Totoro 2dd2e5415c
feat(scheduled-tasks): finish the user-facing side of conversation schedules (RFC #6340, 1/2) (#6378)
* feat(scheduler): lifecycle rules, goal/limit parity and coded errors for scheduled tasks

- Migration 0031: nullable scheduled_tasks.unmet_streak_after_seq (internal
  streak boundary) and stop_condition (the user's stop rule, own column).
- Stop rule is normalized (stop_rule.py) and appended only at launch; the
  stored prompt never contains it. Wording adapts when scheduler.tool_enabled
  is off.
- Willem 1: page-created tasks get goal evaluation, <standing_notes>, the
  previous-run reference and own-schedule stop; request_stop and the
  scheduled capability no longer require an origin conversation.
- Repository: single reactivation choke point raising
  ScheduledTaskLimitsExhausted; streak boundary moves on goal/prompt/stop
  condition/note changes (not on resume); goal-check failures neither count
  nor reset the streak; pause of a finished task returns "finished"; trials
  on a paused task keep the host pause marker.
- New repository reads: automatic_runs_used_for, active_run_status_for,
  list_manageable_from_thread, thread_relation/thread_run on thread tasks,
  task_ids_for_thread, run_number, and run_number/total_tokens/summary on
  run history rows.
- REST: goal/max_runs/end_at/stop_condition on create and PATCH (null
  clears, naive end_at = task timezone), resume recomputes from now with an
  optional renewal body, once_time_passed, task_finished, limits_exhausted,
  scheduler_not_running on create, trigger returns outcome/existing/thread_id,
  task responses add automatic_runs_used and active_run_status.
- Coded errors {code, message, params} for routes, shared validation and the
  chat capability (scheduled_task_errors.py), pinned by
  contracts/scheduled_task_errors_contract.json; goal notes contract v2 with
  check_failure_codes, scheduled_origin_key and host_run_errors (host_notes.py).
- /api/features adds scheduled_tasks {available, running, tool_enabled,
  min_interval_seconds}; ScheduledTaskService.is_running.
- Docs: six README scheduler sections, API.md scheduled tasks section
  (breaking error shape), CONFIGURATION.md, AGENTS notes, CHANGELOGs.
- Tests: migration 0031, stop rule, error contract, run listing, lifecycle
  over HTTP, repository, service and capability cases; updated tests for the
  new error shape, finished-task pause and head revision.

* feat(scheduler): conversation update/resume, run-conversation authority and readable launches

- schedule_task: update and resume actions, stop_condition and clear_fields
  parameters, plain parameter types (value rules come back as coded results),
  rewritten docstrings for schedule_task and stop_scheduled_task.
- Capability: update/resume share the REST validation and error codes;
  interactive turns in a task's run conversation may manage that task;
  scheduled runs keep only own-stop; grants require a running scheduler.
- Results: compact JSON-safe task views with local times, display card/text,
  last run in list, timezone_source/browser_timezone, now_local; no ISO, user,
  lease or origin fields; stop_instructions removed.
- Timezone: explicit > browser (context.client_timezone, validated in
  start_run and never forwarded to the run config) > not needed for intervals
  and offset run_at > timezone_required.
- Trial gate accepts natural direct requests after acknowledgements and
  particles; trial results report thread_id and existing.
- Scheduled launches: stable message id scheduled-<task_run_id>, server-owned
  deerflow_scheduled_origin metadata with the user-language parts, run thread
  title for fresh-thread tasks.
- Worker records goal continuations in the verdict; lead prompt language rule
  covers stored task text and scheduled runs.
- Docs: six READMEs, CONFIGURATION, API, runtime/tools AGENTS, CHANGELOGs.

* feat(frontend): scheduled-task core types, formatting, errors and glossary

- throwGatewayApiError now throws GatewayApiError (status, code, params,
  rawMessage); message stays the string detail or detail.message
- scheduled-task types gain stop_condition, automatic_runs_used,
  active_run_status, origin/notes, run_number/total_tokens/summary, thread
  relation, trigger result, renewal and scheduled origin; isTaskBusy and
  hasActiveRun helpers
- api: fetchScheduledTask, resume with optional renewal body, typed trigger
  result and update payload with null clears
- hooks: polling at 3 s while a run is active (list, thread list, run
  history), useScheduledTask with live gating and final 404, useInView,
  localized error toasts; run history refreshes tasks when a run finishes
- new pure modules: errors.ts (contract code to localized copy), format.ts
  (relative task times, viewer time, display zone), status.ts, actions.ts,
  run-error.ts; describeTaskSchedule in cron.ts; goal-outcome adds unchecked
  goal checks, describeTaskOutcome and parseStopRunId
- features: scheduled_tasks block with defaults when missing
- buildRunContext sends client_timezone
- titleOfThread takes a localized untitled label; breadcrumb names scheduled
  tasks and agents; reference chips use the localized untitled label
- schedule input: shared browserTimeZone, labelled selects, aria-pressed
  type toggles, interval minimum from the hint template
- i18n: all PR1 scheduled-task keys in en-US and zh-CN, glossary fixes,
  recipe instructions moved into i18n
- e2e mocks follow the new task, trigger, resume, thread-task and features
  shapes; expectNoRawIdentifiers helpers for e2e and DOM tests
- tests for errors, format, cron, status, actions, goal outcome, run errors,
  hooks, run context, thread titles and features; scheduled e2e copy updated

* feat(frontend): list-first scheduled tasks page with outcomes and editable goals

- page.tsx is now a thin composition of components/workspace/scheduled-tasks:
  status tabs (All/Active/Paused/Finished) and search over the task list,
  ?task_id= deep link with router.replace on selection, ?thread_id= chip
  with Show all, empty state, scheduler-off notice and unavailable state
- task list rows show the schedule in words and one status line (next run,
  running now, paused by agent, auto-paused, finished by its cap)
- task detail: status badge, actions from availableActions with reasons,
  More actions menu (Duplicate, Copy task ID, Delete), outcome notice,
  Runs / Stops when / Each run's goal / Does / Notes from chat / History,
  origin chat link; success toasts for every action
- run rows: run number or Trial run, summary, goal and assumption badges,
  continuations, tokens, Open chat link; raw errors and the evaluator
  reason only behind Details
- create/edit/duplicate dialog with goal, stop condition, safety caps and
  advanced agent/context options; PATCH sends only changed fields, null
  clears a cap
- renew dialog raises or removes caps and resumes in one request; a
  limits_exhausted Resume opens it
- removed i18n keys the old page used; added feedback.resumedNoTime
- recorded en-3 and zh-1 page fixtures; scheduled e2e specs rewritten for
  the new page; DOM tests for the detail and the form dialog
- CHANGELOG entries and the frontend AGENTS.md scheduled-task note

* feat(frontend): live schedule card, run conversation provenance and header entry

- schedule_task results (create, update, pause, resume, trial, delete) become
  an assistant:scheduled-task message group rendered as a live card: schedule,
  next run, stop condition with the safety cap, goal, where results go, Run
  once now, Pause/Resume and Open task; the card polls the task only while it
  is on screen and shows deleted, scheduler-off and limits-exhausted states
- one card per task per assistant turn; the card group is not a turn boundary
  for usage, branching, editing, outline or skill attribution
- a human message with deerflow_scheduled_origin stays a human group with
  scheduledOrigin and renders as a "Scheduled run / Trial run" block with the
  task instructions, stop condition and notes collapsed; the launched text is
  never shown and the message is not editable
- readable step labels for schedule_task actions and stop_scheduled_task
- ThreadScheduledTasksButton replaces the header link: hidden without tasks,
  shows the count, links to the task (or the chat filter), and a run's chat
  links to its task
- recorded en-3 / zh-1 chat and run-thread fixtures; chat-card and run-thread
  e2e specs; unit and DOM tests for parsing, grouping, turn boundaries, card,
  run block, header button, step labels and reconnect hydration
- i18n: header.countLabelOne added, unused card.next removed; CHANGELOG and
  frontend AGENTS.md notes

* fix(scheduler): address verification findings

Move the scheduled-task lifecycle guidance from backend/AGENTS.md into the persistence guide and leave a one-line pointer, so the effective AGENTS.md chains for agents/middlewares, sandbox and subagents stay under the 98304-byte hard limit enforced by scripts/check_agent_guidance.py in lint-check.

* fix(scheduler): address review findings

* fix(scheduled-tasks): polish from live acceptance

- zh schedule wording: an interval of one unit reads 每分钟 / 每小时 / 每秒,
  and a saved interval of whole days reads 每天 / 每 2 天 (Every day / Every 2
  days) instead of 每 1 分钟 or 每 24 小时; several units keep the number
- zh spacing: 已于{time} 满足 and 在{time} 的运行中 now leave a space between
  the interpolated time and the Chinese after it; a copy test guards every
  scheduled-task zh string against a placeholder glued to Chinese
- run summary: when the first line of the final reply only leads in to a list
  (ends with ":" or ":"), the list items follow it as plain text (bullets,
  numbering, checkboxes, bold, code and links stripped), joined with ";" for
  CJK text and "; " otherwise, within the 160-character cap
- a schedule_task result (create, update, pause, resume, trial, delete) that
  arrives in a chat invalidates that chat's task list, the tasks list and the
  named task, so the header button and cards update without waiting for the
  idle poll; results already in the loaded history do not refetch
- e2e and unit fixtures are now the live acceptance recordings (DeepSeek
  Flash, demo data, fictional names): live-weekday.json (create, trial, edit,
  pause, resume in one zh chat) and live-minute.json (per-minute chat, run 1
  and run 2, paused by the agent), fetched with GET from the demo Gateway and
  trimmed; the hand-shaped en-3 / zh-1 fixtures are removed and the chat-card,
  run-thread and tasks-page specs run in both locales over the recorded data

* docs(changelog): reference #6378 for the scheduled-tasks entries

* docs(agents): shorten the scheduled-task pointer to stay under the guidance limit

* test(scheduled-tasks): pin the live takes to their recorded time zone

The live fixtures were recorded in Asia/Shanghai, and an interval task
reads in the viewer's zone, so the 16:48 assertions failed on UTC CI
runners. Pin the browser zone in the two live-take e2e specs and the
zh live-take unit test.

* fix(scheduled-tasks): keep untouched end times and drop a chat filter the new task is not in

- The edit, duplicate and renew dialogs keep a stored end time's instant
  while its field still shows it. A minute-precision wall value cannot
  keep seconds or name the later 01:30 of a DST fall-back, so a
  title-only edit moved the cap an hour earlier, and raising the run
  limit re-sent the end time without its seconds.
- Creating or duplicating a task from a chat's task view drops the chat
  filter when the new task does not belong to that chat, instead of
  showing "This task isn't one of this chat's tasks".

* fix(scheduled-tasks): tie pause notices to the pause they describe

- Paused by agent links and times only the run named in last_error. When
  that run is not loaded, the notice shows no link and the task's own time
  instead of an earlier run that also asked to stop.
- The outcome notice reads the latest history page whichever page is
  shown, so browsing older runs no longer swaps the auto-pause reason and
  "Open latest run" to an earlier miss. It shares that page's request.

* fix(scheduled-tasks): three lifecycle gaps found while re-checking review classes

- The edit form compares a cron in the form its schedule input emits, so an
  untouched "0 09 * * 0,6" is not re-sent as "0 9 * * 6,0" and a title-only
  edit no longer re-arms or refuses a finished task.
- Chat resume asks for a timezone, as update does, when a naive end_at would
  land in the UTC placeholder of a zone-free task.
- Re-arming a task clears a host pause marker, as resume does, so a later
  manual pause no longer reads as "Paused by agent".

* fix(scheduled-tasks): keep the notice's latest-runs query from refreshing older pages

useLatestScheduledTaskRuns kept React Query's default refetch on mount,
focus and reconnect, so going offline and back while an older history page
was shown fetched the latest page again. Refreshing stays with the history,
which refreshes the latest page only while it is shown.

* test(scheduled-tasks): let the viewer's time carry its own day label

Between 16:00 and 24:00 UTC, UTC and Asia/Shanghai are on different days,
so the run prompt shows "Tomorrow 01:00 · Today 09:00 your time" and the
fixed "01:00 · 09:00 your time" assertion failed depending on the hour.

---------

Co-authored-by: Totoro-qaq <279883115+Totoro-qaq@users.noreply.github.com>
Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
2026-10-07 07:47:32 +08:00

186 lines
9.5 KiB
Python

"""Conversation schedule management through a current-run host capability."""
from typing import Any, Literal
from langchain.tools import tool
from deerflow.agents.interaction_policy import resolve_run_interaction_policy
from deerflow.scheduler.runtime import (
SCHEDULER_CAPABILITY_CONTEXT_KEY,
SchedulerCapabilityMode,
SchedulerRunCapability,
is_scheduler_capability,
scheduler_tools_enabled,
)
from deerflow.tools.types import Runtime
def _capability(runtime: Runtime, mode: SchedulerCapabilityMode) -> SchedulerRunCapability | None:
context = runtime.context if runtime is not None and isinstance(runtime.context, dict) else {}
if context.get("is_subagent") or not scheduler_tools_enabled(context.get("app_config")):
return None
capability = context.get(SCHEDULER_CAPABILITY_CONTEXT_KEY)
if not is_scheduler_capability(capability) or capability.mode != mode:
return None
config = dict(runtime.config) if isinstance(runtime.config, dict) else {}
config["context"] = context
try:
policy = resolve_run_interaction_policy(config)
except ValueError:
return None
return capability if policy.mode.value == mode else None
@tool(parse_docstring=True)
async def schedule_task(
action: Literal["create", "update", "list", "pause", "resume", "delete", "note", "trial"],
runtime: Runtime,
task_id: str | None = None,
title: str | None = None,
prompt: str | None = None,
stop_condition: str | None = None,
schedule_type: Literal["once", "interval", "cron"] | None = None,
schedule_spec: dict[str, Any] | None = None,
timezone: str | None = None,
context_mode: Literal["fresh_thread_per_run", "reuse_thread"] = "fresh_thread_per_run",
goal_objective: str | None = None,
max_runs: int | None = None,
end_at: str | None = None,
note: str | None = None,
clear_fields: list[Literal["goal_objective", "max_runs", "end_at", "stop_condition"]] | None = None,
) -> dict[str, Any]:
"""Create and manage the user's scheduled tasks from this conversation.
Use create only after the user asked for scheduled or recurring work. Ask
first when the timing or the work itself is unclear. Write the title,
prompt and stop_condition in the user's language.
Keep the parts of a task apart:
- prompt: what every run does, written as instructions for a future run of
you. Do not put the cadence, the stop rule or any IDs in it.
- stop_condition: the user's "stop when ..." rule in the user's own words,
for example "every item on the checklist is checked". Every run checks it
and pauses its own schedule with stop_scheduled_task when it holds.
Scheduled runs can stop themselves; never tell the user a task cannot
stop itself.
- goal_objective: optional. What a single run must achieve, checked after
every run. Never put the cadence or the stop rule in it. Meeting it does
not end the schedule. Goals require fresh_thread_per_run.
- max_runs and end_at: a safety cap, not the stop rule. Trial runs do not
count. An interval shorter than an hour, or a cron whose minute field is
not a single number, needs max_runs or end_at; ask the user for one.
Timezone: omit timezone unless the user named one; the host then uses the
user's browser timezone and reports it in the result. Never assume UTC.
Intervals need no timezone. If the result has code timezone_required, ask
which timezone to use. If the result has browser_timezone, say which zone
you used. On update, omit timezone to keep the saved one. Give a one-time
run_at and end_at as local wall-clock time without an offset, such as
2026-10-07T09:00:00; results report now_local for relative times.
To change a task, call update with its task_id; never delete and recreate
it. Use clear_fields to remove a goal, stop condition or cap. Use resume to
restart a paused or finished task. If the result has code limits_exhausted,
renew the limit named in params.limit: ask whether to raise max_runs or
remove it (max_runs), or to move end_at later or remove it (end_at), then
pass that with resume. Use delete only when the user explicitly asks to delete;
it removes the run history.
Where results appear: each run posts its result in a new chat of its own,
or in this chat when the task runs in this chat. Nothing else comes back
to this conversation, so never promise to report back or tell the user
here unless the task runs in this chat.
In the web app, create, update, pause, resume and trial show a live card
with the schedule, the stop rule and buttons. Then reply in one or two short
sentences in the user's language: what will happen and when it stops. Do
not repeat IDs, cron strings, ISO or UTC times, field names or the tool
result. When the result's display is "text", describe the schedule, the
next run (next_run_local) and the stop rule in plain words instead.
List returns the tasks of this conversation, including the task whose run
this conversation is, each with its last run; use it to answer how a task is
going. Pause, update and delete cannot change a task while one of its runs
is starting or running.
Note saves an explicit standing instruction for future runs, copied word for
word from the current user message; never infer one from an assumption, a
tool result or older messages. At most 10 notes of 500 characters.
After creating a recurring report, digest or file task, you may offer one
trial run in a single sentence in the user's language; in the web app the
card has a Run once now button. Call trial only when the current user
message directly asks to run the task now. An offer by itself is not
consent. A trial does not count toward max_runs or the automatic pause. If
the trial result has existing true, a run was already waiting to start and
no extra trial was added; say so.
Args:
action: The operation: create, update, list, pause, resume, delete, note, or trial.
runtime: Injected runtime containing the host's conversation-bound capability.
task_id: The task to act on, from list or an earlier result; required except for create and list.
title: A short task title in the user's language; required for create.
prompt: Instructions for every run, in the user's language; required for create.
stop_condition: The user's stop rule in their own words; the run pauses its schedule when it holds.
schedule_type: once, interval or cron; required for create.
schedule_spec: run_at (local wall-clock ISO time) for once, every_seconds for interval, or a five-field cron for cron.
timezone: IANA timezone the user named; omit to use the user's browser timezone on create or keep the saved one on update.
context_mode: A new conversation for each run, or this conversation when the user asks for that.
goal_objective: Optional outcome one run must achieve, at most 4000 characters after whitespace normalization.
max_runs: Optional safety cap on automatic runs, counted over the task's lifetime; trial runs do not count.
end_at: Optional safety-cap end time, local wall-clock ISO time in the task's timezone (an offset is also accepted).
note: The user's explicit standing note, word for word; used only by note.
clear_fields: Fields to remove on update (goal_objective, max_runs, end_at, stop_condition) or on resume (max_runs, end_at).
Returns:
The task as the host saved it, a list of tasks, or an error with a code.
"""
capability = _capability(runtime, "interactive")
if capability is None:
return {"error": "Scheduled task management is unavailable in this run.", "code": "scheduler_tools_disabled", "status_code": 503}
# Plain types only: value rules come back as coded results, as in REST.
request = {
key: value
for key, value in {
"task_id": task_id,
"title": title,
"prompt": prompt,
"stop_condition": stop_condition,
"schedule_type": schedule_type,
"schedule_spec": schedule_spec,
"timezone": timezone,
"goal_objective": goal_objective,
"max_runs": max_runs,
"end_at": end_at,
"note": note,
"clear_fields": list(clear_fields) if clear_fields else None,
}.items()
if value is not None
}
if action == "create":
request["context_mode"] = context_mode
return await capability.manage(action=action, request=request)
@tool(parse_docstring=True)
async def stop_scheduled_task(runtime: Runtime) -> dict[str, Any]:
"""Pause this run's own schedule after this run finishes.
Call this when the stop rule in your task instructions is met, for example
"every item on the checklist is checked". Meeting this run's goal does not
by itself mean the stop rule is met. The current run continues; the
schedule pauses when it finishes, and the user can resume it later. After
calling it, tell the user in their language that the task paused itself and
why.
Args:
runtime: Injected runtime bound by the host to this scheduled occurrence.
Returns:
Whether the host recorded the stop request, or an error with a code.
"""
capability = _capability(runtime, "scheduled")
if capability is None:
return {"error": "Stopping a schedule is unavailable in this run.", "code": "scheduler_tools_disabled", "status_code": 503}
return await capability.stop_current_schedule()