Skip to content

common-setups.mdx

Latest commit

 

History

History
95 lines (75 loc) · 4.7 KB

common-setups.mdx

File metadata and controls

95 lines (75 loc) · 4.7 KB
Raw
title Common Setups
description End-to-end setup playbooks that combine providers, channels, and gateway ownership.

Common Setups

Use this page when onboard, ask, or chat already makes sense and you want one practical setup shape instead of reading provider, channel, and gateway pages separately.

This page is now the setup hub, not another long cookbook. The detailed operational steps live in dedicated playbooks. If you want the shared public config shape before you pick a playbook, start with Configuration Patterns.

Start With The Common Cases

These playbooks cover a few repeatable rollout shapes. They are representative paths, not the full support matrix. Use Provider Guides and Channel Guides when you want the broader family-by-family map instead of one end-to-end playbook. Keep Provider Recipes and Channel Recipes for representative patterns.

All routes here stay inside the current public contract:

  • runtime-backed service channels are still Feishu / Lark, Telegram, Matrix, WhatsApp, and WeCom
  • outbound-only surfaces stay outbound-only
  • gateway run remains the explicit owner contract for longer-lived service supervision
  • grouped operator shells such as runtime, channels, and gateway are the canonical docs surface

Choose A Playbook

If you want... Start here Why
one hosted provider plus a Feishu or Lark team room Volcengine Plus Feishu Or Lark it keeps the primary hosted and team-chat path together
WeCom as the long-lived enterprise lane WeCom Rollout it matches the shipped AIBot long-connection contract
a dedicated coding lane plus a lightweight bot surface BytePlus Coding Plus Telegram coding traffic and runtime delivery stay explicit
a local model plus governed outbound delivery Local Model Plus Outbound Delivery local inference and outbound notifications stay separate from reply-loop runtimes
several runtime-backed channels on one host Gateway Rollout it moves from one healthy surface to explicit gateway ownership

If you still just need one provider to work locally, go back to First Run and Provider Guides instead of treating this hub like a provider-only guide.

Shared Validation Loop

Use the same short loop after each setup slice:

loong doctor
loong runtime list models
loong channels

When gateway ownership is involved, add:

loong gateway status --json
loong status --json

Use gateway status --json for the shortest ownership-specific view and status --json for the broader operator summary across gateway, ACP, and work-unit surfaces.

Reading Rules

  • Start with the base CLI path first. Do not treat a channel or gateway setup as step zero.
  • Use Configuration Patterns when the rollout is clear but you still want the shared provider, account, and memory shape before a playbook.
  • Use a dedicated playbook when the rollout shape is already clear.
  • Use provider-only or channel-only recipe pages when the setup is still narrow.
  • Move to gateway selectors only after named accounts.<id> entries exist.

Continue Reading

If you want to... Go here
stay on the main hosted team-chat lane Volcengine Plus Feishu Or Lark
follow the WeCom-specific enterprise path WeCom Rollout
follow the dedicated coding-plus-bot route BytePlus Coding Plus Telegram
use a local model without overclaiming delivery support Local Model Plus Outbound Delivery
supervise several runtime-backed channels Gateway Rollout
inspect the shared public config shape first Configuration Patterns
step back to provider-only setup Provider Guides and Provider Recipes
step back to channel-only setup Channel Guides and Channel Recipes
inspect the owner contract directly Gateway And Supervision
return to the wider runtime map Use Loong