(reg, env_var_secret=env_var_secret)
|
||||
|
||||
|
||||
def teardown_consolidated(
|
||||
@@ -45,10 +54,15 @@ def teardown_consolidated(
|
||||
transport: GatewayTransport,
|
||||
*,
|
||||
orchestrator_url: str,
|
||||
timeout: float | None = None,
|
||||
) -> None:
|
||||
"""Deregister the bottle and remove its git-gate state. Both steps are
|
||||
idempotent so this is safe from a cleanup trap."""
|
||||
OrchestratorClient(orchestrator_url).teardown_bottle(bottle_id)
|
||||
from ..orchestrator.config_store import DEFAULT_TEARDOWN_TIMEOUT_SECONDS
|
||||
OrchestratorClient(
|
||||
orchestrator_url,
|
||||
timeout=timeout if timeout is not None else DEFAULT_TEARDOWN_TIMEOUT_SECONDS,
|
||||
).teardown_bottle(bottle_id)
|
||||
deprovision_git_gate(transport, bottle_id)
|
||||
|
||||
|
||||
|
||||
@@ -31,7 +31,7 @@ from ...env import ResolvedEnv
|
||||
from ...git_gate import GitGatePlan
|
||||
from ...supervise import SupervisePlan
|
||||
from ...manifest import Manifest
|
||||
from .. import ActiveAgent, BottleBackend, BottleSpec
|
||||
from .. import ActiveAgent, BottleBackend, BottleImages, BottleSpec
|
||||
from . import cleanup as _cleanup
|
||||
from . import enumerate as _enumerate
|
||||
from . import launch as _launch
|
||||
@@ -100,9 +100,15 @@ class DockerBottleBackend(BottleBackend["DockerBottlePlan", "DockerBottleCleanup
|
||||
stage_dir=stage_dir,
|
||||
)
|
||||
|
||||
def prelaunch_checks(self, plan: DockerBottlePlan) -> None:
|
||||
_launch.stale_checks(plan)
|
||||
|
||||
def _build_or_load_images(self, plan: DockerBottlePlan) -> BottleImages:
|
||||
return _launch.build_or_load_images(plan)
|
||||
|
||||
@contextmanager
|
||||
def launch(self, plan: DockerBottlePlan) -> Generator[DockerBottle, None, None]:
|
||||
with _launch.launch(plan, provision=self.provision) as bottle:
|
||||
def _launch_impl(self, plan: DockerBottlePlan, images: BottleImages) -> Generator[DockerBottle, None, None]:
|
||||
with _launch.launch(plan, images, provision=self.provision) as bottle:
|
||||
yield bottle
|
||||
|
||||
def ensure_orchestrator(self) -> str:
|
||||
|
||||
@@ -39,6 +39,10 @@ class DockerBottlePlan(BottlePlan):
|
||||
# (egress proxy credentials, git-gate/supervise headers); set by launch
|
||||
# from the orchestrator registration. Empty pre-registration.
|
||||
identity_token: str = ""
|
||||
# Encryption key for the agent's stored egress secrets; injected into the
|
||||
# agent container as ENV_VAR_SECRET via the compose subprocess env (bare
|
||||
# name — value never written to the compose file). Empty pre-registration.
|
||||
env_var_secret: str = ""
|
||||
|
||||
@property
|
||||
def container_name(self) -> str:
|
||||
|
||||
@@ -17,6 +17,7 @@ from __future__ import annotations
|
||||
from typing import Any
|
||||
|
||||
from ...egress import egress_agent_env_entries
|
||||
from ...orchestrator.secret_store import ENV_VAR_SECRET_NAME
|
||||
from ..util import AGENT_CA_BUNDLE, AGENT_CA_PATH
|
||||
from .bottle_plan import DockerBottlePlan
|
||||
from .egress import EGRESS_PORT
|
||||
@@ -58,6 +59,10 @@ def consolidated_agent_compose(
|
||||
# the secret value never lands on argv or in the compose file.
|
||||
for name in sorted(plan.forwarded_env.keys()):
|
||||
env.append(name)
|
||||
# ENV_VAR_SECRET: bare name so the value comes from the compose subprocess
|
||||
# env (set in launch.py) and is never written to the compose file on disk.
|
||||
if getattr(plan, "env_var_secret", ""):
|
||||
env.append(ENV_VAR_SECRET_NAME)
|
||||
env.extend(egress_agent_env_entries(plan.egress_plan))
|
||||
|
||||
service: dict[str, Any] = {
|
||||
|
||||
@@ -15,12 +15,15 @@ from __future__ import annotations
|
||||
|
||||
from dataclasses import dataclass
|
||||
|
||||
from ... import log
|
||||
from ...docker_cmd import run_docker
|
||||
from ...egress import EgressPlan
|
||||
from ...git_gate import GitGatePlan
|
||||
from ...orchestrator.client import OrchestratorClient
|
||||
from ...orchestrator.gateway import GATEWAY_NETWORK
|
||||
from ...orchestrator.lifecycle import INFRA_NAME, OrchestratorService
|
||||
from ...orchestrator.secret_store import ENV_VAR_SECRET_NAME
|
||||
from ...orchestrator.reprovision import reprovision_bottles
|
||||
from ..consolidated_util import provision_bottle
|
||||
from ..consolidated_util import teardown_consolidated as _teardown_util
|
||||
from .gateway_provision import DockerGatewayTransport
|
||||
@@ -41,6 +44,7 @@ class LaunchContext:
|
||||
network: str # the shared gateway network to attach to
|
||||
gateway_ip: str # the gateway's address — the agent's proxy target
|
||||
orchestrator_url: str
|
||||
env_var_secret: str = "" # encryption key injected into the agent's env
|
||||
|
||||
|
||||
def _network_cidr(network: str) -> str:
|
||||
@@ -85,6 +89,55 @@ def _network_container_ips(network: str) -> list[str]:
|
||||
return ips
|
||||
|
||||
|
||||
def _reprovision_running_bottles(
|
||||
orchestrator_url: str,
|
||||
network: str = GATEWAY_NETWORK,
|
||||
infra_name: str = INFRA_NAME,
|
||||
) -> None:
|
||||
"""Re-inject egress tokens for any registered bottles that lost their
|
||||
in-memory tokens (e.g., after an infra container restart).
|
||||
|
||||
For each registered bottle whose source IP maps to a live container on the
|
||||
gateway network, reads ENV_VAR_SECRET via ``docker exec … printenv`` and
|
||||
calls ``POST /bottles/<id>/reprovision_gateway``. Idempotent — a no-op
|
||||
when the orchestrator already has all tokens loaded. Best-effort: a single
|
||||
container exec failure never blocks a new bottle launch."""
|
||||
client = OrchestratorClient(orchestrator_url)
|
||||
# Build {source_ip: container_name} from live containers on the gateway
|
||||
# network, excluding the infra container itself.
|
||||
try:
|
||||
proc = run_docker([
|
||||
"docker", "network", "inspect",
|
||||
"--format", "{{range .Containers}}{{.Name}} {{.IPv4Address}}\n{{end}}",
|
||||
network,
|
||||
])
|
||||
except OSError as exc:
|
||||
log.info(f"egress token reprovision skipped: {exc}")
|
||||
return
|
||||
ip_to_container: dict[str, str] = {}
|
||||
for line in proc.stdout.splitlines():
|
||||
parts = line.strip().split()
|
||||
if len(parts) >= 2 and parts[0] != infra_name:
|
||||
ip = parts[1].split("/", 1)[0]
|
||||
if ip:
|
||||
ip_to_container[ip] = parts[0]
|
||||
|
||||
secrets_by_ip: dict[str, str] = {}
|
||||
for source_ip, container_name in ip_to_container.items():
|
||||
proc = run_docker(
|
||||
["docker", "exec", container_name, "printenv", ENV_VAR_SECRET_NAME]
|
||||
)
|
||||
if proc.returncode == 0 and proc.stdout.strip():
|
||||
secrets_by_ip[source_ip] = proc.stdout.strip()
|
||||
|
||||
reprovisioned = reprovision_bottles(client, secrets_by_ip)
|
||||
if reprovisioned:
|
||||
log.info(
|
||||
"reprovisioned egress tokens",
|
||||
context={"count": reprovisioned},
|
||||
)
|
||||
|
||||
|
||||
def launch_consolidated(
|
||||
egress_plan: EgressPlan,
|
||||
git_gate_plan: GitGatePlan,
|
||||
@@ -96,9 +149,14 @@ def launch_consolidated(
|
||||
network: str = GATEWAY_NETWORK,
|
||||
) -> LaunchContext:
|
||||
"""Ensure the infra container is up, allocate + register the bottle, and
|
||||
provision its git-gate state. Returns the agent's attach context."""
|
||||
provision its git-gate state. Returns the agent's attach context.
|
||||
|
||||
Also reprovisiones egress tokens for any already-running bottles that lost
|
||||
their in-memory credentials (e.g. after an infra container restart), so
|
||||
they regain egress access before the new bottle is registered."""
|
||||
service = service or OrchestratorService()
|
||||
url = service.ensure_running()
|
||||
_reprovision_running_bottles(url, network=network, infra_name=infra_name)
|
||||
client = OrchestratorClient(url)
|
||||
|
||||
cidr = _network_cidr(network)
|
||||
@@ -117,15 +175,17 @@ def launch_consolidated(
|
||||
network=network,
|
||||
gateway_ip=gateway_ip,
|
||||
orchestrator_url=url,
|
||||
env_var_secret=reg.env_var_secret,
|
||||
)
|
||||
|
||||
|
||||
def teardown_consolidated(
|
||||
bottle_id: str, *, orchestrator_url: str, infra_name: str = INFRA_NAME,
|
||||
timeout: float | None = None,
|
||||
) -> None:
|
||||
"""Deregister the bottle and remove its git-gate state. Idempotent."""
|
||||
_teardown_util(bottle_id, DockerGatewayTransport(infra_name),
|
||||
orchestrator_url=orchestrator_url)
|
||||
orchestrator_url=orchestrator_url, timeout=timeout)
|
||||
|
||||
|
||||
__all__ = [
|
||||
|
||||
@@ -42,7 +42,9 @@ from ...git_gate import (
|
||||
provision_git_gate_dynamic_keys,
|
||||
revoke_git_gate_provisioned_keys,
|
||||
)
|
||||
from ...log import info, warn
|
||||
from ...image_cache import check_stale
|
||||
from ...log import die, info, warn
|
||||
from .. import BottleImages
|
||||
from . import util as docker_mod
|
||||
from .bottle import DockerBottle
|
||||
from .bottle_plan import DockerBottlePlan
|
||||
@@ -62,6 +64,7 @@ from .compose import (
|
||||
write_compose_file,
|
||||
)
|
||||
from .consolidated_compose import consolidated_agent_compose
|
||||
from ...orchestrator.config_store import resolve_teardown_timeout
|
||||
from .consolidated_launch import launch_consolidated, teardown_consolidated
|
||||
from ...orchestrator.gateway import DockerGateway
|
||||
|
||||
@@ -70,16 +73,47 @@ from ...orchestrator.gateway import DockerGateway
|
||||
_REPO_DIR = str(Path(__file__).resolve().parent.parent.parent.parent)
|
||||
|
||||
|
||||
def build_or_load_images(plan: DockerBottlePlan) -> BottleImages:
|
||||
"""Resolve the agent image ref for this plan.
|
||||
|
||||
Returns the committed snapshot if one exists, the cached image when the
|
||||
policy is 'cached', or builds a fresh image and returns that."""
|
||||
committed = read_committed_image(plan.slug)
|
||||
if committed and docker_mod.image_exists(committed):
|
||||
info(f"using committed image {committed!r}")
|
||||
return BottleImages(agent=committed)
|
||||
if plan.spec.image_policy == "cached":
|
||||
if not docker_mod.image_exists(plan.image):
|
||||
die(
|
||||
f"cached agent image {plan.image!r} not found; "
|
||||
"run without --cached-images to build it"
|
||||
)
|
||||
info(f"using cached agent image {plan.image!r}")
|
||||
return BottleImages(agent=plan.image)
|
||||
docker_mod.build_image(plan.image, _REPO_DIR, dockerfile=plan.dockerfile_path)
|
||||
docker_mod.verify_agent_image(
|
||||
plan.image, runtime_for(plan.agent_provider_template).smoke_test,
|
||||
)
|
||||
return BottleImages(agent=plan.image)
|
||||
|
||||
|
||||
@contextmanager
|
||||
def launch(
|
||||
plan: DockerBottlePlan,
|
||||
images: BottleImages,
|
||||
*,
|
||||
provision: Callable[[DockerBottlePlan, "DockerBottle"], str | None],
|
||||
) -> Generator[DockerBottle, None, None]:
|
||||
"""Build, launch, and provision a Docker bottle via compose.
|
||||
Teardown on exit."""
|
||||
"""Launch and provision a Docker bottle via compose. Teardown on exit."""
|
||||
stack = ExitStack()
|
||||
|
||||
# Stamp the resolved agent image ref into the plan so compose rendering
|
||||
# picks up the right image (may be a committed snapshot or cached ref).
|
||||
plan = dataclasses.replace(
|
||||
plan,
|
||||
agent_provision=dataclasses.replace(plan.agent_provision, image=str(images.agent)),
|
||||
)
|
||||
|
||||
_bottle_for_revoke = plan.manifest.bottle
|
||||
_git_gate_dir_for_revoke = git_gate_state_dir(plan.slug)
|
||||
|
||||
@@ -96,25 +130,6 @@ def launch(
|
||||
)
|
||||
|
||||
try:
|
||||
# Step 1: agent image. Use a committed snapshot when one exists
|
||||
# and is present in the local daemon; otherwise build from the
|
||||
# Dockerfile. (The gateway image is built by the orchestrator.)
|
||||
committed = read_committed_image(plan.slug)
|
||||
if committed and docker_mod.image_exists(committed):
|
||||
info(f"using committed image {committed!r}")
|
||||
plan = dataclasses.replace(
|
||||
plan,
|
||||
agent_provision=dataclasses.replace(plan.agent_provision, image=committed),
|
||||
)
|
||||
else:
|
||||
docker_mod.build_image(
|
||||
plan.image, _REPO_DIR,
|
||||
dockerfile=plan.dockerfile_path,
|
||||
)
|
||||
docker_mod.verify_agent_image(
|
||||
plan.image, runtime_for(plan.agent_provider_template).smoke_test,
|
||||
)
|
||||
|
||||
# Step 2: mint the git-gate dynamic (gitea) deploy keys, if any, before
|
||||
# provisioning the bottle's repos into the shared gateway.
|
||||
git_gate_plan = plan.git_gate_plan
|
||||
@@ -133,11 +148,14 @@ def launch(
|
||||
token_values = egress_resolve_token_values(
|
||||
plan.egress_plan.token_env_map, effective_env,
|
||||
)
|
||||
teardown_timeout = resolve_teardown_timeout()
|
||||
ctx = launch_consolidated(
|
||||
plan.egress_plan, git_gate_plan, image_ref=plan.image, tokens=token_values,
|
||||
)
|
||||
stack.callback(
|
||||
teardown_consolidated, ctx.bottle_id, orchestrator_url=ctx.orchestrator_url,
|
||||
teardown_consolidated, ctx.bottle_id,
|
||||
orchestrator_url=ctx.orchestrator_url,
|
||||
timeout=teardown_timeout,
|
||||
)
|
||||
|
||||
# Step 4: install the SHARED gateway CA into the agent (replaces the
|
||||
@@ -168,6 +186,7 @@ def launch(
|
||||
agent_git_gate_url=git_gate_url,
|
||||
agent_supervise_url=supervise_url,
|
||||
identity_token=ctx.identity_token,
|
||||
env_var_secret=ctx.env_var_secret,
|
||||
)
|
||||
|
||||
# Step 5: render + up the agent-only compose, pinned on the shared
|
||||
@@ -180,7 +199,12 @@ def launch(
|
||||
project = compose_project_name(plan.slug)
|
||||
# Forwarded vars (OAuth token, host interpolations) flow through the
|
||||
# subprocess env as bare names so values never land in the file.
|
||||
# ENV_VAR_SECRET follows the same pattern: bare name in the compose
|
||||
# spec, value only in the subprocess env so it is never written to disk.
|
||||
compose_env: dict[str, str] = {**os.environ, **plan.forwarded_env}
|
||||
if plan.env_var_secret:
|
||||
from ...orchestrator.secret_store import ENV_VAR_SECRET_NAME
|
||||
compose_env[ENV_VAR_SECRET_NAME] = plan.env_var_secret
|
||||
info(
|
||||
f"docker compose up -d (project {project}, agent on shared "
|
||||
f"gateway {ctx.gateway_ip}, ip {ctx.source_ip})"
|
||||
@@ -207,3 +231,21 @@ def launch(
|
||||
yield bottle
|
||||
finally:
|
||||
teardown()
|
||||
|
||||
|
||||
def stale_checks(plan: DockerBottlePlan) -> None:
|
||||
"""Raise StaleImageError if a cached image is older than the configured
|
||||
threshold. Only runs when image_policy is 'cached'. Called by the backend
|
||||
class's _image_stale_checks before _launch_impl starts any resources."""
|
||||
if plan.spec.image_policy != "cached":
|
||||
return
|
||||
committed = read_committed_image(plan.slug)
|
||||
if committed and docker_mod.image_exists(committed):
|
||||
ts = docker_mod.image_created_at(committed)
|
||||
if ts is not None:
|
||||
check_stale(f"agent image {committed!r}", ts)
|
||||
return
|
||||
if docker_mod.image_exists(plan.image):
|
||||
ts = docker_mod.image_created_at(plan.image)
|
||||
if ts is not None:
|
||||
check_stale(f"agent image {plan.image!r}", ts)
|
||||
|
||||
@@ -5,6 +5,7 @@ existence, and building images."""
|
||||
from __future__ import annotations
|
||||
|
||||
import os
|
||||
from datetime import datetime, timezone
|
||||
import re
|
||||
import shutil
|
||||
import subprocess
|
||||
@@ -197,3 +198,46 @@ def commit_container(container_name: str, image_tag: str) -> None:
|
||||
f"{(result.stderr or '').strip() or '<no stderr>'}"
|
||||
)
|
||||
info(f"committed {container_name!r} → {image_tag!r}")
|
||||
|
||||
|
||||
def image_created_at(ref: str) -> datetime | None:
|
||||
"""Return Docker's image Created timestamp as an aware UTC datetime, or
|
||||
None when the field is absent or unparseable. Callers should skip the
|
||||
stale check when None is returned."""
|
||||
r = subprocess.run(
|
||||
["docker", "image", "inspect", "--format", "{{.Created}}", ref],
|
||||
capture_output=True,
|
||||
text=True,
|
||||
check=False,
|
||||
)
|
||||
if r.returncode != 0:
|
||||
die(
|
||||
f"docker image inspect for {ref!r} failed: "
|
||||
f"{(r.stderr or '').strip() or '<no stderr>'}"
|
||||
)
|
||||
raw = r.stdout.strip()
|
||||
if not raw:
|
||||
return None
|
||||
try:
|
||||
return _parse_docker_timestamp(raw)
|
||||
except ValueError:
|
||||
return None
|
||||
|
||||
|
||||
def _parse_docker_timestamp(raw: str) -> datetime:
|
||||
text = raw.strip()
|
||||
if text.endswith("Z"):
|
||||
text = text[:-1] + "+00:00"
|
||||
dot = text.find(".")
|
||||
if dot != -1:
|
||||
tz_plus = text.find("+", dot)
|
||||
tz_minus = text.find("-", dot)
|
||||
tz_candidates = [pos for pos in (tz_plus, tz_minus) if pos != -1]
|
||||
if tz_candidates:
|
||||
tz_pos = min(tz_candidates)
|
||||
frac = text[dot + 1:tz_pos]
|
||||
text = text[:dot + 1] + frac[:6].ljust(6, "0") + text[tz_pos:]
|
||||
dt = datetime.fromisoformat(text)
|
||||
if dt.tzinfo is None:
|
||||
dt = dt.replace(tzinfo=timezone.utc)
|
||||
return dt.astimezone(timezone.utc)
|
||||
|
||||
@@ -18,7 +18,7 @@ from ...env import ResolvedEnv
|
||||
from ...git_gate import GitGatePlan
|
||||
from ...manifest import Manifest
|
||||
from ...supervise import SupervisePlan
|
||||
from .. import ActiveAgent, BottleBackend, BottleSpec
|
||||
from .. import ActiveAgent, BottleBackend, BottleImages, BottleSpec
|
||||
from . import cleanup as _cleanup
|
||||
from . import enumerate as _enumerate
|
||||
from . import launch as _launch
|
||||
@@ -92,11 +92,18 @@ class FirecrackerBottleBackend(
|
||||
stage_dir=stage_dir,
|
||||
)
|
||||
|
||||
def _build_or_load_images(self, plan: FirecrackerBottlePlan) -> BottleImages:
|
||||
return BottleImages(agent=_launch.build_or_load_agent_base(plan))
|
||||
|
||||
def prelaunch_checks(self, plan: FirecrackerBottlePlan) -> None:
|
||||
_launch.stale_checks(plan)
|
||||
|
||||
@contextmanager
|
||||
def launch(
|
||||
self, plan: FirecrackerBottlePlan
|
||||
def _launch_impl(
|
||||
self, plan: FirecrackerBottlePlan, images: BottleImages,
|
||||
) -> Generator[FirecrackerBottle, None, None]:
|
||||
with _launch.launch(plan, provision=self.provision) as bottle:
|
||||
assert isinstance(images.agent, Path)
|
||||
with _launch.launch(plan, images.agent, provision=self.provision) as bottle:
|
||||
yield bottle
|
||||
|
||||
def prepare_cleanup(self) -> FirecrackerBottleCleanupPlan:
|
||||
|
||||
@@ -22,6 +22,9 @@ class FirecrackerBottlePlan(BottlePlan):
|
||||
# (egress proxy credentials, git-gate/supervise headers); set by launch
|
||||
# from the orchestrator registration. Empty pre-registration.
|
||||
identity_token: str = ""
|
||||
# Applied to every agent SSH exec and mirrored into /run inside the VM so
|
||||
# the host can recover it after the infra VM restarts.
|
||||
env_var_secret: str = ""
|
||||
|
||||
@property
|
||||
def container_name(self) -> str:
|
||||
|
||||
@@ -1,8 +1,23 @@
|
||||
"""Cleanup for the Firecracker backend.
|
||||
|
||||
Orphans are: firecracker VMM processes whose config lives under our run
|
||||
dir, and the per-bottle run dirs. TAP slots free themselves (the flock
|
||||
drops when the launcher exits), so there is nothing to reclaim there.
|
||||
Reaps *orphans* only — resources with no live VM behind them:
|
||||
|
||||
* orphan run dirs: a per-bottle run dir (holding the ~1G rootfs.ext4)
|
||||
whose firecracker process has exited. These leak when a launch is
|
||||
hard-killed before its teardown runs (host OOM/crash, a cancelled CI
|
||||
job, `kill -9`); the clean-exit path already removes its own dir in
|
||||
launch.py.
|
||||
* orphan VM pids: a firecracker process whose run dir is already gone
|
||||
— 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.)
|
||||
|
||||
TAP slots free themselves (the flock drops when the launcher exits), so
|
||||
there is nothing to reclaim there.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
@@ -22,38 +37,79 @@ def _run_root() -> Path:
|
||||
return util.cache_dir() / "run"
|
||||
|
||||
|
||||
def _orphan_vm_pids() -> list[int]:
|
||||
"""firecracker processes whose --config-file is under our run dir."""
|
||||
run_root = str(_run_root())
|
||||
def _run_dir_of(cmd: 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`,
|
||||
so the run dir is the config file's parent when it sits directly under
|
||||
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
|
||||
if parent.parent == run_root:
|
||||
return parent
|
||||
return None
|
||||
|
||||
|
||||
def _scan_processes(run_root: Path) -> tuple[set[str], list[int]]:
|
||||
"""Inspect running firecracker VMs under ``run_root``.
|
||||
|
||||
Returns ``(live_run_dirs, orphan_pids)``:
|
||||
* ``live_run_dirs`` — run dirs backed by a running VM (never reaped);
|
||||
* ``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:
|
||||
return []
|
||||
pids: list[int] = []
|
||||
return set(), []
|
||||
live: set[str] = set()
|
||||
orphan_pids: list[int] = []
|
||||
for line in result.stdout.splitlines():
|
||||
parts = line.split(None, 1)
|
||||
if len(parts) != 2 or run_root not in parts[1]:
|
||||
if len(parts) != 2:
|
||||
continue
|
||||
try:
|
||||
pids.append(int(parts[0]))
|
||||
pid = int(parts[0])
|
||||
except ValueError:
|
||||
continue
|
||||
return pids
|
||||
run_dir = _run_dir_of(parts[1], run_root)
|
||||
if run_dir is None:
|
||||
continue
|
||||
if run_dir.is_dir():
|
||||
live.add(str(run_dir))
|
||||
else:
|
||||
orphan_pids.append(pid)
|
||||
return live, orphan_pids
|
||||
|
||||
|
||||
def _run_dirs() -> list[str]:
|
||||
run_root = _run_root()
|
||||
def live_run_dirs() -> tuple[Path, ...]:
|
||||
"""Run directories backed by currently running agent microVMs."""
|
||||
live, _ = _scan_processes(_run_root())
|
||||
return tuple(Path(path) for path in sorted(live))
|
||||
|
||||
|
||||
def _orphan_run_dirs(run_root: Path, live: set[str]) -> list[str]:
|
||||
"""Run dirs with no live VM behind them — the leaked ones to remove."""
|
||||
if not run_root.is_dir():
|
||||
return []
|
||||
return sorted(str(p) for p in run_root.iterdir() if p.is_dir())
|
||||
return sorted(
|
||||
str(p) for p in run_root.iterdir()
|
||||
if p.is_dir() and str(p) not in live
|
||||
)
|
||||
|
||||
|
||||
def prepare_cleanup() -> FirecrackerBottleCleanupPlan:
|
||||
run_root = _run_root()
|
||||
live, orphan_pids = _scan_processes(run_root)
|
||||
return FirecrackerBottleCleanupPlan(
|
||||
vm_pids=tuple(_orphan_vm_pids()),
|
||||
run_dirs=tuple(_run_dirs()),
|
||||
vm_pids=tuple(orphan_pids),
|
||||
run_dirs=tuple(_orphan_run_dirs(run_root, live)),
|
||||
)
|
||||
|
||||
|
||||
|
||||
@@ -25,16 +25,27 @@ 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 ...orchestrator.client import OrchestratorClient
|
||||
from ...log import info
|
||||
from ...orchestrator.client import OrchestratorClient, OrchestratorClientError
|
||||
from ...orchestrator.lifecycle import (
|
||||
OrchestratorStartError, # re-exported so callers can catch it
|
||||
)
|
||||
from ..consolidated_util import provision_bottle, teardown_consolidated as _teardown_util
|
||||
from . import infra_vm
|
||||
from ...orchestrator.reprovision import reprovision_bottles
|
||||
from ...orchestrator.secret_store import ENV_VAR_SECRET_NAME
|
||||
from ..consolidated_util import (
|
||||
provision_bottle,
|
||||
teardown_consolidated as _teardown_util,
|
||||
)
|
||||
from . import cleanup, infra_vm, util
|
||||
|
||||
_ENV_VAR_SECRET_PATH = "/run/bot-bottle/env-var-secret"
|
||||
|
||||
|
||||
class ConsolidatedLaunchError(RuntimeError):
|
||||
@@ -50,6 +61,55 @@ class LaunchContext:
|
||||
source_ip: str # the VM's guest IP — the attribution key
|
||||
gateway_ca_pem: str # the shared gateway CA the provisioner installs
|
||||
orchestrator_url: str
|
||||
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(
|
||||
util.ssh_base_argv(private_key, guest_ip)
|
||||
+ [f"umask 077; mkdir -p /run/bot-bottle; cat > {_ENV_VAR_SECRET_PATH}"],
|
||||
input=secret, capture_output=True, text=True, check=False,
|
||||
)
|
||||
if proc.returncode != 0:
|
||||
raise ConsolidatedLaunchError(
|
||||
f"failed to persist {ENV_VAR_SECRET_NAME} in agent VM: "
|
||||
f"{proc.stderr.strip() or '<no stderr>'}"
|
||||
)
|
||||
|
||||
|
||||
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(
|
||||
@@ -66,6 +126,7 @@ def launch_consolidated(
|
||||
infra = infra_vm.ensure_running()
|
||||
url = infra.control_plane_url
|
||||
client = OrchestratorClient(url)
|
||||
_reprovision_running_bottles(client)
|
||||
|
||||
transport = infra_vm.gateway_transport()
|
||||
reg = provision_bottle(
|
||||
@@ -80,15 +141,19 @@ def launch_consolidated(
|
||||
source_ip=guest_ip,
|
||||
gateway_ca_pem=infra.gateway_ca_pem(),
|
||||
orchestrator_url=url,
|
||||
env_var_secret=reg.env_var_secret,
|
||||
)
|
||||
|
||||
|
||||
def teardown_consolidated(bottle_id: str, *, orchestrator_url: str) -> None:
|
||||
def teardown_consolidated(
|
||||
bottle_id: str, *, orchestrator_url: str, timeout: float | None = None,
|
||||
) -> None:
|
||||
"""Deregister the bottle and remove its git-gate state from the gateway
|
||||
VM. Both steps are idempotent so this is safe from a cleanup trap. Does
|
||||
NOT stop the infra VM — it's a persistent per-host singleton shared by
|
||||
every bottle."""
|
||||
_teardown_util(bottle_id, infra_vm.gateway_transport(), orchestrator_url=orchestrator_url)
|
||||
_teardown_util(bottle_id, infra_vm.gateway_transport(),
|
||||
orchestrator_url=orchestrator_url, timeout=timeout)
|
||||
|
||||
|
||||
__all__ = [
|
||||
|
||||
@@ -5,7 +5,7 @@ backend — we stream the guest root filesystem out over the control
|
||||
channel (SSH here). Unlike the other backends this needs no Docker: the
|
||||
tar *is* the resumable artifact. `resume` extracts it and rebuilds a
|
||||
fresh per-bottle ext4 with `mke2fs -d` (see `util.build_committed_rootfs_dir`
|
||||
and `launch._build_agent_base`). The bottle keeps running after the
|
||||
and `launch.build_or_load_agent_base`). The bottle keeps running after the
|
||||
snapshot.
|
||||
"""
|
||||
|
||||
|
||||
@@ -58,6 +58,12 @@ def _rootfs_digest(dockerfile: Path) -> str:
|
||||
return h.hexdigest()[:16]
|
||||
|
||||
|
||||
def cached_agent_rootfs_dir(dockerfile: Path) -> Path | None:
|
||||
"""Return the ready cached rootfs for ``dockerfile``, if one exists."""
|
||||
base = util.cache_dir() / "rootfs" / f"agent-{_rootfs_digest(dockerfile)}"
|
||||
return base if (base / ".bb-ready").is_file() else None
|
||||
|
||||
|
||||
def build_agent_rootfs_dir(
|
||||
dockerfile: Path, *, image_tag: str, smoke_test: tuple[str, ...] = (),
|
||||
) -> Path:
|
||||
@@ -72,7 +78,7 @@ def build_agent_rootfs_dir(
|
||||
silent-failure image at build time rather than at first agent use."""
|
||||
digest = _rootfs_digest(dockerfile)
|
||||
base = util.cache_dir() / "rootfs" / f"agent-{digest}"
|
||||
if (base / ".bb-ready").is_file():
|
||||
if cached_agent_rootfs_dir(dockerfile) is not None:
|
||||
info(f"using cached agent rootfs {base.name}")
|
||||
return base
|
||||
|
||||
|
||||
@@ -33,6 +33,7 @@ from pathlib import Path
|
||||
from typing import Generator
|
||||
|
||||
from ...log import die, info
|
||||
from .. import util as backend_util
|
||||
from ..docker import util as docker_mod
|
||||
from ..docker.gateway_provision import GatewayProvisionError
|
||||
from . import firecracker_vm, infra_artifact, netpool, util
|
||||
@@ -93,19 +94,18 @@ class InfraVm:
|
||||
"""The gateway's mitmproxy CA (PEM) that agents install to trust its
|
||||
TLS interception. Generated a moment after boot, so this polls over
|
||||
SSH until it appears (mirrors DockerGateway.ca_cert_pem)."""
|
||||
deadline = time.monotonic() + timeout
|
||||
while True:
|
||||
def _fetch() -> str | None:
|
||||
proc = subprocess.run(
|
||||
util.ssh_base_argv(self.private_key, self.guest_ip)
|
||||
+ [f"cat {_GATEWAY_CA_PATH}"],
|
||||
capture_output=True, text=True, timeout=15, check=False,
|
||||
)
|
||||
if proc.returncode == 0 and "BEGIN CERTIFICATE" in proc.stdout:
|
||||
return proc.stdout
|
||||
if time.monotonic() >= deadline:
|
||||
die(f"gateway CA not available after {timeout:g}s: "
|
||||
f"{proc.stderr.strip() or 'empty'}")
|
||||
time.sleep(_HEALTH_POLL_SECONDS)
|
||||
ok = proc.returncode == 0 and "BEGIN CERTIFICATE" in proc.stdout
|
||||
return proc.stdout if ok else None
|
||||
try:
|
||||
return backend_util.poll_ca_cert(_fetch, timeout=timeout)
|
||||
except TimeoutError as exc:
|
||||
die(str(exc))
|
||||
|
||||
|
||||
def ensure_built() -> None:
|
||||
|
||||
@@ -26,6 +26,7 @@ from __future__ import annotations
|
||||
|
||||
import dataclasses
|
||||
import os
|
||||
import shutil
|
||||
from contextlib import ExitStack, contextmanager
|
||||
from pathlib import Path
|
||||
from typing import Callable, Generator
|
||||
@@ -45,15 +46,19 @@ from ...git_gate import (
|
||||
provision_git_gate_dynamic_keys,
|
||||
revoke_git_gate_provisioned_keys,
|
||||
)
|
||||
from ...log import info, warn
|
||||
from ...image_cache import check_stale_path
|
||||
from ...log import die, info, warn
|
||||
from ...supervise 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 .bottle import FirecrackerBottle
|
||||
from .bottle_plan import FirecrackerBottlePlan
|
||||
from ...orchestrator.config_store import resolve_teardown_timeout
|
||||
from ...orchestrator.secret_store import ENV_VAR_SECRET_NAME
|
||||
from .consolidated_launch import (
|
||||
launch_consolidated,
|
||||
persist_env_var_secret,
|
||||
teardown_consolidated,
|
||||
)
|
||||
|
||||
@@ -64,6 +69,7 @@ _GIT_HTTP_PORT = 9420
|
||||
@contextmanager
|
||||
def launch(
|
||||
plan: FirecrackerBottlePlan,
|
||||
agent_base: Path,
|
||||
*,
|
||||
provision: Callable[[FirecrackerBottlePlan, "FirecrackerBottle"], str | None],
|
||||
) -> Generator[FirecrackerBottle, None, None]:
|
||||
@@ -85,11 +91,9 @@ def launch(
|
||||
raise teardown_exc
|
||||
|
||||
try:
|
||||
# Step 1: agent rootfs. Built from the Dockerfile inside a Firecracker
|
||||
# builder VM (buildah, no host docker); a committed snapshot is reused
|
||||
# when present. Returns the base dir the per-bottle ext4 is made from.
|
||||
plan, agent_base = _build_agent_base(plan)
|
||||
|
||||
# Step 1 (rootfs resolution/build) runs in BottleBackend.launch before
|
||||
# this context starts resources. ``agent_base`` is the selected cache,
|
||||
# fresh build, or committed snapshot.
|
||||
# Step 2: mint the git-gate dynamic (gitea) deploy keys, if any.
|
||||
git_gate_plan = plan.git_gate_plan
|
||||
if git_gate_plan.upstreams:
|
||||
@@ -112,6 +116,7 @@ def launch(
|
||||
token_values = egress_resolve_token_values(
|
||||
plan.egress_plan.token_env_map, effective_env,
|
||||
)
|
||||
teardown_timeout = resolve_teardown_timeout()
|
||||
ctx = launch_consolidated(
|
||||
plan.egress_plan, git_gate_plan,
|
||||
guest_ip=slot.guest_ip,
|
||||
@@ -121,6 +126,7 @@ def launch(
|
||||
stack.callback(
|
||||
teardown_consolidated, ctx.bottle_id,
|
||||
orchestrator_url=ctx.orchestrator_url,
|
||||
timeout=teardown_timeout,
|
||||
)
|
||||
|
||||
# Step 5: install the SHARED gateway CA (replaces the per-bottle CA).
|
||||
@@ -149,6 +155,7 @@ def launch(
|
||||
git_gate_plan=git_gate_plan,
|
||||
egress_plan=egress_plan,
|
||||
identity_token=ctx.identity_token,
|
||||
env_var_secret=ctx.env_var_secret,
|
||||
# Deliver the identity token as egress proxy credentials — clients
|
||||
# honor `HTTPS_PROXY=http://id:token@gw` without app changes; the
|
||||
# gateway reads Proxy-Authorization, validates the (source_ip,
|
||||
@@ -164,6 +171,10 @@ 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)
|
||||
@@ -179,6 +190,7 @@ def launch(
|
||||
)
|
||||
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)
|
||||
|
||||
# Authoritative fail-closed egress-boundary check, before the agent
|
||||
# runs: prove the VM cannot reach the host directly.
|
||||
@@ -206,9 +218,7 @@ def launch(
|
||||
teardown()
|
||||
|
||||
|
||||
def _build_agent_base(
|
||||
plan: FirecrackerBottlePlan,
|
||||
) -> tuple[FirecrackerBottlePlan, Path]:
|
||||
def build_or_load_agent_base(plan: FirecrackerBottlePlan) -> Path:
|
||||
"""Produce the agent's base rootfs dir. Primary path: build the Dockerfile
|
||||
inside a Firecracker builder VM (buildah, no host docker), smoke-testing
|
||||
the image before export. A committed snapshot (freeze/migrate) is resumed
|
||||
@@ -217,13 +227,36 @@ def _build_agent_base(
|
||||
committed_tar = committed_rootfs_path(plan.slug)
|
||||
if committed and committed_tar.is_file():
|
||||
info(f"resuming from committed rootfs {committed_tar}")
|
||||
return plan, util.build_committed_rootfs_dir(committed_tar)
|
||||
base = image_builder.build_agent_rootfs_dir(
|
||||
Path(plan.dockerfile_path),
|
||||
return util.build_committed_rootfs_dir(committed_tar)
|
||||
dockerfile = Path(plan.dockerfile_path)
|
||||
if plan.spec.image_policy == "cached":
|
||||
cached = image_builder.cached_agent_rootfs_dir(dockerfile)
|
||||
if cached is None:
|
||||
die(
|
||||
f"cached agent rootfs for {plan.image!r} not found; "
|
||||
"run without --cached-images to build it"
|
||||
)
|
||||
info(f"using cached agent rootfs {cached.name}")
|
||||
return cached
|
||||
return image_builder.build_agent_rootfs_dir(
|
||||
dockerfile,
|
||||
image_tag=plan.image,
|
||||
smoke_test=runtime_for(plan.agent_provider_template).smoke_test,
|
||||
)
|
||||
return plan, base
|
||||
|
||||
|
||||
def stale_checks(plan: FirecrackerBottlePlan) -> None:
|
||||
"""Raise when the cached rootfs selected by this plan is stale."""
|
||||
if plan.spec.image_policy != "cached":
|
||||
return
|
||||
committed = read_committed_image(plan.slug)
|
||||
committed_tar = committed_rootfs_path(plan.slug)
|
||||
if committed and committed_tar.is_file():
|
||||
check_stale_path(f"agent rootfs {committed_tar}", committed_tar)
|
||||
return
|
||||
cached = image_builder.cached_agent_rootfs_dir(Path(plan.dockerfile_path))
|
||||
if cached is not None:
|
||||
check_stale_path(f"agent rootfs {cached}", cached / ".bb-ready")
|
||||
|
||||
|
||||
# --- agent guest env -------------------------------------------------
|
||||
@@ -239,6 +272,11 @@ def _agent_guest_env(plan: FirecrackerBottlePlan, host_ip: str) -> dict[str, str
|
||||
"HTTPS_PROXY": proxy_url, "HTTP_PROXY": proxy_url,
|
||||
"https_proxy": proxy_url, "http_proxy": proxy_url,
|
||||
"NO_PROXY": no_proxy, "no_proxy": no_proxy,
|
||||
# Rootfs export can leave Git's implicit XDG paths unreadable even
|
||||
# after the runtime repair. Bypass that discovery and name the
|
||||
# provisioned global config explicitly so insteadOf can never fall
|
||||
# through to the credential-bearing upstream URL.
|
||||
"GIT_CONFIG_GLOBAL": f"{plan.guest_home}/.gitconfig",
|
||||
"NODE_EXTRA_CA_CERTS": AGENT_CA_PATH,
|
||||
"SSL_CERT_FILE": AGENT_CA_BUNDLE,
|
||||
"REQUESTS_CA_BUNDLE": AGENT_CA_BUNDLE,
|
||||
@@ -247,6 +285,8 @@ def _agent_guest_env(plan: FirecrackerBottlePlan, host_ip: str) -> dict[str, str
|
||||
env["GIT_GATE_URL"] = plan.agent_git_gate_url
|
||||
if plan.agent_supervise_url:
|
||||
env["MCP_SUPERVISE_URL"] = plan.agent_supervise_url
|
||||
if plan.env_var_secret:
|
||||
env[ENV_VAR_SECRET_NAME] = plan.env_var_secret
|
||||
for entry in egress_agent_env_entries(plan.egress_plan):
|
||||
key, _, value = entry.partition("=")
|
||||
env[key] = value
|
||||
|
||||
@@ -131,6 +131,29 @@ def build_artifact(out_dir: Path) -> tuple[str, Path, Path]:
|
||||
return version, gz, sha
|
||||
|
||||
|
||||
def _try_download_published(out_dir: Path) -> tuple[str, Path, Path] | None:
|
||||
"""If this version's artifact is already in the registry, download the gz
|
||||
and sha to out_dir and return (version, gz_path, sha_path). Returns None
|
||||
when not yet published."""
|
||||
version = infra_artifact.infra_artifact_version(infra_vm._infra_init())
|
||||
sha_url = infra_artifact.artifact_url(version, "rootfs.ext4.gz.sha256")
|
||||
try:
|
||||
with urllib.request.urlopen(infra_artifact._open(sha_url)):
|
||||
pass
|
||||
except urllib.error.HTTPError as e:
|
||||
if e.code == 404:
|
||||
return None
|
||||
raise SystemExit(f"registry check failed (HTTP {e.code}): {sha_url}")
|
||||
except urllib.error.URLError as e:
|
||||
raise SystemExit(f"registry unreachable: {sha_url} ({e.reason})")
|
||||
print(f"infra rootfs {version} already published — downloading instead of building")
|
||||
gz = out_dir / "rootfs.ext4.gz"
|
||||
sha = out_dir / "rootfs.ext4.gz.sha256"
|
||||
infra_artifact._download(infra_artifact.artifact_url(version, "rootfs.ext4.gz"), gz)
|
||||
infra_artifact._download(infra_artifact.artifact_url(version, "rootfs.ext4.gz.sha256"), sha)
|
||||
return version, gz, sha
|
||||
|
||||
|
||||
def _publish_bundle(root: Path, token: str) -> str:
|
||||
version_file = root / "version.txt"
|
||||
# Guard the read so a missing version.txt is a clean error, not a raw
|
||||
@@ -187,6 +210,8 @@ def main(argv: list[str] | None = None) -> int:
|
||||
help="build a candidate bundle in DIR without publishing")
|
||||
mode.add_argument("--publish-dir", type=Path,
|
||||
help="publish an already-built and tested candidate bundle")
|
||||
parser.add_argument("--reuse-published", action="store_true",
|
||||
help="with --output: download from registry if already published instead of building")
|
||||
args = parser.parse_args(argv)
|
||||
|
||||
_, _, token = infra_artifact._config()
|
||||
@@ -197,6 +222,14 @@ def main(argv: list[str] | None = None) -> int:
|
||||
|
||||
if args.output is not None:
|
||||
args.output.mkdir(parents=True, exist_ok=True)
|
||||
reused = None
|
||||
if args.reuse_published:
|
||||
reused = _try_download_published(args.output)
|
||||
if reused is not None:
|
||||
version, _, _ = reused
|
||||
(args.output / "version.txt").write_text(version + "\n", encoding="utf-8")
|
||||
print(f"reused published infra rootfs candidate {version}")
|
||||
return 0
|
||||
version, _gz, _sha = build_artifact(args.output)
|
||||
(args.output / "version.txt").write_text(version + "\n", encoding="utf-8")
|
||||
print(f"built infra rootfs candidate {version}")
|
||||
|
||||
@@ -373,6 +373,12 @@ mount -o remount,rw / 2>/dev/null
|
||||
# scratch dirs there — git worktrees, build temp, `git init /tmp/...`, etc.
|
||||
mkdir -p /tmp && chmod 1777 /tmp
|
||||
|
||||
# Rootfs export also maps the image's original owners to the unprivileged
|
||||
# host build uid. That uid is not guaranteed to be node's uid in the guest;
|
||||
# restore the home-directory boundary before any SSH provisioning runs.
|
||||
chown node:node /home/node 2>/dev/null || true
|
||||
chmod 755 /home/node 2>/dev/null || true
|
||||
|
||||
# Install the per-bottle SSH pubkey from the kernel cmdline.
|
||||
KEY=$(sed -n 's/.*bb_pubkey=\([^ ]*\).*/\1/p' /proc/cmdline | base64 -d 2>/dev/null)
|
||||
if [ -n "$KEY" ]; then
|
||||
@@ -393,6 +399,9 @@ fi
|
||||
chown -R 0:0 /root 2>/dev/null || true
|
||||
|
||||
mkdir -p /etc/dropbear /run
|
||||
# Keep restart-recovery key material memory-backed, separate from both the
|
||||
# agent rootfs and the infra VM's persistent registry volume.
|
||||
mount -t tmpfs -o mode=0755 tmpfs /run 2>/dev/null || true
|
||||
# -R: generate host keys on demand. -E: log auth failures to stderr,
|
||||
# captured in the host-side console.log for debugging.
|
||||
/bb-dropbear -R -E -p 22 &
|
||||
|
||||
@@ -12,7 +12,7 @@ from ...env import ResolvedEnv
|
||||
from ...git_gate import GitGatePlan
|
||||
from ...supervise import SupervisePlan
|
||||
from ...manifest import Manifest
|
||||
from .. import ActiveAgent, BottleBackend, BottleSpec
|
||||
from .. import ActiveAgent, BottleBackend, BottleImages, BottleSpec
|
||||
from . import cleanup as _cleanup
|
||||
from . import enumerate as _enumerate
|
||||
from . import launch as _launch
|
||||
@@ -31,6 +31,7 @@ class MacosContainerBottleBackend(
|
||||
`--backend=macos-container`."""
|
||||
|
||||
name = "macos-container"
|
||||
supports_nested_containers = True
|
||||
|
||||
@classmethod
|
||||
def is_available(cls) -> bool:
|
||||
@@ -82,11 +83,17 @@ class MacosContainerBottleBackend(
|
||||
stage_dir=stage_dir,
|
||||
)
|
||||
|
||||
def prelaunch_checks(self, plan: MacosContainerBottlePlan) -> None:
|
||||
_launch.stale_checks(plan)
|
||||
|
||||
def _build_or_load_images(self, plan: MacosContainerBottlePlan) -> BottleImages:
|
||||
return _launch.build_or_load_images(plan)
|
||||
|
||||
@contextmanager
|
||||
def launch(
|
||||
self, plan: MacosContainerBottlePlan
|
||||
def _launch_impl(
|
||||
self, plan: MacosContainerBottlePlan, images: BottleImages
|
||||
) -> Generator[MacosContainerBottle, None, None]:
|
||||
with _launch.launch(plan, provision=self.provision) as bottle:
|
||||
with _launch.launch(plan, images, provision=self.provision) as bottle:
|
||||
yield bottle
|
||||
|
||||
def ensure_orchestrator(self) -> str:
|
||||
|
||||
@@ -68,9 +68,14 @@ class MacosContainerBottle(Bottle):
|
||||
# reaches the agent (PRD 0070): registration mints it *after* the
|
||||
# container exists — its source IP is the registration key and Apple
|
||||
# Container assigns that by DHCP — so it cannot be in the run-time env
|
||||
# the way docker's compose spec does it. `container exec --env` wins
|
||||
# over the run-time value, so the token-bearing proxy URL set here
|
||||
# supersedes the token-less one baked in at launch.
|
||||
# the way docker's compose spec does it.
|
||||
#
|
||||
# `container exec --env` does NOT override a run-time value — it
|
||||
# appends, leaving duplicate entries in the agent's `environ` whose
|
||||
# resolution is runtime-specific (Node last-wins, Rust first-wins). So
|
||||
# nothing here may rely on superseding: the proxy vars are supplied
|
||||
# *only* at exec time and are deliberately absent from the run-time
|
||||
# env. See `launch._agent_env_entries`.
|
||||
self._exec_env = dict(exec_env or {})
|
||||
self._closed = False
|
||||
|
||||
|
||||
@@ -20,6 +20,12 @@ class MacosContainerBottlePlan(BottlePlan):
|
||||
# bottle is registered. See launch.py's stamp for why it lives here and not
|
||||
# only in the exec-time proxy env.
|
||||
identity_token: str = ""
|
||||
# Guest-local container engine (issue #392). Gates the derived image, the
|
||||
# device-mode relaxation, and the resident podman service.
|
||||
nested_containers: bool = False
|
||||
# Generated before `container run` so it becomes part of the container's
|
||||
# configured environment and can be read back after an infra restart.
|
||||
env_var_secret: str = ""
|
||||
|
||||
@property
|
||||
def container_name(self) -> str:
|
||||
|
||||
@@ -36,8 +36,16 @@ from dataclasses import dataclass
|
||||
|
||||
from ...egress import EgressPlan
|
||||
from ...git_gate import GitGatePlan
|
||||
from ...orchestrator.client import OrchestratorClient
|
||||
from ..consolidated_util import provision_bottle, teardown_consolidated as _teardown_util
|
||||
from ...log import info
|
||||
from ...orchestrator.client import OrchestratorClient, OrchestratorClientError
|
||||
from ...orchestrator.reprovision import reprovision_bottles
|
||||
from ...orchestrator.secret_store import ENV_VAR_SECRET_NAME
|
||||
from ..consolidated_util import (
|
||||
provision_bottle,
|
||||
teardown_consolidated as _teardown_util,
|
||||
)
|
||||
from . import util as container_mod
|
||||
from .enumerate import CONTAINER_NAME_PREFIX, EnumerationError, enumerate_active
|
||||
from .gateway import GATEWAY_NETWORK
|
||||
from .gateway_provision import AppleGatewayTransport
|
||||
from .infra import MacosInfraService, OrchestratorStartError
|
||||
@@ -69,6 +77,7 @@ class LaunchContext:
|
||||
gateway_ip: str
|
||||
network: str
|
||||
orchestrator_url: str
|
||||
env_var_secret: str = "" # encryption key injected into the agent's env
|
||||
|
||||
|
||||
def ensure_gateway(
|
||||
@@ -80,12 +89,61 @@ def ensure_gateway(
|
||||
needs `gateway_ip` at run time."""
|
||||
service = service or MacosInfraService()
|
||||
infra = service.ensure_running()
|
||||
return GatewayEndpoint(
|
||||
endpoint = GatewayEndpoint(
|
||||
orchestrator_url=infra.control_plane_url,
|
||||
gateway_ip=infra.gateway_ip,
|
||||
gateway_ca_pem=service.ca_cert_pem(),
|
||||
network=service.network,
|
||||
)
|
||||
_reprovision_running_bottles(endpoint)
|
||||
return endpoint
|
||||
|
||||
|
||||
def _reprovision_running_bottles(endpoint: GatewayEndpoint) -> None:
|
||||
"""Recover keys from live Apple containers and restore gateway tokens."""
|
||||
try:
|
||||
secrets_by_ip: dict[str, str] = {}
|
||||
for agent in enumerate_active():
|
||||
name = f"{CONTAINER_NAME_PREFIX}{agent.slug}"
|
||||
source_ip = container_mod.inspect_container_network_ip(name, endpoint.network)
|
||||
if not source_ip:
|
||||
continue
|
||||
secret = container_mod.read_container_env(name, ENV_VAR_SECRET_NAME)
|
||||
if secret:
|
||||
secrets_by_ip[source_ip] = secret
|
||||
count = reprovision_bottles(
|
||||
OrchestratorClient(endpoint.orchestrator_url), secrets_by_ip,
|
||||
)
|
||||
if count:
|
||||
info(f"reprovisioned egress tokens for {count} macOS bottle(s)")
|
||||
except (OrchestratorClientError, EnumerationError, OSError) as exc:
|
||||
info(f"egress token reprovision skipped: {exc}")
|
||||
|
||||
|
||||
def live_source_ips(network: str) -> list[str]:
|
||||
"""Every running agent container's address on `network`.
|
||||
|
||||
The reconciliation input: the orchestrator lives inside the infra
|
||||
container and cannot enumerate the host's containers, so the host has to
|
||||
tell it which bottles are actually up. Containers that have not been
|
||||
assigned an address yet contribute nothing — the reap's grace window, not
|
||||
this list, is what protects an in-flight launch.
|
||||
|
||||
Raises `EnumerationError` when the live set cannot be determined
|
||||
authoritatively: either the container listing fails or any individual
|
||||
inspect fails. Callers must skip reconciliation in that case to avoid
|
||||
unregistering healthy bottles."""
|
||||
ips: list[str] = []
|
||||
for agent in enumerate_active():
|
||||
name = f"{CONTAINER_NAME_PREFIX}{agent.slug}"
|
||||
ip = container_mod.inspect_container_network_ip(name, network)
|
||||
if ip is None:
|
||||
raise EnumerationError(
|
||||
f"container inspect {name!r} failed; live set is not authoritative"
|
||||
)
|
||||
if ip:
|
||||
ips.append(ip)
|
||||
return ips
|
||||
|
||||
|
||||
def register_agent(
|
||||
@@ -96,15 +154,27 @@ def register_agent(
|
||||
endpoint: GatewayEndpoint,
|
||||
image_ref: str = "",
|
||||
tokens: dict[str, str] | None = None,
|
||||
env_var_secret: str | None = None,
|
||||
) -> LaunchContext:
|
||||
"""Register the (already running) agent by its address and provision its
|
||||
git-gate state into the gateway. `source_ip` must be read from the live
|
||||
container — it is the attribution key the gateway resolves policy by.
|
||||
Raises on failure; the caller tears down."""
|
||||
client = OrchestratorClient(endpoint.orchestrator_url)
|
||||
# Self-heal before registering: a launcher that died hard (SIGKILL, closed
|
||||
# terminal, host sleep) never ran its teardown callback, leaving an active
|
||||
# row with no container. vmnet recycles addresses, so such a row can
|
||||
# collide with this bottle's — and `by_source_ip` fail-closes on ambiguity,
|
||||
# which would resolve no policy at all and deny every host. Best-effort: a
|
||||
# reconciliation failure must not block an otherwise-fine launch.
|
||||
try:
|
||||
client.reconcile(live_source_ips(endpoint.network))
|
||||
except (OrchestratorClientError, EnumerationError) as e:
|
||||
info(f"registry reconciliation skipped: {e}")
|
||||
reg = provision_bottle(
|
||||
client, source_ip, egress_plan, git_gate_plan, AppleGatewayTransport(),
|
||||
image_ref=image_ref, tokens=tokens,
|
||||
env_var_secret=env_var_secret,
|
||||
)
|
||||
return LaunchContext(
|
||||
bottle_id=reg.bottle_id,
|
||||
@@ -113,20 +183,25 @@ def register_agent(
|
||||
gateway_ip=endpoint.gateway_ip,
|
||||
network=endpoint.network,
|
||||
orchestrator_url=endpoint.orchestrator_url,
|
||||
env_var_secret=reg.env_var_secret,
|
||||
)
|
||||
|
||||
|
||||
def teardown_consolidated(bottle_id: str, *, orchestrator_url: str) -> None:
|
||||
def teardown_consolidated(
|
||||
bottle_id: str, *, orchestrator_url: str, timeout: float | None = None,
|
||||
) -> None:
|
||||
"""Deregister the bottle and remove its git-gate state from the gateway.
|
||||
Both steps are idempotent so this is safe from a cleanup trap. Does NOT
|
||||
stop the gateway — it's a persistent per-host singleton."""
|
||||
_teardown_util(bottle_id, AppleGatewayTransport(), orchestrator_url=orchestrator_url)
|
||||
_teardown_util(bottle_id, AppleGatewayTransport(),
|
||||
orchestrator_url=orchestrator_url, timeout=timeout)
|
||||
|
||||
|
||||
__all__ = [
|
||||
"GatewayEndpoint",
|
||||
"LaunchContext",
|
||||
"ensure_gateway",
|
||||
"live_source_ips",
|
||||
"register_agent",
|
||||
"teardown_consolidated",
|
||||
"ConsolidatedLaunchError",
|
||||
|
||||
@@ -8,13 +8,21 @@ from ...bottle_state import read_metadata
|
||||
from .. import ActiveAgent
|
||||
from .infra import INFRA_NAME
|
||||
|
||||
_PREFIX = "bot-bottle-"
|
||||
# The name every agent container carries: `bot-bottle-<slug>`. Exported
|
||||
# because callers that act on a running bottle (gateway-host rewrites,
|
||||
# registry reconciliation) have to map an enumerated slug back to a
|
||||
# container name.
|
||||
CONTAINER_NAME_PREFIX = "bot-bottle-"
|
||||
# The shared per-host infra container carries the same prefix as agent
|
||||
# containers but is infrastructure, not a bottle — one control plane + gateway
|
||||
# serves every agent, so listing it as an agent would invent one per host.
|
||||
_INFRA_NAMES = frozenset({INFRA_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"],
|
||||
@@ -23,12 +31,15 @@ def enumerate_active() -> list[ActiveAgent]:
|
||||
check=False,
|
||||
)
|
||||
if result.returncode != 0:
|
||||
return []
|
||||
raise EnumerationError(
|
||||
f"container list failed: "
|
||||
f"{(result.stderr or '').strip() or '<no stderr>'}"
|
||||
)
|
||||
out: list[ActiveAgent] = []
|
||||
for name in sorted(line.strip() for line in result.stdout.splitlines()):
|
||||
if not name.startswith(_PREFIX) or name in _INFRA_NAMES:
|
||||
if not name.startswith(CONTAINER_NAME_PREFIX) or name in _INFRA_NAMES:
|
||||
continue
|
||||
slug = name[len(_PREFIX):]
|
||||
slug = name[len(CONTAINER_NAME_PREFIX):]
|
||||
metadata = read_metadata(slug)
|
||||
out.append(ActiveAgent(
|
||||
backend_name="macos-container",
|
||||
|
||||
@@ -0,0 +1,96 @@
|
||||
"""Stable gateway name for macOS agents, via each bottle's `/etc/hosts`.
|
||||
|
||||
The shared gateway's address is assigned by vmnet's DHCP and changes whenever
|
||||
the infra container is recreated — a source-hash bump, an image upgrade, a
|
||||
crash. Every agent-facing URL (egress proxy, git-http, supervise) embeds that
|
||||
address, and the proxy URL reaches the agent as **process environment** at
|
||||
`container exec` time. A running process's `environ` cannot be rewritten from
|
||||
outside, so a moved gateway used to strand every running bottle permanently:
|
||||
not degraded, unreachable, until the bottle was relaunched and its session
|
||||
thrown away.
|
||||
|
||||
So the agent never learns the address. It is given a stable *name*
|
||||
(`GATEWAY_HOSTNAME`) in every URL, resolved through its own `/etc/hosts`.
|
||||
Unlike `environ`, that is a file — it can be rewritten inside a container that
|
||||
is already running, so a gateway that comes back at a new address is picked up
|
||||
by live bottles instead of orphaning them.
|
||||
|
||||
Apple Container 1.0 offers no container-name DNS on a user network (the only
|
||||
nameserver an agent sees is vmnet's, which does not know container names) and
|
||||
`container run` has no `--add-host`, so the entry is written by exec after the
|
||||
container starts.
|
||||
|
||||
Writing it needs root, and the agent runs as `node`: the agent therefore
|
||||
cannot repoint its own gateway name, while the host (which drives `container
|
||||
exec --user root`) can. That asymmetry is deliberate — keep it.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
from ...log import warn
|
||||
from . import util as container_mod
|
||||
from .enumerate import CONTAINER_NAME_PREFIX, enumerate_active
|
||||
|
||||
# The name every agent-facing gateway URL uses. Must not collide with a real
|
||||
# DNS name the agent might resolve; it is bottle-local by construction.
|
||||
GATEWAY_HOSTNAME = "bot-bottle-gateway"
|
||||
|
||||
# Marker so the rewrite is idempotent and only ever touches our own line —
|
||||
# the rest of /etc/hosts (localhost, the container's own name) is preserved.
|
||||
_MARKER = "# bot-bottle gateway"
|
||||
|
||||
|
||||
def _rewrite_script(gateway_ip: str) -> str:
|
||||
"""A shell one-liner that replaces our managed line in `/etc/hosts`.
|
||||
|
||||
Rewrites in place via a temp file + `cat` rather than `mv`, so the file
|
||||
keeps its original inode, ownership, and mode — a bind-mounted or
|
||||
pre-created `/etc/hosts` must not be replaced by a root-owned 0644 copy
|
||||
that the runtime then refuses to update.
|
||||
"""
|
||||
return (
|
||||
"set -e; "
|
||||
f"grep -v '{_MARKER}' /etc/hosts > /tmp/.bb-hosts || true; "
|
||||
f"printf '%s %s %s\\n' '{gateway_ip}' '{GATEWAY_HOSTNAME}' "
|
||||
f"'{_MARKER}' >> /tmp/.bb-hosts; "
|
||||
"cat /tmp/.bb-hosts > /etc/hosts; "
|
||||
"rm -f /tmp/.bb-hosts"
|
||||
)
|
||||
|
||||
|
||||
def set_gateway_host(container_name: str, gateway_ip: str) -> None:
|
||||
"""Point `GATEWAY_HOSTNAME` at `gateway_ip` inside one running container.
|
||||
|
||||
Must run before the agent is exec'd: the agent's proxy URL names the
|
||||
gateway, so the entry has to exist for its first connection. Idempotent —
|
||||
re-running with the same address is a no-op in effect.
|
||||
"""
|
||||
container_mod.exec_container_as_root(
|
||||
container_name, ["sh", "-c", _rewrite_script(gateway_ip)],
|
||||
)
|
||||
|
||||
|
||||
def refresh_gateway_host(gateway_ip: str) -> list[str]:
|
||||
"""Re-point every running bottle at the current gateway address.
|
||||
|
||||
Called once the shared gateway is known to be up, so a bottle stranded by
|
||||
an earlier gateway restart re-attaches instead of needing a relaunch.
|
||||
Returns the containers updated.
|
||||
|
||||
Best-effort per bottle: one container that refuses the write (already
|
||||
exiting, say) must not stop the others from being repaired, and must not
|
||||
fail the launch that triggered the sweep.
|
||||
"""
|
||||
updated: list[str] = []
|
||||
for agent in enumerate_active():
|
||||
name = f"{CONTAINER_NAME_PREFIX}{agent.slug}"
|
||||
try:
|
||||
set_gateway_host(name, gateway_ip)
|
||||
updated.append(name)
|
||||
# One bad bottle must not stop the sweep, so this is deliberately broad.
|
||||
except Exception as e: # noqa: BLE001 # pylint: disable=broad-exception-caught
|
||||
warn(f"could not re-point {name} at the gateway: {e}")
|
||||
return updated
|
||||
|
||||
|
||||
__all__ = ["GATEWAY_HOSTNAME", "set_gateway_host", "refresh_gateway_host"]
|
||||
@@ -41,7 +41,7 @@ from dataclasses import dataclass
|
||||
from pathlib import Path
|
||||
|
||||
from ... import log
|
||||
from ...orchestrator.gateway import GATEWAY_CA_CERT
|
||||
from ...orchestrator.gateway import GATEWAY_CA_CERT, MITMPROXY_HOME
|
||||
from ...orchestrator.lifecycle import (
|
||||
DEFAULT_PORT,
|
||||
DEFAULT_STARTUP_TIMEOUT_SECONDS,
|
||||
@@ -52,7 +52,9 @@ from ...paths import (
|
||||
CONTROL_PLANE_TOKEN_ENV,
|
||||
HOST_DB_FILENAME,
|
||||
host_control_plane_token,
|
||||
host_gateway_ca_dir,
|
||||
)
|
||||
from .. import util as backend_util
|
||||
from . import util as container_mod
|
||||
from .gateway import (
|
||||
DEFAULT_CA_TIMEOUT_SECONDS,
|
||||
@@ -217,6 +219,14 @@ class MacosInfraService:
|
||||
# Container-only DB volume: one kernel writes bot-bottle.db, never
|
||||
# shared with the host or another guest.
|
||||
"--volume", f"{self._db_volume}:{_DB_ROOT_IN_CONTAINER}",
|
||||
# The DB needs a container-only ext4 volume for coherent SQLite
|
||||
# locking, but the CA has no such constraint. Keep it in the host
|
||||
# app-data root so infra-container recreation and Apple Container
|
||||
# volume pruning cannot silently rotate every bottle's trust
|
||||
# anchor (issue #450).
|
||||
"--mount",
|
||||
container_mod.bind_mount_spec(
|
||||
str(host_gateway_ca_dir()), MITMPROXY_HOME),
|
||||
# Bind-mount the control-plane source (read-only); a code change
|
||||
# takes effect on relaunch with no image rebuild.
|
||||
"--mount",
|
||||
@@ -260,21 +270,19 @@ class MacosInfraService:
|
||||
|
||||
def ca_cert_pem(self, *, timeout: float = DEFAULT_CA_TIMEOUT_SECONDS) -> str:
|
||||
"""The gateway's mitmproxy CA (PEM) agents install to trust its TLS
|
||||
interception. Read out of the container (the CA lives on a
|
||||
container-internal path, not a host mount); polls because mitmproxy
|
||||
writes it a beat after start."""
|
||||
deadline = time.monotonic() + timeout
|
||||
while True:
|
||||
interception. Read through the container path backed by the persistent
|
||||
host CA directory; polls because mitmproxy writes it a beat after
|
||||
start."""
|
||||
def _fetch() -> str | None:
|
||||
result = container_mod.run_container_argv(
|
||||
["container", "exec", self._name, "cat", GATEWAY_CA_CERT])
|
||||
if result.returncode == 0 and result.stdout.strip():
|
||||
return result.stdout
|
||||
if time.monotonic() >= deadline:
|
||||
raise GatewayError(
|
||||
f"gateway CA not available in {self._name} after {timeout:g}s: "
|
||||
f"{(result.stderr or '').strip() or 'empty'}"
|
||||
)
|
||||
time.sleep(_CA_POLL_SECONDS)
|
||||
return result.stdout if result.returncode == 0 and result.stdout.strip() else None
|
||||
try:
|
||||
return backend_util.poll_ca_cert(_fetch, timeout=timeout)
|
||||
except TimeoutError as exc:
|
||||
raise GatewayError(
|
||||
f"gateway CA not available in {self._name} after {timeout:g}s"
|
||||
) from exc
|
||||
|
||||
def stop(self) -> None:
|
||||
"""Remove the infra container (idempotent). The DB volume persists."""
|
||||
|
||||
@@ -53,13 +53,23 @@ from ...git_gate import (
|
||||
revoke_git_gate_provisioned_keys,
|
||||
)
|
||||
from ...git_http_backend import DEFAULT_PORT as _GIT_HTTP_PORT
|
||||
from ...image_cache import check_stale
|
||||
from ...log import die, info, warn
|
||||
from .. import BottleImages
|
||||
from ...supervise import SUPERVISE_PORT
|
||||
from ..docker.egress import EGRESS_PORT
|
||||
from ..util import AGENT_CA_BUNDLE, AGENT_CA_PATH
|
||||
from . import util as container_mod
|
||||
from .bottle import MacosContainerBottle
|
||||
from .gateway_hosts import (
|
||||
GATEWAY_HOSTNAME,
|
||||
refresh_gateway_host,
|
||||
set_gateway_host,
|
||||
)
|
||||
from . import nested_containers as nested_containers_mod
|
||||
from .bottle_plan import MacosContainerBottlePlan
|
||||
from ...orchestrator.config_store import resolve_teardown_timeout
|
||||
from ...orchestrator.secret_store import ENV_VAR_SECRET_NAME, new_env_var_secret
|
||||
from .consolidated_launch import (
|
||||
GatewayEndpoint,
|
||||
ensure_gateway,
|
||||
@@ -71,18 +81,69 @@ _REPO_DIR = str(Path(__file__).resolve().parent.parent.parent.parent)
|
||||
_AGENT_SLEEP_SECONDS = "2147483647"
|
||||
|
||||
|
||||
def build_or_load_images(plan: MacosContainerBottlePlan) -> BottleImages:
|
||||
"""Resolve the agent image ref for this plan. The gateway's own image is
|
||||
built by `ensure_gateway` — it belongs to the shared singleton."""
|
||||
return BottleImages(agent=_layer_nested_containers(plan, _agent_image(plan)))
|
||||
|
||||
|
||||
def _agent_image(plan: MacosContainerBottlePlan) -> str:
|
||||
committed = read_committed_image(plan.slug)
|
||||
if committed and container_mod.image_exists(committed):
|
||||
info(f"using committed image {committed!r}")
|
||||
return committed
|
||||
if plan.spec.image_policy == "cached":
|
||||
if not container_mod.image_exists(plan.image):
|
||||
die(
|
||||
f"cached agent image {plan.image!r} not found; "
|
||||
"run without --cached-images to build it"
|
||||
)
|
||||
info(f"using cached agent image {plan.image!r}")
|
||||
return plan.image
|
||||
container_mod.build_image(plan.image, _REPO_DIR, dockerfile=plan.dockerfile_path)
|
||||
return plan.image
|
||||
|
||||
|
||||
def _layer_nested_containers(
|
||||
plan: MacosContainerBottlePlan, agent_image: str,
|
||||
) -> str:
|
||||
"""Add the guest-local container tooling on top of the agent image.
|
||||
|
||||
A separate derived tag, not the provider Dockerfile, so bottles that never
|
||||
ask for nested containers carry none of its weight.
|
||||
"""
|
||||
if not plan.nested_containers:
|
||||
return agent_image
|
||||
derived = f"{agent_image}{nested_containers_mod.IMAGE_SUFFIX}"
|
||||
if plan.spec.image_policy == "cached":
|
||||
if not container_mod.image_exists(derived):
|
||||
die(
|
||||
f"cached nested-container image {derived!r} not found; "
|
||||
"run without --cached-images to build it"
|
||||
)
|
||||
info(f"using cached nested-container image {derived!r}")
|
||||
return derived
|
||||
return nested_containers_mod.build_image(agent_image, container_mod.build_image)
|
||||
|
||||
|
||||
@contextmanager
|
||||
def launch(
|
||||
plan: MacosContainerBottlePlan,
|
||||
images: BottleImages,
|
||||
*,
|
||||
provision: Callable[[MacosContainerBottlePlan, "MacosContainerBottle"], str | None],
|
||||
) -> Generator[MacosContainerBottle, None, None]:
|
||||
"""Build, run, register, provision, and yield an Apple Container bottle on
|
||||
the shared per-host gateway."""
|
||||
"""Run, register, provision, and yield an Apple Container bottle on the
|
||||
shared per-host gateway."""
|
||||
stack = ExitStack()
|
||||
bottle_for_revoke = plan.manifest.bottle
|
||||
git_gate_dir_for_revoke = git_gate_state_dir(plan.slug)
|
||||
|
||||
plan = dataclasses.replace(
|
||||
plan,
|
||||
agent_provision=dataclasses.replace(plan.agent_provision, image=str(images.agent)),
|
||||
)
|
||||
|
||||
def teardown() -> None:
|
||||
teardown_exc: BaseException | None = None
|
||||
try:
|
||||
@@ -95,17 +156,21 @@ def launch(
|
||||
raise teardown_exc
|
||||
|
||||
try:
|
||||
plan = _build_images(plan)
|
||||
|
||||
# Step 1: the per-host singletons. Must precede the agent run — its
|
||||
# proxy env needs the gateway's address at `container run` time.
|
||||
endpoint = ensure_gateway()
|
||||
# The gateway's address may have changed since these bottles launched
|
||||
# (any infra recreate re-runs DHCP). They name the gateway rather than
|
||||
# address it, so re-pointing /etc/hosts re-attaches them in place
|
||||
# instead of leaving them stranded until relaunch.
|
||||
refresh_gateway_host(endpoint.gateway_ip)
|
||||
|
||||
# Step 2: mint this bottle's deploy keys, then point it at the SHARED
|
||||
# gateway's CA + git-http/supervise ports.
|
||||
plan = _provision_git_gate_keys(plan)
|
||||
plan = _install_gateway_ca(plan, endpoint)
|
||||
plan = _stamp_agent_urls(plan, endpoint)
|
||||
plan = dataclasses.replace(plan, env_var_secret=new_env_var_secret())
|
||||
|
||||
# Step 3: run the agent. It has no identity token yet — registration
|
||||
# needs the address this run assigns.
|
||||
@@ -117,6 +182,9 @@ def launch(
|
||||
# attribution key; `--cap-drop CAP_NET_RAW` at run is what makes it
|
||||
# unforgeable. Poll: `container run --detach` can return before vmnet's
|
||||
# DHCP has assigned the address.
|
||||
# Resolve the gateway name before anything execs: every agent-facing
|
||||
# URL uses it, so the entry must exist for the first connection.
|
||||
set_gateway_host(plan.container_name, endpoint.gateway_ip)
|
||||
source_ip = container_mod.wait_container_ipv4_on_network(
|
||||
plan.container_name, endpoint.network,
|
||||
)
|
||||
@@ -129,6 +197,7 @@ def launch(
|
||||
token_values = egress_resolve_token_values(
|
||||
plan.egress_plan.token_env_map, effective_env,
|
||||
)
|
||||
teardown_timeout = resolve_teardown_timeout()
|
||||
ctx = register_agent(
|
||||
plan.egress_plan,
|
||||
plan.git_gate_plan,
|
||||
@@ -136,10 +205,12 @@ def launch(
|
||||
endpoint=endpoint,
|
||||
image_ref=plan.image,
|
||||
tokens=token_values,
|
||||
env_var_secret=plan.env_var_secret,
|
||||
)
|
||||
stack.callback(
|
||||
teardown_consolidated, ctx.bottle_id,
|
||||
orchestrator_url=ctx.orchestrator_url,
|
||||
timeout=teardown_timeout,
|
||||
)
|
||||
info(
|
||||
f"agent {plan.container_name} registered "
|
||||
@@ -155,6 +226,10 @@ def launch(
|
||||
# token above, so — unlike the run-time env — the plan CAN carry it.
|
||||
plan = dataclasses.replace(plan, identity_token=ctx.identity_token)
|
||||
|
||||
exec_env = {
|
||||
**_identity_proxy_env(endpoint, ctx.identity_token),
|
||||
**nested_containers_mod.guest_env(plan.nested_containers),
|
||||
}
|
||||
bottle = MacosContainerBottle(
|
||||
plan.container_name,
|
||||
teardown,
|
||||
@@ -168,31 +243,38 @@ def launch(
|
||||
),
|
||||
terminal_color=plan.spec.color,
|
||||
agent_workdir=plan.workspace_plan.workdir,
|
||||
exec_env=_identity_proxy_env(endpoint, ctx.identity_token),
|
||||
exec_env=exec_env,
|
||||
)
|
||||
bottle.prompt_path = provision(plan, bottle)
|
||||
|
||||
if plan.nested_containers:
|
||||
nested_containers_mod.prepare_guest_devices(
|
||||
plan.container_name, container_mod.exec_container_as_root,
|
||||
)
|
||||
nested_containers_mod.start(bottle)
|
||||
|
||||
yield bottle
|
||||
finally:
|
||||
teardown()
|
||||
|
||||
|
||||
def _build_images(plan: MacosContainerBottlePlan) -> MacosContainerBottlePlan:
|
||||
"""Build the agent image. The gateway's own image is built by
|
||||
`ensure_gateway` — it belongs to the shared singleton, not to a bottle."""
|
||||
|
||||
def stale_checks(plan: MacosContainerBottlePlan) -> None:
|
||||
"""Raise StaleImageError if a cached image is older than the configured
|
||||
threshold. Only runs when image_policy is 'cached'. Called by the backend
|
||||
class's _image_stale_checks before _launch_impl starts any resources."""
|
||||
if plan.spec.image_policy != "cached":
|
||||
return
|
||||
committed = read_committed_image(plan.slug)
|
||||
if committed and container_mod.image_exists(committed):
|
||||
info(f"using committed image {committed!r}")
|
||||
return dataclasses.replace(
|
||||
plan,
|
||||
agent_provision=dataclasses.replace(
|
||||
plan.agent_provision, image=committed,
|
||||
),
|
||||
)
|
||||
container_mod.build_image(
|
||||
plan.image, _REPO_DIR, dockerfile=plan.dockerfile_path,
|
||||
)
|
||||
return plan
|
||||
ts = container_mod.image_created_at(committed)
|
||||
if ts is not None:
|
||||
check_stale(f"agent image {committed!r}", ts)
|
||||
return
|
||||
if container_mod.image_exists(plan.image):
|
||||
ts = container_mod.image_created_at(plan.image)
|
||||
if ts is not None:
|
||||
check_stale(f"agent image {plan.image!r}", ts)
|
||||
|
||||
|
||||
def _provision_git_gate_keys(
|
||||
@@ -231,13 +313,20 @@ def _stamp_agent_urls(
|
||||
) -> MacosContainerBottlePlan:
|
||||
"""Point the agent's git-gate insteadOf rewrites + supervise MCP at the
|
||||
shared gateway's ports. Both bypass the egress proxy (NO_PROXY covers the
|
||||
gateway address)."""
|
||||
gateway name).
|
||||
|
||||
Addressed by `GATEWAY_HOSTNAME`, never by IP: these URLs are baked into
|
||||
the agent's gitconfig and MCP config at provision time, so an address here
|
||||
would strand the bottle the moment the gateway moved. The name is resolved
|
||||
per connection through `/etc/hosts`, which stays rewritable while the
|
||||
bottle runs."""
|
||||
del endpoint # addressed by name; the address reaches the bottle via /etc/hosts
|
||||
git_gate_url = (
|
||||
f"http://{endpoint.gateway_ip}:{_GIT_HTTP_PORT}"
|
||||
f"http://{GATEWAY_HOSTNAME}:{_GIT_HTTP_PORT}"
|
||||
if plan.git_gate_plan.upstreams else ""
|
||||
)
|
||||
supervise_url = (
|
||||
f"http://{endpoint.gateway_ip}:{SUPERVISE_PORT}/"
|
||||
f"http://{GATEWAY_HOSTNAME}:{SUPERVISE_PORT}/"
|
||||
if plan.supervise_plan is not None else ""
|
||||
)
|
||||
return dataclasses.replace(
|
||||
@@ -247,30 +336,43 @@ def _stamp_agent_urls(
|
||||
)
|
||||
|
||||
|
||||
def _proxy_url(gateway_ip: str, identity_token: str = "") -> str:
|
||||
def _proxy_url(identity_token: str = "") -> str:
|
||||
"""The agent's egress proxy URL. The identity token rides as proxy
|
||||
credentials — the gateway reads Proxy-Authorization, resolves the
|
||||
(source_ip, token) pair against the control plane, and strips it before
|
||||
upstream. Without a valid pair `/resolve` denies the request (#366)."""
|
||||
upstream. Without a valid pair `/resolve` denies the request (#366).
|
||||
|
||||
Names the gateway rather than addressing it: this URL reaches the agent as
|
||||
process environment, which cannot be rewritten once the agent is running,
|
||||
so an address baked here is unfixable if the gateway moves."""
|
||||
cred = f"bottle:{identity_token}@" if identity_token else ""
|
||||
return f"http://{cred}{gateway_ip}:{EGRESS_PORT}"
|
||||
return f"http://{cred}{GATEWAY_HOSTNAME}:{EGRESS_PORT}"
|
||||
|
||||
|
||||
def _no_proxy(gateway_ip: str) -> str:
|
||||
def _no_proxy() -> str:
|
||||
# git-http + supervise live on the gateway and must NOT go through the
|
||||
# egress proxy — the agent reaches them directly by its address.
|
||||
return f"localhost,127.0.0.1,{gateway_ip}"
|
||||
# egress proxy — the agent reaches them directly by name. Deliberately
|
||||
# address-free: NO_PROXY is baked into the run-time env and is therefore
|
||||
# just as unfixable as the proxy URL if the gateway moves.
|
||||
return f"localhost,127.0.0.1,{GATEWAY_HOSTNAME}"
|
||||
|
||||
|
||||
def _identity_proxy_env(
|
||||
endpoint: GatewayEndpoint, identity_token: str,
|
||||
) -> dict[str, str]:
|
||||
"""The token-bearing proxy env applied at `container exec`. It supersedes
|
||||
the token-less run-time value (exec `--env` wins), which is the only way to
|
||||
get the token in: it does not exist until after the container runs."""
|
||||
"""The token-bearing proxy env applied at `container exec` — the only way
|
||||
to get the token in, since it does not exist until after the container
|
||||
runs (registration keys on the DHCP-assigned address).
|
||||
|
||||
This is the *sole* source of `*_PROXY` for the agent. It deliberately does
|
||||
not rely on overriding a run-time value: `container exec --env` appends
|
||||
rather than replaces, so a run-time `HTTPS_PROXY` would survive alongside
|
||||
this one and first-wins runtimes would read the wrong entry. See
|
||||
`_agent_env_entries`."""
|
||||
if not identity_token:
|
||||
return {}
|
||||
url = _proxy_url(endpoint.gateway_ip, identity_token)
|
||||
del endpoint # the gateway is named, not addressed
|
||||
url = _proxy_url(identity_token)
|
||||
return {
|
||||
"HTTPS_PROXY": url, "HTTP_PROXY": url,
|
||||
"https_proxy": url, "http_proxy": url,
|
||||
@@ -317,16 +419,23 @@ def _agent_run_argv(
|
||||
def _agent_env_entries(
|
||||
plan: MacosContainerBottlePlan, endpoint: GatewayEndpoint,
|
||||
) -> tuple[str, ...]:
|
||||
# Token-less at run time — the token does not exist yet (see
|
||||
# `_identity_proxy_env`). Anything egressing before the exec-time override
|
||||
# is denied by `/resolve`, which is the safe direction.
|
||||
proxy_url = _proxy_url(endpoint.gateway_ip)
|
||||
no_proxy = _no_proxy(endpoint.gateway_ip)
|
||||
# No `*_PROXY` here on purpose. The token-bearing URL is applied at
|
||||
# `container exec` (`_identity_proxy_env`), and Apple's `container exec
|
||||
# --env` **appends** to the run-time environment rather than replacing it:
|
||||
# setting a token-less value here leaves two `HTTPS_PROXY` entries in the
|
||||
# agent's `environ`, token-less first. Which one a runtime reads is then
|
||||
# pure luck — Node takes the last (and worked), Rust's `std::env::var`
|
||||
# takes the first, so Codex proxied without its identity token and
|
||||
# `/resolve` fail-closed on every request.
|
||||
#
|
||||
# A token-less proxy URL has no legitimate consumer anyway: the init
|
||||
# process is `sleep` and everything that egresses arrives via exec. Its
|
||||
# only value was a tidy 403 for unattributed callers, which is not worth
|
||||
# silently dropping attribution for. Without it a process that egresses
|
||||
# before the exec-time env still fails closed — the agent network is
|
||||
# host-only, so there is no route off it except the gateway.
|
||||
no_proxy = _no_proxy()
|
||||
env = [
|
||||
f"HTTPS_PROXY={proxy_url}",
|
||||
f"HTTP_PROXY={proxy_url}",
|
||||
f"https_proxy={proxy_url}",
|
||||
f"http_proxy={proxy_url}",
|
||||
f"NO_PROXY={no_proxy}",
|
||||
f"no_proxy={no_proxy}",
|
||||
f"NODE_EXTRA_CA_CERTS={AGENT_CA_PATH}",
|
||||
@@ -337,6 +446,8 @@ def _agent_env_entries(
|
||||
env.append(f"GIT_GATE_URL={plan.agent_git_gate_url}")
|
||||
if plan.agent_supervise_url:
|
||||
env.append(f"MCP_SUPERVISE_URL={plan.agent_supervise_url}")
|
||||
if getattr(plan, "env_var_secret", ""):
|
||||
env.append(f"{ENV_VAR_SECRET_NAME}={plan.env_var_secret}")
|
||||
for name, value in sorted(plan.agent_provision.guest_env.items()):
|
||||
env.append(f"{name}={value}")
|
||||
# Forwarded vars: bare name → inherits from the `container run` process env
|
||||
|
||||
@@ -0,0 +1,210 @@
|
||||
#!/bin/sh
|
||||
set -eu
|
||||
|
||||
uid="$(id -u)"
|
||||
if [ "$uid" -eq 0 ]; then
|
||||
echo "refusing to run the guest container engine as root" >&2
|
||||
exit 1
|
||||
fi
|
||||
|
||||
# Every piece of podman 5's networking stack is checked here, because each
|
||||
# one fails at a different and misleading layer if it is absent: no pasta and
|
||||
# nothing starts at all; no nft and netavark cannot build the bridge every
|
||||
# compose file expects; no aardvark-dns and DNS inside nested containers fails
|
||||
# while everything else looks healthy.
|
||||
for command in podman docker fuse-overlayfs pasta nft slirp4netns; do
|
||||
command -v "$command" >/dev/null 2>&1 || {
|
||||
echo "missing nested-container prerequisite: $command" >&2
|
||||
exit 1
|
||||
}
|
||||
done
|
||||
|
||||
# The inverse of the rootless-Docker check, and the whole point of the podman
|
||||
# variant: a subordinate range would push podman onto newuidmap, which cannot
|
||||
# write a multi-range uid_map without CAP_SYS_ADMIN in this guest. An empty
|
||||
# range keeps it on the single-UID self-mapping an unprivileged process may
|
||||
# write itself.
|
||||
if grep -q "^$(id -un):" /etc/subuid 2>/dev/null; then
|
||||
echo "unexpected subordinate UID range for $(id -un): podman would" >&2
|
||||
echo "require CAP_SYS_ADMIN via newuidmap in this guest" >&2
|
||||
exit 1
|
||||
fi
|
||||
|
||||
for device in /dev/fuse /dev/net/tun; do
|
||||
[ -r "$device" ] && [ -w "$device" ] || {
|
||||
echo "device $device is not readable/writable by $(id -un)" >&2
|
||||
exit 1
|
||||
}
|
||||
done
|
||||
|
||||
# Short by necessity, not by accident: conmon's attach socket lives under
|
||||
# this directory and must fit in a 108-byte sun_path. See nested_containers.py.
|
||||
# Must stay in step with AGENT_CA_BUNDLE in bot_bottle/backend/util.py; a unit
|
||||
# test pins the two together.
|
||||
CA_BUNDLE="/etc/ssl/certs/ca-certificates.crt"
|
||||
[ -r "$CA_BUNDLE" ] || {
|
||||
echo "gateway CA bundle $CA_BUNDLE is missing or unreadable" >&2
|
||||
exit 1
|
||||
}
|
||||
|
||||
# The proxy URL the agent inherits names `bot-bottle-gateway`, which resolves
|
||||
# only through this bottle's /etc/hosts. A nested container gets its own hosts
|
||||
# file, so it cannot resolve the name and dies at "Could not resolve proxy".
|
||||
#
|
||||
# podman's containers.conf `hosts_file` would fix that, except the
|
||||
# Docker-compatible API ignores it — it only takes effect for native
|
||||
# `podman run`, and the agent types `docker`. So the name is resolved *here*
|
||||
# and the address, not the name, goes into the proxy URL the nested container
|
||||
# receives. Verified on macOS 26 / podman 5.4.2: with the address in place,
|
||||
# https://quay.io returns 200 and a non-allowlisted host still gets 403, so
|
||||
# the egress boundary applies inside nested containers too.
|
||||
GATEWAY_NAME="bot-bottle-gateway"
|
||||
gateway_ip="$(
|
||||
awk -v name="$GATEWAY_NAME" '$2 == name { print $1; exit }' /etc/hosts
|
||||
)"
|
||||
[ -n "$gateway_ip" ] || {
|
||||
echo "no /etc/hosts entry for $GATEWAY_NAME; the gateway address is" >&2
|
||||
echo "needed so nested containers can reach the egress proxy" >&2
|
||||
exit 1
|
||||
}
|
||||
|
||||
export XDG_RUNTIME_DIR="${XDG_RUNTIME_DIR:-/tmp/bbp}"
|
||||
config="$HOME/.config/containers"
|
||||
mkdir -p "$XDG_RUNTIME_DIR" "$config"
|
||||
chmod 700 "$XDG_RUNTIME_DIR"
|
||||
|
||||
# ignore_chown_errors is required, not incidental: with a single-UID mapping
|
||||
# there is no second UID for image layers to be chowned to, so layers that
|
||||
# record other owners would otherwise fail to extract.
|
||||
cat > "$config/storage.conf" <<'CONF'
|
||||
[storage]
|
||||
driver="overlay"
|
||||
[storage.options.overlay]
|
||||
mount_program="/usr/bin/fuse-overlayfs"
|
||||
ignore_chown_errors="true"
|
||||
CONF
|
||||
|
||||
# No cgroup delegation reaches this guest, so asking podman to manage cgroups
|
||||
# fails; events_logger=file avoids the journald socket that is equally absent.
|
||||
#
|
||||
# The rest of this config is what lets a nested container reach the network:
|
||||
#
|
||||
# hosts_file only takes effect for native `podman run` — the
|
||||
# Docker-compatible API ignores it, and the agent types
|
||||
# `docker`. Kept anyway because it costs nothing and makes
|
||||
# podman-native use behave; the compat path is covered by the
|
||||
# address-bearing proxy URL below.
|
||||
# volumes/env the gateway TLS-intercepts, so a container that does not
|
||||
# trust the bottle's CA bundle gets "unable to get local issuer
|
||||
# certificate". Mounting the bundle read-only and pointing the
|
||||
# usual env vars at it covers curl, wget, python, and node
|
||||
# without distro-specific trust commands.
|
||||
#
|
||||
# The proxy URL carries the bottle's identity token. podman already forwards
|
||||
# that same URL into every nested container from the agent's own environment,
|
||||
# so writing it to a 0600 file inside this disposable VM hands it to nobody
|
||||
# new. It is never echoed.
|
||||
CA_BUNDLE="$CA_BUNDLE" GATEWAY_NAME="$GATEWAY_NAME" GATEWAY_IP="$gateway_ip" \
|
||||
CONTAINERS_CONF="$config/containers.conf" python3 - <<'PY'
|
||||
import os
|
||||
from pathlib import Path
|
||||
|
||||
ca = os.environ["CA_BUNDLE"]
|
||||
name = os.environ["GATEWAY_NAME"]
|
||||
ip = os.environ["GATEWAY_IP"]
|
||||
|
||||
entries = [
|
||||
f"SSL_CERT_FILE={ca}",
|
||||
f"CURL_CA_BUNDLE={ca}",
|
||||
f"REQUESTS_CA_BUNDLE={ca}",
|
||||
f"NODE_EXTRA_CA_CERTS={ca}",
|
||||
]
|
||||
# The gateway name resolves only through the bottle's /etc/hosts, which a
|
||||
# nested container does not inherit, so hand it the address instead.
|
||||
for var in ("HTTP_PROXY", "HTTPS_PROXY", "http_proxy", "https_proxy"):
|
||||
value = os.environ.get(var)
|
||||
if value:
|
||||
entries.append(f"{var}={value.replace(name, ip)}")
|
||||
# NO_PROXY keeps the name: it is matched against what a client asks for, and
|
||||
# code inside a nested container still says "bot-bottle-gateway".
|
||||
for var in ("NO_PROXY", "no_proxy"):
|
||||
value = os.environ.get(var)
|
||||
if value:
|
||||
entries.append(f"{var}={value}")
|
||||
|
||||
path = Path(os.environ["CONTAINERS_CONF"])
|
||||
path.write_text("\n".join([
|
||||
"[containers]",
|
||||
'cgroups="disabled"',
|
||||
# podman copies the host's proxy vars into every container by default,
|
||||
# and that copy *wins* over the env below — putting the unresolvable
|
||||
# gateway name back. Turn it off so the address-bearing URLs stand.
|
||||
"http_proxy=false",
|
||||
'hosts_file="/etc/hosts"',
|
||||
f'volumes=["{ca}:{ca}:ro"]',
|
||||
"env=[",
|
||||
*[f' "{entry}",' for entry in entries],
|
||||
"]",
|
||||
"[engine]",
|
||||
'cgroup_manager="cgroupfs"',
|
||||
'events_logger="file"',
|
||||
"",
|
||||
]), encoding="utf-8")
|
||||
path.chmod(0o600)
|
||||
PY
|
||||
|
||||
# Registry pulls egress through the bottle's proxy like everything else. The
|
||||
# token-bearing proxy URL is already in the agent's environment; persisting it
|
||||
# inside this disposable VM does not broaden its authority.
|
||||
#
|
||||
# This file is also what the Docker CLI copies into every container it starts,
|
||||
# and being client-side it beats anything the podman service does — it is why
|
||||
# containers.conf `env`, `http_proxy=false`, and the service's own environment
|
||||
# all failed to change what a nested container saw. The address goes in here
|
||||
# for the same reason it goes everywhere else: `bot-bottle-gateway` resolves
|
||||
# in the bottle, never inside a nested container.
|
||||
GATEWAY_NAME="$GATEWAY_NAME" GATEWAY_IP="$gateway_ip" python3 - <<'PY'
|
||||
import json
|
||||
import os
|
||||
from pathlib import Path
|
||||
|
||||
name = os.environ["GATEWAY_NAME"]
|
||||
ip = os.environ["GATEWAY_IP"]
|
||||
|
||||
proxy = os.environ.get("HTTPS_PROXY") or os.environ.get("https_proxy", "")
|
||||
# NO_PROXY keeps the name: it is matched against what a client asks for, and
|
||||
# code inside a nested container still says "bot-bottle-gateway".
|
||||
no_proxy = os.environ.get("NO_PROXY") or os.environ.get("no_proxy", "")
|
||||
config = {"proxies": {"default": {
|
||||
"httpProxy": proxy.replace(name, ip),
|
||||
"httpsProxy": proxy.replace(name, ip),
|
||||
"noProxy": no_proxy,
|
||||
}}}
|
||||
path = Path.home() / ".docker" / "config.json"
|
||||
path.parent.mkdir(parents=True, exist_ok=True)
|
||||
path.write_text(json.dumps(config), encoding="utf-8")
|
||||
path.chmod(0o600)
|
||||
PY
|
||||
|
||||
if docker info >/dev/null 2>&1; then
|
||||
exit 0
|
||||
fi
|
||||
|
||||
# Belt to the ~/.docker/config.json braces above, which is what actually
|
||||
# decides this for `docker run`. The service environment is what podman falls
|
||||
# back to for anything the CLI does not stamp — its own registry pulls, and
|
||||
# containers created through the API by something other than the Docker CLI.
|
||||
# Cheap, and it keeps the address consistent across both paths.
|
||||
#
|
||||
# Assigned via parameter expansion, never echoed: these carry the bottle's
|
||||
# identity token.
|
||||
for var in HTTP_PROXY HTTPS_PROXY http_proxy https_proxy; do
|
||||
eval "value=\${$var:-}"
|
||||
[ -n "$value" ] || continue
|
||||
eval "export $var=\"\${value%%$GATEWAY_NAME*}$gateway_ip\${value#*$GATEWAY_NAME}\""
|
||||
done
|
||||
|
||||
log=/tmp/bot-bottle-nested-containers.log
|
||||
nohup podman system service --time=0 \
|
||||
"unix://$XDG_RUNTIME_DIR/podman.sock" \
|
||||
>"$log" 2>&1 </dev/null &
|
||||
@@ -0,0 +1,161 @@
|
||||
"""Guest-local container engine for Apple-container bottles (issue #392).
|
||||
|
||||
The service and every nested container remain inside the existing per-bottle
|
||||
VM. This module refuses to compensate for missing prerequisites with outer
|
||||
capabilities, a privileged container, or a host Docker socket.
|
||||
|
||||
Podman is used rather than rootless Docker for one specific reason: Apple
|
||||
Container's capability bounding set omits `CAP_SYS_ADMIN`, which the kernel
|
||||
requires to write a multi-range `uid_map` via `newuidmap`. Rootless Docker
|
||||
has no path that avoids that write. Podman does — with no subordinate UID
|
||||
range configured it falls back to a single-UID self-mapping, which an
|
||||
unprivileged process may write itself. See
|
||||
`docs/research/rootless-docker-in-apple-container-spike.md`.
|
||||
|
||||
That fallback is why `build_image` *removes* the agent user's `/etc/subuid`
|
||||
and `/etc/subgid` entries instead of adding them: their presence is precisely
|
||||
what would send podman down the `newuidmap` path that cannot work here.
|
||||
|
||||
The agent still talks to `docker` and `docker compose`; those speak to
|
||||
podman's Docker-compatible API socket, so nothing in the agent's habits
|
||||
changes.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import shlex
|
||||
import shutil
|
||||
import tempfile
|
||||
import time
|
||||
from pathlib import Path
|
||||
from typing import Callable
|
||||
|
||||
from ...log import die, info
|
||||
|
||||
_INIT = "/usr/local/libexec/bot-bottle/nested-containers-init"
|
||||
# Deliberately cryptic and short. podman derives conmon's attach socket as
|
||||
# `$XDG_RUNTIME_DIR/libpod/tmp/socket/<64-hex-id>/attach`, and a Unix socket
|
||||
# path may not exceed 108 bytes (`sun_path`). The descriptive
|
||||
# `/tmp/bot-bottle-podman-run` produced a 116-byte path — over the limit, so
|
||||
# attach would have broken as soon as anything got far enough to attach. Do
|
||||
# not lengthen this for readability; it buys 8 bytes of headroom.
|
||||
_RUNTIME_DIR = "/tmp/bbp"
|
||||
_SOCKET = f"{_RUNTIME_DIR}/podman.sock"
|
||||
_LOG = "/tmp/bot-bottle-nested-containers.log"
|
||||
IMAGE_SUFFIX = "-nested-containers"
|
||||
READY_RETRIES = 30
|
||||
|
||||
# Apple Container creates both device nodes 0600 root:root, so the agent user
|
||||
# cannot open them: /dev/fuse blocks the fuse-overlayfs storage driver and
|
||||
# /dev/net/tun blocks slirp4netns, which rootless podman uses for the default
|
||||
# bridge network that stock compose files expect. Relaxing the modes needs no
|
||||
# capability the bottle does not already hold — unlike CAP_SYS_ADMIN, which is
|
||||
# what killed the rootless-Docker approach.
|
||||
_GUEST_DEVICES = ("/dev/fuse", "/dev/net/tun")
|
||||
|
||||
|
||||
def build_image(
|
||||
base_image: str,
|
||||
build: Callable[..., None],
|
||||
) -> str:
|
||||
"""Layer the nested-container tooling onto an already-built agent image.
|
||||
|
||||
Podman and its networking stack live here rather than in the base agent
|
||||
images so that bottles without the flag pay no image-size cost.
|
||||
|
||||
# TODO(#394): replace this hand-rolled Dockerfile with a docker-layer
|
||||
# abstraction once that infrastructure exists.
|
||||
"""
|
||||
image = f"{base_image}{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"
|
||||
"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/"
|
||||
"docker-compose /usr/local/libexec/docker/cli-plugins/docker-compose\n"
|
||||
"RUN apt-get update \\\n"
|
||||
# podman 5's networking stack, installed explicitly because
|
||||
# --no-install-recommends omits it and each missing piece fails
|
||||
# at a different, misleading layer:
|
||||
# podman -> moved here from the base agent images so that
|
||||
# bottles without nested_containers pay no cost
|
||||
# passt -> `pasta`, the default rootless netns helper
|
||||
# (podman 4 used slirp4netns); without it
|
||||
# nothing starts: "could not find pasta"
|
||||
# nftables -> `nft`, which netavark shells out to for the
|
||||
# bridge network every compose file expects
|
||||
# aardvark-dns -> name resolution *inside* nested containers;
|
||||
# without it DNS fails while everything else
|
||||
# looks healthy
|
||||
# slirp4netns stays as the documented fallback for pasta.
|
||||
" && apt-get install -y --no-install-recommends "
|
||||
"aardvark-dns fuse-overlayfs netavark nftables passt podman "
|
||||
"slirp4netns uidmap \\\n"
|
||||
" && rm -rf /var/lib/apt/lists/* \\\n"
|
||||
# Deliberate: an empty subordinate range keeps podman on the
|
||||
# single-UID mapping that needs no CAP_SYS_ADMIN. Adding ranges
|
||||
# here would reintroduce the newuidmap failure this design exists
|
||||
# to route around.
|
||||
" && sed -i '/^node:/d' /etc/subuid /etc/subgid\n"
|
||||
"COPY nested-containers-init.sh "
|
||||
"/usr/local/libexec/bot-bottle/nested-containers-init\n"
|
||||
"RUN chmod 0755 /usr/local/libexec/bot-bottle/nested-containers-init\n"
|
||||
"USER node\n",
|
||||
encoding="utf-8",
|
||||
)
|
||||
build(image, str(context), dockerfile=str(context / "Dockerfile"))
|
||||
return image
|
||||
|
||||
|
||||
def guest_env(enabled: bool) -> dict[str, str]:
|
||||
"""Environment consumed by the Docker CLI inside an enabled bottle."""
|
||||
if not enabled:
|
||||
return {}
|
||||
return {
|
||||
"DOCKER_HOST": f"unix://{_SOCKET}",
|
||||
"XDG_RUNTIME_DIR": _RUNTIME_DIR,
|
||||
}
|
||||
|
||||
|
||||
def prepare_guest_devices(container_name: str, exec_as_root: Callable[..., None]) -> None:
|
||||
"""Make /dev/fuse and /dev/net/tun openable by the agent user.
|
||||
|
||||
Runs as root inside the bottle because the agent must not be able to
|
||||
re-mode device nodes itself. No outer capability is involved.
|
||||
"""
|
||||
exec_as_root(
|
||||
container_name,
|
||||
["sh", "-c", f"chmod 0666 {' '.join(_GUEST_DEVICES)}"],
|
||||
)
|
||||
|
||||
|
||||
def start(bottle: object) -> None:
|
||||
"""Start and verify the unprivileged service through the bottle exec API."""
|
||||
info("starting guest-local container engine")
|
||||
result = bottle.exec(shlex.quote(_INIT)) # type: ignore[attr-defined]
|
||||
if result.returncode != 0:
|
||||
detail = (result.stderr or result.stdout or "").strip()
|
||||
die(f"nested-container bootstrap failed: {detail or '<no output>'}")
|
||||
|
||||
for _ in range(READY_RETRIES):
|
||||
result = bottle.exec("docker info >/dev/null 2>&1") # type: ignore[attr-defined]
|
||||
if result.returncode == 0:
|
||||
info("guest-local container engine is ready")
|
||||
return
|
||||
time.sleep(0.2)
|
||||
|
||||
logs = bottle.exec( # type: ignore[attr-defined]
|
||||
f"tail -n 80 {_LOG} 2>/dev/null || true"
|
||||
)
|
||||
die(
|
||||
"guest-local container engine did not become ready without additional "
|
||||
f"outer privileges:\n{(logs.stdout or logs.stderr or '<no log>').strip()}"
|
||||
)
|
||||
|
||||
|
||||
__all__ = ["build_image", "guest_env", "prepare_guest_devices", "start"]
|
||||
@@ -44,4 +44,5 @@ def resolve_plan(
|
||||
egress_plan=egress_plan,
|
||||
supervise_plan=supervise_plan,
|
||||
agent_provision=agent_provision_plan,
|
||||
nested_containers=manifest.bottle.nested_containers,
|
||||
)
|
||||
|
||||
@@ -10,6 +10,7 @@ import shutil
|
||||
import subprocess
|
||||
import tempfile
|
||||
import time
|
||||
from datetime import datetime, timezone
|
||||
from typing import Iterable
|
||||
|
||||
from ...log import die, info
|
||||
@@ -360,6 +361,27 @@ def exec_container(name: str, argv: list[str]) -> None:
|
||||
)
|
||||
|
||||
|
||||
def read_container_env(name: str, env_name: str) -> str:
|
||||
"""Read one configured env value from a running container, or ``""``."""
|
||||
result = _run_container_op([_CONTAINER, "exec", name, "printenv", env_name])
|
||||
return result.stdout.strip() if result.returncode == 0 else ""
|
||||
|
||||
|
||||
def exec_container_as_root(name: str, argv: list[str]) -> None:
|
||||
"""`exec_container`, but as uid 0 inside the container.
|
||||
|
||||
For host-driven maintenance the agent itself must not be able to perform —
|
||||
rewriting `/etc/hosts` to point the gateway name at an address. The agent
|
||||
runs as `node`, so it cannot repoint its own gateway; the host can.
|
||||
"""
|
||||
result = _run_container_op([_CONTAINER, "exec", "--user", "root", name, *argv])
|
||||
if result.returncode != 0:
|
||||
die(
|
||||
f"container exec (root) in {name} failed: "
|
||||
f"{(result.stderr or '').strip() or '<no stderr>'}"
|
||||
)
|
||||
|
||||
|
||||
def _run_container_op(cmd: list[str]) -> subprocess.CompletedProcess[str]:
|
||||
result = subprocess.run(
|
||||
cmd,
|
||||
@@ -557,6 +579,41 @@ def try_container_ipv4_on_network(name: str, network: str) -> str:
|
||||
return ""
|
||||
|
||||
|
||||
def inspect_container_network_ip(name: str, network: str) -> str | None:
|
||||
"""IP of `name` on `network`, distinguishing inspect failure from "not yet".
|
||||
|
||||
Returns:
|
||||
- the IP string when the container has one on `network`
|
||||
- "" when inspect succeeds but no address is assigned yet (in-flight DHCP)
|
||||
- None when the inspect command itself fails (authoritative list impossible)
|
||||
"""
|
||||
result = subprocess.run(
|
||||
[_CONTAINER, "inspect", name],
|
||||
capture_output=True, text=True, check=False,
|
||||
)
|
||||
if result.returncode != 0:
|
||||
return None
|
||||
try:
|
||||
data = json.loads(result.stdout or "[]")
|
||||
except json.JSONDecodeError:
|
||||
return None
|
||||
if isinstance(data, list):
|
||||
data = data[0] if data else {}
|
||||
if not isinstance(data, dict):
|
||||
return None
|
||||
status = data.get("status")
|
||||
networks = status.get("networks") if isinstance(status, dict) else None
|
||||
if not isinstance(networks, list):
|
||||
return ""
|
||||
for entry in networks:
|
||||
if not isinstance(entry, dict) or entry.get("network") != network:
|
||||
continue
|
||||
raw = entry.get("ipv4Address")
|
||||
if isinstance(raw, str) and raw:
|
||||
return raw.split("/", 1)[0]
|
||||
return ""
|
||||
|
||||
|
||||
def wait_container_ipv4_on_network(
|
||||
name: str, network: str, *, timeout: float = 15.0, poll: float = 0.25,
|
||||
) -> str:
|
||||
@@ -611,6 +668,39 @@ def image_id(ref: str) -> str:
|
||||
raise AssertionError("unreachable")
|
||||
|
||||
|
||||
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
|
||||
pulled from registries that omit the field). Callers should skip the stale
|
||||
check when None is returned rather than treating it as an error."""
|
||||
result = subprocess.run(
|
||||
[_CONTAINER, "image", "inspect", ref],
|
||||
capture_output=True,
|
||||
text=True,
|
||||
check=False,
|
||||
)
|
||||
if result.returncode != 0:
|
||||
die(
|
||||
f"container image inspect for {ref!r} failed: "
|
||||
f"{(result.stderr or '').strip() or '<no stderr>'}"
|
||||
)
|
||||
try:
|
||||
data = json.loads(result.stdout or "{}")
|
||||
except json.JSONDecodeError as exc:
|
||||
die(f"container image inspect for {ref!r} returned malformed JSON: {exc}")
|
||||
if isinstance(data, list) and data:
|
||||
data = data[0]
|
||||
if isinstance(data, dict):
|
||||
value = data.get("created") or data.get("Created")
|
||||
if isinstance(value, str) and value:
|
||||
try:
|
||||
ts = value.rstrip("Z")
|
||||
return datetime.fromisoformat(ts).replace(tzinfo=timezone.utc)
|
||||
except ValueError:
|
||||
pass
|
||||
return None
|
||||
|
||||
|
||||
def save(ref: str, output: str) -> None:
|
||||
subprocess.run([_CONTAINER, "image", "save", ref, "-o", output], check=True)
|
||||
|
||||
|
||||
@@ -26,6 +26,7 @@ from ..bottle_state import (
|
||||
)
|
||||
from ..egress import Egress, EgressPlan
|
||||
from ..git_gate import GitGate, GitGatePlan
|
||||
from ..log import die
|
||||
from ..manifest import Manifest, ManifestBottle
|
||||
from ..supervise import Supervise, SupervisePlan
|
||||
from . import BottleSpec
|
||||
@@ -112,6 +113,22 @@ def merge_provision_env_vars(provision: AgentProvisionPlan) -> AgentProvisionPla
|
||||
return replace(provision, guest_env=merged)
|
||||
|
||||
|
||||
def reject_nested_containers(backend: str, manifest: Manifest) -> None:
|
||||
"""Fail loudly when a backend cannot honor `nested_containers: true`.
|
||||
|
||||
Silently ignoring it would hand the agent a bottle where `docker` is not
|
||||
there — and the only sound alternatives on these backends (a host daemon
|
||||
socket, a privileged container) are exactly what issue #392 rules out.
|
||||
"""
|
||||
if not manifest.bottle.nested_containers:
|
||||
return
|
||||
die(
|
||||
f"nested_containers is not supported on the {backend} backend. "
|
||||
"Only macos-container runs a guest-local container engine today; "
|
||||
"mounting the host Docker socket is not an option bot-bottle offers."
|
||||
)
|
||||
|
||||
|
||||
def resolve_manifest_dockerfile(path_value: str, spec: BottleSpec) -> str:
|
||||
"""Resolve a manifest-supplied dockerfile path relative to user_cwd."""
|
||||
path = Path(os.path.expanduser(path_value))
|
||||
@@ -122,6 +139,7 @@ def resolve_manifest_dockerfile(path_value: str, spec: BottleSpec) -> str:
|
||||
|
||||
__all__ = [
|
||||
"merge_provision_env_vars",
|
||||
"reject_nested_containers",
|
||||
"mint_slug",
|
||||
"prepare_agent_state_dir",
|
||||
"prepare_egress",
|
||||
|
||||
@@ -7,6 +7,8 @@ from __future__ import annotations
|
||||
import hashlib
|
||||
import os
|
||||
import ssl
|
||||
import time
|
||||
from collections.abc import Callable
|
||||
from pathlib import Path
|
||||
from typing import TYPE_CHECKING
|
||||
|
||||
@@ -15,6 +17,24 @@ from ..log import die, info
|
||||
if TYPE_CHECKING:
|
||||
from ..egress import EgressPlan
|
||||
|
||||
_CA_POLL_INTERVAL = 0.5
|
||||
|
||||
|
||||
def poll_ca_cert(fetch: Callable[[], str | None], *, timeout: float) -> str:
|
||||
"""Poll `fetch` until it returns a non-empty PEM string or `timeout` expires.
|
||||
|
||||
`fetch` should return the PEM on success and `None` (or empty string) when
|
||||
the cert is not yet available. Raises `TimeoutError` if the cert never
|
||||
appears within `timeout` seconds."""
|
||||
deadline = time.monotonic() + timeout
|
||||
while True:
|
||||
result = fetch()
|
||||
if result:
|
||||
return result
|
||||
if time.monotonic() >= deadline:
|
||||
raise TimeoutError(f"CA cert not available after {timeout:g}s")
|
||||
time.sleep(_CA_POLL_INTERVAL)
|
||||
|
||||
|
||||
# Debian-family CA layout, shared by every backend (all guest images
|
||||
# are Debian-family). AGENT_CA_PATH is the source path that
|
||||
|
||||
@@ -114,7 +114,3 @@ def main(argv: list[str] | None = None) -> int:
|
||||
return e.code if isinstance(e.code, int) else 1
|
||||
except KeyboardInterrupt:
|
||||
return 130
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
sys.exit(main())
|
||||
|
||||
@@ -0,0 +1,15 @@
|
||||
"""Entry point for `python -m bot_bottle.cli`.
|
||||
|
||||
`cli.py` at the repo root is the usual way in; this makes the package
|
||||
runnable too, so the CLI works from an installed copy where there is no
|
||||
`cli.py` on disk to point at.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import sys
|
||||
|
||||
from . import main
|
||||
|
||||
if __name__ == "__main__":
|
||||
sys.exit(main())
|
||||
+23
-8
@@ -18,10 +18,12 @@ import json
|
||||
import os
|
||||
import socket
|
||||
import sys
|
||||
import tempfile
|
||||
import time
|
||||
import urllib.error
|
||||
import urllib.request
|
||||
from pathlib import Path
|
||||
from typing import Any
|
||||
|
||||
from ..paths import bot_bottle_root
|
||||
|
||||
@@ -48,7 +50,7 @@ def _flag(argv: list[str], name: str) -> str | None:
|
||||
return None
|
||||
|
||||
|
||||
def _post(url: str, payload: dict) -> dict:
|
||||
def _post(url: str, payload: dict[str, Any]) -> dict[str, Any]:
|
||||
data = json.dumps(payload).encode()
|
||||
req = urllib.request.Request(
|
||||
url, data=data, headers={"Content-Type": "application/json"}
|
||||
@@ -57,7 +59,7 @@ def _post(url: str, payload: dict) -> dict:
|
||||
return json.loads(resp.read())
|
||||
|
||||
|
||||
def _get(url: str) -> tuple[int, dict]:
|
||||
def _get(url: str) -> tuple[int, dict[str, Any]]:
|
||||
req = urllib.request.Request(url)
|
||||
try:
|
||||
with urllib.request.urlopen(req, timeout=10) as resp:
|
||||
@@ -71,7 +73,7 @@ def _save_credentials(
|
||||
) -> Path:
|
||||
path = bot_bottle_root() / "console.json"
|
||||
path.parent.mkdir(parents=True, exist_ok=True)
|
||||
path.write_text(
|
||||
content = (
|
||||
json.dumps(
|
||||
{
|
||||
"url": console_url,
|
||||
@@ -83,7 +85,19 @@ def _save_credentials(
|
||||
)
|
||||
+ "\n"
|
||||
)
|
||||
path.chmod(0o600)
|
||||
fd, tmp_path_str = tempfile.mkstemp(dir=path.parent, prefix=".console-")
|
||||
tmp = Path(tmp_path_str)
|
||||
try:
|
||||
tmp.chmod(0o600)
|
||||
with os.fdopen(fd, "w") as f:
|
||||
f.write(content)
|
||||
os.replace(tmp, path)
|
||||
except OSError:
|
||||
try:
|
||||
tmp.unlink()
|
||||
except OSError:
|
||||
pass
|
||||
raise
|
||||
return path
|
||||
|
||||
|
||||
@@ -104,17 +118,18 @@ def cmd_login(argv: list[str]) -> int:
|
||||
|
||||
try:
|
||||
resp = _post(f"{console_url}/api/v1/hosts/authorize", {"label": label})
|
||||
except Exception as exc:
|
||||
except (OSError, ValueError) as exc:
|
||||
sys.stderr.write(f"bb login: failed to start authorization: {exc}\n")
|
||||
return 1
|
||||
|
||||
device_code = resp["device_code"]
|
||||
user_code = resp["user_code"]
|
||||
expires_in = resp.get("expires_in", 300)
|
||||
poll_sleep = max(1, min(int(resp.get("poll_interval", _POLL_SLEEP)), 60))
|
||||
|
||||
sys.stderr.write(
|
||||
f"\nOpen this URL in your browser to authorize this host:\n\n"
|
||||
f" {console_url}/authorize?code={user_code}\n\n"
|
||||
f" {console_url}/hosts/authorize?code={user_code}\n\n"
|
||||
f"Waiting for approval"
|
||||
)
|
||||
|
||||
@@ -122,13 +137,13 @@ def cmd_login(argv: list[str]) -> int:
|
||||
while time.monotonic() < deadline:
|
||||
sys.stderr.write(".")
|
||||
sys.stderr.flush()
|
||||
time.sleep(_POLL_SLEEP)
|
||||
time.sleep(poll_sleep)
|
||||
|
||||
try:
|
||||
code, result = _get(
|
||||
f"{console_url}/api/v1/hosts/authorize/{device_code}"
|
||||
)
|
||||
except Exception:
|
||||
except (OSError, ValueError):
|
||||
continue
|
||||
|
||||
if code == 410:
|
||||
|
||||
+35
-4
@@ -35,6 +35,7 @@ from ..bottle_state import (
|
||||
is_preserved,
|
||||
mark_preserved,
|
||||
)
|
||||
from ..image_cache import StaleImageError
|
||||
from ..log import info, die
|
||||
from ..manifest import Manifest, ManifestIndex
|
||||
from ._common import PROG, USER_CWD, read_tty_line
|
||||
@@ -64,6 +65,14 @@ def cmd_start(argv: list[str]) -> int:
|
||||
"skip all prompts. For orchestrators, CI, and webhooks."
|
||||
),
|
||||
)
|
||||
parser.add_argument(
|
||||
"--cached-images",
|
||||
action="store_true",
|
||||
help=(
|
||||
"quickstart with existing local agent and sidecar images; "
|
||||
"only valid with --headless"
|
||||
),
|
||||
)
|
||||
parser.add_argument(
|
||||
"--bottle",
|
||||
action="append",
|
||||
@@ -96,6 +105,8 @@ def cmd_start(argv: list[str]) -> int:
|
||||
help="agent name defined in bot-bottle.json (omit to pick interactively)",
|
||||
)
|
||||
args = parser.parse_args(argv)
|
||||
if args.cached_images and not args.headless:
|
||||
die("--cached-images is only supported with --headless")
|
||||
|
||||
dry_run = args.dry_run or os.environ.get("BOT_BOTTLE_DRY_RUN") == "1"
|
||||
if args.no_cache or os.environ.get("BOT_BOTTLE_NO_CACHE") == "1":
|
||||
@@ -147,6 +158,10 @@ def cmd_start(argv: list[str]) -> int:
|
||||
label, color = tui.name_color_modal(default_label=agent_name)
|
||||
label, color = _resolve_unique_label(label, color)
|
||||
|
||||
image_policy = _select_image_policy()
|
||||
if image_policy is None:
|
||||
return 0
|
||||
|
||||
spec = BottleSpec(
|
||||
manifest=manifest,
|
||||
agent_name=agent_name,
|
||||
@@ -155,6 +170,7 @@ def cmd_start(argv: list[str]) -> int:
|
||||
label=label,
|
||||
color=color,
|
||||
bottle_names=bottle_names,
|
||||
image_policy=image_policy,
|
||||
)
|
||||
return _launch_bottle(
|
||||
spec,
|
||||
@@ -213,6 +229,7 @@ def _start_headless(
|
||||
color=args.color or "",
|
||||
bottle_names=bottle_names,
|
||||
headless=True,
|
||||
image_policy="cached" if args.cached_images else "fresh",
|
||||
)
|
||||
return _launch_bottle(
|
||||
spec,
|
||||
@@ -395,6 +412,13 @@ def _text_prompt_yes() -> bool:
|
||||
return reply in ("y", "Y", "yes", "YES")
|
||||
|
||||
|
||||
def _select_image_policy() -> str | None:
|
||||
return tui.filter_select(
|
||||
["fresh", "cached"],
|
||||
title="Select image startup mode",
|
||||
)
|
||||
|
||||
|
||||
def _text_render_preflight():
|
||||
def _render(plan: DockerBottlePlan, backend_name: str) -> None:
|
||||
print(file=sys.stderr)
|
||||
@@ -500,6 +524,8 @@ def _manifest_to_yaml(manifest: Manifest) -> str:
|
||||
lines.append(f" scheme: {r.AuthScheme}")
|
||||
|
||||
lines.append(f" supervise: {'true' if bottle.supervise else 'false'}")
|
||||
if bottle.nested_containers:
|
||||
lines.append(" nested_containers: true")
|
||||
|
||||
return "\n".join(lines)
|
||||
|
||||
@@ -537,6 +563,15 @@ def _launch_bottle(
|
||||
return 0
|
||||
|
||||
backend = get_bottle_backend(backend_name)
|
||||
try:
|
||||
backend.prelaunch_checks(plan)
|
||||
except StaleImageError as exc:
|
||||
if assume_yes:
|
||||
die(str(exc))
|
||||
sys.stderr.write(f"bot-bottle: {exc}\nLaunch anyway? [y/N] ")
|
||||
sys.stderr.flush()
|
||||
if read_tty_line() not in ("y", "Y", "yes", "YES"):
|
||||
return 0
|
||||
with backend.launch(plan) as bottle:
|
||||
agent_provider_template = getattr(plan, "agent_provider_template", "claude")
|
||||
extra_args: tuple[str, ...] = ()
|
||||
@@ -555,10 +590,6 @@ def _launch_bottle(
|
||||
f"session ended (exit {exit_code}); "
|
||||
f"container {bottle.name} will be removed"
|
||||
)
|
||||
# While the container is still alive: always snapshot the
|
||||
# transcript and — if the agent exited non-zero — mark
|
||||
# the state for preservation. This picks up crashes /
|
||||
# Ctrl-Cs / OOM kills before cleanup removes the state dir.
|
||||
if agent_provider_template == "claude":
|
||||
capture_claude_session_state(identity, exit_code)
|
||||
return 0
|
||||
|
||||
@@ -0,0 +1,71 @@
|
||||
"""SQLite-backed bot-bottle configuration store."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
from pathlib import Path
|
||||
|
||||
try:
|
||||
from .db_store import DbStore
|
||||
from .migrations import TableMigrations
|
||||
from .paths import host_db_path
|
||||
except ImportError:
|
||||
from db_store import DbStore # type: ignore[import-not-found] # pylint: disable=import-error,no-name-in-module
|
||||
from migrations import TableMigrations # type: ignore[import-not-found] # pylint: disable=import-error,no-name-in-module
|
||||
from paths import host_db_path # type: ignore[import-not-found] # pylint: disable=import-error,no-name-in-module
|
||||
|
||||
|
||||
DEFAULT_CACHED_IMAGE_STALE_WARNING_DAYS = 1
|
||||
|
||||
|
||||
class ConfigStore(DbStore):
|
||||
"""SQLite configuration for host-side bot-bottle settings."""
|
||||
|
||||
def __init__(self, db_path: Path | None = None) -> None:
|
||||
migrations = TableMigrations("config_store", [
|
||||
# v1 — host-side bot-bottle settings
|
||||
"""
|
||||
CREATE TABLE IF NOT EXISTS bot_bottle_config (
|
||||
id INTEGER PRIMARY KEY CHECK (id = 1),
|
||||
cached_image_stale_warning_days INTEGER NOT NULL DEFAULT 1
|
||||
)
|
||||
""",
|
||||
])
|
||||
super().__init__(db_path or host_db_path(), migrations)
|
||||
|
||||
def cached_image_stale_warning_days(self) -> int:
|
||||
if not self.db_path.is_file():
|
||||
return DEFAULT_CACHED_IMAGE_STALE_WARNING_DAYS
|
||||
with self._connect() as conn:
|
||||
row = conn.execute(
|
||||
"""
|
||||
SELECT cached_image_stale_warning_days
|
||||
FROM bot_bottle_config
|
||||
WHERE id = 1
|
||||
""",
|
||||
).fetchone()
|
||||
if row is None:
|
||||
return DEFAULT_CACHED_IMAGE_STALE_WARNING_DAYS
|
||||
try:
|
||||
return int(row["cached_image_stale_warning_days"])
|
||||
except (TypeError, ValueError):
|
||||
return DEFAULT_CACHED_IMAGE_STALE_WARNING_DAYS
|
||||
|
||||
def set_cached_image_stale_warning_days(self, days: int) -> Path:
|
||||
with self._connect() as conn:
|
||||
conn.execute(
|
||||
"""
|
||||
INSERT INTO bot_bottle_config (id, cached_image_stale_warning_days)
|
||||
VALUES (1, ?)
|
||||
ON CONFLICT(id) DO UPDATE SET
|
||||
cached_image_stale_warning_days = excluded.cached_image_stale_warning_days
|
||||
""",
|
||||
(days,),
|
||||
)
|
||||
self._chmod()
|
||||
return self.db_path
|
||||
|
||||
|
||||
__all__ = [
|
||||
"DEFAULT_CACHED_IMAGE_STALE_WARNING_DAYS",
|
||||
"ConfigStore",
|
||||
]
|
||||
@@ -10,7 +10,7 @@
|
||||
|
||||
# Current Node LTS; slim variant keeps the image small while still
|
||||
# providing apt-get for any future additions.
|
||||
FROM node:22-slim
|
||||
FROM node:22-trixie-slim
|
||||
|
||||
# Install runtime system deps. claude-code shells out to git for several
|
||||
# features (status checks, commits, PR creation) — without git in the
|
||||
@@ -21,7 +21,14 @@ FROM node:22-slim
|
||||
# to it) works against egress's bumped TLS without the agent needing
|
||||
# local DNS.
|
||||
RUN apt-get update \
|
||||
&& apt-get install -y --no-install-recommends git ca-certificates curl ripgrep iproute2 dnsutils \
|
||||
&& apt-get install -y --no-install-recommends \
|
||||
git \
|
||||
ca-certificates \
|
||||
curl \
|
||||
openssh-client \
|
||||
ripgrep \
|
||||
iproute2 \
|
||||
dnsutils \
|
||||
&& rm -rf /var/lib/apt/lists/*
|
||||
|
||||
# App-specific deps. Python isn't required by claude-code itself
|
||||
@@ -39,6 +46,11 @@ RUN apt-get update \
|
||||
RUN npm install -g --no-fund --no-audit @anthropic-ai/claude-code@2.1.172 \
|
||||
&& npm cache clean --force
|
||||
|
||||
# Git reads both ~/.gitconfig and ~/.config/git/config. Keep its XDG config
|
||||
# path traversable by the non-root runtime user so permission errors do not
|
||||
# suppress bot-bottle's git-gate insteadOf rules.
|
||||
RUN install -d -o node -g node -m 755 /home/node/.config /home/node/.config/git
|
||||
|
||||
# Run as a non-root user. The node image already provides a `node` user
|
||||
# (uid 1000) with a home directory, which is where claude-code will write
|
||||
# its session state.
|
||||
|
||||
@@ -23,8 +23,9 @@ from ...agent_provider import (
|
||||
provider_startup_args,
|
||||
)
|
||||
from ...backend.docker import util as docker_mod
|
||||
from ...egress import EgressRoute
|
||||
from ...egress import CLAUDE_HOST_CREDENTIAL_TOKEN_REF, EgressRoute
|
||||
from ...log import die, info, warn
|
||||
from .claude_auth import claude_host_access_token
|
||||
|
||||
|
||||
if TYPE_CHECKING:
|
||||
@@ -118,7 +119,6 @@ class ClaudeAgentProvider(AgentProvider):
|
||||
color: str = "",
|
||||
provider_settings: dict[str, object] | None = None,
|
||||
) -> AgentProvisionPlan:
|
||||
del forward_host_credentials, host_env
|
||||
resolved_guest_env = dict(guest_env or {})
|
||||
startup_args = provider_startup_args(provider_settings)
|
||||
guest_home = self.guest_home
|
||||
@@ -180,13 +180,24 @@ class ClaudeAgentProvider(AgentProvider):
|
||||
claude_settings,
|
||||
f"{guest_home}/.claude/settings.json",
|
||||
))
|
||||
provisioned_env: dict[str, str] = {}
|
||||
if forward_host_credentials:
|
||||
_host_env = host_env or dict(os.environ)
|
||||
provisioned_env[CLAUDE_HOST_CREDENTIAL_TOKEN_REF] = (
|
||||
claude_host_access_token(_host_env)
|
||||
)
|
||||
|
||||
cred_token_ref = (
|
||||
CLAUDE_HOST_CREDENTIAL_TOKEN_REF if forward_host_credentials
|
||||
else auth_token
|
||||
)
|
||||
egress_routes = (EgressRoute(
|
||||
host="api.anthropic.com",
|
||||
auth_scheme="Bearer" if auth_token else "",
|
||||
token_ref=auth_token,
|
||||
auth_scheme="Bearer" if (auth_token or forward_host_credentials) else "",
|
||||
token_ref=cred_token_ref,
|
||||
),)
|
||||
hidden_env_names: frozenset[str] = frozenset()
|
||||
if auth_token:
|
||||
if auth_token or forward_host_credentials:
|
||||
env_vars["CLAUDE_CODE_OAUTH_TOKEN"] = "egress-placeholder"
|
||||
hidden_env_names = frozenset({"CLAUDE_CODE_OAUTH_TOKEN"})
|
||||
|
||||
@@ -208,6 +219,7 @@ class ClaudeAgentProvider(AgentProvider):
|
||||
files=tuple(files),
|
||||
egress_routes=egress_routes,
|
||||
hidden_env_names=hidden_env_names,
|
||||
provisioned_env=provisioned_env,
|
||||
)
|
||||
|
||||
def provision_skills(self, plan: "BottlePlan", bottle: "Bottle") -> None:
|
||||
|
||||
@@ -0,0 +1,114 @@
|
||||
"""Host Claude auth helpers.
|
||||
|
||||
Reads the host's Claude Code credentials and returns only the access
|
||||
token needed by egress. Does not expose refresh tokens or raw payloads.
|
||||
|
||||
Credential storage by platform:
|
||||
Linux — ~/.claude/.credentials.json
|
||||
macOS — macOS Keychain, service "Claude Code-credentials"
|
||||
(file path is tried first; Keychain is the fallback)
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import json
|
||||
import os
|
||||
import subprocess
|
||||
import sys
|
||||
from datetime import datetime, timezone
|
||||
from pathlib import Path
|
||||
|
||||
from ...log import die
|
||||
|
||||
|
||||
_KEYCHAIN_SERVICE = "Claude Code-credentials"
|
||||
|
||||
|
||||
def claude_auth_path(host_env: dict[str, str] | None = None) -> Path:
|
||||
env = os.environ if host_env is None else host_env
|
||||
home = env.get("HOME")
|
||||
if home:
|
||||
return Path(home) / ".claude" / ".credentials.json"
|
||||
return Path.home() / ".claude" / ".credentials.json"
|
||||
|
||||
|
||||
def _read_keychain() -> dict[str, object] | None:
|
||||
"""Try the macOS Keychain. Returns parsed JSON dict or None."""
|
||||
if sys.platform != "darwin":
|
||||
return None
|
||||
try:
|
||||
result = subprocess.run(
|
||||
["security", "find-generic-password", "-s", _KEYCHAIN_SERVICE, "-w"],
|
||||
capture_output=True,
|
||||
text=True,
|
||||
timeout=10,
|
||||
)
|
||||
except (FileNotFoundError, subprocess.TimeoutExpired):
|
||||
return None
|
||||
if result.returncode != 0 or not result.stdout.strip():
|
||||
return None
|
||||
try:
|
||||
raw = json.loads(result.stdout.strip())
|
||||
except json.JSONDecodeError:
|
||||
return None
|
||||
return raw if isinstance(raw, dict) else None
|
||||
|
||||
|
||||
def claude_host_access_token(
|
||||
host_env: dict[str, str] | None = None,
|
||||
*,
|
||||
now: datetime | None = None,
|
||||
) -> str:
|
||||
path = claude_auth_path(host_env)
|
||||
raw: dict[str, object] | None = None
|
||||
|
||||
if path.is_file():
|
||||
try:
|
||||
raw = json.loads(path.read_text())
|
||||
except (OSError, json.JSONDecodeError) as e:
|
||||
die(f"claude host credentials: could not read valid JSON at {path}: {e}")
|
||||
if not isinstance(raw, dict):
|
||||
die(f"claude host credentials: {path} must contain a JSON object")
|
||||
else:
|
||||
raw = _read_keychain()
|
||||
if raw is None:
|
||||
die(
|
||||
f"claude host credentials: auth file missing at {path} and "
|
||||
f"macOS Keychain lookup for '{_KEYCHAIN_SERVICE}' failed. "
|
||||
"Run `claude login` on the host or disable "
|
||||
"agent_provider.forward_host_credentials."
|
||||
)
|
||||
|
||||
oauth = raw.get("claudeAiOauth")
|
||||
if not isinstance(oauth, dict):
|
||||
die(
|
||||
"claude host credentials: claudeAiOauth is missing from credentials. "
|
||||
"Run `claude login` on the host or disable "
|
||||
"agent_provider.forward_host_credentials."
|
||||
)
|
||||
|
||||
access_token = oauth.get("accessToken")
|
||||
if not isinstance(access_token, str) or not access_token:
|
||||
die(
|
||||
"claude host credentials: claudeAiOauth.accessToken is missing or empty. "
|
||||
"Run `claude login` on the host and restart the bottle."
|
||||
)
|
||||
|
||||
# expiresAt is in milliseconds
|
||||
expires_at = oauth.get("expiresAt")
|
||||
if isinstance(expires_at, (int, float)):
|
||||
check_now = now or datetime.now(timezone.utc)
|
||||
exp_dt = datetime.fromtimestamp(float(expires_at) / 1000.0, timezone.utc)
|
||||
if exp_dt <= check_now:
|
||||
die(
|
||||
"claude host credentials: host Claude access token is expired. "
|
||||
"Run `claude login` on the host and restart the bottle."
|
||||
)
|
||||
|
||||
return access_token
|
||||
|
||||
|
||||
__all__ = [
|
||||
"claude_auth_path",
|
||||
"claude_host_access_token",
|
||||
]
|
||||
@@ -3,10 +3,16 @@
|
||||
# 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-slim
|
||||
FROM node:22-trixie-slim
|
||||
|
||||
RUN apt-get update \
|
||||
&& apt-get install -y --no-install-recommends git ca-certificates curl procps ripgrep \
|
||||
&& apt-get install -y --no-install-recommends \
|
||||
git \
|
||||
ca-certificates \
|
||||
curl \
|
||||
openssh-client \
|
||||
procps \
|
||||
ripgrep \
|
||||
&& rm -rf /var/lib/apt/lists/*
|
||||
|
||||
# App-specific deps. Python isn't required by codex itself
|
||||
@@ -17,6 +23,8 @@ RUN apt-get update \
|
||||
&& apt-get install -y --no-install-recommends python3 python3-pip python3-venv \
|
||||
&& rm -rf /var/lib/apt/lists/*
|
||||
|
||||
RUN install -d -o node -g node -m 755 /home/node/.config /home/node/.config/git
|
||||
|
||||
USER node
|
||||
WORKDIR /home/node
|
||||
|
||||
|
||||
@@ -2,7 +2,7 @@
|
||||
#
|
||||
# Node LTS, git/network tooling, and the Pi coding-agent CLI installed globally.
|
||||
|
||||
FROM node:22-slim
|
||||
FROM node:22-trixie-slim
|
||||
|
||||
RUN apt-get update \
|
||||
&& apt-get install -y --no-install-recommends \
|
||||
@@ -10,6 +10,7 @@ RUN apt-get update \
|
||||
ca-certificates \
|
||||
curl \
|
||||
fd-find \
|
||||
openssh-client \
|
||||
ripgrep \
|
||||
&& ln -s /usr/bin/fdfind /usr/local/bin/fd \
|
||||
&& rm -rf /var/lib/apt/lists/*
|
||||
@@ -21,7 +22,8 @@ RUN apt-get update \
|
||||
RUN npm install -g --ignore-scripts --no-fund --no-audit @earendil-works/pi-coding-agent \
|
||||
&& npm cache clean --force
|
||||
|
||||
RUN mkdir -p /home/node/.pi/agent \
|
||||
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 \
|
||||
/tmp/pi-subagents-uid-1000 \
|
||||
&& chown -R node:node /home/node/.pi /tmp \
|
||||
|
||||
+50
-32
@@ -30,6 +30,7 @@ if TYPE_CHECKING:
|
||||
from .manifest import ManifestBottle
|
||||
|
||||
CODEX_HOST_CREDENTIAL_TOKEN_REF = "BOT_BOTTLE_CODEX_HOST_ACCESS_TOKEN"
|
||||
CLAUDE_HOST_CREDENTIAL_TOKEN_REF = "BOT_BOTTLE_CLAUDE_HOST_ACCESS_TOKEN"
|
||||
|
||||
EGRESS_HOSTNAME = "egress"
|
||||
|
||||
@@ -145,6 +146,8 @@ def egress_manifest_routes(
|
||||
outbound_detectors=r.OutboundDetectors,
|
||||
inbound_detectors=r.InboundDetectors,
|
||||
outbound_on_match=r.OutboundOnMatch,
|
||||
preserve_auth=r.PreserveAuth,
|
||||
inspect=r.Inspect,
|
||||
))
|
||||
return tuple(out)
|
||||
|
||||
@@ -224,9 +227,13 @@ def _yaml_str_escape(s: str) -> str:
|
||||
|
||||
def _route_to_yaml_fields(r: Route) -> dict[str, object]:
|
||||
fields: dict[str, object] = {"host": r.host}
|
||||
if not r.inspect:
|
||||
fields["inspect"] = False
|
||||
return fields
|
||||
inspect: dict[str, object] = {}
|
||||
if r.auth_scheme and r.token_env:
|
||||
fields["auth_scheme"] = r.auth_scheme
|
||||
fields["token_env"] = r.token_env
|
||||
inspect["auth_scheme"] = r.auth_scheme
|
||||
inspect["token_env"] = r.token_env
|
||||
if r.matches:
|
||||
matches_data: list[dict[str, object]] = []
|
||||
for entry in r.matches:
|
||||
@@ -250,28 +257,30 @@ def _route_to_yaml_fields(r: Route) -> dict[str, object]:
|
||||
headers_data.append(hd)
|
||||
entry_data["headers"] = headers_data
|
||||
matches_data.append(entry_data)
|
||||
fields["matches"] = matches_data
|
||||
inspect["matches"] = matches_data
|
||||
if r.git_fetch:
|
||||
fields["git"] = {"fetch": True}
|
||||
inspect["git"] = {"fetch": True}
|
||||
if r.preserve_auth:
|
||||
inspect["preserve_auth"] = True
|
||||
if (
|
||||
r.outbound_detectors is not None
|
||||
or r.inbound_detectors is not None
|
||||
or r.outbound_on_match
|
||||
):
|
||||
dlp: dict[str, object] = {}
|
||||
if r.outbound_detectors is not None:
|
||||
dlp["outbound_detectors"] = (
|
||||
inspect["outbound_detectors"] = (
|
||||
False if not r.outbound_detectors
|
||||
else list(r.outbound_detectors)
|
||||
)
|
||||
if r.inbound_detectors is not None:
|
||||
dlp["inbound_detectors"] = (
|
||||
inspect["inbound_detectors"] = (
|
||||
False if not r.inbound_detectors
|
||||
else list(r.inbound_detectors)
|
||||
)
|
||||
if r.outbound_on_match:
|
||||
dlp["outbound_on_match"] = r.outbound_on_match
|
||||
fields["dlp"] = dlp
|
||||
inspect["outbound_on_match"] = r.outbound_on_match
|
||||
if inspect:
|
||||
fields["inspect"] = inspect
|
||||
return fields
|
||||
|
||||
|
||||
@@ -279,30 +288,30 @@ def _render_match_entry(entry: dict[str, object]) -> list[str]:
|
||||
lines: list[str] = []
|
||||
first_key = True
|
||||
if "paths" in entry:
|
||||
lines.append(" - paths:")
|
||||
lines.append(" - paths:")
|
||||
first_key = False
|
||||
for pd in entry["paths"]: # type: ignore[union-attr]
|
||||
pd_dict: dict[str, str] = pd # type: ignore[assignment]
|
||||
if "type" in pd_dict:
|
||||
lines.append(f' - type: "{_yaml_str_escape(pd_dict["type"])}"')
|
||||
lines.append(f' value: "{_yaml_str_escape(pd_dict["value"])}"')
|
||||
lines.append(f' - type: "{_yaml_str_escape(pd_dict["type"])}"')
|
||||
lines.append(f' value: "{_yaml_str_escape(pd_dict["value"])}"')
|
||||
else:
|
||||
lines.append(f' - value: "{_yaml_str_escape(pd_dict["value"])}"')
|
||||
lines.append(f' - value: "{_yaml_str_escape(pd_dict["value"])}"')
|
||||
if "methods" in entry:
|
||||
methods_str = ", ".join(f'"{_yaml_str_escape(m)}"' for m in entry["methods"]) # type: ignore[union-attr]
|
||||
prefix = " - " if first_key else " "
|
||||
prefix = " - " if first_key else " "
|
||||
lines.append(f'{prefix}methods: [{methods_str}]')
|
||||
first_key = False
|
||||
if "headers" in entry:
|
||||
prefix = " - " if first_key else " "
|
||||
prefix = " - " if first_key else " "
|
||||
lines.append(f"{prefix}headers:")
|
||||
first_key = False
|
||||
for hd in entry["headers"]: # type: ignore[union-attr]
|
||||
hd_dict: dict[str, str] = hd # type: ignore[assignment]
|
||||
lines.append(f' - name: "{_yaml_str_escape(hd_dict["name"])}"')
|
||||
lines.append(f' value: "{_yaml_str_escape(hd_dict["value"])}"')
|
||||
lines.append(f' - name: "{_yaml_str_escape(hd_dict["name"])}"')
|
||||
lines.append(f' value: "{_yaml_str_escape(hd_dict["value"])}"')
|
||||
if first_key:
|
||||
lines.append(" - {}")
|
||||
lines.append(" - {}")
|
||||
return lines
|
||||
|
||||
|
||||
@@ -321,22 +330,30 @@ def egress_render_routes(
|
||||
for r in routes:
|
||||
f = _route_to_yaml_fields(r)
|
||||
lines.append(f' - host: "{_yaml_str_escape(str(f["host"]))}"')
|
||||
if "auth_scheme" in f:
|
||||
lines.append(f' auth_scheme: "{_yaml_str_escape(str(f["auth_scheme"]))}"')
|
||||
lines.append(f' token_env: "{_yaml_str_escape(str(f["token_env"]))}"')
|
||||
if "matches" in f:
|
||||
lines.append(" matches:")
|
||||
for entry in f["matches"]: # type: ignore[union-attr]
|
||||
if f.get("inspect") is False:
|
||||
lines.append(" inspect: false")
|
||||
continue
|
||||
inspect: dict[str, object] = f.get("inspect", {}) # type: ignore[assignment]
|
||||
if not inspect:
|
||||
continue
|
||||
lines.append(" inspect:")
|
||||
if "auth_scheme" in inspect:
|
||||
lines.append(f' auth_scheme: "{_yaml_str_escape(str(inspect["auth_scheme"]))}"')
|
||||
lines.append(f' token_env: "{_yaml_str_escape(str(inspect["token_env"]))}"')
|
||||
if "matches" in inspect:
|
||||
lines.append(" matches:")
|
||||
for entry in inspect["matches"]: # type: ignore[union-attr]
|
||||
lines.extend(_render_match_entry(entry)) # type: ignore[arg-type]
|
||||
if "git" in f:
|
||||
git_dict: dict[str, object] = f["git"] # type: ignore
|
||||
lines.append(" git:")
|
||||
if "git" in inspect:
|
||||
git_dict: dict[str, object] = inspect["git"] # type: ignore
|
||||
lines.append(" git:")
|
||||
if git_dict.get("fetch") is True:
|
||||
lines.append(" fetch: true")
|
||||
if "dlp" in f:
|
||||
dlp_dict: dict[str, object] = f["dlp"] # type: ignore
|
||||
lines.append(" dlp:")
|
||||
for dk, dv in dlp_dict.items():
|
||||
lines.append(" fetch: true")
|
||||
if inspect.get("preserve_auth") is True:
|
||||
lines.append(" preserve_auth: true")
|
||||
for dk in ("outbound_detectors", "inbound_detectors", "outbound_on_match"):
|
||||
if dk in inspect:
|
||||
dv = inspect[dk]
|
||||
if dv is False:
|
||||
lines.append(f" {dk}: false")
|
||||
elif isinstance(dv, list):
|
||||
@@ -400,6 +417,7 @@ class Egress(ABC):
|
||||
)
|
||||
|
||||
__all__ = [
|
||||
"CLAUDE_HOST_CREDENTIAL_TOKEN_REF",
|
||||
"CODEX_HOST_CREDENTIAL_TOKEN_REF",
|
||||
"EGRESS_HOSTNAME",
|
||||
"EGRESS_ROUTES_FILENAME",
|
||||
|
||||
+70
-16
@@ -97,10 +97,11 @@ class EgressAddon:
|
||||
# comes from the orchestrator's /resolve (PRD 0070); there is no static
|
||||
# per-bottle routes file, SIGHUP reload, or single-tenant fallback.
|
||||
_resolver: "PolicyResolver"
|
||||
# Class default so __new__-built addons have it (real runs get a fresh
|
||||
# per-instance dict in __init__; only http_connect mutates it, which the
|
||||
# request-flow tests don't exercise).
|
||||
# Class defaults so __new__-built addons have them (real runs get fresh
|
||||
# per-instance collections in __init__; only http_connect mutates them,
|
||||
# which request-flow tests don't exercise unless they call http_connect).
|
||||
_conn_tokens: "dict[str, str]" = {}
|
||||
_passthrough_conns: "set[str]" = set()
|
||||
|
||||
def __init__(self) -> None:
|
||||
# Resolver-only: the gateway is always multi-tenant, resolving each
|
||||
@@ -125,6 +126,10 @@ class EgressAddon:
|
||||
# `Proxy-Authorization` (HTTPS tunnels don't repeat it on the bumped
|
||||
# inner requests). Keyed by client_conn.id; cleared on disconnect.
|
||||
self._conn_tokens: dict[str, str] = {}
|
||||
# Connections whose route carries `inspect: false` — mitmproxy tunnels
|
||||
# these without TLS interception so the client sees the server's real
|
||||
# cert. Keyed by client_conn.id; cleared on disconnect.
|
||||
self._passthrough_conns: set[str] = set()
|
||||
self._token_allow_timeout = _token_allow_timeout_from_env(os.environ)
|
||||
|
||||
@staticmethod
|
||||
@@ -305,25 +310,68 @@ class EgressAddon:
|
||||
def http_connect(self, flow: http.HTTPFlow) -> None:
|
||||
"""Capture the identity token from an HTTPS tunnel's CONNECT (the inner
|
||||
bumped requests won't carry `Proxy-Authorization`), keyed by client
|
||||
connection, and strip it so it never reaches upstream."""
|
||||
connection, and strip it so it never reaches upstream.
|
||||
|
||||
For `inspect: false` routes, also resolve the policy here to make the
|
||||
allowlist decision before the TLS handshake: the tunnel is either
|
||||
blocked immediately or marked for passthrough in `_passthrough_conns`
|
||||
so `tls_clienthello` skips interception."""
|
||||
token = _token_from_proxy_auth(
|
||||
flow.request.headers.get("Proxy-Authorization", ""))
|
||||
flow.request.headers.pop("Proxy-Authorization", None)
|
||||
conn = flow.client_conn
|
||||
if conn is not None and getattr(conn, "id", ""):
|
||||
self._conn_tokens[conn.id] = token
|
||||
conn_id = getattr(conn, "id", "") if conn is not None else ""
|
||||
if conn_id:
|
||||
self._conn_tokens[conn_id] = token
|
||||
|
||||
# Resolve the policy here for all HTTPS connections and stash it so
|
||||
# request() reuses it without a second orchestrator round-trip. For
|
||||
# passthrough hosts we also make the allowlist decision now because
|
||||
# inner requests never reach request() after the TLS bypass.
|
||||
client_ip = conn.peername[0] if conn is not None and conn.peername else ""
|
||||
config, slug, env = resolve_client_context(self._resolver, client_ip, token)
|
||||
self._stash_flow_ctx(flow, config, slug, env)
|
||||
host = flow.request.pretty_host
|
||||
route = match_route(config.routes, host)
|
||||
if route is not None and not route.inspect:
|
||||
decision = decide(config.routes, host, "/", env, deny_reason=config.deny_reason)
|
||||
if decision.action == "block":
|
||||
flow.response = http.Response.make(
|
||||
403,
|
||||
decision.reason.encode("utf-8"),
|
||||
{"Content-Type": "text/plain; charset=utf-8"},
|
||||
)
|
||||
return
|
||||
if conn_id:
|
||||
self._passthrough_conns.add(conn_id)
|
||||
|
||||
def tls_clienthello(self, client_hello: typing.Any) -> None:
|
||||
"""Skip TLS interception for `inspect: false` routes so the client sees
|
||||
the server's real certificate rather than the MITM CA's leaf."""
|
||||
conn_id = getattr(client_hello.context.client, "id", "")
|
||||
if conn_id in self._passthrough_conns:
|
||||
client_hello.ignore_connection = True
|
||||
|
||||
def client_disconnected(self, client: typing.Any) -> None:
|
||||
"""Drop the per-connection token when the client goes away."""
|
||||
self._conn_tokens.pop(getattr(client, "id", ""), None)
|
||||
"""Drop the per-connection token and passthrough flag when the client
|
||||
goes away."""
|
||||
conn_id = getattr(client, "id", "")
|
||||
self._conn_tokens.pop(conn_id, None)
|
||||
self._passthrough_conns.discard(conn_id)
|
||||
|
||||
async def request(self, flow: http.HTTPFlow) -> None:
|
||||
request_path, _, query = flow.request.path.partition("?")
|
||||
|
||||
config, slug, env = self._resolve_flow(flow)
|
||||
# Stash for the response / websocket hooks so their DLP scans reuse this
|
||||
# bottle's resolved policy (one /resolve per flow — see _flow_ctx).
|
||||
self._stash_flow_ctx(flow, config, slug, env)
|
||||
# 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
|
||||
@@ -335,8 +383,10 @@ class EgressAddon:
|
||||
# DLP outbound scan BEFORE stripping auth — catches tokens the
|
||||
# agent tried to smuggle in any header, path, query param, or body.
|
||||
# Hostname is included to catch DNS-tunnelling exfiltration attempts.
|
||||
# `inspect: false` routes skip scanning entirely (TLS is also not
|
||||
# intercepted for HTTPS, so this branch only fires for plain HTTP).
|
||||
route = match_route(config.routes, flow.request.pretty_host)
|
||||
if route is not None:
|
||||
if route is not None and route.inspect:
|
||||
if not await self._handle_outbound_dlp(flow, route, slug, env):
|
||||
return
|
||||
# The redact policy may have rewritten the request line; recompute
|
||||
@@ -367,7 +417,10 @@ class EgressAddon:
|
||||
|
||||
# Strip agent-set Authorization after DLP scan so smuggled tokens
|
||||
# are caught above; the route may inject gateway-owned auth below.
|
||||
flow.request.headers.pop("authorization", None)
|
||||
# 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:
|
||||
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()}
|
||||
@@ -379,6 +432,7 @@ class EgressAddon:
|
||||
env,
|
||||
request_method=flow.request.method,
|
||||
request_headers=req_headers,
|
||||
deny_reason=config.deny_reason,
|
||||
)
|
||||
|
||||
if decision.action == "block":
|
||||
@@ -602,7 +656,7 @@ class EgressAddon:
|
||||
bottle's resolved config (`request()` stashed it — see `_flow_ctx`)."""
|
||||
config, _slug, env = self._flow_ctx(flow)
|
||||
route = match_route(config.routes, flow.request.pretty_host)
|
||||
if route is None:
|
||||
if route is None or not route.inspect:
|
||||
return
|
||||
if flow.response is None:
|
||||
return
|
||||
@@ -648,7 +702,7 @@ class EgressAddon:
|
||||
return
|
||||
config, slug, env = self._flow_ctx(flow)
|
||||
route = match_route(config.routes, flow.request.pretty_host)
|
||||
if route is None:
|
||||
if route is None or not route.inspect:
|
||||
return
|
||||
message = flow.websocket.messages[-1] # type: ignore[union-attr]
|
||||
content = message.content.decode("utf-8", errors="replace")
|
||||
|
||||
+115
-26
@@ -28,7 +28,7 @@ from .egress_dlp_config import (
|
||||
ON_MATCH_SUPERVISE,
|
||||
OUTBOUND_DETECTOR_NAMES,
|
||||
OUTBOUND_ON_MATCH_VALUES,
|
||||
parse_dlp_block,
|
||||
parse_inspect_block,
|
||||
)
|
||||
|
||||
|
||||
@@ -78,6 +78,9 @@ class Route:
|
||||
inbound_detectors: tuple[str, ...] | None = None
|
||||
# "" means unset → DEFAULT_OUTBOUND_ON_MATCH. See OUTBOUND_ON_MATCH_VALUES.
|
||||
outbound_on_match: str = ""
|
||||
preserve_auth: bool = False
|
||||
# False tunnels HTTPS without TLS interception or HTTP-level controls.
|
||||
inspect: bool = True
|
||||
|
||||
|
||||
LOG_OFF = 0 # no logging
|
||||
@@ -89,6 +92,14 @@ LOG_FULL = 2 # log block/warn events + full request and response bodies
|
||||
class Config:
|
||||
routes: tuple[Route, ...]
|
||||
log: int = LOG_OFF
|
||||
# Why this Config is a deny-all, when it is one for a reason *other* than
|
||||
# the bottle's own policy genuinely not listing the host. A deny-all is
|
||||
# indistinguishable from "policy loaded, host not allowed" at the decision
|
||||
# point — both are simply "no matching route" — so without this the
|
||||
# operator sees `host X is not in the allowlist` and goes hunting for a
|
||||
# missing route that was never the problem. Empty for a normally-parsed
|
||||
# policy; `decide` prefers it over the allowlist wording when set.
|
||||
deny_reason: str = ""
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
@@ -250,10 +261,31 @@ def _parse_one(idx: int, raw: object) -> Route:
|
||||
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 = raw_dict.get("matches")
|
||||
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")
|
||||
@@ -263,8 +295,8 @@ def _parse_one(idx: int, raw: object) -> Route:
|
||||
)
|
||||
|
||||
# auth (unchanged wire format)
|
||||
auth_scheme: object = raw_dict.get("auth_scheme", "")
|
||||
token_env: object = raw_dict.get("token_env", "")
|
||||
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):
|
||||
@@ -278,7 +310,7 @@ def _parse_one(idx: int, raw: object) -> Route:
|
||||
|
||||
# git-over-HTTPS policy
|
||||
git_fetch = False
|
||||
git_raw = raw_dict.get("git")
|
||||
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")
|
||||
@@ -296,15 +328,30 @@ def _parse_one(idx: int, raw: object) -> Route:
|
||||
)
|
||||
|
||||
# dlp detectors
|
||||
outbound_detectors, inbound_detectors, outbound_on_match = parse_dlp_block(
|
||||
idx, host, raw_dict,
|
||||
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 k not in ("host", "matches", "auth_scheme", "token_env", "dlp", "git"):
|
||||
if not legacy_flat and k not in ("host", "inspect"):
|
||||
raise ValueError(
|
||||
f"{label} ({host}): unknown key {k!r}; accepted keys "
|
||||
f"are 'host', 'matches', 'auth_scheme', 'token_env', 'dlp', 'git'"
|
||||
f"are 'host' and 'inspect'"
|
||||
)
|
||||
|
||||
return Route(
|
||||
@@ -316,6 +363,8 @@ def _parse_one(idx: int, raw: object) -> Route:
|
||||
outbound_detectors=outbound_detectors,
|
||||
inbound_detectors=inbound_detectors,
|
||||
outbound_on_match=outbound_on_match,
|
||||
preserve_auth=preserve_auth,
|
||||
inspect=inspect,
|
||||
)
|
||||
|
||||
|
||||
@@ -352,22 +401,27 @@ def route_to_yaml_dict(r: Route) -> dict[str, object]:
|
||||
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:
|
||||
d["auth_scheme"] = r.auth_scheme
|
||||
d["token_env"] = r.token_env
|
||||
inspected["auth_scheme"] = r.auth_scheme
|
||||
inspected["token_env"] = r.token_env
|
||||
if r.matches:
|
||||
d["matches"] = [_match_entry_to_dict(m) for m in r.matches]
|
||||
inspected["matches"] = [_match_entry_to_dict(m) for m in r.matches]
|
||||
if r.git_fetch:
|
||||
d["git"] = {"fetch": True}
|
||||
dlp: dict[str, object] = {}
|
||||
inspected["git"] = {"fetch": True}
|
||||
if r.outbound_detectors is not None:
|
||||
dlp["outbound_detectors"] = list(r.outbound_detectors)
|
||||
inspected["outbound_detectors"] = list(r.outbound_detectors)
|
||||
if r.inbound_detectors is not None:
|
||||
dlp["inbound_detectors"] = list(r.inbound_detectors)
|
||||
inspected["inbound_detectors"] = list(r.inbound_detectors)
|
||||
if r.outbound_on_match:
|
||||
dlp["outbound_on_match"] = r.outbound_on_match
|
||||
if dlp:
|
||||
d["dlp"] = dlp
|
||||
inspected["outbound_on_match"] = r.outbound_on_match
|
||||
if r.preserve_auth:
|
||||
inspected["preserve_auth"] = True
|
||||
if inspected:
|
||||
d["inspect"] = inspected
|
||||
return d
|
||||
|
||||
|
||||
@@ -405,16 +459,40 @@ class PolicyResolverLike(typing.Protocol):
|
||||
...
|
||||
|
||||
|
||||
# Deny-all explanations. Each names the *actual* failure so an operator isn't
|
||||
# sent looking for a missing egress route when the bottle never had a policy
|
||||
# to begin with — the failure mode that made a bricked registration read like
|
||||
# a misconfigured allowlist.
|
||||
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."
|
||||
)
|
||||
|
||||
|
||||
def _config_from_policy(policy: "str | None") -> "Config":
|
||||
"""Parse a resolved policy blob into a Config, fail-closed: None / empty /
|
||||
unparseable all become a deny-all Config (no routes → every request
|
||||
blocked)."""
|
||||
blocked). Each deny-all carries the reason it is one, so the block message
|
||||
names the real fault instead of blaming the allowlist."""
|
||||
if not policy:
|
||||
return Config(routes=()) # unattributed or empty → deny-all
|
||||
return Config(routes=(), deny_reason=DENY_UNATTRIBUTED)
|
||||
try:
|
||||
return load_config(policy)
|
||||
except ValueError:
|
||||
return Config(routes=()) # unparseable policy → deny
|
||||
return Config(routes=(), deny_reason=DENY_UNPARSEABLE)
|
||||
|
||||
|
||||
def resolve_client_config(
|
||||
@@ -428,7 +506,7 @@ def resolve_client_config(
|
||||
try:
|
||||
policy = resolver.resolve(client_ip, identity_token)
|
||||
except Exception: # noqa: BLE001 # pylint: disable=broad-exception-caught
|
||||
return Config(routes=()) # orchestrator unreachable/errored → deny
|
||||
return Config(routes=(), deny_reason=DENY_RESOLVER_ERROR)
|
||||
return _config_from_policy(policy)
|
||||
|
||||
|
||||
@@ -457,7 +535,7 @@ def resolve_client_context(
|
||||
client_ip, identity_token,
|
||||
)
|
||||
except Exception: # noqa: BLE001 # pylint: disable=broad-exception-caught
|
||||
return Config(routes=()), "", {} # orchestrator unreachable/errored → deny
|
||||
return Config(routes=(), deny_reason=DENY_RESOLVER_ERROR), "", {}
|
||||
return _config_from_policy(policy), (bottle_id or ""), tokens
|
||||
|
||||
|
||||
@@ -572,12 +650,16 @@ def decide(
|
||||
*,
|
||||
request_method: str = "GET",
|
||||
request_headers: typing.Mapping[str, str] | None = None,
|
||||
deny_reason: str = "",
|
||||
) -> Decision:
|
||||
"""`deny_reason` is `Config.deny_reason`: when the deny-all came from a
|
||||
missing/unparseable policy rather than the bottle's own allowlist, report
|
||||
that instead of implying a route is merely absent."""
|
||||
route = match_route(routes, request_host)
|
||||
if route is None:
|
||||
return Decision(
|
||||
action="block",
|
||||
reason=(
|
||||
reason=deny_reason or (
|
||||
f"egress: host {request_host!r} is not in the "
|
||||
f"bottle's egress.routes allowlist. Declare a "
|
||||
f"route for it or remove the request."
|
||||
@@ -711,6 +793,8 @@ def scan_outbound(
|
||||
safe_tokens: typing.AbstractSet[str] | None = None,
|
||||
crlf_text: str | None = None,
|
||||
) -> ScanResult | None:
|
||||
if not route.inspect:
|
||||
return None
|
||||
# Lazy import to avoid circular deps and keep dlp_detectors optional
|
||||
# at import time (the gateway copies it flat alongside this file).
|
||||
try:
|
||||
@@ -808,6 +892,8 @@ 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 - host-side path
|
||||
@@ -835,7 +921,7 @@ __all__ = [
|
||||
"DEFAULT_OUTBOUND_ON_MATCH",
|
||||
"OUTBOUND_DETECTOR_NAMES",
|
||||
"INBOUND_DETECTOR_NAMES",
|
||||
"parse_dlp_block",
|
||||
"parse_inspect_block",
|
||||
"Config",
|
||||
"Decision",
|
||||
"HeaderMatch",
|
||||
@@ -852,6 +938,9 @@ __all__ = [
|
||||
"is_git_push_request",
|
||||
"is_git_fetch_request",
|
||||
"load_config",
|
||||
"DENY_UNATTRIBUTED",
|
||||
"DENY_UNPARSEABLE",
|
||||
"DENY_RESOLVER_ERROR",
|
||||
"resolve_client_config",
|
||||
"resolve_client_context",
|
||||
"PolicyResolverLike",
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
"""DLP detector-config parsing for egress routes (PRD 0053, PRD 0062).
|
||||
"""Inspection and DLP configuration parsing for egress routes.
|
||||
|
||||
A route's optional `dlp:` block names which outbound/inbound detectors run
|
||||
A route's optional `inspect:` object names which outbound/inbound detectors run
|
||||
and what the proxy does when an outbound detector matches a token
|
||||
(`outbound_on_match`). This module owns parsing and validating that block,
|
||||
kept apart from the request-time scan/decision flow in `egress_addon_core`
|
||||
@@ -26,20 +26,14 @@ OUTBOUND_ON_MATCH_VALUES = (ON_MATCH_BLOCK, ON_MATCH_REDACT, ON_MATCH_SUPERVISE)
|
||||
DEFAULT_OUTBOUND_ON_MATCH = ON_MATCH_SUPERVISE
|
||||
|
||||
|
||||
def parse_dlp_block(
|
||||
def parse_inspect_block(
|
||||
idx: int,
|
||||
host: str,
|
||||
raw_dict: dict[str, object],
|
||||
inspect: dict[str, object],
|
||||
) -> tuple[tuple[str, ...] | None, tuple[str, ...] | None, str]:
|
||||
"""Parse the optional `dlp` block on a route, returning
|
||||
(outbound_detectors, inbound_detectors, outbound_on_match)."""
|
||||
dlp_raw = raw_dict.get("dlp")
|
||||
if dlp_raw is None:
|
||||
return None, None, ""
|
||||
"""Parse DLP settings from an inspected route."""
|
||||
label = f"route[{idx}] ({host})"
|
||||
if not isinstance(dlp_raw, dict):
|
||||
raise ValueError(f"{label}: 'dlp' must be an object")
|
||||
dlp = typing.cast(dict[str, object], dlp_raw)
|
||||
dlp = inspect
|
||||
|
||||
def _parse_detector_field(
|
||||
field: str,
|
||||
@@ -52,18 +46,18 @@ def parse_dlp_block(
|
||||
return ()
|
||||
if not isinstance(val, list):
|
||||
raise ValueError(
|
||||
f"{label}: dlp.{field} must be false, a list, or omitted"
|
||||
f"{label}: inspect.{field} must be false, a list, or omitted"
|
||||
)
|
||||
items = typing.cast(list[object], val)
|
||||
names: list[str] = []
|
||||
for j, item in enumerate(items):
|
||||
if not isinstance(item, str):
|
||||
raise ValueError(
|
||||
f"{label}: dlp.{field}[{j}] must be a string"
|
||||
f"{label}: inspect.{field}[{j}] must be a string"
|
||||
)
|
||||
if item not in valid_names:
|
||||
raise ValueError(
|
||||
f"{label}: dlp.{field}[{j}] {item!r} is not a valid "
|
||||
f"{label}: inspect.{field}[{j}] {item!r} is not a valid "
|
||||
f"detector name; valid names: {', '.join(sorted(valid_names))}"
|
||||
)
|
||||
names.append(item)
|
||||
@@ -77,16 +71,9 @@ def parse_dlp_block(
|
||||
if on_match_raw is not None:
|
||||
if not isinstance(on_match_raw, str) or on_match_raw not in OUTBOUND_ON_MATCH_VALUES:
|
||||
raise ValueError(
|
||||
f"{label}: dlp.outbound_on_match must be one of "
|
||||
f"{label}: inspect.outbound_on_match must be one of "
|
||||
f"{', '.join(OUTBOUND_ON_MATCH_VALUES)} (got {on_match_raw!r})"
|
||||
)
|
||||
on_match = on_match_raw
|
||||
|
||||
for k in dlp:
|
||||
if k not in ("outbound_detectors", "inbound_detectors", "outbound_on_match"):
|
||||
raise ValueError(
|
||||
f"{label}: dlp has unknown key {k!r}; accepted keys "
|
||||
f"are 'outbound_detectors', 'inbound_detectors', "
|
||||
f"'outbound_on_match'"
|
||||
)
|
||||
return outbound, inbound, on_match
|
||||
|
||||
@@ -0,0 +1,42 @@
|
||||
"""Shared helpers for cached-image quickstart stale checks."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
from datetime import datetime, timezone
|
||||
from pathlib import Path
|
||||
|
||||
try:
|
||||
from .config_store import ConfigStore
|
||||
except ImportError:
|
||||
from config_store import ConfigStore # type: ignore[import-not-found] # pylint: disable=import-error,no-name-in-module
|
||||
|
||||
|
||||
class StaleImageError(Exception):
|
||||
"""Raised when a cached image or artifact exceeds the configured staleness
|
||||
threshold. Callers can catch this to prompt interactively; headless paths
|
||||
let it propagate as a fatal error."""
|
||||
|
||||
|
||||
def check_stale(label: str, created_at: datetime) -> None:
|
||||
"""Raise StaleImageError if `created_at` is older than the configured
|
||||
stale-warning threshold. Negative threshold disables the check."""
|
||||
threshold_days = ConfigStore().cached_image_stale_warning_days()
|
||||
if threshold_days < 0:
|
||||
return
|
||||
now = datetime.now(timezone.utc)
|
||||
created = created_at.astimezone(timezone.utc)
|
||||
age = now - created
|
||||
if age.total_seconds() <= threshold_days * 86400:
|
||||
return
|
||||
raise StaleImageError(
|
||||
f"cached {label} is {age.days} day(s) old; "
|
||||
"quickstart does not verify it matches the current Dockerfile/context"
|
||||
)
|
||||
|
||||
|
||||
def check_stale_path(label: str, path: Path) -> None:
|
||||
"""Raise StaleImageError if `path`'s mtime exceeds the staleness threshold."""
|
||||
check_stale(label, datetime.fromtimestamp(path.stat().st_mtime, tz=timezone.utc))
|
||||
|
||||
|
||||
__all__ = ["StaleImageError", "check_stale", "check_stale_path"]
|
||||
@@ -20,6 +20,7 @@ Bottle schema (frontmatter):
|
||||
egress: { routes: [ <egress-route>, ... ] }
|
||||
# route keys: host, matches, auth, role, dlp
|
||||
supervise: <bool> # optional (default true)
|
||||
nested_containers: <bool> # optional (default false)
|
||||
|
||||
Agent schema (frontmatter):
|
||||
bottle: <bottle-name> # required
|
||||
|
||||
@@ -25,8 +25,9 @@ class ManifestAgentProvider:
|
||||
header, and sets a placeholder CLAUDE_CODE_OAUTH_TOKEN in the agent
|
||||
so the Claude Code CLI starts.
|
||||
|
||||
`forward_host_credentials` forwards the host Codex auth token into
|
||||
the egress daemon (Codex only).
|
||||
`forward_host_credentials` forwards the host provider auth token into
|
||||
the egress sidecar (Codex and Claude). For Codex this reads
|
||||
`~/.codex/auth.json`; for Claude it reads `~/.claude/.credentials.json`.
|
||||
"""
|
||||
|
||||
template: str = "claude"
|
||||
@@ -92,10 +93,15 @@ class ManifestAgentProvider:
|
||||
f"is only supported for built-in templates "
|
||||
f"({', '.join(sorted(PROVIDER_TEMPLATES))})"
|
||||
)
|
||||
if forward_host_credentials and template != "codex":
|
||||
if forward_host_credentials and template not in {"codex", "claude"}:
|
||||
raise ManifestError(
|
||||
f"bottle '{bottle_name}' agent_provider.forward_host_credentials "
|
||||
"is currently only supported for template 'codex'"
|
||||
"is only supported for templates 'codex' and 'claude'"
|
||||
)
|
||||
if forward_host_credentials and auth_token:
|
||||
raise ManifestError(
|
||||
f"bottle '{bottle_name}' agent_provider.forward_host_credentials "
|
||||
"and auth_token both set; use one or the other"
|
||||
)
|
||||
settings = _parse_provider_settings(bottle_name, template, d.get("settings"))
|
||||
return cls(
|
||||
|
||||
@@ -44,6 +44,15 @@ class ManifestBottle:
|
||||
# daemon that exposes egress MCP tools to the agent. Set
|
||||
# `supervise: false` to skip the gateway.
|
||||
supervise: bool = True
|
||||
# Guest-local container engine (issue #392). Not a host-daemon grant:
|
||||
# backends implement it inside the bottle or reject it. Gated because it
|
||||
# costs image weight, a resident service, and relaxed guest device modes
|
||||
# that the majority of bottles never need.
|
||||
nested_containers: bool = False
|
||||
# Source fields retained across extends/runtime composition. Boolean
|
||||
# defaults otherwise erase the distinction between "omitted" and an
|
||||
# explicitly declared value (especially False).
|
||||
declared_fields: frozenset[str] = frozenset()
|
||||
|
||||
@classmethod
|
||||
def from_dict(cls, name: str, raw: object) -> "ManifestBottle":
|
||||
@@ -123,7 +132,16 @@ class ManifestBottle:
|
||||
f"(was {type(supervise_raw).__name__})"
|
||||
)
|
||||
|
||||
nested_raw = d.get("nested_containers", False)
|
||||
if not isinstance(nested_raw, bool):
|
||||
raise ManifestError(
|
||||
f"bottle '{name}' nested_containers must be a boolean "
|
||||
f"(was {type(nested_raw).__name__})"
|
||||
)
|
||||
|
||||
return cls(
|
||||
env=env, agent_provider=agent_provider, git=git,
|
||||
git_user=git_user, egress=egress, supervise=supervise_raw,
|
||||
nested_containers=nested_raw,
|
||||
declared_fields=frozenset(d),
|
||||
)
|
||||
|
||||
@@ -71,6 +71,8 @@ class ManifestEgressRoute:
|
||||
OutboundDetectors: tuple[str, ...] | None = None
|
||||
InboundDetectors: tuple[str, ...] | None = None
|
||||
OutboundOnMatch: str = ""
|
||||
PreserveAuth: bool = False
|
||||
Inspect: bool = True
|
||||
|
||||
@classmethod
|
||||
def from_dict(cls, bottle_name: str, idx: int, raw: object) -> "ManifestEgressRoute":
|
||||
@@ -80,9 +82,17 @@ class ManifestEgressRoute:
|
||||
if not isinstance(host, str) or not host:
|
||||
raise ManifestError(f"{label} missing required string field 'host'")
|
||||
|
||||
inspect_raw = d.get("inspect", {})
|
||||
if inspect_raw is False:
|
||||
inspect = False
|
||||
inspect_d: dict[str, object] = {}
|
||||
else:
|
||||
inspect = True
|
||||
inspect_d = as_json_object(inspect_raw, f"{label} inspect")
|
||||
|
||||
# --- matches ---
|
||||
matches: tuple[ManifestMatchEntry, ...] = ()
|
||||
matches_raw = d.get("matches")
|
||||
matches_raw = inspect_d.get("matches")
|
||||
if matches_raw is not None:
|
||||
if not isinstance(matches_raw, list):
|
||||
raise ManifestError(
|
||||
@@ -100,9 +110,9 @@ class ManifestEgressRoute:
|
||||
# --- auth ---
|
||||
auth_scheme = ""
|
||||
token_ref = ""
|
||||
if "auth" in d:
|
||||
auth_raw = d.get("auth")
|
||||
auth_d = as_json_object(auth_raw, f"{label} auth")
|
||||
if "auth" in inspect_d:
|
||||
auth_raw = inspect_d.get("auth")
|
||||
auth_d = as_json_object(auth_raw, f"{label} inspect.auth")
|
||||
if not auth_d:
|
||||
raise ManifestError(
|
||||
f"{label} auth is empty ({{}}); omit the 'auth' key "
|
||||
@@ -162,19 +172,19 @@ class ManifestEgressRoute:
|
||||
f"the 'role' field is reserved for future use"
|
||||
)
|
||||
|
||||
# --- dlp ---
|
||||
# --- DLP settings (inspection-only) ---
|
||||
outbound_detectors: tuple[str, ...] | None = None
|
||||
inbound_detectors: tuple[str, ...] | None = None
|
||||
outbound_on_match = ""
|
||||
if "dlp" in d:
|
||||
outbound_detectors, inbound_detectors, outbound_on_match = _parse_dlp_block(
|
||||
label, d.get("dlp"),
|
||||
if inspect:
|
||||
outbound_detectors, inbound_detectors, outbound_on_match = _parse_inspect_block(
|
||||
label, inspect_d,
|
||||
)
|
||||
|
||||
# --- git-over-HTTPS policy ---
|
||||
git_fetch = False
|
||||
if "git" in d:
|
||||
git_d = as_json_object(d.get("git"), f"{label} git")
|
||||
if "git" in inspect_d:
|
||||
git_d = as_json_object(inspect_d.get("git"), f"{label} inspect.git")
|
||||
raw_fetch = git_d.get("fetch", False)
|
||||
if isinstance(raw_fetch, bool):
|
||||
git_fetch = raw_fetch
|
||||
@@ -190,11 +200,33 @@ class ManifestEgressRoute:
|
||||
f"only 'fetch' is accepted"
|
||||
)
|
||||
|
||||
# --- preserve_auth ---
|
||||
preserve_auth = False
|
||||
if "preserve_auth" in inspect_d:
|
||||
raw_preserve_auth = inspect_d.get("preserve_auth")
|
||||
if not isinstance(raw_preserve_auth, bool):
|
||||
raise ManifestError(
|
||||
f"{label} preserve_auth must be a boolean "
|
||||
f"(was {type(raw_preserve_auth).__name__})"
|
||||
)
|
||||
preserve_auth = raw_preserve_auth
|
||||
|
||||
for k in inspect_d:
|
||||
if k not in (
|
||||
"matches", "auth", "git", "preserve_auth",
|
||||
"outbound_detectors", "inbound_detectors", "outbound_on_match",
|
||||
):
|
||||
raise ManifestError(
|
||||
f"{label} inspect has unknown key {k!r}; accepted keys are "
|
||||
f"'matches', 'auth', 'git', 'preserve_auth', "
|
||||
f"'outbound_detectors', 'inbound_detectors', "
|
||||
f"'outbound_on_match'"
|
||||
)
|
||||
for k in d:
|
||||
if k not in ("host", "matches", "auth", "role", "dlp", "git"):
|
||||
if k not in ("host", "role", "inspect"):
|
||||
raise ManifestError(
|
||||
f"{label} has unknown key {k!r}; accepted keys are "
|
||||
f"'host', 'matches', 'auth', 'role', 'dlp', 'git'"
|
||||
f"'host', 'role', and 'inspect'"
|
||||
)
|
||||
|
||||
return cls(
|
||||
@@ -207,6 +239,8 @@ class ManifestEgressRoute:
|
||||
OutboundDetectors=outbound_detectors,
|
||||
InboundDetectors=inbound_detectors,
|
||||
OutboundOnMatch=outbound_on_match,
|
||||
PreserveAuth=preserve_auth,
|
||||
Inspect=inspect,
|
||||
)
|
||||
|
||||
|
||||
@@ -326,12 +360,13 @@ def _parse_header_match(
|
||||
return ManifestHeaderMatch(Name=name, Value=value, Type=htype)
|
||||
|
||||
|
||||
def _parse_dlp_block(
|
||||
def _parse_inspect_block(
|
||||
route_label: str,
|
||||
raw: object,
|
||||
inspect: dict[str, object],
|
||||
) -> tuple[tuple[str, ...] | None, tuple[str, ...] | None, str]:
|
||||
label = f"{route_label} dlp"
|
||||
d = as_json_object(raw, label)
|
||||
"""Parse DLP settings from an inspected route."""
|
||||
label = f"{route_label} inspect"
|
||||
d = inspect
|
||||
|
||||
def _parse_field(
|
||||
field: str,
|
||||
@@ -374,13 +409,6 @@ def _parse_dlp_block(
|
||||
)
|
||||
on_match = on_match_raw
|
||||
|
||||
for k in d:
|
||||
if k not in ("outbound_detectors", "inbound_detectors", "outbound_on_match"):
|
||||
raise ManifestError(
|
||||
f"{label} has unknown key {k!r}; accepted keys are "
|
||||
f"'outbound_detectors', 'inbound_detectors', "
|
||||
f"'outbound_on_match'"
|
||||
)
|
||||
return outbound, inbound, on_match
|
||||
|
||||
|
||||
|
||||
@@ -8,6 +8,17 @@ from .manifest_git import ManifestGitUser, parse_git_gate_config
|
||||
from .manifest_util import ManifestError, as_json_object
|
||||
|
||||
|
||||
def _overlay_declared_bool(
|
||||
base: ManifestBottle,
|
||||
override: ManifestBottle,
|
||||
field: str,
|
||||
) -> bool:
|
||||
"""Overlay a defaulted boolean only when override declared it."""
|
||||
value = getattr(override if field in override.declared_fields else base, field)
|
||||
assert isinstance(value, bool)
|
||||
return value
|
||||
|
||||
|
||||
def merge_bottles_runtime(bottles: "list[ManifestBottle]") -> "ManifestBottle":
|
||||
"""Merge an ordered list of pre-resolved ManifestBottle objects.
|
||||
|
||||
@@ -15,7 +26,13 @@ def merge_bottles_runtime(bottles: "list[ManifestBottle]") -> "ManifestBottle":
|
||||
the same field-merge rules as the file-based extends machinery:
|
||||
env: dict merge, later wins; git_user: per-field overlay, later
|
||||
wins on non-empty; git (repos): union by name, later wins; egress
|
||||
routes: concatenate; agent_provider, supervise: later replaces.
|
||||
routes: concatenate; agent_provider, supervise, nested_containers:
|
||||
later replaces (presence-aware).
|
||||
|
||||
Defaulted booleans use presence-aware replacement: if the later bottle
|
||||
was loaded from a source that explicitly declared the key, its value
|
||||
wins (so an explicit `false` can override an earlier `true`). If the
|
||||
later bottle never mentioned the key, the earlier value is preserved.
|
||||
"""
|
||||
if not bottles:
|
||||
raise ValueError("merge_bottles_runtime requires at least one bottle")
|
||||
@@ -53,7 +70,11 @@ def _merge_two_bottles_runtime(base: "ManifestBottle", override: "ManifestBottle
|
||||
git=merged_git,
|
||||
git_user=merged_git_user,
|
||||
egress=merged_egress,
|
||||
supervise=override.supervise,
|
||||
supervise=_overlay_declared_bool(base, override, "supervise"),
|
||||
nested_containers=_overlay_declared_bool(
|
||||
base, override, "nested_containers"
|
||||
),
|
||||
declared_fields=base.declared_fields | override.declared_fields,
|
||||
)
|
||||
|
||||
|
||||
@@ -205,7 +226,11 @@ def _fold_two_bottles(
|
||||
git=merged_git,
|
||||
git_user=merged_git_user,
|
||||
egress=merged_egress,
|
||||
supervise=later.supervise,
|
||||
supervise=_overlay_declared_bool(earlier, later, "supervise"),
|
||||
nested_containers=_overlay_declared_bool(
|
||||
earlier, later, "nested_containers"
|
||||
),
|
||||
declared_fields=earlier.declared_fields | later.declared_fields,
|
||||
), merged_repos_raw
|
||||
|
||||
|
||||
@@ -263,8 +288,9 @@ def _merge_bottles(
|
||||
if "agent_provider" in child_raw
|
||||
else parent.agent_provider
|
||||
)
|
||||
merged_supervise = (
|
||||
child.supervise if "supervise" in child_raw else parent.supervise
|
||||
merged_supervise = _overlay_declared_bool(parent, child, "supervise")
|
||||
merged_nested_containers = _overlay_declared_bool(
|
||||
parent, child, "nested_containers"
|
||||
)
|
||||
validate_egress_routes(name, merged_egress.routes)
|
||||
|
||||
@@ -275,6 +301,8 @@ def _merge_bottles(
|
||||
git_user=merged_git_user,
|
||||
egress=merged_egress,
|
||||
supervise=merged_supervise,
|
||||
nested_containers=merged_nested_containers,
|
||||
declared_fields=parent.declared_fields | child.declared_fields,
|
||||
)
|
||||
|
||||
|
||||
|
||||
@@ -16,7 +16,10 @@ _FILENAME_RX = re.compile(r"^[a-z][a-z0-9-]*$")
|
||||
# sets dies with a "did you mean" pointer: typos should not silently
|
||||
# ghost into an empty config.
|
||||
BOTTLE_KEYS = frozenset(
|
||||
{"env", "extends", "agent_provider", "git-gate", "egress", "supervise"}
|
||||
{
|
||||
"env", "extends", "agent_provider", "git-gate", "egress",
|
||||
"supervise", "nested_containers",
|
||||
}
|
||||
)
|
||||
AGENT_KEYS_REQUIRED: frozenset[str] = frozenset()
|
||||
AGENT_KEYS_OPTIONAL = frozenset({"bottle", "skills", "git-gate"})
|
||||
|
||||
@@ -15,6 +15,7 @@ from __future__ import annotations
|
||||
import json
|
||||
import urllib.error
|
||||
import urllib.request
|
||||
from collections.abc import Iterable
|
||||
from dataclasses import dataclass
|
||||
|
||||
from ..paths import host_control_plane_token
|
||||
@@ -40,10 +41,13 @@ class OrchestratorClientError(RuntimeError):
|
||||
@dataclass(frozen=True)
|
||||
class RegisteredBottle:
|
||||
"""What `POST /bottles` returns: the minted bottle id and the per-bottle
|
||||
identity token the agent presents for app-layer attribution."""
|
||||
identity token the agent presents for app-layer attribution. `env_var_secret`
|
||||
is set by the caller (not from the server response) and carries the
|
||||
encryption key so it can be injected into the agent container's env."""
|
||||
|
||||
bottle_id: str
|
||||
identity_token: str
|
||||
env_var_secret: str = ""
|
||||
|
||||
|
||||
class OrchestratorClient:
|
||||
@@ -119,17 +123,21 @@ class OrchestratorClient:
|
||||
metadata: str = "",
|
||||
policy: str = "",
|
||||
tokens: dict[str, str] | None = None,
|
||||
env_var_secret: str = "",
|
||||
) -> RegisteredBottle:
|
||||
"""Register a bottle and broker its launch (`POST /bottles`). `tokens`
|
||||
are the per-bottle egress auth values (env_name -> value) the
|
||||
orchestrator holds in memory for the gateway to inject. Returns the
|
||||
minted id + identity token."""
|
||||
orchestrator holds in memory for the gateway to inject. When
|
||||
*env_var_secret* is provided, the orchestrator also encrypts the token
|
||||
values and stores them in ``bottled_agent_secrets`` for restart
|
||||
recovery. Returns the minted id + identity token."""
|
||||
payload = self._ok("POST", "/bottles", {
|
||||
"source_ip": source_ip,
|
||||
"image_ref": image_ref,
|
||||
"metadata": metadata,
|
||||
"policy": policy,
|
||||
"tokens": tokens or {},
|
||||
"env_var_secret": env_var_secret,
|
||||
})
|
||||
bottle_id = payload.get("bottle_id")
|
||||
token = payload.get("identity_token")
|
||||
@@ -137,6 +145,24 @@ class OrchestratorClient:
|
||||
raise OrchestratorClientError("register: response missing bottle_id/identity_token")
|
||||
return RegisteredBottle(bottle_id=bottle_id, identity_token=token)
|
||||
|
||||
def reprovision_gateway(self, bottle_id: str, env_var_secret: str) -> bool:
|
||||
"""Re-inject a bottle's egress tokens from its ENV_VAR_SECRET
|
||||
(`POST /bottles/<id>/reprovision_gateway`). Returns True when the
|
||||
orchestrator successfully decrypted and restored the tokens, False
|
||||
when it had no stored secrets for this bottle (404)."""
|
||||
status, _ = self._request(
|
||||
"POST",
|
||||
f"/bottles/{bottle_id}/reprovision_gateway",
|
||||
{"env_var_secret": env_var_secret},
|
||||
)
|
||||
if status == 404:
|
||||
return False
|
||||
if not 200 <= status < 300:
|
||||
raise OrchestratorClientError(
|
||||
f"reprovision_gateway {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."""
|
||||
@@ -147,6 +173,20 @@ class OrchestratorClient:
|
||||
raise OrchestratorClientError(f"teardown {bottle_id}: HTTP {status}")
|
||||
return True
|
||||
|
||||
def reconcile(
|
||||
self, live_source_ips: Iterable[str], *, grace_seconds: float | None = None,
|
||||
) -> list[str]:
|
||||
"""Drop registry rows for bottles that are no longer running
|
||||
(`POST /reconcile`), returning the reaped bottle ids. `live_source_ips`
|
||||
is the caller's enumeration of its live bottles — the orchestrator
|
||||
can't see the backend from inside the infra container."""
|
||||
body: dict[str, object] = {"live_source_ips": list(live_source_ips)}
|
||||
if grace_seconds is not None:
|
||||
body["grace_seconds"] = grace_seconds
|
||||
payload = self._ok("POST", "/reconcile", body)
|
||||
reaped = payload.get("reaped")
|
||||
return [r for r in reaped if isinstance(r, str)] if isinstance(reaped, list) else []
|
||||
|
||||
def set_policy(self, bottle_id: str, policy: str) -> bool:
|
||||
"""Live-reload a bottle's policy (`PUT /bottles/<id>/policy`). False on
|
||||
404 (unknown bottle)."""
|
||||
|
||||
@@ -0,0 +1,107 @@
|
||||
"""Per-host orchestrator configuration store (settings in bot-bottle.db).
|
||||
|
||||
Co-tenants the shared `bot-bottle.db` via the `DbStore` framework. Settings
|
||||
are readable by the host launch path directly (no HTTP round-trip to the
|
||||
orchestrator), so they take effect even before the orchestrator is reachable.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import os
|
||||
import sqlite3
|
||||
from pathlib import Path
|
||||
|
||||
from ..db_store import DbStore
|
||||
from ..migrations import TableMigrations
|
||||
from ..paths import host_db_path
|
||||
|
||||
TEARDOWN_TIMEOUT_ENV = "BOT_BOTTLE_ORCHESTRATOR_TEARDOWN_TIMEOUT_SECONDS"
|
||||
DEFAULT_TEARDOWN_TIMEOUT_SECONDS = 30.0
|
||||
|
||||
_MIGRATIONS = TableMigrations(
|
||||
"orchestrator_config",
|
||||
[
|
||||
"""
|
||||
CREATE TABLE IF NOT EXISTS orchestrator_config (
|
||||
id INTEGER PRIMARY KEY CHECK (id = 1),
|
||||
teardown_timeout_seconds REAL
|
||||
)
|
||||
""",
|
||||
],
|
||||
)
|
||||
|
||||
|
||||
class OrchestratorConfigStore(DbStore):
|
||||
"""Orchestrator settings in the shared host DB."""
|
||||
|
||||
def __init__(self, db_path: Path | None = None) -> None:
|
||||
super().__init__(db_path or host_db_path(), _MIGRATIONS)
|
||||
|
||||
def _connect(self) -> sqlite3.Connection:
|
||||
conn = super()._connect()
|
||||
conn.execute("PRAGMA busy_timeout=5000")
|
||||
return conn
|
||||
|
||||
def get_teardown_timeout_seconds(self) -> float | None:
|
||||
"""Return the configured teardown timeout, or None if not set."""
|
||||
try:
|
||||
with self._connection() as conn:
|
||||
row = conn.execute(
|
||||
"SELECT teardown_timeout_seconds FROM orchestrator_config WHERE id = 1"
|
||||
).fetchone()
|
||||
except sqlite3.OperationalError:
|
||||
return None
|
||||
return row["teardown_timeout_seconds"] if row else None
|
||||
|
||||
def set_teardown_timeout_seconds(self, value: float) -> None:
|
||||
"""Persist the teardown timeout."""
|
||||
with self._connection() as conn:
|
||||
conn.execute(
|
||||
"INSERT OR REPLACE INTO orchestrator_config"
|
||||
" (id, teardown_timeout_seconds) VALUES (1, ?)",
|
||||
(value,),
|
||||
)
|
||||
self._chmod()
|
||||
|
||||
def delete_teardown_timeout_seconds(self) -> bool:
|
||||
"""Clear the stored teardown timeout. Returns True if a value existed."""
|
||||
with self._connection() as conn:
|
||||
cur = conn.execute(
|
||||
"UPDATE orchestrator_config SET teardown_timeout_seconds = NULL"
|
||||
" WHERE id = 1 AND teardown_timeout_seconds IS NOT NULL"
|
||||
)
|
||||
return cur.rowcount > 0
|
||||
|
||||
|
||||
def resolve_teardown_timeout(db_path: Path | None = None) -> float:
|
||||
"""Return the teardown timeout to use, in priority order:
|
||||
|
||||
1. ``BOT_BOTTLE_ORCHESTRATOR_TEARDOWN_TIMEOUT_SECONDS`` env var
|
||||
2. ``teardown_timeout_seconds`` in the orchestrator config DB
|
||||
3. ``DEFAULT_TEARDOWN_TIMEOUT_SECONDS`` (30 s)
|
||||
"""
|
||||
raw = os.environ.get(TEARDOWN_TIMEOUT_ENV, "").strip()
|
||||
if raw:
|
||||
try:
|
||||
value = float(raw)
|
||||
if value > 0:
|
||||
return value
|
||||
except ValueError:
|
||||
pass
|
||||
|
||||
store = OrchestratorConfigStore(db_path)
|
||||
if not store.is_migrated():
|
||||
store.migrate()
|
||||
db_value = store.get_teardown_timeout_seconds()
|
||||
if db_value is not None and db_value > 0:
|
||||
return db_value
|
||||
|
||||
return DEFAULT_TEARDOWN_TIMEOUT_SECONDS
|
||||
|
||||
|
||||
__all__ = [
|
||||
"OrchestratorConfigStore",
|
||||
"resolve_teardown_timeout",
|
||||
"TEARDOWN_TIMEOUT_ENV",
|
||||
"DEFAULT_TEARDOWN_TIMEOUT_SECONDS",
|
||||
]
|
||||
@@ -9,10 +9,17 @@ vsock / unix-socket portability caveats):
|
||||
GET /bottles -> 200 {"bottles": [ <redacted record>, ...]}
|
||||
POST /bottles -> 201 {"bottle_id","identity_token"} (launch)
|
||||
body: {"source_ip", ["image_ref"],
|
||||
["metadata"], ["policy"]}
|
||||
["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"}
|
||||
@@ -113,12 +120,14 @@ def dispatch( # pylint: disable=too-many-return-statements,too-many-branches
|
||||
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}
|
||||
|
||||
@@ -135,12 +144,50 @@ def dispatch( # pylint: disable=too-many-return-statements,too-many-branches
|
||||
return 200, {"updated": True}
|
||||
return 404, {"error": "no such bottle"}
|
||||
|
||||
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"}
|
||||
|
||||
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)
|
||||
|
||||
@@ -27,6 +27,7 @@ from ..paths import (
|
||||
CONTROL_PLANE_TOKEN_ENV,
|
||||
host_control_plane_token,
|
||||
host_db_path,
|
||||
host_gateway_ca_dir,
|
||||
)
|
||||
from ..supervise import DB_PATH_IN_CONTAINER
|
||||
|
||||
@@ -48,14 +49,23 @@ GATEWAY_LABEL = "bot-bottle-orch-gateway=1"
|
||||
# the source IP the gateway attributes by is the address on this network.
|
||||
GATEWAY_NETWORK = "bot-bottle-gateway"
|
||||
|
||||
# mitmproxy's CA dir in the bundle. A persistent named volume here keeps the
|
||||
# gateway's self-generated CA STABLE across container recreation — every agent
|
||||
# installs this one CA to trust the shared gateway's TLS interception, so it
|
||||
# must not rotate when the gateway restarts.
|
||||
# mitmproxy's CA dir in the bundle. The host's gateway-CA dir (see
|
||||
# `host_gateway_ca_dir`) is bind-mounted here so the gateway's self-generated
|
||||
# CA stays STABLE across container recreation — every agent installs this one
|
||||
# CA to trust the shared gateway's TLS interception, so it must not rotate when
|
||||
# the gateway restarts. A host bind-mount rather than a named volume: a named
|
||||
# volume is silently wiped by `docker volume prune`, minting a fresh CA that
|
||||
# breaks every running bottle (issue #450).
|
||||
MITMPROXY_HOME = "/home/mitmproxy/.mitmproxy"
|
||||
GATEWAY_CA_VOLUME = "bot-bottle-gateway-mitmproxy"
|
||||
GATEWAY_CA_CERT = f"{MITMPROXY_HOME}/mitmproxy-ca-cert.pem"
|
||||
|
||||
# The CA material mitmproxy writes into its confdir. mitmproxy reuses these on
|
||||
# startup when present and generates them only on first run, so persisting them
|
||||
# is what makes the CA stable; deleting them (see `rotate_gateway_ca`) forces a
|
||||
# fresh CA on the next start. `mitmproxy-ca.pem` (cert + private key) is the
|
||||
# signing identity; the rest are derived encodings agents/clients consume.
|
||||
GATEWAY_CA_GLOB = "mitmproxy-ca*"
|
||||
|
||||
# The gateway data-plane image + its Dockerfile. Kept as a local constant
|
||||
# rather than imported from the backend layer, which would drag
|
||||
# the whole backend layer into the lean orchestrator (see #359); unify when
|
||||
@@ -73,6 +83,26 @@ def _host_db_dir() -> str:
|
||||
return str(db_dir)
|
||||
|
||||
|
||||
def rotate_gateway_ca(ca_dir: Path | None = None) -> list[Path]:
|
||||
"""Delete the persisted mitmproxy CA so the next gateway start mints a
|
||||
fresh one — the explicit, deliberate CA-rollover path (issue #450).
|
||||
|
||||
Persistence keeps the CA stable across restarts precisely because mitmproxy
|
||||
reuses the on-disk CA; rotation is therefore just removing that material.
|
||||
Returns the files removed (empty when there was no CA yet); idempotent.
|
||||
|
||||
This only clears the on-disk CA. It does NOT stop the running gateway (whose
|
||||
mitmproxy still holds the old CA in memory) or re-provision agents — the
|
||||
caller recreates the gateway to mint the new CA and re-attaches bottles.
|
||||
`rotate-ca` on the orchestrator CLI wires those steps together."""
|
||||
ca_dir = ca_dir if ca_dir is not None else host_gateway_ca_dir()
|
||||
removed: list[Path] = []
|
||||
for path in sorted(ca_dir.glob(GATEWAY_CA_GLOB)):
|
||||
path.unlink()
|
||||
removed.append(path)
|
||||
return removed
|
||||
|
||||
|
||||
class GatewayError(Exception):
|
||||
"""The shared gateway failed to build/start/stop (non-zero `docker` exit)."""
|
||||
|
||||
@@ -221,9 +251,10 @@ class DockerGateway(Gateway):
|
||||
"--name", self.name,
|
||||
"--label", GATEWAY_LABEL,
|
||||
"--network", self.network,
|
||||
# Persist the self-generated CA so it survives restarts (agents
|
||||
# trust it) — see GATEWAY_CA_VOLUME.
|
||||
"--volume", f"{GATEWAY_CA_VOLUME}:{MITMPROXY_HOME}",
|
||||
# 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}",
|
||||
# Share the one host DB: the supervise daemon queues proposals
|
||||
# into the same file the orchestrator (and the operator, over
|
||||
# HTTP) reads — no second, disconnected DB in the container.
|
||||
@@ -272,7 +303,7 @@ class DockerGateway(Gateway):
|
||||
|
||||
|
||||
__all__ = [
|
||||
"Gateway", "DockerGateway", "GatewayError",
|
||||
"Gateway", "DockerGateway", "GatewayError", "rotate_gateway_ca",
|
||||
"GATEWAY_NAME", "GATEWAY_LABEL", "GATEWAY_IMAGE", "GATEWAY_NETWORK",
|
||||
"GATEWAY_CA_VOLUME", "GATEWAY_CA_CERT",
|
||||
"GATEWAY_CA_CERT", "GATEWAY_CA_GLOB",
|
||||
]
|
||||
|
||||
@@ -23,10 +23,16 @@ from pathlib import Path
|
||||
|
||||
from .. import log
|
||||
from ..docker_cmd import run_docker
|
||||
from ..paths import CONTROL_PLANE_TOKEN_ENV, bot_bottle_root, host_control_plane_token
|
||||
from ..paths import (
|
||||
CONTROL_PLANE_TOKEN_ENV,
|
||||
bot_bottle_root,
|
||||
host_control_plane_token,
|
||||
host_gateway_ca_dir,
|
||||
)
|
||||
from ..supervise import DB_PATH_IN_CONTAINER
|
||||
from .gateway import (
|
||||
GATEWAY_CA_VOLUME,
|
||||
GATEWAY_DOCKERFILE,
|
||||
GATEWAY_IMAGE,
|
||||
GATEWAY_NETWORK,
|
||||
GatewayError,
|
||||
MITMPROXY_HOME,
|
||||
@@ -160,9 +166,10 @@ class OrchestratorService:
|
||||
)
|
||||
|
||||
def _build_images(self) -> None:
|
||||
"""Build the orchestrator image (build intermediate), then the infra
|
||||
image. Both are cache-aware: a no-op when nothing changed."""
|
||||
"""Build the gateway base, the orchestrator intermediate, then the
|
||||
infra image. All are cache-aware: a no-op when nothing changed."""
|
||||
for tag, dockerfile in (
|
||||
(GATEWAY_IMAGE, GATEWAY_DOCKERFILE),
|
||||
(ORCHESTRATOR_IMAGE, ORCHESTRATOR_DOCKERFILE),
|
||||
(self.image, INFRA_DOCKERFILE),
|
||||
):
|
||||
@@ -188,9 +195,13 @@ class OrchestratorService:
|
||||
"--label", f"{INFRA_SOURCE_HASH_LABEL}={current_hash}",
|
||||
"--network", self.network,
|
||||
# Host CLI reaches the control plane here (loopback only).
|
||||
"--publish", f"127.0.0.1:{self.port}:{self.port}",
|
||||
# Persist the mitmproxy CA so it survives container recreation.
|
||||
"--volume", f"{GATEWAY_CA_VOLUME}:{MITMPROXY_HOME}",
|
||||
# gateway_init always starts the orchestrator on DEFAULT_PORT (8099)
|
||||
# inside the container; self.port is the host-side published port.
|
||||
"--publish", f"127.0.0.1:{self.port}:{DEFAULT_PORT}",
|
||||
# Persist the mitmproxy CA on the host so it survives container
|
||||
# recreation AND docker volume pruning (issue #450): every agent
|
||||
# trusts this one CA, so a fresh one would break all running bottles.
|
||||
"--volume", f"{host_gateway_ca_dir()}:{MITMPROXY_HOME}",
|
||||
# Shared supervise DB (same file the operator reads over HTTP).
|
||||
"--volume", f"{_host_db_dir()}:{_SUPERVISE_DB_DIR_IN_CONTAINER}",
|
||||
"--env", f"SUPERVISE_DB_PATH={DB_PATH_IN_CONTAINER}",
|
||||
@@ -206,8 +217,9 @@ class OrchestratorService:
|
||||
# Control-plane secret: required by the orchestrator (to enforce)
|
||||
# and by the gateway daemons (to present on /resolve calls).
|
||||
"--env", CONTROL_PLANE_TOKEN_ENV,
|
||||
# Gateway daemons reach the orchestrator over loopback.
|
||||
"--env", f"BOT_BOTTLE_ORCHESTRATOR_URL=http://127.0.0.1:{self.port}",
|
||||
# Gateway daemons reach the orchestrator over loopback at its
|
||||
# fixed internal port (DEFAULT_PORT), independent of self.port.
|
||||
"--env", f"BOT_BOTTLE_ORCHESTRATOR_URL=http://127.0.0.1:{DEFAULT_PORT}",
|
||||
# Opt the orchestrator into gateway_init's supervise tree.
|
||||
"--env", f"BOT_BOTTLE_GATEWAY_DAEMONS={_INFRA_DAEMONS}",
|
||||
self.image,
|
||||
|
||||
@@ -32,6 +32,7 @@ import hmac
|
||||
import secrets
|
||||
import sqlite3
|
||||
import time
|
||||
from collections.abc import Iterable
|
||||
from dataclasses import dataclass
|
||||
from pathlib import Path
|
||||
|
||||
@@ -42,6 +43,12 @@ from ..paths import host_db_path
|
||||
# 256 bits of urandom, URL-safe — unguessable per-bottle identity token.
|
||||
IDENTITY_TOKEN_BYTES = 32
|
||||
|
||||
# How recently a row must have been registered to be exempt from
|
||||
# `reap_absent`. Covers the window between `container run` and the address
|
||||
# becoming visible to another launch's enumeration, so reconciliation never
|
||||
# reaps a bottle that is still coming up.
|
||||
DEFAULT_REAP_GRACE_SECONDS = 120.0
|
||||
|
||||
|
||||
def new_identity_token() -> str:
|
||||
"""A fresh per-bottle identity token (PRD 0070 attribution defence)."""
|
||||
@@ -106,6 +113,22 @@ _MIGRATIONS = TableMigrations(
|
||||
# egress allowlist / routes / git config selected by source IP. The
|
||||
# multi-tenant gateway resolves it per request via `attribute`.
|
||||
"ALTER TABLE orchestrator_bottles ADD COLUMN policy TEXT NOT NULL DEFAULT ''",
|
||||
# v4 — per-bottle encrypted egress secrets (PRD prd-new-secret-provider).
|
||||
# One row per env-var: key (env-var name) is plaintext for auditing;
|
||||
# value is the encrypted token string. The encryption key (ENV_VAR_SECRET)
|
||||
# lives only in the agent's environment — a row alone cannot recover the
|
||||
# credential.
|
||||
"""
|
||||
CREATE TABLE IF NOT EXISTS bottled_agent_secrets (
|
||||
bottled_agent_id TEXT NOT NULL,
|
||||
key TEXT NOT NULL,
|
||||
value TEXT NOT NULL,
|
||||
type TEXT NOT NULL DEFAULT 'injected_env_var'
|
||||
)
|
||||
""",
|
||||
# v5 — index for fast per-bottle lookups and bulk DELETE on teardown.
|
||||
"CREATE INDEX IF NOT EXISTS idx_bottled_agent_secrets_id "
|
||||
"ON bottled_agent_secrets (bottled_agent_id, type)",
|
||||
],
|
||||
)
|
||||
|
||||
@@ -225,6 +248,70 @@ class RegistryStore(DbStore):
|
||||
).fetchall()
|
||||
return [_row_to_record(r) for r in rows]
|
||||
|
||||
def reap_absent(
|
||||
self,
|
||||
live_source_ips: Iterable[str],
|
||||
*,
|
||||
grace_seconds: float = DEFAULT_REAP_GRACE_SECONDS,
|
||||
now: float | None = None,
|
||||
) -> list[BottleRecord]:
|
||||
"""Delete active rows whose source IP is not held by a live bottle.
|
||||
|
||||
A row only ever leaves the registry two ways: an explicit
|
||||
`teardown_bottle` (the launcher's cleanup callback) or the supersede
|
||||
sweep in `register`. Neither runs when the launching CLI dies hard —
|
||||
SIGKILL, a closed terminal, a host sleep/crash — so the row outlives
|
||||
its container. That orphan is not inert: source IPs are recycled by
|
||||
the backend's DHCP, and `by_source_ip` fail-closes on ambiguity, so a
|
||||
leftover row at a reused address can brick the *next* bottle that
|
||||
lands on it (no policy resolved -> every host denied, reported to the
|
||||
agent as "not in the allowlist"). Reconciling against the live set at
|
||||
launch keeps the registry from accumulating those landmines.
|
||||
|
||||
Restores the invariant the data plane needs: **at most one active row
|
||||
per live address, and none at all for a dead one.** Two cases, because
|
||||
a dead bottle's address may already have been handed to a live one:
|
||||
|
||||
* no live bottle holds the address — every row there is an orphan;
|
||||
* a live bottle holds it but several rows claim it — the newest
|
||||
registration is authoritative and the rest are orphans, the same
|
||||
rule `register`'s same-IP supersede sweep applies. Without this
|
||||
second case a recycled address stays ambiguous, which is exactly
|
||||
the state that resolves no policy.
|
||||
|
||||
`grace_seconds` protects an in-flight launch: registration happens
|
||||
moments after `container run`, and a concurrent launch's address may
|
||||
not be visible to the caller's enumeration yet. Rows younger than the
|
||||
grace window are never reaped, so reconciliation can't race a bottle
|
||||
that is still coming up. Returns the deleted records."""
|
||||
live = {ip for ip in live_source_ips if ip}
|
||||
cutoff = (time.time() if now is None else now) - grace_seconds
|
||||
with self._connection() as conn:
|
||||
rows = conn.execute(
|
||||
"SELECT * FROM orchestrator_bottles WHERE state = 'active'",
|
||||
).fetchall()
|
||||
by_ip: dict[str, list[BottleRecord]] = {}
|
||||
for row in rows:
|
||||
rec = _row_to_record(row)
|
||||
by_ip.setdefault(rec.source_ip, []).append(rec)
|
||||
candidates: list[BottleRecord] = []
|
||||
for ip, recs in by_ip.items():
|
||||
if ip not in live:
|
||||
candidates.extend(recs)
|
||||
continue
|
||||
# Keep the newest claim on a live address; supersede the rest.
|
||||
recs.sort(key=lambda r: r.created_at)
|
||||
candidates.extend(recs[:-1])
|
||||
doomed = [r for r in candidates if r.created_at <= cutoff]
|
||||
for rec in doomed:
|
||||
conn.execute(
|
||||
"DELETE FROM orchestrator_bottles WHERE bottle_id = ?",
|
||||
(rec.bottle_id,),
|
||||
)
|
||||
if doomed:
|
||||
self._chmod()
|
||||
return doomed
|
||||
|
||||
def by_source_ip(self, source_ip: str) -> BottleRecord | None:
|
||||
"""Network-layer attribution: the single active bottle at this source
|
||||
IP, or None if unknown or ambiguous (more than one — a
|
||||
@@ -255,6 +342,57 @@ class RegistryStore(DbStore):
|
||||
return None
|
||||
return rec
|
||||
|
||||
# --- encrypted egress secret store ------------------------------------
|
||||
|
||||
def store_agent_secrets(
|
||||
self,
|
||||
bottle_id: str,
|
||||
encrypted_values: dict[str, str],
|
||||
secret_type: str = "injected_env_var",
|
||||
) -> None:
|
||||
"""Replace all stored secrets for *bottle_id* with *encrypted_values*
|
||||
(env-var name → encrypted ciphertext). Deletes then re-inserts so a
|
||||
re-registration is always consistent with the current token set."""
|
||||
with self._connection() as conn:
|
||||
conn.execute(
|
||||
"DELETE FROM bottled_agent_secrets "
|
||||
"WHERE bottled_agent_id = ? AND type = ?",
|
||||
(bottle_id, secret_type),
|
||||
)
|
||||
conn.executemany(
|
||||
"INSERT INTO bottled_agent_secrets "
|
||||
"(bottled_agent_id, key, value, type) VALUES (?, ?, ?, ?)",
|
||||
[(bottle_id, k, v, secret_type) for k, v in encrypted_values.items()],
|
||||
)
|
||||
self._chmod()
|
||||
|
||||
def get_agent_secrets(
|
||||
self,
|
||||
bottle_id: str,
|
||||
secret_type: str = "injected_env_var",
|
||||
) -> dict[str, str]:
|
||||
"""Return {env_var_name: encrypted_value} for *bottle_id*, or {} if none."""
|
||||
with self._connection() as conn:
|
||||
rows = conn.execute(
|
||||
"SELECT key, value FROM bottled_agent_secrets "
|
||||
"WHERE bottled_agent_id = ? AND type = ?",
|
||||
(bottle_id, secret_type),
|
||||
).fetchall()
|
||||
return {row[0]: row[1] for row in rows}
|
||||
|
||||
def delete_agent_secrets(
|
||||
self,
|
||||
bottle_id: str,
|
||||
secret_type: str = "injected_env_var",
|
||||
) -> None:
|
||||
"""Remove all stored secrets for *bottle_id* (e.g. on teardown)."""
|
||||
with self._connection() as conn:
|
||||
conn.execute(
|
||||
"DELETE FROM bottled_agent_secrets "
|
||||
"WHERE bottled_agent_id = ? AND type = ?",
|
||||
(bottle_id, secret_type),
|
||||
)
|
||||
|
||||
|
||||
__all__ = [
|
||||
"BottleRecord",
|
||||
@@ -262,4 +400,5 @@ __all__ = [
|
||||
"new_identity_token",
|
||||
"default_db_path",
|
||||
"IDENTITY_TOKEN_BYTES",
|
||||
"DEFAULT_REAP_GRACE_SECONDS",
|
||||
]
|
||||
|
||||
@@ -0,0 +1,35 @@
|
||||
"""Shared host-side join for backend-discovered bottle encryption keys."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
from .client import OrchestratorClient, OrchestratorClientError
|
||||
|
||||
|
||||
def reprovision_bottles(
|
||||
client: OrchestratorClient,
|
||||
secrets_by_source_ip: dict[str, str],
|
||||
) -> int:
|
||||
"""Restore tokens for registered bottles whose backend exposes a key.
|
||||
|
||||
Backends own discovery because containers and microVMs have different
|
||||
enumeration primitives. This helper owns the shared registry join and
|
||||
intentionally tolerates one bad/missing key without blocking a launch.
|
||||
"""
|
||||
restored = 0
|
||||
for bottle in client.list_bottles():
|
||||
bottle_id = bottle.get("bottle_id")
|
||||
source_ip = bottle.get("source_ip")
|
||||
if not isinstance(bottle_id, str) or not isinstance(source_ip, str):
|
||||
continue
|
||||
secret = secrets_by_source_ip.get(source_ip, "").strip()
|
||||
if not secret:
|
||||
continue
|
||||
try:
|
||||
if client.reprovision_gateway(bottle_id, secret):
|
||||
restored += 1
|
||||
except OrchestratorClientError:
|
||||
continue
|
||||
return restored
|
||||
|
||||
|
||||
__all__ = ["reprovision_bottles"]
|
||||
@@ -0,0 +1,62 @@
|
||||
"""Rotate the shared gateway's mitmproxy CA (issue #450).
|
||||
|
||||
python -m bot_bottle.orchestrator.rotate_ca
|
||||
|
||||
A deliberate CA rollover has two halves: drop the *persisted* CA so a fresh one
|
||||
is minted, and drop the *running* gateway so its mitmproxy (which holds the old
|
||||
CA in memory) is replaced. This one-shot command does both:
|
||||
|
||||
1. Delete the persisted CA under the host gateway-CA dir — the next gateway
|
||||
start generates a new one (mitmproxy reuses an existing CA, generates only
|
||||
when absent).
|
||||
2. Force-remove the infra / standalone-gateway containers so the stale
|
||||
in-memory CA is gone; the next bottle launch's idempotent `ensure_running`
|
||||
brings the gateway back up and mints the fresh CA.
|
||||
|
||||
It does NOT re-provision the new CA into already-running bottles — those must be
|
||||
re-attached so they install the new trust anchor. Rotation is thus an explicit,
|
||||
operator-driven action with a brief egress interruption, not an automatic one.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import sys
|
||||
from pathlib import Path
|
||||
|
||||
from ..docker_cmd import run_docker
|
||||
from ..paths import host_gateway_ca_dir
|
||||
from .gateway import GATEWAY_NAME, rotate_gateway_ca
|
||||
from .lifecycle import INFRA_NAME
|
||||
|
||||
# The containers whose mitmproxy would still be serving the old CA from memory:
|
||||
# the consolidated infra container and the standalone per-host gateway.
|
||||
_GATEWAY_CONTAINERS = (INFRA_NAME, GATEWAY_NAME)
|
||||
|
||||
|
||||
def _out(msg: str) -> None:
|
||||
sys.stdout.write(f"rotate-ca: {msg}\n")
|
||||
|
||||
|
||||
def main(argv: list[str] | None = None) -> int:
|
||||
del argv # no flags — a single deliberate action
|
||||
ca_dir: Path = host_gateway_ca_dir()
|
||||
removed = rotate_gateway_ca(ca_dir)
|
||||
if removed:
|
||||
_out(f"removed {len(removed)} CA file(s) from {ca_dir}")
|
||||
else:
|
||||
_out(f"no persisted CA under {ca_dir}; a fresh one is minted on next start")
|
||||
|
||||
# Drop any running gateway so its in-memory (now-stale) CA is replaced on
|
||||
# the next launch. `rm --force` on an absent name is a tolerated no-op.
|
||||
for name in _GATEWAY_CONTAINERS:
|
||||
proc = run_docker(["docker", "rm", "--force", name])
|
||||
if proc.returncode == 0 and proc.stdout.strip():
|
||||
_out(f"removed running container {name}")
|
||||
|
||||
_out("done — the next bottle launch remints the CA; re-attach bottles to "
|
||||
"install the new trust anchor")
|
||||
return 0
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
raise SystemExit(main())
|
||||
@@ -0,0 +1,94 @@
|
||||
"""Symmetric encryption for per-bottle egress secrets (PRD prd-new-secret-provider).
|
||||
|
||||
Each agent receives a random ENV_VAR_SECRET at startup — passed as an env var,
|
||||
never logged or persisted. The host uses this key to encrypt each egress auth
|
||||
token value before writing it to the bottled_agent_secrets table; the DB rows
|
||||
(ciphertext, plaintext env-var name) without the key are insufficient to
|
||||
recover the credentials.
|
||||
|
||||
On orchestrator restart the in-memory token map is lost. The host-side
|
||||
reattachment path reads ENV_VAR_SECRET from the running agent container via
|
||||
``docker exec … printenv ENV_VAR_SECRET`` and posts it to
|
||||
``POST /bottles/<id>/reprovision_gateway``; the orchestrator decrypts the
|
||||
stored rows and re-populates ``_tokens``.
|
||||
|
||||
Encryption scheme: HMAC-SHA256 used as a PRF in CTR mode (stdlib-only,
|
||||
no external deps). Each value is encrypted independently. The output blob is
|
||||
``nonce (16 bytes) || ciphertext`` encoded as URL-safe base64 (no padding).
|
||||
|
||||
keystream_block_i = HMAC-SHA256(key, nonce || i.to_bytes(4, "big"))
|
||||
ciphertext_i = plaintext_i XOR keystream_block_i[:len(plaintext_i)]
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import base64
|
||||
import hashlib
|
||||
import hmac
|
||||
import secrets
|
||||
|
||||
_KEY_BYTES = 32 # 256-bit key from ENV_VAR_SECRET
|
||||
_NONCE_BYTES = 16 # 128-bit random nonce per encrypt call
|
||||
_BLOCK = 32 # HMAC-SHA256 output width == one keystream block
|
||||
|
||||
# Env-var name the agent container receives at startup.
|
||||
ENV_VAR_SECRET_NAME = "ENV_VAR_SECRET"
|
||||
|
||||
|
||||
def new_env_var_secret() -> str:
|
||||
"""Generate a fresh ENV_VAR_SECRET: 32 random bytes as URL-safe base64."""
|
||||
return base64.urlsafe_b64encode(secrets.token_bytes(_KEY_BYTES)).rstrip(b"=").decode()
|
||||
|
||||
|
||||
def _b64dec(s: str) -> bytes:
|
||||
return base64.urlsafe_b64decode(s + "=" * (-len(s) % 4))
|
||||
|
||||
|
||||
def _keystream(key: bytes, nonce: bytes, block_index: int) -> bytes:
|
||||
return hmac.new(
|
||||
key, nonce + block_index.to_bytes(4, "big"), hashlib.sha256
|
||||
).digest()
|
||||
|
||||
|
||||
def encrypt_value(secret_b64: str, plaintext: str) -> str:
|
||||
"""Encrypt a single string value with *secret_b64* (the ENV_VAR_SECRET).
|
||||
|
||||
Returns a URL-safe base64 blob ``nonce || ciphertext`` suitable for
|
||||
the ``bottled_agent_secrets.value`` column."""
|
||||
key = _b64dec(secret_b64)
|
||||
pt = plaintext.encode()
|
||||
nonce = secrets.token_bytes(_NONCE_BYTES)
|
||||
ct = bytearray()
|
||||
for i in range(0, len(pt), _BLOCK):
|
||||
chunk = pt[i : i + _BLOCK]
|
||||
ks = _keystream(key, nonce, i)[: len(chunk)]
|
||||
ct.extend(p ^ k for p, k in zip(chunk, ks))
|
||||
return base64.urlsafe_b64encode(nonce + bytes(ct)).rstrip(b"=").decode()
|
||||
|
||||
|
||||
def decrypt_value(secret_b64: str, blob_b64: str) -> str:
|
||||
"""Decrypt a blob produced by :func:`encrypt_value`.
|
||||
|
||||
Returns the original plaintext string. Raises ``ValueError`` for malformed
|
||||
input or a key mismatch (wrong key produces garbage, not an error, unless
|
||||
the plaintext is non-UTF-8 — treat all such failures as wrong key)."""
|
||||
key = _b64dec(secret_b64)
|
||||
try:
|
||||
blob = _b64dec(blob_b64)
|
||||
except Exception as exc:
|
||||
raise ValueError(f"invalid ciphertext blob: {exc}") from exc
|
||||
if len(blob) < _NONCE_BYTES:
|
||||
raise ValueError("ciphertext blob too short")
|
||||
nonce, ciphertext = blob[:_NONCE_BYTES], blob[_NONCE_BYTES:]
|
||||
pt = bytearray()
|
||||
for i in range(0, len(ciphertext), _BLOCK):
|
||||
chunk = ciphertext[i : i + _BLOCK]
|
||||
ks = _keystream(key, nonce, i)[: len(chunk)]
|
||||
pt.extend(c ^ k for c, k in zip(chunk, ks))
|
||||
try:
|
||||
return bytes(pt).decode()
|
||||
except UnicodeDecodeError as exc:
|
||||
raise ValueError(f"decryption produced non-UTF-8 output (wrong key?): {exc}") from exc
|
||||
|
||||
|
||||
__all__ = ["ENV_VAR_SECRET_NAME", "new_env_var_secret", "encrypt_value", "decrypt_value"]
|
||||
@@ -13,15 +13,20 @@ Launch lifecycle:
|
||||
and returns the record. If the broker rejects/fails, the registry entry
|
||||
is rolled back so a failed launch leaves no orphan.
|
||||
* `teardown_bottle` sends a signed teardown request, then deregisters.
|
||||
* `reconcile` sweeps rows whose bottle is no longer running — the
|
||||
self-heal for the teardown paths that never got to run (a hard-killed
|
||||
launcher), since an orphan row at a recycled source IP bricks the next
|
||||
bottle that lands on it.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import json
|
||||
from collections.abc import Iterable
|
||||
from datetime import datetime, timezone
|
||||
|
||||
from .broker import LaunchBroker, LaunchRequest, sign_request
|
||||
from .registry import BottleRecord, RegistryStore
|
||||
from .registry import DEFAULT_REAP_GRACE_SECONDS, BottleRecord, RegistryStore
|
||||
from .gateway import Gateway
|
||||
from ..supervise import (
|
||||
AuditEntry,
|
||||
@@ -82,13 +87,22 @@ class Orchestrator:
|
||||
metadata: str = "",
|
||||
policy: str = "",
|
||||
tokens: dict[str, str] | None = None,
|
||||
env_var_secret: str = "",
|
||||
) -> BottleRecord:
|
||||
"""Register a bottle (with its gateway policy + in-memory egress auth
|
||||
tokens) and broker its launch. Rolls the registry entry back if the
|
||||
launch doesn't take, so a failure leaves no orphan."""
|
||||
launch doesn't take, so a failure leaves no orphan.
|
||||
|
||||
When *env_var_secret* is provided alongside *tokens*, the token values
|
||||
are also encrypted and written to ``bottled_agent_secrets`` so they can
|
||||
survive an orchestrator restart (see ``reprovision_from_secret``)."""
|
||||
rec = self.registry.register(source_ip, metadata=metadata, policy=policy)
|
||||
if tokens:
|
||||
self._tokens[rec.bottle_id] = dict(tokens)
|
||||
if env_var_secret:
|
||||
from .secret_store import encrypt_value
|
||||
encrypted = {k: encrypt_value(env_var_secret, v) for k, v in tokens.items()}
|
||||
self.registry.store_agent_secrets(rec.bottle_id, encrypted)
|
||||
req = LaunchRequest(
|
||||
op="launch",
|
||||
bottle_id=rec.bottle_id,
|
||||
@@ -117,6 +131,30 @@ class Orchestrator:
|
||||
self._tokens.pop(bottle_id, None)
|
||||
return True
|
||||
|
||||
def reconcile(
|
||||
self,
|
||||
live_source_ips: Iterable[str],
|
||||
*,
|
||||
grace_seconds: float = DEFAULT_REAP_GRACE_SECONDS,
|
||||
) -> list[str]:
|
||||
"""Drop registry rows for bottles that are no longer running, and
|
||||
forget their in-memory egress tokens. Returns the reaped bottle ids.
|
||||
|
||||
The caller supplies the live set because only the host can enumerate
|
||||
its own containers — the orchestrator runs *inside* the infra
|
||||
container and has no view of the backend. Deliberately does not
|
||||
broker a teardown: the container is already gone, so there is nothing
|
||||
to stop, and a broker error must not stop the sweep from clearing
|
||||
the row that would otherwise brick the next bottle at that address.
|
||||
|
||||
See `RegistryStore.reap_absent` for why orphans accumulate and why
|
||||
they are harmful rather than merely untidy."""
|
||||
reaped = self.registry.reap_absent(
|
||||
live_source_ips, grace_seconds=grace_seconds)
|
||||
for rec in reaped:
|
||||
self._tokens.pop(rec.bottle_id, None)
|
||||
return [rec.bottle_id for rec in reaped]
|
||||
|
||||
def tokens_for(self, bottle_id: str) -> dict[str, str]:
|
||||
"""The bottle's in-memory egress auth tokens (env_name -> value), or
|
||||
empty. The gateway injects these per request; they are never
|
||||
@@ -255,6 +293,26 @@ class Orchestrator:
|
||||
))
|
||||
return True, ""
|
||||
|
||||
# --- secret reprovision -----------------------------------------------
|
||||
|
||||
def reprovision_from_secret(self, bottle_id: str, env_var_secret: str) -> bool:
|
||||
"""Re-inject a bottle's egress tokens from its ENV_VAR_SECRET.
|
||||
|
||||
Reads the encrypted rows from ``bottled_agent_secrets``, decrypts each
|
||||
value with *env_var_secret*, and restores ``_tokens[bottle_id]``.
|
||||
Returns True on success, False when no stored secrets exist for this
|
||||
bottle or decryption fails (wrong key / corrupt data)."""
|
||||
from .secret_store import decrypt_value
|
||||
encrypted = self.registry.get_agent_secrets(bottle_id)
|
||||
if not encrypted:
|
||||
return False
|
||||
try:
|
||||
self._tokens[bottle_id] = {k: decrypt_value(env_var_secret, v)
|
||||
for k, v in encrypted.items()}
|
||||
except ValueError:
|
||||
return False
|
||||
return True
|
||||
|
||||
# --- consolidated gateway ----------------------------------------------
|
||||
|
||||
def ensure_gateway(self) -> None:
|
||||
|
||||
@@ -33,6 +33,13 @@ HOST_DB_FILENAME = "bot-bottle.db"
|
||||
CONTROL_PLANE_TOKEN_FILENAME = "control-plane-token"
|
||||
CONTROL_PLANE_TOKEN_ENV = "BOT_BOTTLE_CONTROL_PLANE_TOKEN"
|
||||
|
||||
# The host directory holding the gateway's persistent mitmproxy CA. Bind-mounted
|
||||
# into the infra/gateway container at mitmproxy's confdir so the self-generated
|
||||
# CA survives container recreation — every agent installs this one CA to trust
|
||||
# the shared gateway's TLS interception, so it must not rotate on restart. See
|
||||
# host_gateway_ca_dir() for why this is a host bind-mount, not a named volume.
|
||||
GATEWAY_CA_DIRNAME = "gateway-ca"
|
||||
|
||||
|
||||
def bot_bottle_root() -> Path:
|
||||
"""The app data root — `$BOT_BOTTLE_ROOT` if set, else `~/.bot-bottle`."""
|
||||
@@ -59,6 +66,23 @@ def host_db_dir() -> Path:
|
||||
return db_dir
|
||||
|
||||
|
||||
def host_gateway_ca_dir() -> Path:
|
||||
"""The directory holding the gateway's persistent mitmproxy CA, created if
|
||||
missing. Backends bind-mount this into the infra/gateway container at
|
||||
mitmproxy's confdir so the CA persists across container recreation.
|
||||
|
||||
A host bind-mount under the app-data root — deliberately NOT a Docker
|
||||
named volume. A named volume survives `docker rm` but is silently wiped by
|
||||
`docker volume prune` / `docker system prune --volumes` during routine host
|
||||
maintenance; the gateway then mints a fresh CA that every already-running
|
||||
bottle distrusts, failing the TLS handshake even after it reconnects to the
|
||||
moved gateway (issue #450). A path under the root docker never prunes it,
|
||||
and it stays directly inspectable + rotatable from the host."""
|
||||
ca_dir = bot_bottle_root() / GATEWAY_CA_DIRNAME
|
||||
ca_dir.mkdir(parents=True, exist_ok=True)
|
||||
return ca_dir
|
||||
|
||||
|
||||
def host_control_plane_token() -> str:
|
||||
"""The per-host control-plane secret, minted (256-bit, url-safe) and
|
||||
persisted 0600 on first use, then reused.
|
||||
@@ -94,8 +118,10 @@ __all__ = [
|
||||
"HOST_DB_FILENAME",
|
||||
"CONTROL_PLANE_TOKEN_FILENAME",
|
||||
"CONTROL_PLANE_TOKEN_ENV",
|
||||
"GATEWAY_CA_DIRNAME",
|
||||
"bot_bottle_root",
|
||||
"host_db_path",
|
||||
"host_db_dir",
|
||||
"host_gateway_ca_dir",
|
||||
"host_control_plane_token",
|
||||
]
|
||||
|
||||
@@ -6,9 +6,11 @@ from pathlib import Path
|
||||
|
||||
try:
|
||||
from .audit_store import AuditStore
|
||||
from .config_store import ConfigStore
|
||||
from .queue_store import QueueStore
|
||||
except ImportError:
|
||||
from audit_store import AuditStore # type: ignore[import-not-found] # pylint: disable=import-error,no-name-in-module
|
||||
from config_store import ConfigStore # type: ignore[import-not-found] # pylint: disable=import-error,no-name-in-module
|
||||
from queue_store import QueueStore # type: ignore[import-not-found] # pylint: disable=import-error,no-name-in-module
|
||||
|
||||
_instance: StoreManager | None = None
|
||||
@@ -47,11 +49,13 @@ class StoreManager:
|
||||
return (
|
||||
QueueStore("", self.db_path).is_migrated()
|
||||
and AuditStore(self.db_path).is_migrated()
|
||||
and ConfigStore(self.db_path).is_migrated()
|
||||
)
|
||||
|
||||
def migrate(self) -> None:
|
||||
QueueStore("", self.db_path).migrate()
|
||||
AuditStore(self.db_path).migrate()
|
||||
ConfigStore(self.db_path).migrate()
|
||||
|
||||
|
||||
__all__ = ["StoreManager"]
|
||||
|
||||
@@ -168,15 +168,16 @@ _ROUTES_YAML_DESCRIPTION = (
|
||||
"Full proposed /etc/egress/routes.yaml content. "
|
||||
"Each route entry accepts these keys:\n"
|
||||
" host: <hostname> (required)\n"
|
||||
" auth_scheme: Bearer|token (must pair with token_env)\n"
|
||||
" token_env: <ENV_VAR_NAME> (must pair with auth_scheme)\n"
|
||||
" matches: (optional list of match entries)\n"
|
||||
" - paths: [{type: prefix|exact|regex, value: /...}]\n"
|
||||
" methods: [GET, POST, ...]\n"
|
||||
" headers: [{name: X-Hdr, value: val, type: exact|regex}]\n"
|
||||
" git: (optional; omit to block git clone/fetch)\n"
|
||||
" fetch: true\n"
|
||||
" dlp: (optional DLP scanner overrides)\n"
|
||||
" inspect: false (opaque whole-host TLS tunnel; no HTTP controls)\n"
|
||||
" inspect: (omit for inspected defaults)\n"
|
||||
" auth_scheme: Bearer|token (must pair with token_env)\n"
|
||||
" token_env: <ENV_VAR_NAME> (must pair with auth_scheme)\n"
|
||||
" matches: (optional list of match entries)\n"
|
||||
" - paths: [{type: prefix|exact|regex, value: /...}]\n"
|
||||
" methods: [GET, POST, ...]\n"
|
||||
" headers: [{name: X-Hdr, value: val, type: exact|regex}]\n"
|
||||
" git: (optional; omit to block git clone/fetch)\n"
|
||||
" fetch: true\n"
|
||||
" outbound_detectors: [token_patterns, known_secrets]\n"
|
||||
" inbound_detectors: [naive_injection_detection]\n"
|
||||
" outbound_on_match: block|redact|supervise (default supervise)\n"
|
||||
|
||||
@@ -312,6 +312,44 @@ reaches over the RPC rather than a shared mount into the VM. WAL on the
|
||||
shared DB is therefore a deliberate, tested future change — not enabled ad
|
||||
hoc. `sqlite3` itself is stdlib, so "the host needs SQLite" is a non-cost.
|
||||
|
||||
### Gateway CA: host-resident, like the DB
|
||||
|
||||
The shared gateway bumps TLS with a self-generated mitmproxy CA, and **every
|
||||
bottle installs that CA** into its trust store to accept the bumped leaves. So
|
||||
the CA is durable per-host state with the same rule as the DB: it must outlive
|
||||
any single gateway container, or a restart mints a fresh CA that every
|
||||
already-running bottle distrusts — the TLS handshake then fails even after the
|
||||
bottle re-resolves and reconnects to the moved gateway (issue #450, a
|
||||
re-attachment blocker distinct from #443/#445).
|
||||
|
||||
The CA lives on the **host filesystem** at `bot_bottle_root()/gateway-ca`
|
||||
(`host_gateway_ca_dir()`), bind-mounted into the container at mitmproxy's
|
||||
confdir. This is deliberately a host bind-mount, **not a container-runtime
|
||||
named volume**: a named volume survives ordinary container removal but can be
|
||||
silently wiped by Docker's or Apple Container's volume-prune commands during
|
||||
routine host maintenance, which is exactly how the ephemeral-CA symptom shows
|
||||
up in practice. A path under the app-data root is not managed or pruned by the
|
||||
container runtime, and stays directly inspectable and rotatable from the host.
|
||||
mitmproxy reuses an existing CA and generates one only on first run, so the
|
||||
bind-mount alone gives
|
||||
"adopt-existing, generate-on-first-run" for free.
|
||||
|
||||
The macOS backend uses the same host-resident CA directory and bind-mounts it
|
||||
into the consolidated Apple infra container. Its `bot-bottle-mac-db` named
|
||||
volume remains container-only because that prevents incoherent cross-kernel
|
||||
SQLite locking, but the CA is deliberately not stored there: Apple Container
|
||||
also has a `container volume prune` operation, and the named volume is
|
||||
temporarily unreferenced while the infra container is recreated. Keeping the
|
||||
CA on the host makes both ordinary recreation and volume pruning safe.
|
||||
|
||||
**Deliberate rollover** is the explicit inverse: `rotate_gateway_ca()` removes
|
||||
the persisted CA material so the next start remints it, and the
|
||||
`python -m bot_bottle.orchestrator.rotate_ca` one-shot wires that together with
|
||||
dropping the running gateway container (whose mitmproxy still holds the old CA
|
||||
in memory). Rotation does not auto-re-provision the new CA into running bottles
|
||||
— those re-attach to install the new anchor — so it is an operator action with
|
||||
a brief egress interruption, never an implicit one.
|
||||
|
||||
## Sequencing
|
||||
|
||||
Jump straight to the **virtualized** end state (not a host-daemon stepping
|
||||
|
||||
@@ -0,0 +1,110 @@
|
||||
# PRD prd-new: CI artifact-based coverage and local Firecracker candidate flow
|
||||
|
||||
- **Status:** Active
|
||||
- **Author:** Claude
|
||||
- **Created:** 2026-07-21
|
||||
- **Issue:** #446
|
||||
|
||||
## Summary
|
||||
|
||||
Restructure the CI test pipeline to run each test suite exactly once, upload
|
||||
small `.coverage.*` artifacts, and combine them in a lightweight aggregation
|
||||
job. Move the infra build onto the KVM runner so the ~194 MB rootfs never
|
||||
crosses the network for PRs. On main-branch pushes, publish the byte-identical
|
||||
rootfs that was tested.
|
||||
|
||||
## Motivation
|
||||
|
||||
The prior pipeline had two redundant costs:
|
||||
|
||||
1. **Duplicate artifact transfers.** `build-infra` (ubuntu-latest) built and
|
||||
uploaded the ~194 MB rootfs; `integration-firecracker` downloaded it; the
|
||||
`coverage` job downloaded it a second time. Combined download overhead: ~83
|
||||
seconds per run, plus the ~70-second upload.
|
||||
|
||||
2. **Duplicate test execution.** `integration-firecracker` ran the Firecracker
|
||||
integration suite; `coverage` ran the entire unit + integration suite again
|
||||
on the same KVM runner to collect coverage data. Every line of Firecracker
|
||||
code was tested twice per CI run.
|
||||
|
||||
## Goals
|
||||
|
||||
- Each test suite (unit, integration-docker, integration-firecracker) executes
|
||||
exactly once per workflow run.
|
||||
- PRs incur no large artifact transfers — the rootfs stays on the KVM runner.
|
||||
- Main-branch pushes publish a byte-for-byte identical rootfs to the one that
|
||||
passed the integration tests.
|
||||
- Concurrent workflow runs cannot cross-publish candidates (naturally enforced
|
||||
by Gitea Actions' per-run artifact scoping).
|
||||
- Failed or cancelled runs block publication (enforced by the `needs:` chain on
|
||||
`publish-infra`).
|
||||
|
||||
## Non-goals
|
||||
|
||||
- Changing test semantics or the coverage policy (ADR 0004).
|
||||
- Removing the KVM runner guard on `integration-firecracker` and `coverage`.
|
||||
- Changing how `publish_infra.py` builds or uploads the rootfs.
|
||||
|
||||
## Design
|
||||
|
||||
### Job graph
|
||||
|
||||
```
|
||||
unit ──────────────────────────────────┐
|
||||
integration-docker ────────────────────┤──► coverage ──► publish-infra (main only)
|
||||
integration-firecracker (KVM) ─────────┘
|
||||
```
|
||||
|
||||
### `unit`
|
||||
|
||||
Unchanged except: `coverage run` writes `--data-file=.coverage.unit`; the file
|
||||
is uploaded as the `coverage-unit` artifact.
|
||||
|
||||
### `integration-docker`
|
||||
|
||||
Adds a `coverage` install step. `coverage run` writes `--data-file=.coverage.docker`;
|
||||
the file is uploaded as `coverage-docker`.
|
||||
|
||||
### `integration-firecracker` (KVM runner)
|
||||
|
||||
Replaces the old `stage-firecracker-inputs` → `build-infra` → download chain:
|
||||
|
||||
1. Builds the infra candidate locally with
|
||||
`BOT_BOTTLE_FC_DROPBEAR=/var/cache/bot-bottle-fc/dropbear`.
|
||||
2. Boots the candidate and runs integration tests with coverage, writing
|
||||
`.coverage.firecracker`.
|
||||
3. Uploads the small `coverage-firecracker` artifact unconditionally.
|
||||
4. On main-branch pushes only, uploads the rootfs as `infra-candidate` and the
|
||||
dropbear as `firecracker-inputs` so `publish-infra` can verify and publish
|
||||
the byte-identical artifact.
|
||||
|
||||
### `coverage`
|
||||
|
||||
Moves from a KVM runner to `ubuntu-latest`. No tests are re-executed:
|
||||
|
||||
1. Downloads `coverage-unit`, `coverage-docker`, and `coverage-firecracker`.
|
||||
2. Runs `scripts/coverage.sh aggregate critical`, which calls
|
||||
`coverage combine` then `coverage report`.
|
||||
3. Runs the diff-coverage gate (`scripts/diff_coverage.py`).
|
||||
|
||||
Coverage files use `relative_files = True` (`.coveragerc`) so they combine
|
||||
cleanly across runners with different absolute workspace paths.
|
||||
|
||||
### `publish-infra`
|
||||
|
||||
Depends on all four predecessor jobs (unchanged gate). Downloads `infra-candidate`
|
||||
and `firecracker-inputs` that were uploaded by `integration-firecracker` on
|
||||
main — the same byte sequence that passed the integration tests.
|
||||
|
||||
### Eliminated jobs
|
||||
|
||||
- `stage-firecracker-inputs`: existed only to copy the dropbear to ubuntu-latest
|
||||
for `build-infra`. No longer needed.
|
||||
- `build-infra`: the infra candidate is now built on the KVM runner in
|
||||
`integration-firecracker`.
|
||||
|
||||
### Script changes
|
||||
|
||||
`scripts/coverage.sh` gains an `aggregate` mode (`coverage.sh aggregate [critical]`)
|
||||
that combines pre-existing `.coverage.*` files instead of re-running tests.
|
||||
The existing run mode (`coverage.sh [critical]`) is preserved for local dev.
|
||||
@@ -0,0 +1,146 @@
|
||||
# PRD prd-new: Claude forward_host_credentials
|
||||
|
||||
- **Status:** Draft
|
||||
- **Author:** claude
|
||||
- **Created:** 2026-07-01
|
||||
- **Issue:** #325
|
||||
|
||||
## Summary
|
||||
|
||||
Add `agent_provider.forward_host_credentials: true` support for the
|
||||
`claude` template, mirroring the existing Codex flow. When enabled,
|
||||
bot-bottle reads the host's Claude OAuth session key from
|
||||
`~/.claude/.credentials.json` at launch, forwards it only to the egress sidecar,
|
||||
and injects a placeholder `CLAUDE_CODE_OAUTH_TOKEN` into the agent so
|
||||
Claude Code starts without ever seeing the real credential.
|
||||
|
||||
## Problem
|
||||
|
||||
Running a Claude agent in a container today requires the operator to
|
||||
manually extract a long-lived OAuth token (`claude setup-token`), export
|
||||
it as `BOT_BOTTLE_CLAUDE_OAUTH_TOKEN`, and reference it explicitly in
|
||||
the manifest with `agent_provider.auth_token:
|
||||
"BOT_BOTTLE_CLAUDE_OAUTH_TOKEN"`. This is a two-step manual ceremony
|
||||
that is easy to skip or do incorrectly.
|
||||
|
||||
The host already stores a valid Claude session in `~/.claude/.credentials.json`
|
||||
after `claude login`. Codex already automates an
|
||||
equivalent extraction from `~/.codex/auth.json`. There is no reason
|
||||
Claude bottles cannot do the same.
|
||||
|
||||
## Goals / Success Criteria
|
||||
|
||||
- A Claude bottle with `forward_host_credentials: true` in the manifest
|
||||
uses the host's `~/.claude/.credentials.json` session key at launch with no
|
||||
additional operator steps.
|
||||
- The agent container receives only `CLAUDE_CODE_OAUTH_TOKEN=egress-placeholder`
|
||||
— never the real token.
|
||||
- The real session key lives only in the egress sidecar's environment.
|
||||
- Missing, malformed, or expired host Claude auth fails launch with a
|
||||
clear operator-facing message.
|
||||
- Existing `auth_token` behavior is unchanged.
|
||||
- `forward_host_credentials: true` is rejected in the manifest when both
|
||||
`auth_token` and `forward_host_credentials` are set, since they serve
|
||||
the same purpose.
|
||||
|
||||
## Non-goals
|
||||
|
||||
- Refreshing Claude OAuth tokens in the sidecar.
|
||||
- Writing a dummy `~/.claude.json` auth state to the agent (unlike the
|
||||
Codex flow, Claude Code reads its credential from `CLAUDE_CODE_OAUTH_TOKEN`
|
||||
in env, not from an auth file — no guest-side auth marker is needed).
|
||||
- Supporting `forward_host_credentials` for providers other than `codex`
|
||||
and `claude`.
|
||||
|
||||
## Design
|
||||
|
||||
### Manifest schema
|
||||
|
||||
```yaml
|
||||
agent_provider:
|
||||
template: claude
|
||||
forward_host_credentials: true
|
||||
```
|
||||
|
||||
Rejects in manifest validation when:
|
||||
- Template is not `codex` or `claude`.
|
||||
- Both `auth_token` and `forward_host_credentials` are set.
|
||||
|
||||
### Host auth extraction (`contrib/claude/claude_auth.py`)
|
||||
|
||||
Claude Code credential storage varies by platform:
|
||||
|
||||
- **Linux**: `~/.claude/.credentials.json`
|
||||
- **macOS**: macOS Keychain, service `"Claude Code-credentials"`
|
||||
(the file path is tried first; Keychain is the fallback when the file
|
||||
is absent)
|
||||
|
||||
`~/.claude.json` contains only UI state and profile metadata — no token.
|
||||
|
||||
The credentials JSON schema (same whether from file or Keychain):
|
||||
|
||||
```json
|
||||
{
|
||||
"claudeAiOauth": {
|
||||
"accessToken": "<access-token>",
|
||||
"refreshToken": "<refresh-token>",
|
||||
"expiresAt": 1748276587173,
|
||||
"scopes": ["user:inference", "user:profile"]
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
`expiresAt` is in **milliseconds** (not seconds).
|
||||
|
||||
At prepare/launch time, when `forward_host_credentials: true`:
|
||||
|
||||
1. Try `~/.claude/.credentials.json`; on macOS, if absent, run
|
||||
`security find-generic-password -s "Claude Code-credentials" -w`
|
||||
and parse its stdout as JSON.
|
||||
2. Require a `claudeAiOauth` dict.
|
||||
3. Require a non-empty `claudeAiOauth.accessToken` string.
|
||||
4. If `claudeAiOauth.expiresAt` is present, divide by 1000 and require
|
||||
the result to be in the future.
|
||||
5. Return only the access token to the launch path.
|
||||
|
||||
Errors name the missing or invalid condition and point the operator at
|
||||
`claude login`, without printing token values.
|
||||
|
||||
### Egress route
|
||||
|
||||
When `forward_host_credentials: true`:
|
||||
|
||||
- Provision the session key in `provisioned_env` under
|
||||
`BOT_BOTTLE_CLAUDE_HOST_ACCESS_TOKEN` (new constant in `egress.py`).
|
||||
- Set up the `api.anthropic.com` egress route with `auth_scheme: Bearer`
|
||||
and `token_ref: BOT_BOTTLE_CLAUDE_HOST_ACCESS_TOKEN`.
|
||||
- Set `CLAUDE_CODE_OAUTH_TOKEN=egress-placeholder` in the agent env and
|
||||
add it to `hidden_env_names`.
|
||||
|
||||
No dummy auth file and no `verify` step are needed — Claude Code reads
|
||||
the credential from the env var, not from a file.
|
||||
|
||||
### Constants
|
||||
|
||||
- `CLAUDE_HOST_CREDENTIAL_TOKEN_REF = "BOT_BOTTLE_CLAUDE_HOST_ACCESS_TOKEN"`
|
||||
in `egress.py` (alongside the existing `CODEX_HOST_CREDENTIAL_TOKEN_REF`).
|
||||
- `CLAUDE_HOST_CREDENTIAL_HOSTS = ("api.anthropic.com",)` in
|
||||
`agent_provider.py` (alongside the existing `CODEX_HOST_CREDENTIAL_HOSTS`).
|
||||
|
||||
### Data flow
|
||||
|
||||
```
|
||||
Host ~/.claude/.credentials.json → bot-bottle launch
|
||||
│
|
||||
├──► egress sidecar env (real token only)
|
||||
│
|
||||
└──► agent env: CLAUDE_CODE_OAUTH_TOKEN=egress-placeholder
|
||||
|
||||
Agent → HTTPS to api.anthropic.com (via egress)
|
||||
Egress → injects Authorization: Bearer <real token>
|
||||
Egress → forwards to api.anthropic.com
|
||||
```
|
||||
|
||||
## Open questions
|
||||
|
||||
None — the Codex precedent makes the design clear.
|
||||
@@ -90,8 +90,9 @@ first (`DockerGateway.ensure_running`), then orchestrator. After this PRD:
|
||||
- Single `docker run` of `bot-bottle-infra:latest`
|
||||
- Container name: `bot-bottle-infra` (replaces `bot-bottle-orch-gateway` +
|
||||
`bot-bottle-orchestrator`)
|
||||
- Published ports: `127.0.0.1:{port}:{port}` for the control plane (same as
|
||||
today)
|
||||
- Published ports: `127.0.0.1:{host_port}:8099` for the control plane
|
||||
(`gateway_init` listens on a fixed internal port 8099; the caller-chosen
|
||||
host port maps to it)
|
||||
- Bind mounts: repo root + host root (same as today)
|
||||
- `DockerGateway` becomes an implementation detail of `OrchestratorService`
|
||||
rather than a separately started container; the gateway image name
|
||||
|
||||
@@ -0,0 +1,47 @@
|
||||
# PRD prd-new: Modernize built-in agent images
|
||||
|
||||
- **Status:** Draft
|
||||
- **Author:** Codex
|
||||
- **Created:** 2026-07-21
|
||||
- **Issue:** #451
|
||||
|
||||
## Summary
|
||||
|
||||
Keep every built-in agent provider on Debian's current stable release and make
|
||||
Podman available inside each image. This gives agents a consistent, modern
|
||||
userspace and an OCI container tool without requiring per-project setup.
|
||||
|
||||
## Problem
|
||||
|
||||
The Claude, Codex, and Pi images inherit the generic `node:22-slim` tag. That
|
||||
tag does not state which Debian release the project supports and currently
|
||||
leaves the images on the older Bookworm release. None of the built-in images
|
||||
installs Podman, so tasks that need to inspect or build OCI images must first
|
||||
modify the bottle or cannot run at all.
|
||||
|
||||
## Goals / success criteria
|
||||
|
||||
- Every Dockerfile under `bot_bottle/contrib/*/Dockerfile` explicitly inherits
|
||||
`node:22-trixie-slim`, based on Debian 13 (the current stable release).
|
||||
- Every built-in agent image installs Podman from Debian stable.
|
||||
- Every built-in agent image retains an SSH client for Git-over-SSH workflows.
|
||||
- The non-root agent user owns a traversable XDG Git configuration directory,
|
||||
so Git can load bot-bottle's global git-gate rewrites without permission
|
||||
errors.
|
||||
- A shared test enforces both requirements for current and future built-in
|
||||
providers.
|
||||
|
||||
## Non-goals
|
||||
|
||||
- Configuring privileged or nested-container execution for bottles.
|
||||
- Pinning Podman outside Debian's stable package repository.
|
||||
- Changing the Node.js or agent CLI release policy.
|
||||
|
||||
## Design
|
||||
|
||||
Use the explicit `node:22-trixie-slim` base rather than the floating `slim`
|
||||
variant. Install the `podman` package with each image's existing `apt-get`
|
||||
dependency layer, so package metadata and caches are still removed in the same
|
||||
layer. Treat Debian stable as the Podman stability and update channel; this
|
||||
keeps the images stdlib/distribution-first and avoids adding a third-party
|
||||
package repository.
|
||||
@@ -0,0 +1,153 @@
|
||||
# PRD prd-new: Containers inside a bottle
|
||||
|
||||
- **Status:** Draft
|
||||
- **Author:** Claude
|
||||
- **Created:** 2026-07-21
|
||||
- **Issue:** #392
|
||||
|
||||
## Summary
|
||||
|
||||
Let an agent run `docker` and `docker compose` *inside* its bottle by starting
|
||||
a guest-local rootless podman service that exposes a Docker-compatible API
|
||||
socket. Gated per bottle by `nested_containers: true`. No host daemon socket is
|
||||
mounted and no capability is added to the guest, on any backend.
|
||||
|
||||
## Problem
|
||||
|
||||
Agent tasks routinely involve containers: `docker compose up` to verify a
|
||||
scaffolded stack, a throwaway database for a test run, building an image to
|
||||
check a Dockerfile works. Bottles have no way to do any of that, so those tasks
|
||||
either fail or get done outside the bottle — which defeats the point of the
|
||||
bottle.
|
||||
|
||||
## Goals / success criteria
|
||||
|
||||
- A bottle with `nested_containers: true` on the `macos-container` backend can
|
||||
run `docker compose up -d --wait` against a stock compose file, pulling from
|
||||
a routed registry and serving from the workspace.
|
||||
- The agent's habits do not change: `docker` and `docker compose`, not
|
||||
`podman`.
|
||||
- No host Docker socket is mounted, on any backend.
|
||||
- No capability is added to the Apple Container guest.
|
||||
- Backends without a guest-local engine reject the flag with a clear error
|
||||
rather than ignoring it.
|
||||
- Bottles that do not set the flag carry none of its cost.
|
||||
|
||||
## Non-goals
|
||||
|
||||
- Nested containers as an isolation layer. The single-UID mapping means `root`
|
||||
inside a nested container is the agent user outside it. This is for build and
|
||||
test workloads; the bottle stays the security boundary.
|
||||
- The `docker` and `firecracker` backends. Both reject the flag for now.
|
||||
- Reaching registries that are not routed through the bottle's egress proxy.
|
||||
|
||||
## Design
|
||||
|
||||
### Why podman, not rootless Docker
|
||||
|
||||
Apple Container's capability bounding set omits `CAP_SYS_ADMIN`, which the
|
||||
kernel requires in order to write a multi-range `uid_map` via `newuidmap`.
|
||||
Rootless Docker has no path that avoids that write, so it cannot run in a
|
||||
bottle without granting `CAP_SYS_ADMIN` — which is close to root in practical
|
||||
terms and gives up most of what the bottle is for.
|
||||
|
||||
Podman does have a path: with **no** subordinate UID range configured it falls
|
||||
back to a single-UID self-mapping, which an unprivileged process may write
|
||||
itself. The image build therefore *removes* the agent user's `/etc/subuid` and
|
||||
`/etc/subgid` entries rather than adding them — their presence is exactly what
|
||||
would send podman down the `newuidmap` path. Full negative result in
|
||||
[`docs/research/rootless-docker-in-apple-container-spike.md`](../research/rootless-docker-in-apple-container-spike.md).
|
||||
|
||||
### The flag, and its name
|
||||
|
||||
The flag is kept because it gates real costs, not because podman needs a
|
||||
privilege grant: ~100MB of derived image, a resident service per bottle, and
|
||||
relaxed modes on `/dev/fuse` and `/dev/net/tun` that the majority of bottles
|
||||
should not get.
|
||||
|
||||
It is named `nested_containers`, not `docker_access`. It implies no Docker and
|
||||
grants access to nothing on the host — naming it after Docker access would
|
||||
describe the one thing the design refuses to do.
|
||||
|
||||
### Shape
|
||||
|
||||
- `bot_bottle/backend/macos_container/nested_containers.py` — derived-image
|
||||
build, guest env, device preparation, service start/readiness.
|
||||
- `bot_bottle/backend/macos_container/nested-containers-init.sh` — the
|
||||
unprivileged bootstrap that runs inside the bottle. Fails closed on every
|
||||
prerequisite it needs (podman, the storage/network helpers, writable device
|
||||
nodes, an *empty* subordinate range) rather than degrading.
|
||||
- The derived image `…-nested-containers` layers the Docker CLI, the compose
|
||||
plugin, and podman 5's networking stack — `passt` (pasta), `netavark`,
|
||||
`nftables`, `aardvark-dns` — plus `fuse-overlayfs`, `slirp4netns`, and
|
||||
`uidmap` onto the agent image. Podman itself already ships in every built-in
|
||||
image (#451), but with `--no-install-recommends`, so none of the networking
|
||||
pieces arrive with it. Each absence fails at a different and misleading
|
||||
layer: no pasta and nothing starts; no `nft` and containers are created but
|
||||
never start; no aardvark-dns and DNS inside a container fails while
|
||||
everything else looks healthy. Image pulls keep working throughout, which is
|
||||
what makes these read as compat-API bugs.
|
||||
- `BottleBackend.supports_nested_containers` — false by default, so a backend
|
||||
that cannot honor the flag fails in the shared `prepare` template.
|
||||
|
||||
Guest configuration the single-UID mapping forces:
|
||||
`ignore_chown_errors` (no second UID for layers to be chowned to),
|
||||
`cgroups="disabled"` and `cgroup_manager="cgroupfs"` (no cgroup delegation
|
||||
reaches the guest), `events_logger="file"` (no journald socket).
|
||||
|
||||
### Registry reach
|
||||
|
||||
Image pulls egress through the bottle's proxy like everything else, so each
|
||||
registry needs a route — **and so does the CDN it redirects blobs to**, which
|
||||
is a separate host: `production.cloudfront.docker.com` for Docker Hub,
|
||||
`pkg-containers.githubusercontent.com` for GHCR, `cdn0*.quay.io` for quay.
|
||||
Without those the pull authenticates, fetches the manifest, and then 403s
|
||||
partway through. Docker Hub and GHCR need `preserve_auth: true` — their
|
||||
token dance uses a client-fetched per-scope bearer token that the proxy would
|
||||
otherwise strip. Layer pulls should also set `dlp.outbound_detectors: false`
|
||||
and `dlp.inbound_detectors: false`: body scanning on a multi-hundred-MB layer
|
||||
is what triggers #455, and a registry route's scanned bodies are compressed
|
||||
layer blobs rather than anything a detector can read.
|
||||
|
||||
### Reaching the network from a nested container
|
||||
|
||||
Public DNS inside a nested container fails by design: everything egresses
|
||||
through the proxy. What was actually broken was reaching the proxy at all, and
|
||||
it took four attempts to fix because podman applies proxy settings at several
|
||||
layers and the last writer wins:
|
||||
|
||||
| Layer | Applies to |
|
||||
|---|---|
|
||||
| `~/.docker/config.json` proxies block | **every container the Docker CLI starts** — client-side, beats everything below |
|
||||
| service environment | podman's own pulls, non-CLI API clients |
|
||||
| `containers.conf` `env` | native `podman run` |
|
||||
| `containers.conf` `hosts_file`, `http_proxy` | native `podman run` only — the compat API ignores both |
|
||||
|
||||
The gateway is named `bot-bottle-gateway`, which resolves only through the
|
||||
bottle's `/etc/hosts`; a nested container gets its own. Since no config key
|
||||
reaches the compat path, the name is resolved in the bottle and the *address*
|
||||
is substituted into the proxy URL at each layer above. `NO_PROXY` keeps the
|
||||
name, which is matched against what a client asks for.
|
||||
|
||||
The gateway TLS-intercepts, so the CA bundle is mounted read-only and
|
||||
`SSL_CERT_FILE`, `CURL_CA_BUNDLE`, `REQUESTS_CA_BUNDLE`, and
|
||||
`NODE_EXTRA_CA_CERTS` point at it — no distro-specific trust commands.
|
||||
|
||||
## Verified on macOS 26 / Apple Container 1.0.0 / podman 5.4.2
|
||||
|
||||
With plain `docker`, no extra flags: image pulls from Docker Hub, GHCR, and
|
||||
quay; `docker run` with correct exit-code propagation; `docker compose` up,
|
||||
logs, down, and a published port curl'd from the bottle; `curl https://quay.io`
|
||||
and `https://pypi.org/simple/` returning 200 from inside a nested container;
|
||||
and `https://example.com` returning **403** — the egress allowlist applies to
|
||||
nested containers, not just the bottle.
|
||||
|
||||
Alpine's BusyBox `wget` drops the connection after TLS interception and
|
||||
reports "error getting response". The proxy logs the decrypted request, and
|
||||
`curl` on the same host succeeds, so this is a BusyBox client limitation
|
||||
rather than anything in the egress path.
|
||||
|
||||
## Open questions
|
||||
|
||||
- Whether the `docker` and `firecracker` backends want an equivalent, or
|
||||
whether guest-local containers stay macOS-only.
|
||||
@@ -0,0 +1,131 @@
|
||||
# PRD prd-new: Encrypted at-rest egress secrets (SecretProvider, interim slice)
|
||||
|
||||
- **Status:** Draft
|
||||
- **Author:** didericis
|
||||
- **Created:** 2026-07-21
|
||||
- **Issue:** #355
|
||||
|
||||
## Summary
|
||||
|
||||
An interim step toward the generic `SecretProvider` (#355) that stops short
|
||||
of per-request minting. Today the orchestrator holds each bottle's egress
|
||||
auth tokens **in process memory only**, so any infra-container recreation
|
||||
silently strips every already-running bottle of its upstream credentials.
|
||||
This PRD makes those secrets survive a gateway restart by persisting them
|
||||
**encrypted**, under a key that is not itself sitting next to the
|
||||
ciphertext.
|
||||
|
||||
The end state in #355 — short-lived, scoped credentials minted per request
|
||||
— removes the need to store anything durable at all. That is a larger
|
||||
change gated on per-upstream minting support. This slice buys back
|
||||
restart-survivability now without regressing to plaintext secrets at rest.
|
||||
|
||||
## Problem
|
||||
|
||||
`Orchestrator._tokens` (`bot_bottle/orchestrator/service.py:74-79`) is a
|
||||
plain in-memory dict, deliberately never written to the registry DB:
|
||||
|
||||
> Held **in memory only** — never written to the registry DB — so the
|
||||
> gateway can inject each bottle's upstream credential without secrets at
|
||||
> rest. Lost on restart (re-launch re-registers them); the future
|
||||
> SecretProvider (#355) replaces this with per-request minting.
|
||||
|
||||
The registry itself *is* durable (SQLite on a container-only volume), and
|
||||
so is the gateway CA since #450 / `2cd44cf7`. The tokens are now the only
|
||||
piece of gateway state that does not survive a restart, which makes the
|
||||
failure mode both silent and confusing.
|
||||
|
||||
### Observed failure
|
||||
|
||||
Checking out a branch that touches `bot_bottle/**/*.py` changes
|
||||
`source_hash()` (`bot_bottle/orchestrator/lifecycle.py:88-99`).
|
||||
`MacosInfraService._source_current()`
|
||||
(`bot_bottle/backend/macos_container/infra.py:159-169`) sees the mismatch
|
||||
and `ensure_running()` force-removes and recreates the infra container
|
||||
(`infra.py:198-208`). The registry rows survive on the DB volume; the CA
|
||||
survives on its host bind-mount; `_tokens` comes back empty.
|
||||
|
||||
Every already-running bottle then fails closed, mid-session, on its next
|
||||
outbound request:
|
||||
|
||||
- `/resolve` succeeds — the bottle is still `active` in
|
||||
`orchestrator_bottles` and its policy blob is served intact, including
|
||||
`- host: "api.anthropic.com"` with `auth_scheme: Bearer` /
|
||||
`token_env: EGRESS_TOKEN_0`.
|
||||
- `tokens_for()` returns `{}`, so the resolved env overlay has no
|
||||
`EGRESS_TOKEN_0`.
|
||||
- `decide()` (`bot_bottle/egress_addon_core.py:644-652`) blocks with
|
||||
`egress: route for 'api.anthropic.com' declared auth but env var
|
||||
'EGRESS_TOKEN_0' is unset` — an 89-byte `403` on every request.
|
||||
|
||||
Confirmed live on the macOS backend on 2026-07-21: two bottles running
|
||||
since 20:29/20:30 were still registered `active` with valid policy after
|
||||
the 23:05 infra recreation, and both took 89-byte `403`s from then on,
|
||||
while a bottle launched *after* the recreation egressed normally. The
|
||||
recovery today is to relaunch every affected bottle.
|
||||
|
||||
Note this is a re-attachment blocker distinct from #443/#445 and from #450
|
||||
— the CA and the gateway address were both fine. It is specifically the
|
||||
credential wipe.
|
||||
|
||||
## Goals / Success criteria
|
||||
|
||||
1. A bottle's egress auth tokens survive infra-container recreation: an
|
||||
already-running bottle keeps egressing across a gateway restart with no
|
||||
relaunch and no operator action.
|
||||
2. Secrets are **never** at rest in plaintext, and never at rest next to a
|
||||
key that trivially decrypts them.
|
||||
3. Compromise of the registry DB file alone does not yield usable
|
||||
upstream credentials.
|
||||
4. The stored form is revocable and rotatable without relaunching bottles
|
||||
that are not affected.
|
||||
5. When the retained bottle record reaches the lifecycle status `removed`,
|
||||
its stored secrets are destroyed. Status/event persistence and the removal
|
||||
transition land separately; this interim slice intentionally retains the
|
||||
ciphertext across today's teardown/reconcile calls until that lifecycle is
|
||||
available.
|
||||
6. Migration is transparent: existing bottles keep working, no manifest
|
||||
changes required.
|
||||
|
||||
## Non-goals
|
||||
|
||||
- **Per-request minting** of short-lived scoped credentials. That is the
|
||||
#355 end state; this PRD is explicitly the interim slice and should not
|
||||
foreclose it.
|
||||
- Generalizing `DeployKeyProvisioner` into the full `SecretProvider` ABC,
|
||||
or the manifest-level `{ provider: <name> }` reference surface.
|
||||
- User-extensible provider discovery (`~/.bot-bottle/contrib/<name>/`).
|
||||
- Changing the `/resolve` contract's shape (it already carries `tokens`).
|
||||
- Fixing the *trigger* — `source_hash` churn on branch switch. Recreating
|
||||
infra is legitimate; it just must not cost running bottles their
|
||||
credentials. A separate guard that refuses recreation while bottles are
|
||||
active is complementary and out of scope here.
|
||||
|
||||
## Design
|
||||
|
||||
> **TODO (didericis):** the encryption flow goes here — key custody, where
|
||||
> the key material lives relative to the ciphertext, the wrap/unwrap path
|
||||
> at register and at `/resolve`, and what an attacker who holds only the
|
||||
> DB (or only the host, or only the infra container) can recover.
|
||||
|
||||
Constraints the design has to satisfy, for reference while drafting:
|
||||
|
||||
- The gateway's `PolicyResolver` needs the cleartext at request time, on
|
||||
the data-plane path, so unwrap has to be cheap enough to sit in a
|
||||
per-flow `/resolve` (or be cached in memory after first unwrap).
|
||||
- The infra container is recreated routinely and unattended. Anything
|
||||
requiring an interactive unlock on every recreation defeats the goal.
|
||||
- The DB lives on a container-only volume that the host does not mount, so
|
||||
host-side and guest-side components see different filesystems — that
|
||||
asymmetry is available as a place to split custody.
|
||||
- The agent must never be able to reach the key material. It is a separate
|
||||
container with no control-plane token, which is the existing boundary.
|
||||
|
||||
## Open questions
|
||||
|
||||
- Where does the unwrap key live, and what recreates/re-derives it when the
|
||||
infra container is rebuilt?
|
||||
- Is the cleartext cached in memory after first unwrap, or unwrapped per
|
||||
request? (Latency vs. exposure window.)
|
||||
- What is the rotation story — re-wrap in place, or force re-registration?
|
||||
- Does this land behind a flag, or replace `_tokens` outright?
|
||||
@@ -0,0 +1,86 @@
|
||||
# Egress proxy OOMs on large downloads
|
||||
|
||||
Found on 2026-07-21 while running the rootless-podman spike
|
||||
(`docs/research/rootless-docker-in-apple-container-spike.md`). Recorded
|
||||
rather than fixed — the fix is a security-relevant decision, not a
|
||||
mechanical patch.
|
||||
|
||||
## Summary
|
||||
|
||||
A single large HTTPS download through the gateway kills the egress
|
||||
proxy. `mitmdump` buffers whole response bodies so the DLP detectors can
|
||||
scan them, grows past the gateway container's memory limit, and is
|
||||
OOM-killed by the cgroup. Nothing restarts it.
|
||||
|
||||
Two properties make this worse than a failed download:
|
||||
|
||||
- **The gateway is a per-host singleton.** Every bottle shares it, so
|
||||
one bottle's download takes egress away from all of them.
|
||||
- **There is no restart on death.** The gateway supervisor is
|
||||
`while : ; do wait ; done`; a killed daemon stays dead until the infra
|
||||
container is recreated.
|
||||
|
||||
So ordinary agent activity — pulling a container image, downloading a
|
||||
model or dataset, fetching a large tarball — is a denial of service
|
||||
against every other bottle on the host. No malice required, though it is
|
||||
trivially reachable on purpose.
|
||||
|
||||
## Evidence
|
||||
|
||||
Triggered by `docker compose up` pulling `quay.io/fedora/python-312`
|
||||
(two layers, ~82MB and ~83MB) inside a bottle. The pull itself
|
||||
succeeded; the *next* request failed:
|
||||
|
||||
```
|
||||
initializing source docker://quay.io/fedora/python-312:latest:
|
||||
pinging container registry quay.io: Get "https://quay.io/v2/":
|
||||
proxyconnect tcp: dial tcp 192.168.128.39:9099: connect: connection refused
|
||||
```
|
||||
|
||||
From the gateway's `dmesg`:
|
||||
|
||||
```
|
||||
python3 invoked oom-killer: gfp_mask=0x100cca(GFP_HIGHUSER_MOVABLE), order=0
|
||||
oom-kill:constraint=CONSTRAINT_MEMCG,
|
||||
oom_memcg=/container/bot-bottle-mac-infra,
|
||||
task_memcg=/container/bot-bottle-mac-infra,task=mitmdump,pid=118
|
||||
Memory cgroup out of memory: Killed process 118 (mitmdump)
|
||||
total-vm:1391936kB, anon-rss:997768kB
|
||||
```
|
||||
|
||||
~1GB RSS against a 1024MB container. Note the amplification: ~165MB of
|
||||
layers produced ~1GB of resident memory, so the buffering is several
|
||||
copies deep (encoded body, decoded body, and the text conversion the
|
||||
regex detectors scan).
|
||||
|
||||
Afterwards the gateway container was still running and healthy-looking —
|
||||
orchestrator, supervise, and git-http all alive — with no `mitmdump`
|
||||
process at all, and it stayed that way until the container was
|
||||
recreated. A liveness check on the container would not have caught this.
|
||||
|
||||
## Reproduction
|
||||
|
||||
1. Launch any bottle with an egress route to a host serving a large file.
|
||||
2. Download >~150MB over HTTPS through the proxy.
|
||||
3. `dmesg | grep -i oom` inside `bot-bottle-mac-infra`, and note that no
|
||||
`mitmdump` process remains.
|
||||
|
||||
Beware a false negative when checking: truncating the process listing
|
||||
(`cut -c1-45`) cuts before the binary name, because `mitmdump` runs as
|
||||
`/usr/local/bin/python3.12 /usr/local/bin/mitmdump …`.
|
||||
|
||||
## Fix options, not yet chosen
|
||||
|
||||
1. **Restart dead daemons.** Smallest change and strictly an
|
||||
improvement: an OOM then degrades one download instead of removing
|
||||
egress for every bottle. Does not stop the OOM.
|
||||
2. **Cap the scanned body size.** Above a threshold, stop buffering —
|
||||
either skip the scan or stream it. This is the root-cause fix and a
|
||||
security decision: a size threshold is exactly the hole an exfiltrator
|
||||
would aim for, so "skip above N" trades a DoS for a covert channel.
|
||||
Streaming with a bounded window keeps coverage, at more complexity.
|
||||
3. **Raise the gateway's memory limit.** Moves the threshold; does not
|
||||
remove it.
|
||||
|
||||
Worth noting that (1) and (2) are complementary — the restart gap is
|
||||
worth closing regardless of how the memory behaviour is resolved.
|
||||
@@ -0,0 +1,178 @@
|
||||
# Firecracker Image Remote Store
|
||||
|
||||
**Date:** 2026-07-22
|
||||
**Context:** PR #459 (run-dir leak fix) surfaced that committed Firecracker snapshots
|
||||
currently live only on the host machine. Once a host is wiped or a run-dir is
|
||||
evicted, a user's preserved bottle is gone. This note investigates a secure remote
|
||||
store so committed images survive host turnover and can be restored without the
|
||||
user having to pre-flag which sessions to keep.
|
||||
|
||||
## Verdict
|
||||
|
||||
Backblaze B2 + Cloudflare CDN is the cost-optimal choice for most deployments.
|
||||
Cloudflare R2 is the simpler zero-config option at slightly higher storage cost.
|
||||
Self-hosted MinIO is the right call for air-gapped or on-premises installs.
|
||||
|
||||
On the image-size front, zstd-compressing the committed tar before upload
|
||||
produces roughly a 60–70% reduction with negligible impact on restore latency.
|
||||
OverlayFS (for in-flight working rootfs, not for the committed artifact) cuts
|
||||
per-instance disk use to ~10–50 MB per extra bottle sharing the same base.
|
||||
|
||||
---
|
||||
|
||||
## What Gets Stored
|
||||
|
||||
The Firecracker backend produces two artifact types:
|
||||
|
||||
| Artifact | Created by | Size | Lifetime |
|
||||
|----------|-----------|------|---------|
|
||||
| `rootfs/agent-<digest>/` (dir) | `image_builder.py` → `mke2fs -d` | ~1 GB as ext4 | Cached per Dockerfile hash; evictable |
|
||||
| `committed/<slug>/rootfs.tar` | `FirecrackerFreezer._freeze` via SSH tar | 500 MB–1 GB | User-preserved; must survive host wipe |
|
||||
|
||||
The committed artifact is a tar of the guest's live filesystem streamed out over
|
||||
SSH (`freezer.py:58–90`). At resume time `launch.py` calls `mke2fs -d` to
|
||||
rebuild a fresh ext4 from this tar. The tar — not the ext4 — is what needs to be
|
||||
pushed to remote storage and pulled back at restore time.
|
||||
|
||||
The base image cache (`rootfs/agent-<digest>/`) is derivable from the Dockerfile
|
||||
and can be rebuilt on demand; it is lower priority for remote storage.
|
||||
|
||||
---
|
||||
|
||||
## Storage Candidates
|
||||
|
||||
### Object storage
|
||||
|
||||
| Provider | Storage | Egress | Notes |
|
||||
|----------|---------|--------|-------|
|
||||
| **Backblaze B2** | $0.006/GB | Free (via Cloudflare Bandwidth Alliance) | Cheapest storage; pairs with Cloudflare CDN to eliminate egress |
|
||||
| **Cloudflare R2** | $0.015/GB | $0 always | Zero-config egress; no lifecycle transitions (limitation) |
|
||||
| **Wasabi** | $0.0069/GB | Free (1:1 ratio) | 90-day minimum retention; good for archival; lifecycle evaluated daily |
|
||||
| **AWS S3** | $0.023/GB | $0.09/GB | Richest lifecycle support; expensive at scale; avoid unless already in AWS |
|
||||
| **MinIO** (self-hosted) | Host cost only | None | S3-compatible; best for private/on-prem deployments |
|
||||
|
||||
**B2 + Cloudflare CDN** is effectively $0.006/GB with zero egress — about 18×
|
||||
cheaper than S3 for restore-heavy workloads. **R2** is the zero-config choice
|
||||
($0 egress by default, no Bandwidth Alliance pairing needed) at a slightly
|
||||
higher storage rate.
|
||||
|
||||
**Cloudflare R2's missing lifecycle support** is the main caveat: auto-eviction
|
||||
rules (evict images older than N days) cannot currently be expressed natively in
|
||||
R2. Wasabi and S3 both support declarative lifecycle policies.
|
||||
|
||||
### Retention policy recommendation
|
||||
|
||||
The comment proposes:
|
||||
- Retain images for ~1 week by default
|
||||
- Warn when approaching a capacity threshold
|
||||
- Auto-evict oldest images once threshold is exceeded
|
||||
|
||||
This maps cleanly to an application-level policy (not a provider lifecycle rule),
|
||||
which avoids the R2 limitation and works consistently across providers:
|
||||
|
||||
1. On `commit`: upload tar, record `(slug, size_bytes, uploaded_at)` in a local
|
||||
or remote manifest file.
|
||||
2. On startup / on `list`: scan the manifest, warn if total stored size exceeds
|
||||
e.g. 80% of the configured threshold.
|
||||
3. On eviction run (CLI or cron): delete objects older than `retention_days`
|
||||
(default 7) that push total over `max_capacity`; oldest-first.
|
||||
|
||||
This keeps the policy logic in bot-bottle and the storage provider as a dumb
|
||||
object store — no vendor-specific lifecycle API required.
|
||||
|
||||
---
|
||||
|
||||
## Image Size Reduction
|
||||
|
||||
### Current artifact sizes
|
||||
|
||||
A typical committed tar for a Claude Code agent image is 500 MB–1 GB uncompressed.
|
||||
The per-run ext4 (copy of the base, written at `start`) adds another ~1 GB of
|
||||
local disk. The leak fix in this PR addresses the ext4 copies; the remote store
|
||||
addresses the committed tars.
|
||||
|
||||
### Compression
|
||||
|
||||
zstd compression of the committed tar before upload is the highest-leverage
|
||||
single change:
|
||||
|
||||
| Codec | Typical size (1 GB rootfs) | Compress speed | Decompress speed |
|
||||
|-------|---------------------------|---------------|-----------------|
|
||||
| gzip | 350–430 MB | ~100 MB/s | ~500 MB/s |
|
||||
| **zstd (default)** | **330–360 MB** | **~400 MB/s** | **~2 GB/s** |
|
||||
| xz | 290–320 MB | ~20 MB/s | ~200 MB/s |
|
||||
|
||||
**zstd is the best trade-off**: 65–67% size reduction, near-instantaneous
|
||||
decompression. The `tar` call in `freezer.py` could pipe through `zstd` before
|
||||
writing to disk and to the remote; `resume` decompresses on the way back. A
|
||||
`.tar.zst` suffix marks compressed artifacts so old tars remain restorable
|
||||
without the codec.
|
||||
|
||||
### SquashFS for the base image cache
|
||||
|
||||
The `rootfs/agent-<digest>/` directory (the buildah-exported tree) is rebuilt by
|
||||
`image_builder.py` and turned into per-run ext4 by `mke2fs -d`. Storing the
|
||||
base as a SquashFS image instead of a flat directory tree would reduce it from
|
||||
~1 GB to ~330–360 MB and make the cache remote-friendly. Firecracker does not
|
||||
directly boot SquashFS, but the existing `mke2fs -d` path reads a directory tree
|
||||
— a SquashFS mount could serve as the source. This is a larger change and lower
|
||||
priority than tar compression.
|
||||
|
||||
### OverlayFS for per-run rootfs
|
||||
|
||||
Multiple simultaneous bottles sharing the same agent image today each get a full
|
||||
`mke2fs -d` copy (~1 GB). OverlayFS (read-only base + writable sparse overlay)
|
||||
would reduce this to ~10–50 MB per instance beyond the first:
|
||||
|
||||
- Mount the base image directory as read-only lower layer
|
||||
- Attach a sparse ext4 or tmpfs writable layer per bottle
|
||||
- Pass the merged overlay to Firecracker as the block device
|
||||
|
||||
E2B's public write-up on Firecracker + OverlayFS confirms this approach works
|
||||
at scale. The `launch.py` changes would be non-trivial (device mapper or
|
||||
`fuse-overlayfs` plumbing), so this is a follow-up rather than a prerequisite
|
||||
for the remote store.
|
||||
|
||||
---
|
||||
|
||||
## Recommended Approach
|
||||
|
||||
**Phase 1 — remote store with zstd (tight scope, actionable now)**
|
||||
|
||||
1. Add `--zstd` to the `tar` call in `FirecrackerFreezer._freeze`; name the
|
||||
artifact `rootfs.tar.zst`. Keep uncompressed restore path for legacy tars.
|
||||
2. Add a `bb firecracker upload <slug>` / `bb firecracker pull <slug>` pair that
|
||||
pushes/fetches the compressed tar to the configured object store (S3-compatible
|
||||
API, so B2, R2, MinIO, and Wasabi all work with the same client).
|
||||
3. Store a `manifest.json` in the bucket (or a local mirror) tracking slug →
|
||||
`{size, uploaded_at}`. Use it for threshold warnings and eviction.
|
||||
4. Default retention: 7 days, configurable via `firecracker.image_retention_days`
|
||||
in `~/.config/bot-bottle/config.toml` (or equivalent).
|
||||
5. Warn at 80% of `max_capacity` (default e.g. 50 GB); evict oldest on commit
|
||||
once at 100%.
|
||||
|
||||
**Storage recommendation:** Cloudflare R2 for hosted deployments (zero egress,
|
||||
zero config), MinIO for private/on-premises.
|
||||
|
||||
**Phase 2 — base image cache compression**
|
||||
|
||||
Compress the `agent-<digest>` cache dir as a `.tar.zst` to save ~65% on repeated
|
||||
image uploads. Low urgency since the base image is rebuildable.
|
||||
|
||||
**Phase 3 — OverlayFS per-run disk**
|
||||
|
||||
Replace the full per-run ext4 copy with an OverlayFS sparse layer. Largest disk
|
||||
impact (~90–95% savings per concurrent bottle) but highest implementation
|
||||
complexity. Track as a separate PRD.
|
||||
|
||||
---
|
||||
|
||||
## Open Questions
|
||||
|
||||
- Does the host have a configured object-store credential path, or should the
|
||||
remote store be an opt-in with an explicit `bb config set image-store.url ...`?
|
||||
- Should `commit` automatically upload, or should upload be an explicit step to
|
||||
avoid surprise egress?
|
||||
- What is the acceptable cold-start latency for a restore from remote? A 330 MB
|
||||
zstd tar at 100 Mbit/s takes ~26 s; at 1 Gbit/s, ~2.6 s. This bounds the
|
||||
retention strategy (evict from local after successful upload vs keep local copy).
|
||||
@@ -0,0 +1,359 @@
|
||||
# Rootless Docker inside Apple Container bottles
|
||||
|
||||
Spike branch: `spike/rootless-docker-macos` (`a4d8461`)
|
||||
|
||||
**Outcome:** the podman recommendation below shipped as the
|
||||
`nested_containers` bottle flag — see
|
||||
[`docs/prds/prd-new-nested-containers.md`](../prds/prd-new-nested-containers.md).
|
||||
The `docker_access` name used throughout the spike text was renamed on the
|
||||
way in; it granted no access to anything on the host.
|
||||
|
||||
## Summary
|
||||
|
||||
**Negative result.** Rootless Docker cannot run inside an Apple
|
||||
Container bottle without granting the bottle `CAP_SYS_ADMIN`. This is a
|
||||
kernel constraint on writing multi-range `uid_map`, not a packaging gap
|
||||
we can close with a better init script, a different base image, or more
|
||||
careful `/etc/subuid` handling.
|
||||
|
||||
The spike was built on the premise — stated in
|
||||
`bot_bottle/backend/macos_container/rootless_docker.py` — that it would
|
||||
*"deliberately refuse to compensate for missing prerequisites with outer
|
||||
capabilities, a privileged container, or a host Docker socket."* That
|
||||
premise is exactly what the experiment falsified. The two ways forward
|
||||
are to abandon the premise (add `CAP_SYS_ADMIN` to the bottle, and with
|
||||
it most of the isolation the bottle exists to provide) or to abandon
|
||||
rootless Docker.
|
||||
|
||||
Recommendation: abandon rootless Docker. Podman does not have this
|
||||
problem — see [Podman is not blocked by
|
||||
this](#podman-is-not-blocked-by-this) below.
|
||||
|
||||
## Local environment
|
||||
|
||||
Tested on 2026-07-21:
|
||||
|
||||
```console
|
||||
$ sw_vers
|
||||
ProductName: macOS
|
||||
ProductVersion: 26.5.1
|
||||
BuildVersion: 25F80
|
||||
|
||||
$ container --version
|
||||
container CLI version 1.0.0 (build: release, commit: ee848e3)
|
||||
|
||||
$ uname -a # inside the bottle
|
||||
Linux ... 6.18.15 #1 SMP Tue Mar 17 01:36:53 UTC 2026 aarch64 GNU/Linux
|
||||
```
|
||||
|
||||
## The failure
|
||||
|
||||
`tests/integration/test_macos_rootless_docker_spike.py` builds the
|
||||
image, launches the bottle, and dies in `rootless_docker.start`:
|
||||
|
||||
```
|
||||
+ exec rootlesskit --net=slirp4netns --mtu=65520 ... dockerd-rootless.sh
|
||||
[rootlesskit:parent] error: failed to setup UID/GID map:
|
||||
newuidmap 1100 [0 1000 1 1 100000 65536] failed:
|
||||
newuidmap: write to uid_map failed: Operation not permitted
|
||||
```
|
||||
|
||||
## Why it fails
|
||||
|
||||
Every prerequisite you would normally suspect is present and correct in
|
||||
the guest:
|
||||
|
||||
| Check | Result |
|
||||
| --- | --- |
|
||||
| `/usr/bin/newuidmap` | `-rwsr-xr-x root root` — setuid bit intact, survived the OCI export |
|
||||
| `/` mount options | `rw,relatime` — **not** `nosuid` |
|
||||
| `NoNewPrivs` | `0` |
|
||||
| `Seccomp` | `0`, no filters |
|
||||
| `/etc/subuid`, `/etc/subgid` | `node:100000:65536` in both |
|
||||
| user namespace | `user:[4026531837]`, identical to pid 1 — the *initial* userns |
|
||||
| `unshare -U -r true` | succeeds |
|
||||
| `/proc/sys/user/max_user_namespaces` | `4505` |
|
||||
|
||||
The one thing that is missing is in the capability bounding set that
|
||||
Apple Container gives the container:
|
||||
|
||||
```
|
||||
CapBnd: 00000000a80425fb
|
||||
= chown, dac_override, fowner, fsetid, kill, setgid, setuid, setpcap,
|
||||
net_bind_service, net_raw, sys_chroot, mknod, audit_write, setfcap
|
||||
```
|
||||
|
||||
No `CAP_SYS_ADMIN`. That is the whole story, and the chain is:
|
||||
|
||||
1. The kernel's `map_write()` gates writing a `uid_map` on
|
||||
`file_ns_capable(file, ns, CAP_SYS_ADMIN)` — capability over the
|
||||
**new** user namespace, evaluated against the credentials that opened
|
||||
`/proc/<pid>/uid_map`.
|
||||
2. `newuidmap` is setuid-root, so it runs with euid 0 — but its
|
||||
capability sets are clamped by the bounding set, which has no
|
||||
`CAP_SYS_ADMIN`.
|
||||
3. `cap_capable()` has a shortcut that grants *all* capabilities when
|
||||
the caller's userns is the new namespace's parent **and**
|
||||
`ns->owner == cred->euid`. It does not apply: the namespace was
|
||||
created by `node` (uid 1000) while `newuidmap` runs as euid 0.
|
||||
4. So the check falls through to the effective-set test in the initial
|
||||
userns, which fails. `EPERM`.
|
||||
|
||||
Note that the single-line unprivileged path (`unshare -U -r`) works
|
||||
precisely because it does not go through `newuidmap` and does not need
|
||||
`CAP_SYS_ADMIN`. Only the multi-range subuid mapping that rootless
|
||||
Docker requires does.
|
||||
|
||||
This is the same constraint that makes upstream's `dind-rootless` image
|
||||
require `--privileged`. It is not specific to Apple Container, except
|
||||
that Apple Container gives us no bounding set that includes
|
||||
`CAP_SYS_ADMIN` by default.
|
||||
|
||||
## It does work with the capability — which is the point
|
||||
|
||||
Adding the capability clears the failure immediately, and exposes one
|
||||
further, much smaller blocker: `/dev/net/tun` exists (the kernel has
|
||||
tun; `/proc/misc` lists `200 tun`) but Apple Container creates it
|
||||
`crw------- root root`, so uid 1000 cannot open it and `slirp4netns`
|
||||
fails with `open: Permission denied`. A `chmod 0666 /dev/net/tun` as
|
||||
root inside the bottle fixes that, and needs no capability beyond what
|
||||
the bottle already has.
|
||||
|
||||
With both applied by hand, the daemon comes up completely:
|
||||
|
||||
```console
|
||||
$ container run --rm -u root --cap-add CAP_SYS_ADMIN \
|
||||
bot-bottle-claude:latest-rootless-docker sh -c '...'
|
||||
Server Version: 20.10.24+dfsg1
|
||||
Storage Driver: fuse-overlayfs
|
||||
Cgroup Driver: none
|
||||
Cgroup Version: 2
|
||||
API listen on /tmp/rt/docker.sock
|
||||
```
|
||||
|
||||
So `rootless-docker-init.sh` and `rootless_docker.py` are *correct*.
|
||||
The spike did not fail on a bug. It failed on its own premise.
|
||||
|
||||
Two secondary findings from that run, relevant if anyone revisits this:
|
||||
|
||||
- Debian's `docker.io` package pins Docker **20.10** (EOL), not the 28.x
|
||||
implied by the `docker:28-cli` compose plugin the image copies in.
|
||||
- `Cgroup Driver: none` — no resource limits on nested containers.
|
||||
|
||||
## Why we should not just add the capability
|
||||
|
||||
`CAP_SYS_ADMIN` is close to a superset of "root" in practical terms —
|
||||
mount, `pivot_root`, namespace manipulation, and a long tail of
|
||||
subsystem-specific powers. Granting it to the agent bottle would
|
||||
undercut the containment argument the rest of the backend is built
|
||||
around, including the deliberately narrow choices immediately adjacent
|
||||
to it in `launch.py` (`--cap-drop CAP_NET_RAW`, no `NET_ADMIN`, a
|
||||
host-only agent network). Trading all of that for nested `docker
|
||||
compose` is a bad exchange.
|
||||
|
||||
## Podman is not blocked by this
|
||||
|
||||
Sanity-checked on the same host, same kernel, same runtime, so the
|
||||
comparison is apples to apples:
|
||||
|
||||
| Scenario | Result |
|
||||
| --- | --- |
|
||||
| Podman rootless, `/etc/subuid` populated | **Fails identically** — `newuidmap: write to uid_map failed: Operation not permitted` |
|
||||
| Podman rootless, no subuid ranges, `--network=host` | **Works**, no added capabilities |
|
||||
| Podman rootless, no subuid ranges, default netns, `/dev/net/tun` at `0600` | Fails — `slirp4netns: open("/dev/net/tun"): Permission denied` |
|
||||
| Podman rootless, no subuid ranges, default netns, `/dev/net/tun` at `0666` | **Works**, no added capabilities |
|
||||
|
||||
The difference is that podman degrades gracefully when no subuid range
|
||||
is available: it falls back to a single-UID self-mapping, which an
|
||||
unprivileged process may write itself, so `newuidmap` is never invoked
|
||||
and `CAP_SYS_ADMIN` is never needed. Docker's rootless mode has no
|
||||
equivalent fallback.
|
||||
|
||||
The cost of that fallback is real and should be weighed before building
|
||||
on it: with a single-UID mapping, every UID inside a nested container
|
||||
collapses onto the bottle's own uid 1000. There is no UID separation
|
||||
between the agent and anything it runs — `root` in a nested container is
|
||||
the agent user outside it. It also requires `ignore_chown_errors` on the
|
||||
storage driver. Whether that is acceptable depends on whether the bottle
|
||||
boundary (which is unchanged) or the nested-container boundary (which is
|
||||
effectively nil) is the one we are relying on.
|
||||
|
||||
## What the podman spike then needed
|
||||
|
||||
The podman implementation that replaced the Docker one on this branch
|
||||
turned up two more device-node blockers of the same shape as
|
||||
`/dev/net/tun` — Apple Container creates the node, but 0600 root:root:
|
||||
|
||||
- **`/dev/fuse`** — blocks the `fuse-overlayfs` storage driver
|
||||
(`fuse: failed to open /dev/fuse: Permission denied`). Without it the
|
||||
only working driver is `vfs`, which copies whole layers per container.
|
||||
- **`/dev/net/tun`** — blocks `slirp4netns`, which rootless podman uses
|
||||
for the default bridge network.
|
||||
|
||||
Both are fixed by `chmod 0666` as root inside the bottle, which needs no
|
||||
capability the bottle does not already hold. This is categorically
|
||||
different from the `CAP_SYS_ADMIN` requirement: it is a permission on a
|
||||
node that already exists, not an outer privilege grant.
|
||||
|
||||
One design note worth recording: the agent-facing surface stays `docker`
|
||||
and `docker compose`, pointed at podman's Docker-compatible API socket
|
||||
via `DOCKER_HOST`. Setting `netns="host"` in `containers.conf` does *not*
|
||||
propagate through that compat API — stock `docker run` and compose files
|
||||
request bridge networking explicitly — so slirp4netns (and therefore the
|
||||
`/dev/net/tun` chmod) is required for ordinary compose files to work at
|
||||
all. Host networking remains available per-workload via
|
||||
`--network=host`.
|
||||
|
||||
Verified working in a bottle with zero added capabilities: fuse-overlayfs
|
||||
storage, the compat API socket, `docker run` on both bridge and host
|
||||
networking, and published ports.
|
||||
|
||||
### Nested pulls collide with our own egress DLP
|
||||
|
||||
The first live run got podman up and `docker compose` running, then
|
||||
failed on the image pull:
|
||||
|
||||
```
|
||||
web Pulling
|
||||
initializing source docker://python:3.12-alpine: reading manifest ...
|
||||
StatusCode: 403, egress DLP: Generic Bearer JWT found in body
|
||||
```
|
||||
|
||||
This is bot-bottle's own egress scanner, not a podman problem. The
|
||||
Docker registry auth flow carries a bearer JWT *by protocol*, and the
|
||||
`token_patterns` detector's `Generic Bearer JWT` rule
|
||||
(`Bearer\s+[A-Za-z0-9._\-]{50,}`) matches it on every pull. Any bottle
|
||||
that pulls images will hit this.
|
||||
|
||||
The fix is per-route detector scoping, which the egress config already
|
||||
supports — drop `token_patterns` on the registry hosts and keep
|
||||
`known_secrets`:
|
||||
|
||||
```json
|
||||
{"host": "registry-1.docker.io",
|
||||
"dlp": {"outbound_detectors": ["known_secrets"]}}
|
||||
```
|
||||
|
||||
That is the right trade rather than a grudging one: `known_secrets`
|
||||
matches the bottle's *actual* credential values, so real exfil through a
|
||||
registry host is still caught. `token_patterns` on a registry route only
|
||||
ever produces protocol noise.
|
||||
|
||||
Worth generalising later: any manifest enabling `nested_containers` needs
|
||||
this on its registry routes, so it probably belongs in a shared
|
||||
registry-route snippet rather than being copy-pasted per bottle.
|
||||
|
||||
### And then registry auth collides with the Authorization strip
|
||||
|
||||
With DLP scoped, the pull failed differently: `unauthorized:
|
||||
authentication required`. This one is architectural.
|
||||
|
||||
`egress_addon.py` strips agent-set `Authorization` unconditionally
|
||||
before forwarding — deliberately, so an agent cannot smuggle a
|
||||
credential out in a header the DLP detectors don't recognise. A route
|
||||
may carry gateway-injected auth instead, but only from a *static* token
|
||||
in an env var (`auth_scheme` + `token_env`).
|
||||
|
||||
Docker registry auth doesn't fit that shape. The client fetches a
|
||||
short-lived, per-repository-scope bearer token from `auth.docker.io` and
|
||||
presents it to `registry-1.docker.io`. There is no static token to
|
||||
inject, and the token the client legitimately obtained is stripped.
|
||||
|
||||
Measured inside a bottle, by hand:
|
||||
|
||||
| Step | Result |
|
||||
| --- | --- |
|
||||
| Fetch token from `auth.docker.io` | 200, 5409-byte token body |
|
||||
| Manifest request **with** that valid token | 401 |
|
||||
| Manifest request with **no** Authorization | 401 — identical |
|
||||
|
||||
A valid token behaves exactly like sending none, which is direct
|
||||
evidence the header never arrives. Any nested-container workflow that
|
||||
pulls from a registry is blocked on this, so it is not a detail that can
|
||||
be deferred: pulling base images is most of what nested containers are
|
||||
for.
|
||||
|
||||
### Registries that skip the token dance work today
|
||||
|
||||
Not every registry needs the stripped header. Measured directly:
|
||||
|
||||
| Registry | Manifest request with no `Authorization` |
|
||||
| --- | --- |
|
||||
| `quay.io` | 200 |
|
||||
| `mcr.microsoft.com` | 200 |
|
||||
| `registry.k8s.io` | 307 (redirect, no auth) |
|
||||
| `ghcr.io` | 401 |
|
||||
| `registry-1.docker.io` | 401 |
|
||||
|
||||
So "just add the registry to the bottle config" genuinely works — for
|
||||
quay, MCR, registry.k8s.io, or any unauthenticated internal registry.
|
||||
Docker Hub and GHCR are the ones that need the strip resolved. The
|
||||
acceptance test uses quay for exactly this reason.
|
||||
|
||||
Resolving it for Docker Hub means picking one of:
|
||||
|
||||
1. **Per-route opt-in to preserve client Authorization.** Smallest
|
||||
change. Note the compounding effect on exactly these routes: the DLP
|
||||
scoping above already removed `token_patterns` there, so a
|
||||
preserved-auth registry route is one where the agent may send bearer
|
||||
tokens that neither the strip nor the pattern detector inspects.
|
||||
`known_secrets` still applies, so the bottle's real credentials are
|
||||
still caught.
|
||||
2. **A registry-aware gateway** that performs the token dance itself and
|
||||
injects the result. Preserves the invariant fully; materially more
|
||||
work, and it makes the gateway speak a specific registry protocol.
|
||||
3. **Pre-seed images at provision time** (host-side `container image
|
||||
save` into podman storage), so bottles never pull at runtime.
|
||||
Preserves the invariant, and limits nested containers to
|
||||
pre-approved images — which fits the custody positioning, at the cost
|
||||
of no ad-hoc `docker pull`.
|
||||
4. **Stop.** Nested containers are not supported on this backend.
|
||||
|
||||
### Podman 4.3.1 silently swallows container exit codes
|
||||
|
||||
Debian bookworm — which the current agent base image is built on —
|
||||
ships podman 4.3.1. Through its Docker-compatible API, `docker run`
|
||||
returns 0 no matter what the container did:
|
||||
|
||||
| Command | podman 4.3.1 | podman 5.4.2 |
|
||||
| --- | --- | --- |
|
||||
| `docker run … sh -c 'exit 7'` (compat API) | **0** | 7 |
|
||||
| `docker run … sh -c 'exit 0'` (compat API) | 0 | 0 |
|
||||
| `podman run … sh -c 'exit 7'` (native) | 7 | 7 |
|
||||
|
||||
This is worse than a broken feature: every failing command an agent runs
|
||||
via `docker run` reports success. A test suite, a build step, or a CI
|
||||
script inside a bottle would pass while failing. It also silently
|
||||
defeated the acceptance test's egress-containment assertion, which is
|
||||
why that assertion now checks an in-band marker rather than an exit
|
||||
code.
|
||||
|
||||
Podman 5.4.2 (Debian trixie) fixes it, but needs two packages that
|
||||
bookworm's podman does not: `passt` (podman 5's default network tool)
|
||||
and `nftables` (netavark shells out to `nft`; without it every run fails
|
||||
with `unable to upgrade to tcp, received 500`). With both installed,
|
||||
exit codes propagate correctly and the compat API behaves.
|
||||
|
||||
The open question this leaves is where podman 5 comes from, since the
|
||||
agent base is bookworm-based:
|
||||
|
||||
1. **Move the agent images to Debian trixie.** Trixie is current stable.
|
||||
Correct, and the blast radius is every bottle, not just this feature.
|
||||
2. **Drop the compat socket and use podman natively** (`podman-docker`
|
||||
provides a `docker` shim; compose comes from `podman-compose`).
|
||||
Native podman propagates exit codes correctly even on 4.3.1. Contained
|
||||
to this feature, at the cost of `docker compose` becoming
|
||||
`docker-compose`/`podman-compose`.
|
||||
3. **Ship bookworm's podman 4.3.1 with the compat socket** — not viable.
|
||||
Silent false success is a correctness bug agents cannot see.
|
||||
|
||||
## Recommendation
|
||||
|
||||
1. Do not revive rootless Docker on this backend. This document is the
|
||||
record of why.
|
||||
2. Nested containers, if wanted, come from podman under the
|
||||
single-mapping constraint — with the explicit understanding that the
|
||||
nested-container boundary carries no security weight. `root` in a
|
||||
nested container is the agent user outside it.
|
||||
3. Nested containers are therefore a build/test convenience. The bottle
|
||||
remains the security boundary, exactly as it was.
|
||||
+28
-8
@@ -1,15 +1,19 @@
|
||||
#!/usr/bin/env bash
|
||||
# Combined unit + integration coverage (see docs/decisions/0004-coverage-policy.md).
|
||||
#
|
||||
# Runs the unit suite, then appends the integration suite (which skips
|
||||
# cleanly when Docker / the backend CLIs are unavailable), and prints one
|
||||
# combined report. The integration suite is what scores the subprocess /
|
||||
# backend orchestration modules, so the number here is the policy's
|
||||
# yardstick — not the unit-only badge.
|
||||
# Two modes:
|
||||
#
|
||||
# Usage:
|
||||
# scripts/coverage.sh # combined report
|
||||
# scripts/coverage.sh critical # also report just the critical modules
|
||||
# scripts/coverage.sh [critical]
|
||||
# Run mode (default, for local dev): executes the unit suite then the
|
||||
# integration suite under coverage and prints a combined report.
|
||||
#
|
||||
# scripts/coverage.sh aggregate [critical]
|
||||
# Aggregate mode (used by CI): combines pre-existing .coverage.* files
|
||||
# produced by individual test jobs and prints a combined report. No tests
|
||||
# are re-executed; no KVM or Docker dependency.
|
||||
#
|
||||
# Pass "critical" as the last argument in either mode to also report just the
|
||||
# critical modules (ADR 0004 target: 90%).
|
||||
set -euo pipefail
|
||||
|
||||
cd "$(dirname "$0")/.."
|
||||
@@ -21,6 +25,22 @@ PY="${PYTHON:-python3}"
|
||||
# README "core coverage" badge can't drift; comma-join it for --include.
|
||||
CRITICAL=$(grep -vE '^[[:space:]]*(#|$)' scripts/critical-modules.txt | paste -sd, -)
|
||||
|
||||
if [ "${1:-}" = "aggregate" ]; then
|
||||
# Aggregate mode: combine .coverage.* artifacts already in the workspace.
|
||||
echo "== combining coverage artifacts ==" >&2
|
||||
"$PY" -m coverage combine
|
||||
|
||||
echo "== combined report ==" >&2
|
||||
"$PY" -m coverage report -m
|
||||
|
||||
if [ "${2:-}" = "critical" ]; then
|
||||
echo "== critical modules (ADR 0004 target: 90%) ==" >&2
|
||||
"$PY" -m coverage report --include="$CRITICAL"
|
||||
fi
|
||||
exit 0
|
||||
fi
|
||||
|
||||
# Run mode (default): execute both suites under coverage in this process.
|
||||
rm -f .coverage
|
||||
|
||||
echo "== unit ==" >&2
|
||||
|
||||
@@ -172,7 +172,7 @@ class TestSandboxEscape(unittest.TestCase):
|
||||
# base image without producing five confusing
|
||||
# command-not-found failures down the suite.
|
||||
missing: list[str] = []
|
||||
for tool in ("curl", "git", "dig"):
|
||||
for tool in ("curl", "git", "dig", "ssh"):
|
||||
r = cls._bottle.exec(f"command -v {tool} >/dev/null 2>&1")
|
||||
if r.returncode != 0:
|
||||
missing.append(tool)
|
||||
|
||||
@@ -46,7 +46,9 @@ def _manifest(*, supervise: bool, with_git: bool, with_egress: bool) -> Manifest
|
||||
bottle["egress"] = {
|
||||
"routes": [{
|
||||
"host": "api.example",
|
||||
"auth": {"scheme": "Bearer", "token_ref": "TOK"},
|
||||
"inspect": {
|
||||
"auth": {"scheme": "Bearer", "token_ref": "TOK"},
|
||||
},
|
||||
}],
|
||||
}
|
||||
return ManifestIndex.from_json_obj({
|
||||
|
||||
@@ -9,11 +9,15 @@ import unittest
|
||||
from pathlib import Path
|
||||
|
||||
from bot_bottle.agent_provider import (
|
||||
CLAUDE_HOST_CREDENTIAL_HOSTS,
|
||||
CODEX_HOST_CREDENTIAL_HOSTS,
|
||||
build_agent_provision_plan,
|
||||
prompt_args,
|
||||
)
|
||||
from bot_bottle.egress import CODEX_HOST_CREDENTIAL_TOKEN_REF
|
||||
from bot_bottle.egress import (
|
||||
CLAUDE_HOST_CREDENTIAL_TOKEN_REF,
|
||||
CODEX_HOST_CREDENTIAL_TOKEN_REF,
|
||||
)
|
||||
|
||||
|
||||
def _jwt(exp: int) -> str:
|
||||
@@ -292,6 +296,67 @@ class TestAgentProviderRuntime(unittest.TestCase):
|
||||
)
|
||||
self.assertEqual({}, plan.provisioned_env)
|
||||
|
||||
def test_claude_forward_host_credentials_populates_egress_route(self):
|
||||
access_token = "sk-ant-oat01-test-key" # gitleaks:allow
|
||||
with tempfile.TemporaryDirectory(prefix="bb-provider.") as tmp:
|
||||
home = Path(tmp) / "host-claude"
|
||||
cred_dir = home / ".claude"
|
||||
cred_dir.mkdir(parents=True)
|
||||
(cred_dir / ".credentials.json").write_text(json.dumps({
|
||||
"claudeAiOauth": {"accessToken": access_token},
|
||||
}))
|
||||
plan = build_agent_provision_plan(
|
||||
template="claude",
|
||||
dockerfile="",
|
||||
state_dir=Path(tmp),
|
||||
instance_name="bot-bottle-test",
|
||||
prompt_file=Path(tmp) / "prompt.txt",
|
||||
forward_host_credentials=True,
|
||||
host_env={"HOME": str(home)},
|
||||
)
|
||||
self.assertEqual(1, len(plan.egress_routes))
|
||||
route = plan.egress_routes[0]
|
||||
self.assertIn(route.host, CLAUDE_HOST_CREDENTIAL_HOSTS)
|
||||
self.assertEqual("Bearer", route.auth_scheme)
|
||||
self.assertEqual(CLAUDE_HOST_CREDENTIAL_TOKEN_REF, route.token_ref)
|
||||
self.assertEqual("egress-placeholder", plan.env_vars["CLAUDE_CODE_OAUTH_TOKEN"])
|
||||
self.assertEqual(frozenset({"CLAUDE_CODE_OAUTH_TOKEN"}), plan.hidden_env_names)
|
||||
|
||||
def test_claude_forward_host_credentials_populates_provisioned_env(self):
|
||||
access_token = "sk-ant-oat01-test-key" # gitleaks:allow
|
||||
with tempfile.TemporaryDirectory(prefix="bb-provider.") as tmp:
|
||||
home = Path(tmp) / "host-claude"
|
||||
cred_dir = home / ".claude"
|
||||
cred_dir.mkdir(parents=True)
|
||||
(cred_dir / ".credentials.json").write_text(json.dumps({
|
||||
"claudeAiOauth": {"accessToken": access_token},
|
||||
}))
|
||||
plan = build_agent_provision_plan(
|
||||
template="claude",
|
||||
dockerfile="",
|
||||
state_dir=Path(tmp),
|
||||
instance_name="bot-bottle-test",
|
||||
prompt_file=Path(tmp) / "prompt.txt",
|
||||
forward_host_credentials=True,
|
||||
host_env={"HOME": str(home)},
|
||||
)
|
||||
self.assertEqual(
|
||||
{CLAUDE_HOST_CREDENTIAL_TOKEN_REF: access_token},
|
||||
plan.provisioned_env,
|
||||
)
|
||||
|
||||
def test_claude_without_forward_host_credentials_has_empty_provisioned_env(self):
|
||||
with tempfile.TemporaryDirectory(prefix="bb-provider.") as tmp:
|
||||
plan = build_agent_provision_plan(
|
||||
template="claude",
|
||||
dockerfile="",
|
||||
state_dir=Path(tmp),
|
||||
instance_name="bot-bottle-test",
|
||||
prompt_file=Path(tmp) / "prompt.txt",
|
||||
forward_host_credentials=False,
|
||||
)
|
||||
self.assertEqual({}, plan.provisioned_env)
|
||||
|
||||
def test_pi_plan_writes_default_ollama_models(self):
|
||||
with tempfile.TemporaryDirectory(prefix="bb-provider.") as tmp:
|
||||
plan = build_agent_provision_plan(
|
||||
|
||||
@@ -21,7 +21,7 @@ from bot_bottle.backend.firecracker import FirecrackerBottleBackend
|
||||
from bot_bottle.manifest import ManifestIndex
|
||||
|
||||
|
||||
def _manifest() -> ManifestIndex:
|
||||
def _manifest(*, nested_containers: bool = False) -> ManifestIndex:
|
||||
return ManifestIndex.from_json_obj({
|
||||
"bottles": {
|
||||
"dev": {
|
||||
@@ -29,6 +29,7 @@ def _manifest() -> ManifestIndex:
|
||||
"LITERAL_ENV": "literal-value",
|
||||
"FORWARDED_ENV": "${HOST_SECRET_ENV}",
|
||||
},
|
||||
"nested_containers": nested_containers,
|
||||
},
|
||||
},
|
||||
"agents": {
|
||||
@@ -41,9 +42,11 @@ def _manifest() -> ManifestIndex:
|
||||
})
|
||||
|
||||
|
||||
def _spec(tmp: Path, *, identity: str) -> BottleSpec:
|
||||
def _spec(
|
||||
tmp: Path, *, identity: str, nested_containers: bool = False,
|
||||
) -> BottleSpec:
|
||||
return BottleSpec(
|
||||
manifest=_manifest(),
|
||||
manifest=_manifest(nested_containers=nested_containers),
|
||||
agent_name="demo",
|
||||
copy_cwd=False,
|
||||
user_cwd=str(tmp),
|
||||
@@ -113,6 +116,42 @@ class TestFirecrackerPrepare(_FakeStateMixin, unittest.TestCase):
|
||||
self.assertEqual({"FORWARDED_ENV": "secret-value"}, plan.forwarded_env)
|
||||
|
||||
|
||||
class TestNestedContainersRejection(_FakeStateMixin, unittest.TestCase):
|
||||
"""A backend with no guest-local engine must refuse the flag outright.
|
||||
|
||||
Ignoring it would leave the agent without `docker`, and the only ways to
|
||||
fake it here (a host daemon socket, a privileged container) are what
|
||||
issue #392 rules out.
|
||||
"""
|
||||
|
||||
def test_docker_backend_refuses_the_flag(self) -> None:
|
||||
backend = DockerBottleBackend()
|
||||
spec = _spec(
|
||||
Path(self.tmp.name), identity="demo-docker", nested_containers=True,
|
||||
)
|
||||
with (
|
||||
patch(
|
||||
"bot_bottle.backend.resolve_common.die", side_effect=RuntimeError,
|
||||
) as die,
|
||||
self.assertRaises(RuntimeError),
|
||||
):
|
||||
backend.prepare(spec, Path(self.tmp.name) / "stage")
|
||||
self.assertIn("nested_containers", die.call_args.args[0])
|
||||
self.assertIn("docker", die.call_args.args[0])
|
||||
|
||||
def test_firecracker_backend_refuses_the_flag(self) -> None:
|
||||
backend = FirecrackerBottleBackend()
|
||||
spec = _spec(Path(self.tmp.name), identity="demo-fc", nested_containers=True)
|
||||
with (
|
||||
patch(
|
||||
"bot_bottle.backend.resolve_common.die", side_effect=RuntimeError,
|
||||
) as die,
|
||||
self.assertRaises(RuntimeError),
|
||||
):
|
||||
backend.prepare(spec, Path(self.tmp.name) / "stage")
|
||||
self.assertIn("firecracker", die.call_args.args[0])
|
||||
|
||||
|
||||
class TestMintSlug(unittest.TestCase):
|
||||
def _spec(self, *, label: str = "", identity: str = "") -> BottleSpec:
|
||||
manifest = _manifest()
|
||||
|
||||
@@ -0,0 +1,160 @@
|
||||
"""Backend-agnostic and backend-specific encrypted-secret recovery tests."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import json
|
||||
import subprocess
|
||||
import tempfile
|
||||
import unittest
|
||||
from pathlib import Path
|
||||
from types import SimpleNamespace
|
||||
from unittest.mock import Mock, patch
|
||||
|
||||
from bot_bottle.orchestrator.reprovision import reprovision_bottles
|
||||
from bot_bottle.backend.firecracker import consolidated_launch as fc
|
||||
from bot_bottle.backend.macos_container import consolidated_launch as mac
|
||||
from bot_bottle.backend.docker import consolidated_launch as docker
|
||||
from bot_bottle.orchestrator.client import OrchestratorClientError
|
||||
|
||||
|
||||
def _proc(returncode: int = 0, stdout: str = "", stderr: str = ""):
|
||||
return subprocess.CompletedProcess([], returncode, stdout=stdout, stderr=stderr)
|
||||
|
||||
|
||||
class TestSharedReprovision(unittest.TestCase):
|
||||
def test_joins_registry_records_by_source_ip(self) -> None:
|
||||
client = Mock()
|
||||
client.list_bottles.return_value = [
|
||||
{"bottle_id": "b1", "source_ip": "10.0.0.1"},
|
||||
{"bottle_id": "b2", "source_ip": "10.0.0.2"},
|
||||
{"bottle_id": 3, "source_ip": "10.0.0.3"},
|
||||
]
|
||||
client.reprovision_gateway.side_effect = [True, False]
|
||||
count = reprovision_bottles(
|
||||
client, {"10.0.0.1": " key-1\n", "10.0.0.2": "key-2"},
|
||||
)
|
||||
self.assertEqual(1, count)
|
||||
self.assertEqual(
|
||||
[("b1", "key-1"), ("b2", "key-2")],
|
||||
[call.args for call in client.reprovision_gateway.call_args_list],
|
||||
)
|
||||
|
||||
def test_one_failure_does_not_block_other_bottles(self) -> None:
|
||||
client = Mock()
|
||||
client.list_bottles.return_value = [
|
||||
{"bottle_id": "b1", "source_ip": "10.0.0.1"},
|
||||
{"bottle_id": "b2", "source_ip": "10.0.0.2"},
|
||||
]
|
||||
client.reprovision_gateway.side_effect = [
|
||||
OrchestratorClientError("bad key"), True,
|
||||
]
|
||||
self.assertEqual(
|
||||
1,
|
||||
reprovision_bottles(
|
||||
client, {"10.0.0.1": "key-1", "10.0.0.2": "key-2"},
|
||||
),
|
||||
)
|
||||
|
||||
|
||||
class TestMacosReprovision(unittest.TestCase):
|
||||
def test_reads_configured_container_env_and_reprovisions(self) -> None:
|
||||
endpoint = mac.GatewayEndpoint("http://orch", "10.0.0.9", "PEM", "net")
|
||||
agent = SimpleNamespace(slug="demo")
|
||||
client = Mock()
|
||||
with patch.object(mac, "enumerate_active", return_value=[agent]), \
|
||||
patch.object(mac.container_mod, "inspect_container_network_ip",
|
||||
return_value="10.0.0.1"), \
|
||||
patch.object(mac.container_mod, "read_container_env", return_value="key"), \
|
||||
patch.object(mac, "OrchestratorClient", return_value=client), \
|
||||
patch.object(mac, "reprovision_bottles", return_value=1) as restore, \
|
||||
patch.object(mac, "info"):
|
||||
mac._reprovision_running_bottles(endpoint)
|
||||
restore.assert_called_once_with(client, {"10.0.0.1": "key"})
|
||||
|
||||
def test_enumeration_failure_is_best_effort(self) -> None:
|
||||
endpoint = mac.GatewayEndpoint("http://orch", "10.0.0.9", "PEM", "net")
|
||||
with patch.object(mac, "enumerate_active",
|
||||
side_effect=mac.EnumerationError("failed")), \
|
||||
patch.object(mac, "info") as info:
|
||||
mac._reprovision_running_bottles(endpoint)
|
||||
self.assertIn("skipped", info.call_args.args[0])
|
||||
|
||||
|
||||
class TestDockerReprovision(unittest.TestCase):
|
||||
def test_maps_network_containers_to_keys(self) -> None:
|
||||
inspect = _proc(stdout=(
|
||||
"bot-bottle-infra 172.18.0.2/16\n"
|
||||
"bot-bottle-a 172.18.0.3/16\n"
|
||||
"malformed\n"
|
||||
))
|
||||
key = _proc(stdout="secret\n")
|
||||
client = Mock()
|
||||
with patch.object(docker, "OrchestratorClient", return_value=client), \
|
||||
patch.object(docker, "run_docker", side_effect=[inspect, key]), \
|
||||
patch.object(docker, "reprovision_bottles", return_value=1) as restore, \
|
||||
patch.object(docker.log, "info"):
|
||||
docker._reprovision_running_bottles("http://orch")
|
||||
restore.assert_called_once_with(client, {"172.18.0.3": "secret"})
|
||||
|
||||
def test_missing_docker_is_best_effort(self) -> None:
|
||||
with patch.object(docker, "run_docker", side_effect=FileNotFoundError("docker")), \
|
||||
patch.object(docker.log, "info") as info:
|
||||
docker._reprovision_running_bottles("http://orch")
|
||||
self.assertIn("skipped", info.call_args.args[0])
|
||||
|
||||
|
||||
class TestFirecrackerReprovision(unittest.TestCase):
|
||||
def _run_dir(self, root: Path, ip: str = "10.243.0.3") -> Path:
|
||||
run_dir = root / "demo"
|
||||
run_dir.mkdir()
|
||||
(run_dir / "bottle_id_ed25519").write_text("key")
|
||||
(run_dir / "config.json").write_text(json.dumps({
|
||||
"boot-source": {"boot_args": f"root=/dev/vda ip={ip}::gw:mask::eth0:off"}
|
||||
}))
|
||||
return run_dir
|
||||
|
||||
def test_extracts_guest_ip_from_config(self) -> None:
|
||||
with tempfile.TemporaryDirectory() as tmp:
|
||||
run_dir = self._run_dir(Path(tmp))
|
||||
self.assertEqual("10.243.0.3", fc._guest_ip_from_config(run_dir / "config.json"))
|
||||
self.assertEqual("", fc._guest_ip_from_config(run_dir / "missing.json"))
|
||||
|
||||
def test_persists_key_over_stdin_not_argv(self) -> None:
|
||||
with patch.object(fc.util, "ssh_base_argv", return_value=["ssh", "guest"]), \
|
||||
patch.object(fc.subprocess, "run", return_value=_proc()) as run:
|
||||
fc.persist_env_var_secret(Path("/key"), "10.0.0.1", "super-secret")
|
||||
self.assertEqual("super-secret", run.call_args.kwargs["input"])
|
||||
self.assertNotIn("super-secret", " ".join(run.call_args.args[0]))
|
||||
|
||||
def test_persist_failure_is_fatal_to_launch(self) -> None:
|
||||
with patch.object(fc.util, "ssh_base_argv", return_value=["ssh", "guest"]), \
|
||||
patch.object(fc.subprocess, "run", return_value=_proc(1, stderr="denied")):
|
||||
with self.assertRaisesRegex(fc.ConsolidatedLaunchError, "denied"):
|
||||
fc.persist_env_var_secret(Path("/key"), "10.0.0.1", "secret")
|
||||
|
||||
def test_reads_live_vm_key_and_reprovisions(self) -> None:
|
||||
with tempfile.TemporaryDirectory() as tmp:
|
||||
run_dir = self._run_dir(Path(tmp))
|
||||
client = Mock()
|
||||
with patch.object(fc.cleanup, "live_run_dirs", return_value=(run_dir,)), \
|
||||
patch.object(fc.util, "ssh_base_argv", return_value=["ssh", "guest"]), \
|
||||
patch.object(fc.subprocess, "run", return_value=_proc(stdout="secret\n")), \
|
||||
patch.object(fc, "reprovision_bottles", return_value=1) as restore, \
|
||||
patch.object(fc, "info"):
|
||||
fc._reprovision_running_bottles(client)
|
||||
restore.assert_called_once_with(client, {"10.243.0.3": "secret"})
|
||||
|
||||
def test_unreadable_vm_is_skipped(self) -> None:
|
||||
with tempfile.TemporaryDirectory() as tmp:
|
||||
run_dir = self._run_dir(Path(tmp))
|
||||
client = Mock()
|
||||
with patch.object(fc.cleanup, "live_run_dirs", return_value=(run_dir,)), \
|
||||
patch.object(fc.util, "ssh_base_argv", return_value=["ssh", "guest"]), \
|
||||
patch.object(fc.subprocess, "run", return_value=_proc(1)), \
|
||||
patch.object(fc, "reprovision_bottles", return_value=0) as restore:
|
||||
fc._reprovision_running_bottles(client)
|
||||
restore.assert_called_once_with(client, {})
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
unittest.main()
|
||||
@@ -0,0 +1,29 @@
|
||||
"""Unit: shared cross-backend helpers in backend/util.py."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import unittest
|
||||
from unittest.mock import patch
|
||||
|
||||
from bot_bottle.backend import util as backend_util
|
||||
|
||||
|
||||
class TestPollCaCert(unittest.TestCase):
|
||||
def test_returns_pem_on_first_success(self) -> None:
|
||||
result = backend_util.poll_ca_cert(lambda: "PEM", timeout=1.0)
|
||||
self.assertEqual("PEM", result)
|
||||
|
||||
def test_raises_timeout_error_when_cert_never_appears(self) -> None:
|
||||
with self.assertRaises(TimeoutError):
|
||||
backend_util.poll_ca_cert(lambda: None, timeout=0.0)
|
||||
|
||||
def test_polls_until_cert_appears(self) -> None:
|
||||
responses = iter([None, None, "-----BEGIN CERTIFICATE-----\n"])
|
||||
with patch("bot_bottle.backend.util.time.sleep") as mock_sleep:
|
||||
result = backend_util.poll_ca_cert(lambda: next(responses), timeout=5.0)
|
||||
self.assertTrue(result.startswith("-----BEGIN CERTIFICATE-----"))
|
||||
self.assertEqual(2, mock_sleep.call_count)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
unittest.main()
|
||||
@@ -0,0 +1,51 @@
|
||||
"""Unit contracts shared by all built-in agent images."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import re
|
||||
import unittest
|
||||
from pathlib import Path
|
||||
|
||||
|
||||
_CONTRIB_DIR = Path(__file__).resolve().parents[2] / "bot_bottle/contrib"
|
||||
_AGENT_DOCKERFILES = tuple(sorted(_CONTRIB_DIR.glob("*/Dockerfile")))
|
||||
|
||||
|
||||
class TestBuiltinAgentImages(unittest.TestCase):
|
||||
def test_all_use_debian_trixie_stable(self):
|
||||
self.assertTrue(_AGENT_DOCKERFILES)
|
||||
for dockerfile in _AGENT_DOCKERFILES:
|
||||
with self.subTest(provider=dockerfile.parent.name):
|
||||
self.assertRegex(
|
||||
dockerfile.read_text(),
|
||||
r"(?m)^FROM node:22-trixie-slim\s*$",
|
||||
)
|
||||
|
||||
def test_none_install_podman(self):
|
||||
# podman lives in the nested-containers derived layer (nested_containers.py),
|
||||
# not in the base agent images, so bottles without the flag pay no cost.
|
||||
for dockerfile in _AGENT_DOCKERFILES:
|
||||
with self.subTest(provider=dockerfile.parent.name):
|
||||
self.assertNotRegex(
|
||||
dockerfile.read_text(),
|
||||
re.compile(r"(?m)^\s*podman(?:\s|\\|$)"),
|
||||
)
|
||||
|
||||
def test_all_install_ssh_client(self):
|
||||
for dockerfile in _AGENT_DOCKERFILES:
|
||||
with self.subTest(provider=dockerfile.parent.name):
|
||||
self.assertRegex(
|
||||
dockerfile.read_text(),
|
||||
re.compile(r"(?m)^\s*openssh-client(?:\s|\\|$)"),
|
||||
)
|
||||
|
||||
def test_all_prepare_node_git_config_directory(self):
|
||||
for dockerfile in _AGENT_DOCKERFILES:
|
||||
with self.subTest(provider=dockerfile.parent.name):
|
||||
dockerfile_text = dockerfile.read_text()
|
||||
self.assertIn("install -d -o node -g node", dockerfile_text)
|
||||
self.assertIn("/home/node/.config/git", dockerfile_text)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
unittest.main()
|
||||
+138
-17
@@ -6,6 +6,9 @@ import json
|
||||
import os
|
||||
import tempfile
|
||||
import unittest
|
||||
import urllib.error
|
||||
from email.message import Message
|
||||
from typing import Any
|
||||
from unittest.mock import MagicMock, patch
|
||||
|
||||
|
||||
@@ -16,7 +19,9 @@ class TestFlagParsing(unittest.TestCase):
|
||||
|
||||
def test_console_url_equals_form(self) -> None:
|
||||
from bot_bottle.cli.login import _flag
|
||||
self.assertEqual(_flag(["--console-url=http://x"], "--console-url"), "http://x")
|
||||
self.assertEqual(
|
||||
_flag(["--console-url=http://x"], "--console-url"), "http://x"
|
||||
)
|
||||
|
||||
def test_label_flag(self) -> None:
|
||||
from bot_bottle.cli.login import _flag
|
||||
@@ -27,6 +32,42 @@ class TestFlagParsing(unittest.TestCase):
|
||||
self.assertIsNone(_flag([], "--console-url"))
|
||||
|
||||
|
||||
class TestHttpHelpers(unittest.TestCase):
|
||||
def test_post_sends_json_and_decodes_response(self) -> None:
|
||||
from bot_bottle.cli.login import _post
|
||||
|
||||
response = MagicMock()
|
||||
response.__enter__.return_value.read.return_value = b'{"ok": true}'
|
||||
with patch("urllib.request.urlopen", return_value=response) as urlopen:
|
||||
self.assertEqual(
|
||||
_post("http://console/start", {"label": "host"}), {"ok": True}
|
||||
)
|
||||
|
||||
request = urlopen.call_args.args[0]
|
||||
self.assertEqual(request.data, b'{"label": "host"}')
|
||||
self.assertEqual(request.get_header("Content-type"), "application/json")
|
||||
|
||||
def test_get_decodes_success_response(self) -> None:
|
||||
from bot_bottle.cli.login import _get
|
||||
|
||||
response = MagicMock()
|
||||
response.__enter__.return_value.status = 200
|
||||
response.__enter__.return_value.read.return_value = b'{"status": "pending"}'
|
||||
with patch("urllib.request.urlopen", return_value=response):
|
||||
self.assertEqual(
|
||||
_get("http://console/status"), (200, {"status": "pending"})
|
||||
)
|
||||
|
||||
def test_get_returns_http_error_status(self) -> None:
|
||||
from bot_bottle.cli.login import _get
|
||||
|
||||
error = urllib.error.HTTPError(
|
||||
"http://console/status", 410, "gone", Message(), None
|
||||
)
|
||||
with patch("urllib.request.urlopen", side_effect=error):
|
||||
self.assertEqual(_get("http://console/status"), (410, {}))
|
||||
|
||||
|
||||
class TestSaveCredentials(unittest.TestCase):
|
||||
def test_writes_json_and_sets_perms(self) -> None:
|
||||
from bot_bottle.cli.login import _save_credentials
|
||||
@@ -42,8 +83,47 @@ class TestSaveCredentials(unittest.TestCase):
|
||||
self.assertEqual(data["refresh_token"], "rt")
|
||||
self.assertEqual(oct(path.stat().st_mode & 0o777), oct(0o600))
|
||||
|
||||
def test_temp_file_is_private_before_replace(self) -> None:
|
||||
"""Temp file must be 0600 at the moment os.replace is called."""
|
||||
from bot_bottle.cli.login import _save_credentials
|
||||
from pathlib import Path as _Path
|
||||
|
||||
tmp_perms_at_replace: list[int] = []
|
||||
real_replace = os.replace
|
||||
|
||||
def _spy_replace(
|
||||
src: str | os.PathLike[str], dst: str | os.PathLike[str]
|
||||
) -> None:
|
||||
tmp_perms_at_replace.append(_Path(src).stat().st_mode & 0o777)
|
||||
real_replace(src, dst)
|
||||
|
||||
with tempfile.TemporaryDirectory() as tmp:
|
||||
with patch.dict(os.environ, {"BOT_BOTTLE_ROOT": tmp}):
|
||||
with patch("os.replace", side_effect=_spy_replace):
|
||||
path = _save_credentials("http://c", "hid", "at", "rt")
|
||||
self.assertEqual(len(tmp_perms_at_replace), 1)
|
||||
self.assertEqual(oct(tmp_perms_at_replace[0]), oct(0o600))
|
||||
self.assertEqual(oct(path.stat().st_mode & 0o777), oct(0o600))
|
||||
|
||||
def test_cleanup_on_write_failure(self) -> None:
|
||||
"""Temp file is removed and no credentials remain if replace fails."""
|
||||
from bot_bottle.cli.login import _save_credentials
|
||||
|
||||
with tempfile.TemporaryDirectory() as tmp:
|
||||
with patch.dict(os.environ, {"BOT_BOTTLE_ROOT": tmp}):
|
||||
with patch("os.replace", side_effect=OSError("disk full")):
|
||||
with self.assertRaises(OSError):
|
||||
_save_credentials("http://c", "hid", "at", "rt")
|
||||
leftovers = [f for f in os.listdir(tmp) if f.startswith(".console-")]
|
||||
self.assertEqual(leftovers, [])
|
||||
|
||||
|
||||
class TestCmdLoginMissingUrl(unittest.TestCase):
|
||||
def test_help_returns_0(self) -> None:
|
||||
from bot_bottle.cli.login import cmd_login
|
||||
|
||||
self.assertEqual(cmd_login(["--help"]), 0)
|
||||
|
||||
def test_returns_1_without_url(self) -> None:
|
||||
from bot_bottle.cli.login import cmd_login
|
||||
with patch.dict(os.environ, {}, clear=True):
|
||||
@@ -55,18 +135,26 @@ class TestCmdLoginMissingUrl(unittest.TestCase):
|
||||
"""Exits 1 (network error) not because of missing URL when env var is set."""
|
||||
from bot_bottle.cli.login import cmd_login
|
||||
|
||||
def _fail_post(url, payload):
|
||||
def _fail_post(_url: str, _payload: dict[str, Any]) -> dict[str, Any]:
|
||||
raise OSError("connection refused")
|
||||
|
||||
with tempfile.TemporaryDirectory() as tmp:
|
||||
with patch.dict(os.environ, {"BB_CONSOLE_URL": "http://localhost:9999", "BOT_BOTTLE_ROOT": tmp}):
|
||||
with patch.dict(
|
||||
os.environ,
|
||||
{
|
||||
"BB_CONSOLE_URL": "http://localhost:9999",
|
||||
"BOT_BOTTLE_ROOT": tmp,
|
||||
},
|
||||
):
|
||||
with patch("bot_bottle.cli.login._post", side_effect=_fail_post):
|
||||
result = cmd_login([])
|
||||
self.assertEqual(result, 1)
|
||||
|
||||
|
||||
class TestCmdLoginFlow(unittest.TestCase):
|
||||
def _run_with_mocks(self, poll_responses: list[dict], tmp: str) -> int:
|
||||
def _run_with_mocks(
|
||||
self, poll_responses: list[dict[str, Any]], tmp: str
|
||||
) -> int:
|
||||
from bot_bottle.cli.login import cmd_login
|
||||
|
||||
start_resp = {
|
||||
@@ -78,20 +166,18 @@ class TestCmdLoginFlow(unittest.TestCase):
|
||||
|
||||
poll_iter = iter(poll_responses)
|
||||
|
||||
def _fake_post(url, payload):
|
||||
def _fake_post(
|
||||
_url: str, _payload: dict[str, Any]
|
||||
) -> dict[str, Any]:
|
||||
return start_resp
|
||||
|
||||
def _fake_get(url):
|
||||
try:
|
||||
resp = next(poll_iter)
|
||||
except StopIteration:
|
||||
return 200, {"status": "pending"}
|
||||
return 200, resp
|
||||
def _fake_get(_url: str) -> tuple[int, dict[str, Any]]:
|
||||
return 200, next(poll_iter, {"status": "pending"})
|
||||
|
||||
with patch.dict(os.environ, {"BOT_BOTTLE_ROOT": tmp}):
|
||||
with patch("bot_bottle.cli.login._post", side_effect=_fake_post):
|
||||
with patch("bot_bottle.cli.login._get", side_effect=_fake_get):
|
||||
with patch("bot_bottle.cli.login._POLL_SLEEP", 0):
|
||||
with patch("time.sleep"):
|
||||
return cmd_login(["--console-url", "http://console"])
|
||||
|
||||
def test_approved_flow_returns_0(self) -> None:
|
||||
@@ -106,7 +192,7 @@ class TestCmdLoginFlow(unittest.TestCase):
|
||||
[{"status": "pending"}, approved], tmp
|
||||
)
|
||||
self.assertEqual(result, 0)
|
||||
with open(os.path.join(tmp, "console.json")) as f:
|
||||
with open(os.path.join(tmp, "console.json"), encoding="utf-8") as f:
|
||||
creds = json.loads(f.read())
|
||||
self.assertEqual(creds["host_id"], "hid")
|
||||
|
||||
@@ -121,17 +207,52 @@ class TestCmdLoginFlow(unittest.TestCase):
|
||||
start_resp = {
|
||||
"device_code": "dc",
|
||||
"user_code": "ZZZ-ZZZ",
|
||||
"expires_in": 0, # already expired
|
||||
"poll_interval": 0,
|
||||
"expires_in": 0, # already expired; loop never runs
|
||||
"poll_interval": 2,
|
||||
}
|
||||
|
||||
with tempfile.TemporaryDirectory() as tmp:
|
||||
with patch.dict(os.environ, {"BOT_BOTTLE_ROOT": tmp}):
|
||||
with patch("bot_bottle.cli.login._post", return_value=start_resp):
|
||||
with patch("bot_bottle.cli.login._POLL_SLEEP", 0):
|
||||
result = cmd_login(["--console-url", "http://console"])
|
||||
result = cmd_login(["--console-url", "http://console"])
|
||||
self.assertEqual(result, 1)
|
||||
|
||||
def test_poll_interval_from_server_is_used(self) -> None:
|
||||
"""time.sleep must be called with the server-provided poll_interval."""
|
||||
from bot_bottle.cli.login import cmd_login
|
||||
|
||||
server_interval = 7
|
||||
start_resp = {
|
||||
"device_code": "dc",
|
||||
"user_code": "ABC-DEF",
|
||||
"expires_in": 300,
|
||||
"poll_interval": server_interval,
|
||||
}
|
||||
approved = {
|
||||
"status": "approved",
|
||||
"host_id": "hid",
|
||||
"access_token": "at",
|
||||
"refresh_token": "rt",
|
||||
}
|
||||
poll_iter = iter([{"status": "pending"}, approved])
|
||||
|
||||
def _fake_get(_url: str) -> tuple[int, dict[str, str]]:
|
||||
return 200, next(poll_iter)
|
||||
|
||||
with tempfile.TemporaryDirectory() as tmp:
|
||||
with patch.dict(os.environ, {"BOT_BOTTLE_ROOT": tmp}):
|
||||
with patch("bot_bottle.cli.login._post", return_value=start_resp):
|
||||
with patch(
|
||||
"bot_bottle.cli.login._get", side_effect=_fake_get
|
||||
):
|
||||
with patch("time.sleep") as mock_sleep:
|
||||
result = cmd_login(["--console-url", "http://console"])
|
||||
|
||||
self.assertEqual(result, 0)
|
||||
self.assertTrue(mock_sleep.called)
|
||||
for call in mock_sleep.call_args_list:
|
||||
self.assertEqual(call.args[0], server_interval)
|
||||
|
||||
|
||||
class TestDispatcherRegistration(unittest.TestCase):
|
||||
def test_login_in_commands(self) -> None:
|
||||
|
||||
@@ -0,0 +1,40 @@
|
||||
"""The CLI package is runnable as `python -m bot_bottle.cli`."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import subprocess
|
||||
import sys
|
||||
import unittest
|
||||
from pathlib import Path
|
||||
|
||||
_REPO_ROOT = Path(__file__).resolve().parents[2]
|
||||
|
||||
|
||||
def _run(*args: str) -> subprocess.CompletedProcess[str]:
|
||||
return subprocess.run(
|
||||
[sys.executable, "-m", "bot_bottle.cli", *args],
|
||||
cwd=_REPO_ROOT,
|
||||
capture_output=True,
|
||||
text=True,
|
||||
check=False,
|
||||
)
|
||||
|
||||
|
||||
class TestModuleEntry(unittest.TestCase):
|
||||
def test_help_exits_zero(self) -> None:
|
||||
result = _run("--help")
|
||||
self.assertEqual(result.returncode, 0, result.stderr)
|
||||
self.assertIn("login", result.stderr)
|
||||
|
||||
def test_no_args_prints_usage(self) -> None:
|
||||
# main() returns 2 with no command, matching the cli.py entry point.
|
||||
self.assertEqual(_run().returncode, 2)
|
||||
|
||||
def test_subcommand_help_reaches_handler(self) -> None:
|
||||
result = _run("login", "--help")
|
||||
self.assertEqual(result.returncode, 0, result.stderr)
|
||||
self.assertIn("--console-url", result.stderr)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
unittest.main()
|
||||
@@ -176,6 +176,18 @@ class TestCmdStartHeadless(unittest.TestCase):
|
||||
self.assertEqual("researcher-2", self._spec().label)
|
||||
|
||||
|
||||
def test_cached_images_sets_cached_policy(self):
|
||||
start_mod.cmd_start(
|
||||
["--headless", "--cached-images", "researcher", "--bottle", "claude",
|
||||
"--prompt", "Do it"]
|
||||
)
|
||||
self.assertEqual("cached", self._spec().image_policy)
|
||||
|
||||
def test_cached_images_requires_headless(self):
|
||||
with self.assertRaises(Die):
|
||||
start_mod.cmd_start(["--cached-images", "researcher"])
|
||||
self._launch_mock.assert_not_called()
|
||||
|
||||
|
||||
class TestPrepareWithPreflight(unittest.TestCase):
|
||||
"""prepare_with_preflight calls render_preflight with the plan and backend name."""
|
||||
|
||||
@@ -65,6 +65,12 @@ class TestCmdStartSelector(unittest.TestCase):
|
||||
)
|
||||
self._modal_patch.start()
|
||||
|
||||
self._image_policy_patch = patch(
|
||||
"bot_bottle.cli.start._select_image_policy",
|
||||
return_value="fresh",
|
||||
)
|
||||
self._image_policy_patch.start()
|
||||
|
||||
self._env_patch = patch.dict(os.environ, {}, clear=False)
|
||||
self._env_patch.start()
|
||||
os.environ.pop("BOT_BOTTLE_BACKEND", None)
|
||||
@@ -75,6 +81,7 @@ class TestCmdStartSelector(unittest.TestCase):
|
||||
self._agent_picker_patch.stop()
|
||||
self._bottle_picker_patch.stop()
|
||||
self._modal_patch.stop()
|
||||
self._image_policy_patch.stop()
|
||||
self._env_patch.stop()
|
||||
|
||||
# ------------------------------------------------------------------
|
||||
@@ -133,6 +140,19 @@ class TestCmdStartSelector(unittest.TestCase):
|
||||
spec = self._launch_mock.call_args[0][0]
|
||||
self.assertEqual(("claude", "dev"), spec.bottle_names)
|
||||
|
||||
def test_image_policy_forwarded_to_spec(self):
|
||||
with patch("bot_bottle.cli.start._select_image_policy", return_value="cached"):
|
||||
start_mod.cmd_start(["researcher"])
|
||||
self._launch_mock.assert_called_once()
|
||||
spec = self._launch_mock.call_args[0][0]
|
||||
self.assertEqual("cached", spec.image_policy)
|
||||
|
||||
def test_image_policy_cancel_returns_0(self):
|
||||
with patch("bot_bottle.cli.start._select_image_policy", return_value=None):
|
||||
rc = start_mod.cmd_start(["researcher"])
|
||||
self.assertEqual(0, rc)
|
||||
self._launch_mock.assert_not_called()
|
||||
|
||||
def test_empty_bottle_selection_forwarded(self):
|
||||
self._bottle_picker_mock.return_value = []
|
||||
start_mod.cmd_start(["researcher"])
|
||||
@@ -214,6 +234,7 @@ class TestCmdStartLabelCollision(unittest.TestCase):
|
||||
).start()
|
||||
# Stub the bottle picker to always return a selection.
|
||||
patch.object(tui_mod, "filter_multiselect", return_value=["claude"]).start()
|
||||
patch("bot_bottle.cli.start._select_image_policy", return_value="fresh").start()
|
||||
self.addCleanup(patch.stopall)
|
||||
|
||||
def test_no_collision_proceeds_without_reprompt(self):
|
||||
|
||||
@@ -0,0 +1,146 @@
|
||||
"""Unit: _launch_bottle StaleImageError handling.
|
||||
|
||||
Exercises prelaunch_checks / backend.launch flow:
|
||||
- headless mode → die on stale
|
||||
- interactive mode, user declines → stop without launching
|
||||
- interactive mode, user confirms → skip stale check and launch once
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import io
|
||||
import tempfile
|
||||
import unittest
|
||||
from types import SimpleNamespace
|
||||
from typing import Any, cast
|
||||
from unittest.mock import MagicMock, patch
|
||||
|
||||
from bot_bottle.image_cache import StaleImageError
|
||||
from bot_bottle.log import Die
|
||||
|
||||
|
||||
def _fake_plan() -> Any:
|
||||
provision = SimpleNamespace(startup_args=())
|
||||
return cast(Any, SimpleNamespace(
|
||||
agent_provision=provision,
|
||||
agent_provider_template="claude",
|
||||
slug="dev-abc",
|
||||
))
|
||||
|
||||
|
||||
def _ok_cm(bottle: Any) -> MagicMock:
|
||||
"""Return a context-manager mock that yields `bottle`."""
|
||||
cm = MagicMock()
|
||||
cm.__enter__ = MagicMock(return_value=bottle)
|
||||
cm.__exit__ = MagicMock(return_value=False)
|
||||
return cm
|
||||
|
||||
|
||||
class TestLaunchBottleStaleHandling(unittest.TestCase):
|
||||
def setUp(self) -> None:
|
||||
self._tmp = tempfile.mkdtemp(prefix="cli-stale-test.")
|
||||
|
||||
def _spec(self) -> Any:
|
||||
from bot_bottle.backend import BottleSpec
|
||||
from bot_bottle.manifest import ManifestIndex
|
||||
idx = ManifestIndex.from_json_obj({
|
||||
"bottles": {"dev": {}},
|
||||
"agents": {"demo": {"skills": [], "prompt": "", "bottle": "dev"}},
|
||||
})
|
||||
return BottleSpec(
|
||||
manifest=idx,
|
||||
agent_name="demo",
|
||||
copy_cwd=False,
|
||||
user_cwd=self._tmp,
|
||||
identity="dev-abc",
|
||||
)
|
||||
|
||||
def _run_launch(self, **patch_kwargs: Any) -> int:
|
||||
import bot_bottle.cli.start as start_mod
|
||||
spec = self._spec()
|
||||
with patch.object(start_mod, "prepare_with_preflight",
|
||||
return_value=(_fake_plan(), "dev-abc")), \
|
||||
patch.object(start_mod, "settle_state"), \
|
||||
patch.object(start_mod, "info"):
|
||||
return start_mod._launch_bottle(
|
||||
spec,
|
||||
dry_run=False,
|
||||
backend_name="docker",
|
||||
**patch_kwargs,
|
||||
)
|
||||
|
||||
def test_headless_stale_calls_die(self) -> None:
|
||||
"""In headless mode (assume_yes=True), a StaleImageError from prelaunch_checks must call die()."""
|
||||
import bot_bottle.cli.start as start_mod
|
||||
|
||||
backend_mock = MagicMock()
|
||||
backend_mock.prelaunch_checks.side_effect = StaleImageError("image is 5 day(s) old")
|
||||
|
||||
with patch.object(start_mod, "get_bottle_backend", return_value=backend_mock), \
|
||||
patch.object(start_mod, "die", side_effect=Die()):
|
||||
with self.assertRaises(Die):
|
||||
self._run_launch(assume_yes=True)
|
||||
|
||||
backend_mock.launch.assert_not_called()
|
||||
|
||||
def test_interactive_user_declines_stops_before_launch(self) -> None:
|
||||
"""Interactive user answering 'n' → launch is never called."""
|
||||
import bot_bottle.cli.start as start_mod
|
||||
|
||||
backend_mock = MagicMock()
|
||||
backend_mock.prelaunch_checks.side_effect = StaleImageError("image is 5 day(s) old")
|
||||
|
||||
with patch.object(start_mod, "get_bottle_backend", return_value=backend_mock), \
|
||||
patch.object(start_mod, "read_tty_line", return_value="n"), \
|
||||
patch("sys.stderr", new_callable=io.StringIO):
|
||||
rc = self._run_launch(assume_yes=False)
|
||||
|
||||
self.assertEqual(0, rc)
|
||||
backend_mock.launch.assert_not_called()
|
||||
|
||||
def test_interactive_user_confirms_launches_once(self) -> None:
|
||||
"""Interactive user answering 'y' → prelaunch stale error is bypassed; launch called once."""
|
||||
import bot_bottle.cli.start as start_mod
|
||||
|
||||
bottle_mock = MagicMock()
|
||||
bottle_mock.name = "dev-abc"
|
||||
|
||||
backend_mock = MagicMock()
|
||||
backend_mock.prelaunch_checks.side_effect = StaleImageError("image is 5 day(s) old")
|
||||
backend_mock.launch.return_value = _ok_cm(bottle_mock)
|
||||
|
||||
with patch.object(start_mod, "get_bottle_backend", return_value=backend_mock), \
|
||||
patch.object(start_mod, "read_tty_line", return_value="y"), \
|
||||
patch.object(start_mod, "attach_agent", return_value=0), \
|
||||
patch.object(start_mod, "capture_claude_session_state"), \
|
||||
patch("sys.stderr", new_callable=io.StringIO):
|
||||
rc = self._run_launch(assume_yes=False)
|
||||
|
||||
self.assertEqual(0, rc)
|
||||
backend_mock.prelaunch_checks.assert_called_once()
|
||||
backend_mock.launch.assert_called_once()
|
||||
|
||||
def test_interactive_yes_uppercase_also_accepted(self) -> None:
|
||||
"""'Y' or 'YES' should also be accepted as confirmation."""
|
||||
import bot_bottle.cli.start as start_mod
|
||||
|
||||
bottle_mock = MagicMock()
|
||||
bottle_mock.name = "dev-abc"
|
||||
|
||||
backend_mock = MagicMock()
|
||||
backend_mock.prelaunch_checks.side_effect = StaleImageError("image is 5 day(s) old")
|
||||
backend_mock.launch.return_value = _ok_cm(bottle_mock)
|
||||
|
||||
with patch.object(start_mod, "get_bottle_backend", return_value=backend_mock), \
|
||||
patch.object(start_mod, "read_tty_line", return_value="YES"), \
|
||||
patch.object(start_mod, "attach_agent", return_value=0), \
|
||||
patch.object(start_mod, "capture_claude_session_state"), \
|
||||
patch("sys.stderr", new_callable=io.StringIO):
|
||||
rc = self._run_launch(assume_yes=False)
|
||||
|
||||
self.assertEqual(0, rc)
|
||||
backend_mock.launch.assert_called_once()
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
unittest.main()
|
||||
@@ -0,0 +1,86 @@
|
||||
"""Unit tests for the host-side configuration store."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import sqlite3
|
||||
import tempfile
|
||||
import unittest
|
||||
from pathlib import Path
|
||||
|
||||
from bot_bottle.config_store import (
|
||||
DEFAULT_CACHED_IMAGE_STALE_WARNING_DAYS,
|
||||
ConfigStore,
|
||||
)
|
||||
from bot_bottle.store_manager import StoreManager
|
||||
|
||||
|
||||
class TestConfigStore(unittest.TestCase):
|
||||
def test_cached_image_warning_days_defaults_to_one(self) -> None:
|
||||
with tempfile.TemporaryDirectory(prefix="config-store.") as tmp:
|
||||
store = ConfigStore(Path(tmp) / "bot-bottle.db")
|
||||
store.migrate()
|
||||
self.assertEqual(
|
||||
DEFAULT_CACHED_IMAGE_STALE_WARNING_DAYS,
|
||||
store.cached_image_stale_warning_days(),
|
||||
)
|
||||
|
||||
def test_cached_image_warning_days_reads_value(self) -> None:
|
||||
with tempfile.TemporaryDirectory(prefix="config-store.") as tmp:
|
||||
store = ConfigStore(Path(tmp) / "bot-bottle.db")
|
||||
store.migrate()
|
||||
store.set_cached_image_stale_warning_days(7)
|
||||
self.assertEqual(7, store.cached_image_stale_warning_days())
|
||||
|
||||
def test_config_schema_uses_explicit_settings_columns(self) -> None:
|
||||
with tempfile.TemporaryDirectory(prefix="config-store.") as tmp:
|
||||
store = ConfigStore(Path(tmp) / "bot-bottle.db")
|
||||
store.migrate()
|
||||
with sqlite3.connect(store.db_path) as conn:
|
||||
conn.row_factory = sqlite3.Row
|
||||
columns = [
|
||||
row["name"]
|
||||
for row in conn.execute("PRAGMA table_info(bot_bottle_config)")
|
||||
]
|
||||
self.assertEqual([
|
||||
"id",
|
||||
"cached_image_stale_warning_days",
|
||||
], columns)
|
||||
|
||||
def test_store_manager_includes_config_store(self) -> None:
|
||||
with tempfile.TemporaryDirectory(prefix="config-store.") as tmp:
|
||||
db = Path(tmp) / "bot-bottle.db"
|
||||
manager = StoreManager(db)
|
||||
self.assertFalse(manager.is_migrated())
|
||||
manager.migrate()
|
||||
self.assertTrue(manager.is_migrated())
|
||||
|
||||
def test_cached_image_warning_days_returns_default_when_db_missing(self) -> None:
|
||||
# When the db file doesn't exist yet (parent exists, file doesn't),
|
||||
# the store returns the default without touching the file.
|
||||
with tempfile.TemporaryDirectory(prefix="config-store.") as tmp:
|
||||
store = ConfigStore(Path(tmp) / "missing.db")
|
||||
self.assertEqual(
|
||||
DEFAULT_CACHED_IMAGE_STALE_WARNING_DAYS,
|
||||
store.cached_image_stale_warning_days(),
|
||||
)
|
||||
|
||||
def test_cached_image_warning_days_returns_default_on_null_value(self) -> None:
|
||||
# If the row exists but the value is NULL (or not castable to int),
|
||||
# the store falls back to the default.
|
||||
with tempfile.TemporaryDirectory(prefix="config-store.") as tmp:
|
||||
db_path = Path(tmp) / "bot-bottle.db"
|
||||
store = ConfigStore(db_path)
|
||||
store.migrate()
|
||||
# Write a NULL value directly.
|
||||
with sqlite3.connect(db_path) as conn:
|
||||
conn.execute(
|
||||
"UPDATE bot_bottle_config SET cached_image_stale_warning_days = NULL WHERE id = 1"
|
||||
)
|
||||
self.assertEqual(
|
||||
DEFAULT_CACHED_IMAGE_STALE_WARNING_DAYS,
|
||||
store.cached_image_stale_warning_days(),
|
||||
)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
unittest.main()
|
||||
@@ -2,6 +2,7 @@
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import dataclasses
|
||||
import unittest
|
||||
|
||||
from bot_bottle.backend.docker.consolidated_compose import consolidated_agent_compose
|
||||
@@ -46,6 +47,15 @@ class TestConsolidatedAgentCompose(unittest.TestCase):
|
||||
# forwarded secrets are bare names (value inherited from process env).
|
||||
self.assertIn("CLAUDE_CODE_OAUTH_TOKEN", env)
|
||||
|
||||
def test_env_var_secret_stays_a_bare_name(self) -> None:
|
||||
plan = _plan(with_egress=True, supervise=True, with_git=True)
|
||||
plan = dataclasses.replace(plan, env_var_secret="secret-value")
|
||||
env = consolidated_agent_compose(
|
||||
plan, gateway_ip=_GW, source_ip=_IP, network=_NET,
|
||||
)["services"]["agent"]["environment"]
|
||||
self.assertIn("ENV_VAR_SECRET", env)
|
||||
self.assertNotIn("ENV_VAR_SECRET=secret-value", env)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
unittest.main()
|
||||
|
||||
@@ -0,0 +1,186 @@
|
||||
"""Unit: host Claude auth extraction."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import json
|
||||
import tempfile
|
||||
import unittest
|
||||
from datetime import datetime, timezone
|
||||
from pathlib import Path
|
||||
from unittest.mock import MagicMock, patch
|
||||
|
||||
from bot_bottle.contrib.claude.claude_auth import (
|
||||
claude_auth_path,
|
||||
claude_host_access_token,
|
||||
)
|
||||
from bot_bottle.log import Die
|
||||
|
||||
|
||||
def _cred_json(access_token: str, **extra: object) -> str:
|
||||
payload: dict[str, object] = {"claudeAiOauth": {"accessToken": access_token, **extra}}
|
||||
return json.dumps(payload)
|
||||
|
||||
|
||||
class TestClaudeHostAccessToken(unittest.TestCase):
|
||||
def setUp(self):
|
||||
self.tmp = tempfile.TemporaryDirectory(prefix="bb-claude-auth.")
|
||||
self.home = Path(self.tmp.name)
|
||||
self.cred_dir = self.home / ".claude"
|
||||
self.cred_dir.mkdir()
|
||||
self.auth_path = self.cred_dir / ".credentials.json"
|
||||
|
||||
def tearDown(self):
|
||||
self.tmp.cleanup()
|
||||
|
||||
def _write(self, payload: dict) -> None: # type: ignore[no-untyped-def]
|
||||
self.auth_path.write_text(json.dumps(payload))
|
||||
|
||||
def test_auth_path_uses_home_env(self):
|
||||
self.assertEqual(
|
||||
self.auth_path,
|
||||
claude_auth_path({"HOME": str(self.home)}),
|
||||
)
|
||||
|
||||
# --- file-based (Linux) ---
|
||||
|
||||
def test_file_returns_access_token(self):
|
||||
key = "sk-ant-oat01-real-key" # gitleaks:allow
|
||||
self._write({"claudeAiOauth": {"accessToken": key}})
|
||||
out = claude_host_access_token({"HOME": str(self.home)})
|
||||
self.assertEqual(key, out)
|
||||
|
||||
def test_file_missing_claude_ai_oauth_dies(self):
|
||||
self._write({"hasCompletedOnboarding": True})
|
||||
with self.assertRaises(Die):
|
||||
claude_host_access_token({"HOME": str(self.home)})
|
||||
|
||||
def test_file_missing_access_token_dies(self):
|
||||
self._write({"claudeAiOauth": {"expiresAt": 2000000000000}})
|
||||
with self.assertRaises(Die):
|
||||
claude_host_access_token({"HOME": str(self.home)})
|
||||
|
||||
def test_file_empty_access_token_dies(self):
|
||||
self._write({"claudeAiOauth": {"accessToken": ""}})
|
||||
with self.assertRaises(Die):
|
||||
claude_host_access_token({"HOME": str(self.home)})
|
||||
|
||||
def test_file_expired_token_dies(self):
|
||||
# expiresAt is milliseconds; 1_000_000 ms is year 1970
|
||||
self._write({
|
||||
"claudeAiOauth": {"accessToken": "sk-ant-oat01-x", "expiresAt": 1_000_000}, # gitleaks:allow
|
||||
})
|
||||
with self.assertRaises(Die):
|
||||
claude_host_access_token(
|
||||
{"HOME": str(self.home)},
|
||||
now=datetime(2026, 1, 1, tzinfo=timezone.utc),
|
||||
)
|
||||
|
||||
def test_file_future_expiry_is_accepted(self):
|
||||
key = "sk-ant-oat01-y" # gitleaks:allow
|
||||
# 2_000_000_000_000 ms ≈ year 2033
|
||||
self._write({
|
||||
"claudeAiOauth": {"accessToken": key, "expiresAt": 2_000_000_000_000},
|
||||
})
|
||||
out = claude_host_access_token(
|
||||
{"HOME": str(self.home)},
|
||||
now=datetime(2026, 1, 1, tzinfo=timezone.utc),
|
||||
)
|
||||
self.assertEqual(key, out)
|
||||
|
||||
def test_file_absent_expiry_is_accepted(self):
|
||||
key = "sk-ant-oat01-z" # gitleaks:allow
|
||||
self._write({"claudeAiOauth": {"accessToken": key}})
|
||||
out = claude_host_access_token({"HOME": str(self.home)})
|
||||
self.assertEqual(key, out)
|
||||
|
||||
def test_file_non_json_dies(self):
|
||||
self.auth_path.write_text("not json {{{")
|
||||
with self.assertRaises(Die):
|
||||
claude_host_access_token({"HOME": str(self.home)})
|
||||
|
||||
def test_file_json_array_root_dies(self):
|
||||
self.auth_path.write_text("[]")
|
||||
with self.assertRaises(Die):
|
||||
claude_host_access_token({"HOME": str(self.home)})
|
||||
|
||||
def test_file_extra_fields_are_ignored(self):
|
||||
key = "sk-ant-oat01-real" # gitleaks:allow
|
||||
self._write({
|
||||
"claudeAiOauth": {
|
||||
"accessToken": key,
|
||||
"refreshToken": "sk-ant-ort01-secret", # gitleaks:allow
|
||||
"scopes": ["user:inference"],
|
||||
"expiresAt": 2_000_000_000_000,
|
||||
},
|
||||
})
|
||||
out = claude_host_access_token({"HOME": str(self.home)})
|
||||
self.assertEqual(key, out)
|
||||
|
||||
# --- macOS Keychain fallback ---
|
||||
|
||||
def _home_without_creds(self) -> Path:
|
||||
"""A home dir that has .claude/ but no .credentials.json."""
|
||||
empty = self.home / "no-creds"
|
||||
(empty / ".claude").mkdir(parents=True)
|
||||
return empty
|
||||
|
||||
def _mock_keychain(self, stdout: str, returncode: int = 0) -> MagicMock:
|
||||
mock = MagicMock()
|
||||
mock.returncode = returncode
|
||||
mock.stdout = stdout
|
||||
return mock
|
||||
|
||||
def test_keychain_used_when_file_absent(self):
|
||||
key = "sk-ant-oat01-keychain" # gitleaks:allow
|
||||
home = self._home_without_creds()
|
||||
with patch(
|
||||
"bot_bottle.contrib.claude.claude_auth.subprocess.run",
|
||||
return_value=self._mock_keychain(_cred_json(key)),
|
||||
), patch(
|
||||
"bot_bottle.contrib.claude.claude_auth.sys.platform", "darwin",
|
||||
):
|
||||
out = claude_host_access_token({"HOME": str(home)})
|
||||
self.assertEqual(key, out)
|
||||
|
||||
def test_keychain_failure_when_file_absent_dies(self):
|
||||
home = self._home_without_creds()
|
||||
with patch(
|
||||
"bot_bottle.contrib.claude.claude_auth.subprocess.run",
|
||||
return_value=self._mock_keychain("", returncode=44),
|
||||
), patch(
|
||||
"bot_bottle.contrib.claude.claude_auth.sys.platform", "darwin",
|
||||
):
|
||||
with self.assertRaises(Die):
|
||||
claude_host_access_token({"HOME": str(home)})
|
||||
|
||||
def test_no_file_no_keychain_on_linux_dies(self):
|
||||
home = self._home_without_creds()
|
||||
with patch("bot_bottle.contrib.claude.claude_auth.sys.platform", "linux"):
|
||||
with self.assertRaises(Die):
|
||||
claude_host_access_token({"HOME": str(home)})
|
||||
|
||||
def test_keychain_non_json_dies(self):
|
||||
home = self._home_without_creds()
|
||||
with patch(
|
||||
"bot_bottle.contrib.claude.claude_auth.subprocess.run",
|
||||
return_value=self._mock_keychain("not-json"),
|
||||
), patch(
|
||||
"bot_bottle.contrib.claude.claude_auth.sys.platform", "darwin",
|
||||
):
|
||||
with self.assertRaises(Die):
|
||||
claude_host_access_token({"HOME": str(home)})
|
||||
|
||||
def test_keychain_security_not_found_dies(self):
|
||||
home = self._home_without_creds()
|
||||
with patch(
|
||||
"bot_bottle.contrib.claude.claude_auth.subprocess.run",
|
||||
side_effect=FileNotFoundError,
|
||||
), patch(
|
||||
"bot_bottle.contrib.claude.claude_auth.sys.platform", "darwin",
|
||||
):
|
||||
with self.assertRaises(Die):
|
||||
claude_host_access_token({"HOME": str(home)})
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
unittest.main()
|
||||
@@ -3,6 +3,7 @@
|
||||
from __future__ import annotations
|
||||
|
||||
import contextlib
|
||||
import dataclasses
|
||||
import io
|
||||
import tempfile
|
||||
import unittest
|
||||
@@ -18,6 +19,7 @@ from bot_bottle.backend.docker.bottle_plan import DockerBottlePlan
|
||||
from bot_bottle.backend.docker.consolidated_launch import LaunchContext
|
||||
from bot_bottle.egress import EgressPlan
|
||||
from bot_bottle.git_gate import GitGatePlan
|
||||
from bot_bottle.log import Die
|
||||
from bot_bottle.manifest import ManifestIndex
|
||||
from tests.unit import use_bottle_root
|
||||
|
||||
@@ -92,6 +94,7 @@ class TestLaunchCommittedImage(unittest.TestCase):
|
||||
mock.patch.object(launch_mod.docker_mod, "image_exists", return_value=image_present), \
|
||||
mock.patch.object(launch_mod.docker_mod, "build_image", side_effect=_build), \
|
||||
mock.patch.object(launch_mod.docker_mod, "verify_agent_image"), \
|
||||
mock.patch.object(launch_mod.docker_mod, "image_created_at"), \
|
||||
mock.patch.object(launch_mod, "launch_consolidated", return_value=_CTX), \
|
||||
mock.patch.object(launch_mod, "teardown_consolidated"), \
|
||||
mock.patch.object(launch_mod, "DockerGateway", return_value=gw), \
|
||||
@@ -112,7 +115,8 @@ class TestLaunchCommittedImage(unittest.TestCase):
|
||||
with self._patched(
|
||||
committed_tag=committed_tag, image_present=image_present, compose=compose,
|
||||
) as built:
|
||||
with launch_mod.launch(plan, provision=mock.Mock(return_value=None)):
|
||||
images = launch_mod.build_or_load_images(plan)
|
||||
with launch_mod.launch(plan, images, provision=mock.Mock(return_value=None)):
|
||||
pass
|
||||
return built
|
||||
|
||||
@@ -127,14 +131,34 @@ class TestLaunchCommittedImage(unittest.TestCase):
|
||||
captured.append(p)
|
||||
return {"services": {"agent": {}}}
|
||||
|
||||
with self._patched(committed_tag=_COMMITTED_TAG, image_present=True, compose=compose):
|
||||
with launch_mod.launch(_plan(self._tmp), provision=mock.Mock(return_value=None)):
|
||||
with self._patched(committed_tag=_COMMITTED_TAG, image_present=True, compose=compose) as _:
|
||||
plan = _plan(self._tmp)
|
||||
images = launch_mod.build_or_load_images(plan)
|
||||
with launch_mod.launch(plan, images, provision=mock.Mock(return_value=None)):
|
||||
pass
|
||||
self.assertEqual(_COMMITTED_TAG, captured[0].image)
|
||||
|
||||
def test_falls_back_to_build_when_no_committed_image(self) -> None:
|
||||
self.assertEqual([_DEFAULT_IMAGE], self._run_launch(_plan(self._tmp), committed_tag=None))
|
||||
|
||||
def test_cached_images_skip_build_when_present(self) -> None:
|
||||
base = _plan(self._tmp)
|
||||
plan = dataclasses.replace(
|
||||
base,
|
||||
spec=dataclasses.replace(base.spec, image_policy="cached"),
|
||||
)
|
||||
built = self._run_launch(plan, committed_tag=None, image_present=True)
|
||||
self.assertEqual([], built)
|
||||
|
||||
def test_cached_images_die_when_agent_missing(self) -> None:
|
||||
base = _plan(self._tmp)
|
||||
plan = dataclasses.replace(
|
||||
base,
|
||||
spec=dataclasses.replace(base.spec, image_policy="cached"),
|
||||
)
|
||||
with self.assertRaises(Die):
|
||||
self._run_launch(plan, committed_tag=None, image_present=False)
|
||||
|
||||
def test_falls_back_to_build_when_committed_image_missing_from_daemon(self) -> None:
|
||||
built = self._run_launch(_plan(self._tmp), committed_tag=_COMMITTED_TAG, image_present=False)
|
||||
self.assertEqual([_DEFAULT_IMAGE], built)
|
||||
|
||||
@@ -16,7 +16,7 @@ from pathlib import Path
|
||||
from unittest import mock
|
||||
|
||||
from bot_bottle.agent_provider import AgentProvisionPlan
|
||||
from bot_bottle.backend import BottleSpec
|
||||
from bot_bottle.backend import BottleImages, BottleSpec
|
||||
from bot_bottle.backend.docker import launch as launch_mod
|
||||
from bot_bottle.backend.docker.bottle_plan import DockerBottlePlan
|
||||
from bot_bottle.backend.docker.consolidated_launch import LaunchContext
|
||||
@@ -91,8 +91,11 @@ class TestTeardownWarning(unittest.TestCase):
|
||||
bottle_id="b1", identity_token="t", source_ip="172.20.0.4",
|
||||
network="bot-bottle-gateway", gateway_ip="172.20.0.2",
|
||||
orchestrator_url="http://orch:8099",
|
||||
env_var_secret="encryption-key",
|
||||
)
|
||||
|
||||
images = BottleImages(agent="bot-bottle-claude:latest", sidecar="bot-bottle-sidecars:latest")
|
||||
|
||||
with mock.patch.object(launch_mod.docker_mod, "build_image"), \
|
||||
mock.patch.object(launch_mod.docker_mod, "verify_agent_image"), \
|
||||
mock.patch.object(launch_mod, "launch_consolidated", return_value=ctx), \
|
||||
@@ -105,7 +108,7 @@ class TestTeardownWarning(unittest.TestCase):
|
||||
mock.patch.object(
|
||||
launch_mod, "write_compose_file", return_value=Path("/tmp/compose.yml"),
|
||||
), \
|
||||
mock.patch.object(launch_mod, "compose_up"), \
|
||||
mock.patch.object(launch_mod, "compose_up") as compose_up, \
|
||||
mock.patch.object(launch_mod, "compose_dump_logs"), \
|
||||
mock.patch.object(
|
||||
launch_mod, "compose_down",
|
||||
@@ -113,13 +116,16 @@ class TestTeardownWarning(unittest.TestCase):
|
||||
), \
|
||||
contextlib.redirect_stderr(buf):
|
||||
provision = mock.Mock(return_value=None)
|
||||
with launch_mod.launch(plan, provision=provision):
|
||||
with launch_mod.launch(plan, images, provision=provision):
|
||||
pass
|
||||
|
||||
output = buf.getvalue()
|
||||
self.assertIn("bot-bottle: warning:", output)
|
||||
self.assertIn("bot-bottle-test-teardown-abc", output)
|
||||
self.assertIn("compose-down", output)
|
||||
self.assertEqual(
|
||||
"encryption-key", compose_up.call_args.kwargs["env"]["ENV_VAR_SECRET"],
|
||||
)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
|
||||
@@ -45,12 +45,15 @@ _PROVIDER = _Provider()
|
||||
|
||||
|
||||
def _plan(*, git_user: dict | None = None, # type: ignore
|
||||
git_repos: dict | None = None, # type: ignore
|
||||
copy_cwd: bool = False,
|
||||
user_cwd: str = "/tmp/x",
|
||||
stage_dir: Path | None = None) -> DockerBottlePlan:
|
||||
bottle_json: dict = {} # type: ignore
|
||||
if git_user is not None:
|
||||
bottle_json["git-gate"] = {"user": git_user}
|
||||
if git_repos is not None:
|
||||
bottle_json.setdefault("git-gate", {})["repos"] = git_repos
|
||||
index = ManifestIndex.from_json_obj({
|
||||
"bottles": {"dev": bottle_json},
|
||||
"agents": {"demo": {"skills": [], "prompt": "", "bottle": "dev"}},
|
||||
@@ -125,6 +128,62 @@ class TestProvisionGitUser(unittest.TestCase):
|
||||
_PROVIDER.provision_git(bottle, _plan(stage_dir=self.stage))
|
||||
self.assertEqual([], _git_config_exec_calls(bottle))
|
||||
|
||||
def test_repairs_git_xdg_directory_for_runtime_user(self):
|
||||
bottle = _make_bottle()
|
||||
_PROVIDER.provision_git(bottle, _plan(stage_dir=self.stage))
|
||||
|
||||
script, user = next(
|
||||
(call.args[0], call.kwargs.get("user", "node"))
|
||||
for call in bottle.exec.call_args_list
|
||||
if "/home/node/.config/git" in call.args[0]
|
||||
)
|
||||
self.assertEqual("root", user)
|
||||
self.assertIn("chown node:node /home/node", script)
|
||||
self.assertIn("chmod 755 /home/node", script)
|
||||
self.assertIn("mkdir -p /home/node/.config/git", script)
|
||||
self.assertIn("chown -R node:node /home/node/.config", script)
|
||||
self.assertIn("chmod -R u+rwX,go+rX /home/node/.config", script)
|
||||
|
||||
def test_fails_closed_when_home_permissions_cannot_be_repaired(self):
|
||||
bottle = _make_bottle()
|
||||
bottle.exec.return_value = ExecResult(1, "", "read-only filesystem")
|
||||
|
||||
with self.assertRaises(SystemExit):
|
||||
_PROVIDER.provision_git(bottle, _plan(stage_dir=self.stage))
|
||||
|
||||
def _git_plan(self) -> DockerBottlePlan:
|
||||
return _plan(
|
||||
git_repos={
|
||||
"repo": {
|
||||
"url": "ssh://git@example.com/repo.git",
|
||||
"key": {"provider": "static", "path": "/dev/null"},
|
||||
"host_key": "ssh-ed25519 AAAA",
|
||||
},
|
||||
},
|
||||
stage_dir=self.stage,
|
||||
)
|
||||
|
||||
def test_fails_closed_when_gitconfig_permissions_cannot_be_set(self):
|
||||
bottle = _make_bottle()
|
||||
bottle.exec.side_effect = [
|
||||
ExecResult(0, "", ""),
|
||||
ExecResult(1, "", "chown failed"),
|
||||
]
|
||||
|
||||
with self.assertRaises(SystemExit):
|
||||
_PROVIDER.provision_git(bottle, self._git_plan())
|
||||
|
||||
def test_fails_closed_when_runtime_user_cannot_read_gitconfig(self):
|
||||
bottle = _make_bottle()
|
||||
bottle.exec.side_effect = [
|
||||
ExecResult(0, "", ""),
|
||||
ExecResult(0, "", ""),
|
||||
ExecResult(1, "", "permission denied"),
|
||||
]
|
||||
|
||||
with self.assertRaises(SystemExit):
|
||||
_PROVIDER.provision_git(bottle, self._git_plan())
|
||||
|
||||
def test_sets_name_and_email(self):
|
||||
plan = _plan(
|
||||
git_user={"name": "Eric Bauerfeld", "email": "eric@dideric.is"},
|
||||
|
||||
Some files were not shown because too many files have changed in this diff Show More
Reference in New Issue
Block a user