opencode-devbox/scripts/generate-dockerhub-md.py

#!/usr/bin/env python3
"""
Generate DOCKER_HUB.md from README.md.

Rationale
---------
README.md is the authoritative source. DOCKER_HUB.md is a subset
intended for users pulling the pre-built image from Docker Hub — so
build-from-source instructions, developer setup (git hooks, gitleaks),
and CI/contribution content are dropped.

Docker Hub enforces a 25 kB limit on the full description field.

Usage
-----
Regenerate in place:
    python3 scripts/generate-dockerhub-md.py

Fail if DOCKER_HUB.md is out of sync with what this script would emit
(run this in CI):
    python3 scripts/generate-dockerhub-md.py --check

Design
------
Sections are selected and in some cases rewritten via `SECTION_RULES`
below. This keeps the transformation explicit and easy to audit — if
a new section is added to README.md that should also appear on Docker
Hub, extend SECTION_RULES rather than inventing implicit heuristics.
"""

from __future__ import annotations

import argparse
import re
import sys
from pathlib import Path

REPO_ROOT = Path(__file__).resolve().parent.parent
README = REPO_ROOT / "README.md"
DOCKER_HUB = REPO_ROOT / "DOCKER_HUB.md"

# Max size for Docker Hub full_description (bytes, UTF-8).
MAX_SIZE_BYTES = 25_000

# Per-section transformation.
#
# Each key is a top-level section title as it appears in README.md
# (without the leading "## ").
#
# The value is one of:
#   "keep"      — include verbatim.
#   "drop"      — exclude entirely.
#   "replace"   — substitute a custom body (see REPLACEMENTS).
#   "trim"      — keep but drop selected level-3 sub-sections listed
#                 in TRIM_SUBSECTIONS[title].
#
# Unknown sections default to "drop" with a warning — forcing an
# explicit decision whenever README gains a new section.
SECTION_RULES: dict[str, str] = {
    "Why?": "drop",                             # build-motivation, not user-facing
    "Quick Start": "replace",                   # swap docker compose clone flow for docker run
    "Features": "keep",
    "Usage": "keep",
    "Configuration": "trim",                    # drop dev-build sub-sections
    "oh-my-opencode-slim (Multi-Agent Orchestration)": "keep",
    "pi (alternative/complementary harness)": "drop",   # full README only, would push past 25 kB
    "AWS Bedrock Authentication": "keep",
    "MemPalace — persistent AI memory": "keep",
    "Gitea MCP server": "keep",
    "Context7 MCP server": "drop",
    "Shell defaults": "drop",                   # detail, full README covers it
    "Secret Scanning": "drop",                  # dev-only — gitleaks is for committers
    "Architecture": "keep",
    "License": "replace",                       # point at source repo instead
}

# Level-3 sub-section titles (without the leading "### ") to drop from
# sections flagged as "trim". These are dev/build-oriented — Docker Hub
# users already have the image and don't need rebuild or multi-user
# compose instructions.
TRIM_SUBSECTIONS: dict[str, set[str]] = {
    "Configuration": {
        "Multi-user setup",
        "Rebuilding the Image",
        "Build Args",
    },
}

# Replacement bodies. Keys match SECTION_RULES entries marked "replace".
# Each value is the full section including the "## Title" heading.
REPLACEMENTS: dict[str, str] = {
    "Quick Start": """## Quick Start

```bash
docker run -it --rm \\
  -e ANTHROPIC_API_KEY=your-key \\
  -e OPENCODE_PROVIDER=anthropic \\
  -e GIT_USER_NAME="Your Name" \\
  -e GIT_USER_EMAIL="you@example.com" \\
  -v ~/projects:/workspace \\
  -v ~/.ssh:/home/developer/.ssh:ro \\
  joakimp/opencode-devbox:latest
```

This drops you straight into opencode with your project mounted at `/workspace`.

For an interactive shell first (useful for AWS SSO login):

```bash
docker run -it --rm \\
  -e ANTHROPIC_API_KEY=your-key \\
  -e OPENCODE_PROVIDER=anthropic \\
  -v ~/projects:/workspace \\
  -v ~/.ssh:/home/developer/.ssh:ro \\
  joakimp/opencode-devbox:latest bash
```

Then run `opencode` when ready.

For docker-compose users, see the source repo for `docker-compose.yml` and `.env.example` templates.
""",
    "License": """## Source

MIT licensed. Source, issues, and `docker-compose.yml` templates: <https://gitea.jordbo.se/joakimp/opencode-devbox>
""",
}


# Prepended to the generated file.
HEADER = """# opencode-devbox — Docker Hub

Portable AI developer environment for [opencode](https://opencode.ai). Debian-based, with git, SSH, Node.js, AWS CLI v2, and common dev tools pre-installed.

## Image Variants

Two image variants are published for each release:

| Tag | Description |
|---|---|
| `latest` / `vX.Y.Z` | Base image — opencode, Node.js, AWS CLI, dev tools |
| `latest-omos` / `vX.Y.Z-omos` | Base + [oh-my-opencode-slim](https://github.com/alvinunreal/oh-my-opencode-slim) multi-agent orchestration and Bun |

Both variants support `linux/amd64` and `linux/arm64`.

> **NOTE:** This file is auto-generated from `README.md` by `scripts/generate-dockerhub-md.py`. Edit README.md and regenerate rather than editing this file directly.

"""


def split_sections(md: str) -> list[tuple[str, str]]:
    """Split markdown on level-2 headings, returning (title, body) pairs.

    The body includes the heading line and everything up to (but not
    including) the next level-2 heading or EOF. Content before the first
    ``## `` is returned with an empty title (the document preamble).
    """
    pattern = re.compile(r"^## ", re.MULTILINE)
    parts = pattern.split(md)
    preamble, *rest = parts

    sections: list[tuple[str, str]] = []
    if preamble.strip():
        sections.append(("", preamble))
    for part in rest:
        line, _, body = part.partition("\n")
        sections.append((line.strip(), f"## {line}\n{body}"))
    return sections


def trim_subsections(body: str, drop: set[str]) -> str:
    """Remove level-3 sub-sections whose title is in `drop`.

    A sub-section starts at a line beginning with "### " and ends at
    the next "### " or "## " (or EOF).
    """
    if not drop:
        return body

    # Split on level-3 headings while preserving the level-2 header
    # block. First piece is everything up to the first "### ".
    parts = re.split(r"(^### .+\n)", body, flags=re.MULTILINE)
    # parts alternates: [before_first_h3, "### Title\n", body, "### Title\n", body, ...]
    kept: list[str] = [parts[0]] if parts else []
    i = 1
    while i < len(parts):
        heading = parts[i]
        content = parts[i + 1] if i + 1 < len(parts) else ""
        title = heading[4:].strip()
        if title not in drop:
            kept.append(heading)
            kept.append(content)
        i += 2
    return "".join(kept)


def generate() -> str:
    """Produce the DOCKER_HUB.md content string."""
    readme = README.read_text(encoding="utf-8")
    sections = split_sections(readme)

    out: list[str] = [HEADER]
    unknown: list[str] = []

    for title, body in sections:
        if title == "":
            # README preamble is replaced by our HEADER; skip.
            continue

        rule = SECTION_RULES.get(title)
        if rule is None:
            unknown.append(title)
            continue
        if rule == "drop":
            continue
        if rule == "keep":
            out.append(body.rstrip() + "\n\n")
        elif rule == "trim":
            trimmed = trim_subsections(body, TRIM_SUBSECTIONS.get(title, set()))
            out.append(trimmed.rstrip() + "\n\n")
        elif rule == "replace":
            out.append(REPLACEMENTS[title].rstrip() + "\n\n")
        else:  # pragma: no cover — programmer error
            raise AssertionError(f"unknown rule {rule!r} for section {title!r}")

    if unknown:
        print(
            "ERROR: README.md contains sections not classified in "
            "SECTION_RULES:\n  - "
            + "\n  - ".join(unknown)
            + "\n\nAdd each to SECTION_RULES in "
            "scripts/generate-dockerhub-md.py (choose keep/drop/replace).",
            file=sys.stderr,
        )
        raise SystemExit(2)

    return "".join(out).rstrip() + "\n"


def main() -> int:
    parser = argparse.ArgumentParser(description=__doc__)
    parser.add_argument(
        "--check",
        action="store_true",
        help="Fail if DOCKER_HUB.md differs from generated content.",
    )
    args = parser.parse_args()

    content = generate()
    size = len(content.encode("utf-8"))
    if size > MAX_SIZE_BYTES:
        print(
            f"ERROR: generated DOCKER_HUB.md is {size} bytes, exceeding the "
            f"Docker Hub limit of {MAX_SIZE_BYTES} bytes.",
            file=sys.stderr,
        )
        return 1

    if args.check:
        existing = DOCKER_HUB.read_text(encoding="utf-8") if DOCKER_HUB.exists() else ""
        if existing != content:
            print(
                "ERROR: DOCKER_HUB.md is out of sync with README.md.\n"
                "Run: python3 scripts/generate-dockerhub-md.py",
                file=sys.stderr,
            )
            # Show a small diff hint.
            import difflib

            diff = difflib.unified_diff(
                existing.splitlines(keepends=True),
                content.splitlines(keepends=True),
                fromfile="DOCKER_HUB.md (committed)",
                tofile="DOCKER_HUB.md (generated)",
                n=2,
            )
            sys.stderr.writelines(list(diff)[:80])
            return 1
        print(
            f"OK: DOCKER_HUB.md is in sync with README.md "
            f"({size} bytes, {MAX_SIZE_BYTES} limit).",
        )
        return 0

    DOCKER_HUB.write_text(content, encoding="utf-8")
    print(
        f"Wrote {DOCKER_HUB} ({size} bytes, {MAX_SIZE_BYTES} limit).",
    )
    return 0


if __name__ == "__main__":
    raise SystemExit(main())