fix(types): remove unused new_env_var_secret import

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

.coveragerc

@@ -1,6 +1,10 @@
 [run]
 branch = True
 source = .
+# Store paths relative to the project root so .coverage.* files produced on
+# different runners (ubuntu-latest vs self-hosted KVM) can be combined by the
+# coverage job without a [paths] remapping section.
+relative_files = True
 
 [report]
 # Coverage policy: see docs/decisions/0004-coverage-policy.md.

.gitea/workflows/canaries.yml

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

.gitea/workflows/lint.yml

@@ -13,20 +13,30 @@ jobs:
     steps:
       - uses: actions/checkout@v3
 
-      - name: Set up Python
-        uses: actions/setup-python@v4
-        with:
-          python-version: "3.12"
-
+      # No actions/setup-python: the runner image already ships Python 3.12,
+      # and older act_runner engines mishandle setup-python's PATH. Install
+      # into the ephemeral job container's system Python — the pylint/pyright
+      # console scripts land on /usr/local/bin (on PATH) so the steps below
+      # still resolve. --break-system-packages is safe: the container is
+      # disposable.
       - name: Install dev dependencies
-        run: |
-          python -m pip install --upgrade pip
-          pip install -r requirements-dev.txt
+        run: python3 -m pip install --break-system-packages -r requirements-dev.txt
 
       - name: Run pylint
         run: |
-          # Run pylint on all Python files in the repo
-          find . -name '*.py' -not -path './.venv/*' -not -path './.git/*' | xargs pylint --fail-under=8.0
+          # Pylint's normal exit code is nonzero for any emitted finding,
+          # regardless of --fail-under. Preserve the full report but enforce
+          # the aggregate score this workflow promises.
+          set +e
+          find . -name '*.py' -not -path './.venv/*' -not -path './.git/*' \
+            | xargs pylint --fail-under=8.0 \
+            | tee /tmp/pylint-output.txt
+          set -e
+          SCORE=$(sed -n \
+            's/^Your code has been rated at \([-0-9.]*\)\/10.*/\1/p' \
+            /tmp/pylint-output.txt | tail -1)
+          test -n "$SCORE"
+          awk -v score="$SCORE" 'BEGIN { exit !(score >= 8.0) }'
 
       - name: Run pyright
         run: |

.gitea/workflows/prd-number.yml

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

.gitea/workflows/test.yml

@@ -1,19 +1,21 @@
-# Run the project's test suite on every PR push and on push to main.
+# Run the project's test suite when package or runtime inputs change on a PR
+# or on push to main.
 #
 # The suite uses stdlib `unittest` discovery — no external Python
 # dependencies are required to execute it. Tests are split by directory:
 #
 #   tests/unit/         — pure unit tests; always run
-#   tests/integration/  — need a reachable Docker daemon; skip cleanly
-#                         (via tests/_docker.py:skip_unless_docker) when
-#                         Docker isn't available on the runner
+#   tests/integration/  — need a reachable backend; skip cleanly when
+#                         the backend isn't available on the runner
 #   tests/canaries/     — upstream regression canaries; run on a separate
 #                         schedule (see canaries.yml), not here
 #
-# This workflow assumes the Gitea Actions runner exposes the host Docker
-# socket to the job container so `docker` commands inside the job can
-# reach the daemon. If that's not yet configured on the runner the
-# integration tests will skip rather than fail.
+# Each test job runs once under coverage and uploads a small .coverage.*
+# artifact. The `coverage` job combines them — no test reruns, no KVM
+# dependency on that job. For main-branch pushes only, the tested rootfs
+# and matching dropbear are uploaded so `publish-infra` can publish the
+# byte-identical artifact that was tested. PRs avoid the ~194 MB rootfs
+# transfer entirely.
 
 name: test
 
@@ -22,10 +24,35 @@ on:
     branches:
       - main
     paths:
-      - '**.py'
+      - 'bot_bottle/**'
+      - 'tests/**/*.py'
+      - 'cli.py'
+      - 'scripts/coverage.sh'
+      - 'scripts/critical-modules.txt'
+      - 'scripts/diff_coverage.py'
+      - 'scripts/tracker_policy.py'
+      - 'scripts/firecracker-netpool.sh'
+      - 'Dockerfile*'
+      - 'pyproject.toml'
+      - 'requirements-dev.txt'
+      - '.coveragerc'
+      - '.dockerignore'
   pull_request:
     paths:
-      - '**.py'
+      - 'bot_bottle/**'
+      - 'tests/**/*.py'
+      - 'cli.py'
+      - 'scripts/coverage.sh'
+      - 'scripts/critical-modules.txt'
+      - 'scripts/diff_coverage.py'
+      - 'scripts/tracker_policy.py'
+      - 'scripts/firecracker-netpool.sh'
+      - 'Dockerfile*'
+      - 'pyproject.toml'
+      - 'requirements-dev.txt'
+      - '.coveragerc'
+      - '.dockerignore'
+  workflow_dispatch:
 
 jobs:
   unit:
@@ -34,30 +61,47 @@ jobs:
       - name: Checkout
         uses: actions/checkout@v4
 
-      - name: Set up Python
-        uses: actions/setup-python@v5
-        with:
-          python-version: "3.12"
-
+      # No actions/setup-python: the runner image already ships Python 3.12,
+      # and older act_runner engines mishandle setup-python's PATH (coverage
+      # lands in one interpreter, `python3` resolves to another). Install
+      # straight into the ephemeral job container's system Python —
+      # --break-system-packages is safe because the container is disposable.
       - name: Install dev requirements
-        run: python3 -m pip install -r requirements-dev.txt
+        run: python3 -m pip install --break-system-packages -r requirements-dev.txt
 
-      - name: Run unit tests
+      - name: Run unit tests with coverage
+        env:
+          COVERAGE_FILE: ${{ github.workspace }}/.coverage.unit
         run: python3 -m coverage run -m unittest discover -t . -s tests/unit -v
 
       - name: Report unit coverage
+        env:
+          COVERAGE_FILE: ${{ github.workspace }}/.coverage.unit
         run: python3 -m coverage report -m
 
-  integration:
+      # upload-artifact@v3's glob skips dotfiles, so a bare `.coverage.unit`
+      # silently uploads nothing ("No files were found"). Stage it under a
+      # non-dot name; the coverage job renames it back before `coverage
+      # combine`. `cp` also fails loudly if coverage never wrote the file.
+      - name: Stage unit coverage for upload
+        run: cp .coverage.unit coverage-unit.dat
+
+      - name: Upload unit coverage artifact
+        uses: actions/upload-artifact@v3
+        with:
+          name: coverage-unit
+          path: coverage-unit.dat
+
+  integration-docker:
     runs-on: ubuntu-latest
     steps:
       - name: Checkout
         uses: actions/checkout@v4
 
-      - name: Set up Python
-        uses: actions/setup-python@v5
-        with:
-          python-version: "3.12"
+      # No actions/setup-python (see the note in the `unit` job); the
+      # container's system Python 3.12 runs the stdlib test suite directly.
+      - name: Install coverage
+        run: python3 -m pip install --break-system-packages coverage
 
       - name: Show environment
         run: |
@@ -68,33 +112,193 @@ jobs:
             echo "docker not on PATH — integration tests will skip"
           fi
 
-      - name: Run integration tests
-        run: python3 -m unittest discover -t . -s tests/integration -v
+      - name: Run integration tests (docker) with coverage
+        env:
+          BOT_BOTTLE_BACKEND: docker
+          COVERAGE_FILE: ${{ github.workspace }}/.coverage.docker
+        run: python3 -m coverage run -m unittest discover -t . -s tests/integration -v
 
-  # Combined unit+integration coverage report (informational). See
-  # docs/decisions/0004-coverage-policy.md.
+      # Non-dot name so upload-artifact's dotfile-skipping glob picks it up.
+      - name: Stage docker coverage for upload
+        run: cp .coverage.docker coverage-docker.dat
+
+      - name: Upload docker coverage artifact
+        uses: actions/upload-artifact@v3
+        with:
+          name: coverage-docker
+          path: coverage-docker.dat
+
+  # Integration tests against the Firecracker backend. Runs on a self-hosted
+  # KVM runner (label `kvm`) where /dev/kvm and the TAP/nft pool are available.
   #
-  # The hard diff-coverage gate (changed lines >= 90%) is DEFERRED: the
-  # Firecracker backend's VM/SSH orchestration is covered by the integration
-  # suite, which needs /dev/kvm + the provisioned TAP/nft pool — a
-  # container-based runner skips it and those lines read uncovered, so the
-  # gate can't pass here. Re-enabling it on a self-hosted KVM runner is
-  # tracked separately (see PRD 0069 / #348 and the ci-runner branch).
+  # Restricted to same-repo PRs, push to main, and workflow_dispatch — fork
+  # PRs don't execute untrusted code on the privileged runner.
+  #
+  # Runner prerequisites (provision once; see README "Firecracker on Linux"):
+  # `firecracker` on PATH, `/dev/kvm` accessible, cached kernel +
+  # static dropbear at /var/cache/bot-bottle-fc/dropbear, and the pool as a
+  # persistent systemd unit.
+  #
+  # The infra candidate is built here directly (no artifact download) to
+  # eliminate the ~70 s ubuntu-latest upload + ~83 s combined download that
+  # the old build-infra → integration-firecracker + coverage chain incurred.
+  # For main-branch pushes the tested rootfs and matching dropbear are
+  # uploaded so publish-infra can publish the byte-identical artifact; PRs
+  # skip those uploads entirely.
+  integration-firecracker:
+    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: Build infra candidate from this checkout
+        env:
+          BOT_BOTTLE_FC_DROPBEAR: /var/cache/bot-bottle-fc/dropbear
+        run: python3 -m bot_bottle.backend.firecracker.publish_infra --output infra-candidate --reuse-published
+
+      - name: Replace the persistent infra VM with the candidate
+        run: python3 -c 'from bot_bottle.backend.firecracker import infra_vm; infra_vm.stop()'
+
+      # No dev-requirements install: `coverage` is already provided by the
+      # self-hosted runner's Nix python env, and that env has no `pip`
+      # module to install into anyway.
+      - name: Run integration tests (firecracker) with coverage
+        env:
+          BOT_BOTTLE_BACKEND: firecracker
+          BOT_BOTTLE_INFRA_ARTIFACT_DIR: ${{ github.workspace }}/infra-candidate
+          COVERAGE_FILE: ${{ github.workspace }}/.coverage.firecracker
+        run: python3 -m coverage run -m unittest discover -t . -s tests/integration -v
+
+      # Non-dot name so upload-artifact's dotfile-skipping glob picks it up.
+      - name: Stage firecracker coverage for upload
+        run: cp .coverage.firecracker coverage-firecracker.dat
+
+      - name: Upload firecracker coverage artifact
+        uses: actions/upload-artifact@v3
+        with:
+          name: coverage-firecracker
+          path: coverage-firecracker.dat
+
+      # Only upload the large rootfs artifact on main-branch pushes;
+      # PRs avoid the ~194 MB transfer. publish-infra only runs on main
+      # and downloads these to publish the byte-identical tested rootfs.
+      - name: Upload tested rootfs (main branch only)
+        if: github.event_name == 'push' && github.ref == 'refs/heads/main'
+        uses: actions/upload-artifact@v3
+        with:
+          name: infra-candidate
+          path: infra-candidate/
+
+      - name: Upload dropbear for publish verification (main branch only)
+        if: github.event_name == 'push' && github.ref == 'refs/heads/main'
+        uses: actions/upload-artifact@v3
+        with:
+          name: firecracker-inputs
+          path: /var/cache/bot-bottle-fc/dropbear
+
+  # Combined coverage gate: aggregates .coverage.* artifacts uploaded by each
+  # test job, then runs the diff-coverage gate (new/changed lines >= 90%).
+  #
+  # Runs on ubuntu-latest — no KVM needed, no test reruns. Coverage files use
+  # relative_files = True (.coveragerc) so they combine cleanly across runners.
+  # Each test job sets COVERAGE_FILE to an absolute path so coverage.py writes
+  # to a known location that upload-artifact can find regardless of runner env.
+  #
+  # Restricted to the same events as integration-firecracker: it depends on
+  # that job's coverage artifact and skips for fork PRs alongside it.
   coverage:
+    needs: [unit, integration-docker, integration-firecracker]
+    timeout-minutes: 15
     runs-on: ubuntu-latest
+    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: Set up Python
-        uses: actions/setup-python@v5
+      - name: Install coverage
+        run: python3 -m pip install --break-system-packages coverage
+
+      - name: Download unit coverage artifact
+        uses: actions/download-artifact@v3
         with:
-          python-version: "3.12"
+          name: coverage-unit
+          path: ${{ github.workspace }}
 
-      - name: Install dev requirements
-        run: python3 -m pip install -r requirements-dev.txt
+      - name: Download docker coverage artifact
+        uses: actions/download-artifact@v3
+        with:
+          name: coverage-docker
+          path: ${{ github.workspace }}
 
-      - name: Combined coverage report (unit + integration)
-        run: PYTHON=python3 bash scripts/coverage.sh critical
+      - name: Download firecracker coverage artifact
+        uses: actions/download-artifact@v3
+        with:
+          name: coverage-firecracker
+          path: ${{ github.workspace }}
+
+      # Rename the non-dot upload names back to the .coverage.* files that
+      # `coverage combine` discovers (see the staging steps in each test job).
+      - name: Reassemble coverage data files
+        run: |
+          mv coverage-unit.dat .coverage.unit
+          mv coverage-docker.dat .coverage.docker
+          mv coverage-firecracker.dat .coverage.firecracker
+
+      - name: Combined coverage (unit + integration, incl. firecracker)
+        run: PYTHON=python3 bash scripts/coverage.sh aggregate 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: [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 rootfs
+        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. Download the SAME dropbear integration-firecracker used, or
+      # the recheck computes a "<missing>"-dropbear version and rejects the
+      # candidate.
+      - name: Download the staged dropbear (matches build's version)
+        uses: actions/download-artifact@v3
+        with:
+          name: firecracker-inputs
+          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

@@ -0,0 +1,17 @@
+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

@@ -0,0 +1,18 @@
+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/update-badges.yml

@@ -14,27 +14,27 @@ on:
 jobs:
   update-badges:
     runs-on: ubuntu-latest
+    permissions:
+      contents: write
+
     steps:
       - uses: actions/checkout@v3
         with:
           fetch-depth: 0
-          token: ${{ secrets.GITHUB_TOKEN }}
-
-      - name: Set up Python
-        uses: actions/setup-python@v4
-        with:
-          python-version: '3.12'
+          token: ${{ secrets.BADGE_PUSH_TOKEN }}
 
+      # No actions/setup-python: the runner image ships Python 3.12 and older
+      # act_runner engines mishandle setup-python's PATH. Install into the
+      # ephemeral job container's system Python (--break-system-packages is
+      # safe because the container is disposable).
       - name: Install dev dependencies
-        run: |
-          python -m pip install --upgrade pip
-          pip install -r requirements-dev.txt
+        run: python3 -m pip install --break-system-packages -r requirements-dev.txt
 
       - name: Run coverage and extract percentage
         id: coverage
         run: |
-          python -m coverage run -m unittest discover -t . -s tests/unit > /dev/null 2>&1 || true
-          PERCENT=$(python -m coverage report 2>/dev/null | grep '^TOTAL' | grep -oP '\d+(?=%)' | tail -1)
+          python3 -m coverage run -m unittest discover -t . -s tests/unit > /dev/null 2>&1 || true
+          PERCENT=$(python3 -m coverage report 2>/dev/null | grep '^TOTAL' | grep -oP '\d+(?=%)' | tail -1)
           echo "percent=$PERCENT" >> $GITHUB_OUTPUT
           echo "Coverage: $PERCENT%"
 
@@ -45,7 +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=$(python -m coverage report --include="$INCLUDE" 2>/dev/null | grep '^TOTAL' | grep -oP '\d+(?=%)' | tail -1)
+          PERCENT=$(python3 -m coverage report --include="$INCLUDE" 2>/dev/null | grep '^TOTAL' | grep -oP '\d+(?=%)' | tail -1)
           echo "percent=$PERCENT" >> $GITHUB_OUTPUT
           echo "Core coverage: $PERCENT%"
 

Dockerfile.gateway

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

Dockerfile.infra

@@ -1,45 +1,22 @@
-# Firecracker single infra-VM image (PRD 0070 Stage B).
+# Shared infra image: gateway data plane + orchestrator control plane.
 #
-# The per-host infra VM runs the orchestrator control plane, the gateway
-# data plane, AND builds agent images (buildah) — all in one microVM (see
-# backend/firecracker/infra_vm.py). It composes:
-#   * FROM the gateway image (mitmproxy / git / gitleaks / supervise + the
-#     flat daemon modules) — now trixie-based, so buildah 1.39 is available;
-#   * `COPY --from` the orchestrator image's content (the single definition
-#     of the control-plane payload — see Dockerfile.orchestrator), so this
-#     VM and the docker backend share one orchestrator definition; and
-#   * buildah, installed HERE only (the docker orchestrator/gateway images
-#     never carry it).
+# Used directly by the Docker backend (run as one `bot-bottle-infra`
+# container, replacing the prior two-container split). The Firecracker
+# backend extends this via Dockerfile.infra.fc, adding buildah/crun/
+# netavark for in-VM agent-image building.
+#
+# Dockerfile.orchestrator is the single definition of the orchestrator
+# content (the lean `bot_bottle` package on python:3.12-slim). Both this
+# image and Dockerfile.infra.fc pull it in via `COPY --from`.
 #
 # multi-`FROM` can't union two bases (that's multi-stage, not multiple
 # inheritance), so the orchestrator content is pulled in via `COPY --from`
 # rather than a second base. Both images share the trixie `python:3.12-slim`
 # base, so the copy is clean (same python; future installed deps copy too).
-#
-# The docker backend keeps orchestrator + gateway as separate images; this
-# combined image exists only for the Firecracker single-VM cut. Splitting a
-# service back into its own VM later is a routing change, not a repackaging
-# (PRD 0070's "secret concentration"; a disposable builder can boot from
-# this same image on its own TAP).
 FROM bot-bottle-gateway:latest
 
-# --- in-VM agent-image builder (PRD 0069 Stage 3) -------------------
-# The Firecracker backend builds users' agent Dockerfiles *inside this VM*
-# with buildah (rootless, daemonless) instead of on the host — no host
-# Docker daemon, no root-equivalent `docker` group. `crun` is the OCI
-# runtime; `netavark` + `aardvark-dns` are the network backend for `FROM`
-# pulls + `RUN` egress. Requires the trixie base (buildah 1.39: bookworm's
-# 1.28 can't parse Dockerfile heredocs that agent images use).
-RUN apt-get update \
- && apt-get install -y --no-install-recommends \
-      buildah crun netavark aardvark-dns \
- && rm -rf /var/lib/apt/lists/*
-# vfs + chroot: buildah works as root in the bare microVM (no
-# fuse-overlayfs / overlay module / subuid maps). Matches image_builder.
-ENV STORAGE_DRIVER=vfs \
-    BUILDAH_ISOLATION=chroot
-
-# The orchestrator content, pulled from its single definition. The gateway
-# image already has the flat daemon modules under /app; this adds the full
-# `bot_bottle` package so `python3 -m bot_bottle.orchestrator` resolves.
+# The orchestrator content, from its single definition. The gateway image
+# already has the flat daemon modules under /app; this adds the full
+# `bot_bottle` package so `python3 -m bot_bottle.orchestrator` resolves —
+# used by gateway_init when BOT_BOTTLE_GATEWAY_DAEMONS includes `orchestrator`.
 COPY --from=bot-bottle-orchestrator:latest /app/bot_bottle /app/bot_bottle

Dockerfile.infra.fc

@@ -0,0 +1,23 @@
+# Firecracker infra VM image (PRD 0070 Stage B).
+#
+# Extends the shared infra base (Dockerfile.infra: gateway + orchestrator
+# control plane) with the in-VM agent-image builder. The Firecracker backend
+# builds users' agent Dockerfiles *inside this VM* with buildah (rootless,
+# daemonless) instead of on the host — no host Docker daemon, no
+# root-equivalent `docker` group.
+#
+# Requires the trixie base from bot-bottle-gateway (buildah 1.39: bookworm's
+# 1.28 can't parse Dockerfile heredocs that agent images use).
+#
+# `crun` is the OCI runtime; `netavark` + `aardvark-dns` are the network
+# backend for `FROM` pulls + `RUN` egress. `vfs` + `chroot`: buildah works
+# as root in the bare microVM (no fuse-overlayfs / overlay module / subuid
+# maps). Matches image_builder.
+FROM bot-bottle-infra:latest
+
+RUN apt-get update \
+ && apt-get install -y --no-install-recommends \
+      buildah crun netavark aardvark-dns \
+ && rm -rf /var/lib/apt/lists/*
+ENV STORAGE_DRIVER=vfs \
+    BUILDAH_ISOLATION=chroot

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-82%25-brightgreen)](https://coverage.readthedocs.io/)
-[![core coverage](https://img.shields.io/badge/core%20coverage-95%25-brightgreen)](https://gitea.dideric.is/didericis/bot-bottle/src/branch/main/docs/decisions/0004-coverage-policy.md)
+[![coverage](https://img.shields.io/badge/coverage-83%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)
 
 **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.
 
@@ -90,6 +90,8 @@ 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
 ```
@@ -171,6 +173,15 @@ When an outbound DLP detector matches a token, the route's `dlp.outbound_on_matc
 
 More examples in `examples/`. Full design lives under `docs/prds/`; the trust-boundary rationale is in `docs/prds/0011-per-file-md-manifest.md`.
 
+## Tracker policy
+
+Issues are the canonical work items and own all tracker labels; every issue
+must have at least one. Pull requests stay unlabeled and deliberately reference
+an issue with `Closes #…`, `Part of #…`, or another form defined in
+[`ADR 0005`](docs/decisions/0005-issues-own-tracker-metadata.md). Gitea Actions
+enforces the convention for new work from 2026-07-18 onward. Earlier closed
+PRs are grandfathered rather than given artificial retrospective issues.
+
 ## Trademarks
 
 bot-bottle is an independent project and is not affiliated with, endorsed by, or sponsored by Anthropic, PBC. "Claude" and "Claude Code" are trademarks of Anthropic, PBC; the project name uses "claude" descriptively to indicate that the tool runs Claude Code inside a sandbox.

bot_bottle/agent_provider.py

@@ -45,6 +45,10 @@ PROVIDER_TEMPLATES = frozenset({PROVIDER_CLAUDE, PROVIDER_CODEX, PROVIDER_PI})
 # forward_host_credentials is enabled. Pipelock must pass these through
 # (no TLS MITM) or its header DLP blocks the injected JWT.
 CODEX_HOST_CREDENTIAL_HOSTS = ("api.openai.com", "chatgpt.com")
+
+# Host that egress injects the host Claude bearer on when Claude
+# forward_host_credentials is enabled.
+CLAUDE_HOST_CREDENTIAL_HOSTS = ("api.anthropic.com",)
 PromptMode = Literal[
     "append_file",
     "read_prompt_file",
@@ -257,7 +261,28 @@ class AgentProvider(ABC):
         Default: Debian/node — writes the git-gate insteadOf gitconfig
         and sets user.name/email as node. Workspace copy runs through
         BottleBackend.provision_workspace against the running bottle."""
-        from .log import info
+        from .log import die, info
+
+        # Firecracker exports image rootfs files through an unprivileged host
+        # tar extraction, so image-time ownership of XDG directories is not
+        # preserved.  Git consults ~/.config/git even when the actual config
+        # is ~/.gitconfig; an unreadable directory there can prevent the
+        # git-gate insteadOf rules below from taking effect.  Repair this at
+        # runtime, after every backend's copy/export path has completed.
+        git_xdg_dir = f"{plan.guest_home}/.config/git"
+        repair = bottle.exec(
+            f"chown node:node {shlex.quote(plan.guest_home)} && "
+            f"chmod 755 {shlex.quote(plan.guest_home)} && "
+            f"mkdir -p {shlex.quote(git_xdg_dir)} && "
+            f"chown -R node:node {shlex.quote(f'{plan.guest_home}/.config')} && "
+            f"chmod -R u+rwX,go+rX {shlex.quote(f'{plan.guest_home}/.config')}",
+            user="root",
+        )
+        if repair.returncode != 0:
+            die(
+                "git provisioning: could not make the runtime Git config "
+                f"directory readable: {(repair.stderr or repair.stdout).strip()}"
+            )
 
         manifest_bottle = plan.manifest.bottle
         if manifest_bottle.git:
@@ -280,11 +305,27 @@ class AgentProvider(ABC):
                 f"{len(manifest_bottle.git)} insteadOf rule(s)"
             )
             bottle.cp_in(str(config_file), guest_gitconfig)
-            bottle.exec(
+            permissions = bottle.exec(
                 f"chown node:node {shlex.quote(guest_gitconfig)} && "
                 f"chmod 644 {shlex.quote(guest_gitconfig)}",
                 user="root",
             )
+            if permissions.returncode != 0:
+                die(
+                    "git provisioning: could not set ownership on "
+                    f"{guest_gitconfig}: "
+                    f"{(permissions.stderr or permissions.stdout).strip()}"
+                )
+            configured = bottle.exec(
+                "git config --global --get-regexp '^url\\..*\\.insteadof$'",
+                user="node",
+            )
+            if configured.returncode != 0:
+                die(
+                    "git provisioning: the runtime user cannot read the "
+                    f"git-gate insteadOf rules from {guest_gitconfig}: "
+                    f"{(configured.stderr or configured.stdout).strip()}"
+                )
 
         gu = manifest_bottle.git_user
         if not gu.is_empty():

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._connect() as conn:
+        with self._connection() 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._connect() as conn:
+        with self._connection() as conn:
             rows = conn.execute(
                 """
                 SELECT * FROM supervise_audit_entries

bot_bottle/backend/__init__.py

@@ -37,15 +37,16 @@ import os
 import shlex
 import sys
 from abc import ABC, abstractmethod
-from contextlib import AbstractContextManager
+from contextlib import AbstractContextManager, contextmanager
 from dataclasses import dataclass
 from pathlib import Path
-from typing import Any, Generic, Sequence, TypeVar
+from typing import TYPE_CHECKING, Any, Generator, Generic, Sequence, TypeVar
 
 from ..agent_provider import AgentProvisionPlan, get_provider, build_agent_provision_plan
 from ..egress import EgressPlan
 from ..git_gate import GitGatePlan
-from ..log import die, info
+from ..log import die, info, warn
+from ..util import read_tty_line
 from ..manifest import Manifest, ManifestIndex
 from ..supervise import SupervisePlan
 from ..util import expand_tilde
@@ -54,6 +55,9 @@ 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:
@@ -79,6 +83,9 @@ class BottleSpec:
     # True when launched via --headless (no TTY, no interactive prompts).
     # The git-gate host-key preflight uses this to error rather than prompt.
     headless: bool = False
+    # Image startup policy. "fresh" preserves the normal build path;
+    # "cached" reuses the current local image/artifact without rebuilding.
+    image_policy: str = "fresh"
 
 
 @dataclass(frozen=True)
@@ -274,6 +281,18 @@ PlanT = TypeVar("PlanT", bound=BottlePlan)
 CleanupT = TypeVar("CleanupT", bound=BottleCleanupPlan)
 
 
+@dataclass(frozen=True)
+class BottleImages:
+    """Resolved image references (or artifact paths) for a bottle launch.
+
+    For Docker/macOS-container backends, `agent` and `sidecar` are string
+    image refs. For the smolmachines backend they are Path objects pointing
+    to pre-built `.smolmachine` artifacts."""
+
+    agent: str | Path
+    sidecar: str | Path = ""
+
+
 class BottleBackend(ABC, Generic[PlanT, CleanupT]):
     """Abstract base for selectable bottle backends. Concrete subclasses
     (e.g. DockerBottleBackend) own their own prepare/launch impls.
@@ -433,9 +452,27 @@ class BottleBackend(ABC, Generic[PlanT, CleanupT]):
         prompt file, Dockerfile path, and guest home all live on
         `agent_provision_plan` — the source of truth."""
 
+    def prelaunch_checks(self, plan: PlanT) -> None:
+        """Raise StaleImageError if any cached image used by this plan is stale.
+        No-op default; backends override to call the shared check_stale*
+        helpers on their image/artifact timestamps. Called by the CLI before
+        launch so the operator can be prompted outside the launch context."""
+
+    @contextmanager
+    def launch(self, plan: PlanT) -> Generator[Bottle, None, None]:
+        """Template: build or load images, then delegate to _launch_impl."""
+        images = self._build_or_load_images(plan)
+        with self._launch_impl(plan, images) as bottle:
+            yield bottle
+
     @abstractmethod
-    def launch(self, plan: PlanT) -> AbstractContextManager[Bottle]:
-        """Build/run the bottle and yield a handle; tear down on exit."""
+    def _build_or_load_images(self, plan: PlanT) -> BottleImages:
+        """Return the agent and sidecar image references (or artifact paths)
+        for this plan, building fresh images when the policy requires it."""
+
+    @abstractmethod
+    def _launch_impl(self, plan: PlanT, images: BottleImages) -> AbstractContextManager[Bottle]:
+        """Bring up the bottle using pre-resolved images; yield a handle; tear down on exit."""
 
     def provision(self, plan: PlanT, bottle: "Bottle") -> str | None:
         """Copy host-side files (CA cert, prompt, skills, .git) into
@@ -584,68 +621,170 @@ class BottleBackend(ABC, Generic[PlanT, CleanupT]):
         Not called by the launch path or the test suite."""
 
 
-# Import concrete backend classes AFTER the base types are defined, so
-# each backend module can pull BottleSpec / BottlePlan / BottleBackend
-# via `from . import ...` without hitting a partially-initialized module.
-from .docker import DockerBottleBackend  # noqa: E402  # pylint: disable=wrong-import-position
-from .firecracker import FirecrackerBottleBackend  # noqa: E402  # pylint: disable=wrong-import-position
-from .macos_container import MacosContainerBottleBackend  # noqa: E402  # pylint: disable=wrong-import-position
-
-# Freezer is imported after the backend classes for the same reason:
-# Freezer.commit_slug constructs ActiveAgent, which must be fully
-# defined first.
-from .freeze import CommitCancelled, Freezer, get_freezer  # noqa: E402  # pylint: disable=wrong-import-position
+# _backends is None until the first call to _get_backends(), at which
+# point all three concrete backend classes are imported and instantiated.
+# Keeping the imports out of module scope means that importing any
+# backend sub-module (e.g. `backend.docker.util`) no longer drags the
+# firecracker and macos-container implementations into memory.
+#
+# Tests may replace _backends with a {name: fake} dict via patch.object;
+# _get_backends() returns the current module-level value as-is when it
+# is not None, so test fakes take effect without triggering real imports.
+_backends: dict[str, BottleBackend[Any, Any]] | None = None
 
 
-# The dict is heterogeneous: each value is a BottleBackend specialized
-# over its own plan type. Concrete plan types are erased here because
-# the registry is selected at runtime and the CLI only needs the
-# unparameterized methods (prepare → plan → launch(plan), cleanup, etc.).
-_BACKENDS: dict[str, BottleBackend[Any, Any]] = {
-    "docker": DockerBottleBackend(),
-    "firecracker": FirecrackerBottleBackend(),
-    "macos-container": MacosContainerBottleBackend(),
-}
+def _get_backends() -> dict[str, BottleBackend[Any, Any]]:
+    """Return the registry of all backend instances, loading lazily on first call."""
+    global _backends  # pylint: disable=global-statement
+    if _backends is None:
+        from .docker import DockerBottleBackend
+        from .firecracker import FirecrackerBottleBackend
+        from .macos_container import MacosContainerBottleBackend
+        _backends = {
+            "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 (CLI `--backend=<name>` passes through here)
+      1. explicit arg (e.g. resume passes the recorded backend name)
       2. BOT_BOTTLE_BACKEND env var
-      3. `macos-container` on compatible macOS hosts
-      4. `firecracker` on KVM-capable Linux hosts
-      5. default `docker`
+      3. auto-selection: VM backend first, docker fallback with prompt
+
+    `prompt` controls whether auto-selection may block on an interactive
+    [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") or _default_backend_name()
-    if resolved not in _BACKENDS:
-        known = ", ".join(sorted(_BACKENDS))
+    resolved = name or os.environ.get("BOT_BOTTLE_BACKEND")
+    if resolved is None:
+        resolved = _auto_select_backend(prompt=prompt)
+    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 _default_backend_name() -> str:
+def _platform_vm_suggestion() -> 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 `_BACKENDS`. Used by
+    """Sorted tuple of all backend keys in `_get_backends()`. Used by
     argparse (`--backend` choices) and the dashboard's backend
     picker."""
-    return tuple(sorted(_BACKENDS))
+    return tuple(sorted(_get_backends()))
 
 
 def has_backend(name: str) -> bool:
@@ -657,9 +796,10 @@ def has_backend(name: str) -> bool:
 
     Returns False for unknown names so callers can pass
     arbitrary input without separate validation."""
-    if name not in _BACKENDS:
+    backends = _get_backends()
+    if name not in backends:
         return False
-    return _BACKENDS[name].is_available()
+    return backends[name].is_available()
 
 
 def enumerate_active_agents() -> list[ActiveAgent]:
@@ -675,10 +815,11 @@ def enumerate_active_agents() -> list[ActiveAgent]:
     deterministic tiebreaker. Agents with missing metadata
     (`started_at == ""`) sort first."""
     out: list[ActiveAgent] = []
-    for name in known_backend_names():
-        if not has_backend(name):
+    backends = _get_backends()
+    for name in sorted(backends):
+        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/consolidated_util.py

@@ -0,0 +1,68 @@
+"""Shared helpers for the consolidated launch sequence (PRD 0070).
+
+Logic that was duplicated across the docker, macos_container, and
+firecracker consolidated_launch modules — extracted so each backend
+imports it rather than re-implementing it.
+"""
+
+from __future__ import annotations
+
+import dataclasses
+
+from ..egress import EgressPlan
+from ..git_gate import GitGatePlan
+from ..orchestrator.client import OrchestratorClient, RegisteredBottle
+from ..orchestrator.registration import registration_inputs
+from ..orchestrator.secret_store import new_env_var_secret
+from .docker.gateway_provision import GatewayTransport, deprovision_git_gate, provision_git_gate
+
+
+def provision_bottle(
+    client: OrchestratorClient,
+    source_ip: str,
+    egress_plan: EgressPlan,
+    git_gate_plan: GitGatePlan,
+    transport: GatewayTransport,
+    *,
+    image_ref: str = "",
+    tokens: dict[str, str] | None = None,
+) -> RegisteredBottle:
+    """Register the bottle and provision its git-gate state. Rolls back the
+    registration if provisioning fails so no orphan is left.
+
+    Generates a fresh ENV_VAR_SECRET, passes it to the orchestrator so it can
+    encrypt the token values at rest, and stamps the secret onto the returned
+    ``RegisteredBottle`` so callers can inject it into the agent container's
+    environment."""
+    inputs = registration_inputs(egress_plan)
+    env_var_secret = new_env_var_secret()
+    reg = client.register_bottle(
+        source_ip, image_ref=image_ref, policy=inputs.policy,
+        metadata=inputs.metadata, tokens=tokens, env_var_secret=env_var_secret,
+    )
+    try:
+        provision_git_gate(transport, reg.bottle_id, git_gate_plan)
+    except Exception:
+        client.teardown_bottle(reg.bottle_id)
+        raise
+    return dataclasses.replace(reg, env_var_secret=env_var_secret)
+
+
+def teardown_consolidated(
+    bottle_id: str,
+    transport: GatewayTransport,
+    *,
+    orchestrator_url: str,
+    timeout: float | None = None,
+) -> None:
+    """Deregister the bottle and remove its git-gate state. Both steps are
+    idempotent so this is safe from a cleanup trap."""
+    from ..orchestrator.config_store import DEFAULT_TEARDOWN_TIMEOUT_SECONDS
+    OrchestratorClient(
+        orchestrator_url,
+        timeout=timeout if timeout is not None else DEFAULT_TEARDOWN_TIMEOUT_SECONDS,
+    ).teardown_bottle(bottle_id)
+    deprovision_git_gate(transport, bottle_id)
+
+
+__all__ = ["provision_bottle", "teardown_consolidated"]

bot_bottle/backend/docker/backend.py

@@ -31,7 +31,7 @@ from ...env import ResolvedEnv
 from ...git_gate import GitGatePlan
 from ...supervise import SupervisePlan
 from ...manifest import Manifest
-from .. import ActiveAgent, BottleBackend, BottleSpec
+from .. import ActiveAgent, BottleBackend, BottleImages, BottleSpec
 from . import cleanup as _cleanup
 from . import enumerate as _enumerate
 from . import launch as _launch
@@ -100,9 +100,15 @@ class DockerBottleBackend(BottleBackend["DockerBottlePlan", "DockerBottleCleanup
             stage_dir=stage_dir,
         )
 
+    def prelaunch_checks(self, plan: DockerBottlePlan) -> None:
+        _launch.stale_checks(plan)
+
+    def _build_or_load_images(self, plan: DockerBottlePlan) -> BottleImages:
+        return _launch.build_or_load_images(plan)
+
     @contextmanager
-    def launch(self, plan: DockerBottlePlan) -> Generator[DockerBottle, None, None]:
-        with _launch.launch(plan, provision=self.provision) as bottle:
+    def _launch_impl(self, plan: DockerBottlePlan, images: BottleImages) -> Generator[DockerBottle, None, None]:
+        with _launch.launch(plan, images, provision=self.provision) as bottle:
             yield bottle
 
     def ensure_orchestrator(self) -> str:

bot_bottle/backend/docker/bottle_plan.py

@@ -39,6 +39,10 @@ class DockerBottlePlan(BottlePlan):
     # (egress proxy credentials, git-gate/supervise headers); set by launch
     # from the orchestrator registration. Empty pre-registration.
     identity_token: str = ""
+    # Encryption key for the agent's stored egress secrets; injected into the
+    # agent container as ENV_VAR_SECRET via the compose subprocess env (bare
+    # name — value never written to the compose file). Empty pre-registration.
+    env_var_secret: str = ""
 
     @property
     def container_name(self) -> str:

bot_bottle/backend/docker/consolidated_compose.py

@@ -17,6 +17,7 @@ from __future__ import annotations
 from typing import Any
 
 from ...egress import egress_agent_env_entries
+from ...orchestrator.secret_store import ENV_VAR_SECRET_NAME
 from ..util import AGENT_CA_BUNDLE, AGENT_CA_PATH
 from .bottle_plan import DockerBottlePlan
 from .egress import EGRESS_PORT
@@ -58,6 +59,10 @@ def consolidated_agent_compose(
     # the secret value never lands on argv or in the compose file.
     for name in sorted(plan.forwarded_env.keys()):
         env.append(name)
+    # ENV_VAR_SECRET: bare name so the value comes from the compose subprocess
+    # env (set in launch.py) and is never written to the compose file on disk.
+    if getattr(plan, "env_var_secret", ""):
+        env.append(ENV_VAR_SECRET_NAME)
     env.extend(egress_agent_env_entries(plan.egress_plan))
 
     service: dict[str, Any] = {

bot_bottle/backend/docker/consolidated_launch.py

@@ -1,19 +1,13 @@
 """Consolidated bottle launch sequence for the docker backend (PRD 0070).
 
-Composes the orchestrator primitives into the register/teardown sequence that
-replaces the per-bottle gateway:
+Composes the orchestrator primitives into the register/teardown sequence:
 
-  1. ensure the orchestrator control plane + shared gateway are up;
-  2. allocate the bottle a pinned source IP on the gateway network (the
-     attribution key), skipping the gateway's own address + live bottles;
-  3. register it (egress policy blob + slug metadata) → bottle id + identity
-     token;
-  4. provision its git-gate repos/creds into the running gateway.
+  1. ensure the single infra container (control plane + gateway) is up;
+  2. allocate the bottle a pinned source IP on the gateway network;
+  3. register it and provision its git-gate repos/creds into the gateway.
 
-It returns a `LaunchContext` with everything the agent container needs to
-attach — network, pinned IP, the gateway's address (its proxy target), the
-orchestrator URL, and the identity token. The agent `docker run` itself is
-the backend's job (it owns provider provisioning); this owns the
+Returns a `LaunchContext` with everything the agent container needs to
+attach. The agent `docker run` itself is the backend's job; this owns the
 orchestrator-facing wiring so that sequence stays testable in isolation.
 """
 
@@ -21,19 +15,18 @@ from __future__ import annotations
 
 from dataclasses import dataclass
 
+from ... import log
 from ...docker_cmd import run_docker
 from ...egress import EgressPlan
 from ...git_gate import GitGatePlan
 from ...orchestrator.client import OrchestratorClient
-from ...orchestrator.gateway import GATEWAY_NAME, GATEWAY_NETWORK
-from ...orchestrator.lifecycle import OrchestratorService
-from ...orchestrator.registration import registration_inputs
+from ...orchestrator.gateway import GATEWAY_NETWORK
+from ...orchestrator.lifecycle import INFRA_NAME, OrchestratorService
+from ...orchestrator.secret_store import ENV_VAR_SECRET_NAME
+from ..consolidated_util import provision_bottle
+from ..consolidated_util import teardown_consolidated as _teardown_util
+from .gateway_provision import DockerGatewayTransport
 from .gateway_net import next_free_ip
-from .gateway_provision import (
-    DockerGatewayTransport,
-    deprovision_git_gate,
-    provision_git_gate,
-)
 
 
 class ConsolidatedLaunchError(RuntimeError):
@@ -50,6 +43,7 @@ class LaunchContext:
     network: str            # the shared gateway network to attach to
     gateway_ip: str         # the gateway's address — the agent's proxy target
     orchestrator_url: str
+    env_var_secret: str = ""  # encryption key injected into the agent's env
 
 
 def _network_cidr(network: str) -> str:
@@ -75,28 +69,85 @@ def _container_ip(name: str, network: str) -> str:
     ip = proc.stdout.strip()
     if proc.returncode != 0 or not ip:
         raise ConsolidatedLaunchError(
-            f"gateway {name} has no address on {network}: {proc.stderr.strip()}"
+            f"container {name} has no address on {network}: {proc.stderr.strip()}"
         )
     return ip
 
 
 def _network_container_ips(network: str) -> list[str]:
     """Every address currently assigned on the gateway network — the ground
-    truth for "in use": the gateway + orchestrator infrastructure containers
-    and every live agent. Read from the network so a new bottle can't collide
-    with anything actually attached (a registry-only view would miss the
-    orchestrator/gateway containers)."""
+    truth for "in use": the infra container and every live agent. Read from
+    the network so a new bottle can't collide with anything actually attached."""
     proc = run_docker([
         "docker", "network", "inspect", "--format",
         "{{range .Containers}}{{.IPv4Address}} {{end}}", network,
     ])
     ips: list[str] = []
     for entry in proc.stdout.split():
-        # entries look like "172.20.0.2/16" — keep the address.
         ips.append(entry.split("/", 1)[0])
     return ips
 
 
+def _reprovision_running_bottles(
+    orchestrator_url: str,
+    network: str = GATEWAY_NETWORK,
+    infra_name: str = INFRA_NAME,
+) -> None:
+    """Re-inject egress tokens for any registered bottles that lost their
+    in-memory tokens (e.g., after an infra container restart).
+
+    For each registered bottle whose source IP maps to a live container on the
+    gateway network, reads ENV_VAR_SECRET via ``docker exec … printenv`` and
+    calls ``POST /bottles/<id>/reprovision_gateway``. Idempotent — a no-op
+    when the orchestrator already has all tokens loaded. Best-effort: a single
+    container exec failure never blocks a new bottle launch."""
+    client = OrchestratorClient(orchestrator_url)
+    bottles = client.list_bottles()
+    if not bottles:
+        return
+
+    # Build {source_ip: container_name} from live containers on the gateway
+    # network, excluding the infra container itself.
+    proc = run_docker([
+        "docker", "network", "inspect",
+        "--format", "{{range .Containers}}{{.Name}} {{.IPv4Address}}\n{{end}}",
+        network,
+    ])
+    ip_to_container: dict[str, str] = {}
+    for line in proc.stdout.splitlines():
+        parts = line.strip().split()
+        if len(parts) >= 2 and parts[0] != infra_name:
+            ip = parts[1].split("/", 1)[0]
+            if ip:
+                ip_to_container[ip] = parts[0]
+
+    reprovisioned = 0
+    for bottle in bottles:
+        bottle_id = bottle.get("bottle_id")
+        source_ip = bottle.get("source_ip")
+        if not isinstance(bottle_id, str) or not isinstance(source_ip, str):
+            continue
+        container_name = ip_to_container.get(source_ip)
+        if not container_name:
+            continue
+        proc = run_docker(
+            ["docker", "exec", container_name, "printenv", ENV_VAR_SECRET_NAME]
+        )
+        if proc.returncode != 0 or not proc.stdout.strip():
+            continue
+        try:
+            if client.reprovision_gateway(bottle_id, proc.stdout.strip()):
+                reprovisioned += 1
+        except Exception:  # noqa: BLE001 — best-effort, never block a launch
+            pass
+
+    if reprovisioned:
+        log.info(
+            "reprovisioned egress tokens",
+            context={"count": reprovisioned},
+        )
+
+
 def launch_consolidated(
     egress_plan: EgressPlan,
     git_gate_plan: GitGatePlan,
@@ -104,33 +155,29 @@ def launch_consolidated(
     image_ref: str = "",
     tokens: dict[str, str] | None = None,
     service: OrchestratorService | None = None,
-    gateway_name: str = GATEWAY_NAME,
+    infra_name: str = INFRA_NAME,
     network: str = GATEWAY_NETWORK,
 ) -> LaunchContext:
-    """Ensure the orchestrator + gateway are up, allocate + register the
-    bottle, and provision its git-gate state. Returns the agent's attach
-    context. Raises `ConsolidatedLaunchError` (or the primitives' own errors)
-    if any step fails — the caller tears down on failure."""
+    """Ensure the infra container is up, allocate + register the bottle, and
+    provision its git-gate state. Returns the agent's attach context.
+
+    Also reprovisiones egress tokens for any already-running bottles that lost
+    their in-memory credentials (e.g. after an infra container restart), so
+    they regain egress access before the new bottle is registered."""
     service = service or OrchestratorService()
     url = service.ensure_running()
+    _reprovision_running_bottles(url, network=network, infra_name=infra_name)
     client = OrchestratorClient(url)
 
     cidr = _network_cidr(network)
-    gateway_ip = _container_ip(gateway_name, network)
+    gateway_ip = _container_ip(infra_name, network)
     source_ip = next_free_ip(cidr, _network_container_ips(network))
 
-    inputs = registration_inputs(egress_plan)
-    reg = client.register_bottle(
-        source_ip, image_ref=image_ref, policy=inputs.policy,
-        metadata=inputs.metadata, tokens=tokens,
+    transport = DockerGatewayTransport(infra_name)
+    reg = provision_bottle(
+        client, source_ip, egress_plan, git_gate_plan, transport,
+        image_ref=image_ref, tokens=tokens,
     )
-    try:
-        provision_git_gate(
-            DockerGatewayTransport(gateway_name), reg.bottle_id, git_gate_plan)
-    except Exception:
-        # Roll the registration back so a provisioning failure leaves no orphan.
-        client.teardown_bottle(reg.bottle_id)
-        raise
     return LaunchContext(
         bottle_id=reg.bottle_id,
         identity_token=reg.identity_token,
@@ -138,16 +185,17 @@ def launch_consolidated(
         network=network,
         gateway_ip=gateway_ip,
         orchestrator_url=url,
+        env_var_secret=reg.env_var_secret,
     )
 
 
 def teardown_consolidated(
-    bottle_id: str, *, orchestrator_url: str, gateway_name: str = GATEWAY_NAME,
+    bottle_id: str, *, orchestrator_url: str, infra_name: str = INFRA_NAME,
+    timeout: float | None = None,
 ) -> None:
-    """Deregister the bottle and remove its git-gate state from the gateway.
-    Both steps are idempotent so this is safe from a cleanup trap."""
-    OrchestratorClient(orchestrator_url).teardown_bottle(bottle_id)
-    deprovision_git_gate(DockerGatewayTransport(gateway_name), bottle_id)
+    """Deregister the bottle and remove its git-gate state. Idempotent."""
+    _teardown_util(bottle_id, DockerGatewayTransport(infra_name),
+                   orchestrator_url=orchestrator_url, timeout=timeout)
 
 
 __all__ = [

bot_bottle/backend/docker/launch.py

@@ -42,7 +42,9 @@ from ...git_gate import (
     provision_git_gate_dynamic_keys,
     revoke_git_gate_provisioned_keys,
 )
-from ...log import info, warn
+from ...image_cache import check_stale
+from ...log import die, info, warn
+from .. import BottleImages
 from . import util as docker_mod
 from .bottle import DockerBottle
 from .bottle_plan import DockerBottlePlan
@@ -62,6 +64,7 @@ from .compose import (
     write_compose_file,
 )
 from .consolidated_compose import consolidated_agent_compose
+from ...orchestrator.config_store import resolve_teardown_timeout
 from .consolidated_launch import launch_consolidated, teardown_consolidated
 from ...orchestrator.gateway import DockerGateway
 
@@ -70,16 +73,47 @@ from ...orchestrator.gateway import DockerGateway
 _REPO_DIR = str(Path(__file__).resolve().parent.parent.parent.parent)
 
 
+def build_or_load_images(plan: DockerBottlePlan) -> BottleImages:
+    """Resolve the agent image ref for this plan.
+
+    Returns the committed snapshot if one exists, the cached image when the
+    policy is 'cached', or builds a fresh image and returns that."""
+    committed = read_committed_image(plan.slug)
+    if committed and docker_mod.image_exists(committed):
+        info(f"using committed image {committed!r}")
+        return BottleImages(agent=committed)
+    if plan.spec.image_policy == "cached":
+        if not docker_mod.image_exists(plan.image):
+            die(
+                f"cached agent image {plan.image!r} not found; "
+                "run without --cached-images to build it"
+            )
+        info(f"using cached agent image {plan.image!r}")
+        return BottleImages(agent=plan.image)
+    docker_mod.build_image(plan.image, _REPO_DIR, dockerfile=plan.dockerfile_path)
+    docker_mod.verify_agent_image(
+        plan.image, runtime_for(plan.agent_provider_template).smoke_test,
+    )
+    return BottleImages(agent=plan.image)
+
+
 @contextmanager
 def launch(
     plan: DockerBottlePlan,
+    images: BottleImages,
     *,
     provision: Callable[[DockerBottlePlan, "DockerBottle"], str | None],
 ) -> Generator[DockerBottle, None, None]:
-    """Build, launch, and provision a Docker bottle via compose.
-    Teardown on exit."""
+    """Launch and provision a Docker bottle via compose. Teardown on exit."""
     stack = ExitStack()
 
+    # Stamp the resolved agent image ref into the plan so compose rendering
+    # picks up the right image (may be a committed snapshot or cached ref).
+    plan = dataclasses.replace(
+        plan,
+        agent_provision=dataclasses.replace(plan.agent_provision, image=str(images.agent)),
+    )
+
     _bottle_for_revoke = plan.manifest.bottle
     _git_gate_dir_for_revoke = git_gate_state_dir(plan.slug)
 
@@ -96,25 +130,6 @@ def launch(
         )
 
     try:
-        # Step 1: agent image. Use a committed snapshot when one exists
-        # and is present in the local daemon; otherwise build from the
-        # Dockerfile. (The gateway image is built by the orchestrator.)
-        committed = read_committed_image(plan.slug)
-        if committed and docker_mod.image_exists(committed):
-            info(f"using committed image {committed!r}")
-            plan = dataclasses.replace(
-                plan,
-                agent_provision=dataclasses.replace(plan.agent_provision, image=committed),
-            )
-        else:
-            docker_mod.build_image(
-                plan.image, _REPO_DIR,
-                dockerfile=plan.dockerfile_path,
-            )
-            docker_mod.verify_agent_image(
-                plan.image, runtime_for(plan.agent_provider_template).smoke_test,
-            )
-
         # Step 2: mint the git-gate dynamic (gitea) deploy keys, if any, before
         # provisioning the bottle's repos into the shared gateway.
         git_gate_plan = plan.git_gate_plan
@@ -133,11 +148,14 @@ def launch(
         token_values = egress_resolve_token_values(
             plan.egress_plan.token_env_map, effective_env,
         )
+        teardown_timeout = resolve_teardown_timeout()
         ctx = launch_consolidated(
             plan.egress_plan, git_gate_plan, image_ref=plan.image, tokens=token_values,
         )
         stack.callback(
-            teardown_consolidated, ctx.bottle_id, orchestrator_url=ctx.orchestrator_url,
+            teardown_consolidated, ctx.bottle_id,
+            orchestrator_url=ctx.orchestrator_url,
+            timeout=teardown_timeout,
         )
 
         # Step 4: install the SHARED gateway CA into the agent (replaces the
@@ -168,6 +186,7 @@ def launch(
             agent_git_gate_url=git_gate_url,
             agent_supervise_url=supervise_url,
             identity_token=ctx.identity_token,
+            env_var_secret=ctx.env_var_secret,
         )
 
         # Step 5: render + up the agent-only compose, pinned on the shared
@@ -180,7 +199,12 @@ def launch(
         project = compose_project_name(plan.slug)
         # Forwarded vars (OAuth token, host interpolations) flow through the
         # subprocess env as bare names so values never land in the file.
+        # ENV_VAR_SECRET follows the same pattern: bare name in the compose
+        # spec, value only in the subprocess env so it is never written to disk.
         compose_env: dict[str, str] = {**os.environ, **plan.forwarded_env}
+        if plan.env_var_secret:
+            from ...orchestrator.secret_store import ENV_VAR_SECRET_NAME
+            compose_env[ENV_VAR_SECRET_NAME] = plan.env_var_secret
         info(
             f"docker compose up -d  (project {project}, agent on shared "
             f"gateway {ctx.gateway_ip}, ip {ctx.source_ip})"
@@ -207,3 +231,21 @@ def launch(
         yield bottle
     finally:
         teardown()
+
+
+def stale_checks(plan: DockerBottlePlan) -> None:
+    """Raise StaleImageError if a cached image is older than the configured
+    threshold. Only runs when image_policy is 'cached'. Called by the backend
+    class's _image_stale_checks before _launch_impl starts any resources."""
+    if plan.spec.image_policy != "cached":
+        return
+    committed = read_committed_image(plan.slug)
+    if committed and docker_mod.image_exists(committed):
+        ts = docker_mod.image_created_at(committed)
+        if ts is not None:
+            check_stale(f"agent image {committed!r}", ts)
+        return
+    if docker_mod.image_exists(plan.image):
+        ts = docker_mod.image_created_at(plan.image)
+        if ts is not None:
+            check_stale(f"agent image {plan.image!r}", ts)

bot_bottle/backend/docker/setup.py

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

bot_bottle/backend/docker/util.py

@@ -5,10 +5,11 @@ existence, and building images."""
 from __future__ import annotations
 
 import os
+from datetime import datetime, timezone
 import re
 import shutil
 import subprocess
-from typing import Iterable, Iterator
+from typing import Iterator
 
 from ...docker_cmd import run_docker
 from ...log import die, info
@@ -32,12 +33,7 @@ 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 = subprocess.run(
-        ["docker", "info", "--format", "{{json .Runtimes}}"],
-        capture_output=True,
-        text=True,
-        check=False,
-    )
+    r = run_docker(["docker", "info", "--format", "{{json .Runtimes}}"])
     return r.returncode == 0 and "runsc" in r.stdout
 
 
@@ -51,20 +47,15 @@ def require_docker() -> None:
 
 
 def image_exists(ref: str) -> bool:
-    return _silent_run(["docker", "image", "inspect", ref]) == 0
+    return run_docker(["docker", "image", "inspect", ref]).returncode == 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>$` so substring
     matches don't false-positive."""
-    result = subprocess.run(
-        ["docker", "ps", "-a", "-q", "-f", f"name=^{name}$"],
-        capture_output=True,
-        text=True,
-        check=True,
-    )
-    return bool(result.stdout.strip())
+    result = run_docker(["docker", "ps", "-a", "-q", "-f", f"name=^{name}$"])
+    return result.returncode == 0 and bool(result.stdout.strip())
 
 
 def force_remove_container(name: str) -> None:
@@ -72,12 +63,7 @@ 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):
-        subprocess.run(
-            ["docker", "rm", "-f", name],
-            stdout=subprocess.DEVNULL,
-            stderr=subprocess.DEVNULL,
-            check=False,
-        )
+        run_docker(["docker", "rm", "-f", name])
 
 
 def docker_exec_root(container: str, argv: list[str]) -> None:
@@ -205,10 +191,7 @@ 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 = subprocess.run(
-        ["docker", "commit", container_name, image_tag],
-        capture_output=True, text=True, check=False,
-    )
+    result = run_docker(["docker", "commit", container_name, image_tag])
     if result.returncode != 0:
         die(
             f"docker commit {container_name!r} → {image_tag!r} failed: "
@@ -217,10 +200,44 @@ def commit_container(container_name: str, image_tag: str) -> None:
     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,
+def image_created_at(ref: str) -> datetime | None:
+    """Return Docker's image Created timestamp as an aware UTC datetime, or
+    None when the field is absent or unparseable. Callers should skip the
+    stale check when None is returned."""
+    r = subprocess.run(
+        ["docker", "image", "inspect", "--format", "{{.Created}}", ref],
+        capture_output=True,
+        text=True,
         check=False,
-    ).returncode
+    )
+    if r.returncode != 0:
+        die(
+            f"docker image inspect for {ref!r} failed: "
+            f"{(r.stderr or '').strip() or '<no stderr>'}"
+        )
+    raw = r.stdout.strip()
+    if not raw:
+        return None
+    try:
+        return _parse_docker_timestamp(raw)
+    except ValueError:
+        return None
+
+
+def _parse_docker_timestamp(raw: str) -> datetime:
+    text = raw.strip()
+    if text.endswith("Z"):
+        text = text[:-1] + "+00:00"
+    dot = text.find(".")
+    if dot != -1:
+        tz_plus = text.find("+", dot)
+        tz_minus = text.find("-", dot)
+        tz_candidates = [pos for pos in (tz_plus, tz_minus) if pos != -1]
+        if tz_candidates:
+            tz_pos = min(tz_candidates)
+            frac = text[dot + 1:tz_pos]
+            text = text[:dot + 1] + frac[:6].ljust(6, "0") + text[tz_pos:]
+    dt = datetime.fromisoformat(text)
+    if dt.tzinfo is None:
+        dt = dt.replace(tzinfo=timezone.utc)
+    return dt.astimezone(timezone.utc)

bot_bottle/backend/firecracker/backend.py

@@ -18,7 +18,7 @@ from ...env import ResolvedEnv
 from ...git_gate import GitGatePlan
 from ...manifest import Manifest
 from ...supervise import SupervisePlan
-from .. import ActiveAgent, BottleBackend, BottleSpec
+from .. import ActiveAgent, BottleBackend, BottleImages, BottleSpec
 from . import cleanup as _cleanup
 from . import enumerate as _enumerate
 from . import launch as _launch
@@ -92,11 +92,18 @@ class FirecrackerBottleBackend(
             stage_dir=stage_dir,
         )
 
+    def _build_or_load_images(self, plan: FirecrackerBottlePlan) -> BottleImages:
+        return BottleImages(agent=_launch.build_or_load_agent_base(plan))
+
+    def prelaunch_checks(self, plan: FirecrackerBottlePlan) -> None:
+        _launch.stale_checks(plan)
+
     @contextmanager
-    def launch(
-        self, plan: FirecrackerBottlePlan
+    def _launch_impl(
+        self, plan: FirecrackerBottlePlan, images: BottleImages,
     ) -> Generator[FirecrackerBottle, None, None]:
-        with _launch.launch(plan, provision=self.provision) as bottle:
+        assert isinstance(images.agent, Path)
+        with _launch.launch(plan, images.agent, provision=self.provision) as bottle:
             yield bottle
 
     def prepare_cleanup(self) -> FirecrackerBottleCleanupPlan:

bot_bottle/backend/firecracker/cleanup.py

@@ -1,8 +1,23 @@
 """Cleanup for the Firecracker backend.
 
-Orphans are: firecracker VMM processes whose config lives under our run
-dir, and the per-bottle run dirs. TAP slots free themselves (the flock
-drops when the launcher exits), so there is nothing to reclaim there.
+Reaps *orphans* only — resources with no live VM behind them:
+
+  * orphan run dirs: a per-bottle run dir (holding the ~1G rootfs.ext4)
+    whose firecracker process has exited. These leak when a launch is
+    hard-killed before its teardown runs (host OOM/crash, a cancelled CI
+    job, `kill -9`); the clean-exit path already removes its own dir in
+    launch.py.
+  * orphan VM pids: a firecracker process whose run dir is already gone
+    — a VMM left lingering after its dir was removed.
+
+A run dir with a *live* firecracker process is a running bottle and is
+left strictly alone: it is neither killed nor removed. (The backend's
+`enumerate_active` registry is still a stub — #354 — so a live process
+is the only reliable "this bottle is in use" signal we have. Once the
+registry lands, registry-orphaned-but-running VMs can be reaped too.)
+
+TAP slots free themselves (the flock drops when the launcher exits), so
+there is nothing to reclaim there.
 """
 
 from __future__ import annotations
@@ -22,38 +37,73 @@ def _run_root() -> Path:
     return util.cache_dir() / "run"
 
 
-def _orphan_vm_pids() -> list[int]:
-    """firecracker processes whose --config-file is under our run dir."""
-    run_root = str(_run_root())
+def _run_dir_of(cmd: str, run_root: Path) -> Path | None:
+    """The bottle run dir a firecracker cmdline belongs to, or None.
+
+    A bottle VM is launched with `--config-file <run_root>/<slug>/config.json`,
+    so the run dir is the config file's parent when it sits directly under
+    the run root. Anything else (a builder VM, the infra VM elsewhere) is
+    not ours to reap here.
+    """
+    toks = cmd.split()
+    for i, tok in enumerate(toks):
+        if tok == "--config-file" and i + 1 < len(toks):
+            parent = Path(toks[i + 1]).parent
+            if parent.parent == run_root:
+                return parent
+    return None
+
+
+def _scan_processes(run_root: Path) -> tuple[set[str], list[int]]:
+    """Inspect running firecracker VMs under ``run_root``.
+
+    Returns ``(live_run_dirs, orphan_pids)``:
+      * ``live_run_dirs`` — run dirs backed by a running VM (never reaped);
+      * ``orphan_pids`` — firecracker pids whose run dir no longer exists
+        (a lingering VMM to kill).
+    """
     result = subprocess.run(
         ["pgrep", "-a", "firecracker"],
         capture_output=True, text=True, check=False,
     )
     if result.returncode != 0:
-        return []
-    pids: list[int] = []
+        return set(), []
+    live: set[str] = set()
+    orphan_pids: list[int] = []
     for line in result.stdout.splitlines():
         parts = line.split(None, 1)
-        if len(parts) != 2 or run_root not in parts[1]:
+        if len(parts) != 2:
             continue
         try:
-            pids.append(int(parts[0]))
+            pid = int(parts[0])
         except ValueError:
             continue
-    return pids
+        run_dir = _run_dir_of(parts[1], run_root)
+        if run_dir is None:
+            continue
+        if run_dir.is_dir():
+            live.add(str(run_dir))
+        else:
+            orphan_pids.append(pid)
+    return live, orphan_pids
 
 
-def _run_dirs() -> list[str]:
-    run_root = _run_root()
+def _orphan_run_dirs(run_root: Path, live: set[str]) -> list[str]:
+    """Run dirs with no live VM behind them — the leaked ones to remove."""
     if not run_root.is_dir():
         return []
-    return sorted(str(p) for p in run_root.iterdir() if p.is_dir())
+    return sorted(
+        str(p) for p in run_root.iterdir()
+        if p.is_dir() and str(p) not in live
+    )
 
 
 def prepare_cleanup() -> FirecrackerBottleCleanupPlan:
+    run_root = _run_root()
+    live, orphan_pids = _scan_processes(run_root)
     return FirecrackerBottleCleanupPlan(
-        vm_pids=tuple(_orphan_vm_pids()),
-        run_dirs=tuple(_run_dirs()),
+        vm_pids=tuple(orphan_pids),
+        run_dirs=tuple(_orphan_run_dirs(run_root, live)),
     )
 
 

bot_bottle/backend/firecracker/consolidated_launch.py

@@ -33,8 +33,7 @@ from ...orchestrator.client import OrchestratorClient
 from ...orchestrator.lifecycle import (
     OrchestratorStartError,  # re-exported so callers can catch it
 )
-from ...orchestrator.registration import registration_inputs
-from ..docker.gateway_provision import deprovision_git_gate, provision_git_gate
+from ..consolidated_util import provision_bottle, teardown_consolidated as _teardown_util
 from . import infra_vm
 
 
@@ -51,6 +50,7 @@ class LaunchContext:
     source_ip: str          # the VM's guest IP — the attribution key
     gateway_ca_pem: str     # the shared gateway CA the provisioner installs
     orchestrator_url: str
+    env_var_secret: str = ""  # encryption key injected into the agent's env
 
 
 def launch_consolidated(
@@ -68,18 +68,11 @@ def launch_consolidated(
     url = infra.control_plane_url
     client = OrchestratorClient(url)
 
-    inputs = registration_inputs(egress_plan)
-    reg = client.register_bottle(
-        guest_ip, image_ref=image_ref, policy=inputs.policy,
-        metadata=inputs.metadata, tokens=tokens,
+    transport = infra_vm.gateway_transport()
+    reg = provision_bottle(
+        client, guest_ip, egress_plan, git_gate_plan, transport,
+        image_ref=image_ref, tokens=tokens,
     )
-    try:
-        provision_git_gate(
-            infra_vm.gateway_transport(), reg.bottle_id, git_gate_plan)
-    except Exception:
-        client.teardown_bottle(reg.bottle_id)
-        raise
-
     # The shared gateway CA every agent on this host trusts for TLS
     # interception — fetched from the infra VM over SSH.
     return LaunchContext(
@@ -88,16 +81,19 @@ def launch_consolidated(
         source_ip=guest_ip,
         gateway_ca_pem=infra.gateway_ca_pem(),
         orchestrator_url=url,
+        env_var_secret=reg.env_var_secret,
     )
 
 
-def teardown_consolidated(bottle_id: str, *, orchestrator_url: str) -> None:
+def teardown_consolidated(
+    bottle_id: str, *, orchestrator_url: str, timeout: float | None = None,
+) -> None:
     """Deregister the bottle and remove its git-gate state from the gateway
     VM. Both steps are idempotent so this is safe from a cleanup trap. Does
     NOT stop the infra VM — it's a persistent per-host singleton shared by
     every bottle."""
-    OrchestratorClient(orchestrator_url).teardown_bottle(bottle_id)
-    deprovision_git_gate(infra_vm.gateway_transport(), bottle_id)
+    _teardown_util(bottle_id, infra_vm.gateway_transport(),
+                   orchestrator_url=orchestrator_url, timeout=timeout)
 
 
 __all__ = [

bot_bottle/backend/firecracker/freezer.py

@@ -5,7 +5,7 @@ backend — we stream the guest root filesystem out over the control
 channel (SSH here). Unlike the other backends this needs no Docker: the
 tar *is* the resumable artifact. `resume` extracts it and rebuilds a
 fresh per-bottle ext4 with `mke2fs -d` (see `util.build_committed_rootfs_dir`
-and `launch._build_agent_base`). The bottle keeps running after the
+and `launch.build_or_load_agent_base`). The bottle keeps running after the
 snapshot.
 """
 

bot_bottle/backend/firecracker/image_builder.py

@@ -38,27 +38,47 @@ _BUILD_TIMEOUT_SECONDS = 900.0
 
 
 def _dockerfile_hash(dockerfile: Path) -> str:
-    """Cache key: the Dockerfile's content. The shipped agent Dockerfiles
-    COPY nothing from the build context (see .dockerignore), so their content
-    fully determines the image; a Dockerfile that adds COPY will want the
+    """The Dockerfile's content hash. The shipped agent Dockerfiles COPY
+    nothing from the build context (see .dockerignore), so their content fully
+    determines the built 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 cached_agent_rootfs_dir(dockerfile: Path) -> Path | None:
+    """Return the ready cached rootfs for ``dockerfile``, if one exists."""
+    base = util.cache_dir() / "rootfs" / f"agent-{_rootfs_digest(dockerfile)}"
+    return base if (base / ".bb-ready").is_file() else None
+
+
 def build_agent_rootfs_dir(
     dockerfile: Path, *, image_tag: str, smoke_test: tuple[str, ...] = (),
 ) -> Path:
     """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,
-    so a repeat launch skips the rebuild.
+    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
+    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 = _dockerfile_hash(dockerfile)
+    digest = _rootfs_digest(dockerfile)
     base = util.cache_dir() / "rootfs" / f"agent-{digest}"
-    if (base / ".bb-ready").is_file():
+    if cached_agent_rootfs_dir(dockerfile) is not None:
         info(f"using cached agent rootfs {base.name}")
         return base
 

bot_bottle/backend/firecracker/infra_artifact.py

@@ -41,7 +41,7 @@ from . import util
 _ARTIFACT_FORMAT = "1"
 
 _REPO_ROOT = Path(__file__).resolve().parents[3]
-_DOCKERFILES = ("Dockerfile.orchestrator", "Dockerfile.gateway", "Dockerfile.infra")
+_DOCKERFILES = ("Dockerfile.orchestrator", "Dockerfile.gateway", "Dockerfile.infra", "Dockerfile.infra.fc")
 
 _DEFAULT_BASE = "https://gitea.dideric.is"
 _DEFAULT_OWNER = "didericis"
@@ -85,6 +85,11 @@ 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]
@@ -111,6 +116,7 @@ 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:
@@ -160,6 +166,33 @@ 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

@@ -33,6 +33,7 @@ from pathlib import Path
 from typing import Generator
 
 from ...log import die, info
+from .. import util as backend_util
 from ..docker import util as docker_mod
 from ..docker.gateway_provision import GatewayProvisionError
 from . import firecracker_vm, infra_artifact, netpool, util
@@ -93,19 +94,18 @@ class InfraVm:
         """The gateway's mitmproxy CA (PEM) that agents install to trust its
         TLS interception. Generated a moment after boot, so this polls over
         SSH until it appears (mirrors DockerGateway.ca_cert_pem)."""
-        deadline = time.monotonic() + timeout
-        while True:
+        def _fetch() -> str | None:
             proc = subprocess.run(
                 util.ssh_base_argv(self.private_key, self.guest_ip)
                 + [f"cat {_GATEWAY_CA_PATH}"],
                 capture_output=True, text=True, timeout=15, check=False,
             )
-            if proc.returncode == 0 and "BEGIN CERTIFICATE" in proc.stdout:
-                return proc.stdout
-            if time.monotonic() >= deadline:
-                die(f"gateway CA not available after {timeout:g}s: "
-                    f"{proc.stderr.strip() or 'empty'}")
-            time.sleep(_HEALTH_POLL_SECONDS)
+            ok = proc.returncode == 0 and "BEGIN CERTIFICATE" in proc.stdout
+            return proc.stdout if ok else None
+        try:
+            return backend_util.poll_ca_cert(_fetch, timeout=timeout)
+        except TimeoutError as exc:
+            die(str(exc))
 
 
 def ensure_built() -> None:
@@ -125,16 +125,19 @@ def ensure_built() -> None:
 
 
 def build_infra_images_with_docker() -> None:
-    """Build the three fixed images from source with host Docker: orchestrator,
-    gateway, then the combined infra image (`COPY --from` orchestrator, `FROM`
-    gateway). The launch host uses this only in `BOT_BOTTLE_INFRA_BUILD=local`
-    mode; `publish_infra` uses it off-host to produce the published artifact."""
+    """Build the four fixed images from source with host Docker: orchestrator,
+    gateway, the shared infra base (Dockerfile.infra), then the Firecracker
+    infra image (Dockerfile.infra.fc: FROM infra + buildah). The launch host
+    uses this only in `BOT_BOTTLE_INFRA_BUILD=local` mode; `publish_infra`
+    uses it off-host to produce the published artifact."""
     docker_mod.build_image(
         _ORCHESTRATOR_IMAGE, str(_REPO_ROOT), dockerfile="Dockerfile.orchestrator")
     docker_mod.build_image(
         _GATEWAY_IMAGE, str(_REPO_ROOT), dockerfile="Dockerfile.gateway")
     docker_mod.build_image(
-        _INFRA_IMAGE, str(_REPO_ROOT), dockerfile="Dockerfile.infra")
+        "bot-bottle-infra:latest", str(_REPO_ROOT), dockerfile="Dockerfile.infra")
+    docker_mod.build_image(
+        _INFRA_IMAGE, str(_REPO_ROOT), dockerfile="Dockerfile.infra.fc")
 
 
 def build_infra_rootfs_dir() -> Path:
@@ -161,20 +164,23 @@ def ensure_running() -> InfraVm:
     slot = netpool.orch_slot()
     url = f"http://{slot.guest_ip}:{CONTROL_PLANE_PORT}"
     key = _infra_dir() / "id_ed25519"
-    if key.exists() and _health_ok(url):
+    want = _expected_version()
+    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 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)
-        stop()  # clear a stale/hung VM holding the link before booting fresh
+        # Clear a stale/hung/OUTDATED VM holding the link before booting fresh.
+        stop()
         ensure_built()
         infra = boot()
         wait_for_health(infra)
+        _record_booted_version(want)
         return infra
 
 
@@ -193,9 +199,15 @@ def _singleton_lock() -> Generator[None, None, None]:
 
 
 def stop() -> None:
-    """Stop the infra VM singleton (idempotent — absent is success)."""
+    """Stop the infra VM singleton (idempotent — absent is success). Reaps the
+    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:
@@ -238,6 +250,36 @@ 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
@@ -309,6 +351,28 @@ 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:
@@ -433,7 +497,7 @@ 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 /app/gateway_init.py &
+    python3 -m bot_bottle.gateway_init &
 
 # Reap as PID 1; children are backgrounded, so `wait` blocks.
 while : ; do wait ; done

bot_bottle/backend/firecracker/launch.py

@@ -26,6 +26,7 @@ from __future__ import annotations
 
 import dataclasses
 import os
+import shutil
 from contextlib import ExitStack, contextmanager
 from pathlib import Path
 from typing import Callable, Generator
@@ -45,13 +46,15 @@ from ...git_gate import (
     provision_git_gate_dynamic_keys,
     revoke_git_gate_provisioned_keys,
 )
-from ...log import info, warn
+from ...image_cache import check_stale_path
+from ...log import die, info, warn
 from ...supervise import SUPERVISE_PORT
 from ..docker.egress import EGRESS_PORT
 from ..util import AGENT_CA_BUNDLE, AGENT_CA_PATH
 from . import firecracker_vm, image_builder, isolation_probe, netpool, util
 from .bottle import FirecrackerBottle
 from .bottle_plan import FirecrackerBottlePlan
+from ...orchestrator.config_store import resolve_teardown_timeout
 from .consolidated_launch import (
     launch_consolidated,
     teardown_consolidated,
@@ -64,6 +67,7 @@ _GIT_HTTP_PORT = 9420
 @contextmanager
 def launch(
     plan: FirecrackerBottlePlan,
+    agent_base: Path,
     *,
     provision: Callable[[FirecrackerBottlePlan, "FirecrackerBottle"], str | None],
 ) -> Generator[FirecrackerBottle, None, None]:
@@ -85,11 +89,9 @@ def launch(
             raise teardown_exc
 
     try:
-        # Step 1: agent rootfs. Built from the Dockerfile inside a Firecracker
-        # builder VM (buildah, no host docker); a committed snapshot is reused
-        # when present. Returns the base dir the per-bottle ext4 is made from.
-        plan, agent_base = _build_agent_base(plan)
-
+        # Step 1 (rootfs resolution/build) runs in BottleBackend.launch before
+        # this context starts resources. ``agent_base`` is the selected cache,
+        # fresh build, or committed snapshot.
         # Step 2: mint the git-gate dynamic (gitea) deploy keys, if any.
         git_gate_plan = plan.git_gate_plan
         if git_gate_plan.upstreams:
@@ -112,6 +114,7 @@ def launch(
         token_values = egress_resolve_token_values(
             plan.egress_plan.token_env_map, effective_env,
         )
+        teardown_timeout = resolve_teardown_timeout()
         ctx = launch_consolidated(
             plan.egress_plan, git_gate_plan,
             guest_ip=slot.guest_ip,
@@ -121,6 +124,7 @@ def launch(
         stack.callback(
             teardown_consolidated, ctx.bottle_id,
             orchestrator_url=ctx.orchestrator_url,
+            timeout=teardown_timeout,
         )
 
         # Step 5: install the SHARED gateway CA (replaces the per-bottle CA).
@@ -164,6 +168,10 @@ def launch(
         # Step 6: build the per-bottle rootfs + SSH key, then boot.
         run_dir = util.cache_dir() / "run" / plan.slug
         run_dir.mkdir(parents=True, exist_ok=True)
+        # Remove the run dir on teardown so the per-bottle rootfs.ext4 (~1G)
+        # doesn't leak. Registered before vm.terminate below so it runs *after*
+        # it (ExitStack is LIFO): the VM is gone before we rm its rootfs.
+        stack.callback(lambda: shutil.rmtree(run_dir, ignore_errors=True))
         rootfs = run_dir / "rootfs.ext4"
         util.build_rootfs_ext4(agent_base, rootfs)
         private_key, pubkey = util.generate_keypair(run_dir)
@@ -206,9 +214,7 @@ def launch(
         teardown()
 
 
-def _build_agent_base(
-    plan: FirecrackerBottlePlan,
-) -> tuple[FirecrackerBottlePlan, Path]:
+def build_or_load_agent_base(plan: FirecrackerBottlePlan) -> Path:
     """Produce the agent's base rootfs dir. Primary path: build the Dockerfile
     inside a Firecracker builder VM (buildah, no host docker), smoke-testing
     the image before export. A committed snapshot (freeze/migrate) is resumed
@@ -217,13 +223,36 @@ def _build_agent_base(
     committed_tar = committed_rootfs_path(plan.slug)
     if committed and committed_tar.is_file():
         info(f"resuming from committed rootfs {committed_tar}")
-        return plan, util.build_committed_rootfs_dir(committed_tar)
-    base = image_builder.build_agent_rootfs_dir(
-        Path(plan.dockerfile_path),
+        return util.build_committed_rootfs_dir(committed_tar)
+    dockerfile = Path(plan.dockerfile_path)
+    if plan.spec.image_policy == "cached":
+        cached = image_builder.cached_agent_rootfs_dir(dockerfile)
+        if cached is None:
+            die(
+                f"cached agent rootfs for {plan.image!r} not found; "
+                "run without --cached-images to build it"
+            )
+        info(f"using cached agent rootfs {cached.name}")
+        return cached
+    return image_builder.build_agent_rootfs_dir(
+        dockerfile,
         image_tag=plan.image,
         smoke_test=runtime_for(plan.agent_provider_template).smoke_test,
     )
-    return plan, base
+
+
+def stale_checks(plan: FirecrackerBottlePlan) -> None:
+    """Raise when the cached rootfs selected by this plan is stale."""
+    if plan.spec.image_policy != "cached":
+        return
+    committed = read_committed_image(plan.slug)
+    committed_tar = committed_rootfs_path(plan.slug)
+    if committed and committed_tar.is_file():
+        check_stale_path(f"agent rootfs {committed_tar}", committed_tar)
+        return
+    cached = image_builder.cached_agent_rootfs_dir(Path(plan.dockerfile_path))
+    if cached is not None:
+        check_stale_path(f"agent rootfs {cached}", cached / ".bb-ready")
 
 
 # --- agent guest env -------------------------------------------------
@@ -239,6 +268,11 @@ def _agent_guest_env(plan: FirecrackerBottlePlan, host_ip: str) -> dict[str, str
         "HTTPS_PROXY": proxy_url, "HTTP_PROXY": proxy_url,
         "https_proxy": proxy_url, "http_proxy": proxy_url,
         "NO_PROXY": no_proxy, "no_proxy": no_proxy,
+        # Rootfs export can leave Git's implicit XDG paths unreadable even
+        # after the runtime repair. Bypass that discovery and name the
+        # provisioned global config explicitly so insteadOf can never fall
+        # through to the credential-bearing upstream URL.
+        "GIT_CONFIG_GLOBAL": f"{plan.guest_home}/.gitconfig",
         "NODE_EXTRA_CA_CERTS": AGENT_CA_PATH,
         "SSL_CERT_FILE": AGENT_CA_BUNDLE,
         "REQUESTS_CA_BUNDLE": AGENT_CA_BUNDLE,

bot_bottle/backend/firecracker/publish_infra.py

@@ -11,7 +11,8 @@ 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 [--dry-run] [--force]
+  python3 -m bot_bottle.backend.firecracker.publish_infra --output DIR
+  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`.
@@ -24,7 +25,6 @@ import gzip
 import hashlib
 import shutil
 import sys
-import tempfile
 import urllib.error
 import urllib.request
 from pathlib import Path
@@ -131,36 +131,112 @@ def build_artifact(out_dir: Path) -> tuple[str, Path, Path]:
     return version, gz, sha
 
 
+def _try_download_published(out_dir: Path) -> tuple[str, Path, Path] | None:
+    """If this version's artifact is already in the registry, download the gz
+    and sha to out_dir and return (version, gz_path, sha_path). Returns None
+    when not yet published."""
+    version = infra_artifact.infra_artifact_version(infra_vm._infra_init())
+    sha_url = infra_artifact.artifact_url(version, "rootfs.ext4.gz.sha256")
+    try:
+        with urllib.request.urlopen(infra_artifact._open(sha_url)):
+            pass
+    except urllib.error.HTTPError as e:
+        if e.code == 404:
+            return None
+        raise SystemExit(f"registry check failed (HTTP {e.code}): {sha_url}")
+    except urllib.error.URLError as e:
+        raise SystemExit(f"registry unreachable: {sha_url} ({e.reason})")
+    print(f"infra rootfs {version} already published — downloading instead of building")
+    gz = out_dir / "rootfs.ext4.gz"
+    sha = out_dir / "rootfs.ext4.gz.sha256"
+    infra_artifact._download(infra_artifact.artifact_url(version, "rootfs.ext4.gz"), gz)
+    infra_artifact._download(infra_artifact.artifact_url(version, "rootfs.ext4.gz.sha256"), sha)
+    return version, gz, sha
+
+
+def _publish_bundle(root: Path, token: str) -> str:
+    version_file = root / "version.txt"
+    # Guard the read so a missing version.txt is a clean error, not a raw
+    # 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.")
-    parser.add_argument("--dry-run", action="store_true",
-                        help="build the artifact but do not upload")
-    parser.add_argument("--force", action="store_true",
-                        help="overwrite an already-published artifact of this version")
+    mode = parser.add_mutually_exclusive_group(required=True)
+    mode.add_argument("--output", type=Path,
+                      help="build a candidate bundle in DIR without publishing")
+    mode.add_argument("--publish-dir", type=Path,
+                      help="publish an already-built and tested candidate bundle")
+    parser.add_argument("--reuse-published", action="store_true",
+                        help="with --output: download from registry if already published instead of building")
     args = parser.parse_args(argv)
 
     _, _, token = infra_artifact._config()
-    if not args.dry_run and not token:
+    if args.publish_dir is not None and not token:
         raise SystemExit(
             "no publish token: set BOT_BOTTLE_INFRA_ARTIFACT_TOKEN to a token "
             "with write:package")
 
-    with tempfile.TemporaryDirectory(prefix="bb-publish-infra.") as tmp:
-        version, gz, sha = build_artifact(Path(tmp))
-        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)
-        if args.dry_run:
-            print(f"dry-run: would upload -> {gz_url}")
+    if args.output is not None:
+        args.output.mkdir(parents=True, exist_ok=True)
+        reused = None
+        if args.reuse_published:
+            reused = _try_download_published(args.output)
+        if reused is not None:
+            version, _, _ = reused
+            (args.output / "version.txt").write_text(version + "\n", encoding="utf-8")
+            print(f"reused published infra rootfs candidate {version}")
             return 0
-        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
+        version, _gz, _sha = build_artifact(args.output)
+        (args.output / "version.txt").write_text(version + "\n", encoding="utf-8")
+        print(f"built infra rootfs candidate {version}")
+        return 0
+
+    assert args.publish_dir is not None
+    version = _publish_bundle(args.publish_dir, token)
     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 --backend=macos-container.")
+            "On macOS use the macos-container backend.")
     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")
@@ -368,6 +368,17 @@ 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
+
+# Rootfs export also maps the image's original owners to the unprivileged
+# host build uid. That uid is not guaranteed to be node's uid in the guest;
+# restore the home-directory boundary before any SSH provisioning runs.
+chown node:node /home/node 2>/dev/null || true
+chmod 755 /home/node 2>/dev/null || true
+
 # Install the per-bottle SSH pubkey from the kernel cmdline.
 KEY=$(sed -n 's/.*bb_pubkey=\([^ ]*\).*/\1/p' /proc/cmdline | base64 -d 2>/dev/null)
 if [ -n "$KEY" ]; then

bot_bottle/backend/macos_container/backend.py

@@ -12,7 +12,7 @@ from ...env import ResolvedEnv
 from ...git_gate import GitGatePlan
 from ...supervise import SupervisePlan
 from ...manifest import Manifest
-from .. import ActiveAgent, BottleBackend, BottleSpec
+from .. import ActiveAgent, BottleBackend, BottleImages, BottleSpec
 from . import cleanup as _cleanup
 from . import enumerate as _enumerate
 from . import launch as _launch
@@ -82,11 +82,17 @@ class MacosContainerBottleBackend(
             stage_dir=stage_dir,
         )
 
+    def prelaunch_checks(self, plan: MacosContainerBottlePlan) -> None:
+        _launch.stale_checks(plan)
+
+    def _build_or_load_images(self, plan: MacosContainerBottlePlan) -> BottleImages:
+        return _launch.build_or_load_images(plan)
+
     @contextmanager
-    def launch(
-        self, plan: MacosContainerBottlePlan
+    def _launch_impl(
+        self, plan: MacosContainerBottlePlan, images: BottleImages
     ) -> Generator[MacosContainerBottle, None, None]:
-        with _launch.launch(plan, provision=self.provision) as bottle:
+        with _launch.launch(plan, images, provision=self.provision) as bottle:
             yield bottle
 
     def ensure_orchestrator(self) -> str:

bot_bottle/backend/macos_container/bottle.py

@@ -68,9 +68,14 @@ class MacosContainerBottle(Bottle):
         # reaches the agent (PRD 0070): registration mints it *after* the
         # container exists — its source IP is the registration key and Apple
         # Container assigns that by DHCP — so it cannot be in the run-time env
-        # the way docker's compose spec does it. `container exec --env` wins
-        # over the run-time value, so the token-bearing proxy URL set here
-        # supersedes the token-less one baked in at launch.
+        # the way docker's compose spec does it.
+        #
+        # `container exec --env` does NOT override a run-time value — it
+        # appends, leaving duplicate entries in the agent's `environ` whose
+        # resolution is runtime-specific (Node last-wins, Rust first-wins). So
+        # nothing here may rely on superseding: the proxy vars are supplied
+        # *only* at exec time and are deliberately absent from the run-time
+        # env. See `launch._agent_env_entries`.
         self._exec_env = dict(exec_env or {})
         self._closed = False
 

bot_bottle/backend/macos_container/consolidated_launch.py

@@ -36,9 +36,11 @@ from dataclasses import dataclass
 
 from ...egress import EgressPlan
 from ...git_gate import GitGatePlan
-from ...orchestrator.client import OrchestratorClient
-from ...orchestrator.registration import registration_inputs
-from ..docker.gateway_provision import deprovision_git_gate, provision_git_gate
+from ...log import info
+from ...orchestrator.client import OrchestratorClient, OrchestratorClientError
+from ..consolidated_util import provision_bottle, teardown_consolidated as _teardown_util
+from . import util as container_mod
+from .enumerate import CONTAINER_NAME_PREFIX, EnumerationError, enumerate_active
 from .gateway import GATEWAY_NETWORK
 from .gateway_provision import AppleGatewayTransport
 from .infra import MacosInfraService, OrchestratorStartError
@@ -70,6 +72,7 @@ class LaunchContext:
     gateway_ip: str
     network: str
     orchestrator_url: str
+    env_var_secret: str = ""  # encryption key injected into the agent's env
 
 
 def ensure_gateway(
@@ -89,6 +92,32 @@ 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,
@@ -103,17 +132,20 @@ 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)
-    inputs = registration_inputs(egress_plan)
-    reg = client.register_bottle(
-        source_ip, image_ref=image_ref, policy=inputs.policy,
-        metadata=inputs.metadata, tokens=tokens,
-    )
+    # 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:
-        provision_git_gate(AppleGatewayTransport(), reg.bottle_id, git_gate_plan)
-    except Exception:
-        # Roll the registration back so a provisioning failure leaves no orphan.
-        client.teardown_bottle(reg.bottle_id)
-        raise
+        client.reconcile(live_source_ips(endpoint.network))
+    except (OrchestratorClientError, EnumerationError) as e:
+        info(f"registry reconciliation skipped: {e}")
+    reg = provision_bottle(
+        client, source_ip, egress_plan, git_gate_plan, AppleGatewayTransport(),
+        image_ref=image_ref, tokens=tokens,
+    )
     return LaunchContext(
         bottle_id=reg.bottle_id,
         identity_token=reg.identity_token,
@@ -121,21 +153,25 @@ def register_agent(
         gateway_ip=endpoint.gateway_ip,
         network=endpoint.network,
         orchestrator_url=endpoint.orchestrator_url,
+        env_var_secret=reg.env_var_secret,
     )
 
 
-def teardown_consolidated(bottle_id: str, *, orchestrator_url: str) -> None:
+def teardown_consolidated(
+    bottle_id: str, *, orchestrator_url: str, timeout: float | None = None,
+) -> None:
     """Deregister the bottle and remove its git-gate state from the gateway.
     Both steps are idempotent so this is safe from a cleanup trap. Does NOT
     stop the gateway — it's a persistent per-host singleton."""
-    OrchestratorClient(orchestrator_url).teardown_bottle(bottle_id)
-    deprovision_git_gate(AppleGatewayTransport(), bottle_id)
+    _teardown_util(bottle_id, AppleGatewayTransport(),
+                   orchestrator_url=orchestrator_url, timeout=timeout)
 
 
 __all__ = [
     "GatewayEndpoint",
     "LaunchContext",
     "ensure_gateway",
+    "live_source_ips",
     "register_agent",
     "teardown_consolidated",
     "ConsolidatedLaunchError",

bot_bottle/backend/macos_container/enumerate.py

@@ -8,13 +8,21 @@ from ...bottle_state import read_metadata
 from .. import ActiveAgent
 from .infra import INFRA_NAME
 
-_PREFIX = "bot-bottle-"
+# The name every agent container carries: `bot-bottle-<slug>`. Exported
+# because callers that act on a running bottle (gateway-host rewrites,
+# registry reconciliation) have to map an enumerated slug back to a
+# container name.
+CONTAINER_NAME_PREFIX = "bot-bottle-"
 # The shared per-host infra container carries the same prefix as agent
 # containers but is infrastructure, not a bottle — one control plane + gateway
 # serves every agent, so listing it as an agent would invent one per host.
 _INFRA_NAMES = frozenset({INFRA_NAME})
 
 
+class EnumerationError(RuntimeError):
+    """container list failed; the resulting live set is not authoritative."""
+
+
 def enumerate_active() -> list[ActiveAgent]:
     result = subprocess.run(
         ["container", "list", "--quiet"],
@@ -23,12 +31,15 @@ def enumerate_active() -> list[ActiveAgent]:
         check=False,
     )
     if result.returncode != 0:
-        return []
+        raise EnumerationError(
+            f"container list failed: "
+            f"{(result.stderr or '').strip() or '<no stderr>'}"
+        )
     out: list[ActiveAgent] = []
     for name in sorted(line.strip() for line in result.stdout.splitlines()):
-        if not name.startswith(_PREFIX) or name in _INFRA_NAMES:
+        if not name.startswith(CONTAINER_NAME_PREFIX) or name in _INFRA_NAMES:
             continue
-        slug = name[len(_PREFIX):]
+        slug = name[len(CONTAINER_NAME_PREFIX):]
         metadata = read_metadata(slug)
         out.append(ActiveAgent(
             backend_name="macos-container",

bot_bottle/backend/macos_container/gateway_hosts.py

@@ -0,0 +1,96 @@
+"""Stable gateway name for macOS agents, via each bottle's `/etc/hosts`.
+
+The shared gateway's address is assigned by vmnet's DHCP and changes whenever
+the infra container is recreated — a source-hash bump, an image upgrade, a
+crash. Every agent-facing URL (egress proxy, git-http, supervise) embeds that
+address, and the proxy URL reaches the agent as **process environment** at
+`container exec` time. A running process's `environ` cannot be rewritten from
+outside, so a moved gateway used to strand every running bottle permanently:
+not degraded, unreachable, until the bottle was relaunched and its session
+thrown away.
+
+So the agent never learns the address. It is given a stable *name*
+(`GATEWAY_HOSTNAME`) in every URL, resolved through its own `/etc/hosts`.
+Unlike `environ`, that is a file — it can be rewritten inside a container that
+is already running, so a gateway that comes back at a new address is picked up
+by live bottles instead of orphaning them.
+
+Apple Container 1.0 offers no container-name DNS on a user network (the only
+nameserver an agent sees is vmnet's, which does not know container names) and
+`container run` has no `--add-host`, so the entry is written by exec after the
+container starts.
+
+Writing it needs root, and the agent runs as `node`: the agent therefore
+cannot repoint its own gateway name, while the host (which drives `container
+exec --user root`) can. That asymmetry is deliberate — keep it.
+"""
+
+from __future__ import annotations
+
+from ...log import warn
+from . import util as container_mod
+from .enumerate import CONTAINER_NAME_PREFIX, enumerate_active
+
+# The name every agent-facing gateway URL uses. Must not collide with a real
+# DNS name the agent might resolve; it is bottle-local by construction.
+GATEWAY_HOSTNAME = "bot-bottle-gateway"
+
+# Marker so the rewrite is idempotent and only ever touches our own line —
+# the rest of /etc/hosts (localhost, the container's own name) is preserved.
+_MARKER = "# bot-bottle gateway"
+
+
+def _rewrite_script(gateway_ip: str) -> str:
+    """A shell one-liner that replaces our managed line in `/etc/hosts`.
+
+    Rewrites in place via a temp file + `cat` rather than `mv`, so the file
+    keeps its original inode, ownership, and mode — a bind-mounted or
+    pre-created `/etc/hosts` must not be replaced by a root-owned 0644 copy
+    that the runtime then refuses to update.
+    """
+    return (
+        "set -e; "
+        f"grep -v '{_MARKER}' /etc/hosts > /tmp/.bb-hosts || true; "
+        f"printf '%s %s %s\\n' '{gateway_ip}' '{GATEWAY_HOSTNAME}' "
+        f"'{_MARKER}' >> /tmp/.bb-hosts; "
+        "cat /tmp/.bb-hosts > /etc/hosts; "
+        "rm -f /tmp/.bb-hosts"
+    )
+
+
+def set_gateway_host(container_name: str, gateway_ip: str) -> None:
+    """Point `GATEWAY_HOSTNAME` at `gateway_ip` inside one running container.
+
+    Must run before the agent is exec'd: the agent's proxy URL names the
+    gateway, so the entry has to exist for its first connection. Idempotent —
+    re-running with the same address is a no-op in effect.
+    """
+    container_mod.exec_container_as_root(
+        container_name, ["sh", "-c", _rewrite_script(gateway_ip)],
+    )
+
+
+def refresh_gateway_host(gateway_ip: str) -> list[str]:
+    """Re-point every running bottle at the current gateway address.
+
+    Called once the shared gateway is known to be up, so a bottle stranded by
+    an earlier gateway restart re-attaches instead of needing a relaunch.
+    Returns the containers updated.
+
+    Best-effort per bottle: one container that refuses the write (already
+    exiting, say) must not stop the others from being repaired, and must not
+    fail the launch that triggered the sweep.
+    """
+    updated: list[str] = []
+    for agent in enumerate_active():
+        name = f"{CONTAINER_NAME_PREFIX}{agent.slug}"
+        try:
+            set_gateway_host(name, gateway_ip)
+            updated.append(name)
+        # One bad bottle must not stop the sweep, so this is deliberately broad.
+        except Exception as e:  # noqa: BLE001  # pylint: disable=broad-exception-caught
+            warn(f"could not re-point {name} at the gateway: {e}")
+    return updated
+
+
+__all__ = ["GATEWAY_HOSTNAME", "set_gateway_host", "refresh_gateway_host"]

bot_bottle/backend/macos_container/infra.py

@@ -41,7 +41,7 @@ from dataclasses import dataclass
 from pathlib import Path
 
 from ... import log
-from ...orchestrator.gateway import GATEWAY_CA_CERT
+from ...orchestrator.gateway import GATEWAY_CA_CERT, MITMPROXY_HOME
 from ...orchestrator.lifecycle import (
     DEFAULT_PORT,
     DEFAULT_STARTUP_TIMEOUT_SECONDS,
@@ -52,7 +52,9 @@ from ...paths import (
     CONTROL_PLANE_TOKEN_ENV,
     HOST_DB_FILENAME,
     host_control_plane_token,
+    host_gateway_ca_dir,
 )
+from .. import util as backend_util
 from . import util as container_mod
 from .gateway import (
     DEFAULT_CA_TIMEOUT_SECONDS,
@@ -101,7 +103,7 @@ 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 /app/gateway_init.py ) &\n"
+        f"SUPERVISE_DB_PATH={_DB_PATH_IN_CONTAINER} python3 -m bot_bottle.gateway_init ) &\n"
         "while : ; do wait ; done\n"
     )
 
@@ -217,6 +219,14 @@ class MacosInfraService:
             # Container-only DB volume: one kernel writes bot-bottle.db, never
             # shared with the host or another guest.
             "--volume", f"{self._db_volume}:{_DB_ROOT_IN_CONTAINER}",
+            # The DB needs a container-only ext4 volume for coherent SQLite
+            # locking, but the CA has no such constraint. Keep it in the host
+            # app-data root so infra-container recreation and Apple Container
+            # volume pruning cannot silently rotate every bottle's trust
+            # anchor (issue #450).
+            "--mount",
+            container_mod.bind_mount_spec(
+                str(host_gateway_ca_dir()), MITMPROXY_HOME),
             # Bind-mount the control-plane source (read-only); a code change
             # takes effect on relaunch with no image rebuild.
             "--mount",
@@ -260,21 +270,19 @@ class MacosInfraService:
 
     def ca_cert_pem(self, *, timeout: float = DEFAULT_CA_TIMEOUT_SECONDS) -> str:
         """The gateway's mitmproxy CA (PEM) agents install to trust its TLS
-        interception. Read out of the container (the CA lives on a
-        container-internal path, not a host mount); polls because mitmproxy
-        writes it a beat after start."""
-        deadline = time.monotonic() + timeout
-        while True:
+        interception. Read through the container path backed by the persistent
+        host CA directory; polls because mitmproxy writes it a beat after
+        start."""
+        def _fetch() -> str | None:
             result = container_mod.run_container_argv(
                 ["container", "exec", self._name, "cat", GATEWAY_CA_CERT])
-            if result.returncode == 0 and result.stdout.strip():
-                return result.stdout
-            if time.monotonic() >= deadline:
-                raise GatewayError(
-                    f"gateway CA not available in {self._name} after {timeout:g}s: "
-                    f"{(result.stderr or '').strip() or 'empty'}"
-                )
-            time.sleep(_CA_POLL_SECONDS)
+            return result.stdout if result.returncode == 0 and result.stdout.strip() else None
+        try:
+            return backend_util.poll_ca_cert(_fetch, timeout=timeout)
+        except TimeoutError as exc:
+            raise GatewayError(
+                f"gateway CA not available in {self._name} after {timeout:g}s"
+            ) from exc
 
     def stop(self) -> None:
         """Remove the infra container (idempotent). The DB volume persists."""

bot_bottle/backend/macos_container/launch.py

@@ -53,13 +53,21 @@ from ...git_gate import (
     revoke_git_gate_provisioned_keys,
 )
 from ...git_http_backend import DEFAULT_PORT as _GIT_HTTP_PORT
+from ...image_cache import check_stale
 from ...log import die, info, warn
+from .. import BottleImages
 from ...supervise import SUPERVISE_PORT
 from ..docker.egress import EGRESS_PORT
 from ..util import AGENT_CA_BUNDLE, AGENT_CA_PATH
 from . import util as container_mod
 from .bottle import MacosContainerBottle
+from .gateway_hosts import (
+    GATEWAY_HOSTNAME,
+    refresh_gateway_host,
+    set_gateway_host,
+)
 from .bottle_plan import MacosContainerBottlePlan
+from ...orchestrator.config_store import resolve_teardown_timeout
 from .consolidated_launch import (
     GatewayEndpoint,
     ensure_gateway,
@@ -71,18 +79,43 @@ _REPO_DIR = str(Path(__file__).resolve().parent.parent.parent.parent)
 _AGENT_SLEEP_SECONDS = "2147483647"
 
 
+def build_or_load_images(plan: MacosContainerBottlePlan) -> BottleImages:
+    """Resolve the agent image ref for this plan. The gateway's own image is
+    built by `ensure_gateway` — it belongs to the shared singleton."""
+    committed = read_committed_image(plan.slug)
+    if committed and container_mod.image_exists(committed):
+        info(f"using committed image {committed!r}")
+        return BottleImages(agent=committed)
+    if plan.spec.image_policy == "cached":
+        if not container_mod.image_exists(plan.image):
+            die(
+                f"cached agent image {plan.image!r} not found; "
+                "run without --cached-images to build it"
+            )
+        info(f"using cached agent image {plan.image!r}")
+        return BottleImages(agent=plan.image)
+    container_mod.build_image(plan.image, _REPO_DIR, dockerfile=plan.dockerfile_path)
+    return BottleImages(agent=plan.image)
+
+
 @contextmanager
 def launch(
     plan: MacosContainerBottlePlan,
+    images: BottleImages,
     *,
     provision: Callable[[MacosContainerBottlePlan, "MacosContainerBottle"], str | None],
 ) -> Generator[MacosContainerBottle, None, None]:
-    """Build, run, register, provision, and yield an Apple Container bottle on
-    the shared per-host gateway."""
+    """Run, register, provision, and yield an Apple Container bottle on the
+    shared per-host gateway."""
     stack = ExitStack()
     bottle_for_revoke = plan.manifest.bottle
     git_gate_dir_for_revoke = git_gate_state_dir(plan.slug)
 
+    plan = dataclasses.replace(
+        plan,
+        agent_provision=dataclasses.replace(plan.agent_provision, image=str(images.agent)),
+    )
+
     def teardown() -> None:
         teardown_exc: BaseException | None = None
         try:
@@ -95,11 +128,14 @@ def launch(
             raise teardown_exc
 
     try:
-        plan = _build_images(plan)
-
         # Step 1: the per-host singletons. Must precede the agent run — its
         # proxy env needs the gateway's address at `container run` time.
         endpoint = ensure_gateway()
+        # The gateway's address may have changed since these bottles launched
+        # (any infra recreate re-runs DHCP). They name the gateway rather than
+        # address it, so re-pointing /etc/hosts re-attaches them in place
+        # instead of leaving them stranded until relaunch.
+        refresh_gateway_host(endpoint.gateway_ip)
 
         # Step 2: mint this bottle's deploy keys, then point it at the SHARED
         # gateway's CA + git-http/supervise ports.
@@ -117,6 +153,9 @@ def launch(
         # attribution key; `--cap-drop CAP_NET_RAW` at run is what makes it
         # unforgeable. Poll: `container run --detach` can return before vmnet's
         # DHCP has assigned the address.
+        # Resolve the gateway name before anything execs: every agent-facing
+        # URL uses it, so the entry must exist for the first connection.
+        set_gateway_host(plan.container_name, endpoint.gateway_ip)
         source_ip = container_mod.wait_container_ipv4_on_network(
             plan.container_name, endpoint.network,
         )
@@ -129,6 +168,7 @@ def launch(
         token_values = egress_resolve_token_values(
             plan.egress_plan.token_env_map, effective_env,
         )
+        teardown_timeout = resolve_teardown_timeout()
         ctx = register_agent(
             plan.egress_plan,
             plan.git_gate_plan,
@@ -140,6 +180,7 @@ def launch(
         stack.callback(
             teardown_consolidated, ctx.bottle_id,
             orchestrator_url=ctx.orchestrator_url,
+            timeout=teardown_timeout,
         )
         info(
             f"agent {plan.container_name} registered "
@@ -177,22 +218,23 @@ def launch(
         teardown()
 
 
-def _build_images(plan: MacosContainerBottlePlan) -> MacosContainerBottlePlan:
-    """Build the agent image. The gateway's own image is built by
-    `ensure_gateway` — it belongs to the shared singleton, not to a bottle."""
+
+def stale_checks(plan: MacosContainerBottlePlan) -> None:
+    """Raise StaleImageError if a cached image is older than the configured
+    threshold. Only runs when image_policy is 'cached'. Called by the backend
+    class's _image_stale_checks before _launch_impl starts any resources."""
+    if plan.spec.image_policy != "cached":
+        return
     committed = read_committed_image(plan.slug)
     if committed and container_mod.image_exists(committed):
-        info(f"using committed image {committed!r}")
-        return dataclasses.replace(
-            plan,
-            agent_provision=dataclasses.replace(
-                plan.agent_provision, image=committed,
-            ),
-        )
-    container_mod.build_image(
-        plan.image, _REPO_DIR, dockerfile=plan.dockerfile_path,
-    )
-    return plan
+        ts = container_mod.image_created_at(committed)
+        if ts is not None:
+            check_stale(f"agent image {committed!r}", ts)
+        return
+    if container_mod.image_exists(plan.image):
+        ts = container_mod.image_created_at(plan.image)
+        if ts is not None:
+            check_stale(f"agent image {plan.image!r}", ts)
 
 
 def _provision_git_gate_keys(
@@ -231,13 +273,20 @@ def _stamp_agent_urls(
 ) -> MacosContainerBottlePlan:
     """Point the agent's git-gate insteadOf rewrites + supervise MCP at the
     shared gateway's ports. Both bypass the egress proxy (NO_PROXY covers the
-    gateway address)."""
+    gateway name).
+
+    Addressed by `GATEWAY_HOSTNAME`, never by IP: these URLs are baked into
+    the agent's gitconfig and MCP config at provision time, so an address here
+    would strand the bottle the moment the gateway moved. The name is resolved
+    per connection through `/etc/hosts`, which stays rewritable while the
+    bottle runs."""
+    del endpoint  # addressed by name; the address reaches the bottle via /etc/hosts
     git_gate_url = (
-        f"http://{endpoint.gateway_ip}:{_GIT_HTTP_PORT}"
+        f"http://{GATEWAY_HOSTNAME}:{_GIT_HTTP_PORT}"
         if plan.git_gate_plan.upstreams else ""
     )
     supervise_url = (
-        f"http://{endpoint.gateway_ip}:{SUPERVISE_PORT}/"
+        f"http://{GATEWAY_HOSTNAME}:{SUPERVISE_PORT}/"
         if plan.supervise_plan is not None else ""
     )
     return dataclasses.replace(
@@ -247,30 +296,43 @@ def _stamp_agent_urls(
     )
 
 
-def _proxy_url(gateway_ip: str, identity_token: str = "") -> str:
+def _proxy_url(identity_token: str = "") -> str:
     """The agent's egress proxy URL. The identity token rides as proxy
     credentials — the gateway reads Proxy-Authorization, resolves the
     (source_ip, token) pair against the control plane, and strips it before
-    upstream. Without a valid pair `/resolve` denies the request (#366)."""
+    upstream. Without a valid pair `/resolve` denies the request (#366).
+
+    Names the gateway rather than addressing it: this URL reaches the agent as
+    process environment, which cannot be rewritten once the agent is running,
+    so an address baked here is unfixable if the gateway moves."""
     cred = f"bottle:{identity_token}@" if identity_token else ""
-    return f"http://{cred}{gateway_ip}:{EGRESS_PORT}"
+    return f"http://{cred}{GATEWAY_HOSTNAME}:{EGRESS_PORT}"
 
 
-def _no_proxy(gateway_ip: str) -> str:
+def _no_proxy() -> str:
     # git-http + supervise live on the gateway and must NOT go through the
-    # egress proxy — the agent reaches them directly by its address.
-    return f"localhost,127.0.0.1,{gateway_ip}"
+    # egress proxy — the agent reaches them directly by name. Deliberately
+    # address-free: NO_PROXY is baked into the run-time env and is therefore
+    # just as unfixable as the proxy URL if the gateway moves.
+    return f"localhost,127.0.0.1,{GATEWAY_HOSTNAME}"
 
 
 def _identity_proxy_env(
     endpoint: GatewayEndpoint, identity_token: str,
 ) -> dict[str, str]:
-    """The token-bearing proxy env applied at `container exec`. It supersedes
-    the token-less run-time value (exec `--env` wins), which is the only way to
-    get the token in: it does not exist until after the container runs."""
+    """The token-bearing proxy env applied at `container exec` — the only way
+    to get the token in, since it does not exist until after the container
+    runs (registration keys on the DHCP-assigned address).
+
+    This is the *sole* source of `*_PROXY` for the agent. It deliberately does
+    not rely on overriding a run-time value: `container exec --env` appends
+    rather than replaces, so a run-time `HTTPS_PROXY` would survive alongside
+    this one and first-wins runtimes would read the wrong entry. See
+    `_agent_env_entries`."""
     if not identity_token:
         return {}
-    url = _proxy_url(endpoint.gateway_ip, identity_token)
+    del endpoint  # the gateway is named, not addressed
+    url = _proxy_url(identity_token)
     return {
         "HTTPS_PROXY": url, "HTTP_PROXY": url,
         "https_proxy": url, "http_proxy": url,
@@ -317,16 +379,23 @@ def _agent_run_argv(
 def _agent_env_entries(
     plan: MacosContainerBottlePlan, endpoint: GatewayEndpoint,
 ) -> tuple[str, ...]:
-    # Token-less at run time — the token does not exist yet (see
-    # `_identity_proxy_env`). Anything egressing before the exec-time override
-    # is denied by `/resolve`, which is the safe direction.
-    proxy_url = _proxy_url(endpoint.gateway_ip)
-    no_proxy = _no_proxy(endpoint.gateway_ip)
+    # No `*_PROXY` here on purpose. The token-bearing URL is applied at
+    # `container exec` (`_identity_proxy_env`), and Apple's `container exec
+    # --env` **appends** to the run-time environment rather than replacing it:
+    # setting a token-less value here leaves two `HTTPS_PROXY` entries in the
+    # agent's `environ`, token-less first. Which one a runtime reads is then
+    # pure luck — Node takes the last (and worked), Rust's `std::env::var`
+    # takes the first, so Codex proxied without its identity token and
+    # `/resolve` fail-closed on every request.
+    #
+    # A token-less proxy URL has no legitimate consumer anyway: the init
+    # process is `sleep` and everything that egresses arrives via exec. Its
+    # only value was a tidy 403 for unattributed callers, which is not worth
+    # silently dropping attribution for. Without it a process that egresses
+    # before the exec-time env still fails closed — the agent network is
+    # host-only, so there is no route off it except the gateway.
+    no_proxy = _no_proxy()
     env = [
-        f"HTTPS_PROXY={proxy_url}",
-        f"HTTP_PROXY={proxy_url}",
-        f"https_proxy={proxy_url}",
-        f"http_proxy={proxy_url}",
         f"NO_PROXY={no_proxy}",
         f"no_proxy={no_proxy}",
         f"NODE_EXTRA_CA_CERTS={AGENT_CA_PATH}",

bot_bottle/backend/macos_container/util.py

@@ -10,6 +10,7 @@ import shutil
 import subprocess
 import tempfile
 import time
+from datetime import datetime, timezone
 from typing import Iterable
 
 from ...log import die, info
@@ -360,6 +361,21 @@ 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,
@@ -557,6 +573,41 @@ def try_container_ipv4_on_network(name: str, network: str) -> str:
     return ""
 
 
+def inspect_container_network_ip(name: str, network: str) -> str | None:
+    """IP of `name` on `network`, distinguishing inspect failure from "not yet".
+
+    Returns:
+      - the IP string when the container has one on `network`
+      - "" when inspect succeeds but no address is assigned yet (in-flight DHCP)
+      - None when the inspect command itself fails (authoritative list impossible)
+    """
+    result = subprocess.run(
+        [_CONTAINER, "inspect", name],
+        capture_output=True, text=True, check=False,
+    )
+    if result.returncode != 0:
+        return None
+    try:
+        data = json.loads(result.stdout or "[]")
+    except json.JSONDecodeError:
+        return None
+    if isinstance(data, list):
+        data = data[0] if data else {}
+    if not isinstance(data, dict):
+        return None
+    status = data.get("status")
+    networks = status.get("networks") if isinstance(status, dict) else None
+    if not isinstance(networks, list):
+        return ""
+    for entry in networks:
+        if not isinstance(entry, dict) or entry.get("network") != network:
+            continue
+        raw = entry.get("ipv4Address")
+        if isinstance(raw, str) and raw:
+            return raw.split("/", 1)[0]
+    return ""
+
+
 def wait_container_ipv4_on_network(
     name: str, network: str, *, timeout: float = 15.0, poll: float = 0.25,
 ) -> str:
@@ -611,6 +662,39 @@ def image_id(ref: str) -> str:
     raise AssertionError("unreachable")
 
 
+def image_created_at(ref: str) -> datetime | None:
+    """Return the image creation timestamp as an aware UTC datetime, or None
+    when the field is absent or unparseable (e.g. FROM-scratch images, images
+    pulled from registries that omit the field). Callers should skip the stale
+    check when None is returned rather than treating it as an error."""
+    result = subprocess.run(
+        [_CONTAINER, "image", "inspect", ref],
+        capture_output=True,
+        text=True,
+        check=False,
+    )
+    if result.returncode != 0:
+        die(
+            f"container image inspect for {ref!r} failed: "
+            f"{(result.stderr or '').strip() or '<no stderr>'}"
+        )
+    try:
+        data = json.loads(result.stdout or "{}")
+    except json.JSONDecodeError as exc:
+        die(f"container image inspect for {ref!r} returned malformed JSON: {exc}")
+    if isinstance(data, list) and data:
+        data = data[0]
+    if isinstance(data, dict):
+        value = data.get("created") or data.get("Created")
+        if isinstance(value, str) and value:
+            try:
+                ts = value.rstrip("Z")
+                return datetime.fromisoformat(ts).replace(tzinfo=timezone.utc)
+            except ValueError:
+                pass
+    return None
+
+
 def save(ref: str, output: str) -> None:
     subprocess.run([_CONTAINER, "image", "save", ref, "-o", output], check=True)
 

bot_bottle/backend/util.py

@@ -7,6 +7,8 @@ from __future__ import annotations
 import hashlib
 import os
 import ssl
+import time
+from collections.abc import Callable
 from pathlib import Path
 from typing import TYPE_CHECKING
 
@@ -15,6 +17,24 @@ from ..log import die, info
 if TYPE_CHECKING:
     from ..egress import EgressPlan
 
+_CA_POLL_INTERVAL = 0.5
+
+
+def poll_ca_cert(fetch: Callable[[], str | None], *, timeout: float) -> str:
+    """Poll `fetch` until it returns a non-empty PEM string or `timeout` expires.
+
+    `fetch` should return the PEM on success and `None` (or empty string) when
+    the cert is not yet available. Raises `TimeoutError` if the cert never
+    appears within `timeout` seconds."""
+    deadline = time.monotonic() + timeout
+    while True:
+        result = fetch()
+        if result:
+            return result
+        if time.monotonic() >= deadline:
+            raise TimeoutError(f"CA cert not available after {timeout:g}s")
+        time.sleep(_CA_POLL_INTERVAL)
+
 
 # Debian-family CA layout, shared by every backend (all guest images
 # are Debian-family). AGENT_CA_PATH is the source path that

bot_bottle/cli/__init__.py

@@ -19,6 +19,7 @@ from .commit import cmd_commit
 from .edit import cmd_edit
 from .info import cmd_info
 from .init import cmd_init
+from .login import cmd_login
 from .resume import cmd_resume
 from .start import cmd_start
 from .supervise import cmd_supervise
@@ -33,11 +34,19 @@ COMMANDS = {
     "info": cmd_info,
     "init": cmd_init,
     "list": cmd_list,
+    "login": cmd_login,
     "resume": cmd_resume,
     "start": cmd_start,
     "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", "login"})
+
 
 def usage() -> None:
     sys.stderr.write(f"usage: {PROG} <command> [args...]\n\n")
@@ -49,6 +58,7 @@ def usage() -> None:
     sys.stderr.write("  info      print env, skills, and prompt details for a named agent\n")
     sys.stderr.write("  init      interactively create a new agent and add it to bot-bottle.json\n")
     sys.stderr.write("  list      list available agents or active containers\n")
+    sys.stderr.write("  login     register this host with a bot-bottle console\n")
     sys.stderr.write(
         "  resume    re-launch a bottle by its identity "
         "(continues state from PRD 0016)\n"
@@ -80,7 +90,7 @@ def main(argv: list[str] | None = None) -> int:
         usage()
         die(f"unknown command: {command}")
     mgr = StoreManager.instance()
-    if not mgr.is_migrated():
+    if command not in NO_MIGRATION_COMMANDS and 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()
@@ -104,7 +114,3 @@ def main(argv: list[str] | None = None) -> int:
         return e.code if isinstance(e.code, int) else 1
     except KeyboardInterrupt:
         return 130
-
-
-if __name__ == "__main__":
-    sys.exit(main())

bot_bottle/cli/__main__.py

@@ -0,0 +1,15 @@
+"""Entry point for `python -m bot_bottle.cli`.
+
+`cli.py` at the repo root is the usual way in; this makes the package
+runnable too, so the CLI works from an installed copy where there is no
+`cli.py` on disk to point at.
+"""
+
+from __future__ import annotations
+
+import sys
+
+from . import main
+
+if __name__ == "__main__":
+    sys.exit(main())

bot_bottle/cli/_common.py

@@ -3,18 +3,10 @@
 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

@@ -21,16 +21,20 @@ from __future__ import annotations
 
 import sys
 
-from ..backend import get_bottle_backend, known_backend_names
+from ..backend import get_bottle_backend, has_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.
+    # deterministic across runs. Skip backends whose runtime
+    # isn't available on this host so e.g. macos-container
+    # doesn't error on Linux.
     plans = [
-        (name, get_bottle_backend(name)) for name in known_backend_names()
+        (name, get_bottle_backend(name))
+        for name in known_backend_names()
+        if has_backend(name)
     ]
     prepared = [(name, b, b.prepare_cleanup()) for name, b in plans]
 

bot_bottle/cli/login.py

@@ -0,0 +1,168 @@
+"""bb login — register this host with a bot-bottle console.
+
+Opens a device-authorization flow against the target console, waits for the
+operator to approve, then writes access and refresh tokens to
+~/.bot-bottle/console.json (or $BOT_BOTTLE_ROOT/console.json).
+
+Usage:
+  bb login [--console-url URL] [--label LABEL]
+
+Flags:
+  --console-url URL   Target console URL (overrides BB_CONSOLE_URL env var)
+  --label LABEL       Host label shown in the console (default: hostname)
+"""
+
+from __future__ import annotations
+
+import json
+import os
+import socket
+import sys
+import tempfile
+import time
+import urllib.error
+import urllib.request
+from pathlib import Path
+from typing import Any
+
+from ..paths import bot_bottle_root
+
+_CONSOLE_URL_ENV = "BB_CONSOLE_URL"
+_POLL_SLEEP = 2  # seconds between polls; matches console's poll_interval default
+
+
+def _usage() -> None:
+    sys.stderr.write(
+        "usage: bb login [--console-url URL] [--label LABEL]\n"
+        "\n"
+        "Options:\n"
+        "  --console-url URL  Console base URL (or BB_CONSOLE_URL env var)\n"
+        "  --label LABEL      Host label shown in the console (default: hostname)\n"
+    )
+
+
+def _flag(argv: list[str], name: str) -> str | None:
+    for i, arg in enumerate(argv):
+        if arg == name and i + 1 < len(argv):
+            return argv[i + 1]
+        if arg.startswith(f"{name}="):
+            return arg[len(name) + 1:]
+    return None
+
+
+def _post(url: str, payload: dict[str, Any]) -> dict[str, Any]:
+    data = json.dumps(payload).encode()
+    req = urllib.request.Request(
+        url, data=data, headers={"Content-Type": "application/json"}
+    )
+    with urllib.request.urlopen(req, timeout=10) as resp:
+        return json.loads(resp.read())
+
+
+def _get(url: str) -> tuple[int, dict[str, Any]]:
+    req = urllib.request.Request(url)
+    try:
+        with urllib.request.urlopen(req, timeout=10) as resp:
+            return resp.status, json.loads(resp.read())
+    except urllib.error.HTTPError as e:
+        return e.code, {}
+
+
+def _save_credentials(
+    console_url: str, host_id: str, access_token: str, refresh_token: str
+) -> Path:
+    path = bot_bottle_root() / "console.json"
+    path.parent.mkdir(parents=True, exist_ok=True)
+    content = (
+        json.dumps(
+            {
+                "url": console_url,
+                "host_id": host_id,
+                "access_token": access_token,
+                "refresh_token": refresh_token,
+            },
+            indent=2,
+        )
+        + "\n"
+    )
+    fd, tmp_path_str = tempfile.mkstemp(dir=path.parent, prefix=".console-")
+    tmp = Path(tmp_path_str)
+    try:
+        tmp.chmod(0o600)
+        with os.fdopen(fd, "w") as f:
+            f.write(content)
+        os.replace(tmp, path)
+    except OSError:
+        try:
+            tmp.unlink()
+        except OSError:
+            pass
+        raise
+    return path
+
+
+def cmd_login(argv: list[str]) -> int:
+    if "--help" in argv or "-h" in argv:
+        _usage()
+        return 0
+
+    console_url = _flag(argv, "--console-url") or os.environ.get(_CONSOLE_URL_ENV)
+    if not console_url:
+        sys.stderr.write(
+            "bb login: --console-url or BB_CONSOLE_URL is required\n"
+        )
+        return 1
+    console_url = console_url.rstrip("/")
+
+    label = _flag(argv, "--label") or socket.gethostname()
+
+    try:
+        resp = _post(f"{console_url}/api/v1/hosts/authorize", {"label": label})
+    except (OSError, ValueError) as exc:
+        sys.stderr.write(f"bb login: failed to start authorization: {exc}\n")
+        return 1
+
+    device_code = resp["device_code"]
+    user_code = resp["user_code"]
+    expires_in = resp.get("expires_in", 300)
+    poll_sleep = max(1, min(int(resp.get("poll_interval", _POLL_SLEEP)), 60))
+
+    sys.stderr.write(
+        f"\nOpen this URL in your browser to authorize this host:\n\n"
+        f"  {console_url}/hosts/authorize?code={user_code}\n\n"
+        f"Waiting for approval"
+    )
+
+    deadline = time.monotonic() + expires_in
+    while time.monotonic() < deadline:
+        sys.stderr.write(".")
+        sys.stderr.flush()
+        time.sleep(poll_sleep)
+
+        try:
+            code, result = _get(
+                f"{console_url}/api/v1/hosts/authorize/{device_code}"
+            )
+        except (OSError, ValueError):
+            continue
+
+        if code == 410:
+            break
+
+        st = result.get("status")
+        if st == "approved":
+            sys.stderr.write("\n\nApproved.\n")
+            path = _save_credentials(
+                console_url,
+                result["host_id"],
+                result["access_token"],
+                result["refresh_token"],
+            )
+            sys.stderr.write(f"Credentials saved to {path}\n")
+            return 0
+        if st == "denied":
+            sys.stderr.write("\n\nDenied by operator.\n")
+            return 1
+
+    sys.stderr.write("\n\nAuthorization timed out.\n")
+    return 1

bot_bottle/cli/start.py

@@ -27,7 +27,6 @@ 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
@@ -36,6 +35,7 @@ from ..bottle_state import (
     is_preserved,
     mark_preserved,
 )
+from ..image_cache import StaleImageError
 from ..log import info, die
 from ..manifest import Manifest, ManifestIndex
 from ._common import PROG, USER_CWD, read_tty_line
@@ -57,15 +57,6 @@ 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",
@@ -74,6 +65,14 @@ def cmd_start(argv: list[str]) -> int:
             "skip all prompts. For orchestrators, CI, and webhooks."
         ),
     )
+    parser.add_argument(
+        "--cached-images",
+        action="store_true",
+        help=(
+            "quickstart with existing local agent and sidecar images; "
+            "only valid with --headless"
+        ),
+    )
     parser.add_argument(
         "--bottle",
         action="append",
@@ -106,6 +105,8 @@ def cmd_start(argv: list[str]) -> int:
         help="agent name defined in bot-bottle.json (omit to pick interactively)",
     )
     args = parser.parse_args(argv)
+    if args.cached_images and not args.headless:
+        die("--cached-images is only supported with --headless")
 
     dry_run = args.dry_run or os.environ.get("BOT_BOTTLE_DRY_RUN") == "1"
     if args.no_cache or os.environ.get("BOT_BOTTLE_NO_CACHE") == "1":
@@ -115,11 +116,10 @@ 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, backend_name=backend_name
+            manifest, args, dry_run=dry_run
         )
 
     agent_name: str | None = args.name
@@ -158,6 +158,10 @@ def cmd_start(argv: list[str]) -> int:
     label, color = tui.name_color_modal(default_label=agent_name)
     label, color = _resolve_unique_label(label, color)
 
+    image_policy = _select_image_policy()
+    if image_policy is None:
+        return 0
+
     spec = BottleSpec(
         manifest=manifest,
         agent_name=agent_name,
@@ -166,11 +170,11 @@ def cmd_start(argv: list[str]) -> int:
         label=label,
         color=color,
         bottle_names=bottle_names,
+        image_policy=image_policy,
     )
     return _launch_bottle(
         spec,
         dry_run=dry_run,
-        backend_name=backend_name,
     )
 
 
@@ -182,7 +186,6 @@ def _start_headless(
     args: argparse.Namespace,
     *,
     dry_run: bool,
-    backend_name: str | None,
 ) -> int:
     """Non-interactive launch path for orchestrators / CI / webhooks.
 
@@ -226,11 +229,11 @@ def _start_headless(
         color=args.color or "",
         bottle_names=bottle_names,
         headless=True,
+        image_policy="cached" if args.cached_images else "fresh",
     )
     return _launch_bottle(
         spec,
         dry_run=dry_run,
-        backend_name=backend_name,
         assume_yes=True,
         headless_prompt_text=prompt,
     )
@@ -268,15 +271,18 @@ def prepare_with_preflight(
     injected callable, prompt y/N via the injected callable.
 
     `backend_name` selects which backend prepares the plan
-    (`None` → `$BOT_BOTTLE_BACKEND` → host auto-selection). The CLI
-    passes whatever `--backend` resolved to.
+    (`None` → `$BOT_BOTTLE_BACKEND` → host auto-selection).
+
+    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)
+    backend = get_bottle_backend(backend_name, prompt=not spec.headless)
     plan = backend.prepare(spec, stage_dir=stage_dir)
     identity = _identity_from_plan(plan)
 
@@ -406,6 +412,13 @@ def _text_prompt_yes() -> bool:
     return reply in ("y", "Y", "yes", "YES")
 
 
+def _select_image_policy() -> str | None:
+    return tui.filter_select(
+        ["fresh", "cached"],
+        title="Select image startup mode",
+    )
+
+
 def _text_render_preflight():
     def _render(plan: DockerBottlePlan, backend_name: str) -> None:
         print(file=sys.stderr)
@@ -548,6 +561,15 @@ def _launch_bottle(
             return 0
 
         backend = get_bottle_backend(backend_name)
+        try:
+            backend.prelaunch_checks(plan)
+        except StaleImageError as exc:
+            if assume_yes:
+                die(str(exc))
+            sys.stderr.write(f"bot-bottle: {exc}\nLaunch anyway? [y/N] ")
+            sys.stderr.flush()
+            if read_tty_line() not in ("y", "Y", "yes", "YES"):
+                return 0
         with backend.launch(plan) as bottle:
             agent_provider_template = getattr(plan, "agent_provider_template", "claude")
             extra_args: tuple[str, ...] = ()
@@ -566,10 +588,6 @@ def _launch_bottle(
                 f"session ended (exit {exit_code}); "
                 f"container {bottle.name} will be removed"
             )
-            # While the container is still alive: always snapshot the
-            # transcript and — if the agent exited non-zero — mark
-            # the state for preservation. This picks up crashes /
-            # Ctrl-Cs / OOM kills before cleanup removes the state dir.
             if agent_provider_template == "claude":
                 capture_claude_session_state(identity, exit_code)
         return 0

bot_bottle/config_store.py

@@ -0,0 +1,71 @@
+"""SQLite-backed bot-bottle configuration store."""
+
+from __future__ import annotations
+
+from pathlib import Path
+
+try:
+    from .db_store import DbStore
+    from .migrations import TableMigrations
+    from .paths import host_db_path
+except ImportError:
+    from db_store import DbStore  # type: ignore[import-not-found]  # pylint: disable=import-error,no-name-in-module
+    from migrations import TableMigrations  # type: ignore[import-not-found]  # pylint: disable=import-error,no-name-in-module
+    from paths import host_db_path  # type: ignore[import-not-found]  # pylint: disable=import-error,no-name-in-module
+
+
+DEFAULT_CACHED_IMAGE_STALE_WARNING_DAYS = 1
+
+
+class ConfigStore(DbStore):
+    """SQLite configuration for host-side bot-bottle settings."""
+
+    def __init__(self, db_path: Path | None = None) -> None:
+        migrations = TableMigrations("config_store", [
+            # v1 — host-side bot-bottle settings
+            """
+            CREATE TABLE IF NOT EXISTS bot_bottle_config (
+                id INTEGER PRIMARY KEY CHECK (id = 1),
+                cached_image_stale_warning_days INTEGER NOT NULL DEFAULT 1
+            )
+            """,
+        ])
+        super().__init__(db_path or host_db_path(), migrations)
+
+    def cached_image_stale_warning_days(self) -> int:
+        if not self.db_path.is_file():
+            return DEFAULT_CACHED_IMAGE_STALE_WARNING_DAYS
+        with self._connect() as conn:
+            row = conn.execute(
+                """
+                SELECT cached_image_stale_warning_days
+                FROM bot_bottle_config
+                WHERE id = 1
+                """,
+            ).fetchone()
+        if row is None:
+            return DEFAULT_CACHED_IMAGE_STALE_WARNING_DAYS
+        try:
+            return int(row["cached_image_stale_warning_days"])
+        except (TypeError, ValueError):
+            return DEFAULT_CACHED_IMAGE_STALE_WARNING_DAYS
+
+    def set_cached_image_stale_warning_days(self, days: int) -> Path:
+        with self._connect() as conn:
+            conn.execute(
+                """
+                INSERT INTO bot_bottle_config (id, cached_image_stale_warning_days)
+                VALUES (1, ?)
+                ON CONFLICT(id) DO UPDATE SET
+                    cached_image_stale_warning_days = excluded.cached_image_stale_warning_days
+                """,
+                (days,),
+            )
+        self._chmod()
+        return self.db_path
+
+
+__all__ = [
+    "DEFAULT_CACHED_IMAGE_STALE_WARNING_DAYS",
+    "ConfigStore",
+]

bot_bottle/constants.py

@@ -0,0 +1,17 @@
+"""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/contrib/claude/Dockerfile

@@ -10,7 +10,7 @@
 
 # Current Node LTS; slim variant keeps the image small while still
 # providing apt-get for any future additions.
-FROM node:22-slim
+FROM node:22-trixie-slim
 
 # Install runtime system deps. claude-code shells out to git for several
 # features (status checks, commits, PR creation) — without git in the
@@ -21,7 +21,15 @@ FROM node:22-slim
 # to it) works against egress's bumped TLS without the agent needing
 # local DNS.
 RUN apt-get update \
-  && apt-get install -y --no-install-recommends git ca-certificates curl ripgrep iproute2 dnsutils \
+  && apt-get install -y --no-install-recommends \
+  git \
+  ca-certificates \
+  curl \
+  openssh-client \
+  podman \
+  ripgrep \
+  iproute2 \
+  dnsutils \
   && rm -rf /var/lib/apt/lists/*
 
 # App-specific deps. Python isn't required by claude-code itself
@@ -39,6 +47,11 @@ RUN apt-get update \
 RUN npm install -g --no-fund --no-audit @anthropic-ai/claude-code@2.1.172 \
   && npm cache clean --force
 
+# Git reads both ~/.gitconfig and ~/.config/git/config. Keep its XDG config
+# path traversable by the non-root runtime user so permission errors do not
+# suppress bot-bottle's git-gate insteadOf rules.
+RUN install -d -o node -g node -m 755 /home/node/.config /home/node/.config/git
+
 # Run as a non-root user. The node image already provides a `node` user
 # (uid 1000) with a home directory, which is where claude-code will write
 # its session state.

bot_bottle/contrib/claude/agent_provider.py

@@ -23,8 +23,9 @@ from ...agent_provider import (
     provider_startup_args,
 )
 from ...backend.docker import util as docker_mod
-from ...egress import EgressRoute
+from ...egress import CLAUDE_HOST_CREDENTIAL_TOKEN_REF, EgressRoute
 from ...log import die, info, warn
+from .claude_auth import claude_host_access_token
 
 
 if TYPE_CHECKING:
@@ -118,7 +119,6 @@ class ClaudeAgentProvider(AgentProvider):
         color: str = "",
         provider_settings: dict[str, object] | None = None,
     ) -> AgentProvisionPlan:
-        del forward_host_credentials, host_env
         resolved_guest_env = dict(guest_env or {})
         startup_args = provider_startup_args(provider_settings)
         guest_home = self.guest_home
@@ -180,13 +180,24 @@ class ClaudeAgentProvider(AgentProvider):
                 claude_settings,
                 f"{guest_home}/.claude/settings.json",
             ))
+        provisioned_env: dict[str, str] = {}
+        if forward_host_credentials:
+            _host_env = host_env or dict(os.environ)
+            provisioned_env[CLAUDE_HOST_CREDENTIAL_TOKEN_REF] = (
+                claude_host_access_token(_host_env)
+            )
+
+        cred_token_ref = (
+            CLAUDE_HOST_CREDENTIAL_TOKEN_REF if forward_host_credentials
+            else auth_token
+        )
         egress_routes = (EgressRoute(
             host="api.anthropic.com",
-            auth_scheme="Bearer" if auth_token else "",
-            token_ref=auth_token,
+            auth_scheme="Bearer" if (auth_token or forward_host_credentials) else "",
+            token_ref=cred_token_ref,
         ),)
         hidden_env_names: frozenset[str] = frozenset()
-        if auth_token:
+        if auth_token or forward_host_credentials:
             env_vars["CLAUDE_CODE_OAUTH_TOKEN"] = "egress-placeholder"
             hidden_env_names = frozenset({"CLAUDE_CODE_OAUTH_TOKEN"})
 
@@ -208,6 +219,7 @@ class ClaudeAgentProvider(AgentProvider):
             files=tuple(files),
             egress_routes=egress_routes,
             hidden_env_names=hidden_env_names,
+            provisioned_env=provisioned_env,
         )
 
     def provision_skills(self, plan: "BottlePlan", bottle: "Bottle") -> None:

bot_bottle/contrib/claude/claude_auth.py

@@ -0,0 +1,114 @@
+"""Host Claude auth helpers.
+
+Reads the host's Claude Code credentials and returns only the access
+token needed by egress. Does not expose refresh tokens or raw payloads.
+
+Credential storage by platform:
+  Linux  — ~/.claude/.credentials.json
+  macOS  — macOS Keychain, service "Claude Code-credentials"
+            (file path is tried first; Keychain is the fallback)
+"""
+
+from __future__ import annotations
+
+import json
+import os
+import subprocess
+import sys
+from datetime import datetime, timezone
+from pathlib import Path
+
+from ...log import die
+
+
+_KEYCHAIN_SERVICE = "Claude Code-credentials"
+
+
+def claude_auth_path(host_env: dict[str, str] | None = None) -> Path:
+    env = os.environ if host_env is None else host_env
+    home = env.get("HOME")
+    if home:
+        return Path(home) / ".claude" / ".credentials.json"
+    return Path.home() / ".claude" / ".credentials.json"
+
+
+def _read_keychain() -> dict[str, object] | None:
+    """Try the macOS Keychain. Returns parsed JSON dict or None."""
+    if sys.platform != "darwin":
+        return None
+    try:
+        result = subprocess.run(
+            ["security", "find-generic-password", "-s", _KEYCHAIN_SERVICE, "-w"],
+            capture_output=True,
+            text=True,
+            timeout=10,
+        )
+    except (FileNotFoundError, subprocess.TimeoutExpired):
+        return None
+    if result.returncode != 0 or not result.stdout.strip():
+        return None
+    try:
+        raw = json.loads(result.stdout.strip())
+    except json.JSONDecodeError:
+        return None
+    return raw if isinstance(raw, dict) else None
+
+
+def claude_host_access_token(
+    host_env: dict[str, str] | None = None,
+    *,
+    now: datetime | None = None,
+) -> str:
+    path = claude_auth_path(host_env)
+    raw: dict[str, object] | None = None
+
+    if path.is_file():
+        try:
+            raw = json.loads(path.read_text())
+        except (OSError, json.JSONDecodeError) as e:
+            die(f"claude host credentials: could not read valid JSON at {path}: {e}")
+        if not isinstance(raw, dict):
+            die(f"claude host credentials: {path} must contain a JSON object")
+    else:
+        raw = _read_keychain()
+        if raw is None:
+            die(
+                f"claude host credentials: auth file missing at {path} and "
+                f"macOS Keychain lookup for '{_KEYCHAIN_SERVICE}' failed. "
+                "Run `claude login` on the host or disable "
+                "agent_provider.forward_host_credentials."
+            )
+
+    oauth = raw.get("claudeAiOauth")
+    if not isinstance(oauth, dict):
+        die(
+            "claude host credentials: claudeAiOauth is missing from credentials. "
+            "Run `claude login` on the host or disable "
+            "agent_provider.forward_host_credentials."
+        )
+
+    access_token = oauth.get("accessToken")
+    if not isinstance(access_token, str) or not access_token:
+        die(
+            "claude host credentials: claudeAiOauth.accessToken is missing or empty. "
+            "Run `claude login` on the host and restart the bottle."
+        )
+
+    # expiresAt is in milliseconds
+    expires_at = oauth.get("expiresAt")
+    if isinstance(expires_at, (int, float)):
+        check_now = now or datetime.now(timezone.utc)
+        exp_dt = datetime.fromtimestamp(float(expires_at) / 1000.0, timezone.utc)
+        if exp_dt <= check_now:
+            die(
+                "claude host credentials: host Claude access token is expired. "
+                "Run `claude login` on the host and restart the bottle."
+            )
+
+    return access_token
+
+
+__all__ = [
+    "claude_auth_path",
+    "claude_host_access_token",
+]

bot_bottle/contrib/codex/Dockerfile

@@ -3,10 +3,17 @@
 # Mirrors the default Claude image shape: Node LTS, git/network tooling,
 # non-root node user, and the provider CLI installed for that user.
 
-FROM node:22-slim
+FROM node:22-trixie-slim
 
 RUN apt-get update \
-  && apt-get install -y --no-install-recommends git ca-certificates curl procps ripgrep \
+  && apt-get install -y --no-install-recommends \
+  git \
+  ca-certificates \
+  curl \
+  openssh-client \
+  podman \
+  procps \
+  ripgrep \
   && rm -rf /var/lib/apt/lists/*
 
 # App-specific deps. Python isn't required by codex itself
@@ -17,6 +24,8 @@ RUN apt-get update \
   && apt-get install -y --no-install-recommends python3 python3-pip python3-venv \
   && rm -rf /var/lib/apt/lists/*
 
+RUN install -d -o node -g node -m 755 /home/node/.config /home/node/.config/git
+
 USER node
 WORKDIR /home/node
 

bot_bottle/contrib/pi/Dockerfile

@@ -2,7 +2,7 @@
 #
 # Node LTS, git/network tooling, and the Pi coding-agent CLI installed globally.
 
-FROM node:22-slim
+FROM node:22-trixie-slim
 
 RUN apt-get update \
   && apt-get install -y --no-install-recommends \
@@ -10,6 +10,8 @@ RUN apt-get update \
   ca-certificates \
   curl \
   fd-find \
+  openssh-client \
+  podman \
   ripgrep \
   && ln -s /usr/bin/fdfind /usr/local/bin/fd \
   && rm -rf /var/lib/apt/lists/*
@@ -21,7 +23,8 @@ RUN apt-get update \
 RUN npm install -g --ignore-scripts --no-fund --no-audit @earendil-works/pi-coding-agent \
   && npm cache clean --force
 
-RUN mkdir -p /home/node/.pi/agent \
+RUN install -d -o node -g node -m 755 /home/node/.config /home/node/.config/git \
+  && mkdir -p /home/node/.pi/agent \
   /home/node/.pi/context-mode/sessions \
   /tmp/pi-subagents-uid-1000 \
   && chown -R node:node /home/node/.pi /tmp \

bot_bottle/db_store.py

@@ -3,6 +3,7 @@
 from __future__ import annotations
 
 import sqlite3
+from contextlib import contextmanager
 from pathlib import Path
 
 try:
@@ -28,12 +29,21 @@ 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._connect() as conn:
+            with self._connection() as conn:
                 row = conn.execute(
                     "SELECT version FROM schema_versions WHERE module = ?",
                     (self._migrations.schema_key,),
@@ -45,7 +55,7 @@ class DbStore:
 
     def migrate(self) -> None:
         """Apply any pending migrations and set permissions on the DB file."""
-        with self._connect() as conn:
+        with self._connection() as conn:
             self._migrations.apply(conn)
         self._chmod()
 

bot_bottle/dlp_detectors.py

@@ -3,9 +3,8 @@
 Pure Python, no mitmproxy dependency. Each detector is a module-level
 function returning `ScanResult | None`.
 
-Ships flat into the gateway image alongside
-`egress_addon_core.py` — both this file and the package source use
-the same try/except import shim pattern.
+Available in the gateway via the installed `bot_bottle` package
+(see `Dockerfile.gateway`).
 """
 
 from __future__ import annotations
@@ -20,10 +19,7 @@ from math import log2
 from collections import Counter
 from urllib.parse import quote as url_quote
 
-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
+from .egress_addon_core import ScanResult
 
 
 # ---------------------------------------------------------------------------

bot_bottle/egress.py

@@ -30,6 +30,7 @@ if TYPE_CHECKING:
     from .manifest import ManifestBottle
 
 CODEX_HOST_CREDENTIAL_TOKEN_REF = "BOT_BOTTLE_CODEX_HOST_ACCESS_TOKEN"
+CLAUDE_HOST_CREDENTIAL_TOKEN_REF = "BOT_BOTTLE_CLAUDE_HOST_ACCESS_TOKEN"
 
 EGRESS_HOSTNAME = "egress"
 
@@ -145,6 +146,7 @@ def egress_manifest_routes(
             outbound_detectors=r.OutboundDetectors,
             inbound_detectors=r.InboundDetectors,
             outbound_on_match=r.OutboundOnMatch,
+            preserve_auth=r.PreserveAuth,
         ))
     return tuple(out)
 
@@ -400,6 +402,7 @@ class Egress(ABC):
         )
 
 __all__ = [
+    "CLAUDE_HOST_CREDENTIAL_TOKEN_REF",
     "CODEX_HOST_CREDENTIAL_TOKEN_REF",
     "EGRESS_HOSTNAME",
     "EGRESS_ROUTES_FILENAME",

bot_bottle/egress_addon.py

@@ -15,7 +15,9 @@ import typing
 
 from mitmproxy import http  # type: ignore[import-not-found]  # pylint: disable=import-error
 
-from egress_addon_core import (  # type: ignore[import-not-found]  # pylint: disable=import-error
+from bot_bottle.constants import IDENTITY_HEADER
+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,
@@ -38,24 +40,8 @@ from egress_addon_core import (  # type: ignore[import-not-found]  # pylint: dis
     scan_inbound,
     scan_outbound,
 )
-
-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
+from bot_bottle import supervise as _sv
+from bot_bottle.policy_resolver import PolicyResolver
 
 
 INTROSPECT_HOST = "_egress.local"
@@ -66,13 +52,6 @@ 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
@@ -388,7 +367,10 @@ class EgressAddon:
 
         # Strip agent-set Authorization after DLP scan so smuggled tokens
         # are caught above; the route may inject gateway-owned auth below.
-        flow.request.headers.pop("authorization", None)
+        # Routes with preserve_auth=True pass the header through as-is so the
+        # agent's own credentials (e.g. registry bearer tokens) reach the upstream.
+        if route is None or not route.preserve_auth:
+            flow.request.headers.pop("authorization", None)
 
         # Build headers mapping for match evaluation
         req_headers = {k.lower(): v for k, v in flow.request.headers.items()}
@@ -400,6 +382,7 @@ 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 + `yaml_subset` (which is itself stdlib-only and
-ships flat into the gateway image alongside this file —
-see `Dockerfile.gateway`)."""
+Imports: stdlib + sibling package modules (`yaml_subset`,
+`egress_dlp_config`). Available in the gateway via the installed
+`bot_bottle` package (see `Dockerfile.gateway`)."""
 
 from __future__ import annotations
 
@@ -16,36 +16,20 @@ import re
 import typing
 from dataclasses import dataclass
 
-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
+from .yaml_subset import YamlSubsetError, parse_yaml_subset
 
-# DLP detector-config parsing lives in a sibling module (also flat-bundled
-# into the gateway — see Dockerfile.gateway). Re-exported below so existing
-# `from egress_addon_core import ON_MATCH_*` callers keep working.
-try:
-    from egress_dlp_config import (  # type: ignore[import-not-found]
-        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,
-    )
-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,
-    )
+# DLP detector-config parsing lives in a sibling module. Re-exported below
+# so existing `from egress_addon_core import ON_MATCH_*` callers keep working.
+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,
+)
 
 
 # ---------------------------------------------------------------------------
@@ -94,6 +78,7 @@ class Route:
     inbound_detectors: tuple[str, ...] | None = None
     # "" means unset → DEFAULT_OUTBOUND_ON_MATCH. See OUTBOUND_ON_MATCH_VALUES.
     outbound_on_match: str = ""
+    preserve_auth: bool = False
 
 
 LOG_OFF = 0    # no logging
@@ -105,6 +90,14 @@ LOG_FULL = 2    # log block/warn events + full request and response bodies
 class Config:
     routes: tuple[Route, ...]
     log: int = LOG_OFF
+    # Why this Config is a deny-all, when it is one for a reason *other* than
+    # the bottle's own policy genuinely not listing the host. A deny-all is
+    # indistinguishable from "policy loaded, host not allowed" at the decision
+    # point — both are simply "no matching route" — so without this the
+    # operator sees `host X is not in the allowlist` and goes hunting for a
+    # missing route that was never the problem. Empty for a normally-parsed
+    # policy; `decide` prefers it over the allowlist wording when set.
+    deny_reason: str = ""
 
 
 @dataclass(frozen=True)
@@ -316,11 +309,18 @@ def _parse_one(idx: int, raw: object) -> Route:
         idx, host, raw_dict,
     )
 
+    preserve_auth_raw = raw_dict.get("preserve_auth", False)
+    if preserve_auth_raw is not True and preserve_auth_raw is not False:
+        raise ValueError(
+            f"{label} ({host}): 'preserve_auth' must be a boolean"
+        )
+    preserve_auth: bool = preserve_auth_raw
+
     for k in raw_dict:
-        if k not in ("host", "matches", "auth_scheme", "token_env", "dlp", "git"):
+        if k not in ("host", "matches", "auth_scheme", "token_env", "dlp", "git", "preserve_auth"):
             raise ValueError(
                 f"{label} ({host}): unknown key {k!r}; accepted keys "
-                f"are 'host', 'matches', 'auth_scheme', 'token_env', 'dlp', 'git'"
+                f"are 'host', 'matches', 'auth_scheme', 'token_env', 'dlp', 'git', 'preserve_auth'"
             )
 
     return Route(
@@ -332,6 +332,7 @@ def _parse_one(idx: int, raw: object) -> Route:
         outbound_detectors=outbound_detectors,
         inbound_detectors=inbound_detectors,
         outbound_on_match=outbound_on_match,
+        preserve_auth=preserve_auth,
     )
 
 
@@ -384,6 +385,8 @@ def route_to_yaml_dict(r: Route) -> dict[str, object]:
         dlp["outbound_on_match"] = r.outbound_on_match
     if dlp:
         d["dlp"] = dlp
+    if r.preserve_auth:
+        d["preserve_auth"] = True
     return d
 
 
@@ -421,16 +424,40 @@ class PolicyResolverLike(typing.Protocol):
         ...
 
 
+# Deny-all explanations. Each names the *actual* failure so an operator isn't
+# sent looking for a missing egress route when the bottle never had a policy
+# to begin with — the failure mode that made a bricked registration read like
+# a misconfigured allowlist.
+DENY_UNATTRIBUTED = (
+    "egress: this request was not attributed to any bottle, so no egress "
+    "policy applies and every host is denied. Either the bottle's registry "
+    "row is missing/ambiguous (torn down, or another bottle claimed its "
+    "source IP), or the request carried no matching identity token — check "
+    "that the caller's proxy URL includes it. This is not an allowlist problem."
+)
+DENY_UNPARSEABLE = (
+    "egress: this bottle's egress policy could not be parsed, so it is being "
+    "treated as deny-all. Fix the bottle's egress.routes; every host is denied "
+    "until it loads."
+)
+DENY_RESOLVER_ERROR = (
+    "egress: the orchestrator could not be reached to resolve this bottle's "
+    "egress policy, so every host is denied (fail-closed). Check that the "
+    "control plane is up; this is not an allowlist problem."
+)
+
+
 def _config_from_policy(policy: "str | None") -> "Config":
     """Parse a resolved policy blob into a Config, fail-closed: None / empty /
     unparseable all become a deny-all Config (no routes → every request
-    blocked)."""
+    blocked). Each deny-all carries the reason it is one, so the block message
+    names the real fault instead of blaming the allowlist."""
     if not policy:
-        return Config(routes=())  # unattributed or empty → deny-all
+        return Config(routes=(), deny_reason=DENY_UNATTRIBUTED)
     try:
         return load_config(policy)
     except ValueError:
-        return Config(routes=())  # unparseable policy → deny
+        return Config(routes=(), deny_reason=DENY_UNPARSEABLE)
 
 
 def resolve_client_config(
@@ -444,7 +471,7 @@ def resolve_client_config(
     try:
         policy = resolver.resolve(client_ip, identity_token)
     except Exception:  # noqa: BLE001  # pylint: disable=broad-exception-caught
-        return Config(routes=())  # orchestrator unreachable/errored → deny
+        return Config(routes=(), deny_reason=DENY_RESOLVER_ERROR)
     return _config_from_policy(policy)
 
 
@@ -473,7 +500,7 @@ def resolve_client_context(
             client_ip, identity_token,
         )
     except Exception:  # noqa: BLE001  # pylint: disable=broad-exception-caught
-        return Config(routes=()), "", {}  # orchestrator unreachable/errored → deny
+        return Config(routes=(), deny_reason=DENY_RESOLVER_ERROR), "", {}
     return _config_from_policy(policy), (bottle_id or ""), tokens
 
 
@@ -588,12 +615,16 @@ def decide(
     *,
     request_method: str = "GET",
     request_headers: typing.Mapping[str, str] | None = None,
+    deny_reason: str = "",
 ) -> Decision:
+    """`deny_reason` is `Config.deny_reason`: when the deny-all came from a
+    missing/unparseable policy rather than the bottle's own allowlist, report
+    that instead of implying a route is merely absent."""
     route = match_route(routes, request_host)
     if route is None:
         return Decision(
             action="block",
-            reason=(
+            reason=deny_reason or (
                 f"egress: host {request_host!r} is not in the "
                 f"bottle's egress.routes allowlist. Declare a "
                 f"route for it or remove the request."
@@ -868,6 +899,9 @@ __all__ = [
     "is_git_push_request",
     "is_git_fetch_request",
     "load_config",
+    "DENY_UNATTRIBUTED",
+    "DENY_UNPARSEABLE",
+    "DENY_RESOLVER_ERROR",
     "resolve_client_config",
     "resolve_client_context",
     "PolicyResolverLike",

bot_bottle/gateway_init.py

@@ -61,6 +61,11 @@ class _DaemonSpec:
 _EGRESS_ONLY_ENV_PREFIXES: tuple[str, ...] = ("EGRESS_TOKEN_",)
 _READY_GATED_DAEMONS: tuple[str, ...] = ("git-gate", "git-http")
 
+# Daemons that must be requested explicitly via BOT_BOTTLE_GATEWAY_DAEMONS
+# and are NOT started in the default (env-var-unset) case. The orchestrator
+# only runs in the combined infra container, never in a standalone gateway.
+_OPT_IN_DAEMONS: frozenset[str] = frozenset({"orchestrator"})
+
 
 def _env_for_daemon(name: str, base_env: dict[str, str]) -> dict[str, str]:
     """Egress sees the full bundle env. Everyone else gets a copy
@@ -75,11 +80,18 @@ def _env_for_daemon(name: str, base_env: dict[str, str]) -> dict[str, str]:
     }
 
 
+# The orchestrator is listed first so it starts before the gateway daemons,
+# giving the control plane a head start to accept /resolve calls. The gateway
+# daemons tolerate early /resolve failures and retry per-request.
 _DAEMONS: tuple[_DaemonSpec, ...] = (
+    _DaemonSpec("orchestrator", (
+        "python3", "-m", "bot_bottle.orchestrator",
+        "--host", "0.0.0.0", "--port", "8099", "--broker", "stub",
+    )),
     _DaemonSpec("egress", ("/bin/sh", "/app/egress-entrypoint.sh")),
     _DaemonSpec("git-gate", ("/bin/sh", "/git-gate-entrypoint.sh")),
-    _DaemonSpec("git-http", ("python3", "/app/git_http_backend.py")),
-    _DaemonSpec("supervise", ("python3", "/app/supervise_server.py")),
+    _DaemonSpec("git-http", ("python3", "-m", "bot_bottle.git_http_backend")),
+    _DaemonSpec("supervise", ("python3", "-m", "bot_bottle.supervise_server")),
 )
 
 
@@ -103,18 +115,20 @@ def _selected_daemons(
     env: dict[str, str],
     all_daemons: Sequence[_DaemonSpec] | None = None,
 ) -> tuple[_DaemonSpec, ...]:
-    """Filter the daemon set by the BOT_BOTTLE_GATEWAY_DAEMONS env
-    var. Unknown names in the list are ignored — the caller is the
-    source of truth for which daemons are wired.
+    """Filter the daemon set by the BOT_BOTTLE_GATEWAY_DAEMONS env var.
 
-    `all_daemons` defaults to `_DAEMONS` resolved at call time (not
-    at definition time), so tests can monkey-patch the module-level
-    `_DAEMONS` and have the new value take effect."""
+    When the var is unset/empty, return all non-opt-in daemons (the
+    standard gateway subset). Opt-in daemons (e.g. `orchestrator`) only
+    run when explicitly named — they never start in a plain gateway
+    container that doesn't set the env var. Unknown names are ignored.
+
+    `all_daemons` defaults to `_DAEMONS` resolved at call time (not at
+    definition time), so tests can pass a custom list."""
     if all_daemons is None:
         all_daemons = _DAEMONS
     raw = env.get("BOT_BOTTLE_GATEWAY_DAEMONS", "").strip()
     if not raw:
-        return tuple(all_daemons)
+        return tuple(d for d in all_daemons if d.name not in _OPT_IN_DAEMONS)
     wanted = {n.strip() for n in raw.split(",") if n.strip()}
     return tuple(d for d in all_daemons if d.name in wanted)
 
@@ -136,7 +150,7 @@ def _pump(name: str, stream: IO[bytes]) -> None:
 
 def _spawn(spec: _DaemonSpec) -> subprocess.Popen[bytes]:
     env = _env_for_daemon(spec.name, dict(os.environ))
-    proc = subprocess.Popen(
+    proc = subprocess.Popen(  # pylint: disable=consider-using-with
         _argv_for_daemon(spec.name, spec.argv, env),
         stdout=subprocess.PIPE,
         stderr=subprocess.STDOUT,
@@ -183,6 +197,14 @@ class _Supervisor:
                 except ProcessLookupError:
                     pass
 
+    def _sigkill_all(self) -> None:
+        for _, p in self.procs:
+            if p.poll() is None:
+                try:
+                    p.kill()
+                except ProcessLookupError:
+                    pass
+
     def request_restart(self, daemon_name: str) -> bool:
         """Queue a daemon restart for the main loop to process.
 
@@ -235,12 +257,7 @@ class _Supervisor:
                         f"grace ({_GRACE_SECONDS:.0f}s) elapsed; SIGKILL on "
                         f"{', '.join(still_running)}"
                     )
-                    for _, p in self.procs:
-                        if p.poll() is None:
-                            try:
-                                p.kill()
-                            except ProcessLookupError:
-                                pass
+                    self._sigkill_all()
 
         done = all(p.poll() is not None for _, p in self.procs)
         if done:
@@ -361,7 +378,10 @@ def main(argv: Sequence[str] | None = None) -> int:
     # --signal HUP <bundle>` after writing routes.yaml. The kernel
     # delivers SIGHUP to PID 1 (this supervisor); forward it to
     # mitmdump so it reloads its addon.
-    signal.signal(signal.SIGHUP, lambda *_: sup.forward_signal(signal.SIGHUP, "egress"))  # type: ignore
+    signal.signal(
+        signal.SIGHUP,
+        lambda *_: sup.forward_signal(signal.SIGHUP, "egress"),  # type: ignore[misc]
+    )
 
     while not sup.tick():
         time.sleep(_POLL_INTERVAL)

bot_bottle/git_gate_render.py

@@ -14,18 +14,12 @@ 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)
@@ -425,18 +419,24 @@ PY
 while IFS=' ' read -r old new ref; do
   [ -z "$ref" ] && continue
   [ "$new" = "$zero" ] && continue
-  if [ "$old" = "$zero" ]; then
-    # New ref: scan only the commits this push introduces — those
-    # reachable from $new but not from any ref the gate already has.
-    # Everything already on the gate arrived via upstream mirror-fetch
-    # or a previously gitleaks-scanned push, so it's already-upstream
-    # or already-scanned; re-scanning it (the old `$new` full-ancestry
-    # range) only resurfaces historical findings and blocks every new
-    # branch. See PRD 0028 / issue #106.
-    log_opts="$new --not --all"
-  else
-    log_opts="$old..$new"
-  fi
+  # Scan only the commits this push introduces — those reachable from
+  # $new but not from any ref the gate already has. Everything already
+  # on the gate arrived via upstream mirror-fetch or a previously
+  # gitleaks-scanned push, so it's already-upstream or already-scanned;
+  # re-scanning it only resurfaces historical fixture findings.
+  #
+  # Applies to both new refs and updates. The old existing-branch range
+  # `$old..$new` walks commits reachable from the new tip but not the
+  # *old branch tip*: on a rebase/force-push onto a freshly-advanced
+  # main that pulls in all of main's new history (incl. the deliberate
+  # sandbox-escape gitleaks fixtures), blocking the push. `--not --all`
+  # excludes anything already on the gate regardless of ancestry, so it
+  # is also correct for non-fast-forward pushes (a rebase can skip
+  # commits off the direct path). Security-equivalent per PRD 0028's
+  # analysis: the bare repo's refs come only from trusted upstream
+  # mirror-fetch or gitleaks-gated pushes.
+  # See PRD 0028 (open question) / issues #106, #346.
+  log_opts="$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

@@ -26,16 +26,8 @@ from http.server import BaseHTTPRequestHandler, ThreadingHTTPServer
 from pathlib import Path
 from urllib.parse import urlsplit
 
-# policy_resolver ships flat alongside this file in the gateway
-# 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
+from bot_bottle.constants import GIT_GATE_TIMEOUT_SECS, IDENTITY_HEADER
+from bot_bottle.policy_resolver import PolicyResolveError, PolicyResolver
 
 
 DEFAULT_PORT = 9420
@@ -46,12 +38,6 @@ 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"
 
@@ -89,13 +75,6 @@ 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/image_cache.py

@@ -0,0 +1,42 @@
+"""Shared helpers for cached-image quickstart stale checks."""
+
+from __future__ import annotations
+
+from datetime import datetime, timezone
+from pathlib import Path
+
+try:
+    from .config_store import ConfigStore
+except ImportError:
+    from config_store import ConfigStore  # type: ignore[import-not-found]  # pylint: disable=import-error,no-name-in-module
+
+
+class StaleImageError(Exception):
+    """Raised when a cached image or artifact exceeds the configured staleness
+    threshold. Callers can catch this to prompt interactively; headless paths
+    let it propagate as a fatal error."""
+
+
+def check_stale(label: str, created_at: datetime) -> None:
+    """Raise StaleImageError if `created_at` is older than the configured
+    stale-warning threshold. Negative threshold disables the check."""
+    threshold_days = ConfigStore().cached_image_stale_warning_days()
+    if threshold_days < 0:
+        return
+    now = datetime.now(timezone.utc)
+    created = created_at.astimezone(timezone.utc)
+    age = now - created
+    if age.total_seconds() <= threshold_days * 86400:
+        return
+    raise StaleImageError(
+        f"cached {label} is {age.days} day(s) old; "
+        "quickstart does not verify it matches the current Dockerfile/context"
+    )
+
+
+def check_stale_path(label: str, path: Path) -> None:
+    """Raise StaleImageError if `path`'s mtime exceeds the staleness threshold."""
+    check_stale(label, datetime.fromtimestamp(path.stat().st_mtime, tz=timezone.utc))
+
+
+__all__ = ["StaleImageError", "check_stale", "check_stale_path"]

bot_bottle/manifest_agent.py

@@ -25,8 +25,9 @@ class ManifestAgentProvider:
     header, and sets a placeholder CLAUDE_CODE_OAUTH_TOKEN in the agent
     so the Claude Code CLI starts.
 
-    `forward_host_credentials` forwards the host Codex auth token into
-    the egress daemon (Codex only).
+    `forward_host_credentials` forwards the host provider auth token into
+    the egress sidecar (Codex and Claude). For Codex this reads
+    `~/.codex/auth.json`; for Claude it reads `~/.claude/.credentials.json`.
     """
 
     template: str = "claude"
@@ -92,10 +93,15 @@ class ManifestAgentProvider:
                 f"is only supported for built-in templates "
                 f"({', '.join(sorted(PROVIDER_TEMPLATES))})"
             )
-        if forward_host_credentials and template != "codex":
+        if forward_host_credentials and template not in {"codex", "claude"}:
             raise ManifestError(
                 f"bottle '{bottle_name}' agent_provider.forward_host_credentials "
-                "is currently only supported for template 'codex'"
+                "is only supported for templates 'codex' and 'claude'"
+            )
+        if forward_host_credentials and auth_token:
+            raise ManifestError(
+                f"bottle '{bottle_name}' agent_provider.forward_host_credentials "
+                "and auth_token both set; use one or the other"
             )
         settings = _parse_provider_settings(bottle_name, template, d.get("settings"))
         return cls(

bot_bottle/manifest_egress.py

@@ -71,6 +71,7 @@ class ManifestEgressRoute:
     OutboundDetectors: tuple[str, ...] | None = None
     InboundDetectors: tuple[str, ...] | None = None
     OutboundOnMatch: str = ""
+    PreserveAuth: bool = False
 
     @classmethod
     def from_dict(cls, bottle_name: str, idx: int, raw: object) -> "ManifestEgressRoute":
@@ -190,11 +191,22 @@ class ManifestEgressRoute:
                         f"only 'fetch' is accepted"
                     )
 
+        # --- preserve_auth ---
+        preserve_auth = False
+        if "preserve_auth" in d:
+            raw_preserve_auth = d.get("preserve_auth")
+            if not isinstance(raw_preserve_auth, bool):
+                raise ManifestError(
+                    f"{label} preserve_auth must be a boolean "
+                    f"(was {type(raw_preserve_auth).__name__})"
+                )
+            preserve_auth = raw_preserve_auth
+
         for k in d:
-            if k not in ("host", "matches", "auth", "role", "dlp", "git"):
+            if k not in ("host", "matches", "auth", "role", "dlp", "git", "preserve_auth"):
                 raise ManifestError(
                     f"{label} has unknown key {k!r}; accepted keys are "
-                    f"'host', 'matches', 'auth', 'role', 'dlp', 'git'"
+                    f"'host', 'matches', 'auth', 'role', 'dlp', 'git', 'preserve_auth'"
                 )
 
         return cls(
@@ -207,6 +219,7 @@ class ManifestEgressRoute:
             OutboundDetectors=outbound_detectors,
             InboundDetectors=inbound_detectors,
             OutboundOnMatch=outbound_on_match,
+            PreserveAuth=preserve_auth,
         )
 
 

bot_bottle/orchestrator/client.py

@@ -15,6 +15,7 @@ from __future__ import annotations
 import json
 import urllib.error
 import urllib.request
+from collections.abc import Iterable
 from dataclasses import dataclass
 
 from ..paths import host_control_plane_token
@@ -40,10 +41,13 @@ class OrchestratorClientError(RuntimeError):
 @dataclass(frozen=True)
 class RegisteredBottle:
     """What `POST /bottles` returns: the minted bottle id and the per-bottle
-    identity token the agent presents for app-layer attribution."""
+    identity token the agent presents for app-layer attribution. `env_var_secret`
+    is set by the caller (not from the server response) and carries the
+    encryption key so it can be injected into the agent container's env."""
 
     bottle_id: str
     identity_token: str
+    env_var_secret: str = ""
 
 
 class OrchestratorClient:
@@ -119,17 +123,21 @@ class OrchestratorClient:
         metadata: str = "",
         policy: str = "",
         tokens: dict[str, str] | None = None,
+        env_var_secret: str = "",
     ) -> RegisteredBottle:
         """Register a bottle and broker its launch (`POST /bottles`). `tokens`
         are the per-bottle egress auth values (env_name -> value) the
-        orchestrator holds in memory for the gateway to inject. Returns the
-        minted id + identity token."""
+        orchestrator holds in memory for the gateway to inject. When
+        *env_var_secret* is provided, the orchestrator also encrypts the token
+        values and stores them in ``bottled_agent_secrets`` for restart
+        recovery. Returns the minted id + identity token."""
         payload = self._ok("POST", "/bottles", {
             "source_ip": source_ip,
             "image_ref": image_ref,
             "metadata": metadata,
             "policy": policy,
             "tokens": tokens or {},
+            "env_var_secret": env_var_secret,
         })
         bottle_id = payload.get("bottle_id")
         token = payload.get("identity_token")
@@ -137,6 +145,24 @@ class OrchestratorClient:
             raise OrchestratorClientError("register: response missing bottle_id/identity_token")
         return RegisteredBottle(bottle_id=bottle_id, identity_token=token)
 
+    def reprovision_gateway(self, bottle_id: str, env_var_secret: str) -> bool:
+        """Re-inject a bottle's egress tokens from its ENV_VAR_SECRET
+        (`POST /bottles/<id>/reprovision_gateway`). Returns True when the
+        orchestrator successfully decrypted and restored the tokens, False
+        when it had no stored secrets for this bottle (404)."""
+        status, _ = self._request(
+            "POST",
+            f"/bottles/{bottle_id}/reprovision_gateway",
+            {"env_var_secret": env_var_secret},
+        )
+        if status == 404:
+            return False
+        if not 200 <= status < 300:
+            raise OrchestratorClientError(
+                f"reprovision_gateway {bottle_id}: HTTP {status}"
+            )
+        return True
+
     def teardown_bottle(self, bottle_id: str) -> bool:
         """Tear a bottle down (`DELETE /bottles/<id>`). False if the
         orchestrator didn't know it (404) — idempotent for cleanup paths."""
@@ -147,6 +173,20 @@ class OrchestratorClient:
             raise OrchestratorClientError(f"teardown {bottle_id}: HTTP {status}")
         return True
 
+    def reconcile(
+        self, live_source_ips: Iterable[str], *, grace_seconds: float | None = None,
+    ) -> list[str]:
+        """Drop registry rows for bottles that are no longer running
+        (`POST /reconcile`), returning the reaped bottle ids. `live_source_ips`
+        is the caller's enumeration of its live bottles — the orchestrator
+        can't see the backend from inside the infra container."""
+        body: dict[str, object] = {"live_source_ips": list(live_source_ips)}
+        if grace_seconds is not None:
+            body["grace_seconds"] = grace_seconds
+        payload = self._ok("POST", "/reconcile", body)
+        reaped = payload.get("reaped")
+        return [r for r in reaped if isinstance(r, str)] if isinstance(reaped, list) else []
+
     def set_policy(self, bottle_id: str, policy: str) -> bool:
         """Live-reload a bottle's policy (`PUT /bottles/<id>/policy`). False on
         404 (unknown bottle)."""

bot_bottle/orchestrator/config_store.py

@@ -0,0 +1,107 @@
+"""Per-host orchestrator configuration store (settings in bot-bottle.db).
+
+Co-tenants the shared `bot-bottle.db` via the `DbStore` framework.  Settings
+are readable by the host launch path directly (no HTTP round-trip to the
+orchestrator), so they take effect even before the orchestrator is reachable.
+"""
+
+from __future__ import annotations
+
+import os
+import sqlite3
+from pathlib import Path
+
+from ..db_store import DbStore
+from ..migrations import TableMigrations
+from ..paths import host_db_path
+
+TEARDOWN_TIMEOUT_ENV = "BOT_BOTTLE_ORCHESTRATOR_TEARDOWN_TIMEOUT_SECONDS"
+DEFAULT_TEARDOWN_TIMEOUT_SECONDS = 30.0
+
+_MIGRATIONS = TableMigrations(
+    "orchestrator_config",
+    [
+        """
+        CREATE TABLE IF NOT EXISTS orchestrator_config (
+            id                       INTEGER PRIMARY KEY CHECK (id = 1),
+            teardown_timeout_seconds REAL
+        )
+        """,
+    ],
+)
+
+
+class OrchestratorConfigStore(DbStore):
+    """Orchestrator settings in the shared host DB."""
+
+    def __init__(self, db_path: Path | None = None) -> None:
+        super().__init__(db_path or host_db_path(), _MIGRATIONS)
+
+    def _connect(self) -> sqlite3.Connection:
+        conn = super()._connect()
+        conn.execute("PRAGMA busy_timeout=5000")
+        return conn
+
+    def get_teardown_timeout_seconds(self) -> float | None:
+        """Return the configured teardown timeout, or None if not set."""
+        try:
+            with self._connection() as conn:
+                row = conn.execute(
+                    "SELECT teardown_timeout_seconds FROM orchestrator_config WHERE id = 1"
+                ).fetchone()
+        except sqlite3.OperationalError:
+            return None
+        return row["teardown_timeout_seconds"] if row else None
+
+    def set_teardown_timeout_seconds(self, value: float) -> None:
+        """Persist the teardown timeout."""
+        with self._connection() as conn:
+            conn.execute(
+                "INSERT OR REPLACE INTO orchestrator_config"
+                " (id, teardown_timeout_seconds) VALUES (1, ?)",
+                (value,),
+            )
+        self._chmod()
+
+    def delete_teardown_timeout_seconds(self) -> bool:
+        """Clear the stored teardown timeout. Returns True if a value existed."""
+        with self._connection() as conn:
+            cur = conn.execute(
+                "UPDATE orchestrator_config SET teardown_timeout_seconds = NULL"
+                " WHERE id = 1 AND teardown_timeout_seconds IS NOT NULL"
+            )
+        return cur.rowcount > 0
+
+
+def resolve_teardown_timeout(db_path: Path | None = None) -> float:
+    """Return the teardown timeout to use, in priority order:
+
+    1. ``BOT_BOTTLE_ORCHESTRATOR_TEARDOWN_TIMEOUT_SECONDS`` env var
+    2. ``teardown_timeout_seconds`` in the orchestrator config DB
+    3. ``DEFAULT_TEARDOWN_TIMEOUT_SECONDS`` (30 s)
+    """
+    raw = os.environ.get(TEARDOWN_TIMEOUT_ENV, "").strip()
+    if raw:
+        try:
+            value = float(raw)
+            if value > 0:
+                return value
+        except ValueError:
+            pass
+
+    store = OrchestratorConfigStore(db_path)
+    if not store.is_migrated():
+        store.migrate()
+    db_value = store.get_teardown_timeout_seconds()
+    if db_value is not None and db_value > 0:
+        return db_value
+
+    return DEFAULT_TEARDOWN_TIMEOUT_SECONDS
+
+
+__all__ = [
+    "OrchestratorConfigStore",
+    "resolve_teardown_timeout",
+    "TEARDOWN_TIMEOUT_ENV",
+    "DEFAULT_TEARDOWN_TIMEOUT_SECONDS",
+]

bot_bottle/orchestrator/control_plane.py

@@ -9,10 +9,17 @@ vsock / unix-socket portability caveats):
     GET    /bottles                   -> 200 {"bottles": [ <redacted record>, ...]}
     POST   /bottles                   -> 201 {"bottle_id","identity_token"}  (launch)
                                          body: {"source_ip", ["image_ref"],
-                                                ["metadata"], ["policy"]}
+                                                ["metadata"], ["policy"],
+                                                ["tokens"], ["env_var_secret"]}
     PUT    /bottles/<bottle_id>/policy -> 200 {"updated": true} | 404  (live reload)
                                          body: {"policy"}
+    POST   /bottles/<bottle_id>/reprovision_gateway
+                                      -> 200 {"reprovisioned": true} | 404
+                                         body: {"env_var_secret"}
     DELETE /bottles/<bottle_id>        -> 200 {"torn_down": true} | 404  (teardown)
+    POST   /reconcile                 -> 200 {"reaped": [bottle_id, ...]}
+                                         body: {"live_source_ips": [...],
+                                                ["grace_seconds"]}
     POST   /attribute                 -> 200 {"bottle_id"} | 403
     POST   /resolve                   -> 200 {"bottle_id","policy"} | 403
                                          body: {"source_ip","identity_token"}
@@ -113,12 +120,14 @@ def dispatch(  # pylint: disable=too-many-return-statements,too-many-branches
         tokens = {
             k: v for k, v in raw_tokens.items() if isinstance(k, str) and isinstance(v, str)
         } if isinstance(raw_tokens, dict) else {}
+        env_var_secret = data.get("env_var_secret", "")
         rec = orch.launch_bottle(
             source_ip,
             image_ref=image_ref if isinstance(image_ref, str) else "",
             metadata=metadata if isinstance(metadata, str) else "",
             policy=policy if isinstance(policy, str) else "",
             tokens=tokens,
+            env_var_secret=env_var_secret if isinstance(env_var_secret, str) else "",
         )
         return 201, {"bottle_id": rec.bottle_id, "identity_token": rec.identity_token}
 
@@ -135,12 +144,50 @@ def dispatch(  # pylint: disable=too-many-return-statements,too-many-branches
             return 200, {"updated": True}
         return 404, {"error": "no such bottle"}
 
+    if (
+        method == "POST"
+        and route.startswith("/bottles/")
+        and route.endswith("/reprovision_gateway")
+    ):
+        bottle_id = route[len("/bottles/") : -len("/reprovision_gateway")]
+        try:
+            data = _parse_json_object(body)
+        except ValueError as e:
+            return 400, {"error": f"invalid JSON: {e}"}
+        env_var_secret = data.get("env_var_secret")
+        if not isinstance(env_var_secret, str) or not env_var_secret:
+            return 400, {"error": "env_var_secret (string) is required"}
+        if orch.reprovision_from_secret(bottle_id, env_var_secret):
+            return 200, {"reprovisioned": True}
+        return 404, {"error": "no stored secrets for this bottle"}
+
     if method == "DELETE" and route.startswith("/bottles/"):
         bottle_id = route[len("/bottles/"):]
         if orch.teardown_bottle(bottle_id):
             return 200, {"torn_down": True}
         return 404, {"error": "no such bottle"}
 
+    if method == "POST" and route == "/reconcile":
+        # Host-driven self-heal: the caller enumerates its live bottles (only
+        # the host can see the backend) and the orchestrator drops rows for
+        # every other active bottle. Trusted-caller only — an agent that could
+        # reach this would be able to unregister its neighbours.
+        try:
+            data = _parse_json_object(body)
+        except ValueError as e:
+            return 400, {"error": f"invalid JSON: {e}"}
+        raw_ips = data.get("live_source_ips")
+        if not isinstance(raw_ips, list):
+            return 400, {"error": "live_source_ips (list of strings) is required"}
+        live = [ip for ip in raw_ips if isinstance(ip, str) and ip]
+        grace = data.get("grace_seconds")
+        kwargs = (
+            {"grace_seconds": float(grace)}
+            if isinstance(grace, (int, float)) and not isinstance(grace, bool)
+            else {}
+        )
+        return 200, {"reaped": orch.reconcile(live, **kwargs)}
+
     if method == "POST" and route == "/attribute":
         try:
             data = _parse_json_object(body)

bot_bottle/orchestrator/gateway.py

@@ -27,6 +27,7 @@ from ..paths import (
     CONTROL_PLANE_TOKEN_ENV,
     host_control_plane_token,
     host_db_path,
+    host_gateway_ca_dir,
 )
 from ..supervise import DB_PATH_IN_CONTAINER
 
@@ -48,14 +49,23 @@ GATEWAY_LABEL = "bot-bottle-orch-gateway=1"
 # the source IP the gateway attributes by is the address on this network.
 GATEWAY_NETWORK = "bot-bottle-gateway"
 
-# mitmproxy's CA dir in the bundle. A persistent named volume here keeps the
-# gateway's self-generated CA STABLE across container recreation — every agent
-# installs this one CA to trust the shared gateway's TLS interception, so it
-# must not rotate when the gateway restarts.
+# mitmproxy's CA dir in the bundle. The host's gateway-CA dir (see
+# `host_gateway_ca_dir`) is bind-mounted here so the gateway's self-generated
+# CA stays STABLE across container recreation — every agent installs this one
+# CA to trust the shared gateway's TLS interception, so it must not rotate when
+# the gateway restarts. A host bind-mount rather than a named volume: a named
+# volume is silently wiped by `docker volume prune`, minting a fresh CA that
+# breaks every running bottle (issue #450).
 MITMPROXY_HOME = "/home/mitmproxy/.mitmproxy"
-GATEWAY_CA_VOLUME = "bot-bottle-gateway-mitmproxy"
 GATEWAY_CA_CERT = f"{MITMPROXY_HOME}/mitmproxy-ca-cert.pem"
 
+# The CA material mitmproxy writes into its confdir. mitmproxy reuses these on
+# startup when present and generates them only on first run, so persisting them
+# is what makes the CA stable; deleting them (see `rotate_gateway_ca`) forces a
+# fresh CA on the next start. `mitmproxy-ca.pem` (cert + private key) is the
+# signing identity; the rest are derived encodings agents/clients consume.
+GATEWAY_CA_GLOB = "mitmproxy-ca*"
+
 # The gateway data-plane image + its Dockerfile. Kept as a local constant
 # rather than imported from the backend layer, which would drag
 # the whole backend layer into the lean orchestrator (see #359); unify when
@@ -73,6 +83,26 @@ def _host_db_dir() -> str:
     return str(db_dir)
 
 
+def rotate_gateway_ca(ca_dir: Path | None = None) -> list[Path]:
+    """Delete the persisted mitmproxy CA so the next gateway start mints a
+    fresh one — the explicit, deliberate CA-rollover path (issue #450).
+
+    Persistence keeps the CA stable across restarts precisely because mitmproxy
+    reuses the on-disk CA; rotation is therefore just removing that material.
+    Returns the files removed (empty when there was no CA yet); idempotent.
+
+    This only clears the on-disk CA. It does NOT stop the running gateway (whose
+    mitmproxy still holds the old CA in memory) or re-provision agents — the
+    caller recreates the gateway to mint the new CA and re-attaches bottles.
+    `rotate-ca` on the orchestrator CLI wires those steps together."""
+    ca_dir = ca_dir if ca_dir is not None else host_gateway_ca_dir()
+    removed: list[Path] = []
+    for path in sorted(ca_dir.glob(GATEWAY_CA_GLOB)):
+        path.unlink()
+        removed.append(path)
+    return removed
+
+
 class GatewayError(Exception):
     """The shared gateway failed to build/start/stop (non-zero `docker` exit)."""
 
@@ -221,9 +251,10 @@ class DockerGateway(Gateway):
             "--name", self.name,
             "--label", GATEWAY_LABEL,
             "--network", self.network,
-            # Persist the self-generated CA so it survives restarts (agents
-            # trust it) — see GATEWAY_CA_VOLUME.
-            "--volume", f"{GATEWAY_CA_VOLUME}:{MITMPROXY_HOME}",
+            # Persist the self-generated CA on the host so it survives both
+            # container recreation AND docker volume pruning (agents trust it)
+            # — see host_gateway_ca_dir / issue #450.
+            "--volume", f"{host_gateway_ca_dir()}:{MITMPROXY_HOME}",
             # Share the one host DB: the supervise daemon queues proposals
             # into the same file the orchestrator (and the operator, over
             # HTTP) reads — no second, disconnected DB in the container.
@@ -272,7 +303,7 @@ class DockerGateway(Gateway):
 
 
 __all__ = [
-    "Gateway", "DockerGateway", "GatewayError",
+    "Gateway", "DockerGateway", "GatewayError", "rotate_gateway_ca",
     "GATEWAY_NAME", "GATEWAY_LABEL", "GATEWAY_IMAGE", "GATEWAY_NETWORK",
-    "GATEWAY_CA_VOLUME", "GATEWAY_CA_CERT",
+    "GATEWAY_CA_CERT", "GATEWAY_CA_GLOB",
 ]

bot_bottle/orchestrator/lifecycle.py

@@ -1,17 +1,15 @@
 """Orchestrator + gateway lifecycle (PRD 0070, docker slice).
 
-Runs the orchestrator control plane **as a container** on the shared gateway
-network, alongside the gateway container. This is the PRD's "virtualize the
-orchestrator": container↔container between the gateway and the orchestrator
-avoids the host firewall (which drops container→host traffic), and the gateway
-reaches the control plane by container name over docker DNS. The host CLI
-reaches it via a published loopback port.
+Runs both the orchestrator control plane and the gateway data plane inside
+a single `bot-bottle-infra` container on the shared gateway network —
+matching the structure already used by the macOS and Firecracker backends.
+`gateway_init` is PID 1 and supervises both; the infra container is an
+idempotent per-host singleton.
 
-The orchestrator runs with the **register-only broker** — the *backend*
-launches agent containers (compose), so the orchestrator needs no docker
-socket. That keeps this control-plane container unprivileged; the host manages
-both containers. `ensure_running` is an idempotent singleton (fixed container
-names + the published port).
+The combined container replaces the prior two-container split
+(bot-bottle-orchestrator + bot-bottle-orch-gateway). The host CLI reaches
+the control plane via a published loopback port; gateway daemons reach it
+over 127.0.0.1 (same container).
 """
 
 from __future__ import annotations
@@ -25,50 +23,75 @@ from pathlib import Path
 
 from .. import log
 from ..docker_cmd import run_docker
-from ..paths import CONTROL_PLANE_TOKEN_ENV, bot_bottle_root, host_control_plane_token
-from .gateway import GATEWAY_IMAGE, GATEWAY_NAME, GATEWAY_NETWORK, DockerGateway, GatewayError
+from ..paths import (
+    CONTROL_PLANE_TOKEN_ENV,
+    bot_bottle_root,
+    host_control_plane_token,
+    host_gateway_ca_dir,
+)
+from ..supervise import DB_PATH_IN_CONTAINER
+from .gateway import (
+    GATEWAY_DOCKERFILE,
+    GATEWAY_IMAGE,
+    GATEWAY_NETWORK,
+    GatewayError,
+    MITMPROXY_HOME,
+    _host_db_dir,
+)
 
 DEFAULT_PORT = 8099
-ORCHESTRATOR_NAME = "bot-bottle-orchestrator"
-ORCHESTRATOR_LABEL = "bot-bottle-orchestrator=1"
-# The control-plane's own runtime image — lean (python + the stdlib-only
-# `bot_bottle` package, bind-mounted at run time), distinct from the heavy
-# gateway data-plane image it used to borrow (#384). Env override for
-# operators pinning a published build.
+DEFAULT_STARTUP_TIMEOUT_SECONDS = 45.0
+
+INFRA_NAME = "bot-bottle-infra"
+INFRA_LABEL = "bot-bottle-infra=1"
+# The combined infra image: gateway data plane + orchestrator content.
+# Built from Dockerfile.infra (FROM gateway + COPY --from orchestrator).
+INFRA_IMAGE = os.environ.get("BOT_BOTTLE_INFRA_IMAGE", "bot-bottle-infra:latest")
+INFRA_DOCKERFILE = "Dockerfile.infra"
+# Baked as a container label so `ensure_running` can detect whether the
+# running container is executing the current bind-mounted source.
+INFRA_SOURCE_HASH_LABEL = "bot-bottle-infra-source-hash"
+
+# Orchestrator image: the single canonical definition of the control-plane
+# content (lean: python:3.12-slim + bot_bottle package, no mitmproxy/git).
+# Used as a build intermediate: `Dockerfile.infra` COPY --from this image.
 ORCHESTRATOR_IMAGE = os.environ.get(
     "BOT_BOTTLE_ORCHESTRATOR_IMAGE", "bot-bottle-orchestrator:latest"
 )
 ORCHESTRATOR_DOCKERFILE = "Dockerfile.orchestrator"
-# Baked onto the container as a label so `ensure_running` can tell whether the
-# running process is executing the *current* bind-mounted source — see
-# `source_hash`.
-ORCHESTRATOR_SOURCE_HASH_LABEL = "bot-bottle-orchestrator-source-hash"
 
-# The repo root is bind-mounted into the control-plane container so
-# `python -m bot_bottle.orchestrator` resolves the package (the orchestrator
-# is stdlib-only, so the lean orchestrator image's python is enough).
-_REPO_ROOT = Path(__file__).resolve().parents[2]
-_APP_DIR = "/app"
+# The gateway daemons + orchestrator the infra container runs.
+# BOT_BOTTLE_GATEWAY_DAEMONS listing `orchestrator` opts it in to
+# gateway_init's supervise tree (see gateway_init._OPT_IN_DAEMONS).
+_INFRA_DAEMONS = "egress,git-http,supervise,orchestrator"
+
+# The bind-mount path for the live control-plane source inside the
+# container. Separate from /app so the gateway's baked scripts
+# (egress_addon.py, egress-entrypoint.sh) are not overlaid.
+_SRC_IN_CONTAINER = "/bot-bottle-src"
+# Bot-bottle host-root bind-mount inside the container (DB + state).
 _ROOT_IN_CONTAINER = "/bot-bottle-root"
 
+# The supervise daemon writes proposals into the host DB directory.
+_SUPERVISE_DB_DIR_IN_CONTAINER = os.path.dirname(DB_PATH_IN_CONTAINER)
+
 _HEALTH_POLL_SECONDS = 0.25
-DEFAULT_STARTUP_TIMEOUT_SECONDS = 45.0
 _HEALTH_REQUEST_TIMEOUT_SECONDS = 1.0
 
+_REPO_ROOT = Path(__file__).resolve().parents[2]
+
 
 class OrchestratorStartError(RuntimeError):
-    """The orchestrator container did not become healthy within the timeout."""
+    """The infra container did not become healthy within the timeout."""
 
 
 def source_hash(repo_root: Path) -> str:
     """Content hash of the orchestrator's bind-mounted Python source (the
-    `bot_bottle` package the control-plane process imports). This only
-    changes when the code that would actually run inside the container
-    changes — `ensure_running` recreates the container on a mismatch and
-    otherwise leaves a healthy one alone, so a bottle launch that isn't
-    accompanied by a code change doesn't restart the process and drop every
-    *other* active bottle's in-memory egress tokens (`Orchestrator._tokens`
-    in `service.py`, never persisted to disk by design)."""
+    `bot_bottle` package the control-plane process imports). Changes only
+    when the code that would actually run changes — `ensure_running`
+    recreates the container on a mismatch so a code change takes effect,
+    but leaves a healthy up-to-date container alone to preserve in-memory
+    egress tokens."""
     h = hashlib.sha256()
     for path in sorted((repo_root / "bot_bottle").rglob("*.py")):
         h.update(str(path.relative_to(repo_root)).encode())
@@ -77,57 +100,37 @@ def source_hash(repo_root: Path) -> str:
 
 
 class OrchestratorService:
-    """Manages the orchestrator control-plane container + the shared gateway.
+    """Manages the single per-host infra container (control plane + gateway).
     Callers only need `ensure_running()` + `url`.
 
-    `orchestrator_name` / `orchestrator_label` let backends run independent
-    orchestrators on the same host without name collisions (e.g. the
-    Firecracker backend uses `bot-bottle-fc-orchestrator` alongside the Docker
-    backend's `bot-bottle-orchestrator`); `gateway_name` gives the paired
-    gateway container the same treatment (e.g. isolated integration tests
-    that can't share the production `GATEWAY_NAME` singleton). Subclass and
-    override `_gateway()` for anything `_gateway_image`/`gateway_name` can't
-    express (a genuinely backend-specific gateway variant)."""
+    `infra_name` / `infra_label` let backends run independent infra containers
+    on the same host without name collisions (e.g. isolated integration tests
+    that can't share the production INFRA_NAME singleton)."""
 
     def __init__(
         self,
         *,
         port: int = DEFAULT_PORT,
         network: str = GATEWAY_NETWORK,
-        image: str = ORCHESTRATOR_IMAGE,
-        gateway_image: str = GATEWAY_IMAGE,
-        gateway_name: str = GATEWAY_NAME,
+        image: str = INFRA_IMAGE,
         repo_root: Path = _REPO_ROOT,
         host_root: Path | None = None,
-        orchestrator_name: str = ORCHESTRATOR_NAME,
-        orchestrator_label: str = ORCHESTRATOR_LABEL,
+        infra_name: str = INFRA_NAME,
+        infra_label: str = INFRA_LABEL,
     ) -> None:
         self.port = port
         self.network = network
-        # Two distinct images (#384): `image` is the lean control-plane
-        # runtime this container runs; `_gateway_image` is the heavy egress /
-        # git-gate / supervise data plane the gateway container runs. They
-        # were one conflated image before the split.
         self.image = image
-        self._gateway_image = gateway_image
-        self._gateway_name = gateway_name
         self._repo_root = repo_root
         self._host_root = host_root or bot_bottle_root()
-        self._orchestrator_name = orchestrator_name
-        self._orchestrator_label = orchestrator_label
+        self._infra_name = infra_name
+        self._infra_label = infra_label
 
     @property
     def url(self) -> str:
         """Host-side control-plane URL (published loopback port)."""
         return f"http://127.0.0.1:{self.port}"
 
-    @property
-    def internal_url(self) -> str:
-        """Control-plane URL as the gateway container reaches it — by name over
-        docker DNS on the shared network. This is the gateway's
-        BOT_BOTTLE_ORCHESTRATOR_URL."""
-        return f"http://{self._orchestrator_name}:{self.port}"
-
     def is_healthy(self, *, timeout: float = _HEALTH_REQUEST_TIMEOUT_SECONDS) -> bool:
         try:
             with urllib.request.urlopen(f"{self.url}/health", timeout=timeout) as resp:
@@ -139,139 +142,131 @@ class OrchestratorService:
         proc = run_docker(["docker", "ps", "--filter", f"name=^/{name}$", "--format", "{{.Names}}"])
         return name in proc.stdout.split()
 
-    def _run_orchestrator_container(self, current_hash: str) -> None:
-        """Start the control-plane container (idempotent: clears a stale
-        fixed-name container first). Register-only broker → no docker socket.
-        Labels the container with `current_hash` so a later `ensure_running`
-        can detect a real code change (see `source_hash`)."""
-        run_docker(["docker", "rm", "--force", self._orchestrator_name])
-        proc = run_docker([
-            "docker", "run", "--detach",
-            "--name", self._orchestrator_name,
-            "--label", self._orchestrator_label,
-            "--label", f"{ORCHESTRATOR_SOURCE_HASH_LABEL}={current_hash}",
-            "--network", self.network,
-            # Host CLI reaches the control plane here; bound to loopback so it
-            # is not exposed on the host's external interfaces. NOTE: the
-            # container is still on `self.network` (the shared gateway network),
-            # so agents can reach it by container IP — which is exactly why the
-            # control plane requires the secret below rather than trusting the
-            # network boundary.
-            "--publish", f"127.0.0.1:{self.port}:{self.port}",
-            "--volume", f"{self._repo_root}:{_APP_DIR}:ro",
-            "--workdir", _APP_DIR,
-            # Persist the registry DB on the host (sole-owner: only the
-            # orchestrator opens bot-bottle.db).
-            "--volume", f"{self._host_root}:{_ROOT_IN_CONTAINER}",
-            "--env", f"BOT_BOTTLE_ROOT={_ROOT_IN_CONTAINER}",
-            # The control-plane secret it requires on every route but /health.
-            # Bare `--env NAME` → docker inherits the value from the run env
-            # below, so the secret never lands on argv / `docker inspect`.
-            "--env", CONTROL_PLANE_TOKEN_ENV,
-            "--entrypoint", "python3",
-            self.image,
-            "-m", "bot_bottle.orchestrator",
-            "--host", "0.0.0.0", "--port", str(self.port), "--broker", "stub",
-        ], env={**os.environ, CONTROL_PLANE_TOKEN_ENV: host_control_plane_token()})
-        if proc.returncode != 0:
-            raise OrchestratorStartError(
-                f"orchestrator container failed to start: {proc.stderr.strip()}"
-            )
-
-    def _gateway(self) -> DockerGateway:
-        return DockerGateway(
-            self._gateway_image,
-            name=self._gateway_name,
-            network=self.network,
-            orchestrator_url=self.internal_url,
-        )
-
-    def _ensure_orchestrator_image(self) -> None:
-        """Build the lean control-plane image from `Dockerfile.orchestrator`
-        when it's missing (#384). Cheap — a `FROM python:*-slim` base with no
-        deps to install, so the layer cache makes rebuilds a no-op. Unlike the
-        gateway image this is build-if-missing, not build-every-time: the
-        control plane bind-mounts its source, so a code change is caught by the
-        source-hash recreate (below), not by an image rebuild."""
-        if run_docker(["docker", "image", "inspect", self.image]).returncode == 0:
-            return
-        argv = ["docker", "build", "-t", self.image,
-                "-f", str(self._repo_root / ORCHESTRATOR_DOCKERFILE),
-                str(self._repo_root)]
-        if os.environ.get("BOT_BOTTLE_NO_CACHE"):
-            argv.insert(2, "--no-cache")
-        proc = run_docker(argv)
-        if proc.returncode != 0:
-            raise GatewayError(
-                f"orchestrator image build failed: {proc.stderr.strip()}"
-            )
-
-    def _orchestrator_source_current(self, current_hash: str) -> bool:
-        """True iff the running orchestrator container was created from the
-        *current* bind-mounted source. Mirrors `DockerGateway`'s
-        image-staleness check, but by content hash rather than image id since
-        the orchestrator runs bind-mounted source, not a built image."""
-        if not self._container_running(self._orchestrator_name):
+    def _infra_source_current(self, current_hash: str) -> bool:
+        """True iff the running infra container was started from the current
+        bind-mounted source. Mirrors the macOS backend's `_source_current`."""
+        if not self._container_running(self._infra_name):
             return False
         proc = run_docker([
             "docker", "inspect", "--format",
-            "{{ index .Config.Labels \"" + ORCHESTRATOR_SOURCE_HASH_LABEL + "\" }}",
-            self._orchestrator_name,
+            "{{ index .Config.Labels \"" + INFRA_SOURCE_HASH_LABEL + "\" }}",
+            self._infra_name,
         ])
         if proc.returncode != 0:
-            return True  # can't compare -> don't churn a working container
+            return True  # can't compare → don't churn a working container
         return proc.stdout.strip() == current_hash
 
+    def _ensure_network(self) -> None:
+        if run_docker(["docker", "network", "inspect", self.network]).returncode == 0:
+            return
+        proc = run_docker(["docker", "network", "create", self.network])
+        if proc.returncode != 0 and "already exists" not in proc.stderr:
+            raise GatewayError(
+                f"gateway network {self.network} failed to create: {proc.stderr.strip()}"
+            )
+
+    def _build_images(self) -> None:
+        """Build the gateway base, the orchestrator intermediate, then the
+        infra image. All are cache-aware: a no-op when nothing changed."""
+        for tag, dockerfile in (
+            (GATEWAY_IMAGE, GATEWAY_DOCKERFILE),
+            (ORCHESTRATOR_IMAGE, ORCHESTRATOR_DOCKERFILE),
+            (self.image, INFRA_DOCKERFILE),
+        ):
+            argv = ["docker", "build", "-t", tag,
+                    "-f", str(self._repo_root / dockerfile),
+                    str(self._repo_root)]
+            if os.environ.get("BOT_BOTTLE_NO_CACHE"):
+                argv.insert(2, "--no-cache")
+            proc = run_docker(argv)
+            if proc.returncode != 0:
+                raise GatewayError(f"{dockerfile} build failed: {proc.stderr.strip()}")
+
+    def _run_infra_container(self, current_hash: str) -> None:
+        """Start the combined infra container (idempotent: clears a stale
+        fixed-name container first). Labels the container with `current_hash`
+        so a later `ensure_running` can detect a real code change."""
+        self._ensure_network()
+        run_docker(["docker", "rm", "--force", self._infra_name])
+        proc = run_docker([
+            "docker", "run", "--detach",
+            "--name", self._infra_name,
+            "--label", self._infra_label,
+            "--label", f"{INFRA_SOURCE_HASH_LABEL}={current_hash}",
+            "--network", self.network,
+            # Host CLI reaches the control plane here (loopback only).
+            # gateway_init always starts the orchestrator on DEFAULT_PORT (8099)
+            # inside the container; self.port is the host-side published port.
+            "--publish", f"127.0.0.1:{self.port}:{DEFAULT_PORT}",
+            # Persist the mitmproxy CA on the host so it survives container
+            # recreation AND docker volume pruning (issue #450): every agent
+            # trusts this one CA, so a fresh one would break all running bottles.
+            "--volume", f"{host_gateway_ca_dir()}:{MITMPROXY_HOME}",
+            # Shared supervise DB (same file the operator reads over HTTP).
+            "--volume", f"{_host_db_dir()}:{_SUPERVISE_DB_DIR_IN_CONTAINER}",
+            "--env", f"SUPERVISE_DB_PATH={DB_PATH_IN_CONTAINER}",
+            # Live control-plane source, mounted to a path that does not
+            # overlay the gateway's baked /app scripts.
+            "--volume", f"{self._repo_root}:{_SRC_IN_CONTAINER}:ro",
+            # PYTHONPATH lets the orchestrator (and other Python daemons)
+            # import the live source ahead of the installed package.
+            "--env", f"PYTHONPATH={_SRC_IN_CONTAINER}",
+            # Orchestrator registry DB on the host (sole writer: control plane).
+            "--volume", f"{self._host_root}:{_ROOT_IN_CONTAINER}",
+            "--env", f"BOT_BOTTLE_ROOT={_ROOT_IN_CONTAINER}",
+            # Control-plane secret: required by the orchestrator (to enforce)
+            # and by the gateway daemons (to present on /resolve calls).
+            "--env", CONTROL_PLANE_TOKEN_ENV,
+            # Gateway daemons reach the orchestrator over loopback at its
+            # fixed internal port (DEFAULT_PORT), independent of self.port.
+            "--env", f"BOT_BOTTLE_ORCHESTRATOR_URL=http://127.0.0.1:{DEFAULT_PORT}",
+            # Opt the orchestrator into gateway_init's supervise tree.
+            "--env", f"BOT_BOTTLE_GATEWAY_DAEMONS={_INFRA_DAEMONS}",
+            self.image,
+        ], env={**os.environ, CONTROL_PLANE_TOKEN_ENV: host_control_plane_token()})
+        if proc.returncode != 0:
+            raise OrchestratorStartError(
+                f"infra container failed to start: {proc.stderr.strip()}"
+            )
+
     def ensure_running(
         self, *, startup_timeout: float = DEFAULT_STARTUP_TIMEOUT_SECONDS,
     ) -> str:
-        """Ensure the control plane + shared gateway are up; return the host
-        control-plane URL. Idempotent — a healthy control plane running
-        current code and a running gateway are left untouched. Raises
-        `OrchestratorStartError` on timeout."""
-        gateway = self._gateway()
-        gateway.ensure_built()  # rebuild the bundle image on a source change
-        gateway.ensure_running()  # creates the shared network + (re)starts gateway
+        """Ensure the infra container (control plane + gateway) is up; return
+        the host control-plane URL. Idempotent — a healthy container on current
+        source is left untouched. Raises `OrchestratorStartError` on timeout."""
+        self._build_images()
 
-        # Recreate the orchestrator container only when its bind-mounted
-        # source has actually changed since it started — its Python process
-        # loaded that code at startup and won't reload, so a stale container
-        # would keep running OLD control-plane code. Recreating on *every*
-        # launch (the prior behaviour) would drop every other active
-        # bottle's in-memory egress tokens each time a new bottle starts,
-        # since the orchestrator process holds them only in memory (#381).
         current_hash = source_hash(self._repo_root)
-        if self.is_healthy() and self._orchestrator_source_current(current_hash):
+        if self.is_healthy() and self._infra_source_current(current_hash):
             return self.url
 
-        self._ensure_orchestrator_image()
-        log.info(
-            "starting orchestrator container",
-            context={"name": self._orchestrator_name},
-        )
-        self._run_orchestrator_container(current_hash)
+        log.info("starting infra container", context={"name": self._infra_name})
+        self._run_infra_container(current_hash)
 
         deadline = time.monotonic() + startup_timeout
         while time.monotonic() < deadline:
             if self.is_healthy():
-                log.info("orchestrator healthy", context={"url": self.url})
+                log.info("infra container healthy", context={"url": self.url})
                 return self.url
             time.sleep(_HEALTH_POLL_SECONDS)
         raise OrchestratorStartError(
-            f"orchestrator at {self.url} did not become healthy within {startup_timeout:g}s"
+            f"infra container at {self.url} did not become healthy within {startup_timeout:g}s"
         )
 
     def stop(self) -> None:
-        """Remove the orchestrator + gateway containers (idempotent)."""
-        run_docker(["docker", "rm", "--force", self._orchestrator_name])
-        self._gateway().stop()
+        """Remove the infra container (idempotent)."""
+        run_docker(["docker", "rm", "--force", self._infra_name])
 
 
 __all__ = [
     "OrchestratorService",
     "OrchestratorStartError",
-    "ORCHESTRATOR_NAME",
+    "INFRA_NAME",
+    "INFRA_IMAGE",
+    "INFRA_SOURCE_HASH_LABEL",
     "ORCHESTRATOR_IMAGE",
     "DEFAULT_PORT",
     "DEFAULT_STARTUP_TIMEOUT_SECONDS",
+    "source_hash",
 ]

bot_bottle/orchestrator/registry.py

@@ -32,6 +32,7 @@ import hmac
 import secrets
 import sqlite3
 import time
+from collections.abc import Iterable
 from dataclasses import dataclass
 from pathlib import Path
 
@@ -42,6 +43,12 @@ from ..paths import host_db_path
 # 256 bits of urandom, URL-safe — unguessable per-bottle identity token.
 IDENTITY_TOKEN_BYTES = 32
 
+# How recently a row must have been registered to be exempt from
+# `reap_absent`. Covers the window between `container run` and the address
+# becoming visible to another launch's enumeration, so reconciliation never
+# reaps a bottle that is still coming up.
+DEFAULT_REAP_GRACE_SECONDS = 120.0
+
 
 def new_identity_token() -> str:
     """A fresh per-bottle identity token (PRD 0070 attribution defence)."""
@@ -106,6 +113,22 @@ _MIGRATIONS = TableMigrations(
         # egress allowlist / routes / git config selected by source IP. The
         # multi-tenant gateway resolves it per request via `attribute`.
         "ALTER TABLE orchestrator_bottles ADD COLUMN policy TEXT NOT NULL DEFAULT ''",
+        # v4 — per-bottle encrypted egress secrets (PRD prd-new-secret-provider).
+        # One row per env-var: key (env-var name) is plaintext for auditing;
+        # value is the encrypted token string. The encryption key (ENV_VAR_SECRET)
+        # lives only in the agent's environment — a row alone cannot recover the
+        # credential.
+        """
+        CREATE TABLE IF NOT EXISTS bottled_agent_secrets (
+            bottled_agent_id TEXT NOT NULL,
+            key              TEXT NOT NULL,
+            value            TEXT NOT NULL,
+            type             TEXT NOT NULL DEFAULT 'injected_env_var'
+        )
+        """,
+        # v5 — index for fast per-bottle lookups and bulk DELETE on teardown.
+        "CREATE INDEX IF NOT EXISTS idx_bottled_agent_secrets_id "
+        "ON bottled_agent_secrets (bottled_agent_id, type)",
     ],
 )
 
@@ -167,7 +190,7 @@ class RegistryStore(DbStore):
             metadata=metadata,
             policy=policy,
         )
-        with self._connect() as conn:
+        with self._connection() as conn:
             conn.execute(
                 "DELETE FROM orchestrator_bottles "
                 "WHERE source_ip = ? AND state = 'active' AND bottle_id != ?",
@@ -193,7 +216,7 @@ 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._connect() as conn:
+        with self._connection() as conn:
             cur = conn.execute(
                 "UPDATE orchestrator_bottles SET policy = ? WHERE bottle_id = ?",
                 (policy, bottle_id),
@@ -203,7 +226,7 @@ class RegistryStore(DbStore):
 
     def deregister(self, bottle_id: str) -> bool:
         """Remove a bottle. Returns True if a row was deleted."""
-        with self._connect() as conn:
+        with self._connection() as conn:
             cur = conn.execute(
                 "DELETE FROM orchestrator_bottles WHERE bottle_id = ?", (bottle_id,)
             )
@@ -211,7 +234,7 @@ class RegistryStore(DbStore):
 
     def get(self, bottle_id: str) -> BottleRecord | None:
         """Return the bottle by id, or None if absent."""
-        with self._connect() as conn:
+        with self._connection() as conn:
             row = conn.execute(
                 "SELECT * FROM orchestrator_bottles WHERE bottle_id = ?", (bottle_id,)
             ).fetchone()
@@ -219,12 +242,76 @@ class RegistryStore(DbStore):
 
     def all(self) -> list[BottleRecord]:
         """Every registered bottle, oldest first."""
-        with self._connect() as conn:
+        with self._connection() 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
@@ -232,7 +319,7 @@ 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._connect() as conn:
+        with self._connection() as conn:
             rows = conn.execute(
                 "SELECT * FROM orchestrator_bottles "
                 "WHERE source_ip = ? AND state = 'active'",
@@ -255,6 +342,57 @@ class RegistryStore(DbStore):
             return None
         return rec
 
+    # --- encrypted egress secret store ------------------------------------
+
+    def store_agent_secrets(
+        self,
+        bottle_id: str,
+        encrypted_values: dict[str, str],
+        secret_type: str = "injected_env_var",
+    ) -> None:
+        """Replace all stored secrets for *bottle_id* with *encrypted_values*
+        (env-var name → encrypted ciphertext). Deletes then re-inserts so a
+        re-registration is always consistent with the current token set."""
+        with self._connection() as conn:
+            conn.execute(
+                "DELETE FROM bottled_agent_secrets "
+                "WHERE bottled_agent_id = ? AND type = ?",
+                (bottle_id, secret_type),
+            )
+            conn.executemany(
+                "INSERT INTO bottled_agent_secrets "
+                "(bottled_agent_id, key, value, type) VALUES (?, ?, ?, ?)",
+                [(bottle_id, k, v, secret_type) for k, v in encrypted_values.items()],
+            )
+        self._chmod()
+
+    def get_agent_secrets(
+        self,
+        bottle_id: str,
+        secret_type: str = "injected_env_var",
+    ) -> dict[str, str]:
+        """Return {env_var_name: encrypted_value} for *bottle_id*, or {} if none."""
+        with self._connection() as conn:
+            rows = conn.execute(
+                "SELECT key, value FROM bottled_agent_secrets "
+                "WHERE bottled_agent_id = ? AND type = ?",
+                (bottle_id, secret_type),
+            ).fetchall()
+        return {row[0]: row[1] for row in rows}
+
+    def delete_agent_secrets(
+        self,
+        bottle_id: str,
+        secret_type: str = "injected_env_var",
+    ) -> None:
+        """Remove all stored secrets for *bottle_id* (e.g. on teardown)."""
+        with self._connection() as conn:
+            conn.execute(
+                "DELETE FROM bottled_agent_secrets "
+                "WHERE bottled_agent_id = ? AND type = ?",
+                (bottle_id, secret_type),
+            )
+
 
 __all__ = [
     "BottleRecord",
@@ -262,4 +400,5 @@ __all__ = [
     "new_identity_token",
     "default_db_path",
     "IDENTITY_TOKEN_BYTES",
+    "DEFAULT_REAP_GRACE_SECONDS",
 ]

bot_bottle/orchestrator/rotate_ca.py

@@ -0,0 +1,62 @@
+"""Rotate the shared gateway's mitmproxy CA (issue #450).
+
+    python -m bot_bottle.orchestrator.rotate_ca
+
+A deliberate CA rollover has two halves: drop the *persisted* CA so a fresh one
+is minted, and drop the *running* gateway so its mitmproxy (which holds the old
+CA in memory) is replaced. This one-shot command does both:
+
+  1. Delete the persisted CA under the host gateway-CA dir — the next gateway
+     start generates a new one (mitmproxy reuses an existing CA, generates only
+     when absent).
+  2. Force-remove the infra / standalone-gateway containers so the stale
+     in-memory CA is gone; the next bottle launch's idempotent `ensure_running`
+     brings the gateway back up and mints the fresh CA.
+
+It does NOT re-provision the new CA into already-running bottles — those must be
+re-attached so they install the new trust anchor. Rotation is thus an explicit,
+operator-driven action with a brief egress interruption, not an automatic one.
+"""
+
+from __future__ import annotations
+
+import sys
+from pathlib import Path
+
+from ..docker_cmd import run_docker
+from ..paths import host_gateway_ca_dir
+from .gateway import GATEWAY_NAME, rotate_gateway_ca
+from .lifecycle import INFRA_NAME
+
+# The containers whose mitmproxy would still be serving the old CA from memory:
+# the consolidated infra container and the standalone per-host gateway.
+_GATEWAY_CONTAINERS = (INFRA_NAME, GATEWAY_NAME)
+
+
+def _out(msg: str) -> None:
+    sys.stdout.write(f"rotate-ca: {msg}\n")
+
+
+def main(argv: list[str] | None = None) -> int:
+    del argv  # no flags — a single deliberate action
+    ca_dir: Path = host_gateway_ca_dir()
+    removed = rotate_gateway_ca(ca_dir)
+    if removed:
+        _out(f"removed {len(removed)} CA file(s) from {ca_dir}")
+    else:
+        _out(f"no persisted CA under {ca_dir}; a fresh one is minted on next start")
+
+    # Drop any running gateway so its in-memory (now-stale) CA is replaced on
+    # the next launch. `rm --force` on an absent name is a tolerated no-op.
+    for name in _GATEWAY_CONTAINERS:
+        proc = run_docker(["docker", "rm", "--force", name])
+        if proc.returncode == 0 and proc.stdout.strip():
+            _out(f"removed running container {name}")
+
+    _out("done — the next bottle launch remints the CA; re-attach bottles to "
+         "install the new trust anchor")
+    return 0
+
+
+if __name__ == "__main__":
+    raise SystemExit(main())

bot_bottle/orchestrator/secret_store.py

@@ -0,0 +1,94 @@
+"""Symmetric encryption for per-bottle egress secrets (PRD prd-new-secret-provider).
+
+Each agent receives a random ENV_VAR_SECRET at startup — passed as an env var,
+never logged or persisted. The host uses this key to encrypt each egress auth
+token value before writing it to the bottled_agent_secrets table; the DB rows
+(ciphertext, plaintext env-var name) without the key are insufficient to
+recover the credentials.
+
+On orchestrator restart the in-memory token map is lost. The host-side
+reattachment path reads ENV_VAR_SECRET from the running agent container via
+``docker exec … printenv ENV_VAR_SECRET`` and posts it to
+``POST /bottles/<id>/reprovision_gateway``; the orchestrator decrypts the
+stored rows and re-populates ``_tokens``.
+
+Encryption scheme: HMAC-SHA256 used as a PRF in CTR mode (stdlib-only,
+no external deps). Each value is encrypted independently. The output blob is
+``nonce (16 bytes) || ciphertext`` encoded as URL-safe base64 (no padding).
+
+    keystream_block_i = HMAC-SHA256(key, nonce || i.to_bytes(4, "big"))
+    ciphertext_i      = plaintext_i XOR keystream_block_i[:len(plaintext_i)]
+"""
+
+from __future__ import annotations
+
+import base64
+import hashlib
+import hmac
+import secrets
+
+_KEY_BYTES = 32    # 256-bit key from ENV_VAR_SECRET
+_NONCE_BYTES = 16  # 128-bit random nonce per encrypt call
+_BLOCK = 32        # HMAC-SHA256 output width == one keystream block
+
+# Env-var name the agent container receives at startup.
+ENV_VAR_SECRET_NAME = "ENV_VAR_SECRET"
+
+
+def new_env_var_secret() -> str:
+    """Generate a fresh ENV_VAR_SECRET: 32 random bytes as URL-safe base64."""
+    return base64.urlsafe_b64encode(secrets.token_bytes(_KEY_BYTES)).rstrip(b"=").decode()
+
+
+def _b64dec(s: str) -> bytes:
+    return base64.urlsafe_b64decode(s + "=" * (-len(s) % 4))
+
+
+def _keystream(key: bytes, nonce: bytes, block_index: int) -> bytes:
+    return hmac.new(
+        key, nonce + block_index.to_bytes(4, "big"), hashlib.sha256
+    ).digest()
+
+
+def encrypt_value(secret_b64: str, plaintext: str) -> str:
+    """Encrypt a single string value with *secret_b64* (the ENV_VAR_SECRET).
+
+    Returns a URL-safe base64 blob ``nonce || ciphertext`` suitable for
+    the ``bottled_agent_secrets.value`` column."""
+    key = _b64dec(secret_b64)
+    pt = plaintext.encode()
+    nonce = secrets.token_bytes(_NONCE_BYTES)
+    ct = bytearray()
+    for i in range(0, len(pt), _BLOCK):
+        chunk = pt[i : i + _BLOCK]
+        ks = _keystream(key, nonce, i)[: len(chunk)]
+        ct.extend(p ^ k for p, k in zip(chunk, ks))
+    return base64.urlsafe_b64encode(nonce + bytes(ct)).rstrip(b"=").decode()
+
+
+def decrypt_value(secret_b64: str, blob_b64: str) -> str:
+    """Decrypt a blob produced by :func:`encrypt_value`.
+
+    Returns the original plaintext string. Raises ``ValueError`` for malformed
+    input or a key mismatch (wrong key produces garbage, not an error, unless
+    the plaintext is non-UTF-8 — treat all such failures as wrong key)."""
+    key = _b64dec(secret_b64)
+    try:
+        blob = _b64dec(blob_b64)
+    except Exception as exc:
+        raise ValueError(f"invalid ciphertext blob: {exc}") from exc
+    if len(blob) < _NONCE_BYTES:
+        raise ValueError("ciphertext blob too short")
+    nonce, ciphertext = blob[:_NONCE_BYTES], blob[_NONCE_BYTES:]
+    pt = bytearray()
+    for i in range(0, len(ciphertext), _BLOCK):
+        chunk = ciphertext[i : i + _BLOCK]
+        ks = _keystream(key, nonce, i)[: len(chunk)]
+        pt.extend(c ^ k for c, k in zip(chunk, ks))
+    try:
+        return bytes(pt).decode()
+    except UnicodeDecodeError as exc:
+        raise ValueError(f"decryption produced non-UTF-8 output (wrong key?): {exc}") from exc
+
+
+__all__ = ["ENV_VAR_SECRET_NAME", "new_env_var_secret", "encrypt_value", "decrypt_value"]

bot_bottle/orchestrator/service.py

@@ -13,15 +13,20 @@ Launch lifecycle:
     and returns the record. If the broker rejects/fails, the registry entry
     is rolled back so a failed launch leaves no orphan.
   * `teardown_bottle` sends a signed teardown request, then deregisters.
+  * `reconcile` sweeps rows whose bottle is no longer running — the
+    self-heal for the teardown paths that never got to run (a hard-killed
+    launcher), since an orphan row at a recycled source IP bricks the next
+    bottle that lands on it.
 """
 
 from __future__ import annotations
 
 import json
+from collections.abc import Iterable
 from datetime import datetime, timezone
 
 from .broker import LaunchBroker, LaunchRequest, sign_request
-from .registry import BottleRecord, RegistryStore
+from .registry import DEFAULT_REAP_GRACE_SECONDS, BottleRecord, RegistryStore
 from .gateway import Gateway
 from ..supervise import (
     AuditEntry,
@@ -82,13 +87,22 @@ class Orchestrator:
         metadata: str = "",
         policy: str = "",
         tokens: dict[str, str] | None = None,
+        env_var_secret: str = "",
     ) -> BottleRecord:
         """Register a bottle (with its gateway policy + in-memory egress auth
         tokens) and broker its launch. Rolls the registry entry back if the
-        launch doesn't take, so a failure leaves no orphan."""
+        launch doesn't take, so a failure leaves no orphan.
+
+        When *env_var_secret* is provided alongside *tokens*, the token values
+        are also encrypted and written to ``bottled_agent_secrets`` so they can
+        survive an orchestrator restart (see ``reprovision_from_secret``)."""
         rec = self.registry.register(source_ip, metadata=metadata, policy=policy)
         if tokens:
             self._tokens[rec.bottle_id] = dict(tokens)
+            if env_var_secret:
+                from .secret_store import encrypt_value
+                encrypted = {k: encrypt_value(env_var_secret, v) for k, v in tokens.items()}
+                self.registry.store_agent_secrets(rec.bottle_id, encrypted)
         req = LaunchRequest(
             op="launch",
             bottle_id=rec.bottle_id,
@@ -117,6 +131,30 @@ class Orchestrator:
         self._tokens.pop(bottle_id, None)
         return True
 
+    def reconcile(
+        self,
+        live_source_ips: Iterable[str],
+        *,
+        grace_seconds: float = DEFAULT_REAP_GRACE_SECONDS,
+    ) -> list[str]:
+        """Drop registry rows for bottles that are no longer running, and
+        forget their in-memory egress tokens. Returns the reaped bottle ids.
+
+        The caller supplies the live set because only the host can enumerate
+        its own containers — the orchestrator runs *inside* the infra
+        container and has no view of the backend. Deliberately does not
+        broker a teardown: the container is already gone, so there is nothing
+        to stop, and a broker error must not stop the sweep from clearing
+        the row that would otherwise brick the next bottle at that address.
+
+        See `RegistryStore.reap_absent` for why orphans accumulate and why
+        they are harmful rather than merely untidy."""
+        reaped = self.registry.reap_absent(
+            live_source_ips, grace_seconds=grace_seconds)
+        for rec in reaped:
+            self._tokens.pop(rec.bottle_id, None)
+        return [rec.bottle_id for rec in reaped]
+
     def tokens_for(self, bottle_id: str) -> dict[str, str]:
         """The bottle's in-memory egress auth tokens (env_name -> value), or
         empty. The gateway injects these per request; they are never
@@ -255,6 +293,26 @@ class Orchestrator:
             ))
         return True, ""
 
+    # --- secret reprovision -----------------------------------------------
+
+    def reprovision_from_secret(self, bottle_id: str, env_var_secret: str) -> bool:
+        """Re-inject a bottle's egress tokens from its ENV_VAR_SECRET.
+
+        Reads the encrypted rows from ``bottled_agent_secrets``, decrypts each
+        value with *env_var_secret*, and restores ``_tokens[bottle_id]``.
+        Returns True on success, False when no stored secrets exist for this
+        bottle or decryption fails (wrong key / corrupt data)."""
+        from .secret_store import decrypt_value
+        encrypted = self.registry.get_agent_secrets(bottle_id)
+        if not encrypted:
+            return False
+        try:
+            self._tokens[bottle_id] = {k: decrypt_value(env_var_secret, v)
+                                       for k, v in encrypted.items()}
+        except ValueError:
+            return False
+        return True
+
     # --- consolidated gateway ----------------------------------------------
 
     def ensure_gateway(self) -> None:

bot_bottle/paths.py

@@ -33,6 +33,13 @@ HOST_DB_FILENAME = "bot-bottle.db"
 CONTROL_PLANE_TOKEN_FILENAME = "control-plane-token"
 CONTROL_PLANE_TOKEN_ENV = "BOT_BOTTLE_CONTROL_PLANE_TOKEN"
 
+# The host directory holding the gateway's persistent mitmproxy CA. Bind-mounted
+# into the infra/gateway container at mitmproxy's confdir so the self-generated
+# CA survives container recreation — every agent installs this one CA to trust
+# the shared gateway's TLS interception, so it must not rotate on restart. See
+# host_gateway_ca_dir() for why this is a host bind-mount, not a named volume.
+GATEWAY_CA_DIRNAME = "gateway-ca"
+
 
 def bot_bottle_root() -> Path:
     """The app data root — `$BOT_BOTTLE_ROOT` if set, else `~/.bot-bottle`."""
@@ -59,6 +66,23 @@ def host_db_dir() -> Path:
     return db_dir
 
 
+def host_gateway_ca_dir() -> Path:
+    """The directory holding the gateway's persistent mitmproxy CA, created if
+    missing. Backends bind-mount this into the infra/gateway container at
+    mitmproxy's confdir so the CA persists across container recreation.
+
+    A host bind-mount under the app-data root — deliberately NOT a Docker
+    named volume. A named volume survives `docker rm` but is silently wiped by
+    `docker volume prune` / `docker system prune --volumes` during routine host
+    maintenance; the gateway then mints a fresh CA that every already-running
+    bottle distrusts, failing the TLS handshake even after it reconnects to the
+    moved gateway (issue #450). A path under the root docker never prunes it,
+    and it stays directly inspectable + rotatable from the host."""
+    ca_dir = bot_bottle_root() / GATEWAY_CA_DIRNAME
+    ca_dir.mkdir(parents=True, exist_ok=True)
+    return ca_dir
+
+
 def host_control_plane_token() -> str:
     """The per-host control-plane secret, minted (256-bit, url-safe) and
     persisted 0600 on first use, then reused.
@@ -94,8 +118,10 @@ __all__ = [
     "HOST_DB_FILENAME",
     "CONTROL_PLANE_TOKEN_FILENAME",
     "CONTROL_PLANE_TOKEN_ENV",
+    "GATEWAY_CA_DIRNAME",
     "bot_bottle_root",
     "host_db_path",
     "host_db_dir",
+    "host_gateway_ca_dir",
     "host_control_plane_token",
 ]

bot_bottle/policy_resolver.py

@@ -22,8 +22,7 @@ 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 so it can be COPYed flat into
-the gateway.
+stdlib-only and free of bot-bottle imports.
 """
 
 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._connect() as conn:
+        with self._connection() 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._connect() as conn:
+        with self._connection() 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._connect() as conn:
+        with self._connection() 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._connect() as conn:
+        with self._connection() 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._connect() as conn:
+        with self._connection() 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._connect() as conn:
+        with self._connection() 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._connect() as conn:
+        with self._connection() as conn:
             conn.execute(
                 """
                 UPDATE supervise_proposals SET archived = 1

bot_bottle/store_manager.py

@@ -6,9 +6,11 @@ from pathlib import Path
 
 try:
     from .audit_store import AuditStore
+    from .config_store import ConfigStore
     from .queue_store import QueueStore
 except ImportError:
     from audit_store import AuditStore  # type: ignore[import-not-found]  # pylint: disable=import-error,no-name-in-module
+    from config_store import ConfigStore  # type: ignore[import-not-found]  # pylint: disable=import-error,no-name-in-module
     from queue_store import QueueStore  # type: ignore[import-not-found]  # pylint: disable=import-error,no-name-in-module
 
 _instance: StoreManager | None = None
@@ -47,11 +49,13 @@ class StoreManager:
         return (
             QueueStore("", self.db_path).is_migrated()
             and AuditStore(self.db_path).is_migrated()
+            and ConfigStore(self.db_path).is_migrated()
         )
 
     def migrate(self) -> None:
         QueueStore("", self.db_path).migrate()
         AuditStore(self.db_path).migrate()
+        ConfigStore(self.db_path).migrate()
 
 
 __all__ = ["StoreManager"]

bot_bottle/supervise.py

@@ -37,40 +37,23 @@ from abc import ABC
 from dataclasses import dataclass
 from pathlib import Path
 
-try:
-    from .supervise_types import (
-        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,
-    )
-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,
-    )
+from .supervise_types import (
+    ACTION_OPERATOR_EDIT,
+    AuditEntry,
+    Proposal,
+    Response,
+    STATUSES,
+    STATUS_APPROVED,
+    STATUS_MODIFIED,
+    STATUS_REJECTED,
+    TOOLS,
+    TOOL_CHECK_PROPOSAL,
+    TOOL_EGRESS_ALLOW,
+    TOOL_EGRESS_BLOCK,
+    TOOL_EGRESS_TOKEN_ALLOW,
+    TOOL_GITLEAKS_ALLOW,
+    TOOL_LIST_EGRESS_ROUTES,
+)
 
 
 try:
@@ -281,6 +264,7 @@ __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

@@ -2,14 +2,24 @@
 
 Per-bottle MCP server exposing tools the agent calls to propose egress
 config changes when stuck. The tools are `egress-allow`,
-`egress-block`, and `list-egress-routes`.
+`egress-block`, `list-egress-routes`, and `check-proposal`.
 
-Each queued tool call:
+Each queued proposal 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.
-  4. Returns the operator's `{status, notes}` to the agent.
+  3. Blocks polling for a matching Response row, up to a short grace
+     window (`SUPERVISE_RESPONSE_TIMEOUT_SECONDS`, default 30s).
+  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
@@ -22,13 +32,14 @@ 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, blocks, returns.
+  * `tools/call`           — validates, queues, waits out the grace
+                             window, returns (pending past it); or, for
+                             `check-proposal`, a non-blocking status poll.
 
 Everything else returns JSON-RPC error -32601 (method not found).
 
-Stdlib-only. The Dockerfile copies this file + bot_bottle/supervise.py
-into the image; the server imports `supervise` for the queue / Proposal
-plumbing.
+The Dockerfile copies this script to /app/supervise_server.py and installs
+the bot_bottle package so its `from bot_bottle.*` imports resolve.
 """
 
 from __future__ import annotations
@@ -42,29 +53,18 @@ import time
 import typing
 from dataclasses import dataclass, replace
 
-try:
-    # Same-directory imports inside the bundle container; these files are
-    # COPYed flat under /app by Dockerfile.gateway.
-    from egress_addon_core import (
-        LOG_OFF, load_config, resolve_client_context, route_to_yaml_dict,
-    )
-    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
+from bot_bottle.constants import IDENTITY_HEADER
+from bot_bottle.egress_addon_core import (
+    LOG_OFF, load_config, resolve_client_context, route_to_yaml_dict,
+)
+from bot_bottle.policy_resolver import PolicyResolveError, PolicyResolver
+from bot_bottle 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"
 
@@ -244,6 +244,31 @@ 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,
+        },
+    },
 ]
 
 
@@ -365,7 +390,7 @@ def handle_tools_call(
             deadline=deadline,
         )
     except TimeoutError:
-        text = format_pending_response_text(config.response_timeout_seconds)
+        text = format_pending_response_text(proposal.id, config.response_timeout_seconds)
         return {
             "content": [{"type": "text", "text": text}],
             "isError": False,
@@ -382,6 +407,54 @@ 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."""
@@ -394,12 +467,35 @@ def format_response_text(response: "_sv.Response") -> str:
     return "\n".join(lines)
 
 
-def format_pending_response_text(timeout_seconds: float) -> str:
+def format_pending_response_text(proposal_id: str, 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}",
         (
-            "notes: operator response timed out after "
-            f"{timeout_seconds:g}s; proposal remains queued"
+            f"notes: no operator decision within {timeout_seconds:g}s; the "
+            "proposal remains queued. Poll it (do not re-propose) by calling "
+            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."
         ),
     ])
 
@@ -494,6 +590,11 @@ 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

@@ -20,6 +20,10 @@ 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,
@@ -156,6 +160,7 @@ __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

@@ -7,6 +7,7 @@ from __future__ import annotations
 
 import ipaddress
 import os
+import sys
 
 
 def is_ip_literal(value: str) -> bool:
@@ -17,6 +18,15 @@ 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/decisions/0005-issues-own-tracker-metadata.md

@@ -0,0 +1,57 @@
+# ADR 0005: Keep tracker metadata on issues
+
+- **Status:** Accepted
+- **Date:** 2026-07-18
+- **Deciders:** didericis
+
+## Context
+
+Gitea exposes labels on both issues and pull requests. Applying the same labels
+to both copies planning metadata, creates a synchronization obligation, and
+makes disagreements between the two records possible. At the same time,
+unlabelled objects look accidental unless the repository states which object
+owns the metadata.
+
+The repository already uses issues as work items and PRs as implementations of
+those work items. At this decision's cutoff, all open PRs reference issues, but
+121 of 219 historically merged PRs do not. Manufacturing retrospective issues
+for that history would create records that never participated in planning and
+would make the issue history less truthful.
+
+## Decision
+
+Issues are the canonical tracker records and own labels. Every issue has at
+least one label. An issue opened or left without labels receives
+`Status/Needs Triage` automatically until it is classified.
+
+Pull requests carry no labels. Every new PR deliberately references at least
+one existing issue in its title or description with one of these forms:
+
+- `Closes #123`, `Fixes #123`, or `Resolves #123` when merging completes it.
+- `Part of #123`, `Related to #123`, `Refs #123`, or `References #123` when it
+  contributes without completing it.
+
+Gitea Actions enforces both PR rules as a status check and repairs the empty
+issue-label state. Branch protection makes the PR policy check required.
+
+The policy applies from 2026-07-18 onward. Existing issues may be labelled as
+they are encountered, but closed PRs are grandfathered: no retrospective
+issues or PR labels are created solely to make history conform.
+
+## Consequences
+
+- Classification, priority, and workflow metadata have one source of truth.
+- A PR's issue link is the navigation path to its planning metadata.
+- Multi-PR issues do not require copied or synchronized labels.
+- `Status/Needs Triage` is an intentional fallback, not a final
+  classification.
+- Direct issue creation remains convenient; automation repairs a missing label
+  immediately after creation because Gitea has no native required-label rule.
+- The required check must be configured in branch protection after this
+  workflow lands.
+
+## Links
+
+- Issue #405.
+- `.gitea/workflows/tracker-policy.yml`.
+- `scripts/tracker_policy.py`.

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/landscape-containerized-claude.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/agent-sandbox-landscape.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/landscape-containerized-claude.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/agent-sandbox-landscape.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/landscape-containerized-claude.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/agent-sandbox-landscape.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/landscape-containerized-claude.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/agent-sandbox-landscape.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/landscape-containerized-claude.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/agent-sandbox-landscape.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/landscape-containerized-claude.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/agent-sandbox-landscape.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/landscape-containerized-claude.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/agent-sandbox-landscape.md`.
 
 - **Status:** Superseded (2026-07-11) — was Active
 - **Author:** Claude

docs/prds/0070-per-host-orchestrator.md

@@ -312,6 +312,44 @@ reaches over the RPC rather than a shared mount into the VM. WAL on the
 shared DB is therefore a deliberate, tested future change — not enabled ad
 hoc. `sqlite3` itself is stdlib, so "the host needs SQLite" is a non-cost.
 
+### Gateway CA: host-resident, like the DB
+
+The shared gateway bumps TLS with a self-generated mitmproxy CA, and **every
+bottle installs that CA** into its trust store to accept the bumped leaves. So
+the CA is durable per-host state with the same rule as the DB: it must outlive
+any single gateway container, or a restart mints a fresh CA that every
+already-running bottle distrusts — the TLS handshake then fails even after the
+bottle re-resolves and reconnects to the moved gateway (issue #450, a
+re-attachment blocker distinct from #443/#445).
+
+The CA lives on the **host filesystem** at `bot_bottle_root()/gateway-ca`
+(`host_gateway_ca_dir()`), bind-mounted into the container at mitmproxy's
+confdir. This is deliberately a host bind-mount, **not a container-runtime
+named volume**: a named volume survives ordinary container removal but can be
+silently wiped by Docker's or Apple Container's volume-prune commands during
+routine host maintenance, which is exactly how the ephemeral-CA symptom shows
+up in practice. A path under the app-data root is not managed or pruned by the
+container runtime, and stays directly inspectable and rotatable from the host.
+mitmproxy reuses an existing CA and generates one only on first run, so the
+bind-mount alone gives
+"adopt-existing, generate-on-first-run" for free.
+
+The macOS backend uses the same host-resident CA directory and bind-mounts it
+into the consolidated Apple infra container. Its `bot-bottle-mac-db` named
+volume remains container-only because that prevents incoherent cross-kernel
+SQLite locking, but the CA is deliberately not stored there: Apple Container
+also has a `container volume prune` operation, and the named volume is
+temporarily unreferenced while the infra container is recreated. Keeping the
+CA on the host makes both ordinary recreation and volume pruning safe.
+
+**Deliberate rollover** is the explicit inverse: `rotate_gateway_ca()` removes
+the persisted CA material so the next start remints it, and the
+`python -m bot_bottle.orchestrator.rotate_ca` one-shot wires that together with
+dropping the running gateway container (whose mitmproxy still holds the old CA
+in memory). Rotation does not auto-re-provision the new CA into running bottles
+— those re-attach to install the new anchor — so it is an operator action with
+a brief egress interruption, never an implicit one.
+
 ## Sequencing
 
 Jump straight to the **virtualized** end state (not a host-daemon stepping

docs/prds/prd-new-ci-artifact-coverage.md

@@ -0,0 +1,110 @@
+# PRD prd-new: CI artifact-based coverage and local Firecracker candidate flow
+
+- **Status:** Active
+- **Author:** Claude
+- **Created:** 2026-07-21
+- **Issue:** #446
+
+## Summary
+
+Restructure the CI test pipeline to run each test suite exactly once, upload
+small `.coverage.*` artifacts, and combine them in a lightweight aggregation
+job. Move the infra build onto the KVM runner so the ~194 MB rootfs never
+crosses the network for PRs. On main-branch pushes, publish the byte-identical
+rootfs that was tested.
+
+## Motivation
+
+The prior pipeline had two redundant costs:
+
+1. **Duplicate artifact transfers.** `build-infra` (ubuntu-latest) built and
+   uploaded the ~194 MB rootfs; `integration-firecracker` downloaded it; the
+   `coverage` job downloaded it a second time. Combined download overhead: ~83
+   seconds per run, plus the ~70-second upload.
+
+2. **Duplicate test execution.** `integration-firecracker` ran the Firecracker
+   integration suite; `coverage` ran the entire unit + integration suite again
+   on the same KVM runner to collect coverage data. Every line of Firecracker
+   code was tested twice per CI run.
+
+## Goals
+
+- Each test suite (unit, integration-docker, integration-firecracker) executes
+  exactly once per workflow run.
+- PRs incur no large artifact transfers — the rootfs stays on the KVM runner.
+- Main-branch pushes publish a byte-for-byte identical rootfs to the one that
+  passed the integration tests.
+- Concurrent workflow runs cannot cross-publish candidates (naturally enforced
+  by Gitea Actions' per-run artifact scoping).
+- Failed or cancelled runs block publication (enforced by the `needs:` chain on
+  `publish-infra`).
+
+## Non-goals
+
+- Changing test semantics or the coverage policy (ADR 0004).
+- Removing the KVM runner guard on `integration-firecracker` and `coverage`.
+- Changing how `publish_infra.py` builds or uploads the rootfs.
+
+## Design
+
+### Job graph
+
+```
+unit ──────────────────────────────────┐
+integration-docker ────────────────────┤──► coverage ──► publish-infra (main only)
+integration-firecracker (KVM) ─────────┘
+```
+
+### `unit`
+
+Unchanged except: `coverage run` writes `--data-file=.coverage.unit`; the file
+is uploaded as the `coverage-unit` artifact.
+
+### `integration-docker`
+
+Adds a `coverage` install step. `coverage run` writes `--data-file=.coverage.docker`;
+the file is uploaded as `coverage-docker`.
+
+### `integration-firecracker` (KVM runner)
+
+Replaces the old `stage-firecracker-inputs` → `build-infra` → download chain:
+
+1. Builds the infra candidate locally with
+   `BOT_BOTTLE_FC_DROPBEAR=/var/cache/bot-bottle-fc/dropbear`.
+2. Boots the candidate and runs integration tests with coverage, writing
+   `.coverage.firecracker`.
+3. Uploads the small `coverage-firecracker` artifact unconditionally.
+4. On main-branch pushes only, uploads the rootfs as `infra-candidate` and the
+   dropbear as `firecracker-inputs` so `publish-infra` can verify and publish
+   the byte-identical artifact.
+
+### `coverage`
+
+Moves from a KVM runner to `ubuntu-latest`. No tests are re-executed:
+
+1. Downloads `coverage-unit`, `coverage-docker`, and `coverage-firecracker`.
+2. Runs `scripts/coverage.sh aggregate critical`, which calls
+   `coverage combine` then `coverage report`.
+3. Runs the diff-coverage gate (`scripts/diff_coverage.py`).
+
+Coverage files use `relative_files = True` (`.coveragerc`) so they combine
+cleanly across runners with different absolute workspace paths.
+
+### `publish-infra`
+
+Depends on all four predecessor jobs (unchanged gate). Downloads `infra-candidate`
+and `firecracker-inputs` that were uploaded by `integration-firecracker` on
+main — the same byte sequence that passed the integration tests.
+
+### Eliminated jobs
+
+- `stage-firecracker-inputs`: existed only to copy the dropbear to ubuntu-latest
+  for `build-infra`. No longer needed.
+- `build-infra`: the infra candidate is now built on the KVM runner in
+  `integration-firecracker`.
+
+### Script changes
+
+`scripts/coverage.sh` gains an `aggregate` mode (`coverage.sh aggregate [critical]`)
+that combines pre-existing `.coverage.*` files instead of re-running tests.
+The existing run mode (`coverage.sh [critical]`) is preserved for local dev.

docs/prds/prd-new-claude-forward-host-credentials.md

@@ -0,0 +1,146 @@
+# PRD prd-new: Claude forward_host_credentials
+
+- **Status:** Draft
+- **Author:** claude
+- **Created:** 2026-07-01
+- **Issue:** #325
+
+## Summary
+
+Add `agent_provider.forward_host_credentials: true` support for the
+`claude` template, mirroring the existing Codex flow. When enabled,
+bot-bottle reads the host's Claude OAuth session key from
+`~/.claude/.credentials.json` at launch, forwards it only to the egress sidecar,
+and injects a placeholder `CLAUDE_CODE_OAUTH_TOKEN` into the agent so
+Claude Code starts without ever seeing the real credential.
+
+## Problem
+
+Running a Claude agent in a container today requires the operator to
+manually extract a long-lived OAuth token (`claude setup-token`), export
+it as `BOT_BOTTLE_CLAUDE_OAUTH_TOKEN`, and reference it explicitly in
+the manifest with `agent_provider.auth_token:
+"BOT_BOTTLE_CLAUDE_OAUTH_TOKEN"`. This is a two-step manual ceremony
+that is easy to skip or do incorrectly.
+
+The host already stores a valid Claude session in `~/.claude/.credentials.json`
+after `claude login`. Codex already automates an
+equivalent extraction from `~/.codex/auth.json`. There is no reason
+Claude bottles cannot do the same.
+
+## Goals / Success Criteria
+
+- A Claude bottle with `forward_host_credentials: true` in the manifest
+  uses the host's `~/.claude/.credentials.json` session key at launch with no
+  additional operator steps.
+- The agent container receives only `CLAUDE_CODE_OAUTH_TOKEN=egress-placeholder`
+  — never the real token.
+- The real session key lives only in the egress sidecar's environment.
+- Missing, malformed, or expired host Claude auth fails launch with a
+  clear operator-facing message.
+- Existing `auth_token` behavior is unchanged.
+- `forward_host_credentials: true` is rejected in the manifest when both
+  `auth_token` and `forward_host_credentials` are set, since they serve
+  the same purpose.
+
+## Non-goals
+
+- Refreshing Claude OAuth tokens in the sidecar.
+- Writing a dummy `~/.claude.json` auth state to the agent (unlike the
+  Codex flow, Claude Code reads its credential from `CLAUDE_CODE_OAUTH_TOKEN`
+  in env, not from an auth file — no guest-side auth marker is needed).
+- Supporting `forward_host_credentials` for providers other than `codex`
+  and `claude`.
+
+## Design
+
+### Manifest schema
+
+```yaml
+agent_provider:
+  template: claude
+  forward_host_credentials: true
+```
+
+Rejects in manifest validation when:
+- Template is not `codex` or `claude`.
+- Both `auth_token` and `forward_host_credentials` are set.
+
+### Host auth extraction (`contrib/claude/claude_auth.py`)
+
+Claude Code credential storage varies by platform:
+
+- **Linux**: `~/.claude/.credentials.json`
+- **macOS**: macOS Keychain, service `"Claude Code-credentials"`
+  (the file path is tried first; Keychain is the fallback when the file
+  is absent)
+
+`~/.claude.json` contains only UI state and profile metadata — no token.
+
+The credentials JSON schema (same whether from file or Keychain):
+
+```json
+{
+  "claudeAiOauth": {
+    "accessToken": "<access-token>",
+    "refreshToken": "<refresh-token>",
+    "expiresAt": 1748276587173,
+    "scopes": ["user:inference", "user:profile"]
+  }
+}
+```
+
+`expiresAt` is in **milliseconds** (not seconds).
+
+At prepare/launch time, when `forward_host_credentials: true`:
+
+1. Try `~/.claude/.credentials.json`; on macOS, if absent, run
+   `security find-generic-password -s "Claude Code-credentials" -w`
+   and parse its stdout as JSON.
+2. Require a `claudeAiOauth` dict.
+3. Require a non-empty `claudeAiOauth.accessToken` string.
+4. If `claudeAiOauth.expiresAt` is present, divide by 1000 and require
+   the result to be in the future.
+5. Return only the access token to the launch path.
+
+Errors name the missing or invalid condition and point the operator at
+`claude login`, without printing token values.
+
+### Egress route
+
+When `forward_host_credentials: true`:
+
+- Provision the session key in `provisioned_env` under
+  `BOT_BOTTLE_CLAUDE_HOST_ACCESS_TOKEN` (new constant in `egress.py`).
+- Set up the `api.anthropic.com` egress route with `auth_scheme: Bearer`
+  and `token_ref: BOT_BOTTLE_CLAUDE_HOST_ACCESS_TOKEN`.
+- Set `CLAUDE_CODE_OAUTH_TOKEN=egress-placeholder` in the agent env and
+  add it to `hidden_env_names`.
+
+No dummy auth file and no `verify` step are needed — Claude Code reads
+the credential from the env var, not from a file.
+
+### Constants
+
+- `CLAUDE_HOST_CREDENTIAL_TOKEN_REF = "BOT_BOTTLE_CLAUDE_HOST_ACCESS_TOKEN"`
+  in `egress.py` (alongside the existing `CODEX_HOST_CREDENTIAL_TOKEN_REF`).
+- `CLAUDE_HOST_CREDENTIAL_HOSTS = ("api.anthropic.com",)` in
+  `agent_provider.py` (alongside the existing `CODEX_HOST_CREDENTIAL_HOSTS`).
+
+### Data flow
+
+```
+Host ~/.claude/.credentials.json  →  bot-bottle launch
+                            │
+                            ├──► egress sidecar env (real token only)
+                            │
+                            └──► agent env: CLAUDE_CODE_OAUTH_TOKEN=egress-placeholder
+
+Agent  →  HTTPS to api.anthropic.com (via egress)
+Egress →  injects Authorization: Bearer <real token>
+Egress →  forwards to api.anthropic.com
+```
+
+## Open questions
+
+None — the Codex precedent makes the design clear.

docs/prds/prd-new-consolidate-docker-infra-backend.md

@@ -0,0 +1,156 @@
+# PRD prd-new: Consolidate infra backend for Docker
+
+- **Status:** Active
+- **Author:** Claude
+- **Created:** 2026-07-20
+- **Issue:** #431
+
+## Summary
+
+The Docker backend runs two containers — `bot-bottle-orch-gateway` (gateway
+data plane) and `bot-bottle-orchestrator` (control plane) — where the
+macOS and Firecracker backends already run a single combined infra
+unit. This PRD collapses Docker to the same model: one `bot-bottle-infra`
+container running both processes under the `gateway_init` supervise tree, a
+restructured `Dockerfile.infra` as the shared gateway+orchestrator base,
+and a handful of extracted shared utilities (CA cert polling, teardown
+sequence, launch skeleton) that are currently duplicated across all three
+`consolidated_launch.py` files.
+
+## Goals / success criteria
+
+- Docker backend starts exactly one infra container instead of two.
+- `Dockerfile.infra` is the shared base image (gateway + orchestrator, no
+  buildah); the Firecracker image layers buildah on top of it.
+- The orchestrator process runs under the `gateway_init` supervise tree
+  inside the combined container (one PID-1, one restart/health surface).
+- CA cert polling, the teardown sequence, and the shared launch skeleton
+  (ensure-infra → register → provision → return context) live in a single
+  shared module; all three backends import from it.
+- No functional change to macOS or Firecracker launch paths.
+
+## Non-goals
+
+- Changing per-bottle isolation — agents stay one-VM/container-each.
+- Consolidating transport implementations (`DockerGatewayTransport`,
+  `AppleGatewayTransport`, `SshGatewayTransport`) — these are already the
+  right abstraction boundary.
+- macOS DHCP-inversion of registration order — irreducible backend
+  difference, stays as-is.
+- Any changes to the orchestrator RPC protocol or the attribution model.
+
+## Design
+
+### Dockerfile restructuring
+
+**Current shape:**
+
+- `Dockerfile.gateway` — data plane (mitmproxy, gitleaks, git, openssh,
+  supervise daemons)
+- `Dockerfile.orchestrator` — control plane (python:3.12-slim + bot_bottle
+  package; stdlib-only, no third-party deps)
+- `Dockerfile.infra` — Firecracker only: `FROM bot-bottle-gateway` +
+  buildah + `COPY --from bot-bottle-orchestrator`
+
+**New shape:**
+
+- `Dockerfile.gateway` — unchanged
+- `Dockerfile.orchestrator` — unchanged (single definition of orchestrator
+  content; both Docker infra and Firecracker infra `COPY --from` it)
+- `Dockerfile.infra` — **shared base**: `FROM bot-bottle-gateway` + `COPY
+  --from bot-bottle-orchestrator` (no buildah — Docker infra image)
+- `Dockerfile.infra.fc` — Firecracker only: `FROM bot-bottle-infra` +
+  buildah/crun/netavark/aardvark-dns (layered on the shared base, same net
+  result as today)
+
+The comment in `Dockerfile.infra` that says "the docker backend keeps
+orchestrator + gateway as separate images; this combined image exists only
+for the Firecracker single-VM cut" is removed.
+
+### Orchestrator in the supervise tree
+
+`gateway_init` already supervises the data-plane daemons (egress, git-http,
+supervise-MCP). The orchestrator control plane is added as another supervised
+process: `python3 -m bot_bottle.orchestrator --host 0.0.0.0 --port <port>
+--broker stub`.
+
+The orchestrator source is bind-mounted (`/app` → repo root, as today) so
+dev live-reload still works. `source_hash`-based container recreation in
+`OrchestratorService.ensure_running` continues to apply — a code change
+recreates the combined infra container, which bounces both gateway and
+orchestrator. This is acceptable: the docker backend is a dev/legacy target
+where in-flight egress connections across a code deploy are not a hard
+requirement.
+
+### `OrchestratorService` changes
+
+`OrchestratorService` currently starts two containers in sequence: gateway
+first (`DockerGateway.ensure_running`), then orchestrator. After this PRD:
+
+- Single `docker run` of `bot-bottle-infra:latest`
+- Container name: `bot-bottle-infra` (replaces `bot-bottle-orch-gateway` +
+  `bot-bottle-orchestrator`)
+- Published ports: `127.0.0.1:{host_port}:8099` for the control plane
+  (`gateway_init` listens on a fixed internal port 8099; the caller-chosen
+  host port maps to it)
+- Bind mounts: repo root + host root (same as today)
+- `DockerGateway` becomes an implementation detail of `OrchestratorService`
+  rather than a separately started container; the gateway image name
+  (`GATEWAY_IMAGE`) is no longer referenced at runtime, only at build time
+  for the `Dockerfile.infra` base
+
+The `_gateway()` / `ensure_running` two-step in `OrchestratorService` is
+replaced by a single `_run_infra_container()`.
+
+### Shared backend utilities
+
+Three items are duplicated across
+`backend/docker/consolidated_launch.py`,
+`backend/macos_container/consolidated_launch.py`, and
+`backend/firecracker/consolidated_launch.py`:
+
+1. **CA cert polling loop** — `deadline = time.monotonic() + timeout; while
+   ...: try fetch CA; sleep` — extracted to
+   `backend/consolidated_util.py:poll_ca_cert(transport, *, timeout)`.
+
+2. **Teardown sequence** — `OrchestratorClient(url).teardown_bottle(id)` +
+   `deprovision_git_gate(transport, id)` — extracted to
+   `backend/consolidated_util.py:teardown_consolidated(url, transport,
+   bottle_id)`.
+
+3. **Launch skeleton** — all three follow: ensure-infra → allocate/register
+   → provision git-gate → fetch CA cert → return launch context. The macOS
+   inversion (agent starts before registration, source IP from DHCP) is the
+   only deviation. Extract a shared `_provision_bottle(transport, bottle_id,
+   plan, orchestrator_url)` helper covering the register → provision →
+   return-token steps; the backends keep their own `launch_consolidated`
+   wrappers for the before/after (infra-ensure + agent-start + IP
+   allocation), calling the shared helper.
+
+The new `backend/consolidated_util.py` module holds only backend-neutral,
+transport-agnostic logic. All three backends import from it.
+
+## Implementation chunks
+
+1. **(this PR)** Dockerfile restructuring: rename current `Dockerfile.infra`
+   content to `Dockerfile.infra.fc`; write new `Dockerfile.infra` as
+   gateway+orchestrator base. Update Firecracker image-build references from
+   `Dockerfile.infra` → `Dockerfile.infra.fc`.
+
+2. Add orchestrator process to `gateway_init` supervise tree.
+
+3. Collapse `OrchestratorService` to a single-container start; rename
+   container from `bot-bottle-orch-gateway`/`bot-bottle-orchestrator` →
+   `bot-bottle-infra`; update image name constant.
+
+4. Extract `backend/consolidated_util.py` with `poll_ca_cert`,
+   `teardown_consolidated`, and `_provision_bottle`; update all three
+   `consolidated_launch.py` files to import from it.
+
+5. Update tests that reference the old container names or two-container
+   startup sequence.
+
+## Open questions
+
+None — the supervise-tree approach and shared Dockerfile layering were
+confirmed in issue #431.

docs/prds/prd-new-modernize-built-in-agent-images.md

@@ -0,0 +1,47 @@
+# PRD prd-new: Modernize built-in agent images
+
+- **Status:** Draft
+- **Author:** Codex
+- **Created:** 2026-07-21
+- **Issue:** #451
+
+## Summary
+
+Keep every built-in agent provider on Debian's current stable release and make
+Podman available inside each image. This gives agents a consistent, modern
+userspace and an OCI container tool without requiring per-project setup.
+
+## Problem
+
+The Claude, Codex, and Pi images inherit the generic `node:22-slim` tag. That
+tag does not state which Debian release the project supports and currently
+leaves the images on the older Bookworm release. None of the built-in images
+installs Podman, so tasks that need to inspect or build OCI images must first
+modify the bottle or cannot run at all.
+
+## Goals / success criteria
+
+- Every Dockerfile under `bot_bottle/contrib/*/Dockerfile` explicitly inherits
+  `node:22-trixie-slim`, based on Debian 13 (the current stable release).
+- Every built-in agent image installs Podman from Debian stable.
+- Every built-in agent image retains an SSH client for Git-over-SSH workflows.
+- The non-root agent user owns a traversable XDG Git configuration directory,
+  so Git can load bot-bottle's global git-gate rewrites without permission
+  errors.
+- A shared test enforces both requirements for current and future built-in
+  providers.
+
+## Non-goals
+
+- Configuring privileged or nested-container execution for bottles.
+- Pinning Podman outside Debian's stable package repository.
+- Changing the Node.js or agent CLI release policy.
+
+## Design
+
+Use the explicit `node:22-trixie-slim` base rather than the floating `slim`
+variant. Install the `podman` package with each image's existing `apt-get`
+dependency layer, so package metadata and caches are still removed in the same
+layer. Treat Debian stable as the Podman stability and update channel; this
+keeps the images stdlib/distribution-first and avoids adding a third-party
+package repository.

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

@@ -0,0 +1,125 @@
+# 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/prds/prd-new-secret-provider-encrypted-env.md

@@ -0,0 +1,128 @@
+# PRD prd-new: Encrypted at-rest egress secrets (SecretProvider, interim slice)
+
+- **Status:** Draft
+- **Author:** didericis
+- **Created:** 2026-07-21
+- **Issue:** #355
+
+## Summary
+
+An interim step toward the generic `SecretProvider` (#355) that stops short
+of per-request minting. Today the orchestrator holds each bottle's egress
+auth tokens **in process memory only**, so any infra-container recreation
+silently strips every already-running bottle of its upstream credentials.
+This PRD makes those secrets survive a gateway restart by persisting them
+**encrypted**, under a key that is not itself sitting next to the
+ciphertext.
+
+The end state in #355 — short-lived, scoped credentials minted per request
+— removes the need to store anything durable at all. That is a larger
+change gated on per-upstream minting support. This slice buys back
+restart-survivability now without regressing to plaintext secrets at rest.
+
+## Problem
+
+`Orchestrator._tokens` (`bot_bottle/orchestrator/service.py:74-79`) is a
+plain in-memory dict, deliberately never written to the registry DB:
+
+> Held **in memory only** — never written to the registry DB — so the
+> gateway can inject each bottle's upstream credential without secrets at
+> rest. Lost on restart (re-launch re-registers them); the future
+> SecretProvider (#355) replaces this with per-request minting.
+
+The registry itself *is* durable (SQLite on a container-only volume), and
+so is the gateway CA since #450 / `2cd44cf7`. The tokens are now the only
+piece of gateway state that does not survive a restart, which makes the
+failure mode both silent and confusing.
+
+### Observed failure
+
+Checking out a branch that touches `bot_bottle/**/*.py` changes
+`source_hash()` (`bot_bottle/orchestrator/lifecycle.py:88-99`).
+`MacosInfraService._source_current()`
+(`bot_bottle/backend/macos_container/infra.py:159-169`) sees the mismatch
+and `ensure_running()` force-removes and recreates the infra container
+(`infra.py:198-208`). The registry rows survive on the DB volume; the CA
+survives on its host bind-mount; `_tokens` comes back empty.
+
+Every already-running bottle then fails closed, mid-session, on its next
+outbound request:
+
+- `/resolve` succeeds — the bottle is still `active` in
+  `orchestrator_bottles` and its policy blob is served intact, including
+  `- host: "api.anthropic.com"` with `auth_scheme: Bearer` /
+  `token_env: EGRESS_TOKEN_0`.
+- `tokens_for()` returns `{}`, so the resolved env overlay has no
+  `EGRESS_TOKEN_0`.
+- `decide()` (`bot_bottle/egress_addon_core.py:644-652`) blocks with
+  `egress: route for 'api.anthropic.com' declared auth but env var
+  'EGRESS_TOKEN_0' is unset` — an 89-byte `403` on every request.
+
+Confirmed live on the macOS backend on 2026-07-21: two bottles running
+since 20:29/20:30 were still registered `active` with valid policy after
+the 23:05 infra recreation, and both took 89-byte `403`s from then on,
+while a bottle launched *after* the recreation egressed normally. The
+recovery today is to relaunch every affected bottle.
+
+Note this is a re-attachment blocker distinct from #443/#445 and from #450
+— the CA and the gateway address were both fine. It is specifically the
+credential wipe.
+
+## Goals / Success criteria
+
+1. A bottle's egress auth tokens survive infra-container recreation: an
+   already-running bottle keeps egressing across a gateway restart with no
+   relaunch and no operator action.
+2. Secrets are **never** at rest in plaintext, and never at rest next to a
+   key that trivially decrypts them.
+3. Compromise of the registry DB file alone does not yield usable
+   upstream credentials.
+4. The stored form is revocable and rotatable without relaunching bottles
+   that are not affected.
+5. Reap/teardown destroys a bottle's stored secrets along with its
+   registry row (no ciphertext outliving its bottle).
+6. Migration is transparent: existing bottles keep working, no manifest
+   changes required.
+
+## Non-goals
+
+- **Per-request minting** of short-lived scoped credentials. That is the
+  #355 end state; this PRD is explicitly the interim slice and should not
+  foreclose it.
+- Generalizing `DeployKeyProvisioner` into the full `SecretProvider` ABC,
+  or the manifest-level `{ provider: <name> }` reference surface.
+- User-extensible provider discovery (`~/.bot-bottle/contrib/<name>/`).
+- Changing the `/resolve` contract's shape (it already carries `tokens`).
+- Fixing the *trigger* — `source_hash` churn on branch switch. Recreating
+  infra is legitimate; it just must not cost running bottles their
+  credentials. A separate guard that refuses recreation while bottles are
+  active is complementary and out of scope here.
+
+## Design
+
+> **TODO (didericis):** the encryption flow goes here — key custody, where
+> the key material lives relative to the ciphertext, the wrap/unwrap path
+> at register and at `/resolve`, and what an attacker who holds only the
+> DB (or only the host, or only the infra container) can recover.
+
+Constraints the design has to satisfy, for reference while drafting:
+
+- The gateway's `PolicyResolver` needs the cleartext at request time, on
+  the data-plane path, so unwrap has to be cheap enough to sit in a
+  per-flow `/resolve` (or be cached in memory after first unwrap).
+- The infra container is recreated routinely and unattended. Anything
+  requiring an interactive unlock on every recreation defeats the goal.
+- The DB lives on a container-only volume that the host does not mount, so
+  host-side and guest-side components see different filesystems — that
+  asymmetry is available as a place to split custody.
+- The agent must never be able to reach the key material. It is a separate
+  container with no control-plane token, which is the existing boundary.
+
+## Open questions
+
+- Where does the unwrap key live, and what recreates/re-derives it when the
+  infra container is rebuilt?
+- Is the cleartext cached in memory after first unwrap, or unwrapped per
+  request? (Latency vs. exposure window.)
+- What is the rotation story — re-wrap in place, or force re-registration?
+- Does this land behind a flag, or replace `_tokens` outright?

docs/research/agent-sandbox-landscape.md

@@ -1,32 +1,81 @@
 # Landscape: AI-agent sandbox tools
 
-A broader survey than [`landscape-containerized-claude.md`](landscape-containerized-claude.md),
-which focused on Claude-Code-specific containerizers. This one covers
-general AI-agent sandbox / containment projects — some Claude-specific,
-some agent-agnostic, some hosted SaaS — and contrasts them with
-bot-bottle's design.
+Survey of AI-agent sandbox and containment projects — including local
+coding-agent wrappers, agent-agnostic runtimes, hosted platforms, and
+governance layers — contrasted with bot-bottle's design. The original
+Claude-Code-specific containerizer survey was folded into this note on
+2026-07-20 so there is one landscape and one positioning verdict.
 
-Research conducted 2026-05-11.
+Research conducted 2026-05-11. CubeSandbox added 2026-07-18 (see its
+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
 
-Eight projects surveyed. None duplicate bot-bottle's combination of
-local Docker, declarative JSON manifest, per-agent egress allowlist via
-pipelock, and bottle/agent split. Two clusters stand out:
+The main table compares bot-bottle against fifteen isolation/sandbox tools.
+Governance/pre-action authorization and credential-only layers are covered
+separately because they don't provide VM or container isolation. None
+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** — tilde.run (hosted SaaS), boxlite and
-  microsandbox (microVM libraries for platform builders), endo-familiar
+- **Different category (isolation)** — tilde.run (hosted SaaS), boxlite
+  and microsandbox (microVM libraries for platform builders), E2B and Daytona
+  (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) is
-the most relevant for the v2 isolation discussion in
+The microVM cluster (matchlock, smolmachines, boxlite, microsandbox,
+CubeSandbox) is 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 a `"runtime": "microvm"` option on a bottle is now
-plausible without a heavy stack.
+ergonomic enough that microVMs are **now bot-bottle's default backend**
+(Firecracker on KVM Linux, Apple Container on macOS), with Docker kept
+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
 
@@ -63,7 +112,8 @@ plausible without a heavy stack.
 
 ### agent-safehouse
 - **Source**: https://agent-safehouse.dev/ ; https://github.com/eugene1g/agent-safehouse
-- **License**: Apache 2.0 (~1,400 stars)
+- **HN launch**: [#47301085](https://news.ycombinator.com/item?id=47301085) (March 12 2026) — 823 points
+- **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.
@@ -73,6 +123,16 @@ plausible without a heavy stack.
 - **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
@@ -155,73 +215,474 @@ plausible without a heavy stack.
   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
 
-| Axis | bot-bottle | endo-familiar | litterbox | agent-safehouse | matchlock | tilde.run | boxlite | microsandbox | smolmachines |
-|---|---|---|---|---|---|---|---|---|---|
-| 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 |
-| 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 |
-| Agent target | Claude Code | Generic (demo) | Generic | Multi-agent wrapper | Generic (+ Claude/OpenAI SDKs) | Claude focus | Generic | Claude + Cursor (MCP/Skills) | Generic (AGENTS.md) |
-| 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 |
-| Parallel agents | Yes (one bottle per agent) | n/a | Not addressed | One at a time | Multiple VMs | Yes (dashboard) | SDK-level | SDK-level | Architectural |
-| Config | JSON manifest (bottles + agents) | Programmatic refs | CLI wizard | Profile files / shell fns | CLI / SDK | DSL + CLI + SDK | SDK | CLI / SDK / MCP | TOML Smolfile |
-| Maturity | Active May 2026 | Research (2022+) | Early (~66 ⭐) | Active (~1.4k ⭐) | Experimental (~574 ⭐) | Private preview | YC, ~4.7k ⭐ | YC, ~6k ⭐, beta | ~3.1k ⭐ |
+*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 | E2B | Daytona | CubeSandbox | Cleanroom | container-use | Docker sbx | Anthropic srt |
+|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
+| 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 |
+| 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 |
+| 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) |
+| 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) |
+| 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 |
+| 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 |
+| 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 uses Docker + pipelock egress (plus gVisor where
-available); agent-safehouse uses `sandbox-exec`; litterbox uses Podman +
-Landlock. matchlock and smolmachines are spiritually close on the
-*policy* side (default-deny net, per-host allowlist) but use microVMs
-instead of containers.
+bot-bottle now defaults to a VM per bottle (Firecracker microVM on KVM
+Linux, Apple Container on macOS) with its own DLP-scanning egress proxy,
+keeping Docker only as a legacy fallback; agent-safehouse uses
+`sandbox-exec`; litterbox uses Podman + Landlock. matchlock and
+smolmachines are close on *both* the policy side (default-deny net,
+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. boxlite and
-microsandbox are infrastructure libraries aimed at platform builders
-embedding sandboxes into agent frameworks; they would be a *backend*
-bot-bottle could call, not a competitor to its manifest layer.
-endo-familiar is in a different paradigm entirely: capability passing
-rather than kernel boundaries.
+opposite to bot-bottle's "infrastructure I control" goal. E2B and Daytona
+are hosted sandbox platforms, while boxlite, microsandbox, and CubeSandbox
+are infrastructure libraries/services aimed at platform builders embedding
+sandboxes into agent frameworks; they
+would be a *backend* bot-bottle could call, not a competitor to its
+manifest layer. endo-familiar is in a different paradigm entirely:
+capability passing rather than kernel boundaries.
 
 ## Borrowable ideas
 
-What bot-bottle already has that the survey suggested as
-differentiators:
-- Default-deny egress with a per-agent allowlist (pipelock).
+### Already shipped or otherwise addressed
+
+- Default-deny egress with a per-agent allowlist (own egress scanner).
 - 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.
 
-Ideas worth considering, without abandoning the Python-stdlib-first / local-Docker
-stance:
+### Still worth considering
 
-1. **Per-use SSH key confirmation** (from litterbox). Even with
-   KnownHostKey pinning and pipelock egress, a wrapper SSH agent that
-   prompts on each key use (e.g. via `osascript` / `notify-send`) would
-   catch an agent doing something off-policy with a key it legitimately
-   holds. Pure-stdlib, no new deps.
-2. **In-flight secret injection** (from matchlock). Pipelock already
-   does egress allowlisting and DLP; teaching it to *inject* tokens at
-   proxy time so e.g. `GITEA_TOKEN` never appears in the container's
-   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.
+- **Live network activity in the supervisor TUI** (from Docker sbx): show
+  allowed and blocked connections and let the operator propose policy changes
+  from the existing supervision surface.
+- **Tamper-evident audit records** (from OAP): sign and hash-chain egress and
+  supervision decisions for compliance-sensitive deployments.
+- **Behaviour-informed policy downgrade** (from Microsoft AGT): use repeated
+  DLP alerts or supervision holds as a signal to narrow policy or request
+  closer review. This needs a carefully specified trust model before it can be
+  more than a heuristic.
 
 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.
@@ -230,3 +691,180 @@ hosted-SaaS dashboard model of tilde.run (cuts against the
 - 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/firecracker-image-remote-store.md

@@ -0,0 +1,178 @@
+# Firecracker Image Remote Store
+
+**Date:** 2026-07-22  
+**Context:** PR #459 (run-dir leak fix) surfaced that committed Firecracker snapshots
+currently live only on the host machine. Once a host is wiped or a run-dir is
+evicted, a user's preserved bottle is gone. This note investigates a secure remote
+store so committed images survive host turnover and can be restored without the
+user having to pre-flag which sessions to keep.
+
+## Verdict
+
+Backblaze B2 + Cloudflare CDN is the cost-optimal choice for most deployments.
+Cloudflare R2 is the simpler zero-config option at slightly higher storage cost.
+Self-hosted MinIO is the right call for air-gapped or on-premises installs.
+
+On the image-size front, zstd-compressing the committed tar before upload
+produces roughly a 60–70% reduction with negligible impact on restore latency.
+OverlayFS (for in-flight working rootfs, not for the committed artifact) cuts
+per-instance disk use to ~10–50 MB per extra bottle sharing the same base.
+
+---
+
+## What Gets Stored
+
+The Firecracker backend produces two artifact types:
+
+| Artifact | Created by | Size | Lifetime |
+|----------|-----------|------|---------|
+| `rootfs/agent-<digest>/` (dir) | `image_builder.py` → `mke2fs -d` | ~1 GB as ext4 | Cached per Dockerfile hash; evictable |
+| `committed/<slug>/rootfs.tar` | `FirecrackerFreezer._freeze` via SSH tar | 500 MB–1 GB | User-preserved; must survive host wipe |
+
+The committed artifact is a tar of the guest's live filesystem streamed out over
+SSH (`freezer.py:58–90`). At resume time `launch.py` calls `mke2fs -d` to
+rebuild a fresh ext4 from this tar. The tar — not the ext4 — is what needs to be
+pushed to remote storage and pulled back at restore time.
+
+The base image cache (`rootfs/agent-<digest>/`) is derivable from the Dockerfile
+and can be rebuilt on demand; it is lower priority for remote storage.
+
+---
+
+## Storage Candidates
+
+### Object storage
+
+| Provider | Storage | Egress | Notes |
+|----------|---------|--------|-------|
+| **Backblaze B2** | $0.006/GB | Free (via Cloudflare Bandwidth Alliance) | Cheapest storage; pairs with Cloudflare CDN to eliminate egress |
+| **Cloudflare R2** | $0.015/GB | $0 always | Zero-config egress; no lifecycle transitions (limitation) |
+| **Wasabi** | $0.0069/GB | Free (1:1 ratio) | 90-day minimum retention; good for archival; lifecycle evaluated daily |
+| **AWS S3** | $0.023/GB | $0.09/GB | Richest lifecycle support; expensive at scale; avoid unless already in AWS |
+| **MinIO** (self-hosted) | Host cost only | None | S3-compatible; best for private/on-prem deployments |
+
+**B2 + Cloudflare CDN** is effectively $0.006/GB with zero egress — about 18×
+cheaper than S3 for restore-heavy workloads. **R2** is the zero-config choice
+($0 egress by default, no Bandwidth Alliance pairing needed) at a slightly
+higher storage rate.
+
+**Cloudflare R2's missing lifecycle support** is the main caveat: auto-eviction
+rules (evict images older than N days) cannot currently be expressed natively in
+R2. Wasabi and S3 both support declarative lifecycle policies.
+
+### Retention policy recommendation
+
+The comment proposes:
+- Retain images for ~1 week by default
+- Warn when approaching a capacity threshold
+- Auto-evict oldest images once threshold is exceeded
+
+This maps cleanly to an application-level policy (not a provider lifecycle rule),
+which avoids the R2 limitation and works consistently across providers:
+
+1. On `commit`: upload tar, record `(slug, size_bytes, uploaded_at)` in a local
+   or remote manifest file.
+2. On startup / on `list`: scan the manifest, warn if total stored size exceeds
+   e.g. 80% of the configured threshold.
+3. On eviction run (CLI or cron): delete objects older than `retention_days`
+   (default 7) that push total over `max_capacity`; oldest-first.
+
+This keeps the policy logic in bot-bottle and the storage provider as a dumb
+object store — no vendor-specific lifecycle API required.
+
+---
+
+## Image Size Reduction
+
+### Current artifact sizes
+
+A typical committed tar for a Claude Code agent image is 500 MB–1 GB uncompressed.
+The per-run ext4 (copy of the base, written at `start`) adds another ~1 GB of
+local disk. The leak fix in this PR addresses the ext4 copies; the remote store
+addresses the committed tars.
+
+### Compression
+
+zstd compression of the committed tar before upload is the highest-leverage
+single change:
+
+| Codec | Typical size (1 GB rootfs) | Compress speed | Decompress speed |
+|-------|---------------------------|---------------|-----------------|
+| gzip | 350–430 MB | ~100 MB/s | ~500 MB/s |
+| **zstd (default)** | **330–360 MB** | **~400 MB/s** | **~2 GB/s** |
+| xz | 290–320 MB | ~20 MB/s | ~200 MB/s |
+
+**zstd is the best trade-off**: 65–67% size reduction, near-instantaneous
+decompression. The `tar` call in `freezer.py` could pipe through `zstd` before
+writing to disk and to the remote; `resume` decompresses on the way back. A
+`.tar.zst` suffix marks compressed artifacts so old tars remain restorable
+without the codec.
+
+### SquashFS for the base image cache
+
+The `rootfs/agent-<digest>/` directory (the buildah-exported tree) is rebuilt by
+`image_builder.py` and turned into per-run ext4 by `mke2fs -d`. Storing the
+base as a SquashFS image instead of a flat directory tree would reduce it from
+~1 GB to ~330–360 MB and make the cache remote-friendly. Firecracker does not
+directly boot SquashFS, but the existing `mke2fs -d` path reads a directory tree
+— a SquashFS mount could serve as the source. This is a larger change and lower
+priority than tar compression.
+
+### OverlayFS for per-run rootfs
+
+Multiple simultaneous bottles sharing the same agent image today each get a full
+`mke2fs -d` copy (~1 GB). OverlayFS (read-only base + writable sparse overlay)
+would reduce this to ~10–50 MB per instance beyond the first:
+
+- Mount the base image directory as read-only lower layer
+- Attach a sparse ext4 or tmpfs writable layer per bottle
+- Pass the merged overlay to Firecracker as the block device
+
+E2B's public write-up on Firecracker + OverlayFS confirms this approach works
+at scale. The `launch.py` changes would be non-trivial (device mapper or
+`fuse-overlayfs` plumbing), so this is a follow-up rather than a prerequisite
+for the remote store.
+
+---
+
+## Recommended Approach
+
+**Phase 1 — remote store with zstd (tight scope, actionable now)**
+
+1. Add `--zstd` to the `tar` call in `FirecrackerFreezer._freeze`; name the
+   artifact `rootfs.tar.zst`. Keep uncompressed restore path for legacy tars.
+2. Add a `bb firecracker upload <slug>` / `bb firecracker pull <slug>` pair that
+   pushes/fetches the compressed tar to the configured object store (S3-compatible
+   API, so B2, R2, MinIO, and Wasabi all work with the same client).
+3. Store a `manifest.json` in the bucket (or a local mirror) tracking slug →
+   `{size, uploaded_at}`. Use it for threshold warnings and eviction.
+4. Default retention: 7 days, configurable via `firecracker.image_retention_days`
+   in `~/.config/bot-bottle/config.toml` (or equivalent).
+5. Warn at 80% of `max_capacity` (default e.g. 50 GB); evict oldest on commit
+   once at 100%.
+
+**Storage recommendation:** Cloudflare R2 for hosted deployments (zero egress,
+zero config), MinIO for private/on-premises.
+
+**Phase 2 — base image cache compression**
+
+Compress the `agent-<digest>` cache dir as a `.tar.zst` to save ~65% on repeated
+image uploads. Low urgency since the base image is rebuildable.
+
+**Phase 3 — OverlayFS per-run disk**
+
+Replace the full per-run ext4 copy with an OverlayFS sparse layer. Largest disk
+impact (~90–95% savings per concurrent bottle) but highest implementation
+complexity. Track as a separate PRD.
+
+---
+
+## Open Questions
+
+- Does the host have a configured object-store credential path, or should the
+  remote store be an opt-in with an explicit `bb config set image-store.url ...`?
+- Should `commit` automatically upload, or should upload be an explicit step to
+  avoid surprise egress?
+- What is the acceptable cold-start latency for a restore from remote? A 330 MB
+  zstd tar at 100 Mbit/s takes ~26 s; at 1 Gbit/s, ~2.6 s. This bounds the
+  retention strategy (evict from local after successful upload vs keep local copy).