flint-slating 0.1.0__tar.gz

flint_slating-0.1.0/.github/workflows/license-check.yml

@@ -0,0 +1,35 @@
+name: License check
+
+on:
+  pull_request:
+    branches: [main, develop]
+  push:
+    branches: [main, develop]
+
+permissions:
+  contents: read
+
+jobs:
+  licenses:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Install uv
+        uses: astral-sh/setup-uv@v3
+
+      - name: Sync deps (including dev for pip-licenses)
+        run: uv sync
+
+      # We use a fail-on deny-list rather than an allow-list because PyPI
+      # license metadata is wildly inconsistent (MIT-CMU, "Apache 2.0
+      # License", multi-license SPDX expressions, etc.). The real concern
+      # is keeping copyleft out — specifically the PyMuPDF AGPL, Marker
+      # GPL, and Unstructured's AGPL transitive (ultralytics) trapdoors
+      # we explicitly designed this stack to avoid.
+      - name: Check transitive licenses
+        run: |
+          uv run pip-licenses \
+            --from=mixed \
+            --fail-on="GPL;GPL v2;GPL v3;GNU General Public License;GNU General Public License v2 (GPLv2);GNU General Public License v3 (GPLv3);AGPL;Affero;GNU Affero General Public License v3;GNU Affero General Public License v3 (AGPLv3);LGPL;GNU Lesser General Public License;GNU Lesser General Public License v2 (LGPLv2);GNU Lesser General Public License v3 (LGPLv3);GNU Library or Lesser General Public License (LGPL);SSPL;Server Side Public License" \
+            --order=license

flint_slating-0.1.0/.github/workflows/release.yml

@@ -0,0 +1,97 @@
+name: Release
+
+on:
+  push:
+    tags: ['v*']
+
+permissions:
+  contents: read
+  packages: write       # GHCR push
+  id-token: write       # PyPI trusted publishing
+
+jobs:
+  # Pre-flight checks. Both publish jobs depend on this, so a failed gate
+  # prevents *any* artifact from shipping (no half-shipped state).
+  gate:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          fetch-depth: 0          # full history needed for the ancestor check below
+
+      - name: Install uv
+        uses: astral-sh/setup-uv@v3
+
+      - name: Verify tag matches pyproject version
+        run: |
+          TAG="${GITHUB_REF#refs/tags/v}"
+          PROJECT_VERSION=$(uv run python -c "import tomllib; print(tomllib.load(open('pyproject.toml','rb'))['project']['version'])")
+          if [ "$TAG" != "$PROJECT_VERSION" ]; then
+            echo "tag $TAG != pyproject $PROJECT_VERSION"
+            exit 1
+          fi
+
+      - name: Verify tag is reachable from origin/main
+        run: |
+          git fetch --no-tags origin main
+          if ! git merge-base --is-ancestor "$GITHUB_SHA" origin/main; then
+            echo "tagged commit $GITHUB_SHA is not on origin/main"
+            echo "release tags must come from main — back-merge through, then re-tag from main"
+            exit 1
+          fi
+
+  docker:
+    needs: gate
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Set up QEMU (arm64 emulation)
+        uses: docker/setup-qemu-action@v3
+
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v3
+
+      - name: Log in to GHCR
+        uses: docker/login-action@v3
+        with:
+          registry: ghcr.io
+          username: ${{ github.actor }}
+          password: ${{ secrets.GITHUB_TOKEN }}
+
+      - name: Extract metadata (tags + labels)
+        id: meta
+        uses: docker/metadata-action@v5
+        with:
+          images: ghcr.io/${{ github.repository }}
+          tags: |
+            type=semver,pattern={{version}}
+            type=semver,pattern={{major}}.{{minor}}
+            type=raw,value=latest
+
+      - name: Build and push (linux/amd64 + linux/arm64)
+        uses: docker/build-push-action@v5
+        with:
+          context: .
+          platforms: linux/amd64,linux/arm64
+          push: true
+          tags: ${{ steps.meta.outputs.tags }}
+          labels: ${{ steps.meta.outputs.labels }}
+          cache-from: type=gha
+          cache-to: type=gha,mode=max
+
+  pypi:
+    needs: gate
+    runs-on: ubuntu-latest
+    environment: pypi   # matches the trusted-publisher config on PyPI
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Install uv
+        uses: astral-sh/setup-uv@v3
+
+      - name: Build wheel + sdist
+        run: uv build
+
+      - name: Publish to PyPI
+        uses: pypa/gh-action-pypi-publish@release/v1

flint_slating-0.1.0/.github/workflows/test.yml

@@ -0,0 +1,28 @@
+name: Test
+
+on:
+  pull_request:
+    branches: [main, develop]
+  push:
+    branches: [main, develop]
+
+permissions:
+  contents: read
+
+jobs:
+  test:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Install uv
+        uses: astral-sh/setup-uv@v3
+
+      - name: Sync deps
+        run: uv sync
+
+      - name: Lint
+        run: uv run ruff check src tests
+
+      - name: Tests (excluding network + docling marker)
+        run: uv run pytest -m "not network and not docling" -q

flint_slating-0.1.0/.gitignore

@@ -0,0 +1,14 @@
+__pycache__/
+*.pyc
+.venv/
+.pytest_cache/
+.ruff_cache/
+.ty_cache/
+*.egg-info/
+dist/
+build/
+.DS_Store
+.claude/
+output/
+cache/
+.docling-models/

flint_slating-0.1.0/Dockerfile

@@ -0,0 +1,40 @@
+FROM ghcr.io/astral-sh/uv:python3.13-bookworm-slim
+
+WORKDIR /app
+
+# CA certs for httpx URL downloads. No system PDF tools needed — the
+# whole PDF stack is pure-Python wheels (docling, pypdf, pdfplumber,
+# pypdfium2). git is dev-time only.
+RUN apt-get update \
+ && apt-get install -y --no-install-recommends ca-certificates \
+ && rm -rf /var/lib/apt/lists/*
+
+# Resolve deps first so they cache across source changes.
+COPY pyproject.toml uv.lock ./
+RUN --mount=type=cache,target=/root/.cache/uv \
+    uv sync --no-dev --no-install-project
+
+# README.md is part of the package metadata (pyproject.toml -> readme).
+COPY README.md ./
+COPY src/ src/
+RUN --mount=type=cache,target=/root/.cache/uv \
+    uv sync --no-dev
+
+# Pre-fetch Docling's layout model so the first user-facing call is hot.
+# Failure here is not fatal — the runtime will re-download on first use.
+ENV DOCLING_ARTIFACTS_PATH=/opt/docling-models
+RUN uv run python -c "from docling.document_converter import DocumentConverter; DocumentConverter()" || true
+
+ENV PYTHONUNBUFFERED=1 \
+    OUTPUT_ROOT=/data/output \
+    CACHE_ROOT=/data/cache \
+    PORT=35833 \
+    HOST=0.0.0.0
+
+EXPOSE 35833
+VOLUME ["/data"]
+
+# Container always runs the HTTP transport — stdio across a container
+# boundary doesn't make sense. HTTP is the default; --transport http is
+# explicit so anyone reading the Dockerfile knows what mode it runs in.
+CMD ["uv", "run", "python", "-m", "flint_slating", "--transport", "http"]

flint_slating-0.1.0/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 Parkview Lab
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

flint_slating-0.1.0/PKG-INFO

@@ -0,0 +1,188 @@
+Metadata-Version: 2.4
+Name: flint-slating
+Version: 0.1.0
+Summary: MCP server that reads PDFs (metadata, TOC, Markdown, text, images, tables) for downstream LLM consumers.
+Author: Parkview Lab
+License-Expression: MIT
+License-File: LICENSE
+Requires-Python: >=3.13
+Requires-Dist: anyio
+Requires-Dist: docling>=2.0
+Requires-Dist: fastapi
+Requires-Dist: httpx
+Requires-Dist: mcp[cli]>=1.27.0
+Requires-Dist: pdfplumber>=0.11
+Requires-Dist: pydantic
+Requires-Dist: pypdf>=5.0
+Requires-Dist: starlette
+Requires-Dist: uvicorn[standard]
+Description-Content-Type: text/markdown
+
+# flint-slating
+
+MCP server that reads PDFs and exposes them to LLM consumers as
+structured Markdown, plus the usual ancillaries: metadata, outline,
+images, tables.
+
+Designed to pair with a separate "wiki" MCP server that handles the
+*writing* side — an agent calls `flint-slating` to read PDFs and another
+MCP to persist notes about them into a frontmattered-markdown knowledge
+base.
+
+## What it does
+
+Built on a permissive-license PDF stack:
+
+| Library | License | Role |
+|---|---|---|
+| [Docling](https://github.com/docling-project/docling) | MIT | PDF → Markdown with heading hierarchy, multi-column reading order, and Markdown tables |
+| [pypdf](https://github.com/py-pdf/pypdf) | BSD-3 | metadata, TOC, page count, encryption checks, image enumeration |
+| [pdfplumber](https://github.com/jsvine/pdfplumber) | MIT | per-page table extraction |
+
+**There is no PyMuPDF, no MuPDF, no AGPL or GPL anywhere in the
+dependency tree.** A CI license-check job rejects PRs that pull in
+copyleft transitive deps.
+
+## Transports
+
+Two transports off the same MCP server, selected via `--transport`:
+
+| Transport | Run via | Use case |
+|---|---|---|
+| **Streamable-HTTP** (default) | `uvx flint-slating` or `--transport http` | Long-lived local daemon, container, or shared service. |
+| **stdio** | `uvx flint-slating --transport stdio` | The standard MCP integration shape — drop into `claude_desktop_config.json` or any `mcp.json`. |
+
+## Run
+
+### As an HTTP daemon (default)
+
+```bash
+uvx flint-slating                    # listens on PORT (default 35833)
+curl http://127.0.0.1:35833/health
+```
+
+Or pin it:
+
+```bash
+uv tool install flint-slating
+flint-slating
+```
+
+### As a stdio MCP server
+
+```bash
+uvx flint-slating --transport stdio
+```
+
+Wire into Claude Code's MCP config:
+
+```json
+{
+  "mcpServers": {
+    "flint-slating": {
+      "command": "uvx",
+      "args": ["flint-slating", "--transport", "stdio"]
+    }
+  }
+}
+```
+
+### Docker
+
+```bash
+docker run --rm \
+  -p 35833:35833 \
+  -v $(pwd)/pdfs:/pdfs:ro \
+  -v flint-slating-data:/data \
+  ghcr.io/parkviewlab/flint-slating:latest
+```
+
+Or use [`docker-compose.yml`](docker-compose.yml) for a persistent stack.
+
+## MCP tools
+
+All PDF tools take a `source` argument with one of:
+
+- `{"path": "/abs/path/to/file.pdf"}` — local file
+- `{"url": "https://..."}` — streamed to a content-addressed cache
+- `{"bytes_b64": "...", "filename": "x.pdf"}` — base64 upload (size-capped)
+
+| Tool | What it does |
+|---|---|
+| `pdf_info` | `{page_count, metadata, is_encrypted, sha256}` |
+| `pdf_toc` | flat outline `[{level, title, page}]` |
+| `pdf_read_text` | plain text by page range (fast — pypdf, no ML) |
+| `pdf_read_markdown` | high-quality Markdown via Docling (hybrid sync/async — see below) |
+| `pdf_read_chunks` | per-page Markdown chunks with tables/images/toc_items (hybrid sync/async) |
+| `pdf_list_images` | enumerate images: `[{page, index, name, width, height, ext}]` |
+| `pdf_extract_image` | base64 bytes of one image |
+| `pdf_find_tables` | per-page Markdown tables via pdfplumber |
+| `get_job_status` | poll a background job |
+| `get_job_result` | fetch a finished job's artifact |
+| `cancel_job` | cancel a running job |
+
+### Hybrid sync/async
+
+`pdf_read_markdown` and `pdf_read_chunks` run inline when
+`page_count <= SYNC_PAGE_THRESHOLD` (default 20). For larger PDFs they
+queue a background job and return a `job_id` — poll `get_job_status`
+until `state=="done"`, then call `get_job_result` (or, in HTTP mode,
+fetch `output_url` directly).
+
+**stdio mode** transparently waits for the job inline — there's no HTTP
+server to download from, so the originating tool call blocks until the
+result is ready and returns it directly.
+
+## HTTP endpoints (HTTP mode only)
+
+- `GET /health` — `{ok, version, uptime_seconds}`
+- `GET /admin/version` — package and dependency versions, Docling model status
+- `GET /admin/jobs` — recent job list
+- `GET /outputs/{job_id}/result.md` — finished Markdown
+- `GET /outputs/{job_id}/result.json` — finished chunked output
+- `GET /outputs/{job_id}/log.jsonl` — append-only job log
+- `POST /sse` — MCP Streamable-HTTP transport
+
+## Configuration
+
+| Env var | Default (daemon) | Default (container) | Purpose |
+|---|---|---|---|
+| `PORT` | `35833` | `35833` | HTTP bind port |
+| `HOST` | `0.0.0.0` | `0.0.0.0` | HTTP bind address |
+| `OUTPUT_ROOT` | `./output` | `/data/output` | Per-job output dirs |
+| `CACHE_ROOT` | `./cache` | `/data/cache` | Materialized URL / base64 PDFs |
+| `OUTPUT_EXPIRY_DAYS` | `7` | `7` | Sweep finished jobs older than N days |
+| `MAX_INLINE_PDF_BYTES` | `25 MB` | `25 MB` | Cap on base64 upload size |
+| `MAX_URL_PDF_BYTES` | `200 MB` | `200 MB` | Cap on URL download size |
+| `SYNC_PAGE_THRESHOLD` | `20` | `20` | Inline-vs-job cutoff for Markdown conversion |
+| `DOCLING_ARTIFACTS_PATH` | `~/.cache/docling` | `/opt/docling-models` | Docling layout-model cache |
+| `ENABLE_OCR` | `false` | `false` | Enable Docling OCR (Tesseract required) |
+| `PUBLIC_BASE_URL` | `http://localhost:35833` | `http://localhost:35833` | Used to build `output_url` |
+
+## Resource notes
+
+- Docling downloads a ~200–500 MB layout model on first use. The
+  container image pre-fetches it at build time; the daemon warms it at
+  startup (`stdio_entry` / HTTP lifespan).
+- pypdf, pdfplumber, and the URL / base64 paths are fast and have no ML
+  overhead — use `pdf_info`, `pdf_toc`, `pdf_read_text`, and
+  `pdf_find_tables` whenever Markdown isn't strictly needed.
+
+## Releasing
+
+Tag-driven CI publishes to both PyPI (`flint-slating`) and GHCR
+(`ghcr.io/parkviewlab/flint-slating`):
+
+```bash
+# Bump version in pyproject.toml first, then:
+git tag v0.1.0
+git push origin v0.1.0
+```
+
+The release workflow refuses tags that don't match `pyproject.toml`'s
+`version`, or that aren't on `origin/main`.
+
+## License
+
+[MIT](LICENSE). flint-slating only depends on permissive-licensed
+libraries; the CI `license-check` job enforces this on every PR.

flint_slating-0.1.0/README.md

@@ -0,0 +1,168 @@
+# flint-slating
+
+MCP server that reads PDFs and exposes them to LLM consumers as
+structured Markdown, plus the usual ancillaries: metadata, outline,
+images, tables.
+
+Designed to pair with a separate "wiki" MCP server that handles the
+*writing* side — an agent calls `flint-slating` to read PDFs and another
+MCP to persist notes about them into a frontmattered-markdown knowledge
+base.
+
+## What it does
+
+Built on a permissive-license PDF stack:
+
+| Library | License | Role |
+|---|---|---|
+| [Docling](https://github.com/docling-project/docling) | MIT | PDF → Markdown with heading hierarchy, multi-column reading order, and Markdown tables |
+| [pypdf](https://github.com/py-pdf/pypdf) | BSD-3 | metadata, TOC, page count, encryption checks, image enumeration |
+| [pdfplumber](https://github.com/jsvine/pdfplumber) | MIT | per-page table extraction |
+
+**There is no PyMuPDF, no MuPDF, no AGPL or GPL anywhere in the
+dependency tree.** A CI license-check job rejects PRs that pull in
+copyleft transitive deps.
+
+## Transports
+
+Two transports off the same MCP server, selected via `--transport`:
+
+| Transport | Run via | Use case |
+|---|---|---|
+| **Streamable-HTTP** (default) | `uvx flint-slating` or `--transport http` | Long-lived local daemon, container, or shared service. |
+| **stdio** | `uvx flint-slating --transport stdio` | The standard MCP integration shape — drop into `claude_desktop_config.json` or any `mcp.json`. |
+
+## Run
+
+### As an HTTP daemon (default)
+
+```bash
+uvx flint-slating                    # listens on PORT (default 35833)
+curl http://127.0.0.1:35833/health
+```
+
+Or pin it:
+
+```bash
+uv tool install flint-slating
+flint-slating
+```
+
+### As a stdio MCP server
+
+```bash
+uvx flint-slating --transport stdio
+```
+
+Wire into Claude Code's MCP config:
+
+```json
+{
+  "mcpServers": {
+    "flint-slating": {
+      "command": "uvx",
+      "args": ["flint-slating", "--transport", "stdio"]
+    }
+  }
+}
+```
+
+### Docker
+
+```bash
+docker run --rm \
+  -p 35833:35833 \
+  -v $(pwd)/pdfs:/pdfs:ro \
+  -v flint-slating-data:/data \
+  ghcr.io/parkviewlab/flint-slating:latest
+```
+
+Or use [`docker-compose.yml`](docker-compose.yml) for a persistent stack.
+
+## MCP tools
+
+All PDF tools take a `source` argument with one of:
+
+- `{"path": "/abs/path/to/file.pdf"}` — local file
+- `{"url": "https://..."}` — streamed to a content-addressed cache
+- `{"bytes_b64": "...", "filename": "x.pdf"}` — base64 upload (size-capped)
+
+| Tool | What it does |
+|---|---|
+| `pdf_info` | `{page_count, metadata, is_encrypted, sha256}` |
+| `pdf_toc` | flat outline `[{level, title, page}]` |
+| `pdf_read_text` | plain text by page range (fast — pypdf, no ML) |
+| `pdf_read_markdown` | high-quality Markdown via Docling (hybrid sync/async — see below) |
+| `pdf_read_chunks` | per-page Markdown chunks with tables/images/toc_items (hybrid sync/async) |
+| `pdf_list_images` | enumerate images: `[{page, index, name, width, height, ext}]` |
+| `pdf_extract_image` | base64 bytes of one image |
+| `pdf_find_tables` | per-page Markdown tables via pdfplumber |
+| `get_job_status` | poll a background job |
+| `get_job_result` | fetch a finished job's artifact |
+| `cancel_job` | cancel a running job |
+
+### Hybrid sync/async
+
+`pdf_read_markdown` and `pdf_read_chunks` run inline when
+`page_count <= SYNC_PAGE_THRESHOLD` (default 20). For larger PDFs they
+queue a background job and return a `job_id` — poll `get_job_status`
+until `state=="done"`, then call `get_job_result` (or, in HTTP mode,
+fetch `output_url` directly).
+
+**stdio mode** transparently waits for the job inline — there's no HTTP
+server to download from, so the originating tool call blocks until the
+result is ready and returns it directly.
+
+## HTTP endpoints (HTTP mode only)
+
+- `GET /health` — `{ok, version, uptime_seconds}`
+- `GET /admin/version` — package and dependency versions, Docling model status
+- `GET /admin/jobs` — recent job list
+- `GET /outputs/{job_id}/result.md` — finished Markdown
+- `GET /outputs/{job_id}/result.json` — finished chunked output
+- `GET /outputs/{job_id}/log.jsonl` — append-only job log
+- `POST /sse` — MCP Streamable-HTTP transport
+
+## Configuration
+
+| Env var | Default (daemon) | Default (container) | Purpose |
+|---|---|---|---|
+| `PORT` | `35833` | `35833` | HTTP bind port |
+| `HOST` | `0.0.0.0` | `0.0.0.0` | HTTP bind address |
+| `OUTPUT_ROOT` | `./output` | `/data/output` | Per-job output dirs |
+| `CACHE_ROOT` | `./cache` | `/data/cache` | Materialized URL / base64 PDFs |
+| `OUTPUT_EXPIRY_DAYS` | `7` | `7` | Sweep finished jobs older than N days |
+| `MAX_INLINE_PDF_BYTES` | `25 MB` | `25 MB` | Cap on base64 upload size |
+| `MAX_URL_PDF_BYTES` | `200 MB` | `200 MB` | Cap on URL download size |
+| `SYNC_PAGE_THRESHOLD` | `20` | `20` | Inline-vs-job cutoff for Markdown conversion |
+| `DOCLING_ARTIFACTS_PATH` | `~/.cache/docling` | `/opt/docling-models` | Docling layout-model cache |
+| `ENABLE_OCR` | `false` | `false` | Enable Docling OCR (Tesseract required) |
+| `PUBLIC_BASE_URL` | `http://localhost:35833` | `http://localhost:35833` | Used to build `output_url` |
+
+## Resource notes
+
+- Docling downloads a ~200–500 MB layout model on first use. The
+  container image pre-fetches it at build time; the daemon warms it at
+  startup (`stdio_entry` / HTTP lifespan).
+- pypdf, pdfplumber, and the URL / base64 paths are fast and have no ML
+  overhead — use `pdf_info`, `pdf_toc`, `pdf_read_text`, and
+  `pdf_find_tables` whenever Markdown isn't strictly needed.
+
+## Releasing
+
+Tag-driven CI publishes to both PyPI (`flint-slating`) and GHCR
+(`ghcr.io/parkviewlab/flint-slating`):
+
+```bash
+# Bump version in pyproject.toml first, then:
+git tag v0.1.0
+git push origin v0.1.0
+```
+
+The release workflow refuses tags that don't match `pyproject.toml`'s
+`version`, or that aren't on `origin/main`.
+
+## License
+
+[MIT](LICENSE). flint-slating only depends on permissive-licensed
+libraries; the CI `license-check` job enforces this on every PR.

flint_slating-0.1.0/docker-compose.yml

@@ -0,0 +1,54 @@
+# flint-slating — example compose stack.
+#
+# Copy this file, edit the CHANGE-ME values, then:
+#   docker compose up -d
+#
+# To upgrade:
+#   docker compose pull && docker compose up -d
+
+services:
+  flint-slating:
+    image: ghcr.io/parkviewlab/flint-slating:latest
+    container_name: flint-slating
+    restart: unless-stopped
+
+    ports:
+      - "35833:35833"
+
+    environment:
+      OUTPUT_ROOT: /data/output
+      CACHE_ROOT: /data/cache
+
+      # Auto-purge finished job dirs older than this many days. 0 disables.
+      OUTPUT_EXPIRY_DAYS: "7"
+
+      # CHANGE-ME: the externally-reachable URL of this daemon. Used to
+      # build absolute `output_url` values returned by the job tools.
+      # Examples:
+      #   PUBLIC_BASE_URL: "http://192.168.1.50:35833"
+      #   PUBLIC_BASE_URL: "https://flint.example.com"
+      PUBLIC_BASE_URL: "http://CHANGE-ME:35833"
+
+      # Docling layout model cache — baked into the image at build time.
+      DOCLING_ARTIFACTS_PATH: /opt/docling-models
+
+      # Set to "true" to enable Docling OCR (requires tesseract; not in
+      # this image — extend the Dockerfile or use a mount).
+      ENABLE_OCR: "false"
+
+    volumes:
+      # Default: a docker-managed named volume.
+      - flint-slating-data:/data
+
+      # OR — bind-mount a host directory:
+      # - /srv/flint-slating:/data
+
+      # If your PDFs live on the host filesystem and you want to feed
+      # them in via `source.path`, mount that read-only:
+      # - /srv/pdf-corpus:/pdfs:ro
+
+    extra_hosts:
+      - "host.docker.internal:host-gateway"
+
+volumes:
+  flint-slating-data: