# Python packages pre-baked into the runtime's system python (read-only
# bind-mounted into every Bash sandbox). The agent CANNOT `pip install` at
# runtime — it is rejected in all modes — so anything it might `import` must
# be listed here and re-provisioned. See docs/operations/bash-sandbox-provisioning.md.
#
# NOTE: the Bash sandbox runs with --unshare-net (no network), so network
# libraries (requests/httpx/aiohttp/yt-dlp/scrapy ...) are intentionally NOT
# listed — outbound HTTP must go through the WebFetch/DownloadFile/MCP tools.

# ── Documents / file-format readers ──────────────────────────
pypdf
pymupdf>=1.24          # fitz; PDF render/extract (musllinux wheels >=1.24)
pdfplumber             # PDF text + table extraction (pdfminer.six based)
python-docx            # .docx read/write
python-pptx            # .pptx read/write
openpyxl               # .xlsx read/write
xlsxwriter             # .xlsx write with formatting/charts
xlrd                   # legacy .xls (pre-2007 Excel) read
odfpy                  # OpenDocument .odt / .ods
striprtf               # .rtf -> plain text
beautifulsoup4         # HTML/XML parsing
lxml                   # fast XML/HTML backend
markdownify            # HTML -> Markdown
markdown               # Markdown -> HTML

# ── Data / analysis ──────────────────────────────────────────
numpy
pandas
tabulate               # render tables as markdown/plain text
python-dateutil        # flexible date parsing
matplotlib             # offline charts -> image files in output/ (HEAVY: on
                       # alpine/musl needs freetype/libpng build deps; fine on host)

# ── Images / text ────────────────────────────────────────────
Pillow                 # image processing
charset-normalizer     # robust encoding detection for messy text
PyYAML                 # YAML read/write (stdlib json covers JSON)