mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-07-22 16:25:58 +00:00
d9cdb81923
Add agent.reasoning_overrides dict to config.yaml. Users can now set
a reasoning_effort per model, overriding the global agent.reasoning_effort.
Example:
agent:
reasoning_effort: "medium" # global default
reasoning_overrides:
"openrouter/anthropic/claude-opus-4.5": "xhigh"
"openai/gpt-5": "low"
"claude-sonnet-4.6": "high" # bare model name also works
The helper is spelling-tolerant: override keys match regardless of
provider prefix or dots-vs-dashes normalization, so users can write
keys in any sensible form and they'll match.
Resolution priority:
1. Session-scoped /reasoning --session override (gateway only; unchanged)
2. Per-model override from agent.reasoning_overrides (spelling-tolerant)
3. Global agent.reasoning_effort (existing)
4. Provider default (unchanged)
Wired into:
- CLI startup (cli.py)
- Messaging gateway agent construction (gateway/run.py)
- Desktop/TUI _load_reasoning_config (tui_gateway/server.py)
- Cron job scheduler (cron/scheduler.py)
- /model mid-session switch (agent/agent_runtime_helpers.py)
+ _primary_runtime now tracks reasoning_config for correct fallback recovery
- Fallback activation (agent/chat_completion_helpers.py::try_activate_fallback)
+ Re-resolves reasoning_config for the fallback model (best-effort)
Closes #21256 (per-model reasoning_effort defaults).
Note: no hermes config set agent.reasoning_overrides.<model> support;
users edit the YAML directly. _set_nested splits on "." and would
corrupt model keys containing version dots.
106 lines
4.1 KiB
Python
106 lines
4.1 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_cron_handles_missing_model_key(self):
|
|
"""Works when config has no model.default."""
|
|
from hermes_constants import resolve_per_model_reasoning_effort
|
|
|
|
_cfg = {
|
|
"agent": {
|
|
"reasoning_effort": "medium",
|
|
"reasoning_overrides": {"claude-opus-4.5": "high"},
|
|
},
|
|
}
|
|
_model_cfg = _cfg.get("model", {}) if isinstance(_cfg.get("model", {}), dict) else {}
|
|
_model = str(_model_cfg.get("default", "") or _model_cfg.get("model", "") or "").strip()
|
|
_overrides = (_cfg.get("agent", {}) or {}).get("reasoning_overrides", {}) or {}
|
|
|
|
# Empty model → resolve returns None → scheduler uses global
|
|
result = resolve_per_model_reasoning_effort(_model, _overrides)
|
|
assert result is None
|
|
|
|
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
|