How do I ask an AI agent to make a first small project change?
Choose the project folder first, then describe one small change. Use Plan mode for multi-step work and inspect the resulting diff and checks.
Read the full answerStart with the desktop app, connect a model, choose an Agent, and add a useful Skill. Find step-by-step answers for setup, QQ chats, troubleshooting, and billing.
Choose the project folder first, then describe one small change. Use Plan mode for multi-step work and inspect the resulting diff and checks.
Read the full answerOpen the frontend project, name the page and acceptance criteria, then review both the patch and the rendered page.
Read the full answerOpen a local folder containing the materials, specify inputs and output format, and keep the originals for verification.
Read the full answerInspect the patch, then confirm which tests and reviews actually ran. Do not treat an unrun check as a pass.
Read the full answerInstall the desktop app, confirm a usable model connection and an agent, then review before applying configuration changes.
Read the full answerChoose a desktop app for a graphical workflow and a CLI for terminals or scripts; configuration management depends on adapter support.
Read the full answerReview and confirm a supported native configuration before writing it; reopen the agent to load the new settings.
Read the full answerA model configuration applies to the target agent path; desktop and CLI clients sharing that path may both change, while old conversation history is not migrated or rewritten.
Read the full answer路墨 Lumoswitch is an AI console for model aggregation, one-key access to multiple models, automatic installation of agents, and Skills management.
Read the full answerConfirm that the desktop app and QQ connection are online, pair from the owner's private QQ chat, test the model, then send a real QQ message.
Read the full answerPrepare official bot credentials, save the configuration in Lumoswitch, pair from your own QQ account, and connect explicitly.
Read the full answerGroup chat requires separate platform capabilities, bot membership, and group pairing; only a real @ mention is handled.
Read the full answerManually pausing clears the intent to auto-recover next time; fix the configuration, reconnect from Playbooks, and check the status.
Read the full answerMemory types are managed separately and default to off; changing a switch pauses QQ and requires reconnection, while disabling alone keeps saved content.
Read the full answerA normal in-place update preserves saved memory on the device; use the original account. Updates are neither cloud sync nor a way to undo deletion.
Read the full answerInstallation only places a Skill on the device. Check its enabled state, permissions, and compatibility, then select it for the agent or current workspace.
Read the full answerUse the community to discover resources; review compatibility, files, and conflicts in the app before installing.
Read the full answerInstalled does not mean enabled. Apply it using the agent's supported Skills workflow, then verify in a new session.
Read the full answerA prompt gives instructions for a conversation; a Skill can package reusable instructions, workflows, and files and must be supported by the agent.
Read the full answerMatch it to a real task, then review its source, agent compatibility, files, and permissions; inspect unfamiliar content carefully.
Read the full answerDo not bypass conflict checks; verify the target agent and directory, back up existing content, then decide whether to replace it or choose a compatible Skill.
Read the full answerOnline configurations run through Lumoswitch's service; local LiteLLM connects directly to a provider and requires the desktop app while in use.
Read the full answerLocal BYOK credentials stay on the device and connect directly to the provider; hosted and local keys use different paths.
Read the full answerA fixed connection is predictable; a failover group only tries configured candidates and may change capabilities and cost.
Read the full answerLumoswitch brings models and agents into one AI console, with one key across multiple models, automatic installation of agents, and Skills management.
Read the full answerExisting OpenAI-compatible clients generally replace their Base URL, Lumoswitch access key, and published model ID, then validate the current deployment's capabilities with a minimal request.
Read the full answerBring models together in the AI console and choose connections for Codex and other agents. Use one key within each configuration and prepare supported tools through the client.
Read the full answerConfirm the active configuration path and model ID first, then check keys, provider access, limits, and request records.
Read the full answerFailover requires configured available candidates and an order in advance; fixed routing does not switch automatically. It reduces the impact of one upstream failure but cannot guarantee permanent model or upstream availability.
Read the full answerLocal history is derived from logs that remain on the device and may be incomplete; platform bills cover Lumoswitch service calls. Do not add the two together.
Read the full answerPlatform calls are metered under the current displayed rules; local BYOK is generally billed by the provider. Follow the actual connection path and bill for prices and limits.
Read the full answerSeparate access keys, model configurations, and rate controls, together with account balance, call logs, and usage bills, create clearer permission and cost boundaries for LLM calls.
Read the full answerComplete your first Lumoswitch integration, from model configuration and an access key to a minimal-request validation.
Read the full guideLearn how model metering, account balance, promotional credit, and current prices are presented.
Read the full guideUnderstand the difference between adapted channels and models that are actually published and callable in the current deployment.
Read the full guideReview current campaign status, eligibility, grant timing, and usage boundaries.
Read the full guideLearn about Lumoswitch product boundaries, access controls, data, and support in one place.
Read the full guide