ci: enforce pylint score instead of warning exit bits

.gitea/workflows/canaries.yml

@@ -22,7 +22,10 @@ jobs:
       - name: Checkout
         uses: actions/checkout@v4
 
-      # No actions/setup-python: canaries are stdlib unittest on the image's
+      - name: Set up Python
-      # system Python 3.12 (older act_runner mishandles setup-python's PATH).
+        uses: actions/setup-python@v5
+        with:
+          python-version: "3.12"
+
       - name: Run canaries
         run: python3 -m unittest discover -t . -s tests/canaries -v

.gitea/workflows/lint.yml

@@ -13,14 +13,15 @@ jobs:
     steps:
       - uses: actions/checkout@v3
 
-      # No actions/setup-python: the runner image already ships Python 3.12,
+      - name: Set up Python
-      # and older act_runner engines mishandle setup-python's PATH. Install
+        uses: actions/setup-python@v4
-      # into the ephemeral job container's system Python — the pylint/pyright
+        with:
-      # console scripts land on /usr/local/bin (on PATH) so the steps below
+          python-version: "3.12"
-      # still resolve. --break-system-packages is safe: the container is
+
-      # disposable.
       - name: Install dev dependencies
-        run: python3 -m pip install --break-system-packages -r requirements-dev.txt
+        run: |
+          python -m pip install --upgrade pip
+          pip install -r requirements-dev.txt
 
       - name: Run pylint
         run: |

.gitea/workflows/prd-number.yml

@@ -37,8 +37,11 @@ jobs:
           fetch-depth: 0
           token: ${{ secrets.GITHUB_TOKEN }}
 
-      # No actions/setup-python: the inline script is stdlib-only on the
+      - name: Set up Python
-      # image's system Python 3.12 (older act_runner mishandles its PATH).
+        uses: actions/setup-python@v5
+        with:
+          python-version: "3.12"
+
       - name: Configure git
         run: |
           git config user.name "github-actions[bot]"

.gitea/workflows/test.yml

@@ -4,15 +4,16 @@
 # dependencies are required to execute it. Tests are split by directory:
 #
 #   tests/unit/         — pure unit tests; always run
-#   tests/integration/  — need a reachable backend; skip cleanly when
+#   tests/integration/  — need a reachable Docker daemon; skip cleanly
-#                         the backend isn't available on the runner
+#                         (via tests/_docker.py:skip_unless_docker) when
+#                         Docker isn't available on the runner
 #   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
+# This workflow assumes the Gitea Actions runner exposes the host Docker
-# BOT_BOTTLE_BACKEND explicitly so the test suite uses the right backend.
+# socket to the job container so `docker` commands inside the job can
-# Backends that aren't available on the runner fail the preflight step
+# reach the daemon. If that's not yet configured on the runner the
-# rather than silently skipping inside the test output.
+# integration tests will skip rather than fail.
 
 name: test
 
@@ -22,84 +23,24 @@ on:
       - 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.
-      - 'Dockerfile*'
-      - 'pyproject.toml'
   pull_request:
     paths:
       - '**.py'
-      - '.gitea/workflows/**.yml'
-      - 'scripts/**'
-      - 'README.md'
-      - 'Dockerfile*'
-      - 'pyproject.toml'
-  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:
       - name: Checkout
         uses: actions/checkout@v4
 
-      # No actions/setup-python: the runner image already ships Python 3.12,
+      - name: Set up Python
-      # and older act_runner engines mishandle setup-python's PATH (coverage
+        uses: actions/setup-python@v5
-      # lands in one interpreter, `python3` resolves to another). Install
+        with:
-      # straight into the ephemeral job container's system Python —
+          python-version: "3.12"
-      # --break-system-packages is safe because the container is disposable.
+
       - name: Install dev requirements
-        run: python3 -m pip install --break-system-packages -r requirements-dev.txt
+        run: python3 -m pip install -r requirements-dev.txt
 
       - name: Run unit tests
         run: python3 -m coverage run -m unittest discover -t . -s tests/unit -v
@@ -107,14 +48,17 @@ jobs:
       - name: Report unit coverage
         run: python3 -m coverage report -m
 
-  integration-docker:
+  integration:
     runs-on: ubuntu-latest
     steps:
       - name: Checkout
         uses: actions/checkout@v4
 
-      # No actions/setup-python (see the note in the `unit` job); the
+      - name: Set up Python
-      # container's system Python 3.12 runs the stdlib test suite directly.
+        uses: actions/setup-python@v5
+        with:
+          python-version: "3.12"
+
       - name: Show environment
         run: |
           python3 --version
@@ -124,150 +68,33 @@ jobs:
             echo "docker not on PATH — integration tests will skip"
           fi
 
-      - name: Run integration tests (docker)
+      - name: Run integration tests
-        env:
-          BOT_BOTTLE_BACKEND: docker
         run: python3 -m unittest discover -t . -s tests/integration -v
 
-  # Integration tests against the Firecracker backend. Runs on a self-hosted
+  # Combined unit+integration coverage report (informational). See
-  # KVM runner (label `kvm`) where /dev/kvm and the TAP/nft pool are available.
+  # docs/decisions/0004-coverage-policy.md.
   #
-  # Restricted to same-repo PRs, push to main, and workflow_dispatch — fork
+  # The hard diff-coverage gate (changed lines >= 90%) is DEFERRED: the
-  # PRs don't execute untrusted code on the privileged runner.
+  # Firecracker backend's VM/SSH orchestration is covered by the integration
-  #
+  # suite, which needs /dev/kvm + the provisioned TAP/nft pool — a
-  # Runner prerequisites (provision once; see README "Firecracker on Linux"):
+  # container-based runner skips it and those lines read uncovered, so the
-  # `firecracker` on PATH, `/dev/kvm` accessible, cached kernel +
+  # gate can't pass here. Re-enabling it on a self-hosted KVM runner is
-  # static dropbear, and the pool as a persistent systemd unit.
+  # tracked separately (see PRD 0069 / #348 and the ci-runner branch).
-  integration-firecracker:
-    needs: build-infra
-    runs-on: [self-hosted, kvm]
-    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: Checkout
-        uses: actions/checkout@v4
-
-      - 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: Download the candidate built from this checkout
-        uses: actions/download-artifact@v3
-        with:
-          name: infra-candidate
-          path: infra-candidate
-
-      - 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)
-        env:
-          BOT_BOTTLE_BACKEND: firecracker
-          BOT_BOTTLE_INFRA_ARTIFACT_DIR: ${{ github.workspace }}/infra-candidate
-        run: python3 -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.
-  #
-  # 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.
-  #
-  # 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.
   coverage:
-    needs: [build-infra, integration-firecracker]
+    runs-on: ubuntu-latest
-    timeout-minutes: 15
-    runs-on: [self-hosted, kvm]
-    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: Checkout
         uses: actions/checkout@v4
         with:
           fetch-depth: 0
 
-      - name: Preflight — Firecracker host is ready
+      - name: Set up Python
-        run: |
+        uses: actions/setup-python@v5
-          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: Download the candidate already exercised by integration
-        uses: actions/download-artifact@v3
         with:
-          name: infra-candidate
+          python-version: "3.12"
-          path: infra-candidate
 
-      # No dev-requirements install: `coverage` is already provided by the
+      - name: Install dev requirements
-      # self-hosted runner's Nix python env, and that env has no `pip`
+        run: python3 -m pip install -r requirements-dev.txt
-      # module to install into anyway. `scripts/coverage.sh` +
+
-      # `diff_coverage.py` need only `coverage` (not pylint/pyright).
+      - name: Combined coverage report (unit + integration)
-      - 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
-
-      - name: Diff-coverage gate (changed lines >= 90%)
-        run: |
-          git fetch --no-tags origin main:refs/remotes/origin/main
-          python3 scripts/diff_coverage.py --base origin/main --min 90
-
-  publish-infra:
-    needs: [stage-firecracker-inputs, build-infra, 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
-        uses: actions/download-artifact@v3
-        with:
-          name: infra-candidate
-          path: infra-candidate
-
-      # 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)
-        uses: actions/download-artifact@v3
-        with:
-          name: firecracker-inputs
-          path: firecracker-inputs
-
-      - name: Publish the tested candidate
-        env:
-          BOT_BOTTLE_INFRA_ARTIFACT_TOKEN: ${{ secrets.BOT_BOTTLE_INFRA_ARTIFACT_TOKEN }}
-          BOT_BOTTLE_FC_DROPBEAR: ${{ github.workspace }}/firecracker-inputs/dropbear
-        run: python3 -m bot_bottle.backend.firecracker.publish_infra --publish-dir infra-candidate

.gitea/workflows/tracker-policy-issues.yml

@@ -1,17 +0,0 @@
-name: tracker-policy-issues
-
-on:
-  issues:
-    types: [opened, unlabeled]
-
-jobs:
-  label-issue:
-    runs-on: ubuntu-latest
-    permissions:
-      issues: write
-    steps:
-      - uses: actions/checkout@v4
-      - name: Ensure the issue has a label
-        env:
-          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-        run: python3 scripts/tracker_policy.py label-issue

.gitea/workflows/tracker-policy-pr.yml

@@ -1,18 +0,0 @@
-name: tracker-policy-pr
-
-on:
-  pull_request:
-    types: [opened, edited, reopened, synchronize, labeled, unlabeled]
-
-jobs:
-  check-pr:
-    runs-on: ubuntu-latest
-    permissions:
-      issues: read
-      pull-requests: read
-    steps:
-      - uses: actions/checkout@v4
-      - name: Require an unlabeled PR linked to an issue
-        env:
-          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-        run: python3 scripts/tracker_policy.py check-pr

.gitea/workflows/tracker-policy.yml

@@ -0,0 +1,33 @@
+name: tracker-policy
+
+on:
+  issues:
+    types: [opened, unlabeled]
+  pull_request:
+    types: [opened, edited, reopened, synchronized, labeled, unlabeled]
+
+jobs:
+  label-issue:
+    if: ${{ github.event_name == 'issues' }}
+    runs-on: ubuntu-latest
+    permissions:
+      issues: write
+    steps:
+      - uses: actions/checkout@v4
+      - name: Ensure the issue has a label
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+        run: python3 scripts/tracker_policy.py label-issue
+
+  check-pr:
+    if: ${{ github.event_name == 'pull_request' }}
+    runs-on: ubuntu-latest
+    permissions:
+      issues: read
+      pull-requests: read
+    steps:
+      - uses: actions/checkout@v4
+      - name: Require an unlabeled PR linked to an issue
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+        run: python3 scripts/tracker_policy.py check-pr

.gitea/workflows/update-badges.yml

@@ -20,18 +20,21 @@ jobs:
           fetch-depth: 0
           token: ${{ secrets.GITHUB_TOKEN }}
 
-      # No actions/setup-python: the runner image ships Python 3.12 and older
+      - name: Set up Python
-      # act_runner engines mishandle setup-python's PATH. Install into the
+        uses: actions/setup-python@v4
-      # ephemeral job container's system Python (--break-system-packages is
+        with:
-      # safe because the container is disposable).
+          python-version: '3.12'
+
       - name: Install dev dependencies
-        run: python3 -m pip install --break-system-packages -r requirements-dev.txt
+        run: |
+          python -m pip install --upgrade pip
+          pip install -r requirements-dev.txt
 
       - name: Run coverage and extract percentage
         id: coverage
         run: |
-          python3 -m coverage run -m unittest discover -t . -s tests/unit > /dev/null 2>&1 || true
+          python -m coverage run -m unittest discover -t . -s tests/unit > /dev/null 2>&1 || true
-          PERCENT=$(python3 -m coverage report 2>/dev/null | grep '^TOTAL' | grep -oP '\d+(?=%)' | tail -1)
+          PERCENT=$(python -m coverage report 2>/dev/null | grep '^TOTAL' | grep -oP '\d+(?=%)' | tail -1)
           echo "percent=$PERCENT" >> $GITHUB_OUTPUT
           echo "Coverage: $PERCENT%"
 
@@ -42,7 +45,7 @@ jobs:
           # the single source of truth in scripts/critical-modules.txt; every
           # core module is unit-tested, so the unit-only run is accurate for it.
           INCLUDE=$(grep -vE '^[[:space:]]*(#|$)' scripts/critical-modules.txt | paste -sd, -)
-          PERCENT=$(python3 -m coverage report --include="$INCLUDE" 2>/dev/null | grep '^TOTAL' | grep -oP '\d+(?=%)' | tail -1)
+          PERCENT=$(python -m coverage report --include="$INCLUDE" 2>/dev/null | grep '^TOTAL' | grep -oP '\d+(?=%)' | tail -1)
           echo "percent=$PERCENT" >> $GITHUB_OUTPUT
           echo "Core coverage: $PERCENT%"
 

Dockerfile.gateway

@@ -16,12 +16,10 @@
 # Layout:
 #
 #   /usr/bin/gitleaks                    gitleaks binary
-#   /app/egress_addon.py                 mitmproxy addon entry point
+#   /app/egress_addon.py + siblings      mitmproxy addon (egress)
 #   /app/egress-entrypoint.sh            mitmdump launcher
-#   /usr/local/lib/python*/bot_bottle/   installed package (all daemons + shared modules)
+#   /app/supervise_server.py + .py       supervise MCP server
-#   /app/egress_addon.py                 one-line shim: re-exports addons from package
+#   /app/gateway_init.py                 PID 1 supervisor
-#                                        (mitmdump -s requires a file path, not a module)
-#   /etc/egress/routes.yaml              bind-mounted at run time
 #   /etc/git-gate/pre-receive            docker-cp'd at start time
 #   /git-gate-entrypoint.sh              docker-cp'd at start time
 #   /git-gate/creds/*                    docker-cp'd at start time
@@ -89,19 +87,27 @@ RUN arch="${TARGETARCH:-$(dpkg --print-architecture)}" \
  && tar -xzf /tmp/gitleaks.tar.gz -C /usr/bin gitleaks \
  && rm /tmp/gitleaks.tar.gz
 
-# Install bot_bottle as a proper package so entry-point scripts can use
+# Project Python: addon + server modules + the init supervisor.
-# `from bot_bottle.X import Y` absolute imports. A rename or a missing
+# Kept flat under /app/ so mitmdump's loader resolves them as
-# module is caught at pip-install time — not at container runtime.
+# top-level siblings (absolute imports), matching the prior
-COPY pyproject.toml /src/
+# Dockerfile.egress / Dockerfile.supervise layout.
-COPY bot_bottle/    /src/bot_bottle/
+COPY bot_bottle/egress_addon_core.py /app/egress_addon_core.py
-RUN pip install --no-cache-dir /src/
+COPY bot_bottle/egress_dlp_config.py /app/egress_dlp_config.py
-
+COPY bot_bottle/egress_addon.py      /app/egress_addon.py
-# mitmdump -s requires a file path, not a module. Write a one-line shim that
+COPY bot_bottle/policy_resolver.py   /app/policy_resolver.py
-# re-exports `addons` from the installed package; mitmdump finds it there.
+COPY bot_bottle/dlp_detectors.py     /app/dlp_detectors.py
-# WORKDIR here also creates /app so the shim + COPYs below can write into it
+COPY bot_bottle/yaml_subset.py       /app/yaml_subset.py
-# (nothing created /app before this point).
+COPY bot_bottle/paths.py             /app/paths.py
-WORKDIR /app
+COPY bot_bottle/migrations.py        /app/migrations.py
-RUN printf 'from bot_bottle.egress_addon import addons\n' > /app/egress_addon.py
+COPY bot_bottle/db_store.py          /app/db_store.py
+COPY bot_bottle/supervise_types.py   /app/supervise_types.py
+COPY bot_bottle/queue_store.py       /app/queue_store.py
+COPY bot_bottle/audit_store.py       /app/audit_store.py
+COPY bot_bottle/store_manager.py     /app/store_manager.py
+COPY bot_bottle/supervise.py         /app/supervise.py
+COPY bot_bottle/supervise_server.py  /app/supervise_server.py
+COPY bot_bottle/gateway_init.py      /app/gateway_init.py
+COPY bot_bottle/git_http_backend.py  /app/git_http_backend.py
 COPY bot_bottle/egress_entrypoint.sh /app/egress-entrypoint.sh
 RUN chmod +x /app/egress-entrypoint.sh
 
@@ -120,6 +126,10 @@ RUN mkdir -p \
 # subset the bottle uses.
 EXPOSE 8888 9099 9418 9420 9100
 
+# WORKDIR matches Dockerfile.supervise's prior layout so the
+# in-app same-dir import in supervise_server.py stays deterministic.
+WORKDIR /app
+
 # PID 1 is the supervisor. It owns signal handling and exit-code
 # propagation; no `exec` chain in the entrypoint itself.
-ENTRYPOINT ["python3", "-m", "bot_bottle.gateway_init"]
+ENTRYPOINT ["python3", "/app/gateway_init.py"]

README.md

@@ -5,8 +5,8 @@
 # bot-bottle
 
 [![test](https://gitea.dideric.is/didericis/bot-bottle/actions/workflows/test.yml/badge.svg?branch=main)](https://gitea.dideric.is/didericis/bot-bottle/actions?workflow=test.yml)
-[![coverage](https://img.shields.io/badge/coverage-81%25-brightgreen)](https://coverage.readthedocs.io/)
+[![coverage](https://img.shields.io/badge/coverage-82%25-brightgreen)](https://coverage.readthedocs.io/)
-[![core coverage](https://img.shields.io/badge/core%20coverage-94%25-brightgreen)](https://gitea.dideric.is/didericis/bot-bottle/src/branch/main/docs/decisions/0004-coverage-policy.md)
+[![core coverage](https://img.shields.io/badge/core%20coverage-95%25-brightgreen)](https://gitea.dideric.is/didericis/bot-bottle/src/branch/main/docs/decisions/0004-coverage-policy.md)
 
 **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.
 
@@ -75,22 +75,6 @@ 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.
 
-> **Experimental containers-in-bottle spike (#392):** a bottle may set
-> `docker_access: true`. On the macOS backend this starts a guest-local,
-> rootless **podman** service after the bottle is registered, exposing its
-> Docker-compatible API socket — the agent still uses `docker` and `docker
-> compose`. It does not mount Docker Desktop's socket or add outer VM
-> capabilities. 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.
-
 ### Firecracker on Linux
 
 On Linux, a KVM-capable host defaults to the Firecracker backend. It needs:
@@ -106,8 +90,6 @@ BOT_BOTTLE_BACKEND=firecracker ./cli.py start <agent>
 
 > **NixOS:** enable `virtualisation.docker`, ensure the KVM module is loaded (`boot.kernelModules = [ "kvm-intel" ];` or `kvm-amd`), and add your user to the `kvm` and `docker` groups. For the network pool, consume the flake module — `imports = [ inputs.bot-bottle.nixosModules.firecracker-netpool ]; services.bot-bottle-firecracker = { enable = true; owner = "you"; };` — then `nixos-rebuild switch` (imperative nft/TAP rules don't survive a rebuild; channel users can `imports = [ <bot-bottle>/nix/firecracker-netpool.nix ]`). `firecracker` isn't in nixpkgs by default as a user binary — install the release binary (pin the version) and put it on `PATH`.
 
-> **CI:** the coverage gate (`.gitea/workflows/test.yml` → `coverage` job) runs on a self-hosted runner labelled `kvm`, because the Firecracker backend's VM/SSH orchestration is exercised only by the integration suite, which needs `/dev/kvm` + the provisioned pool (a container runner would skip it and read as uncovered). Provision that runner exactly like a normal Firecracker host — `firecracker` on `PATH`, `/dev/kvm`, the cached guest kernel + static dropbear, and the pool installed as the persistent systemd unit — then register it with the `kvm` label. A Docker-capable hosted job builds the candidate once; KVM tests boot those exact bytes, and a successful main run publishes them. The unit/lint jobs still run on `ubuntu-latest`.
-
 ```sh
 ./cli.py start <agent>   # builds the image on first run, drops you into claude
 ```

bot_bottle/audit_store.py

@@ -42,7 +42,7 @@ class AuditStore(DbStore):
         super().__init__(db_path or host_db_path(), migrations)
 
     def write_audit_entry(self, entry: AuditEntry) -> Path:
-        with self._connection() as conn:
+        with self._connect() as conn:
             conn.execute(
                 """
                 INSERT INTO supervise_audit_entries (
@@ -66,7 +66,7 @@ class AuditStore(DbStore):
     def read_audit_entries(self, component: str, slug: str) -> list[AuditEntry]:
         if not self.db_path.is_file():
             return []
-        with self._connection() as conn:
+        with self._connect() as conn:
             rows = conn.execute(
                 """
                 SELECT * FROM supervise_audit_entries

bot_bottle/backend/__init__.py

@@ -40,13 +40,12 @@ from abc import ABC, abstractmethod
 from contextlib import AbstractContextManager
 from dataclasses import dataclass
 from pathlib import Path
-from typing import TYPE_CHECKING, Any, Generic, Sequence, TypeVar
+from typing import Any, Generic, Sequence, TypeVar
 
 from ..agent_provider import AgentProvisionPlan, get_provider, build_agent_provision_plan
 from ..egress import EgressPlan
 from ..git_gate import GitGatePlan
-from ..log import die, info, warn
+from ..log import die, info
-from ..util import read_tty_line
 from ..manifest import Manifest, ManifestIndex
 from ..supervise import SupervisePlan
 from ..util import expand_tilde
@@ -55,9 +54,6 @@ from ..workspace import WorkspacePlan, workspace_plan
 from .print_util import print_multi, visible_agent_env_names
 from .util import host_skill_dir
 
-if TYPE_CHECKING:
-    from .freeze import CommitCancelled, Freezer, get_freezer
-
 
 @dataclass(frozen=True)
 class BottleSpec:
@@ -588,170 +584,68 @@ class BottleBackend(ABC, Generic[PlanT, CleanupT]):
         Not called by the launch path or the test suite."""
 
 
-# _backends is None until the first call to _get_backends(), at which
+# Import concrete backend classes AFTER the base types are defined, so
-# point all three concrete backend classes are imported and instantiated.
+# each backend module can pull BottleSpec / BottlePlan / BottleBackend
-# Keeping the imports out of module scope means that importing any
+# via `from . import ...` without hitting a partially-initialized module.
-# backend sub-module (e.g. `backend.docker.util`) no longer drags the
+from .docker import DockerBottleBackend  # noqa: E402  # pylint: disable=wrong-import-position
-# firecracker and macos-container implementations into memory.
+from .firecracker import FirecrackerBottleBackend  # noqa: E402  # pylint: disable=wrong-import-position
-#
+from .macos_container import MacosContainerBottleBackend  # noqa: E402  # pylint: disable=wrong-import-position
-# Tests may replace _backends with a {name: fake} dict via patch.object;
+
-# _get_backends() returns the current module-level value as-is when it
+# Freezer is imported after the backend classes for the same reason:
-# is not None, so test fakes take effect without triggering real imports.
+# Freezer.commit_slug constructs ActiveAgent, which must be fully
-_backends: dict[str, BottleBackend[Any, Any]] | None = None
+# defined first.
+from .freeze import CommitCancelled, Freezer, get_freezer  # noqa: E402  # pylint: disable=wrong-import-position
 
 
-def _get_backends() -> dict[str, BottleBackend[Any, Any]]:
+# The dict is heterogeneous: each value is a BottleBackend specialized
-    """Return the registry of all backend instances, loading lazily on first call."""
+# over its own plan type. Concrete plan types are erased here because
-    global _backends  # pylint: disable=global-statement
+# the registry is selected at runtime and the CLI only needs the
-    if _backends is None:
+# unparameterized methods (prepare → plan → launch(plan), cleanup, etc.).
-        from .docker import DockerBottleBackend
+_BACKENDS: dict[str, BottleBackend[Any, Any]] = {
-        from .firecracker import FirecrackerBottleBackend
+    "docker": DockerBottleBackend(),
-        from .macos_container import MacosContainerBottleBackend
+    "firecracker": FirecrackerBottleBackend(),
-        _backends = {
+    "macos-container": MacosContainerBottleBackend(),
-            "docker": DockerBottleBackend(),
+}
-            "firecracker": FirecrackerBottleBackend(),
-            "macos-container": MacosContainerBottleBackend(),
-        }
-    return _backends
-
-
-def __getattr__(name: str) -> Any:
-    """Lazily surface concrete backend classes and freeze symbols at the
-    package level so existing `from bot_bottle.backend import X` and
-    `patch.object(backend_mod, X, ...)` call-sites keep working without
-    forcing an import of every backend at module-init time."""
-    if name == "DockerBottleBackend":
-        from .docker import DockerBottleBackend
-        globals()[name] = DockerBottleBackend
-        return DockerBottleBackend
-    if name == "FirecrackerBottleBackend":
-        from .firecracker import FirecrackerBottleBackend
-        globals()[name] = FirecrackerBottleBackend
-        return FirecrackerBottleBackend
-    if name == "MacosContainerBottleBackend":
-        from .macos_container import MacosContainerBottleBackend
-        globals()[name] = MacosContainerBottleBackend
-        return MacosContainerBottleBackend
-    if name == "CommitCancelled":
-        from .freeze import CommitCancelled
-        globals()[name] = CommitCancelled
-        return CommitCancelled
-    if name == "Freezer":
-        from .freeze import Freezer
-        globals()[name] = Freezer
-        return Freezer
-    if name == "get_freezer":
-        from .freeze import get_freezer
-        globals()[name] = get_freezer
-        return get_freezer
-    raise AttributeError(f"module {__name__!r} has no attribute {name!r}")
 
 
 def get_bottle_backend(
     name: str | None = None,
-    *,
-    prompt: bool = True,
 ) -> BottleBackend[Any, Any]:
     """Resolve the bottle backend.
 
     `name` precedence:
-      1. explicit arg (e.g. resume passes the recorded backend name)
+      1. explicit arg (CLI `--backend=<name>` passes through here)
       2. BOT_BOTTLE_BACKEND env var
-      3. auto-selection: VM backend first, docker fallback with prompt
+      3. `macos-container` on compatible macOS hosts
-
+      4. `firecracker` on KVM-capable Linux hosts
-    `prompt` controls whether auto-selection may block on an interactive
+      5. default `docker`
-    [i/d/q] prompt when falling back to docker. Pass `prompt=False` in
-    non-interactive contexts (headless launches, CI) so the call dies
-    with an actionable message instead of hanging.
 
     Dies with a pointer at the known backends if the chosen name
     isn't implemented."""
-    resolved = name or os.environ.get("BOT_BOTTLE_BACKEND")
+    resolved = name or os.environ.get("BOT_BOTTLE_BACKEND") or _default_backend_name()
-    if resolved is None:
+    if resolved not in _BACKENDS:
-        resolved = _auto_select_backend(prompt=prompt)
+        known = ", ".join(sorted(_BACKENDS))
-    backends = _get_backends()
-    if resolved not in backends:
-        known = ", ".join(sorted(backends))
         die(f"unknown backend {resolved!r}; known backends: {known}")
-    return backends[resolved]
+    return _BACKENDS[resolved]
 
 
-def _platform_vm_suggestion() -> str:
+def _default_backend_name() -> str:
-    """Platform-appropriate VM backend name for install suggestions."""
-    return "macos-container" if sys.platform == "darwin" else "firecracker"
-
-
-def _print_vm_install_instructions() -> None:
-    """Print platform-appropriate VM backend install instructions to stderr."""
-    vm = _platform_vm_suggestion()
-    if vm == "macos-container":
-        info("Install Apple Container: https://github.com/apple/container/releases")
-        info("Then start the service:  container system start")
-    else:
-        info("Install Firecracker: https://github.com/firecracker-microvm/firecracker/releases")
-        info("Configure the host:  ./cli.py backend setup")
-
-
-def _auto_select_backend(prompt: bool = True) -> str:
-    """Tier-1 / tier-2 backend auto-selection.
-
-    Tier 1: VM backend — macos-container on macOS when Apple Container is
-    installed; firecracker on KVM-capable Linux even before the binary is
-    present (its preflight prints an install pointer).
-
-    Tier 2: docker, with a security warning and an interactive prompt.
-    When `prompt=False` (headless / CI), dies with an actionable message
-    instead of blocking on a TTY read. When docker is also absent, prints
-    VM install instructions and exits.
-    """
-    # --- Tier 1: VM backend -----------------------------------------
     if has_backend("macos-container"):
         return "macos-container"
     # A KVM-capable Linux host defaults to firecracker even when the
     # `firecracker` binary isn't installed yet: selecting it here routes
     # start through firecracker's preflight, which prints an install
     # pointer, instead of silently falling back to docker.
-    from .firecracker import FirecrackerBottleBackend
     if FirecrackerBottleBackend.is_host_capable():
         return "firecracker"
-
+    return "docker"
-    # --- Tier 2: docker fallback ------------------------------------
-    if not has_backend("docker"):
-        info("No backend available on this host.")
-        _print_vm_install_instructions()
-        die("no backend available; install a VM backend and re-run")
-
-    vm = _platform_vm_suggestion()
-    warn(
-        "docker is less secure than VM backends — "
-        "containers share the host kernel."
-    )
-    if not prompt:
-        die(
-            f"no VM backend available; set BOT_BOTTLE_BACKEND=docker to proceed "
-            f"with docker, or install the {vm!r} backend."
-        )
-    sys.stderr.write(
-        f"bot-bottle: For better isolation, install the {vm!r} backend.\n"
-        f"  [i] show {vm} install instructions and exit\n"
-        "  [d] use docker anyway\n"
-        "  [q] quit\n"
-        "bot-bottle: choice [i/d/q]: "
-    )
-    sys.stderr.flush()
-    reply = read_tty_line().strip().lower()
-    if reply == "d":
-        return "docker"
-    if reply == "i":
-        _print_vm_install_instructions()
-    die("not proceeding with docker; install a VM backend or set BOT_BOTTLE_BACKEND=docker")
 
 
 def known_backend_names() -> tuple[str, ...]:
-    """Sorted tuple of all backend keys in `_get_backends()`. Used by
+    """Sorted tuple of all backend keys in `_BACKENDS`. Used by
     argparse (`--backend` choices) and the dashboard's backend
     picker."""
-    return tuple(sorted(_get_backends()))
+    return tuple(sorted(_BACKENDS))
 
 
 def has_backend(name: str) -> bool:
@@ -763,10 +657,9 @@ def has_backend(name: str) -> bool:
 
     Returns False for unknown names so callers can pass
     arbitrary input without separate validation."""
-    backends = _get_backends()
+    if name not in _BACKENDS:
-    if name not in backends:
         return False
-    return backends[name].is_available()
+    return _BACKENDS[name].is_available()
 
 
 def enumerate_active_agents() -> list[ActiveAgent]:
@@ -782,11 +675,10 @@ def enumerate_active_agents() -> list[ActiveAgent]:
     deterministic tiebreaker. Agents with missing metadata
     (`started_at == ""`) sort first."""
     out: list[ActiveAgent] = []
-    backends = _get_backends()
+    for name in known_backend_names():
-    for name in sorted(backends):
+        if not has_backend(name):
-        if not backends[name].is_available():
             continue
-        out.extend(backends[name].enumerate_active())
+        out.extend(_BACKENDS[name].enumerate_active())
     out.sort(key=lambda a: (a.started_at, a.slug))
     return out
 

bot_bottle/backend/docker/consolidated_launch.py

@@ -142,19 +142,11 @@ def launch_consolidated(
 
 
 def teardown_consolidated(
-    bottle_id: str,
+    bottle_id: str, *, orchestrator_url: str, gateway_name: str = GATEWAY_NAME,
-    *,
-    orchestrator_url: str,
-    gateway_name: str = GATEWAY_NAME,
-    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."""
-    from ...orchestrator.config_store import DEFAULT_TEARDOWN_TIMEOUT_SECONDS
+    OrchestratorClient(orchestrator_url).teardown_bottle(bottle_id)
-    OrchestratorClient(
-        orchestrator_url,
-        timeout=timeout if timeout is not None else DEFAULT_TEARDOWN_TIMEOUT_SECONDS,
-    ).teardown_bottle(bottle_id)
     deprovision_git_gate(DockerGatewayTransport(gateway_name), bottle_id)
 
 

bot_bottle/backend/docker/launch.py

@@ -62,7 +62,6 @@ 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
 
@@ -134,14 +133,11 @@ 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,
+            teardown_consolidated, ctx.bottle_id, orchestrator_url=ctx.orchestrator_url,
-            orchestrator_url=ctx.orchestrator_url,
-            timeout=teardown_timeout,
         )
 
         # Step 4: install the SHARED gateway CA into the agent (replaces the

bot_bottle/backend/docker/setup.py

@@ -27,14 +27,10 @@ def _docker_on_path() -> bool:
 def _daemon_reachable() -> bool:
     if not _docker_on_path():
         return False
-    try:
+    return subprocess.run(
-        return subprocess.run(
+        ["docker", "info"],
-            ["docker", "info"],
+        stdout=subprocess.DEVNULL, stderr=subprocess.DEVNULL, check=False,
-            stdout=subprocess.DEVNULL, stderr=subprocess.DEVNULL,
+    ).returncode == 0
-            check=False, timeout=5,
-        ).returncode == 0
-    except subprocess.TimeoutExpired:
-        return False
 
 
 def _print_install_pointer() -> None:

bot_bottle/backend/docker/util.py

@@ -8,7 +8,7 @@ import os
 import re
 import shutil
 import subprocess
-from typing import Iterator
+from typing import Iterable, Iterator
 
 from ...docker_cmd import run_docker
 from ...log import die, info
@@ -32,7 +32,12 @@ def container_name_candidates(base: str) -> Iterator[str]:
 def runsc_available() -> bool:
     """Return True if the Docker daemon has the gVisor (`runsc`) runtime
     registered. Called once per prepare; the result lives on the plan."""
-    r = run_docker(["docker", "info", "--format", "{{json .Runtimes}}"])
+    r = subprocess.run(
+        ["docker", "info", "--format", "{{json .Runtimes}}"],
+        capture_output=True,
+        text=True,
+        check=False,
+    )
     return r.returncode == 0 and "runsc" in r.stdout
 
 
@@ -46,15 +51,20 @@ def require_docker() -> None:
 
 
 def image_exists(ref: str) -> bool:
-    return run_docker(["docker", "image", "inspect", ref]).returncode == 0
+    return _silent_run(["docker", "image", "inspect", ref]) == 0
 
 
 def container_exists(name: str) -> bool:
     """Returns True if a container (running or stopped) with the given
     name exists. Uses `docker ps -a -q -f name=^<name>$` so substring
     matches don't false-positive."""
-    result = run_docker(["docker", "ps", "-a", "-q", "-f", f"name=^{name}$"])
+    result = subprocess.run(
-    return result.returncode == 0 and bool(result.stdout.strip())
+        ["docker", "ps", "-a", "-q", "-f", f"name=^{name}$"],
+        capture_output=True,
+        text=True,
+        check=True,
+    )
+    return bool(result.stdout.strip())
 
 
 def force_remove_container(name: str) -> None:
@@ -62,7 +72,12 @@ def force_remove_container(name: str) -> None:
     doesn't — and the rm itself is best-effort (errors swallowed) so
     this is safe to register as a teardown callback."""
     if container_exists(name):
-        run_docker(["docker", "rm", "-f", name])
+        subprocess.run(
+            ["docker", "rm", "-f", name],
+            stdout=subprocess.DEVNULL,
+            stderr=subprocess.DEVNULL,
+            check=False,
+        )
 
 
 def docker_exec_root(container: str, argv: list[str]) -> None:
@@ -190,10 +205,22 @@ def verify_agent_image(image: str, argv: tuple[str, ...]) -> None:
 def commit_container(container_name: str, image_tag: str) -> None:
     """Run `docker commit <container_name> <image_tag>` to snapshot the
     running container's filesystem state as a local Docker image."""
-    result = run_docker(["docker", "commit", container_name, image_tag])
+    result = subprocess.run(
+        ["docker", "commit", container_name, image_tag],
+        capture_output=True, text=True, check=False,
+    )
     if result.returncode != 0:
         die(
             f"docker commit {container_name!r} → {image_tag!r} failed: "
             f"{(result.stderr or '').strip() or '<no stderr>'}"
         )
     info(f"committed {container_name!r} → {image_tag!r}")
+
+
+def _silent_run(cmd: Iterable[str]) -> int:
+    return subprocess.run(
+        list(cmd),
+        stdout=subprocess.DEVNULL,
+        stderr=subprocess.DEVNULL,
+        check=False,
+    ).returncode

bot_bottle/backend/firecracker/consolidated_launch.py

@@ -91,18 +91,12 @@ def launch_consolidated(
     )
 
 
-def teardown_consolidated(
+def teardown_consolidated(bottle_id: str, *, orchestrator_url: str) -> None:
-    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."""
-    from ...orchestrator.config_store import DEFAULT_TEARDOWN_TIMEOUT_SECONDS
+    OrchestratorClient(orchestrator_url).teardown_bottle(bottle_id)
-    OrchestratorClient(
-        orchestrator_url,
-        timeout=timeout if timeout is not None else DEFAULT_TEARDOWN_TIMEOUT_SECONDS,
-    ).teardown_bottle(bottle_id)
     deprovision_git_gate(infra_vm.gateway_transport(), bottle_id)
 
 

bot_bottle/backend/firecracker/image_builder.py

@@ -38,39 +38,25 @@ _BUILD_TIMEOUT_SECONDS = 900.0
 
 
 def _dockerfile_hash(dockerfile: Path) -> str:
-    """The Dockerfile's content hash. The shipped agent Dockerfiles COPY
+    """Cache key: the Dockerfile's content. The shipped agent Dockerfiles
-    nothing from the build context (see .dockerignore), so their content fully
+    COPY nothing from the build context (see .dockerignore), so their content
-    determines the built image; a Dockerfile that adds COPY will want the
+    fully determines the image; a Dockerfile that adds COPY will want the
     context folded in here too."""
     return hashlib.sha256(dockerfile.read_bytes()).hexdigest()[:16]
 
 
-def _rootfs_digest(dockerfile: Path) -> str:
-    """Cache key for the built AND boot-injected agent rootfs. Two inputs
-    determine the on-disk rootfs: the Dockerfile (the image) and the guest init
-    injected into it (`util._GUEST_INIT`). Folding the init in means a fix to
-    it — e.g. making /tmp world-writable — busts the cache instead of silently
-    reusing a stale rootfs built with the old init."""
-    h = hashlib.sha256()
-    h.update(_dockerfile_hash(dockerfile).encode())
-    h.update(b"\0")
-    h.update(util._GUEST_INIT.encode())
-    return h.hexdigest()[:16]
-
-
 def build_agent_rootfs_dir(
     dockerfile: Path, *, image_tag: str, smoke_test: tuple[str, ...] = (),
 ) -> Path:
     """Build `dockerfile` in the infra VM (buildah, no host docker), export its
     rootfs, inject the guest boot bits, and return the cached base dir — the
-    same shape `util.build_rootfs_ext4` consumes. Cached by Dockerfile content
+    same shape `util.build_rootfs_ext4` consumes. Cached by Dockerfile content,
-    + injected guest init, so a repeat launch skips the rebuild but an init or
+    so a repeat launch skips the rebuild.
-    Dockerfile change rebuilds.
 
     `smoke_test` (the provider's declared argv, e.g. `("claude","--version")`)
     is run in the freshly built image before export, catching an npm
     silent-failure image at build time rather than at first agent use."""
-    digest = _rootfs_digest(dockerfile)
+    digest = _dockerfile_hash(dockerfile)
     base = util.cache_dir() / "rootfs" / f"agent-{digest}"
     if (base / ".bb-ready").is_file():
         info(f"using cached agent rootfs {base.name}")

bot_bottle/backend/firecracker/infra_artifact.py

@@ -85,11 +85,6 @@ def infra_artifact_version(init_script: str, *, repo_root: Path = _REPO_ROOT) ->
         h.update(name.encode())
         h.update(b"\0")
         h.update((repo_root / name).read_bytes())
-    h.update(b"pyproject.toml\0")
-    h.update((repo_root / "pyproject.toml").read_bytes())
-    h.update(b"dropbear\0")
-    dropbear = util.dropbear_path()
-    h.update(dropbear.read_bytes() if dropbear.is_file() else b"<missing>")
     h.update(b"init\0")
     h.update(init_script.encode())
     return h.hexdigest()[:16]
@@ -116,7 +111,6 @@ def artifact_url(version: str, filename: str) -> str:
 
 _GZ_NAME = "rootfs.ext4.gz"
 _SHA_NAME = "rootfs.ext4.gz.sha256"
-_CANDIDATE_DIR_ENV = "BOT_BOTTLE_INFRA_ARTIFACT_DIR"
 
 
 def _cache_root(version: str) -> Path:
@@ -166,33 +160,6 @@ def ensure_artifact_gz(version: str) -> Path:
     """The verified, cached `rootfs.ext4.gz` for `version` — downloading it (and
     its `.sha256`) once, then reusing it. Fail-closed on a checksum mismatch:
     the partial is removed and we die rather than boot an unverified rootfs."""
-    candidate_dir = os.environ.get(_CANDIDATE_DIR_ENV, "").strip()
-    if candidate_dir:
-        root = Path(candidate_dir)
-        version_file = root / "version.txt"
-        # Guard the read so a missing version.txt is a clean error, not a raw
-        # FileNotFoundError.
-        if not version_file.is_file():
-            die(f"infra candidate bundle is incomplete: {root}")
-        declared = version_file.read_text(encoding="utf-8").strip()
-        if declared != version:
-            die(
-                f"infra candidate version mismatch: expected {version}, "
-                f"bundle contains {declared or '<empty>'}"
-            )
-        gz = root / _GZ_NAME
-        sha = root / _SHA_NAME
-        if not gz.is_file() or not sha.is_file():
-            die(f"infra candidate bundle is incomplete: {root}")
-        expected = sha.read_text().split()[0].strip().lower()
-        actual = _sha256_file(gz)
-        if actual != expected:
-            die(
-                f"infra candidate checksum mismatch for {version}:\n"
-                f"    expected {expected}\n    actual   {actual}"
-            )
-        return gz
-
     root = _cache_root(version)
     root.mkdir(parents=True, exist_ok=True)
     gz = root / _GZ_NAME

bot_bottle/backend/firecracker/infra_vm.py

@@ -161,23 +161,20 @@ def ensure_running() -> InfraVm:
     slot = netpool.orch_slot()
     url = f"http://{slot.guest_ip}:{CONTROL_PLANE_PORT}"
     key = _infra_dir() / "id_ed25519"
-    want = _expected_version()
+    if key.exists() and _health_ok(url):
-    if _adoptable(key, url, want):
         info(f"adopting running infra VM at {url}")
         return InfraVm(guest_ip=slot.guest_ip, private_key=key)
 
     with _singleton_lock():
         # Re-check under the lock: another launcher may have booted it while
         # we waited for the lock (double-checked, so we adopt not re-boot).
-        if _adoptable(key, url, want):
+        if key.exists() and _health_ok(url):
             info(f"adopting running infra VM at {url}")
             return InfraVm(guest_ip=slot.guest_ip, private_key=key)
-        # Clear a stale/hung/OUTDATED VM holding the link before booting fresh.
+        stop()  # clear a stale/hung VM holding the link before booting fresh
-        stop()
         ensure_built()
         infra = boot()
         wait_for_health(infra)
-        _record_booted_version(want)
         return infra
 
 
@@ -196,15 +193,9 @@ def _singleton_lock() -> Generator[None, None, None]:
 
 
 def stop() -> None:
-    """Stop the infra VM singleton (idempotent — absent is success). Reaps the
+    """Stop the infra VM singleton (idempotent — absent is success)."""
-    recorded VMM AND any orphaned firecracker still bound to the infra config —
-    the PID file drifts after crashes / out-of-band kills, and a survivor would
-    hold the orchestrator TAP so the next boot dies with "tap … Resource busy".
-    Drops the version marker so a stopped VM is never treated as adoptable."""
     _kill_pidfile()
-    _kill_infra_firecrackers()
     _pid_file().unlink(missing_ok=True)
-    _version_file().unlink(missing_ok=True)
 
 
 def boot() -> InfraVm:
@@ -247,36 +238,6 @@ def _pid_file() -> Path:
     return _infra_dir() / "vm.pid"
 
 
-def _version_file() -> Path:
-    """Records the infra-artifact version the *running* VM booted from, so a
-    later launcher can tell whether the singleton it found is the current code.
-    Without it, a healthy VM built from an older image gets adopted forever and
-    the new code never boots — every infra change would need an out-of-band
-    kill to dislodge the stale VM (and races whatever launched next)."""
-    return _infra_dir() / "booted-version"
-
-
-def _expected_version() -> str:
-    return infra_artifact.infra_artifact_version(_infra_init())
-
-
-def _adoptable(key: Path, url: str, want: str) -> bool:
-    """Adopt a running infra VM only if it booted from the CURRENT version and
-    its control plane is healthy. A missing/mismatched marker means a prior
-    launcher booted an older infra image — reboot rather than reuse stale code."""
-    if not key.exists():
-        return False
-    try:
-        booted = _version_file().read_text(encoding="utf-8").strip()
-    except OSError:
-        return False
-    return booted == want and _health_ok(url)
-
-
-def _record_booted_version(version: str) -> None:
-    _version_file().write_text(version + "\n", encoding="utf-8")
-
-
 # The registry "volume": a host-side ext4 file attached to the infra VM as a
 # second virtio-block device (guest /dev/vdb), mounted at the control plane's
 # DB dir. It outlives the ephemeral rootfs, so the bottle registry survives an
@@ -348,28 +309,6 @@ def _kill_pidfile() -> None:
         pass
 
 
-def _kill_infra_firecrackers(proc_root: Path = Path("/proc")) -> None:
-    """SIGKILL any firecracker VMM whose `--config-file` is this host's infra
-    config, independent of the PID file — reaps orphans it lost track of so the
-    orchestrator TAP is free to rebind. Scoped to the infra config path, so the
-    interactive pool's agent/infra VMs (other config paths) are untouched."""
-    cfg = str(_infra_dir() / "config.json")
-    for entry in proc_root.iterdir():
-        if not entry.name.isdigit():
-            continue
-        try:
-            if (entry / "comm").read_text().strip() != "firecracker":
-                continue
-            args = (entry / "cmdline").read_bytes().split(b"\0")
-        except OSError:
-            continue  # process vanished / not ours
-        if any(a.decode("utf-8", "replace") == cfg for a in args):
-            try:
-                os.kill(int(entry.name), signal.SIGKILL)
-            except (OSError, ValueError):
-                pass
-
-
 def _health_ok(url: str) -> bool:
     try:
         with urllib.request.urlopen(f"{url}/health", timeout=1.0) as resp:
@@ -494,7 +433,7 @@ BOT_BOTTLE_ROOT=/var/lib/bot-bottle python3 -m bot_bottle.orchestrator \\
 BOT_BOTTLE_GATEWAY_DAEMONS=egress,git-http,supervise \\
 BOT_BOTTLE_ORCHESTRATOR_URL=http://127.0.0.1:{CONTROL_PLANE_PORT} \\
 SUPERVISE_DB_PATH=/var/lib/bot-bottle/db/bot-bottle.db \\
-    python3 -m bot_bottle.gateway_init &
+    python3 /app/gateway_init.py &
 
 # Reap as PID 1; children are backgrounded, so `wait` blocks.
 while : ; do wait ; done

bot_bottle/backend/firecracker/launch.py

@@ -52,7 +52,6 @@ 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 .consolidated_launch import (
     launch_consolidated,
     teardown_consolidated,
@@ -113,7 +112,6 @@ 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,
@@ -123,7 +121,6 @@ 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).

bot_bottle/backend/firecracker/publish_infra.py

@@ -11,8 +11,7 @@ The `<version>` is `infra_artifact.infra_artifact_version(...)`, the content
 hash of the rootfs inputs, so a launch host at the same code checkout resolves
 the exact artifact this produced.
 
-  python3 -m bot_bottle.backend.firecracker.publish_infra --output DIR
+  python3 -m bot_bottle.backend.firecracker.publish_infra [--dry-run] [--force]
-  python3 -m bot_bottle.backend.firecracker.publish_infra --publish-dir DIR
 
 Auth: a token with `write:package` on the target owner, from
 `BOT_BOTTLE_INFRA_ARTIFACT_TOKEN`.
@@ -25,6 +24,7 @@ import gzip
 import hashlib
 import shutil
 import sys
+import tempfile
 import urllib.error
 import urllib.request
 from pathlib import Path
@@ -131,79 +131,36 @@ def build_artifact(out_dir: Path) -> tuple[str, Path, Path]:
     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
-    # FileNotFoundError.
-    if not version_file.is_file():
-        raise SystemExit(f"incomplete artifact bundle: {root}")
-    version = version_file.read_text(encoding="utf-8").strip()
-    expected = infra_artifact.infra_artifact_version(infra_vm._infra_init())
-    if version != expected:
-        raise SystemExit(
-            f"artifact bundle version {version!r} does not match checkout {expected!r}"
-        )
-    gz = root / "rootfs.ext4.gz"
-    sha = root / "rootfs.ext4.gz.sha256"
-    if not gz.is_file() or not sha.is_file():
-        raise SystemExit(f"incomplete artifact bundle: {root}")
-    expected_sha = sha.read_text().split()[0].strip().lower()
-    if _sha256(gz) != expected_sha:
-        raise SystemExit("artifact bundle checksum mismatch")
-
-    gz_url = infra_artifact.artifact_url(version, gz.name)
-    sha_url = infra_artifact.artifact_url(version, sha.name)
-    about_url = infra_artifact.artifact_url(version, _ABOUT_NAME)
-
-    # Publishing is idempotent. If this exact complete artifact is already
-    # present, a test-only main commit is a no-op. Otherwise clear any partial
-    # upload left by an interrupted prior attempt and upload the complete set.
-    try:
-        with urllib.request.urlopen(infra_artifact._open(sha_url)) as resp:
-            remote_sha = resp.read().decode("utf-8").split()[0].strip().lower()
-    except urllib.error.HTTPError as e:
-        if e.code != 404:
-            raise SystemExit(f"checking existing artifact failed (HTTP {e.code})")
-        remote_sha = ""
-    except urllib.error.URLError as e:
-        raise SystemExit(f"registry unreachable: {sha_url} ({e.reason})")
-    if remote_sha == expected_sha:
-        print(f"infra rootfs {version} already published")
-        return version
-
-    for url in (gz_url, sha_url, about_url):
-        _delete(url, token)
-    _put(gz_url, gz, token)
-    _put(sha_url, sha.read_bytes(), token)
-    _put(about_url, _ABOUT_TEXT.encode(), token)
-    return version
-
-
 def main(argv: list[str] | None = None) -> int:
     parser = argparse.ArgumentParser(
         prog="publish_infra", description="Build + publish the infra rootfs artifact.")
-    mode = parser.add_mutually_exclusive_group(required=True)
+    parser.add_argument("--dry-run", action="store_true",
-    mode.add_argument("--output", type=Path,
+                        help="build the artifact but do not upload")
-                      help="build a candidate bundle in DIR without publishing")
+    parser.add_argument("--force", action="store_true",
-    mode.add_argument("--publish-dir", type=Path,
+                        help="overwrite an already-published artifact of this version")
-                      help="publish an already-built and tested candidate bundle")
     args = parser.parse_args(argv)
 
     _, _, token = infra_artifact._config()
-    if args.publish_dir is not None and not token:
+    if not args.dry_run and not token:
         raise SystemExit(
             "no publish token: set BOT_BOTTLE_INFRA_ARTIFACT_TOKEN to a token "
             "with write:package")
 
-    if args.output is not None:
+    with tempfile.TemporaryDirectory(prefix="bb-publish-infra.") as tmp:
-        args.output.mkdir(parents=True, exist_ok=True)
+        version, gz, sha = build_artifact(Path(tmp))
-        version, _gz, _sha = build_artifact(args.output)
+        gz_url = infra_artifact.artifact_url(version, gz.name)
-        (args.output / "version.txt").write_text(version + "\n", encoding="utf-8")
+        sha_url = infra_artifact.artifact_url(version, sha.name)
-        print(f"built infra rootfs candidate {version}")
+        about_url = infra_artifact.artifact_url(version, _ABOUT_NAME)
-        return 0
+        if args.dry_run:
-
+            print(f"dry-run: would upload -> {gz_url}")
-    assert args.publish_dir is not None
+            return 0
-    version = _publish_bundle(args.publish_dir, token)
+        if args.force:
+            _delete(gz_url, token)
+            _delete(sha_url, token)
+            _delete(about_url, token)
+        _put(gz_url, gz, token)  # streamed from disk (hundreds of MB)
+        _put(sha_url, sha.read_bytes(), token)  # tiny, in-memory is fine
+        _put(about_url, _ABOUT_TEXT.encode(), token)  # package description
     print(f"published infra rootfs {version}")
     return 0
 

bot_bottle/backend/firecracker/util.py

@@ -88,7 +88,7 @@ def require_firecracker() -> None:
     booting a VM without it."""
     if not is_linux():
         die("firecracker backend is only supported on Linux (KVM). "
-            "On macOS use the macos-container backend.")
+            "On macOS use --backend=macos-container.")
     if shutil.which("firecracker") is None:
         info("Firecracker is required but was not found on PATH.")
         info("Install: https://github.com/firecracker-microvm/firecracker/releases")
@@ -368,11 +368,6 @@ mount -t devtmpfs dev /dev 2>/dev/null
 mkdir -p /dev/pts && mount -t devpts devpts /dev/pts 2>/dev/null
 mount -o remount,rw / 2>/dev/null
 
-# /tmp must be world-writable + sticky. The rootless rootfs build can land
-# it 0755/root-owned, leaving the agent (uid 1000 node) unable to create
-# scratch dirs there — git worktrees, build temp, `git init /tmp/...`, etc.
-mkdir -p /tmp && chmod 1777 /tmp
-
 # 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

bot_bottle/backend/macos_container/bottle.py

@@ -68,14 +68,9 @@ 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.
+        # 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
-        # `container exec --env` does NOT override a run-time value — it
+        # supersedes the token-less one baked in at launch.
-        # 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
 

bot_bottle/backend/macos_container/bottle_plan.py

@@ -20,7 +20,6 @@ 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 = ""
-    docker_access: bool = False
 
     @property
     def container_name(self) -> str:

bot_bottle/backend/macos_container/consolidated_launch.py

@@ -36,12 +36,9 @@ from dataclasses import dataclass
 
 from ...egress import EgressPlan
 from ...git_gate import GitGatePlan
-from ...log import info
+from ...orchestrator.client import OrchestratorClient
-from ...orchestrator.client import OrchestratorClient, OrchestratorClientError
 from ...orchestrator.registration import registration_inputs
 from ..docker.gateway_provision import deprovision_git_gate, provision_git_gate
-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
@@ -92,32 +89,6 @@ def ensure_gateway(
     )
 
 
-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(
     egress_plan: EgressPlan,
     git_gate_plan: GitGatePlan,
@@ -132,16 +103,6 @@ def register_agent(
     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}")
     inputs = registration_inputs(egress_plan)
     reg = client.register_bottle(
         source_ip, image_ref=image_ref, policy=inputs.policy,
@@ -163,17 +124,11 @@ def register_agent(
     )
 
 
-def teardown_consolidated(
+def teardown_consolidated(bottle_id: str, *, orchestrator_url: str) -> None:
-    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."""
-    from ...orchestrator.config_store import DEFAULT_TEARDOWN_TIMEOUT_SECONDS
+    OrchestratorClient(orchestrator_url).teardown_bottle(bottle_id)
-    OrchestratorClient(
-        orchestrator_url,
-        timeout=timeout if timeout is not None else DEFAULT_TEARDOWN_TIMEOUT_SECONDS,
-    ).teardown_bottle(bottle_id)
     deprovision_git_gate(AppleGatewayTransport(), bottle_id)
 
 
@@ -181,7 +136,6 @@ __all__ = [
     "GatewayEndpoint",
     "LaunchContext",
     "ensure_gateway",
-    "live_source_ips",
     "register_agent",
     "teardown_consolidated",
     "ConsolidatedLaunchError",

bot_bottle/backend/macos_container/enumerate.py

@@ -8,21 +8,13 @@ from ...bottle_state import read_metadata
 from .. import ActiveAgent
 from .infra import INFRA_NAME
 
-# The name every agent container carries: `bot-bottle-<slug>`. Exported
+_PREFIX = "bot-bottle-"
-# 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"],
@@ -31,15 +23,12 @@ def enumerate_active() -> list[ActiveAgent]:
         check=False,
     )
     if result.returncode != 0:
-        raise EnumerationError(
+        return []
-            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(CONTAINER_NAME_PREFIX) or name in _INFRA_NAMES:
+        if not name.startswith(_PREFIX) or name in _INFRA_NAMES:
             continue
-        slug = name[len(CONTAINER_NAME_PREFIX):]
+        slug = name[len(_PREFIX):]
         metadata = read_metadata(slug)
         out.append(ActiveAgent(
             backend_name="macos-container",

bot_bottle/backend/macos_container/gateway_hosts.py

@@ -1,96 +0,0 @@
-"""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"]

bot_bottle/backend/macos_container/infra.py

@@ -101,7 +101,7 @@ def _init_script(port: int) -> str:
         # Gateway data plane, multi-tenant against the local control plane.
         f"( cd /app && BOT_BOTTLE_GATEWAY_DAEMONS={_GATEWAY_DAEMONS} "
         f"BOT_BOTTLE_ORCHESTRATOR_URL=http://127.0.0.1:{port} "
-        f"SUPERVISE_DB_PATH={_DB_PATH_IN_CONTAINER} python3 -m bot_bottle.gateway_init ) &\n"
+        f"SUPERVISE_DB_PATH={_DB_PATH_IN_CONTAINER} python3 /app/gateway_init.py ) &\n"
         "while : ; do wait ; done\n"
     )
 

bot_bottle/backend/macos_container/launch.py

@@ -59,14 +59,7 @@ 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 rootless_podman
 from .bottle_plan import MacosContainerBottlePlan
-from ...orchestrator.config_store import resolve_teardown_timeout
 from .consolidated_launch import (
     GatewayEndpoint,
     ensure_gateway,
@@ -107,11 +100,6 @@ def launch(
         # 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.
@@ -129,9 +117,6 @@ 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,
         )
@@ -144,7 +129,6 @@ 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,
@@ -156,7 +140,6 @@ def launch(
         stack.callback(
             teardown_consolidated, ctx.bottle_id,
             orchestrator_url=ctx.orchestrator_url,
-            timeout=teardown_timeout,
         )
         info(
             f"agent {plan.container_name} registered "
@@ -172,10 +155,6 @@ 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),
-            **rootless_podman.guest_env(plan.docker_access),
-        }
         bottle = MacosContainerBottle(
             plan.container_name,
             teardown,
@@ -189,16 +168,10 @@ def launch(
             ),
             terminal_color=plan.spec.color,
             agent_workdir=plan.workspace_plan.workdir,
-            exec_env=exec_env,
+            exec_env=_identity_proxy_env(endpoint, ctx.identity_token),
         )
         bottle.prompt_path = provision(plan, bottle)
 
-        if plan.docker_access:
-            rootless_podman.prepare_guest_devices(
-                plan.container_name, container_mod.exec_container_as_root,
-            )
-            rootless_podman.start(bottle)
-
         yield bottle
     finally:
         teardown()
@@ -210,22 +183,15 @@ def _build_images(plan: MacosContainerBottlePlan) -> MacosContainerBottlePlan:
     committed = read_committed_image(plan.slug)
     if committed and container_mod.image_exists(committed):
         info(f"using committed image {committed!r}")
-        plan = dataclasses.replace(
+        return dataclasses.replace(
             plan,
             agent_provision=dataclasses.replace(
                 plan.agent_provision, image=committed,
             ),
         )
-    else:
+    container_mod.build_image(
-        container_mod.build_image(
+        plan.image, _REPO_DIR, dockerfile=plan.dockerfile_path,
-            plan.image, _REPO_DIR, dockerfile=plan.dockerfile_path,
+    )
-        )
-    if plan.docker_access:
-        image = rootless_podman.build_image(plan.image, container_mod.build_image)
-        plan = dataclasses.replace(
-            plan,
-            agent_provision=dataclasses.replace(plan.agent_provision, image=image),
-        )
     return plan
 
 
@@ -265,20 +231,13 @@ 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 name).
+    gateway address)."""
-
-    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://{GATEWAY_HOSTNAME}:{_GIT_HTTP_PORT}"
+        f"http://{endpoint.gateway_ip}:{_GIT_HTTP_PORT}"
         if plan.git_gate_plan.upstreams else ""
     )
     supervise_url = (
-        f"http://{GATEWAY_HOSTNAME}:{SUPERVISE_PORT}/"
+        f"http://{endpoint.gateway_ip}:{SUPERVISE_PORT}/"
         if plan.supervise_plan is not None else ""
     )
     return dataclasses.replace(
@@ -288,43 +247,30 @@ def _stamp_agent_urls(
     )
 
 
-def _proxy_url(identity_token: str = "") -> str:
+def _proxy_url(gateway_ip: str, 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_HOSTNAME}:{EGRESS_PORT}"
+    return f"http://{cred}{gateway_ip}:{EGRESS_PORT}"
 
 
-def _no_proxy() -> str:
+def _no_proxy(gateway_ip: str) -> str:
     # git-http + supervise live on the gateway and must NOT go through the
-    # egress proxy — the agent reaches them directly by name. Deliberately
+    # egress proxy — the agent reaches them directly by its address.
-    # address-free: NO_PROXY is baked into the run-time env and is therefore
+    return f"localhost,127.0.0.1,{gateway_ip}"
-    # 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` — the only way
+    """The token-bearing proxy env applied at `container exec`. It supersedes
-    to get the token in, since it does not exist until after the container
+    the token-less run-time value (exec `--env` wins), which is the only way to
-    runs (registration keys on the DHCP-assigned address).
+    get the token in: it does not exist until after the container runs."""
-
-    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 {}
-    del endpoint  # the gateway is named, not addressed
+    url = _proxy_url(endpoint.gateway_ip, identity_token)
-    url = _proxy_url(identity_token)
     return {
         "HTTPS_PROXY": url, "HTTP_PROXY": url,
         "https_proxy": url, "http_proxy": url,
@@ -371,23 +317,16 @@ def _agent_run_argv(
 def _agent_env_entries(
     plan: MacosContainerBottlePlan, endpoint: GatewayEndpoint,
 ) -> tuple[str, ...]:
-    # No `*_PROXY` here on purpose. The token-bearing URL is applied at
+    # Token-less at run time — the token does not exist yet (see
-    # `container exec` (`_identity_proxy_env`), and Apple's `container exec
+    # `_identity_proxy_env`). Anything egressing before the exec-time override
-    # --env` **appends** to the run-time environment rather than replacing it:
+    # is denied by `/resolve`, which is the safe direction.
-    # setting a token-less value here leaves two `HTTPS_PROXY` entries in the
+    proxy_url = _proxy_url(endpoint.gateway_ip)
-    # agent's `environ`, token-less first. Which one a runtime reads is then
+    no_proxy = _no_proxy(endpoint.gateway_ip)
-    # 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}",

bot_bottle/backend/macos_container/resolve_plan.py

@@ -44,5 +44,4 @@ def resolve_plan(
         egress_plan=egress_plan,
         supervise_plan=supervise_plan,
         agent_provision=agent_provision_plan,
-        docker_access=manifest.bottle.docker_access,
     )

bot_bottle/backend/macos_container/rootless-podman-init.sh

@@ -1,89 +0,0 @@
-#!/bin/sh
-set -eu
-
-uid="$(id -u)"
-if [ "$uid" -eq 0 ]; then
-    echo "refusing to run rootless podman as root" >&2
-    exit 1
-fi
-
-for command in podman docker fuse-overlayfs slirp4netns; do
-    command -v "$command" >/dev/null 2>&1 || {
-        echo "missing rootless podman 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 $(id -un)" >&2
-        exit 1
-    }
-done
-
-export XDG_RUNTIME_DIR="${XDG_RUNTIME_DIR:-/tmp/bot-bottle-podman-run}"
-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 > "$config/storage.conf" <<'CONF'
-[storage]
-driver="overlay"
-[storage.options.overlay]
-mount_program="/usr/bin/fuse-overlayfs"
-ignore_chown_errors="true"
-CONF
-
-# No cgroup delegation reaches this guest, so asking podman to manage cgroups
-# fails; events_logger=file avoids the journald socket that is equally absent.
-cat > "$config/containers.conf" <<'CONF'
-[containers]
-cgroups="disabled"
-[engine]
-cgroup_manager="cgroupfs"
-events_logger="file"
-CONF
-
-# 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.
-python3 - <<'PY'
-import json
-import os
-from pathlib import Path
-
-proxy = os.environ.get("HTTPS_PROXY") or os.environ.get("https_proxy", "")
-no_proxy = os.environ.get("NO_PROXY") or os.environ.get("no_proxy", "")
-config = {"proxies": {"default": {
-    "httpProxy": proxy,
-    "httpsProxy": proxy,
-    "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
-
-log=/tmp/bot-bottle-rootless-podman.log
-nohup podman system service --time=0 \
-    "unix://$XDG_RUNTIME_DIR/podman.sock" \
-    >"$log" 2>&1 </dev/null &

bot_bottle/backend/macos_container/rootless_podman.py

@@ -1,132 +0,0 @@
-"""Experimental rootless podman bootstrap for Apple-container bottles.
-
-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/rootless-podman-init"
-_RUNTIME_DIR = "/tmp/bot-bottle-podman-run"
-_SOCKET = f"{_RUNTIME_DIR}/podman.sock"
-_LOG = "/tmp/bot-bottle-rootless-podman.log"
-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 spike-only tooling on an already-built provider image."""
-    image = f"{base_image}-rootless-podman"
-    init_script = Path(__file__).with_name("rootless-podman-init.sh")
-    with tempfile.TemporaryDirectory(prefix="bot-bottle-rootless-podman.") as tmp:
-        context = Path(tmp)
-        shutil.copy2(init_script, context / "rootless-podman-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"
-            " && apt-get install -y --no-install-recommends podman "
-            "fuse-overlayfs 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 spike exists
-            # to route around.
-            " && sed -i '/^node:/d' /etc/subuid /etc/subgid\n"
-            "COPY rootless-podman-init.sh "
-            "/usr/local/libexec/bot-bottle/rootless-podman-init\n"
-            "RUN chmod 0755 /usr/local/libexec/bot-bottle/rootless-podman-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 experimental rootless podman service")
-    result = bottle.exec(shlex.quote(_INIT))  # type: ignore[attr-defined]
-    if result.returncode != 0:
-        detail = (result.stderr or result.stdout or "").strip()
-        die(f"rootless podman 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("rootless podman service is ready")
-            return
-        time.sleep(0.2)
-
-    logs = bottle.exec(  # type: ignore[attr-defined]
-        f"tail -n 80 {_LOG} 2>/dev/null || true"
-    )
-    die(
-        "rootless podman did not become ready without additional outer "
-        f"privileges:\n{(logs.stdout or logs.stderr or '<no log>').strip()}"
-    )
-
-
-__all__ = ["build_image", "guest_env", "prepare_guest_devices", "start"]

bot_bottle/backend/macos_container/util.py

@@ -360,21 +360,6 @@ def exec_container(name: str, argv: list[str]) -> None:
         )
 
 
-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,
@@ -572,41 +557,6 @@ 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:

bot_bottle/cli/__init__.py

@@ -38,13 +38,6 @@ COMMANDS = {
     "supervise": cmd_supervise,
 }
 
-# Commands that manage host prerequisites (or are otherwise store-free) and
-# must run before — or without — a migrated DB. `backend` provisions/probes
-# the host (TAP pool, /dev/kvm, firecracker) and never opens the store, so
-# gating it on the schema breaks preflight on a fresh CI runner where stdin
-# isn't a TTY and the migration prompt can't be answered.
-NO_MIGRATION_COMMANDS = frozenset({"backend"})
-
 
 def usage() -> None:
     sys.stderr.write(f"usage: {PROG} <command> [args...]\n\n")
@@ -87,7 +80,7 @@ def main(argv: list[str] | None = None) -> int:
         usage()
         die(f"unknown command: {command}")
     mgr = StoreManager.instance()
-    if command not in NO_MIGRATION_COMMANDS and not mgr.is_migrated():
+    if not mgr.is_migrated():
         sys.stderr.write("bot-bottle: database schema is out of date\n")
         sys.stderr.write("Migrate now? [y/N] ")
         sys.stderr.flush()

bot_bottle/cli/_common.py

@@ -3,10 +3,18 @@
 from __future__ import annotations
 
 import os
+import sys
 from pathlib import Path
 
-from ..util import read_tty_line as read_tty_line
-
 PROG = "cli.py"
 USER_CWD = os.getcwd()
 REPO_DIR = str(Path(__file__).resolve().parent.parent.parent)
+
+
+def read_tty_line() -> str:
+    """Mirror `IFS= read -r REPLY </dev/tty`. Falls back to stdin."""
+    try:
+        with open("/dev/tty", "r", encoding="utf-8") as tty:
+            return tty.readline().rstrip("\n")
+    except OSError:
+        return sys.stdin.readline().rstrip("\n")

bot_bottle/cli/cleanup.py

@@ -21,20 +21,16 @@ from __future__ import annotations
 
 import sys
 
-from ..backend import get_bottle_backend, has_backend, known_backend_names
+from ..backend import get_bottle_backend, known_backend_names
 from ..log import info
 from ._common import read_tty_line
 
 
 def cmd_cleanup(_argv: list[str]) -> int:
     # Order: stable backend iteration so the y/N output is
-    # deterministic across runs. Skip backends whose runtime
+    # deterministic across runs.
-    # isn't available on this host so e.g. macos-container
-    # doesn't error on Linux.
     plans = [
-        (name, get_bottle_backend(name))
+        (name, get_bottle_backend(name)) for name in known_backend_names()
-        for name in known_backend_names()
-        if has_backend(name)
     ]
     prepared = [(name, b, b.prepare_cleanup()) for name, b in plans]
 

bot_bottle/cli/start.py

@@ -27,6 +27,7 @@ from ..backend import (
     BottleSpec,
     enumerate_active_agents,
     get_bottle_backend,
+    known_backend_names,
 )
 from ..backend.docker import util as docker_mod
 from ..backend.docker.bottle_plan import DockerBottlePlan
@@ -56,6 +57,15 @@ def cmd_start(argv: list[str]) -> int:
             "into a cached layer."
         ),
     )
+    parser.add_argument(
+        "--backend",
+        choices=known_backend_names(),
+        default=None,
+        help=(
+            "backend to launch the bottle on (default: $BOT_BOTTLE_BACKEND "
+            "or host auto-selection). Overrides the env var when set."
+        ),
+    )
     parser.add_argument(
         "--headless",
         action="store_true",
@@ -105,10 +115,11 @@ def cmd_start(argv: list[str]) -> int:
         os.environ["BOT_BOTTLE_NO_CACHE"] = "1"
 
     manifest = ManifestIndex.resolve(USER_CWD)
+    backend_name: str | None = args.backend
 
     if args.headless:
         return _start_headless(
-            manifest, args, dry_run=dry_run
+            manifest, args, dry_run=dry_run, backend_name=backend_name
         )
 
     agent_name: str | None = args.name
@@ -159,6 +170,7 @@ def cmd_start(argv: list[str]) -> int:
     return _launch_bottle(
         spec,
         dry_run=dry_run,
+        backend_name=backend_name,
     )
 
 
@@ -170,6 +182,7 @@ def _start_headless(
     args: argparse.Namespace,
     *,
     dry_run: bool,
+    backend_name: str | None,
 ) -> int:
     """Non-interactive launch path for orchestrators / CI / webhooks.
 
@@ -217,6 +230,7 @@ def _start_headless(
     return _launch_bottle(
         spec,
         dry_run=dry_run,
+        backend_name=backend_name,
         assume_yes=True,
         headless_prompt_text=prompt,
     )
@@ -254,18 +268,15 @@ def prepare_with_preflight(
     injected callable, prompt y/N via the injected callable.
 
     `backend_name` selects which backend prepares the plan
-    (`None` → `$BOT_BOTTLE_BACKEND` → host auto-selection).
+    (`None` → `$BOT_BOTTLE_BACKEND` → host auto-selection). The CLI
-
+    passes whatever `--backend` resolved to.
-    When `spec.headless` is True the docker-fallback prompt is suppressed:
-    auto-selection dies with an actionable message rather than blocking
-    on a TTY read (which would hang CI, webhook dispatch, and orchestrators).
 
     Returns `(plan, identity)`. `plan` is None on dry-run or
     operator-N, but `identity` is set as soon as `backend.prepare`
     returns so callers can reap the prepare-time state dir via
     `settle_state(identity)` in their finally — exactly the existing
     semantics."""
-    backend = get_bottle_backend(backend_name, prompt=not spec.headless)
+    backend = get_bottle_backend(backend_name)
     plan = backend.prepare(spec, stage_dir=stage_dir)
     identity = _identity_from_plan(plan)
 

bot_bottle/constants.py

@@ -1,17 +0,0 @@
-"""Shared wire-protocol constants for gateway-bundled modules.
-
-Single source of truth for values that appear across the egress addon,
-git-http backend, supervise server, and git-gate renderer. Importing
-from this module instead of duplicating the literals means a rename is
-a one-line change and is caught by the type checker at the import site."""
-
-# App-layer identity token header. Delivered as proxy credentials
-# (HTTPS_PROXY=http://<bottle_id>:<token>@gw) by launch; the egress
-# addon reads and strips it, the supervise server and git-http backend
-# read it for attribution, and none of them forward it upstream.
-IDENTITY_HEADER = "x-bot-bottle-identity"
-
-# Shared timeout (seconds) for all git-gate subprocess and CGI calls:
-# git daemon (--timeout/--init-timeout), the access-hook subprocess in
-# git_http_backend, and the git http-backend CGI subprocess.
-GIT_GATE_TIMEOUT_SECS = 15

bot_bottle/db_store.py

@@ -3,7 +3,6 @@
 from __future__ import annotations
 
 import sqlite3
-from contextlib import contextmanager
 from pathlib import Path
 
 try:
@@ -29,21 +28,12 @@ class DbStore:
         conn.row_factory = sqlite3.Row
         return conn
 
-    @contextmanager
-    def _connection(self):
-        conn = self._connect()
-        try:
-            with conn:
-                yield conn
-        finally:
-            conn.close()
-
     def is_migrated(self) -> bool:
         """Return True if the DB is fully up-to-date, False if migration is needed."""
         if not self.db_path.exists():
             return False
         try:
-            with self._connection() as conn:
+            with self._connect() as conn:
                 row = conn.execute(
                     "SELECT version FROM schema_versions WHERE module = ?",
                     (self._migrations.schema_key,),
@@ -55,7 +45,7 @@ class DbStore:
 
     def migrate(self) -> None:
         """Apply any pending migrations and set permissions on the DB file."""
-        with self._connection() as conn:
+        with self._connect() as conn:
             self._migrations.apply(conn)
         self._chmod()
 

bot_bottle/dlp_detectors.py

@@ -3,8 +3,9 @@
 Pure Python, no mitmproxy dependency. Each detector is a module-level
 function returning `ScanResult | None`.
 
-Available in the gateway via the installed `bot_bottle` package
+Ships flat into the gateway image alongside
-(see `Dockerfile.gateway`).
+`egress_addon_core.py` — both this file and the package source use
+the same try/except import shim pattern.
 """
 
 from __future__ import annotations
@@ -19,7 +20,10 @@ from math import log2
 from collections import Counter
 from urllib.parse import quote as url_quote
 
-from .egress_addon_core import ScanResult
+try:
+    from egress_addon_core import ScanResult  # type: ignore[import-not-found]
+except ImportError:  # pragma: no cover - host-side path
+    from .egress_addon_core import ScanResult
 
 
 # ---------------------------------------------------------------------------

bot_bottle/egress_addon.py

@@ -15,9 +15,7 @@ import typing
 
 from mitmproxy import http  # type: ignore[import-not-found]  # pylint: disable=import-error
 
-from bot_bottle.constants import IDENTITY_HEADER
+from egress_addon_core import (  # type: ignore[import-not-found]  # pylint: disable=import-error
-from bot_bottle.dlp_detectors import redact_tokens, strip_crlf
-from bot_bottle.egress_addon_core import (
     LOG_BLOCKS,
     LOG_FULL,
     DEFAULT_OUTBOUND_ON_MATCH,
@@ -40,8 +38,24 @@ from bot_bottle.egress_addon_core import (
     scan_inbound,
     scan_outbound,
 )
-from bot_bottle import supervise as _sv
+
-from bot_bottle.policy_resolver import PolicyResolver
+try:
+    from dlp_detectors import redact_tokens, strip_crlf  # type: ignore[import-not-found]
+except ImportError:  # pragma: no cover - host-side path
+    from bot_bottle.dlp_detectors import (  # type: ignore[import-not-found]
+        redact_tokens,
+        strip_crlf,
+    )
+
+try:
+    import supervise as _sv  # type: ignore[import-not-found]
+except ImportError:  # pragma: no cover - host-side path
+    from bot_bottle import supervise as _sv  # type: ignore[import-not-found]
+
+try:
+    from policy_resolver import PolicyResolver  # type: ignore[import-not-found]
+except ImportError:  # pragma: no cover - host-side path
+    from bot_bottle.policy_resolver import PolicyResolver
 
 
 INTROSPECT_HOST = "_egress.local"
@@ -52,6 +66,13 @@ INTROSPECT_HOST = "_egress.local"
 # back to — so an unset value is a fatal misconfiguration (see __init__).
 ORCHESTRATOR_URL_ENV = "BOT_BOTTLE_ORCHESTRATOR_URL"
 
+# App-layer identity token. Delivered as proxy credentials
+# (`HTTPS_PROXY=http://<bottle_id>:<token>@gw`): clients honor it as part of
+# the proxy protocol without app changes, and the addon reads + strips it so
+# it never leaks upstream. The legacy `x-bot-bottle-identity` request header
+# is still stripped defensively (git-http uses that header on its own port).
+IDENTITY_HEADER = "x-bot-bottle-identity"
+
 # Per-flow key under which `request()` stashes the resolved (Config, supervise
 # slug, env) so the later `response()` and `websocket_message()` hooks scan
 # against the *calling bottle's* policy — the same one the request was decided
@@ -379,7 +400,6 @@ class EgressAddon:
             env,
             request_method=flow.request.method,
             request_headers=req_headers,
-            deny_reason=config.deny_reason,
         )
 
         if decision.action == "block":

bot_bottle/egress_addon_core.py

@@ -6,9 +6,9 @@ exercise the parse + decision functions without depending on the
 `mitmproxy.http.HTTPFlow` API and is loaded inside the gateway
 container.
 
-Imports: stdlib + sibling package modules (`yaml_subset`,
+Imports: stdlib + `yaml_subset` (which is itself stdlib-only and
-`egress_dlp_config`). Available in the gateway via the installed
+ships flat into the gateway image alongside this file —
-`bot_bottle` package (see `Dockerfile.gateway`)."""
+see `Dockerfile.gateway`)."""
 
 from __future__ import annotations
 
@@ -16,20 +16,36 @@ import re
 import typing
 from dataclasses import dataclass
 
-from .yaml_subset import YamlSubsetError, parse_yaml_subset
+try:
+    from yaml_subset import YamlSubsetError, parse_yaml_subset  # type: ignore[import-not-found]
+except ImportError:  # pragma: no cover - host-side path
+    from .yaml_subset import YamlSubsetError, parse_yaml_subset
 
-# DLP detector-config parsing lives in a sibling module. Re-exported below
+# DLP detector-config parsing lives in a sibling module (also flat-bundled
-# so existing `from egress_addon_core import ON_MATCH_*` callers keep working.
+# into the gateway — see Dockerfile.gateway). Re-exported below so existing
-from .egress_dlp_config import (
+# `from egress_addon_core import ON_MATCH_*` callers keep working.
-    DEFAULT_OUTBOUND_ON_MATCH,
+try:
-    INBOUND_DETECTOR_NAMES,
+    from egress_dlp_config import (  # type: ignore[import-not-found]
-    ON_MATCH_BLOCK,
+        DEFAULT_OUTBOUND_ON_MATCH,
-    ON_MATCH_REDACT,
+        INBOUND_DETECTOR_NAMES,
-    ON_MATCH_SUPERVISE,
+        ON_MATCH_BLOCK,
-    OUTBOUND_DETECTOR_NAMES,
+        ON_MATCH_REDACT,
-    OUTBOUND_ON_MATCH_VALUES,
+        ON_MATCH_SUPERVISE,
-    parse_dlp_block,
+        OUTBOUND_DETECTOR_NAMES,
-)
+        OUTBOUND_ON_MATCH_VALUES,
+        parse_dlp_block,
+    )
+except ImportError:  # pragma: no cover - host-side path
+    from .egress_dlp_config import (
+        DEFAULT_OUTBOUND_ON_MATCH,
+        INBOUND_DETECTOR_NAMES,
+        ON_MATCH_BLOCK,
+        ON_MATCH_REDACT,
+        ON_MATCH_SUPERVISE,
+        OUTBOUND_DETECTOR_NAMES,
+        OUTBOUND_ON_MATCH_VALUES,
+        parse_dlp_block,
+    )
 
 
 # ---------------------------------------------------------------------------
@@ -89,14 +105,6 @@ 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)
@@ -413,40 +421,16 @@ 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). Each deny-all carries the reason it is one, so the block message
+    blocked)."""
-    names the real fault instead of blaming the allowlist."""
     if not policy:
-        return Config(routes=(), deny_reason=DENY_UNATTRIBUTED)
+        return Config(routes=())  # unattributed or empty → deny-all
     try:
         return load_config(policy)
     except ValueError:
-        return Config(routes=(), deny_reason=DENY_UNPARSEABLE)
+        return Config(routes=())  # unparseable policy → deny
 
 
 def resolve_client_config(
@@ -460,7 +444,7 @@ def resolve_client_config(
     try:
         policy = resolver.resolve(client_ip, identity_token)
     except Exception:  # noqa: BLE001  # pylint: disable=broad-exception-caught
-        return Config(routes=(), deny_reason=DENY_RESOLVER_ERROR)
+        return Config(routes=())  # orchestrator unreachable/errored → deny
     return _config_from_policy(policy)
 
 
@@ -489,7 +473,7 @@ def resolve_client_context(
             client_ip, identity_token,
         )
     except Exception:  # noqa: BLE001  # pylint: disable=broad-exception-caught
-        return Config(routes=(), deny_reason=DENY_RESOLVER_ERROR), "", {}
+        return Config(routes=()), "", {}  # orchestrator unreachable/errored → deny
     return _config_from_policy(policy), (bottle_id or ""), tokens
 
 
@@ -604,16 +588,12 @@ 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=deny_reason or (
+            reason=(
                 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."
@@ -888,9 +868,6 @@ __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",

bot_bottle/gateway_init.py

@@ -78,8 +78,8 @@ def _env_for_daemon(name: str, base_env: dict[str, str]) -> dict[str, str]:
 _DAEMONS: tuple[_DaemonSpec, ...] = (
     _DaemonSpec("egress", ("/bin/sh", "/app/egress-entrypoint.sh")),
     _DaemonSpec("git-gate", ("/bin/sh", "/git-gate-entrypoint.sh")),
-    _DaemonSpec("git-http", ("python3", "-m", "bot_bottle.git_http_backend")),
+    _DaemonSpec("git-http", ("python3", "/app/git_http_backend.py")),
-    _DaemonSpec("supervise", ("python3", "-m", "bot_bottle.supervise_server")),
+    _DaemonSpec("supervise", ("python3", "/app/supervise_server.py")),
 )
 
 

bot_bottle/git_gate_render.py

@@ -14,12 +14,18 @@ import shlex
 from dataclasses import dataclass
 from pathlib import Path
 
-from .constants import GIT_GATE_TIMEOUT_SECS, IDENTITY_HEADER
 from .manifest import ManifestBottle, ManifestGitEntry
 
 # Short network alias for git-gate inside the gateway. The
 # agent's `.gitconfig` insteadOf rewrites resolve through this name.
 GIT_GATE_HOSTNAME = "git-gate"
+# App-layer identity token header the agent's git sends to git-http and the
+# gateway validates (mirrors egress_addon / git_http_backend IDENTITY_HEADER).
+IDENTITY_HEADER = "x-bot-bottle-identity"
+# Shared timeout (seconds) for all git-gate subprocess and CGI calls:
+# git daemon (--timeout/--init-timeout), the access-hook subprocess in
+# git_http_backend, and the git http-backend CGI subprocess.
+GIT_GATE_TIMEOUT_SECS = 15
 
 
 @dataclass(frozen=True)
@@ -419,24 +425,18 @@ PY
 while IFS=' ' read -r old new ref; do
   [ -z "$ref" ] && continue
   [ "$new" = "$zero" ] && continue
-  # Scan only the commits this push introduces — those reachable from
+  if [ "$old" = "$zero" ]; then
-  # $new but not from any ref the gate already has. Everything already
+    # New ref: scan only the commits this push introduces — those
-  # on the gate arrived via upstream mirror-fetch or a previously
+    # reachable from $new but not from any ref the gate already has.
-  # gitleaks-scanned push, so it's already-upstream or already-scanned;
+    # Everything already on the gate arrived via upstream mirror-fetch
-  # re-scanning it only resurfaces historical fixture findings.
+    # or a previously gitleaks-scanned push, so it's already-upstream
-  #
+    # or already-scanned; re-scanning it (the old `$new` full-ancestry
-  # Applies to both new refs and updates. The old existing-branch range
+    # range) only resurfaces historical findings and blocks every new
-  # `$old..$new` walks commits reachable from the new tip but not the
+    # branch. See PRD 0028 / issue #106.
-  # *old branch tip*: on a rebase/force-push onto a freshly-advanced
+    log_opts="$new --not --all"
-  # main that pulls in all of main's new history (incl. the deliberate
+  else
-  # sandbox-escape gitleaks fixtures), blocking the push. `--not --all`
+    log_opts="$old..$new"
-  # excludes anything already on the gate regardless of ancestry, so it
+  fi
-  # is also correct for non-fast-forward pushes (a rebase can skip
-  # commits off the direct path). Security-equivalent per PRD 0028's
-  # analysis: the bare repo's refs come only from trusted upstream
-  # mirror-fetch or gitleaks-gated pushes.
-  # See PRD 0028 (open question) / issues #106, #346.
-  log_opts="$new --not --all"
   echo "git-gate: gitleaks scanning $ref ($log_opts)" >&2
   if ! gitleaks git --log-opts="$log_opts" --no-banner --redact 1>&2; then
     echo "git-gate: gitleaks rejected push to $ref" >&2

bot_bottle/git_http_backend.py

@@ -26,8 +26,16 @@ from http.server import BaseHTTPRequestHandler, ThreadingHTTPServer
 from pathlib import Path
 from urllib.parse import urlsplit
 
-from bot_bottle.constants import GIT_GATE_TIMEOUT_SECS, IDENTITY_HEADER
+# policy_resolver ships flat alongside this file in the gateway
-from bot_bottle.policy_resolver import PolicyResolveError, PolicyResolver
+# image (see Dockerfile.gateway); the bot_bottle.* fallback is the
+# host-side / test path. Mirrors egress_addon's import shape.
+try:
+    from policy_resolver import (  # type: ignore[import-not-found]
+        PolicyResolveError,
+        PolicyResolver,
+    )
+except ImportError:  # pragma: no cover - host-side path
+    from bot_bottle.policy_resolver import PolicyResolveError, PolicyResolver
 
 
 DEFAULT_PORT = 9420
@@ -38,6 +46,12 @@ DEFAULT_PORT = 9420
 # repo-root fallback.
 ORCHESTRATOR_URL_ENV = "BOT_BOTTLE_ORCHESTRATOR_URL"
 
+# App-layer identity token (defense-in-depth over the source-IP invariant);
+# the agent injects it, the backend reads it for attribution and never
+# forwards it to `git http-backend`. Mirrors egress_addon.IDENTITY_HEADER
+# (duplicated, not imported: egress_addon pulls in mitmproxy).
+IDENTITY_HEADER = "x-bot-bottle-identity"
+
 # The base under which each bottle's `<bottle_id>` repo namespace is nested.
 DEFAULT_REPO_ROOT = "/git"
 
@@ -75,6 +89,13 @@ def resolve_sandbox_root(
         return None  # bottle_id tried to escape the root → deny
     return namespace
 
+# Mirrors git_gate_render.GIT_GATE_TIMEOUT_SECS. Duplicated rather than
+# imported: this module ships as a flat top-level sibling in the gateway
+# bundle image (see Dockerfile.gateway), not as part of the bot_bottle
+# package, so `bot_bottle.git_gate` and its dependency chain aren't
+# available at runtime.
+GIT_GATE_TIMEOUT_SECS = 15
+
 # Bound memory use while still allowing ordinary git push packfiles.
 MAX_BODY_BYTES = 100 * 1024 * 1024
 

bot_bottle/manifest_bottle.py

@@ -44,9 +44,6 @@ class ManifestBottle:
     # daemon that exposes egress MCP tools to the agent. Set
     # `supervise: false` to skip the gateway.
     supervise: bool = True
-    # Experimental guest-local container engine (issue #392). Backends must
-    # implement this without granting access to a host/shared daemon.
-    docker_access: bool = False
 
     @classmethod
     def from_dict(cls, name: str, raw: object) -> "ManifestBottle":
@@ -126,15 +123,7 @@ class ManifestBottle:
                 f"(was {type(supervise_raw).__name__})"
             )
 
-        docker_access_raw = d.get("docker_access", False)
-        if not isinstance(docker_access_raw, bool):
-            raise ManifestError(
-                f"bottle '{name}' docker_access must be a boolean "
-                f"(was {type(docker_access_raw).__name__})"
-            )
-
         return cls(
             env=env, agent_provider=agent_provider, git=git,
             git_user=git_user, egress=egress, supervise=supervise_raw,
-            docker_access=docker_access_raw,
         )

bot_bottle/manifest_extends.py

@@ -54,7 +54,6 @@ def _merge_two_bottles_runtime(base: "ManifestBottle", override: "ManifestBottle
         git_user=merged_git_user,
         egress=merged_egress,
         supervise=override.supervise,
-        docker_access=override.docker_access,
     )
 
 
@@ -207,7 +206,6 @@ def _fold_two_bottles(
         git_user=merged_git_user,
         egress=merged_egress,
         supervise=later.supervise,
-        docker_access=later.docker_access,
     ), merged_repos_raw
 
 
@@ -268,11 +266,6 @@ def _merge_bottles(
     merged_supervise = (
         child.supervise if "supervise" in child_raw else parent.supervise
     )
-    merged_docker_access = (
-        child.docker_access
-        if "docker_access" in child_raw
-        else parent.docker_access
-    )
     validate_egress_routes(name, merged_egress.routes)
 
     return ManifestBottle(
@@ -282,7 +275,6 @@ def _merge_bottles(
         git_user=merged_git_user,
         egress=merged_egress,
         supervise=merged_supervise,
-        docker_access=merged_docker_access,
     )
 
 

bot_bottle/manifest_schema.py

@@ -16,10 +16,7 @@ _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",
-        "docker_access",
-    }
 )
 AGENT_KEYS_REQUIRED: frozenset[str] = frozenset()
 AGENT_KEYS_OPTIONAL = frozenset({"bottle", "skills", "git-gate"})

bot_bottle/orchestrator/client.py

@@ -15,7 +15,6 @@ 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
@@ -148,20 +147,6 @@ 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)."""

bot_bottle/orchestrator/config_store.py

@@ -1,107 +0,0 @@
-"""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",
-]

bot_bottle/orchestrator/control_plane.py

@@ -13,9 +13,6 @@ vsock / unix-socket portability caveats):
     PUT    /bottles/<bottle_id>/policy -> 200 {"updated": true} | 404  (live reload)
                                          body: {"policy"}
     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"}
@@ -144,27 +141,6 @@ def dispatch(  # pylint: disable=too-many-return-statements,too-many-branches
             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)

bot_bottle/orchestrator/registry.py

@@ -32,7 +32,6 @@ import hmac
 import secrets
 import sqlite3
 import time
-from collections.abc import Iterable
 from dataclasses import dataclass
 from pathlib import Path
 
@@ -43,12 +42,6 @@ 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)."""
@@ -174,7 +167,7 @@ class RegistryStore(DbStore):
             metadata=metadata,
             policy=policy,
         )
-        with self._connection() as conn:
+        with self._connect() as conn:
             conn.execute(
                 "DELETE FROM orchestrator_bottles "
                 "WHERE source_ip = ? AND state = 'active' AND bottle_id != ?",
@@ -200,7 +193,7 @@ class RegistryStore(DbStore):
     def set_policy(self, bottle_id: str, policy: str) -> bool:
         """Update a bottle's policy in place (live reload). Returns True if
         the bottle exists."""
-        with self._connection() as conn:
+        with self._connect() as conn:
             cur = conn.execute(
                 "UPDATE orchestrator_bottles SET policy = ? WHERE bottle_id = ?",
                 (policy, bottle_id),
@@ -210,7 +203,7 @@ class RegistryStore(DbStore):
 
     def deregister(self, bottle_id: str) -> bool:
         """Remove a bottle. Returns True if a row was deleted."""
-        with self._connection() as conn:
+        with self._connect() as conn:
             cur = conn.execute(
                 "DELETE FROM orchestrator_bottles WHERE bottle_id = ?", (bottle_id,)
             )
@@ -218,7 +211,7 @@ class RegistryStore(DbStore):
 
     def get(self, bottle_id: str) -> BottleRecord | None:
         """Return the bottle by id, or None if absent."""
-        with self._connection() as conn:
+        with self._connect() as conn:
             row = conn.execute(
                 "SELECT * FROM orchestrator_bottles WHERE bottle_id = ?", (bottle_id,)
             ).fetchone()
@@ -226,76 +219,12 @@ class RegistryStore(DbStore):
 
     def all(self) -> list[BottleRecord]:
         """Every registered bottle, oldest first."""
-        with self._connection() as conn:
+        with self._connect() as conn:
             rows = conn.execute(
                 "SELECT * FROM orchestrator_bottles ORDER BY created_at"
             ).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
@@ -303,7 +232,7 @@ class RegistryStore(DbStore):
         source IP is unspoofable (Firecracker `/31` + nft) and the control
         plane is reachable only by the trusted gateway; pair with the
         identity token (`attribute`) elsewhere."""
-        with self._connection() as conn:
+        with self._connect() as conn:
             rows = conn.execute(
                 "SELECT * FROM orchestrator_bottles "
                 "WHERE source_ip = ? AND state = 'active'",
@@ -333,5 +262,4 @@ __all__ = [
     "new_identity_token",
     "default_db_path",
     "IDENTITY_TOKEN_BYTES",
-    "DEFAULT_REAP_GRACE_SECONDS",
 ]

bot_bottle/orchestrator/service.py

@@ -13,20 +13,15 @@ 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 DEFAULT_REAP_GRACE_SECONDS, BottleRecord, RegistryStore
+from .registry import BottleRecord, RegistryStore
 from .gateway import Gateway
 from ..supervise import (
     AuditEntry,
@@ -122,30 +117,6 @@ 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

bot_bottle/policy_resolver.py

@@ -22,7 +22,8 @@ closed too rather than silently serving stale or empty policy.
 
 The resolved value is the policy blob the orchestrator stores verbatim; the
 consumer parses it (e.g. the egress addon's `load_config`). This module is
-stdlib-only and free of bot-bottle imports.
+stdlib-only and free of bot-bottle imports so it can be COPYed flat into
+the gateway.
 """
 
 from __future__ import annotations

bot_bottle/queue_store.py

@@ -66,7 +66,7 @@ class QueueStore(DbStore):
         super().__init__(resolved, migrations)
 
     def write_proposal(self, proposal: Proposal) -> Path:
-        with self._connection() as conn:
+        with self._connect() as conn:
             conn.execute(
                 """
                 INSERT OR REPLACE INTO supervise_proposals (
@@ -89,7 +89,7 @@ class QueueStore(DbStore):
         return self.db_path
 
     def read_proposal(self, proposal_id: str) -> Proposal:
-        with self._connection() as conn:
+        with self._connect() as conn:
             row = conn.execute(
                 """
                 SELECT * FROM supervise_proposals
@@ -104,7 +104,7 @@ class QueueStore(DbStore):
     def list_pending_proposals(self) -> list[Proposal]:
         if not self.db_path.is_file():
             return []
-        with self._connection() as conn:
+        with self._connect() as conn:
             rows = conn.execute(
                 """
                 SELECT p.* FROM supervise_proposals p
@@ -125,7 +125,7 @@ class QueueStore(DbStore):
     def list_all_pending_proposals(self) -> list[Proposal]:
         if not self.db_path.is_file():
             return []
-        with self._connection() as conn:
+        with self._connect() as conn:
             rows = conn.execute(
                 """
                 SELECT p.* FROM supervise_proposals p
@@ -142,7 +142,7 @@ class QueueStore(DbStore):
         return [self._row_to_proposal(row) for row in rows]
 
     def write_response(self, response: Response) -> Path:
-        with self._connection() as conn:
+        with self._connect() as conn:
             conn.execute(
                 """
                 INSERT OR REPLACE INTO supervise_responses (
@@ -161,7 +161,7 @@ class QueueStore(DbStore):
         return self.db_path
 
     def read_response(self, proposal_id: str) -> Response:
-        with self._connection() as conn:
+        with self._connect() as conn:
             row = conn.execute(
                 """
                 SELECT * FROM supervise_responses
@@ -176,7 +176,7 @@ class QueueStore(DbStore):
     def archive_proposal(self, proposal_id: str) -> None:
         if not self.db_path.is_file():
             return
-        with self._connection() as conn:
+        with self._connect() as conn:
             conn.execute(
                 """
                 UPDATE supervise_proposals SET archived = 1

bot_bottle/supervise.py

@@ -37,23 +37,40 @@ from abc import ABC
 from dataclasses import dataclass
 from pathlib import Path
 
-from .supervise_types import (
+try:
-    ACTION_OPERATOR_EDIT,
+    from .supervise_types import (
-    AuditEntry,
+        ACTION_OPERATOR_EDIT,
-    Proposal,
+        AuditEntry,
-    Response,
+        Proposal,
-    STATUSES,
+        Response,
-    STATUS_APPROVED,
+        STATUSES,
-    STATUS_MODIFIED,
+        STATUS_APPROVED,
-    STATUS_REJECTED,
+        STATUS_MODIFIED,
-    TOOLS,
+        STATUS_REJECTED,
-    TOOL_CHECK_PROPOSAL,
+        TOOLS,
-    TOOL_EGRESS_ALLOW,
+        TOOL_EGRESS_ALLOW,
-    TOOL_EGRESS_BLOCK,
+        TOOL_EGRESS_BLOCK,
-    TOOL_EGRESS_TOKEN_ALLOW,
+        TOOL_EGRESS_TOKEN_ALLOW,
-    TOOL_GITLEAKS_ALLOW,
+        TOOL_GITLEAKS_ALLOW,
-    TOOL_LIST_EGRESS_ROUTES,
+        TOOL_LIST_EGRESS_ROUTES,
-)
+    )
+except ImportError:
+    from supervise_types import (  # type: ignore[import-not-found,no-redef]  # pylint: disable=import-error,no-name-in-module
+        ACTION_OPERATOR_EDIT,
+        AuditEntry,
+        Proposal,
+        Response,
+        STATUSES,
+        STATUS_APPROVED,
+        STATUS_MODIFIED,
+        STATUS_REJECTED,
+        TOOLS,
+        TOOL_EGRESS_ALLOW,
+        TOOL_EGRESS_BLOCK,
+        TOOL_EGRESS_TOKEN_ALLOW,
+        TOOL_GITLEAKS_ALLOW,
+        TOOL_LIST_EGRESS_ROUTES,
+    )
 
 
 try:
@@ -264,7 +281,6 @@ __all__ = [
     "TOOLS",
     "EGRESS_FORWARD_PROXY",
     "EGRESS_INTROSPECT_URL",
-    "TOOL_CHECK_PROPOSAL",
     "TOOL_EGRESS_ALLOW",
     "TOOL_EGRESS_BLOCK",
     "TOOL_GITLEAKS_ALLOW",

bot_bottle/supervise_server.py

@@ -2,24 +2,14 @@
 
 Per-bottle MCP server exposing tools the agent calls to propose egress
 config changes when stuck. The tools are `egress-allow`,
-`egress-block`, `list-egress-routes`, and `check-proposal`.
+`egress-block`, and `list-egress-routes`.
 
-Each queued proposal tool call:
+Each queued tool call:
 
   1. Validates the proposed file syntactically.
   2. Writes a Proposal to the host SQLite database.
-  3. Blocks polling for a matching Response row, up to a short grace
+  3. Blocks polling for a matching Response row.
-     window (`SUPERVISE_RESPONSE_TIMEOUT_SECONDS`, default 30s).
+  4. Returns the operator's `{status, notes}` to the agent.
-  4. On a decision within the window, returns the operator's
-     `{status, notes}`. On timeout, returns `status: pending` **with the
-     proposal id** and leaves the proposal queued — the flow is
-     non-blocking past the grace window (PRD prd-new / issue #412).
-
-`check-proposal` is the non-blocking companion: given a `proposal_id`
-returned by a `pending` response, it reports the current decision
-(`pending` | `approved` | `modified` | `rejected`) without re-proposing,
-so an approval made out-of-band (e.g. a web review console) can be resumed
-without holding an HTTP request open.
 
 One shared server fronts every bottle (PRD 0070) and attributes each
 proposal to the calling bottle by source IP, resolved from the orchestrator
@@ -32,14 +22,13 @@ Speaks MCP over HTTP+JSON-RPC. Methods handled:
   * `initialize`           — handshake; returns server info + caps.
   * `notifications/initialized` — ack-only.
   * `tools/list`           — returns the tool definitions.
-  * `tools/call`           — validates, queues, waits out the grace
+  * `tools/call`           — validates, queues, blocks, returns.
-                             window, returns (pending past it); or, for
-                             `check-proposal`, a non-blocking status poll.
 
 Everything else returns JSON-RPC error -32601 (method not found).
 
-The Dockerfile copies this script to /app/supervise_server.py and installs
+Stdlib-only. The Dockerfile copies this file + bot_bottle/supervise.py
-the bot_bottle package so its `from bot_bottle.*` imports resolve.
+into the image; the server imports `supervise` for the queue / Proposal
+plumbing.
 """
 
 from __future__ import annotations
@@ -53,18 +42,29 @@ import time
 import typing
 from dataclasses import dataclass, replace
 
-from bot_bottle.constants import IDENTITY_HEADER
+try:
-from bot_bottle.egress_addon_core import (
+    # Same-directory imports inside the bundle container; these files are
-    LOG_OFF, load_config, resolve_client_context, route_to_yaml_dict,
+    # COPYed flat under /app by Dockerfile.gateway.
-)
+    from egress_addon_core import (
-from bot_bottle.policy_resolver import PolicyResolveError, PolicyResolver
+        LOG_OFF, load_config, resolve_client_context, route_to_yaml_dict,
-from bot_bottle import supervise as _sv
+    )
+    from policy_resolver import PolicyResolveError, PolicyResolver
+    import supervise as _sv
+except ModuleNotFoundError:
+    # Package imports for host-side tests and tooling.
+    from .egress_addon_core import (
+        LOG_OFF, load_config, resolve_client_context, route_to_yaml_dict,
+    )
+    from .policy_resolver import PolicyResolveError, PolicyResolver
+    from . import supervise as _sv
 
 
 # --- JSON-RPC / MCP plumbing ----------------------------------------------
 
 
 MCP_PROTOCOL_VERSION = "2024-11-05"
+# App-layer identity token header (mirrors egress_addon / git_http_backend).
+IDENTITY_HEADER = "x-bot-bottle-identity"
 SERVER_NAME = "bot-bottle-supervise"
 SERVER_VERSION = "0.1.0"
 
@@ -244,31 +244,6 @@ TOOL_DEFINITIONS: list[dict[str, object]] = [
         ),
         "inputSchema": _proposal_input_schema(),
     },
-    {
-        "name": _sv.TOOL_CHECK_PROPOSAL,
-        "description": (
-            "Poll a previously queued proposal for the operator's decision "
-            "WITHOUT blocking or re-proposing. Pass the `proposal_id` you "
-            "got back when an `egress-allow`/`egress-block` call returned "
-            "`status: pending`. Returns the current status: `pending` (no "
-            "decision yet — poll again later), `approved`, `modified`, "
-            "`rejected`, or `unknown` (no such queued proposal — wrong id, "
-            "or it was already resolved and read)."
-        ),
-        "inputSchema": {
-            "type": "object",
-            "properties": {
-                "proposal_id": {
-                    "type": "string",
-                    "description": (
-                        "The proposal id from a `pending` response."
-                    ),
-                },
-            },
-            "required": ["proposal_id"],
-            "additionalProperties": False,
-        },
-    },
 ]
 
 
@@ -390,7 +365,7 @@ def handle_tools_call(
             deadline=deadline,
         )
     except TimeoutError:
-        text = format_pending_response_text(proposal.id, config.response_timeout_seconds)
+        text = format_pending_response_text(config.response_timeout_seconds)
         return {
             "content": [{"type": "text", "text": text}],
             "isError": False,
@@ -407,54 +382,6 @@ def handle_tools_call(
     }
 
 
-def handle_check_proposal(
-    params: dict[str, object],
-    config: ServerConfig,
-) -> dict[str, object]:
-    """Non-blocking poll of a queued proposal's decision, by id.
-
-    Never creates a Proposal (so `check-proposal` isn't in `TOOLS`); it only
-    reads the queue. Resolution order mirrors the synchronous path's terminal
-    step — a decided proposal is archived here exactly as `handle_tools_call`
-    archives it after `wait_for_response`, so `pending` proposals stay visible
-    to the operator until they're both decided *and* polled."""
-    args_raw = params.get("arguments", {})
-    if not isinstance(args_raw, dict):
-        raise _RpcClientError(ERR_INVALID_PARAMS, "tools/call 'arguments' must be an object")
-    proposal_id = args_raw.get("proposal_id")
-    if not isinstance(proposal_id, str) or not proposal_id.strip():
-        raise _RpcClientError(
-            ERR_INVALID_PARAMS,
-            "check-proposal: 'proposal_id' is required and must be a non-empty string",
-        )
-    proposal_id = proposal_id.strip()
-
-    try:
-        response = _sv.read_response(config.bottle_slug, proposal_id)
-    except FileNotFoundError:
-        # No decision yet — distinguish "still queued" from "unknown id".
-        try:
-            _sv.read_proposal(config.bottle_slug, proposal_id)
-        except FileNotFoundError:
-            return {
-                "content": [{"type": "text", "text": format_unknown_proposal_text(proposal_id)}],
-                "isError": True,
-            }
-        return {
-            "content": [{"type": "text", "text": format_still_pending_text(proposal_id)}],
-            "isError": False,
-        }
-
-    try:
-        _sv.archive_proposal(config.bottle_slug, proposal_id)
-    except OSError as e:
-        raise _RpcInternalError(f"failed to archive proposal: {e}") from e
-    return {
-        "content": [{"type": "text", "text": format_response_text(response)}],
-        "isError": response.status == _sv.STATUS_REJECTED,
-    }
-
-
 def format_response_text(response: "_sv.Response") -> str:
     """Pretty-print a Response for the tool's text content. The agent
     reads the text and decides whether to retry / give up / surface."""
@@ -467,35 +394,12 @@ def format_response_text(response: "_sv.Response") -> str:
     return "\n".join(lines)
 
 
-def format_pending_response_text(proposal_id: str, timeout_seconds: float) -> str:
+def format_pending_response_text(timeout_seconds: float) -> str:
-    """Grace-window timeout: the proposal stays queued, and the agent is
-    told the id so it can `check-proposal` instead of re-proposing."""
     return "\n".join([
         "status: pending",
-        f"proposal_id: {proposal_id}",
         (
-            f"notes: no operator decision within {timeout_seconds:g}s; the "
+            "notes: operator response timed out after "
-            "proposal remains queued. Poll it (do not re-propose) by calling "
+            f"{timeout_seconds:g}s; proposal remains queued"
-            f"`check-proposal` with proposal_id={proposal_id!r}."
-        ),
-    ])
-
-
-def format_still_pending_text(proposal_id: str) -> str:
-    return "\n".join([
-        "status: pending",
-        f"proposal_id: {proposal_id}",
-        "notes: still queued; no operator decision yet. Call `check-proposal` again later.",
-    ])
-
-
-def format_unknown_proposal_text(proposal_id: str) -> str:
-    return "\n".join([
-        "status: unknown",
-        f"proposal_id: {proposal_id}",
-        (
-            "notes: no queued proposal with this id for this bottle — the id "
-            "may be wrong, or the proposal was already resolved and read."
         ),
     ])
 
@@ -590,11 +494,6 @@ class MCPHandler(http.server.BaseHTTPRequestHandler):
             # — silently dropping base routes like api.anthropic.com on approval.
             if req.params.get("name") == _sv.TOOL_LIST_EGRESS_ROUTES:
                 return self._resolved_routes_payload()
-            # `check-proposal` is a non-blocking read of the calling bottle's
-            # own queue — attributed by source IP like a proposal, but it
-            # never queues or blocks.
-            if req.params.get("name") == _sv.TOOL_CHECK_PROPOSAL:
-                return handle_check_proposal(req.params, self._attributed_config(config))
             # Attribute the proposal to the source-IP-resolved bottle, so the one
             # shared server queues each bottle's proposal under its own slug.
             return handle_tools_call(req.params, self._attributed_config(config))

bot_bottle/supervise_types.py

@@ -20,10 +20,6 @@ TOOL_EGRESS_ALLOW = "egress-allow"
 TOOL_GITLEAKS_ALLOW = "gitleaks-allow"
 TOOL_EGRESS_TOKEN_ALLOW = "egress-token-allow"
 TOOL_LIST_EGRESS_ROUTES = "list-egress-routes"
-# Read-only agent tool: poll a queued proposal for the operator's decision
-# without blocking or re-proposing. It never becomes a `Proposal.tool` (no
-# queue record is created for it), so it is intentionally NOT in `TOOLS`.
-TOOL_CHECK_PROPOSAL = "check-proposal"
 TOOLS: tuple[str, ...] = (
     TOOL_EGRESS_ALLOW,
     TOOL_EGRESS_BLOCK,
@@ -160,7 +156,6 @@ __all__ = [
     "TOOLS",
     "TOOL_EGRESS_ALLOW",
     "TOOL_EGRESS_BLOCK",
-    "TOOL_CHECK_PROPOSAL",
     "TOOL_EGRESS_TOKEN_ALLOW",
     "TOOL_GITLEAKS_ALLOW",
     "TOOL_LIST_EGRESS_ROUTES",

bot_bottle/util.py

@@ -7,7 +7,6 @@ from __future__ import annotations
 
 import ipaddress
 import os
-import sys
 
 
 def is_ip_literal(value: str) -> bool:
@@ -18,15 +17,6 @@ def is_ip_literal(value: str) -> bool:
     return True
 
 
-def read_tty_line() -> str:
-    """Mirror `IFS= read -r REPLY </dev/tty`. Falls back to stdin."""
-    try:
-        with open("/dev/tty", "r", encoding="utf-8") as tty:
-            return tty.readline().rstrip("\n")
-    except OSError:
-        return sys.stdin.readline().rstrip("\n")
-
-
 def expand_tilde(path: str) -> str:
     """Expand a leading '~' to $HOME. Leaves paths without a leading
     tilde unchanged. Falls back to the empty string if $HOME is unset

docs/prds/0023-smolmachines-backend.md

@@ -1,6 +1,6 @@
 # PRD 0023: smolmachines bottle backend
 
-> **Superseded (2026-07-11).** The smolmachines backend was removed — Linux now uses the Firecracker backend, macOS uses macos-container. Kept as a historical record; see the removal commit `c07ebca` and `docs/research/agent-sandbox-landscape.md`.
+> **Superseded (2026-07-11).** The smolmachines backend was removed — Linux now uses the Firecracker backend, macOS uses macos-container. Kept as a historical record; see the removal commit `c07ebca` and `docs/research/landscape-containerized-claude.md`.
 
 - **Status:** Superseded (2026-07-11) — was Active
 - **Author:** didericis

docs/prds/0032-smolmachines-launch-decomposition.md

@@ -1,6 +1,6 @@
 # PRD 0032: Decompose smolmachines launch and harden bringup sequencing
 
-> **Superseded (2026-07-11).** The smolmachines backend was removed — Linux now uses the Firecracker backend, macOS uses macos-container. Kept as a historical record; see the removal commit `c07ebca` and `docs/research/agent-sandbox-landscape.md`.
+> **Superseded (2026-07-11).** The smolmachines backend was removed — Linux now uses the Firecracker backend, macOS uses macos-container. Kept as a historical record; see the removal commit `c07ebca` and `docs/research/landscape-containerized-claude.md`.
 
 - **Status:** Superseded (2026-07-11) — was Active
 - **Author:** didericis-claude

docs/prds/0038-smolmachines-env-contract.md

@@ -1,6 +1,6 @@
 # PRD 0038: smolmachines Env Contract and Secret-Safe Injection
 
-> **Superseded (2026-07-11).** The smolmachines backend was removed — Linux now uses the Firecracker backend, macOS uses macos-container. Kept as a historical record; see the removal commit `c07ebca` and `docs/research/agent-sandbox-landscape.md`.
+> **Superseded (2026-07-11).** The smolmachines backend was removed — Linux now uses the Firecracker backend, macOS uses macos-container. Kept as a historical record; see the removal commit `c07ebca` and `docs/research/landscape-containerized-claude.md`.
 
 - **Status:** Superseded (2026-07-11) — was Active
 - **Author:** didericis-codex

docs/prds/0039-smolmachines-capability-remediation.md

@@ -1,6 +1,6 @@
 # PRD 0039: smolmachines Capability-Block Remediation
 
-> **Superseded (2026-07-11).** The smolmachines backend was removed — Linux now uses the Firecracker backend, macOS uses macos-container. Kept as a historical record; see the removal commit `c07ebca` and `docs/research/agent-sandbox-landscape.md`.
+> **Superseded (2026-07-11).** The smolmachines backend was removed — Linux now uses the Firecracker backend, macOS uses macos-container. Kept as a historical record; see the removal commit `c07ebca` and `docs/research/landscape-containerized-claude.md`.
 
 - **Status:** Superseded (2026-07-11) — was Active
 - **Author:** didericis-codex

docs/prds/0042-smolmachines-parity-tests.md

@@ -1,6 +1,6 @@
 # PRD 0042: smolmachines Cross-Backend Parity Tests
 
-> **Superseded (2026-07-11).** The smolmachines backend was removed — Linux now uses the Firecracker backend, macOS uses macos-container. Kept as a historical record; see the removal commit `c07ebca` and `docs/research/agent-sandbox-landscape.md`.
+> **Superseded (2026-07-11).** The smolmachines backend was removed — Linux now uses the Firecracker backend, macOS uses macos-container. Kept as a historical record; see the removal commit `c07ebca` and `docs/research/landscape-containerized-claude.md`.
 
 - **Status:** Superseded (2026-07-11) — was Active
 - **Author:** didericis-codex

docs/prds/0057-smolmachines-default.md

@@ -1,6 +1,6 @@
 # PRD 0057: Promote smolmachines to default backend; convert Docker to example-only
 
-> **Superseded (2026-07-11).** The smolmachines backend was removed — Linux now uses the Firecracker backend, macOS uses macos-container. Kept as a historical record; see the removal commit `c07ebca` and `docs/research/agent-sandbox-landscape.md`.
+> **Superseded (2026-07-11).** The smolmachines backend was removed — Linux now uses the Firecracker backend, macOS uses macos-container. Kept as a historical record; see the removal commit `c07ebca` and `docs/research/landscape-containerized-claude.md`.
 
 - **Status:** Superseded (2026-07-11) — was Active
 - **Author:** didericis

docs/prds/0068-smolmachines-linux.md

@@ -1,6 +1,6 @@
 # PRD 0068: smolmachines backend on Linux
 
-> **Superseded (2026-07-11).** The smolmachines backend was removed — Linux now uses the Firecracker backend, macOS uses macos-container. Kept as a historical record; see the removal commit `c07ebca` and `docs/research/agent-sandbox-landscape.md`.
+> **Superseded (2026-07-11).** The smolmachines backend was removed — Linux now uses the Firecracker backend, macOS uses macos-container. Kept as a historical record; see the removal commit `c07ebca` and `docs/research/landscape-containerized-claude.md`.
 
 - **Status:** Superseded (2026-07-11) — was Active
 - **Author:** Claude

docs/prds/prd-new-nonblocking-supervise.md

@@ -1,125 +0,0 @@
-# PRD prd-new: Non-blocking supervise (async approval + proposal polling)
-
-- **Status:** Draft
-- **Author:** didericis
-- **Created:** 2026-07-18
-- **Issue:** #412
-
-## Summary
-
-The per-bottle supervise MCP server (`bot_bottle/supervise_server.py`)
-answers `tools/call` **synchronously**: it queues the agent's proposal and
-blocks the tool call polling for the operator's decision. On timeout it
-returns `status: pending` and leaves the proposal queued — but it hands the
-agent **no proposal id** and offers **no way to poll a specific pending
-proposal**, so the only way to learn the outcome is to re-propose (a
-duplicate).
-
-This PRD makes the MCP flow non-blocking and pollable, so an approval can
-happen out-of-band (a human taking minutes-to-hours in a review console)
-without holding an HTTP request open or wedging the agent:
-
-1. Include the `proposal_id` in the `pending` response.
-2. Add a `check-proposal` MCP tool: a non-blocking status lookup by
-   proposal id.
-3. Keep the short synchronous grace window for the common "operator is
-   right there" fast path.
-
-## Problem
-
-`handle_tools_call` → `_sv.wait_for_response(...)` blocks up to
-`SUPERVISE_RESPONSE_TIMEOUT_SECONDS` (default 30s). Two problems follow:
-
-- **Human latency ≠ tool-call latency.** A real review — rendered diff,
-  RBAC routing to an approver, someone tapping approve on their phone — is
-  minutes-to-hours. Holding the MCP request open that long is fragile
-  (proxy/keepalive timeouts, the mitmproxy egress hop, and the agent
-  harness's own tool-call timeout, which a long block can trip and stall
-  the whole turn).
-- **No resume path.** The pending fallback already exists, but without a
-  proposal id and a poll tool the agent can't reconnect to that specific
-  decision — it re-proposes, duplicating the queue entry.
-
-This is also the precondition for the planned web-console human-review
-flow (RBAC, audit retention, mobile) — see issue #412.
-
-**Safety note:** the MCP tools only *propose* policy changes; enforcement
-stays at the egress proxy and the git-gate. Returning early on `pending`
-therefore opens no hole — the agent still cannot egress or push anything
-unapproved.
-
-## Goals / success criteria
-
-- A `pending` MCP response carries the `proposal_id`.
-- An agent can call `check-proposal(proposal_id)` and get the current
-  state (`pending` | `approved` | `modified` | `rejected`) **without
-  blocking** and **without creating a new proposal**.
-- The synchronous fast path (operator approves within the grace window) is
-  unchanged: the first `tools/call` still returns the decision directly.
-- No change to enforcement, attribution (source-IP → bottle), or the
-  operator-side queue/response schema.
-
-## Non-goals
-
-- The git-gate `pre-receive` path (it is synchronous by nature and cannot
-  poll — its async variant is reject-fast + re-push; tracked as a
-  follow-up).
-- Backpressure / in-flight-proposal caps.
-- MCP server→client notifications (event-driven resume).
-- Any web-console UI (this PRD is the protocol groundwork it needs).
-
-## Design
-
-### `pending` response carries the id
-
-`handle_tools_call`'s timeout branch formats the pending text with the
-`proposal.id` and a pointer to `check-proposal`, so the agent knows what to
-poll.
-
-### `check-proposal` tool
-
-A new read-only MCP tool (`TOOL_CHECK_PROPOSAL = "check-proposal"`),
-attributed to the calling bottle by source IP exactly like the proposal
-tools. Input: `{ "proposal_id": string }`. Behavior:
-
-1. `read_response(slug, id)` →
-   - **found**: archive the proposal (same terminal step the synchronous
-     path takes) and return the decision via `format_response_text`;
-     `isError` iff rejected.
-2. **not found** → `read_proposal(slug, id)` →
-   - **found**: still queued → return `status: pending`.
-   - **not found**: unknown id, or already resolved-and-archived (e.g. a
-     second poll) → return `status: unknown`, `isError: true`.
-
-Both lookups already raise `FileNotFoundError` when absent
-(`queue_store.py`), so the handler needs no new store methods. `check-`
-`proposal` is the only path (besides the synchronous response) that
-archives, so a proposal that times out to `pending` stays visible to the
-operator until it is decided and then polled.
-
-### Grace window
-
-Left at the existing 30s default (`SUPERVISE_RESPONSE_TIMEOUT_SECONDS`),
-which doubles as the instant-approve fast path. Tuning it down is an
-operator setting, not a code change; noted for the console rollout.
-
-## Implementation chunks
-
-1. **(this PR)** `TOOL_CHECK_PROPOSAL` constant; `check-proposal` tool
-   definition + `handle_check_proposal`; dispatch wiring; `proposal_id` in
-   the pending text; unit tests. Files: `bot_bottle/supervise_types.py`,
-   `bot_bottle/supervise.py` (re-export), `bot_bottle/supervise_server.py`,
-   `tests/unit/test_supervise_server.py`.
-2. **(follow-up)** git-gate `pre-receive` reject-fast + re-push.
-3. **(follow-up)** per-bottle in-flight-proposal backpressure cap.
-4. **(follow-up)** MCP notifications for event-driven resume; web-console
-   review flow (RBAC, audit retention) on top.
-
-## Open questions
-
-- Should a resolved-but-unpolled proposal auto-archive after some TTL, or
-  only on poll? (Leaning: only on poll, so a decision is never lost to a
-  reaper before the agent sees it.)
-- Does the agent harness need an explicit "you have a pending proposal"
-  nudge, or is returning `pending` from the original call enough? (Deferred
-  to the notifications chunk.)

docs/research/agent-sandbox-landscape.md

@@ -1,81 +1,32 @@
 # Landscape: AI-agent sandbox tools
 
-Survey of AI-agent sandbox and containment projects — including local
+A broader survey than [`landscape-containerized-claude.md`](landscape-containerized-claude.md),
-coding-agent wrappers, agent-agnostic runtimes, hosted platforms, and
+which focused on Claude-Code-specific containerizers. This one covers
-governance layers — contrasted with bot-bottle's design. The original
+general AI-agent sandbox / containment projects — some Claude-specific,
-Claude-Code-specific containerizer survey was folded into this note on
+some agent-agnostic, some hosted SaaS — and contrasts them with
-2026-07-20 so there is one landscape and one positioning verdict.
+bot-bottle's design.
 
-Research conducted 2026-05-11. CubeSandbox added 2026-07-18 (see its
+Research conducted 2026-05-11.
-per-project note and the addendum at the end). Also updated 2026-07-18:
-bot-bottle no longer uses **pipelock** — outbound DLP is now bot-bottle's
-own (deliberately simple) egress scanner (a mitmproxy addon with custom
-detectors, PRD 0017 / 0052), and git-push secret scanning is handled by
-**gitleaks** in the git-gate. "pipelock" below has been replaced with the
-current mechanism; it survives only in older PRDs as history.
-
-Updated again 2026-07-18: six additional tools added (Cleanroom,
-container-use, Docker sbx, Anthropic srt, Microsoft AGT, Open Agent
-Passport); an **Agent-tailored policy** row added to the comparison table;
-a separate Governance layers section added for AGT and OAP. See the
-second addendum at the end.
-
-Updated 2026-07-20: the borrowable-ideas status was reconciled with the
-current implementation. In-flight credential injection and the microVM
-backends have shipped, while per-use SSH confirmation was superseded by
-keeping git credentials out of the agent entirely.
-
-Also updated 2026-07-20: **E2B and Daytona added as first-class entries.**
-Earlier revisions mentioned E2B only as the API and lifecycle model that
-CubeSandbox implements, and omitted Daytona entirely. That was a survey gap,
-not a principled scope exclusion: both are major hosted sandbox platforms and
-belong in this landscape even though they target platform builders rather than
-bot-bottle's local single-operator workflow.
 
 ## Summary
 
-The main table compares bot-bottle against fifteen isolation/sandbox tools.
+Eight projects surveyed. None duplicate bot-bottle's combination of
-Governance/pre-action authorization and credential-only layers are covered
+local Docker, declarative JSON manifest, per-agent egress allowlist via
-separately because they don't provide VM or container isolation. None
+pipelock, and bottle/agent split. Two clusters stand out:
-duplicate bot-bottle's combination of local
-VM-per-bottle isolation, a declarative per-role manifest, per-agent
-egress allowlist + outbound-content DLP, bottle/agent split, and the
-composable `extends:` policy model. Three clusters stand out:
 
 - **Closest neighbours** — agent-safehouse and litterbox: local,
   single-user, thin wrappers over an existing OS primitive
   (`sandbox-exec`, Podman + Landlock).
-- **Different category (isolation)** — tilde.run (hosted SaaS), boxlite
+- **Different category** — tilde.run (hosted SaaS), boxlite and
-  and microsandbox (microVM libraries for platform builders), E2B and Daytona
+  microsandbox (microVM libraries for platform builders), endo-familiar
-  (hosted sandbox platforms), CubeSandbox (self-hosted multi-tenant microVM
-  service), endo-familiar
   (capability-security paradigm, no OS isolation).
-- **New: governance/pre-action layers** — Microsoft AGT and Open Agent
-  Passport (OAP): framework-embedded tool-call interceptors with
-  per-agent declarative policy. Closest competitors on agent-tailored
-  policy, but operate at the tool-call level rather than providing
-  network/filesystem isolation; they complement rather than substitute.
 
-The microVM cluster (matchlock, smolmachines, boxlite, microsandbox,
+The microVM cluster (matchlock, smolmachines, boxlite, microsandbox) is
-CubeSandbox) is the most relevant for the v2 isolation discussion in
+the most relevant for the v2 isolation discussion in
 [`stronger-isolation-alternatives.md`](stronger-isolation-alternatives.md):
 libkrun and Apple's Virtualization.framework have made local microVMs
-ergonomic enough that microVMs are **now bot-bottle's default backend**
+ergonomic enough that a `"runtime": "microvm"` option on a bottle is now
-(Firecracker on KVM Linux, Apple Container on macOS), with Docker kept
+plausible without a heavy stack.
-only as a legacy fallback for CI / hosts without KVM or Apple Container.
-That discussion has since shipped, not just been theorized.
-
-**The one that matters most for positioning is CubeSandbox** — it ships
-bot-bottle's bundle of default-deny egress allowlisting, full audit logs, and
-in-flight credential custody *combined with* per-sandbox microVM isolation,
-open-source under Apache 2.0, with Tencent Cloud behind it and 10.4k
-stars. It's a self-hosted multi-tenant service for platform builders, not
-a single-user declarative tool, so it doesn't collide head-on — but it
-narrows the "nobody else bundles egress custody + credential injection"
-claim that the monetization positioning leans on. Daytona now also offers
-domain/CIDR firewall policy plus in-flight header credential substitution and
-response scrubbing, although its higher tiers are not default-deny and its
-production platform is proprietary. See the addendum.
 
 ## Per-project notes
 
@@ -112,8 +63,7 @@ production platform is proprietary. See the addendum.
 
 ### agent-safehouse
 - **Source**: https://agent-safehouse.dev/ ; https://github.com/eugene1g/agent-safehouse
-- **HN launch**: [#47301085](https://news.ycombinator.com/item?id=47301085) (March 12 2026) — 823 points
+- **License**: Apache 2.0 (~1,400 stars)
-- **License**: Apache 2.0 (~1,781 stars at launch)
 - **Isolation**: macOS `sandbox-exec` (Seatbelt) profiles — kernel-level
   syscall interception, no container.
 - **Locality**: Local, macOS only.
@@ -123,16 +73,6 @@ production platform is proprietary. See the addendum.
 - **Config**: Shell functions or custom `sandbox-exec` profile files;
   LLM-assisted profile generation supported.
 - **Network policy**: Not addressed.
-- **Notable from HN thread**: Creator acknowledged the project is "just a
-  policy-generator for `sandbox-exec` — no dependencies, no daemons, no
-  subscription; I did put in many hours to identify the minimum required
-  permissions for agents to continue working." Simon Willison noted that
-  evaluating whether a sandboxing tool actually works as intended is hard.
-  Top community sentiment: *"I honestly think that sandboxing is currently
-  THE major challenge that needs to be solved for the tech to fully realise
-  its potential."* The macOS Docker gap (Docker for Mac runs inside a Linux
-  VM, so `sandbox-exec` is the only native primitive for bare-metal macOS
-  processes) was the stated motivation.
 - **Maturity**: Active through March 2026.
 
 ### matchlock
@@ -215,474 +155,73 @@ production platform is proprietary. See the addendum.
   also supported.
 - **Maturity**: Active through April 2026.
 
-### E2B *(added 2026-07-20)*
-
-- **Source**: https://github.com/e2b-dev/e2b ; https://e2b.dev/docs
-- **License**: Apache 2.0 (~12.4k stars); commercial hosted service with
-  self-hosting/BYOC support.
-- **Isolation**: Firecracker microVM per sandbox.
-- **Locality**: Cloud-hosted by default; self-hosting uses Terraform on AWS or
-  GCP (with other targets documented as works in progress).
-- **Agent integration**: LLM-agnostic Python and JavaScript/TypeScript SDKs;
-  code-interpreter and desktop-sandbox products. Platform primitive rather
-  than a coding-agent wrapper.
-- **Config**: Programmatic SDK/API plus templates. Network configuration
-  supports internet on/off, outbound allow/deny rules, and a custom egress
-  proxy.
-- **Network policy**: Configurable per sandbox, but not documented as
-  default-deny and no built-in outbound-content DLP is documented.
-- **Credentials**: Environment variables passed to the sandbox are explicitly
-  not private at the OS level. No built-in in-flight application-credential
-  injection is documented.
-- **Persistence**: Full memory + filesystem pause/resume, snapshots, and
-  auto-resume. Continuous runtime is tier-limited, while paused sandboxes are
-  retained indefinitely.
-- **Maturity**: Established hosted platform and the API compatibility target
-  used by CubeSandbox.
-
-### Daytona *(added 2026-07-20)*
-
-- **Source**: https://github.com/daytonaio/daytona ;
-  https://www.daytona.io/docs/
-- **License**: Current production platform is proprietary. The former AGPL
-  repository remains public but is no longer maintained after Daytona moved
-  production development closed-source in June 2026.
-- **Isolation**: Hosted container sandboxes by default, with separate Linux
-  and Windows VM sandbox classes for dedicated-OS workloads. Each sandbox has
-  its own filesystem and network stack; VM-only features include memory
-  pause/resume and forking.
-- **Locality**: Hosted multi-tenant service, with dedicated/custom regions and
-  customer runners available.
-- **Agent integration**: LLM/framework-agnostic SDKs (Python, TypeScript, Go,
-  Ruby, Java), API, and CLI; official agent-framework guides. Platform
-  primitive rather than a local coding-agent wrapper.
-- **Config**: Programmatic per-sandbox image/snapshot, resources, lifecycle,
-  firewall, and secrets.
-- **Network policy**: Per-sandbox IPv4/domain allowlists and block-all mode,
-  subordinate to organization/tier policy. Full internet access is the
-  default on higher tiers, so it is configurable rather than uniformly
-  default-deny.
-- **Credentials**: First-class secret manager with the same phantom-token
-  pattern as bot-bottle: the sandbox environment gets an opaque placeholder,
-  an HTTPS proxy substitutes the real secret in headers only for allowed
-  hosts, and responses are scrubbed back to the placeholder.
-- **Persistence**: Persistent filesystem for stopped container sandboxes;
-  memory + filesystem pause/resume for VM sandboxes; snapshots and configurable
-  auto-stop.
-- **Maturity**: Production commercial platform. Notable April 2026 credential
-  exposure was patched; the June 2026 closed-source transition materially
-  changes its transparency/self-hosting posture.
-
-### Other hosted runtimes carried forward from the earlier survey
-
-- **Northflank Sandboxes** — hosted or customer-cloud, microVM-backed
-  containers with SDK-managed lifecycle, optional persistent volumes, and
-  sub-second claimed boot. This is a platform primitive for untrusted code and
-  agents, not a local agent wrapper or role-policy layer.
-- **Cloudflare Sandbox SDK** — Workers/Durable Objects API over VM-isolated
-  Linux containers for command, file, process, and service execution. It is a
-  hosted TypeScript platform primitive; application authentication,
-  authorization, and credential-proxy patterns remain the integrator's job.
-
-Both belong to the same “build your agent platform on this runtime” category as
-E2B and Daytona. They were named but not analyzed in depth by the original
-Claude-specific note, so they remain outside the main comparison table rather
-than being presented with false precision.
-
-### CubeSandbox *(added 2026-07-18)*
-- **Source**: https://github.com/TencentCloud/CubeSandbox ;
-  HN launch https://news.ycombinator.com/item?id=47863430
-- **License**: Apache 2.0 (~10.4k stars). By Tencent Cloud; described as
-  "battle-tested, production-ready" infra already running in Tencent
-  Cloud. Rust / Go / C.
-- **Isolation**: MicroVMs via RustVMM + KVM — "each sandbox gets its own
-  Guest OS kernel, no Docker shared-kernel escapes." Hardware-level
-  isolation, dedicated kernel per instance.
-- **Locality**: Self-hosted, but **server/cluster-oriented**, not a
-  single-user local CLI. Deploy guides target PVM cloud VMs, bare metal,
-  and dev. A single 96-vCPU host is claimed to run 2,000+ concurrent
-  sandboxes.
-- **Agent integration**: **Drop-in E2B SDK replacement** (single env-var
-  change) — the headline compatibility claim. OpenClaw assistant
-  integration; general LLM-code execution. Aimed at platform builders,
-  not one developer's laptop.
-- **Config**: Programmatic via the E2B-compatible SDK. No declarative
-  manifest.
-- **Network policy**: This is the striking part — **domain allowlists,
-  instant block on unauthorized egress, full audit logs, per-sandbox
-  traffic tokens, policy-routing egress**, enforced by an eBPF-based
-  virtual switch giving kernel-level network isolation. Closest match yet
-  to bot-bottle's own default-deny + per-bottle allowlist egress model.
-- **Credentials**: **Credential vault** — agents call external APIs / LLMs
-  while "keys never enter the sandbox, model context, or logs." Same
-  in-flight-injection idea as matchlock, but productized as a vault.
-- **Performance**: <60ms cold start (claimed 2.5–50× faster than
-  alternatives), <5MB memory per instance; millisecond snapshot rollback
-  is upcoming.
-- **Maturity**: Open-sourced July 2026 off production Tencent Cloud use;
-  most-starred project in this set (~10.4k).
-
-### Cleanroom *(added 2026-07-18)*
-- **Source**: https://github.com/buildkite/cleanroom
-- **License**: Apache 2.0
-- **Isolation**: MicroVM — Firecracker on Linux, Virtualization.framework
-  on macOS. Digest-pinned OCI images.
-- **Locality**: Self-hosted server (CI-oriented).
-- **Agent integration**: Generic process sandbox; CI-first, not a
-  Claude/agent wrapper.
-- **Config**: `cleanroom.yaml` in the repo being sandboxed defines egress
-  rules, resources, and network policy. Cleanroom resolves this from the
-  commit being run.
-- **Network policy**: Default-deny + per-repo hostname allowlist (resolved
-  from DNS answers + destination IP:port). Co-hosted services on the same
-  IP:port are not distinguished. OIDC-backed auth for remote servers.
-- **Credentials**: Host-side only; not injected in-flight but not present
-  in the VM.
-- **Notable**: Policy lives in the *repo being sandboxed*, not in an
-  agent-role definition — closer to per-repo scoping than per-role.
-  Supports Docker-inside-sandbox (`services.docker.required: true`), OIDC
-  authorization, suspend/resume lifecycle.
-- **Maturity**: Active Buildkite product.
-
-### container-use *(added 2026-07-18)*
-- **Source**: https://github.com/dagger/container-use
-- **License**: Apache 2.0
-- **Isolation**: Docker container per agent + git worktree per agent.
-  Containers share the host kernel; stronger than bare host but weaker
-  than microVM.
-- **Locality**: Local.
-- **Agent integration**: MCP stdio server — Claude Code, Cursor, Windsurf.
-  `claude mcp add container-use -- container-use stdio`.
-- **Config**: None for security policy. Environments are provisioned on
-  demand; no allowlist or credential config.
-- **Network policy**: Not addressed.
-- **Notable**: Per-agent git branches (`container-use/<env_name>`);
-  parallel agents without filesystem conflict; real-time log visibility
-  and terminal attach for intervention; git-based review workflow.
-  Oriented toward parallel development safety, not security containment.
-- **Maturity**: Early development, active.
-
-### Docker sbx *(added 2026-07-18)*
-- **Source**: Docker proprietary (`sbx` CLI, separate from `docker`).
-- **License**: Proprietary.
-- **Isolation**: MicroVM (Docker's own implementation) — each session gets
-  its own kernel, Docker daemon inside the VM, and filesystem.
-- **Locality**: Local (macOS and Windows; does not require Docker Desktop).
-- **Agent integration**: Explicit wrapper — Claude Code, Codex, Gemini
-  CLI, Copilot CLI, Kiro. Launches agent inside the VM with
-  `--dangerously-skip-permissions` by default.
-- **Config**: Open / Balanced / Locked Down network presets at launch. No
-  per-role manifest.
-- **Network policy**: Default-deny; preset levels control strictness. TUI
-  dashboard shows a live log of every outbound connection (allowed and
-  blocked) with point-and-click allow/block for hosts.
-- **Credentials**: OS keychain + host-side proxy injection — API keys
-  never enter the VM.
-- **Notable**: Best DX among microVM tools (one command, works like native
-  yolo Claude but inside a VM); branch mode creates a git worktree in
-  `.sbx/`. Network policy is preset-based, not role-declarative.
-- **Maturity**: GA 2026.
-
-### Anthropic srt *(added 2026-07-18)*
-- **Source**: https://github.com/anthropic-experimental/sandbox-runtime
-  (`@anthropic-ai/sandbox-runtime` on npm, `sandbox-runtime` on PyPI)
-- **License**: Apache 2.0 (experimental).
-- **Isolation**: OS-level only — Seatbelt (`sandbox-exec`) on macOS,
-  bubblewrap on Linux, WFP (Windows Filtering Platform) account-fenced on
-  Windows. **No container or VM.** Lowest overhead in the set.
-- **Locality**: Local.
-- **Agent integration**: Claude Code's sandboxed bash tool uses this
-  internally. Can wrap any arbitrary process (`srt <command>`). Cloud
-  Claude Code sessions use full microVMs instead.
-- **Config**: Programmatic per-invocation — allow/deny path lists for
-  filesystem; allow/denylist for network (HTTP proxy + SOCKS5).
-- **Network policy**: Proxy-based filtering (HTTP + SOCKS5); domain
-  allowlist/denylist enforced at proxy layer. Custom proxy supported
-  (e.g. mitmproxy for inspection + audit). Processes that ignore proxy
-  env vars may bypass filtering on some platforms.
-- **Notable**: Cross-platform (macOS/Linux/Windows); wraps any process,
-  not just agents; no role/manifest concept. Annotated as a research
-  preview — APIs may change.
-- **Maturity**: Early research preview.
-
-## Claude-specific wrappers and developer environments
-
-These projects were the focus of the original containerized-Claude survey.
-They remain useful comparisons for local developer experience, but most are
-templates or wrappers rather than policy-bearing sandbox platforms, so they
-are grouped here instead of widening the main table further.
-
-### claudebox
-
-- **Source**: https://github.com/RchGrav/claudebox
-- **Isolation**: Docker, with per-project images, authentication state, and
-  configuration.
-- **Agent integration**: Claude Code wrapper with 15+ preconfigured language
-  and task profiles.
-- **Network policy**: Per-project firewall allowlists.
-- **Closest overlap**: local one-command developer workflow and project-scoped
-  network policy.
-- **Difference**: profiles describe development toolchains, not named agent
-  roles. There is no bottle/agent split, composable role manifest, provider
-  plugin layer, or outbound-content DLP.
-
-### Spritz / claude-code-sandbox
-
-- **Source**: https://github.com/textcortex/claude-code-sandbox (archived;
-  points to its successor, Spritz).
-- **Isolation**: The original project ran Claude Code in local Docker with
-  bypass permissions; Spritz moved toward Kubernetes-native multi-agent
-  infrastructure.
-- **Difference**: the successor targets cluster orchestration rather than a
-  low-dependency local launcher. It is architecturally closer to hosted or
-  Kubernetes platform runtimes than to bot-bottle's single-operator CLI.
-
-### Trail of Bits claude-code-devcontainer
-
-- **Source**: https://github.com/trailofbits/claude-code-devcontainer
-- **Isolation**: A Docker devcontainer that exposes only project files and is
-  designed to run Claude Code with `bypassPermissions` for security audits and
-  untrusted-code review.
-- **Difference**: a hardened, reusable environment definition rather than an
-  agent launcher or fleet. It has no named-role manifest, per-role credential
-  custody, supervision plane, or multi-backend abstraction.
-
-### Smaller wrappers and official templates
-
-Projects such as `arezi/claude-sandbox`, `nkrefman/claude-sandbox`, and
-`VishalJ99/claude-docker`, plus Docker/Anthropic devcontainer templates, prove
-there is steady demand for “Claude in a container.” They are deliberately
-small launch/build configurations. They compete on setup simplicity, not on
-role-aware policy, credential custody, persistent supervision, or a fleet
-model, and are better treated as a product category than as individual rows.
-
-### SuperHQ
-
-- **Source**: https://superhq.ai/
-- **Isolation**: Apple-Silicon desktop application using local microVMs via
-  Virtualization.framework/libkrun-era components.
-- **Agent integration**: Claude Code, Codex, and Pi in a GUI, with mobile
-  remote access.
-- **Credentials and review**: host-side auth gateway injects credentials on
-  the wire; a temporary overlay stages writes for diff-and-accept review.
-- **Closest overlap**: local microVM isolation, multi-provider launching, and
-  credential custody for security-minded individual developers.
-- **Difference**: GUI desktop product on Apple Silicon rather than a
-  cross-platform declarative CLI/fleet layer. The July 2026 snapshot in the
-  original survey recorded a user request for per-run tool-call and network
-  audit logging; treat that as point-in-time rather than a permanent gap.
-
-## Credential gateway without isolation
-
-### OneCLI
-
-[OneCLI](https://onecli.sh/) is a framework-agnostic identity gateway rather
-than a sandbox. Its phantom-token design gives the agent a placeholder and
-substitutes the encrypted real credential at the network layer. It therefore
-matches bot-bottle closely on secret custody, and is more portable because it
-can sit in front of agents launched by anything, but it supplies no container
-or VM boundary, filesystem isolation, role manifest, or egress-content DLP.
-
-The positioning consequence from the earlier survey still holds: secret
-custody alone is not unique. bot-bottle's relevant combination is local
-isolation + default-deny egress + payload DLP + declarative roles + credential
-custody. OneCLI's managed tier also places custody with a third party, whereas
-bot-bottle keeps it within operator-controlled infrastructure. See
-[`agent-credential-proxy-landscape.md`](agent-credential-proxy-landscape.md)
-for the detailed build-versus-adopt analysis.
-
-## Governance / pre-action authorization layers
-
-These two tools don't provide VM or filesystem isolation; they intercept
-tool calls before execution and evaluate them against a per-agent
-declarative policy. They are the closest competitors on **agent-tailored
-policy** and complement isolation sandboxes rather than substituting for
-them.
-
-### Microsoft Agent Governance Toolkit (AGT) *(added 2026-07-18)*
-- **Source**: https://github.com/microsoft/agent-governance-toolkit
-- **License**: MIT (~3.3k stars, open-sourced April 2, 2026).
-- **Isolation**: None (OS/VM). Execution rings (0–3, inspired by CPU
-  privilege levels) control what an agent can do at the framework layer.
-  MCP security gateway treats MCP traffic as an untrusted boundary.
-- **Locality**: Embedded in the agent framework (Python, TypeScript, .NET,
-  Rust, Go; 20+ framework adapters).
-- **Agent integration**: Framework-agnostic. Plugs into Semantic Kernel,
-  AutoGen, and others as a middleware layer.
-- **Config**: YAML policy per agent — tools can be `allowed`, `denied`,
-  `sandboxed`, or routed through an `approval` step. Every action passes
-  through a governance gate checking: agent DID, trust score, risk tier,
-  requested tool, action type, and policy rules.
-- **Network policy**: Not directly — operates at tool-call level.
-- **Credentials**: Per-agent DID (Ed25519 decentralized identifier); agent
-  does not borrow a human's credentials.
-- **Notable**: Dynamic trust score (0–1,000, behavioral decay) —
-  privilege follows observed behaviour, not just provisioning. Covers all
-  10 OWASP Agentic Top 10 risks. Kill switch + SLO monitoring. Sub-ms
-  policy enforcement.
-- **Maturity**: MIT, ~3.3k ⭐, v3.7.0 May 2026.
-
-### Open Agent Passport (OAP) *(added 2026-07-18)*
-- **Source**: https://github.com/aporthq/aport-spec ; spec at
-  https://api.aport.io/spec/spec/oap/oap-spec.md/ ; arXiv 2603.20953
-- **License**: Open specification.
-- **Isolation**: None. Pre-action hook only — intercepts tool calls
-  synchronously before execution, evaluates against a cloud-registry
-  declarative policy, fails closed.
-- **Locality**: Local hook + cloud policy registry.
-- **Agent integration**: Framework-agnostic; hook pattern.
-- **Config**: Declarative policy rules in a cloud registry (evaluated in
-  order; first failing rule denies). Ed25519-signed, hash-chained audit
-  records per decision.
-- **Network policy**: Not directly.
-- **Notable**: 53ms median authorization decision (N=1,000). In an
-  adversarial testbed ($5,000 bounty, 1,151 sessions), social engineering
-  succeeded 74.6% of the time under a permissive policy; under a
-  restrictive OAP policy, 0% success across 879 attempts. Assumes
-  framework runtime is not compromised.
-- **Maturity**: Specification + reference implementation, 2026.
-
 ## Comparison table
 
-*Isolation/sandbox tools only. AGT and OAP are governance layers — see their per-project notes above.*
+| Axis | bot-bottle | endo-familiar | litterbox | agent-safehouse | matchlock | tilde.run | boxlite | microsandbox | smolmachines |
-
+|---|---|---|---|---|---|---|---|---|---|
-| Axis | bot-bottle | endo-familiar | litterbox | agent-safehouse | matchlock | tilde.run | boxlite | microsandbox | smolmachines | E2B | Daytona | CubeSandbox | Cleanroom | container-use | Docker sbx | Anthropic srt |
+| Isolation | Docker + internal net + pipelock; gVisor if present | Object-capability (no OS isolation) | Podman + opt. Landlock | macOS `sandbox-exec` | MicroVM (Firecracker / Virt.fw) | Hosted container (unverified) | MicroVM (KVM / Hypervisor.fw) | MicroVM (libkrun) | MicroVM (libkrun / KVM) |
-|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
+| Local vs hosted | Local | Local | Local (Linux) | Local (macOS) | Local | Hosted SaaS | Local | Local | Local |
-| Isolation | MicroVM per bottle default (Firecracker/KVM on Linux, Apple Container on macOS) + own egress DLP scanner; Docker legacy fallback, gVisor there if present | Object-capability (no OS isolation) | Podman + opt. Landlock | macOS `sandbox-exec` | MicroVM (Firecracker / Virt.fw) | Hosted container (unverified) | MicroVM (KVM / Hypervisor.fw) | MicroVM (libkrun) | MicroVM (libkrun / KVM) | Firecracker microVM | Container or Linux/Windows VM class | MicroVM (RustVMM / KVM) | MicroVM (Firecracker / Virt.fw) | Docker container + git worktree | MicroVM (proprietary) | OS-level (Seatbelt / bubblewrap / WFP) — no container |
+| Open source | Apache 2.0 | Apache 2.0 | Apache 2.0 | Apache 2.0 | MIT | No | Apache 2.0 | Apache 2.0 | Apache 2.0 |
-| Local vs hosted | Local | Local | Local (Linux) | Local (macOS) | Local | Hosted SaaS | Local | Local | Local | Hosted; self-host/BYOC available | Hosted; dedicated/custom regions | Self-hosted (server/cluster) | Self-hosted server | Local | Local | Local |
+| Agent target | Claude Code | Generic (demo) | Generic | Multi-agent wrapper | Generic (+ Claude/OpenAI SDKs) | Claude focus | Generic | Claude + Cursor (MCP/Skills) | Generic (AGENTS.md) |
-| Open source | Apache 2.0 | Apache 2.0 | Apache 2.0 | Apache 2.0 | MIT | No | Apache 2.0 | Apache 2.0 | Apache 2.0 | Apache 2.0 | Production closed-source; legacy AGPL repo unmaintained | Apache 2.0 | Apache 2.0 | Apache 2.0 | Proprietary | Apache 2.0 (experimental) |
+| Network policy | Default-deny via pipelock + per-bottle allowlist + DLP | Capability model only | Limited | Not addressed | Default-deny + allowlist + secret-injecting proxy | Default-deny + logging | Per-VM net (unverified) | Not documented | Off by default + allowlist |
-| Agent target | Claude Code, Codex, Pi, and provider plugins | Generic (demo) | Generic | Multi-agent wrapper | Generic (+ Claude/OpenAI SDKs) | Claude focus | Generic | Claude + Cursor (MCP/Skills) | Generic (AGENTS.md) | LLM-agnostic platform builders | LLM-agnostic platform builders | E2B-compatible (platform builders) | CI / generic process | Claude Code, Cursor, Windsurf (MCP) | Claude Code, Codex, Gemini CLI, Copilot, Kiro | Claude Code (and any process) |
+| Parallel agents | Yes (one bottle per agent) | n/a | Not addressed | One at a time | Multiple VMs | Yes (dashboard) | SDK-level | SDK-level | Architectural |
-| Network policy | Default-deny via own egress scanner + per-bottle allowlist + content DLP + gitleaks on git push | Capability model only | Limited | Not addressed | Default-deny + allowlist + secret-injecting proxy | Default-deny + logging | Per-VM net (unverified) | Not documented | Off by default + allowlist | Per-sandbox allow/deny rules and custom egress proxy; internet configurable | Per-sandbox CIDR/domain allowlist or block-all; tier policy; secret-injecting proxy | Default-deny allowlist + instant egress block + audit logs + per-sandbox tokens (eBPF) + credential vault | Default-deny + per-repo host allowlist (cleanroom.yaml) | Not addressed | Default-deny; Open / Balanced / Locked Down presets; live TUI network panel | Proxy-based allowlist/denylist (HTTP + SOCKS5); custom proxy supported |
+| Config | JSON manifest (bottles + agents) | Programmatic refs | CLI wizard | Profile files / shell fns | CLI / SDK | DSL + CLI + SDK | SDK | CLI / SDK / MCP | TOML Smolfile |
-| Parallel agents | Yes (one bottle per agent) | n/a | Not addressed | One at a time | Multiple VMs | Yes (dashboard) | SDK-level | SDK-level | Architectural | Yes (platform service) | Yes (platform service) | Yes (2,000+/host claimed) | Yes (server model) | Yes (per-agent containers + worktrees) | Yes | Yes |
+| Maturity | Active May 2026 | Research (2022+) | Early (~66 ⭐) | Active (~1.4k ⭐) | Experimental (~574 ⭐) | Private preview | YC, ~4.7k ⭐ | YC, ~6k ⭐, beta | ~3.1k ⭐ |
-| Long-running posture | Persistent by default (named, supervised) | n/a (demo) | Session (up while in use) | Per-invocation | Ephemeral VM per run | Per-run (versioned) | Ephemeral + snapshot/fork | Ephemeral / on-demand | Named persistent by default | Runtime tier limits + indefinite pause/resume | Persistent filesystem; VM pause/resume; configurable auto-stop | Ephemeral + auto pause/resume | Per-run + suspend/resume | Per-agent container (ephemeral) | Per-session; branch mode creates git worktree in .sbx/ | Per-invocation |
-| DX: run Claude yolo-style | One command → interactive yolo Claude (`start <agent>`, `--dangerously-skip-permissions` default) | n/a (lib demo) | Wizard + build, then run claude inside (Linux only) | One-command wrapper (`safehouse claude --dangerously-skip-permissions`) | CLI: run a cmd in a VM (not a Claude wrapper) | Hosted (`tilde exec`), not local-native | SDK code required (build the run yourself) | CLI/MCP: sandbox-as-a-tool for the agent, not a wrapper around it | SSH into a named machine, run claude there | SDK/CLI sandbox; wire the agent yourself | SDK/CLI sandbox; wire the agent yourself | Stand up a cluster + drive via E2B SDK | CI-oriented, not a Claude wrapper | MCP server: `claude mcp add container-use -- container-use stdio` | One command: `sbx` wraps claude with `--dangerously-skip-permissions` default | Library/wrapper, not a standalone CLI |
-| Config | YAML-in-Markdown manifests (bottles + agents) | Programmatic refs | CLI wizard | Profile files / shell fns | CLI / SDK | DSL + CLI + SDK | SDK | CLI / SDK / MCP | TOML Smolfile | SDK/API + templates | SDK/API/CLI + images/snapshots | E2B-compatible SDK | cleanroom.yaml in repo | None (no policy config) | Preset levels at launch | Programmatic per-invocation (allow/deny lists) |
-| Agent-tailored policy | Yes — bottle/agent split; declarative per-role egress + credentials; composable via `extends:` | Partial — capability model scopes per-agent, but no declarative role manifest | No | Partial — per-agent profile files (Seatbelt); no egress | No | Yes — per-agent DSL RBAC (allow/deny/approve per action/repo/agent) | No | No | No | No — per-sandbox SDK config | No — per-sandbox SDK config | No — per-sandbox SDK config, not role-scoped | Partial — per-repo cleanroom.yaml, not per-role | No | No — network presets only | No |
-| Maturity | Active July 2026 | Research (2022+) | Early (~66 ⭐) | Active (~1.8k ⭐) | Experimental (~574 ⭐) | Private preview | YC, ~4.7k ⭐ | YC, ~6k ⭐, beta | ~3.1k ⭐ | Established hosted platform, ~12.4k ⭐ | Production commercial; closed-source since June 2026 | Tencent, prod, ~10.4k ⭐ | Active (Buildkite product) | Early development | GA 2026 | Early research preview |
 
 ## What's closest, what's different
 
 **Closest in design and scope.** agent-safehouse and litterbox sit
 nearest bot-bottle: local, single-user, thin wrappers over an
 existing OS primitive, low-dep. The split is the isolation primitive —
-bot-bottle now defaults to a VM per bottle (Firecracker microVM on KVM
+bot-bottle uses Docker + pipelock egress (plus gVisor where
-Linux, Apple Container on macOS) with its own DLP-scanning egress proxy,
+available); agent-safehouse uses `sandbox-exec`; litterbox uses Podman +
-keeping Docker only as a legacy fallback; agent-safehouse uses
+Landlock. matchlock and smolmachines are spiritually close on the
-`sandbox-exec`; litterbox uses Podman + Landlock. matchlock and
+*policy* side (default-deny net, per-host allowlist) but use microVMs
-smolmachines are close on *both* the policy side (default-deny net,
+instead of containers.
-per-host allowlist) and — now that bot-bottle has moved off
-containers-by-default — the microVM isolation primitive. Note: Apple
-Container 1.0 stable shipped June 9 2026 (frozen CLI and APIs), which
-makes the macOS backend stable surface area rather than a moving target.
-
-**New closest on agent-tailored policy.** Two governance tools are the
-direct competitors on the "coarse-grained sandbox" axis. **tilde.run**
-has had per-agent DSL RBAC since its launch (though it's hosted SaaS).
-**Microsoft AGT** is the most serious new entrant: per-agent DID
-identity, YAML policy that can allow/deny/sandbox/approve individual tool
-calls per agent, and a dynamic behavioural trust score. It operates at
-the framework tool-call layer, not the network layer — so it's
-complementary to bot-bottle's network/filesystem isolation rather than a
-direct substitute, but on the "does this sandbox know what this agent is
-for?" question it is the most complete answer in the field. OAP's
-pre-action hook pattern achieves similar goals with cryptographic audit
-and a 0% adversarial-attack success rate under a restrictive policy.
-
-**New closest on DX.** **Docker sbx** is the first tool in this set that
-matches bot-bottle on the "one command, dangerously-skip-permissions safe
-by default" DX bar, at microVM isolation strength, with host-side
-credential injection. It is proprietary, preset-based (not role-
-declarative), and cloud-agent-specific, but it directly competes on the
-UX proposition. agent-safehouse was the previous DX peer; Docker sbx
-materially raises the bar.
-
-**New closest on repo-scoped policy.** **Cleanroom** (Buildkite) is the
-first tool to combine microVM isolation with a declarative egress policy
-file — though the policy lives in the repo being sandboxed
-(`cleanroom.yaml`), not in an agent-role manifest. That makes it per-
-repo rather than per-role: the same Cleanroom config applies to any
-agent running in that repo. The distinction matters for bot-bottle's
-use case (one developer running multiple agent *roles* with different
-egress footprints), but for CI/CD use cases Cleanroom is a direct
-alternative.
 
 **Solving a different problem.** tilde.run is hosted SaaS for team /
 production agent pipelines with data-versioned rollback — explicitly
-opposite to bot-bottle's "infrastructure I control" goal. E2B and Daytona
+opposite to bot-bottle's "infrastructure I control" goal. boxlite and
-are hosted sandbox platforms, while boxlite, microsandbox, and CubeSandbox
+microsandbox are infrastructure libraries aimed at platform builders
-are infrastructure libraries/services aimed at platform builders embedding
+embedding sandboxes into agent frameworks; they would be a *backend*
-sandboxes into agent frameworks; they
+bot-bottle could call, not a competitor to its manifest layer.
-would be a *backend* bot-bottle could call, not a competitor to its
+endo-familiar is in a different paradigm entirely: capability passing
-manifest layer. endo-familiar is in a different paradigm entirely:
+rather than kernel boundaries.
-capability passing rather than kernel boundaries.
 
 ## Borrowable ideas
 
-### Already shipped or otherwise addressed
+What bot-bottle already has that the survey suggested as
-
+differentiators:
-- Default-deny egress with a per-agent allowlist (own egress scanner).
+- Default-deny egress with a per-agent allowlist (pipelock).
 - DLP scanning of outbound traffic.
 - Bottle / agent split (manifest layer above the isolation primitive).
 - gVisor auto-detection on Linux.
-- **In-flight secret injection** (suggested by matchlock) — **shipped.**
-  Real provider and git-host tokens are held outside the agent and injected
-  by the egress gateway on matching routes. The agent receives only proxy
-  URLs and, where a client requires a credential-shaped value, a placeholder;
-  `GITEA_TOKEN` and equivalent real tokens do not appear in the agent's
-  environment.
-- **MicroVM backend** — **shipped.** MicroVMs are now the default:
-  Firecracker on KVM Linux and Apple Container on macOS. Docker is the legacy
-  fallback.
-- **Per-use SSH key confirmation** (suggested by litterbox) — **addressed by
-  stronger credential custody instead.** The agent does not hold the upstream
-  git SSH key or an SSH-agent socket: git-gate holds the credential and gates
-  git operations. A confirmation wrapper inside the agent would therefore
-  protect a credential that is no longer there. Operator approval at the gate
-  remains the appropriate control point for any future per-use confirmation.
 
-### Still worth considering
+Ideas worth considering, without abandoning the Python-stdlib-first / local-Docker
+stance:
 
-- **Live network activity in the supervisor TUI** (from Docker sbx): show
+1. **Per-use SSH key confirmation** (from litterbox). Even with
-  allowed and blocked connections and let the operator propose policy changes
+   KnownHostKey pinning and pipelock egress, a wrapper SSH agent that
-  from the existing supervision surface.
+   prompts on each key use (e.g. via `osascript` / `notify-send`) would
-- **Tamper-evident audit records** (from OAP): sign and hash-chain egress and
+   catch an agent doing something off-policy with a key it legitimately
-  supervision decisions for compliance-sensitive deployments.
+   holds. Pure-stdlib, no new deps.
-- **Behaviour-informed policy downgrade** (from Microsoft AGT): use repeated
+2. **In-flight secret injection** (from matchlock). Pipelock already
-  DLP alerts or supervision holds as a signal to narrow policy or request
+   does egress allowlisting and DLP; teaching it to *inject* tokens at
-  closer review. This needs a carefully specified trust model before it can be
+   proxy time so e.g. `GITEA_TOKEN` never appears in the container's
-  more than a heuristic.
+   env would close the "agent reads its own env and exfiltrates" path.
+   Fits the existing pipelock architecture.
+3. **MicroVM backend as an opt-in bottle type** — already on the radar
+   in `stronger-isolation-alternatives.md`. microsandbox, smolmachines,
+   and matchlock all show that libkrun + Apple's
+   Virtualization.framework is ergonomic enough that a
+   `"runtime": "microvm"` field on a bottle is plausible without a heavy
+   stack.
 
 Not worth borrowing: the SDK-first programmatic API style of boxlite /
 microsandbox (cuts against the declarative-manifest stance), and the
 hosted-SaaS dashboard model of tilde.run (cuts against the
 "infrastructure I control" goal).
 
-## Publishing and positioning verdict
-
-Publishing remains worthwhile, but the defensible claim is the combination,
-not any single primitive. Credential custody is matched by OneCLI, matchlock,
-Daytona, Docker sbx, and CubeSandbox; local one-command isolation is matched by
-agent-safehouse and Docker sbx; hosted microVM execution is a crowded platform
-category.
-
-bot-bottle remains unusual in combining:
-
-- local, operator-controlled execution with persistent named bottles;
-- one declarative role layer across Claude Code, Codex, Pi, and provider
-  plugins;
-- composable agent/bottle manifests, skills, and system prompts;
-- Firecracker/Apple Container isolation with a Docker fallback;
-- default-deny per-role egress, payload DLP, and git-push secret scanning;
-- credentials injected outside the agent process; and
-- supervision and audit state suited to long-running parallel agents.
-
-The practical wedge is “as easy as native yolo, with declarative role policy
-and self-hosted custody,” including scoped access to private LAN/Tailnet
-services that cloud-first runtimes cannot provide without additional network
-plumbing. The main competitive risks are a local wrapper such as claudebox or
-Docker sbx growing a role-manifest layer, and GUI products such as SuperHQ
-adding equivalent policy and audit depth.
-
 ## Caveats
 
 - Star counts and last-commit dates are point-in-time snapshots.
@@ -691,180 +230,3 @@ adding equivalent policy and audit depth.
 - The `superradcompany/microsandbox` URL in the original prompt
   redirects to `microsandbox/microsandbox`; the surveyed project is the
   same.
-- CubeSandbox performance/scale numbers (<60ms cold start, <5MB/instance,
-  2,000+ sandboxes per 96-vCPU host) are the project's own launch claims,
-  not independently verified here.
-
-## Addendum 2026-07-18 — CubeSandbox and the positioning read
-
-CubeSandbox (Tencent Cloud, Apache 2.0, ~10.4k stars, HN launch
-[#47863430](https://news.ycombinator.com/item?id=47863430)) is the first
-open-source, self-hostable project in this survey to combine, in one stack,
-the main primitives
-bot-bottle treated as its differentiator:
-
-- **Egress custody (connection level)** — default-deny domain allowlist
-  (L7 domain/SNI filtering), instant block on unauthorized egress,
-  per-sandbox traffic tokens, full audit logs of destinations (eBPF
-  virtual switch, "CubeVS"). This matches bot-bottle's egress scanner at
-  the *connection level*, productized — see the one thing it does **not**
-  match, below.
-- **Credential custody** — a vault where keys "never enter the sandbox,
-  model context, or logs." This is the in-flight-injection idea from
-  matchlock, but as a first-class feature, and it's exactly the
-  cross-vendor "egress audit + custody" wedge the monetization
-  positioning treats as the one defensible moat.
-- **Isolation on par with bot-bottle's current default** — a dedicated
-  guest kernel per sandbox (RustVMM/KVM). bot-bottle now defaults to the
-  same class of boundary (Firecracker microVM / Apple Container), so this
-  is parity, not an edge; CubeSandbox's remaining edge is running that
-  per-kernel isolation multi-tenant at scale on one host.
-
-The one axis CubeSandbox does **not** cover — and where bot-bottle stays
-distinctive:
-
-- **Content DLP on *authorized* channels.** CubeSandbox's egress control
-  is connection-level: it decides *whether* a destination is allowed and
-  logs it, and its vault keeps *injected* credentials out of the sandbox
-  entirely. Neither inspects the *payload* of traffic to an allowed
-  destination. So an agent that exfiltrates over a permitted channel —
-  pasting a repo's contents, an agent-derived secret, or PHI into an
-  allowed API/domain — is not caught by CubeSandbox. bot-bottle's own
-  egress DLP scanner does scan that: response + websocket content against
-  the resolved per-flow config, with per-bottle token redaction (see
-  recent egress commits). The vault
-  approach is arguably *stronger* for the specific case of pre-known
-  injected credentials (they can't leak if they were never present), but
-  it is not a substitute for content inspection of everything else.
-
-**Long-running posture — a sharper axis than raw isolation.** E2B and
-CubeSandbox are *ephemeral-per-task* by design; a long-running agent is an
-architected pattern on top, not the default. E2B: 5-minute default
-timeout, continuous runtime tier-capped (~1h Hobby / ~24h Pro), duration
-achieved via **pause/resume** (preserves filesystem + memory + processes;
-reconnect by sandbox ID via `Sandbox.connect()`; resume resets the timeout
-to 5 min; auto-pause via `on_timeout: "pause"`). CubeSandbox mirrors this
-(E2B drop-in) with first-class auto pause/resume and hundred-ms
-checkpoint/fork — and, self-hosted, sets its own timeout policy with no
-vendor tier caps. bot-bottle inverts the model: a bottle is **persistent,
-named, and supervised by default** — long-running *is* the default, not a
-session-management loop over pause/resume. smolmachines is the other
-persistent-by-default project in this set. For anyone building agents that
-run for hours/days, this posture difference matters more than the
-isolation primitive.
-
-**DX — the "run Claude yolo-style" bar.** The reason `claude
---dangerously-skip-permissions` is so widely used is DX: it's one command
-and the agent just goes. The bottle thesis is to make a *sandboxed* run
-that easy — `start <agent>` builds the image on first run and drops you
-into an interactive Claude session that already has
-`--dangerously-skip-permissions` on by default
-(`contrib/claude/agent_provider.py`), with the sandbox as the guardrail
-instead of per-action prompts. On this axis the field splits cleanly:
-- **Wrappers around the agent** (as-easy-as-native): bot-bottle and
-  **agent-safehouse** (`safehouse claude --dangerously-skip-permissions`).
-  These *are* the run-Claude experience. agent-safehouse is the real DX
-  peer — but it's macOS-only Seatbelt, single-run, and doesn't address
-  network egress; bot-bottle adds VM-grade isolation, egress DLP, and
-  persistent/parallel bottles across macOS + Linux.
-- **Libraries / services** (you build the run yourself): boxlite,
-  microsandbox, CubeSandbox, E2B, Daytona. These hand you an SDK or a cluster and
-  expect you to wire the agent in — powerful for platform builders,
-  heavyweight for "just run Claude on my laptop." microsandbox's MCP/Skills
-  angle is *sandbox-as-a-tool the agent calls*, which is the inverse of
-  wrapping the agent.
-- **In between:** litterbox (wizard + build, Linux only), smolmachines
-  (SSH into a named machine), matchlock (run a command in a VM).
-
-So DX is a genuine bot-bottle differentiator. agent-safehouse matches the
-one-command wrapper with weaker isolation and no egress story; Docker sbx now
-matches it at microVM strength but remains proprietary and preset-based. "As
-easy as native yolo, with declarative role policy" is the narrower defensible
-one-liner.
-
-Why it still doesn't collide head-on:
-
-1. **Shape.** CubeSandbox is a *multi-tenant service for platform
-   builders* (drop-in E2B replacement, SDK-driven, 2,000 sandboxes on a
-   box). bot-bottle is a *single-operator, declarative-manifest tool for
-   the infrastructure I run*. Different buyer, different ergonomics — no
-   declarative role manifest, no bottle/agent split, no "one command on my
-   laptop."
-2. **Backend, not competitor.** Like boxlite/microsandbox, CubeSandbox is
-   something bot-bottle could sit *on top of* — a `"runtime": "microvm"`
-   or `"runtime": "cubesandbox"` backend under the manifest layer — while
-   keeping the manifest, the bottle/agent split, and the local,
-   single-operator default.
-
-Why it matters anyway:
-
-- The "nobody else bundles connection-level egress allowlist + audit +
-  in-flight credential custody" line is **no longer true for the
-  primitive** — CubeSandbox ships the open-source/self-hosted combination,
-  and Daytona ships a proprietary firewall + credential-substitution variant.
-  But **content DLP on authorized channels is still not matched** (see
-  above), and neither is the *layer above* the primitive (declarative
-  manifest, cross-vendor orchestration, operator UX, the
-  phone-control/dashboard north star). Those two — outbound-payload DLP
-  and the orchestration layer — are where the defensible ground now sits;
-  the connection-level allowlist + vault mechanism, on its own, is no
-  longer differentiating. Revisit the monetization open/paid line with
-  that in mind.
-- Worth a closer look at **how** CubeSandbox does credential injection
-  and per-sandbox egress tokens (eBPF virtual switch vs. bot-bottle's
-  mitmproxy egress proxy) when hardening bot-bottle's now-shipped
-  credential-custody implementation.
-
-## Addendum 2026-07-18 (second pass) — agent-tailored policy landscape
-
-The second-pass question was: how novel is bot-bottle's per-agent,
-role-tailored sandbox relative to the expanded field?
-
-**The short answer:** on the isolation + network + role-tailoring
-combination, bot-bottle remains the only tool in this set. On
-role-tailored *policy at the tool-call level*, Microsoft AGT and OAP are
-the most complete answers, but they don't provide isolation; they
-complement rather than substitute.
-
-**The competitive picture by axis:**
-
-- *Agent-tailored egress (declarative, per-role)* — bot-bottle and
-  tilde.run. Cleanroom is per-repo, not per-role. Everyone else is
-  per-session or not addressed.
-- *Agent-tailored tool-call policy (declarative, per-agent identity)* —
-  Microsoft AGT (YAML policy + DID identity + trust score), OAP
-  (declarative policy rules + cryptographic audit). Neither provides
-  network/filesystem isolation.
-- *Composable policy (role overlays)* — bot-bottle (`extends:`). No
-  other tool surveyed supports composable role-policy inheritance.
-- *Isolation + DX (one-command safe yolo)* — bot-bottle and Docker sbx.
-  Docker sbx is proprietary, preset-based, and cloud-agent-specific;
-  it's the first DX-class competitor at microVM isolation strength.
-
-**What the HN "coarse-grained" complaint maps to:** The complaint is
-that a VM isolates the filesystem but doesn't know if the agent
-*should* be sending an email. bot-bottle's bottle/agent split is a
-structural answer to this: the bottle manifest declares exactly what
-the role can reach, and the sandbox enforces it at the network layer.
-Microsoft AGT is the most complete answer at the semantic/tool-call
-layer. The gap both leave open is *intent classification* — knowing
-whether a permitted action is consistent with the agent's actual task.
-See `hn-agent-safety-discourse-july-2026.md` for the blast-radius
-analysis.
-
-**Open ideas from new tools (also summarized above):**
-
-- **Microsoft AGT's trust-score decay** — privilege that reflects
-  observed behaviour rather than static provisioning. Applied to
-  bot-bottle: a bottle that has triggered DLP alerts or supervise holds
-  could auto-downgrade its network preset, or flag the session for
-  closer review. Fits the existing supervise-server architecture.
-- **Docker sbx's live network TUI** — real-time per-session view of
-  allowed and blocked outbound connections with point-and-click
-  allow/block. `cli.py supervise` is the right surface; adding a
-  live-connections panel would directly address the "I can't see what
-  the agent is doing" gap without any backend changes.
-- **OAP's cryptographic audit chain** — Ed25519-signed, hash-chained
-  audit records. Currently bot-bottle logs egress decisions but doesn't
-  chain them. A tamper-evident audit record per session would be useful
-  for the compliance use case the CubeSandbox positioning targets.

docs/research/egress-proxy-oom-on-large-downloads.md

@@ -1,86 +0,0 @@
-# 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.

docs/research/hn-agent-safety-discourse-july-2026.md

@@ -1,357 +0,0 @@
-# HN discourse on agent sandbox safety — June/July 2026
-
-A survey of community opinion and notable security disclosures on Hacker
-News and adjacent sources over June–July 2026. The question: what does
-the current discourse say about whether sandboxes are sufficient for
-agentic AI safety, and where does bot-bottle land against the issues
-being raised?
-
-Research conducted 2026-07-18.
-
-## Summary
-
-The past month marks a turning point in community opinion. Earlier in
-2026, the debate was mostly "which sandbox tool is best?" By June–July,
-a cascade of critical CVEs and novel attack classes has shifted the
-framing to "sandboxes are not enough — what else do you need?" The
-attacks that drove this shift are structurally distinct: most route
-through legitimate, trusted channels (Sentry issues, MCP descriptions,
-README files) rather than exploiting the isolation boundary directly.
-
-bot-bottle's architecture holds up well against the direct-escape class
-(Firecracker/Apple Container default backends, credentials never in the
-agent's env, harness entirely on the host). The remaining gap is prompt
-injection — attacker-controlled data interpreted as model instructions.
-Egress controls and prompt injection defenses are orthogonal: egress
-limits what the agent can *send out*; injection is about what it is
-*told to do*. The two don't substitute for each other. Inside a tightly-
-egressed sandbox a successful injection can't exfiltrate to unknown
-hosts, but it can still corrupt the work product, push malicious commits
-past a secret scanner, or use allowlisted channels for exfiltration.
-Those residual risks are addressed below.
-
-## The sandboxing boom sets the stage
-
-The preceding months generated a wave of sandbox tooling. A March 28
-Ask HN thread
-([#47444917](https://news.ycombinator.com/item?id=47444917)) catalogued
-the explosion: E2B, AIO Sandbox, AgentSphere, Yolobox, Exe.dev,
-AgentFence, DenoSandbox, Capsule (WASM), ERA, Vibekit, Daytona, Modal,
-Nono, and more — all launched within roughly 12 months. A parallel March
-9 thread ([#47185250](https://news.ycombinator.com/item?id=47185250))
-surveyed what developers were actually deploying: "containers or YOLO"
-dominated. The honest community mood was that most teams hadn't solved
-this and were shipping anyway.
-
-The March 12 launch of **Agent Safehouse**
-([#47301085](https://news.ycombinator.com/item?id=47301085), 823 points)
-crystallised the community framing: a zero-dep `sandbox-exec` wrapper for
-macOS that attracted the top comment *"I honestly think that sandboxing is
-currently THE major challenge that needs to be solved for the tech to fully
-realise its potential."* The creator's own framing — "no dependencies, no
-daemons, no subscription; the simplicity is the feature" — and Simon
-Willison's observation that evaluating whether a sandboxing tool works as
-intended is itself hard, both prefigure the June–July shift in tone. See
-[`agent-sandbox-landscape.md`](agent-sandbox-landscape.md) for a full
-per-project breakdown.
-
-## The June–July attack cascade
-
-Six attack patterns broke in quick succession. Together they form the
-argument that the community's framing was wrong: the threat model for
-agents isn't just "code that escapes its container" — it's also prompt
-injection, where attacker-controlled data is interpreted as model
-instructions regardless of whether any isolation boundary was crossed.
-Sections 2–4 below are all the same attack class; the "trusted channel"
-label describes the delivery vector, not a different threat.
-
-### 1. Sandbox escape CVEs (DuneSlide, CVE-2026-39861)
-
-Cato AI Labs disclosed **DuneSlide** (CVE-2026-50548/50549, CVSS 9.8),
-a pair of flaws in Cursor 2.x. CVE-2026-50548 abuses the sandbox's
-`working_directory` parameter to point writes at system files; CVE-26-50549
-exploits a symlink-resolution fallback that fails open. Both start with
-a prompt injection and end in sandbox escape — and Cato's framing was
-blunt: "each CVE defeats a different guardrail; the problem is
-structural, not a string of one-offs."
-
-Claude Code's own sandbox had a similar escape this year:
-**CVE-2026-39861** (symlink flaw). The CurXecute/MCPoison/CVE-2026-26268
-chain from Cursor added a poisoned Slack message, a swap-after-approval
-MCP config, and a Git hook as three more entry points in the same
-attack class.
-
-All patched, but the pattern holds: any application-level sandbox that
-takes attacker-influenced values as path parameters is reachable from a
-prompt injection.
-
-### 2. Prompt injection via MCP data (Agentjacking)
-
-Tenet's "Agentjacking" technique planted a fake bug report in Sentry's
-MCP output. When an agent queries Sentry to fix open issues, the
-malicious event is rendered as structured content visually
-indistinguishable from a real Sentry event, and the agent executes the
-embedded instructions with the developer's full privileges. Hit rate
-across Claude Code and Cursor: **85%**. The route is entirely through a
-legitimately-authorized MCP channel — no isolation boundary is crossed;
-the injection arrives inbound through a channel the sandbox explicitly
-trusts.
-
-The Cloud Security Alliance's summary: treat observability, bug-report,
-and integration data as **untrusted agent input**, not neutral
-development metadata.
-
-### 3. README-embedded prompt injection
-
-A July disclosure showed malicious instructions hidden in `README.md`
-— a file that receives no trust prompt and requires no elevated access.
-When asked point-blank whether the repo held hidden instructions, both
-Claude Sonnet 4.6 and GPT-5.5 said no. A payload written for Sonnet
-4.6 transferred unchanged to Sonnet 5, Opus 4.8, and GPT-5.5. The
-attack surface is every repo an agent is asked to work in.
-
-### 4. Prompt injection via MCP tool descriptions
-
-Microsoft research (June 30) showed that attacker-controlled MCP tool
-description fields can silently redirect agent behavior. The injection
-is embedded in metadata the model reads during tool selection — before
-any sandbox enforcement or egress check runs, and entirely on the
-inbound path that egress controls cannot touch.
-
-### 5. MCP STDIO command injection (10 CVEs)
-
-OX Security disclosed a systemic command injection class in Anthropic's
-MCP protocol, covering 10 CVEs across multiple coding agents. The
-Windsurf case (CVE-2026-30615): processing attacker-controlled HTML
-causes the agent to auto-register a malicious MCP STDIO server and
-execute arbitrary commands with no further user interaction.
-
-### 6. LiteLLM gateway compromise (CVE-2026-40217, CVE-2026-42271)
-
-CVE-2026-40217 exposes LiteLLM's guardrail sandbox via `exec()` with no
-source filtering. CVE-2026-42271 (exploited in the wild, added to CISA's
-KEV catalog) lets callers spawn subprocesses through MCP preview
-endpoints. The threat extends to any agent routed through a compromised
-LiteLLM proxy: the proxy can swap model responses for forged tool calls
-in transit, giving the attacker a reverse shell from the developer's
-machine.
-
-## HN community opinion clusters
-
-**"Move enforcement to the kernel, not the app"** — the Nono Show HN
-([#46849615](https://news.ycombinator.com/item?id=46849615)) and a
-kernel-sandbox thread
-([#47066574](https://news.ycombinator.com/item?id=47066574)) both argued
-that application-layer sandboxes are inherently bypassable by the code
-they're sandboxing. The academic framing, from *Red-Teaming the Agentic
-Red-Team* ([arXiv 2606.24496](https://arxiv.org/pdf/2606.24496)):
-"enforcement should occur at the OS level via the kernel refusing system
-calls that violate policy at runtime — not pre-execution argument
-validation in tool calls."
-
-**"The harness belongs outside the sandbox"** — a May thread
-([#47990675](https://news.ycombinator.com/item?id=47990675)) converged
-on clean architectural separation: harness in one VM, tool execution in
-another. Top comment: "having the harness in one VM, and tool use applied
-to user data in another, is about as safe as you can be at present."
-Several replies described a hypervisor-like policy layer — sitting outside
-both VMs — as the right long-term model.
-
-**"Sandboxes are too coarse-grained"** — a Feb thread
-([#47006445](https://news.ycombinator.com/item?id=47006445)) argued
-that VMs don't answer the real question: knowing whether an agent
-*should* be sending an email or making a transaction. "Everything's just
-in the same big box." This framing picked up traction through June–July
-as the trusted-channel attacks dominated.
-
-**"MCP's trust model is the real problem"** — the month's recurring
-theme. MCP by design gives agents access to authorized external services.
-Once a trusted channel delivers a malicious payload, filesystem sandboxing
-is irrelevant. The community call: treat all MCP tool metadata and return
-values as untrusted input subject to policy validation before ingestion,
-and disable automatic MCP server loading from untrusted repositories.
-
-## How bot-bottle addresses these issues
-
-### What it covers well
-
-**Direct sandbox escape (CVEs, container breakout)**
-
-bot-bottle's default backends are Firecracker microVM (KVM Linux) and
-Apple Container (macOS). Both run the agent in a separate VM with a
-dedicated kernel — the container-escape CVE class (Dirty Pipe, runc
-escapes, DuneSlide's path-parameter abuse) requires escaping a real
-hypervisor boundary, not just a namespace. On the legacy Docker backend,
-gVisor auto-detection provides a userspace syscall barrier for hosts where
-neither KVM nor Apple Container is available.
-
-The bot-bottle process itself runs entirely on the host, outside the VM.
-This is the "harness outside the sandbox" architecture the HN thread
-converged on as best practice. The bottle manifest, egress rules, and
-secrets never enter the agent VM.
-
-**Credential theft on sandbox escape**
-
-Even on a successful VM/container escape, the agent has nothing useful
-to steal. Credentials are injected in-flight by the gateway proxy
-(`auth.scheme` / `auth.token_ref` in the egress route config) — `printenv`
-inside the agent shows proxy URLs only. The git-gate similarly holds the
-upstream SSH credential on the host; the agent pushes through a
-gitleaks-scanned daemon that forwards clean refs upstream. An escaped
-agent gets the host filesystem, not the keys.
-
-**Orphaned-agent credential risk**
-
-bot-bottle is explicitly ephemeral: when the agent exits, `cli.py` tears
-down every gateway and both networks — nothing persists between runs. The
-agent never holds credentials, so there is nothing to orphan.
-
-**MCP config redirection / STDIO auto-registration**
-
-The trust boundary at `$HOME` means bottles live only under
-`~/.bot-bottle/bottles/` — a cloned repo cannot add egress routes or
-redirect env vars to attacker hosts (the design rationale is in
-`docs/prds/0011-per-file-md-manifest.md`). Auto-registering a malicious
-MCP STDIO server from within the agent is still sandboxed by the VM, and
-any outbound calls from that server must pass the egress allowlist and
-outbound DLP scanner.
-
-**Per-agent role tailoring (the "coarse-grained sandbox" complaint)**
-
-The Feb 2026 HN thread that argued "sandboxes are too coarse-grained"
-was pointing at a real gap: a VM isolates the filesystem but doesn't
-know whether an agent *should* be sending email or calling an external
-API. bot-bottle's bottle/agent split is a structural answer at the
-network layer — the bottle manifest declares exactly what each role can
-reach (which hosts, which paths, which HTTP methods), and the egress
-scanner enforces it. A `gitea-dev` bottle that only lists
-`gitea.dideric.is` and `api.anthropic.com` structurally cannot send
-email or reach AWS, not because the model was told not to, but because
-those routes don't exist.
-
-The `extends:` composition model means provider-level policy (the Claude
-auth route) lives in one base bottle and role-specific overlays are
-stacked on top — no duplication, and changing the base propagates to all
-derived roles.
-
-Competitive position on this axis (from `agent-sandbox-landscape.md`):
-
-| Tool | Agent-tailored policy |
-|---|---|
-| **bot-bottle** | Yes — declarative per-role manifest; `extends:` composition; egress + credentials scoped to role |
-| **tilde.run** | Yes — per-agent DSL RBAC (allow/deny/approve per action/repo/agent), but hosted SaaS |
-| **Microsoft AGT** | Yes — YAML policy + per-agent DID + trust score, but tool-call level only (no network isolation) |
-| **OAP** | Yes — declarative pre-action policy + cryptographic audit, but no isolation |
-| **Cleanroom** | Partial — per-repo `cleanroom.yaml`, not per-role |
-| **Docker sbx** | No — network presets only |
-| **Anthropic srt** | No — programmatic per-invocation |
-| **matchlock / smolmachines / microsandbox** | No |
-| **agent-safehouse** | Partial — per-agent Seatbelt profiles; no egress |
-
-Two takeaways: bot-bottle and tilde.run are the only isolation tools
-with declarative role-tailored policy; Microsoft AGT and OAP are the
-closest competitors on role-tailoring but operate at the tool-call layer
-without network/filesystem isolation — complementary, not substitutes.
-
-**Outbound exfiltration (any injection class)**
-
-Whatever triggers the agent — README injection, Agentjacking, MCP
-description poisoning — the final step in most attacks is exfiltration.
-bot-bottle's egress allowlist is default-deny with a per-bottle host
-allowlist; unknown hosts get a hard 403. Outbound DLP scanning
-(`outbound_detectors: [token_patterns, known_secrets]`) catches tokens
-and secrets in outbound bodies; the `supervise` policy (default for
-manifest routes) holds the request for operator approval rather than
-silently blocking it. Together these limit what a successful injection
-can *do* even if it succeeds at the model layer.
-
-**LiteLLM / compromised-proxy attacks**
-
-bot-bottle does not use LiteLLM. The model API route (e.g.
-`api.anthropic.com`) is an auto-injected provider route on the egress
-allowlist; the agent dials the gateway, not the model API directly.
-A compromised third-party proxy is not in the architecture.
-
-### Where it is weaker
-
-**Prompt injection**
-
-Egress controls and prompt injection defenses are orthogonal. Egress
-limits what the agent can *send out* (outbound leg); prompt injection
-is about what attacker-controlled data *tells the agent to do* (inbound
-leg). The two don't substitute for each other and must be treated
-separately.
-
-The inbound DLP scanner (`inbound_detectors: [naive_injection_detection]`)
-is the only runtime defense against injection arriving through allowlisted
-channels — Sentry MCP responses, MCP tool descriptions, README content.
-It is explicitly pattern-matching and will not catch a sufficiently
-crafted payload. There is no semantic / intent-level gate between what
-the model decides and what the agent executes.
-
-**Blast radius within the permitted scope**
-
-Inside a tightly-egressed sandbox a successful injection can't
-exfiltrate to unknown hosts, but it still has real options:
-
-- *Work product corruption.* The agent can modify, delete, or backdoor
-  files in the working directory. This is within its permitted scope;
-  egress controls have nothing to say about it.
-
-- *Malicious commits past the git-gate.* The git-gate scans outbound
-  refs for secrets (gitleaks), not for semantic code intent. A prompt-
-  injected agent can commit subtly malicious code — logic bombs,
-  backdoored auth paths, code that exfiltrates data through the
-  application's own HTTP clients at runtime — that looks clean to a
-  secret scanner.
-
-- *Exfiltration through allowlisted channels.* If an attacker knows or
-  can predict what hosts are in the egress allowlist, those channels are
-  available for exfiltration. A GitHub remote being allowlisted means
-  "push to an attacker-controlled fork" is viable. A logging endpoint
-  being allowlisted means structured data can leave through it. The
-  outbound DLP scanner catches credential tokens and known secrets but
-  not arbitrary business data.
-
-- *Dependency installation within the sandbox.* An agent that runs
-  `npm install` or `pip install` on attacker-specified packages executes
-  code inside the sandbox with the same capabilities the agent has:
-  filesystem access, tool calls, calls to allowlisted hosts. Supply chain
-  injection via package names is in the same injection family, triggered
-  by the same prompt-injection path.
-
-### What would close the remaining gaps
-
-The blast-radius risks above point at two distinct mitigations that
-don't yet exist in bot-bottle:
-
-- *Outbound intent classification.* The egress addon today scans
-  outbound request content for token patterns. What it lacks is
-  awareness of context — it can't distinguish "agent is pushing a
-  legitimate commit" from "agent was injected and is pushing a backdoor."
-  The `supervise` policy is already the right shape for human-in-the-loop
-  review on sensitive outbound actions; extending it with context from
-  the agent's recent tool calls (what files were touched, what was the
-  triggering task) would narrow the gap.
-
-- *Semantic code review on git push.* gitleaks is the wrong tool for
-  catching injected logic. A review step on outbound commits — even a
-  simple diff summary surfaced in `cli.py supervise` before the push is
-  forwarded — would close the malicious-commit path without requiring
-  the agent to be fully trusted.
-
-## Sources
-
-- [Ask HN: The new wave of AI agent sandboxes? (Mar 2026)](https://news.ycombinator.com/item?id=47444917)
-- [OK, let's survey how everybody is sandboxing AI coding agents (Mar 2026)](https://news.ycombinator.com/item?id=47185250)
-- [The agent harness belongs outside the sandbox (May 2026)](https://news.ycombinator.com/item?id=47990675)
-- [Show HN: Nono – Kernel-enforced sandboxing for AI agents (Feb 2026)](https://news.ycombinator.com/item?id=46849615)
-- [Kernel-enforced sandbox for AI agents, MCP and LLM workloads (Feb 2026)](https://news.ycombinator.com/item?id=47066574)
-- [Sandboxes will be left in 2026 (Feb 2026)](https://news.ycombinator.com/item?id=47006445)
-- [Critical Cursor Flaws / DuneSlide – The Hacker News](https://thehackernews.com/2026/07/critical-cursor-flaws-could-let-prompt.html)
-- [Agentjacking Attack – The Hacker News](https://thehackernews.com/2026/06/agentjacking-attack-tricks-ai-coding.html)
-- [Friendly Fire: AI Agents Built to Catch Malicious Code – The Hacker News](https://thehackernews.com/2026/07/friendly-fire-ai-agents-built-to-catch.html)
-- [Microsoft Warns Poisoned MCP Tool Descriptions – The Hacker News](https://thehackernews.com/2026/06/microsoft-warns-poisoned-mcp-tool.html)
-- [MCP STDIO Command Injection Advisory – OX Security](https://www.ox.security/blog/mcp-supply-chain-advisory-rce-vulnerabilities-across-the-ai-ecosystem/)
-- [LiteLLM Vulnerability Chain – The Hacker News](https://thehackernews.com/2026/06/litellm-vulnerability-chain-lets-low.html)
-- [Red-Teaming the Agentic Red-Team (arXiv 2606.24496)](https://arxiv.org/pdf/2606.24496)

docs/research/landscape-containerized-claude.md

@@ -0,0 +1,182 @@
+# Landscape: containerized AI coding agent tools
+
+Research into whether bot-bottle is redundant with existing projects, and
+whether it's worth publishing.
+
+## Summary
+
+The "AI coding agents in isolated sandboxes" space is active but not saturated.
+bot-bottle occupies a distinct position: no surveyed project combines all five
+of its defining features. Publishing is likely worthwhile, with the main risk
+being claudebox expanding to absorb the same niche.
+
+**Updated 2026-07-09:** bot-bottle now supports three isolation backends
+(Docker, Apple `container`, smolmachines/libkrun microVMs) and three built-in
+agent providers (Claude Code, OpenAI Codex, Pi) with an open plugin system for
+arbitrary providers. This meaningfully strengthens the differentiation against
+all surveyed competitors.
+
+## Closest competitor: claudebox
+
+[RchGrav/claudebox](https://github.com/RchGrav/claudebox) is the most
+feature-complete analog. It runs Claude Code in Docker with per-project
+isolated images, 15+ pre-configured dev-language profiles, and per-project
+network firewall allowlists. Actively maintained with multiple forks.
+
+What it lacks: manifest-driven named agents, per-agent env resolution modes
+(prompt / host-forward / literal), skill directory injection, per-agent system
+prompts, SSH-agent forwarding without copying private keys, home+project
+manifest merge.
+
+## Other surveyed projects
+
+- **textcortex/claude-code-sandbox → spritz** — evolved toward
+  Kubernetes-native multi-agent infra; not stdlib-first or local-Docker.
+  Original sandbox repo is archived.
+- **trailofbits/claude-code-devcontainer** — devcontainer config for security
+  audits; not a general agent launcher.
+- **Several small solo repos** (arezi/claude-sandbox, nkrefman/claude-sandbox,
+  VishalJ99/claude-docker) — lightweight Docker wrappers with no multi-agent
+  config layer.
+- **Docker's official sandbox templates** — launch-and-run Dockerfiles plus an
+  npm-based runtime; not a manifest-driven fleet manager.
+
+## Adjacent (different model)
+
+- **dagger/container-use** (mid-2025) — exposes an MCP server so the *agent*
+  spins up its own containers with Git worktrees. Inverted model vs. bot-bottle
+  (agent controls container rather than being launched into one by a manifest).
+  Still marked early-development.
+- **E2B, Northflank, Cloudflare Sandbox SDK** — cloud-hosted SaaS sandbox
+  runtimes; fundamentally different architecture.
+- **superhq.ai / SuperHQ** (v0.4.4, April 2026) — macOS desktop app (Rust/GPUI)
+  that runs Claude Code, Codex, and Pi inside microVMs via Apple's
+  Virtualization.framework (their own shuru-sdk / libkrun). Auth gateway
+  injects API keys on the wire so the sandbox never sees them; tmpfs overlay
+  stages agent writes for diff-and-accept review; mobile remote access via
+  remote.superhq.ai. Early alpha, free on launch, Apple Silicon only.
+
+  Overlap: both projects cover agent isolation, credential proxying, and
+  multi-provider support (Claude Code / Codex / Pi). Differences: SuperHQ is a
+  GUI desktop app with no manifest layer; bot-bottle is a CLI fleet manager with
+  named agents, skills injection, per-agent system prompts, and cross-platform
+  backends (Docker, Apple `container`, smolmachines). SuperHQ's microVM
+  isolation story is now partially matched by bot-bottle's `macos_container` and
+  smolmachines backends. Worth watching — it targets the same security-minded
+  power-user audience and moves fast.
+
+  **Known gap in SuperHQ (user-requested, as of 2026-07-09):** A named user
+  (Brian Cheong, Founder, Dunialabs.io) explicitly called out the absence of
+  per-run audit logging: tool calls and network egress. Bot-bottle covers both:
+  network egress is logged by pipelock/mitmproxy, and per-run op-log/audit state
+  is persisted to SQLite.
+
+- **OneCLI** ([onecli.sh](https://onecli.sh/)) — YC-backed, GA, open-source
+  (Apache-2.0, Rust) "identity gateway for AI agents": a credential/secret
+  broker that holds API keys and OAuth tokens out of the agent's reach and
+  injects them at the network layer (phantom-token — the agent sees a
+  placeholder, the gateway swaps in the real, AES-256-GCM-encrypted credential
+  at request time). Framework-agnostic and drop-in for any HTTP-calling agent,
+  50+ app integrations, plus a hosted cloud tier with a per-agent dashboard and
+  audit logs. Full technical breakdown in
+  [`agent-credential-proxy-landscape.md`](agent-credential-proxy-landscape.md).
+
+  **How close a competitor:** near-exact on the *single axis of agent secret
+  custody* — the exact thing bot-bottle sells as "the agent never sees real
+  credentials, even via `printenv`." OneCLI does that one job well, is mature
+  and funded, and is *more portable* (it sits in front of anything; bot-bottle
+  only helps agents launched through bot-bottle). Takeaway: bot-bottle should
+  stop treating secret custody as a *unique* differentiator. But OneCLI is
+  **not** a competitor to bot-bottle's actual product — it does no agent
+  sandboxing (containers/microVMs), no fleet/manifest layer, no named agents /
+  skills / per-agent system prompts, no multi-provider launching, no egress
+  firewall.
+
+  **Our edge:** (1) *Isolation is the product, not a proxy.* OneCLI keeps the
+  key out of reach at the network layer, but the agent itself still runs
+  unsandboxed — a hijacked agent behind OneCLI has full run of its host and can
+  exfil captured data through any allowed host. bot-bottle runs the agent inside
+  a kernel/VM-enforced sandbox, injects credentials across that same
+  out-of-process boundary, *and* clamps egress with pipelock — defense in depth
+  vs. a single network layer. (2) *Fleet + manifest model* with named agents,
+  skills, per-agent system prompts, multi-provider and multi-backend — OneCLI
+  has no equivalent. (3) *Trust posture:* OneCLI's managed tier reintroduces a
+  third-party credential custodian, whereas bot-bottle's OSS-runtime +
+  paid-control-plane split keeps custody inside the operator's own boundary —
+  the stronger story for the security-minded self-hoster. (4) *Runs inside your
+  network boundary — local/internal reach.* Because bot-bottle executes the
+  agent on your own host (homelab, corporate LAN, a Tailnet) and egress is a
+  manifest field, giving an agent *scoped* access to **internal** resources — a
+  private Gitea, a LAN database, a Tailscale node — is just another egress-route
+  line, not a networking project (the same move an operator already makes to
+  reach their Tailscale services). OneCLI's OSS core can self-host too, but it's
+  a credential *broker* for outbound API calls, not an agent runtime, and its
+  managed tier + 50+ integrations are oriented at public SaaS — it doesn't put
+  the agent behind your firewall for you. This is a reach advantage, distinct
+  from the isolation ones above, and it's a wedge cloud-first agent products
+  (Devin, Copilot Workspace, OneCLI Cloud) structurally can't match. **Tactical
+  read:**
+  adopt OneCLI's OSS core for the credential slice if building is undesirable
+  (it's mature now); don't build atop its managed tier (competitor, not
+  dependency); re-position bot-bottle on isolation + fleet + self-hosted custody
+  rather than "we hide your secrets."
+
+## What no found project does
+
+None combine:
+1. Named-agent manifest with per-agent env resolution (prompt / host-forward / literal), supporting multiple providers (Claude Code, Codex, Pi, arbitrary plugins)
+2. Skills directory injection
+3. Per-agent system prompts
+4. SSH-agent key forwarding without copying private keys into the container
+5. Home + project manifest merge
+6. Pluggable isolation backends: Docker (Linux/macOS), Apple `container` (macOS microVMs), smolmachines/libkrun microVMs
+7. Per-run audit log: network egress via pipelock/mitmproxy + op-log persisted to SQLite
+
+**In-flight directions (not yet shipped):**
+
+- **Forge-native dispatch (issue #317):** Gitea webhook → orchestrator spins up a bottle
+  with the issue body as prompt → agent works → bottle freezes awaiting review comment →
+  rehydrates on comment → tears down on PR close. The issue-to-PR lifecycle concept is not
+  novel (Devin, Copilot Workspace, SWE-agent all do this as cloud services); what's
+  distinct is doing it self-hosted, manifest-driven, inside bot-bottle's isolation
+  primitives.
+- **Paid web control plane (issue #327):** Browser-based multi-host agent launch and
+  monitoring; account-scoped bottle and agent definitions; secret custody (encrypted at
+  rest, injected into the sidecar at launch, never exposed to the agent or returned by any
+  read API). Monetization model: OSS runtime free, control plane paid — a standard split
+  (HashiCorp, Grafana) applied to a self-hosted agent sandbox. The principled secret
+  custody model (agent never sees real credentials, even via printenv) is more rigorous
+  than most surveyed tools but not unprecedented.
+
+## Publishing verdict
+
+Worth publishing. Differentiators that matter to the target audience (power
+users running parallel AI coding agent sessions with distinct personas/tooling):
+
+- The Python-stdlib-first, low-dependency design — competitors are npm-based,
+  Rust/GUI, or Kubernetes-native.
+- Named agents with distinct skills and system prompts, not just language profiles.
+- Multi-backend isolation: Docker, Apple `container` microVMs, and
+  smolmachines/libkrun — single manifest works across all three.
+- Multi-provider: Claude Code, Codex, Pi, plus an open plugin system for
+  arbitrary providers.
+- SSH forwarding without key copying.
+- Per-run audit log (tool calls + network egress) — an explicitly requested gap
+  in SuperHQ as of 2026-07-09.
+- Forge-native dispatch and a paid control plane (in flight) bring bot-bottle
+  into the same product category as cloud services like Devin and Copilot
+  Workspace — but self-hosted, with stronger isolation guarantees and a
+  manifest-driven fleet model those services don't have.
+
+Main risk: claudebox adds manifest/agent config; SuperHQ is moving fast on the
+GUI / microVM side. The space is moving fast enough that publishing sooner is
+better if establishing prior art matters.
+
+Discovery will be slow without active promotion; an Anthropic Discord post or
+HN "Show HN" would do most of the work.
+
+## Caveats
+
+- GitHub search cannot surface private or very new repos comprehensively.
+- Counts (stars, forks) were not confirmed for every project.
+- Initial research conducted 2026-05-07; SuperHQ entry added 2026-07-09; the space moves fast.

docs/research/malicious-commit-scanning.md

@@ -1,204 +0,0 @@
-# Scanning for malicious commits at the git-gate — and whether the semantic layer is a paid feature
-
-A sandboxed agent's most durable way out isn't live exfiltration — it's the
-**artifact it pushes**. Code committed through the git-gate leaves the
-sandbox and runs *later*, in CI or production, with none of the bottle's
-isolation or egress control. gitleaks covers *secrets* on that channel
-(see [`git-gate` pre-receive](../../bot_bottle/git_gate_render.py)); this
-note asks the harder question — can we scan for *malicious code* in
-commits — and the product question the answer raises: is the semantic
-(LLM) layer a decent paid feature on "git egress," alongside a paid
-human-review console for the supervise flow?
-
-## Summary
-
-- **No scanner reliably detects malicious code.** It's undecidable in
-  general and adversarial in practice — a capable agent hides a backdoor
-  from any pattern scanner (and from human reviewers). So the frame is not
-  "detect malice"; it's **raise the cost, cover the common/obvious cases,
-  and put a human on the high-leverage ones.**
-- **Layered, ranked by ROI:** (1) supply-chain / malicious-dependency
-  scanning (Socket, OSV-Scanner, GuardDog) — highest ROI, best git fit;
-  (2) fast heuristic / obfuscation / dangerous-sink scanning
-  (Semgrep-on-diff) — gitleaks-shaped; (3) **risk-based human gating** via
-  the existing supervise plane on high-risk file classes; (4) **LLM
-  semantic diff-review** as a best-effort backstop for novel backdoors.
-- **Architecture:** the git-gate's `pre-receive` is *synchronous* (it
-  blocks the push), so run only fast scanners inline and push heavy
-  analysis (CodeQL, full LLM review) to an **async post-push CI lane** that
-  can't hold the developer hostage.
-- **Monetization verdict: yes — but the paid unit is the *governed
-  git-egress review bundle*, not the raw scanner.** The pre-receive
-  mechanics and the fast OSS scanners stay free (open-core social
-  contract, same as gitleaks). The sell is the control-plane workflow
-  around them: **managed semantic review + a web-console human-review flow
-  + RBAC + audit retention + cross-run policy.** A bare per-push scan is
-  borderline "single-run = free" by our own heuristic, and its detection
-  accuracy is not something to sell on. Sell the *workflow and the
-  governance*, not the detector.
-
-## The threat: temporal escape
-
-This is the one containment fundamentally can't close. bot-bottle's VM
-isolation + egress DLP shrink *live* exfiltration, but the git push
-channel launders a payload past all of it: the agent commits code that
-looks benign at review time and does its work later, outside the
-perimeter — the "blind-XSS"-style temporal escape that both the "3 reasons
-sandboxing won't secure your AI agent" talk and Embroidery's "In sandboxes
-we (shouldn't) trust" call the sharpest gap. gitleaks gates *secrets* on
-this channel; malicious *code* is the uncovered surface, and it's the
-behavioral half of the isolation-vs-behavioral split noted in
-[`agent-sandbox-landscape.md`](agent-sandbox-landscape.md).
-
-## Why it's fundamentally hard
-
-Distinguishing malicious from legitimate code is undecidable in general
-and adversarial in the specific. The underhanded-code contests show humans
-hide backdoors from *human reviewers*; a scanner reduces to regex/dataflow
-heuristics a motivated agent writes around. So "catch malicious commits"
-is the wrong success metric. The right ones: *how much did we raise the
-cost*, *did we cover the common and the obvious*, and *did a human see the
-dangerous changes before they left*.
-
-## Landscape of git-pluggable approaches (ranked by ROI)
-
-1. **Supply-chain / malicious-dependency scanning — highest ROI.** The
-   most likely agent-introduced threat is a malicious or typosquatted
-   *dependency*, not a hand-written backdoor — and it's far more
-   detectable. **Socket** (behavioral analysis of packages: install
-   scripts, obfuscation, unexpected network/fs access, typosquats) is the
-   closest thing to malicious-intent detection that actually works;
-   **OSV-Scanner** (known-bad DB, fast) and **GuardDog** (PyPI/npm
-   heuristics) complement it. Trigger only when a commit changes a
-   lockfile/manifest → block or escalate.
-2. **Fast heuristic / obfuscation / dangerous-sink scanning.** **Semgrep**
-   with a curated ruleset, scanning the *diff* (fast enough for
-   pre-receive). Catches obfuscation (`eval(atob(...))`, base64/hex blobs,
-   minified source), exfil primitives (`curl | sh`, reverse shells,
-   DNS-exfil), and dangerous sinks (`shell=True`, `pickle.loads`, unsafe
-   `yaml.load`, `child_process.exec`). Tune noisy rules to *escalate*, not
-   block.
-3. **Risk-based human gating — the most robust control, already
-   half-built.** The git-gate already escalates `# gitleaks:allow`
-   findings to a supervisor proposal and blocks the push pending approval
-   (`supervise_gitleaks_allow`, [`git_gate_render.py`](../../bot_bottle/git_gate_render.py)).
-   Extend the same flow to **high-risk file classes**: any commit touching
-   CI/build/deploy scripts, auth/crypto code, egress config, or
-   adding/changing dependencies → route to `./cli.py supervise`. This is
-   attribution/policy, not detection, and it's the strongest thing here —
-   a human on exactly the temporal-escape surfaces.
-4. **LLM semantic diff-review — the behavioral backstop.** The only
-   approach with a shot at a novel, benign-looking backdoor: a model
-   reviews the diff for a backdoor / exfiltration / obfuscated payload /
-   dangerous behavior. This is the behavioral-detection thesis applied to
-   the *artifact* (the diff) rather than the agent's reasoning. Real
-   caveats: false positives and negatives, latency/cost, it can be
-   prompt-injected by hostile content *in the diff itself*, and it invites
-   over-trust. Useful, never a guarantee.
-
-**Not for this job:** CodeQL, Trivy, Grype, Bandit. They find *known
-vulns and insecure patterns* (bugs), not deliberate backdoors, and the
-powerful ones (CodeQL taint) need a build + database — too heavy for a
-synchronous gate. They belong in the async CI lane if at all.
-
-## Fit into bot-bottle's git-gate
-
-The `pre-receive` hook today is: gitleaks-scan each ref → escalate
-`# gitleaks:allow` findings to supervise → forward to upstream
-([`git_gate_render.py`](../../bot_bottle/git_gate_render.py)). The
-additions slot in cleanly:
-
-- **Inline (fast), before forward:** a dep-scan phase (on manifest/lockfile
-  change) and a Semgrep-diff phase. Findings block or open a supervise
-  proposal, same shape as gitleaks.
-- **New supervise tool types** alongside the existing
-  `egress-block/allow`, `gitleaks-allow`, `egress-token-allow`
-  ([`supervise_types.py`](../../bot_bottle/supervise_types.py)) — e.g. a
-  `commit-review` proposal for risky-file-class gating and for semantic
-  review. The supervise plane is already the right abstraction; this is
-  another *producer* feeding it, and [`supervise_server.py`](../../bot_bottle/supervise_server.py)
-  (JSON-RPC) is already the console backend.
-- **Async lane (heavy):** full LLM review + any CodeQL run out of band
-  after the push, feeding the same review/audit surface, so the
-  synchronous gate stays fast.
-
-## The product question: paid feature on git egress?
-
-Restating the open-core line bot-bottle runs on: *give away the
-sandbox/runtime, charge for the control plane; single-run/single-node =
-free, cross-run aggregation + central enforcement + identity/fleet = paid;
-the moat is uniform egress audit + secret custody + policy across
-untrusted agents.*
-
-Against that line, the split is clean:
-
-**Free (OSS runtime — the trust funnel):**
-- the `pre-receive` gate mechanics and gitleaks;
-- wiring the OSS scanners (Socket CLI / OSV-Scanner / Semgrep);
-- the CLI supervise flow.
-Keeping the raw scanners free is the same social contract as gitleaks and
-preserves the bottom-up distribution funnel.
-
-**Paid (the governed git-egress bundle — the control plane):**
-- **Managed semantic diff-review** — hosted inference + a curated,
-  maintained malicious-pattern/policy set. This is *capability* (metered),
-  not *insurance* — the thing individuals actually pay for. Position it as
-  **governed code-egress review**, not "we resell inference" (the
-  monetization notes explicitly warn against reselling compute).
-- **The web-console supervise/review flow — the strongest anchor.** Turn
-  the CLI `./cli.py supervise` approval into a real review surface:
-  rendered diff + finding context, approve/reject, **who-approved audit
-  trail, RBAC on approvers, mobile/phone-control** (ties to the
-  dashboard/vault north star). This is "central enforcement +
-  identity/fleet = paid" almost verbatim — and it generalizes across
-  *every* supervise proposal (egress block/allow, gitleaks-allow,
-  commit-review), so it's worth building for the whole plane, with the
-  semantic check as one producer.
-- **Cross-run governance:** fleet-wide policy for what escalates,
-  review-decision history/search/export, and drift alerts.
-
-**Why it fits the moat rather than bolting on:** a git push *is* an egress
-channel. A semantic review + human approval + audit on it extends the
-uniform "egress audit + custody + policy across untrusted agents" wedge to
-**code artifacts** — the same product, applied to the one channel gitleaks
-only half-covers. That's on-moat, not a detour.
-
-**The honest nuance (don't oversell):** a bare per-push LLM scan is
-arguably *free* by the single-run heuristic, and its detection accuracy is
-not defensible to charge for. The paid value is the **governance around
-it** — the console, RBAC, audit retention, cross-run policy — plus the
-managed capability. Sell the *review-and-approve-and-audit workflow*; let
-the detector be explicitly best-effort. And per the monetization
-guardrail, the "anti-corporate" free crowd must not veto these team
-features: the review console + RBAC + audit *are* the monetization.
-
-## Recommendation
-
-1. **Land the free layer first.** Add the dep-scan and Semgrep-diff phases
-   to `pre-receive`, and extend supervise to risky-file-class gating —
-   reuses existing machinery, immediate value, stays OSS.
-2. **Build the supervise web console** over `supervise_server`'s JSON-RPC
-   (already the Phase-1 move in the monetization path). This is the paid
-   anchor and it serves *all* proposal types, not just commit review.
-3. **Add managed semantic diff-review as a paid producer** feeding that
-   console — "governed code-egress review," metered, explicitly
-   best-effort on detection.
-4. **Don't oversell detection.** Market the workflow (review + approve +
-   audit) and the cross-run policy/RBAC, where the value is real and
-   defensible; keep the raw scanners open.
-
-## Sources / references
-
-- [`agent-sandbox-landscape.md`](agent-sandbox-landscape.md) — the
-  egress-DLP gap and isolation-vs-behavioral framing.
-- Git-gate internals: [`git_gate_render.py`](../../bot_bottle/git_gate_render.py),
-  [`supervise_types.py`](../../bot_bottle/supervise_types.py),
-  [`supervise_server.py`](../../bot_bottle/supervise_server.py).
-- External tools: Socket (socket.dev), OSV-Scanner (google/osv-scanner),
-  GuardDog (DataDog/guarddog), Semgrep (semgrep/semgrep).
-- Threat framing: "3 reasons sandboxing won't secure your AI agent"
-  (youtube TsYDazwHJ6U); Embroidery, "In sandboxes we (shouldn't) trust."
-- The authoritative monetization/positioning analysis (the open-core line,
-  the wedge, single-run-free/cross-run-paid) lives in the **separate
-  `bot-bottle-console` repo**, not this one — cited here from memory, not
-  linked.

docs/research/rootless-docker-in-apple-container-spike.md

@@ -1,353 +0,0 @@
-# Rootless Docker inside Apple Container bottles
-
-Spike branch: `spike/rootless-docker-macos` (`a4d8461`)
-
-## 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 `docker_access` 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.

docs/research/smolmachines-as-vm-backend.md

@@ -1,6 +1,6 @@
 # smolmachines as a VM backend for bot-bottle
 
-> **Superseded (2026-07-11).** The smolmachines backend was removed — Linux now uses the Firecracker backend, macOS uses macos-container. Kept as a historical record; see the removal commit `c07ebca` and `docs/research/agent-sandbox-landscape.md`.
+> **Superseded (2026-07-11).** The smolmachines backend was removed — Linux now uses the Firecracker backend, macOS uses macos-container. Kept as a historical record; see the removal commit `c07ebca` and `docs/research/landscape-containerized-claude.md`.
 
 Evaluation of whether [smolmachines](https://smolmachines.com/) would
 simplify the macOS agent-VM-isolation work spelled out in

pyproject.toml

@@ -1,8 +0,0 @@
-[build-system]
-requires = ["setuptools>=68"]
-build-backend = "setuptools.build_meta"
-
-[project]
-name = "bot-bottle"
-version = "0.0.0"
-requires-python = ">=3.11"

scripts/coverage.sh

@@ -26,10 +26,8 @@ rm -f .coverage
 echo "== unit ==" >&2
 "$PY" -m coverage run -m unittest discover -t . -s tests/unit
 
-echo "== integration (firecracker; skips docker tests) ==" >&2
+echo "== integration (skips without Docker) ==" >&2
-BOT_BOTTLE_BACKEND=firecracker SKIP_DOCKER_TESTS=1 \
+"$PY" -m coverage run --append -m unittest discover -t . -s tests/integration
-    BOT_BOTTLE_INFRA_ARTIFACT_DIR="${BOT_BOTTLE_CI_INFRA_ARTIFACT_DIR:-}" \
-    "$PY" -m coverage run --append -m unittest discover -t . -s tests/integration
 
 echo "== combined report ==" >&2
 "$PY" -m coverage report -m

tests/_bin.py

@@ -1,23 +0,0 @@
-"""Resolved paths to system binaries used by subprocess-based tests.
-
-NixOS and other non-FHS hosts don't populate ``/bin`` (there is no
-``/bin/sleep``), so tests that spawn real short-lived helper processes
-must resolve the binary from ``PATH`` rather than hardcoding an FHS path.
-Import the resolved constant (e.g. ``SLEEP``) instead of writing
-``/bin/sleep`` inline.
-"""
-
-from __future__ import annotations
-
-import shutil
-
-
-def resolve(name: str, fallback: str) -> str:
-    """Absolute path to ``name`` from ``PATH``; ``fallback`` on FHS hosts
-    where the binary isn't on ``PATH`` but lives at a known ``/bin`` path."""
-    return shutil.which(name) or fallback
-
-
-# Real ``sleep`` binary. ``/bin/sleep`` is absent on NixOS; resolve from
-# PATH so subprocess tests run instead of erroring with FileNotFoundError.
-SLEEP = resolve("sleep", "/bin/sleep")

tests/_docker.py

@@ -2,44 +2,24 @@
 
 from __future__ import annotations
 
-import os
 import shutil
 import subprocess
 import unittest
 
 
 def docker_available() -> bool:
-    if os.environ.get("SKIP_DOCKER_TESTS"):
-        return False
     if shutil.which("docker") is None:
         return False
-    try:
+    return (
-        return (
+        subprocess.run(
-            subprocess.run(
+            ["docker", "info"],
-                ["docker", "info"],
+            stdout=subprocess.DEVNULL,
-                stdout=subprocess.DEVNULL,
+            stderr=subprocess.DEVNULL,
-                stderr=subprocess.DEVNULL,
+            check=False,
-                check=False,
+        ).returncode
-                timeout=5,
+        == 0
-            ).returncode
+    )
-            == 0
-        )
-    except subprocess.TimeoutExpired:
-        return False
 
 
 def skip_unless_docker(reason: str = "docker unreachable"):
     return unittest.skipUnless(docker_available(), reason)
-
-
-def skip_unless_docker_or_firecracker(
-    reason: str = "neither Docker nor Firecracker selected",
-):
-    """Skip a backend-agnostic test unless one supported backend can run.
-
-    Firecracker does not require the host Docker daemon. The KVM coverage job
-    deliberately sets ``SKIP_DOCKER_TESTS`` to exclude Docker-only integration
-    classes while still exercising this path.
-    """
-    firecracker_selected = os.environ.get("BOT_BOTTLE_BACKEND") == "firecracker"
-    return unittest.skipUnless(firecracker_selected or docker_available(), reason)

tests/integration/test_gateway_image.py

@@ -86,12 +86,13 @@ class TestGatewayImage(unittest.TestCase):
         self.assertIn("Mitmproxy", out)
 
     def test_python_imports_supervise_module(self):
-        # The supervise daemon is installed as part of the bot_bottle
+        # The bundle's supervise daemon imports `supervise` as a
-        # package (5ad3449), not as flat sibling modules under /app.
+        # same-directory sibling of `supervise_server`. Probe the
-        # Probe that the package imports resolve inside the image.
+        # import resolves with `python3 -c` from /app (the
+        # Dockerfile's WORKDIR).
         rc, out = self._run_in_image(
             "python3", "-c",
-            "from bot_bottle import supervise, supervise_server; print('ok')",
+            "import supervise; import supervise_server; print('ok')",
         )
         self.assertEqual(0, rc, msg=out)
         self.assertIn("ok", out)

tests/integration/test_macos_rootless_podman_spike.py

@@ -1,154 +0,0 @@
-"""Live-Mac acceptance spike for guest-local rootless podman (issue #392).
-
-Run explicitly on an Apple Silicon/macOS 26 host:
-
-    BOT_BOTTLE_ROOTLESS_PODMAN_SPIKE=1 \
-      python3 -m unittest tests.integration.test_macos_rootless_podman_spike -v
-
-The opt-in is deliberate: ordinary Linux CI cannot execute Apple Container.
-
-Podman rather than Docker because Apple Container's capability bounding set
-omits CAP_SYS_ADMIN; see
-docs/research/rootless-docker-in-apple-container-spike.md.  The agent-facing
-surface is still `docker` and `docker compose`, which talk to podman's
-Docker-compatible API socket.
-"""
-
-from __future__ import annotations
-
-import os
-import platform
-import shutil
-import tempfile
-import unittest
-from pathlib import Path
-
-from bot_bottle.backend import BottleSpec, get_bottle_backend
-from bot_bottle.manifest import ManifestIndex
-
-
-@unittest.skipUnless(
-    platform.system() == "Darwin"
-    and os.environ.get("BOT_BOTTLE_ROOTLESS_PODMAN_SPIKE") == "1",
-    "requires an explicit live-Mac rootless-podman spike run",
-)
-class TestMacosRootlessPodmanSpike(unittest.TestCase):
-    def test_compose_stays_inside_registered_bottle(self) -> None:
-        workspace = Path(tempfile.mkdtemp(prefix="rootless-podman-spike."))
-        stage = Path(tempfile.mkdtemp(prefix="rootless-podman-stage."))
-        try:
-            (workspace / "index.html").write_text("bottle-compose-ok\n")
-            (workspace / "compose.yaml").write_text(
-                "services:\n"
-                "  web:\n"
-                "    image: quay.io/prometheus/busybox\n"
-                "    working_dir: /workspace\n"
-                "    command: httpd -f -p 8000 -h /workspace\n"
-                "    volumes: ['.:/workspace']\n"
-                "    ports: ['18080:8000']\n",
-                encoding="utf-8",
-            )
-            manifest = ManifestIndex.from_json_obj({
-                "bottles": {"dev": {
-                    "docker_access": True,
-                    # A deliberately tiny image. Pulling a ~165MB one
-                    # OOM-kills the shared egress proxy, which buffers whole
-                    # response bodies to scan them — a real defect, but a
-                    # separate one from what this test covers. See the
-                    # research note.
-                    #
-                    # quay.io deliberately, not Docker Hub: the egress proxy
-                    # strips agent-set Authorization (so an agent cannot
-                    # smuggle a credential out in a header), and Docker Hub
-                    # requires a client-fetched, per-scope bearer token that
-                    # the strip therefore removes. quay serves manifests with
-                    # no Authorization at all, so a plain route is enough.
-                    #
-                    # token_patterns is still scoped off: registry traffic
-                    # carries bearer JWTs by protocol and trips the generic
-                    # rule. known_secrets stays on — it matches the bottle's
-                    # own credentials, which is the detector that catches
-                    # real exfil.
-                    "egress": {"routes": [
-                        {"host": "quay.io", "dlp": {
-                            "outbound_detectors": ["known_secrets"],
-                        }},
-                        {"host": "cdn01.quay.io", "dlp": {
-                            "outbound_detectors": ["known_secrets"],
-                        }},
-                    ]},
-                }},
-                "agents": {"spike": {
-                    "bottle": "dev", "skills": [], "prompt": "",
-                }},
-            })
-            spec = BottleSpec(
-                manifest=manifest,
-                agent_name="spike",
-                copy_cwd=True,
-                user_cwd=str(workspace),
-            )
-            backend = get_bottle_backend("macos-container")
-            plan = backend.prepare(spec, stage_dir=stage)
-            with backend.launch(plan) as bottle:
-                workdir = plan.workspace_plan.workdir
-                checks = (
-                    "docker info >/dev/null && docker compose version && "
-                    f"cd {workdir} && docker compose up -d --wait && "
-                    "curl --fail --silent http://127.0.0.1:18080/ | "
-                    "grep -q bottle-compose-ok"
-                )
-                result = bottle.exec(checks)
-                self.assertEqual(
-                    0, result.returncode,
-                    f"stdout={result.stdout!r}\nstderr={result.stderr!r}",
-                )
-                # podman's compat API reports rootlessness through its own
-                # native endpoint; the Docker-shaped SecurityOptions field does
-                # not carry it.
-                inspect = bottle.exec(
-                    "podman info --format '{{.Host.Security.Rootless}}'"
-                )
-                self.assertIn("true", inspect.stdout.lower())
-                self.assertEqual(
-                    0,
-                    bottle.exec(
-                        "test \"$(id -u)\" -ne 0"
-                    ).returncode,
-                    "the podman service must not be running as bottle root",
-                )
-                self.assertNotEqual(
-                    0,
-                    bottle.exec("test -S /var/run/docker.sock").returncode,
-                    "spike must never expose a host/rootful Docker socket",
-                )
-                # Asserted on an in-band marker, not on `docker run`'s exit
-                # code: podman 4.3.1's Docker-compat API swallows the
-                # container's status and returns 0 for everything, so an
-                # exit-code assertion here passes whether egress was blocked
-                # or wide open. That silent false pass is worse than no check
-                # at all, and it is exactly this check — the one proving a
-                # nested container cannot escape the egress path.
-                #
-                # busybox ships wget, so a failure here means egress was
-                # refused rather than the binary being absent.
-                direct = bottle.exec(
-                    "docker run --rm --env HTTP_PROXY= --env HTTPS_PROXY= "
-                    "--env http_proxy= --env https_proxy= "
-                    "quay.io/prometheus/busybox sh -c "
-                    "'wget -T 4 -qO- https://evil.example.com/ "
-                    "&& echo ESCAPED || echo CONTAINED'"
-                )
-                self.assertIn(
-                    "CONTAINED", direct.stdout,
-                    "an inner container obtained direct, unproxied egress: "
-                    f"stdout={direct.stdout!r} stderr={direct.stderr!r}",
-                )
-                self.assertNotIn("ESCAPED", direct.stdout)
-        finally:
-            shutil.rmtree(workspace, ignore_errors=True)
-            shutil.rmtree(stage, ignore_errors=True)
-
-
-if __name__ == "__main__":
-    unittest.main()

tests/integration/test_sandbox_escape.py

@@ -31,7 +31,7 @@ from pathlib import Path
 from bot_bottle.backend import BottleSpec, get_bottle_backend
 from bot_bottle.bottle_state import cleanup_state
 from bot_bottle.manifest import ManifestIndex
-from tests._docker import skip_unless_docker_or_firecracker
+from tests._docker import skip_unless_docker
 
 
 # Secrets planted in the bottle env as literals (agents substitute via
@@ -67,14 +67,13 @@ _DUMMY_HOST_KEY = (
 )
 
 
-@skip_unless_docker_or_firecracker()
+@skip_unless_docker()
 @unittest.skipIf(
-    os.environ.get("GITEA_ACTIONS") == "true"
+    os.environ.get("GITEA_ACTIONS") == "true",
-    and os.environ.get("BOT_BOTTLE_BACKEND") != "firecracker",
+    "skipped under act_runner: egress_tls_init uses a host bind mount "
-    "skipped under act_runner unless BOT_BOTTLE_BACKEND=firecracker: "
+    "the runner container can't see, and the network topology hides "
-    "egress_tls_init uses a host bind mount the runner container can't "
+    "sibling-gateway visibility — same constraint as the other "
-    "see, and the network topology hides sibling-gateway visibility — "
+    "bottle-bringup integration tests",
-    "these constraints don't apply on the self-hosted KVM runner",
 )
 class TestSandboxEscape(unittest.TestCase):
     """End-to-end attacks against a real bottle. The bottle stays
@@ -91,9 +90,11 @@ class TestSandboxEscape(unittest.TestCase):
 
     @classmethod
     def setUpClass(cls) -> None:
-        # Pin Docker when BOT_BOTTLE_BACKEND is unset to preserve the
+        # Docker is always required (the agent + companion containers run under it,
-        # Docker-backed CI path. Firecracker uses its persistent infra VM for
+        # and VM backends still use it for the gateway); the
-        # the shared gateway and therefore does not require host Docker.
+        # class-level @skip_unless_docker already covers that. Pin
+        # Docker when BOT_BOTTLE_BACKEND is unset to preserve the
+        # Docker-backed CI path.
         cls._backend_name = os.environ.get("BOT_BOTTLE_BACKEND", "docker")
 
         # Throwaway static key for the git-gate fixture. It need not

tests/unit/test_backend_selection.py

@@ -40,7 +40,7 @@ class TestGetBottleBackend(unittest.TestCase):
                 return True
 
         with patch.dict(os.environ, {}, clear=True), \
-             patch.object(backend_mod, "_backends", {
+             patch.object(backend_mod, "_BACKENDS", {
                  "macos-container": _FakeBackend(),
                  "docker": _FakeBackend(),
              }):
@@ -57,16 +57,14 @@ class TestGetBottleBackend(unittest.TestCase):
                 return self._available
 
         # No macOS container and the host can't run firecracker (no
-        # KVM / not Linux) → docker fallback with a prompt. Simulate
+        # KVM / not Linux) → docker is the last resort.
-        # the user picking "d" (use docker anyway).
         with patch.dict(os.environ, {}, clear=True), \
              patch.object(backend_mod.FirecrackerBottleBackend,
                           "is_host_capable", classmethod(lambda cls: False)), \
-             patch.object(backend_mod, "_backends", {
+             patch.object(backend_mod, "_BACKENDS", {
                  "macos-container": _FakeBackend("macos-container", False),
                  "docker": _FakeBackend("docker", True),
-             }), \
+             }):
-             patch.object(backend_mod, "read_tty_line", return_value="d"):
             b = get_bottle_backend()
         self.assertEqual("docker", b.name)
 
@@ -85,7 +83,7 @@ class TestGetBottleBackend(unittest.TestCase):
         with patch.dict(os.environ, {}, clear=True), \
              patch.object(backend_mod.FirecrackerBottleBackend,
                           "is_host_capable", classmethod(lambda cls: True)), \
-             patch.object(backend_mod, "_backends", {
+             patch.object(backend_mod, "_BACKENDS", {
                  "macos-container": _FakeBackend("macos-container", False),
                  "firecracker": _FakeBackend("firecracker", False),
                  "docker": _FakeBackend("docker", True),
@@ -98,145 +96,6 @@ class TestGetBottleBackend(unittest.TestCase):
             with self.assertRaises(SystemExit):
                 get_bottle_backend("nonexistent")
 
-    def test_no_backend_available_dies(self):
-        # No VM and no docker → print install instructions and die.
-        class _FakeBackend:
-            def __init__(self, name: str, available: bool) -> None:
-                self.name = name
-                self._available = available
-
-            def is_available(self) -> bool:
-                return self._available
-
-        with patch.dict(os.environ, {}, clear=True), \
-             patch.object(backend_mod.FirecrackerBottleBackend,
-                          "is_host_capable", classmethod(lambda cls: False)), \
-             patch.object(backend_mod, "_backends", {
-                 "macos-container": _FakeBackend("macos-container", False),
-                 "docker": _FakeBackend("docker", False),
-             }), \
-             patch.object(backend_mod, "die", side_effect=SystemExit("die")):
-            with self.assertRaises(SystemExit):
-                get_bottle_backend()
-
-    def test_docker_fallback_user_quits(self):
-        # VM unavailable, docker available, user picks "q" → die.
-        class _FakeBackend:
-            def __init__(self, name: str, available: bool) -> None:
-                self.name = name
-                self._available = available
-
-            def is_available(self) -> bool:
-                return self._available
-
-        with patch.dict(os.environ, {}, clear=True), \
-             patch.object(backend_mod.FirecrackerBottleBackend,
-                          "is_host_capable", classmethod(lambda cls: False)), \
-             patch.object(backend_mod, "_backends", {
-                 "macos-container": _FakeBackend("macos-container", False),
-                 "docker": _FakeBackend("docker", True),
-             }), \
-             patch.object(backend_mod, "read_tty_line", return_value="q"), \
-             patch.object(backend_mod, "die", side_effect=SystemExit("die")):
-            with self.assertRaises(SystemExit):
-                get_bottle_backend()
-
-
-    def test_docker_fallback_non_interactive_dies(self):
-        # prompt=False: headless/CI contexts must not block on a TTY read.
-        class _FakeBackend:
-            def __init__(self, name: str, available: bool) -> None:
-                self.name = name
-                self._available = available
-
-            def is_available(self) -> bool:
-                return self._available
-
-        with patch.dict(os.environ, {}, clear=True), \
-             patch.object(backend_mod.FirecrackerBottleBackend,
-                          "is_host_capable", classmethod(lambda cls: False)), \
-             patch.object(backend_mod, "_backends", {
-                 "macos-container": _FakeBackend("macos-container", False),
-                 "docker": _FakeBackend("docker", True),
-             }), \
-             patch.object(backend_mod, "die", side_effect=SystemExit("die")):
-            with self.assertRaises(SystemExit):
-                get_bottle_backend(prompt=False)
-
-    def test_docker_fallback_user_picks_install(self):
-        # User picks [i] → print install instructions then die.
-        class _FakeBackend:
-            def __init__(self, name: str, available: bool) -> None:
-                self.name = name
-                self._available = available
-
-            def is_available(self) -> bool:
-                return self._available
-
-        with patch.dict(os.environ, {}, clear=True), \
-             patch.object(backend_mod.FirecrackerBottleBackend,
-                          "is_host_capable", classmethod(lambda cls: False)), \
-             patch.object(backend_mod, "_backends", {
-                 "macos-container": _FakeBackend("macos-container", False),
-                 "docker": _FakeBackend("docker", True),
-             }), \
-             patch.object(backend_mod, "read_tty_line", return_value="i"), \
-             patch.object(backend_mod, "_print_vm_install_instructions") as mock_inst, \
-             patch.object(backend_mod, "die", side_effect=SystemExit("die")):
-            with self.assertRaises(SystemExit):
-                get_bottle_backend()
-        mock_inst.assert_called_once()
-
-
-class TestReadTtyLine(unittest.TestCase):
-    """Unit tests for the shared read_tty_line helper in bot_bottle.util."""
-
-    def test_reads_from_dev_tty(self):
-        from unittest.mock import mock_open
-        from bot_bottle.util import read_tty_line
-
-        m = mock_open(read_data="hello\n")
-        with patch("builtins.open", m):
-            result = read_tty_line()
-        self.assertEqual("hello", result)
-        m.assert_called_once_with("/dev/tty", "r", encoding="utf-8")
-
-    def test_falls_back_to_stdin_on_oserror(self):
-        import io
-        from bot_bottle.util import read_tty_line
-        import sys as _sys
-
-        with patch("builtins.open", side_effect=OSError("no tty")), \
-             patch.object(_sys, "stdin", io.StringIO("world\n")):
-            result = read_tty_line()
-        self.assertEqual("world", result)
-
-
-class TestPrintVmInstallInstructions(unittest.TestCase):
-    """Unit tests for _print_vm_install_instructions platform branches."""
-
-    def test_linux_prints_firecracker_instructions(self):
-        from bot_bottle.backend import _print_vm_install_instructions
-
-        with patch.object(backend_mod, "_platform_vm_suggestion",
-                          return_value="firecracker"), \
-             patch.object(backend_mod, "info") as mock_info:
-            _print_vm_install_instructions()
-
-        messages = [str(c[0][0]) for c in mock_info.call_args_list]
-        self.assertTrue(any("Firecracker" in m for m in messages))
-
-    def test_macos_prints_apple_container_instructions(self):
-        from bot_bottle.backend import _print_vm_install_instructions
-
-        with patch.object(backend_mod, "_platform_vm_suggestion",
-                          return_value="macos-container"), \
-             patch.object(backend_mod, "info") as mock_info:
-            _print_vm_install_instructions()
-
-        messages = [str(c[0][0]) for c in mock_info.call_args_list]
-        self.assertTrue(any("Apple Container" in m for m in messages))
-
 
 class TestKnownBackendNames(unittest.TestCase):
     def test_returns_backends_sorted(self):
@@ -274,7 +133,7 @@ class TestEnumerateActiveAgents(unittest.TestCase):
                 return self._items
 
         with patch.object(
-            backend_mod, "_backends",
+            backend_mod, "_BACKENDS",
             {"docker": _FakeBackend([a]), "firecracker": _FakeBackend([b])},
         ):
             self.assertEqual([a, b], enumerate_active_agents())
@@ -308,7 +167,7 @@ class TestEnumerateActiveAgents(unittest.TestCase):
                 return self._items
 
         with patch.object(
-            backend_mod, "_backends",
+            backend_mod, "_BACKENDS",
             {
                 "docker": _FakeBackend([newer, tie_b]),
                 "firecracker": _FakeBackend([missing_metadata, tie_a]),
@@ -328,7 +187,7 @@ class TestEnumerateActiveAgents(unittest.TestCase):
                 return []
 
         with patch.object(
-            backend_mod, "_backends",
+            backend_mod, "_BACKENDS",
             {"docker": _FakeBackend(), "firecracker": _FakeBackend()},
         ):
             self.assertEqual([], enumerate_active_agents())
@@ -359,7 +218,7 @@ class TestEnumerateActiveAgents(unittest.TestCase):
                 return self._items
 
         with patch.object(
-            backend_mod, "_backends",
+            backend_mod, "_BACKENDS",
             {
                 "docker": _FakeBackend([present], available=True),
                 "firecracker": _FakeBackend([hidden], available=False),
@@ -375,7 +234,7 @@ class TestHasBackend(unittest.TestCase):
                 return False
 
         with patch.object(
-            backend_mod, "_backends", {"docker": _FakeBackend()},
+            backend_mod, "_BACKENDS", {"docker": _FakeBackend()},
         ):
             from bot_bottle.backend import has_backend
             self.assertFalse(has_backend("docker"))

tests/unit/test_backend_setup.py

@@ -215,18 +215,6 @@ class TestDockerSetupStatus(unittest.TestCase):
         with patch.object(dk.shutil, "which", return_value=None):
             self.assertFalse(dk._daemon_reachable())
 
-    def test_daemon_reachable_true_when_daemon_responds(self):
-        with patch.object(dk.shutil, "which", return_value="/usr/bin/docker"), \
-             patch.object(dk.subprocess, "run",
-                          return_value=subprocess.CompletedProcess([], 0)):
-            self.assertTrue(dk._daemon_reachable())
-
-    def test_daemon_reachable_false_on_timeout(self):
-        with patch.object(dk.shutil, "which", return_value="/usr/bin/docker"), \
-             patch.object(dk.subprocess, "run",
-                          side_effect=subprocess.TimeoutExpired(["docker", "info"], 5)):
-            self.assertFalse(dk._daemon_reachable())
-
     def test_status_reports_missing_docker(self):
         with patch.object(dk.shutil, "which", return_value=None):
             rc, out = _cap(dk.status)

tests/unit/test_cli_cleanup_cross_backend.py

@@ -1,10 +1,8 @@
-"""Unit: `cli.py cleanup` walks every available backend.
+"""Unit: `cli.py cleanup` walks every backend (issue follow-up).
 
-Asserts cmd_cleanup queries each available backend's `prepare_cleanup`,
+Asserts cmd_cleanup queries each backend's `prepare_cleanup`,
-combines the y/N output, and runs each backend's `cleanup` when the
+combines the y/N output, and runs each backend's `cleanup` when
-operator confirms. Unavailable backends (e.g. macos-container on Linux)
+the operator confirms.  Mocks the backends and stdin."""
-are skipped so that `cleanup` never errors on a platform where a backend
-is not installed. Mocks the backends and stdin."""
 
 from __future__ import annotations
 
@@ -23,7 +21,7 @@ def _make_backend(empty: bool = True):
 
 
 class TestCmdCleanup(unittest.TestCase):
-    def test_iterates_every_available_backend(self):
+    def test_iterates_every_backend(self):
         docker, docker_plan = _make_backend(empty=False)
         fc, fc_plan = _make_backend(empty=False)
         backends_by_name = {"docker": docker, "firecracker": fc}
@@ -34,8 +32,6 @@ class TestCmdCleanup(unittest.TestCase):
         ), patch.object(
             cmd, "get_bottle_backend",
             side_effect=lambda name: backends_by_name[name],  # type: ignore
-        ), patch.object(
-            cmd, "has_backend", return_value=True,
         ), patch.object(
             cmd, "_prompt_yes", return_value=True,
         ):
@@ -46,32 +42,6 @@ class TestCmdCleanup(unittest.TestCase):
         docker.cleanup.assert_called_once_with(docker_plan)
         fc.cleanup.assert_called_once_with(fc_plan)
 
-    def test_skips_unavailable_backends(self):
-        # macos-container is not available on Linux — must be silently skipped.
-        docker, docker_plan = _make_backend(empty=False)
-        macos = MagicMock()
-        backends_by_name = {"docker": docker}
-
-        def _has(name: str) -> bool:
-            return name == "docker"
-
-        with patch.object(
-            cmd, "known_backend_names",
-            return_value=("docker", "macos-container"),
-        ), patch.object(
-            cmd, "get_bottle_backend",
-            side_effect=lambda name: backends_by_name[name],  # type: ignore
-        ), patch.object(
-            cmd, "has_backend", side_effect=_has,
-        ), patch.object(
-            cmd, "_prompt_yes", return_value=True,
-        ):
-            self.assertEqual(0, cmd.cmd_cleanup([]))
-
-        docker.prepare_cleanup.assert_called_once()
-        docker.cleanup.assert_called_once_with(docker_plan)
-        macos.prepare_cleanup.assert_not_called()
-
     def test_short_circuits_when_all_empty(self):
         docker, _ = _make_backend(empty=True)
         fc, _ = _make_backend(empty=True)
@@ -83,8 +53,6 @@ class TestCmdCleanup(unittest.TestCase):
         ), patch.object(
             cmd, "get_bottle_backend",
             side_effect=lambda name: backends_by_name[name],  # type: ignore
-        ), patch.object(
-            cmd, "has_backend", return_value=True,
         ), patch.object(
             cmd, "_prompt_yes",
         ) as prompt:
@@ -104,8 +72,6 @@ class TestCmdCleanup(unittest.TestCase):
         ), patch.object(
             cmd, "get_bottle_backend",
             side_effect=lambda name: backends_by_name[name],  # type: ignore
-        ), patch.object(
-            cmd, "has_backend", return_value=True,
         ), patch.object(
             cmd, "_prompt_yes", return_value=False,
         ):
@@ -126,8 +92,6 @@ class TestCmdCleanup(unittest.TestCase):
         ), patch.object(
             cmd, "get_bottle_backend",
             side_effect=lambda name: backends_by_name[name],  # type: ignore
-        ), patch.object(
-            cmd, "has_backend", return_value=True,
         ), patch.object(
             cmd, "_prompt_yes", return_value=True,
         ):

tests/unit/test_cli_dispatch.py

@@ -95,60 +95,5 @@ class TestMainDispatch(unittest.TestCase):
             self.assertEqual(130, main(["x"]))
 
 
-class TestMigrationGate(unittest.TestCase):
-    """The dispatcher's schema-migration gate (cli/__init__.py)."""
-
-    def setUp(self) -> None:
-        # Force the "schema out of date" branch for every test here.
-        patcher = patch.object(StoreManager, "is_migrated", return_value=False)
-        patcher.start()
-        self.addCleanup(patcher.stop)
-        self.addCleanup(StoreManager.reset)
-
-    def test_store_command_blocks_when_stdin_cannot_confirm(self) -> None:
-        # Non-TTY stdin at EOF (as in CI): the [y/N] prompt reads "" and the
-        # command is refused rather than migrating silently.
-        ran: list[bool] = []
-
-        def handler(_rest: list[str]) -> int:
-            ran.append(True)
-            return 0
-
-        with patch.dict(climod.COMMANDS, {"list": handler}), \
-                patch("sys.stdin", io.StringIO("")), \
-                patch("sys.stderr", io.StringIO()):
-            self.assertEqual(1, main(["list"]))
-        self.assertEqual([], ran, "gated command must not dispatch")
-
-    def test_backend_command_skips_gate(self) -> None:
-        # `backend` provisions/probes the host and never opens the store, so
-        # it must run even on an unmigrated DB with unanswerable stdin.
-        ran: list[bool] = []
-
-        def handler(_rest: list[str]) -> int:
-            ran.append(True)
-            return 0
-
-        with patch.dict(climod.COMMANDS, {"backend": handler}), \
-                patch("sys.stdin", io.StringIO("")), \
-                patch("sys.stderr", io.StringIO()):
-            self.assertEqual(0, main(["backend", "status"]))
-        self.assertEqual([True], ran, "exempt command must dispatch")
-
-    def test_store_command_migrates_on_confirmation(self) -> None:
-        migrated: list[bool] = []
-
-        def handler(_rest: list[str]) -> int:
-            return 0
-
-        with patch.dict(climod.COMMANDS, {"list": handler}), \
-                patch.object(StoreManager, "migrate",
-                             side_effect=lambda: migrated.append(True)), \
-                patch("sys.stdin", io.StringIO("y\n")), \
-                patch("sys.stderr", io.StringIO()):
-            self.assertEqual(0, main(["list"]))
-        self.assertEqual([True], migrated, "confirmed gate must migrate")
-
-
 if __name__ == "__main__":
     unittest.main()

tests/unit/test_cli_start_backend_flag.py

@@ -1,29 +1,61 @@
-"""Unit: backend resolution priority — explicit name > env var.
+"""Unit: `cli.py start --backend=<name>` flag (issue #77).
 
-The `--backend` flag has been removed from `cli.py start`; backend
+Asserts that the flag wins over the env var, that the env var is
-selection is driven by BOT_BOTTLE_BACKEND or auto-selection only.
+the fallback, and that the choices are pulled from the backend
-`get_bottle_backend` still accepts an explicit name so that `resume`
+registry (so adding a backend lights up in argparse without code
-(which records the backend from a prior session) and the `backend`
+edits)."""
-sub-command can pass one directly."""
 
 from __future__ import annotations
 
+import argparse
 import os
 import unittest
 from unittest.mock import patch
 
 
-class TestBackendResolutionPriority(unittest.TestCase):
+from bot_bottle.backend import known_backend_names
-    def test_explicit_name_overrides_env_var(self):
+
+
+class TestStartBackendFlag(unittest.TestCase):
+    """The flag is wired by `cmd_start`'s argparse and threaded
+    through `prepare_with_preflight(backend_name=...)`. Rather than
+    drive the whole start flow (which builds containers), we test
+    the argparse shape and the resolution function separately."""
+
+    def _build_parser(self):
+        # Mirror the parser definition from `cmd_start` so this
+        # test doesn't have to invoke the full command.
+        parser = argparse.ArgumentParser(prog="cb start")
+        parser.add_argument(
+            "--backend",
+            choices=known_backend_names(),
+            default=None,
+        )
+        parser.add_argument("name")
+        return parser
+
+    def test_flag_recognized(self):
+        args = self._build_parser().parse_args(["--backend=firecracker", "researcher"])
+        self.assertEqual("firecracker", args.backend)
+        self.assertEqual("researcher", args.name)
+
+    def test_flag_default_none_means_env_or_default_backend(self):
+        args = self._build_parser().parse_args(["researcher"])
+        self.assertIsNone(args.backend)
+
+    def test_invalid_backend_rejected_by_argparse(self):
+        parser = self._build_parser()
+        with self.assertRaises(SystemExit):
+            parser.parse_args(["--backend=garbage", "researcher"])
+
+    def test_resolution_priority_explicit_over_env(self):
+        # Independent assertion that get_bottle_backend (where
+        # `--backend` ultimately threads to) prefers the explicit
+        # name over BOT_BOTTLE_BACKEND.
         from bot_bottle.backend import get_bottle_backend
         with patch.dict(os.environ, {"BOT_BOTTLE_BACKEND": "firecracker"}):
             self.assertEqual("docker", get_bottle_backend("docker").name)
 
-    def test_env_var_used_when_no_explicit_name(self):
-        from bot_bottle.backend import get_bottle_backend
-        with patch.dict(os.environ, {"BOT_BOTTLE_BACKEND": "firecracker"}):
-            self.assertEqual("firecracker", get_bottle_backend().name)
-
 
 if __name__ == "__main__":
     unittest.main()

tests/unit/test_cli_start_headless.py

@@ -175,6 +175,14 @@ class TestCmdStartHeadless(unittest.TestCase):
             )
         self.assertEqual("researcher-2", self._spec().label)
 
+    # -- backend wiring ------------------------------------------------
+
+    def test_backend_flag_forwarded(self):
+        start_mod.cmd_start(
+            ["--headless", "--backend=docker", "researcher", "--bottle", "claude",
+             "--prompt", "Do it"]
+        )
+        self.assertEqual("docker", self._launch_mock.call_args[1]["backend_name"])
 
 
 class TestPrepareWithPreflight(unittest.TestCase):

tests/unit/test_cli_start_selector.py

@@ -57,14 +57,6 @@ class TestCmdStartSelector(unittest.TestCase):
         self._bottle_picker_mock = self._bottle_picker_patch.start()
         self._bottle_picker_mock.return_value = ["claude"]  # default: one bottle selected
 
-        # name_color_modal opens /dev/tty and blocks on keyboard input on
-        # self-hosted runners that have a real controlling terminal. Stub it
-        # out like the other tui pickers so tests don't wait for a keypress.
-        self._modal_patch = patch.object(
-            tui_mod, "name_color_modal", return_value=("researcher", ""),
-        )
-        self._modal_patch.start()
-
         self._env_patch = patch.dict(os.environ, {}, clear=False)
         self._env_patch.start()
         os.environ.pop("BOT_BOTTLE_BACKEND", None)
@@ -74,7 +66,6 @@ class TestCmdStartSelector(unittest.TestCase):
         self._launch_patch.stop()
         self._agent_picker_patch.stop()
         self._bottle_picker_patch.stop()
-        self._modal_patch.stop()
         self._env_patch.stop()
 
     # ------------------------------------------------------------------
@@ -82,7 +73,7 @@ class TestCmdStartSelector(unittest.TestCase):
     # ------------------------------------------------------------------
 
     def test_explicit_agent_skips_agent_picker(self):
-        rc = start_mod.cmd_start(["researcher"])
+        rc = start_mod.cmd_start(["--backend=docker", "researcher"])
         self.assertEqual(0, rc)
         self._agent_picker_mock.assert_not_called()
         self._bottle_picker_mock.assert_called_once()
@@ -100,7 +91,7 @@ class TestCmdStartSelector(unittest.TestCase):
 
     def test_agent_absent_shows_agent_picker(self):
         self._agent_picker_mock.return_value = "researcher"
-        rc = start_mod.cmd_start([])
+        rc = start_mod.cmd_start(["--backend=docker"])
         self.assertEqual(0, rc)
         self._agent_picker_mock.assert_called_once()
         call_kwargs = self._agent_picker_mock.call_args
@@ -111,7 +102,7 @@ class TestCmdStartSelector(unittest.TestCase):
 
     def test_agent_picker_cancel_skips_bottle_picker(self):
         self._agent_picker_mock.return_value = None
-        rc = start_mod.cmd_start([])
+        rc = start_mod.cmd_start(["--backend=docker"])
         self.assertEqual(0, rc)
         self._bottle_picker_mock.assert_not_called()
         self._launch_mock.assert_not_called()
@@ -168,6 +159,16 @@ class TestCmdStartSelector(unittest.TestCase):
     # Backend wiring
     # ------------------------------------------------------------------
 
+    def test_explicit_backend_forwarded(self):
+        start_mod.cmd_start(["--backend=docker", "researcher"])
+        _, kwargs = self._launch_mock.call_args
+        self.assertEqual("docker", kwargs["backend_name"])
+
+    def test_absent_backend_uses_default(self):
+        start_mod.cmd_start(["researcher"])
+        _, kwargs = self._launch_mock.call_args
+        self.assertIsNone(kwargs["backend_name"])
+
     def test_bot_bottle_backend_env_skips_backend_picker(self):
         os.environ["BOT_BOTTLE_BACKEND"] = "docker"
         try:

tests/unit/test_db_store.py

@@ -1,58 +0,0 @@
-"""Unit: DbStore._connection() context manager and is_migrated()."""
-
-from __future__ import annotations
-
-import sqlite3
-import tempfile
-import unittest
-from pathlib import Path
-
-from bot_bottle.db_store import DbStore
-from bot_bottle.migrations import TableMigrations
-
-
-def _store(tmp: Path) -> DbStore:
-    migrations = TableMigrations("test", ["CREATE TABLE items (id INTEGER PRIMARY KEY)"])
-    return DbStore(tmp / "test.db", migrations)
-
-
-class TestDbStoreIsMigrated(unittest.TestCase):
-    def test_returns_false_when_db_absent(self):
-        with tempfile.TemporaryDirectory() as d:
-            store = _store(Path(d))
-            self.assertFalse(store.is_migrated())
-
-    def test_returns_false_when_schema_versions_missing(self):
-        # DB file exists but has no schema_versions table → OperationalError → False.
-        with tempfile.TemporaryDirectory() as d:
-            store = _store(Path(d))
-            conn = sqlite3.connect(store.db_path)
-            conn.close()
-            self.assertFalse(store.is_migrated())
-
-    def test_returns_true_after_migrate(self):
-        with tempfile.TemporaryDirectory() as d:
-            store = _store(Path(d))
-            store.migrate()
-            self.assertTrue(store.is_migrated())
-
-    def test_returns_false_when_behind(self):
-        with tempfile.TemporaryDirectory() as d:
-            migrations = TableMigrations(
-                "test",
-                [
-                    "CREATE TABLE items (id INTEGER PRIMARY KEY)",
-                    "ALTER TABLE items ADD COLUMN name TEXT",
-                ],
-            )
-            store = DbStore(Path(d) / "test.db", migrations)
-            # Apply only the first migration manually.
-            conn = sqlite3.connect(store.db_path)
-            with conn:
-                TableMigrations("test", [migrations.migrations[0]]).apply(conn)
-            conn.close()
-            self.assertFalse(store.is_migrated())
-
-
-if __name__ == "__main__":
-    unittest.main()

tests/unit/test_docker_test_helpers.py

@@ -1,35 +0,0 @@
-"""Tests for integration-test backend selection helpers."""
-
-from __future__ import annotations
-
-import os
-import unittest
-from unittest.mock import patch
-
-from tests._docker import skip_unless_docker_or_firecracker
-
-
-class TestSkipUnlessDockerOrFirecracker(unittest.TestCase):
-    def test_firecracker_runs_when_docker_tests_are_disabled(self):
-        with patch.dict(
-            os.environ,
-            {"BOT_BOTTLE_BACKEND": "firecracker", "SKIP_DOCKER_TESTS": "1"},
-            clear=True,
-        ):
-            decorated = skip_unless_docker_or_firecracker()(type("Case", (), {}))
-
-        self.assertFalse(getattr(decorated, "__unittest_skip__", False))
-
-    def test_non_firecracker_still_skips_when_docker_tests_are_disabled(self):
-        with patch.dict(
-            os.environ,
-            {"BOT_BOTTLE_BACKEND": "docker", "SKIP_DOCKER_TESTS": "1"},
-            clear=True,
-        ):
-            decorated = skip_unless_docker_or_firecracker()(type("Case", (), {}))
-
-        self.assertTrue(getattr(decorated, "__unittest_skip__", False))
-
-
-if __name__ == "__main__":
-    unittest.main()

tests/unit/test_docker_util_image.py

@@ -29,7 +29,7 @@ def _fail(stderr: str = "boom") -> subprocess.CompletedProcess:  # type: ignore
 class TestCommitContainer(unittest.TestCase):
     def test_runs_docker_commit(self):
         with patch.object(
-            docker_mod, "run_docker", return_value=_ok(),
+            docker_mod.subprocess, "run", return_value=_ok(),
         ) as run, patch.object(docker_mod, "info"):
             docker_mod.commit_container(
                 "bot-bottle-dev-abc12",
@@ -47,7 +47,7 @@ class TestCommitContainer(unittest.TestCase):
 
     def test_dies_on_docker_commit_failure(self):
         with patch.object(
-            docker_mod, "run_docker", return_value=_fail("No such container"),
+            docker_mod.subprocess, "run", return_value=_fail("No such container"),
         ), patch.object(
             docker_mod, "die", side_effect=SystemExit("die"),
         ) as die:
@@ -58,7 +58,7 @@ class TestCommitContainer(unittest.TestCase):
 
     def test_die_message_includes_image_tag(self):
         with patch.object(
-            docker_mod, "run_docker", return_value=_fail("boom"),
+            docker_mod.subprocess, "run", return_value=_fail("boom"),
         ), patch.object(
             docker_mod, "die", side_effect=SystemExit("die"),
         ) as die:

tests/unit/test_egress_addon_log_redaction.py

@@ -18,7 +18,7 @@ from unittest.mock import patch
 
 
 # ---------------------------------------------------------------------------
-# mitmproxy stub — must run before importing egress_addon
+# Gateway-import shims — must run before importing egress_addon
 # ---------------------------------------------------------------------------
 
 def _ensure_shims() -> None:
@@ -32,6 +32,9 @@ def _ensure_shims() -> None:
         setattr(_mm, "http", _mh)
         sys.modules["mitmproxy"] = _mm
         sys.modules["mitmproxy.http"] = _mh
+    if "egress_addon_core" not in sys.modules:
+        import bot_bottle.egress_addon_core as _core
+        sys.modules["egress_addon_core"] = _core
 
 
 _ensure_shims()

tests/unit/test_egress_addon_request_flow.py

@@ -190,6 +190,9 @@ def _ensure_shims() -> None:
         setattr(mh, "Response", _Response)
     if not hasattr(mh, "HTTPFlow"):
         setattr(mh, "HTTPFlow", object)
+    if "egress_addon_core" not in sys.modules:
+        import bot_bottle.egress_addon_core as _core
+        sys.modules["egress_addon_core"] = _core
 
 
 _ensure_shims()

tests/unit/test_egress_multitenant.py

@@ -4,14 +4,7 @@ from __future__ import annotations
 
 import unittest
 
-from bot_bottle.egress_addon_core import (
+from bot_bottle.egress_addon_core import resolve_client_config, resolve_client_context
-    DENY_RESOLVER_ERROR,
-    DENY_UNATTRIBUTED,
-    DENY_UNPARSEABLE,
-    decide,
-    resolve_client_config,
-    resolve_client_context,
-)
 from bot_bottle.policy_resolver import PolicyResolveError
 
 
@@ -115,55 +108,3 @@ class TestResolveClientContext(unittest.TestCase):
 
 if __name__ == "__main__":
     unittest.main()
-
-
-class TestDenyReasonNamesTheRealFault(unittest.TestCase):
-    """A deny-all must not masquerade as a missing allowlist entry.
-
-    Regression: an unregistered bottle resolves no policy, so *every* host is
-    denied — but the block message said `host X is not in the allowlist`,
-    which reads as a config problem and sends the operator hunting for a route
-    that was never missing. The structural reason wins over that wording.
-    """
-
-    def _reason(self, resolver: object, host: str = "chatgpt.com") -> str:
-        cfg = resolve_client_config(resolver, "10.243.0.1")  # type: ignore[arg-type]
-        return decide(cfg.routes, host, "/v1/x", {}, deny_reason=cfg.deny_reason).reason
-
-    def test_unattributed_says_unattributed_not_allowlist(self) -> None:
-        reason = self._reason(_FakeResolver(result=None))
-        self.assertEqual(DENY_UNATTRIBUTED, reason)
-        # The misleading claim is the one that must be gone: the host was
-        # never "not in the allowlist" — there was no allowlist at all.
-        self.assertNotIn("is not in the bottle's egress.routes allowlist", reason)
-        # Both causes must be named. `/resolve` fail-closes on a missing row
-        # *and* on a token mismatch, and the message pointing only at the row
-        # sent us hunting for a deregistered bottle that was registered fine.
-        self.assertIn("registry row", reason)
-        self.assertIn("identity token", reason)
-
-    def test_resolver_error_says_orchestrator_unreachable(self) -> None:
-        self.assertEqual(DENY_RESOLVER_ERROR, self._reason(_FakeResolver(raises=True)))
-
-    def test_unparseable_policy_says_so(self) -> None:
-        self.assertEqual(
-            DENY_UNPARSEABLE, self._reason(_FakeResolver(result="routes: notalist\n")))
-
-    def test_a_real_allowlist_miss_keeps_the_allowlist_wording(self) -> None:
-        """The message only changes for structural deny-alls — a loaded policy
-        that genuinely lacks the host still points at the allowlist."""
-        reason = self._reason(_FakeResolver(result='routes:\n  - host: "api.example.com"\n'))
-        self.assertIn("is not in the bottle's egress.routes allowlist", reason)
-        self.assertIn("chatgpt.com", reason)
-
-    def test_allowed_host_is_still_forwarded(self) -> None:
-        cfg = resolve_client_config(
-            _FakeResolver(result='routes:\n  - host: "api.example.com"\n'), "10.243.0.1")
-        decision = decide(
-            cfg.routes, "api.example.com", "/v1/x", {}, deny_reason=cfg.deny_reason)
-        self.assertEqual("forward", decision.action)
-
-    def test_a_parsed_policy_carries_no_deny_reason(self) -> None:
-        cfg = resolve_client_config(
-            _FakeResolver(result='routes:\n  - host: "api.example.com"\n'), "10.243.0.1")
-        self.assertEqual("", cfg.deny_reason)

tests/unit/test_firecracker_backend.py

@@ -35,12 +35,9 @@ class TestNetpoolSlots(unittest.TestCase):
     def test_slot_ip_math_31_pairs(self):
         with patch.dict(os.environ, {"BOT_BOTTLE_FC_IP_BASE": "100.64.0.0"}):
             s0, s1 = netpool.slot(0), netpool.slot(1)
-        # Iface names track netpool's (env-driven) prefix — the KVM CI runner
+        self.assertEqual(("bbfc0", "100.64.0.0", "100.64.0.1"),
-        # overrides it for its isolated pool, so don't hardcode "bbfc".
-        pfx = netpool.IFACE_PREFIX
-        self.assertEqual((f"{pfx}0", "100.64.0.0", "100.64.0.1"),
                          (s0.iface, s0.host_ip, s0.guest_ip))
-        self.assertEqual((f"{pfx}1", "100.64.0.2", "100.64.0.3"),
+        self.assertEqual(("bbfc1", "100.64.0.2", "100.64.0.3"),
                          (s1.iface, s1.host_ip, s1.guest_ip))
 
     def test_guest_cidr_is_31(self):
@@ -183,14 +180,11 @@ class TestNetpoolOverlap(unittest.TestCase):
         self.assertEqual("tailscale0", conflicts[0].dev)
 
     def test_ignores_own_taps_and_default(self):
-        # The "own tap" route uses netpool's (env-driven) iface name, so the
-        # test still exercises the self-ignore path on the KVM CI runner, whose
-        # BOT_BOTTLE_FC_IFACE_PREFIX differs from the default.
         with patch.dict(os.environ, {"BOT_BOTTLE_FC_IP_BASE": "10.243.0.0",
                                      "BOT_BOTTLE_FC_POOL_SIZE": "8"}), \
              self._routes([
                  {"dst": "default", "dev": "enp4s0"},
-                 {"dst": "10.243.0.0/31", "dev": netpool.slot(0).iface},
+                 {"dst": "10.243.0.0/31", "dev": "bbfc0"},
                  {"dst": "192.168.1.0/24", "dev": "enp4s0"},
              ]):
             self.assertEqual([], netpool.overlapping_routes())
@@ -209,7 +203,7 @@ class TestNetpoolAllocation(unittest.TestCase):
             # over (and here, exhaust the pool).
             slot, lock = netpool.allocate("first")
             self.addCleanup(lock.close)
-            self.assertEqual(netpool.slot(0).iface, slot.iface)
+            self.assertEqual("bbfc0", slot.iface)
             with patch.object(netpool, "die",
                               side_effect=SystemExit("exhausted")):
                 with self.assertRaises(SystemExit):
@@ -329,14 +323,9 @@ class TestNetpoolDefaultsSingleSource(unittest.TestCase):
         with patch.dict(os.environ, {}, clear=True):
             self.assertEqual(int(d["BOT_BOTTLE_FC_POOL_SIZE"]), netpool.pool_size())
             self.assertEqual(d["BOT_BOTTLE_FC_IP_BASE"], netpool.ip_base())
-        # The module's *defaults* come from the same shared file. Assert the
+        # Module constants resolve through the same shared file.
-        # parsed defaults (not IFACE_PREFIX/NFT_TABLE, which layer a live env
+        self.assertEqual(d["BOT_BOTTLE_FC_IFACE_PREFIX"], netpool.IFACE_PREFIX)
-        # override on top — the KVM CI runner sets those for its isolated pool,
+        self.assertEqual(d["BOT_BOTTLE_FC_NFT_TABLE"], netpool.NFT_TABLE)
-        # which would otherwise mask this single-source check).
-        self.assertEqual(d["BOT_BOTTLE_FC_IFACE_PREFIX"],
-                         netpool._DEFAULTS["BOT_BOTTLE_FC_IFACE_PREFIX"])
-        self.assertEqual(d["BOT_BOTTLE_FC_NFT_TABLE"],
-                         netpool._DEFAULTS["BOT_BOTTLE_FC_NFT_TABLE"])
 
     def test_env_var_overrides_the_shared_default(self):
         with patch.dict(os.environ, {"BOT_BOTTLE_FC_IP_BASE": "10.99.0.0"}):

tests/unit/test_firecracker_helpers.py

@@ -63,12 +63,9 @@ class TestNetpoolProbes(unittest.TestCase):
         self.assertEqual(2, ok.call_count)
 
     def test_missing_taps(self):
-        # Derive the expected iface from netpool's (env-driven) config rather
-        # than hardcoding "bbfc1": the KVM CI runner sets BOT_BOTTLE_FC_* for
-        # its isolated pool, so the prefix there is not the default.
         with patch.dict("os.environ", {"BOT_BOTTLE_FC_POOL_SIZE": "2"}), \
              patch.object(netpool, "tap_present", side_effect=[True, False]):
-            self.assertEqual([netpool.slot(1).iface], netpool.missing_taps())
+            self.assertEqual(["bbfc1"], netpool.missing_taps())
 
     def test_orch_slot_is_top_of_ip_base_16(self):
         # Dedicated orchestrator link: /31 at the top of the IP_BASE /16,

tests/unit/test_firecracker_image_builder.py

@@ -24,7 +24,7 @@ class TestBuildAgentRootfsDir(unittest.TestCase):
         self.addCleanup(self._tmp.cleanup)
 
     def test_cache_hit_skips_rebuild(self):
-        digest = image_builder._rootfs_digest(self.dockerfile)
+        digest = image_builder._dockerfile_hash(self.dockerfile)
         base = self.cache / "rootfs" / f"agent-{digest}"
         base.mkdir(parents=True)
         (base / ".bb-ready").write_text("ok\n")
@@ -55,17 +55,6 @@ class TestBuildAgentRootfsDir(unittest.TestCase):
             image_builder._dockerfile_hash(other),
         )
 
-    def test_rootfs_digest_tracks_dockerfile_and_init(self):
-        # Same Dockerfile, different injected init -> different rootfs key, so
-        # an init fix (e.g. /tmp perms) rebuilds instead of reusing a stale
-        # rootfs; different Dockerfiles also differ.
-        base = image_builder._rootfs_digest(self.dockerfile)
-        with patch.object(image_builder.util, "_GUEST_INIT", "#!/bin/sh\n# changed\n"):
-            self.assertNotEqual(base, image_builder._rootfs_digest(self.dockerfile))
-        other = self.cache / "Dockerfile2"
-        other.write_text("FROM python:3.12-slim\n")
-        self.assertNotEqual(base, image_builder._rootfs_digest(other))
-
 
 class TestSmokeTest(unittest.TestCase):
     def test_empty_argv_is_noop(self):

tests/unit/test_firecracker_infra_vm.py

@@ -38,9 +38,7 @@ class TestBuildInfraRootfs(unittest.TestCase):
         # and exports PATH so gateway_init's subprocess daemons find python3.
         init = build.call_args.kwargs["init_script"]
         self.assertIn("bot_bottle.orchestrator", init)
-        # Gateway launches via the installed package (there is no
+        self.assertIn("gateway_init.py", init)
-        # /app/gateway_init.py file since the daemons moved into bot_bottle).
-        self.assertIn("bot_bottle.gateway_init", init)
         self.assertIn("export PATH=", init)
         # Persistent registry volume mounted at the DB dir before the CP starts.
         self.assertIn("/dev/vdb", init)
@@ -100,11 +98,7 @@ class TestRegistryVolume(unittest.TestCase):
 class TestEnsureBuilt(unittest.TestCase):
     def test_default_pulls_artifact_without_docker(self):
         # PRD 0069 Stage 2: the launch host pulls the prebuilt rootfs; no Docker.
-        # Pin BOT_BOTTLE_INFRA_BUILD off: the coverage CI job exports it =local
+        with patch.object(infra_vm.docker_mod, "build_image") as build, \
-        # for the integration suite, and that ambient value would otherwise send
-        # this default-path test down the local Docker-build branch.
-        with patch.dict(os.environ, {"BOT_BOTTLE_INFRA_BUILD": ""}), \
-                patch.object(infra_vm.docker_mod, "build_image") as build, \
                 patch.object(infra_vm.infra_artifact, "ensure_artifact_gz") as pull:
             infra_vm.ensure_built()
         build.assert_not_called()
@@ -144,58 +138,27 @@ class TestWaitForHealth(unittest.TestCase):
 
 
 class TestEnsureRunningSingleton(unittest.TestCase):
-    def test_adopts_when_healthy_and_version_matches(self):
+    def test_adopts_when_healthy(self):
-        # Healthy control plane + existing key + matching version marker
+        # A healthy control plane + existing key -> adopt (no boot), vm=None.
-        # -> adopt (no boot), vm=None.
+        with patch.object(infra_vm, "_health_ok", return_value=True), \
-        import tempfile
+             patch.object(infra_vm, "_infra_dir") as d, \
-        with tempfile.TemporaryDirectory() as td:
+             patch.object(infra_vm, "boot") as boot:
-            d = Path(td)
+            keydir = MagicMock()
-            (d / "id_ed25519").write_text("k")
+            (keydir / "id_ed25519").exists.return_value = True
-            (d / "booted-version").write_text("v-current\n")
+            d.return_value = keydir
-            with patch.object(infra_vm, "_infra_dir", return_value=d), \
+            infra = infra_vm.ensure_running()
-                 patch.object(infra_vm, "_expected_version", return_value="v-current"), \
-                 patch.object(infra_vm, "_health_ok", return_value=True), \
-                 patch.object(infra_vm, "boot") as boot:
-                infra = infra_vm.ensure_running()
         boot.assert_not_called()
         self.assertIsNone(infra.vm)
 
-    def test_reboots_when_version_stale(self):
-        # Healthy control plane but the running VM booted an OLDER image
-        # (marker mismatch) -> reboot rather than adopt stale code.
-        import tempfile
-        with tempfile.TemporaryDirectory() as td:
-            d = Path(td)
-            (d / "id_ed25519").write_text("k")
-            (d / "booted-version").write_text("v-old\n")
-            with patch.object(infra_vm, "_infra_dir", return_value=d), \
-                 patch.object(infra_vm, "_expected_version", return_value="v-current"), \
-                 patch.object(infra_vm, "_health_ok", return_value=True), \
-                 patch.object(infra_vm, "stop") as stop, \
-                 patch.object(infra_vm, "ensure_built"), \
-                 patch.object(infra_vm, "wait_for_health"), \
-                 patch.object(infra_vm, "boot") as boot:
-                boot.return_value = infra_vm.InfraVm(
-                    guest_ip="10.243.255.1", private_key=Path("/k"), vm=MagicMock())
-                infra_vm.ensure_running()
-            stop.assert_called_once()      # dislodge the outdated VM
-            boot.assert_called_once()
-            # The fresh boot records the current version for the next launcher.
-            self.assertEqual("v-current\n", (d / "booted-version").read_text())
-
     def test_boots_when_unhealthy(self):
-        import tempfile
+        with patch.object(infra_vm, "_health_ok", return_value=False), \
-        with tempfile.TemporaryDirectory() as td:
+             patch.object(infra_vm, "stop") as stop, \
-            with patch.object(infra_vm, "_infra_dir", return_value=Path(td)), \
+             patch.object(infra_vm, "ensure_built") as built, \
-                 patch.object(infra_vm, "_expected_version", return_value="v-current"), \
+             patch.object(infra_vm, "boot") as boot, \
-                 patch.object(infra_vm, "_health_ok", return_value=False), \
+             patch.object(infra_vm, "wait_for_health") as wait:
-                 patch.object(infra_vm, "stop") as stop, \
+            boot.return_value = infra_vm.InfraVm(
-                 patch.object(infra_vm, "ensure_built") as built, \
+                guest_ip="10.243.255.1", private_key=Path("/k"), vm=MagicMock())
-                 patch.object(infra_vm, "boot") as boot, \
+            infra_vm.ensure_running()
-                 patch.object(infra_vm, "wait_for_health") as wait:
-                boot.return_value = infra_vm.InfraVm(
-                    guest_ip="10.243.255.1", private_key=Path("/k"), vm=MagicMock())
-                infra_vm.ensure_running()
         stop.assert_called_once()      # clear a stale VM first
         built.assert_called_once()
         boot.assert_called_once()
@@ -222,74 +185,5 @@ class TestKillPidfile(unittest.TestCase):
             kill.assert_not_called()
 
 
-class TestAdoptable(unittest.TestCase):
-    def _dir(self, td: str, *, key: bool = True, version: str | None = None) -> Path:
-        d = Path(td)
-        if key:
-            (d / "id_ed25519").write_text("k")
-        if version is not None:
-            (d / "booted-version").write_text(version + "\n")
-        return d
-
-    def test_true_when_key_version_and_health(self):
-        import tempfile
-        with tempfile.TemporaryDirectory() as td:
-            d = self._dir(td, version="v1")
-            with patch.object(infra_vm, "_infra_dir", return_value=d), \
-                 patch.object(infra_vm, "_health_ok", return_value=True):
-                self.assertTrue(infra_vm._adoptable(d / "id_ed25519", "u", "v1"))
-
-    def test_false_when_key_missing(self):
-        import tempfile
-        with tempfile.TemporaryDirectory() as td:
-            d = self._dir(td, key=False, version="v1")
-            with patch.object(infra_vm, "_infra_dir", return_value=d):
-                self.assertFalse(infra_vm._adoptable(d / "id_ed25519", "u", "v1"))
-
-    def test_false_when_no_version_marker(self):
-        import tempfile
-        with tempfile.TemporaryDirectory() as td:
-            d = self._dir(td)  # key present, no booted-version
-            with patch.object(infra_vm, "_infra_dir", return_value=d):
-                self.assertFalse(infra_vm._adoptable(d / "id_ed25519", "u", "v1"))
-
-    def test_false_when_version_mismatch(self):
-        import tempfile
-        with tempfile.TemporaryDirectory() as td:
-            d = self._dir(td, version="v-old")
-            with patch.object(infra_vm, "_infra_dir", return_value=d), \
-                 patch.object(infra_vm, "_health_ok", return_value=True):
-                self.assertFalse(infra_vm._adoptable(d / "id_ed25519", "u", "v1"))
-
-
-class TestKillInfraFirecrackers(unittest.TestCase):
-    def _fake_proc(self, root: Path, pid: int, comm: str, cmdline: list[str]) -> None:
-        p = root / str(pid)
-        p.mkdir()
-        (p / "comm").write_text(comm + "\n")
-        (p / "cmdline").write_bytes(b"\0".join(a.encode() for a in cmdline) + b"\0")
-
-    def test_kills_only_matching_infra_firecracker(self):
-        import tempfile
-        with tempfile.TemporaryDirectory() as td, \
-             tempfile.TemporaryDirectory() as proc:
-            infra_dir = Path(td)
-            cfg = str(infra_dir / "config.json")
-            root = Path(proc)
-            # target: firecracker bound to the infra config -> killed
-            self._fake_proc(root, 111, "firecracker",
-                            ["firecracker", "--no-api", "--config-file", cfg])
-            # a firecracker for a different (interactive) VM -> spared
-            self._fake_proc(root, 222, "firecracker",
-                            ["firecracker", "--config-file", "/home/u/other.json"])
-            # a non-firecracker process on the same config path -> spared
-            self._fake_proc(root, 333, "python3", ["python3", cfg])
-            (root / "not-a-pid").mkdir()
-            with patch.object(infra_vm, "_infra_dir", return_value=infra_dir), \
-                 patch.object(infra_vm.os, "kill") as kill:
-                infra_vm._kill_infra_firecrackers(proc_root=root)
-            kill.assert_called_once_with(111, infra_vm.signal.SIGKILL)
-
-
 if __name__ == "__main__":
     unittest.main()

tests/unit/test_gateway_init.py

@@ -2,9 +2,9 @@
 
 Tests both the helper functions in `bot_bottle.gateway_init`
 and the supervisor's end-to-end signal / exit-code behavior. The
-end-to-end tests use real subprocesses (`sleep`, `/bin/sh -c '...'`) —
+end-to-end tests use real subprocesses (`/bin/sleep`,
-short-lived, no docker required — so they run under `tests/unit/`
+`/bin/sh -c '...'`) — short-lived, no docker required — so they
-rather than `tests/integration/`."""
+run under `tests/unit/` rather than `tests/integration/`."""
 
 from __future__ import annotations
 
@@ -25,7 +25,6 @@ from bot_bottle.gateway_init import (
     _env_for_daemon,
     _selected_daemons,
 )
-from tests._bin import SLEEP
 
 
 class TestEnvForDaemon(unittest.TestCase):
@@ -183,7 +182,7 @@ class TestSupervisor(unittest.TestCase):
         # up and the supervisor never set shutdown_at.
         specs = [
             _DaemonSpec("crasher", ("/bin/sh", "-c", "exit 1")),
-            _DaemonSpec("longrun", (SLEEP, "30")),
+            _DaemonSpec("longrun", ("/bin/sleep", "30")),
         ]
         sup = _Supervisor(specs)
         sup.start_all()
@@ -215,7 +214,7 @@ class TestSupervisor(unittest.TestCase):
         # signal-killed longrun's negative returncode.
         specs = [
             _DaemonSpec("crasher", ("/bin/sh", "-c", "exit 1")),
-            _DaemonSpec("longrun", (SLEEP, "30")),
+            _DaemonSpec("longrun", ("/bin/sleep", "30")),
         ]
         sup = _Supervisor(specs)
         sup.start_all()
@@ -260,7 +259,7 @@ class TestSupervisor(unittest.TestCase):
         )
         specs = [
             _DaemonSpec("egress", sighup_marker),
-            _DaemonSpec("other",  (SLEEP, "30")),
+            _DaemonSpec("other",  ("/bin/sleep", "30")),
         ]
         sup = _Supervisor(specs)
         sup.start_all()
@@ -283,7 +282,7 @@ class TestSupervisor(unittest.TestCase):
         self._drive(sup)
 
     def test_forward_signal_unknown_daemon_no_op(self):
-        specs = [_DaemonSpec("a", (SLEEP, "30"))]
+        specs = [_DaemonSpec("a", ("/bin/sleep", "30"))]
         sup = _Supervisor(specs)
         sup.start_all()
         delivered = sup.forward_signal(signal.SIGHUP, "ghost")
@@ -295,8 +294,8 @@ class TestSupervisor(unittest.TestCase):
         # Restart one daemon; the other (supervise, the MCP server
         # in production) must remain untouched.
         specs = [
-            _DaemonSpec("git-gate", (SLEEP, "30")),
+            _DaemonSpec("git-gate", ("/bin/sleep", "30")),
-            _DaemonSpec("supervise", (SLEEP, "30")),
+            _DaemonSpec("supervise", ("/bin/sleep", "30")),
         ]
         sup = _Supervisor(specs)
         sup.start_all()
@@ -320,8 +319,8 @@ class TestSupervisor(unittest.TestCase):
 
     def test_request_restart_is_drained_by_tick(self):
         specs = [
-            _DaemonSpec("git-gate", (SLEEP, "30")),
+            _DaemonSpec("git-gate", ("/bin/sleep", "30")),
-            _DaemonSpec("supervise", (SLEEP, "30")),
+            _DaemonSpec("supervise", ("/bin/sleep", "30")),
         ]
         sup = _Supervisor(specs)
         sup.start_all()
@@ -344,7 +343,7 @@ class TestSupervisor(unittest.TestCase):
         self._drive(sup)
 
     def test_repeated_restart_requests_coalesce(self):
-        specs = [_DaemonSpec("git-gate", (SLEEP, "30"))]
+        specs = [_DaemonSpec("git-gate", ("/bin/sleep", "30"))]
         sup = _Supervisor(specs)
         sup.start_all()
         time.sleep(0.1)
@@ -367,7 +366,7 @@ class TestSupervisor(unittest.TestCase):
         self._drive(sup)
 
     def test_request_restart_unknown_daemon_no_op(self):
-        specs = [_DaemonSpec("a", (SLEEP, "30"))]
+        specs = [_DaemonSpec("a", ("/bin/sleep", "30"))]
         sup = _Supervisor(specs)
         sup.start_all()
         ok = sup.request_restart("ghost")
@@ -377,7 +376,7 @@ class TestSupervisor(unittest.TestCase):
         self._drive(sup)
 
     def test_restart_unknown_daemon_no_op(self):
-        specs = [_DaemonSpec("a", (SLEEP, "30"))]
+        specs = [_DaemonSpec("a", ("/bin/sleep", "30"))]
         sup = _Supervisor(specs)
         sup.start_all()
         ok = sup.restart_daemon("ghost")
@@ -386,7 +385,7 @@ class TestSupervisor(unittest.TestCase):
         self._drive(sup)
 
     def test_restart_during_shutdown_is_no_op(self):
-        specs = [_DaemonSpec("git-gate", (SLEEP, "30"))]
+        specs = [_DaemonSpec("git-gate", ("/bin/sleep", "30"))]
         sup = _Supervisor(specs)
         sup.start_all()
         sup.request_shutdown(reason="test")
@@ -396,7 +395,7 @@ class TestSupervisor(unittest.TestCase):
         self._drive(sup)
 
     def test_pending_restart_dropped_during_shutdown(self):
-        specs = [_DaemonSpec("git-gate", (SLEEP, "30"))]
+        specs = [_DaemonSpec("git-gate", ("/bin/sleep", "30"))]
         sup = _Supervisor(specs)
         sup.start_all()
         time.sleep(0.1)
@@ -414,8 +413,8 @@ class TestSupervisor(unittest.TestCase):
         # both should receive SIGTERM and exit. Signal-only
         # shutdown clamps to a zero supervisor exit code.
         specs = [
-            _DaemonSpec("a", (SLEEP, "60")),
+            _DaemonSpec("a", ("/bin/sleep", "60")),
-            _DaemonSpec("b", (SLEEP, "60")),
+            _DaemonSpec("b", ("/bin/sleep", "60")),
         ]
         sup = _Supervisor(specs)
         sup.start_all()
@@ -450,7 +449,7 @@ class TestSupervisor(unittest.TestCase):
         self.assertEqual(0, rc)
 
     def test_idempotent_shutdown_requests(self):
-        specs = [_DaemonSpec("a", (SLEEP, "60"))]
+        specs = [_DaemonSpec("a", ("/bin/sleep", "60"))]
         sup = _Supervisor(specs)
         sup.start_all()
         time.sleep(0.1)
@@ -471,7 +470,7 @@ class TestMainEndToEnd(unittest.TestCase):
 
     @classmethod
     def setUpClass(cls):
-        for p in ("/bin/sh", SLEEP):
+        for p in ("/bin/sh", "/bin/sleep"):
             if not Path(p).exists():
                 raise unittest.SkipTest(f"missing {p}")
 
@@ -486,8 +485,8 @@ class TestMainEndToEnd(unittest.TestCase):
             "import os, runpy, sys\n"
             "from bot_bottle import gateway_init as si\n"
             "si._DAEMONS = (\n"
-            f"  si._DaemonSpec('alpha', ({SLEEP!r},'30')),\n"
+            "  si._DaemonSpec('alpha', ('/bin/sleep','30')),\n"
-            f"  si._DaemonSpec('beta',  ({SLEEP!r},'30')),\n"
+            "  si._DaemonSpec('beta',  ('/bin/sleep','30')),\n"
             ")\n"
             "sys.exit(si.main([]))\n"
         )