When DeepSeek returns 402, try other chat providers before giving up, and cancel the sole active task only during LLM outages so user 123 can cancel without Goose.
Co-authored-by: Cursor <cursoragent@cursor.com>
Use a lightweight LLM over active task lists to pick taskId for cancel,
exclude page.generate from scheduled-task inbound, and remove single-task
auto-cancel so Cursor page generation stays isolated.
Co-authored-by: Cursor <cursoragent@cursor.com>
When a user has exactly one active automation task, cancel it by taskId
after listTasks instead of relying on Goose when the LLM provider fails.
Co-authored-by: Cursor <cursoragent@cursor.com>
Stop schedule todo replies from intercepting cancel/list/create automation
requests, and recognize 有哪些 for inbound scheduled task listing.
Co-authored-by: Cursor <cursoragent@cursor.com>
Pass cancel requests to Goose like create instead of inbound title matching,
and add scheduled_task_update_spec so format or execution constraints update
taskSpec without triggering page delivery guards.
Co-authored-by: Cursor <cursoragent@cursor.com>
Stop ITL regex from intercepting new messages before Agent execution; move
scheduled task and schedule write confirmation to MCP tool calls with draft commit on 确认.
Co-authored-by: Cursor <cursoragent@cursor.com>
New followers receive capability overview plus WeChat anchor links for the
deep intro page and account binding instead of exposing raw URLs.
Co-authored-by: Cursor <cursoragent@cursor.com>
Materialize wechat-mp uploads into dated public/images paths during vision
preprocessing and fail closed when delivered HTML references stale workspace
images instead of the current turn allowlist.
Co-authored-by: Cursor <cursoragent@cursor.com>
Expand ASR normalization and colloquial reminder parsing so simple timed reminders route to L1 confirm cards instead of the agent, and disable schedule-guard false failures when ITL is enabled.
Co-authored-by: Cursor <cursoragent@cursor.com>
Support colloquial forms like「设置每天18：00提醒打卡」, persist daily metadata on
commit, and schedule the next reminder after each delivery.
Co-authored-by: Cursor <cursoragent@cursor.com>
Introduce Draft → Confirm → Commit flow for WeChat schedule intents behind
feature flags, plus h5_tasks dual-write/read aggregation and rollout scripts
so reminders and automations get explicit user confirmation before persisting.
Co-authored-by: Cursor <cursoragent@cursor.com>
Phrases like "解读详细报告，做成页面" now bind to the in-session report
context instead of behaving like a brand-new page topic.
Co-authored-by: Cursor <cursoragent@cursor.com>
Scheduled automations were saved but never executed because the worker
required an explicit env flag. Follow H5_REMINDER_WORKER_ENABLED when unset,
add WeChat preflight to write tasks deterministically, and surface worker
warnings on create.
Co-authored-by: Cursor <cursoragent@cursor.com>
Prevent chat-to-page flows like writing a poem then saying "做成页面吧" from opening
a fresh session without carried content, failing with a vague error, or letting Memory
page-template preferences replace the immediate topic.
Co-authored-by: Cursor <cursoragent@cursor.com>
Generate SVG/PNG sidecars at HTML delivery and after share-preview repair so
forwarded service-account links get a raster og:image when only meta exists.
Co-authored-by: Cursor <cursoragent@cursor.com>
Persist formal replies when WeChat customer-service quota is exhausted,
claim them once on the next passive response, skip progress notices for
page generation, and suppress failure notices while a formal reply is pending.
Co-authored-by: Cursor <cursoragent@cursor.com>
Production WeChat delivery strips localPath from artifacts, so share-preview
auto-repair never wrote back to HTML. Resolve paths via publishDir +
relativePath, repair at materialize and delivery prep, and pass h5Root from
Portal so page.generate can patch missing meta before sending links.
Co-authored-by: Cursor <cursoragent@cursor.com>
Pages with real HTML content but missing description, mindspace-cover, or
platform brand markers are patched in-place so WeChat link delivery no longer
fails after successful generation.
Co-authored-by: Cursor <cursoragent@cursor.com>
Skip memory injection for short filler messages, demote page-workflow memory
pollution, keep scheduled automation off page.generate, and fail scheduled
tasks that only return clarification instead of deliverables.
Co-authored-by: Cursor <cursoragent@cursor.com>
Schedule LLM now binds an explicit provider key and fails closed on network errors so dead relay endpoints cannot block ordinary chat; relay bootstrap is opt-in only.
Co-authored-by: Cursor <cursoragent@cursor.com>
Introduce scheduled-task-automation for H5 and WeChat, persist tasks in h5_scheduled_tasks, and run due jobs via a dedicated worker that executes agent tasks and delivers results.
Co-authored-by: Cursor <cursoragent@cursor.com>
Prevent text-only planning replies from marking WeChat delivery done when
static-page-publish never confirmed a public HTML file.
Co-authored-by: Cursor <cursoragent@cursor.com>
Recognize retry, HTML page, page edits, and poem content edits as session continuations so delivery skips fresh-thumbnail forcing and retains agent context for multi-turn page work.
Co-authored-by: Cursor <cursoragent@cursor.com>
Skip fresh thumbnail forcing and retry in-session when load_skill completes without HTML落盘, so「把刚才的诗做成页面」can deliver the prior poem as a static page.
Co-authored-by: Cursor <cursoragent@cursor.com>
Page Data questionnaires were returning publication slugs to users; password-mode
pages always fell back to /u/ routes. Prefer MindSpace paths at publish time and
rewrite mistaken delivery links in WeChat and Portal chat.
Co-authored-by: Cursor <cursoragent@cursor.com>
When schedule_create_item includes a start time and reminder intent, create the
matching h5_schedule_reminders row in the same tool call so 10:00 pushes are not
lost. Also reconcile Goose SSE request ids with the portal agent-run gate to keep
MindSpace chat streaming reliable.
Co-authored-by: Cursor <cursoragent@cursor.com>
Inject serve-time CSS so author styles cannot hide TKMind · 智趣 with
low opacity, which made pages like weather.html look brandless.
Co-authored-by: Cursor <cursoragent@cursor.com>
Backfill missing platform-brand footer at serve time and block service-
account links when the HTML file omits data-mindspace-page-tag.
Co-authored-by: Cursor <cursoragent@cursor.com>
Block service-account page links when HTML lacks mindspace-cover and
description so WeChat forwards always get TKMind branding and thumbnail.
Co-authored-by: Cursor <cursoragent@cursor.com>
Extract schedule, greeting/status/connectivity replies, chat-general prompt, and display-name helpers from wechat-mp.mjs. Route sync intents via classifyWechatIntent and add channel isolation CI check.
Co-authored-by: Cursor <cursoragent@cursor.com>
Replace fixed ackText with a rule-based AckProvider that picks
response templates by message type and intent (translate, summary,
rewrite, poster, ppt, mindmap, code, search, schedule). Pure sync,
zero I/O, auto-falls back to config.ackText on any error.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
john
tkmind