marketplace/skills/sync/scripts/evict.py

#!/usr/bin/env python3
"""
evict.py — ask Gitea which stored issues are closed, then evict those.

    evict.py                  check every synced issue in the store, evict the
                              ones Gitea says are closed
    evict.py old-thing …      only these
    evict.py --dry-run        ask, report, change nothing

The offline command is `/tea:issue`'s `issue_evict.py`, and it is the one that
decides and deletes — this script adds exactly one thing in front of it: a
`state:` that is not stale. A local `state:` is only as fresh as the last pull,
so an issue closed in the web UI an hour ago still reads `open` here and the
offline command will (correctly) leave it alone. That is the gap this closes,
and it is the observed workflow: before this existed the operator had to
`pull.py 11 12 13 14 15` first, which re-wrote the five closed files onto disk
before anything could remove them.

Order of operations, and it is the whole safety argument:

    1. every candidate's state is fetched — ALL of them, before anything is
       removed;
    2. each answer must be an object carrying the number we asked about and a
       state from the domain's own vocabulary (`confirmed_state`);
    3. only then is the eviction run, by handing the refreshed issues to
       `issue_evict.run` — the same decision, the same deletion, the same
       protection of `origin: local`, in one place.

A `tea` that will not run, a non-2xx, an answer for another issue, a state
nobody recognizes: the run stops at step 2 and NOTHING is deleted, not even the
issues whose answers had already arrived. That is stricter than `push.py`, which
deletes as it goes, and it costs nothing here — there is no ordering constraint
between evictions, so there is no reason to start before every answer is in.

A candidate is an issue carrying a `gitea:` handle. `origin: local` work has
none, is never asked about, and is never evicted — it is not in the tracker to
be closed. An `origin: gitea` issue whose handle is missing or unparseable
cannot be verified, so it is reported and kept rather than guessed at.

Cost: one GET per candidate. The store is a working set that push keeps small,
and a wrong answer here deletes a file, so each issue is asked about by its own
address rather than inferred from a list that a `--limit` could have truncated.

Login: the operator's pin from .claude/settings.local.json (see /tea:auth).
"""
import argparse
import os
import sys

_HERE = os.path.dirname(os.path.abspath(__file__))
sys.path[:0] = [_HERE, os.path.normpath(os.path.join(_HERE, "..", "..", "issue", "scripts"))]

import _gitea  # noqa: E402
import issue  # noqa: E402
import issue_evict  # noqa: E402
import map as gmap  # noqa: E402


def candidates(issues, ids=None):
    """(checkable, unverifiable) — which issues the tracker can be asked about.

    checkable is [(id, repo, number)] read off the `gitea:` handle, so an issue
    that lives in another repo is asked about there. unverifiable is
    [(id, why)]: it names a tracker but carries no handle to reach it by, which
    is a file to report, never one to delete on a guess.

    An `origin: local` issue is in neither list. It has no handle because it has
    never left this machine, and asking Gitea about it is not a question that
    has an answer.
    """
    checkable, unverifiable = [], []
    for id in (list(ids) if ids else sorted(issues)):
        iss = issues[id]
        if iss.is_local:
            continue
        repo, number = gmap.parse_remote_key(iss.extra.get("gitea", ""))
        if not repo or not number:
            unverifiable.append((id, "origin: %s but no usable `gitea:` handle"
                                 % iss.origin))
            continue
        checkable.append((id, repo, number))
    return checkable, unverifiable


def confirmed_state(got, number):
    """The state Gitea confirmed for `number`, or None — the deletion gate.

    The counterpart of `push.confirmed_number`, and written the same way: boring,
    and saying no by default, because everything downstream of a `str` return
    here may delete a file. An answer counts only when it is a dict, carries the
    very number we asked about, and names a state the domain recognizes.

    `bool` is rejected explicitly: `True` is an `int` in Python, and an answer
    about issue `true` is not an answer about issue 42.

    What it does not have to catch, because it never gets here: a non-2xx or a
    `tea` that would not run at all — `_gitea.api` exits on both.
    """
    if not isinstance(got, dict):
        return None
    n = got.get("number")
    if isinstance(n, bool) or not isinstance(n, int) or n != number:
        return None
    state = got.get("state")
    return state if state in issue.STATES else None


def main(argv=None):
    ap = argparse.ArgumentParser(
        description="Evict issues Gitea reports as closed from the local store")
    ap.add_argument("ids", nargs="*",
                    help="issue ids (default: every synced issue in the store)")
    ap.add_argument("--dry-run", action="store_true",
                    help="ask the tracker and report; write and delete nothing")
    ap.add_argument("--out", default=issue.ISSUE_ROOT,
                    help="store root (default: <repo>/tmp/issues)")
    args = ap.parse_args(argv)

    root = args.out
    if not issue.store_exists(root):
        _gitea.die("store %s does not exist — nothing to evict" % root)
    issues = issue.load_all(root)
    missing = [i for i in args.ids if i not in issues]
    if missing:
        _gitea.die("no such issue(s) in the store: %s" % ", ".join(missing))

    checkable, unverifiable = candidates(issues, args.ids)
    for id, why in unverifiable:
        _gitea.warn("%s: %s — kept, and not asked about" % (id, why))
    if not checkable:
        print("nothing to check: no issue in the store carries a `gitea:` handle")
        return 0

    login = _gitea.require_login()

    # ---- every answer first, deletions after -----------------------------
    fresh = {}
    for id, repo, number in checkable:
        got = _gitea.api(login, "%s/issues/%d" % (_gitea.repo_base(repo), number))
        state = confirmed_state(got, number)
        if state is None:
            _gitea.die("%s: the tracker's answer for %s#%d does not confirm a state "
                       "(%.200r). Nothing was evicted."
                       % (id, repo, number, got))
        fresh[id] = state

    # The store stops lying even about the issues that stay: an answer already
    # paid for is written back when it disagrees with the file. This is the only
    # write this script makes, and a dry run makes none.
    for id, state in sorted(fresh.items()):
        was = issues[id].state
        if was == state:
            continue
        print("state       %s  %s -> %s" % (id, was, state))
        issues[id].state = state
        if not args.dry_run:
            issue.save(root, issues[id])

    issue_evict.run(root, issues, [id for id, _, _ in checkable], args.dry_run)
    return 0


if __name__ == "__main__":
    sys.exit(main())