agent-orchestrator/tangled_comments.py

#!/usr/bin/env python3
"""Read the review comments on a Tangled pull (top-level discussion comments).

WHY: the appview has no read API for pull comments, and eyeballing the pull page
HTML per comment is slow. This fetches the pull (or a specific round) and prints
every top-level comment as author / time / body — so acting on operator review
notes is one command, not a WebFetch guess.

Same session-cookie auth as tangled_pr.py (cookie from the encrypted store,
tangled.cookie). Read-only: it never posts.

USAGE:
  tangled_comments.py --owner notplants-bot.bsky.social --repo lichen.page.review --pull 75
  tangled_comments.py ... --pull 75 --round 2        # a specific round's page
  tangled_comments.py ... --pull 75 --json           # machine-readable
"""
import argparse, html, json, os, re, sys, urllib.request

BASE = "https://tangled.org"


def load_cookie():
    """Cookie from the encrypted store (tangled.cookie) — see engine/README.md (Secrets)."""
    sys.path.insert(0, os.path.dirname(os.path.abspath(__file__)))
    import secrets as _store
    c = _store.get("tangled.cookie")
    if not c:
        sys.exit("no tangled.cookie in the secret store — add it with: sops /secrets/store.yaml")
    return c


def fetch(url, cookie):
    req = urllib.request.Request(url, headers={"Cookie": cookie, "User-Agent": "tangled-pr-bot"})
    return urllib.request.urlopen(req, timeout=60).read().decode()


def _text(fragment):
    """Strip tags from a body fragment down to readable plaintext."""
    t = re.sub(r"(?is)<br\s*/?>", "\n", fragment)
    t = re.sub(r"(?is)</p\s*>", "\n\n", t)
    t = re.sub(r"(?is)<li[^>]*>", "\n- ", t)
    t = re.sub(r"(?s)<[^>]+>", "", t)
    return html.unescape(t).strip()


def parse_comments(doc):
    """Return [{cid, author, when, iso, uri, body}] in document order.

    Anchored on the per-comment header block the appview emits:
      id="comment-header-{cid}" ... <a href="/{handle}">{handle}</a> ...
      <time datetime="{iso}">{when}</time> ... class="...comment-body"><div class="prose...">{body}</div>
    """
    out = []
    heads = list(re.finditer(r'id="comment-header-([0-9a-z]+)"', doc))
    for i, hm in enumerate(heads):
        cid = hm.group(1)
        # bound by the next comment header, not a fixed window: a comment's own
        # reaction/button markup can push its body several KB past the header.
        end = heads[i + 1].start() if i + 1 < len(heads) else len(doc)
        seg = doc[hm.end(): end]
        am = re.search(r'href="/([^"/]+)"[^>]*>\s*([^<]+?)\s*</a>', seg)
        author = html.unescape(am.group(2)) if am else "?"
        tm = re.search(r'<time datetime="([^"]+)"[^>]*>\s*([^<]+?)\s*</time>', seg)
        iso = html.unescape(tm.group(1)) if tm else ""
        when = html.unescape(tm.group(2)) if tm else ""
        bm = re.search(r'comment-body">\s*<div class="prose[^"]*">(.*?)</div>\s*<div class="reactions', seg, re.S)
        if not bm:
            bm = re.search(r'comment-body">\s*<div class="prose[^"]*">(.*?)</div>', seg, re.S)
        body = _text(bm.group(1)) if bm else ""
        out.append({"cid": cid, "author": author, "when": when, "iso": iso,
                    "uri": f"at://.../sh.tangled.feed.comment/{cid}", "body": body})
    return out


def main():
    ap = argparse.ArgumentParser(description="read a Tangled pull's review comments")
    ap.add_argument("--owner", required=True)
    ap.add_argument("--repo", required=True)
    ap.add_argument("--pull", required=True, type=int)
    ap.add_argument("--round", type=int, default=None, help="a specific round page (default: latest)")
    ap.add_argument("--json", action="store_true")
    a = ap.parse_args()

    cookie = load_cookie()
    url = f"{BASE}/{a.owner}/{a.repo}/pulls/{a.pull}"
    if a.round is not None:
        url += f"/round/{a.round}"
    doc = fetch(url, cookie)

    # A 404 page renders 200 and carries no pull record, so "0 comments" used to be
    # indistinguishable from "no such pull". On 2026-08-22 that cost a false report that
    # #428 was filed and unreviewed, and a reviewer's time chasing it. The post tool never
    # had the defect because it MUST resolve a subject-uri to work at all — so require the
    # same identifier here, and refuse rather than print a header for a phantom.
    if not re.search(r'name="subject-uri"[^>]*value="(at://[^"]+)"', doc):
        sys.exit(
            f"pull #{a.pull} does not exist in {a.owner}/{a.repo} "
            f"(no pull record on {url}).\n"
            "  This is NOT an auth failure: the page rendered, it simply carries no pull.\n"
            "  A pull that exists always yields a subject-uri."
        )

    comments = parse_comments(doc)

    if a.json:
        print(json.dumps({"url": url, "count": len(comments), "comments": comments}, indent=2))
        return
    print(f"# pull #{a.pull}  ({url})  — {len(comments)} comment(s)\n")
    for i, c in enumerate(comments, 1):
        print(f"[{i}] {c['author']}  ·  {c['when']}  ({c['iso']})  #{c['cid']}")
        for line in (c["body"] or "(empty)").splitlines():
            print(f"    {line}")
        print()


if __name__ == "__main__":
    main()