hermes-agent/tests/tools/test_budget_config.py
Teknium 39975613b1
test: prune wave 2 + speed fixes — 28,106 → 19,757 test functions, suite wall 315s → 294s
Second, deeper pass over tools/gateway/hermes_cli plus first pass over
the trees wave 1 missed (acp, acp_adapter, skills, computer_use, docker,
dashboard, conformance, monitoring, secret_sources, hermes_state,
providers). Same rubric as wave 1 (AGENTS.md test policy); security,
alternation/caching invariants, issue-number regressions, and E2E kept.

Real test-quality fixes found and rooted out along the way:
- tests/tools/test_command_guards.py made real auxiliary-LLM HTTPS calls
  (DEFAULT_CONFIG smart-approval leaked in) — pinned approval
  mode=manual via autouse fixture: 17.4s → 0.4s.
- test_model_switch_custom_providers.py / test_user_providers_model_switch.py
  silently probed live provider catalogs (~2s/test) — stubbed
  cached_provider_model_ids/provider_model_ids/fetch_api_models.
- test_telegram_noise_filter.py: 15-platform copy-paste matrix over
  shared gateway.run logic → 3 representative platforms (55s → 3.9s).
- test_gateway_shutdown.py: stop()'s 5s interrupt-deadline loop spun on
  MagicMock agents — interrupt.side_effect now clears _running_agents
  (22s → 1.0s).
- test_gateway_inactivity_timeout.py poll-harness timings shrunk 3-5x
  (24s → 1.1s); test_mcp_stability.py backoff/SIGTERM-grace sleeps
  patched (15.4s → 2.5s); test_async_delegation.py negative-drain wait
  5s → 0.5s.
- test_telegram_init_deadline.py: loop-block margin restored to 1.0s
  with rationale comment — the watchdog-dump assertion needs the loop
  blocked well past deadline+grace under parallel load (flaked once in
  the 40-worker verification run at a 0.2s margin).

Verification: full hermetic suite via scripts/run_tests.sh —
2,438 files, 21,718 tests passed, 0 failed, 293.9s wall.
Suite totals vs original baseline: 46,820 → 19,757 test functions
(−57.8%), wall 583.5s → 293.9s (−50%), subprocess CPU 13,564s → 11,623s.
2026-07-29 13:39:40 -07:00

175 lines
5.9 KiB
Python
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

"""Unit tests for tools/budget_config.py.
Covers default values, resolve_threshold() priority chain
(pinned > tool_overrides > registry > default), immutability,
and the PINNED_THRESHOLDS escape-hatch for read_file.
"""
import dataclasses
import math
from unittest.mock import patch
import pytest
from tools.budget_config import (
DEFAULT_BUDGET,
DEFAULT_PREVIEW_SIZE_CHARS,
DEFAULT_RESULT_SIZE_CHARS,
DEFAULT_TURN_BUDGET_CHARS,
PINNED_THRESHOLDS,
BudgetConfig,
budget_for_context_window,
)
# ---------------------------------------------------------------------------
# Module-level constants
# ---------------------------------------------------------------------------
class TestModuleConstants:
"""Verify documented default values haven't drifted."""
def test_default_result_size(self):
assert DEFAULT_RESULT_SIZE_CHARS == 100_000
def test_default_preview_size(self):
assert DEFAULT_PREVIEW_SIZE_CHARS == 1_500
class TestPinnedThresholds:
"""PINNED_THRESHOLDS tools whose values must never be overridden."""
def test_read_file_is_inf(self):
assert PINNED_THRESHOLDS["read_file"] == float("inf")
assert math.isinf(PINNED_THRESHOLDS["read_file"])
def test_pinned_is_not_empty(self):
assert len(PINNED_THRESHOLDS) >= 1
# ---------------------------------------------------------------------------
# BudgetConfig defaults
# ---------------------------------------------------------------------------
class TestBudgetConfigDefaults:
"""BudgetConfig() should match the module-level defaults exactly."""
def test_default_result_size(self):
cfg = BudgetConfig()
assert cfg.default_result_size == DEFAULT_RESULT_SIZE_CHARS
def test_default_budget_singleton_matches(self):
"""DEFAULT_BUDGET should equal a freshly constructed BudgetConfig."""
assert DEFAULT_BUDGET == BudgetConfig()
# ---------------------------------------------------------------------------
# Immutability (frozen=True)
# ---------------------------------------------------------------------------
class TestBudgetConfigFrozen:
"""Frozen dataclass must reject attribute mutation."""
def test_cannot_set_default_result_size(self):
cfg = BudgetConfig()
with pytest.raises(dataclasses.FrozenInstanceError):
cfg.default_result_size = 999
def test_cannot_set_tool_overrides(self):
cfg = BudgetConfig()
with pytest.raises(dataclasses.FrozenInstanceError):
cfg.tool_overrides = {"foo": 1}
# ---------------------------------------------------------------------------
# Custom construction
# ---------------------------------------------------------------------------
class TestBudgetConfigCustom:
"""BudgetConfig can be created with non-default values."""
def test_custom_values(self):
cfg = BudgetConfig(
default_result_size=50_000,
turn_budget=100_000,
preview_size=500,
tool_overrides={"my_tool": 42},
)
assert cfg.default_result_size == 50_000
assert cfg.turn_budget == 100_000
assert cfg.preview_size == 500
assert cfg.tool_overrides == {"my_tool": 42}
# ---------------------------------------------------------------------------
# resolve_threshold() priority chain
# ---------------------------------------------------------------------------
class TestResolveThreshold:
"""Priority: pinned > tool_overrides > registry > default."""
def test_pinned_wins_over_override(self):
"""Even if tool_overrides contains read_file, pinned value wins."""
cfg = BudgetConfig(tool_overrides={"read_file": 1})
result = cfg.resolve_threshold("read_file")
assert result == float("inf")
def test_tool_override_wins_over_default(self):
"""tool_overrides should be returned before falling back to registry."""
cfg = BudgetConfig(tool_overrides={"my_tool": 42})
result = cfg.resolve_threshold("my_tool")
assert result == 42
@patch("tools.registry.registry")
def test_registry_value_capped_at_default(self, mock_registry):
"""A scaled-down budget caps an oversized registry value (#23767).
web/terminal/x_search register max_result_size_chars=100_000; a small
model's scaled budget must not be re-inflated by that.
"""
mock_registry.get_max_result_size.return_value = 100_000
cfg = BudgetConfig(default_result_size=30_000)
assert cfg.resolve_threshold("web_search") == 30_000
@patch("tools.registry.registry")
def test_default_budget_unchanged_for_100k_tool(self, mock_registry):
"""Default budget keeps 100K registry tools at 100K (no behavior change)."""
mock_registry.get_max_result_size.return_value = 100_000
cfg = BudgetConfig() # default_result_size == 100_000
assert cfg.resolve_threshold("web_search") == 100_000
# ---------------------------------------------------------------------------
# budget_for_context_window() — context-aware scaling (#23767)
# ---------------------------------------------------------------------------
class TestBudgetForContextWindow:
"""Scaling the tool-output budget to the active model's context window."""
def test_none_returns_default(self):
assert budget_for_context_window(None) is DEFAULT_BUDGET
def test_zero_or_negative_returns_default(self):
assert budget_for_context_window(0) is DEFAULT_BUDGET
assert budget_for_context_window(-5) is DEFAULT_BUDGET
def test_scaled_budget_constrains_oversized_result(self):
"""A 279K-char result against a 65K model exceeds the scaled per-result
threshold, so it will be persisted/truncated rather than sent whole."""
cfg = budget_for_context_window(65_536)
huge_len = 279_549
threshold = cfg.resolve_threshold("mcp_firecrawl_firecrawl_search")
assert threshold < huge_len
assert cfg.default_result_size < huge_len