Inject English recipe hints for fiber/offline/excel/continue, ack the first queued follow-up, localize gate copy, and classify execManagedNe errors so agents stop blind retries.
Co-authored-by: Cursor <cursoragent@cursor.com>
Default progress, quote wrappers, tool-error copy, and playbook recipes to English unless lang is explicitly zh.
Co-authored-by: Cursor <cursoragent@cursor.com>
Wire channel inbound on_progress/on_tool_ui to outbound queue so group users see wait signals for CLI/UME work without sharing per-speaker session context.
Co-authored-by: Cursor <cursoragent@cursor.com>
Unregistered tools now suggest close matches; MCP insufficient_scope is rewritten with fallbacks so ops agents stop blind-retrying SQL without sql:query.
Co-authored-by: Cursor <cursoragent@cursor.com>
Production usage showed schema mismatches and multi-tool loops; accept common arg aliases and route agents to <=3-call alarm recipes.
Co-authored-by: Cursor <cursoragent@cursor.com>
Keep 01-06 as summarized general knowledge; route on-site reports into 07 and update the ops playbook retrieval order.
Co-authored-by: Cursor <cursoragent@cursor.com>
Mirror NETX_NE_EXEC_MAX_COMMANDS and updated show/ping/traceroute/pipe rules in builtin tool and playbook.
Co-authored-by: Cursor <cursoragent@cursor.com>
Wire should_stop from aborted runs, snapshot abort before clearing flags so finals are not emitted after stop, and keep fail-path turn_uuid aligned for bubble splitting.
Co-authored-by: Cursor <cursoragent@cursor.com>
Keeps the running-count badge visible without competing with the new-chat action above the session list.
Co-authored-by: Cursor <cursoragent@cursor.com>
start_job/get_job/sleep replace blocked run_command for multi-hour work; Chat shows a live count badge and allows manual kill, with a reaper reclaiming timed-out or stale processes.
Co-authored-by: Cursor <cursoragent@cursor.com>
Enqueue deliverable tool attachments on the WhatsApp queue path, and dedupe the same attachment_id within one Chat bubble (prefer deliverable).
Co-authored-by: Cursor <cursoragent@cursor.com>
Claim pending rows atomically and serialize the sidecar poller so overlapping polls cannot send the same reply twice; also stop inbound queue delivery from falling through to a second enqueue.
Co-authored-by: Cursor <cursoragent@cursor.com>
Strip @mention prefixes and widen history lookup so reply-to of the bot's own prior answer is not wrapped as [被引用消息] again.
Co-authored-by: Cursor <cursoragent@cursor.com>
Serialize per-session inbound turns and merge follow-ups after the active run; show composing while busy and enqueue final replies so long agent runs still reach the group.
Co-authored-by: Cursor <cursoragent@cursor.com>
Give the ops specialist a skill to search docs/ip-knowledge-base and verify findings via netx before concluding.
Co-authored-by: Cursor <cursoragent@cursor.com>
Align administrator session deletion with the administrator chat view so
sessions surfaced through channel_session_v2 can be removed without a
ui_session_owner row.
Co-authored-by: Cursor <cursoragent@cursor.com>
Reuse channel_session_v2 per job_id so cron runs do not create a new
oclaw session each time; isolate scheduled turn context to the active
turn_uuid so shared sessions do not leak prior run history.
Co-authored-by: Cursor <cursoragent@cursor.com>
Pass the active workspace lane into tool execution and default schedule_create to that specialist so WhatsApp ops-bound jobs are stored and run as ops instead of generalist.
Co-authored-by: Cursor <cursoragent@cursor.com>
Use a fresh execution session per run while keeping source_session_id for delivery only; filter bot JIDs and default scheduled @mentions to the job creator.
Co-authored-by: Cursor <cursoragent@cursor.com>
Scheduled outbound only sent text via pollOutboundQueue; collect deliverable attachments from the turn, encode them in source JSON, and send via sendReplyWithAttachments.
Co-authored-by: Cursor <cursoragent@cursor.com>
Replace hardcoded dark modal, menu, toast, and lightbox colors with theme CSS variables so text stays readable in light mode.
Co-authored-by: Cursor <cursoragent@cursor.com>
Require preview confirmation for schedule_delete, extra confirm_foreign for others' jobs in groups, and mirror the same flow in chat slash commands.
Co-authored-by: Cursor <cursoragent@cursor.com>
Store self-contained playbook recipes on scheduled jobs, add schedule_propose draft gate, and run playbook instructions at fire time instead of only short reminders.
Co-authored-by: Cursor <cursoragent@cursor.com>
Wire mention JIDs/names through scheduled delivery and immediate replies (including attachment captions), sanitize group message text for the model, and surface channel-derived sessions in admin Chat.
Co-authored-by: Cursor <cursoragent@cursor.com>
Require deliverable:true for all channel attachments including images; extend save_deliverable_attachment with attachment_id; add WeChat proactive attachment delivery; inject channel file rules via system prompt instead of repeating on every user message.
Co-authored-by: Cursor <cursoragent@cursor.com>
Guide the model to use run_command with openpyxl for xlsx exports instead of claiming the tool is unavailable.
Co-authored-by: Cursor <cursoragent@cursor.com>
Add save_deliverable_attachment for explicit document outbound, pass channel user_id into tool risk gating so write_file/run_command respect per-user allow_high settings, and document the workflow in channel-file-delivery skill.
Co-authored-by: Cursor <cursoragent@cursor.com>
WhatsApp/channel binary_ref uploads now expand into text_ref/tabular summaries for the model, and outbound replies only auto-attach generated image/video media instead of lookup tool text_ref results.
Co-authored-by: Cursor <cursoragent@cursor.com>
Default WhatsApp groups to per-user sessions, skip redundant quoted-text injection when already in recent history, and disable group long-term memory writes unless explicitly enabled.
Co-authored-by: Cursor <cursoragent@cursor.com>
Track send attempts and schedule retry windows for pending WhatsApp outbound messages, then mark as failed after max retries to avoid silent drops without infinite resend loops.
Co-authored-by: Cursor <cursoragent@cursor.com>
Replace hardcoded Asia/Shanghai with host IANA timezone detection for new scheduled jobs across tools, admin API, gateway cron, and store layer.
Co-authored-by: Cursor <cursoragent@cursor.com>
When the model omits specialist, inject selected_specialist from the current tool executor context so scheduled jobs run under the expert that created them.
Co-authored-by: Cursor <cursoragent@cursor.com>
Move schedule_* tool factories into the public registry so ops/generalist both can create and manage scheduled jobs, and add an English schedule shortcut.
Co-authored-by: Cursor <cursoragent@cursor.com>
Introduce whitelist/blacklist gating, pending requests, Admin UI management, and stanza-mapped quote approval so admins can approve via WhatsApp DM without blocking normal LLM chat.
Co-authored-by: Cursor <cursoragent@cursor.com>
Introduce persisted cron/interval jobs, gateway scheduler loop, worker turns,
and admin CRUD/edit UI. Route proactive reminders via the originating chat
channel (WhatsApp vs WeChat), harden Weixin outbound with durable queue and
PG-compatible polling, and fix chat UI to show each scheduled reminder separately.
Co-authored-by: Cursor <cursoragent@cursor.com>
Extract quotedText from reply context correctly and enrich inbound only after mention detection, keeping strict @-required group policy.
Co-authored-by: Cursor <cursoragent@cursor.com>
