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).
95 lines
2.4 KiB
Python
95 lines
2.4 KiB
Python
"""Tests for agent.replay_cleanup — shared replay-tail sanitizers.
|
|
|
|
These functions were extracted from gateway/run.py so every resume surface
|
|
(messaging gateway AND TUI/WebUI gateway) strips poisoned tool-call tails the
|
|
same way. Regression coverage for #29086 (WebUI session permanently stuck
|
|
because the dangling tool-call tail was replayed on every resume).
|
|
"""
|
|
|
|
from agent.replay_cleanup import (
|
|
is_interrupted_tool_result,
|
|
strip_dangling_tool_call_tail,
|
|
strip_interrupted_tool_tails,
|
|
sanitize_replay_history,
|
|
)
|
|
|
|
|
|
def _user(text):
|
|
return {"role": "user", "content": text}
|
|
|
|
|
|
def _assistant_tc(name):
|
|
return {
|
|
"role": "assistant",
|
|
"content": "",
|
|
"tool_calls": [
|
|
{"id": "c1", "type": "function", "function": {"name": name, "arguments": "{}"}}
|
|
],
|
|
}
|
|
|
|
|
|
def _tool(content):
|
|
return {"role": "tool", "tool_call_id": "c1", "content": content}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def test_mixed_dangling_batch_uses_truthful_per_call_wording():
|
|
assistant = {
|
|
"role": "assistant",
|
|
"content": "",
|
|
"tool_calls": [
|
|
{"id": "read", "function": {"name": "read_file", "arguments": "{}"}},
|
|
{"id": "write", "function": {"name": "write_file", "arguments": "{}"}},
|
|
],
|
|
}
|
|
out = strip_dangling_tool_call_tail([_user("hi"), assistant])
|
|
|
|
read_result, write_result = out[-2:]
|
|
assert read_result["effect_disposition"] == "none"
|
|
assert "no effect" in read_result["content"].lower()
|
|
assert "unknown" not in read_result["content"].lower()
|
|
assert write_result["effect_disposition"] == "unknown"
|
|
assert "unknown" in write_result["content"].lower()
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def test_sanitize_replay_history_combines_both():
|
|
# interrupted block is removed; a dangling read-only call is safe to erase
|
|
history = [
|
|
_user("first"),
|
|
_assistant_tc("terminal"), _tool("[Command interrupted]"),
|
|
_user("second"),
|
|
_assistant_tc("read_file"), # dangling
|
|
]
|
|
out = sanitize_replay_history(history)
|
|
assert out[:2] == [
|
|
_user("first"),
|
|
_assistant_tc("terminal"),
|
|
]
|
|
assert out[2]["effect_disposition"] == "unknown"
|
|
assert out[-1] == _user("second")
|
|
|
|
|
|
def test_sanitize_replay_history_noop_on_clean_history():
|
|
history = [_user("hi"), {"role": "assistant", "content": "hello"}]
|
|
assert sanitize_replay_history(history) == history
|
|
|
|
|
|
def test_sanitize_replay_history_empty():
|
|
assert sanitize_replay_history([]) == []
|