mirror of
https://github.com/agent0ai/agent-zero.git
synced 2026-10-18 07:52:15 +00:00
cc098d3e98
Reuse Git version metadata within each chat-load operation and pass saved message token counts into reconstruction. Preserve per-agent settings and credential reads, initialization hooks, profiles and legacy token behavior. Give the existing deferred embedding preload up to 10 extra seconds after chat restoration, within extensible init_a0. Continue startup on timeout or task failure while allowing unfinished model loading to complete. Across five trials per version with the same chat workload and a cached embedding model, median HTTP readiness after the restart command returned fell from 38.1 to 27.8 seconds: 10.3 seconds saved, or 27% less waiting. Boot-to-first-token fell from 42.7 to 33.4 seconds. Post-send first-token latency did not improve in this sample (4.709 to 5.108 seconds). Validation: 146 focused framework tests passed, followed by 20 preload tests including seven new edge cases. Real ten-second stalled-loading/inference checks and offline missing/cached-model checks passed. Five DeferredTask lifecycle tests passed separately; an existing test-order failure when combined with preload imports also reproduces without the new cases. Fresh-install performance was not measured; the full repository suite was not run.
56 lines
1.8 KiB
Python
56 lines
1.8 KiB
Python
import pytest
|
|
|
|
from helpers import history
|
|
from helpers.history import output_langchain
|
|
from langchain_core.messages import AIMessage, HumanMessage
|
|
|
|
|
|
def test_output_langchain_omits_leading_assistant_messages():
|
|
messages = output_langchain(
|
|
[
|
|
{"ai": True, "content": "Welcome"},
|
|
{"ai": False, "content": "Hello"},
|
|
{"ai": True, "content": "Hi"},
|
|
]
|
|
)
|
|
|
|
assert messages == [HumanMessage("Hello"), AIMessage("Hi")]
|
|
|
|
|
|
def test_restored_message_reuses_saved_tokens_and_summary(monkeypatch):
|
|
data = {
|
|
"_cls": "Message", "ai": False, "content": "original content",
|
|
"id": "message", "sequence": 2, "metadata": {"custom": True},
|
|
"summary": "saved summary", "tokens": 42,
|
|
}
|
|
|
|
def recount(_text):
|
|
pytest.fail("Restoring a saved count must not tokenize the message again")
|
|
|
|
monkeypatch.setattr(history.tokens, "approximate_tokens", recount)
|
|
restored = history.Message.from_dict(data, history=None)
|
|
|
|
assert restored.to_dict() == data
|
|
assert restored.get_tokens() == 42
|
|
assert restored.output()[0]["content"] == "saved summary"
|
|
|
|
|
|
@pytest.mark.parametrize("saved", [{}, {"tokens": 0}, {"tokens": None}])
|
|
def test_restored_message_without_token_count_recounts_using_summary(monkeypatch, saved):
|
|
counted = []
|
|
|
|
def count(text):
|
|
counted.append(text)
|
|
return 7
|
|
|
|
monkeypatch.setattr(history.tokens, "approximate_tokens", count)
|
|
restored = history.Message.from_dict(
|
|
{"ai": False, "content": "original", "summary": "summary", **saved},
|
|
history=None,
|
|
)
|
|
|
|
assert restored.tokens == saved.get("tokens", 0)
|
|
assert restored.get_tokens() == 7
|
|
assert counted == ["user: original", "user: summary"]
|
|
assert restored.get_tokens() == 7
|
|
assert len(counted) == 2
|