fix(gateway): use transcript timestamp for auto-continue freshness

Follow-up to PR #16802 (BeliefanX). The original fix read
`agent_history[-1].get("timestamp")` for the tool-tail freshness gate,
but `gateway/run.py` strips the `timestamp` field off all tool/tool_call
rows when building `agent_history` from the raw transcript (see
`clean_msg = {k: v for k, v in msg.items() if k != "timestamp"}`).  At
runtime the tool-tail branch always saw `None` and silently took the
legacy-fresh path — the stale-guard never fired for the tool-tail case
it was supposed to cover.

Changes:
- Read the freshness signal from the RAW `history` list (via new
  `_last_transcript_timestamp()` helper) BEFORE the strip.  Both the
  resume_pending branch and the tool-tail branch use this single signal,
  replacing the two divergent ones.
- Default window bumped 15 min → 1 hour via new
  `_AUTO_CONTINUE_FRESHNESS_SECS_DEFAULT`.  The 15-minute default was
  shorter than the default `gateway_timeout` of 30 min, so a legitimate
  long-running turn interrupted near its timeout boundary and resumed
  shortly after would have been misclassified as stale.
- Configurable via `config.yaml` `agent.gateway_auto_continue_freshness`
  (bridged to `HERMES_AUTO_CONTINUE_FRESHNESS` at gateway startup — same
  pattern as `gateway_timeout`).  Set to 0 to disable the gate.
- `_coerce_gateway_timestamp` now explicitly rejects bool (which is a
  subclass of int and would otherwise coerce to 0.0/1.0).
- Tests rewritten to exercise the real production data shape: raw
  `history` → `_build_agent_history` strip → freshness decision.  A
  regression guard (`test_stale_tool_tail_with_production_data_shape`)
  asserts `agent_history` tool rows carry NO timestamp, protecting
  against someone "fixing" the original bug by re-adding the stripped
  field (which would break the OpenAI tool-result message contract).

Add BeliefanX to scripts/release.py AUTHOR_MAP.

E2E verified: config.yaml → env var bridge → helper returns configured
value; default 1h window; malformed/empty env var falls back to default;
ISO-Z timestamps parse; ms-epoch coerced; bool rejected.
This commit is contained in:
teknium1 2026-04-28 05:00:26 -07:00 committed by Teknium
parent 93feffbcfa
commit 7444e49d4e
4 changed files with 407 additions and 35 deletions

View file

@ -43,7 +43,22 @@ _AGENT_CACHE_IDLE_TTL_SECS = 3600.0 # evict agents idle for >1h
# Only auto-continue interrupted gateway turns while the interruption is fresh.
# Stale tool-tail/resume markers can otherwise revive an unrelated old task
# after a gateway restart when the user's next message starts new work.
_AUTO_CONTINUE_FRESHNESS_SECS = 15 * 60
#
# The freshness signal is the timestamp of the last transcript row, which
# ``hermes_state.get_messages`` carries on every persisted message. This
# handles the two auto-continue cases uniformly:
# * resume_pending (gateway restart/shutdown watchdog marked the session)
# * tool-tail (last persisted message is a tool result the agent
# never got to reply to)
# In both cases "when did we last do anything on this transcript" is the
# correct freshness question, so one signal replaces two divergent ones.
#
# Default window: 1 hour. This comfortably covers ``agent.gateway_timeout``
# (30 min default) plus runtime slack — a legitimate long-running turn that
# gets interrupted near its timeout boundary and is resumed shortly after
# is still classified fresh. Override via
# ``config.yaml`` ``agent.gateway_auto_continue_freshness``.
_AUTO_CONTINUE_FRESHNESS_SECS_DEFAULT = 60 * 60
def _coerce_gateway_timestamp(value: Any) -> Optional[float]:
@ -51,11 +66,16 @@ def _coerce_gateway_timestamp(value: Any) -> Optional[float]:
Missing/unparseable timestamps return None so legacy transcripts keep the
historical auto-continue behaviour instead of being silently dropped.
Accepts: datetime, epoch seconds (int/float), epoch milliseconds (when
the magnitude exceeds year-2286), ISO-8601 strings (with or without a
trailing ``Z``), and numeric strings.
"""
if value is None:
return None
if isinstance(value, datetime):
return value.timestamp()
if isinstance(value, bool): # bool is a subclass of int — skip it
return None
if isinstance(value, (int, float)):
# Some platform events use milliseconds; Hermes state rows use seconds.
return float(value) / 1000.0 if float(value) > 10_000_000_000 else float(value)
@ -75,17 +95,77 @@ def _coerce_gateway_timestamp(value: Any) -> Optional[float]:
return None
def _is_fresh_gateway_interruption(value: Any, *, now: Optional[float] = None) -> bool:
def _auto_continue_freshness_window() -> float:
"""Return the configured auto-continue freshness window in seconds.
Reads ``HERMES_AUTO_CONTINUE_FRESHNESS`` (bridged from
``config.yaml`` ``agent.gateway_auto_continue_freshness`` at gateway
startup, same pattern as ``HERMES_AGENT_TIMEOUT``). Falls back to the
module default when unset or malformed. Non-positive values disable
the freshness gate (restores the pre-fix "always fresh" behaviour for
users who want to opt out).
"""
raw = os.environ.get("HERMES_AUTO_CONTINUE_FRESHNESS")
if raw is None or raw == "":
return float(_AUTO_CONTINUE_FRESHNESS_SECS_DEFAULT)
try:
return float(raw)
except (TypeError, ValueError):
return float(_AUTO_CONTINUE_FRESHNESS_SECS_DEFAULT)
def _is_fresh_gateway_interruption(
value: Any,
*,
now: Optional[float] = None,
window_secs: Optional[float] = None,
) -> bool:
"""Return True when an interruption marker is fresh enough to auto-continue.
Unknown timestamps are treated as fresh for backward compatibility with
legacy transcripts/tests that predate timestamp persistence.
legacy transcripts (pre-dating timestamp persistence) and with in-memory
test scaffolding that constructs history entries without timestamps.
A non-positive ``window_secs`` disables the gate (always fresh), which
restores the pre-fix behaviour for users who opt out via config.
"""
window = (
float(window_secs)
if window_secs is not None
else float(_AUTO_CONTINUE_FRESHNESS_SECS_DEFAULT)
)
if window <= 0:
return True
timestamp = _coerce_gateway_timestamp(value)
if timestamp is None:
return True
current = time.time() if now is None else now
return current - timestamp <= _AUTO_CONTINUE_FRESHNESS_SECS
return current - timestamp <= window
def _last_transcript_timestamp(history: Optional[List[Dict[str, Any]]]) -> Any:
"""Return the ``timestamp`` of the last usable transcript row, if any.
Skips metadata-only rows (``session_meta``, system injections) that are
dropped before being handed to the agent. Returns ``None`` when no
usable row carries a timestamp callers should treat that as "fresh"
for backward compatibility.
"""
if not history:
return None
for msg in reversed(history):
if not isinstance(msg, dict):
continue
role = msg.get("role")
if not role or role in ("session_meta", "system"):
continue
ts = msg.get("timestamp")
if ts is not None:
return ts
# First non-meta row without a timestamp — legacy transcript row.
# Returning None lets the caller fall through to the legacy-fresh path.
return None
return None
# ---------------------------------------------------------------------------
@ -260,6 +340,13 @@ if _config_path.exists():
os.environ["HERMES_AGENT_NOTIFY_INTERVAL"] = str(_agent_cfg["gateway_notify_interval"])
if "restart_drain_timeout" in _agent_cfg and "HERMES_RESTART_DRAIN_TIMEOUT" not in os.environ:
os.environ["HERMES_RESTART_DRAIN_TIMEOUT"] = str(_agent_cfg["restart_drain_timeout"])
if (
"gateway_auto_continue_freshness" in _agent_cfg
and "HERMES_AUTO_CONTINUE_FRESHNESS" not in os.environ
):
os.environ["HERMES_AUTO_CONTINUE_FRESHNESS"] = str(
_agent_cfg["gateway_auto_continue_freshness"]
)
_display_cfg = _cfg.get("display", {})
if _display_cfg and isinstance(_display_cfg, dict):
if "busy_input_mode" in _display_cfg and "HERMES_GATEWAY_BUSY_INPUT_MODE" not in os.environ:
@ -10554,26 +10641,38 @@ class GatewayRunner:
# anything (tool, assistant with unfinished work, etc.), so we
# give a stronger, reason-aware instruction that subsumes the
# tool-tail case.
#
# Freshness gate (#16802): both branches are gated on the age
# of the last persisted transcript row. That is the correct
# "when did we last do anything here" signal for both the
# resume_pending path (restart watchdog) and the tool-tail
# path (in-flight tool loop killed). We read ``history[-1]``
# here because ``agent_history`` has already stripped the
# ``timestamp`` field off tool/tool_call rows for API purity
# (see the `k != "timestamp"` filter above). Rows without a
# timestamp (legacy transcripts) are treated as fresh so the
# historical auto-continue behaviour is preserved.
_freshness_window = _auto_continue_freshness_window()
_interruption_is_fresh = _is_fresh_gateway_interruption(
_last_transcript_timestamp(history),
window_secs=_freshness_window,
)
_resume_entry = None
if session_key:
try:
_resume_entry = self.session_store._entries.get(session_key)
except Exception:
_resume_entry = None
_resume_marked_at = (
getattr(_resume_entry, "last_resume_marked_at", None)
if _resume_entry is not None
else None
)
_is_resume_pending = bool(
_resume_entry is not None
and getattr(_resume_entry, "resume_pending", False)
and _is_fresh_gateway_interruption(_resume_marked_at)
and _interruption_is_fresh
)
_has_fresh_tool_tail = bool(
agent_history
and agent_history[-1].get("role") == "tool"
and _is_fresh_gateway_interruption(agent_history[-1].get("timestamp"))
and _interruption_is_fresh
)
if _is_resume_pending:

View file

@ -411,6 +411,20 @@ DEFAULT_CONFIG = {
# (60+ tool iterations with tiny output) before users assume the
# bot is dead and /restart.
"gateway_notify_interval": 180,
# Freshness window for the gateway auto-continue note (seconds).
# After a gateway crash/restart/SIGTERM mid-run, the next user
# message gets a "[System note: your previous turn was
# interrupted — process the unfinished tool result(s) first]"
# prepended so the model picks up where it left off. That's the
# right behaviour while the interruption is fresh, but stale
# markers (transcript last touched hours or days ago) can revive
# an unrelated old task when the user's next message starts new
# work. This window is the max age of the last persisted
# transcript row for which we still inject the continue note.
# Default 3600s comfortably covers a long turn (gateway_timeout
# default is 1800s) plus runtime slack. Set to 0 to disable the
# gate and restore pre-fix behaviour (always inject).
"gateway_auto_continue_freshness": 3600,
# How user-attached images are presented to the main model on each turn.
# "auto" — attach natively when the active model reports
# supports_vision=True AND the user hasn't explicitly

View file

@ -58,6 +58,7 @@ AUTHOR_MAP = {
"yes999zc@163.com": "yes999zc",
"343873859@qq.com": "DrStrangerUJN",
"uzmpsk.dilekakbas@gmail.com": "dlkakbs",
"beliefanx@gmail.com": "BeliefanX",
"jefferson@heimdallstrategy.com": "Mind-Dragon",
"steve.westerhouse@origami-analytics.com": "westers",
"130918800+devorun@users.noreply.github.com": "devorun",

View file

@ -33,7 +33,12 @@ from unittest.mock import AsyncMock, MagicMock, patch
import pytest
from gateway.config import GatewayConfig, Platform, PlatformConfig
from gateway.run import _is_fresh_gateway_interruption
from gateway.run import (
_auto_continue_freshness_window,
_coerce_gateway_timestamp,
_is_fresh_gateway_interruption,
_last_transcript_timestamp,
)
from gateway.session import SessionEntry, SessionSource, SessionStore
from tests.gateway.restart_test_helpers import (
make_restart_runner,
@ -54,28 +59,69 @@ def _make_store(tmp_path):
return SessionStore(sessions_dir=tmp_path, config=GatewayConfig())
def _build_agent_history(history: list) -> list:
"""Mirror gateway/run.py's ``history → agent_history`` conversion.
This is the transformation that strips ``timestamp`` off tool/tool_call
rows before the agent sees them. Tests that check the freshness gate
must go through this conversion so they exercise the *real* data the
note-injection code sees.
"""
agent_history: list = []
for msg in history:
role = msg.get("role")
if not role or role in ("session_meta", "system"):
continue
has_tool_calls = "tool_calls" in msg
has_tool_call_id = "tool_call_id" in msg
is_tool_message = role == "tool"
if has_tool_calls or has_tool_call_id or is_tool_message:
agent_history.append({k: v for k, v in msg.items() if k != "timestamp"})
else:
content = msg.get("content")
if content:
agent_history.append({"role": role, "content": content})
return agent_history
def _simulate_note_injection(
agent_history: list,
history: list,
user_message: str,
resume_entry: SessionEntry | None,
*,
agent_history: list | None = None,
window_secs: float | None = None,
) -> str:
"""Mirror the note-injection logic in gateway/run.py _run_agent().
Matches the production code in the ``run_sync`` closure so we can
test the decision tree without a full gateway runner.
The freshness signal reads ``history[-1].timestamp`` (the raw transcript
row), NOT ``agent_history[-1].timestamp`` (which has been stripped).
Tests pass the raw ``history`` ``agent_history`` is derived from it
via the real conversion if not supplied explicitly.
"""
if agent_history is None:
agent_history = _build_agent_history(history)
window = (
float(window_secs)
if window_secs is not None
else _auto_continue_freshness_window()
)
interruption_is_fresh = _is_fresh_gateway_interruption(
_last_transcript_timestamp(history),
window_secs=window,
)
message = user_message
is_resume_pending = bool(
resume_entry is not None
and getattr(resume_entry, "resume_pending", False)
and _is_fresh_gateway_interruption(
getattr(resume_entry, "last_resume_marked_at", None)
)
and interruption_is_fresh
)
has_fresh_tool_tail = bool(
agent_history
and agent_history[-1].get("role") == "tool"
and _is_fresh_gateway_interruption(agent_history[-1].get("timestamp"))
and interruption_is_fresh
)
if is_resume_pending:
@ -366,7 +412,9 @@ class TestResumePendingSystemNote:
def test_resume_pending_restart_note_mentions_restart(self):
entry = self._pending_entry(reason="restart_timeout")
result = _simulate_note_injection(
agent_history=[{"role": "assistant", "content": "in progress"}],
history=[
{"role": "assistant", "content": "in progress", "timestamp": time.time()},
],
user_message="what happened?",
resume_entry=entry,
)
@ -377,7 +425,9 @@ class TestResumePendingSystemNote:
def test_resume_pending_shutdown_note_mentions_shutdown(self):
entry = self._pending_entry(reason="shutdown_timeout")
result = _simulate_note_injection(
agent_history=[{"role": "assistant", "content": "in progress"}],
history=[
{"role": "assistant", "content": "in progress", "timestamp": time.time()},
],
user_message="ping",
resume_entry=entry,
)
@ -388,8 +438,8 @@ class TestResumePendingSystemNote:
even when the transcript's last role is NOT ``tool``."""
entry = self._pending_entry()
history = [
{"role": "user", "content": "run a long thing"},
{"role": "assistant", "content": "ok, starting..."},
{"role": "user", "content": "run a long thing", "timestamp": time.time() - 10},
{"role": "assistant", "content": "ok, starting...", "timestamp": time.time()},
]
result = _simulate_note_injection(history, "ping", resume_entry=entry)
assert "[System note:" in result
@ -402,8 +452,9 @@ class TestResumePendingSystemNote:
history = [
{"role": "assistant", "content": None, "tool_calls": [
{"id": "c1", "function": {"name": "x", "arguments": "{}"}},
]},
{"role": "tool", "tool_call_id": "c1", "content": "result"},
], "timestamp": time.time() - 1},
{"role": "tool", "tool_call_id": "c1", "content": "result",
"timestamp": time.time()},
]
result = _simulate_note_injection(history, "ping", resume_entry=entry)
assert result.count("[System note:") == 1
@ -416,31 +467,41 @@ class TestResumePendingSystemNote:
history = [
{"role": "assistant", "content": None, "tool_calls": [
{"id": "c1", "function": {"name": "x", "arguments": "{}"}},
]},
{"role": "tool", "tool_call_id": "c1", "content": "result"},
], "timestamp": time.time() - 1},
{"role": "tool", "tool_call_id": "c1", "content": "result",
"timestamp": time.time()},
]
result = _simulate_note_injection(history, "ping", resume_entry=None)
assert "[System note:" in result
assert "tool result" in result
def test_stale_resume_pending_does_not_inject_restart_note(self):
"""Old restart markers must not revive an unrelated stale task."""
"""Old restart markers must not revive an unrelated stale task.
The transcript's last row is from an hour ago — well outside the
default 1h freshness window (fixture uses window=1800 to exercise
the stale path without tying the test to the production default).
"""
entry = self._pending_entry()
entry.last_resume_marked_at = datetime.now() - timedelta(hours=1)
history = [
{"role": "assistant", "content": "old in progress",
"timestamp": time.time() - 3600},
]
result = _simulate_note_injection(
agent_history=[{"role": "assistant", "content": "old in progress"}],
history=history,
user_message="start a new task",
resume_entry=entry,
window_secs=1800,
)
assert result == "start a new task"
def test_fresh_tool_tail_preserves_auto_continue_note(self):
history = [
{"role": "assistant", "content": None, "tool_calls": [
{"id": "c1", "function": {"name": "x", "arguments": "{}"}},
]},
], "timestamp": time.time() - 1},
{
"role": "tool",
"tool_call_id": "c1",
@ -453,10 +514,15 @@ class TestResumePendingSystemNote:
assert "tool result" in result
def test_stale_tool_tail_does_not_inject_auto_continue_note(self):
"""The core bug fix: stale tool-tail must not revive a dead task.
Uses window_secs=1800 (30 min) to verify the gate fires at 1h
keeps the test stable regardless of the production default.
"""
history = [
{"role": "assistant", "content": None, "tool_calls": [
{"id": "c1", "function": {"name": "x", "arguments": "{}"}},
]},
], "timestamp": time.time() - 3601},
{
"role": "tool",
"tool_call_id": "c1",
@ -464,18 +530,210 @@ class TestResumePendingSystemNote:
"timestamp": time.time() - 3600,
},
]
result = _simulate_note_injection(history, "start a new task", resume_entry=None)
result = _simulate_note_injection(
history,
"start a new task",
resume_entry=None,
window_secs=1800,
)
assert result == "start a new task"
def test_stale_tool_tail_with_production_data_shape(self):
"""Regression guard for #16802: exercise the REAL production path
where ``agent_history`` has been stripped of timestamps.
The original PR #16802 fix read ``agent_history[-1].get("timestamp")``
which is always ``None`` at runtime because the gateway strips
``timestamp`` off tool/tool_call rows in ``history agent_history``.
This test builds a stale history, runs it through the real
``_build_agent_history`` conversion, then asserts:
1. The stripped ``agent_history`` carries NO timestamp (protects
against someone "fixing" the original PR by re-adding the
stripped field which would break the API contract).
2. The freshness gate still correctly classifies the transcript
as stale because the signal is read from ``history`` BEFORE
the strip.
3. No auto-continue note is injected.
"""
history = [
{"role": "assistant", "content": None, "tool_calls": [
{"id": "c1", "function": {"name": "x", "arguments": "{}"}},
], "timestamp": time.time() - 7201},
{
"role": "tool",
"tool_call_id": "c1",
"content": "stale result",
"timestamp": time.time() - 7200, # 2 hours old
},
]
agent_history = _build_agent_history(history)
# Invariant 1: strip contract preserved
assert agent_history[-1]["role"] == "tool"
assert "timestamp" not in agent_history[-1], (
"agent_history tool rows must NOT carry a timestamp — the "
"freshness gate must read from raw history, not agent_history"
)
# Invariant 2+3: stale classification, no note injection
result = _simulate_note_injection(
history,
"start a new task",
resume_entry=None,
agent_history=agent_history,
)
assert result == "start a new task"
def test_freshness_gate_disabled_via_zero_window(self):
"""window_secs=0 restores pre-fix behaviour (always inject)."""
history = [
{"role": "assistant", "content": None, "tool_calls": [
{"id": "c1", "function": {"name": "x", "arguments": "{}"}},
], "timestamp": time.time() - 86400},
{
"role": "tool",
"tool_call_id": "c1",
"content": "day-old result",
"timestamp": time.time() - 86400, # 24 hours old
},
]
result = _simulate_note_injection(
history, "ping", resume_entry=None, window_secs=0,
)
assert "[System note:" in result
assert "tool result" in result
def test_legacy_history_without_timestamps_still_injects(self):
"""Transcripts predating timestamp persistence must keep the old
behaviour freshness unknown treat as fresh."""
history = [
{"role": "assistant", "content": None, "tool_calls": [
{"id": "c1", "function": {"name": "x", "arguments": "{}"}},
]},
{"role": "tool", "tool_call_id": "c1", "content": "result"},
]
result = _simulate_note_injection(history, "ping", resume_entry=None)
assert "[System note:" in result
assert "tool result" in result
def test_no_note_when_nothing_to_resume(self):
history = [
{"role": "user", "content": "hello"},
{"role": "assistant", "content": "hi"},
{"role": "user", "content": "hello", "timestamp": time.time() - 2},
{"role": "assistant", "content": "hi", "timestamp": time.time() - 1},
]
result = _simulate_note_injection(history, "ping", resume_entry=None)
assert result == "ping"
# ---------------------------------------------------------------------------
# Freshness helpers
# ---------------------------------------------------------------------------
class TestFreshnessHelpers:
def test_coerce_datetime(self):
now = datetime.now()
assert _coerce_gateway_timestamp(now) == pytest.approx(now.timestamp(), abs=1e-3)
def test_coerce_epoch_seconds(self):
assert _coerce_gateway_timestamp(1_700_000_000) == 1_700_000_000.0
assert _coerce_gateway_timestamp(1_700_000_000.5) == 1_700_000_000.5
def test_coerce_epoch_milliseconds(self):
# Values > 10^10 treated as ms
assert _coerce_gateway_timestamp(1_700_000_000_000) == 1_700_000_000.0
def test_coerce_iso_string(self):
iso = "2026-04-18T12:00:00+00:00"
expected = datetime.fromisoformat(iso).timestamp()
assert _coerce_gateway_timestamp(iso) == pytest.approx(expected, abs=1e-3)
def test_coerce_iso_string_with_z_suffix(self):
iso_z = "2026-04-18T12:00:00Z"
expected = datetime.fromisoformat("2026-04-18T12:00:00+00:00").timestamp()
assert _coerce_gateway_timestamp(iso_z) == pytest.approx(expected, abs=1e-3)
def test_coerce_numeric_string(self):
assert _coerce_gateway_timestamp("1700000000") == 1_700_000_000.0
def test_coerce_rejects_garbage(self):
assert _coerce_gateway_timestamp(None) is None
assert _coerce_gateway_timestamp("") is None
assert _coerce_gateway_timestamp("not-a-timestamp") is None
assert _coerce_gateway_timestamp(True) is None # bool rejected
assert _coerce_gateway_timestamp(False) is None
assert _coerce_gateway_timestamp([1, 2, 3]) is None
def test_is_fresh_unknown_is_fresh(self):
"""Legacy-compat: unknown timestamp → fresh."""
assert _is_fresh_gateway_interruption(None) is True
assert _is_fresh_gateway_interruption("not-a-timestamp") is True
def test_is_fresh_window_bounds(self):
now = 1_700_000_000.0
# 1h window, 30min old → fresh
assert _is_fresh_gateway_interruption(
now - 1800, now=now, window_secs=3600,
) is True
# 1h window, 2h old → stale
assert _is_fresh_gateway_interruption(
now - 7200, now=now, window_secs=3600,
) is False
# 1h window, exactly at boundary → fresh (<=)
assert _is_fresh_gateway_interruption(
now - 3600, now=now, window_secs=3600,
) is True
def test_is_fresh_zero_window_always_fresh(self):
"""Opt-out: window_secs=0 disables the gate entirely."""
assert _is_fresh_gateway_interruption(
0.0, now=1_700_000_000.0, window_secs=0,
) is True
assert _is_fresh_gateway_interruption(
-1.0, now=1_700_000_000.0, window_secs=-5,
) is True
def test_last_transcript_timestamp_skips_meta(self):
history = [
{"role": "user", "content": "hi", "timestamp": 100.0},
{"role": "assistant", "content": "hey", "timestamp": 200.0},
{"role": "session_meta", "content": "tools:{}", "timestamp": 999.0},
{"role": "system", "content": "ignore", "timestamp": 999.0},
]
assert _last_transcript_timestamp(history) == 200.0
def test_last_transcript_timestamp_empty(self):
assert _last_transcript_timestamp([]) is None
assert _last_transcript_timestamp(None) is None
def test_last_transcript_timestamp_row_without_timestamp(self):
"""Legacy transcript row (no timestamp) returns None → caller
treats as fresh."""
history = [
{"role": "user", "content": "hi"},
{"role": "assistant", "content": "hey"},
]
assert _last_transcript_timestamp(history) is None
def test_auto_continue_freshness_window_reads_env(self, monkeypatch):
monkeypatch.setenv("HERMES_AUTO_CONTINUE_FRESHNESS", "7200")
assert _auto_continue_freshness_window() == 7200.0
def test_auto_continue_freshness_window_default_when_unset(self, monkeypatch):
monkeypatch.delenv("HERMES_AUTO_CONTINUE_FRESHNESS", raising=False)
# Default is 1 hour
assert _auto_continue_freshness_window() == 3600.0
def test_auto_continue_freshness_window_malformed_falls_back(self, monkeypatch):
monkeypatch.setenv("HERMES_AUTO_CONTINUE_FRESHNESS", "not-a-number")
assert _auto_continue_freshness_window() == 3600.0
def test_auto_continue_freshness_window_empty_falls_back(self, monkeypatch):
monkeypatch.setenv("HERMES_AUTO_CONTINUE_FRESHNESS", "")
assert _auto_continue_freshness_window() == 3600.0
# ---------------------------------------------------------------------------
# Drain-timeout path marks sessions resume_pending
# ---------------------------------------------------------------------------