mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-07-31 19:16:29 +00:00
6b81590c55
Systematic prune per AGENTS.md test policy, one pass over every major test tree (gateway, hermes_cli, tools, agent, run_agent, plugins, cli, cron, tui_gateway, honcho/openviking, root-level): - DELETE: source-reading tests (read_text/getsource on prod files), change-detector tests (exact catalog counts, model-name snapshots, config version literals), mock-echo tests (assert a mock returns what it was told), assertion-free/trivial tests, near-duplicate parametrizations (boundaries + one representative kept), async/sync twin duplicates, cosmetic within-file variations. - KEEP (mandatory): security/redaction/approval guards, message-role alternation invariants, prompt-caching/deterministic-call-id invariants, issue-number regression tests (deduped), E2E tests. - 6 test files deleted outright (script-style/no-assert or fully redundant); conftest.py, fakes/, fixtures/ untouched. - tests/acp/conftest.py added: autouse fixture stubs the live models.dev/GitHub/Copilot/Anthropic inventory fetches that ACP server tests performed on every session create — test_server.py 147s → 3.4s, and the tests are now genuinely hermetic. - Sleep-based slowness shrunk where safe (codex_ttfb_watchdog, compression_concurrent_fork, etc.); no wall-clock assertion tightened. Verification: full hermetic suite via scripts/run_tests.sh — 2439 files, 31,130 tests passed, 0 failed, 0 flaky retries, 315s wall (baseline: 583s wall, 13,564s subprocess CPU).
90 lines
2.7 KiB
Python
90 lines
2.7 KiB
Python
"""Tests for the kanban worker turn-end stop guard."""
|
|
|
|
from __future__ import annotations
|
|
|
|
import pytest
|
|
|
|
from agent.kanban_stop import (
|
|
build_kanban_stop_nudge,
|
|
kanban_stop_nudge_enabled,
|
|
session_called_kanban_terminal,
|
|
)
|
|
|
|
|
|
@pytest.fixture
|
|
def clear_kanban_env(monkeypatch):
|
|
for var in ("HERMES_KANBAN_TASK", "HERMES_KANBAN_STOP_NUDGE"):
|
|
monkeypatch.delenv(var, raising=False)
|
|
return monkeypatch
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def test_env_can_disable(clear_kanban_env):
|
|
clear_kanban_env.setenv("HERMES_KANBAN_TASK", "t_abc")
|
|
clear_kanban_env.setenv("HERMES_KANBAN_STOP_NUDGE", "0")
|
|
assert kanban_stop_nudge_enabled() is False
|
|
assert build_kanban_stop_nudge(messages=[]) is None
|
|
|
|
|
|
def test_nudge_when_no_terminal_tool(clear_kanban_env):
|
|
clear_kanban_env.setenv("HERMES_KANBAN_TASK", "t_46be8aa5")
|
|
messages = [
|
|
{"role": "user", "content": "work kanban task"},
|
|
{
|
|
"role": "assistant",
|
|
"content": "Let me write the comprehensive recipe.",
|
|
"tool_calls": [
|
|
{
|
|
"id": "1",
|
|
"type": "function",
|
|
"function": {"name": "kanban_heartbeat", "arguments": "{}"},
|
|
}
|
|
],
|
|
},
|
|
{"role": "tool", "name": "kanban_heartbeat", "tool_call_id": "1", "content": "ok"},
|
|
]
|
|
nudge = build_kanban_stop_nudge(messages=messages, attempts=0)
|
|
assert nudge is not None
|
|
assert "kanban_complete" in nudge
|
|
assert "kanban_block" in nudge
|
|
assert "t_46be8aa5" in nudge
|
|
assert "protocol violation" in nudge.lower() or "protocol" in nudge.lower()
|
|
|
|
|
|
def test_no_nudge_after_kanban_complete(clear_kanban_env):
|
|
clear_kanban_env.setenv("HERMES_KANBAN_TASK", "t_abc")
|
|
messages = [
|
|
{
|
|
"role": "assistant",
|
|
"content": "",
|
|
"tool_calls": [
|
|
{
|
|
"id": "1",
|
|
"type": "function",
|
|
"function": {"name": "kanban_complete", "arguments": "{}"},
|
|
}
|
|
],
|
|
},
|
|
{"role": "tool", "name": "kanban_complete", "tool_call_id": "1", "content": "done"},
|
|
]
|
|
assert session_called_kanban_terminal(messages) is True
|
|
assert build_kanban_stop_nudge(messages=messages) is None
|
|
|
|
|
|
|
|
|
|
|
|
|
|
# ── Integration: agent nudge + dispatcher bounded retry ──────────────
|
|
# These tests verify the two layers compose correctly: the agent-side
|
|
# nudge fires first (up to 2 attempts), and if the worker still exits
|
|
# without a terminal call, the dispatcher's bounded retry (streak of 3)
|
|
# handles it. See also tests/hermes_cli/test_kanban_core_functionality.py
|
|
# for the dispatcher-side streak tests.
|
|
|
|
|
|
|
|
|