mirror of
https://github.com/openswarm-ai/openswarm.git
synced 2026-09-30 21:44:50 +02:00
* [eric] ci: gitleaks-ignore the known historical secrets so our branch stops failing on leaks it didnt add * [eric] workflows: restore scheduled-tasks on the workflow line (revert removal, keep windows fixes + 1.1.69) * [eric] workflows: re-apply uncommitted scheduling wip (schedule pill, calendar view, slice) * [eric] ops: gitignore dev-team local state files * [eric] ops: backlog item for download-tracking visibility * [eric] ci: allowlist the cdp-routes redaction-test token in gitleaks * [aidan] feat/scheduled-tasks: keep step labels in sync on edit and show chevron on every step * [aidan] fix: schedule time in chat * [aidan] ux/workflows: add workflow step removal (#91) * [aidan] feat/scheduled-tasks: remember workflow tool permissions across runs * [aidan] feat/task-scheduling: add hourly and minute (15-min minimum) schedule intervals (#93) * [aidan] feat/scheduled-tasks: calendar, rename, and edit workflows (#94) * [aidan] bug: fix schedule button * [aidan] fix/agent-errors: surface provider rate limits * [aidan] ux/cards: click-to-rename for chat and workflow titles Single-click a card's title to enter edit mode inline. Commit on Enter/blur, cancel on Escape. Rename persists via PATCH for workflows and sessions. * [aidan] feat/workflows: seed build prompt for zero-step workflows When a new workflow has no steps, seed the agent with a prompt asking the user to describe what the workflow should do, rather than starting blank. * [aidan] feat/workflows: add-to-schedule popover for unscheduled workflows Clicking the "+" on an unscheduled workflow row opens a popover with two options: - Keep this schedule: enables the workflow's existing cadence and moves it to Scheduled - Change schedule: opens the scheduling editor to pick a different time * [aidan] ux/workflows: wire add-to-schedule popover and simplify New button - Made the "+" icon on unscheduled workflow rows clickable, opening a popover to keep or change the schedule - Removed AddIcon from toolbar "New" button (now reads "New" instead of "+ New") * [aidan] fix/scheduled-tasks: open schedule calendar when Schedule pill clicked Fixed the Schedule pill click being swallowed by the toolbar's dismiss handler. Exempted the toolbar pills via data-toolbar-pills so their click handlers fire. * [aidan] ux/workflows: open New workflow in agent build chat instead of empty card When creating a new workflow from the hub, open it in edit_agent view (with the agent builder chat) instead of a preview card. The workflow is created on the backend first so the embedded session has a real ID. * [aidan] feat/workflow-edit: add draft testing save flow * [aidan] ux/chat: remove continue chat button * [aidan] ux/workflows: polish workflow card interactions * [aidan] fix/workflow-scheduling: save unscheduled workflows as drafts * aidan ui: schedule naming changes * [aidan] ui: tool calling desc/naming * [aidan] ui: calendar sidebar naming * [aidan] ui: fix stop viewing closing chat * [aidan] feat/workflows: auto-name workflows and polish the build flow (#95) * [aidan] feat/workflow-auto-naming: auto-generate workflow titles from steps Generate a title + description from a workflow's steps (one aux call, reused for step labels) whenever it is still auto_named, so a workflow built in the Edit Agent names itself on commit instead of staying "New workflow". A manual rename sets auto_named=False and is never overwritten. Stream the aux call (non-streaming drops content on some 9router lanes) and fall back to a step-derived title when the model is unavailable. * [aidan] feat/workflows: hide unsaved new workflows until first save A brand-new "+ New" workflow is created with unsaved=true and kept out of the hub's scheduled/unscheduled lists while the user is still building it in the Edit Agent. The first commit (Save) clears the flag and the workflow appears. Every other create path stays visible immediately. * [aidan] ux/workflows: remove redundant save workflow button The Edit Agent already has Discard/Save controls in its strip, so the header "Save Workflow" button was a duplicate save path. Remove it and its pulse/edit-session-id wiring; the model/time subtitle stays. * [aidan] ux/workflows: animate title on auto-rename Wrap the workflow card title in the same Typewriter the chat card uses, so when the auto-generated name replaces the placeholder after Save it retypes letter-by-letter. Gated on a real (non-placeholder) title so it never animates on mount or for already-named workflows. * [aidan] ux/workflows: animate sidebar title on auto-rename Wrap the calendar hub's sidebar row title in the same Typewriter the workflow card uses, so a title that auto-renames retypes letter-by-letter in the sidebar too. Extract the placeholder/isRealTitle guard into the shared workflowVisuals so the card and sidebar stay in sync. * [aidan] fix/workflows: connect watch tether, keep watched chat open, wire draft run/history * [aidan] ui: grey out chat pill when not selected * [aidan] ui: fix running agent display * [aidan] feat/history-popover: add chat history and scheduled tasks run log tabs (#96) * [aidan] ux/schedule: toast when calendar view already open on expand * [aidan] ui: fix popover descs * [aidan] feat/workflow-runs: add pause, resume, and stop controls for live runs * [aidan] feat/schedule-calendar: add calendar occurrences endpoint and concrete timezones * [aidan] feat/workflows: require at least one step to save a workflow * [aidan] ux/edit-agent: hide Discard for an unsaved new workflow * [aidan] ux/edit-agent: move fix-prefix card below the step list * [aidan] feat/workflows: toast when an unattended scheduled run starts * [aidan] fix/dashboard-tethers: anchor workflow-sidecar tethers to measured card rects * [aidan] feat/workflows: validate steps before scheduling and keep chat tool memory * [aidan] feat/mcp-suggestions: dismissable integration banner with per-session cooldown * [aidan] feat/workflows: add scheduled-run "running now" toast with click-to-view (#97) * [aidan] ux/workflows: surface paused state on card, sidebar, and calendar; tidy run history * [aidan] feat/mcp-suggestions: suggest both Google and Microsoft when provider is ambiguous * [aidan] fix/agent-tokens: friendly out-of-tokens card across all agent surfaces * [aidan] feat/workflow-model: persist edit-agent model on save with switch notice and fresh drafts * [aidan] fix/workflow-chat: force stop on watched run mirrors workflow card stop * [aidan] fix/workflow-cards: keep watched run tethered on finish to avoid duplicate chat * [aidan] feat/schedule-calendar: mark current time with a now line in week view * [aidan] refactor/private-names: rename error and schedule classifiers from _ to p_ * [aidan] feat/scheduled-tasks: agent workflow scheduling and in-chat convert (#98) * [aidan] feat/workflow-suggest: nudge user to convert repeatable chat to workflow Add SuggestConvertToWorkflow MCP tool that agents call at the end of a task when they've completed something worth repeating (daily report, weekly check, recurring data pull). Frontend detects the tool call and glows the "Convert to workflow" button 3 times to draw the eye. When user clicks it, the suggested cadence (e.g. "every weekday at 9am") is stored in the draft and seeded into the scheduling agent's first prompt, so the agent can act on the suggestion rather than asking the user again. Tool is never auto-called — agents decide when a task is genuinely repeatable (not debugging, creative work, one-off lookup). Tool description emphasizes sparse, high-confidence use only (once per session max). Files changed: - backend/apps/agents/schedule_mcp_server.py: add SuggestConvertToWorkflow tool - frontend/src/shared/mcpToolMeta.ts: add label for new tool - frontend/src/app/pages/Dashboard/cards/AgentCard.tsx: detect suggestion in session messages, show+glow "Convert to workflow" button, pass cadence to draft - frontend/src/shared/state/workflowsSlice.ts: add suggested_cadence field to Workflow interface - frontend/src/app/pages/Workflows/SchedulingView.tsx: seed scheduling agent prompt with suggested cadence hint * [aidan] feat/agent-scheduling: route recurring asks through native workflows, deny claude cron skill * [aidan] feat/workflow-convert: in-chat convert popup and auto-open scheduled workflow card * [aidan] ux/calendar-page: schedule calendar restyle + popover fixes (#99) * [aidan] fix/dashboard-delete: remove workflows calendar panel on delete key * [aidan] ux/workflows-calendar: restyle hub, fix today highlight, add toolbar toggle * [aidan] ux/schedule-popover: compact density, fix sticky header bleed, add header spacing * [aidan] ux/schedule-calendar: hollow ring dot for past fires in month view * [aidan] ux/schedule-calendar: clickable +N more opens day's full run list * [aidan] feat/run-log-filters: add success and skipped pills to scheduled task history * [aidan] fix/convert-button: stop drag capture so convert-to-workflow click fires * [aidan] ux/calendar-card: match border color and radius to chat and workflow cards * [aidan] fix/minimap: render missed-runs card on the minimap * [aidan] ux/run-sparkline: simplify tooltip to plain run tally * [aidan] ux/run-history: collapse expanded run view to one clickable line * [aidan] ux/calendar-card: match corner radius to browser cards * [aidan] feat/workflows: launch-time scheduling UX and workflow-card polish (#101) * [aidan] feat/schedule-list: lazy-load list view via scroll sentinel * [aidan] feat/missed-runs: launch toast with per-workflow counts and pan-to-card * [aidan] fix/dashboard-tethers: keep watching line anchored on canvas zoom * [aidan] feat/scheduled-tasks: review missed runs at launch instead of auto-firing on_missed * [aidan] refactor/workflow-cards: use radius and status design tokens, polish card chrome * [aidan] ux/agent-card: keep convert-to-workflow visible during runs with mid-turn toast * [aidan] ux/mcp-bubble: drop redundant verb label when a workflow label is shown * [aidan] chore/backend: remove stale explanatory comments * [aidan] fix/workflows-hub: load workflows on hub mount so calendar fills at launch * [aidan] feat/workflows: generate title, description, step labels at convert time * [aidan] fix/tidy-layout: include workflows hub in tidy and fit-to-view * [aidan] feat/schedule-list: window long list via measured-height virtualizer * [aidan] ux/workflows-hub: remove time-saved badge from calendar header * [aidan] fix/types: add missing semantic-type labels and drop stray fade arg * [aidan] feat/schedule: pin monthly day-of-month and honor repeat-every intervals * [aidan] feat/schedule: inherit source-session tool surface for scheduled runs * [aidan] ux/calendar: restack hour-cell events as bars with overflow affordance * [aidan] feat/calendar: open the run card when clicking a scheduled occurrence * [aidan] ux/missed-runs: add per-group select-all toggle and rename skip action * [aidan] feat: new scheduled task design ported * [aidan] ui: sidebar reorder, repeat controls on schedule card * [aidan] ui: sidebar, scheduling time * [aidan] feat/schedule: pin monthly last-day-of-month * [aidan] feat/steps: per-step enable toggle * [aidan] feat/workflows: per-workflow color swatch * [aidan] feat/trash: soft-delete workflows with restore and purge * [aidan] feat/run-monitor: live run monitor card on the canvas * [aidan] feat/run-context: attach a run as removable chat context * [aidan] feat/compose: new-workflow landing page and auto-commit build flow * [aidan] ui/workflows: dark mode and design-system cohesion * [aidan] ui/calendar: overflow popover, condensed week view, scroll fix * [aidan] feat/home: ongoing runs, missed review, and accurate Coming-up counts * [aidan] fix/run-status: sync ongoing runs and heal stuck/interrupted runs * [aidan] ux/schedule: last-day-of-month UI, Run-at time typing, interval input * [aidan] ux/workflows: default window size and toolbar icon * [aidan] fix/schedule: measure ran_late from start and anchor recurrences to created_at * [aidan] feat/calendar: render fire times from backend, drop JS recurrence reimpl * [aidan] chore/dashboard: drop dead configure/missed-run cards, refetch on reconnect * [aidan] chore/agent-card: remove unreachable convert-to-workflow action * [aidan] fix/workflows: don't bump updated_at on a no-op draft commit so viewing a workflow doesn't reorder the sidebar * [aidan] feat/schedule: warn when scheduling a workflow that has no steps * [aidan] fix/selection-tool: never select the workflows app, and exit the tool on Escape without dropping selections * [aidan] ux/compose: diversify new-workflow starter prompts across personas * [aidan] ux/run-monitor: spawn the run card a bit farther right of the workflows app * [aidan] fix/schedule: harden run recovery and storage writes against crashes * [aidan] ux/compose: restyle new-workflow starters as a clean pill cluster with rich prompts * [aidan] fix/workflows: optimistically apply edits so the schedule banner updates instantly * [aidan] ui/workflows: three-tone surface depth so the window lifts off the canvas in both themes * [aidan] ui/workflows: close buttons turn red on hover, matching the chat card * [aidan] test/schedule: cover executor pipeline, storage durability, and recurrence gaps * [aidan] fix: remove package-lock json * [aidan] fix/workflows-compose: keep compose view until edit agent replies * [aidan] feat/workflows: auto-generate workflow + step titles with typewriter animation * [eric] deps: restore frontend/package-lock.json (PR #105 deletion broke npm ci) --------- Co-authored-by: Eric <ciregenz@berkeley.edu> Co-authored-by: cire <134991075+ciregenz@users.noreply.github.com>
302 lines
10 KiB
Python
302 lines
10 KiB
Python
# mypy: allow-untyped-defs
|
|
"""Support for skip/xfail functions and markers."""
|
|
|
|
from __future__ import annotations
|
|
|
|
from collections.abc import Mapping
|
|
import dataclasses
|
|
import os
|
|
import platform
|
|
import sys
|
|
import traceback
|
|
from typing import Generator
|
|
from typing import Optional
|
|
|
|
from _pytest.config import Config
|
|
from _pytest.config import hookimpl
|
|
from _pytest.config.argparsing import Parser
|
|
from _pytest.mark.structures import Mark
|
|
from _pytest.nodes import Item
|
|
from _pytest.outcomes import fail
|
|
from _pytest.outcomes import skip
|
|
from _pytest.outcomes import xfail
|
|
from _pytest.reports import BaseReport
|
|
from _pytest.reports import TestReport
|
|
from _pytest.runner import CallInfo
|
|
from _pytest.stash import StashKey
|
|
|
|
|
|
def pytest_addoption(parser: Parser) -> None:
|
|
group = parser.getgroup("general")
|
|
group.addoption(
|
|
"--runxfail",
|
|
action="store_true",
|
|
dest="runxfail",
|
|
default=False,
|
|
help="Report the results of xfail tests as if they were not marked",
|
|
)
|
|
|
|
parser.addini(
|
|
"xfail_strict",
|
|
"Default for the strict parameter of xfail "
|
|
"markers when not given explicitly (default: False)",
|
|
default=False,
|
|
type="bool",
|
|
)
|
|
|
|
|
|
def pytest_configure(config: Config) -> None:
|
|
if config.option.runxfail:
|
|
# yay a hack
|
|
import pytest
|
|
|
|
old = pytest.xfail
|
|
config.add_cleanup(lambda: setattr(pytest, "xfail", old))
|
|
|
|
def nop(*args, **kwargs):
|
|
pass
|
|
|
|
nop.Exception = xfail.Exception # type: ignore[attr-defined]
|
|
setattr(pytest, "xfail", nop)
|
|
|
|
config.addinivalue_line(
|
|
"markers",
|
|
"skip(reason=None): skip the given test function with an optional reason. "
|
|
'Example: skip(reason="no way of currently testing this") skips the '
|
|
"test.",
|
|
)
|
|
config.addinivalue_line(
|
|
"markers",
|
|
"skipif(condition, ..., *, reason=...): "
|
|
"skip the given test function if any of the conditions evaluate to True. "
|
|
"Example: skipif(sys.platform == 'win32') skips the test if we are on the win32 platform. "
|
|
"See https://docs.pytest.org/en/stable/reference/reference.html#pytest-mark-skipif",
|
|
)
|
|
config.addinivalue_line(
|
|
"markers",
|
|
"xfail(condition, ..., *, reason=..., run=True, raises=None, strict=xfail_strict): "
|
|
"mark the test function as an expected failure if any of the conditions "
|
|
"evaluate to True. Optionally specify a reason for better reporting "
|
|
"and run=False if you don't even want to execute the test function. "
|
|
"If only specific exception(s) are expected, you can list them in "
|
|
"raises, and if the test fails in other ways, it will be reported as "
|
|
"a true failure. See https://docs.pytest.org/en/stable/reference/reference.html#pytest-mark-xfail",
|
|
)
|
|
|
|
|
|
def evaluate_condition(item: Item, mark: Mark, condition: object) -> tuple[bool, str]:
|
|
"""Evaluate a single skipif/xfail condition.
|
|
|
|
If an old-style string condition is given, it is eval()'d, otherwise the
|
|
condition is bool()'d. If this fails, an appropriately formatted pytest.fail
|
|
is raised.
|
|
|
|
Returns (result, reason). The reason is only relevant if the result is True.
|
|
"""
|
|
# String condition.
|
|
if isinstance(condition, str):
|
|
globals_ = {
|
|
"os": os,
|
|
"sys": sys,
|
|
"platform": platform,
|
|
"config": item.config,
|
|
}
|
|
for dictionary in reversed(
|
|
item.ihook.pytest_markeval_namespace(config=item.config)
|
|
):
|
|
if not isinstance(dictionary, Mapping):
|
|
raise ValueError(
|
|
f"pytest_markeval_namespace() needs to return a dict, got {dictionary!r}"
|
|
)
|
|
globals_.update(dictionary)
|
|
if hasattr(item, "obj"):
|
|
globals_.update(item.obj.__globals__)
|
|
try:
|
|
filename = f"<{mark.name} condition>"
|
|
condition_code = compile(condition, filename, "eval")
|
|
result = eval(condition_code, globals_)
|
|
except SyntaxError as exc:
|
|
msglines = [
|
|
f"Error evaluating {mark.name!r} condition",
|
|
" " + condition,
|
|
" " + " " * (exc.offset or 0) + "^",
|
|
"SyntaxError: invalid syntax",
|
|
]
|
|
fail("\n".join(msglines), pytrace=False)
|
|
except Exception as exc:
|
|
msglines = [
|
|
f"Error evaluating {mark.name!r} condition",
|
|
" " + condition,
|
|
*traceback.format_exception_only(type(exc), exc),
|
|
]
|
|
fail("\n".join(msglines), pytrace=False)
|
|
|
|
# Boolean condition.
|
|
else:
|
|
try:
|
|
result = bool(condition)
|
|
except Exception as exc:
|
|
msglines = [
|
|
f"Error evaluating {mark.name!r} condition as a boolean",
|
|
*traceback.format_exception_only(type(exc), exc),
|
|
]
|
|
fail("\n".join(msglines), pytrace=False)
|
|
|
|
reason = mark.kwargs.get("reason", None)
|
|
if reason is None:
|
|
if isinstance(condition, str):
|
|
reason = "condition: " + condition
|
|
else:
|
|
# XXX better be checked at collection time
|
|
msg = (
|
|
f"Error evaluating {mark.name!r}: "
|
|
+ "you need to specify reason=STRING when using booleans as conditions."
|
|
)
|
|
fail(msg, pytrace=False)
|
|
|
|
return result, reason
|
|
|
|
|
|
@dataclasses.dataclass(frozen=True)
|
|
class Skip:
|
|
"""The result of evaluate_skip_marks()."""
|
|
|
|
reason: str = "unconditional skip"
|
|
|
|
|
|
def evaluate_skip_marks(item: Item) -> Skip | None:
|
|
"""Evaluate skip and skipif marks on item, returning Skip if triggered."""
|
|
for mark in item.iter_markers(name="skipif"):
|
|
if "condition" not in mark.kwargs:
|
|
conditions = mark.args
|
|
else:
|
|
conditions = (mark.kwargs["condition"],)
|
|
|
|
# Unconditional.
|
|
if not conditions:
|
|
reason = mark.kwargs.get("reason", "")
|
|
return Skip(reason)
|
|
|
|
# If any of the conditions are true.
|
|
for condition in conditions:
|
|
result, reason = evaluate_condition(item, mark, condition)
|
|
if result:
|
|
return Skip(reason)
|
|
|
|
for mark in item.iter_markers(name="skip"):
|
|
try:
|
|
return Skip(*mark.args, **mark.kwargs)
|
|
except TypeError as e:
|
|
raise TypeError(str(e) + " - maybe you meant pytest.mark.skipif?") from None
|
|
|
|
return None
|
|
|
|
|
|
@dataclasses.dataclass(frozen=True)
|
|
class Xfail:
|
|
"""The result of evaluate_xfail_marks()."""
|
|
|
|
__slots__ = ("reason", "run", "strict", "raises")
|
|
|
|
reason: str
|
|
run: bool
|
|
strict: bool
|
|
raises: tuple[type[BaseException], ...] | None
|
|
|
|
|
|
def evaluate_xfail_marks(item: Item) -> Xfail | None:
|
|
"""Evaluate xfail marks on item, returning Xfail if triggered."""
|
|
for mark in item.iter_markers(name="xfail"):
|
|
run = mark.kwargs.get("run", True)
|
|
strict = mark.kwargs.get("strict", item.config.getini("xfail_strict"))
|
|
raises = mark.kwargs.get("raises", None)
|
|
if "condition" not in mark.kwargs:
|
|
conditions = mark.args
|
|
else:
|
|
conditions = (mark.kwargs["condition"],)
|
|
|
|
# Unconditional.
|
|
if not conditions:
|
|
reason = mark.kwargs.get("reason", "")
|
|
return Xfail(reason, run, strict, raises)
|
|
|
|
# If any of the conditions are true.
|
|
for condition in conditions:
|
|
result, reason = evaluate_condition(item, mark, condition)
|
|
if result:
|
|
return Xfail(reason, run, strict, raises)
|
|
|
|
return None
|
|
|
|
|
|
# Saves the xfail mark evaluation. Can be refreshed during call if None.
|
|
xfailed_key = StashKey[Optional[Xfail]]()
|
|
|
|
|
|
@hookimpl(tryfirst=True)
|
|
def pytest_runtest_setup(item: Item) -> None:
|
|
skipped = evaluate_skip_marks(item)
|
|
if skipped:
|
|
raise skip.Exception(skipped.reason, _use_item_location=True)
|
|
|
|
item.stash[xfailed_key] = xfailed = evaluate_xfail_marks(item)
|
|
if xfailed and not item.config.option.runxfail and not xfailed.run:
|
|
xfail("[NOTRUN] " + xfailed.reason)
|
|
|
|
|
|
@hookimpl(wrapper=True)
|
|
def pytest_runtest_call(item: Item) -> Generator[None]:
|
|
xfailed = item.stash.get(xfailed_key, None)
|
|
if xfailed is None:
|
|
item.stash[xfailed_key] = xfailed = evaluate_xfail_marks(item)
|
|
|
|
if xfailed and not item.config.option.runxfail and not xfailed.run:
|
|
xfail("[NOTRUN] " + xfailed.reason)
|
|
|
|
try:
|
|
return (yield)
|
|
finally:
|
|
# The test run may have added an xfail mark dynamically.
|
|
xfailed = item.stash.get(xfailed_key, None)
|
|
if xfailed is None:
|
|
item.stash[xfailed_key] = xfailed = evaluate_xfail_marks(item)
|
|
|
|
|
|
@hookimpl(wrapper=True)
|
|
def pytest_runtest_makereport(
|
|
item: Item, call: CallInfo[None]
|
|
) -> Generator[None, TestReport, TestReport]:
|
|
rep = yield
|
|
xfailed = item.stash.get(xfailed_key, None)
|
|
if item.config.option.runxfail:
|
|
pass # don't interfere
|
|
elif call.excinfo and isinstance(call.excinfo.value, xfail.Exception):
|
|
assert call.excinfo.value.msg is not None
|
|
rep.wasxfail = "reason: " + call.excinfo.value.msg
|
|
rep.outcome = "skipped"
|
|
elif not rep.skipped and xfailed:
|
|
if call.excinfo:
|
|
raises = xfailed.raises
|
|
if raises is not None and not isinstance(call.excinfo.value, raises):
|
|
rep.outcome = "failed"
|
|
else:
|
|
rep.outcome = "skipped"
|
|
rep.wasxfail = xfailed.reason
|
|
elif call.when == "call":
|
|
if xfailed.strict:
|
|
rep.outcome = "failed"
|
|
rep.longrepr = "[XPASS(strict)] " + xfailed.reason
|
|
else:
|
|
rep.outcome = "passed"
|
|
rep.wasxfail = xfailed.reason
|
|
return rep
|
|
|
|
|
|
def pytest_report_teststatus(report: BaseReport) -> tuple[str, str, str] | None:
|
|
if hasattr(report, "wasxfail"):
|
|
if report.skipped:
|
|
return "xfailed", "x", "XFAIL"
|
|
elif report.passed:
|
|
return "xpassed", "X", "XPASS"
|
|
return None
|