fix(projekt-matching): break infinite alert loop (issue 2)

Root cause chain (evidence: 25+ failed traces on nproj/3022414):
straight quote in page text ends the guided-decoding JSON string
early -> grammar deadlock -> whitespace loop until context/token
limit -> chat_json fails 3x (~35 min) -> IMAP conn idles out ->
move_to_trash raises -> mail never trashed -> reprocessed forever.

- ingest/mailer: MailBox.ensure_alive() reconnect before finalize;
  move_to_trash failure falls back to flag_checked, run continues
- stages: page_text() feeds only div.content minus skill-tag cloud
  to the LLM and maps quote chars to apostrophes (the actual
  degeneration trigger, live-verified: extract now OK in 21 s)
- llm: requirements maxItems 40; max_tokens 8192 caps degenerate
  runs at ~100 s instead of ~10 min

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
This commit is contained in:
tlg
2026-07-14 10:33:52 +02:00
parent f40a5bb0f8
commit 36eac66abc
8 changed files with 208 additions and 13 deletions

View File

@@ -156,6 +156,63 @@ def test_close_called_even_if_unchecked_uids_raises(tmp_path):
box.close.assert_called_once()
def test_ensure_alive_called_before_finalize(tmp_path):
mails = {"1": mail("Mail", PROJECT_HTML)}
summary, box, sent = run(tmp_path, mails,
dispatch_result={"status": "failed",
"error": "Read timed out"})
names = [c[0] for c in box.method_calls]
assert "ensure_alive" in names
assert names.index("ensure_alive") < names.index("move_to_trash")
box.move_to_trash.assert_called_once_with("1")
assert len(sent) == 1
def test_trash_failure_falls_back_to_flag_and_continues(tmp_path):
mails = {"1": mail("Mail A", PROJECT_HTML),
"2": mail("Mail B", PROJECT_HTML)}
box = mock.Mock()
box.unchecked_uids.return_value = ["1", "2"]
box.fetch.side_effect = lambda uid: mails[uid]
box.move_to_trash.side_effect = [OSError("socket error: EOF"), None]
espo = mock.Mock()
espo.find_opportunity_by_link.return_value = None
with mock.patch("projektmatch.ingest.mailparse.bodies",
side_effect=lambda m: (m["html"], "")), \
mock.patch("projektmatch.ingest.mailer.send_mail", lambda *a: None):
summary = ingest.run_ingest(
cfg(tmp_path), mailbox=box, espo=espo,
resolve=lambda url: "https://www.freelancermap.de/projekt/eins",
dispatch=lambda item: {"status": "created"})
assert summary["trashFailed"] == 1
assert summary["created"] == 2
box.flag_checked.assert_called_once_with("1")
assert box.move_to_trash.call_count == 2
def test_dead_connection_everywhere_still_finishes_run(tmp_path):
mails = {"1": mail("Mail A", PROJECT_HTML),
"2": mail("Mail B", PROJECT_HTML)}
box = mock.Mock()
box.unchecked_uids.return_value = ["1", "2"]
box.fetch.side_effect = lambda uid: mails[uid]
box.ensure_alive.side_effect = OSError("server unreachable")
box.move_to_trash.side_effect = OSError("socket error: EOF")
box.flag_checked.side_effect = OSError("socket error: EOF")
espo = mock.Mock()
espo.find_opportunity_by_link.return_value = None
with mock.patch("projektmatch.ingest.mailparse.bodies",
side_effect=lambda m: (m["html"], "")), \
mock.patch("projektmatch.ingest.mailer.send_mail", lambda *a: None):
summary = ingest.run_ingest(
cfg(tmp_path), mailbox=box, espo=espo,
resolve=lambda url: "https://www.freelancermap.de/projekt/eins",
dispatch=lambda item: {"status": "created"})
assert summary["trashFailed"] == 2
assert summary["created"] == 2
box.close.assert_called_once()
def test_parse_run_result_finds_status_json():
inner = json.dumps({"status": "created", "mustMatch": 90})
payload = {"outputs": [{"outputs": [{"results": {"text": {