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>
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>
Image turns already get a vision-model description injected into the prompt,
but the agent kept calling read_image to "confirm" the pictures. Those tool
results carry base64 image parts that Goose persists, so every later turn
against the text-only chat provider failed with `unknown variant image_url`
before the agent could write the page. WeChat page requests therefore fell
through to the fail-closed delivery message.
Drop read_image for the turn whenever a vision model handles the images, say
so explicitly in the injected prompt, and teach the poison scan to recognise
tool image parts so already-polluted sessions rotate instead of failing again.
Co-authored-by: Cursor <cursoragent@cursor.com>
Wait for HTML materialization before releasing delivery contracts, pass
verified MindSpace URLs through proactive WeChat sends, resend on reconcile
when pages land late, and report deferred customer-service delivery as unsent.
Co-authored-by: Cursor <cursoragent@cursor.com>
After a successful image report flow, Goose may keep image_url parts that
DeepSeek rejects on later turns while PUT scrub returns 405. Detect polluted
sessions up front, rotate to a fresh agent route with carried assistant
context, and recover image URLs from recent media on historical retries.
Co-authored-by: Cursor <cursoragent@cursor.com>
Goose cannot persist historical image scrub (PUT 405), so DeepSeek rejects
image_url on the next turn. Reattach the recent report image and rotate to a
fresh session instead of treating the follow-up as a missing page source.
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>
When passive Recognition is empty, convert AMR to mp3 and call WeChat
addvoicetorecofortext before the existing asr.tkmind.cn fallback.
Co-authored-by: Cursor <cursoragent@cursor.com>
Remove per-user gray gates so WeChat MP always honors agentReplyTimeoutMs and enables Page Data Aider review when the feature flag is on.
Co-authored-by: Cursor <cursoragent@cursor.com>
Collect request-scoped tool messages in the WeChat SSE stream, infer this
turn Page Data HTML via mtime when messages lack writes, and limit bind and
delivery smoke to those paths so historical already_bound pages cannot block new surveys.
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>
Intent routing and reply content now both trigger HTML delivery: public links,
public/*.html paths, or html writes in the agent reply enable artifact recovery,
link attachment, and fail-closed when the claimed page is missing.
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>
Add keyword fallback and dedupe for pgvector resolve, score personal vs episodic memories by relevance, record WeChat recall product events, and disable broken chatrecall on Postgres session storage.
Co-authored-by: Cursor <cursoragent@cursor.com>
Give WeChat MP its own chat.general→page.generate LLM refinement layer with memindadm toggles, shadow mode, and canary openids so service account routing stays independent of the H5 chatIntentRouter.
Co-authored-by: Cursor <cursoragent@cursor.com>
Fall back to workspace share thumbnails so already-published HTML can be
sent instead of blocking on REQUIRED_FRESH. Also allow an explicit
ALLOW_DIRECT_STABLE_RELEASE path matching the pre-2026-07-23 direct
stable packaging flow.
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>
Match phrases like「生成一个精美的 HTML 页面」so poem follow-ups skip fresh-thumbnail forcing and reuse the same session poem context.
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>
Short follow-ups like "把刚才的诗做成页面" must keep the existing agent
session so Goose still sees the adjacent poem in snapshot history. Rotating
orphan routes before these requests dropped the poem and revived stale memory.
Co-authored-by: Cursor <cursoragent@cursor.com>
Stop blocking WeChat delivery when Page Data insert works but publish
quota blocks h5_publish_records; fix smoke URL missing /api; patch survey
radios for WeChat X5 and detect dataset constants in admin pages.
Co-authored-by: Cursor <cursoragent@cursor.com>
john