Skip to main content
Glama

agents_trigger_create

Create a new trigger for an AI agent.

Triggers determine when the agent activates.

Trigger types:

  • incoming_message: Activates on new incoming messages

  • schedule: Activates on a schedule

  • webhook: Activates on webhook events

  • blockchain_event: Activates when something happens on a crypto wallet address (funds arrive or leave, its risk grows, it is sanctioned or frozen). Saving the trigger is the whole setup: the address starts being watched

  • event: Activates on system events

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "agent_id": "<agent_id>",
      "trigger_type": "<trigger_type>"
    },
    "name": "agents_trigger_create"
  }
}

Input Schema

NameRequiredDescriptionDefault
enabledNoWhether the trigger is enabled. OMIT to use the default (true).
agent_idYesID of the agent to create a trigger for
priorityNoTrigger priority — lower numbers run first (default: 100)
send_modeNoSend mode override for this trigger. OMIT to inherit from the agent.
conditionsNoTrigger conditions (JSON). For blockchain_event (all three required): blockchain_addresses: ["<address>"] — the wallets to watch; blockchain_chains: any of ["bitcoin","ethereum","bsc","tron","solana"] (the chain is part of the wallet's identity: the same 0x address is a different wallet on ethereum and on bsc, so name only the chains meant); blockchain_events: any of ["transfer_in","transfer_out","risk_level_up","sanctioned","frozen"]. Optional, transfers only: blockchain_tokens: ["USDT"], blockchain_min_amount: 100. The run receives the event kind, chain, address and, for transfers, the list of transfers (tx, time, token, amount, USD value, counterparty and its risk). If the answer carries watch_note, the address is saved but not watched yet. Supported fields for incoming_message: - keywords: ["pricing","demo"] — message must contain keyword(s) (free, no LLM cost) - keyword_match: "any" (default, OR) or "all" (AND) - channel_types: ["telegram","whatsapp","livechat_voice","twilio_voice","telegram_voice","voice",...] — filter by channel. For voice, use EITHER the three per-channel keys (scoped) OR "voice" alone (wildcard matching all three) — mixing them is redundant. Per-channel keys: "livechat_voice" (web widget), "twilio_voice" (PSTN inbound), "telegram_voice" (Telegram p2p calls) - context_types: ["dm","group","channel","livechat"] — filter by chat type - group_mode: "mentions_only" or "questions" — for group chats - channel_account_ids: ["123"] — restrict to specific accounts. Only accounts THIS workspace answers: a trigger never fires for another workspace's channel, so create it on an agent there - folder_ids: [5,10] — restrict to threads in folders - ai_tag_ids: [1,2] — restrict to threads with AI tags - ai_filter_ids: [1,2] — semantic intent filters (message matched via embedding similarity, works in noisy groups) - ai_filter_mode: "any" (default, OR) or "all" (AND) — how multiple AI filters combine - ai_filters: [{id: 1}, {name: "...", description: "..."}] — shorthand: reference existing by id or create inline (calls Voyage embedding API). If a filter with the same name already exists, it is reused by id. Prefer referencing existing filters by id when available. Use ai_filters.create + ai_filters.test for fine-tuning before assigning. - template: the reply a rule_based agent sends, with no model run. Either a string ("Hi {from_name}, we open at 9") or a card object {text, attachments, buttons} — text is required, attachments is a list of file ids (files.upload), buttons is a list of {label, value|url|web_app} carrying exactly ONE target each: value = a reply the bot receives back, url = opens a link (add track: true to count each tap per conversation, readable as analytics_link_clicks_v in analytics.query; add tag: <ai_tag id> beside it to put that tag on the CONVERSATION at the tap, so for people, not groups, where any member's tap tags the whole group; add pass: "<name>" to open the url with <name>=<the chat's id on its channel, a Telegram user id for a bot chat>, so the site can name the person back in its own events; add pass_source: "<name>" to also add <name>=<where the chat came from: a bot link's start parameter, an ad's ref>, nothing when unknown; a web_app button takes pass and pass_source too, written into its url at send), web_app = opens a Mini App over https. The string, and a card's text, substitute {from_name}, {message_text}, {channel_type}, {thread_id}, {raw_data}; button labels and targets are sent verbatim. A card with buttons needs send_mode auto — a draft row cannot carry a keyboard. Buttons need a channel that renders them (telegram_bot). A card needs a chat to land in, so it refuses on webhook, schedule and other thread-less triggers where a string still drafts. - handoff: {agent_id, task} — only on a rule_based agent's trigger (refused elsewhere). After the rule's deterministic part has actually happened — the template's message delivered, or the agent's script completed — the named agent runs on the same thread, in its own send mode, exactly as its own trigger would run it: the customer's message reaches it as the incoming message, and `task` reaches it as the handoff brief from this rule. The rule stays instant; the thinking — a reminder, a referral code, a personal follow-up — happens behind it. Script plus handoff is how a workspace does something deterministic the platform has no verb for (file the thread, stamp a tag, push a row) and still lets an agent answer, with the deterministic part living in that agent's own script rather than in platform code. `task` substitutes {channel_type} and {thread_id} only; {message_text}, {from_name} and {raw_data} are refused (the sender would be writing the instruction — the message and its sender already reach the target as the incoming message). The target must be an active agentic or claude_channels agent in this workspace (the engines that read the brief). The target's run is a normal trigger run: it holds the thread lock, its own safety gates apply, and its final answer is delivered like any DM reply — a follow-up that should stay silent must call agent.silence. Nothing runs when the message was drafted, refused or failed, when the script failed, when a safety gate has the rule in draft mode, or when the event carries no thread for the target to answer on. A target paused or deleted after the trigger was written does not stop the rule's message: it goes out, and the reason the follow-up did not start is recorded in the rule's activity row (error field) and in the target's activity as an execution_error. - contact_states: ["active"] — filter by contact state - cooldown_seconds: 30 — min gap between runs per thread - max_runs_per_thread_per_hour: 5 — rate limit - once_per_thread: true — after this trigger completes on a conversation it steps aside there and the next matching trigger answers later messages. For a rule that files / tags / hands off once, not for the agent that holds the conversation. - answer_delay_s: 15 — voice pickup only (incoming_call, or incoming_message scoped to a voice channel). Ring the human's own devices this long before the agent answers; if they pick up, the agent stands down. 0/absent = answer immediately. Honoured on WhatsApp and Telegram 1:1 — other voice channels have nothing ringing to wait for and still answer at once. - auto_join: true|false — voice pickup, GROUP calls only. Whether the bot enters a matching group call on its own (true) or the call becomes a pending invite an operator accepts (false). OMIT THE KEY to defer to the channel setting (channel_account.state.voice_auto_join_policy, default 'approval'); resolution is trigger-when-present, then channel, then approval, so an explicit false beats a channel set to auto. Absent and false are different answers. - chat_ids: ["-5172634473"] — voice pickup, Telegram GROUP calls only. Scopes the trigger to specific groups; omit for every group call. Any id spelling works (5172634473, -5172634473, -1005172634473 are the same group). A call whose chat is unknown never satisfies it, so do NOT set this together with 1:1 / Twilio / Telnyx / WhatsApp / Android / LiveChat voice channels or the "voice" wildcard: those calls have no chat and the trigger would stop answering them. Supported fields for job_completed (proactive callback when a delegated job finishes): - source_agent_id: <int> — fire only when this agent's job completed - source_agent_slug: <str> — alternate to source_agent_id - job_type: "agentic_session" — match a specific job type (default: any) - outcome: ["completed"] | ["escalated"] | ["completed","escalated"] — default ["completed"] - min_duration_seconds: <int> — skip very-short jobs (noise filter) - thread_filter: {thread_ids: [<int>...]} — restrict to specific threads Supported fields for calendar_event (fires N minutes before a Google Calendar event starts): - window_minutes_before: <int 1-1440> — REQUIRED, fire when an event starts within this window - channel_account_ids: [<int>...] — restrict to specific calendar accounts (default: all) - keywords: ["standup"] — word-boundary match on event title - prepare_meet_join: true — pre-invite the pool bots that can join signed in (none when none can) to the event, for an unattended Meet join Supported fields for task_assigned (a task on the workspace board was assigned to this agent): - target_session: <session_id> — for a Claude Code agent, the session the task goes to (default: the agent's own session) Supported fields for job_continuation (this agent's own call or video finished): - job_types: ["voice_call", "video_generation"] — which kinds re-invoke it (default: all) Supported fields for message_reaction (somebody ADDED an emoji reaction to a message; one run per reaction, never for the account's own reactions or for a reaction taken back): - reaction_on: "own" (default: only reactions to messages sent from this account, by the agent or the owner) or "any" (reactions to anybody's messages in the chat) - emojis: ["👍", "❤"] — only these reactions (default: every emoji) - channel_account_ids, channel_types, thread_filter: {thread_ids / excluded_thread_ids} — which accounts and chats, as for incoming_message A Telegram BOT receives reactions in a group only when it is an administrator there. Supported fields for message_edited (a person EDITED a message they had sent; one run per edit that changes the text, at any age, never for our own messages; the agent is told it is an edit and gets the new and, when known, the previous text): - keywords: ["word"], keyword_match: "any"|"all" — matched against the NEW text - channel_account_ids, thread_filter: {thread_ids / excluded_thread_ids}, folder_ids, ai_tag_ids — which accounts and chats, as for incoming_message While the workspace has an enabled message_edited trigger it handles every edit; an edit none of them matches within 2 minutes of sending still gets the built-in re-run. incoming_message action fields: - action: "reply_text" (default, normal agent run) or "join_voice" (deterministically join the voice channel resolved from the message — requires send_mode=auto) - message_source: "real" (default) | "transcript" | "both" — real messages vs turns during a live call. Transcripts are turns that address the agent. - voice_wake_only: true — with message_source "transcript": the trigger only WAKES the agent already live in that call (out of quiet mode) and never sends one into a call where no agent is live (e.g. a transcribe-only bot on a client's meeting). Use it for "are you there?"-style wake words. calendar_event run-mode field (incoming_message uses `action` instead): - run_mode: "text" (default) or "voice" (join the meeting — requires send_mode=auto) - voice: {speak_first: <bool — greet immediately vs stay silent until addressed>, vision_mode: "off"|"on_demand"|"continuous_0_3fps"} — pairs with action=join_voice (incoming_message) or run_mode=voice (calendar_event)
thread_idsNoRestrict this trigger to specific threads (chats) by their numeric thread IDs. When set, the trigger only fires for messages in these threads. Only for incoming_message and job_completed triggers. Maps to conditions.thread_filter.thread_ids.
in_workspaceNoRun this one call in this workspace id instead of the session's. Nothing is stored; other sessions are not affected.
trigger_typeYesType of trigger: 'incoming_message', 'incoming_call', 'schedule', 'webhook', 'event', 'blockchain_event', 'job_completed', 'calendar_event', 'lead_captured', 'task_assigned' (a task on the workspace board was assigned to this agent; without one, assigning a task does not start the agent), 'job_continuation' (this agent's OWN call from calls.make or video from videos.generate finished; without one the agent is not re-invoked to carry on), or 'message_reaction' (somebody put an emoji reaction on a message of a conversation: a client's thumbs-up under a draft; without one a reaction starts nothing), or 'message_edited' (a person EDITED a message they had sent, whatever its age; without one an edit starts nothing except the built-in re-run for an edit made within 2 minutes of sending)
target_sessionNoWhich Claude Code desktop session this trigger's runs go to, by the name / client id / session id that workspace.desktops lists. Only meaningful on a claude_channels agent: that engine hands the run to a connected desktop, and without an address it can only be delivered when EXACTLY ONE is connected (a second open window turns every run into channel_target_missing). A task assigned to the agent still wins — its own target_session is per-request and more specific than the trigger's default. Stored as conditions.target_session.
blocked_sender_idsNoNever react to these senders/callers, by their channel-side id — a phone number, a WhatsApp JID, a Telegram user id, an email address. Explicit deny: it beats every allow-list, and it applies to ALL trigger types, including incoming_call, so it is how you stop an agent answering one nuisance caller without silencing it for everybody. Phone-shaped ids are matched by their digits, so '+998901234567', '998901234567' and '998901234567@s.whatsapp.net' are the same person. Maps to conditions.sender_filter.excluded_external_ids.
excluded_thread_idsNoExclude specific threads (chats) by their numeric thread IDs — the opposite of thread_ids. When set, the trigger NEVER fires for messages in these threads, even if thread_ids would otherwise allow them (explicit deny wins). Only for incoming_message and job_completed triggers. Maps to conditions.thread_filter.excluded_thread_ids.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / conditions / description
      Previous value: -"Trigger conditions (JSON).\nFor blockchain_event (all three required): blockchain_addresses: [\"<address>\"] — the wallets to watch; blockchain_chains: any of [\"bitcoin\",\"ethereum\",\"bsc\",\"tron\",\"solana\"] (the chain is part of the wallet's identity: the same 0x address is a different wallet on ethereum and on bsc, so name only the chains meant); blockchain_events: any of [\"transfer_in\",\"transfer_out\",\"risk_level_up\",\"sanctioned\",\"frozen\"]. Optional, transfers only: blockchain_tokens: [\"USDT\"], blockchain_min_amount: 100. The run receives the event kind, chain, address and, for transfers, the list of transfers (tx, time, token, amount, USD value, counterparty and its risk). If the answer carries watch_note, the address is saved but not watched yet.\nSupported fields for incoming_message:\n- keywords: [\"pricing\",\"demo\"] — message must contain keyword(s) (free, no LLM cost)\n- keyword_match: \"any\" (default, OR) or \"all\" (AND)\n- channel_types: [\"telegram\",\"whatsapp\",\"livechat_voice\",\"twilio_voice\",\"telegram_voice\",\"voice\",...] — filter by channel. For voice, use EITHER the three per-channel keys (scoped) OR \"voice\" alone (wildcard matching all three) — mixing them is redundant. Per-channel keys: \"livechat_voice\" (web widget), \"twilio_voice\" (PSTN inbound), \"telegram_voice\" (Telegram p2p calls)\n- context_types: [\"dm\",\"group\",\"channel\",\"livechat\"] — filter by chat type\n- group_mode: \"mentions_only\" or \"questions\" — for group chats\n- channel_account_ids: [\"123\"] — restrict to specific accounts. Only accounts THIS workspace answers: a trigger never fires for another workspace's channel, so create it on an agent there\n- folder_ids: [5,10] — restrict to threads in folders\n- ai_tag_ids: [1,2] — restrict to threads with AI tags\n- ai_filter_ids: [1,2] — semantic intent filters (message matched via embedding similarity, works in noisy groups)\n- ai_filter_mode: \"any\" (default, OR) or \"all\" (AND) — how multiple AI filters combine\n- ai_filters: [{id: 1}, {name: \"...\", description: \"...\"}] — shorthand: reference existing by id or create inline (calls Voyage embedding API). If a filter with the same name already exists, it is reused by id. Prefer referencing existing filters by id when available. Use ai_filters.create + ai_filters.test for fine-tuning before assigning.\n- template: the reply a rule_based agent sends, with no model run. Either a string (\"Hi {from_name}, we open at 9\") or a card object {text, attachments, buttons} — text is required, attachments is a list of file ids (files.upload), buttons is a list of {label, value|url|web_app} carrying exactly ONE target each: value = a reply the bot receives back, url = opens a link (add track: true to count each tap per conversation, readable as analytics_link_clicks_v in analytics.query; add tag: <ai_tag id> beside it to put that tag on the CONVERSATION at the tap, so for people, not groups, where any member's tap tags the whole group; add pass: \"<name>\" to open the url with <name>=<the chat's id on its channel, a Telegram user id for a bot chat>, so the site can name the person back in its own events; add pass_source: \"<name>\" to also add <name>=<where the chat came from: a bot link's start parameter, an ad's ref>, nothing when unknown), web_app = opens a Mini App over https. The string, and a card's text, substitute {from_name}, {message_text}, {channel_type}, {thread_id}, {raw_data}; button labels and targets are sent verbatim. A card with buttons needs send_mode auto — a draft row cannot carry a keyboard. Buttons need a channel that renders them (telegram_bot). A card needs a chat to land in, so it refuses on webhook, schedule and other thread-less triggers where a string still drafts.\n- handoff: {agent_id, task} — only on a rule_based agent's trigger (refused elsewhere). After the rule's deterministic part has actually happened — the template's message delivered, or the agent's script completed — the named agent runs on the same thread, in its own send mode, exactly as its own trigger would run it: the customer's message reaches it as the incoming message, and `task` reaches it as the handoff brief from this rule. The rule stays instant; the thinking — a reminder, a referral code, a personal follow-up — happens behind it. Script plus handoff is how a workspace does something deterministic the platform has no verb for (file the thread, stamp a tag, push a row) and still lets an agent answer, with the deterministic part living in that agent's own script rather than in platform code. `task` substitutes {channel_type} and {thread_id} only; {message_text}, {from_name} and {raw_data} are refused (the sender would be writing the instruction — the message and its sender already reach the target as the incoming message). The target must be an active agentic or claude_channels agent in this workspace (the engines that read the brief). The target's run is a normal trigger run: it holds the thread lock, its own safety gates apply, and its final answer is delivered like any DM reply — a follow-up that should stay silent must call agent.silence. Nothing runs when the message was drafted, refused or failed, when the script failed, when a safety gate has the rule in draft mode, or when the event carries no thread for the target to answer on. A target paused or deleted after the trigger was written does not stop the rule's message: it goes out, and the reason the follow-up did not start is recorded in the rule's activity row (error field) and in the target's activity as an execution_error.\n- contact_states: [\"active\"] — filter by contact state\n- cooldown_seconds: 30 — min gap between runs per thread\n- max_runs_per_thread_per_hour: 5 — rate limit\n- once_per_thread: true — after this trigger completes on a conversation it steps aside there and the next matching trigger answers later messages. For a rule that files / tags / hands off once, not for the agent that holds the conversation.\n- answer_delay_s: 15 — voice pickup only (incoming_call, or incoming_message scoped to a voice channel). Ring the human's own devices this long before the agent answers; if they pick up, the agent stands down. 0/absent = answer immediately. Honoured on WhatsApp and Telegram 1:1 — other voice channels have nothing ringing to wait for and still answer at once.\n- auto_join: true|false — voice pickup, GROUP calls only. Whether the bot enters a matching group call on its own (true) or the call becomes a pending invite an operator accepts (false). OMIT THE KEY to defer to the channel setting (channel_account.state.voice_auto_join_policy, default 'approval'); resolution is trigger-when-present, then channel, then approval, so an explicit false beats a channel set to auto. Absent and false are different answers.\n- chat_ids: [\"-5172634473\"] — voice pickup, Telegram GROUP calls only. Scopes the trigger to specific groups; omit for every group call. Any id spelling works (5172634473, -5172634473, -1005172634473 are the same group). A call whose chat is unknown never satisfies it, so do NOT set this together with 1:1 / Twilio / Telnyx / WhatsApp / Android / LiveChat voice channels or the \"voice\" wildcard: those calls have no chat and the trigger would stop answering them.\n\nSupported fields for job_completed (proactive callback when a delegated job finishes):\n- source_agent_id: <int> — fire only when this agent's job completed\n- source_agent_slug: <str> — alternate to source_agent_id\n- job_type: \"agentic_session\" — match a specific job type (default: any)\n- outcome: [\"completed\"] | [\"escalated\"] | [\"completed\",\"escalated\"] — default [\"completed\"]\n- min_duration_seconds: <int> — skip very-short jobs (noise filter)\n- thread_filter: {thread_ids: [<int>...]} — restrict to specific threads\n\nSupported fields for calendar_event (fires N minutes before a Google Calendar event starts):\n- window_minutes_before: <int 1-1440> — REQUIRED, fire when an event starts within this window\n- channel_account_ids: [<int>...] — restrict to specific calendar accounts (default: all)\n- keywords: [\"standup\"] — word-boundary match on event title\n- prepare_meet_join: true — pre-invite the pool bots that can join signed in (none when none can) to the event, for an unattended Meet join\n\nSupported fields for task_assigned (a task on the workspace board was assigned to this agent):\n- target_session: <session_id> — for a Claude Code agent, the session the task goes to (default: the agent's own session)\n\nSupported fields for job_continuation (this agent's own call or video finished):\n- job_types: [\"voice_call\", \"video_generation\"] — which kinds re-invoke it (default: all)\n\nSupported fields for message_reaction (somebody ADDED an emoji reaction to a message; one run per reaction, never for the account's own reactions or for a reaction taken back):\n- reaction_on: \"own\" (default: only reactions to messages sent from this account, by the agent or the owner) or \"any\" (reactions to anybody's messages in the chat)\n- emojis: [\"👍\", \"❤\"] — only these reactions (default: every emoji)\n- channel_account_ids, channel_types, thread_filter: {thread_ids / excluded_thread_ids} — which accounts and chats, as for incoming_message\nA Telegram BOT receives reactions in a group only when it is an administrator there.\n\nSupported fields for message_edited (a person EDITED a message they had sent; one run per edit that changes the text, at any age, never for our own messages; the agent is told it is an edit and gets the new and, when known, the previous text):\n- keywords: [\"word\"], keyword_match: \"any\"|\"all\" — matched against the NEW text\n- channel_account_ids, thread_filter: {thread_ids / excluded_thread_ids}, folder_ids, ai_tag_ids — which accounts and chats, as for incoming_message\nWhile the workspace has an enabled message_edited trigger it handles every edit; an edit none of them matches within 2 minutes of sending still gets the built-in re-run.\n\nincoming_message action fields:\n- action: \"reply_text\" (default, normal agent run) or \"join_voice\" (deterministically join the voice channel resolved from the message — requires send_mode=auto)\n- message_source: \"real\" (default) | \"transcript\" | \"both\" — real messages vs turns during a live call. Transcripts are turns that address the agent.\n- voice_wake_only: true — with message_source \"transcript\": the trigger only WAKES the agent already live in that call (out of quiet mode) and never sends one into a call where no agent is live (e.g. a transcribe-only bot on a client's meeting). Use it for \"are you there?\"-style wake words.\n\ncalendar_event run-mode field (incoming_message uses `action` instead):\n- run_mode: \"text\" (default) or \"voice\" (join the meeting — requires send_mode=auto)\n- voice: {speak_first: <bool — greet immediately vs stay silent until addressed>, vision_mode: \"off\"|\"on_demand\"|\"continuous_0_3fps\"} — pairs with action=join_voice (incoming_message) or run_mode=voice (calendar_event)"New value: +"Trigger conditions (JSON).\nFor blockchain_event (all three required): blockchain_addresses: [\"<address>\"] — the wallets to watch; blockchain_chains: any of [\"bitcoin\",\"ethereum\",\"bsc\",\"tron\",\"solana\"] (the chain is part of the wallet's identity: the same 0x address is a different wallet on ethereum and on bsc, so name only the chains meant); blockchain_events: any of [\"transfer_in\",\"transfer_out\",\"risk_level_up\",\"sanctioned\",\"frozen\"]. Optional, transfers only: blockchain_tokens: [\"USDT\"], blockchain_min_amount: 100. The run receives the event kind, chain, address and, for transfers, the list of transfers (tx, time, token, amount, USD value, counterparty and its risk). If the answer carries watch_note, the address is saved but not watched yet.\nSupported fields for incoming_message:\n- keywords: [\"pricing\",\"demo\"] — message must contain keyword(s) (free, no LLM cost)\n- keyword_match: \"any\" (default, OR) or \"all\" (AND)\n- channel_types: [\"telegram\",\"whatsapp\",\"livechat_voice\",\"twilio_voice\",\"telegram_voice\",\"voice\",...] — filter by channel. For voice, use EITHER the three per-channel keys (scoped) OR \"voice\" alone (wildcard matching all three) — mixing them is redundant. Per-channel keys: \"livechat_voice\" (web widget), \"twilio_voice\" (PSTN inbound), \"telegram_voice\" (Telegram p2p calls)\n- context_types: [\"dm\",\"group\",\"channel\",\"livechat\"] — filter by chat type\n- group_mode: \"mentions_only\" or \"questions\" — for group chats\n- channel_account_ids: [\"123\"] — restrict to specific accounts. Only accounts THIS workspace answers: a trigger never fires for another workspace's channel, so create it on an agent there\n- folder_ids: [5,10] — restrict to threads in folders\n- ai_tag_ids: [1,2] — restrict to threads with AI tags\n- ai_filter_ids: [1,2] — semantic intent filters (message matched via embedding similarity, works in noisy groups)\n- ai_filter_mode: \"any\" (default, OR) or \"all\" (AND) — how multiple AI filters combine\n- ai_filters: [{id: 1}, {name: \"...\", description: \"...\"}] — shorthand: reference existing by id or create inline (calls Voyage embedding API). If a filter with the same name already exists, it is reused by id. Prefer referencing existing filters by id when available. Use ai_filters.create + ai_filters.test for fine-tuning before assigning.\n- template: the reply a rule_based agent sends, with no model run. Either a string (\"Hi {from_name}, we open at 9\") or a card object {text, attachments, buttons} — text is required, attachments is a list of file ids (files.upload), buttons is a list of {label, value|url|web_app} carrying exactly ONE target each: value = a reply the bot receives back, url = opens a link (add track: true to count each tap per conversation, readable as analytics_link_clicks_v in analytics.query; add tag: <ai_tag id> beside it to put that tag on the CONVERSATION at the tap, so for people, not groups, where any member's tap tags the whole group; add pass: \"<name>\" to open the url with <name>=<the chat's id on its channel, a Telegram user id for a bot chat>, so the site can name the person back in its own events; add pass_source: \"<name>\" to also add <name>=<where the chat came from: a bot link's start parameter, an ad's ref>, nothing when unknown; a web_app button takes pass and pass_source too, written into its url at send), web_app = opens a Mini App over https. The string, and a card's text, substitute {from_name}, {message_text}, {channel_type}, {thread_id}, {raw_data}; button labels and targets are sent verbatim. A card with buttons needs send_mode auto — a draft row cannot carry a keyboard. Buttons need a channel that renders them (telegram_bot). A card needs a chat to land in, so it refuses on webhook, schedule and other thread-less triggers where a string still drafts.\n- handoff: {agent_id, task} — only on a rule_based agent's trigger (refused elsewhere). After the rule's deterministic part has actually happened — the template's message delivered, or the agent's script completed — the named agent runs on the same thread, in its own send mode, exactly as its own trigger would run it: the customer's message reaches it as the incoming message, and `task` reaches it as the handoff brief from this rule. The rule stays instant; the thinking — a reminder, a referral code, a personal follow-up — happens behind it. Script plus handoff is how a workspace does something deterministic the platform has no verb for (file the thread, stamp a tag, push a row) and still lets an agent answer, with the deterministic part living in that agent's own script rather than in platform code. `task` substitutes {channel_type} and {thread_id} only; {message_text}, {from_name} and {raw_data} are refused (the sender would be writing the instruction — the message and its sender already reach the target as the incoming message). The target must be an active agentic or claude_channels agent in this workspace (the engines that read the brief). The target's run is a normal trigger run: it holds the thread lock, its own safety gates apply, and its final answer is delivered like any DM reply — a follow-up that should stay silent must call agent.silence. Nothing runs when the message was drafted, refused or failed, when the script failed, when a safety gate has the rule in draft mode, or when the event carries no thread for the target to answer on. A target paused or deleted after the trigger was written does not stop the rule's message: it goes out, and the reason the follow-up did not start is recorded in the rule's activity row (error field) and in the target's activity as an execution_error.\n- contact_states: [\"active\"] — filter by contact state\n- cooldown_seconds: 30 — min gap between runs per thread\n- max_runs_per_thread_per_hour: 5 — rate limit\n- once_per_thread: true — after this trigger completes on a conversation it steps aside there and the next matching trigger answers later messages. For a rule that files / tags / hands off once, not for the agent that holds the conversation.\n- answer_delay_s: 15 — voice pickup only (incoming_call, or incoming_message scoped to a voice channel). Ring the human's own devices this long before the agent answers; if they pick up, the agent stands down. 0/absent = answer immediately. Honoured on WhatsApp and Telegram 1:1 — other voice channels have nothing ringing to wait for and still answer at once.\n- auto_join: true|false — voice pickup, GROUP calls only. Whether the bot enters a matching group call on its own (true) or the call becomes a pending invite an operator accepts (false). OMIT THE KEY to defer to the channel setting (channel_account.state.voice_auto_join_policy, default 'approval'); resolution is trigger-when-present, then channel, then approval, so an explicit false beats a channel set to auto. Absent and false are different answers.\n- chat_ids: [\"-5172634473\"] — voice pickup, Telegram GROUP calls only. Scopes the trigger to specific groups; omit for every group call. Any id spelling works (5172634473, -5172634473, -1005172634473 are the same group). A call whose chat is unknown never satisfies it, so do NOT set this together with 1:1 / Twilio / Telnyx / WhatsApp / Android / LiveChat voice channels or the \"voice\" wildcard: those calls have no chat and the trigger would stop answering them.\n\nSupported fields for job_completed (proactive callback when a delegated job finishes):\n- source_agent_id: <int> — fire only when this agent's job completed\n- source_agent_slug: <str> — alternate to source_agent_id\n- job_type: \"agentic_session\" — match a specific job type (default: any)\n- outcome: [\"completed\"] | [\"escalated\"] | [\"completed\",\"escalated\"] — default [\"completed\"]\n- min_duration_seconds: <int> — skip very-short jobs (noise filter)\n- thread_filter: {thread_ids: [<int>...]} — restrict to specific threads\n\nSupported fields for calendar_event (fires N minutes before a Google Calendar event starts):\n- window_minutes_before: <int 1-1440> — REQUIRED, fire when an event starts within this window\n- channel_account_ids: [<int>...] — restrict to specific calendar accounts (default: all)\n- keywords: [\"standup\"] — word-boundary match on event title\n- prepare_meet_join: true — pre-invite the pool bots that can join signed in (none when none can) to the event, for an unattended Meet join\n\nSupported fields for task_assigned (a task on the workspace board was assigned to this agent):\n- target_session: <session_id> — for a Claude Code agent, the session the task goes to (default: the agent's own session)\n\nSupported fields for job_continuation (this agent's own call or video finished):\n- job_types: [\"voice_call\", \"video_generation\"] — which kinds re-invoke it (default: all)\n\nSupported fields for message_reaction (somebody ADDED an emoji reaction to a message; one run per reaction, never for the account's own reactions or for a reaction taken back):\n- reaction_on: \"own\" (default: only reactions to messages sent from this account, by the agent or the owner) or \"any\" (reactions to anybody's messages in the chat)\n- emojis: [\"👍\", \"❤\"] — only these reactions (default: every emoji)\n- channel_account_ids, channel_types, thread_filter: {thread_ids / excluded_thread_ids} — which accounts and chats, as for incoming_message\nA Telegram BOT receives reactions in a group only when it is an administrator there.\n\nSupported fields for message_edited (a person EDITED a message they had sent; one run per edit that changes the text, at any age, never for our own messages; the agent is told it is an edit and gets the new and, when known, the previous text):\n- keywords: [\"word\"], keyword_match: \"any\"|\"all\" — matched against the NEW text\n- channel_account_ids, thread_filter: {thread_ids / excluded_thread_ids}, folder_ids, ai_tag_ids — which accounts and chats, as for incoming_message\nWhile the workspace has an enabled message_edited trigger it handles every edit; an edit none of them matches within 2 minutes of sending still gets the built-in re-run.\n\nincoming_message action fields:\n- action: \"reply_text\" (default, normal agent run) or \"join_voice\" (deterministically join the voice channel resolved from the message — requires send_mode=auto)\n- message_source: \"real\" (default) | \"transcript\" | \"both\" — real messages vs turns during a live call. Transcripts are turns that address the agent.\n- voice_wake_only: true — with message_source \"transcript\": the trigger only WAKES the agent already live in that call (out of quiet mode) and never sends one into a call where no agent is live (e.g. a transcribe-only bot on a client's meeting). Use it for \"are you there?\"-style wake words.\n\ncalendar_event run-mode field (incoming_message uses `action` instead):\n- run_mode: \"text\" (default) or \"voice\" (join the meeting — requires send_mode=auto)\n- voice: {speak_first: <bool — greet immediately vs stay silent until addressed>, vision_mode: \"off\"|\"on_demand\"|\"continuous_0_3fps\"} — pairs with action=join_voice (incoming_message) or run_mode=voice (calendar_event)"
  2. Changed1 schema field changed
    • changedInput schema / properties / conditions / description
      Previous value: -"Trigger conditions (JSON).\nFor blockchain_event (all three required): blockchain_addresses: [\"<address>\"] — the wallets to watch; blockchain_chains: any of [\"bitcoin\",\"ethereum\",\"bsc\",\"tron\",\"solana\"] (the chain is part of the wallet's identity: the same 0x address is a different wallet on ethereum and on bsc, so name only the chains meant); blockchain_events: any of [\"transfer_in\",\"transfer_out\",\"risk_level_up\",\"sanctioned\",\"frozen\"]. Optional, transfers only: blockchain_tokens: [\"USDT\"], blockchain_min_amount: 100. The run receives the event kind, chain, address and, for transfers, the list of transfers (tx, time, token, amount, USD value, counterparty and its risk). If the answer carries watch_note, the address is saved but not watched yet.\nSupported fields for incoming_message:\n- keywords: [\"pricing\",\"demo\"] — message must contain keyword(s) (free, no LLM cost)\n- keyword_match: \"any\" (default, OR) or \"all\" (AND)\n- channel_types: [\"telegram\",\"whatsapp\",\"livechat_voice\",\"twilio_voice\",\"telegram_voice\",\"voice\",...] — filter by channel. For voice, use EITHER the three per-channel keys (scoped) OR \"voice\" alone (wildcard matching all three) — mixing them is redundant. Per-channel keys: \"livechat_voice\" (web widget), \"twilio_voice\" (PSTN inbound), \"telegram_voice\" (Telegram p2p calls)\n- context_types: [\"dm\",\"group\",\"channel\",\"livechat\"] — filter by chat type\n- group_mode: \"mentions_only\" or \"questions\" — for group chats\n- channel_account_ids: [\"123\"] — restrict to specific accounts. Only accounts THIS workspace answers: a trigger never fires for another workspace's channel, so create it on an agent there\n- folder_ids: [5,10] — restrict to threads in folders\n- ai_tag_ids: [1,2] — restrict to threads with AI tags\n- ai_filter_ids: [1,2] — semantic intent filters (message matched via embedding similarity, works in noisy groups)\n- ai_filter_mode: \"any\" (default, OR) or \"all\" (AND) — how multiple AI filters combine\n- ai_filters: [{id: 1}, {name: \"...\", description: \"...\"}] — shorthand: reference existing by id or create inline (calls Voyage embedding API). If a filter with the same name already exists, it is reused by id. Prefer referencing existing filters by id when available. Use ai_filters.create + ai_filters.test for fine-tuning before assigning.\n- template: the reply a rule_based agent sends, with no model run. Either a string (\"Hi {from_name}, we open at 9\") or a card object {text, attachments, buttons} — text is required, attachments is a list of file ids (files.upload), buttons is a list of {label, value|url|web_app} carrying exactly ONE target each: value = a reply the bot receives back, url = opens a link (add track: true to count each tap per conversation, readable as analytics_link_clicks_v in analytics.query; add tag: <ai_tag id> beside it to put that tag on the CONVERSATION at the tap, so for people, not groups, where any member's tap tags the whole group; add pass: \"<name>\" to open the url with <name>=<the chat's id on its channel, a Telegram user id for a bot chat>, so the site can name the person back in its own events; add pass_source: \"<name>\" to also add <name>=<where the chat came from: a bot link's start parameter, an ad's ref>, nothing when unknown), web_app = opens a Mini App over https. The string, and a card's text, substitute {from_name}, {message_text}, {channel_type}, {thread_id}, {raw_data}; button labels and targets are sent verbatim. A card with buttons needs send_mode auto — a draft row cannot carry a keyboard. Buttons need a channel that renders them (telegram_bot). A card needs a chat to land in, so it refuses on webhook, schedule and other thread-less triggers where a string still drafts.\n- handoff: {agent_id, task} — only on a rule_based agent's trigger (refused elsewhere). After the rule's deterministic part has actually happened — the template's message delivered, or the agent's script completed — the named agent runs on the same thread, in its own send mode, exactly as its own trigger would run it: the customer's message reaches it as the incoming message, and `task` reaches it as the handoff brief from this rule. The rule stays instant; the thinking — a reminder, a referral code, a personal follow-up — happens behind it. Script plus handoff is how a workspace does something deterministic the platform has no verb for (file the thread, stamp a tag, push a row) and still lets an agent answer, with the deterministic part living in that agent's own script rather than in platform code. `task` substitutes {channel_type} and {thread_id} only; {message_text}, {from_name} and {raw_data} are refused (the sender would be writing the instruction — the message and its sender already reach the target as the incoming message). The target must be an active agentic or claude_channels agent in this workspace (the engines that read the brief). The target's run is a normal trigger run: it holds the thread lock, its own safety gates apply, and its final answer is delivered like any DM reply — a follow-up that should stay silent must call agent.silence. Nothing runs when the message was drafted, refused or failed, when the script failed, when a safety gate has the rule in draft mode, or when the event carries no thread for the target to answer on. A target paused or deleted after the trigger was written does not stop the rule's message: it goes out, and the reason the follow-up did not start is recorded in the rule's activity row (error field) and in the target's activity as an execution_error.\n- contact_states: [\"active\"] — filter by contact state\n- cooldown_seconds: 30 — min gap between runs per thread\n- max_runs_per_thread_per_hour: 5 — rate limit\n- once_per_thread: true — after this trigger completes on a conversation it steps aside there and the next matching trigger answers later messages. For a rule that files / tags / hands off once, not for the agent that holds the conversation.\n- answer_delay_s: 15 — voice pickup only (incoming_call, or incoming_message scoped to a voice channel). Ring the human's own devices this long before the agent answers; if they pick up, the agent stands down. 0/absent = answer immediately. Honoured on WhatsApp and Telegram 1:1 — other voice channels have nothing ringing to wait for and still answer at once.\n- auto_join: true|false — voice pickup, GROUP calls only. Whether the bot enters a matching group call on its own (true) or the call becomes a pending invite an operator accepts (false). OMIT THE KEY to defer to the channel setting (channel_account.state.voice_auto_join_policy, default 'approval'); resolution is trigger-when-present, then channel, then approval, so an explicit false beats a channel set to auto. Absent and false are different answers.\n- chat_ids: [\"-5172634473\"] — voice pickup, Telegram GROUP calls only. Scopes the trigger to specific groups; omit for every group call. Any id spelling works (5172634473, -5172634473, -1005172634473 are the same group). A call whose chat is unknown never satisfies it, so do NOT set this together with 1:1 / Twilio / Telnyx / WhatsApp / Android / LiveChat voice channels or the \"voice\" wildcard: those calls have no chat and the trigger would stop answering them.\n\nSupported fields for job_completed (proactive callback when a delegated job finishes):\n- source_agent_id: <int> — fire only when this agent's job completed\n- source_agent_slug: <str> — alternate to source_agent_id\n- job_type: \"agentic_session\" — match a specific job type (default: any)\n- outcome: [\"completed\"] | [\"escalated\"] | [\"completed\",\"escalated\"] — default [\"completed\"]\n- min_duration_seconds: <int> — skip very-short jobs (noise filter)\n- thread_filter: {thread_ids: [<int>...]} — restrict to specific threads\n\nSupported fields for calendar_event (fires N minutes before a Google Calendar event starts):\n- window_minutes_before: <int 1-1440> — REQUIRED, fire when an event starts within this window\n- channel_account_ids: [<int>...] — restrict to specific calendar accounts (default: all)\n- keywords: [\"standup\"] — word-boundary match on event title\n- prepare_meet_join: true — pre-invite the pool bots that can join signed in (none when none can) to the event, for an unattended Meet join\n\nSupported fields for task_assigned (a task on the workspace board was assigned to this agent):\n- target_session: <session_id> — for a Claude Code agent, the session the task goes to (default: the agent's own session)\n\nSupported fields for job_continuation (this agent's own call or video finished):\n- job_types: [\"voice_call\", \"video_generation\"] — which kinds re-invoke it (default: all)\n\nSupported fields for message_reaction (somebody ADDED an emoji reaction to a message; one run per reaction, never for the account's own reactions or for a reaction taken back):\n- reaction_on: \"own\" (default: only reactions to messages sent from this account, by the agent or the owner) or \"any\" (reactions to anybody's messages in the chat)\n- emojis: [\"👍\", \"❤\"] — only these reactions (default: every emoji)\n- channel_account_ids, channel_types, thread_filter: {thread_ids / excluded_thread_ids} — which accounts and chats, as for incoming_message\nA Telegram BOT receives reactions in a group only when it is an administrator there.\n\nSupported fields for message_edited (a person EDITED a message they had sent; one run per edit that changes the text, at any age, never for our own messages; the agent is told it is an edit and gets the new and, when known, the previous text):\n- keywords: [\"word\"], keyword_match: \"any\"|\"all\" — matched against the NEW text\n- channel_account_ids, thread_filter: {thread_ids / excluded_thread_ids}, folder_ids, ai_tag_ids — which accounts and chats, as for incoming_message\nWhile the workspace has an enabled message_edited trigger it handles every edit; an edit none of them matches within 2 minutes of sending still gets the built-in re-run.\n\nincoming_message action fields:\n- action: \"reply_text\" (default, normal agent run) or \"join_voice\" (deterministically join the voice channel resolved from the message — requires send_mode=auto)\n- message_source: \"real\" (default) | \"transcript\" | \"both\" — real messages vs turns during a live call. Transcripts are turns that address the agent.\n\ncalendar_event run-mode field (incoming_message uses `action` instead):\n- run_mode: \"text\" (default) or \"voice\" (join the meeting — requires send_mode=auto)\n- voice: {speak_first: <bool — greet immediately vs stay silent until addressed>, vision_mode: \"off\"|\"on_demand\"|\"continuous_0_3fps\"} — pairs with action=join_voice (incoming_message) or run_mode=voice (calendar_event)"New value: +"Trigger conditions (JSON).\nFor blockchain_event (all three required): blockchain_addresses: [\"<address>\"] — the wallets to watch; blockchain_chains: any of [\"bitcoin\",\"ethereum\",\"bsc\",\"tron\",\"solana\"] (the chain is part of the wallet's identity: the same 0x address is a different wallet on ethereum and on bsc, so name only the chains meant); blockchain_events: any of [\"transfer_in\",\"transfer_out\",\"risk_level_up\",\"sanctioned\",\"frozen\"]. Optional, transfers only: blockchain_tokens: [\"USDT\"], blockchain_min_amount: 100. The run receives the event kind, chain, address and, for transfers, the list of transfers (tx, time, token, amount, USD value, counterparty and its risk). If the answer carries watch_note, the address is saved but not watched yet.\nSupported fields for incoming_message:\n- keywords: [\"pricing\",\"demo\"] — message must contain keyword(s) (free, no LLM cost)\n- keyword_match: \"any\" (default, OR) or \"all\" (AND)\n- channel_types: [\"telegram\",\"whatsapp\",\"livechat_voice\",\"twilio_voice\",\"telegram_voice\",\"voice\",...] — filter by channel. For voice, use EITHER the three per-channel keys (scoped) OR \"voice\" alone (wildcard matching all three) — mixing them is redundant. Per-channel keys: \"livechat_voice\" (web widget), \"twilio_voice\" (PSTN inbound), \"telegram_voice\" (Telegram p2p calls)\n- context_types: [\"dm\",\"group\",\"channel\",\"livechat\"] — filter by chat type\n- group_mode: \"mentions_only\" or \"questions\" — for group chats\n- channel_account_ids: [\"123\"] — restrict to specific accounts. Only accounts THIS workspace answers: a trigger never fires for another workspace's channel, so create it on an agent there\n- folder_ids: [5,10] — restrict to threads in folders\n- ai_tag_ids: [1,2] — restrict to threads with AI tags\n- ai_filter_ids: [1,2] — semantic intent filters (message matched via embedding similarity, works in noisy groups)\n- ai_filter_mode: \"any\" (default, OR) or \"all\" (AND) — how multiple AI filters combine\n- ai_filters: [{id: 1}, {name: \"...\", description: \"...\"}] — shorthand: reference existing by id or create inline (calls Voyage embedding API). If a filter with the same name already exists, it is reused by id. Prefer referencing existing filters by id when available. Use ai_filters.create + ai_filters.test for fine-tuning before assigning.\n- template: the reply a rule_based agent sends, with no model run. Either a string (\"Hi {from_name}, we open at 9\") or a card object {text, attachments, buttons} — text is required, attachments is a list of file ids (files.upload), buttons is a list of {label, value|url|web_app} carrying exactly ONE target each: value = a reply the bot receives back, url = opens a link (add track: true to count each tap per conversation, readable as analytics_link_clicks_v in analytics.query; add tag: <ai_tag id> beside it to put that tag on the CONVERSATION at the tap, so for people, not groups, where any member's tap tags the whole group; add pass: \"<name>\" to open the url with <name>=<the chat's id on its channel, a Telegram user id for a bot chat>, so the site can name the person back in its own events; add pass_source: \"<name>\" to also add <name>=<where the chat came from: a bot link's start parameter, an ad's ref>, nothing when unknown), web_app = opens a Mini App over https. The string, and a card's text, substitute {from_name}, {message_text}, {channel_type}, {thread_id}, {raw_data}; button labels and targets are sent verbatim. A card with buttons needs send_mode auto — a draft row cannot carry a keyboard. Buttons need a channel that renders them (telegram_bot). A card needs a chat to land in, so it refuses on webhook, schedule and other thread-less triggers where a string still drafts.\n- handoff: {agent_id, task} — only on a rule_based agent's trigger (refused elsewhere). After the rule's deterministic part has actually happened — the template's message delivered, or the agent's script completed — the named agent runs on the same thread, in its own send mode, exactly as its own trigger would run it: the customer's message reaches it as the incoming message, and `task` reaches it as the handoff brief from this rule. The rule stays instant; the thinking — a reminder, a referral code, a personal follow-up — happens behind it. Script plus handoff is how a workspace does something deterministic the platform has no verb for (file the thread, stamp a tag, push a row) and still lets an agent answer, with the deterministic part living in that agent's own script rather than in platform code. `task` substitutes {channel_type} and {thread_id} only; {message_text}, {from_name} and {raw_data} are refused (the sender would be writing the instruction — the message and its sender already reach the target as the incoming message). The target must be an active agentic or claude_channels agent in this workspace (the engines that read the brief). The target's run is a normal trigger run: it holds the thread lock, its own safety gates apply, and its final answer is delivered like any DM reply — a follow-up that should stay silent must call agent.silence. Nothing runs when the message was drafted, refused or failed, when the script failed, when a safety gate has the rule in draft mode, or when the event carries no thread for the target to answer on. A target paused or deleted after the trigger was written does not stop the rule's message: it goes out, and the reason the follow-up did not start is recorded in the rule's activity row (error field) and in the target's activity as an execution_error.\n- contact_states: [\"active\"] — filter by contact state\n- cooldown_seconds: 30 — min gap between runs per thread\n- max_runs_per_thread_per_hour: 5 — rate limit\n- once_per_thread: true — after this trigger completes on a conversation it steps aside there and the next matching trigger answers later messages. For a rule that files / tags / hands off once, not for the agent that holds the conversation.\n- answer_delay_s: 15 — voice pickup only (incoming_call, or incoming_message scoped to a voice channel). Ring the human's own devices this long before the agent answers; if they pick up, the agent stands down. 0/absent = answer immediately. Honoured on WhatsApp and Telegram 1:1 — other voice channels have nothing ringing to wait for and still answer at once.\n- auto_join: true|false — voice pickup, GROUP calls only. Whether the bot enters a matching group call on its own (true) or the call becomes a pending invite an operator accepts (false). OMIT THE KEY to defer to the channel setting (channel_account.state.voice_auto_join_policy, default 'approval'); resolution is trigger-when-present, then channel, then approval, so an explicit false beats a channel set to auto. Absent and false are different answers.\n- chat_ids: [\"-5172634473\"] — voice pickup, Telegram GROUP calls only. Scopes the trigger to specific groups; omit for every group call. Any id spelling works (5172634473, -5172634473, -1005172634473 are the same group). A call whose chat is unknown never satisfies it, so do NOT set this together with 1:1 / Twilio / Telnyx / WhatsApp / Android / LiveChat voice channels or the \"voice\" wildcard: those calls have no chat and the trigger would stop answering them.\n\nSupported fields for job_completed (proactive callback when a delegated job finishes):\n- source_agent_id: <int> — fire only when this agent's job completed\n- source_agent_slug: <str> — alternate to source_agent_id\n- job_type: \"agentic_session\" — match a specific job type (default: any)\n- outcome: [\"completed\"] | [\"escalated\"] | [\"completed\",\"escalated\"] — default [\"completed\"]\n- min_duration_seconds: <int> — skip very-short jobs (noise filter)\n- thread_filter: {thread_ids: [<int>...]} — restrict to specific threads\n\nSupported fields for calendar_event (fires N minutes before a Google Calendar event starts):\n- window_minutes_before: <int 1-1440> — REQUIRED, fire when an event starts within this window\n- channel_account_ids: [<int>...] — restrict to specific calendar accounts (default: all)\n- keywords: [\"standup\"] — word-boundary match on event title\n- prepare_meet_join: true — pre-invite the pool bots that can join signed in (none when none can) to the event, for an unattended Meet join\n\nSupported fields for task_assigned (a task on the workspace board was assigned to this agent):\n- target_session: <session_id> — for a Claude Code agent, the session the task goes to (default: the agent's own session)\n\nSupported fields for job_continuation (this agent's own call or video finished):\n- job_types: [\"voice_call\", \"video_generation\"] — which kinds re-invoke it (default: all)\n\nSupported fields for message_reaction (somebody ADDED an emoji reaction to a message; one run per reaction, never for the account's own reactions or for a reaction taken back):\n- reaction_on: \"own\" (default: only reactions to messages sent from this account, by the agent or the owner) or \"any\" (reactions to anybody's messages in the chat)\n- emojis: [\"👍\", \"❤\"] — only these reactions (default: every emoji)\n- channel_account_ids, channel_types, thread_filter: {thread_ids / excluded_thread_ids} — which accounts and chats, as for incoming_message\nA Telegram BOT receives reactions in a group only when it is an administrator there.\n\nSupported fields for message_edited (a person EDITED a message they had sent; one run per edit that changes the text, at any age, never for our own messages; the agent is told it is an edit and gets the new and, when known, the previous text):\n- keywords: [\"word\"], keyword_match: \"any\"|\"all\" — matched against the NEW text\n- channel_account_ids, thread_filter: {thread_ids / excluded_thread_ids}, folder_ids, ai_tag_ids — which accounts and chats, as for incoming_message\nWhile the workspace has an enabled message_edited trigger it handles every edit; an edit none of them matches within 2 minutes of sending still gets the built-in re-run.\n\nincoming_message action fields:\n- action: \"reply_text\" (default, normal agent run) or \"join_voice\" (deterministically join the voice channel resolved from the message — requires send_mode=auto)\n- message_source: \"real\" (default) | \"transcript\" | \"both\" — real messages vs turns during a live call. Transcripts are turns that address the agent.\n- voice_wake_only: true — with message_source \"transcript\": the trigger only WAKES the agent already live in that call (out of quiet mode) and never sends one into a call where no agent is live (e.g. a transcribe-only bot on a client's meeting). Use it for \"are you there?\"-style wake words.\n\ncalendar_event run-mode field (incoming_message uses `action` instead):\n- run_mode: \"text\" (default) or \"voice\" (join the meeting — requires send_mode=auto)\n- voice: {speak_first: <bool — greet immediately vs stay silent until addressed>, vision_mode: \"off\"|\"on_demand\"|\"continuous_0_3fps\"} — pairs with action=join_voice (incoming_message) or run_mode=voice (calendar_event)"
  3. Changed1 schema field changed
    • changedInput schema / properties / conditions / description
      Previous value: -"Trigger conditions (JSON).\nFor blockchain_event (all three required): blockchain_addresses: [\"<address>\"] — the wallets to watch; blockchain_chains: any of [\"bitcoin\",\"ethereum\",\"bsc\",\"tron\",\"solana\"] (the chain is part of the wallet's identity: the same 0x address is a different wallet on ethereum and on bsc, so name only the chains meant); blockchain_events: any of [\"transfer_in\",\"transfer_out\",\"risk_level_up\",\"sanctioned\",\"frozen\"]. Optional, transfers only: blockchain_tokens: [\"USDT\"], blockchain_min_amount: 100. The run receives the event kind, chain, address and, for transfers, the list of transfers (tx, time, token, amount, USD value, counterparty and its risk). If the answer carries watch_note, the address is saved but not watched yet.\nSupported fields for incoming_message:\n- keywords: [\"pricing\",\"demo\"] — message must contain keyword(s) (free, no LLM cost)\n- keyword_match: \"any\" (default, OR) or \"all\" (AND)\n- channel_types: [\"telegram\",\"whatsapp\",\"livechat_voice\",\"twilio_voice\",\"telegram_voice\",\"voice\",...] — filter by channel. For voice, use EITHER the three per-channel keys (scoped) OR \"voice\" alone (wildcard matching all three) — mixing them is redundant. Per-channel keys: \"livechat_voice\" (web widget), \"twilio_voice\" (PSTN inbound), \"telegram_voice\" (Telegram p2p calls)\n- context_types: [\"dm\",\"group\",\"channel\",\"livechat\"] — filter by chat type\n- group_mode: \"mentions_only\" or \"questions\" — for group chats\n- channel_account_ids: [\"123\"] — restrict to specific accounts. Only accounts THIS workspace answers: a trigger never fires for another workspace's channel, so create it on an agent there\n- folder_ids: [5,10] — restrict to threads in folders\n- ai_tag_ids: [1,2] — restrict to threads with AI tags\n- ai_filter_ids: [1,2] — semantic intent filters (message matched via embedding similarity, works in noisy groups)\n- ai_filter_mode: \"any\" (default, OR) or \"all\" (AND) — how multiple AI filters combine\n- ai_filters: [{id: 1}, {name: \"...\", description: \"...\"}] — shorthand: reference existing by id or create inline (calls Voyage embedding API). If a filter with the same name already exists, it is reused by id. Prefer referencing existing filters by id when available. Use ai_filters.create + ai_filters.test for fine-tuning before assigning.\n- template: the reply a rule_based agent sends, with no model run. Either a string (\"Hi {from_name}, we open at 9\") or a card object {text, attachments, buttons} — text is required, attachments is a list of file ids (files.upload), buttons is a list of {label, value|url|web_app} carrying exactly ONE target each: value = a reply the bot receives back, url = opens a link (add track: true to count each tap per conversation, readable as analytics_link_clicks_v in analytics.query; add tag: <ai_tag id> beside it to put that tag on the CONVERSATION at the tap, so for people, not groups, where any member's tap tags the whole group; add pass: \"<name>\" to open the url with <name>=<the chat's id on its channel, a Telegram user id for a bot chat>, so the site can name the person back in its own events), web_app = opens a Mini App over https. The string, and a card's text, substitute {from_name}, {message_text}, {channel_type}, {thread_id}, {raw_data}; button labels and targets are sent verbatim. A card with buttons needs send_mode auto — a draft row cannot carry a keyboard. Buttons need a channel that renders them (telegram_bot). A card needs a chat to land in, so it refuses on webhook, schedule and other thread-less triggers where a string still drafts.\n- handoff: {agent_id, task} — only on a rule_based agent's trigger (refused elsewhere). After the rule's deterministic part has actually happened — the template's message delivered, or the agent's script completed — the named agent runs on the same thread, in its own send mode, exactly as its own trigger would run it: the customer's message reaches it as the incoming message, and `task` reaches it as the handoff brief from this rule. The rule stays instant; the thinking — a reminder, a referral code, a personal follow-up — happens behind it. Script plus handoff is how a workspace does something deterministic the platform has no verb for (file the thread, stamp a tag, push a row) and still lets an agent answer, with the deterministic part living in that agent's own script rather than in platform code. `task` substitutes {channel_type} and {thread_id} only; {message_text}, {from_name} and {raw_data} are refused (the sender would be writing the instruction — the message and its sender already reach the target as the incoming message). The target must be an active agentic or claude_channels agent in this workspace (the engines that read the brief). The target's run is a normal trigger run: it holds the thread lock, its own safety gates apply, and its final answer is delivered like any DM reply — a follow-up that should stay silent must call agent.silence. Nothing runs when the message was drafted, refused or failed, when the script failed, when a safety gate has the rule in draft mode, or when the event carries no thread for the target to answer on. A target paused or deleted after the trigger was written does not stop the rule's message: it goes out, and the reason the follow-up did not start is recorded in the rule's activity row (error field) and in the target's activity as an execution_error.\n- contact_states: [\"active\"] — filter by contact state\n- cooldown_seconds: 30 — min gap between runs per thread\n- max_runs_per_thread_per_hour: 5 — rate limit\n- once_per_thread: true — after this trigger completes on a conversation it steps aside there and the next matching trigger answers later messages. For a rule that files / tags / hands off once, not for the agent that holds the conversation.\n- answer_delay_s: 15 — voice pickup only (incoming_call, or incoming_message scoped to a voice channel). Ring the human's own devices this long before the agent answers; if they pick up, the agent stands down. 0/absent = answer immediately. Honoured on WhatsApp and Telegram 1:1 — other voice channels have nothing ringing to wait for and still answer at once.\n- auto_join: true|false — voice pickup, GROUP calls only. Whether the bot enters a matching group call on its own (true) or the call becomes a pending invite an operator accepts (false). OMIT THE KEY to defer to the channel setting (channel_account.state.voice_auto_join_policy, default 'approval'); resolution is trigger-when-present, then channel, then approval, so an explicit false beats a channel set to auto. Absent and false are different answers.\n- chat_ids: [\"-5172634473\"] — voice pickup, Telegram GROUP calls only. Scopes the trigger to specific groups; omit for every group call. Any id spelling works (5172634473, -5172634473, -1005172634473 are the same group). A call whose chat is unknown never satisfies it, so do NOT set this together with 1:1 / Twilio / Telnyx / WhatsApp / Android / LiveChat voice channels or the \"voice\" wildcard: those calls have no chat and the trigger would stop answering them.\n\nSupported fields for job_completed (proactive callback when a delegated job finishes):\n- source_agent_id: <int> — fire only when this agent's job completed\n- source_agent_slug: <str> — alternate to source_agent_id\n- job_type: \"agentic_session\" — match a specific job type (default: any)\n- outcome: [\"completed\"] | [\"escalated\"] | [\"completed\",\"escalated\"] — default [\"completed\"]\n- min_duration_seconds: <int> — skip very-short jobs (noise filter)\n- thread_filter: {thread_ids: [<int>...]} — restrict to specific threads\n\nSupported fields for calendar_event (fires N minutes before a Google Calendar event starts):\n- window_minutes_before: <int 1-1440> — REQUIRED, fire when an event starts within this window\n- channel_account_ids: [<int>...] — restrict to specific calendar accounts (default: all)\n- keywords: [\"standup\"] — word-boundary match on event title\n- prepare_meet_join: true — pre-invite the pool bots that can join signed in (none when none can) to the event, for an unattended Meet join\n\nSupported fields for task_assigned (a task on the workspace board was assigned to this agent):\n- target_session: <session_id> — for a Claude Code agent, the session the task goes to (default: the agent's own session)\n\nSupported fields for job_continuation (this agent's own call or video finished):\n- job_types: [\"voice_call\", \"video_generation\"] — which kinds re-invoke it (default: all)\n\nSupported fields for message_reaction (somebody ADDED an emoji reaction to a message; one run per reaction, never for the account's own reactions or for a reaction taken back):\n- reaction_on: \"own\" (default: only reactions to messages sent from this account, by the agent or the owner) or \"any\" (reactions to anybody's messages in the chat)\n- emojis: [\"👍\", \"❤\"] — only these reactions (default: every emoji)\n- channel_account_ids, channel_types, thread_filter: {thread_ids / excluded_thread_ids} — which accounts and chats, as for incoming_message\nA Telegram BOT receives reactions in a group only when it is an administrator there.\n\nSupported fields for message_edited (a person EDITED a message they had sent; one run per edit that changes the text, at any age, never for our own messages; the agent is told it is an edit and gets the new and, when known, the previous text):\n- keywords: [\"word\"], keyword_match: \"any\"|\"all\" — matched against the NEW text\n- channel_account_ids, thread_filter: {thread_ids / excluded_thread_ids}, folder_ids, ai_tag_ids — which accounts and chats, as for incoming_message\nWhile the workspace has an enabled message_edited trigger it handles every edit; an edit none of them matches within 2 minutes of sending still gets the built-in re-run.\n\nincoming_message action fields:\n- action: \"reply_text\" (default, normal agent run) or \"join_voice\" (deterministically join the voice channel resolved from the message — requires send_mode=auto)\n- message_source: \"real\" (default) | \"transcript\" | \"both\" — real messages vs turns during a live call. Transcripts are turns that address the agent.\n\ncalendar_event run-mode field (incoming_message uses `action` instead):\n- run_mode: \"text\" (default) or \"voice\" (join the meeting — requires send_mode=auto)\n- voice: {speak_first: <bool — greet immediately vs stay silent until addressed>, vision_mode: \"off\"|\"on_demand\"|\"continuous_0_3fps\"} — pairs with action=join_voice (incoming_message) or run_mode=voice (calendar_event)"New value: +"Trigger conditions (JSON).\nFor blockchain_event (all three required): blockchain_addresses: [\"<address>\"] — the wallets to watch; blockchain_chains: any of [\"bitcoin\",\"ethereum\",\"bsc\",\"tron\",\"solana\"] (the chain is part of the wallet's identity: the same 0x address is a different wallet on ethereum and on bsc, so name only the chains meant); blockchain_events: any of [\"transfer_in\",\"transfer_out\",\"risk_level_up\",\"sanctioned\",\"frozen\"]. Optional, transfers only: blockchain_tokens: [\"USDT\"], blockchain_min_amount: 100. The run receives the event kind, chain, address and, for transfers, the list of transfers (tx, time, token, amount, USD value, counterparty and its risk). If the answer carries watch_note, the address is saved but not watched yet.\nSupported fields for incoming_message:\n- keywords: [\"pricing\",\"demo\"] — message must contain keyword(s) (free, no LLM cost)\n- keyword_match: \"any\" (default, OR) or \"all\" (AND)\n- channel_types: [\"telegram\",\"whatsapp\",\"livechat_voice\",\"twilio_voice\",\"telegram_voice\",\"voice\",...] — filter by channel. For voice, use EITHER the three per-channel keys (scoped) OR \"voice\" alone (wildcard matching all three) — mixing them is redundant. Per-channel keys: \"livechat_voice\" (web widget), \"twilio_voice\" (PSTN inbound), \"telegram_voice\" (Telegram p2p calls)\n- context_types: [\"dm\",\"group\",\"channel\",\"livechat\"] — filter by chat type\n- group_mode: \"mentions_only\" or \"questions\" — for group chats\n- channel_account_ids: [\"123\"] — restrict to specific accounts. Only accounts THIS workspace answers: a trigger never fires for another workspace's channel, so create it on an agent there\n- folder_ids: [5,10] — restrict to threads in folders\n- ai_tag_ids: [1,2] — restrict to threads with AI tags\n- ai_filter_ids: [1,2] — semantic intent filters (message matched via embedding similarity, works in noisy groups)\n- ai_filter_mode: \"any\" (default, OR) or \"all\" (AND) — how multiple AI filters combine\n- ai_filters: [{id: 1}, {name: \"...\", description: \"...\"}] — shorthand: reference existing by id or create inline (calls Voyage embedding API). If a filter with the same name already exists, it is reused by id. Prefer referencing existing filters by id when available. Use ai_filters.create + ai_filters.test for fine-tuning before assigning.\n- template: the reply a rule_based agent sends, with no model run. Either a string (\"Hi {from_name}, we open at 9\") or a card object {text, attachments, buttons} — text is required, attachments is a list of file ids (files.upload), buttons is a list of {label, value|url|web_app} carrying exactly ONE target each: value = a reply the bot receives back, url = opens a link (add track: true to count each tap per conversation, readable as analytics_link_clicks_v in analytics.query; add tag: <ai_tag id> beside it to put that tag on the CONVERSATION at the tap, so for people, not groups, where any member's tap tags the whole group; add pass: \"<name>\" to open the url with <name>=<the chat's id on its channel, a Telegram user id for a bot chat>, so the site can name the person back in its own events; add pass_source: \"<name>\" to also add <name>=<where the chat came from: a bot link's start parameter, an ad's ref>, nothing when unknown), web_app = opens a Mini App over https. The string, and a card's text, substitute {from_name}, {message_text}, {channel_type}, {thread_id}, {raw_data}; button labels and targets are sent verbatim. A card with buttons needs send_mode auto — a draft row cannot carry a keyboard. Buttons need a channel that renders them (telegram_bot). A card needs a chat to land in, so it refuses on webhook, schedule and other thread-less triggers where a string still drafts.\n- handoff: {agent_id, task} — only on a rule_based agent's trigger (refused elsewhere). After the rule's deterministic part has actually happened — the template's message delivered, or the agent's script completed — the named agent runs on the same thread, in its own send mode, exactly as its own trigger would run it: the customer's message reaches it as the incoming message, and `task` reaches it as the handoff brief from this rule. The rule stays instant; the thinking — a reminder, a referral code, a personal follow-up — happens behind it. Script plus handoff is how a workspace does something deterministic the platform has no verb for (file the thread, stamp a tag, push a row) and still lets an agent answer, with the deterministic part living in that agent's own script rather than in platform code. `task` substitutes {channel_type} and {thread_id} only; {message_text}, {from_name} and {raw_data} are refused (the sender would be writing the instruction — the message and its sender already reach the target as the incoming message). The target must be an active agentic or claude_channels agent in this workspace (the engines that read the brief). The target's run is a normal trigger run: it holds the thread lock, its own safety gates apply, and its final answer is delivered like any DM reply — a follow-up that should stay silent must call agent.silence. Nothing runs when the message was drafted, refused or failed, when the script failed, when a safety gate has the rule in draft mode, or when the event carries no thread for the target to answer on. A target paused or deleted after the trigger was written does not stop the rule's message: it goes out, and the reason the follow-up did not start is recorded in the rule's activity row (error field) and in the target's activity as an execution_error.\n- contact_states: [\"active\"] — filter by contact state\n- cooldown_seconds: 30 — min gap between runs per thread\n- max_runs_per_thread_per_hour: 5 — rate limit\n- once_per_thread: true — after this trigger completes on a conversation it steps aside there and the next matching trigger answers later messages. For a rule that files / tags / hands off once, not for the agent that holds the conversation.\n- answer_delay_s: 15 — voice pickup only (incoming_call, or incoming_message scoped to a voice channel). Ring the human's own devices this long before the agent answers; if they pick up, the agent stands down. 0/absent = answer immediately. Honoured on WhatsApp and Telegram 1:1 — other voice channels have nothing ringing to wait for and still answer at once.\n- auto_join: true|false — voice pickup, GROUP calls only. Whether the bot enters a matching group call on its own (true) or the call becomes a pending invite an operator accepts (false). OMIT THE KEY to defer to the channel setting (channel_account.state.voice_auto_join_policy, default 'approval'); resolution is trigger-when-present, then channel, then approval, so an explicit false beats a channel set to auto. Absent and false are different answers.\n- chat_ids: [\"-5172634473\"] — voice pickup, Telegram GROUP calls only. Scopes the trigger to specific groups; omit for every group call. Any id spelling works (5172634473, -5172634473, -1005172634473 are the same group). A call whose chat is unknown never satisfies it, so do NOT set this together with 1:1 / Twilio / Telnyx / WhatsApp / Android / LiveChat voice channels or the \"voice\" wildcard: those calls have no chat and the trigger would stop answering them.\n\nSupported fields for job_completed (proactive callback when a delegated job finishes):\n- source_agent_id: <int> — fire only when this agent's job completed\n- source_agent_slug: <str> — alternate to source_agent_id\n- job_type: \"agentic_session\" — match a specific job type (default: any)\n- outcome: [\"completed\"] | [\"escalated\"] | [\"completed\",\"escalated\"] — default [\"completed\"]\n- min_duration_seconds: <int> — skip very-short jobs (noise filter)\n- thread_filter: {thread_ids: [<int>...]} — restrict to specific threads\n\nSupported fields for calendar_event (fires N minutes before a Google Calendar event starts):\n- window_minutes_before: <int 1-1440> — REQUIRED, fire when an event starts within this window\n- channel_account_ids: [<int>...] — restrict to specific calendar accounts (default: all)\n- keywords: [\"standup\"] — word-boundary match on event title\n- prepare_meet_join: true — pre-invite the pool bots that can join signed in (none when none can) to the event, for an unattended Meet join\n\nSupported fields for task_assigned (a task on the workspace board was assigned to this agent):\n- target_session: <session_id> — for a Claude Code agent, the session the task goes to (default: the agent's own session)\n\nSupported fields for job_continuation (this agent's own call or video finished):\n- job_types: [\"voice_call\", \"video_generation\"] — which kinds re-invoke it (default: all)\n\nSupported fields for message_reaction (somebody ADDED an emoji reaction to a message; one run per reaction, never for the account's own reactions or for a reaction taken back):\n- reaction_on: \"own\" (default: only reactions to messages sent from this account, by the agent or the owner) or \"any\" (reactions to anybody's messages in the chat)\n- emojis: [\"👍\", \"❤\"] — only these reactions (default: every emoji)\n- channel_account_ids, channel_types, thread_filter: {thread_ids / excluded_thread_ids} — which accounts and chats, as for incoming_message\nA Telegram BOT receives reactions in a group only when it is an administrator there.\n\nSupported fields for message_edited (a person EDITED a message they had sent; one run per edit that changes the text, at any age, never for our own messages; the agent is told it is an edit and gets the new and, when known, the previous text):\n- keywords: [\"word\"], keyword_match: \"any\"|\"all\" — matched against the NEW text\n- channel_account_ids, thread_filter: {thread_ids / excluded_thread_ids}, folder_ids, ai_tag_ids — which accounts and chats, as for incoming_message\nWhile the workspace has an enabled message_edited trigger it handles every edit; an edit none of them matches within 2 minutes of sending still gets the built-in re-run.\n\nincoming_message action fields:\n- action: \"reply_text\" (default, normal agent run) or \"join_voice\" (deterministically join the voice channel resolved from the message — requires send_mode=auto)\n- message_source: \"real\" (default) | \"transcript\" | \"both\" — real messages vs turns during a live call. Transcripts are turns that address the agent.\n\ncalendar_event run-mode field (incoming_message uses `action` instead):\n- run_mode: \"text\" (default) or \"voice\" (join the meeting — requires send_mode=auto)\n- voice: {speak_first: <bool — greet immediately vs stay silent until addressed>, vision_mode: \"off\"|\"on_demand\"|\"continuous_0_3fps\"} — pairs with action=join_voice (incoming_message) or run_mode=voice (calendar_event)"
  4. Changed3 schema fields changed
    • changedInput schema / properties / conditions / description
      Previous value: -"Trigger conditions (JSON).\nFor blockchain_event (all three required): blockchain_addresses: [\"<address>\"] — the wallets to watch; blockchain_chains: any of [\"bitcoin\",\"ethereum\",\"bsc\",\"tron\",\"solana\"] (the chain is part of the wallet's identity: the same 0x address is a different wallet on ethereum and on bsc, so name only the chains meant); blockchain_events: any of [\"transfer_in\",\"transfer_out\",\"risk_level_up\",\"sanctioned\",\"frozen\"]. Optional, transfers only: blockchain_tokens: [\"USDT\"], blockchain_min_amount: 100. The run receives the event kind, chain, address and, for transfers, the list of transfers (tx, time, token, amount, USD value, counterparty and its risk). If the answer carries watch_note, the address is saved but not watched yet.\nSupported fields for incoming_message:\n- keywords: [\"pricing\",\"demo\"] — message must contain keyword(s) (free, no LLM cost)\n- keyword_match: \"any\" (default, OR) or \"all\" (AND)\n- channel_types: [\"telegram\",\"whatsapp\",\"livechat_voice\",\"twilio_voice\",\"telegram_voice\",\"voice\",...] — filter by channel. For voice, use EITHER the three per-channel keys (scoped) OR \"voice\" alone (wildcard matching all three) — mixing them is redundant. Per-channel keys: \"livechat_voice\" (web widget), \"twilio_voice\" (PSTN inbound), \"telegram_voice\" (Telegram p2p calls)\n- context_types: [\"dm\",\"group\",\"channel\",\"livechat\"] — filter by chat type\n- group_mode: \"mentions_only\" or \"questions\" — for group chats\n- channel_account_ids: [\"123\"] — restrict to specific accounts. Only accounts THIS workspace answers: a trigger never fires for another workspace's channel, so create it on an agent there\n- folder_ids: [5,10] — restrict to threads in folders\n- ai_tag_ids: [1,2] — restrict to threads with AI tags\n- ai_filter_ids: [1,2] — semantic intent filters (message matched via embedding similarity, works in noisy groups)\n- ai_filter_mode: \"any\" (default, OR) or \"all\" (AND) — how multiple AI filters combine\n- ai_filters: [{id: 1}, {name: \"...\", description: \"...\"}] — shorthand: reference existing by id or create inline (calls Voyage embedding API). If a filter with the same name already exists, it is reused by id. Prefer referencing existing filters by id when available. Use ai_filters.create + ai_filters.test for fine-tuning before assigning.\n- template: the reply a rule_based agent sends, with no model run. Either a string (\"Hi {from_name}, we open at 9\") or a card object {text, attachments, buttons} — text is required, attachments is a list of file ids (files.upload), buttons is a list of {label, value|url|web_app} carrying exactly ONE target each: value = a reply the bot receives back, url = opens a link (add track: true to count each tap per conversation, readable as analytics_link_clicks_v in analytics.query; add tag: <ai_tag id> beside it to put that tag on the CONVERSATION at the tap, so for people, not groups, where any member's tap tags the whole group; add pass: \"<name>\" to open the url with <name>=<the chat's id on its channel, a Telegram user id for a bot chat>, so the site can name the person back in its own events), web_app = opens a Mini App over https. The string, and a card's text, substitute {from_name}, {message_text}, {channel_type}, {thread_id}, {raw_data}; button labels and targets are sent verbatim. A card with buttons needs send_mode auto — a draft row cannot carry a keyboard. Buttons need a channel that renders them (telegram_bot). A card needs a chat to land in, so it refuses on webhook, schedule and other thread-less triggers where a string still drafts.\n- handoff: {agent_id, task} — only on a rule_based agent's trigger (refused elsewhere). After the rule's deterministic part has actually happened — the template's message delivered, or the agent's script completed — the named agent runs on the same thread, in its own send mode, exactly as its own trigger would run it: the customer's message reaches it as the incoming message, and `task` reaches it as the handoff brief from this rule. The rule stays instant; the thinking — a reminder, a referral code, a personal follow-up — happens behind it. Script plus handoff is how a workspace does something deterministic the platform has no verb for (file the thread, stamp a tag, push a row) and still lets an agent answer, with the deterministic part living in that agent's own script rather than in platform code. `task` substitutes {channel_type} and {thread_id} only; {message_text}, {from_name} and {raw_data} are refused (the sender would be writing the instruction — the message and its sender already reach the target as the incoming message). The target must be an active agentic or claude_channels agent in this workspace (the engines that read the brief). The target's run is a normal trigger run: it holds the thread lock, its own safety gates apply, and its final answer is delivered like any DM reply — a follow-up that should stay silent must call agent.silence. Nothing runs when the message was drafted, refused or failed, when the script failed, when a safety gate has the rule in draft mode, or when the event carries no thread for the target to answer on. A target paused or deleted after the trigger was written does not stop the rule's message: it goes out, and the reason the follow-up did not start is recorded in the rule's activity row (error field) and in the target's activity as an execution_error.\n- contact_states: [\"active\"] — filter by contact state\n- cooldown_seconds: 30 — min gap between runs per thread\n- max_runs_per_thread_per_hour: 5 — rate limit\n- once_per_thread: true — after this trigger completes on a conversation it steps aside there and the next matching trigger answers later messages. For a rule that files / tags / hands off once, not for the agent that holds the conversation.\n- answer_delay_s: 15 — voice pickup only (incoming_call, or incoming_message scoped to a voice channel). Ring the human's own devices this long before the agent answers; if they pick up, the agent stands down. 0/absent = answer immediately. Honoured on WhatsApp and Telegram 1:1 — other voice channels have nothing ringing to wait for and still answer at once.\n- auto_join: true|false — voice pickup, GROUP calls only. Whether the bot enters a matching group call on its own (true) or the call becomes a pending invite an operator accepts (false). OMIT THE KEY to defer to the channel setting (channel_account.state.voice_auto_join_policy, default 'approval'); resolution is trigger-when-present, then channel, then approval, so an explicit false beats a channel set to auto. Absent and false are different answers.\n- chat_ids: [\"-5172634473\"] — voice pickup, Telegram GROUP calls only. Scopes the trigger to specific groups; omit for every group call. Any id spelling works (5172634473, -5172634473, -1005172634473 are the same group). A call whose chat is unknown never satisfies it, so do NOT set this together with 1:1 / Twilio / Telnyx / WhatsApp / Android / LiveChat voice channels or the \"voice\" wildcard: those calls have no chat and the trigger would stop answering them.\n\nSupported fields for job_completed (proactive callback when a delegated job finishes):\n- source_agent_id: <int> — fire only when this agent's job completed\n- source_agent_slug: <str> — alternate to source_agent_id\n- job_type: \"agentic_session\" — match a specific job type (default: any)\n- outcome: [\"completed\"] | [\"escalated\"] | [\"completed\",\"escalated\"] — default [\"completed\"]\n- min_duration_seconds: <int> — skip very-short jobs (noise filter)\n- thread_filter: {thread_ids: [<int>...]} — restrict to specific threads\n\nSupported fields for calendar_event (fires N minutes before a Google Calendar event starts):\n- window_minutes_before: <int 1-1440> — REQUIRED, fire when an event starts within this window\n- channel_account_ids: [<int>...] — restrict to specific calendar accounts (default: all)\n- keywords: [\"standup\"] — word-boundary match on event title\n- prepare_meet_join: true — pre-invite the pool bots that can join signed in (none when none can) to the event, for an unattended Meet join\n\nSupported fields for task_assigned (a task on the workspace board was assigned to this agent):\n- target_session: <session_id> — for a Claude Code agent, the session the task goes to (default: the agent's own session)\n\nSupported fields for job_continuation (this agent's own call or video finished):\n- job_types: [\"voice_call\", \"video_generation\"] — which kinds re-invoke it (default: all)\n\nSupported fields for message_reaction (somebody ADDED an emoji reaction to a message; one run per reaction, never for the account's own reactions or for a reaction taken back):\n- reaction_on: \"own\" (default: only reactions to messages sent from this account, by the agent or the owner) or \"any\" (reactions to anybody's messages in the chat)\n- emojis: [\"👍\", \"❤\"] — only these reactions (default: every emoji)\n- channel_account_ids, channel_types, thread_filter: {thread_ids / excluded_thread_ids} — which accounts and chats, as for incoming_message\nA Telegram BOT receives reactions in a group only when it is an administrator there.\n\nincoming_message action fields:\n- action: \"reply_text\" (default, normal agent run) or \"join_voice\" (deterministically join the voice channel resolved from the message — requires send_mode=auto)\n- message_source: \"real\" (default) | \"transcript\" | \"both\" — real messages vs turns during a live call. Transcripts are turns that address the agent.\n\ncalendar_event run-mode field (incoming_message uses `action` instead):\n- run_mode: \"text\" (default) or \"voice\" (join the meeting — requires send_mode=auto)\n- voice: {speak_first: <bool — greet immediately vs stay silent until addressed>, vision_mode: \"off\"|\"on_demand\"|\"continuous_0_3fps\"} — pairs with action=join_voice (incoming_message) or run_mode=voice (calendar_event)"New value: +"Trigger conditions (JSON).\nFor blockchain_event (all three required): blockchain_addresses: [\"<address>\"] — the wallets to watch; blockchain_chains: any of [\"bitcoin\",\"ethereum\",\"bsc\",\"tron\",\"solana\"] (the chain is part of the wallet's identity: the same 0x address is a different wallet on ethereum and on bsc, so name only the chains meant); blockchain_events: any of [\"transfer_in\",\"transfer_out\",\"risk_level_up\",\"sanctioned\",\"frozen\"]. Optional, transfers only: blockchain_tokens: [\"USDT\"], blockchain_min_amount: 100. The run receives the event kind, chain, address and, for transfers, the list of transfers (tx, time, token, amount, USD value, counterparty and its risk). If the answer carries watch_note, the address is saved but not watched yet.\nSupported fields for incoming_message:\n- keywords: [\"pricing\",\"demo\"] — message must contain keyword(s) (free, no LLM cost)\n- keyword_match: \"any\" (default, OR) or \"all\" (AND)\n- channel_types: [\"telegram\",\"whatsapp\",\"livechat_voice\",\"twilio_voice\",\"telegram_voice\",\"voice\",...] — filter by channel. For voice, use EITHER the three per-channel keys (scoped) OR \"voice\" alone (wildcard matching all three) — mixing them is redundant. Per-channel keys: \"livechat_voice\" (web widget), \"twilio_voice\" (PSTN inbound), \"telegram_voice\" (Telegram p2p calls)\n- context_types: [\"dm\",\"group\",\"channel\",\"livechat\"] — filter by chat type\n- group_mode: \"mentions_only\" or \"questions\" — for group chats\n- channel_account_ids: [\"123\"] — restrict to specific accounts. Only accounts THIS workspace answers: a trigger never fires for another workspace's channel, so create it on an agent there\n- folder_ids: [5,10] — restrict to threads in folders\n- ai_tag_ids: [1,2] — restrict to threads with AI tags\n- ai_filter_ids: [1,2] — semantic intent filters (message matched via embedding similarity, works in noisy groups)\n- ai_filter_mode: \"any\" (default, OR) or \"all\" (AND) — how multiple AI filters combine\n- ai_filters: [{id: 1}, {name: \"...\", description: \"...\"}] — shorthand: reference existing by id or create inline (calls Voyage embedding API). If a filter with the same name already exists, it is reused by id. Prefer referencing existing filters by id when available. Use ai_filters.create + ai_filters.test for fine-tuning before assigning.\n- template: the reply a rule_based agent sends, with no model run. Either a string (\"Hi {from_name}, we open at 9\") or a card object {text, attachments, buttons} — text is required, attachments is a list of file ids (files.upload), buttons is a list of {label, value|url|web_app} carrying exactly ONE target each: value = a reply the bot receives back, url = opens a link (add track: true to count each tap per conversation, readable as analytics_link_clicks_v in analytics.query; add tag: <ai_tag id> beside it to put that tag on the CONVERSATION at the tap, so for people, not groups, where any member's tap tags the whole group; add pass: \"<name>\" to open the url with <name>=<the chat's id on its channel, a Telegram user id for a bot chat>, so the site can name the person back in its own events), web_app = opens a Mini App over https. The string, and a card's text, substitute {from_name}, {message_text}, {channel_type}, {thread_id}, {raw_data}; button labels and targets are sent verbatim. A card with buttons needs send_mode auto — a draft row cannot carry a keyboard. Buttons need a channel that renders them (telegram_bot). A card needs a chat to land in, so it refuses on webhook, schedule and other thread-less triggers where a string still drafts.\n- handoff: {agent_id, task} — only on a rule_based agent's trigger (refused elsewhere). After the rule's deterministic part has actually happened — the template's message delivered, or the agent's script completed — the named agent runs on the same thread, in its own send mode, exactly as its own trigger would run it: the customer's message reaches it as the incoming message, and `task` reaches it as the handoff brief from this rule. The rule stays instant; the thinking — a reminder, a referral code, a personal follow-up — happens behind it. Script plus handoff is how a workspace does something deterministic the platform has no verb for (file the thread, stamp a tag, push a row) and still lets an agent answer, with the deterministic part living in that agent's own script rather than in platform code. `task` substitutes {channel_type} and {thread_id} only; {message_text}, {from_name} and {raw_data} are refused (the sender would be writing the instruction — the message and its sender already reach the target as the incoming message). The target must be an active agentic or claude_channels agent in this workspace (the engines that read the brief). The target's run is a normal trigger run: it holds the thread lock, its own safety gates apply, and its final answer is delivered like any DM reply — a follow-up that should stay silent must call agent.silence. Nothing runs when the message was drafted, refused or failed, when the script failed, when a safety gate has the rule in draft mode, or when the event carries no thread for the target to answer on. A target paused or deleted after the trigger was written does not stop the rule's message: it goes out, and the reason the follow-up did not start is recorded in the rule's activity row (error field) and in the target's activity as an execution_error.\n- contact_states: [\"active\"] — filter by contact state\n- cooldown_seconds: 30 — min gap between runs per thread\n- max_runs_per_thread_per_hour: 5 — rate limit\n- once_per_thread: true — after this trigger completes on a conversation it steps aside there and the next matching trigger answers later messages. For a rule that files / tags / hands off once, not for the agent that holds the conversation.\n- answer_delay_s: 15 — voice pickup only (incoming_call, or incoming_message scoped to a voice channel). Ring the human's own devices this long before the agent answers; if they pick up, the agent stands down. 0/absent = answer immediately. Honoured on WhatsApp and Telegram 1:1 — other voice channels have nothing ringing to wait for and still answer at once.\n- auto_join: true|false — voice pickup, GROUP calls only. Whether the bot enters a matching group call on its own (true) or the call becomes a pending invite an operator accepts (false). OMIT THE KEY to defer to the channel setting (channel_account.state.voice_auto_join_policy, default 'approval'); resolution is trigger-when-present, then channel, then approval, so an explicit false beats a channel set to auto. Absent and false are different answers.\n- chat_ids: [\"-5172634473\"] — voice pickup, Telegram GROUP calls only. Scopes the trigger to specific groups; omit for every group call. Any id spelling works (5172634473, -5172634473, -1005172634473 are the same group). A call whose chat is unknown never satisfies it, so do NOT set this together with 1:1 / Twilio / Telnyx / WhatsApp / Android / LiveChat voice channels or the \"voice\" wildcard: those calls have no chat and the trigger would stop answering them.\n\nSupported fields for job_completed (proactive callback when a delegated job finishes):\n- source_agent_id: <int> — fire only when this agent's job completed\n- source_agent_slug: <str> — alternate to source_agent_id\n- job_type: \"agentic_session\" — match a specific job type (default: any)\n- outcome: [\"completed\"] | [\"escalated\"] | [\"completed\",\"escalated\"] — default [\"completed\"]\n- min_duration_seconds: <int> — skip very-short jobs (noise filter)\n- thread_filter: {thread_ids: [<int>...]} — restrict to specific threads\n\nSupported fields for calendar_event (fires N minutes before a Google Calendar event starts):\n- window_minutes_before: <int 1-1440> — REQUIRED, fire when an event starts within this window\n- channel_account_ids: [<int>...] — restrict to specific calendar accounts (default: all)\n- keywords: [\"standup\"] — word-boundary match on event title\n- prepare_meet_join: true — pre-invite the pool bots that can join signed in (none when none can) to the event, for an unattended Meet join\n\nSupported fields for task_assigned (a task on the workspace board was assigned to this agent):\n- target_session: <session_id> — for a Claude Code agent, the session the task goes to (default: the agent's own session)\n\nSupported fields for job_continuation (this agent's own call or video finished):\n- job_types: [\"voice_call\", \"video_generation\"] — which kinds re-invoke it (default: all)\n\nSupported fields for message_reaction (somebody ADDED an emoji reaction to a message; one run per reaction, never for the account's own reactions or for a reaction taken back):\n- reaction_on: \"own\" (default: only reactions to messages sent from this account, by the agent or the owner) or \"any\" (reactions to anybody's messages in the chat)\n- emojis: [\"👍\", \"❤\"] — only these reactions (default: every emoji)\n- channel_account_ids, channel_types, thread_filter: {thread_ids / excluded_thread_ids} — which accounts and chats, as for incoming_message\nA Telegram BOT receives reactions in a group only when it is an administrator there.\n\nSupported fields for message_edited (a person EDITED a message they had sent; one run per edit that changes the text, at any age, never for our own messages; the agent is told it is an edit and gets the new and, when known, the previous text):\n- keywords: [\"word\"], keyword_match: \"any\"|\"all\" — matched against the NEW text\n- channel_account_ids, thread_filter: {thread_ids / excluded_thread_ids}, folder_ids, ai_tag_ids — which accounts and chats, as for incoming_message\nWhile the workspace has an enabled message_edited trigger it handles every edit; an edit none of them matches within 2 minutes of sending still gets the built-in re-run.\n\nincoming_message action fields:\n- action: \"reply_text\" (default, normal agent run) or \"join_voice\" (deterministically join the voice channel resolved from the message — requires send_mode=auto)\n- message_source: \"real\" (default) | \"transcript\" | \"both\" — real messages vs turns during a live call. Transcripts are turns that address the agent.\n\ncalendar_event run-mode field (incoming_message uses `action` instead):\n- run_mode: \"text\" (default) or \"voice\" (join the meeting — requires send_mode=auto)\n- voice: {speak_first: <bool — greet immediately vs stay silent until addressed>, vision_mode: \"off\"|\"on_demand\"|\"continuous_0_3fps\"} — pairs with action=join_voice (incoming_message) or run_mode=voice (calendar_event)"
    • changedInput schema / properties / trigger_type / description
      Previous value: -"Type of trigger: 'incoming_message', 'incoming_call', 'schedule', 'webhook', 'event', 'blockchain_event', 'job_completed', 'calendar_event', 'lead_captured', 'task_assigned' (a task on the workspace board was assigned to this agent; without one, assigning a task does not start the agent), 'job_continuation' (this agent's OWN call from calls.make or video from videos.generate finished; without one the agent is not re-invoked to carry on), or 'message_reaction' (somebody put an emoji reaction on a message of a conversation: a client's thumbs-up under a draft; without one a reaction starts nothing)"New value: +"Type of trigger: 'incoming_message', 'incoming_call', 'schedule', 'webhook', 'event', 'blockchain_event', 'job_completed', 'calendar_event', 'lead_captured', 'task_assigned' (a task on the workspace board was assigned to this agent; without one, assigning a task does not start the agent), 'job_continuation' (this agent's OWN call from calls.make or video from videos.generate finished; without one the agent is not re-invoked to carry on), or 'message_reaction' (somebody put an emoji reaction on a message of a conversation: a client's thumbs-up under a draft; without one a reaction starts nothing), or 'message_edited' (a person EDITED a message they had sent, whatever its age; without one an edit starts nothing except the built-in re-run for an edit made within 2 minutes of sending)"
    • changedInput schema / properties / trigger_type / enum
      Previous value: -[
      -  "incoming_message",
      -  "incoming_call",
      -  "schedule",
      -  "webhook",
      -  "event",
      -  "blockchain_event",
      -  "job_completed",
      -  "calendar_event",
      -  "lead_captured",
      -  "task_assigned",
      -  "job_continuation",
      -  "message_reaction"
      -]New value: +[
      +  "incoming_message",
      +  "incoming_call",
      +  "schedule",
      +  "webhook",
      +  "event",
      +  "blockchain_event",
      +  "job_completed",
      +  "calendar_event",
      +  "lead_captured",
      +  "task_assigned",
      +  "job_continuation",
      +  "message_reaction",
      +  "message_edited"
      +]
  5. Changed3 schema fields changed
    • changedInput schema / properties / conditions / description
      Previous value: -"Trigger conditions (JSON).\nFor blockchain_event (all three required): blockchain_addresses: [\"<address>\"] — the wallets to watch; blockchain_chains: any of [\"bitcoin\",\"ethereum\",\"bsc\",\"tron\",\"solana\"] (the chain is part of the wallet's identity: the same 0x address is a different wallet on ethereum and on bsc, so name only the chains meant); blockchain_events: any of [\"transfer_in\",\"transfer_out\",\"risk_level_up\",\"sanctioned\",\"frozen\"]. Optional, transfers only: blockchain_tokens: [\"USDT\"], blockchain_min_amount: 100. The run receives the event kind, chain, address and, for transfers, the list of transfers (tx, time, token, amount, USD value, counterparty and its risk). If the answer carries watch_note, the address is saved but not watched yet.\nSupported fields for incoming_message:\n- keywords: [\"pricing\",\"demo\"] — message must contain keyword(s) (free, no LLM cost)\n- keyword_match: \"any\" (default, OR) or \"all\" (AND)\n- channel_types: [\"telegram\",\"whatsapp\",\"livechat_voice\",\"twilio_voice\",\"telegram_voice\",\"voice\",...] — filter by channel. For voice, use EITHER the three per-channel keys (scoped) OR \"voice\" alone (wildcard matching all three) — mixing them is redundant. Per-channel keys: \"livechat_voice\" (web widget), \"twilio_voice\" (PSTN inbound), \"telegram_voice\" (Telegram p2p calls)\n- context_types: [\"dm\",\"group\",\"channel\",\"livechat\"] — filter by chat type\n- group_mode: \"mentions_only\" or \"questions\" — for group chats\n- channel_account_ids: [\"123\"] — restrict to specific accounts. Only accounts THIS workspace answers: a trigger never fires for another workspace's channel, so create it on an agent there\n- folder_ids: [5,10] — restrict to threads in folders\n- ai_tag_ids: [1,2] — restrict to threads with AI tags\n- ai_filter_ids: [1,2] — semantic intent filters (message matched via embedding similarity, works in noisy groups)\n- ai_filter_mode: \"any\" (default, OR) or \"all\" (AND) — how multiple AI filters combine\n- ai_filters: [{id: 1}, {name: \"...\", description: \"...\"}] — shorthand: reference existing by id or create inline (calls Voyage embedding API). If a filter with the same name already exists, it is reused by id. Prefer referencing existing filters by id when available. Use ai_filters.create + ai_filters.test for fine-tuning before assigning.\n- template: the reply a rule_based agent sends, with no model run. Either a string (\"Hi {from_name}, we open at 9\") or a card object {text, attachments, buttons} — text is required, attachments is a list of file ids (files.upload), buttons is a list of {label, value|url|web_app} carrying exactly ONE target each: value = a reply the bot receives back, url = opens a link (add track: true to count each tap per conversation, readable as analytics_link_clicks_v in analytics.query; add tag: <ai_tag id> beside it to put that tag on the CONVERSATION at the tap, so for people, not groups, where any member's tap tags the whole group; add pass: \"<name>\" to open the url with <name>=<the chat's id on its channel, a Telegram user id for a bot chat>, so the site can name the person back in its own events), web_app = opens a Mini App over https. The string, and a card's text, substitute {from_name}, {message_text}, {channel_type}, {thread_id}, {raw_data}; button labels and targets are sent verbatim. A card with buttons needs send_mode auto — a draft row cannot carry a keyboard. Buttons need a channel that renders them (telegram_bot). A card needs a chat to land in, so it refuses on webhook, schedule and other thread-less triggers where a string still drafts.\n- handoff: {agent_id, task} — only on a rule_based agent's trigger (refused elsewhere). After the rule's deterministic part has actually happened — the template's message delivered, or the agent's script completed — the named agent runs on the same thread, in its own send mode, exactly as its own trigger would run it: the customer's message reaches it as the incoming message, and `task` reaches it as the handoff brief from this rule. The rule stays instant; the thinking — a reminder, a referral code, a personal follow-up — happens behind it. Script plus handoff is how a workspace does something deterministic the platform has no verb for (file the thread, stamp a tag, push a row) and still lets an agent answer, with the deterministic part living in that agent's own script rather than in platform code. `task` substitutes {channel_type} and {thread_id} only; {message_text}, {from_name} and {raw_data} are refused (the sender would be writing the instruction — the message and its sender already reach the target as the incoming message). The target must be an active agentic or claude_channels agent in this workspace (the engines that read the brief). The target's run is a normal trigger run: it holds the thread lock, its own safety gates apply, and its final answer is delivered like any DM reply — a follow-up that should stay silent must call agent.silence. Nothing runs when the message was drafted, refused or failed, when the script failed, when a safety gate has the rule in draft mode, or when the event carries no thread for the target to answer on. A target paused or deleted after the trigger was written does not stop the rule's message: it goes out, and the reason the follow-up did not start is recorded in the rule's activity row (error field) and in the target's activity as an execution_error.\n- contact_states: [\"active\"] — filter by contact state\n- cooldown_seconds: 30 — min gap between runs per thread\n- max_runs_per_thread_per_hour: 5 — rate limit\n- once_per_thread: true — after this trigger completes on a conversation it steps aside there and the next matching trigger answers later messages. For a rule that files / tags / hands off once, not for the agent that holds the conversation.\n- answer_delay_s: 15 — voice pickup only (incoming_call, or incoming_message scoped to a voice channel). Ring the human's own devices this long before the agent answers; if they pick up, the agent stands down. 0/absent = answer immediately. Honoured on WhatsApp and Telegram 1:1 — other voice channels have nothing ringing to wait for and still answer at once.\n- auto_join: true|false — voice pickup, GROUP calls only. Whether the bot enters a matching group call on its own (true) or the call becomes a pending invite an operator accepts (false). OMIT THE KEY to defer to the channel setting (channel_account.state.voice_auto_join_policy, default 'approval'); resolution is trigger-when-present, then channel, then approval, so an explicit false beats a channel set to auto. Absent and false are different answers.\n- chat_ids: [\"-5172634473\"] — voice pickup, Telegram GROUP calls only. Scopes the trigger to specific groups; omit for every group call. Any id spelling works (5172634473, -5172634473, -1005172634473 are the same group). A call whose chat is unknown never satisfies it, so do NOT set this together with 1:1 / Twilio / Telnyx / WhatsApp / Android / LiveChat voice channels or the \"voice\" wildcard: those calls have no chat and the trigger would stop answering them.\n\nSupported fields for job_completed (proactive callback when a delegated job finishes):\n- source_agent_id: <int> — fire only when this agent's job completed\n- source_agent_slug: <str> — alternate to source_agent_id\n- job_type: \"agentic_session\" — match a specific job type (default: any)\n- outcome: [\"completed\"] | [\"escalated\"] | [\"completed\",\"escalated\"] — default [\"completed\"]\n- min_duration_seconds: <int> — skip very-short jobs (noise filter)\n- thread_filter: {thread_ids: [<int>...]} — restrict to specific threads\n\nSupported fields for calendar_event (fires N minutes before a Google Calendar event starts):\n- window_minutes_before: <int 1-1440> — REQUIRED, fire when an event starts within this window\n- channel_account_ids: [<int>...] — restrict to specific calendar accounts (default: all)\n- keywords: [\"standup\"] — word-boundary match on event title\n- prepare_meet_join: true — pre-invite the pool bots that can join signed in (none when none can) to the event, for an unattended Meet join\n\nSupported fields for task_assigned (a task on the workspace board was assigned to this agent):\n- target_session: <session_id> — for a Claude Code agent, the session the task goes to (default: the agent's own session)\n\nSupported fields for job_continuation (this agent's own call or video finished):\n- job_types: [\"voice_call\", \"video_generation\"] — which kinds re-invoke it (default: all)\n\nincoming_message action fields:\n- action: \"reply_text\" (default, normal agent run) or \"join_voice\" (deterministically join the voice channel resolved from the message — requires send_mode=auto)\n- message_source: \"real\" (default) | \"transcript\" | \"both\" — real messages vs turns during a live call. Transcripts are turns that address the agent.\n\ncalendar_event run-mode field (incoming_message uses `action` instead):\n- run_mode: \"text\" (default) or \"voice\" (join the meeting — requires send_mode=auto)\n- voice: {speak_first: <bool — greet immediately vs stay silent until addressed>, vision_mode: \"off\"|\"on_demand\"|\"continuous_0_3fps\"} — pairs with action=join_voice (incoming_message) or run_mode=voice (calendar_event)"New value: +"Trigger conditions (JSON).\nFor blockchain_event (all three required): blockchain_addresses: [\"<address>\"] — the wallets to watch; blockchain_chains: any of [\"bitcoin\",\"ethereum\",\"bsc\",\"tron\",\"solana\"] (the chain is part of the wallet's identity: the same 0x address is a different wallet on ethereum and on bsc, so name only the chains meant); blockchain_events: any of [\"transfer_in\",\"transfer_out\",\"risk_level_up\",\"sanctioned\",\"frozen\"]. Optional, transfers only: blockchain_tokens: [\"USDT\"], blockchain_min_amount: 100. The run receives the event kind, chain, address and, for transfers, the list of transfers (tx, time, token, amount, USD value, counterparty and its risk). If the answer carries watch_note, the address is saved but not watched yet.\nSupported fields for incoming_message:\n- keywords: [\"pricing\",\"demo\"] — message must contain keyword(s) (free, no LLM cost)\n- keyword_match: \"any\" (default, OR) or \"all\" (AND)\n- channel_types: [\"telegram\",\"whatsapp\",\"livechat_voice\",\"twilio_voice\",\"telegram_voice\",\"voice\",...] — filter by channel. For voice, use EITHER the three per-channel keys (scoped) OR \"voice\" alone (wildcard matching all three) — mixing them is redundant. Per-channel keys: \"livechat_voice\" (web widget), \"twilio_voice\" (PSTN inbound), \"telegram_voice\" (Telegram p2p calls)\n- context_types: [\"dm\",\"group\",\"channel\",\"livechat\"] — filter by chat type\n- group_mode: \"mentions_only\" or \"questions\" — for group chats\n- channel_account_ids: [\"123\"] — restrict to specific accounts. Only accounts THIS workspace answers: a trigger never fires for another workspace's channel, so create it on an agent there\n- folder_ids: [5,10] — restrict to threads in folders\n- ai_tag_ids: [1,2] — restrict to threads with AI tags\n- ai_filter_ids: [1,2] — semantic intent filters (message matched via embedding similarity, works in noisy groups)\n- ai_filter_mode: \"any\" (default, OR) or \"all\" (AND) — how multiple AI filters combine\n- ai_filters: [{id: 1}, {name: \"...\", description: \"...\"}] — shorthand: reference existing by id or create inline (calls Voyage embedding API). If a filter with the same name already exists, it is reused by id. Prefer referencing existing filters by id when available. Use ai_filters.create + ai_filters.test for fine-tuning before assigning.\n- template: the reply a rule_based agent sends, with no model run. Either a string (\"Hi {from_name}, we open at 9\") or a card object {text, attachments, buttons} — text is required, attachments is a list of file ids (files.upload), buttons is a list of {label, value|url|web_app} carrying exactly ONE target each: value = a reply the bot receives back, url = opens a link (add track: true to count each tap per conversation, readable as analytics_link_clicks_v in analytics.query; add tag: <ai_tag id> beside it to put that tag on the CONVERSATION at the tap, so for people, not groups, where any member's tap tags the whole group; add pass: \"<name>\" to open the url with <name>=<the chat's id on its channel, a Telegram user id for a bot chat>, so the site can name the person back in its own events), web_app = opens a Mini App over https. The string, and a card's text, substitute {from_name}, {message_text}, {channel_type}, {thread_id}, {raw_data}; button labels and targets are sent verbatim. A card with buttons needs send_mode auto — a draft row cannot carry a keyboard. Buttons need a channel that renders them (telegram_bot). A card needs a chat to land in, so it refuses on webhook, schedule and other thread-less triggers where a string still drafts.\n- handoff: {agent_id, task} — only on a rule_based agent's trigger (refused elsewhere). After the rule's deterministic part has actually happened — the template's message delivered, or the agent's script completed — the named agent runs on the same thread, in its own send mode, exactly as its own trigger would run it: the customer's message reaches it as the incoming message, and `task` reaches it as the handoff brief from this rule. The rule stays instant; the thinking — a reminder, a referral code, a personal follow-up — happens behind it. Script plus handoff is how a workspace does something deterministic the platform has no verb for (file the thread, stamp a tag, push a row) and still lets an agent answer, with the deterministic part living in that agent's own script rather than in platform code. `task` substitutes {channel_type} and {thread_id} only; {message_text}, {from_name} and {raw_data} are refused (the sender would be writing the instruction — the message and its sender already reach the target as the incoming message). The target must be an active agentic or claude_channels agent in this workspace (the engines that read the brief). The target's run is a normal trigger run: it holds the thread lock, its own safety gates apply, and its final answer is delivered like any DM reply — a follow-up that should stay silent must call agent.silence. Nothing runs when the message was drafted, refused or failed, when the script failed, when a safety gate has the rule in draft mode, or when the event carries no thread for the target to answer on. A target paused or deleted after the trigger was written does not stop the rule's message: it goes out, and the reason the follow-up did not start is recorded in the rule's activity row (error field) and in the target's activity as an execution_error.\n- contact_states: [\"active\"] — filter by contact state\n- cooldown_seconds: 30 — min gap between runs per thread\n- max_runs_per_thread_per_hour: 5 — rate limit\n- once_per_thread: true — after this trigger completes on a conversation it steps aside there and the next matching trigger answers later messages. For a rule that files / tags / hands off once, not for the agent that holds the conversation.\n- answer_delay_s: 15 — voice pickup only (incoming_call, or incoming_message scoped to a voice channel). Ring the human's own devices this long before the agent answers; if they pick up, the agent stands down. 0/absent = answer immediately. Honoured on WhatsApp and Telegram 1:1 — other voice channels have nothing ringing to wait for and still answer at once.\n- auto_join: true|false — voice pickup, GROUP calls only. Whether the bot enters a matching group call on its own (true) or the call becomes a pending invite an operator accepts (false). OMIT THE KEY to defer to the channel setting (channel_account.state.voice_auto_join_policy, default 'approval'); resolution is trigger-when-present, then channel, then approval, so an explicit false beats a channel set to auto. Absent and false are different answers.\n- chat_ids: [\"-5172634473\"] — voice pickup, Telegram GROUP calls only. Scopes the trigger to specific groups; omit for every group call. Any id spelling works (5172634473, -5172634473, -1005172634473 are the same group). A call whose chat is unknown never satisfies it, so do NOT set this together with 1:1 / Twilio / Telnyx / WhatsApp / Android / LiveChat voice channels or the \"voice\" wildcard: those calls have no chat and the trigger would stop answering them.\n\nSupported fields for job_completed (proactive callback when a delegated job finishes):\n- source_agent_id: <int> — fire only when this agent's job completed\n- source_agent_slug: <str> — alternate to source_agent_id\n- job_type: \"agentic_session\" — match a specific job type (default: any)\n- outcome: [\"completed\"] | [\"escalated\"] | [\"completed\",\"escalated\"] — default [\"completed\"]\n- min_duration_seconds: <int> — skip very-short jobs (noise filter)\n- thread_filter: {thread_ids: [<int>...]} — restrict to specific threads\n\nSupported fields for calendar_event (fires N minutes before a Google Calendar event starts):\n- window_minutes_before: <int 1-1440> — REQUIRED, fire when an event starts within this window\n- channel_account_ids: [<int>...] — restrict to specific calendar accounts (default: all)\n- keywords: [\"standup\"] — word-boundary match on event title\n- prepare_meet_join: true — pre-invite the pool bots that can join signed in (none when none can) to the event, for an unattended Meet join\n\nSupported fields for task_assigned (a task on the workspace board was assigned to this agent):\n- target_session: <session_id> — for a Claude Code agent, the session the task goes to (default: the agent's own session)\n\nSupported fields for job_continuation (this agent's own call or video finished):\n- job_types: [\"voice_call\", \"video_generation\"] — which kinds re-invoke it (default: all)\n\nSupported fields for message_reaction (somebody ADDED an emoji reaction to a message; one run per reaction, never for the account's own reactions or for a reaction taken back):\n- reaction_on: \"own\" (default: only reactions to messages sent from this account, by the agent or the owner) or \"any\" (reactions to anybody's messages in the chat)\n- emojis: [\"👍\", \"❤\"] — only these reactions (default: every emoji)\n- channel_account_ids, channel_types, thread_filter: {thread_ids / excluded_thread_ids} — which accounts and chats, as for incoming_message\nA Telegram BOT receives reactions in a group only when it is an administrator there.\n\nincoming_message action fields:\n- action: \"reply_text\" (default, normal agent run) or \"join_voice\" (deterministically join the voice channel resolved from the message — requires send_mode=auto)\n- message_source: \"real\" (default) | \"transcript\" | \"both\" — real messages vs turns during a live call. Transcripts are turns that address the agent.\n\ncalendar_event run-mode field (incoming_message uses `action` instead):\n- run_mode: \"text\" (default) or \"voice\" (join the meeting — requires send_mode=auto)\n- voice: {speak_first: <bool — greet immediately vs stay silent until addressed>, vision_mode: \"off\"|\"on_demand\"|\"continuous_0_3fps\"} — pairs with action=join_voice (incoming_message) or run_mode=voice (calendar_event)"
    • changedInput schema / properties / trigger_type / description
      Previous value: -"Type of trigger: 'incoming_message', 'incoming_call', 'schedule', 'webhook', 'event', 'blockchain_event', 'job_completed', 'calendar_event', 'lead_captured', 'task_assigned' (a task on the workspace board was assigned to this agent; without one, assigning a task does not start the agent), or 'job_continuation' (this agent's OWN call from calls.make or video from videos.generate finished; without one the agent is not re-invoked to carry on)"New value: +"Type of trigger: 'incoming_message', 'incoming_call', 'schedule', 'webhook', 'event', 'blockchain_event', 'job_completed', 'calendar_event', 'lead_captured', 'task_assigned' (a task on the workspace board was assigned to this agent; without one, assigning a task does not start the agent), 'job_continuation' (this agent's OWN call from calls.make or video from videos.generate finished; without one the agent is not re-invoked to carry on), or 'message_reaction' (somebody put an emoji reaction on a message of a conversation: a client's thumbs-up under a draft; without one a reaction starts nothing)"
    • changedInput schema / properties / trigger_type / enum
      Previous value: -[
      -  "incoming_message",
      -  "incoming_call",
      -  "schedule",
      -  "webhook",
      -  "event",
      -  "blockchain_event",
      -  "job_completed",
      -  "calendar_event",
      -  "lead_captured",
      -  "task_assigned",
      -  "job_continuation"
      -]New value: +[
      +  "incoming_message",
      +  "incoming_call",
      +  "schedule",
      +  "webhook",
      +  "event",
      +  "blockchain_event",
      +  "job_completed",
      +  "calendar_event",
      +  "lead_captured",
      +  "task_assigned",
      +  "job_continuation",
      +  "message_reaction"
      +]
  6. Changed1 schema field changed
    • changedInput schema / properties / conditions / description
      Previous value: -"Trigger conditions (JSON). Supported fields for incoming_message:\n- keywords: [\"pricing\",\"demo\"] — message must contain keyword(s) (free, no LLM cost)\n- keyword_match: \"any\" (default, OR) or \"all\" (AND)\n- channel_types: [\"telegram\",\"whatsapp\",\"livechat_voice\",\"twilio_voice\",\"telegram_voice\",\"voice\",...] — filter by channel. For voice, use EITHER the three per-channel keys (scoped) OR \"voice\" alone (wildcard matching all three) — mixing them is redundant. Per-channel keys: \"livechat_voice\" (web widget), \"twilio_voice\" (PSTN inbound), \"telegram_voice\" (Telegram p2p calls)\n- context_types: [\"dm\",\"group\",\"channel\",\"livechat\"] — filter by chat type\n- group_mode: \"mentions_only\" or \"questions\" — for group chats\n- channel_account_ids: [\"123\"] — restrict to specific accounts. Only accounts THIS workspace answers: a trigger never fires for another workspace's channel, so create it on an agent there\n- folder_ids: [5,10] — restrict to threads in folders\n- ai_tag_ids: [1,2] — restrict to threads with AI tags\n- ai_filter_ids: [1,2] — semantic intent filters (message matched via embedding similarity, works in noisy groups)\n- ai_filter_mode: \"any\" (default, OR) or \"all\" (AND) — how multiple AI filters combine\n- ai_filters: [{id: 1}, {name: \"...\", description: \"...\"}] — shorthand: reference existing by id or create inline (calls Voyage embedding API). If a filter with the same name already exists, it is reused by id. Prefer referencing existing filters by id when available. Use ai_filters.create + ai_filters.test for fine-tuning before assigning.\n- template: the reply a rule_based agent sends, with no model run. Either a string (\"Hi {from_name}, we open at 9\") or a card object {text, attachments, buttons} — text is required, attachments is a list of file ids (files.upload), buttons is a list of {label, value|url|web_app} carrying exactly ONE target each: value = a reply the bot receives back, url = opens a link (add track: true to count each tap per conversation, readable as analytics_link_clicks_v in analytics.query; add tag: <ai_tag id> beside it to put that tag on the CONVERSATION at the tap, so for people, not groups, where any member's tap tags the whole group; add pass: \"<name>\" to open the url with <name>=<the chat's id on its channel, a Telegram user id for a bot chat>, so the site can name the person back in its own events), web_app = opens a Mini App over https. The string, and a card's text, substitute {from_name}, {message_text}, {channel_type}, {thread_id}, {raw_data}; button labels and targets are sent verbatim. A card with buttons needs send_mode auto — a draft row cannot carry a keyboard. Buttons need a channel that renders them (telegram_bot). A card needs a chat to land in, so it refuses on webhook, schedule and other thread-less triggers where a string still drafts.\n- handoff: {agent_id, task} — only on a rule_based agent's trigger (refused elsewhere). After the rule's deterministic part has actually happened — the template's message delivered, or the agent's script completed — the named agent runs on the same thread, in its own send mode, exactly as its own trigger would run it: the customer's message reaches it as the incoming message, and `task` reaches it as the handoff brief from this rule. The rule stays instant; the thinking — a reminder, a referral code, a personal follow-up — happens behind it. Script plus handoff is how a workspace does something deterministic the platform has no verb for (file the thread, stamp a tag, push a row) and still lets an agent answer, with the deterministic part living in that agent's own script rather than in platform code. `task` substitutes {channel_type} and {thread_id} only; {message_text}, {from_name} and {raw_data} are refused (the sender would be writing the instruction — the message and its sender already reach the target as the incoming message). The target must be an active agentic or claude_channels agent in this workspace (the engines that read the brief). The target's run is a normal trigger run: it holds the thread lock, its own safety gates apply, and its final answer is delivered like any DM reply — a follow-up that should stay silent must call agent.silence. Nothing runs when the message was drafted, refused or failed, when the script failed, when a safety gate has the rule in draft mode, or when the event carries no thread for the target to answer on. A target paused or deleted after the trigger was written does not stop the rule's message: it goes out, and the reason the follow-up did not start is recorded in the rule's activity row (error field) and in the target's activity as an execution_error.\n- contact_states: [\"active\"] — filter by contact state\n- cooldown_seconds: 30 — min gap between runs per thread\n- max_runs_per_thread_per_hour: 5 — rate limit\n- once_per_thread: true — after this trigger completes on a conversation it steps aside there and the next matching trigger answers later messages. For a rule that files / tags / hands off once, not for the agent that holds the conversation.\n- answer_delay_s: 15 — voice pickup only (incoming_call, or incoming_message scoped to a voice channel). Ring the human's own devices this long before the agent answers; if they pick up, the agent stands down. 0/absent = answer immediately. Honoured on WhatsApp and Telegram 1:1 — other voice channels have nothing ringing to wait for and still answer at once.\n- auto_join: true|false — voice pickup, GROUP calls only. Whether the bot enters a matching group call on its own (true) or the call becomes a pending invite an operator accepts (false). OMIT THE KEY to defer to the channel setting (channel_account.state.voice_auto_join_policy, default 'approval'); resolution is trigger-when-present, then channel, then approval, so an explicit false beats a channel set to auto. Absent and false are different answers.\n- chat_ids: [\"-5172634473\"] — voice pickup, Telegram GROUP calls only. Scopes the trigger to specific groups; omit for every group call. Any id spelling works (5172634473, -5172634473, -1005172634473 are the same group). A call whose chat is unknown never satisfies it, so do NOT set this together with 1:1 / Twilio / Telnyx / WhatsApp / Android / LiveChat voice channels or the \"voice\" wildcard: those calls have no chat and the trigger would stop answering them.\n\nSupported fields for job_completed (proactive callback when a delegated job finishes):\n- source_agent_id: <int> — fire only when this agent's job completed\n- source_agent_slug: <str> — alternate to source_agent_id\n- job_type: \"agentic_session\" — match a specific job type (default: any)\n- outcome: [\"completed\"] | [\"escalated\"] | [\"completed\",\"escalated\"] — default [\"completed\"]\n- min_duration_seconds: <int> — skip very-short jobs (noise filter)\n- thread_filter: {thread_ids: [<int>...]} — restrict to specific threads\n\nSupported fields for calendar_event (fires N minutes before a Google Calendar event starts):\n- window_minutes_before: <int 1-1440> — REQUIRED, fire when an event starts within this window\n- channel_account_ids: [<int>...] — restrict to specific calendar accounts (default: all)\n- keywords: [\"standup\"] — word-boundary match on event title\n- prepare_meet_join: true — pre-invite the pool bots that can join signed in (none when none can) to the event, for an unattended Meet join\n\nSupported fields for task_assigned (a task on the workspace board was assigned to this agent):\n- target_session: <session_id> — for a Claude Code agent, the session the task goes to (default: the agent's own session)\n\nSupported fields for job_continuation (this agent's own call or video finished):\n- job_types: [\"voice_call\", \"video_generation\"] — which kinds re-invoke it (default: all)\n\nincoming_message action fields:\n- action: \"reply_text\" (default, normal agent run) or \"join_voice\" (deterministically join the voice channel resolved from the message — requires send_mode=auto)\n- message_source: \"real\" (default) | \"transcript\" | \"both\" — real messages vs turns during a live call. Transcripts are turns that address the agent.\n\ncalendar_event run-mode field (incoming_message uses `action` instead):\n- run_mode: \"text\" (default) or \"voice\" (join the meeting — requires send_mode=auto)\n- voice: {speak_first: <bool — greet immediately vs stay silent until addressed>, vision_mode: \"off\"|\"on_demand\"|\"continuous_0_3fps\"} — pairs with action=join_voice (incoming_message) or run_mode=voice (calendar_event)"New value: +"Trigger conditions (JSON).\nFor blockchain_event (all three required): blockchain_addresses: [\"<address>\"] — the wallets to watch; blockchain_chains: any of [\"bitcoin\",\"ethereum\",\"bsc\",\"tron\",\"solana\"] (the chain is part of the wallet's identity: the same 0x address is a different wallet on ethereum and on bsc, so name only the chains meant); blockchain_events: any of [\"transfer_in\",\"transfer_out\",\"risk_level_up\",\"sanctioned\",\"frozen\"]. Optional, transfers only: blockchain_tokens: [\"USDT\"], blockchain_min_amount: 100. The run receives the event kind, chain, address and, for transfers, the list of transfers (tx, time, token, amount, USD value, counterparty and its risk). If the answer carries watch_note, the address is saved but not watched yet.\nSupported fields for incoming_message:\n- keywords: [\"pricing\",\"demo\"] — message must contain keyword(s) (free, no LLM cost)\n- keyword_match: \"any\" (default, OR) or \"all\" (AND)\n- channel_types: [\"telegram\",\"whatsapp\",\"livechat_voice\",\"twilio_voice\",\"telegram_voice\",\"voice\",...] — filter by channel. For voice, use EITHER the three per-channel keys (scoped) OR \"voice\" alone (wildcard matching all three) — mixing them is redundant. Per-channel keys: \"livechat_voice\" (web widget), \"twilio_voice\" (PSTN inbound), \"telegram_voice\" (Telegram p2p calls)\n- context_types: [\"dm\",\"group\",\"channel\",\"livechat\"] — filter by chat type\n- group_mode: \"mentions_only\" or \"questions\" — for group chats\n- channel_account_ids: [\"123\"] — restrict to specific accounts. Only accounts THIS workspace answers: a trigger never fires for another workspace's channel, so create it on an agent there\n- folder_ids: [5,10] — restrict to threads in folders\n- ai_tag_ids: [1,2] — restrict to threads with AI tags\n- ai_filter_ids: [1,2] — semantic intent filters (message matched via embedding similarity, works in noisy groups)\n- ai_filter_mode: \"any\" (default, OR) or \"all\" (AND) — how multiple AI filters combine\n- ai_filters: [{id: 1}, {name: \"...\", description: \"...\"}] — shorthand: reference existing by id or create inline (calls Voyage embedding API). If a filter with the same name already exists, it is reused by id. Prefer referencing existing filters by id when available. Use ai_filters.create + ai_filters.test for fine-tuning before assigning.\n- template: the reply a rule_based agent sends, with no model run. Either a string (\"Hi {from_name}, we open at 9\") or a card object {text, attachments, buttons} — text is required, attachments is a list of file ids (files.upload), buttons is a list of {label, value|url|web_app} carrying exactly ONE target each: value = a reply the bot receives back, url = opens a link (add track: true to count each tap per conversation, readable as analytics_link_clicks_v in analytics.query; add tag: <ai_tag id> beside it to put that tag on the CONVERSATION at the tap, so for people, not groups, where any member's tap tags the whole group; add pass: \"<name>\" to open the url with <name>=<the chat's id on its channel, a Telegram user id for a bot chat>, so the site can name the person back in its own events), web_app = opens a Mini App over https. The string, and a card's text, substitute {from_name}, {message_text}, {channel_type}, {thread_id}, {raw_data}; button labels and targets are sent verbatim. A card with buttons needs send_mode auto — a draft row cannot carry a keyboard. Buttons need a channel that renders them (telegram_bot). A card needs a chat to land in, so it refuses on webhook, schedule and other thread-less triggers where a string still drafts.\n- handoff: {agent_id, task} — only on a rule_based agent's trigger (refused elsewhere). After the rule's deterministic part has actually happened — the template's message delivered, or the agent's script completed — the named agent runs on the same thread, in its own send mode, exactly as its own trigger would run it: the customer's message reaches it as the incoming message, and `task` reaches it as the handoff brief from this rule. The rule stays instant; the thinking — a reminder, a referral code, a personal follow-up — happens behind it. Script plus handoff is how a workspace does something deterministic the platform has no verb for (file the thread, stamp a tag, push a row) and still lets an agent answer, with the deterministic part living in that agent's own script rather than in platform code. `task` substitutes {channel_type} and {thread_id} only; {message_text}, {from_name} and {raw_data} are refused (the sender would be writing the instruction — the message and its sender already reach the target as the incoming message). The target must be an active agentic or claude_channels agent in this workspace (the engines that read the brief). The target's run is a normal trigger run: it holds the thread lock, its own safety gates apply, and its final answer is delivered like any DM reply — a follow-up that should stay silent must call agent.silence. Nothing runs when the message was drafted, refused or failed, when the script failed, when a safety gate has the rule in draft mode, or when the event carries no thread for the target to answer on. A target paused or deleted after the trigger was written does not stop the rule's message: it goes out, and the reason the follow-up did not start is recorded in the rule's activity row (error field) and in the target's activity as an execution_error.\n- contact_states: [\"active\"] — filter by contact state\n- cooldown_seconds: 30 — min gap between runs per thread\n- max_runs_per_thread_per_hour: 5 — rate limit\n- once_per_thread: true — after this trigger completes on a conversation it steps aside there and the next matching trigger answers later messages. For a rule that files / tags / hands off once, not for the agent that holds the conversation.\n- answer_delay_s: 15 — voice pickup only (incoming_call, or incoming_message scoped to a voice channel). Ring the human's own devices this long before the agent answers; if they pick up, the agent stands down. 0/absent = answer immediately. Honoured on WhatsApp and Telegram 1:1 — other voice channels have nothing ringing to wait for and still answer at once.\n- auto_join: true|false — voice pickup, GROUP calls only. Whether the bot enters a matching group call on its own (true) or the call becomes a pending invite an operator accepts (false). OMIT THE KEY to defer to the channel setting (channel_account.state.voice_auto_join_policy, default 'approval'); resolution is trigger-when-present, then channel, then approval, so an explicit false beats a channel set to auto. Absent and false are different answers.\n- chat_ids: [\"-5172634473\"] — voice pickup, Telegram GROUP calls only. Scopes the trigger to specific groups; omit for every group call. Any id spelling works (5172634473, -5172634473, -1005172634473 are the same group). A call whose chat is unknown never satisfies it, so do NOT set this together with 1:1 / Twilio / Telnyx / WhatsApp / Android / LiveChat voice channels or the \"voice\" wildcard: those calls have no chat and the trigger would stop answering them.\n\nSupported fields for job_completed (proactive callback when a delegated job finishes):\n- source_agent_id: <int> — fire only when this agent's job completed\n- source_agent_slug: <str> — alternate to source_agent_id\n- job_type: \"agentic_session\" — match a specific job type (default: any)\n- outcome: [\"completed\"] | [\"escalated\"] | [\"completed\",\"escalated\"] — default [\"completed\"]\n- min_duration_seconds: <int> — skip very-short jobs (noise filter)\n- thread_filter: {thread_ids: [<int>...]} — restrict to specific threads\n\nSupported fields for calendar_event (fires N minutes before a Google Calendar event starts):\n- window_minutes_before: <int 1-1440> — REQUIRED, fire when an event starts within this window\n- channel_account_ids: [<int>...] — restrict to specific calendar accounts (default: all)\n- keywords: [\"standup\"] — word-boundary match on event title\n- prepare_meet_join: true — pre-invite the pool bots that can join signed in (none when none can) to the event, for an unattended Meet join\n\nSupported fields for task_assigned (a task on the workspace board was assigned to this agent):\n- target_session: <session_id> — for a Claude Code agent, the session the task goes to (default: the agent's own session)\n\nSupported fields for job_continuation (this agent's own call or video finished):\n- job_types: [\"voice_call\", \"video_generation\"] — which kinds re-invoke it (default: all)\n\nincoming_message action fields:\n- action: \"reply_text\" (default, normal agent run) or \"join_voice\" (deterministically join the voice channel resolved from the message — requires send_mode=auto)\n- message_source: \"real\" (default) | \"transcript\" | \"both\" — real messages vs turns during a live call. Transcripts are turns that address the agent.\n\ncalendar_event run-mode field (incoming_message uses `action` instead):\n- run_mode: \"text\" (default) or \"voice\" (join the meeting — requires send_mode=auto)\n- voice: {speak_first: <bool — greet immediately vs stay silent until addressed>, vision_mode: \"off\"|\"on_demand\"|\"continuous_0_3fps\"} — pairs with action=join_voice (incoming_message) or run_mode=voice (calendar_event)"
  7. Changed1 schema field changed
    • changedInput schema / properties / conditions / description
      Previous value: -"Trigger conditions (JSON). Supported fields for incoming_message:\n- keywords: [\"pricing\",\"demo\"] — message must contain keyword(s) (free, no LLM cost)\n- keyword_match: \"any\" (default, OR) or \"all\" (AND)\n- channel_types: [\"telegram\",\"whatsapp\",\"livechat_voice\",\"twilio_voice\",\"telegram_voice\",\"voice\",...] — filter by channel. For voice, use EITHER the three per-channel keys (scoped) OR \"voice\" alone (wildcard matching all three) — mixing them is redundant. Per-channel keys: \"livechat_voice\" (web widget), \"twilio_voice\" (PSTN inbound), \"telegram_voice\" (Telegram p2p calls)\n- context_types: [\"dm\",\"group\",\"channel\",\"livechat\"] — filter by chat type\n- group_mode: \"mentions_only\" or \"questions\" — for group chats\n- channel_account_ids: [\"123\"] — restrict to specific accounts. Only accounts THIS workspace answers: a trigger never fires for another workspace's channel, so create it on an agent there\n- folder_ids: [5,10] — restrict to threads in folders\n- ai_tag_ids: [1,2] — restrict to threads with AI tags\n- ai_filter_ids: [1,2] — semantic intent filters (message matched via embedding similarity, works in noisy groups)\n- ai_filter_mode: \"any\" (default, OR) or \"all\" (AND) — how multiple AI filters combine\n- ai_filters: [{id: 1}, {name: \"...\", description: \"...\"}] — shorthand: reference existing by id or create inline (calls Voyage embedding API). If a filter with the same name already exists, it is reused by id. Prefer referencing existing filters by id when available. Use ai_filters.create + ai_filters.test for fine-tuning before assigning.\n- template: the reply a rule_based agent sends, with no model run. Either a string (\"Hi {from_name}, we open at 9\") or a card object {text, attachments, buttons} — text is required, attachments is a list of file ids (files.upload), buttons is a list of {label, value|url|web_app} carrying exactly ONE target each: value = a reply the bot receives back, url = opens a link (add track: true to count each tap per conversation, readable as analytics_link_clicks_v in analytics.query; add tag: <ai_tag id> beside it to put that tag on the CONVERSATION at the tap, so for people, not groups, where any member's tap tags the whole group; add pass: \"<name>\" to open the url with <name>=<the chat's id on its channel, a Telegram user id for a bot chat>, so the site can name the person back in its own events), web_app = opens a Mini App over https. The string, and a card's text, substitute {from_name}, {message_text}, {channel_type}, {thread_id}, {raw_data}; button labels and targets are sent verbatim. A card with buttons needs send_mode auto — a draft row cannot carry a keyboard. Buttons need a channel that renders them (telegram_bot). A card needs a chat to land in, so it refuses on webhook, schedule and other thread-less triggers where a string still drafts.\n- handoff: {agent_id, task} — only on a rule_based agent's trigger (refused elsewhere). After the rule's deterministic part has actually happened — the template's message delivered, or the agent's script completed — the named agent runs on the same thread, in its own send mode, exactly as its own trigger would run it: the customer's message reaches it as the incoming message, and `task` reaches it as the handoff brief from this rule. The rule stays instant; the thinking — a reminder, a referral code, a personal follow-up — happens behind it. Script plus handoff is how a workspace does something deterministic the platform has no verb for (file the thread, stamp a tag, push a row) and still lets an agent answer, with the deterministic part living in that agent's own script rather than in platform code. `task` substitutes {channel_type} and {thread_id} only; {message_text}, {from_name} and {raw_data} are refused (the sender would be writing the instruction — the message and its sender already reach the target as the incoming message). The target must be an active agentic or claude_channels agent in this workspace (the engines that read the brief). The target's run is a normal trigger run: it holds the thread lock, its own safety gates apply, and its final answer is delivered like any DM reply — a follow-up that should stay silent must call agent.silence. Nothing runs when the message was drafted, refused or failed, when the script failed, when a safety gate has the rule in draft mode, or when the event carries no thread for the target to answer on. A target paused or deleted after the trigger was written does not stop the rule's message: it goes out, and the reason the follow-up did not start is recorded in the rule's activity row (error field) and in the target's activity as an execution_error.\n- contact_states: [\"active\"] — filter by contact state\n- cooldown_seconds: 30 — min gap between runs per thread\n- max_runs_per_thread_per_hour: 5 — rate limit\n- once_per_thread: true — after this trigger completes on a conversation it steps aside there and the next matching trigger answers later messages. For a rule that files / tags / hands off once, not for the agent that holds the conversation.\n- answer_delay_s: 15 — voice pickup only (incoming_call, or incoming_message scoped to a voice channel). Ring the human's own devices this long before the agent answers; if they pick up, the agent stands down. 0/absent = answer immediately. Honoured on WhatsApp and Telegram 1:1 — other voice channels have nothing ringing to wait for and still answer at once.\n- auto_join: true|false — voice pickup, GROUP calls only. Whether the bot enters a matching group call on its own (true) or the call becomes a pending invite an operator accepts (false). OMIT THE KEY to defer to the channel setting (channel_account.state.voice_auto_join_policy, default 'approval'); resolution is trigger-when-present, then channel, then approval, so an explicit false beats a channel set to auto. Absent and false are different answers.\n- chat_ids: [\"-5172634473\"] — voice pickup, Telegram GROUP calls only. Scopes the trigger to specific groups; omit for every group call. Any id spelling works (5172634473, -5172634473, -1005172634473 are the same group). A call whose chat is unknown never satisfies it, so do NOT set this together with 1:1 / Twilio / Telnyx / WhatsApp / Android / LiveChat voice channels or the \"voice\" wildcard: those calls have no chat and the trigger would stop answering them.\n\nSupported fields for job_completed (proactive callback when a delegated job finishes):\n- source_agent_id: <int> — fire only when this agent's job completed\n- source_agent_slug: <str> — alternate to source_agent_id\n- job_type: \"agentic_session\" — match a specific job type (default: any)\n- outcome: [\"completed\"] | [\"escalated\"] | [\"completed\",\"escalated\"] — default [\"completed\"]\n- min_duration_seconds: <int> — skip very-short jobs (noise filter)\n- thread_filter: {thread_ids: [<int>...]} — restrict to specific threads\n\nSupported fields for calendar_event (fires N minutes before a Google Calendar event starts):\n- window_minutes_before: <int 1-1440> — REQUIRED, fire when an event starts within this window\n- channel_account_ids: [<int>...] — restrict to specific calendar accounts (default: all)\n- keywords: [\"standup\"] — word-boundary match on event title\n- prepare_meet_join: true — pre-invite pool bots to the event (enables unattended Meet join)\n\nSupported fields for task_assigned (a task on the workspace board was assigned to this agent):\n- target_session: <session_id> — for a Claude Code agent, the session the task goes to (default: the agent's own session)\n\nSupported fields for job_continuation (this agent's own call or video finished):\n- job_types: [\"voice_call\", \"video_generation\"] — which kinds re-invoke it (default: all)\n\nincoming_message action fields:\n- action: \"reply_text\" (default, normal agent run) or \"join_voice\" (deterministically join the voice channel resolved from the message — requires send_mode=auto)\n- message_source: \"real\" (default) | \"transcript\" | \"both\" — real messages vs turns during a live call. Transcripts are turns that address the agent.\n\ncalendar_event run-mode field (incoming_message uses `action` instead):\n- run_mode: \"text\" (default) or \"voice\" (join the meeting — requires send_mode=auto)\n- voice: {speak_first: <bool — greet immediately vs stay silent until addressed>, vision_mode: \"off\"|\"on_demand\"|\"continuous_0_3fps\"} — pairs with action=join_voice (incoming_message) or run_mode=voice (calendar_event)"New value: +"Trigger conditions (JSON). Supported fields for incoming_message:\n- keywords: [\"pricing\",\"demo\"] — message must contain keyword(s) (free, no LLM cost)\n- keyword_match: \"any\" (default, OR) or \"all\" (AND)\n- channel_types: [\"telegram\",\"whatsapp\",\"livechat_voice\",\"twilio_voice\",\"telegram_voice\",\"voice\",...] — filter by channel. For voice, use EITHER the three per-channel keys (scoped) OR \"voice\" alone (wildcard matching all three) — mixing them is redundant. Per-channel keys: \"livechat_voice\" (web widget), \"twilio_voice\" (PSTN inbound), \"telegram_voice\" (Telegram p2p calls)\n- context_types: [\"dm\",\"group\",\"channel\",\"livechat\"] — filter by chat type\n- group_mode: \"mentions_only\" or \"questions\" — for group chats\n- channel_account_ids: [\"123\"] — restrict to specific accounts. Only accounts THIS workspace answers: a trigger never fires for another workspace's channel, so create it on an agent there\n- folder_ids: [5,10] — restrict to threads in folders\n- ai_tag_ids: [1,2] — restrict to threads with AI tags\n- ai_filter_ids: [1,2] — semantic intent filters (message matched via embedding similarity, works in noisy groups)\n- ai_filter_mode: \"any\" (default, OR) or \"all\" (AND) — how multiple AI filters combine\n- ai_filters: [{id: 1}, {name: \"...\", description: \"...\"}] — shorthand: reference existing by id or create inline (calls Voyage embedding API). If a filter with the same name already exists, it is reused by id. Prefer referencing existing filters by id when available. Use ai_filters.create + ai_filters.test for fine-tuning before assigning.\n- template: the reply a rule_based agent sends, with no model run. Either a string (\"Hi {from_name}, we open at 9\") or a card object {text, attachments, buttons} — text is required, attachments is a list of file ids (files.upload), buttons is a list of {label, value|url|web_app} carrying exactly ONE target each: value = a reply the bot receives back, url = opens a link (add track: true to count each tap per conversation, readable as analytics_link_clicks_v in analytics.query; add tag: <ai_tag id> beside it to put that tag on the CONVERSATION at the tap, so for people, not groups, where any member's tap tags the whole group; add pass: \"<name>\" to open the url with <name>=<the chat's id on its channel, a Telegram user id for a bot chat>, so the site can name the person back in its own events), web_app = opens a Mini App over https. The string, and a card's text, substitute {from_name}, {message_text}, {channel_type}, {thread_id}, {raw_data}; button labels and targets are sent verbatim. A card with buttons needs send_mode auto — a draft row cannot carry a keyboard. Buttons need a channel that renders them (telegram_bot). A card needs a chat to land in, so it refuses on webhook, schedule and other thread-less triggers where a string still drafts.\n- handoff: {agent_id, task} — only on a rule_based agent's trigger (refused elsewhere). After the rule's deterministic part has actually happened — the template's message delivered, or the agent's script completed — the named agent runs on the same thread, in its own send mode, exactly as its own trigger would run it: the customer's message reaches it as the incoming message, and `task` reaches it as the handoff brief from this rule. The rule stays instant; the thinking — a reminder, a referral code, a personal follow-up — happens behind it. Script plus handoff is how a workspace does something deterministic the platform has no verb for (file the thread, stamp a tag, push a row) and still lets an agent answer, with the deterministic part living in that agent's own script rather than in platform code. `task` substitutes {channel_type} and {thread_id} only; {message_text}, {from_name} and {raw_data} are refused (the sender would be writing the instruction — the message and its sender already reach the target as the incoming message). The target must be an active agentic or claude_channels agent in this workspace (the engines that read the brief). The target's run is a normal trigger run: it holds the thread lock, its own safety gates apply, and its final answer is delivered like any DM reply — a follow-up that should stay silent must call agent.silence. Nothing runs when the message was drafted, refused or failed, when the script failed, when a safety gate has the rule in draft mode, or when the event carries no thread for the target to answer on. A target paused or deleted after the trigger was written does not stop the rule's message: it goes out, and the reason the follow-up did not start is recorded in the rule's activity row (error field) and in the target's activity as an execution_error.\n- contact_states: [\"active\"] — filter by contact state\n- cooldown_seconds: 30 — min gap between runs per thread\n- max_runs_per_thread_per_hour: 5 — rate limit\n- once_per_thread: true — after this trigger completes on a conversation it steps aside there and the next matching trigger answers later messages. For a rule that files / tags / hands off once, not for the agent that holds the conversation.\n- answer_delay_s: 15 — voice pickup only (incoming_call, or incoming_message scoped to a voice channel). Ring the human's own devices this long before the agent answers; if they pick up, the agent stands down. 0/absent = answer immediately. Honoured on WhatsApp and Telegram 1:1 — other voice channels have nothing ringing to wait for and still answer at once.\n- auto_join: true|false — voice pickup, GROUP calls only. Whether the bot enters a matching group call on its own (true) or the call becomes a pending invite an operator accepts (false). OMIT THE KEY to defer to the channel setting (channel_account.state.voice_auto_join_policy, default 'approval'); resolution is trigger-when-present, then channel, then approval, so an explicit false beats a channel set to auto. Absent and false are different answers.\n- chat_ids: [\"-5172634473\"] — voice pickup, Telegram GROUP calls only. Scopes the trigger to specific groups; omit for every group call. Any id spelling works (5172634473, -5172634473, -1005172634473 are the same group). A call whose chat is unknown never satisfies it, so do NOT set this together with 1:1 / Twilio / Telnyx / WhatsApp / Android / LiveChat voice channels or the \"voice\" wildcard: those calls have no chat and the trigger would stop answering them.\n\nSupported fields for job_completed (proactive callback when a delegated job finishes):\n- source_agent_id: <int> — fire only when this agent's job completed\n- source_agent_slug: <str> — alternate to source_agent_id\n- job_type: \"agentic_session\" — match a specific job type (default: any)\n- outcome: [\"completed\"] | [\"escalated\"] | [\"completed\",\"escalated\"] — default [\"completed\"]\n- min_duration_seconds: <int> — skip very-short jobs (noise filter)\n- thread_filter: {thread_ids: [<int>...]} — restrict to specific threads\n\nSupported fields for calendar_event (fires N minutes before a Google Calendar event starts):\n- window_minutes_before: <int 1-1440> — REQUIRED, fire when an event starts within this window\n- channel_account_ids: [<int>...] — restrict to specific calendar accounts (default: all)\n- keywords: [\"standup\"] — word-boundary match on event title\n- prepare_meet_join: true — pre-invite the pool bots that can join signed in (none when none can) to the event, for an unattended Meet join\n\nSupported fields for task_assigned (a task on the workspace board was assigned to this agent):\n- target_session: <session_id> — for a Claude Code agent, the session the task goes to (default: the agent's own session)\n\nSupported fields for job_continuation (this agent's own call or video finished):\n- job_types: [\"voice_call\", \"video_generation\"] — which kinds re-invoke it (default: all)\n\nincoming_message action fields:\n- action: \"reply_text\" (default, normal agent run) or \"join_voice\" (deterministically join the voice channel resolved from the message — requires send_mode=auto)\n- message_source: \"real\" (default) | \"transcript\" | \"both\" — real messages vs turns during a live call. Transcripts are turns that address the agent.\n\ncalendar_event run-mode field (incoming_message uses `action` instead):\n- run_mode: \"text\" (default) or \"voice\" (join the meeting — requires send_mode=auto)\n- voice: {speak_first: <bool — greet immediately vs stay silent until addressed>, vision_mode: \"off\"|\"on_demand\"|\"continuous_0_3fps\"} — pairs with action=join_voice (incoming_message) or run_mode=voice (calendar_event)"
  8. Changed3 schema fields changed
    • changedInput schema / properties / conditions / description
      Previous value: -"Trigger conditions (JSON). Supported fields for incoming_message:\n- keywords: [\"pricing\",\"demo\"] — message must contain keyword(s) (free, no LLM cost)\n- keyword_match: \"any\" (default, OR) or \"all\" (AND)\n- channel_types: [\"telegram\",\"whatsapp\",\"livechat_voice\",\"twilio_voice\",\"telegram_voice\",\"voice\",...] — filter by channel. For voice, use EITHER the three per-channel keys (scoped) OR \"voice\" alone (wildcard matching all three) — mixing them is redundant. Per-channel keys: \"livechat_voice\" (web widget), \"twilio_voice\" (PSTN inbound), \"telegram_voice\" (Telegram p2p calls)\n- context_types: [\"dm\",\"group\",\"channel\",\"livechat\"] — filter by chat type\n- group_mode: \"mentions_only\" or \"questions\" — for group chats\n- channel_account_ids: [\"123\"] — restrict to specific accounts. Only accounts THIS workspace answers: a trigger never fires for another workspace's channel, so create it on an agent there\n- folder_ids: [5,10] — restrict to threads in folders\n- ai_tag_ids: [1,2] — restrict to threads with AI tags\n- ai_filter_ids: [1,2] — semantic intent filters (message matched via embedding similarity, works in noisy groups)\n- ai_filter_mode: \"any\" (default, OR) or \"all\" (AND) — how multiple AI filters combine\n- ai_filters: [{id: 1}, {name: \"...\", description: \"...\"}] — shorthand: reference existing by id or create inline (calls Voyage embedding API). If a filter with the same name already exists, it is reused by id. Prefer referencing existing filters by id when available. Use ai_filters.create + ai_filters.test for fine-tuning before assigning.\n- template: the reply a rule_based agent sends, with no model run. Either a string (\"Hi {from_name}, we open at 9\") or a card object {text, attachments, buttons} — text is required, attachments is a list of file ids (files.upload), buttons is a list of {label, value|url|web_app} carrying exactly ONE target each: value = a reply the bot receives back, url = opens a link (add track: true to count each tap per conversation, readable as analytics_link_clicks_v in analytics.query; add tag: <ai_tag id> beside it to put that tag on the CONVERSATION at the tap, so for people, not groups, where any member's tap tags the whole group; add pass: \"<name>\" to open the url with <name>=<the chat's id on its channel, a Telegram user id for a bot chat>, so the site can name the person back in its own events), web_app = opens a Mini App over https. The string, and a card's text, substitute {from_name}, {message_text}, {channel_type}, {thread_id}, {raw_data}; button labels and targets are sent verbatim. A card with buttons needs send_mode auto — a draft row cannot carry a keyboard. Buttons need a channel that renders them (telegram_bot). A card needs a chat to land in, so it refuses on webhook, schedule and other thread-less triggers where a string still drafts.\n- handoff: {agent_id, task} — only on a rule_based agent's trigger (refused elsewhere). After the rule's deterministic part has actually happened — the template's message delivered, or the agent's script completed — the named agent runs on the same thread, in its own send mode, exactly as its own trigger would run it: the customer's message reaches it as the incoming message, and `task` reaches it as the handoff brief from this rule. The rule stays instant; the thinking — a reminder, a referral code, a personal follow-up — happens behind it. Script plus handoff is how a workspace does something deterministic the platform has no verb for (file the thread, stamp a tag, push a row) and still lets an agent answer, with the deterministic part living in that agent's own script rather than in platform code. `task` substitutes {channel_type} and {thread_id} only; {message_text}, {from_name} and {raw_data} are refused (the sender would be writing the instruction — the message and its sender already reach the target as the incoming message). The target must be an active agentic or claude_channels agent in this workspace (the engines that read the brief). The target's run is a normal trigger run: it holds the thread lock, its own safety gates apply, and its final answer is delivered like any DM reply — a follow-up that should stay silent must call agent.silence. Nothing runs when the message was drafted, refused or failed, when the script failed, when a safety gate has the rule in draft mode, or when the event carries no thread for the target to answer on. A target paused or deleted after the trigger was written does not stop the rule's message: it goes out, and the reason the follow-up did not start is recorded in the rule's activity row (error field) and in the target's activity as an execution_error.\n- contact_states: [\"active\"] — filter by contact state\n- cooldown_seconds: 30 — min gap between runs per thread\n- max_runs_per_thread_per_hour: 5 — rate limit\n- once_per_thread: true — after this trigger completes on a conversation it steps aside there and the next matching trigger answers later messages. For a rule that files / tags / hands off once, not for the agent that holds the conversation.\n- answer_delay_s: 15 — voice pickup only (incoming_call, or incoming_message scoped to a voice channel). Ring the human's own devices this long before the agent answers; if they pick up, the agent stands down. 0/absent = answer immediately. Honoured on WhatsApp and Telegram 1:1 — other voice channels have nothing ringing to wait for and still answer at once.\n- auto_join: true|false — voice pickup, GROUP calls only. Whether the bot enters a matching group call on its own (true) or the call becomes a pending invite an operator accepts (false). OMIT THE KEY to defer to the channel setting (channel_account.state.voice_auto_join_policy, default 'approval'); resolution is trigger-when-present, then channel, then approval, so an explicit false beats a channel set to auto. Absent and false are different answers.\n- chat_ids: [\"-5172634473\"] — voice pickup, Telegram GROUP calls only. Scopes the trigger to specific groups; omit for every group call. Any id spelling works (5172634473, -5172634473, -1005172634473 are the same group). A call whose chat is unknown never satisfies it, so do NOT set this together with 1:1 / Twilio / Telnyx / WhatsApp / Android / LiveChat voice channels or the \"voice\" wildcard: those calls have no chat and the trigger would stop answering them.\n\nSupported fields for job_completed (proactive callback when a delegated job finishes):\n- source_agent_id: <int> — fire only when this agent's job completed\n- source_agent_slug: <str> — alternate to source_agent_id\n- job_type: \"agentic_session\" — match a specific job type (default: any)\n- outcome: [\"completed\"] | [\"escalated\"] | [\"completed\",\"escalated\"] — default [\"completed\"]\n- min_duration_seconds: <int> — skip very-short jobs (noise filter)\n- thread_filter: {thread_ids: [<int>...]} — restrict to specific threads\n\nSupported fields for calendar_event (fires N minutes before a Google Calendar event starts):\n- window_minutes_before: <int 1-1440> — REQUIRED, fire when an event starts within this window\n- channel_account_ids: [<int>...] — restrict to specific calendar accounts (default: all)\n- keywords: [\"standup\"] — word-boundary match on event title\n- prepare_meet_join: true — pre-invite pool bots to the event (enables unattended Meet join)\n\nSupported fields for task_assigned (a task on the workspace board was assigned to this agent):\n- target_session: <session_id> — for a Claude Code agent, the session the task goes to (default: the agent's own session)\n\nincoming_message action fields:\n- action: \"reply_text\" (default, normal agent run) or \"join_voice\" (deterministically join the voice channel resolved from the message — requires send_mode=auto)\n- message_source: \"real\" (default) | \"transcript\" | \"both\" — real messages vs turns during a live call. Transcripts are turns that address the agent.\n\ncalendar_event run-mode field (incoming_message uses `action` instead):\n- run_mode: \"text\" (default) or \"voice\" (join the meeting — requires send_mode=auto)\n- voice: {speak_first: <bool — greet immediately vs stay silent until addressed>, vision_mode: \"off\"|\"on_demand\"|\"continuous_0_3fps\"} — pairs with action=join_voice (incoming_message) or run_mode=voice (calendar_event)"New value: +"Trigger conditions (JSON). Supported fields for incoming_message:\n- keywords: [\"pricing\",\"demo\"] — message must contain keyword(s) (free, no LLM cost)\n- keyword_match: \"any\" (default, OR) or \"all\" (AND)\n- channel_types: [\"telegram\",\"whatsapp\",\"livechat_voice\",\"twilio_voice\",\"telegram_voice\",\"voice\",...] — filter by channel. For voice, use EITHER the three per-channel keys (scoped) OR \"voice\" alone (wildcard matching all three) — mixing them is redundant. Per-channel keys: \"livechat_voice\" (web widget), \"twilio_voice\" (PSTN inbound), \"telegram_voice\" (Telegram p2p calls)\n- context_types: [\"dm\",\"group\",\"channel\",\"livechat\"] — filter by chat type\n- group_mode: \"mentions_only\" or \"questions\" — for group chats\n- channel_account_ids: [\"123\"] — restrict to specific accounts. Only accounts THIS workspace answers: a trigger never fires for another workspace's channel, so create it on an agent there\n- folder_ids: [5,10] — restrict to threads in folders\n- ai_tag_ids: [1,2] — restrict to threads with AI tags\n- ai_filter_ids: [1,2] — semantic intent filters (message matched via embedding similarity, works in noisy groups)\n- ai_filter_mode: \"any\" (default, OR) or \"all\" (AND) — how multiple AI filters combine\n- ai_filters: [{id: 1}, {name: \"...\", description: \"...\"}] — shorthand: reference existing by id or create inline (calls Voyage embedding API). If a filter with the same name already exists, it is reused by id. Prefer referencing existing filters by id when available. Use ai_filters.create + ai_filters.test for fine-tuning before assigning.\n- template: the reply a rule_based agent sends, with no model run. Either a string (\"Hi {from_name}, we open at 9\") or a card object {text, attachments, buttons} — text is required, attachments is a list of file ids (files.upload), buttons is a list of {label, value|url|web_app} carrying exactly ONE target each: value = a reply the bot receives back, url = opens a link (add track: true to count each tap per conversation, readable as analytics_link_clicks_v in analytics.query; add tag: <ai_tag id> beside it to put that tag on the CONVERSATION at the tap, so for people, not groups, where any member's tap tags the whole group; add pass: \"<name>\" to open the url with <name>=<the chat's id on its channel, a Telegram user id for a bot chat>, so the site can name the person back in its own events), web_app = opens a Mini App over https. The string, and a card's text, substitute {from_name}, {message_text}, {channel_type}, {thread_id}, {raw_data}; button labels and targets are sent verbatim. A card with buttons needs send_mode auto — a draft row cannot carry a keyboard. Buttons need a channel that renders them (telegram_bot). A card needs a chat to land in, so it refuses on webhook, schedule and other thread-less triggers where a string still drafts.\n- handoff: {agent_id, task} — only on a rule_based agent's trigger (refused elsewhere). After the rule's deterministic part has actually happened — the template's message delivered, or the agent's script completed — the named agent runs on the same thread, in its own send mode, exactly as its own trigger would run it: the customer's message reaches it as the incoming message, and `task` reaches it as the handoff brief from this rule. The rule stays instant; the thinking — a reminder, a referral code, a personal follow-up — happens behind it. Script plus handoff is how a workspace does something deterministic the platform has no verb for (file the thread, stamp a tag, push a row) and still lets an agent answer, with the deterministic part living in that agent's own script rather than in platform code. `task` substitutes {channel_type} and {thread_id} only; {message_text}, {from_name} and {raw_data} are refused (the sender would be writing the instruction — the message and its sender already reach the target as the incoming message). The target must be an active agentic or claude_channels agent in this workspace (the engines that read the brief). The target's run is a normal trigger run: it holds the thread lock, its own safety gates apply, and its final answer is delivered like any DM reply — a follow-up that should stay silent must call agent.silence. Nothing runs when the message was drafted, refused or failed, when the script failed, when a safety gate has the rule in draft mode, or when the event carries no thread for the target to answer on. A target paused or deleted after the trigger was written does not stop the rule's message: it goes out, and the reason the follow-up did not start is recorded in the rule's activity row (error field) and in the target's activity as an execution_error.\n- contact_states: [\"active\"] — filter by contact state\n- cooldown_seconds: 30 — min gap between runs per thread\n- max_runs_per_thread_per_hour: 5 — rate limit\n- once_per_thread: true — after this trigger completes on a conversation it steps aside there and the next matching trigger answers later messages. For a rule that files / tags / hands off once, not for the agent that holds the conversation.\n- answer_delay_s: 15 — voice pickup only (incoming_call, or incoming_message scoped to a voice channel). Ring the human's own devices this long before the agent answers; if they pick up, the agent stands down. 0/absent = answer immediately. Honoured on WhatsApp and Telegram 1:1 — other voice channels have nothing ringing to wait for and still answer at once.\n- auto_join: true|false — voice pickup, GROUP calls only. Whether the bot enters a matching group call on its own (true) or the call becomes a pending invite an operator accepts (false). OMIT THE KEY to defer to the channel setting (channel_account.state.voice_auto_join_policy, default 'approval'); resolution is trigger-when-present, then channel, then approval, so an explicit false beats a channel set to auto. Absent and false are different answers.\n- chat_ids: [\"-5172634473\"] — voice pickup, Telegram GROUP calls only. Scopes the trigger to specific groups; omit for every group call. Any id spelling works (5172634473, -5172634473, -1005172634473 are the same group). A call whose chat is unknown never satisfies it, so do NOT set this together with 1:1 / Twilio / Telnyx / WhatsApp / Android / LiveChat voice channels or the \"voice\" wildcard: those calls have no chat and the trigger would stop answering them.\n\nSupported fields for job_completed (proactive callback when a delegated job finishes):\n- source_agent_id: <int> — fire only when this agent's job completed\n- source_agent_slug: <str> — alternate to source_agent_id\n- job_type: \"agentic_session\" — match a specific job type (default: any)\n- outcome: [\"completed\"] | [\"escalated\"] | [\"completed\",\"escalated\"] — default [\"completed\"]\n- min_duration_seconds: <int> — skip very-short jobs (noise filter)\n- thread_filter: {thread_ids: [<int>...]} — restrict to specific threads\n\nSupported fields for calendar_event (fires N minutes before a Google Calendar event starts):\n- window_minutes_before: <int 1-1440> — REQUIRED, fire when an event starts within this window\n- channel_account_ids: [<int>...] — restrict to specific calendar accounts (default: all)\n- keywords: [\"standup\"] — word-boundary match on event title\n- prepare_meet_join: true — pre-invite pool bots to the event (enables unattended Meet join)\n\nSupported fields for task_assigned (a task on the workspace board was assigned to this agent):\n- target_session: <session_id> — for a Claude Code agent, the session the task goes to (default: the agent's own session)\n\nSupported fields for job_continuation (this agent's own call or video finished):\n- job_types: [\"voice_call\", \"video_generation\"] — which kinds re-invoke it (default: all)\n\nincoming_message action fields:\n- action: \"reply_text\" (default, normal agent run) or \"join_voice\" (deterministically join the voice channel resolved from the message — requires send_mode=auto)\n- message_source: \"real\" (default) | \"transcript\" | \"both\" — real messages vs turns during a live call. Transcripts are turns that address the agent.\n\ncalendar_event run-mode field (incoming_message uses `action` instead):\n- run_mode: \"text\" (default) or \"voice\" (join the meeting — requires send_mode=auto)\n- voice: {speak_first: <bool — greet immediately vs stay silent until addressed>, vision_mode: \"off\"|\"on_demand\"|\"continuous_0_3fps\"} — pairs with action=join_voice (incoming_message) or run_mode=voice (calendar_event)"
    • changedInput schema / properties / trigger_type / description
      Previous value: -"Type of trigger: 'incoming_message', 'incoming_call', 'schedule', 'webhook', 'event', 'blockchain_event', 'job_completed', 'calendar_event', 'lead_captured', or 'task_assigned' (a task on the workspace board was assigned to this agent; without one, assigning a task does not start the agent)"New value: +"Type of trigger: 'incoming_message', 'incoming_call', 'schedule', 'webhook', 'event', 'blockchain_event', 'job_completed', 'calendar_event', 'lead_captured', 'task_assigned' (a task on the workspace board was assigned to this agent; without one, assigning a task does not start the agent), or 'job_continuation' (this agent's OWN call from calls.make or video from videos.generate finished; without one the agent is not re-invoked to carry on)"
    • changedInput schema / properties / trigger_type / enum
      Previous value: -[
      -  "incoming_message",
      -  "incoming_call",
      -  "schedule",
      -  "webhook",
      -  "event",
      -  "blockchain_event",
      -  "job_completed",
      -  "calendar_event",
      -  "lead_captured",
      -  "task_assigned"
      -]New value: +[
      +  "incoming_message",
      +  "incoming_call",
      +  "schedule",
      +  "webhook",
      +  "event",
      +  "blockchain_event",
      +  "job_completed",
      +  "calendar_event",
      +  "lead_captured",
      +  "task_assigned",
      +  "job_continuation"
      +]
  9. Changed3 schema fields changed
    • changedInput schema / properties / conditions / description
      Previous value: -"Trigger conditions (JSON). Supported fields for incoming_message:\n- keywords: [\"pricing\",\"demo\"] — message must contain keyword(s) (free, no LLM cost)\n- keyword_match: \"any\" (default, OR) or \"all\" (AND)\n- channel_types: [\"telegram\",\"whatsapp\",\"livechat_voice\",\"twilio_voice\",\"telegram_voice\",\"voice\",...] — filter by channel. For voice, use EITHER the three per-channel keys (scoped) OR \"voice\" alone (wildcard matching all three) — mixing them is redundant. Per-channel keys: \"livechat_voice\" (web widget), \"twilio_voice\" (PSTN inbound), \"telegram_voice\" (Telegram p2p calls)\n- context_types: [\"dm\",\"group\",\"channel\",\"livechat\"] — filter by chat type\n- group_mode: \"mentions_only\" or \"questions\" — for group chats\n- channel_account_ids: [\"123\"] — restrict to specific accounts. Only accounts THIS workspace answers: a trigger never fires for another workspace's channel, so create it on an agent there\n- folder_ids: [5,10] — restrict to threads in folders\n- ai_tag_ids: [1,2] — restrict to threads with AI tags\n- ai_filter_ids: [1,2] — semantic intent filters (message matched via embedding similarity, works in noisy groups)\n- ai_filter_mode: \"any\" (default, OR) or \"all\" (AND) — how multiple AI filters combine\n- ai_filters: [{id: 1}, {name: \"...\", description: \"...\"}] — shorthand: reference existing by id or create inline (calls Voyage embedding API). If a filter with the same name already exists, it is reused by id. Prefer referencing existing filters by id when available. Use ai_filters.create + ai_filters.test for fine-tuning before assigning.\n- template: the reply a rule_based agent sends, with no model run. Either a string (\"Hi {from_name}, we open at 9\") or a card object {text, attachments, buttons} — text is required, attachments is a list of file ids (files.upload), buttons is a list of {label, value|url|web_app} carrying exactly ONE target each: value = a reply the bot receives back, url = opens a link (add track: true to count each tap per conversation, readable as analytics_link_clicks_v in analytics.query; add tag: <ai_tag id> beside it to put that tag on the CONVERSATION at the tap, so for people, not groups, where any member's tap tags the whole group; add pass: \"<name>\" to open the url with <name>=<the chat's id on its channel, a Telegram user id for a bot chat>, so the site can name the person back in its own events), web_app = opens a Mini App over https. The string, and a card's text, substitute {from_name}, {message_text}, {channel_type}, {thread_id}, {raw_data}; button labels and targets are sent verbatim. A card with buttons needs send_mode auto — a draft row cannot carry a keyboard. Buttons need a channel that renders them (telegram_bot). A card needs a chat to land in, so it refuses on webhook, schedule and other thread-less triggers where a string still drafts.\n- handoff: {agent_id, task} — only on a rule_based agent's trigger (refused elsewhere). After the rule's deterministic part has actually happened — the template's message delivered, or the agent's script completed — the named agent runs on the same thread, in its own send mode, exactly as its own trigger would run it: the customer's message reaches it as the incoming message, and `task` reaches it as the handoff brief from this rule. The rule stays instant; the thinking — a reminder, a referral code, a personal follow-up — happens behind it. Script plus handoff is how a workspace does something deterministic the platform has no verb for (file the thread, stamp a tag, push a row) and still lets an agent answer, with the deterministic part living in that agent's own script rather than in platform code. `task` substitutes {channel_type} and {thread_id} only; {message_text}, {from_name} and {raw_data} are refused (the sender would be writing the instruction — the message and its sender already reach the target as the incoming message). The target must be an active agentic or claude_channels agent in this workspace (the engines that read the brief). The target's run is a normal trigger run: it holds the thread lock, its own safety gates apply, and its final answer is delivered like any DM reply — a follow-up that should stay silent must call agent.silence. Nothing runs when the message was drafted, refused or failed, when the script failed, when a safety gate has the rule in draft mode, or when the event carries no thread for the target to answer on. A target paused or deleted after the trigger was written does not stop the rule's message: it goes out, and the reason the follow-up did not start is recorded in the rule's activity row (error field) and in the target's activity as an execution_error.\n- contact_states: [\"active\"] — filter by contact state\n- cooldown_seconds: 30 — min gap between runs per thread\n- max_runs_per_thread_per_hour: 5 — rate limit\n- once_per_thread: true — after this trigger completes on a conversation it steps aside there and the next matching trigger answers later messages. For a rule that files / tags / hands off once, not for the agent that holds the conversation.\n- answer_delay_s: 15 — voice pickup only (incoming_call, or incoming_message scoped to a voice channel). Ring the human's own devices this long before the agent answers; if they pick up, the agent stands down. 0/absent = answer immediately. Honoured on WhatsApp and Telegram 1:1 — other voice channels have nothing ringing to wait for and still answer at once.\n- auto_join: true|false — voice pickup, GROUP calls only. Whether the bot enters a matching group call on its own (true) or the call becomes a pending invite an operator accepts (false). OMIT THE KEY to defer to the channel setting (channel_account.state.voice_auto_join_policy, default 'approval'); resolution is trigger-when-present, then channel, then approval, so an explicit false beats a channel set to auto. Absent and false are different answers.\n- chat_ids: [\"-5172634473\"] — voice pickup, Telegram GROUP calls only. Scopes the trigger to specific groups; omit for every group call. Any id spelling works (5172634473, -5172634473, -1005172634473 are the same group). A call whose chat is unknown never satisfies it, so do NOT set this together with 1:1 / Twilio / Telnyx / WhatsApp / Android / LiveChat voice channels or the \"voice\" wildcard: those calls have no chat and the trigger would stop answering them.\n\nSupported fields for job_completed (proactive callback when a delegated job finishes):\n- source_agent_id: <int> — fire only when this agent's job completed\n- source_agent_slug: <str> — alternate to source_agent_id\n- job_type: \"agentic_session\" — match a specific job type (default: any)\n- outcome: [\"completed\"] | [\"escalated\"] | [\"completed\",\"escalated\"] — default [\"completed\"]\n- min_duration_seconds: <int> — skip very-short jobs (noise filter)\n- thread_filter: {thread_ids: [<int>...]} — restrict to specific threads\n\nSupported fields for calendar_event (fires N minutes before a Google Calendar event starts):\n- window_minutes_before: <int 1-1440> — REQUIRED, fire when an event starts within this window\n- channel_account_ids: [<int>...] — restrict to specific calendar accounts (default: all)\n- keywords: [\"standup\"] — word-boundary match on event title\n- prepare_meet_join: true — pre-invite pool bots to the event (enables unattended Meet join)\n\nincoming_message action fields:\n- action: \"reply_text\" (default, normal agent run) or \"join_voice\" (deterministically join the voice channel resolved from the message — requires send_mode=auto)\n- message_source: \"real\" (default) | \"transcript\" | \"both\" — real messages vs turns during a live call. Transcripts are turns that address the agent.\n\ncalendar_event run-mode field (incoming_message uses `action` instead):\n- run_mode: \"text\" (default) or \"voice\" (join the meeting — requires send_mode=auto)\n- voice: {speak_first: <bool — greet immediately vs stay silent until addressed>, vision_mode: \"off\"|\"on_demand\"|\"continuous_0_3fps\"} — pairs with action=join_voice (incoming_message) or run_mode=voice (calendar_event)"New value: +"Trigger conditions (JSON). Supported fields for incoming_message:\n- keywords: [\"pricing\",\"demo\"] — message must contain keyword(s) (free, no LLM cost)\n- keyword_match: \"any\" (default, OR) or \"all\" (AND)\n- channel_types: [\"telegram\",\"whatsapp\",\"livechat_voice\",\"twilio_voice\",\"telegram_voice\",\"voice\",...] — filter by channel. For voice, use EITHER the three per-channel keys (scoped) OR \"voice\" alone (wildcard matching all three) — mixing them is redundant. Per-channel keys: \"livechat_voice\" (web widget), \"twilio_voice\" (PSTN inbound), \"telegram_voice\" (Telegram p2p calls)\n- context_types: [\"dm\",\"group\",\"channel\",\"livechat\"] — filter by chat type\n- group_mode: \"mentions_only\" or \"questions\" — for group chats\n- channel_account_ids: [\"123\"] — restrict to specific accounts. Only accounts THIS workspace answers: a trigger never fires for another workspace's channel, so create it on an agent there\n- folder_ids: [5,10] — restrict to threads in folders\n- ai_tag_ids: [1,2] — restrict to threads with AI tags\n- ai_filter_ids: [1,2] — semantic intent filters (message matched via embedding similarity, works in noisy groups)\n- ai_filter_mode: \"any\" (default, OR) or \"all\" (AND) — how multiple AI filters combine\n- ai_filters: [{id: 1}, {name: \"...\", description: \"...\"}] — shorthand: reference existing by id or create inline (calls Voyage embedding API). If a filter with the same name already exists, it is reused by id. Prefer referencing existing filters by id when available. Use ai_filters.create + ai_filters.test for fine-tuning before assigning.\n- template: the reply a rule_based agent sends, with no model run. Either a string (\"Hi {from_name}, we open at 9\") or a card object {text, attachments, buttons} — text is required, attachments is a list of file ids (files.upload), buttons is a list of {label, value|url|web_app} carrying exactly ONE target each: value = a reply the bot receives back, url = opens a link (add track: true to count each tap per conversation, readable as analytics_link_clicks_v in analytics.query; add tag: <ai_tag id> beside it to put that tag on the CONVERSATION at the tap, so for people, not groups, where any member's tap tags the whole group; add pass: \"<name>\" to open the url with <name>=<the chat's id on its channel, a Telegram user id for a bot chat>, so the site can name the person back in its own events), web_app = opens a Mini App over https. The string, and a card's text, substitute {from_name}, {message_text}, {channel_type}, {thread_id}, {raw_data}; button labels and targets are sent verbatim. A card with buttons needs send_mode auto — a draft row cannot carry a keyboard. Buttons need a channel that renders them (telegram_bot). A card needs a chat to land in, so it refuses on webhook, schedule and other thread-less triggers where a string still drafts.\n- handoff: {agent_id, task} — only on a rule_based agent's trigger (refused elsewhere). After the rule's deterministic part has actually happened — the template's message delivered, or the agent's script completed — the named agent runs on the same thread, in its own send mode, exactly as its own trigger would run it: the customer's message reaches it as the incoming message, and `task` reaches it as the handoff brief from this rule. The rule stays instant; the thinking — a reminder, a referral code, a personal follow-up — happens behind it. Script plus handoff is how a workspace does something deterministic the platform has no verb for (file the thread, stamp a tag, push a row) and still lets an agent answer, with the deterministic part living in that agent's own script rather than in platform code. `task` substitutes {channel_type} and {thread_id} only; {message_text}, {from_name} and {raw_data} are refused (the sender would be writing the instruction — the message and its sender already reach the target as the incoming message). The target must be an active agentic or claude_channels agent in this workspace (the engines that read the brief). The target's run is a normal trigger run: it holds the thread lock, its own safety gates apply, and its final answer is delivered like any DM reply — a follow-up that should stay silent must call agent.silence. Nothing runs when the message was drafted, refused or failed, when the script failed, when a safety gate has the rule in draft mode, or when the event carries no thread for the target to answer on. A target paused or deleted after the trigger was written does not stop the rule's message: it goes out, and the reason the follow-up did not start is recorded in the rule's activity row (error field) and in the target's activity as an execution_error.\n- contact_states: [\"active\"] — filter by contact state\n- cooldown_seconds: 30 — min gap between runs per thread\n- max_runs_per_thread_per_hour: 5 — rate limit\n- once_per_thread: true — after this trigger completes on a conversation it steps aside there and the next matching trigger answers later messages. For a rule that files / tags / hands off once, not for the agent that holds the conversation.\n- answer_delay_s: 15 — voice pickup only (incoming_call, or incoming_message scoped to a voice channel). Ring the human's own devices this long before the agent answers; if they pick up, the agent stands down. 0/absent = answer immediately. Honoured on WhatsApp and Telegram 1:1 — other voice channels have nothing ringing to wait for and still answer at once.\n- auto_join: true|false — voice pickup, GROUP calls only. Whether the bot enters a matching group call on its own (true) or the call becomes a pending invite an operator accepts (false). OMIT THE KEY to defer to the channel setting (channel_account.state.voice_auto_join_policy, default 'approval'); resolution is trigger-when-present, then channel, then approval, so an explicit false beats a channel set to auto. Absent and false are different answers.\n- chat_ids: [\"-5172634473\"] — voice pickup, Telegram GROUP calls only. Scopes the trigger to specific groups; omit for every group call. Any id spelling works (5172634473, -5172634473, -1005172634473 are the same group). A call whose chat is unknown never satisfies it, so do NOT set this together with 1:1 / Twilio / Telnyx / WhatsApp / Android / LiveChat voice channels or the \"voice\" wildcard: those calls have no chat and the trigger would stop answering them.\n\nSupported fields for job_completed (proactive callback when a delegated job finishes):\n- source_agent_id: <int> — fire only when this agent's job completed\n- source_agent_slug: <str> — alternate to source_agent_id\n- job_type: \"agentic_session\" — match a specific job type (default: any)\n- outcome: [\"completed\"] | [\"escalated\"] | [\"completed\",\"escalated\"] — default [\"completed\"]\n- min_duration_seconds: <int> — skip very-short jobs (noise filter)\n- thread_filter: {thread_ids: [<int>...]} — restrict to specific threads\n\nSupported fields for calendar_event (fires N minutes before a Google Calendar event starts):\n- window_minutes_before: <int 1-1440> — REQUIRED, fire when an event starts within this window\n- channel_account_ids: [<int>...] — restrict to specific calendar accounts (default: all)\n- keywords: [\"standup\"] — word-boundary match on event title\n- prepare_meet_join: true — pre-invite pool bots to the event (enables unattended Meet join)\n\nSupported fields for task_assigned (a task on the workspace board was assigned to this agent):\n- target_session: <session_id> — for a Claude Code agent, the session the task goes to (default: the agent's own session)\n\nincoming_message action fields:\n- action: \"reply_text\" (default, normal agent run) or \"join_voice\" (deterministically join the voice channel resolved from the message — requires send_mode=auto)\n- message_source: \"real\" (default) | \"transcript\" | \"both\" — real messages vs turns during a live call. Transcripts are turns that address the agent.\n\ncalendar_event run-mode field (incoming_message uses `action` instead):\n- run_mode: \"text\" (default) or \"voice\" (join the meeting — requires send_mode=auto)\n- voice: {speak_first: <bool — greet immediately vs stay silent until addressed>, vision_mode: \"off\"|\"on_demand\"|\"continuous_0_3fps\"} — pairs with action=join_voice (incoming_message) or run_mode=voice (calendar_event)"
    • changedInput schema / properties / trigger_type / description
      Previous value: -"Type of trigger: 'incoming_message', 'incoming_call', 'schedule', 'webhook', 'event', 'blockchain_event', 'job_completed', 'calendar_event', or 'lead_captured'"New value: +"Type of trigger: 'incoming_message', 'incoming_call', 'schedule', 'webhook', 'event', 'blockchain_event', 'job_completed', 'calendar_event', 'lead_captured', or 'task_assigned' (a task on the workspace board was assigned to this agent; without one, assigning a task does not start the agent)"
    • changedInput schema / properties / trigger_type / enum
      Previous value: -[
      -  "incoming_message",
      -  "incoming_call",
      -  "schedule",
      -  "webhook",
      -  "event",
      -  "blockchain_event",
      -  "job_completed",
      -  "calendar_event",
      -  "lead_captured"
      -]New value: +[
      +  "incoming_message",
      +  "incoming_call",
      +  "schedule",
      +  "webhook",
      +  "event",
      +  "blockchain_event",
      +  "job_completed",
      +  "calendar_event",
      +  "lead_captured",
      +  "task_assigned"
      +]
  10. Changed1 schema field changed
    • changedInput schema / properties / conditions / description
      Previous value: -"Trigger conditions (JSON). Supported fields for incoming_message:\n- keywords: [\"pricing\",\"demo\"] — message must contain keyword(s) (free, no LLM cost)\n- keyword_match: \"any\" (default, OR) or \"all\" (AND)\n- channel_types: [\"telegram\",\"whatsapp\",\"livechat_voice\",\"twilio_voice\",\"telegram_voice\",\"voice\",...] — filter by channel. For voice, use EITHER the three per-channel keys (scoped) OR \"voice\" alone (wildcard matching all three) — mixing them is redundant. Per-channel keys: \"livechat_voice\" (web widget), \"twilio_voice\" (PSTN inbound), \"telegram_voice\" (Telegram p2p calls)\n- context_types: [\"dm\",\"group\",\"channel\",\"livechat\"] — filter by chat type\n- group_mode: \"mentions_only\" or \"questions\" — for group chats\n- channel_account_ids: [\"123\"] — restrict to specific accounts. Only accounts THIS workspace answers: a trigger never fires for another workspace's channel, so create it on an agent there\n- folder_ids: [5,10] — restrict to threads in folders\n- ai_tag_ids: [1,2] — restrict to threads with AI tags\n- ai_filter_ids: [1,2] — semantic intent filters (message matched via embedding similarity, works in noisy groups)\n- ai_filter_mode: \"any\" (default, OR) or \"all\" (AND) — how multiple AI filters combine\n- ai_filters: [{id: 1}, {name: \"...\", description: \"...\"}] — shorthand: reference existing by id or create inline (calls Voyage embedding API). If a filter with the same name already exists, it is reused by id. Prefer referencing existing filters by id when available. Use ai_filters.create + ai_filters.test for fine-tuning before assigning.\n- template: the reply a rule_based agent sends, with no model run. Either a string (\"Hi {from_name}, we open at 9\") or a card object {text, attachments, buttons} — text is required, attachments is a list of file ids (files.upload), buttons is a list of {label, value|url|web_app} carrying exactly ONE target each: value = a reply the bot receives back, url = opens a link (add track: true to count each tap per conversation, readable as analytics_link_clicks_v in analytics.query; add tag: <ai_tag id> beside it to put that tag on the CONVERSATION at the tap, so for people, not groups, where any member's tap tags the whole group), web_app = opens a Mini App over https. The string, and a card's text, substitute {from_name}, {message_text}, {channel_type}, {thread_id}, {raw_data}; button labels and targets are sent verbatim. A card with buttons needs send_mode auto — a draft row cannot carry a keyboard. Buttons need a channel that renders them (telegram_bot). A card needs a chat to land in, so it refuses on webhook, schedule and other thread-less triggers where a string still drafts.\n- handoff: {agent_id, task} — only on a rule_based agent's trigger (refused elsewhere). After the rule's deterministic part has actually happened — the template's message delivered, or the agent's script completed — the named agent runs on the same thread, in its own send mode, exactly as its own trigger would run it: the customer's message reaches it as the incoming message, and `task` reaches it as the handoff brief from this rule. The rule stays instant; the thinking — a reminder, a referral code, a personal follow-up — happens behind it. Script plus handoff is how a workspace does something deterministic the platform has no verb for (file the thread, stamp a tag, push a row) and still lets an agent answer, with the deterministic part living in that agent's own script rather than in platform code. `task` substitutes {channel_type} and {thread_id} only; {message_text}, {from_name} and {raw_data} are refused (the sender would be writing the instruction — the message and its sender already reach the target as the incoming message). The target must be an active agentic or claude_channels agent in this workspace (the engines that read the brief). The target's run is a normal trigger run: it holds the thread lock, its own safety gates apply, and its final answer is delivered like any DM reply — a follow-up that should stay silent must call agent.silence. Nothing runs when the message was drafted, refused or failed, when the script failed, when a safety gate has the rule in draft mode, or when the event carries no thread for the target to answer on. A target paused or deleted after the trigger was written does not stop the rule's message: it goes out, and the reason the follow-up did not start is recorded in the rule's activity row (error field) and in the target's activity as an execution_error.\n- contact_states: [\"active\"] — filter by contact state\n- cooldown_seconds: 30 — min gap between runs per thread\n- max_runs_per_thread_per_hour: 5 — rate limit\n- once_per_thread: true — after this trigger completes on a conversation it steps aside there and the next matching trigger answers later messages. For a rule that files / tags / hands off once, not for the agent that holds the conversation.\n- answer_delay_s: 15 — voice pickup only (incoming_call, or incoming_message scoped to a voice channel). Ring the human's own devices this long before the agent answers; if they pick up, the agent stands down. 0/absent = answer immediately. Honoured on WhatsApp and Telegram 1:1 — other voice channels have nothing ringing to wait for and still answer at once.\n- auto_join: true|false — voice pickup, GROUP calls only. Whether the bot enters a matching group call on its own (true) or the call becomes a pending invite an operator accepts (false). OMIT THE KEY to defer to the channel setting (channel_account.state.voice_auto_join_policy, default 'approval'); resolution is trigger-when-present, then channel, then approval, so an explicit false beats a channel set to auto. Absent and false are different answers.\n- chat_ids: [\"-5172634473\"] — voice pickup, Telegram GROUP calls only. Scopes the trigger to specific groups; omit for every group call. Any id spelling works (5172634473, -5172634473, -1005172634473 are the same group). A call whose chat is unknown never satisfies it, so do NOT set this together with 1:1 / Twilio / Telnyx / WhatsApp / Android / LiveChat voice channels or the \"voice\" wildcard: those calls have no chat and the trigger would stop answering them.\n\nSupported fields for job_completed (proactive callback when a delegated job finishes):\n- source_agent_id: <int> — fire only when this agent's job completed\n- source_agent_slug: <str> — alternate to source_agent_id\n- job_type: \"agentic_session\" — match a specific job type (default: any)\n- outcome: [\"completed\"] | [\"escalated\"] | [\"completed\",\"escalated\"] — default [\"completed\"]\n- min_duration_seconds: <int> — skip very-short jobs (noise filter)\n- thread_filter: {thread_ids: [<int>...]} — restrict to specific threads\n\nSupported fields for calendar_event (fires N minutes before a Google Calendar event starts):\n- window_minutes_before: <int 1-1440> — REQUIRED, fire when an event starts within this window\n- channel_account_ids: [<int>...] — restrict to specific calendar accounts (default: all)\n- keywords: [\"standup\"] — word-boundary match on event title\n- prepare_meet_join: true — pre-invite pool bots to the event (enables unattended Meet join)\n\nincoming_message action fields:\n- action: \"reply_text\" (default, normal agent run) or \"join_voice\" (deterministically join the voice channel resolved from the message — requires send_mode=auto)\n- message_source: \"real\" (default) | \"transcript\" | \"both\" — real messages vs turns during a live call. Transcripts are turns that address the agent.\n\ncalendar_event run-mode field (incoming_message uses `action` instead):\n- run_mode: \"text\" (default) or \"voice\" (join the meeting — requires send_mode=auto)\n- voice: {speak_first: <bool — greet immediately vs stay silent until addressed>, vision_mode: \"off\"|\"on_demand\"|\"continuous_0_3fps\"} — pairs with action=join_voice (incoming_message) or run_mode=voice (calendar_event)"New value: +"Trigger conditions (JSON). Supported fields for incoming_message:\n- keywords: [\"pricing\",\"demo\"] — message must contain keyword(s) (free, no LLM cost)\n- keyword_match: \"any\" (default, OR) or \"all\" (AND)\n- channel_types: [\"telegram\",\"whatsapp\",\"livechat_voice\",\"twilio_voice\",\"telegram_voice\",\"voice\",...] — filter by channel. For voice, use EITHER the three per-channel keys (scoped) OR \"voice\" alone (wildcard matching all three) — mixing them is redundant. Per-channel keys: \"livechat_voice\" (web widget), \"twilio_voice\" (PSTN inbound), \"telegram_voice\" (Telegram p2p calls)\n- context_types: [\"dm\",\"group\",\"channel\",\"livechat\"] — filter by chat type\n- group_mode: \"mentions_only\" or \"questions\" — for group chats\n- channel_account_ids: [\"123\"] — restrict to specific accounts. Only accounts THIS workspace answers: a trigger never fires for another workspace's channel, so create it on an agent there\n- folder_ids: [5,10] — restrict to threads in folders\n- ai_tag_ids: [1,2] — restrict to threads with AI tags\n- ai_filter_ids: [1,2] — semantic intent filters (message matched via embedding similarity, works in noisy groups)\n- ai_filter_mode: \"any\" (default, OR) or \"all\" (AND) — how multiple AI filters combine\n- ai_filters: [{id: 1}, {name: \"...\", description: \"...\"}] — shorthand: reference existing by id or create inline (calls Voyage embedding API). If a filter with the same name already exists, it is reused by id. Prefer referencing existing filters by id when available. Use ai_filters.create + ai_filters.test for fine-tuning before assigning.\n- template: the reply a rule_based agent sends, with no model run. Either a string (\"Hi {from_name}, we open at 9\") or a card object {text, attachments, buttons} — text is required, attachments is a list of file ids (files.upload), buttons is a list of {label, value|url|web_app} carrying exactly ONE target each: value = a reply the bot receives back, url = opens a link (add track: true to count each tap per conversation, readable as analytics_link_clicks_v in analytics.query; add tag: <ai_tag id> beside it to put that tag on the CONVERSATION at the tap, so for people, not groups, where any member's tap tags the whole group; add pass: \"<name>\" to open the url with <name>=<the chat's id on its channel, a Telegram user id for a bot chat>, so the site can name the person back in its own events), web_app = opens a Mini App over https. The string, and a card's text, substitute {from_name}, {message_text}, {channel_type}, {thread_id}, {raw_data}; button labels and targets are sent verbatim. A card with buttons needs send_mode auto — a draft row cannot carry a keyboard. Buttons need a channel that renders them (telegram_bot). A card needs a chat to land in, so it refuses on webhook, schedule and other thread-less triggers where a string still drafts.\n- handoff: {agent_id, task} — only on a rule_based agent's trigger (refused elsewhere). After the rule's deterministic part has actually happened — the template's message delivered, or the agent's script completed — the named agent runs on the same thread, in its own send mode, exactly as its own trigger would run it: the customer's message reaches it as the incoming message, and `task` reaches it as the handoff brief from this rule. The rule stays instant; the thinking — a reminder, a referral code, a personal follow-up — happens behind it. Script plus handoff is how a workspace does something deterministic the platform has no verb for (file the thread, stamp a tag, push a row) and still lets an agent answer, with the deterministic part living in that agent's own script rather than in platform code. `task` substitutes {channel_type} and {thread_id} only; {message_text}, {from_name} and {raw_data} are refused (the sender would be writing the instruction — the message and its sender already reach the target as the incoming message). The target must be an active agentic or claude_channels agent in this workspace (the engines that read the brief). The target's run is a normal trigger run: it holds the thread lock, its own safety gates apply, and its final answer is delivered like any DM reply — a follow-up that should stay silent must call agent.silence. Nothing runs when the message was drafted, refused or failed, when the script failed, when a safety gate has the rule in draft mode, or when the event carries no thread for the target to answer on. A target paused or deleted after the trigger was written does not stop the rule's message: it goes out, and the reason the follow-up did not start is recorded in the rule's activity row (error field) and in the target's activity as an execution_error.\n- contact_states: [\"active\"] — filter by contact state\n- cooldown_seconds: 30 — min gap between runs per thread\n- max_runs_per_thread_per_hour: 5 — rate limit\n- once_per_thread: true — after this trigger completes on a conversation it steps aside there and the next matching trigger answers later messages. For a rule that files / tags / hands off once, not for the agent that holds the conversation.\n- answer_delay_s: 15 — voice pickup only (incoming_call, or incoming_message scoped to a voice channel). Ring the human's own devices this long before the agent answers; if they pick up, the agent stands down. 0/absent = answer immediately. Honoured on WhatsApp and Telegram 1:1 — other voice channels have nothing ringing to wait for and still answer at once.\n- auto_join: true|false — voice pickup, GROUP calls only. Whether the bot enters a matching group call on its own (true) or the call becomes a pending invite an operator accepts (false). OMIT THE KEY to defer to the channel setting (channel_account.state.voice_auto_join_policy, default 'approval'); resolution is trigger-when-present, then channel, then approval, so an explicit false beats a channel set to auto. Absent and false are different answers.\n- chat_ids: [\"-5172634473\"] — voice pickup, Telegram GROUP calls only. Scopes the trigger to specific groups; omit for every group call. Any id spelling works (5172634473, -5172634473, -1005172634473 are the same group). A call whose chat is unknown never satisfies it, so do NOT set this together with 1:1 / Twilio / Telnyx / WhatsApp / Android / LiveChat voice channels or the \"voice\" wildcard: those calls have no chat and the trigger would stop answering them.\n\nSupported fields for job_completed (proactive callback when a delegated job finishes):\n- source_agent_id: <int> — fire only when this agent's job completed\n- source_agent_slug: <str> — alternate to source_agent_id\n- job_type: \"agentic_session\" — match a specific job type (default: any)\n- outcome: [\"completed\"] | [\"escalated\"] | [\"completed\",\"escalated\"] — default [\"completed\"]\n- min_duration_seconds: <int> — skip very-short jobs (noise filter)\n- thread_filter: {thread_ids: [<int>...]} — restrict to specific threads\n\nSupported fields for calendar_event (fires N minutes before a Google Calendar event starts):\n- window_minutes_before: <int 1-1440> — REQUIRED, fire when an event starts within this window\n- channel_account_ids: [<int>...] — restrict to specific calendar accounts (default: all)\n- keywords: [\"standup\"] — word-boundary match on event title\n- prepare_meet_join: true — pre-invite pool bots to the event (enables unattended Meet join)\n\nincoming_message action fields:\n- action: \"reply_text\" (default, normal agent run) or \"join_voice\" (deterministically join the voice channel resolved from the message — requires send_mode=auto)\n- message_source: \"real\" (default) | \"transcript\" | \"both\" — real messages vs turns during a live call. Transcripts are turns that address the agent.\n\ncalendar_event run-mode field (incoming_message uses `action` instead):\n- run_mode: \"text\" (default) or \"voice\" (join the meeting — requires send_mode=auto)\n- voice: {speak_first: <bool — greet immediately vs stay silent until addressed>, vision_mode: \"off\"|\"on_demand\"|\"continuous_0_3fps\"} — pairs with action=join_voice (incoming_message) or run_mode=voice (calendar_event)"
  11. Changed1 schema field changed
    • changedInput schema / properties / conditions / description
      Previous value: -"Trigger conditions (JSON). Supported fields for incoming_message:\n- keywords: [\"pricing\",\"demo\"] — message must contain keyword(s) (free, no LLM cost)\n- keyword_match: \"any\" (default, OR) or \"all\" (AND)\n- channel_types: [\"telegram\",\"whatsapp\",\"livechat_voice\",\"twilio_voice\",\"telegram_voice\",\"voice\",...] — filter by channel. For voice, use EITHER the three per-channel keys (scoped) OR \"voice\" alone (wildcard matching all three) — mixing them is redundant. Per-channel keys: \"livechat_voice\" (web widget), \"twilio_voice\" (PSTN inbound), \"telegram_voice\" (Telegram p2p calls)\n- context_types: [\"dm\",\"group\",\"channel\",\"livechat\"] — filter by chat type\n- group_mode: \"mentions_only\" or \"questions\" — for group chats\n- channel_account_ids: [\"123\"] — restrict to specific accounts. Only accounts THIS workspace answers: a trigger never fires for another workspace's channel, so create it on an agent there\n- folder_ids: [5,10] — restrict to threads in folders\n- ai_tag_ids: [1,2] — restrict to threads with AI tags\n- ai_filter_ids: [1,2] — semantic intent filters (message matched via embedding similarity, works in noisy groups)\n- ai_filter_mode: \"any\" (default, OR) or \"all\" (AND) — how multiple AI filters combine\n- ai_filters: [{id: 1}, {name: \"...\", description: \"...\"}] — shorthand: reference existing by id or create inline (calls Voyage embedding API). If a filter with the same name already exists, it is reused by id. Prefer referencing existing filters by id when available. Use ai_filters.create + ai_filters.test for fine-tuning before assigning.\n- template: the reply a rule_based agent sends, with no model run. Either a string (\"Hi {from_name}, we open at 9\") or a card object {text, attachments, buttons} — text is required, attachments is a list of file ids (files.upload), buttons is a list of {label, value|url|web_app} carrying exactly ONE target each: value = a reply the bot receives back, url = opens a link (add track: true to count each tap per conversation, readable as analytics_link_clicks_v in analytics.query), web_app = opens a Mini App over https. The string, and a card's text, substitute {from_name}, {message_text}, {channel_type}, {thread_id}, {raw_data}; button labels and targets are sent verbatim. A card with buttons needs send_mode auto — a draft row cannot carry a keyboard. Buttons need a channel that renders them (telegram_bot). A card needs a chat to land in, so it refuses on webhook, schedule and other thread-less triggers where a string still drafts.\n- handoff: {agent_id, task} — only on a rule_based agent's trigger (refused elsewhere). After the rule's deterministic part has actually happened — the template's message delivered, or the agent's script completed — the named agent runs on the same thread, in its own send mode, exactly as its own trigger would run it: the customer's message reaches it as the incoming message, and `task` reaches it as the handoff brief from this rule. The rule stays instant; the thinking — a reminder, a referral code, a personal follow-up — happens behind it. Script plus handoff is how a workspace does something deterministic the platform has no verb for (file the thread, stamp a tag, push a row) and still lets an agent answer, with the deterministic part living in that agent's own script rather than in platform code. `task` substitutes {channel_type} and {thread_id} only; {message_text}, {from_name} and {raw_data} are refused (the sender would be writing the instruction — the message and its sender already reach the target as the incoming message). The target must be an active agentic or claude_channels agent in this workspace (the engines that read the brief). The target's run is a normal trigger run: it holds the thread lock, its own safety gates apply, and its final answer is delivered like any DM reply — a follow-up that should stay silent must call agent.silence. Nothing runs when the message was drafted, refused or failed, when the script failed, when a safety gate has the rule in draft mode, or when the event carries no thread for the target to answer on. A target paused or deleted after the trigger was written does not stop the rule's message: it goes out, and the reason the follow-up did not start is recorded in the rule's activity row (error field) and in the target's activity as an execution_error.\n- contact_states: [\"active\"] — filter by contact state\n- cooldown_seconds: 30 — min gap between runs per thread\n- max_runs_per_thread_per_hour: 5 — rate limit\n- once_per_thread: true — after this trigger completes on a conversation it steps aside there and the next matching trigger answers later messages. For a rule that files / tags / hands off once, not for the agent that holds the conversation.\n- answer_delay_s: 15 — voice pickup only (incoming_call, or incoming_message scoped to a voice channel). Ring the human's own devices this long before the agent answers; if they pick up, the agent stands down. 0/absent = answer immediately. Honoured on WhatsApp and Telegram 1:1 — other voice channels have nothing ringing to wait for and still answer at once.\n- auto_join: true|false — voice pickup, GROUP calls only. Whether the bot enters a matching group call on its own (true) or the call becomes a pending invite an operator accepts (false). OMIT THE KEY to defer to the channel setting (channel_account.state.voice_auto_join_policy, default 'approval'); resolution is trigger-when-present, then channel, then approval, so an explicit false beats a channel set to auto. Absent and false are different answers.\n- chat_ids: [\"-5172634473\"] — voice pickup, Telegram GROUP calls only. Scopes the trigger to specific groups; omit for every group call. Any id spelling works (5172634473, -5172634473, -1005172634473 are the same group). A call whose chat is unknown never satisfies it, so do NOT set this together with 1:1 / Twilio / Telnyx / WhatsApp / Android / LiveChat voice channels or the \"voice\" wildcard: those calls have no chat and the trigger would stop answering them.\n\nSupported fields for job_completed (proactive callback when a delegated job finishes):\n- source_agent_id: <int> — fire only when this agent's job completed\n- source_agent_slug: <str> — alternate to source_agent_id\n- job_type: \"agentic_session\" — match a specific job type (default: any)\n- outcome: [\"completed\"] | [\"escalated\"] | [\"completed\",\"escalated\"] — default [\"completed\"]\n- min_duration_seconds: <int> — skip very-short jobs (noise filter)\n- thread_filter: {thread_ids: [<int>...]} — restrict to specific threads\n\nSupported fields for calendar_event (fires N minutes before a Google Calendar event starts):\n- window_minutes_before: <int 1-1440> — REQUIRED, fire when an event starts within this window\n- channel_account_ids: [<int>...] — restrict to specific calendar accounts (default: all)\n- keywords: [\"standup\"] — word-boundary match on event title\n- prepare_meet_join: true — pre-invite pool bots to the event (enables unattended Meet join)\n\nincoming_message action fields:\n- action: \"reply_text\" (default, normal agent run) or \"join_voice\" (deterministically join the voice channel resolved from the message — requires send_mode=auto)\n- message_source: \"real\" (default) | \"transcript\" | \"both\" — real messages vs turns during a live call. Transcripts are turns that address the agent.\n\ncalendar_event run-mode field (incoming_message uses `action` instead):\n- run_mode: \"text\" (default) or \"voice\" (join the meeting — requires send_mode=auto)\n- voice: {speak_first: <bool — greet immediately vs stay silent until addressed>, vision_mode: \"off\"|\"on_demand\"|\"continuous_0_3fps\"} — pairs with action=join_voice (incoming_message) or run_mode=voice (calendar_event)"New value: +"Trigger conditions (JSON). Supported fields for incoming_message:\n- keywords: [\"pricing\",\"demo\"] — message must contain keyword(s) (free, no LLM cost)\n- keyword_match: \"any\" (default, OR) or \"all\" (AND)\n- channel_types: [\"telegram\",\"whatsapp\",\"livechat_voice\",\"twilio_voice\",\"telegram_voice\",\"voice\",...] — filter by channel. For voice, use EITHER the three per-channel keys (scoped) OR \"voice\" alone (wildcard matching all three) — mixing them is redundant. Per-channel keys: \"livechat_voice\" (web widget), \"twilio_voice\" (PSTN inbound), \"telegram_voice\" (Telegram p2p calls)\n- context_types: [\"dm\",\"group\",\"channel\",\"livechat\"] — filter by chat type\n- group_mode: \"mentions_only\" or \"questions\" — for group chats\n- channel_account_ids: [\"123\"] — restrict to specific accounts. Only accounts THIS workspace answers: a trigger never fires for another workspace's channel, so create it on an agent there\n- folder_ids: [5,10] — restrict to threads in folders\n- ai_tag_ids: [1,2] — restrict to threads with AI tags\n- ai_filter_ids: [1,2] — semantic intent filters (message matched via embedding similarity, works in noisy groups)\n- ai_filter_mode: \"any\" (default, OR) or \"all\" (AND) — how multiple AI filters combine\n- ai_filters: [{id: 1}, {name: \"...\", description: \"...\"}] — shorthand: reference existing by id or create inline (calls Voyage embedding API). If a filter with the same name already exists, it is reused by id. Prefer referencing existing filters by id when available. Use ai_filters.create + ai_filters.test for fine-tuning before assigning.\n- template: the reply a rule_based agent sends, with no model run. Either a string (\"Hi {from_name}, we open at 9\") or a card object {text, attachments, buttons} — text is required, attachments is a list of file ids (files.upload), buttons is a list of {label, value|url|web_app} carrying exactly ONE target each: value = a reply the bot receives back, url = opens a link (add track: true to count each tap per conversation, readable as analytics_link_clicks_v in analytics.query; add tag: <ai_tag id> beside it to put that tag on the CONVERSATION at the tap, so for people, not groups, where any member's tap tags the whole group), web_app = opens a Mini App over https. The string, and a card's text, substitute {from_name}, {message_text}, {channel_type}, {thread_id}, {raw_data}; button labels and targets are sent verbatim. A card with buttons needs send_mode auto — a draft row cannot carry a keyboard. Buttons need a channel that renders them (telegram_bot). A card needs a chat to land in, so it refuses on webhook, schedule and other thread-less triggers where a string still drafts.\n- handoff: {agent_id, task} — only on a rule_based agent's trigger (refused elsewhere). After the rule's deterministic part has actually happened — the template's message delivered, or the agent's script completed — the named agent runs on the same thread, in its own send mode, exactly as its own trigger would run it: the customer's message reaches it as the incoming message, and `task` reaches it as the handoff brief from this rule. The rule stays instant; the thinking — a reminder, a referral code, a personal follow-up — happens behind it. Script plus handoff is how a workspace does something deterministic the platform has no verb for (file the thread, stamp a tag, push a row) and still lets an agent answer, with the deterministic part living in that agent's own script rather than in platform code. `task` substitutes {channel_type} and {thread_id} only; {message_text}, {from_name} and {raw_data} are refused (the sender would be writing the instruction — the message and its sender already reach the target as the incoming message). The target must be an active agentic or claude_channels agent in this workspace (the engines that read the brief). The target's run is a normal trigger run: it holds the thread lock, its own safety gates apply, and its final answer is delivered like any DM reply — a follow-up that should stay silent must call agent.silence. Nothing runs when the message was drafted, refused or failed, when the script failed, when a safety gate has the rule in draft mode, or when the event carries no thread for the target to answer on. A target paused or deleted after the trigger was written does not stop the rule's message: it goes out, and the reason the follow-up did not start is recorded in the rule's activity row (error field) and in the target's activity as an execution_error.\n- contact_states: [\"active\"] — filter by contact state\n- cooldown_seconds: 30 — min gap between runs per thread\n- max_runs_per_thread_per_hour: 5 — rate limit\n- once_per_thread: true — after this trigger completes on a conversation it steps aside there and the next matching trigger answers later messages. For a rule that files / tags / hands off once, not for the agent that holds the conversation.\n- answer_delay_s: 15 — voice pickup only (incoming_call, or incoming_message scoped to a voice channel). Ring the human's own devices this long before the agent answers; if they pick up, the agent stands down. 0/absent = answer immediately. Honoured on WhatsApp and Telegram 1:1 — other voice channels have nothing ringing to wait for and still answer at once.\n- auto_join: true|false — voice pickup, GROUP calls only. Whether the bot enters a matching group call on its own (true) or the call becomes a pending invite an operator accepts (false). OMIT THE KEY to defer to the channel setting (channel_account.state.voice_auto_join_policy, default 'approval'); resolution is trigger-when-present, then channel, then approval, so an explicit false beats a channel set to auto. Absent and false are different answers.\n- chat_ids: [\"-5172634473\"] — voice pickup, Telegram GROUP calls only. Scopes the trigger to specific groups; omit for every group call. Any id spelling works (5172634473, -5172634473, -1005172634473 are the same group). A call whose chat is unknown never satisfies it, so do NOT set this together with 1:1 / Twilio / Telnyx / WhatsApp / Android / LiveChat voice channels or the \"voice\" wildcard: those calls have no chat and the trigger would stop answering them.\n\nSupported fields for job_completed (proactive callback when a delegated job finishes):\n- source_agent_id: <int> — fire only when this agent's job completed\n- source_agent_slug: <str> — alternate to source_agent_id\n- job_type: \"agentic_session\" — match a specific job type (default: any)\n- outcome: [\"completed\"] | [\"escalated\"] | [\"completed\",\"escalated\"] — default [\"completed\"]\n- min_duration_seconds: <int> — skip very-short jobs (noise filter)\n- thread_filter: {thread_ids: [<int>...]} — restrict to specific threads\n\nSupported fields for calendar_event (fires N minutes before a Google Calendar event starts):\n- window_minutes_before: <int 1-1440> — REQUIRED, fire when an event starts within this window\n- channel_account_ids: [<int>...] — restrict to specific calendar accounts (default: all)\n- keywords: [\"standup\"] — word-boundary match on event title\n- prepare_meet_join: true — pre-invite pool bots to the event (enables unattended Meet join)\n\nincoming_message action fields:\n- action: \"reply_text\" (default, normal agent run) or \"join_voice\" (deterministically join the voice channel resolved from the message — requires send_mode=auto)\n- message_source: \"real\" (default) | \"transcript\" | \"both\" — real messages vs turns during a live call. Transcripts are turns that address the agent.\n\ncalendar_event run-mode field (incoming_message uses `action` instead):\n- run_mode: \"text\" (default) or \"voice\" (join the meeting — requires send_mode=auto)\n- voice: {speak_first: <bool — greet immediately vs stay silent until addressed>, vision_mode: \"off\"|\"on_demand\"|\"continuous_0_3fps\"} — pairs with action=join_voice (incoming_message) or run_mode=voice (calendar_event)"
  12. Changed1 schema field changed
    • changedInput schema / properties / conditions / description
      Previous value: -"Trigger conditions (JSON). Supported fields for incoming_message:\n- keywords: [\"pricing\",\"demo\"] — message must contain keyword(s) (free, no LLM cost)\n- keyword_match: \"any\" (default, OR) or \"all\" (AND)\n- channel_types: [\"telegram\",\"whatsapp\",\"livechat_voice\",\"twilio_voice\",\"telegram_voice\",\"voice\",...] — filter by channel. For voice, use EITHER the three per-channel keys (scoped) OR \"voice\" alone (wildcard matching all three) — mixing them is redundant. Per-channel keys: \"livechat_voice\" (web widget), \"twilio_voice\" (PSTN inbound), \"telegram_voice\" (Telegram p2p calls)\n- context_types: [\"dm\",\"group\",\"channel\",\"livechat\"] — filter by chat type\n- group_mode: \"mentions_only\" or \"questions\" — for group chats\n- channel_account_ids: [\"123\"] — restrict to specific accounts\n- folder_ids: [5,10] — restrict to threads in folders\n- ai_tag_ids: [1,2] — restrict to threads with AI tags\n- ai_filter_ids: [1,2] — semantic intent filters (message matched via embedding similarity, works in noisy groups)\n- ai_filter_mode: \"any\" (default, OR) or \"all\" (AND) — how multiple AI filters combine\n- ai_filters: [{id: 1}, {name: \"...\", description: \"...\"}] — shorthand: reference existing by id or create inline (calls Voyage embedding API). If a filter with the same name already exists, it is reused by id. Prefer referencing existing filters by id when available. Use ai_filters.create + ai_filters.test for fine-tuning before assigning.\n- template: the reply a rule_based agent sends, with no model run. Either a string (\"Hi {from_name}, we open at 9\") or a card object {text, attachments, buttons} — text is required, attachments is a list of file ids (files.upload), buttons is a list of {label, value|url|web_app} carrying exactly ONE target each: value = a reply the bot receives back, url = opens a link (add track: true to count each tap per conversation, readable as analytics_link_clicks_v in analytics.query), web_app = opens a Mini App over https. The string, and a card's text, substitute {from_name}, {message_text}, {channel_type}, {thread_id}, {raw_data}; button labels and targets are sent verbatim. A card with buttons needs send_mode auto — a draft row cannot carry a keyboard. Buttons need a channel that renders them (telegram_bot). A card needs a chat to land in, so it refuses on webhook, schedule and other thread-less triggers where a string still drafts.\n- handoff: {agent_id, task} — only on a rule_based agent's trigger (refused elsewhere). After the rule's deterministic part has actually happened — the template's message delivered, or the agent's script completed — the named agent runs on the same thread, in its own send mode, exactly as its own trigger would run it: the customer's message reaches it as the incoming message, and `task` reaches it as the handoff brief from this rule. The rule stays instant; the thinking — a reminder, a referral code, a personal follow-up — happens behind it. Script plus handoff is how a workspace does something deterministic the platform has no verb for (file the thread, stamp a tag, push a row) and still lets an agent answer, with the deterministic part living in that agent's own script rather than in platform code. `task` substitutes {channel_type} and {thread_id} only; {message_text}, {from_name} and {raw_data} are refused (the sender would be writing the instruction — the message and its sender already reach the target as the incoming message). The target must be an active agentic or claude_channels agent in this workspace (the engines that read the brief). The target's run is a normal trigger run: it holds the thread lock, its own safety gates apply, and its final answer is delivered like any DM reply — a follow-up that should stay silent must call agent.silence. Nothing runs when the message was drafted, refused or failed, when the script failed, when a safety gate has the rule in draft mode, or when the event carries no thread for the target to answer on. A target paused or deleted after the trigger was written does not stop the rule's message: it goes out, and the reason the follow-up did not start is recorded in the rule's activity row (error field) and in the target's activity as an execution_error.\n- contact_states: [\"active\"] — filter by contact state\n- cooldown_seconds: 30 — min gap between runs per thread\n- max_runs_per_thread_per_hour: 5 — rate limit\n- once_per_thread: true — after this trigger completes on a conversation it steps aside there and the next matching trigger answers later messages. For a rule that files / tags / hands off once, not for the agent that holds the conversation.\n- answer_delay_s: 15 — voice pickup only (incoming_call, or incoming_message scoped to a voice channel). Ring the human's own devices this long before the agent answers; if they pick up, the agent stands down. 0/absent = answer immediately. Honoured on WhatsApp and Telegram 1:1 — other voice channels have nothing ringing to wait for and still answer at once.\n- auto_join: true|false — voice pickup, GROUP calls only. Whether the bot enters a matching group call on its own (true) or the call becomes a pending invite an operator accepts (false). OMIT THE KEY to defer to the channel setting (channel_account.state.voice_auto_join_policy, default 'approval'); resolution is trigger-when-present, then channel, then approval, so an explicit false beats a channel set to auto. Absent and false are different answers.\n- chat_ids: [\"-5172634473\"] — voice pickup, Telegram GROUP calls only. Scopes the trigger to specific groups; omit for every group call. Any id spelling works (5172634473, -5172634473, -1005172634473 are the same group). A call whose chat is unknown never satisfies it, so do NOT set this together with 1:1 / Twilio / Telnyx / WhatsApp / Android / LiveChat voice channels or the \"voice\" wildcard: those calls have no chat and the trigger would stop answering them.\n\nSupported fields for job_completed (proactive callback when a delegated job finishes):\n- source_agent_id: <int> — fire only when this agent's job completed\n- source_agent_slug: <str> — alternate to source_agent_id\n- job_type: \"agentic_session\" — match a specific job type (default: any)\n- outcome: [\"completed\"] | [\"escalated\"] | [\"completed\",\"escalated\"] — default [\"completed\"]\n- min_duration_seconds: <int> — skip very-short jobs (noise filter)\n- thread_filter: {thread_ids: [<int>...]} — restrict to specific threads\n\nSupported fields for calendar_event (fires N minutes before a Google Calendar event starts):\n- window_minutes_before: <int 1-1440> — REQUIRED, fire when an event starts within this window\n- channel_account_ids: [<int>...] — restrict to specific calendar accounts (default: all)\n- keywords: [\"standup\"] — word-boundary match on event title\n- prepare_meet_join: true — pre-invite pool bots to the event (enables unattended Meet join)\n\nincoming_message action fields:\n- action: \"reply_text\" (default, normal agent run) or \"join_voice\" (deterministically join the voice channel resolved from the message — requires send_mode=auto)\n- message_source: \"real\" (default) | \"transcript\" | \"both\" — real messages vs turns during a live call. Transcripts are turns that address the agent.\n\ncalendar_event run-mode field (incoming_message uses `action` instead):\n- run_mode: \"text\" (default) or \"voice\" (join the meeting — requires send_mode=auto)\n- voice: {speak_first: <bool — greet immediately vs stay silent until addressed>, vision_mode: \"off\"|\"on_demand\"|\"continuous_0_3fps\"} — pairs with action=join_voice (incoming_message) or run_mode=voice (calendar_event)"New value: +"Trigger conditions (JSON). Supported fields for incoming_message:\n- keywords: [\"pricing\",\"demo\"] — message must contain keyword(s) (free, no LLM cost)\n- keyword_match: \"any\" (default, OR) or \"all\" (AND)\n- channel_types: [\"telegram\",\"whatsapp\",\"livechat_voice\",\"twilio_voice\",\"telegram_voice\",\"voice\",...] — filter by channel. For voice, use EITHER the three per-channel keys (scoped) OR \"voice\" alone (wildcard matching all three) — mixing them is redundant. Per-channel keys: \"livechat_voice\" (web widget), \"twilio_voice\" (PSTN inbound), \"telegram_voice\" (Telegram p2p calls)\n- context_types: [\"dm\",\"group\",\"channel\",\"livechat\"] — filter by chat type\n- group_mode: \"mentions_only\" or \"questions\" — for group chats\n- channel_account_ids: [\"123\"] — restrict to specific accounts. Only accounts THIS workspace answers: a trigger never fires for another workspace's channel, so create it on an agent there\n- folder_ids: [5,10] — restrict to threads in folders\n- ai_tag_ids: [1,2] — restrict to threads with AI tags\n- ai_filter_ids: [1,2] — semantic intent filters (message matched via embedding similarity, works in noisy groups)\n- ai_filter_mode: \"any\" (default, OR) or \"all\" (AND) — how multiple AI filters combine\n- ai_filters: [{id: 1}, {name: \"...\", description: \"...\"}] — shorthand: reference existing by id or create inline (calls Voyage embedding API). If a filter with the same name already exists, it is reused by id. Prefer referencing existing filters by id when available. Use ai_filters.create + ai_filters.test for fine-tuning before assigning.\n- template: the reply a rule_based agent sends, with no model run. Either a string (\"Hi {from_name}, we open at 9\") or a card object {text, attachments, buttons} — text is required, attachments is a list of file ids (files.upload), buttons is a list of {label, value|url|web_app} carrying exactly ONE target each: value = a reply the bot receives back, url = opens a link (add track: true to count each tap per conversation, readable as analytics_link_clicks_v in analytics.query), web_app = opens a Mini App over https. The string, and a card's text, substitute {from_name}, {message_text}, {channel_type}, {thread_id}, {raw_data}; button labels and targets are sent verbatim. A card with buttons needs send_mode auto — a draft row cannot carry a keyboard. Buttons need a channel that renders them (telegram_bot). A card needs a chat to land in, so it refuses on webhook, schedule and other thread-less triggers where a string still drafts.\n- handoff: {agent_id, task} — only on a rule_based agent's trigger (refused elsewhere). After the rule's deterministic part has actually happened — the template's message delivered, or the agent's script completed — the named agent runs on the same thread, in its own send mode, exactly as its own trigger would run it: the customer's message reaches it as the incoming message, and `task` reaches it as the handoff brief from this rule. The rule stays instant; the thinking — a reminder, a referral code, a personal follow-up — happens behind it. Script plus handoff is how a workspace does something deterministic the platform has no verb for (file the thread, stamp a tag, push a row) and still lets an agent answer, with the deterministic part living in that agent's own script rather than in platform code. `task` substitutes {channel_type} and {thread_id} only; {message_text}, {from_name} and {raw_data} are refused (the sender would be writing the instruction — the message and its sender already reach the target as the incoming message). The target must be an active agentic or claude_channels agent in this workspace (the engines that read the brief). The target's run is a normal trigger run: it holds the thread lock, its own safety gates apply, and its final answer is delivered like any DM reply — a follow-up that should stay silent must call agent.silence. Nothing runs when the message was drafted, refused or failed, when the script failed, when a safety gate has the rule in draft mode, or when the event carries no thread for the target to answer on. A target paused or deleted after the trigger was written does not stop the rule's message: it goes out, and the reason the follow-up did not start is recorded in the rule's activity row (error field) and in the target's activity as an execution_error.\n- contact_states: [\"active\"] — filter by contact state\n- cooldown_seconds: 30 — min gap between runs per thread\n- max_runs_per_thread_per_hour: 5 — rate limit\n- once_per_thread: true — after this trigger completes on a conversation it steps aside there and the next matching trigger answers later messages. For a rule that files / tags / hands off once, not for the agent that holds the conversation.\n- answer_delay_s: 15 — voice pickup only (incoming_call, or incoming_message scoped to a voice channel). Ring the human's own devices this long before the agent answers; if they pick up, the agent stands down. 0/absent = answer immediately. Honoured on WhatsApp and Telegram 1:1 — other voice channels have nothing ringing to wait for and still answer at once.\n- auto_join: true|false — voice pickup, GROUP calls only. Whether the bot enters a matching group call on its own (true) or the call becomes a pending invite an operator accepts (false). OMIT THE KEY to defer to the channel setting (channel_account.state.voice_auto_join_policy, default 'approval'); resolution is trigger-when-present, then channel, then approval, so an explicit false beats a channel set to auto. Absent and false are different answers.\n- chat_ids: [\"-5172634473\"] — voice pickup, Telegram GROUP calls only. Scopes the trigger to specific groups; omit for every group call. Any id spelling works (5172634473, -5172634473, -1005172634473 are the same group). A call whose chat is unknown never satisfies it, so do NOT set this together with 1:1 / Twilio / Telnyx / WhatsApp / Android / LiveChat voice channels or the \"voice\" wildcard: those calls have no chat and the trigger would stop answering them.\n\nSupported fields for job_completed (proactive callback when a delegated job finishes):\n- source_agent_id: <int> — fire only when this agent's job completed\n- source_agent_slug: <str> — alternate to source_agent_id\n- job_type: \"agentic_session\" — match a specific job type (default: any)\n- outcome: [\"completed\"] | [\"escalated\"] | [\"completed\",\"escalated\"] — default [\"completed\"]\n- min_duration_seconds: <int> — skip very-short jobs (noise filter)\n- thread_filter: {thread_ids: [<int>...]} — restrict to specific threads\n\nSupported fields for calendar_event (fires N minutes before a Google Calendar event starts):\n- window_minutes_before: <int 1-1440> — REQUIRED, fire when an event starts within this window\n- channel_account_ids: [<int>...] — restrict to specific calendar accounts (default: all)\n- keywords: [\"standup\"] — word-boundary match on event title\n- prepare_meet_join: true — pre-invite pool bots to the event (enables unattended Meet join)\n\nincoming_message action fields:\n- action: \"reply_text\" (default, normal agent run) or \"join_voice\" (deterministically join the voice channel resolved from the message — requires send_mode=auto)\n- message_source: \"real\" (default) | \"transcript\" | \"both\" — real messages vs turns during a live call. Transcripts are turns that address the agent.\n\ncalendar_event run-mode field (incoming_message uses `action` instead):\n- run_mode: \"text\" (default) or \"voice\" (join the meeting — requires send_mode=auto)\n- voice: {speak_first: <bool — greet immediately vs stay silent until addressed>, vision_mode: \"off\"|\"on_demand\"|\"continuous_0_3fps\"} — pairs with action=join_voice (incoming_message) or run_mode=voice (calendar_event)"
  13. Changed1 schema field changed
    • changedInput schema / properties / conditions / description
      Previous value: -"Trigger conditions (JSON). Supported fields for incoming_message:\n- keywords: [\"pricing\",\"demo\"] — message must contain keyword(s) (free, no LLM cost)\n- keyword_match: \"any\" (default, OR) or \"all\" (AND)\n- channel_types: [\"telegram\",\"whatsapp\",\"livechat_voice\",\"twilio_voice\",\"telegram_voice\",\"voice\",...] — filter by channel. For voice, use EITHER the three per-channel keys (scoped) OR \"voice\" alone (wildcard matching all three) — mixing them is redundant. Per-channel keys: \"livechat_voice\" (web widget), \"twilio_voice\" (PSTN inbound), \"telegram_voice\" (Telegram p2p calls)\n- context_types: [\"dm\",\"group\",\"channel\",\"livechat\"] — filter by chat type\n- group_mode: \"mentions_only\" or \"questions\" — for group chats\n- channel_account_ids: [\"123\"] — restrict to specific accounts\n- folder_ids: [5,10] — restrict to threads in folders\n- ai_tag_ids: [1,2] — restrict to threads with AI tags\n- ai_filter_ids: [1,2] — semantic intent filters (message matched via embedding similarity, works in noisy groups)\n- ai_filter_mode: \"any\" (default, OR) or \"all\" (AND) — how multiple AI filters combine\n- ai_filters: [{id: 1}, {name: \"...\", description: \"...\"}] — shorthand: reference existing by id or create inline (calls Voyage embedding API). If a filter with the same name already exists, it is reused by id. Prefer referencing existing filters by id when available. Use ai_filters.create + ai_filters.test for fine-tuning before assigning.\n- template: the reply a rule_based agent sends, with no model run. Either a string (\"Hi {from_name}, we open at 9\") or a card object {text, attachments, buttons} — text is required, attachments is a list of file ids (files.upload), buttons is a list of {label, value|url|web_app} carrying exactly ONE target each: value = a reply the bot receives back, url = opens a link, web_app = opens a Mini App over https. The string, and a card's text, substitute {from_name}, {message_text}, {channel_type}, {thread_id}, {raw_data}; button labels and targets are sent verbatim. A card with buttons needs send_mode auto — a draft row cannot carry a keyboard. Buttons need a channel that renders them (telegram_bot). A card needs a chat to land in, so it refuses on webhook, schedule and other thread-less triggers where a string still drafts.\n- handoff: {agent_id, task} — only on a rule_based agent's trigger (refused elsewhere). After the rule's deterministic part has actually happened — the template's message delivered, or the agent's script completed — the named agent runs on the same thread, in its own send mode, exactly as its own trigger would run it: the customer's message reaches it as the incoming message, and `task` reaches it as the handoff brief from this rule. The rule stays instant; the thinking — a reminder, a referral code, a personal follow-up — happens behind it. Script plus handoff is how a workspace does something deterministic the platform has no verb for (file the thread, stamp a tag, push a row) and still lets an agent answer, with the deterministic part living in that agent's own script rather than in platform code. `task` substitutes {channel_type} and {thread_id} only; {message_text}, {from_name} and {raw_data} are refused (the sender would be writing the instruction — the message and its sender already reach the target as the incoming message). The target must be an active agentic or claude_channels agent in this workspace (the engines that read the brief). The target's run is a normal trigger run: it holds the thread lock, its own safety gates apply, and its final answer is delivered like any DM reply — a follow-up that should stay silent must call agent.silence. Nothing runs when the message was drafted, refused or failed, when the script failed, when a safety gate has the rule in draft mode, or when the event carries no thread for the target to answer on. A target paused or deleted after the trigger was written does not stop the rule's message: it goes out, and the reason the follow-up did not start is recorded in the rule's activity row (error field) and in the target's activity as an execution_error.\n- contact_states: [\"active\"] — filter by contact state\n- cooldown_seconds: 30 — min gap between runs per thread\n- max_runs_per_thread_per_hour: 5 — rate limit\n- once_per_thread: true — after this trigger completes on a conversation it steps aside there and the next matching trigger answers later messages. For a rule that files / tags / hands off once, not for the agent that holds the conversation.\n- answer_delay_s: 15 — voice pickup only (incoming_call, or incoming_message scoped to a voice channel). Ring the human's own devices this long before the agent answers; if they pick up, the agent stands down. 0/absent = answer immediately. Honoured on WhatsApp and Telegram 1:1 — other voice channels have nothing ringing to wait for and still answer at once.\n- auto_join: true|false — voice pickup, GROUP calls only. Whether the bot enters a matching group call on its own (true) or the call becomes a pending invite an operator accepts (false). OMIT THE KEY to defer to the channel setting (channel_account.state.voice_auto_join_policy, default 'approval'); resolution is trigger-when-present, then channel, then approval, so an explicit false beats a channel set to auto. Absent and false are different answers.\n- chat_ids: [\"-5172634473\"] — voice pickup, Telegram GROUP calls only. Scopes the trigger to specific groups; omit for every group call. Any id spelling works (5172634473, -5172634473, -1005172634473 are the same group). A call whose chat is unknown never satisfies it, so do NOT set this together with 1:1 / Twilio / Telnyx / WhatsApp / Android / LiveChat voice channels or the \"voice\" wildcard: those calls have no chat and the trigger would stop answering them.\n\nSupported fields for job_completed (proactive callback when a delegated job finishes):\n- source_agent_id: <int> — fire only when this agent's job completed\n- source_agent_slug: <str> — alternate to source_agent_id\n- job_type: \"agentic_session\" — match a specific job type (default: any)\n- outcome: [\"completed\"] | [\"escalated\"] | [\"completed\",\"escalated\"] — default [\"completed\"]\n- min_duration_seconds: <int> — skip very-short jobs (noise filter)\n- thread_filter: {thread_ids: [<int>...]} — restrict to specific threads\n\nSupported fields for calendar_event (fires N minutes before a Google Calendar event starts):\n- window_minutes_before: <int 1-1440> — REQUIRED, fire when an event starts within this window\n- channel_account_ids: [<int>...] — restrict to specific calendar accounts (default: all)\n- keywords: [\"standup\"] — word-boundary match on event title\n- prepare_meet_join: true — pre-invite pool bots to the event (enables unattended Meet join)\n\nincoming_message action fields:\n- action: \"reply_text\" (default, normal agent run) or \"join_voice\" (deterministically join the voice channel resolved from the message — requires send_mode=auto)\n- message_source: \"real\" (default) | \"transcript\" | \"both\" — real messages vs turns during a live call. Transcripts are turns that address the agent.\n\ncalendar_event run-mode field (incoming_message uses `action` instead):\n- run_mode: \"text\" (default) or \"voice\" (join the meeting — requires send_mode=auto)\n- voice: {speak_first: <bool — greet immediately vs stay silent until addressed>, vision_mode: \"off\"|\"on_demand\"|\"continuous_0_3fps\"} — pairs with action=join_voice (incoming_message) or run_mode=voice (calendar_event)"New value: +"Trigger conditions (JSON). Supported fields for incoming_message:\n- keywords: [\"pricing\",\"demo\"] — message must contain keyword(s) (free, no LLM cost)\n- keyword_match: \"any\" (default, OR) or \"all\" (AND)\n- channel_types: [\"telegram\",\"whatsapp\",\"livechat_voice\",\"twilio_voice\",\"telegram_voice\",\"voice\",...] — filter by channel. For voice, use EITHER the three per-channel keys (scoped) OR \"voice\" alone (wildcard matching all three) — mixing them is redundant. Per-channel keys: \"livechat_voice\" (web widget), \"twilio_voice\" (PSTN inbound), \"telegram_voice\" (Telegram p2p calls)\n- context_types: [\"dm\",\"group\",\"channel\",\"livechat\"] — filter by chat type\n- group_mode: \"mentions_only\" or \"questions\" — for group chats\n- channel_account_ids: [\"123\"] — restrict to specific accounts\n- folder_ids: [5,10] — restrict to threads in folders\n- ai_tag_ids: [1,2] — restrict to threads with AI tags\n- ai_filter_ids: [1,2] — semantic intent filters (message matched via embedding similarity, works in noisy groups)\n- ai_filter_mode: \"any\" (default, OR) or \"all\" (AND) — how multiple AI filters combine\n- ai_filters: [{id: 1}, {name: \"...\", description: \"...\"}] — shorthand: reference existing by id or create inline (calls Voyage embedding API). If a filter with the same name already exists, it is reused by id. Prefer referencing existing filters by id when available. Use ai_filters.create + ai_filters.test for fine-tuning before assigning.\n- template: the reply a rule_based agent sends, with no model run. Either a string (\"Hi {from_name}, we open at 9\") or a card object {text, attachments, buttons} — text is required, attachments is a list of file ids (files.upload), buttons is a list of {label, value|url|web_app} carrying exactly ONE target each: value = a reply the bot receives back, url = opens a link (add track: true to count each tap per conversation, readable as analytics_link_clicks_v in analytics.query), web_app = opens a Mini App over https. The string, and a card's text, substitute {from_name}, {message_text}, {channel_type}, {thread_id}, {raw_data}; button labels and targets are sent verbatim. A card with buttons needs send_mode auto — a draft row cannot carry a keyboard. Buttons need a channel that renders them (telegram_bot). A card needs a chat to land in, so it refuses on webhook, schedule and other thread-less triggers where a string still drafts.\n- handoff: {agent_id, task} — only on a rule_based agent's trigger (refused elsewhere). After the rule's deterministic part has actually happened — the template's message delivered, or the agent's script completed — the named agent runs on the same thread, in its own send mode, exactly as its own trigger would run it: the customer's message reaches it as the incoming message, and `task` reaches it as the handoff brief from this rule. The rule stays instant; the thinking — a reminder, a referral code, a personal follow-up — happens behind it. Script plus handoff is how a workspace does something deterministic the platform has no verb for (file the thread, stamp a tag, push a row) and still lets an agent answer, with the deterministic part living in that agent's own script rather than in platform code. `task` substitutes {channel_type} and {thread_id} only; {message_text}, {from_name} and {raw_data} are refused (the sender would be writing the instruction — the message and its sender already reach the target as the incoming message). The target must be an active agentic or claude_channels agent in this workspace (the engines that read the brief). The target's run is a normal trigger run: it holds the thread lock, its own safety gates apply, and its final answer is delivered like any DM reply — a follow-up that should stay silent must call agent.silence. Nothing runs when the message was drafted, refused or failed, when the script failed, when a safety gate has the rule in draft mode, or when the event carries no thread for the target to answer on. A target paused or deleted after the trigger was written does not stop the rule's message: it goes out, and the reason the follow-up did not start is recorded in the rule's activity row (error field) and in the target's activity as an execution_error.\n- contact_states: [\"active\"] — filter by contact state\n- cooldown_seconds: 30 — min gap between runs per thread\n- max_runs_per_thread_per_hour: 5 — rate limit\n- once_per_thread: true — after this trigger completes on a conversation it steps aside there and the next matching trigger answers later messages. For a rule that files / tags / hands off once, not for the agent that holds the conversation.\n- answer_delay_s: 15 — voice pickup only (incoming_call, or incoming_message scoped to a voice channel). Ring the human's own devices this long before the agent answers; if they pick up, the agent stands down. 0/absent = answer immediately. Honoured on WhatsApp and Telegram 1:1 — other voice channels have nothing ringing to wait for and still answer at once.\n- auto_join: true|false — voice pickup, GROUP calls only. Whether the bot enters a matching group call on its own (true) or the call becomes a pending invite an operator accepts (false). OMIT THE KEY to defer to the channel setting (channel_account.state.voice_auto_join_policy, default 'approval'); resolution is trigger-when-present, then channel, then approval, so an explicit false beats a channel set to auto. Absent and false are different answers.\n- chat_ids: [\"-5172634473\"] — voice pickup, Telegram GROUP calls only. Scopes the trigger to specific groups; omit for every group call. Any id spelling works (5172634473, -5172634473, -1005172634473 are the same group). A call whose chat is unknown never satisfies it, so do NOT set this together with 1:1 / Twilio / Telnyx / WhatsApp / Android / LiveChat voice channels or the \"voice\" wildcard: those calls have no chat and the trigger would stop answering them.\n\nSupported fields for job_completed (proactive callback when a delegated job finishes):\n- source_agent_id: <int> — fire only when this agent's job completed\n- source_agent_slug: <str> — alternate to source_agent_id\n- job_type: \"agentic_session\" — match a specific job type (default: any)\n- outcome: [\"completed\"] | [\"escalated\"] | [\"completed\",\"escalated\"] — default [\"completed\"]\n- min_duration_seconds: <int> — skip very-short jobs (noise filter)\n- thread_filter: {thread_ids: [<int>...]} — restrict to specific threads\n\nSupported fields for calendar_event (fires N minutes before a Google Calendar event starts):\n- window_minutes_before: <int 1-1440> — REQUIRED, fire when an event starts within this window\n- channel_account_ids: [<int>...] — restrict to specific calendar accounts (default: all)\n- keywords: [\"standup\"] — word-boundary match on event title\n- prepare_meet_join: true — pre-invite pool bots to the event (enables unattended Meet join)\n\nincoming_message action fields:\n- action: \"reply_text\" (default, normal agent run) or \"join_voice\" (deterministically join the voice channel resolved from the message — requires send_mode=auto)\n- message_source: \"real\" (default) | \"transcript\" | \"both\" — real messages vs turns during a live call. Transcripts are turns that address the agent.\n\ncalendar_event run-mode field (incoming_message uses `action` instead):\n- run_mode: \"text\" (default) or \"voice\" (join the meeting — requires send_mode=auto)\n- voice: {speak_first: <bool — greet immediately vs stay silent until addressed>, vision_mode: \"off\"|\"on_demand\"|\"continuous_0_3fps\"} — pairs with action=join_voice (incoming_message) or run_mode=voice (calendar_event)"
  14. Changed1 schema field changed
    • addedInput schema / properties / in_workspace
      Added value: +{
      +  "description": "Run this one call in this workspace id instead of the session's. Nothing is stored; other sessions are not affected.",
      +  "type": "integer"
      +}
  15. Added
  16. Removed
  17. Changed1 schema field changed
    • changedInput schema / properties / conditions / description
      Previous value: -"Trigger conditions (JSON). Supported fields for incoming_message:\n- keywords: [\"pricing\",\"demo\"] — message must contain keyword(s) (free, no LLM cost)\n- keyword_match: \"any\" (default, OR) or \"all\" (AND)\n- channel_types: [\"telegram\",\"whatsapp\",\"livechat_voice\",\"twilio_voice\",\"telegram_voice\",\"voice\",...] — filter by channel. For voice, use EITHER the three per-channel keys (scoped) OR \"voice\" alone (wildcard matching all three) — mixing them is redundant. Per-channel keys: \"livechat_voice\" (web widget), \"twilio_voice\" (PSTN inbound), \"telegram_voice\" (Telegram p2p calls)\n- context_types: [\"dm\",\"group\",\"channel\",\"livechat\"] — filter by chat type\n- group_mode: \"mentions_only\" or \"questions\" — for group chats\n- channel_account_ids: [\"123\"] — restrict to specific accounts\n- folder_ids: [5,10] — restrict to threads in folders\n- ai_tag_ids: [1,2] — restrict to threads with AI tags\n- ai_filter_ids: [1,2] — semantic intent filters (message matched via embedding similarity, works in noisy groups)\n- ai_filter_mode: \"any\" (default, OR) or \"all\" (AND) — how multiple AI filters combine\n- ai_filters: [{id: 1}, {name: \"...\", description: \"...\"}] — shorthand: reference existing by id or create inline (calls Voyage embedding API). If a filter with the same name already exists, it is reused by id. Prefer referencing existing filters by id when available. Use ai_filters.create + ai_filters.test for fine-tuning before assigning.\n- contact_states: [\"active\"] — filter by contact state\n- cooldown_seconds: 30 — min gap between runs per thread\n- max_runs_per_thread_per_hour: 5 — rate limit\n\nSupported fields for job_completed (proactive callback when a delegated job finishes):\n- source_agent_id: <int> — fire only when this agent's job completed\n- source_agent_slug: <str> — alternate to source_agent_id\n- job_type: \"agentic_session\" — match a specific job type (default: any)\n- outcome: [\"completed\"] | [\"escalated\"] | [\"completed\",\"escalated\"] — default [\"completed\"]\n- min_duration_seconds: <int> — skip very-short jobs (noise filter)\n- thread_filter: {thread_ids: [<int>...]} — restrict to specific threads\n\nSupported fields for calendar_event (fires N minutes before a Google Calendar event starts):\n- window_minutes_before: <int 1-1440> — REQUIRED, fire when an event starts within this window\n- channel_account_ids: [<int>...] — restrict to specific calendar accounts (default: all)\n- keywords: [\"standup\"] — word-boundary match on event title\n- prepare_meet_join: true — pre-invite pool bots to the event (enables unattended Meet join)\n\nGeneric run-mode fields (incoming_message AND calendar_event):\n- run_mode: \"text\" (default, normal agent run) or \"voice\" (deterministically join the meeting/call resolved from the event or message — requires send_mode=auto)\n- voice: {speak_first: <bool — greet immediately vs stay silent until addressed>, vision_mode: \"off\"|\"on_demand\"|\"continuous_0_3fps\"}"New value: +"Trigger conditions (JSON). Supported fields for incoming_message:\n- keywords: [\"pricing\",\"demo\"] — message must contain keyword(s) (free, no LLM cost)\n- keyword_match: \"any\" (default, OR) or \"all\" (AND)\n- channel_types: [\"telegram\",\"whatsapp\",\"livechat_voice\",\"twilio_voice\",\"telegram_voice\",\"voice\",...] — filter by channel. For voice, use EITHER the three per-channel keys (scoped) OR \"voice\" alone (wildcard matching all three) — mixing them is redundant. Per-channel keys: \"livechat_voice\" (web widget), \"twilio_voice\" (PSTN inbound), \"telegram_voice\" (Telegram p2p calls)\n- context_types: [\"dm\",\"group\",\"channel\",\"livechat\"] — filter by chat type\n- group_mode: \"mentions_only\" or \"questions\" — for group chats\n- channel_account_ids: [\"123\"] — restrict to specific accounts\n- folder_ids: [5,10] — restrict to threads in folders\n- ai_tag_ids: [1,2] — restrict to threads with AI tags\n- ai_filter_ids: [1,2] — semantic intent filters (message matched via embedding similarity, works in noisy groups)\n- ai_filter_mode: \"any\" (default, OR) or \"all\" (AND) — how multiple AI filters combine\n- ai_filters: [{id: 1}, {name: \"...\", description: \"...\"}] — shorthand: reference existing by id or create inline (calls Voyage embedding API). If a filter with the same name already exists, it is reused by id. Prefer referencing existing filters by id when available. Use ai_filters.create + ai_filters.test for fine-tuning before assigning.\n- contact_states: [\"active\"] — filter by contact state\n- cooldown_seconds: 30 — min gap between runs per thread\n- max_runs_per_thread_per_hour: 5 — rate limit\n- answer_delay_s: 15 — voice pickup only (incoming_call, or incoming_message scoped to a voice channel). Ring the human's own devices this long before the agent answers; if they pick up, the agent stands down. 0/absent = answer immediately. Honoured on WhatsApp and Telegram 1:1 — other voice channels have nothing ringing to wait for and still answer at once.\n\nSupported fields for job_completed (proactive callback when a delegated job finishes):\n- source_agent_id: <int> — fire only when this agent's job completed\n- source_agent_slug: <str> — alternate to source_agent_id\n- job_type: \"agentic_session\" — match a specific job type (default: any)\n- outcome: [\"completed\"] | [\"escalated\"] | [\"completed\",\"escalated\"] — default [\"completed\"]\n- min_duration_seconds: <int> — skip very-short jobs (noise filter)\n- thread_filter: {thread_ids: [<int>...]} — restrict to specific threads\n\nSupported fields for calendar_event (fires N minutes before a Google Calendar event starts):\n- window_minutes_before: <int 1-1440> — REQUIRED, fire when an event starts within this window\n- channel_account_ids: [<int>...] — restrict to specific calendar accounts (default: all)\n- keywords: [\"standup\"] — word-boundary match on event title\n- prepare_meet_join: true — pre-invite pool bots to the event (enables unattended Meet join)\n\nGeneric run-mode fields (incoming_message AND calendar_event):\n- run_mode: \"text\" (default, normal agent run) or \"voice\" (deterministically join the meeting/call resolved from the event or message — requires send_mode=auto)\n- voice: {speak_first: <bool — greet immediately vs stay silent until addressed>, vision_mode: \"off\"|\"on_demand\"|\"continuous_0_3fps\"}"
  18. Changed2 schema fields changed
    • changedInput schema / properties / trigger_type / description
      Previous value: -"Type of trigger: 'incoming_message', 'incoming_call', 'schedule', 'webhook', 'event', 'blockchain_event', 'job_completed', or 'calendar_event'"New value: +"Type of trigger: 'incoming_message', 'incoming_call', 'schedule', 'webhook', 'event', 'blockchain_event', 'job_completed', 'calendar_event', or 'lead_captured'"
    • changedInput schema / properties / trigger_type / enum
      Previous value: -[
      -  "incoming_message",
      -  "incoming_call",
      -  "schedule",
      -  "webhook",
      -  "event",
      -  "blockchain_event",
      -  "job_completed",
      -  "calendar_event"
      -]New value: +[
      +  "incoming_message",
      +  "incoming_call",
      +  "schedule",
      +  "webhook",
      +  "event",
      +  "blockchain_event",
      +  "job_completed",
      +  "calendar_event",
      +  "lead_captured"
      +]
  19. Changed2 schema fields changed
    • addedInput schema / properties / excluded_thread_ids
      Added value: +{
      +  "description": "Exclude specific threads (chats) by their numeric thread IDs — the opposite of thread_ids. When set, the trigger NEVER fires for messages in these threads, even if thread_ids would otherwise allow them (explicit deny wins). Only for incoming_message and job_completed triggers. Maps to conditions.thread_filter.excluded_thread_ids.",
      +  "items": {
      +    "type": "integer"
      +  },
      +  "type": "array"
      +}
    • changedInput schema / properties / thread_ids / description
      Previous value: -"Restrict this trigger to specific threads (chats) by their numeric thread IDs. When set, the trigger only fires for messages in these threads. Maps to conditions.thread_filter.thread_ids."New value: +"Restrict this trigger to specific threads (chats) by their numeric thread IDs. When set, the trigger only fires for messages in these threads. Only for incoming_message and job_completed triggers. Maps to conditions.thread_filter.thread_ids."
  20. Changed2 schema fields changed
    • changedInput schema / properties / trigger_type / description
      Previous value: -"Type of trigger: 'incoming_message', 'incoming_call', 'voice_transcript', 'schedule', 'webhook', 'event', 'blockchain_event', 'job_completed', or 'calendar_event'"New value: +"Type of trigger: 'incoming_message', 'incoming_call', 'schedule', 'webhook', 'event', 'blockchain_event', 'job_completed', or 'calendar_event'"
    • changedInput schema / properties / trigger_type / enum
      Previous value: -[
      -  "incoming_message",
      -  "incoming_call",
      -  "voice_transcript",
      -  "schedule",
      -  "webhook",
      -  "event",
      -  "blockchain_event",
      -  "job_completed",
      -  "calendar_event"
      -]New value: +[
      +  "incoming_message",
      +  "incoming_call",
      +  "schedule",
      +  "webhook",
      +  "event",
      +  "blockchain_event",
      +  "job_completed",
      +  "calendar_event"
      +]
  21. Changed3 schema fields changed
    • changedInput schema / properties / conditions / description
      Previous value: -"Trigger conditions (JSON). Supported fields for incoming_message:\n- keywords: [\"pricing\",\"demo\"] — message must contain keyword(s) (free, no LLM cost)\n- keyword_match: \"any\" (default, OR) or \"all\" (AND)\n- channel_types: [\"telegram\",\"whatsapp\",\"livechat_voice\",\"twilio_voice\",\"telegram_voice\",\"voice\",...] — filter by channel. For voice, use EITHER the three per-channel keys (scoped) OR \"voice\" alone (wildcard matching all three) — mixing them is redundant. Per-channel keys: \"livechat_voice\" (web widget), \"twilio_voice\" (PSTN inbound), \"telegram_voice\" (Telegram p2p calls)\n- context_types: [\"dm\",\"group\",\"channel\",\"livechat\"] — filter by chat type\n- group_mode: \"mentions_only\" or \"questions\" — for group chats\n- channel_account_ids: [\"123\"] — restrict to specific accounts\n- folder_ids: [5,10] — restrict to threads in folders\n- ai_tag_ids: [1,2] — restrict to threads with AI tags\n- ai_filter_ids: [1,2] — semantic intent filters (message matched via embedding similarity, works in noisy groups)\n- ai_filter_mode: \"any\" (default, OR) or \"all\" (AND) — how multiple AI filters combine\n- ai_filters: [{id: 1}, {name: \"...\", description: \"...\"}] — shorthand: reference existing by id or create inline (calls Voyage embedding API). If a filter with the same name already exists, it is reused by id. Prefer referencing existing filters by id when available. Use ai_filters.create + ai_filters.test for fine-tuning before assigning.\n- contact_states: [\"active\"] — filter by contact state\n- cooldown_seconds: 30 — min gap between runs per thread\n- max_runs_per_thread_per_hour: 5 — rate limit\n\nSupported fields for job_completed (proactive callback when a delegated job finishes):\n- source_agent_id: <int> — fire only when this agent's job completed\n- source_agent_slug: <str> — alternate to source_agent_id\n- job_type: \"agentic_session\" — match a specific job type (default: any)\n- outcome: [\"completed\"] | [\"escalated\"] | [\"completed\",\"escalated\"] — default [\"completed\"]\n- min_duration_seconds: <int> — skip very-short jobs (noise filter)\n- thread_filter: {thread_ids: [<int>...]} — restrict to specific threads"New value: +"Trigger conditions (JSON). Supported fields for incoming_message:\n- keywords: [\"pricing\",\"demo\"] — message must contain keyword(s) (free, no LLM cost)\n- keyword_match: \"any\" (default, OR) or \"all\" (AND)\n- channel_types: [\"telegram\",\"whatsapp\",\"livechat_voice\",\"twilio_voice\",\"telegram_voice\",\"voice\",...] — filter by channel. For voice, use EITHER the three per-channel keys (scoped) OR \"voice\" alone (wildcard matching all three) — mixing them is redundant. Per-channel keys: \"livechat_voice\" (web widget), \"twilio_voice\" (PSTN inbound), \"telegram_voice\" (Telegram p2p calls)\n- context_types: [\"dm\",\"group\",\"channel\",\"livechat\"] — filter by chat type\n- group_mode: \"mentions_only\" or \"questions\" — for group chats\n- channel_account_ids: [\"123\"] — restrict to specific accounts\n- folder_ids: [5,10] — restrict to threads in folders\n- ai_tag_ids: [1,2] — restrict to threads with AI tags\n- ai_filter_ids: [1,2] — semantic intent filters (message matched via embedding similarity, works in noisy groups)\n- ai_filter_mode: \"any\" (default, OR) or \"all\" (AND) — how multiple AI filters combine\n- ai_filters: [{id: 1}, {name: \"...\", description: \"...\"}] — shorthand: reference existing by id or create inline (calls Voyage embedding API). If a filter with the same name already exists, it is reused by id. Prefer referencing existing filters by id when available. Use ai_filters.create + ai_filters.test for fine-tuning before assigning.\n- contact_states: [\"active\"] — filter by contact state\n- cooldown_seconds: 30 — min gap between runs per thread\n- max_runs_per_thread_per_hour: 5 — rate limit\n\nSupported fields for job_completed (proactive callback when a delegated job finishes):\n- source_agent_id: <int> — fire only when this agent's job completed\n- source_agent_slug: <str> — alternate to source_agent_id\n- job_type: \"agentic_session\" — match a specific job type (default: any)\n- outcome: [\"completed\"] | [\"escalated\"] | [\"completed\",\"escalated\"] — default [\"completed\"]\n- min_duration_seconds: <int> — skip very-short jobs (noise filter)\n- thread_filter: {thread_ids: [<int>...]} — restrict to specific threads\n\nSupported fields for calendar_event (fires N minutes before a Google Calendar event starts):\n- window_minutes_before: <int 1-1440> — REQUIRED, fire when an event starts within this window\n- channel_account_ids: [<int>...] — restrict to specific calendar accounts (default: all)\n- keywords: [\"standup\"] — word-boundary match on event title\n- prepare_meet_join: true — pre-invite pool bots to the event (enables unattended Meet join)\n\nGeneric run-mode fields (incoming_message AND calendar_event):\n- run_mode: \"text\" (default, normal agent run) or \"voice\" (deterministically join the meeting/call resolved from the event or message — requires send_mode=auto)\n- voice: {speak_first: <bool — greet immediately vs stay silent until addressed>, vision_mode: \"off\"|\"on_demand\"|\"continuous_0_3fps\"}"
    • changedInput schema / properties / trigger_type / description
      Previous value: -"Type of trigger: 'incoming_message', 'incoming_call', 'voice_transcript', 'schedule', 'webhook', 'event', 'blockchain_event', or 'job_completed'"New value: +"Type of trigger: 'incoming_message', 'incoming_call', 'voice_transcript', 'schedule', 'webhook', 'event', 'blockchain_event', 'job_completed', or 'calendar_event'"
    • changedInput schema / properties / trigger_type / enum
      Previous value: -[
      -  "incoming_message",
      -  "incoming_call",
      -  "voice_transcript",
      -  "schedule",
      -  "webhook",
      -  "event",
      -  "blockchain_event",
      -  "job_completed"
      -]New value: +[
      +  "incoming_message",
      +  "incoming_call",
      +  "voice_transcript",
      +  "schedule",
      +  "webhook",
      +  "event",
      +  "blockchain_event",
      +  "job_completed",
      +  "calendar_event"
      +]
  22. First observed

TDQS

B3.2/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=false, destructiveHint=false, idempotentHint=false and openWorldHint=false, so the safety profile is covered structurally. The description adds real behavioral context in one place — that saving a blockchain_event trigger is 'the whole setup' and the address starts being watched — but says nothing about duplicate-trigger behavior (idempotentHint is false), permissions, or what a created trigger does once the agent is disabled.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with purpose in the first line, then a compact bulleted type list; nothing is padded. The bullet list is short but incomplete, so its brevity comes partly at the cost of accuracy rather than solely from discipline.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For an 11-parameter tool with nested objects, the description is a thin wrapper that delegates nearly everything to the schema, which is acceptable given full schema coverage. The gap is that the description's partial type enumeration can leave an agent believing unsupported types (job_completed, message_edited, etc.) cannot be created with this tool, when the enum says they can.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% and the conditions parameter is documented exhaustively, so the baseline would be 3. However, the description's type list enumerates only 5 of the 13 values in the trigger_type enum (omitting incoming_call, job_completed, calendar_event, lead_captured, task_assigned, job_continuation, message_reaction, message_edited), which actively understates the parameter's accepted values.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a clear verb+resource ('Create a new trigger for an AI agent') and adds a one-line framing ('Triggers determine when the agent activates'). It never names the obvious sibling agents_trigger_update as the alternative when a trigger already exists, so the boundary with siblings is left to inference.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The type list implies when each trigger variant is appropriate (e.g. incoming_message activates on new messages, blockchain_event watches a wallet), which is genuine usage guidance by example. There is no explicit when-not guidance, no prerequisite statement (e.g. the agent must exist / must be active), and no routing to agents_trigger_update or agents_trigger_delete.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.