Files
hermes-webui/tests/test_run_journal.py
T
e3a7c93dc6 [HELD — independent review pending] Release v0.51.294 — stage-3401 (live-to-final redesign #3401 + 4 deep-review fixes) (#3741)
* Harden interrupted recovery control filtering

* Redesign live-to-final assistant replies

* Fix live activity anchor test fixture

* Fix CI lint issues for live reply tests

* Strengthen live progress prompt contract

* Recover PR #3401 refresh on origin/master

* Repair live-to-final refresh regressions

* Fix live worklog refresh regressions

* Show live footer timer on initial stream start

* Restore live stream shell after reload

* Preserve per-frame live SSE replay cursors

* Preserve reasoning as Worklog Thinking cards

* Quiet Worklog Thinking card styling

* Align Worklog Thinking card styling

* Scope live Worklog Thinking cards by segment

* Suppress exact duplicate settled Thinking

* Close #3401 merge review test gaps

* fix(#3401): resolve 4 deep-review regressions (inline-think, reconnect-dup, neon skin, busy-gate worklog)

Deep review (Codex diff-vs-master + live-browser drive) of the live-to-final refactor
surfaced 4 regressions vs master that the rewritten suite no longer guarded:

1. Inline <think>…</think>answer reasoning vanished — _assistantReasoningPayloadText
   used $-anchored regexes so a leading think block + visible answer extracted nothing
   and the Thinking card never rendered. Removed the 3 $ anchors to match the
   (non-anchored) display stripper. Live: inline-think thinking-only turn now renders.
2. (CORE) reconnect/reload duplicated the live reply — _rememberRunJournalCursor advanced
   a closure-local seq but never wrote INFLIGHT[activeSid].lastRunJournalSeq, so a reload
   replayed the journal from after_seq=0 over restored lastAssistantText. Now mirrors the
   cursor onto INFLIGHT + schedules a throttled persist.
3. Neon skin silently broke — PR deleted the :root[data-skin="neon"] CSS but left Neon in
   the picker. Restored the neon CSS block from master.
4. Settled tool-worklog rebuild gated purely on !S.busy — dropped every prior settled
   turn's worklog when renderMessages re-ran during an active stream (switch-back to an
   in-progress session). Restored master's !S.busy || (S.toolCalls && S.toolCalls.length).
   Live: busy re-render now preserves tool cards (4→4, was 4→0).

Live-verified all 4 + confirmed #3709/#3592 invariants still hold (1 thinking card, none
below footer; distinct siblings preserved). + tests/test_issue3401_deep_review_fixes.py (7).

* test(#3401): realign 3 stale source-shape assertions to the deep-review fixes

Fix commit changed two source literals that existing stage tests scanned for:
- test_live_activity_timeline.py (x2): split anchor 'if(!S.busy){' → the restored
  'if(!S.busy || (S.toolCalls&&S.toolCalls.length)){' guard (fix 4).
- test_run_journal_frontend_static.py: 'after_seq=0' not in source — fix 2's comment
  contained that literal; rephrased the comment to 'the zero floor (after_seq of 0)'.
Intent of all three assertions unchanged; only the matched string updated. No code
behavior change.

* docs(changelog): v0.51.294 — Release JJ (stage-3401, #3401 live-to-final redesign)

---------

Co-authored-by: Frank Song <franksong2702@gmail.com>
Co-authored-by: Nathan-Hermes <nesquena-hermes@users.noreply.github.com>
Co-authored-by: nesquena-hermes <[email protected]>
2026-06-06 12:12:37 -07:00

153 lines
6.3 KiB
Python

import json
from api.run_journal import (
RunJournalWriter,
append_run_event,
find_run_summary,
latest_run_summary,
read_run_events,
stale_interrupted_event,
)
def test_run_journal_appends_monotonic_seq_and_reads_after_cursor(tmp_path):
writer = RunJournalWriter("session_1", "run_1", session_dir=tmp_path)
first = writer.append_sse_event("token", {"text": "hello"})
second = writer.append_sse_event("done", {"session": {"session_id": "session_1"}})
assert first["seq"] == 1
assert first["event_id"] == "run_1:1"
assert first["terminal"] is False
assert second["seq"] == 2
assert second["terminal"] is True
assert second["terminal_state"] == "completed"
journal = read_run_events("session_1", "run_1", after_seq=1, session_dir=tmp_path)
assert [event["event"] for event in journal["events"]] == ["done"]
def test_run_journal_reads_bounded_replay_window(tmp_path):
writer = RunJournalWriter("session_1", "run_1", session_dir=tmp_path)
writer.append_sse_event("token", {"text": "one"})
writer.append_sse_event("token", {"text": "two"})
writer.append_sse_event("token", {"text": "three"})
writer.append_sse_event("token", {"text": "four"})
journal = read_run_events(
"session_1",
"run_1",
after_seq=1,
max_seq=3,
session_dir=tmp_path,
)
assert [event["seq"] for event in journal["events"]] == [2, 3]
assert [event["payload"]["text"] for event in journal["events"]] == ["two", "three"]
def test_run_journal_default_fsyncs_terminal_events_only(tmp_path, monkeypatch):
path = tmp_path / "_run_journal" / "session_1" / "run_1.jsonl"
path.parent.mkdir(parents=True)
path.touch()
fsync_calls = []
monkeypatch.delenv("HERMES_WEBUI_RUN_JOURNAL_FSYNC", raising=False)
monkeypatch.setattr("api.run_journal.os.fsync", lambda fd: fsync_calls.append(fd))
append_run_event("session_1", "run_1", "token", {"text": "ok"}, session_dir=tmp_path)
assert fsync_calls == []
append_run_event("session_1", "run_1", "done", {"session": {}}, session_dir=tmp_path)
assert len(fsync_calls) == 1
def test_run_journal_eager_fsync_mode_fsyncs_non_terminal_events(tmp_path, monkeypatch):
path = tmp_path / "_run_journal" / "session_1" / "run_1.jsonl"
path.parent.mkdir(parents=True)
path.touch()
fsync_calls = []
monkeypatch.setenv("HERMES_WEBUI_RUN_JOURNAL_FSYNC", "eager")
monkeypatch.setattr("api.run_journal.os.fsync", lambda fd: fsync_calls.append(fd))
append_run_event("session_1", "run_1", "token", {"text": "ok"}, session_dir=tmp_path)
assert len(fsync_calls) == 1
def test_run_journal_tolerates_malformed_lines(tmp_path):
append_run_event("session_1", "run_1", "token", {"text": "ok"}, session_dir=tmp_path)
path = tmp_path / "_run_journal" / "session_1" / "run_1.jsonl"
with path.open("a", encoding="utf-8") as fh:
fh.write("{not json}\n")
fh.write(json.dumps(["wrong-shape"]) + "\n")
journal = read_run_events("session_1", "run_1", session_dir=tmp_path)
assert len(journal["events"]) == 1
assert len(journal["malformed"]) == 2
def test_latest_summary_and_find_run_summary_classify_terminal_state(tmp_path):
append_run_event("session_1", "run_1", "token", {"text": "ok"}, session_dir=tmp_path)
append_run_event("session_1", "run_1", "cancel", {"message": "Cancelled by user"}, session_dir=tmp_path)
summary = latest_run_summary("session_1", "run_1", session_dir=tmp_path)
found = find_run_summary("run_1", session_dir=tmp_path)
assert summary["terminal"] is True
assert summary["terminal_state"] == "interrupted-by-user"
assert summary["last_seq"] == 2
assert found["session_id"] == "session_1"
assert found["terminal_state"] == "interrupted-by-user"
def test_terminal_state_classification_distinguishes_crash_from_user_cancel(tmp_path):
append_run_event("session_1", "run_cancelled", "cancel", {"message": "Cancelled by user"}, session_dir=tmp_path)
append_run_event("session_1", "run_crashed", "apperror", {"type": "interrupted"}, session_dir=tmp_path)
append_run_event("session_1", "run_failed", "apperror", {"type": "auth_mismatch"}, session_dir=tmp_path)
append_run_event("session_1", "run_done", "done", {"session": {}}, session_dir=tmp_path)
assert latest_run_summary("session_1", "run_cancelled", session_dir=tmp_path)["terminal_state"] == "interrupted-by-user"
assert latest_run_summary("session_1", "run_crashed", session_dir=tmp_path)["terminal_state"] == "interrupted-by-crash"
assert latest_run_summary("session_1", "run_failed", session_dir=tmp_path)["terminal_state"] == "errored"
assert latest_run_summary("session_1", "run_done", session_dir=tmp_path)["terminal_state"] == "completed"
def test_summary_keeps_logical_terminal_state_when_stream_end_follows(tmp_path):
append_run_event("session_1", "run_1", "apperror", {"type": "auth_mismatch"}, session_dir=tmp_path)
append_run_event("session_1", "run_1", "stream_end", {"session_id": "session_1"}, session_dir=tmp_path)
summary = latest_run_summary("session_1", "run_1", session_dir=tmp_path)
assert summary["terminal"] is True
assert summary["last_event"] == "stream_end"
assert summary["terminal_state"] == "errored"
def test_stale_interrupted_event_reports_non_terminal_journal(tmp_path, monkeypatch):
append_run_event("session_1", "run_1", "token", {"text": "partial"}, session_dir=tmp_path)
monkeypatch.setattr("api.run_journal._default_session_dir", lambda: tmp_path)
event = stale_interrupted_event("session_1", "run_1")
assert event is not None
assert event["event"] == "apperror"
assert event["seq"] == 2
assert event["terminal_state"] == "lost-worker-bookkeeping"
assert event["payload"]["type"] == "interrupted"
assert "last journaled event" in event["payload"]["hint"]
assert "process restarted" not in event["payload"]["message"]
assert "lost the live worker" not in event["payload"]["message"]
assert "live worker stopped" in event["payload"]["message"]
def test_stale_interrupted_event_skips_terminal_journal(tmp_path, monkeypatch):
append_run_event("session_1", "run_1", "done", {"session": {}}, session_dir=tmp_path)
monkeypatch.setattr("api.run_journal._default_session_dir", lambda: tmp_path)
assert stale_interrupted_event("session_1", "run_1") is None