Files
roboco/tests/integration/test_prompter_redraft.py
T
a6b67a6a58 Feat: board redraft loop (#139)
* feat(board): expose board review brief + guard approve-and-start

Slice 1 of the board-informed intake re-draft loop (backend foundation):

- JournalService.board_review_brief(task_id): the PO + Head of Marketing
  DECISION_LOG entries for a task, oldest-first, each tagged with author —
  the board's review as structured data.
- GET /api/tasks/{task_id}/board-review (PM-or-above) backing the CEO's
  approval/redraft surface, so the real board analysis is readable instead
  of a placeholder; BoardReviewEntry response schema.
- Guard: approve_and_start now refuses a board task whose review is not
  complete (service invariant + precise BOARD_REVIEW_INCOMPLETE at the route).
  Previously only the UI hid the button; the backend let an early/rogue call
  hand the task to Main PM mid-review.

Tests: brief filtering/ordering + endpoint (200/404) + the two guard paths.

* feat(panel): show real board review at the approve gate + live refresh

Slice 1 frontend of the board-informed intake re-draft loop:

- tasksApi.getBoardReview + useBoardReview hook consume GET
  /tasks/{id}/board-review.
- The Approve & Start dialog now renders the actual Product Owner + Head of
  Marketing notes (markdown) instead of a static placeholder, so the CEO reads
  the board's analysis before approving.
- C2: useTask polls (4s) while a task is still on the board with an
  incomplete review, so the Approve & Start button appears as soon as the
  board finishes — there is no per-task websocket. Polling stops once
  board_review_complete flips.

* feat(intake): board-informed re-draft loop (backend, cold path)

Slice 2 of the re-draft loop:

- update_live_draft: apply a board-informed re-draft to the EXISTING task in
  place (title/description/acceptance_criteria) — never a duplicate — then route
  it: 'main_pm' hands it to the Main PM via approve_and_start; 'board' clears
  board_review_complete for another review round.
- confirm route branches on task_id → update_live_draft vs confirm_live_draft;
  LiveConfirmRequest.task_id added (scope taken from the task, not required).
- POST /live/re-interview/{task_id} (PM-or-above): spawns a fresh intake session
  seeded with the current draft + the board brief (compose_redraft_message),
  scoped to the task's product/project. The cold path + Slice-3 fallback.
- format_board_briefing / compose_redraft_message helpers.

Tests: pure helpers + update_live_draft (main_pm hand-off, re-board reset,
missing-task).

* feat(panel): board-informed re-draft entry + prompter re-draft guidance

Slice 2 panel of the re-draft loop:

- 'Re-draft with board feedback' button on a board-reviewed task detail →
  /prompter?redraft=<taskId>.
- usePrompter.startRedraft(taskId): calls POST /prompter/live/re-interview/{id},
  scopes the chat to the task, and streams the re-draft; redraftTaskId is
  threaded (persisted across reload) so confirm carries task_id and updates the
  existing task in place rather than creating a duplicate.
- prompterLiveApi.reInterview; ConfirmPayload.task_id.
- Prompter role prompt: a 'Re-drafting after board review' section so the agent
  revises the included draft from the board brief instead of starting over.

Panel verified by CI (no local node_modules).

* feat(intake): keep-alive re-draft — park the intake agent during board review

Slice 3 of the re-draft loop (in-context fidelity; cold path is the fallback):

- Registry: LiveIntakeSession.task_id + park(session_id, task_id) (keep alive
  instead of reaping) + find_by_task() for board-completion injection.
- Confirm: the board route (first pass) PARKS the intake agent instead of
  reaping, so it keeps the whole interview in context.
- Orchestrator: on board-review completion, inject the synthesized board brief
  into the parked session (_inject_board_brief_into_parked_intake) so the
  resident prompter re-drafts in-context. No-op when nothing is parked (the
  container died / a new intake replaced it) — the cold /re-interview path
  covers that. No reaper change needed (an idle parked session spends no tokens
  and the budget sweep is the only agent-stopping sweep).
- Panel: confirm(board) keeps the chat alive (parked, redraftTaskId set) with a
  notice; the injected revised draft arrives over the existing stream to approve.

Tests: registry park/find_by_task/closed-ignored. Container delivery + the full
panel parked flow need live (container-runtime) verification.

---------

Co-authored-by: Renn F <rennf93@users.noreply.github.com>
2026-06-14 00:40:18 +02:00

170 lines
5.5 KiB
Python

from __future__ import annotations
from types import SimpleNamespace
from typing import TYPE_CHECKING
from uuid import uuid4
import pytest
import pytest_asyncio
from roboco.db.tables import AgentTable, ProjectTable, TaskTable
from roboco.models import AgentRole, AgentStatus, Team
from roboco.models.base import TaskNature, TaskStatus, TaskType
from roboco.services.base import NotFoundError
from roboco.services.prompter import (
PrompterService,
compose_redraft_message,
format_board_briefing,
)
if TYPE_CHECKING:
from collections.abc import AsyncIterator
from sqlalchemy.ext.asyncio import AsyncSession
# --------------------------------------------------------------------------- #
# Pure helpers (no DB)
# --------------------------------------------------------------------------- #
def test_format_board_briefing_labels_and_orders() -> None:
entries = [
{"author_role": "product_owner", "author": "po", "title": "PO", "content": "x"},
{
"author_role": "head_marketing",
"author": "hom",
"title": "HoM",
"content": "y",
},
]
out = format_board_briefing(entries)
assert "Product Owner" in out
assert "Head of Marketing" in out
assert out.index("Product Owner") < out.index("Head of Marketing")
assert "x" in out and "y" in out
def test_format_board_briefing_empty() -> None:
assert format_board_briefing([]) == ""
def test_compose_redraft_message_includes_draft_and_brief() -> None:
task = SimpleNamespace(
title="My Task",
description="The current description.",
acceptance_criteria=["does X", "does Y"],
)
entries = [
{"author_role": "product_owner", "author": "po", "title": "PO", "content": "z"}
]
msg = compose_redraft_message(task, entries)
assert "My Task" in msg
assert "The current description." in msg
assert "- does X" in msg
assert "Product Owner" in msg
assert "z" in msg
# --------------------------------------------------------------------------- #
# update_live_draft (DB)
# --------------------------------------------------------------------------- #
@pytest_asyncio.fixture
async def redraft_setup(db_session: AsyncSession) -> AsyncIterator[dict]:
def _agent(slug: str, role: AgentRole) -> AgentTable:
return AgentTable(
id=uuid4(),
name=slug,
slug=slug,
role=role,
team=None,
status=AgentStatus.ACTIVE,
model_config={},
system_prompt="x",
capabilities=[],
permissions={},
metrics={},
)
main_pm = _agent("main-pm", AgentRole.MAIN_PM)
po = _agent(f"product-owner-{uuid4().hex[:4]}", AgentRole.PRODUCT_OWNER)
db_session.add_all([main_pm, po])
await db_session.flush()
project = ProjectTable(
id=uuid4(),
name="P",
slug=f"p-{uuid4().hex[:6]}",
git_url="https://example.com/r.git",
assigned_cell=Team.BACKEND,
created_by=po.id,
)
db_session.add(project)
await db_session.flush()
def _board_task(board_review_complete: bool) -> TaskTable:
t = TaskTable(
id=uuid4(),
title="Original title",
description="Original description, long enough.",
acceptance_criteria=["original ac"],
status=TaskStatus.PENDING,
priority=2,
task_type=TaskType.CODE,
nature=TaskNature.TECHNICAL,
project_id=project.id,
created_by=po.id,
team=Team.BOARD,
board_review_complete=board_review_complete,
assigned_to=po.id,
)
db_session.add(t)
return t
yield {
"svc": PrompterService(db_session),
"db": db_session,
"main_pm": main_pm,
"po": po,
"mk": _board_task,
}
_DRAFT = {
"title": "Revised title",
"objective": "Revised objective after board feedback for the task at hand.",
"acceptance_criteria": ["revised ac one", "revised ac two"],
"description": "Revised description that is comfortably over twenty chars.",
}
@pytest.mark.asyncio
async def test_update_live_draft_main_pm_updates_and_hands_off(
redraft_setup: dict,
) -> None:
task = redraft_setup["mk"](True) # board review complete
await redraft_setup["db"].flush()
out_id = await redraft_setup["svc"].update_live_draft(
task.id, _DRAFT, route="main_pm"
)
assert out_id == task.id
assert task.title == "Revised title"
assert task.acceptance_criteria == ["revised ac one", "revised ac two"]
assert "Revised" in task.description
# Approve & Start ran → handed to Main PM.
assert task.assigned_to == redraft_setup["main_pm"].id
assert task.team == Team.MAIN_PM
@pytest.mark.asyncio
async def test_update_live_draft_reboard_resets_flag(redraft_setup: dict) -> None:
task = redraft_setup["mk"](True)
await redraft_setup["db"].flush()
await redraft_setup["svc"].update_live_draft(task.id, _DRAFT, route="board")
assert task.title == "Revised title"
assert task.board_review_complete is False # back for another review round
assert task.assigned_to == redraft_setup["po"].id # still on the board
assert task.team == Team.BOARD
@pytest.mark.asyncio
async def test_update_live_draft_missing_task_raises(redraft_setup: dict) -> None:
with pytest.raises(NotFoundError):
await redraft_setup["svc"].update_live_draft(uuid4(), _DRAFT, route="main_pm")