fix all broken links

Author: bdougie

docs/docs/advanced/00-overview.mdx

@@ -12,25 +12,25 @@ Explore Continue's advanced capabilities for power users and complex development
 
 Master how Continue understands your codebase and integrates with your development tools.
 
-[Explore Context & Integration →](./context-integration)
+[Explore Context & Integration →](./context-integration/custom-providers)
 
 ## Deep Dives
 
 Detailed technical explanations of Continue's internal workings and advanced configuration options.
 
-[Read Deep Dives →](./deep-dives)
+[Read Deep Dives →](./deep-dives/configuration.md)
 
 ## Model Providers
 
 Configure and optimize different AI model providers for your specific needs and infrastructure.
 
-[Configure Providers →](./model-providers)
+[Configure Providers →](./model-providers/top-level/openai.mdx)
 
 ## Model Roles
 
 Understand how different models can be assigned specific roles in your development workflow.
 
-[Learn Model Roles →](./model-roles)
+[Learn Model Roles →](./model-roles/00-intro.mdx)
 
 ## Reference
 

docs/docs/advanced/context-integration/codebase.mdx

@@ -96,4 +96,4 @@ If you need to force a refresh of the index, reload the VS Code window with <kbd
 
 ## Repository map
 
-Models in the Claude 3, Llama 3.1/3.2, Gemini 1.5, and GPT-4o families will automatically use a [repository map](../context-providers.mdx#repository-map) during codebase retrieval, which allows the model to understand the structure of your codebase and use it to answer questions. Currently, the repository map only contains the filepaths in the codebase.
+Models in the Claude 3, Llama 3.1/3.2, Gemini 1.5, and GPT-4o families will automatically use a [repository map](./custom-providers.mdx#repository-map) during codebase retrieval, which allows the model to understand the structure of your codebase and use it to answer questions. Currently, the repository map only contains the filepaths in the codebase.

docs/docs/advanced/context-integration/custom-providers.mdx

@@ -15,7 +15,7 @@ As an example, say you are working on solving a new GitHub Issue. You type '@Iss
 
 ## Context blocks
 
-You can add context providers to assistants using [`context` blocks](../hub/blocks/block-types.md#context). Explore available context blocks in [the hub](https://hub.continue.dev/explore/context).
+You can add context providers to assistants using [`context` blocks](../../hub/blocks/block-types.md#context). Explore available context blocks in [the hub](https://hub.continue.dev/explore/context).
 
 ## Built-in Context Providers
 
@@ -167,7 +167,7 @@ Reference the contents from any documentation site.
 
 Note that this will only enable the `@Docs` context provider.
 
-To use it, you need to add a documentation site to your config file. See the [docs](../advanced/deep-dives/docs.mdx) page for more information.
+To use it, you need to add a documentation site to your config file. See the [docs](../deep-dives/docs.mdx) page for more information.
 
 ### `@Open`
 
@@ -253,7 +253,7 @@ Reference the most relevant snippets from your codebase.
   </TabItem>
 </Tabs>
 
-Read more about indexing and retrieval [here](../advanced/deep-dives/codebase.mdx).
+Read more about indexing and retrieval [here](../deep-dives/codebase.mdx).
 
 ### `@Folder`
 

docs/docs/advanced/context-integration/documentation.mdx

@@ -19,7 +19,7 @@ import Tabs from "@theme/Tabs";
 
 # @Docs
 
-The [`@Docs` context provider](advanced/context-integration/custom-providers#docs) allows you to efficiently reference documentation directly within Continue.
+The [`@Docs` context provider](./custom-providers#docs) allows you to efficiently reference documentation directly within Continue.
 
 ## Enabling the `@Docs` context provider
 
@@ -111,7 +111,7 @@ For bulk documentation site adds or edits, we recommend editing your global conf
   </TabItem>
 </Tabs>
 
-See [the config reference](../../reference) for all documentation site configuration options.
+See [the config reference](../reference) for all documentation site configuration options.
 
 Indexing will re-sync upon saving the configuration file.
 

docs/docs/advanced/context-integration/slash-commands.mdx

@@ -14,20 +14,20 @@ import Tabs from "@theme/Tabs";
 Slash commands are shortcuts that can be activated by typing '/' in a chat session (press <kbd>cmd/ctrl</kbd> + <kbd>L</kbd> (VS Code) or <kbd>cmd/ctrl</kbd> + <kbd>J</kbd> (JetBrains)), and selecting from the dropdown.
 ![slash-commands](/img/slash-commands.png)
 
-Slash commands can be combined with additional instructions, including [context providers](../context-providers.mdx) or [highlighted code](../../edit/context-selection#highlighted-code).
+Slash commands can be combined with additional instructions, including [context providers](./custom-providers.mdx) or highlighted code.
 
 ## Prompts
 
 ### Assistant prompt blocks
 
-The easiest way to add a slash command is by adding [`prompt` blocks](../../hub/blocks/block-types.md#prompts) to your assistant, which show up as slash commands in [Chat](../../chat/how-it-works.md).
+The easiest way to add a slash command is by adding [`prompt` blocks](../../hub/blocks/block-types.md#prompts) to your assistant, which show up as slash commands in [Chat](../../features/chat/how-it-works.mdx).
 
 ### Prompt files
 
 It is also possible to write your own slash command by defining a “.prompt file.” Prompt files can be as simple as a text file, but also include templating so that you can refer to files, URLs, highlighted code, and more.
 
-Learn more about prompt files [here](./prompts.md)
+Learn more about prompt files [here](../deep-dives/prompts.md)
 
 ### MCP Server prompts
 
-Any prompts provided by [Model Context Protocol](https://modelcontextprotocol.io/introduction) servers are also accessible in chat as Slash Commands. See the [MCP Server Deep Dive](./mcp.mdx) for more details.
+Any prompts provided by [Model Context Protocol](https://modelcontextprotocol.io/introduction) servers are also accessible in chat as Slash Commands. See the [MCP Server Deep Dive](../deep-dives/mcp.mdx) for more details.

docs/docs/advanced/deep-dives/autocomplete.mdx

@@ -98,7 +98,7 @@ The following settings can be configured for autocompletion in the IDE extension
 
 ### `config.json` Configuration
 
-The `config.json` configuration format (deprecated) offers further configuration options through `tabAutocompleteOptions`. See the [JSON Reference](../../json-reference.md#tabautocompleteoptions) for more details.
+The `config.json` configuration format (deprecated) offers further configuration options through `tabAutocompleteOptions`. See the [JSON Reference](../reference.mdx#tabautocompleteoptions) for more details.
 
 ## FAQs
 

docs/docs/advanced/deep-dives/codebase.mdx

@@ -96,4 +96,4 @@ If you need to force a refresh of the index, reload the VS Code window with <kbd
 
 ## Repository map
 
-Models in the Claude 3, Llama 3.1/3.2, Gemini 1.5, and GPT-4o families will automatically use a [repository map](../context-providers.mdx#repository-map) during codebase retrieval, which allows the model to understand the structure of your codebase and use it to answer questions. Currently, the repository map only contains the filepaths in the codebase.
+Models in the Claude 3, Llama 3.1/3.2, Gemini 1.5, and GPT-4o families will automatically use a [repository map](../context-integration/custom-providers.mdx#repository-map) during codebase retrieval, which allows the model to understand the structure of your codebase and use it to answer questions. Currently, the repository map only contains the filepaths in the codebase.

docs/docs/advanced/deep-dives/configuration.md

@@ -31,10 +31,10 @@ See the full reference for `config.yaml` [here](../../advanced/reference).
 ## Deprecated configuration methods
 
 :::info
-View the `config.json` migration guide [here](../../yaml-migration.md)
+View the `config.json` migration guide [here](../yaml-migration.mdx)
 :::
 
-- [`config.json`](../../json-reference.md) - The original configuration format which is stored in a file at the same location as `config.yaml`
+- [`config.json`](../reference.mdx) - The original configuration format which is stored in a file at the same location as `config.yaml`
 - [`.continuerc.json`](#continuercjson) - Workspace-level configuration
 - [`config.ts`](#configts) - Advanced configuration (probably unnecessary) - a TypeScript file in your home directory that can be used to programmatically modify (_merged_) the `config.json` schema:
   - `~/.continue/config.ts` (MacOS / Linux)

docs/docs/advanced/deep-dives/docs.mdx

@@ -19,7 +19,7 @@ import Tabs from "@theme/Tabs";
 
 # @Docs
 
-The [`@Docs` context provider](advanced/context-integration/custom-providers#docs) allows you to efficiently reference documentation directly within Continue.
+The [`@Docs` context provider](../context-integration/custom-providers#docs) allows you to efficiently reference documentation directly within Continue.
 
 ## Enabling the `@Docs` context provider
 
@@ -111,7 +111,7 @@ For bulk documentation site adds or edits, we recommend editing your global conf
   </TabItem>
 </Tabs>
 
-See [the config reference](../../reference) for all documentation site configuration options.
+See [the config reference](../reference) for all documentation site configuration options.
 
 Indexing will re-sync upon saving the configuration file.
 

docs/docs/advanced/deep-dives/slash-commands.mdx

@@ -14,13 +14,13 @@ import Tabs from "@theme/Tabs";
 Slash commands are shortcuts that can be activated by typing '/' in a chat session (press <kbd>cmd/ctrl</kbd> + <kbd>L</kbd> (VS Code) or <kbd>cmd/ctrl</kbd> + <kbd>J</kbd> (JetBrains)), and selecting from the dropdown.
 ![slash-commands](/img/slash-commands.png)
 
-Slash commands can be combined with additional instructions, including [context providers](../context-providers.mdx) or [highlighted code](../../edit/context-selection#highlighted-code).
+Slash commands can be combined with additional instructions, including [context providers](../context-integration/custom-providers.mdx) or highlighted code.
 
 ## Prompts
 
 ### Assistant prompt blocks
 
-The easiest way to add a slash command is by adding [`prompt` blocks](../../hub/blocks/block-types.md#prompts) to your assistant, which show up as slash commands in [Chat](../../chat/how-it-works.md).
+The easiest way to add a slash command is by adding [`prompt` blocks](../../hub/blocks/block-types.md#prompts) to your assistant, which show up as slash commands in [Chat](../../features/chat/how-it-works.mdx).
 
 ### Prompt files
 

docs/docs/advanced/deep-dives/vscode-actions.md

@@ -26,7 +26,7 @@ Right click actions let you highlight a desired region of code, right click, and
 
 The highlighted code you’ve selected will be included in your prompt alongside a pre-written set of instructions depending on the selected action. This is the only section of code that the model will attempt to edit.
 
-Right click actions that generate inline diffs use the same prompt and response processing logic as [Edit](../../edit/how-it-works.md).
+Right click actions that generate inline diffs use the same prompt and response processing logic as [Edit](../../features/edit/how-it-works.mdx).
 
 ![context-menu](/img/context-menu.png)
 

docs/docs/advanced/telemetry.mdx

@@ -26,6 +26,6 @@ The following usage information is collected and reported:
 
 ## How to Opt Out
 
-You can disable anonymous telemetry by visiting the [User Settings Page](./advanced/deep-dives/settings.md) and toggling "Allow Anonymous Telemetry" off.
+You can disable anonymous telemetry by visiting the [User Settings Page](./deep-dives/settings.md) and toggling "Allow Anonymous Telemetry" off.
 
 Alternatively in VS Code, you can disable telemetry through your VS Code settings by unchecking the "Continue: Telemetry Enabled" box (this will override the Settings Page settings). VS Code settings can be accessed with `File` > `Preferences` > `Settings` (or use the keyboard shortcut <kbd>ctrl</kbd> + <kbd>,</kbd> on Windows/Linux or <kbd>cmd</kbd> + <kbd>,</kbd> on macOS).

docs/docs/advanced/yaml-migration.mdx

@@ -11,8 +11,8 @@ Continue's YAML configuration format provides more readable, maintainable, consi
 See also
 
 - [Intro to YAML](https://yaml.org/)
-- [JSON Continue Config Reference](/json-reference)
-- [YAML Continue Config Reference](/advanced/reference)
+- [JSON Continue Config Reference](/advanced/reference)
+- [YAML Continue Config Reference](./reference.mdx)
 
 ## Create YAML file
 
@@ -38,9 +38,9 @@ Add all model configurations in `config.json`, including models in `models`, `ta
   - `inlineEdit` -> e.g. `roles: [chat, edit]`
   - `applyCodeBlock` -> e.g. `roles: [chat, apply]`
 
-Model-level `requestOptions` remain, with minor changes. See [YAML Continue Config Reference](./reference.md#models)
+Model-level `requestOptions` remain, with minor changes. See [YAML Continue Config Reference](./reference.mdx#models)
 
-Model-level `completionOptions` are replaced by `defaultCompletionOptions`, with minor changes. See [YAML Continue Config Reference](./reference.md#models)
+Model-level `completionOptions` are replaced by `defaultCompletionOptions`, with minor changes. See [YAML Continue Config Reference](./reference.mdx#models)
 
 <!-- TODO - ollama autodetect supported? -->
 
@@ -328,9 +328,9 @@ mcpServers:
 
 ## Deprecated configuration options
 
-Some deprecated `config.json` settings are no longer stored in config and have been moved to be editable through the [User Settings Page](./advanced/deep-dives/settings.md) (Gear Icon). If found in `config.json`, they will be auto-migrated to User Settings and removed from `config.json`.
+Some deprecated `config.json` settings are no longer stored in config and have been moved to be editable through the [User Settings Page](./deep-dives/settings.md) (Gear Icon). If found in `config.json`, they will be auto-migrated to User Settings and removed from `config.json`.
 
-See the [JSON Config Reference](./json-reference#fully-deprecated-settings) for more information on fully deprecated options.
+See the [JSON Config Reference](./reference#fully-deprecated-settings) for more information on fully deprecated options.
 
 The following top-level fields from `config.json` still work when using `config.json` but have been deprecated and don't have a YAML equivalent:
 
@@ -355,4 +355,4 @@ The following top-level fields from `config.json` have been deprecated. Most UI-
 
 ## New Configuration options
 
-The YAML configuration format offers new configuration options not available in the JSON format. See the [YAML Config Reference](./reference) for more information.
+The YAML configuration format offers new configuration options not available in the JSON format. See the [YAML Config Reference](./reference.mdx) for more information.

docs/docs/customization/00-overview.mdx

@@ -6,11 +6,11 @@ keywords: [customize, configure, config]
 
 Continue can be deeply customized. For example you might:
 
-- **Change your Model Provider**. Continue allows you to choose your favorite or even add multiple model providers. This allows you to use different models for different tasks, or to try another model if you're not happy with the results from your current model. Continue supports all of the popular model providers, including OpenAI, Anthropic, Microsoft/Azure, Mistral, and more. You can even self host your own model provider if you'd like. Learn more about [model providers](../advanced/model-providers/).
-- **Select different models for specific tasks**. Different Continue features can use different models. We call these _model roles_. For example, you can use a different model for chat than you do for autocomplete. Learn more about [model roles](./model-roles/) .
-- **Add a Context Provider**. Context providers allow you to add information to your prompts, giving your LLM additional context to work with. Context providers allow you to reference snippets from your codebase, or lookup relevant documentation, or use a search engine to find information and much more. Learn more about [context providers](./context-providers.mdx).
-- **Create a Slash Command**. Slash commands allow you to easily add custom functionality to Continue. You can use a slash command that allows you to generate a shell command from natural language, or perhaps generate a commit message, or create your own custom command to do whatever you want. Learn more about [slash commands](./deep-dives/slash-commands.mdx).
-- **Call external tools and functions**. Unchain your LLM with the power of tools using [Agent](../features/agent/quick-start). Add custom tools using [MCP Servers](./deep-dives/mcp.mdx)
+- **Change your Model Provider**. Continue allows you to choose your favorite or even add multiple model providers. This allows you to use different models for different tasks, or to try another model if you're not happy with the results from your current model. Continue supports all of the popular model providers, including OpenAI, Anthropic, Microsoft/Azure, Mistral, and more. You can even self host your own model provider if you'd like. Learn more about [model providers](../advanced/model-providers/top-level/openai.mdx).
+- **Select different models for specific tasks**. Different Continue features can use different models. We call these _model roles_. For example, you can use a different model for chat than you do for autocomplete. Learn more about [model roles](../advanced/model-roles/00-intro.mdx).
+- **Add a Context Provider**. Context providers allow you to add information to your prompts, giving your LLM additional context to work with. Context providers allow you to reference snippets from your codebase, or lookup relevant documentation, or use a search engine to find information and much more. Learn more about [context providers](../advanced/context-integration/custom-providers.mdx).
+- **Create a Slash Command**. Slash commands allow you to easily add custom functionality to Continue. You can use a slash command that allows you to generate a shell command from natural language, or perhaps generate a commit message, or create your own custom command to do whatever you want. Learn more about [slash commands](../advanced/deep-dives/slash-commands.mdx).
+- **Call external tools and functions**. Unchain your LLM with the power of tools using [Agent](../features/agent/quick-start.mdx). Add custom tools using [MCP Servers](../advanced/deep-dives/mcp.mdx)
 
 Whatever you choose, you'll probably start by editing your Assistant.
 
@@ -21,4 +21,4 @@ You can easily access your assistant configuration from the Continue Chat sideba
 ![configure an assistant](/img/configure-continue.png)
 
 - See [Editing Hub Assistants](../hub/assistants/edit-an-assistant.md) for more details on managing your hub assistant
-- See the [Config Deep Dive](./deep-dives/configuration.md) for more details on configuring local assistants.
+- See the [Config Deep Dive](../advanced/deep-dives/configuration.md) for more details on configuring local assistants.

docs/docs/customization/models.mdx

@@ -19,6 +19,6 @@ These blocks form the foundation of the entire assistant experience, offering di
 
 ## Learn More
 
-Continue supports [many model providers](../advanced/model-providers), including Anthropic, OpenAI, Gemini, Ollama, Amazon Bedrock, Azure, xAI, DeepSeek, and more. Models can have various roles like `chat`, `edit`, `apply`, `autocomplete`, `embed`, and `rerank`.
+Continue supports [many model providers](../advanced/model-providers/top-level/openai.mdx), including Anthropic, OpenAI, Gemini, Ollama, Amazon Bedrock, Azure, xAI, DeepSeek, and more. Models can have various roles like `chat`, `edit`, `apply`, `autocomplete`, `embed`, and `rerank`.
 
-Read more about roles [here](../advanced/model-roles/intro.mdx) and view [`models`](../advanced/reference#models) in the YAML Reference.
+Read more about roles [here](../advanced/model-roles/00-intro.mdx) and view [`models`](../advanced/reference#models) in the YAML Reference.

docs/docs/customization/rules.mdx

@@ -18,7 +18,7 @@ By implementing rules, you transform the AI from a generic coding assistant into
 
 ### How Rules Work
 
-Your assistant detects rule blocks and applies the specified rules while in [Agent](../agent/how-to-use-it), [Chat](../chat/how-to-use-it), and [Edit](../edit/how-to-use-it) modes.
+Your assistant detects rule blocks and applies the specified rules while in [Agent](../features/agent/quick-start), [Chat](../features/chat/quick-start), and [Edit](../features/edit/quick-start) modes.
 
 ## Learn More