perf(ttft): salvage easy-win startup optimizations from #3346 (#3395)

* perf(ttft): dedupe shared tool availability checks

* perf(ttft): short-circuit vision auto-resolution

* perf(ttft): make Claude Code version detection lazy

* perf(ttft): reuse loaded toolsets for skills prompt

---------

Co-authored-by: kshitijk4poor <82637225+kshitijk4poor@users.noreply.github.com>
This commit is contained in:
Teknium
2026-03-27 07:49:44 -07:00
committed by GitHub
parent 41d9d08078
commit 5a1e2a307a
7 changed files with 124 additions and 12 deletions

View File

@@ -11,6 +11,7 @@ from agent.auxiliary_client import (
get_text_auxiliary_client,
get_vision_auxiliary_client,
get_available_vision_backends,
resolve_vision_provider_client,
resolve_provider_client,
auxiliary_max_tokens_param,
_read_codex_access_token,
@@ -638,6 +639,30 @@ class TestVisionClientFallback:
assert client.__class__.__name__ == "AnthropicAuxiliaryClient"
assert model == "claude-haiku-4-5-20251001"
def test_selected_codex_provider_short_circuits_vision_auto(self, monkeypatch):
def fake_load_config():
return {"model": {"provider": "openai-codex", "default": "gpt-5.2-codex"}}
codex_client = MagicMock()
with (
patch("hermes_cli.config.load_config", fake_load_config),
patch("agent.auxiliary_client._try_codex", return_value=(codex_client, "gpt-5.2-codex")) as mock_codex,
patch("agent.auxiliary_client._try_openrouter") as mock_openrouter,
patch("agent.auxiliary_client._try_nous") as mock_nous,
patch("agent.auxiliary_client._try_anthropic") as mock_anthropic,
patch("agent.auxiliary_client._try_custom_endpoint") as mock_custom,
):
provider, client, model = resolve_vision_provider_client()
assert provider == "openai-codex"
assert client is codex_client
assert model == "gpt-5.2-codex"
mock_codex.assert_called_once()
mock_openrouter.assert_not_called()
mock_nous.assert_not_called()
mock_anthropic.assert_not_called()
mock_custom.assert_not_called()
def test_vision_auto_includes_codex(self, codex_auth_dir):
"""Codex supports vision (gpt-5.3-codex), so auto mode should use it."""
with patch("agent.auxiliary_client._read_nous_auth", return_value=None), \

View File

@@ -584,6 +584,38 @@ class TestBuildSystemPrompt:
# Should contain current date info like "Conversation started:"
assert "Conversation started:" in prompt
def test_skills_prompt_derives_available_toolsets_from_loaded_tools(self):
tools = _make_tool_defs("web_search", "skills_list", "skill_view", "skill_manage")
toolset_map = {
"web_search": "web",
"skills_list": "skills",
"skill_view": "skills",
"skill_manage": "skills",
}
with (
patch("run_agent.get_tool_definitions", return_value=tools),
patch(
"run_agent.check_toolset_requirements",
side_effect=AssertionError("should not re-check toolset requirements"),
),
patch("run_agent.get_toolset_for_tool", create=True, side_effect=toolset_map.get),
patch("run_agent.build_skills_system_prompt", return_value="SKILLS_PROMPT") as mock_skills,
patch("run_agent.OpenAI"),
):
agent = AIAgent(
api_key="test-k...7890",
quiet_mode=True,
skip_context_files=True,
skip_memory=True,
)
prompt = agent._build_system_prompt()
assert "SKILLS_PROMPT" in prompt
assert mock_skills.call_args.kwargs["available_tools"] == set(toolset_map)
assert mock_skills.call_args.kwargs["available_toolsets"] == {"web", "skills"}
class TestInvalidateSystemPrompt:
def test_clears_cache(self, agent):

View File

@@ -81,6 +81,33 @@ class TestGetDefinitions:
assert len(defs) == 1
assert defs[0]["function"]["name"] == "available"
def test_reuses_shared_check_fn_once_per_call(self):
reg = ToolRegistry()
calls = {"count": 0}
def shared_check():
calls["count"] += 1
return True
reg.register(
name="first",
toolset="shared",
schema=_make_schema("first"),
handler=_dummy_handler,
check_fn=shared_check,
)
reg.register(
name="second",
toolset="shared",
schema=_make_schema("second"),
handler=_dummy_handler,
check_fn=shared_check,
)
defs = reg.get_definitions({"first", "second"})
assert len(defs) == 2
assert calls["count"] == 1
class TestUnknownToolDispatch:
def test_returns_error_json(self):