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:
Teknium
2026-04-19 18:12:55 -07:00
committed by GitHub
parent 5f0a91f31a
commit 424e9f36b0
18 changed files with 96 additions and 664 deletions

View File

@@ -1,129 +1,25 @@
"""Tests for credential pool preservation through smart routing and 429 recovery.
"""Tests for credential pool preservation through turn config and 429 recovery.
Covers:
1. credential_pool flows through resolve_turn_route (no-route and fallback paths)
2. CLI _resolve_turn_agent_config passes credential_pool to primary dict
3. Gateway _resolve_turn_agent_config passes credential_pool to primary dict
4. Eager fallback deferred when credential pool has credentials
5. Eager fallback fires when no credential pool exists
6. Full 429 rotation cycle: retry-same → rotate → exhaust → fallback
1. CLI _resolve_turn_agent_config passes credential_pool to runtime dict
2. Gateway _resolve_turn_agent_config passes credential_pool to runtime dict
3. Eager fallback deferred when credential pool has credentials
4. Eager fallback fires when no credential pool exists
5. Full 429 rotation cycle: retry-same → rotate → exhaust → fallback
"""
import os
import time
from types import SimpleNamespace
from unittest.mock import MagicMock, patch, PropertyMock
import pytest
from unittest.mock import MagicMock, patch
# ---------------------------------------------------------------------------
# 1. smart_model_routing: credential_pool preserved in no-route path
# ---------------------------------------------------------------------------
class TestSmartRoutingPoolPreservation:
def test_no_route_preserves_credential_pool(self):
from agent.smart_model_routing import resolve_turn_route
fake_pool = MagicMock(name="CredentialPool")
primary = {
"model": "gpt-5.4",
"api_key": "sk-test",
"base_url": None,
"provider": "openai-codex",
"api_mode": "codex_responses",
"command": None,
"args": [],
"credential_pool": fake_pool,
}
# routing disabled
result = resolve_turn_route("hello", None, primary)
assert result["runtime"]["credential_pool"] is fake_pool
def test_no_route_none_pool(self):
from agent.smart_model_routing import resolve_turn_route
primary = {
"model": "gpt-5.4",
"api_key": "sk-test",
"base_url": None,
"provider": "openai-codex",
"api_mode": "codex_responses",
"command": None,
"args": [],
}
result = resolve_turn_route("hello", None, primary)
assert result["runtime"]["credential_pool"] is None
def test_routing_disabled_preserves_pool(self):
from agent.smart_model_routing import resolve_turn_route
fake_pool = MagicMock(name="CredentialPool")
primary = {
"model": "gpt-5.4",
"api_key": "sk-test",
"base_url": None,
"provider": "openai-codex",
"api_mode": "codex_responses",
"command": None,
"args": [],
"credential_pool": fake_pool,
}
# routing explicitly disabled
result = resolve_turn_route("hello", {"enabled": False}, primary)
assert result["runtime"]["credential_pool"] is fake_pool
def test_route_fallback_on_resolve_error_preserves_pool(self, monkeypatch):
"""When smart routing picks a cheap model but resolve_runtime_provider
fails, the fallback to primary must still include credential_pool."""
from agent.smart_model_routing import resolve_turn_route
fake_pool = MagicMock(name="CredentialPool")
primary = {
"model": "gpt-5.4",
"api_key": "sk-test",
"base_url": None,
"provider": "openai-codex",
"api_mode": "codex_responses",
"command": None,
"args": [],
"credential_pool": fake_pool,
}
routing_config = {
"enabled": True,
"cheap_model": "openai/gpt-4.1-mini",
"cheap_provider": "openrouter",
"max_tokens": 200,
"patterns": ["^(hi|hello|hey)"],
}
# Force resolve_runtime_provider to fail so it falls back to primary
monkeypatch.setattr(
"hermes_cli.runtime_provider.resolve_runtime_provider",
MagicMock(side_effect=RuntimeError("no credentials")),
)
result = resolve_turn_route("hi", routing_config, primary)
assert result["runtime"]["credential_pool"] is fake_pool
# ---------------------------------------------------------------------------
# 2 & 3. CLI and Gateway _resolve_turn_agent_config include credential_pool
# 1. CLI _resolve_turn_agent_config includes credential_pool
# ---------------------------------------------------------------------------
class TestCliTurnRoutePool:
def test_resolve_turn_includes_pool(self, monkeypatch, tmp_path):
"""CLI's _resolve_turn_agent_config must pass credential_pool to primary."""
from agent.smart_model_routing import resolve_turn_route
captured = {}
def spy_resolve(user_message, routing_config, primary):
captured["primary"] = primary
return resolve_turn_route(user_message, routing_config, primary)
monkeypatch.setattr(
"agent.smart_model_routing.resolve_turn_route", spy_resolve
)
# Build a minimal HermesCLI-like object with the method
def test_resolve_turn_includes_pool(self):
"""CLI's _resolve_turn_agent_config must pass credential_pool in runtime."""
fake_pool = MagicMock(name="FakePool")
shell = SimpleNamespace(
model="gpt-5.4",
api_key="sk-test",
@@ -132,58 +28,46 @@ class TestCliTurnRoutePool:
api_mode="codex_responses",
acp_command=None,
acp_args=[],
_credential_pool=MagicMock(name="FakePool"),
_smart_model_routing={"enabled": False},
_credential_pool=fake_pool,
service_tier=None,
)
# Import and bind the real method
from cli import HermesCLI
bound = HermesCLI._resolve_turn_agent_config.__get__(shell)
bound("test message")
route = bound("test message")
assert "credential_pool" in captured["primary"]
assert captured["primary"]["credential_pool"] is shell._credential_pool
assert route["runtime"]["credential_pool"] is fake_pool
# ---------------------------------------------------------------------------
# 2. Gateway _resolve_turn_agent_config includes credential_pool
# ---------------------------------------------------------------------------
class TestGatewayTurnRoutePool:
def test_resolve_turn_includes_pool(self, monkeypatch):
def test_resolve_turn_includes_pool(self):
"""Gateway's _resolve_turn_agent_config must pass credential_pool."""
from agent.smart_model_routing import resolve_turn_route
captured = {}
def spy_resolve(user_message, routing_config, primary):
captured["primary"] = primary
return resolve_turn_route(user_message, routing_config, primary)
monkeypatch.setattr(
"agent.smart_model_routing.resolve_turn_route", spy_resolve
)
from gateway.run import GatewayRunner
runner = SimpleNamespace(
_smart_model_routing={"enabled": False},
)
fake_pool = MagicMock(name="FakePool")
runner = SimpleNamespace(_service_tier=None)
runtime_kwargs = {
"api_key": "sk-test",
"api_key": "***",
"base_url": None,
"provider": "openai-codex",
"api_mode": "codex_responses",
"command": None,
"args": [],
"credential_pool": MagicMock(name="FakePool"),
"credential_pool": fake_pool,
}
bound = GatewayRunner._resolve_turn_agent_config.__get__(runner)
bound("test message", "gpt-5.4", runtime_kwargs)
route = bound("test message", "gpt-5.4", runtime_kwargs)
assert "credential_pool" in captured["primary"]
assert captured["primary"]["credential_pool"] is runtime_kwargs["credential_pool"]
assert route["runtime"]["credential_pool"] is fake_pool
# ---------------------------------------------------------------------------
# 4 & 5. Eager fallback deferred/fires based on credential pool
# 3 & 4. Eager fallback deferred/fires based on credential pool
# ---------------------------------------------------------------------------
class TestEagerFallbackWithPool:
@@ -251,7 +135,7 @@ class TestEagerFallbackWithPool:
# ---------------------------------------------------------------------------
# 6. Full 429 rotation cycle via _recover_with_credential_pool
# 5. Full 429 rotation cycle via _recover_with_credential_pool
# ---------------------------------------------------------------------------
class TestPoolRotationCycle:

View File

@@ -1,61 +0,0 @@
from agent.smart_model_routing import choose_cheap_model_route
_BASE_CONFIG = {
"enabled": True,
"cheap_model": {
"provider": "openrouter",
"model": "google/gemini-2.5-flash",
},
}
def test_returns_none_when_disabled():
cfg = {**_BASE_CONFIG, "enabled": False}
assert choose_cheap_model_route("what time is it in tokyo?", cfg) is None
def test_routes_short_simple_prompt():
result = choose_cheap_model_route("what time is it in tokyo?", _BASE_CONFIG)
assert result is not None
assert result["provider"] == "openrouter"
assert result["model"] == "google/gemini-2.5-flash"
assert result["routing_reason"] == "simple_turn"
def test_skips_long_prompt():
prompt = "please summarize this carefully " * 20
assert choose_cheap_model_route(prompt, _BASE_CONFIG) is None
def test_skips_code_like_prompt():
prompt = "debug this traceback: ```python\nraise ValueError('bad')\n```"
assert choose_cheap_model_route(prompt, _BASE_CONFIG) is None
def test_skips_tool_heavy_prompt_keywords():
prompt = "implement a patch for this docker error"
assert choose_cheap_model_route(prompt, _BASE_CONFIG) is None
def test_resolve_turn_route_falls_back_to_primary_when_route_runtime_cannot_be_resolved(monkeypatch):
from agent.smart_model_routing import resolve_turn_route
monkeypatch.setattr(
"hermes_cli.runtime_provider.resolve_runtime_provider",
lambda **kwargs: (_ for _ in ()).throw(RuntimeError("bad route")),
)
result = resolve_turn_route(
"what time is it in tokyo?",
_BASE_CONFIG,
{
"model": "anthropic/claude-sonnet-4",
"provider": "openrouter",
"base_url": "https://openrouter.ai/api/v1",
"api_mode": "chat_completions",
"api_key": "sk-primary",
},
)
assert result["model"] == "anthropic/claude-sonnet-4"
assert result["runtime"]["provider"] == "openrouter"
assert result["label"] is None

View File

@@ -207,48 +207,11 @@ def test_cli_turn_routing_uses_primary_when_disabled(monkeypatch):
shell.api_mode = "chat_completions"
shell.base_url = "https://openrouter.ai/api/v1"
shell.api_key = "sk-primary"
shell._smart_model_routing = {"enabled": False}
result = shell._resolve_turn_agent_config("what time is it in tokyo?")
assert result["model"] == "gpt-5"
assert result["runtime"]["provider"] == "openrouter"
assert result["label"] is None
def test_cli_turn_routing_uses_cheap_model_when_simple(monkeypatch):
cli = _import_cli()
def _runtime_resolve(**kwargs):
assert kwargs["requested"] == "zai"
return {
"provider": "zai",
"api_mode": "chat_completions",
"base_url": "https://open.z.ai/api/v1",
"api_key": "cheap-key",
"source": "env/config",
}
monkeypatch.setattr("hermes_cli.runtime_provider.resolve_runtime_provider", _runtime_resolve)
shell = cli.HermesCLI(model="anthropic/claude-sonnet-4", compact=True, max_turns=1)
shell.provider = "openrouter"
shell.api_mode = "chat_completions"
shell.base_url = "https://openrouter.ai/api/v1"
shell.api_key = "primary-key"
shell._smart_model_routing = {
"enabled": True,
"cheap_model": {"provider": "zai", "model": "glm-5-air"},
"max_simple_chars": 160,
"max_simple_words": 28,
}
result = shell._resolve_turn_agent_config("what time is it in tokyo?")
assert result["model"] == "glm-5-air"
assert result["runtime"]["provider"] == "zai"
assert result["runtime"]["api_key"] == "cheap-key"
assert result["label"] is not None
def test_cli_prefers_config_provider_over_stale_env_override(monkeypatch):

View File

@@ -183,27 +183,10 @@ class TestFastModeRouting(unittest.TestCase):
acp_command=None,
acp_args=[],
_credential_pool=None,
_smart_model_routing={},
service_tier="priority",
)
original_runtime = {
"api_key": "***",
"base_url": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"api_mode": "chat_completions",
"command": None,
"args": [],
"credential_pool": None,
}
with patch("agent.smart_model_routing.resolve_turn_route", return_value={
"model": "gpt-5.4",
"runtime": dict(original_runtime),
"label": None,
"signature": ("gpt-5.4", "openrouter", "https://openrouter.ai/api/v1", "chat_completions", None, ()),
}):
route = cli_mod.HermesCLI._resolve_turn_agent_config(stub, "hi")
route = cli_mod.HermesCLI._resolve_turn_agent_config(stub, "hi")
# Provider should NOT have changed
assert route["runtime"]["provider"] == "openrouter"
@@ -222,26 +205,10 @@ class TestFastModeRouting(unittest.TestCase):
acp_command=None,
acp_args=[],
_credential_pool=None,
_smart_model_routing={},
service_tier="priority",
)
primary_route = {
"model": "gpt-5.3-codex",
"runtime": {
"api_key": "***",
"base_url": "https://openrouter.ai/api/v1",
"provider": "openrouter",
"api_mode": "chat_completions",
"command": None,
"args": [],
"credential_pool": None,
},
"label": None,
"signature": ("gpt-5.3-codex", "openrouter", "https://openrouter.ai/api/v1", "chat_completions", None, ()),
}
with patch("agent.smart_model_routing.resolve_turn_route", return_value=primary_route):
route = cli_mod.HermesCLI._resolve_turn_agent_config(stub, "hi")
route = cli_mod.HermesCLI._resolve_turn_agent_config(stub, "hi")
assert route["runtime"]["provider"] == "openrouter"
assert route.get("request_overrides") is None
@@ -329,27 +296,10 @@ class TestAnthropicFastMode(unittest.TestCase):
acp_command=None,
acp_args=[],
_credential_pool=None,
_smart_model_routing={},
service_tier="priority",
)
original_runtime = {
"api_key": "***",
"base_url": "https://api.anthropic.com",
"provider": "anthropic",
"api_mode": "anthropic_messages",
"command": None,
"args": [],
"credential_pool": None,
}
with patch("agent.smart_model_routing.resolve_turn_route", return_value={
"model": "claude-opus-4-6",
"runtime": dict(original_runtime),
"label": None,
"signature": ("claude-opus-4-6", "anthropic", "https://api.anthropic.com", "anthropic_messages", None, ()),
}):
route = cli_mod.HermesCLI._resolve_turn_agent_config(stub, "hi")
route = cli_mod.HermesCLI._resolve_turn_agent_config(stub, "hi")
assert route["runtime"]["provider"] == "anthropic"
assert route["request_overrides"] == {"speed": "fast"}

View File

@@ -152,7 +152,6 @@ def test_gateway_run_agent_codex_path_handles_internal_401_refresh(monkeypatch):
runner._provider_routing = {}
runner._fallback_model = None
runner._running_agents = {}
runner._smart_model_routing = {}
from unittest.mock import MagicMock, AsyncMock
runner.hooks = MagicMock()
runner.hooks.emit = AsyncMock()

View File

@@ -75,7 +75,6 @@ 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

View File

@@ -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