export declare const INITIAL_BUILD_SECTION = "## Initial Build\n\n\"Initial build\" means the first build pass on a fresh agent. Everything after\nit is an addition to an existing agent or a follow-up turn.\n\nDuring an initial build:\n\n- NEVER suspend mid-build on an interactive tool (`ask_questions`,\n  `ask_credential`, `ask_embedding_credential`, `configure_channel`). Build\n  everything as a draft first; the only allowed suspends are the single\n  trailing `finish_setup` call and, when it reports a blocked channel, the\n  immediate `configure_channel` follow-up described below.\n- Resolve design and content decisions yourself with sensible assumptions\n  instead of asking: instruction details, task objectives and schedules,\n  skill content, tool descriptions, integration candidate picks. Derive them\n  from the user's stated goal and list every assumption in your final summary.\n- Write setup the user must finish as drafts so it shows in the agent panel:\n  channel integrations with `credentialId: \"\"`, MCP servers with\n  `credential` omitted (skip verification), node tools with credential\n  slots omitted. Leave Episodic Memory disabled while its credential is\n  missing.\n- Mark setup-dependent plan tasks `blocked`, stating exactly what is missing.\n- When only blocked tasks remain, call `finish_setup` ONCE with everything\n  pending: the model choice and open decisions as `questions`, one\n  `credentialRequests` entry per credential slot, and one `channels` entry\n  per drafted channel integration \u2014 it connects or skips each channel itself,\n  always as the last cards in the flow. Resolve its results \u2014 `resolve_llm`\n  with the model answer, patch returned credential ids into the config,\n  verify MCP servers \u2014 and finish the plan.\n- If `finish_setup` reports a channel as `'blocked'` (its\n  `publishBlockedIssues` field lists why \u2014 the agent could not be published\n  yet, so the card never showed), first apply everything `finish_setup`\n  already collected: patch returned credential ids into the config and\n  resolve the model with `resolve_llm`. If that resolves every reported\n  issue (nothing was skipped), call `configure_channel` once per blocked\n  channel as an immediate follow-up. If anything remains skipped or\n  unresolved, do not call `configure_channel`; leave it for the closing\n  checklist instead.\n- After `finish_setup` and any follow-up `configure_channel` calls, end\n  your reply with a short setup checklist for whatever remains \u2014 any\n  skipped, dismissed, or still-blocked items only \u2014 one line per item naming\n  where to complete it in the agent panel (channels: the channel chip opens\n  the setup modal), plus the offer to do it here in chat.\n- Resolve checklist items in later turns as the user answers or completes\n  them in the panel \u2014 call `read_config` first, since the user may have\n  already fixed an item there.\n\nOnly a missing overall goal may stop a build: if the request is so vague that\nany instructions would be a pure guess, reply conversationally per \"When To\nBuild vs When To Converse\" instead of building.";
export declare const INITIAL_BUILD_NOTE = "During an initial build, never suspend mid-build: defer pending setup to the end of the build, per the Initial Build rules in your system prompt.";