mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-07-25 17:04:52 +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.
100 lines
3.7 KiB
Python
100 lines
3.7 KiB
Python
"""Tests for per-model reasoning_effort override in TUI gateway _load_reasoning_config."""
|
|
|
|
import pytest
|
|
|
|
import tui_gateway.server as tui_server
|
|
|
|
|
|
class TestTUIPerModelReasoningConfig:
|
|
"""Test tui_gateway _load_reasoning_config respects per-model overrides."""
|
|
|
|
def test_per_model_override_takes_precedence(self, monkeypatch):
|
|
"""Per-model override wins over global reasoning_effort."""
|
|
fake_cfg = {
|
|
"model": {"default": "anthropic/claude-opus-4.5"},
|
|
"agent": {
|
|
"reasoning_effort": "medium",
|
|
"reasoning_overrides": {
|
|
"anthropic/claude-opus-4.5": "xhigh",
|
|
},
|
|
},
|
|
}
|
|
monkeypatch.setattr(tui_server, "_load_cfg", lambda: fake_cfg)
|
|
|
|
result = tui_server._load_reasoning_config()
|
|
assert result is not None
|
|
assert result["enabled"] is True
|
|
assert result["effort"] == "xhigh"
|
|
|
|
def test_global_fallback_when_no_override(self, monkeypatch):
|
|
"""Global reasoning_effort applies when no per-model override matches."""
|
|
fake_cfg = {
|
|
"model": {"default": "gpt-5"},
|
|
"agent": {
|
|
"reasoning_effort": "high",
|
|
"reasoning_overrides": {
|
|
"anthropic/claude-opus-4.5": "xhigh",
|
|
},
|
|
},
|
|
}
|
|
monkeypatch.setattr(tui_server, "_load_cfg", lambda: fake_cfg)
|
|
|
|
result = tui_server._load_reasoning_config()
|
|
assert result is not None
|
|
assert result["effort"] == "high"
|
|
|
|
def test_spelling_tolerant_match(self, monkeypatch):
|
|
"""Override matches even with different spelling (provider prefix)."""
|
|
fake_cfg = {
|
|
"model": {"default": "claude-opus-4.5"},
|
|
"agent": {
|
|
"reasoning_effort": "medium",
|
|
"reasoning_overrides": {
|
|
"anthropic/claude-opus-4.5": "high", # key has prefix, model doesn't
|
|
},
|
|
},
|
|
}
|
|
monkeypatch.setattr(tui_server, "_load_cfg", lambda: fake_cfg)
|
|
|
|
result = tui_server._load_reasoning_config()
|
|
assert result is not None
|
|
assert result["effort"] == "high"
|
|
|
|
def test_parity_with_gateway_loader(self, monkeypatch):
|
|
"""TUI and gateway loaders return identical results for same config."""
|
|
import gateway.run as gateway_run
|
|
|
|
fake_cfg = {
|
|
"model": {"default": "openrouter/anthropic/claude-sonnet-4.6"},
|
|
"agent": {
|
|
"reasoning_effort": "low",
|
|
"reasoning_overrides": {
|
|
"claude-sonnet-4.6": "high",
|
|
},
|
|
},
|
|
}
|
|
monkeypatch.setattr(tui_server, "_load_cfg", lambda: fake_cfg)
|
|
monkeypatch.setattr(gateway_run, "_load_gateway_runtime_config", lambda: fake_cfg)
|
|
|
|
tui_result = tui_server._load_reasoning_config()
|
|
gw_result = gateway_run.GatewayRunner._load_reasoning_config()
|
|
assert tui_result == gw_result
|
|
|
|
def test_global_fallback_with_yaml_false(self, monkeypatch):
|
|
"""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}.
|
|
"""
|
|
fake_cfg = {
|
|
"model": {"default": "gpt-5"},
|
|
"agent": {
|
|
"reasoning_effort": False, # YAML boolean, not string
|
|
},
|
|
}
|
|
monkeypatch.setattr(tui_server, "_load_cfg", lambda: fake_cfg)
|
|
|
|
result = tui_server._load_reasoning_config()
|
|
assert result is not None
|
|
assert result.get("enabled") is False
|