mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-04-26 01:01:40 +00:00
refactor: remove smart_model_routing feature (#12732)
Smart model routing (auto-routing short/simple turns to a cheap model across providers) was opt-in and disabled by default. This removes the feature wholesale: the routing module, its config keys, docs, tests, and the orchestration scaffolding it required in cli.py / gateway/run.py / cron/scheduler.py. The /fast (Priority Processing / Anthropic fast mode) feature kept its hooks into _resolve_turn_agent_config — those still build a route dict and attach request_overrides when the model supports it; the route now just always uses the session's primary model/provider rather than running prompts through choose_cheap_model_route() first. Also removed: - DEFAULT_CONFIG['smart_model_routing'] block and matching commented-out example sections in hermes_cli/config.py and cli-config.yaml.example - _load_smart_model_routing() / self._smart_model_routing on GatewayRunner - self._smart_model_routing / self._active_agent_route_signature on HermesCLI (signature kept; just no longer initialised through the smart-routing pipeline) - route_label parameter on HermesCLI._init_agent (only set by smart routing; never read elsewhere) - 'Smart Model Routing' section in website/docs/integrations/providers.md - tip in hermes_cli/tips.py - entries in hermes_cli/dump.py + hermes_cli/web_server.py - row in skills/autonomous-ai-agents/hermes-agent/SKILL.md Tests: - Deleted tests/agent/test_smart_model_routing.py - Rewrote tests/agent/test_credential_pool_routing.py to target the simplified _resolve_turn_agent_config directly (preserves credential pool propagation + 429 rotation coverage) - Dropped 'cheap model' test from test_cli_provider_resolution.py - Dropped resolve_turn_route patches from cli + gateway test_fast_command — they now exercise the real method end-to-end - Removed _smart_model_routing stub assignments from gateway/cron test helpers Targeted suites: 74/74 in the directly affected test files; tests/agent + tests/cron + tests/cli pass except 5 failures that already exist on main (cron silent-delivery + alias quick-command).
This commit is contained in:
parent
5f0a91f31a
commit
424e9f36b0
18 changed files with 96 additions and 664 deletions
|
|
@ -4,7 +4,7 @@ import sys
|
|||
import threading
|
||||
import types
|
||||
from types import SimpleNamespace
|
||||
from unittest.mock import AsyncMock, patch
|
||||
from unittest.mock import AsyncMock
|
||||
|
||||
import pytest
|
||||
import yaml
|
||||
|
|
@ -53,7 +53,6 @@ def _make_runner():
|
|||
runner._service_tier = None
|
||||
runner._provider_routing = {}
|
||||
runner._fallback_model = None
|
||||
runner._smart_model_routing = {}
|
||||
runner._running_agents = {}
|
||||
runner._pending_model_notes = {}
|
||||
runner._session_db = None
|
||||
|
|
@ -97,13 +96,7 @@ def test_turn_route_injects_priority_processing_without_changing_runtime():
|
|||
"credential_pool": None,
|
||||
}
|
||||
|
||||
with patch("agent.smart_model_routing.resolve_turn_route", return_value={
|
||||
"model": "gpt-5.4",
|
||||
"runtime": dict(runtime_kwargs),
|
||||
"label": None,
|
||||
"signature": ("gpt-5.4", "openrouter", "https://openrouter.ai/api/v1", "chat_completions", None, ()),
|
||||
}):
|
||||
route = gateway_run.GatewayRunner._resolve_turn_agent_config(runner, "hi", "gpt-5.4", runtime_kwargs)
|
||||
route = gateway_run.GatewayRunner._resolve_turn_agent_config(runner, "hi", "gpt-5.4", runtime_kwargs)
|
||||
|
||||
assert route["runtime"]["provider"] == "openrouter"
|
||||
assert route["runtime"]["api_mode"] == "chat_completions"
|
||||
|
|
@ -123,13 +116,7 @@ def test_turn_route_skips_priority_processing_for_unsupported_models():
|
|||
"credential_pool": None,
|
||||
}
|
||||
|
||||
with patch("agent.smart_model_routing.resolve_turn_route", return_value={
|
||||
"model": "gpt-5.3-codex",
|
||||
"runtime": dict(runtime_kwargs),
|
||||
"label": None,
|
||||
"signature": ("gpt-5.3-codex", "openrouter", "https://openrouter.ai/api/v1", "chat_completions", None, ()),
|
||||
}):
|
||||
route = gateway_run.GatewayRunner._resolve_turn_agent_config(runner, "hi", "gpt-5.3-codex", runtime_kwargs)
|
||||
route = gateway_run.GatewayRunner._resolve_turn_agent_config(runner, "hi", "gpt-5.3-codex", runtime_kwargs)
|
||||
|
||||
assert route["request_overrides"] is None
|
||||
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue