# Agent Settings - Zed > Map the AI settings pages to Zed AI setup for LLM providers, External Agents, MCP servers, and related settings. - 网址：https://funcoding.ai/agents/zed/ai/agent-settings/ - 来源：Zed 官方文档原文（英文），Apache-2.0 / GPL-3.0 许可，同步于 2026-10-11 - 官方原文：https://zed.dev/docs/ai/agent-settings --- Agent Settings live in the **AI** section of the Settings Editor, which configures model providers, External Agents, and MCP servers. Open it with `agent::OpenSettings` (also available from the top-right menu in the [Agent Panel](https://funcoding.ai/agents/zed/ai/agent-panel/)), which takes you straight to the AI page. You can also reach the same page with `zed::OpenSettings` and selecting **AI** in the sidebar. Within the AI page, LLM Providers, External Agents, and MCP Servers each open as their own sub-page under the **General** section. | Surface | Opens with | Use it for | | --------------- | ------------------------------- | --------------------------------------------------------------------------- | | Settings Editor | `agent::OpenSettings` | AI settings: LLM providers, External Agents, MCP servers, and related pages | | Settings file | `zed::OpenSettingsFile` | Direct JSON edits and settings not exposed in UI | For general settings mechanics, see [Configuring Zed](https://zed.dev/docs/configuring-zed). ## LLM Providers The `LLM Providers` section configures model providers for Zed AI features, including Zed Agent, Inline Assistant, Git commit generation, thread summaries, and similar model-backed features. Use this section to: - sign in to supported subscription-backed providers - enter provider API keys - add OpenAI-compatible providers - remove providers For the model-access paths and provider-specific setup, see [LLM Providers](https://funcoding.ai/agents/zed/ai/llm-providers/). ## Feature-Specific Settings Some Zed AI features have their own model or prompt settings in `settings.json`, including: - `agent.inline_assistant_model` - `agent.commit_message_model` - `agent.thread_summary_model` - `agent.compaction_model` - `agent.subagent_model` - `agent.commit_message_instructions` - `agent.inline_alternatives` Use `agent.commit_message_instructions` for instructions that apply only to generated Git commit messages: ```json [settings] { "agent": { "commit_message_instructions": "Use the Conventional Commits format: (): ." } } ``` For feature-specific model examples, see [Feature-specific Models](#feature-specific-models). ## Automatic Compaction Zed Agent can automatically compact long threads before they reach the selected model's context window. Compaction summarizes earlier messages and keeps the conversation usable without starting a new thread. Automatic compaction is enabled by default and runs when the thread reaches `90%` of the model's context window. You can change the threshold or disable automatic compaction in `settings.json`: ```json [settings] { "agent": { "auto_compact": { "enabled": true, "threshold": "90%" } } } ``` The `threshold` value can be one of: | Value | Meaning | | ------------------------------- | ------------------------------------------------------------------------------ | | Percentage string, like `90%` | Compact when the thread uses that percentage of the model's context window. | | Positive integer, like `100000` | Compact after that many tokens have been used. | | Negative integer, like `-20000` | Compact once fewer than that many tokens remain in the model's context window. | `0` is not a valid threshold. If the threshold is invalid, Zed falls back to `90%`. You can compact a Zed Agent thread manually at any time by typing `/compact` in the Agent Panel message editor. For more on thread token usage and compaction behavior, see [Token Usage and Compaction](https://funcoding.ai/agents/zed/ai/agent-panel/#token-usage). ## Compaction Model By default, context compaction (both `/compact` and auto-compaction) uses the thread's currently selected model. Set `agent.compaction_model` to use a different model: ```json [settings] { "agent": { "default_model": { "provider": "anthropic", "model": "claude-opus-4-6" }, "compaction_model": { "provider": "anthropic", "model": "claude-sonnet-4-5" } } } ``` **Notes:** - The configured model should have a context window at least as large as the thread's primary model for predictable behavior. ## External Agents The External Agents section configures ACP-integrated agents. Use `Add Agent` to: - `Install from Registry` - `Add Custom Agent` For setup details and support boundaries, see [External Agents](https://funcoding.ai/agents/zed/ai/external-agents/). ## MCP Servers The `MCP Servers` page configures Model Context Protocol servers connected to Zed. Use `Add Server` (in the page header) to: - `Add Local Server` - `Add Remote Server` - `Install from Extensions` Each configured server row exposes: - a `Configure` (gear) button to edit the server - an `Uninstall` (trash) button to remove it - a toggle to enable or disable it For MCP setup, auth, server status, and agent-path boundaries, see [MCP](https://funcoding.ai/agents/zed/ai/mcp/). ## Related Configuration Some AI settings are not configured on the AI settings pages: | Task | Go to | | ------------------------------------------------------------ | ---------------------------------------------- | | Choose which tools are available in a Zed Agent thread | [Agent Profiles](https://funcoding.ai/agents/zed/ai/agent-profiles/) | | Control whether tool calls are allowed, denied, or confirmed | [Tool Permissions](https://funcoding.ai/agents/zed/ai/tool-permissions/) | | Configure reusable task instructions | [Skills](https://funcoding.ai/agents/zed/ai/skills/) | | Configure always-on personal or project instructions | [Instructions](https://funcoding.ai/agents/zed/ai/instructions/) | | Configure edit prediction providers | [Edit Prediction](https://funcoding.ai/agents/zed/ai/edit-prediction/) | | Turn AI off | [AI Quick Start](https://funcoding.ai/agents/zed/ai/quick-start/#turn-ai-off) | | Edit raw settings JSON | [Configuring Zed](https://zed.dev/docs/configuring-zed) | ## Feature-Specific Models Zed supports feature-specific model settings for Inline Assistant, Git commit generation, thread summaries, and subagents. Configure these in settings when you need a different model for a specific workflow. See [LLM Providers](https://funcoding.ai/agents/zed/ai/llm-providers/) for model access, and [All Settings](https://funcoding.ai/agents/zed/reference/all-settings/) for the complete settings reference. ## Model Temperature Most Zed AI features use the selected model's default generation behavior. Use `agent.model_parameters` when you need to set a temperature for a provider, a model, or a specific provider/model pair. ```json [settings] { "agent": { "model_parameters": [ { "provider": "anthropic", "model": "claude-sonnet-4-5", "temperature": 0.2 } ] } } ``` Zed checks matching entries from last to first. An entry can omit `provider` or `model` to apply more broadly. For provider-specific model configuration such as custom model entries, context windows, or gateway routing, see [LLM Providers](https://funcoding.ai/agents/zed/ai/llm-providers/) and the provider setup pages. ## Rules, Skills, and Instructions Reusable Rules have been replaced by [Skills](https://funcoding.ai/agents/zed/ai/skills/). Always-on Rules have moved to [Instructions](https://funcoding.ai/agents/zed/ai/instructions/), including personal `AGENTS.md` and project instruction files. Older builds or transitional UI may still refer to `Rules`. Use [Skills](https://funcoding.ai/agents/zed/ai/skills/) for reusable task instructions and [Instructions](https://funcoding.ai/agents/zed/ai/instructions/) for always-on context.