refactor: SandboxAgent + SDK Shell/Filesystem; agent-browser CLI; nuke FastAPI sidecar

Combined commits 2+3 of the migration plan because the FastAPI sidecar
removal in commit 2 broke ``browser_action`` (which lived in the
sidecar); they have to land together.

Sandbox tool layer (commit 2 piece):
- ``build_strix_agent`` now returns a ``SandboxAgent`` with
  ``capabilities=[Filesystem(), Shell()]``. The SDK runtime binds the
  capabilities to the live sandbox session per-run; agents get
  ``exec_command``, ``write_stdin``, ``apply_patch``, ``view_image``
  function tools auto-merged into their tool list. Plain ``Agent``
  short-circuits capability binding (``agents/sandbox/runtime.py:190``).
- Drop ``Compaction`` from the default capability set — it's
  OpenAI-Responses-API-only and useless for our litellm-routed
  Anthropic setup.
- Delete the entire custom in-container tool layer:
  - ``strix/tools/terminal/`` (5 files, 748 LoC libtmux)
  - ``strix/tools/file_edit/`` (3 files, 276 LoC)
  - ``strix/tools/python/`` (5 files, 459 LoC)
  - ``strix/runtime/tool_server.py`` (163 LoC FastAPI sidecar)
  - ``strix/tools/_sandbox_dispatch.py`` (117 LoC)
  - ``strix/tools/registry.py`` (109 LoC)
  - ``strix/tools/context.py`` (12 LoC)
- Drop the corresponding TUI renderers (``terminal_renderer.py``,
  ``file_edit_renderer.py``, ``python_renderer.py``) and update
  ``interface/tool_components/__init__.py``.

Browser → agent-browser CLI (commit 3 piece):
- Install ``agent-browser@0.26.0`` globally in the Dockerfile right
  after the existing ``npm install -g`` block. Run
  ``agent-browser install --with-deps`` (apt, root) and
  ``agent-browser install`` (Chrome download, pentester) +
  ``agent-browser doctor --offline --quick`` smoke test.
- Drop the explicit Playwright system-deps apt list (replaced by
  ``--with-deps``) and ``RUN .venv/bin/python -m playwright install
  chromium``.
- Vendor ``agent-browser/skill-data/core/SKILL.md`` →
  ``strix/skills/tooling/agent_browser.md`` (476 lines). Adapt
  frontmatter to Strix format; strip the install/Quickstart and the
  ``agent-browser skills get electron|slack|...`` specialized-skills
  block; add the "Caido proxy is wired via env vars; do not pass
  ``--proxy``" note.
- ``_resolve_skills`` now eagerly loads ``tooling/agent_browser`` for
  every agent (matches the previous unconditional ``browser_action``
  in ``_BASE_TOOLS``).
- Delete ``strix/tools/browser/`` (5 files, 1338 LoC) and the
  ``browser_renderer.py`` TUI render.

Sandbox plumbing:
- Drop ``bearer`` token, ``tool_server_host_port`` resolution + bundle
  keys, ``TOOL_SERVER_TOKEN``/``TOOL_SERVER_PORT``/
  ``STRIX_SANDBOX_EXECUTION_TIMEOUT`` from the manifest env in
  ``session_manager.create_or_reuse``. Caido proxy env vars
  (``http_proxy``, ``https_proxy``, ``ALL_PROXY``) stay; manifest
  applies them to every ``docker exec``-spawned process.
- Drop ``sandbox_token`` and ``tool_server_host_port`` params from
  ``make_agent_context`` and the ``create_agent`` graph tool.
- Drop the tool-server health-check from ``entry.py`` (only Caido's
  ``wait_for_tcp_ready`` remains).
- ``docker-entrypoint.sh``: delete the ~30 line
  ``Starting tool server...`` block (sudo + uvicorn launch + curl
  /health poll). Add ``NO_PROXY=localhost,127.0.0.1`` to
  ``/etc/profile.d/proxy.sh`` and ``/etc/environment`` so the
  agent-browser daemon's CDP traffic on localhost isn't routed
  through Caido.

pyproject.toml:
- ``[project.optional-dependencies] sandbox = []`` (every member of
  the previous list — fastapi, uvicorn, ipython, openhands-aci,
  playwright, libtmux — is gone with the sidecar).
- Drop ``numpydoc.*``, ``IPython.*``, ``openhands_aci.*``,
  ``playwright.*``, ``uvicorn.*``, ``pyte.*``, ``libtmux.*`` from
  the missing-imports module list.
- Drop the per-file ruff ignores for the deleted modules.

Net delta: −5512 LoC. ruff drops to 3 errors (was 21 baseline). mypy
falls to 69 errors over 3 files (was 84 over 8 — the drop comes from
deleting the modules with the worst untyped-import problems).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
0xallam
2026-04-25 14:33:38 -07:00
parent 5449af2456
commit 2c2ab13c8f
40 changed files with 527 additions and 5572 deletions
+11 -16
View File
@@ -39,7 +39,6 @@ RUN apt-get update && \
nodejs npm pipx \
libcap2-bin \
gdb \
tmux \
libnss3 libnspr4 libdbus-1-3 libatk1.0-0 libatk-bridge2.0-0 libcups2 libdrm2 libatspi2.0-0 \
libxcomposite1 libxdamage1 libxfixes3 libxrandr2 libgbm1 libxkbcommon0 libpango-1.0-0 libcairo2 libasound2t64 \
fonts-unifont fonts-noto-color-emoji fonts-freefont-ttf fonts-dejavu-core ttf-bitstream-vera \
@@ -95,7 +94,14 @@ RUN npm install -g retire@latest && \
npm install -g eslint@latest && \
npm install -g js-beautify@latest && \
npm install -g @ast-grep/cli@latest && \
npm install -g tree-sitter-cli@latest
npm install -g tree-sitter-cli@latest && \
npm install -g agent-browser@0.26.0
USER root
RUN agent-browser install --with-deps
USER pentester
RUN agent-browser install && agent-browser doctor --offline --quick
RUN set -eux; \
TS_PARSER_DIR="/home/pentester/.tree-sitter/parsers"; \
@@ -193,23 +199,12 @@ ENV SSL_CERT_FILE=/etc/ssl/certs/ca-certificates.crt
RUN mkdir -p /workspace && chown -R pentester:pentester /workspace /app
COPY pyproject.toml uv.lock ./
RUN echo "# Sandbox Environment" > README.md && mkdir -p strix && touch strix/__init__.py
USER pentester
RUN uv sync --frozen --no-dev --extra sandbox
RUN /app/.venv/bin/python -m playwright install chromium
RUN uv pip install -r /home/pentester/tools/jwt_tool/requirements.txt && \
RUN pipx install --include-deps -r /home/pentester/tools/jwt_tool/requirements.txt 2>/dev/null || \
python3 -m venv /app/.venv && \
/app/.venv/bin/pip install --no-cache-dir -r /home/pentester/tools/jwt_tool/requirements.txt && \
ln -s /home/pentester/tools/jwt_tool/jwt_tool.py /home/pentester/.local/bin/jwt_tool
COPY strix/__init__.py strix/
COPY strix/config/ /app/strix/config/
COPY strix/utils/ /app/strix/utils/
COPY strix/telemetry/ /app/strix/telemetry/
COPY strix/runtime/tool_server.py strix/runtime/__init__.py strix/runtime/runtime.py /app/strix/runtime/
COPY strix/tools/ /app/strix/tools/
RUN echo 'export PATH="/home/pentester/go/bin:/home/pentester/.local/bin:/home/pentester/.npm-global/bin:$PATH"' >> /home/pentester/.bashrc && \
echo 'export PATH="/home/pentester/go/bin:/home/pentester/.local/bin:/home/pentester/.npm-global/bin:$PATH"' >> /home/pentester/.profile
+2 -28
View File
@@ -57,6 +57,7 @@ export https_proxy=http://127.0.0.1:${CAIDO_PORT}
export HTTP_PROXY=http://127.0.0.1:${CAIDO_PORT}
export HTTPS_PROXY=http://127.0.0.1:${CAIDO_PORT}
export ALL_PROXY=http://127.0.0.1:${CAIDO_PORT}
export NO_PROXY=localhost,127.0.0.1
export REQUESTS_CA_BUNDLE=/etc/ssl/certs/ca-certificates.crt
export SSL_CERT_FILE=/etc/ssl/certs/ca-certificates.crt
EOF
@@ -67,6 +68,7 @@ https_proxy=http://127.0.0.1:${CAIDO_PORT}
HTTP_PROXY=http://127.0.0.1:${CAIDO_PORT}
HTTPS_PROXY=http://127.0.0.1:${CAIDO_PORT}
ALL_PROXY=http://127.0.0.1:${CAIDO_PORT}
NO_PROXY=localhost,127.0.0.1
EOF
cat << EOF | sudo tee /etc/wgetrc
@@ -88,34 +90,6 @@ sudo -u pentester certutil -N -d sql:/home/pentester/.pki/nssdb --empty-password
sudo -u pentester certutil -A -n "Testing Root CA" -t "C,," -i /app/certs/ca.crt -d sql:/home/pentester/.pki/nssdb
echo "✅ CA added to browser trust store"
echo "Starting tool server..."
cd /app
export PYTHONPATH=/app
export STRIX_SANDBOX_MODE=true
export TOOL_SERVER_TIMEOUT="${STRIX_SANDBOX_EXECUTION_TIMEOUT:-120}"
TOOL_SERVER_LOG="/tmp/tool_server.log"
sudo -E -u pentester \
/app/.venv/bin/python -m strix.runtime.tool_server \
--token="$TOOL_SERVER_TOKEN" \
--host=0.0.0.0 \
--port="$TOOL_SERVER_PORT" \
--timeout="$TOOL_SERVER_TIMEOUT" > "$TOOL_SERVER_LOG" 2>&1 &
for i in {1..10}; do
if curl -s "http://127.0.0.1:$TOOL_SERVER_PORT/health" | grep -q '"status":"healthy"'; then
echo "✅ Tool server healthy on port $TOOL_SERVER_PORT"
break
fi
if [ $i -eq 10 ]; then
echo "ERROR: Tool server failed to become healthy"
echo "=== Tool server log ==="
cat "$TOOL_SERVER_LOG" 2>/dev/null || echo "(no log)"
exit 1
fi
sleep 1
done
echo "✅ Container ready"
cd /workspace