mirror of
https://github.com/bytedance/deer-flow.git
synced 2026-10-28 14:10:37 +00:00
cdbcc0d9e9
* docs(scheduler): document tool_enabled, goal notices and goal-evaluation change Follow-up to #6229: - CONFIGURATION.md: add scheduler.tool_enabled to the example and notes. - CONFIGURATION.md, README (en/zh/pt): unmet goal runs send a goal-unmet notice instead of a completion notice, and three unmet runs add an auto-pause notice; the docs still said only success/failed notify. - CHANGELOG (en/zh): the #6229 entry now states the default-on goal evaluation change for scheduled/webhook/autonomous goal runs and that evaluator usage counts toward run usage. * feat(scheduled-tasks): show goal outcomes and end conditions in run history Follow-up to #6229. The API already returns these fields; the tasks page did not show them, so a met goal read as plain "Success", an unmet reason code rendered as a red execution error, and the goal-unmet IM notice pointed to a workspace showing neither objective nor verdict. - Task detail shows the per-run goal, max automatic runs and end time when a conversation-created task has them. - Goal runs show "Goal met" (or met relying on stated assumptions); unmet runs show a localized reason plus the host code in neutral styling. The run whose agent asked to stop the schedule is marked. - Runs without a goal, and failed runs, render as before. Read-only and frontend-only: no API change. * docs(changelog): add #6326 scheduled-task goal outcome entry * fix(scheduled-tasks): show readable unmet reasons instead of raw codes Unmet runs now show only the localized reason; the host code moves to the tooltip so it can still be matched with the IM notice. Codes without a label are still shown verbatim. * fix(scheduler): show readable goal reasons instead of internal codes Task detail now localizes the host-written last_error values from goal and stop finalization (agent stop, automatic pause, unmet reason codes) under a matching label, and Chinese copy is tightened. Goal-unmet and auto-pause IM notices state the reason in words instead of printing the raw code; unknown codes are still not forwarded. * docs(changelog): describe readable goal reasons in #6326 entry * test(scheduler): pin host goal strings with a cross-language contract Address review on #6326: - Add contracts/scheduled_goal_notes_contract.json listing the task last_error strings and unmet reason codes the tasks page and IM notices translate. A backend test checks finalization constants, blocker and stand-down codes against it; a frontend test checks every listed value has a label. - Move the two last_error strings in finalization.py into constants. - Frontend reason lookup strips the blocked: prefix like the IM map and now covers goal_not_met_yet, with en/zh labels. --------- Co-authored-by: Totoro-qaq <279883115+Totoro-qaq@users.noreply.github.com> Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
58 lines
2.4 KiB
Python
58 lines
2.4 KiB
Python
"""Contract tests for host-written scheduled goal strings.
|
|
|
|
The tasks page (``frontend/src/core/scheduled-tasks/goal-outcome.ts``) and the
|
|
IM notice renderer translate these values instead of showing them raw, so the
|
|
backend must keep producing exactly what ``contracts/scheduled_goal_notes_contract.json``
|
|
lists.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import json
|
|
import re
|
|
from pathlib import Path
|
|
|
|
import pytest
|
|
|
|
from app.scheduler.notification_delivery import render_notification_text
|
|
from deerflow.persistence.scheduled_task_runs import finalization
|
|
from deerflow.runtime.goal import DEFAULT_MAX_GOAL_CONTINUATIONS, DEFAULT_MAX_NO_PROGRESS_CONTINUATIONS, GOAL_BLOCKERS
|
|
from deerflow.runtime.runs import worker
|
|
|
|
_REPO_ROOT = Path(__file__).resolve().parents[2]
|
|
_CONTRACT = json.loads((_REPO_ROOT / "contracts" / "scheduled_goal_notes_contract.json").read_text(encoding="utf-8"))
|
|
_CODES = set(_CONTRACT["unmet_reason_codes"])
|
|
|
|
|
|
def test_last_error_strings_match_contract():
|
|
assert finalization.AGENT_STOP_LAST_ERROR_PREFIX == _CONTRACT["agent_stop_last_error_prefix"]
|
|
assert finalization.AUTO_PAUSE_LAST_ERROR == _CONTRACT["auto_pause_last_error"]
|
|
|
|
|
|
def test_blocker_stand_down_codes_are_in_contract():
|
|
# An unsatisfied verdict never carries the "none" blocker.
|
|
assert {f"blocked:{blocker}" for blocker in GOAL_BLOCKERS - {"none"}} <= _CODES
|
|
|
|
|
|
def test_cap_stand_down_reasons_are_in_contract():
|
|
evaluation = {"satisfied": False, "blocker": "goal_not_met_yet", "reason": ""}
|
|
at_cap = {"continuation_count": DEFAULT_MAX_GOAL_CONTINUATIONS}
|
|
assert worker._stand_down_reason(at_cap, evaluation, 0) in _CODES
|
|
assert worker._stand_down_reason({"continuation_count": 0}, evaluation, DEFAULT_MAX_NO_PROGRESS_CONTINUATIONS) in _CODES
|
|
|
|
|
|
def test_literal_stand_down_reasons_and_no_verdict_are_in_contract():
|
|
source = Path(worker.__file__).read_text(encoding="utf-8")
|
|
literals = set(re.findall(r'stand_down_reason\s*=\s*"([a-z_:]+)"', source))
|
|
assert literals, "pattern no longer matches worker.py; update this test"
|
|
assert literals <= _CODES
|
|
assert '"no_verdict"' in Path(finalization.__file__).read_text(encoding="utf-8")
|
|
assert "no_verdict" in _CODES
|
|
|
|
|
|
@pytest.mark.parametrize("code", sorted(_CODES))
|
|
def test_im_notice_translates_every_contract_code(code):
|
|
text = render_notification_text({"event": "run_unmet", "task_id": "task-a", "payload": {"reason_code": code}})
|
|
assert "Reason: unknown." not in text
|
|
assert code not in text
|