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.
49 lines
1.8 KiB
Python
49 lines
1.8 KiB
Python
"""Verify compression trigger excludes reasoning/completion tokens (#12026).
|
|
|
|
Thinking models (GLM-5.1, QwQ, DeepSeek R1) inflate completion_tokens with
|
|
reasoning tokens that don't consume context window space. The compression
|
|
trigger must use only prompt_tokens so sessions aren't prematurely split.
|
|
"""
|
|
|
|
import types
|
|
|
|
|
|
def _make_agent_stub(prompt_tokens, completion_tokens, threshold_tokens):
|
|
"""Create a minimal stub that exercises the compression check path."""
|
|
compressor = types.SimpleNamespace(
|
|
last_prompt_tokens=prompt_tokens,
|
|
last_completion_tokens=completion_tokens,
|
|
threshold_tokens=threshold_tokens,
|
|
)
|
|
# Replicate the fixed logic from run_agent.py ~line 11273
|
|
if compressor.last_prompt_tokens > 0:
|
|
real_tokens = compressor.last_prompt_tokens # Fixed: no completion
|
|
else:
|
|
real_tokens = 0
|
|
return real_tokens, compressor
|
|
|
|
|
|
class TestCompressionTriggerExcludesReasoning:
|
|
def test_high_reasoning_tokens_should_not_trigger_compression(self):
|
|
"""With the old bug, 40k prompt + 80k reasoning = 120k > 100k threshold.
|
|
After the fix, only 40k prompt is compared — no compression."""
|
|
real_tokens, comp = _make_agent_stub(
|
|
prompt_tokens=40_000,
|
|
completion_tokens=80_000, # reasoning-heavy model
|
|
threshold_tokens=100_000,
|
|
)
|
|
assert real_tokens == 40_000
|
|
assert real_tokens < comp.threshold_tokens, (
|
|
"Should NOT trigger compression — only prompt tokens matter"
|
|
)
|
|
|
|
|
|
def test_zero_prompt_tokens_falls_back(self):
|
|
"""When provider returns 0 prompt tokens, real_tokens is 0 (fallback path)."""
|
|
real_tokens, _ = _make_agent_stub(
|
|
prompt_tokens=0,
|
|
completion_tokens=50_000,
|
|
threshold_tokens=100_000,
|
|
)
|
|
assert real_tokens == 0
|