f9f6bc01fd
CI / test (push) Canceled after 0s
## Summary epic r04 - begin refactor ## Change Type - [x] Cowork feature - [ ] Bug fix - [ ] Core AI contribution - [ ] Test / hardening - [ ] Performance - [ ] Documentation ## Related Work Cowork Task: Core Repo: http://34.143.229.138/gitea-admin/fsg-ai-core-assets Core AI Issue: Core Task: Related PR: ## Scope What is intentionally included? What is intentionally NOT included? ## Validation - [ ] Unit tests - [ ] Integration tests - [ ] Manual verification - [ ] Regression check Commands / evidence: ## Security Impact Permission / credential / network / customer data impact: ## Compatibility - [ ] No breaking change - [ ] Breaking change documented ## Reviewer Notes Anything Cowork reviewers should pay attention to. --------- Co-authored-by: Anh Tran Nguyen Minh <anhtnm1@fpt.com> Co-authored-by: Huong Le Thi Thien <huongltt35@fpt.com> Co-authored-by: Nam Pham Dinh Thanh <nampdt@fpt.com> Co-authored-by: Vu Dam Tuan <vudt15@fpt.com> Co-authored-by: Hiep Ha Van <hiephv3@fpt.com> Co-authored-by: Lam Hoang Van <lamhv7@fpt.com> Reviewed-on: #7 Co-authored-by: Duy Le Huu <duylh19@fpt.com>
102 lines
3.4 KiB
Python
102 lines
3.4 KiB
Python
"""R04-T03 (a) — unit tests for the value a finished turn returns.
|
|
|
|
Two callers need different things out of one turn today:
|
|
``ui/chat_panel.py::_finalize_turn`` wants the message list, while
|
|
``core/task_executors.py::_run_agent`` returns a
|
|
``(answer_text, timed_out, incomplete_reason)`` tuple assembled by hand. This
|
|
type is what both read instead, so "what happened in that turn?" has one answer
|
|
with names on it.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
from dataclasses import FrozenInstanceError
|
|
|
|
import pytest
|
|
from cowork_local.domain.agents.agent_event import PlanStep, TurnCompletedEvent
|
|
from cowork_local.domain.agents.agent_result import AgentResult
|
|
|
|
|
|
def test_result_rejects_mutation() -> None:
|
|
result = AgentResult(steps_used=1)
|
|
|
|
with pytest.raises(FrozenInstanceError):
|
|
result.steps_used = 2
|
|
|
|
|
|
def test_messages_are_frozen_into_a_tuple() -> None:
|
|
live = [{"role": "user", "content": "hi"}]
|
|
|
|
result = AgentResult(messages=live)
|
|
live.append({"role": "assistant", "content": "later"})
|
|
|
|
assert result.messages == ({"role": "user", "content": "hi"},)
|
|
|
|
|
|
def test_final_text_is_the_last_non_empty_assistant_message() -> None:
|
|
# A turn ends on a tool message often enough (cancelled mid-loop) that the
|
|
# answer cannot simply be messages[-1].
|
|
result = AgentResult(messages=[
|
|
{"role": "assistant", "content": "first pass"},
|
|
{"role": "assistant", "content": "the answer"},
|
|
{"role": "tool", "tool_call_id": "c", "name": "read_file", "content": "..."},
|
|
])
|
|
|
|
assert result.final_text == "the answer"
|
|
|
|
|
|
def test_final_text_skips_a_blank_assistant_message() -> None:
|
|
result = AgentResult(messages=[
|
|
{"role": "assistant", "content": "the answer"},
|
|
{"role": "assistant", "content": " "},
|
|
])
|
|
|
|
assert result.final_text == "the answer"
|
|
|
|
|
|
def test_final_text_is_empty_when_the_model_never_answered() -> None:
|
|
assert AgentResult(messages=[{"role": "user", "content": "hi"}]).final_text == ""
|
|
|
|
|
|
def test_a_plain_finished_turn_is_ok() -> None:
|
|
assert AgentResult(messages=[{"role": "assistant", "content": "done"}]).ok is True
|
|
|
|
|
|
def test_a_cancelled_turn_is_not_ok() -> None:
|
|
assert AgentResult(cancelled=True).ok is False
|
|
|
|
|
|
def test_a_failed_turn_is_not_ok_and_keeps_its_message() -> None:
|
|
result = AgentResult(error="SecurityBlocked: nope")
|
|
|
|
assert result.ok is False
|
|
assert result.error == "SecurityBlocked: nope"
|
|
|
|
|
|
def test_hitting_the_step_ceiling_is_reported_separately_from_cancelling() -> None:
|
|
# "Stopped because the safety limit was reached" and "the user pressed Stop"
|
|
# need different wording in the transcript, so they stay separate flags.
|
|
result = AgentResult(budget_exhausted=True, steps_used=30)
|
|
|
|
assert result.budget_exhausted is True
|
|
assert result.cancelled is False
|
|
|
|
|
|
def test_result_converts_to_the_turn_completed_event() -> None:
|
|
result = AgentResult(
|
|
messages=[{"role": "assistant", "content": "done"}],
|
|
steps_used=3, cancelled=False, budget_exhausted=True,
|
|
)
|
|
|
|
assert result.to_turn_completed_event() == TurnCompletedEvent(
|
|
final_text="done", steps_used=3, cancelled=False, budget_exhausted=True)
|
|
|
|
|
|
def test_plan_steps_are_frozen_into_a_tuple() -> None:
|
|
steps = [PlanStep(title="Draft", status="done")]
|
|
|
|
result = AgentResult(plan_steps=steps)
|
|
steps.append(PlanStep(title="Review"))
|
|
|
|
assert result.plan_steps == (PlanStep(title="Draft", status="done"),)
|