Files
odysseus/tests/test_streamed_tool_markup.py
T

129 lines
4.8 KiB
Python

from src.agent_loop import (
_streamed_tool_markup_complete,
_streamed_tool_markup_starts,
_strip_incomplete_tool_markup_tail,
)
from src.tool_parsing import strip_tool_blocks
def test_dsml_tool_markup_is_complete_only_after_closing_tag():
start = "<||DSML||tool_calls><||DSML||invoke name=\"host_shell\">"
assert not _streamed_tool_markup_complete(start)
assert _streamed_tool_markup_complete(start + "</||DSML||invoke>")
def test_dsml_tool_markup_strips_to_empty_visible_text():
markup = (
"<||DSML||tool_calls>"
"<||DSML||invoke name=\"host_shell\">"
"<||DSML||parameter name=\"command\" string=\"true\">pwd"
"</||DSML||parameter>"
"</||DSML||invoke>"
"</||DSML||tool_calls>"
)
assert strip_tool_blocks(markup, skip_fenced=True) == ""
def test_chunk_split_tool_call_prefix_is_buffered_and_not_persisted():
assert _streamed_tool_markup_starts('I will search<tool_cal')
assert _strip_incomplete_tool_markup_tail('I will search<tool_cal') == 'I will search'
def test_bare_less_than_and_comparison_operators_false_alarm_recognition():
# A bare "<" starts buffering because it could be a tool-call tag prefix like "<tool_call>"
assert _streamed_tool_markup_starts(' <')
assert _streamed_tool_markup_starts('x <')
assert _streamed_tool_markup_starts('<tool_call')
assert _streamed_tool_markup_starts('<invoke')
# Once subsequent characters arrive and cannot become a tool-call tag, false alarm is detected
assert not _streamed_tool_markup_starts(' < 2')
assert not _streamed_tool_markup_starts('x < 2')
assert not _streamed_tool_markup_starts('len(items) < 2')
assert not _streamed_tool_markup_starts(' < 2:')
assert not _streamed_tool_markup_starts('x <= y')
assert not _streamed_tool_markup_starts('a < b')
async def test_stream_agent_loop_does_not_truncate_at_less_than_operator(monkeypatch):
import json
import src.agent_loop as al
async def fake_stream(*args, **kwargs):
for d in ["def is_short(items):\n", " return len(items)", " <", " 2\n"]:
yield "data: " + json.dumps({"delta": d}) + "\n\n"
yield "data: [DONE]\n\n"
monkeypatch.setattr(al, "get_setting", lambda k, d=None: d, raising=False)
monkeypatch.setattr(al, "get_mcp_manager", lambda: None, raising=False)
monkeypatch.setattr(al, "estimate_tokens", lambda *a, **k: 10, raising=False)
monkeypatch.setattr(al, "stream_llm_with_fallback", fake_stream, raising=False)
deltas = []
async for chunk in al.stream_agent_loop(
"http://local.test/v1",
"qwen3.6-35b-a3b-heretic",
[{"role": "user", "content": "Write python function"}],
max_rounds=1,
owner="test_user",
):
for line in chunk.split("\n"):
line = line.strip()
if line.startswith("data: ") and line[6:] != "[DONE]":
try:
payload = json.loads(line[6:])
if "delta" in payload:
deltas.append(payload["delta"])
except Exception:
pass
full_text = "".join(deltas)
assert full_text == "def is_short(items):\n return len(items) < 2\n"
async def test_stream_agent_loop_still_hides_real_tool_markup(monkeypatch):
import json
import src.agent_loop as al
async def fake_stream(*args, **kwargs):
chunks = [
"Sure.",
" <",
"tool",
"_call",
'>{"name":"host_shell","arguments":{"command":"pwd"}}',
"</",
"tool",
"_call",
">",
" done",
]
for c in chunks:
yield "data: " + json.dumps({"delta": c}) + "\n\n"
yield "data: [DONE]\n\n"
monkeypatch.setattr(al, "get_setting", lambda k, d=None: d, raising=False)
monkeypatch.setattr(al, "get_mcp_manager", lambda: None, raising=False)
monkeypatch.setattr(al, "estimate_tokens", lambda *a, **k: 10, raising=False)
monkeypatch.setattr(al, "stream_llm_with_fallback", fake_stream, raising=False)
deltas = []
async for chunk in al.stream_agent_loop(
"http://local.test/v1",
"qwen3.6-35b-a3b-heretic",
[{"role": "user", "content": "run command"}],
max_rounds=1,
owner="test_user",
):
for line in chunk.split("\n"):
line = line.strip()
if line.startswith("data: ") and line[6:] != "[DONE]":
try:
payload = json.loads(line[6:])
if "delta" in payload:
deltas.append(payload["delta"])
except Exception:
pass
assert "".join(deltas) == "Sure. done"