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.
101 lines
3.2 KiB
Python
101 lines
3.2 KiB
Python
"""Regression coverage for image-only user content across native compaction."""
|
|
|
|
from agent.codex_responses_adapter import _chat_messages_to_responses_input
|
|
from agent.native_compaction import _extract_item_text, prune_pre_checkpoint_items
|
|
|
|
|
|
_IMAGE_URL = "data:image/png;base64,AAAA"
|
|
_CHAT_IMAGE_PART = {"type": "image_url", "image_url": {"url": _IMAGE_URL}}
|
|
_RESPONSES_IMAGE_PART = {"type": "input_image", "image_url": _IMAGE_URL}
|
|
_CHECKPOINT = {"type": "compaction", "encrypted_content": "blob_cp"}
|
|
|
|
|
|
def test_extract_item_text_remains_text_only_for_image_content():
|
|
image_only = {"content": [_RESPONSES_IMAGE_PART]}
|
|
|
|
assert _extract_item_text(image_only) is None
|
|
assert _extract_item_text({"content": []}) is None
|
|
|
|
|
|
def test_image_only_user_message_survives_pre_checkpoint_pruning_verbatim():
|
|
image_only = {"role": "user", "content": [_RESPONSES_IMAGE_PART]}
|
|
items = [
|
|
image_only,
|
|
_CHECKPOINT,
|
|
{"role": "user", "content": "after checkpoint"},
|
|
]
|
|
|
|
pruned = prune_pre_checkpoint_items(items, retained_user_token_budget=1)
|
|
|
|
assert pruned == [
|
|
_CHECKPOINT,
|
|
image_only,
|
|
{"role": "user", "content": "after checkpoint"},
|
|
]
|
|
assert pruned[1] is image_only
|
|
|
|
|
|
def test_image_only_user_message_still_obeys_retention_budget():
|
|
image_only = {"role": "user", "content": [_RESPONSES_IMAGE_PART]}
|
|
|
|
assert prune_pre_checkpoint_items(
|
|
[image_only, _CHECKPOINT],
|
|
retained_user_token_budget=0,
|
|
) == [_CHECKPOINT]
|
|
|
|
|
|
def test_malformed_or_unknown_multipart_is_not_retained():
|
|
invalid_contents = [
|
|
[{}],
|
|
[{"type": "input_image", "image_url": ""}],
|
|
[{"type": "unknown", "value": "not an attachment"}],
|
|
]
|
|
|
|
for content in invalid_contents:
|
|
malformed = {"role": "user", "content": content}
|
|
assert prune_pre_checkpoint_items(
|
|
[malformed, _CHECKPOINT],
|
|
retained_user_token_budget=1,
|
|
) == [_CHECKPOINT]
|
|
|
|
|
|
def test_adapter_preserves_image_only_user_message_across_checkpoint():
|
|
messages = [
|
|
{"role": "user", "content": [_CHAT_IMAGE_PART]},
|
|
{
|
|
"role": "assistant",
|
|
"content": "checkpoint turn",
|
|
"codex_reasoning_items": [_CHECKPOINT],
|
|
},
|
|
{"role": "user", "content": "after checkpoint"},
|
|
]
|
|
|
|
converted = _chat_messages_to_responses_input(
|
|
messages,
|
|
native_compaction_eligible=True,
|
|
)
|
|
|
|
assert converted == [
|
|
_CHECKPOINT,
|
|
{"role": "user", "content": [_RESPONSES_IMAGE_PART]},
|
|
{"role": "assistant", "content": "checkpoint turn"},
|
|
{"role": "user", "content": "after checkpoint"},
|
|
]
|
|
|
|
|
|
def test_image_only_user_message_is_retained_with_interleaved_assistant():
|
|
image_user = {
|
|
"role": "user",
|
|
"content": [_RESPONSES_IMAGE_PART],
|
|
}
|
|
items = [
|
|
image_user,
|
|
{"role": "assistant", "content": "I see the screenshot."},
|
|
_CHECKPOINT,
|
|
{"role": "user", "content": "what was in that screenshot?"},
|
|
]
|
|
out = prune_pre_checkpoint_items(items)
|
|
assert out[0] == _CHECKPOINT
|
|
assert out[1] == image_user
|
|
assert out[2] == {"role": "user", "content": "what was in that screenshot?"}
|