mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-06-23 10:42:00 +00:00
ff85af3fc7
* feat(goals): add /goal wait <pid> barrier to park the loop on a background process
The /goal loop re-pokes the agent every turn via the post-turn judge. When a
goal is gated on a long-running background process (CI poller, build, test
matrix, deploy) that produces nothing to judge yet, this spins the agent into
'is it done?' busy-work and burns the turn budget.
/goal wait <pid> [reason] parks the loop: while the PID is alive, the judge is
skipped, no turn is consumed, no continuation fires, and /goal status shows a
parked indicator. The barrier auto-clears the moment the process exits (the
agent's notify_on_complete watcher is the natural wake signal), then the next
turn resumes normal judging. /goal unwait clears it manually; pause/resume/clear
drop it; a dead/stale PID can never wedge the loop.
Wired across CLI, gateway, and the mid-run command guard for parity. Barrier
persists in SessionDB.state_meta (survives /resume); GoalState gains
backward-compatible waiting_on_pid/waiting_reason/waiting_since fields. 12 new
tests; docs updated.
* fix(goals): use gateway.status._pid_exists for liveness, not os.kill(pid,0)
The Windows-footguns CI guard flagged os.kill(pid, 0) in _pid_alive — on
Windows that's not a no-op, it routes to CTRL_C_EVENT and hard-kills the
target's console process group (bpo-14484). Delegate to the canonical
footgun-safe gateway.status._pid_exists (psutil + ctypes/POSIX fallback)
instead, with a direct-psutil last resort.
* feat(goals): judge-driven auto-wait — the loop parks itself, no manual /goal wait
Makes the wait barrier automatic. Every turn the judge is shown the agent's
live background processes (pid, command, uptime, output tail from the
process_registry) alongside the goal + response, and can return a new 'wait'
verdict instead of continue:
{"verdict":"wait","wait_on_pid":N} → park until that process exits
{"verdict":"wait","wait_for_seconds":N} → park until the deadline passes
evaluate_after_turn acts on the directive (sets the barrier, parks the loop)
so the agent isn't re-poked into busy-work while CI/builds/deploys run. Adds a
time-based waiting_until barrier alongside the pid barrier; both auto-clear and
can never wedge the loop. Drivers (CLI, gateway, tui_gateway) feed the live
registry in via gather_background_processes(). Manual /goal wait stays as an
override. Judge verdict contract widened to (verdict, reason, parse_failed,
wait_directive); legacy {"done":bool} shape still accepted.
* test(goals): update kanban _fake_judge to the 4-tuple judge contract
CI test(3) caught it: test_kanban_goal_mode's _fake_judge still returned the
3-tuple (verdict, reason, parse_failed), but the kanban loop now unpacks the
4-tuple (+ wait_directive). Update the fake to return None for the directive
and accept the background_processes kwarg.
* feat(goals): trigger-based wait — park on a process's own signal, not just exit
Addresses two gaps in the judge-driven wait: (1) the judge could only express
'wait until PID exits' or 'wait N seconds', so a long-lived watcher/server that
fires a trigger MID-RUN (and may never exit) couldn't be waited on; (2) the
process's own watch_patterns/notify_on_complete trigger was invisible to the judge.
Adds a session-based barrier (waiting_on_session) that releases on the process's
OWN trigger via process_registry.is_session_waiting(): the session exits, OR (if
started with watch_patterns) its pattern matches — even while the process keeps
running. list_sessions() now surfaces session_id + watch_patterns/watch_hit/
notify_on_complete so the judge sees the trigger and is told to prefer
wait_on_session for trigger processes. Judge verdict gains a {wait_on_session}
directive (preferred over pid). Backward-compatible GoalState field; pid + time
barriers unchanged.
Tests: TestSessionTriggerBarrier (release on mid-run pattern match while alive,
release on exit, unknown-session, full park→trigger→resume, parse, validation,
backcompat load). 105 goal-surface + 85 process_registry tests green.
1221 lines
50 KiB
Python
1221 lines
50 KiB
Python
"""Tests for hermes_cli/goals.py — persistent cross-turn goals."""
|
|
|
|
from __future__ import annotations
|
|
|
|
import json
|
|
import time
|
|
from unittest.mock import patch, MagicMock
|
|
|
|
import pytest
|
|
|
|
|
|
# ──────────────────────────────────────────────────────────────────────
|
|
# Fixtures
|
|
# ──────────────────────────────────────────────────────────────────────
|
|
|
|
|
|
@pytest.fixture
|
|
def hermes_home(tmp_path, monkeypatch):
|
|
"""Isolated HERMES_HOME so SessionDB.state_meta writes don't clobber the real one."""
|
|
from pathlib import Path
|
|
|
|
home = tmp_path / ".hermes"
|
|
home.mkdir()
|
|
monkeypatch.setattr(Path, "home", lambda: tmp_path)
|
|
monkeypatch.setenv("HERMES_HOME", str(home))
|
|
|
|
# Bust the goal-module's DB cache for each test so it re-resolves HERMES_HOME.
|
|
from hermes_cli import goals
|
|
|
|
goals._DB_CACHE.clear()
|
|
yield home
|
|
goals._DB_CACHE.clear()
|
|
|
|
|
|
# ──────────────────────────────────────────────────────────────────────
|
|
# _parse_judge_response
|
|
# ──────────────────────────────────────────────────────────────────────
|
|
|
|
|
|
class TestParseJudgeResponse:
|
|
def test_clean_json_done(self):
|
|
from hermes_cli.goals import _parse_judge_response
|
|
|
|
verdict, reason, _pf, wait = _parse_judge_response('{"done": true, "reason": "all good"}')
|
|
assert verdict == "done"
|
|
assert reason == "all good"
|
|
assert wait is None
|
|
|
|
def test_clean_json_continue(self):
|
|
from hermes_cli.goals import _parse_judge_response
|
|
|
|
verdict, reason, _pf, wait = _parse_judge_response('{"done": false, "reason": "more work needed"}')
|
|
assert verdict == "continue"
|
|
assert reason == "more work needed"
|
|
assert wait is None
|
|
|
|
def test_json_in_markdown_fence(self):
|
|
from hermes_cli.goals import _parse_judge_response
|
|
|
|
raw = '```json\n{"done": true, "reason": "done"}\n```'
|
|
verdict, reason, _pf, _w = _parse_judge_response(raw)
|
|
assert verdict == "done"
|
|
assert "done" in reason
|
|
|
|
def test_json_embedded_in_prose(self):
|
|
"""Some models prefix reasoning before emitting JSON — we extract it."""
|
|
from hermes_cli.goals import _parse_judge_response
|
|
|
|
raw = 'Looking at this... the agent says X. Verdict: {"done": false, "reason": "partial"}'
|
|
verdict, reason, _pf, _w = _parse_judge_response(raw)
|
|
assert verdict == "continue"
|
|
assert reason == "partial"
|
|
|
|
def test_string_done_values(self):
|
|
from hermes_cli.goals import _parse_judge_response
|
|
|
|
for s in ("true", "yes", "done", "1"):
|
|
verdict, _, _, _ = _parse_judge_response(f'{{"done": "{s}", "reason": "r"}}')
|
|
assert verdict == "done"
|
|
for s in ("false", "no", "not yet"):
|
|
verdict, _, _, _ = _parse_judge_response(f'{{"done": "{s}", "reason": "r"}}')
|
|
assert verdict == "continue"
|
|
|
|
def test_new_verdict_shape(self):
|
|
"""The explicit {"verdict": ...} shape is honored."""
|
|
from hermes_cli.goals import _parse_judge_response
|
|
|
|
v, _, _, _ = _parse_judge_response('{"verdict": "done", "reason": "r"}')
|
|
assert v == "done"
|
|
v, _, _, _ = _parse_judge_response('{"verdict": "continue", "reason": "r"}')
|
|
assert v == "continue"
|
|
|
|
def test_wait_verdict_with_pid(self):
|
|
from hermes_cli.goals import _parse_judge_response
|
|
|
|
v, reason, pf, wait = _parse_judge_response(
|
|
'{"verdict": "wait", "wait_on_pid": 4242, "reason": "CI running"}'
|
|
)
|
|
assert v == "wait"
|
|
assert pf is False
|
|
assert wait == {"pid": 4242}
|
|
assert reason == "CI running"
|
|
|
|
def test_wait_verdict_with_seconds(self):
|
|
from hermes_cli.goals import _parse_judge_response
|
|
|
|
v, _, _, wait = _parse_judge_response(
|
|
'{"verdict": "wait", "wait_for_seconds": 90, "reason": "rate limited"}'
|
|
)
|
|
assert v == "wait"
|
|
assert wait == {"seconds": 90}
|
|
|
|
def test_wait_verdict_without_target_downgrades_to_continue(self):
|
|
"""A wait verdict with no pid/seconds can't park on anything → continue."""
|
|
from hermes_cli.goals import _parse_judge_response
|
|
|
|
v, _, pf, wait = _parse_judge_response('{"verdict": "wait", "reason": "vague"}')
|
|
assert v == "continue"
|
|
assert wait is None
|
|
assert pf is False
|
|
|
|
def test_unknown_verdict_falls_back_to_continue(self):
|
|
from hermes_cli.goals import _parse_judge_response
|
|
|
|
v, _, _, _ = _parse_judge_response('{"verdict": "maybe", "reason": "r"}')
|
|
assert v == "continue"
|
|
|
|
def test_malformed_json_fails_open(self):
|
|
"""Non-JSON → continue + parse_failed, with error-ish reason."""
|
|
from hermes_cli.goals import _parse_judge_response
|
|
|
|
verdict, reason, parse_failed, _w = _parse_judge_response("this is not json at all")
|
|
assert verdict == "continue"
|
|
assert parse_failed is True
|
|
assert reason # non-empty
|
|
|
|
def test_empty_response(self):
|
|
from hermes_cli.goals import _parse_judge_response
|
|
|
|
verdict, reason, parse_failed, _w = _parse_judge_response("")
|
|
assert verdict == "continue"
|
|
assert parse_failed is True
|
|
assert reason
|
|
|
|
|
|
# ──────────────────────────────────────────────────────────────────────
|
|
# judge_goal — fail-open semantics
|
|
# ──────────────────────────────────────────────────────────────────────
|
|
|
|
|
|
class TestJudgeGoal:
|
|
def test_empty_goal_skipped(self):
|
|
from hermes_cli.goals import judge_goal
|
|
|
|
verdict, _, _, _wd = judge_goal("", "some response")
|
|
assert verdict == "skipped"
|
|
|
|
def test_empty_response_continues(self):
|
|
from hermes_cli.goals import judge_goal
|
|
|
|
verdict, _, _, _wd = judge_goal("ship the thing", "")
|
|
assert verdict == "continue"
|
|
|
|
def test_no_aux_client_continues(self):
|
|
"""Fail-open: if no aux client, we must return continue, not skipped/done."""
|
|
from hermes_cli import goals
|
|
|
|
with patch(
|
|
"agent.auxiliary_client.get_text_auxiliary_client",
|
|
return_value=(None, None),
|
|
):
|
|
verdict, _, _, _wd = goals.judge_goal("my goal", "my response")
|
|
assert verdict == "continue"
|
|
|
|
def test_api_error_continues(self):
|
|
"""Judge exception → fail-open continue (don't wedge progress on judge bugs)."""
|
|
from hermes_cli import goals
|
|
|
|
fake_client = MagicMock()
|
|
fake_client.chat.completions.create.side_effect = RuntimeError("boom")
|
|
with patch(
|
|
"agent.auxiliary_client.get_text_auxiliary_client",
|
|
return_value=(fake_client, "judge-model"),
|
|
):
|
|
verdict, reason, _, _wd = goals.judge_goal("goal", "response")
|
|
assert verdict == "continue"
|
|
assert "judge error" in reason.lower()
|
|
|
|
def test_judge_says_done(self):
|
|
from hermes_cli import goals
|
|
|
|
fake_client = MagicMock()
|
|
fake_client.chat.completions.create.return_value = MagicMock(
|
|
choices=[
|
|
MagicMock(
|
|
message=MagicMock(content='{"done": true, "reason": "achieved"}')
|
|
)
|
|
]
|
|
)
|
|
with patch(
|
|
"agent.auxiliary_client.get_text_auxiliary_client",
|
|
return_value=(fake_client, "judge-model"),
|
|
):
|
|
verdict, reason, _, _wd = goals.judge_goal("goal", "agent response")
|
|
assert verdict == "done"
|
|
assert reason == "achieved"
|
|
|
|
def test_judge_says_continue(self):
|
|
from hermes_cli import goals
|
|
|
|
fake_client = MagicMock()
|
|
fake_client.chat.completions.create.return_value = MagicMock(
|
|
choices=[
|
|
MagicMock(
|
|
message=MagicMock(content='{"done": false, "reason": "not yet"}')
|
|
)
|
|
]
|
|
)
|
|
with patch(
|
|
"agent.auxiliary_client.get_text_auxiliary_client",
|
|
return_value=(fake_client, "judge-model"),
|
|
):
|
|
verdict, reason, _, _wd = goals.judge_goal("goal", "agent response")
|
|
assert verdict == "continue"
|
|
assert reason == "not yet"
|
|
|
|
|
|
# ──────────────────────────────────────────────────────────────────────
|
|
# GoalManager lifecycle + persistence
|
|
# ──────────────────────────────────────────────────────────────────────
|
|
|
|
|
|
class TestGoalManager:
|
|
def test_no_goal_initial(self, hermes_home):
|
|
from hermes_cli.goals import GoalManager
|
|
|
|
mgr = GoalManager(session_id="test-sid-1")
|
|
assert mgr.state is None
|
|
assert not mgr.is_active()
|
|
assert not mgr.has_goal()
|
|
assert "No active goal" in mgr.status_line()
|
|
|
|
def test_set_then_status(self, hermes_home):
|
|
from hermes_cli.goals import GoalManager
|
|
|
|
mgr = GoalManager(session_id="test-sid-2", default_max_turns=5)
|
|
state = mgr.set("port the thing")
|
|
assert state.goal == "port the thing"
|
|
assert state.status == "active"
|
|
assert state.max_turns == 5
|
|
assert state.turns_used == 0
|
|
assert mgr.is_active()
|
|
assert "active" in mgr.status_line().lower()
|
|
assert "port the thing" in mgr.status_line()
|
|
|
|
def test_set_rejects_empty(self, hermes_home):
|
|
from hermes_cli.goals import GoalManager
|
|
|
|
mgr = GoalManager(session_id="test-sid-3")
|
|
with pytest.raises(ValueError):
|
|
mgr.set("")
|
|
with pytest.raises(ValueError):
|
|
mgr.set(" ")
|
|
|
|
def test_pause_and_resume(self, hermes_home):
|
|
from hermes_cli.goals import GoalManager
|
|
|
|
mgr = GoalManager(session_id="test-sid-4")
|
|
mgr.set("goal text")
|
|
mgr.pause(reason="user-paused")
|
|
assert mgr.state.status == "paused"
|
|
assert not mgr.is_active()
|
|
assert mgr.has_goal()
|
|
|
|
mgr.resume()
|
|
assert mgr.state.status == "active"
|
|
assert mgr.is_active()
|
|
|
|
def test_clear(self, hermes_home):
|
|
from hermes_cli.goals import GoalManager
|
|
|
|
mgr = GoalManager(session_id="test-sid-5")
|
|
mgr.set("goal")
|
|
mgr.clear()
|
|
assert mgr.state is None
|
|
assert not mgr.is_active()
|
|
|
|
def test_persistence_across_managers(self, hermes_home):
|
|
"""Key invariant: a second manager on the same session sees the goal.
|
|
|
|
This is what makes /resume work — each session rebinds its
|
|
GoalManager and picks up the saved state.
|
|
"""
|
|
from hermes_cli.goals import GoalManager
|
|
|
|
mgr1 = GoalManager(session_id="persist-sid")
|
|
mgr1.set("do the thing")
|
|
|
|
mgr2 = GoalManager(session_id="persist-sid")
|
|
assert mgr2.state is not None
|
|
assert mgr2.state.goal == "do the thing"
|
|
assert mgr2.is_active()
|
|
|
|
def test_evaluate_after_turn_done(self, hermes_home):
|
|
"""Judge says done → status=done, no continuation."""
|
|
from hermes_cli import goals
|
|
from hermes_cli.goals import GoalManager
|
|
|
|
mgr = GoalManager(session_id="eval-sid-1")
|
|
mgr.set("ship it")
|
|
|
|
with patch.object(goals, "judge_goal", return_value=("done", "shipped", False, None)):
|
|
decision = mgr.evaluate_after_turn("I shipped the feature.")
|
|
|
|
assert decision["verdict"] == "done"
|
|
assert decision["should_continue"] is False
|
|
assert decision["continuation_prompt"] is None
|
|
assert mgr.state.status == "done"
|
|
assert mgr.state.turns_used == 1
|
|
|
|
def test_evaluate_after_turn_continue_under_budget(self, hermes_home):
|
|
from hermes_cli import goals
|
|
from hermes_cli.goals import GoalManager
|
|
|
|
mgr = GoalManager(session_id="eval-sid-2", default_max_turns=5)
|
|
mgr.set("a long goal")
|
|
|
|
with patch.object(goals, "judge_goal", return_value=("continue", "more work", False, None)):
|
|
decision = mgr.evaluate_after_turn("made some progress")
|
|
|
|
assert decision["verdict"] == "continue"
|
|
assert decision["should_continue"] is True
|
|
assert decision["continuation_prompt"] is not None
|
|
assert "a long goal" in decision["continuation_prompt"]
|
|
assert mgr.state.status == "active"
|
|
assert mgr.state.turns_used == 1
|
|
|
|
def test_evaluate_after_turn_budget_exhausted(self, hermes_home):
|
|
"""When turn budget hits ceiling, auto-pause instead of continuing."""
|
|
from hermes_cli import goals
|
|
from hermes_cli.goals import GoalManager
|
|
|
|
mgr = GoalManager(session_id="eval-sid-3", default_max_turns=2)
|
|
mgr.set("hard goal")
|
|
|
|
with patch.object(goals, "judge_goal", return_value=("continue", "not yet", False, None)):
|
|
d1 = mgr.evaluate_after_turn("step 1")
|
|
assert d1["should_continue"] is True
|
|
assert mgr.state.turns_used == 1
|
|
assert mgr.state.status == "active"
|
|
|
|
d2 = mgr.evaluate_after_turn("step 2")
|
|
# turns_used is now 2 which equals max_turns → paused
|
|
assert d2["should_continue"] is False
|
|
assert mgr.state.status == "paused"
|
|
assert mgr.state.turns_used == 2
|
|
assert "budget" in (mgr.state.paused_reason or "").lower()
|
|
|
|
def test_evaluate_after_turn_inactive(self, hermes_home):
|
|
"""evaluate_after_turn is a no-op when goal isn't active."""
|
|
from hermes_cli.goals import GoalManager
|
|
|
|
mgr = GoalManager(session_id="eval-sid-4")
|
|
d = mgr.evaluate_after_turn("anything")
|
|
assert d["verdict"] == "inactive"
|
|
assert d["should_continue"] is False
|
|
|
|
mgr.set("a goal")
|
|
mgr.pause()
|
|
d2 = mgr.evaluate_after_turn("anything")
|
|
assert d2["verdict"] == "inactive"
|
|
assert d2["should_continue"] is False
|
|
|
|
def test_continuation_prompt_shape(self, hermes_home):
|
|
"""The continuation prompt must include the goal text verbatim —
|
|
and must be safe to inject as a user-role message (prompt-cache
|
|
invariants: no system-prompt mutation)."""
|
|
from hermes_cli.goals import GoalManager
|
|
|
|
mgr = GoalManager(session_id="cont-sid")
|
|
mgr.set("port goal command to hermes")
|
|
prompt = mgr.next_continuation_prompt()
|
|
assert prompt is not None
|
|
assert "port goal command to hermes" in prompt
|
|
assert prompt.strip() # non-empty
|
|
|
|
|
|
# ──────────────────────────────────────────────────────────────────────
|
|
# Smoke: CommandDef is wired
|
|
# ──────────────────────────────────────────────────────────────────────
|
|
|
|
|
|
def test_goal_command_in_registry():
|
|
from hermes_cli.commands import resolve_command
|
|
|
|
cmd = resolve_command("goal")
|
|
assert cmd is not None
|
|
assert cmd.name == "goal"
|
|
|
|
|
|
def test_goal_command_dispatches_in_cli_registry_helpers():
|
|
"""goal shows up in autocomplete / help categories alongside other Session cmds."""
|
|
from hermes_cli.commands import COMMANDS, COMMANDS_BY_CATEGORY
|
|
|
|
assert "/goal" in COMMANDS
|
|
session_cmds = COMMANDS_BY_CATEGORY.get("Session", {})
|
|
assert "/goal" in session_cmds
|
|
|
|
|
|
# ──────────────────────────────────────────────────────────────────────
|
|
# Auto-pause on consecutive judge parse failures
|
|
# ──────────────────────────────────────────────────────────────────────
|
|
|
|
|
|
class TestJudgeParseFailureAutoPause:
|
|
"""Regression: weak judge models (e.g. deepseek-v4-flash) that return
|
|
empty strings or non-JSON prose must auto-pause the loop after N turns
|
|
instead of burning the whole turn budget."""
|
|
|
|
def test_parse_response_flags_empty_as_parse_failure(self):
|
|
from hermes_cli.goals import _parse_judge_response
|
|
|
|
verdict, reason, parse_failed, _w = _parse_judge_response("")
|
|
assert verdict == "continue"
|
|
assert parse_failed is True
|
|
assert "empty" in reason.lower()
|
|
|
|
def test_parse_response_flags_non_json_as_parse_failure(self):
|
|
from hermes_cli.goals import _parse_judge_response
|
|
|
|
verdict, reason, parse_failed, _w = _parse_judge_response(
|
|
"Let me analyze whether the goal is fully satisfied based on the agent's response..."
|
|
)
|
|
assert verdict == "continue"
|
|
assert parse_failed is True
|
|
assert "not json" in reason.lower()
|
|
|
|
def test_parse_response_clean_json_is_not_parse_failure(self):
|
|
from hermes_cli.goals import _parse_judge_response
|
|
|
|
verdict, _, parse_failed, _w = _parse_judge_response(
|
|
'{"done": false, "reason": "more work"}'
|
|
)
|
|
assert verdict == "continue"
|
|
assert parse_failed is False
|
|
|
|
def test_api_error_does_not_count_as_parse_failure(self):
|
|
"""Transient network/API errors must not trip the auto-pause guard."""
|
|
from hermes_cli import goals
|
|
|
|
fake_client = MagicMock()
|
|
fake_client.chat.completions.create.side_effect = RuntimeError("connection reset")
|
|
with patch(
|
|
"agent.auxiliary_client.get_text_auxiliary_client",
|
|
return_value=(fake_client, "judge-model"),
|
|
):
|
|
verdict, _, parse_failed, _wd = goals.judge_goal("goal", "response")
|
|
assert verdict == "continue"
|
|
assert parse_failed is False
|
|
|
|
def test_empty_judge_reply_flagged_as_parse_failure(self):
|
|
"""End-to-end: judge returns empty content → parse_failed=True."""
|
|
from hermes_cli import goals
|
|
|
|
fake_client = MagicMock()
|
|
fake_client.chat.completions.create.return_value = MagicMock(
|
|
choices=[MagicMock(message=MagicMock(content=""))]
|
|
)
|
|
with patch(
|
|
"agent.auxiliary_client.get_text_auxiliary_client",
|
|
return_value=(fake_client, "judge-model"),
|
|
):
|
|
verdict, _, parse_failed, _wd = goals.judge_goal("goal", "response")
|
|
assert verdict == "continue"
|
|
assert parse_failed is True
|
|
|
|
def test_auto_pause_after_three_consecutive_parse_failures(self, hermes_home):
|
|
"""N=3 consecutive parse failures → auto-pause with config pointer."""
|
|
from hermes_cli import goals
|
|
from hermes_cli.goals import GoalManager, DEFAULT_MAX_CONSECUTIVE_PARSE_FAILURES
|
|
|
|
assert DEFAULT_MAX_CONSECUTIVE_PARSE_FAILURES == 3
|
|
mgr = GoalManager(session_id="parse-fail-sid-1", default_max_turns=20)
|
|
mgr.set("do a thing")
|
|
|
|
with patch.object(
|
|
goals, "judge_goal", return_value=("continue", "judge returned empty response", True, None)
|
|
):
|
|
d1 = mgr.evaluate_after_turn("step 1")
|
|
assert d1["should_continue"] is True
|
|
assert mgr.state.consecutive_parse_failures == 1
|
|
|
|
d2 = mgr.evaluate_after_turn("step 2")
|
|
assert d2["should_continue"] is True
|
|
assert mgr.state.consecutive_parse_failures == 2
|
|
|
|
d3 = mgr.evaluate_after_turn("step 3")
|
|
assert d3["should_continue"] is False
|
|
assert d3["status"] == "paused"
|
|
assert mgr.state.consecutive_parse_failures == 3
|
|
# Message points at the config surface so the user can fix it.
|
|
assert "auxiliary" in d3["message"]
|
|
assert "goal_judge" in d3["message"]
|
|
assert "config.yaml" in d3["message"]
|
|
|
|
def test_parse_failure_counter_resets_on_good_reply(self, hermes_home):
|
|
"""A single good judge reply resets the counter — transient flakes don't pause."""
|
|
from hermes_cli import goals
|
|
from hermes_cli.goals import GoalManager
|
|
|
|
mgr = GoalManager(session_id="parse-fail-sid-2", default_max_turns=20)
|
|
mgr.set("another goal")
|
|
|
|
# Two parse failures…
|
|
with patch.object(
|
|
goals, "judge_goal", return_value=("continue", "not json", True, None)
|
|
):
|
|
mgr.evaluate_after_turn("step 1")
|
|
mgr.evaluate_after_turn("step 2")
|
|
assert mgr.state.consecutive_parse_failures == 2
|
|
|
|
# …then one clean reply resets the counter.
|
|
with patch.object(
|
|
goals, "judge_goal", return_value=("continue", "making progress", False, None)
|
|
):
|
|
d = mgr.evaluate_after_turn("step 3")
|
|
assert d["should_continue"] is True
|
|
assert mgr.state.consecutive_parse_failures == 0
|
|
|
|
def test_parse_failure_counter_not_incremented_by_api_errors(self, hermes_home):
|
|
"""API/transport errors must NOT count toward the auto-pause threshold."""
|
|
from hermes_cli import goals
|
|
from hermes_cli.goals import GoalManager
|
|
|
|
mgr = GoalManager(session_id="parse-fail-sid-3", default_max_turns=20)
|
|
mgr.set("goal")
|
|
|
|
with patch.object(
|
|
goals, "judge_goal", return_value=("continue", "judge error: RuntimeError", False, None)
|
|
):
|
|
for _ in range(5):
|
|
d = mgr.evaluate_after_turn("still going")
|
|
assert d["should_continue"] is True
|
|
assert mgr.state.consecutive_parse_failures == 0
|
|
assert mgr.state.status == "active"
|
|
|
|
def test_consecutive_parse_failures_persists_across_goalmanager_reloads(
|
|
self, hermes_home
|
|
):
|
|
"""The counter must be durable so cross-session resumes see it."""
|
|
from hermes_cli import goals
|
|
from hermes_cli.goals import GoalManager, load_goal
|
|
|
|
mgr = GoalManager(session_id="parse-fail-sid-4", default_max_turns=20)
|
|
mgr.set("persistent goal")
|
|
|
|
with patch.object(
|
|
goals, "judge_goal", return_value=("continue", "empty", True, None)
|
|
):
|
|
mgr.evaluate_after_turn("r")
|
|
mgr.evaluate_after_turn("r")
|
|
|
|
reloaded = load_goal("parse-fail-sid-4")
|
|
assert reloaded is not None
|
|
assert reloaded.consecutive_parse_failures == 2
|
|
|
|
|
|
# ──────────────────────────────────────────────────────────────────────
|
|
# /subgoal — user-added criteria
|
|
# ──────────────────────────────────────────────────────────────────────
|
|
|
|
|
|
class TestGoalStateSubgoalsBackcompat:
|
|
def test_old_state_meta_row_loads_without_subgoals(self):
|
|
"""A goal serialized BEFORE the subgoals field existed must
|
|
round-trip with an empty list, not crash."""
|
|
from hermes_cli.goals import GoalState
|
|
|
|
legacy = json.dumps({
|
|
"goal": "do a thing",
|
|
"status": "active",
|
|
"turns_used": 2,
|
|
"max_turns": 20,
|
|
"created_at": 1.0,
|
|
"last_turn_at": 2.0,
|
|
"consecutive_parse_failures": 0,
|
|
})
|
|
state = GoalState.from_json(legacy)
|
|
assert state.goal == "do a thing"
|
|
assert state.subgoals == []
|
|
|
|
def test_subgoals_round_trip(self):
|
|
from hermes_cli.goals import GoalState
|
|
state = GoalState(goal="g", subgoals=["a", "b", "c"])
|
|
rt = GoalState.from_json(state.to_json())
|
|
assert rt.subgoals == ["a", "b", "c"]
|
|
|
|
|
|
class TestMigrateGoalToSession:
|
|
"""migrate_goal_to_session carries a /goal from a parent session to its
|
|
compression continuation child (#33618). load_goal does a flat
|
|
per-session lookup with no lineage walk, so without migration an active
|
|
goal silently dies when compression rotates session_id."""
|
|
|
|
def test_migrates_active_goal_to_child(self, hermes_home):
|
|
from hermes_cli.goals import save_goal, load_goal, migrate_goal_to_session, GoalState
|
|
save_goal("parent-sid", GoalState(goal="ship the feature"))
|
|
assert migrate_goal_to_session("parent-sid", "child-sid", reason="compression") is True
|
|
child = load_goal("child-sid")
|
|
assert child is not None and child.goal == "ship the feature"
|
|
# Parent row archived (cleared) so only the child is active.
|
|
parent = load_goal("parent-sid")
|
|
assert parent is not None and parent.status == "cleared"
|
|
|
|
def test_no_goal_to_migrate_returns_false(self, hermes_home):
|
|
from hermes_cli.goals import migrate_goal_to_session, load_goal
|
|
assert migrate_goal_to_session("empty-parent", "child2") is False
|
|
assert load_goal("child2") is None
|
|
|
|
def test_does_not_clobber_existing_child_goal(self, hermes_home):
|
|
from hermes_cli.goals import save_goal, load_goal, migrate_goal_to_session, GoalState
|
|
save_goal("p3", GoalState(goal="parent goal"))
|
|
save_goal("c3", GoalState(goal="child already has one"))
|
|
assert migrate_goal_to_session("p3", "c3") is False
|
|
assert load_goal("c3").goal == "child already has one"
|
|
|
|
def test_same_id_is_noop(self, hermes_home):
|
|
from hermes_cli.goals import save_goal, migrate_goal_to_session, GoalState
|
|
save_goal("same", GoalState(goal="g"))
|
|
assert migrate_goal_to_session("same", "same") is False
|
|
|
|
def test_cleared_goal_not_migrated(self, hermes_home):
|
|
from hermes_cli.goals import save_goal, clear_goal, migrate_goal_to_session, load_goal, GoalState
|
|
save_goal("p4", GoalState(goal="done already"))
|
|
clear_goal("p4")
|
|
assert migrate_goal_to_session("p4", "c4") is False
|
|
assert load_goal("c4") is None
|
|
|
|
|
|
class TestGoalManagerSubgoals:
|
|
def test_add_subgoal(self, hermes_home):
|
|
from hermes_cli.goals import GoalManager
|
|
mgr = GoalManager(session_id="sub-add")
|
|
mgr.set("main goal")
|
|
text = mgr.add_subgoal(" use bullet points ")
|
|
assert text == "use bullet points"
|
|
assert mgr.state.subgoals == ["use bullet points"]
|
|
|
|
def test_add_subgoal_requires_active_goal(self, hermes_home):
|
|
import pytest
|
|
from hermes_cli.goals import GoalManager
|
|
mgr = GoalManager(session_id="sub-noactive")
|
|
with pytest.raises(RuntimeError):
|
|
mgr.add_subgoal("oops")
|
|
|
|
def test_add_empty_subgoal_rejected(self, hermes_home):
|
|
import pytest
|
|
from hermes_cli.goals import GoalManager
|
|
mgr = GoalManager(session_id="sub-empty")
|
|
mgr.set("g")
|
|
with pytest.raises(ValueError):
|
|
mgr.add_subgoal(" ")
|
|
|
|
def test_remove_subgoal(self, hermes_home):
|
|
from hermes_cli.goals import GoalManager
|
|
mgr = GoalManager(session_id="sub-remove")
|
|
mgr.set("g")
|
|
mgr.add_subgoal("first")
|
|
mgr.add_subgoal("second")
|
|
mgr.add_subgoal("third")
|
|
removed = mgr.remove_subgoal(2)
|
|
assert removed == "second"
|
|
assert mgr.state.subgoals == ["first", "third"]
|
|
|
|
def test_remove_subgoal_out_of_range(self, hermes_home):
|
|
import pytest
|
|
from hermes_cli.goals import GoalManager
|
|
mgr = GoalManager(session_id="sub-oob")
|
|
mgr.set("g")
|
|
mgr.add_subgoal("only")
|
|
with pytest.raises(IndexError):
|
|
mgr.remove_subgoal(5)
|
|
with pytest.raises(IndexError):
|
|
mgr.remove_subgoal(0)
|
|
|
|
def test_clear_subgoals(self, hermes_home):
|
|
from hermes_cli.goals import GoalManager
|
|
mgr = GoalManager(session_id="sub-clear")
|
|
mgr.set("g")
|
|
mgr.add_subgoal("a")
|
|
mgr.add_subgoal("b")
|
|
prev = mgr.clear_subgoals()
|
|
assert prev == 2
|
|
assert mgr.state.subgoals == []
|
|
|
|
def test_subgoals_persist_across_reloads(self, hermes_home):
|
|
"""Subgoals stored in SessionDB survive a fresh GoalManager."""
|
|
from hermes_cli.goals import GoalManager
|
|
mgr = GoalManager(session_id="sub-persist")
|
|
mgr.set("g")
|
|
mgr.add_subgoal("first")
|
|
mgr.add_subgoal("second")
|
|
|
|
mgr2 = GoalManager(session_id="sub-persist")
|
|
assert mgr2.state.subgoals == ["first", "second"]
|
|
|
|
|
|
class TestContinuationPromptWithSubgoals:
|
|
def test_empty_subgoals_uses_original_template(self, hermes_home):
|
|
from hermes_cli.goals import GoalManager
|
|
mgr = GoalManager(session_id="cp-empty")
|
|
mgr.set("ship the feature")
|
|
prompt = mgr.next_continuation_prompt()
|
|
assert prompt is not None
|
|
assert "ship the feature" in prompt
|
|
assert "Additional criteria" not in prompt
|
|
|
|
def test_with_subgoals_includes_them(self, hermes_home):
|
|
from hermes_cli.goals import GoalManager
|
|
mgr = GoalManager(session_id="cp-with")
|
|
mgr.set("ship the feature")
|
|
mgr.add_subgoal("write tests")
|
|
mgr.add_subgoal("update docs")
|
|
prompt = mgr.next_continuation_prompt()
|
|
assert prompt is not None
|
|
assert "ship the feature" in prompt
|
|
assert "Additional criteria" in prompt
|
|
assert "1. write tests" in prompt
|
|
assert "2. update docs" in prompt
|
|
|
|
|
|
class TestJudgeGoalWithSubgoals:
|
|
def test_judge_uses_subgoals_template_when_provided(self, hermes_home):
|
|
"""judge_goal switches templates when subgoals is non-empty.
|
|
|
|
We don't actually call the model — we patch the aux client to
|
|
capture the prompt that would be sent.
|
|
"""
|
|
from unittest.mock import patch
|
|
from hermes_cli import goals
|
|
|
|
captured = {}
|
|
|
|
class _FakeMsg:
|
|
content = '{"done": true, "reason": "all done"}'
|
|
class _FakeChoice:
|
|
message = _FakeMsg()
|
|
class _FakeResp:
|
|
choices = [_FakeChoice()]
|
|
class _FakeClient:
|
|
class chat:
|
|
class completions:
|
|
@staticmethod
|
|
def create(**kwargs):
|
|
captured.update(kwargs)
|
|
return _FakeResp()
|
|
|
|
with patch.object(goals, "get_text_auxiliary_client",
|
|
return_value=(_FakeClient, "fake-model"), create=True), \
|
|
patch.object(goals, "get_auxiliary_extra_body",
|
|
return_value=None, create=True), \
|
|
patch("agent.auxiliary_client.get_text_auxiliary_client",
|
|
return_value=(_FakeClient, "fake-model")), \
|
|
patch("agent.auxiliary_client.get_auxiliary_extra_body",
|
|
return_value=None):
|
|
verdict, reason, parse_failed, _wd = goals.judge_goal(
|
|
"ship the feature",
|
|
"ok shipped",
|
|
subgoals=["write tests", "update docs"],
|
|
)
|
|
|
|
# The aux client was called with a prompt that includes the subgoals.
|
|
sent_messages = captured.get("messages") or []
|
|
user_msg = next((m["content"] for m in sent_messages if m["role"] == "user"), "")
|
|
assert "Additional criteria" in user_msg
|
|
assert "1. write tests" in user_msg
|
|
assert "2. update docs" in user_msg
|
|
assert "every additional criterion" in user_msg
|
|
assert verdict == "done"
|
|
|
|
def test_judge_uses_original_template_when_no_subgoals(self, hermes_home):
|
|
from unittest.mock import patch
|
|
from hermes_cli import goals
|
|
|
|
captured = {}
|
|
|
|
class _FakeMsg:
|
|
content = '{"done": true, "reason": "ok"}'
|
|
class _FakeChoice:
|
|
message = _FakeMsg()
|
|
class _FakeResp:
|
|
choices = [_FakeChoice()]
|
|
class _FakeClient:
|
|
class chat:
|
|
class completions:
|
|
@staticmethod
|
|
def create(**kwargs):
|
|
captured.update(kwargs)
|
|
return _FakeResp()
|
|
|
|
with patch("agent.auxiliary_client.get_text_auxiliary_client",
|
|
return_value=(_FakeClient, "fake-model")), \
|
|
patch("agent.auxiliary_client.get_auxiliary_extra_body",
|
|
return_value=None):
|
|
goals.judge_goal("ship it", "done", subgoals=None)
|
|
|
|
sent_messages = captured.get("messages") or []
|
|
user_msg = next((m["content"] for m in sent_messages if m["role"] == "user"), "")
|
|
assert "Additional criteria" not in user_msg
|
|
assert "ship it" in user_msg
|
|
|
|
|
|
class TestStatusLineSubgoalCount:
|
|
def test_status_line_no_subgoals(self, hermes_home):
|
|
from hermes_cli.goals import GoalManager
|
|
mgr = GoalManager(session_id="sl-empty")
|
|
mgr.set("ship it")
|
|
line = mgr.status_line()
|
|
assert "ship it" in line
|
|
assert "subgoal" not in line.lower()
|
|
|
|
def test_status_line_with_subgoals(self, hermes_home):
|
|
from hermes_cli.goals import GoalManager
|
|
mgr = GoalManager(session_id="sl-with")
|
|
mgr.set("ship it")
|
|
mgr.add_subgoal("a")
|
|
mgr.add_subgoal("b")
|
|
line = mgr.status_line()
|
|
assert "2 subgoals" in line
|
|
|
|
|
|
# ──────────────────────────────────────────────────────────────────────
|
|
# Wait barrier — parking the goal loop on a background process
|
|
# ──────────────────────────────────────────────────────────────────────
|
|
|
|
|
|
class TestWaitBarrier:
|
|
"""The /goal wait barrier parks the loop on a live PID and resumes when
|
|
the process exits, without burning turns or calling the judge."""
|
|
|
|
@staticmethod
|
|
def _spawn_sleeper():
|
|
"""Start a short-lived child process; return its Popen handle."""
|
|
import subprocess
|
|
import sys
|
|
return subprocess.Popen([sys.executable, "-c", "import time; time.sleep(30)"])
|
|
|
|
@staticmethod
|
|
def _dead_pid():
|
|
"""A PID that is essentially guaranteed not to be running."""
|
|
return 2_000_000_000
|
|
|
|
def test_wait_on_requires_active_goal(self, hermes_home):
|
|
from hermes_cli.goals import GoalManager
|
|
mgr = GoalManager(session_id="wb-noactive")
|
|
with pytest.raises(RuntimeError):
|
|
mgr.wait_on(12345)
|
|
|
|
def test_wait_on_rejects_bad_pid(self, hermes_home):
|
|
from hermes_cli.goals import GoalManager
|
|
mgr = GoalManager(session_id="wb-badpid")
|
|
mgr.set("g")
|
|
with pytest.raises(ValueError):
|
|
mgr.wait_on(0)
|
|
|
|
def test_parked_on_live_pid_does_not_continue_or_judge(self, hermes_home):
|
|
from hermes_cli import goals
|
|
from hermes_cli.goals import GoalManager
|
|
|
|
proc = self._spawn_sleeper()
|
|
try:
|
|
mgr = GoalManager(session_id="wb-live")
|
|
mgr.set("ship it", max_turns=5)
|
|
mgr.wait_on(proc.pid, reason="CI green")
|
|
assert mgr.is_waiting() is True
|
|
|
|
# The judge must NOT be called while parked, and no turn is burned.
|
|
judge = MagicMock(return_value=("continue", "x", False, None))
|
|
with patch.object(goals, "judge_goal", judge):
|
|
decision = mgr.evaluate_after_turn("still waiting on CI")
|
|
|
|
judge.assert_not_called()
|
|
assert decision["verdict"] == "waiting"
|
|
assert decision["should_continue"] is False
|
|
assert decision["continuation_prompt"] is None
|
|
assert mgr.state.turns_used == 0 # no turn consumed while parked
|
|
assert "CI green" in decision["message"]
|
|
assert mgr.state.status == "active" # still active, just parked
|
|
finally:
|
|
proc.terminate()
|
|
proc.wait(timeout=10)
|
|
|
|
def test_barrier_auto_clears_when_process_exits_and_loop_resumes(self, hermes_home):
|
|
from hermes_cli import goals
|
|
from hermes_cli.goals import GoalManager
|
|
|
|
proc = self._spawn_sleeper()
|
|
mgr = GoalManager(session_id="wb-exit")
|
|
mgr.set("ship it", max_turns=5)
|
|
mgr.wait_on(proc.pid, reason="build")
|
|
assert mgr.is_waiting() is True
|
|
|
|
# Kill the process — barrier should auto-clear and judging resumes.
|
|
proc.terminate()
|
|
proc.wait(timeout=10)
|
|
|
|
assert mgr.is_waiting() is False # lazy auto-clear
|
|
assert mgr.state.waiting_on_pid is None
|
|
|
|
with patch.object(goals, "judge_goal", return_value=("continue", "more", False, None)):
|
|
decision = mgr.evaluate_after_turn("process finished, here are results")
|
|
|
|
assert decision["verdict"] == "continue"
|
|
assert decision["should_continue"] is True
|
|
assert mgr.state.turns_used == 1 # now a turn IS consumed
|
|
|
|
def test_dead_pid_never_parks(self, hermes_home):
|
|
from hermes_cli import goals
|
|
from hermes_cli.goals import GoalManager
|
|
|
|
mgr = GoalManager(session_id="wb-dead")
|
|
mgr.set("g", max_turns=5)
|
|
mgr.wait_on(self._dead_pid(), reason="already-dead")
|
|
# is_waiting clears the stale barrier immediately.
|
|
assert mgr.is_waiting() is False
|
|
|
|
with patch.object(goals, "judge_goal", return_value=("continue", "go", False, None)):
|
|
decision = mgr.evaluate_after_turn("response")
|
|
assert decision["should_continue"] is True
|
|
|
|
def test_stop_waiting_clears_barrier(self, hermes_home):
|
|
from hermes_cli.goals import GoalManager
|
|
|
|
proc = self._spawn_sleeper()
|
|
try:
|
|
mgr = GoalManager(session_id="wb-stop")
|
|
mgr.set("g")
|
|
mgr.wait_on(proc.pid)
|
|
assert mgr.is_waiting() is True
|
|
assert mgr.stop_waiting() is True
|
|
assert mgr.state.waiting_on_pid is None
|
|
assert mgr.is_waiting() is False
|
|
assert mgr.stop_waiting() is False # idempotent
|
|
finally:
|
|
proc.terminate()
|
|
proc.wait(timeout=10)
|
|
|
|
def test_pause_and_resume_clear_barrier(self, hermes_home):
|
|
from hermes_cli.goals import GoalManager
|
|
|
|
proc = self._spawn_sleeper()
|
|
try:
|
|
mgr = GoalManager(session_id="wb-pause")
|
|
mgr.set("g")
|
|
mgr.wait_on(proc.pid)
|
|
mgr.pause()
|
|
assert mgr.state.waiting_on_pid is None
|
|
|
|
mgr.resume()
|
|
assert mgr.state.waiting_on_pid is None
|
|
finally:
|
|
proc.terminate()
|
|
proc.wait(timeout=10)
|
|
|
|
def test_barrier_persists_and_reloads(self, hermes_home):
|
|
from hermes_cli.goals import GoalManager
|
|
|
|
proc = self._spawn_sleeper()
|
|
try:
|
|
mgr = GoalManager(session_id="wb-persist")
|
|
mgr.set("g")
|
|
mgr.wait_on(proc.pid, reason="deploy")
|
|
|
|
# Fresh manager loads the persisted barrier.
|
|
mgr2 = GoalManager(session_id="wb-persist")
|
|
assert mgr2.state.waiting_on_pid == proc.pid
|
|
assert mgr2.state.waiting_reason == "deploy"
|
|
assert mgr2.is_waiting() is True
|
|
finally:
|
|
proc.terminate()
|
|
proc.wait(timeout=10)
|
|
|
|
def test_old_state_row_loads_without_barrier_fields(self, hermes_home):
|
|
"""Backwards-compat: a state_meta row written before the barrier
|
|
existed must load with no barrier."""
|
|
from hermes_cli.goals import GoalState
|
|
|
|
legacy = json.dumps({
|
|
"goal": "old goal",
|
|
"status": "active",
|
|
"turns_used": 2,
|
|
"max_turns": 20,
|
|
})
|
|
st = GoalState.from_json(legacy)
|
|
assert st.goal == "old goal"
|
|
assert st.waiting_on_pid is None
|
|
assert st.waiting_reason is None
|
|
assert st.waiting_since == 0.0
|
|
assert st.waiting_until == 0.0
|
|
|
|
|
|
# ──────────────────────────────────────────────────────────────────────
|
|
# Judge-driven auto-wait — the judge parks the loop on its own
|
|
# ──────────────────────────────────────────────────────────────────────
|
|
|
|
|
|
class TestJudgeDrivenWait:
|
|
"""The judge returns a `wait` verdict (given live background-process
|
|
context) and the loop parks automatically — no manual /goal wait."""
|
|
|
|
@staticmethod
|
|
def _spawn_sleeper():
|
|
import subprocess, sys
|
|
return subprocess.Popen([sys.executable, "-c", "import time; time.sleep(30)"])
|
|
|
|
def test_judge_wait_pid_parks_loop(self, hermes_home):
|
|
from hermes_cli import goals
|
|
from hermes_cli.goals import GoalManager
|
|
|
|
proc = self._spawn_sleeper()
|
|
try:
|
|
mgr = GoalManager(session_id="jw-pid", default_max_turns=10)
|
|
mgr.set("ship the PR")
|
|
# Judge sees the running process and says wait-on-pid.
|
|
with patch.object(
|
|
goals, "judge_goal",
|
|
return_value=("wait", "CI watcher still running", False, {"pid": proc.pid}),
|
|
):
|
|
decision = mgr.evaluate_after_turn(
|
|
"Pushed the PR, watching CI.",
|
|
background_processes=[{
|
|
"pid": proc.pid, "command": "wait_for_pr_green.sh",
|
|
"status": "running", "uptime_seconds": 12,
|
|
}],
|
|
)
|
|
assert decision["verdict"] == "wait"
|
|
assert decision["should_continue"] is False
|
|
assert decision["continuation_prompt"] is None
|
|
assert mgr.state.waiting_on_pid == proc.pid
|
|
assert mgr.is_waiting() is True
|
|
|
|
# Next turn while still parked: judge must NOT be called again.
|
|
judge = MagicMock()
|
|
with patch.object(goals, "judge_goal", judge):
|
|
d2 = mgr.evaluate_after_turn("still going")
|
|
judge.assert_not_called()
|
|
assert d2["verdict"] == "waiting"
|
|
assert d2["should_continue"] is False
|
|
finally:
|
|
proc.terminate()
|
|
proc.wait(timeout=10)
|
|
|
|
def test_judge_wait_seconds_parks_loop(self, hermes_home):
|
|
from hermes_cli import goals
|
|
from hermes_cli.goals import GoalManager
|
|
|
|
mgr = GoalManager(session_id="jw-secs", default_max_turns=10)
|
|
mgr.set("retry after backoff")
|
|
with patch.object(
|
|
goals, "judge_goal",
|
|
return_value=("wait", "rate limited", False, {"seconds": 120}),
|
|
):
|
|
decision = mgr.evaluate_after_turn("Hit a 429, backing off.")
|
|
assert decision["verdict"] == "wait"
|
|
assert decision["should_continue"] is False
|
|
assert mgr.state.waiting_until > 0
|
|
assert mgr.state.waiting_on_pid is None
|
|
assert mgr.is_waiting() is True
|
|
|
|
def test_time_barrier_clears_after_deadline(self, hermes_home):
|
|
from hermes_cli.goals import GoalManager
|
|
|
|
mgr = GoalManager(session_id="jw-deadline")
|
|
mgr.set("g")
|
|
mgr.wait_for_seconds(120, reason="backoff")
|
|
assert mgr.is_waiting() is True
|
|
# Force the deadline into the past → barrier auto-clears.
|
|
mgr.state.waiting_until = time.time() - 1
|
|
assert mgr.is_waiting() is False
|
|
assert mgr.state.waiting_until == 0.0
|
|
|
|
def test_continue_verdict_still_continues_with_background(self, hermes_home):
|
|
"""A running process present but judge says continue → normal loop."""
|
|
from hermes_cli import goals
|
|
from hermes_cli.goals import GoalManager
|
|
|
|
mgr = GoalManager(session_id="jw-cont", default_max_turns=10)
|
|
mgr.set("do work")
|
|
with patch.object(
|
|
goals, "judge_goal",
|
|
return_value=("continue", "more to do", False, None),
|
|
):
|
|
decision = mgr.evaluate_after_turn(
|
|
"made progress",
|
|
background_processes=[{"pid": 999999, "command": "x", "status": "running"}],
|
|
)
|
|
assert decision["verdict"] == "continue"
|
|
assert decision["should_continue"] is True
|
|
assert mgr.state.waiting_on_pid is None
|
|
|
|
|
|
# ──────────────────────────────────────────────────────────────────────
|
|
# Session/trigger barrier — wait on a process's OWN trigger, not just exit
|
|
# ──────────────────────────────────────────────────────────────────────
|
|
|
|
|
|
class TestSessionTriggerBarrier:
|
|
"""The session barrier (wait_on_session) releases when a process's own
|
|
trigger fires — a watch_patterns match mid-run (process may never exit)
|
|
OR exit — not only on PID exit. CI-safe: uses synthetic registry session
|
|
objects, no real child processes."""
|
|
|
|
@staticmethod
|
|
def _inject(sid, *, watch_patterns=None, exited=False):
|
|
import time as _t
|
|
from tools.process_registry import process_registry, ProcessSession
|
|
s = ProcessSession(id=sid, command="watcher.sh", task_id="t",
|
|
session_key="", cwd="/tmp", started_at=_t.time())
|
|
if watch_patterns:
|
|
s.watch_patterns = list(watch_patterns)
|
|
s.exited = exited
|
|
if exited:
|
|
process_registry._finished[sid] = s
|
|
else:
|
|
process_registry._running[sid] = s
|
|
return s, process_registry
|
|
|
|
def test_registry_is_session_waiting_running_unmatched(self, hermes_home):
|
|
s, reg = self._inject("proc_t1", watch_patterns=["READY"])
|
|
assert reg.is_session_waiting("proc_t1") is True
|
|
|
|
def test_registry_releases_on_watch_match_while_alive(self, hermes_home):
|
|
s, reg = self._inject("proc_t2", watch_patterns=["READY"])
|
|
assert reg.is_session_waiting("proc_t2") is True
|
|
s._watch_hits = 1 # what _check_watch_patterns sets on a match
|
|
# Released even though the process is STILL running (never exited).
|
|
assert s.exited is False
|
|
assert reg.is_session_waiting("proc_t2") is False
|
|
|
|
def test_registry_releases_on_exit_plain_session(self, hermes_home):
|
|
s, reg = self._inject("proc_t3") # no watch pattern
|
|
assert reg.is_session_waiting("proc_t3") is True
|
|
s.exited = True
|
|
assert reg.is_session_waiting("proc_t3") is False
|
|
|
|
def test_registry_unknown_session_never_waits(self, hermes_home):
|
|
from tools.process_registry import process_registry
|
|
assert process_registry.is_session_waiting("proc_does_not_exist") is False
|
|
|
|
def test_goal_parks_on_session_and_releases_on_trigger(self, hermes_home):
|
|
from hermes_cli import goals
|
|
from hermes_cli.goals import GoalManager
|
|
|
|
s, reg = self._inject("proc_t4", watch_patterns=["BUILD SUCCESSFUL"])
|
|
mgr = GoalManager(session_id="st-goal", default_max_turns=10)
|
|
mgr.set("wait for the build to succeed")
|
|
with patch.object(
|
|
goals, "judge_goal",
|
|
return_value=("wait", "blocked on build", False, {"session_id": "proc_t4"}),
|
|
):
|
|
decision = mgr.evaluate_after_turn(
|
|
"Started the build watcher.",
|
|
background_processes=[{
|
|
"session_id": "proc_t4", "pid": 4242, "command": "watcher.sh",
|
|
"status": "running", "watch_patterns": ["BUILD SUCCESSFUL"],
|
|
"watch_hit": False,
|
|
}],
|
|
)
|
|
assert decision["verdict"] == "wait"
|
|
assert mgr.state.waiting_on_session == "proc_t4"
|
|
assert mgr.is_waiting() is True
|
|
|
|
# Judge must NOT be called again while parked.
|
|
judge = MagicMock()
|
|
with patch.object(goals, "judge_goal", judge):
|
|
d2 = mgr.evaluate_after_turn("still building")
|
|
judge.assert_not_called()
|
|
assert d2["should_continue"] is False
|
|
|
|
# Trigger fires mid-run (process still alive) → barrier releases.
|
|
s._watch_hits = 1
|
|
assert mgr.is_waiting() is False
|
|
assert mgr.state.waiting_on_session is None
|
|
|
|
# Loop resumes with a real judge verdict.
|
|
with patch.object(goals, "judge_goal",
|
|
return_value=("continue", "build done", False, None)):
|
|
d3 = mgr.evaluate_after_turn("build succeeded")
|
|
assert d3["should_continue"] is True
|
|
|
|
def test_wait_on_session_validation(self, hermes_home):
|
|
from hermes_cli.goals import GoalManager
|
|
mgr = GoalManager(session_id="st-val")
|
|
# No active goal → RuntimeError
|
|
try:
|
|
mgr.wait_on_session("proc_x")
|
|
assert False, "expected RuntimeError"
|
|
except RuntimeError:
|
|
pass
|
|
mgr.set("g")
|
|
try:
|
|
mgr.wait_on_session("")
|
|
assert False, "expected ValueError"
|
|
except ValueError:
|
|
pass
|
|
|
|
def test_session_directive_parsed_from_judge(self, hermes_home):
|
|
from hermes_cli.goals import _parse_judge_response
|
|
v, _, pf, wd = _parse_judge_response(
|
|
'{"verdict": "wait", "wait_on_session": "proc_abc", "reason": "r"}'
|
|
)
|
|
assert v == "wait"
|
|
assert pf is False
|
|
assert wd == {"session_id": "proc_abc"}
|
|
|
|
def test_old_state_loads_without_session_field(self, hermes_home):
|
|
from hermes_cli.goals import GoalState
|
|
st = GoalState.from_json(json.dumps({
|
|
"goal": "g", "status": "active", "turns_used": 0, "max_turns": 20,
|
|
}))
|
|
assert st.waiting_on_session is None
|