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).
89 lines
3.3 KiB
Python
89 lines
3.3 KiB
Python
"""Tests for per-model reasoning_effort override in cron scheduler."""
|
|
|
|
import pytest
|
|
|
|
|
|
class TestCronPerModelReasoningConfig:
|
|
"""Test cron scheduler respects per-model reasoning overrides.
|
|
|
|
Rather than spinning up a full CronScheduler (heavy), we verify the
|
|
resolution logic by testing the helper directly against a config dict
|
|
shaped the same way the scheduler reads it.
|
|
"""
|
|
|
|
def test_per_model_override_resolves_for_cron_model(self):
|
|
"""The spelling-tolerant helper resolves the cron config's model."""
|
|
from hermes_constants import resolve_per_model_reasoning_effort
|
|
|
|
# Simulate cron scheduler config shape
|
|
_cfg = {
|
|
"model": {"default": "anthropic/claude-opus-4.5"},
|
|
"agent": {
|
|
"reasoning_effort": "medium",
|
|
"reasoning_overrides": {
|
|
"anthropic/claude-opus-4.5": "xhigh",
|
|
},
|
|
},
|
|
}
|
|
_model_cfg = _cfg.get("model", {})
|
|
_model = str(_model_cfg.get("default", "") or "").strip()
|
|
_overrides = (_cfg.get("agent", {}) or {}).get("reasoning_overrides", {}) or {}
|
|
|
|
result = resolve_per_model_reasoning_effort(_model, _overrides)
|
|
assert result is not None
|
|
assert result["effort"] == "xhigh"
|
|
|
|
def test_cron_falls_back_to_global_when_no_override(self):
|
|
"""When no per-model override matches, global effort is used."""
|
|
from hermes_constants import parse_reasoning_effort, resolve_per_model_reasoning_effort
|
|
|
|
_cfg = {
|
|
"model": {"default": "gpt-5"},
|
|
"agent": {
|
|
"reasoning_effort": "low",
|
|
"reasoning_overrides": {
|
|
"anthropic/claude-opus-4.5": "xhigh",
|
|
},
|
|
},
|
|
}
|
|
_model = _cfg["model"]["default"]
|
|
_overrides = _cfg["agent"]["reasoning_overrides"]
|
|
|
|
per_model = resolve_per_model_reasoning_effort(_model, _overrides)
|
|
assert per_model is None # no match
|
|
|
|
# Scheduler falls back to global
|
|
effort = _cfg["agent"]["reasoning_effort"]
|
|
result = parse_reasoning_effort(effort)
|
|
assert result is not None
|
|
assert result["effort"] == "low"
|
|
|
|
|
|
def test_global_fallback_with_yaml_false(self):
|
|
"""YAML boolean False must reach parse_reasoning_effort uncoerced.
|
|
|
|
Regression: str(... or "").strip() turned False into "", silently
|
|
re-enabling thinking. The raw value must pass through so
|
|
parse_reasoning_effort(False) returns {'enabled': False}.
|
|
"""
|
|
from hermes_constants import parse_reasoning_effort, resolve_per_model_reasoning_effort
|
|
|
|
_cfg = {
|
|
"model": {"default": "gpt-5"},
|
|
"agent": {
|
|
"reasoning_effort": False, # YAML boolean, not string
|
|
"reasoning_overrides": {"claude-opus-4.5": "xhigh"},
|
|
},
|
|
}
|
|
_model = _cfg["model"]["default"]
|
|
_overrides = _cfg["agent"]["reasoning_overrides"]
|
|
|
|
per_model = resolve_per_model_reasoning_effort(_model, _overrides)
|
|
assert per_model is None # no match
|
|
|
|
# Scheduler global fallback — raw value, no coercion
|
|
result = parse_reasoning_effort(
|
|
_cfg.get("agent", {}).get("reasoning_effort", "")
|
|
)
|
|
assert result is not None
|
|
assert result.get("enabled") is False
|