teknium1
d10bb2ab6f
`scripts/run_tests.sh tests/<dir>/` is how a change gets its regression
coverage run, so a test filed under the wrong directory is a test nobody
runs when that code changes. Two kinds of drift had accumulated.
Parallel directories for one source package, folded into the mirror:
tests/acp -> tests/acp_adapter (its __init__/conftest move with it)
tests/cli -> tests/hermes_cli (prompt_toolkit fixture merged into
hermes_cli/conftest.py)
tests/run_agent -> tests/agent (backoff fixture becomes
agent/conftest.py)
tests/relay -> tests/gateway/relay
tests/state -> tests/hermes_state
246 loose files at tests/ root, routed by the package they import/patch:
hermes_cli, hermes_state, agent, gateway, tools, plugins, tui_gateway, cron.
Installer and desktop-update script tests go to tests/scripts/{install,
desktop_update}/. 43 tests of root-level modules (batch_runner, utils,
hermes_constants, packaging) stay at the root.
Filenames drop their issue numbers (95 files: test_89315_x.py -> test_x.py);
the number stays in the module docstring where it has context.
Collisions: test_cli_skin_integration.py existed in both tests/ and tests/cli
with different subsets — merged into one (10 tests, all kept);
run_agent/test_pre_compress_memory_context.py -> agent/..._handoff.py;
tests/test_account_usage.py -> agent/test_account_usage_fetch.py;
tests/test_web_server.py -> hermes_cli/test_web_server_ws_ping.py.
Deleted: test_minisweagent_path.py (empty since PR #2804),
test_model_picker_scroll.py (tested a private copy of the logic, imported
nothing), test_process_loop_event_loop_warning.py (asserted asyncio behaviour,
imported nothing from Hermes).
Repo-root path arithmetic (Path(__file__).parents[N], dirname chains) is
bumped for the 202 files that changed depth and verified by evaluating every
such expression against the new location. classify_changes' desktop-updater
lane prefix, tests-os.yml's ignore glob and every in-tree path comment follow
the moves. tests/test_tests_tree_layout.py keeps the tree from drifting back.
113 lines
3.2 KiB
Python
113 lines
3.2 KiB
Python
"""Tests for AIAgent._summarize_background_review_actions.
|
|
|
|
Regression coverage for issue #14944: the background memory/skill review used
|
|
to re-surface tool results that were already present in the conversation
|
|
history before the review started (e.g. an earlier "Cron job '...' created.").
|
|
"""
|
|
|
|
import json
|
|
|
|
from run_agent import AIAgent
|
|
|
|
|
|
_summarize = AIAgent._summarize_background_review_actions
|
|
|
|
|
|
def _tool_msg(tool_call_id, payload):
|
|
return {
|
|
"role": "tool",
|
|
"tool_call_id": tool_call_id,
|
|
"content": json.dumps(payload),
|
|
}
|
|
|
|
|
|
def test_skips_prior_tool_messages_by_tool_call_id():
|
|
"""Stale 'created' tool result from prior history must not be re-surfaced."""
|
|
prior_payload = {"success": True, "message": "Cron job 'remind-me' created."}
|
|
new_payload = {
|
|
"success": True,
|
|
"message": "Entry added",
|
|
"target": "user",
|
|
}
|
|
|
|
snapshot = [
|
|
{"role": "user", "content": "create a reminder"},
|
|
_tool_msg("call_old", prior_payload),
|
|
{"role": "assistant", "content": "done"},
|
|
]
|
|
review_messages = list(snapshot) + [
|
|
{"role": "user", "content": "<review prompt>"},
|
|
_tool_msg("call_new", new_payload),
|
|
]
|
|
|
|
actions = _summarize(review_messages, snapshot)
|
|
|
|
assert "Cron job 'remind-me' created." not in actions
|
|
assert "User profile updated" in actions
|
|
|
|
|
|
def test_includes_genuinely_new_actions():
|
|
new_payload = {
|
|
"success": True,
|
|
"message": "Memory entry created.",
|
|
}
|
|
review_messages = [_tool_msg("call_new", new_payload)]
|
|
|
|
actions = _summarize(review_messages, prior_snapshot=[])
|
|
|
|
assert actions == ["Memory entry created."]
|
|
|
|
|
|
def test_falls_back_to_content_equality_when_tool_call_id_missing():
|
|
"""If a tool message has no tool_call_id, match prior entries by content."""
|
|
payload = {"success": True, "message": "Cron job 'X' created."}
|
|
raw = json.dumps(payload)
|
|
prior_msg = {"role": "tool", "content": raw} # no tool_call_id
|
|
review_messages = [
|
|
{"role": "tool", "content": raw}, # same content -> stale, skip
|
|
_tool_msg("call_new", {"success": True, "message": "Skill created."}),
|
|
]
|
|
|
|
actions = _summarize(review_messages, [prior_msg])
|
|
|
|
assert "Cron job 'X' created." not in actions
|
|
assert "Skill created." in actions
|
|
|
|
|
|
|
|
|
|
def test_handles_non_json_tool_content_gracefully():
|
|
review_messages = [
|
|
{"role": "tool", "tool_call_id": "x", "content": "not-json"},
|
|
_tool_msg("call_y", {"success": True, "message": "Memory updated."}),
|
|
]
|
|
|
|
actions = _summarize(review_messages, [])
|
|
|
|
assert actions == ["Memory updated."]
|
|
|
|
|
|
def test_empty_inputs():
|
|
assert _summarize([], []) == []
|
|
assert _summarize(None, None) == []
|
|
|
|
|
|
|
|
|
|
def test_removed_or_replaced_relabels_by_target():
|
|
review_messages = [
|
|
_tool_msg(
|
|
"c1",
|
|
{"success": True, "message": "Entry removed.", "target": "user"},
|
|
),
|
|
_tool_msg(
|
|
"c2",
|
|
{"success": True, "message": "Entry replaced.", "target": "memory"},
|
|
),
|
|
]
|
|
|
|
actions = _summarize(review_messages, [])
|
|
|
|
assert "User profile updated" in actions
|
|
assert "Memory updated" in actions
|