@bastani/atomic 0.8.14 → 0.8.15

package/docs/extensions.md

@@ -133,7 +133,7 @@ Additional paths via `settings.json`:
 }
 ```
 
-To share extensions via npm or git as Atomic packages, see [packages.md](packages.md).
+To share extensions via npm or git as Atomic packages, see [Atomic packages](/packages).
 
 ## Available Imports
 
@@ -368,7 +368,7 @@ pi.on("resources_discover", async (event, _ctx) => {
 
 ### Session Events
 
-See [Session Format](session-format.md) for session storage internals and the SessionManager API.
+See [Session Format](/session-format) for session storage internals and the SessionManager API.
 
 #### session_start
 
@@ -420,7 +420,7 @@ Do cleanup work in `session_shutdown`, then reestablish any in-memory state in `
 
 #### session_before_compact / session_compact
 
-Fired on compaction. See [compaction.md](compaction.md) for details.
+Fired on compaction. See [Compaction](/compaction) for details.
 
 ```typescript
 pi.on("session_before_compact", async (event, ctx) => {
@@ -447,7 +447,7 @@ pi.on("session_compact", async (event, ctx) => {
 
 #### session_before_tree / session_tree
 
-Fired on `/tree` navigation. See [Sessions](sessions.md) for tree navigation concepts.
+Fired on `/tree` navigation. See [Sessions](/sessions) for tree navigation concepts.
 
 ```typescript
 pi.on("session_before_tree", async (event, ctx) => {
@@ -601,7 +601,7 @@ pi.on("tool_execution_end", async (event, ctx) => {
 
 #### context
 
-Fired before each LLM call. Modify messages non-destructively. See [Session Format](session-format.md) for message types.
+Fired before each LLM call. Modify messages non-destructively. See [Session Format](/session-format) for message types.
 
 ```typescript
 pi.on("context", async (event, ctx) => {
@@ -872,7 +872,7 @@ UI methods for user interaction. See [Custom UI](#custom-ui) for full details.
 
 ### ctx.hasUI
 
-`false` in print mode (`-p`) and JSON mode. `true` in interactive and RPC mode. In RPC mode, dialog methods (`select`, `confirm`, `input`, `editor`) work via the extension UI sub-protocol, and fire-and-forget methods (`notify`, `setStatus`, `setWidget`, `setTitle`, `setEditorText`) emit requests to the client. Some TUI-specific methods are no-ops or return defaults (see [rpc.md](rpc.md#extension-ui-protocol)).
+`false` in print mode (`-p`) and JSON mode. `true` in interactive and RPC mode. In RPC mode, dialog methods (`select`, `confirm`, `input`, `editor`) work via the extension UI sub-protocol, and fire-and-forget methods (`notify`, `setStatus`, `setWidget`, `setTitle`, `setEditorText`) emit requests to the client. Some TUI-specific methods are no-ops or return defaults (see [RPC mode](/rpc#extension-ui-protocol)).
 
 ### ctx.cwd
 
@@ -880,7 +880,7 @@ Current working directory.
 
 ### ctx.sessionManager
 
-Read-only access to session state. See [Session Format](session-format.md) for the full SessionManager API and entry types.
+Read-only access to session state. See [Session Format](/session-format) for the full SessionManager API and entry types.
 
 For `tool_call`, this state is synchronized through the current assistant message before handlers run. In parallel tool execution mode it is still not guaranteed to include sibling tool results from the same assistant message.
 
@@ -1456,7 +1456,7 @@ Register a custom TUI renderer for messages with your `customType`. See [Custom
 
 ### pi.registerShortcut(shortcut, options)
 
-Register a keyboard shortcut. See [keybindings.md](keybindings.md) for the shortcut format and built-in keybindings.
+Register a keyboard shortcut. See [Keybindings](/keybindings) for the shortcut format and built-in keybindings.
 
 ```typescript
 pi.registerShortcut("ctrl+shift+p", {
@@ -1521,7 +1521,7 @@ Typical `sourceInfo.source` values:
 
 ### pi.setModel(model)
 
-Set the current model. Returns `false` if no API key is available for the model. See [models.md](models.md) for configuring custom models.
+Set the current model. Returns `false` if no API key is available for the model. See [Custom models](/models) for configuring custom models.
 
 ```typescript
 const model = ctx.modelRegistry.find("anthropic", "claude-sonnet-4-5");
@@ -1619,7 +1619,7 @@ pi.registerProvider("corporate-ai", {
 - `oauth` - OAuth provider config for `/login` support. When provided, the provider appears in the login menu.
 - `streamSimple` - Custom streaming implementation for non-standard APIs.
 
-See [custom-provider.md](custom-provider.md) for advanced topics: custom streaming APIs, OAuth details, model definition reference.
+See [Custom providers](/custom-provider) for advanced topics: custom streaming APIs, OAuth details, model definition reference.
 
 ### pi.unregisterProvider(name)
 
@@ -1987,7 +1987,7 @@ export default function (pi: ExtensionAPI) {
 
 ### Custom Rendering
 
-Tools can provide `renderCall` and `renderResult` for custom TUI display. See [tui.md](tui.md) for the full component API and [tool-execution.ts](https://github.com/earendil-works/pi-mono/blob/main/packages/coding-agent/src/modes/interactive/components/tool-execution.ts) for how tool rows are composed.
+Tools can provide `renderCall` and `renderResult` for custom TUI display. See [TUI components](/tui) for the full component API and [tool-execution.ts](https://github.com/earendil-works/pi-mono/blob/main/packages/coding-agent/src/modes/interactive/components/tool-execution.ts) for how tool rows are composed.
 
 By default, tool output is wrapped in a `Box` that handles padding and background. A defined `renderCall` or `renderResult` must return a `Component`. If a slot renderer is not defined, `tool-execution.ts` uses fallback rendering for that slot.
 
@@ -2088,7 +2088,7 @@ Use namespaced keybinding ids:
 - Coding-agent ids use the `app.*` namespace, for example `app.tools.expand`, `app.editor.external`, `app.session.rename`
 - Shared TUI ids use the `tui.*` namespace, for example `tui.select.confirm`, `tui.select.cancel`, `tui.input.tab`
 
-For the exhaustive list of keybinding ids and defaults, see [keybindings.md](keybindings.md). `keybindings.json` uses those same namespaced ids.
+For the exhaustive list of keybinding ids and defaults, see [Keybindings](/keybindings). `keybindings.json` uses those same namespaced ids.
 
 Custom editors and `ctx.ui.custom()` components receive `keybindings: KeybindingsManager` as an injected argument. They should use that injected manager directly instead of calling `getKeybindings()` or `setKeybindings()`.
 
@@ -2114,7 +2114,7 @@ If a slot renderer is not defined or throws:
 
 Extensions can interact with users via `ctx.ui` methods and customize how messages/tools render.
 
-**For custom components, see [tui.md](tui.md)** which has copy-paste patterns for:
+**For custom components, see [TUI components](/tui)** which has copy-paste patterns for:
 - Selection dialogs (SelectList)
 - Async operations with cancel (BorderedLoader)
 - Settings toggles (SettingsList)
@@ -2367,7 +2367,7 @@ The callback receives:
 - `keybindings` - App keybinding manager (for checking shortcuts)
 - `done(value)` - Call to close component and return value
 
-See [tui.md](tui.md) for the full component API.
+See [TUI components](/tui) for the full component API.
 
 #### Overlay Mode (Experimental)
 
@@ -2393,7 +2393,7 @@ const result = await ctx.ui.custom<string | null>(
 );
 ```
 
-See [tui.md](tui.md) for the full `OverlayOptions` API and [overlay-qa-tests.ts](https://github.com/flora131/atomic/blob/main/packages/coding-agent/examples/extensions/overlay-qa-tests.ts) for examples.
+See [TUI components](/tui) for the full `OverlayOptions` API and [overlay-qa-tests.ts](https://github.com/flora131/atomic/blob/main/packages/coding-agent/examples/extensions/overlay-qa-tests.ts) for examples.
 
 ### Custom Editor
 
@@ -2444,7 +2444,7 @@ ctx.ui.setEditorComponent((tui, theme, keybindings) =>
 );
 ```
 
-See [tui.md](tui.md) Pattern 7 for a complete example with mode indicator.
+See [TUI components](/tui) Pattern 7 for a complete example with mode indicator.
 
 ### Message Rendering
 
@@ -2479,7 +2479,7 @@ pi.sendMessage({
 
 ### Theme Colors
 
-All render functions receive a `theme` object. See [themes.md](themes.md) for creating custom themes and the full color palette.
+All render functions receive a `theme` object. See [Themes](/themes) for creating custom themes and the full color palette.
 
 ```typescript
 // Foreground colors
@@ -2521,8 +2521,8 @@ const highlighted = highlightCode(code, lang, theme);
 | Mode | UI Methods | Notes |
 |------|-----------|-------|
 | Interactive | Full TUI | Normal operation |
-| RPC (`--mode rpc`) | JSON protocol | Host handles UI, see [rpc.md](rpc.md) |
-| JSON (`--mode json`) | No-op | Event stream to stdout, see [json.md](json.md) |
+| RPC (`--mode rpc`) | JSON protocol | Host handles UI, see [RPC mode](/rpc) |
+| JSON (`--mode json`) | No-op | Event stream to stdout, see [JSON mode](/json) |
 | Print (`-p`) | No-op | Extensions run but can't prompt |
 
 In non-interactive modes, check `ctx.hasUI` before using UI methods.

package/docs/index.md

@@ -1,3 +1,8 @@
+---
+title: "Overview"
+description: "Atomic documentation overview"
+---
+
 # Atomic Documentation
 
 Atomic is a minimal terminal coding harness. It is designed to stay small at the core while being extended through TypeScript extensions, skills, prompt templates, themes, and Atomic packages.
@@ -29,48 +34,49 @@ atomic
 
 Authenticate with `/login` for subscription providers, or set an API key such as `ANTHROPIC_API_KEY` before starting Atomic.
 
-For the full first-run flow, see [Quickstart](quickstart.md).
+For the full first-run flow, see [Quickstart](/quickstart).
 
 ## Start here
 
-- [Quickstart](quickstart.md) - install, authenticate, and run a first session.
-- [Using Atomic](usage.md) - interactive mode, slash commands, context files, and CLI reference.
-- [Providers](providers.md) - subscription and API-key setup for built-in providers.
-- [Settings](settings.md) - global and project settings.
-- [Keybindings](keybindings.md) - default shortcuts and custom keybindings.
-- [Sessions](sessions.md) - session management, branching, and tree navigation.
-- [Compaction](compaction.md) - context compaction and branch summarization.
+- [Quickstart](/quickstart) - install, authenticate, and run a first session.
+- [Using Atomic](/usage) - interactive mode, slash commands, context files, and CLI reference.
+- [Providers](/providers) - subscription and API-key setup for built-in providers.
+- [Settings](/settings) - global and project settings.
+- [Keybindings](/keybindings) - default shortcuts and custom keybindings.
+- [Sessions](/sessions) - session management, branching, and tree navigation.
+- [Compaction](/compaction) - context compaction and branch summarization.
 
 ## Customization
 
-- [Extensions](extensions.md) - TypeScript modules for tools, commands, events, and custom UI.
-- [Skills](skills.md) - Agent Skills for reusable on-demand capabilities.
-- [Workflows](workflows.md) - reusable multi-stage automation with tracked stages and resumable runs.
-- [Prompt templates](prompt-templates.md) - reusable prompts that expand from slash commands.
-- [Themes](themes.md) - built-in and custom terminal themes.
-- [Atomic packages](packages.md) - bundle and share extensions, skills, prompts, and themes.
-- [Custom models](models.md) - add model entries for supported provider APIs.
-- [Custom providers](custom-provider.md) - implement custom APIs and OAuth flows.
+- [Extensions](/extensions) - TypeScript modules for tools, commands, events, and custom UI.
+- [Skills](/skills) - Agent Skills for reusable on-demand capabilities.
+- [Subagents](/subagents) - focused child agents for research, analysis, debugging, cleanup, and review compositions.
+- [Workflows](/workflows) - reusable multi-stage automation with tracked stages and resumable runs.
+- [Prompt templates](/prompt-templates) - reusable prompts that expand from slash commands.
+- [Themes](/themes) - built-in and custom terminal themes.
+- [Atomic packages](/packages) - bundle and share extensions, skills, prompts, and themes.
+- [Custom models](/models) - add model entries for supported provider APIs.
+- [Custom providers](/custom-provider) - implement custom APIs and OAuth flows.
 
 ## Programmatic usage
 
-- [SDK](sdk.md) - embed Atomic in Node.js applications.
-- [RPC mode](rpc.md) - integrate over stdin/stdout JSONL.
-- [JSON event stream mode](json.md) - print mode with structured events.
-- [TUI components](tui.md) - build custom terminal UI for extensions.
+- [SDK](/sdk) - embed Atomic in Node.js applications.
+- [RPC mode](/rpc) - integrate over stdin/stdout JSONL.
+- [JSON event stream mode](/json) - print mode with structured events.
+- [TUI components](/tui) - build custom terminal UI for extensions.
 
 ## Reference
 
-- [Session format](session-format.md) - JSONL session file format, entry types, and SessionManager API.
+- [Session format](/session-format) - JSONL session file format, entry types, and SessionManager API.
 
 ## Platform setup
 
-- [Windows](windows.md)
-- [Termux on Android](termux.md)
-- [tmux](tmux.md)
-- [Terminal setup](terminal-setup.md)
-- [Shell aliases](shell-aliases.md)
+- [Windows](/windows)
+- [Termux on Android](/termux)
+- [tmux](/tmux)
+- [Terminal setup](/terminal-setup)
+- [Shell aliases](/shell-aliases)
 
 ## Development
 
-- [Development](development.md) - local setup, project structure, and debugging.
+- [Development](/development) - local setup, project structure, and debugging.

package/docs/providers.md

@@ -229,9 +229,9 @@ Or set `GOOGLE_APPLICATION_CREDENTIALS` to a service account key file.
 
 ## Custom Providers
 
-**Via models.json:** Add Ollama, LM Studio, vLLM, or any provider that speaks a supported API (OpenAI Completions, OpenAI Responses, Anthropic Messages, Google Generative AI). See [models.md](models.md).
+**Via models.json:** Add Ollama, LM Studio, vLLM, or any provider that speaks a supported API (OpenAI Completions, OpenAI Responses, Anthropic Messages, Google Generative AI). See [Custom models](/models).
 
-**Via extensions:** For providers that need custom API implementations or OAuth flows, create an extension. See [custom-provider.md](custom-provider.md) and [examples/extensions/custom-provider-gitlab-duo](https://github.com/flora131/atomic/tree/main/packages/coding-agent/examples/extensions/custom-provider-gitlab-duo).
+**Via extensions:** For providers that need custom API implementations or OAuth flows, create an extension. See [Custom providers](/custom-provider) and [examples/extensions/custom-provider-gitlab-duo](https://github.com/flora131/atomic/tree/main/packages/coding-agent/examples/extensions/custom-provider-gitlab-duo).
 
 ## Resolution Order
 

package/docs/quickstart.md

@@ -7,7 +7,7 @@ This page gets you from install to a useful first Atomic session.
 - **Node.js 24 LTS or newer** — Atomic requires the latest Node LTS runtime. Check with `node --version`.
 - **A package manager** — use npm (included with Node), pnpm, Yarn, or Bun. Use Bun 1.3.14+ for Bun installs or workflow-authoring examples.
 - **Model-provider access** — bring an API key or sign in with `/login` after startup.
-- **A compatible terminal** — for the best TUI experience, use a terminal with Kitty keyboard protocol support. See [Terminal setup](terminal-setup.md). On Windows, use Git Bash or WSL.
+- **A compatible terminal** — for the best TUI experience, use a terminal with Kitty keyboard protocol support. See [Terminal setup](/terminal-setup). On Windows, use Git Bash or WSL.
 
 ## Install
 
@@ -58,7 +58,7 @@ atomic
 
 You can also run `/login` and select an API-key provider to store the key in `~/.atomic/agent/auth.json`.
 
-See [Providers](providers.md) for all supported providers, environment variables, and cloud-provider setup.
+See [Providers](/providers) for all supported providers, environment variables, and cloud-provider setup.
 
 ## First session
 
@@ -73,7 +73,7 @@ Atomic ships with three workflows you can run immediately. Use `/workflow list`
 | Workflow | When to use | Example |
 |---|---|---|
 | `deep-research-codebase` | Broad, cross-cutting research before you decide what to change. Scout → research-history → parallel specialist waves → aggregator. | `/workflow deep-research-codebase prompt="How do payment retries work end to end?"` |
-| `ralph` | Larger implementation loops with built-in plan → orchestrate → simplify → parallel review iteration. | `/workflow ralph prompt="Implement specs/2026-03-rate-limit.md and validate the behavior" max_loops=5` |
+| `ralph` | Larger implementation loops with built-in plan → orchestrate → simplify → review iteration, plus final PR preparation when repo state, branch target, and GitHub credentials allow it. | `/workflow ralph prompt="Implement specs/2026-03-rate-limit.md and validate the behavior" max_loops=5` |
 | `open-claude-design` | UI and design-system work with generation, critique, and refinement loops; renders a live `preview.html` you can iterate against. | `/workflow open-claude-design prompt="Refresh the settings page hierarchy" output_type=page` |
 
 <p align="center"><img src="images/workflow-list.png" alt="Workflow List" width="600" /></p>
@@ -86,7 +86,7 @@ You can also launch workflows with **natural language** — just describe the ta
 Run a deep codebase research workflow on how the rate limiter behaves under burst traffic.
 ```
 
-Atomic picks the workflow, fills in inputs from the request, and confirms before launch.
+Atomic picks the workflow, fills in inputs from the request, and confirms before launch. Ralph may create a pull request at the end only when the current repository state, remote/branch target, and available GitHub credentials make that safe; otherwise it reports the exact follow-up steps.
 
 ### Monitor and steer a run
 
@@ -101,7 +101,7 @@ Named workflow runs execute in the background. After launch you get a run id; us
 /workflow kill <run-id>           # destructive abort
 ```
 
-Human-in-the-loop prompts (`ctx.ui.input`, `confirm`, `select`, `editor`) surface in the graph viewer, not as chat modals — connect to the run to answer them. See [Workflows](workflows.md) for the full reference and authoring guide.
+Human-in-the-loop prompts (`ctx.ui.input`, `confirm`, `select`, `editor`) surface in the graph viewer, not as chat modals — connect to the run to answer them. See [Workflows](/workflows) for the full reference and authoring guide.
 
 ### Top skills to invoke directly
 
@@ -119,7 +119,7 @@ Use `/skill:research-codebase` for a focused area and `/workflow deep-research-c
 
 ### Create your own workflow in natural language
 
-You do not have to write TypeScript to add a new workflow. Describe what you want in plain chat and Atomic will design and write it for you using the [Workflows](workflows.md) reference as the source of truth:
+You do not have to write TypeScript to add a new workflow. Describe what you want in plain chat and Atomic will design and write it for you using the [Workflows](/workflows) reference as the source of truth:
 
 ```text
 Create a reusable Atomic workflow called review-changes. It takes one
@@ -136,7 +136,7 @@ Atomic will:
 - write a `.atomic/workflows/<name>.ts` definition that uses `defineWorkflow(...).input(...).run(...).compile()`,
 - and reload so you can immediately run it with `/workflow <name>`.
 
-The same plain-chat approach works for editing or hardening an existing workflow — ask Atomic to add a stage, switch a model, save artifacts, or wire in a human approval gate. For the full authoring reference, see [Workflows](workflows.md).
+The same plain-chat approach works for editing or hardening an existing workflow — ask Atomic to add a stage, switch a model, save artifacts, or wire in a human approval gate. For the full authoring reference, see [Workflows](/workflows).
 
 ### Default tools and prompts
 
@@ -229,12 +229,12 @@ Use `--mode json` for JSON event output or `--mode rpc` for process integration.
 
 ## Next steps
 
-- [Using Atomic](usage.md) - interactive mode, slash commands, sessions, context files, and CLI reference.
-- [Workflows](workflows.md) - run, inspect, and author multi-stage automation (including the three built-in workflows).
-- [Skills](skills.md) - reusable expert instructions invoked with `/skill:<name>`.
-- [Providers](providers.md) - authentication and model setup.
-- [Settings](settings.md) - global and project configuration.
-- [Keybindings](keybindings.md) - shortcuts and customization.
-- [Atomic Packages](packages.md) - install shared extensions, skills, prompts, and themes.
+- [Using Atomic](/usage) - interactive mode, slash commands, sessions, context files, and CLI reference.
+- [Workflows](/workflows) - run, inspect, and author multi-stage automation (including the three built-in workflows).
+- [Skills](/skills) - reusable expert instructions invoked with `/skill:<name>`.
+- [Providers](/providers) - authentication and model setup.
+- [Settings](/settings) - global and project configuration.
+- [Keybindings](/keybindings) - shortcuts and customization.
+- [Atomic Packages](/packages) - install shared extensions, skills, prompts, and themes.
 
-Platform notes: [Windows](windows.md), [Termux](termux.md), [tmux](tmux.md), [Terminal setup](terminal-setup.md), [Shell aliases](shell-aliases.md).
+Platform notes: [Windows](/windows), [Termux](/termux), [tmux](/tmux), [Terminal setup](/terminal-setup), [Shell aliases](/shell-aliases).

package/docs/sdk.md

@@ -1,4 +1,4 @@
-> pi can help you use the SDK. Ask it to build an integration for your use case.
+> Atomic can help you use the SDK. Ask it to build an integration for your use case.
 
 # SDK
 
@@ -582,7 +582,7 @@ await loader.reload();
 const { session } = await createAgentSession({ resourceLoader: loader });
 ```
 
-Extensions can register tools, subscribe to events, add commands, and more. See [extensions.md](extensions.md) for the full API.
+Extensions can register tools, subscribe to events, add commands, and more. See [Extensions](/extensions) for the full API.
 
 **Event Bus:** Extensions can communicate via `pi.events`. Pass a shared `eventBus` to `DefaultResourceLoader` if you need to emit or listen from outside:
 
@@ -598,7 +598,7 @@ await loader.reload();
 eventBus.on("my-extension:status", (data) => console.log(data));
 ```
 
-> See [examples/sdk/06-extensions.ts](https://github.com/flora131/atomic/blob/main/packages/coding-agent/examples/sdk/06-extensions.ts) and [docs/extensions.md](extensions.md)
+> See [examples/sdk/06-extensions.ts](https://github.com/flora131/atomic/blob/main/packages/coding-agent/examples/sdk/06-extensions.ts) and [Extensions](/extensions)
 
 ### Skills
 
@@ -781,7 +781,7 @@ sm.branchWithSummary(id, "Summary...");  // Branch with context summary
 sm.createBranchedSession(leafId);       // Extract path to new file
 ```
 
-> See [examples/sdk/11-sessions.ts](https://github.com/flora131/atomic/blob/main/packages/coding-agent/examples/sdk/11-sessions.ts) and [Session Format](session-format.md)
+> See [examples/sdk/11-sessions.ts](https://github.com/flora131/atomic/blob/main/packages/coding-agent/examples/sdk/11-sessions.ts) and [Session Format](/session-format)
 
 ### Settings Management
 
@@ -1074,17 +1074,17 @@ const runtime = await createAgentSessionRuntime(createRuntime, {
 await runRpcMode(runtime);
 ```
 
-See [RPC documentation](rpc.md) for the JSON protocol.
+See [RPC documentation](/rpc) for the JSON protocol.
 
 ## RPC Mode Alternative
 
 For subprocess-based integration without building with the SDK, use the CLI directly:
 
 ```bash
-pi --mode rpc --no-session
+atomic --mode rpc --no-session
 ```
 
-See [RPC documentation](rpc.md) for the JSON protocol.
+See [RPC documentation](/rpc) for the JSON protocol.
 
 The SDK is preferred when:
 - You want type safety
@@ -1140,4 +1140,4 @@ type PromptTemplate
 type Tool
 ```
 
-For extension types, see [extensions.md](extensions.md) for the full API.
+For extension types, see [Extensions](/extensions) for the full API.

package/docs/sessions.md

@@ -16,7 +16,7 @@ atomic --fork <path|id>    # Fork a session file or partial session ID into a ne
 
 Use `/session` in interactive mode to see the current session file, session ID, message count, tokens, and cost.
 
-For the JSONL file format and SessionManager API, see [Session Format](session-format.md).
+For the JSONL file format and SessionManager API, see [Session Format](/session-format).
 
 ## Session Commands
 
@@ -29,7 +29,7 @@ For the JSONL file format and SessionManager API, see [Session Format](session-f
 | `/tree` | Navigate the current session tree |
 | `/fork` | Create a new session from a previous user message |
 | `/clone` | Duplicate the current active branch into a new session |
-| `/compact [prompt]` | Summarize older context; see [Compaction](compaction.md) |
+| `/compact [prompt]` | Summarize older context; see [Compaction](/compaction) |
 | `/export [file]` | Export session to HTML |
 | `/share` | Upload as private GitHub gist with shareable HTML link |
 
@@ -89,7 +89,7 @@ Example shape:
 | Escape/CTRL+C | Cancel |
 | CTRL+O | Cycle filter mode |
 
-Filter modes are: default, no-tools, user-only, labeled-only, and all. Configure the default with `treeFilterMode` in [Settings](settings.md).
+Filter modes are: default, no-tools, user-only, labeled-only, and all. Configure the default with `treeFilterMode` in [Settings](/settings).
 
 ### Selection Behavior
 
@@ -128,10 +128,10 @@ When prompted, choose one of:
 2. summarize with the default prompt
 3. summarize with custom focus instructions
 
-See [Compaction](compaction.md) for branch summarization internals and extension hooks.
+See [Compaction](/compaction) for branch summarization internals and extension hooks.
 
 ## Session Format
 
 Session files are JSONL and contain message entries, model changes, thinking-level changes, labels, compactions, branch summaries, and extension entries.
 
-For parsers, extensions, SDK usage, and the full SessionManager API, see [Session Format](session-format.md).
+For parsers, extensions, SDK usage, and the full SessionManager API, see [Session Format](/session-format).

package/docs/settings.md

@@ -121,6 +121,31 @@ When a provider requests a retry delay longer than `retry.provider.maxRetryDelay
 }
 ```
 
+### HTTP
+
+| Setting | Type | Default | Description |
+|---------|------|---------|-------------|
+| `httpIdleTimeoutMs` | number | `300000` | HTTP header/body idle timeout in milliseconds. Must be a non-negative finite number; decimals are rounded down. Set to `0` to disable the idle timeout. |
+
+Atomic applies this timeout to the global HTTP dispatcher used by `fetch` and provider SDK HTTP clients. The default is 300,000 ms (5 minutes), which keeps long-running requests working while reclaiming stale idle connections.
+
+The `/settings` picker offers these presets:
+
+| Label | Value |
+|-------|-------|
+| `30 sec` | `30000` |
+| `1 min` | `60000` |
+| `5 min` | `300000` |
+| `10 min` | `600000` |
+| `30 min` | `1800000` |
+| `Disabled` | `0` |
+
+```json
+{
+  "httpIdleTimeoutMs": 300000
+}
+```
+
 ### Message Delivery
 
 | Setting | Type | Default | Description |
@@ -230,7 +255,7 @@ Object form filters which resources to load:
 }
 ```
 
-See [packages.md](packages.md) for package management details.
+See [Atomic packages](/packages) for package management details.
 
 ## Example
 
@@ -249,6 +274,7 @@ See [packages.md](packages.md) for package management details.
     "enabled": true,
     "maxRetries": 3
   },
+  "httpIdleTimeoutMs": 300000,
   "enabledModels": ["claude-*", "gpt-4o"],
   "warnings": {
     "anthropicExtraUsage": true

package/docs/skills.md

@@ -135,10 +135,10 @@ cd /path/to/skill && pnpm install
 ```
 ````
 
-Use relative paths from the skill directory:
+Use relative file paths from the skill directory (these are bundled skill files, not docs routes):
 
 ```markdown
-See [the reference guide](references/REFERENCE.md) for details.
+See the API reference at `references/api-reference.md` for details.
 ```
 
 ## Frontmatter