pllan 2026.3.47 → 2026.3.49

package/docs/sv/help/faq.md

@@ -8,7 +8,7 @@ title: "FAQ"
 
 # FAQ
 
-Quick answers plus deeper troubleshooting for real-world setups (local dev, VPS, multi-agent, OAuth/API keys, model failover). For runtime diagnostics, see [Troubleshooting](/gateway/troubleshooting). For the full config reference, see [Configuration](/gateway/configuration).
+Quick answers plus deeper troubleshooting for real-world setups (local dev, VPS, multi-agent, OAuth/API keys, model failover). For runtime diagnostics, see [Troubleshooting](/sv/gateway/troubleshooting). For the full config reference, see [Configuration](/sv/gateway/configuration).
 
 ## First 60 seconds if something is broken
 
@@ -42,7 +42,7 @@ Quick answers plus deeper troubleshooting for real-world setups (local dev, VPS,
    pllan status --deep
    ```
 
-   Runs gateway health checks + provider probes (requires a reachable gateway). See [Health](/gateway/health).
+   Runs gateway health checks + provider probes (requires a reachable gateway). See [Health](/sv/gateway/health).
 
 5. **Tail the latest log**
 
@@ -56,7 +56,7 @@ Quick answers plus deeper troubleshooting for real-world setups (local dev, VPS,
    tail -f "$(ls -t /tmp/pllan/pllan-*.log | head -1)"
    ```
 
-   File logs are separate from service logs; see [Logging](/logging) and [Troubleshooting](/gateway/troubleshooting).
+   File logs are separate from service logs; see [Logging](/sv/logging) and [Troubleshooting](/sv/gateway/troubleshooting).
 
 6. **Run the doctor (repairs)**
 
@@ -64,7 +64,7 @@ Quick answers plus deeper troubleshooting for real-world setups (local dev, VPS,
    pllan doctor
    ```
 
-   Repairs/migrates config/state + runs health checks. See [Doctor](/gateway/doctor).
+   Repairs/migrates config/state + runs health checks. See [Doctor](/sv/gateway/doctor).
 
 7. **Gateway snapshot**
 
@@ -73,7 +73,7 @@ Quick answers plus deeper troubleshooting for real-world setups (local dev, VPS,
    pllan health --verbose   # shows the target URL + config path on errors
    ```
 
-   Asks the running gateway for a full snapshot (WS-only). See [Health](/gateway/health).
+   Asks the running gateway for a full snapshot (WS-only). See [Health](/sv/gateway/health).
 
 ## Quick start and first-run setup
 
@@ -123,7 +123,7 @@ Quick answers plus deeper troubleshooting for real-world setups (local dev, VPS,
     `pllan gateway status`, `pllan health --verbose`.
 
     Quick debug loop: [First 60 seconds if something is broken](#first-60-seconds-if-something-is-broken).
-    Install docs: [Install](/install), [Installer flags](/install/installer), [Updating](/install/updating).
+    Install docs: [Install](/sv/install), [Installer flags](/sv/install/installer), [Updating](/sv/install/updating).
 
   </Accordion>
 
@@ -169,7 +169,7 @@ Quick answers plus deeper troubleshooting for real-world setups (local dev, VPS,
     - **Tailnet bind**: run `pllan gateway --bind tailnet --token "<token>"`, open `http://<tailscale-ip>:18789/`, paste token in dashboard settings.
     - **SSH tunnel**: `ssh -N -L 18789:127.0.0.1:18789 user@host` then open `http://127.0.0.1:18789/` and paste the token in Control UI settings.
 
-    See [Dashboard](/web/dashboard) and [Web surfaces](/web) for bind modes and auth details.
+    See [Dashboard](/sv/web/dashboard) and [Web surfaces](/sv/web) for bind modes and auth details.
 
   </Accordion>
 
@@ -185,7 +185,7 @@ Quick answers plus deeper troubleshooting for real-world setups (local dev, VPS,
     not a hard minimum.
 
     Tip: a small Pi/VPS can host the Gateway, and you can pair **nodes** on your laptop/phone for
-    local screen/camera/canvas or command execution. See [Nodes](/nodes).
+    local screen/camera/canvas or command execution. See [Nodes](/sv/nodes).
 
   </Accordion>
 
@@ -197,7 +197,7 @@ Quick answers plus deeper troubleshooting for real-world setups (local dev, VPS,
     - Start without channels/skills, then add them one by one.
     - If you hit weird binary issues, it is usually an **ARM compatibility** problem.
 
-    Docs: [Linux](/platforms/linux), [Install](/install).
+    Docs: [Linux](/sv/platforms/linux), [Install](/sv/install).
 
   </Accordion>
 
@@ -227,7 +227,7 @@ Quick answers plus deeper troubleshooting for real-world setups (local dev, VPS,
     ```
 
     If the Gateway is remote, ensure the tunnel/Tailscale connection is up and that the UI
-    is pointed at the right Gateway. See [Remote access](/gateway/remote).
+    is pointed at the right Gateway. See [Remote access](/sv/gateway/remote).
 
   </Accordion>
 
@@ -248,9 +248,9 @@ Quick answers plus deeper troubleshooting for real-world setups (local dev, VPS,
     up **memory + bootstrap files**, but **not** session history or auth. Those live
     under `~/.pllan/` (for example `~/.pllan/agents/<agentId>/sessions/`).
 
-    Related: [Migrating](/install/migrating), [Where things live on disk](#where-things-live-on-disk),
-    [Agent workspace](/concepts/agent-workspace), [Doctor](/gateway/doctor),
-    [Remote mode](/gateway/remote).
+    Related: [Migrating](/sv/install/migrating), [Where things live on disk](#where-things-live-on-disk),
+    [Agent workspace](/sv/concepts/agent-workspace), [Doctor](/sv/gateway/doctor),
+    [Remote mode](/sv/gateway/remote).
 
   </Accordion>
 
@@ -267,7 +267,7 @@ Quick answers plus deeper troubleshooting for real-world setups (local dev, VPS,
   <Accordion title="Cannot access docs.pllan.ai (SSL error)">
     Some Comcast/Xfinity connections incorrectly block `docs.pllan.ai` via Xfinity
     Advanced Security. Disable it or allowlist `docs.pllan.ai`, then retry. More
-    detail: [Troubleshooting](/help/faq#docspllanai-shows-an-ssl-error-comcast-xfinity).
+    detail: [Troubleshooting](/sv/help/faq#docspllanai-shows-an-ssl-error-comcast-xfinity).
     Please help us unblock it by reporting here: [https://spa.xfinity.com/check_url_status](https://spa.xfinity.com/check_url_status).
 
     If you still can't reach the site, the docs are mirrored on GitHub:
@@ -307,7 +307,7 @@ Quick answers plus deeper troubleshooting for real-world setups (local dev, VPS,
     Windows installer (PowerShell):
     [https://pllan.ai/install.ps1](https://pllan.ai/install.ps1)
 
-    More detail: [Development channels](/install/development-channels) and [Installer flags](/install/installer).
+    More detail: [Development channels](/sv/install/development-channels) and [Installer flags](/sv/install/installer).
 
   </Accordion>
 
@@ -339,8 +339,8 @@ Quick answers plus deeper troubleshooting for real-world setups (local dev, VPS,
     pnpm build
     ```
 
-    Docs: [Update](/cli/update), [Development channels](/install/development-channels),
-    [Install](/install).
+    Docs: [Update](/sv/cli/update), [Development channels](/sv/install/development-channels),
+    [Install](/sv/install).
 
   </Accordion>
 
@@ -383,7 +383,7 @@ Quick answers plus deeper troubleshooting for real-world setups (local dev, VPS,
     Set-PSDebug -Trace 0
     ```
 
-    More options: [Installer flags](/install/installer).
+    More options: [Installer flags](/sv/install/installer).
 
   </Accordion>
 
@@ -408,7 +408,7 @@ Quick answers plus deeper troubleshooting for real-world setups (local dev, VPS,
     - Close and reopen PowerShell after updating PATH.
 
     If you want the smoothest Windows setup, use **WSL2** instead of native Windows.
-    Docs: [Windows](/platforms/windows).
+    Docs: [Windows](/sv/platforms/windows).
 
   </Accordion>
 
@@ -449,34 +449,34 @@ Quick answers plus deeper troubleshooting for real-world setups (local dev, VPS,
     curl -fsSL https://pllan.ai/install.sh | bash -s -- --install-method git
     ```
 
-    More detail: [Install](/install) and [Installer flags](/install/installer).
+    More detail: [Install](/sv/install) and [Installer flags](/sv/install/installer).
 
   </Accordion>
 
   <Accordion title="How do I install Pllan on Linux?">
     Short answer: follow the Linux guide, then run onboarding.
 
-    - Linux quick path + service install: [Linux](/platforms/linux).
-    - Full walkthrough: [Getting Started](/start/getting-started).
-    - Installer + updates: [Install & updates](/install/updating).
+    - Linux quick path + service install: [Linux](/sv/platforms/linux).
+    - Full walkthrough: [Getting Started](/sv/start/getting-started).
+    - Installer + updates: [Install & updates](/sv/install/updating).
 
   </Accordion>
 
   <Accordion title="How do I install Pllan on a VPS?">
     Any Linux VPS works. Install on the server, then use SSH/Tailscale to reach the Gateway.
 
-    Guides: [exe.dev](/install/exe-dev), [Hetzner](/install/hetzner), [Fly.io](/install/fly).
-    Remote access: [Gateway remote](/gateway/remote).
+    Guides: [exe.dev](/sv/install/exe-dev), [Hetzner](/sv/install/hetzner), [Fly.io](/sv/install/fly).
+    Remote access: [Gateway remote](/sv/gateway/remote).
 
   </Accordion>
 
   <Accordion title="Where are the cloud/VPS install guides?">
     We keep a **hosting hub** with the common providers. Pick one and follow the guide:
 
-    - [VPS hosting](/vps) (all providers in one place)
-    - [Fly.io](/install/fly)
-    - [Hetzner](/install/hetzner)
-    - [exe.dev](/install/exe-dev)
+    - [VPS hosting](/sv/vps) (all providers in one place)
+    - [Fly.io](/sv/install/fly)
+    - [Hetzner](/sv/install/hetzner)
+    - [exe.dev](/sv/install/exe-dev)
 
     How it works in the cloud: the **Gateway runs on the server**, and you access it
     from your laptop/phone via the Control UI (or Tailscale/SSH). Your state + workspace
@@ -486,8 +486,8 @@ Quick answers plus deeper troubleshooting for real-world setups (local dev, VPS,
     local screen/camera/canvas or run commands on your laptop while keeping the
     Gateway in the cloud.
 
-    Hub: [Platforms](/platforms). Remote access: [Gateway remote](/gateway/remote).
-    Nodes: [Nodes](/nodes), [Nodes CLI](/cli/nodes).
+    Hub: [Platforms](/sv/platforms). Remote access: [Gateway remote](/sv/gateway/remote).
+    Nodes: [Nodes](/sv/nodes), [Nodes CLI](/sv/cli/nodes).
 
   </Accordion>
 
@@ -513,7 +513,7 @@ Quick answers plus deeper troubleshooting for real-world setups (local dev, VPS,
     pllan gateway restart
     ```
 
-    Docs: [Update](/cli/update), [Updating](/install/updating).
+    Docs: [Update](/sv/cli/update), [Updating](/sv/install/updating).
 
   </Accordion>
 
@@ -540,8 +540,8 @@ Quick answers plus deeper troubleshooting for real-world setups (local dev, VPS,
     Anthropic has blocked some subscription usage outside Claude Code in the past.
     OpenAI Codex OAuth is explicitly supported for external tools like Pllan.
 
-    Docs: [Anthropic](/providers/anthropic), [OpenAI](/providers/openai),
-    [Local models](/gateway/local-models), [Models](/concepts/models).
+    Docs: [Anthropic](/sv/providers/anthropic), [OpenAI](/sv/providers/openai),
+    [Local models](/sv/gateway/local-models), [Models](/sv/concepts/models).
 
   </Accordion>
 
@@ -557,7 +557,7 @@ Quick answers plus deeper troubleshooting for real-world setups (local dev, VPS,
   </Accordion>
 
   <Accordion title="How does Anthropic setup-token auth work?">
-    `claude setup-token` generates a **token string** via the Claude Code CLI (it is not available in the web console). You can run it on **any machine**. Choose **Anthropic token (paste setup-token)** in onboarding or paste it with `pllan models auth paste-token --provider anthropic`. The token is stored as an auth profile for the **anthropic** provider and used like an API key (no auto-refresh). More detail: [OAuth](/concepts/oauth).
+    `claude setup-token` generates a **token string** via the Claude Code CLI (it is not available in the web console). You can run it on **any machine**. Choose **Anthropic token (paste setup-token)** in onboarding or paste it with `pllan models auth paste-token --provider anthropic`. The token is stored as an auth profile for the **anthropic** provider and used like an API key (no auto-refresh). More detail: [OAuth](/sv/concepts/oauth).
   </Accordion>
 
   <Accordion title="Where do I find an Anthropic setup-token?">
@@ -567,12 +567,12 @@ Quick answers plus deeper troubleshooting for real-world setups (local dev, VPS,
     claude setup-token
     ```
 
-    Copy the token it prints, then choose **Anthropic token (paste setup-token)** in onboarding. If you want to run it on the gateway host, use `pllan models auth setup-token --provider anthropic`. If you ran `claude setup-token` elsewhere, paste it on the gateway host with `pllan models auth paste-token --provider anthropic`. See [Anthropic](/providers/anthropic).
+    Copy the token it prints, then choose **Anthropic token (paste setup-token)** in onboarding. If you want to run it on the gateway host, use `pllan models auth setup-token --provider anthropic`. If you ran `claude setup-token` elsewhere, paste it on the gateway host with `pllan models auth paste-token --provider anthropic`. See [Anthropic](/sv/providers/anthropic).
 
   </Accordion>
 
   <Accordion title="Do you support Claude subscription auth (Claude Pro or Max)?">
-    Yes - via **setup-token**. Pllan no longer reuses Claude Code CLI OAuth tokens; use a setup-token or an Anthropic API key. Generate the token anywhere and paste it on the gateway host. See [Anthropic](/providers/anthropic) and [OAuth](/concepts/oauth).
+    Yes - via **setup-token**. Pllan no longer reuses Claude Code CLI OAuth tokens; use a setup-token or an Anthropic API key. Generate the token anywhere and paste it on the gateway host. See [Anthropic](/sv/providers/anthropic) and [OAuth](/sv/concepts/oauth).
 
     Important: this is technical compatibility, not a policy guarantee. Anthropic
     has blocked some subscription usage outside Claude Code in the past.
@@ -594,17 +594,17 @@ Quick answers plus deeper troubleshooting for real-world setups (local dev, VPS,
     with Extra Usage enabled).
 
     Tip: set a **fallback model** so Pllan can keep replying while a provider is rate-limited.
-    See [Models](/cli/models), [OAuth](/concepts/oauth), and
-    [/gateway/troubleshooting#anthropic-429-extra-usage-required-for-long-context](/gateway/troubleshooting#anthropic-429-extra-usage-required-for-long-context).
+    See [Models](/sv/cli/models), [OAuth](/sv/concepts/oauth), and
+    [/gateway/troubleshooting#anthropic-429-extra-usage-required-for-long-context](/sv/gateway/troubleshooting#anthropic-429-extra-usage-required-for-long-context).
 
   </Accordion>
 
   <Accordion title="Is AWS Bedrock supported?">
-    Yes - via pi-ai's **Amazon Bedrock (Converse)** provider with **manual config**. You must supply AWS credentials/region on the gateway host and add a Bedrock provider entry in your models config. See [Amazon Bedrock](/providers/bedrock) and [Model providers](/providers/models). If you prefer a managed key flow, an OpenAI-compatible proxy in front of Bedrock is still a valid option.
+    Yes - via pi-ai's **Amazon Bedrock (Converse)** provider with **manual config**. You must supply AWS credentials/region on the gateway host and add a Bedrock provider entry in your models config. See [Amazon Bedrock](/sv/providers/bedrock) and [Model providers](/sv/providers/models). If you prefer a managed key flow, an OpenAI-compatible proxy in front of Bedrock is still a valid option.
   </Accordion>
 
   <Accordion title="How does Codex auth work?">
-    Pllan supports **OpenAI Code (Codex)** via OAuth (ChatGPT sign-in). Onboarding can run the OAuth flow and will set the default model to `openai-codex/gpt-5.4` when appropriate. See [Model providers](/concepts/model-providers) and [Onboarding (CLI)](/start/wizard).
+    Pllan supports **OpenAI Code (Codex)** via OAuth (ChatGPT sign-in). Onboarding can run the OAuth flow and will set the default model to `openai-codex/gpt-5.4` when appropriate. See [Model providers](/sv/concepts/model-providers) and [Onboarding (CLI)](/sv/start/wizard).
   </Accordion>
 
   <Accordion title="Do you support OpenAI subscription auth (Codex OAuth)?">
@@ -612,7 +612,7 @@ Quick answers plus deeper troubleshooting for real-world setups (local dev, VPS,
     OpenAI explicitly allows subscription OAuth usage in external tools/workflows
     like Pllan. Onboarding can run the OAuth flow for you.
 
-    See [OAuth](/concepts/oauth), [Model providers](/concepts/model-providers), and [Onboarding (CLI)](/start/wizard).
+    See [OAuth](/sv/concepts/oauth), [Model providers](/sv/concepts/model-providers), and [Onboarding (CLI)](/sv/start/wizard).
 
   </Accordion>
 
@@ -624,12 +624,12 @@ Quick answers plus deeper troubleshooting for real-world setups (local dev, VPS,
     1. Enable the plugin: `pllan plugins enable google`
     2. Login: `pllan models auth login --provider google-gemini-cli --set-default`
 
-    This stores OAuth tokens in auth profiles on the gateway host. Details: [Model providers](/concepts/model-providers).
+    This stores OAuth tokens in auth profiles on the gateway host. Details: [Model providers](/sv/concepts/model-providers).
 
   </Accordion>
 
   <Accordion title="Is a local model OK for casual chats?">
-    Usually no. Pllan needs large context + strong safety; small cards truncate and leak. If you must, run the **largest** MiniMax M2.5 build you can locally (LM Studio) and see [/gateway/local-models](/gateway/local-models). Smaller/quantized models increase prompt-injection risk - see [Security](/gateway/security).
+    Usually no. Pllan needs large context + strong safety; small cards truncate and leak. If you must, run the **largest** MiniMax M2.5 build you can locally (LM Studio) and see [/gateway/local-models](/sv/gateway/local-models). Smaller/quantized models increase prompt-injection risk - see [Security](/sv/gateway/security).
   </Accordion>
 
   <Accordion title="How do I keep hosted model traffic in a specific region?">
@@ -640,23 +640,23 @@ Quick answers plus deeper troubleshooting for real-world setups (local dev, VPS,
     No. Pllan runs on macOS or Linux (Windows via WSL2). A Mac mini is optional - some people
     buy one as an always-on host, but a small VPS, home server, or Raspberry Pi-class box works too.
 
-    You only need a Mac **for macOS-only tools**. For iMessage, use [BlueBubbles](/channels/bluebubbles) (recommended) - the BlueBubbles server runs on any Mac, and the Gateway can run on Linux or elsewhere. If you want other macOS-only tools, run the Gateway on a Mac or pair a macOS node.
+    You only need a Mac **for macOS-only tools**. For iMessage, use [BlueBubbles](/sv/channels/bluebubbles) (recommended) - the BlueBubbles server runs on any Mac, and the Gateway can run on Linux or elsewhere. If you want other macOS-only tools, run the Gateway on a Mac or pair a macOS node.
 
-    Docs: [BlueBubbles](/channels/bluebubbles), [Nodes](/nodes), [Mac remote mode](/platforms/mac/remote).
+    Docs: [BlueBubbles](/sv/channels/bluebubbles), [Nodes](/sv/nodes), [Mac remote mode](/sv/platforms/mac/remote).
 
   </Accordion>
 
   <Accordion title="Do I need a Mac mini for iMessage support?">
     You need **some macOS device** signed into Messages. It does **not** have to be a Mac mini -
-    any Mac works. **Use [BlueBubbles](/channels/bluebubbles)** (recommended) for iMessage - the BlueBubbles server runs on macOS, while the Gateway can run on Linux or elsewhere.
+    any Mac works. **Use [BlueBubbles](/sv/channels/bluebubbles)** (recommended) for iMessage - the BlueBubbles server runs on macOS, while the Gateway can run on Linux or elsewhere.
 
     Common setups:
 
     - Run the Gateway on Linux/VPS, and run the BlueBubbles server on any Mac signed into Messages.
     - Run everything on the Mac if you want the simplest single-machine setup.
 
-    Docs: [BlueBubbles](/channels/bluebubbles), [Nodes](/nodes),
-    [Mac remote mode](/platforms/mac/remote).
+    Docs: [BlueBubbles](/sv/channels/bluebubbles), [Nodes](/sv/nodes),
+    [Mac remote mode](/sv/platforms/mac/remote).
 
   </Accordion>
 
@@ -671,7 +671,7 @@ Quick answers plus deeper troubleshooting for real-world setups (local dev, VPS,
     - MacBook Pro runs the macOS app or a node host and pairs to the Gateway.
     - Use `pllan nodes status` / `pllan nodes list` to see it.
 
-    Docs: [Nodes](/nodes), [Nodes CLI](/cli/nodes).
+    Docs: [Nodes](/sv/nodes), [Nodes CLI](/sv/cli/nodes).
 
   </Accordion>
 
@@ -701,16 +701,16 @@ Quick answers plus deeper troubleshooting for real-world setups (local dev, VPS,
 
     - DM `@userinfobot` or `@getidsbot`.
 
-    See [/channels/telegram](/channels/telegram#access-control-and-activation).
+    See [/channels/telegram](/sv/channels/telegram#access-control-and-activation).
 
   </Accordion>
 
   <Accordion title="Can multiple people use one WhatsApp number with different Pllan instances?">
-    Yes, via **multi-agent routing**. Bind each sender's WhatsApp **DM** (peer `kind: "direct"`, sender E.164 like `+15551234567`) to a different `agentId`, so each person gets their own workspace and session store. Replies still come from the **same WhatsApp account**, and DM access control (`channels.whatsapp.dmPolicy` / `channels.whatsapp.allowFrom`) is global per WhatsApp account. See [Multi-Agent Routing](/concepts/multi-agent) and [WhatsApp](/channels/whatsapp).
+    Yes, via **multi-agent routing**. Bind each sender's WhatsApp **DM** (peer `kind: "direct"`, sender E.164 like `+15551234567`) to a different `agentId`, so each person gets their own workspace and session store. Replies still come from the **same WhatsApp account**, and DM access control (`channels.whatsapp.dmPolicy` / `channels.whatsapp.allowFrom`) is global per WhatsApp account. See [Multi-Agent Routing](/sv/concepts/multi-agent) and [WhatsApp](/sv/channels/whatsapp).
   </Accordion>
 
   <Accordion title='Can I run a "fast chat" agent and an "Opus for coding" agent?'>
-    Yes. Use multi-agent routing: give each agent its own default model, then bind inbound routes (provider account or specific peers) to each agent. Example config lives in [Multi-Agent Routing](/concepts/multi-agent). See also [Models](/concepts/models) and [Configuration](/gateway/configuration).
+    Yes. Use multi-agent routing: give each agent its own default model, then bind inbound routes (provider account or specific peers) to each agent. Example config lives in [Multi-Agent Routing](/sv/concepts/multi-agent). See also [Models](/sv/concepts/models) and [Configuration](/sv/gateway/configuration).
   </Accordion>
 
   <Accordion title="Does Homebrew work on Linux?">
@@ -734,7 +734,7 @@ Quick answers plus deeper troubleshooting for real-world setups (local dev, VPS,
     - **npm install:** global CLI install, no repo, best for "just run it."
       Updates come from npm dist-tags.
 
-    Docs: [Getting started](/start/getting-started), [Updating](/install/updating).
+    Docs: [Getting started](/sv/start/getting-started), [Updating](/sv/install/updating).
 
   </Accordion>
 
@@ -782,7 +782,7 @@ Quick answers plus deeper troubleshooting for real-world setups (local dev, VPS,
     - **Pros:** always-on, stable network, no laptop sleep issues, easier to keep running.
     - **Cons:** often run headless (use screenshots), remote file access only, you must SSH for updates.
 
-    **Pllan-specific note:** WhatsApp/Telegram/Slack/Mattermost (plugin)/Discord all work fine from a VPS. The only real trade-off is **headless browser** vs a visible window. See [Browser](/tools/browser).
+    **Pllan-specific note:** WhatsApp/Telegram/Slack/Mattermost (plugin)/Discord all work fine from a VPS. The only real trade-off is **headless browser** vs a visible window. See [Browser](/sv/tools/browser).
 
     **Recommended default:** VPS if you had gateway disconnects before. Local is great when you're actively using the Mac and want local file access or UI automation with a visible browser.
 
@@ -794,8 +794,8 @@ Quick answers plus deeper troubleshooting for real-world setups (local dev, VPS,
     - **Dedicated host (VPS/Mac mini/Pi):** always-on, fewer sleep/reboot interruptions, cleaner permissions, easier to keep running.
     - **Shared laptop/desktop:** totally fine for testing and active use, but expect pauses when the machine sleeps or updates.
 
-    If you want the best of both worlds, keep the Gateway on a dedicated host and pair your laptop as a **node** for local screen/camera/exec tools. See [Nodes](/nodes).
-    For security guidance, read [Security](/gateway/security).
+    If you want the best of both worlds, keep the Gateway on a dedicated host and pair your laptop as a **node** for local screen/camera/exec tools. See [Nodes](/sv/nodes).
+    For security guidance, read [Security](/sv/gateway/security).
 
   </Accordion>
 
@@ -807,7 +807,7 @@ Quick answers plus deeper troubleshooting for real-world setups (local dev, VPS,
 
     OS: use **Ubuntu LTS** (or any modern Debian/Ubuntu). The Linux install path is best tested there.
 
-    Docs: [Linux](/platforms/linux), [VPS hosting](/vps).
+    Docs: [Linux](/sv/platforms/linux), [VPS hosting](/sv/vps).
 
   </Accordion>
 
@@ -822,8 +822,8 @@ Quick answers plus deeper troubleshooting for real-world setups (local dev, VPS,
     - **OS:** Ubuntu LTS or another modern Debian/Ubuntu.
 
     If you are on Windows, **WSL2 is the easiest VM style setup** and has the best tooling
-    compatibility. See [Windows](/platforms/windows), [VPS hosting](/vps).
-    If you are running macOS in a VM, see [macOS VM](/install/macos-vm).
+    compatibility. See [Windows](/sv/platforms/windows), [VPS hosting](/sv/vps).
+    If you are running macOS in a VM, see [macOS VM](/sv/install/macos-vm).
 
   </Accordion>
 </AccordionGroup>
@@ -854,8 +854,8 @@ Quick answers plus deeper troubleshooting for real-world setups (local dev, VPS,
       workspace and defaults.
     - **Open source and hackable:** inspect, extend, and self-host without vendor lock-in.
 
-    Docs: [Gateway](/gateway), [Channels](/channels), [Multi-agent](/concepts/multi-agent),
-    [Memory](/concepts/memory).
+    Docs: [Gateway](/sv/gateway), [Channels](/sv/channels), [Multi-agent](/sv/concepts/multi-agent),
+    [Memory](/sv/concepts/memory).
 
   </Accordion>
 
@@ -891,7 +891,7 @@ Quick answers plus deeper troubleshooting for real-world setups (local dev, VPS,
     platform policies, and review anything before it is sent. The safest pattern is to let
     Pllan draft and you approve.
 
-    Docs: [Security](/gateway/security).
+    Docs: [Security](/sv/gateway/security).
 
   </Accordion>
 
@@ -931,7 +931,7 @@ Quick answers plus deeper troubleshooting for real-world setups (local dev, VPS,
     - **Sub-agents**: route tasks to separate agents with different default models.
     - **On-demand switch**: use `/model` to switch the current session model at any time.
 
-    See [Cron jobs](/automation/cron-jobs), [Multi-Agent Routing](/concepts/multi-agent), and [Slash commands](/tools/slash-commands).
+    See [Cron jobs](/sv/automation/cron-jobs), [Multi-Agent Routing](/sv/concepts/multi-agent), and [Slash commands](/sv/tools/slash-commands).
 
   </Accordion>
 
@@ -945,7 +945,7 @@ Quick answers plus deeper troubleshooting for real-world setups (local dev, VPS,
     Token tip: long tasks and sub-agents both consume tokens. If cost is a concern, set a
     cheaper model for sub-agents via `agents.defaults.subagents.model`.
 
-    Docs: [Sub-agents](/tools/subagents).
+    Docs: [Sub-agents](/sv/tools/subagents).
 
   </Accordion>
 
@@ -966,7 +966,7 @@ Quick answers plus deeper troubleshooting for real-world setups (local dev, VPS,
     - Discord overrides: `channels.discord.threadBindings.enabled`, `channels.discord.threadBindings.idleHours`, `channels.discord.threadBindings.maxAgeHours`.
     - Auto-bind on spawn: set `channels.discord.threadBindings.spawnSubagentSessions: true`.
 
-    Docs: [Sub-agents](/tools/subagents), [Discord](/channels/discord), [Configuration Reference](/gateway/configuration-reference), [Slash commands](/tools/slash-commands).
+    Docs: [Sub-agents](/sv/tools/subagents), [Discord](/sv/channels/discord), [Configuration Reference](/sv/gateway/configuration-reference), [Slash commands](/sv/tools/slash-commands).
 
   </Accordion>
 
@@ -987,7 +987,7 @@ Quick answers plus deeper troubleshooting for real-world setups (local dev, VPS,
     pllan cron runs --id <jobId> --limit 50
     ```
 
-    Docs: [Cron jobs](/automation/cron-jobs), [Cron vs Heartbeat](/automation/cron-vs-heartbeat).
+    Docs: [Cron jobs](/sv/automation/cron-jobs), [Cron vs Heartbeat](/sv/automation/cron-vs-heartbeat).
 
   </Accordion>
 
@@ -1014,8 +1014,8 @@ Quick answers plus deeper troubleshooting for real-world setups (local dev, VPS,
     - **Heartbeat** for "main session" periodic checks.
     - **Isolated jobs** for autonomous agents that post summaries or deliver to chats.
 
-    Docs: [Cron jobs](/automation/cron-jobs), [Cron vs Heartbeat](/automation/cron-vs-heartbeat),
-    [Heartbeat](/gateway/heartbeat).
+    Docs: [Cron jobs](/sv/automation/cron-jobs), [Cron vs Heartbeat](/sv/automation/cron-vs-heartbeat),
+    [Heartbeat](/sv/gateway/heartbeat).
 
   </Accordion>
 
@@ -1079,7 +1079,7 @@ Quick answers plus deeper troubleshooting for real-world setups (local dev, VPS,
     clawhub update --all
     ```
 
-    ClawHub installs into `./skills` under your current directory (or falls back to your configured Pllan workspace); Pllan treats that as `<workspace>/skills` on the next session. For shared skills across agents, place them in `~/.pllan/skills/<name>/SKILL.md`. Some skills expect binaries installed via Homebrew; on Linux that means Linuxbrew (see the Homebrew Linux FAQ entry above). See [Skills](/tools/skills) and [ClawHub](/tools/clawhub).
+    ClawHub installs into `./skills` under your current directory (or falls back to your configured Pllan workspace); Pllan treats that as `<workspace>/skills` on the next session. For shared skills across agents, place them in `~/.pllan/skills/<name>/SKILL.md`. Some skills expect binaries installed via Homebrew; on Linux that means Linuxbrew (see the Homebrew Linux FAQ entry above). See [Skills](/sv/tools/skills) and [ClawHub](/sv/tools/clawhub).
 
   </Accordion>
 
@@ -1107,7 +1107,7 @@ Quick answers plus deeper troubleshooting for real-world setups (local dev, VPS,
 
 <AccordionGroup>
   <Accordion title="Is there a dedicated sandboxing doc?">
-    Yes. See [Sandboxing](/gateway/sandboxing). For Docker-specific setup (full gateway in Docker or sandbox images), see [Docker](/install/docker).
+    Yes. See [Sandboxing](/sv/gateway/sandboxing). For Docker-specific setup (full gateway in Docker or sandbox images), see [Docker](/sv/install/docker).
   </Accordion>
 
   <Accordion title="Docker feels limited - how do I enable full features?">
@@ -1120,7 +1120,7 @@ Quick answers plus deeper troubleshooting for real-world setups (local dev, VPS,
       `node /app/node_modules/playwright-core/cli.js install chromium`
     - Set `PLAYWRIGHT_BROWSERS_PATH` and ensure the path is persisted.
 
-    Docs: [Docker](/install/docker), [Browser](/tools/browser).
+    Docs: [Docker](/sv/install/docker), [Browser](/sv/tools/browser).
 
   </Accordion>
 
@@ -1129,14 +1129,14 @@ Quick answers plus deeper troubleshooting for real-world setups (local dev, VPS,
 
     Use `agents.defaults.sandbox.mode: "non-main"` so group/channel sessions (non-main keys) run in Docker, while the main DM session stays on-host. Then restrict what tools are available in sandboxed sessions via `tools.sandbox.tools`.
 
-    Setup walkthrough + example config: [Groups: personal DMs + public groups](/channels/groups#pattern-personal-dms-public-groups-single-agent)
+    Setup walkthrough + example config: [Groups: personal DMs + public groups](/sv/channels/groups#pattern-personal-dms-public-groups-single-agent)
 
-    Key config reference: [Gateway configuration](/gateway/configuration-reference#agents-defaults-sandbox)
+    Key config reference: [Gateway configuration](/sv/gateway/configuration-reference#agents-defaults-sandbox)
 
   </Accordion>
 
   <Accordion title="How do I bind a host folder into the sandbox?">
-    Set `agents.defaults.sandbox.docker.binds` to `["host:path:mode"]` (e.g., `"/home/user/src:/src:ro"`). Global + per-agent binds merge; per-agent binds are ignored when `scope: "shared"`. Use `:ro` for anything sensitive and remember binds bypass the sandbox filesystem walls. See [Sandboxing](/gateway/sandboxing#custom-bind-mounts) and [Sandbox vs Tool Policy vs Elevated](/gateway/sandbox-vs-tool-policy-vs-elevated#bind-mounts-security-quick-check) for examples and safety notes.
+    Set `agents.defaults.sandbox.docker.binds` to `["host:path:mode"]` (e.g., `"/home/user/src:/src:ro"`). Global + per-agent binds merge; per-agent binds are ignored when `scope: "shared"`. Use `:ro` for anything sensitive and remember binds bypass the sandbox filesystem walls. See [Sandboxing](/sv/gateway/sandboxing#custom-bind-mounts) and [Sandbox vs Tool Policy vs Elevated](/sv/gateway/sandbox-vs-tool-policy-vs-elevated#bind-mounts-security-quick-check) for examples and safety notes.
   </Accordion>
 
   <Accordion title="How does memory work?">
@@ -1147,7 +1147,7 @@ Quick answers plus deeper troubleshooting for real-world setups (local dev, VPS,
 
     Pllan also runs a **silent pre-compaction memory flush** to remind the model
     to write durable notes before auto-compaction. This only runs when the workspace
-    is writable (read-only sandboxes skip it). See [Memory](/concepts/memory).
+    is writable (read-only sandboxes skip it). See [Memory](/sv/concepts/memory).
 
   </Accordion>
 
@@ -1159,7 +1159,7 @@ Quick answers plus deeper troubleshooting for real-world setups (local dev, VPS,
     it will know what to do. If it keeps forgetting, verify the Gateway is using the same
     workspace on every run.
 
-    Docs: [Memory](/concepts/memory), [Agent workspace](/concepts/agent-workspace).
+    Docs: [Memory](/sv/concepts/memory), [Agent workspace](/sv/concepts/agent-workspace).
 
   </Accordion>
 
@@ -1169,7 +1169,7 @@ Quick answers plus deeper troubleshooting for real-world setups (local dev, VPS,
     context window, so long conversations can compact or truncate. That is why
     memory search exists - it pulls only the relevant parts back into context.
 
-    Docs: [Memory](/concepts/memory), [Context](/concepts/context).
+    Docs: [Memory](/sv/concepts/memory), [Context](/sv/concepts/context).
 
   </Accordion>
 
@@ -1192,7 +1192,7 @@ Quick answers plus deeper troubleshooting for real-world setups (local dev, VPS,
     `memorySearch.fallback = "none"`). If you want Gemini embeddings, set
     `memorySearch.provider = "gemini"` and provide `GEMINI_API_KEY` (or
     `memorySearch.remote.apiKey`). We support **OpenAI, Gemini, Voyage, Mistral, Ollama, or local** embedding
-    models - see [Memory](/concepts/memory) for the setup details.
+    models - see [Memory](/sv/concepts/memory) for the setup details.
 
   </Accordion>
 </AccordionGroup>
@@ -1211,7 +1211,7 @@ Quick answers plus deeper troubleshooting for real-world setups (local dev, VPS,
     - **You control the footprint:** using local models keeps prompts on your machine, but channel
       traffic still goes through the channel's servers.
 
-    Related: [Agent workspace](/concepts/agent-workspace), [Memory](/concepts/memory).
+    Related: [Agent workspace](/sv/concepts/agent-workspace), [Memory](/sv/concepts/memory).
 
   </Accordion>
 
@@ -1260,7 +1260,7 @@ Quick answers plus deeper troubleshooting for real-world setups (local dev, VPS,
     Tip: if you want a durable behavior or preference, ask the bot to **write it into
     AGENTS.md or MEMORY.md** rather than relying on chat history.
 
-    See [Agent workspace](/concepts/agent-workspace) and [Memory](/concepts/memory).
+    See [Agent workspace](/sv/concepts/agent-workspace) and [Memory](/sv/concepts/memory).
 
   </Accordion>
 
@@ -1273,19 +1273,19 @@ Quick answers plus deeper troubleshooting for real-world setups (local dev, VPS,
     If you need a full restore, back up both the workspace and the state directory
     separately (see the migration question above).
 
-    Docs: [Agent workspace](/concepts/agent-workspace).
+    Docs: [Agent workspace](/sv/concepts/agent-workspace).
 
   </Accordion>
 
   <Accordion title="How do I completely uninstall Pllan?">
-    See the dedicated guide: [Uninstall](/install/uninstall).
+    See the dedicated guide: [Uninstall](/sv/install/uninstall).
   </Accordion>
 
   <Accordion title="Can agents work outside the workspace?">
     Yes. The workspace is the **default cwd** and memory anchor, not a hard sandbox.
     Relative paths resolve inside the workspace, but absolute paths can access other
     host locations unless sandboxing is enabled. If you need isolation, use
-    [`agents.defaults.sandbox`](/gateway/sandboxing) or per-agent sandbox settings. If you
+    [`agents.defaults.sandbox`](/sv/gateway/sandboxing) or per-agent sandbox settings. If you
     want a repo to be the default working directory, point that agent's
     `workspace` to the repo root. The Pllan repo is just source code; keep the
     workspace separate unless you intentionally want the agent to work inside it.
@@ -1305,7 +1305,7 @@ Quick answers plus deeper troubleshooting for real-world setups (local dev, VPS,
   </Accordion>
 
   <Accordion title="I'm in remote mode - where is the session store?">
-    Session state is owned by the **gateway host**. If you're in remote mode, the session store you care about is on the remote machine, not your local laptop. See [Session management](/concepts/session).
+    Session state is owned by the **gateway host**. If you're in remote mode, the session store you care about is on the remote machine, not your local laptop. See [Session management](/sv/concepts/session).
   </Accordion>
 </AccordionGroup>
 
@@ -1431,7 +1431,7 @@ Quick answers plus deeper troubleshooting for real-world setups (local dev, VPS,
     - `web_fetch` is enabled by default (unless explicitly disabled).
     - Daemons read env vars from `~/.pllan/.env` (or the service environment).
 
-    Docs: [Web tools](/tools/web).
+    Docs: [Web tools](/sv/tools/web).
 
   </Accordion>
 
@@ -1451,7 +1451,7 @@ Quick answers plus deeper troubleshooting for real-world setups (local dev, VPS,
     - Use `pllan config set` for small changes.
     - Use `pllan configure` for interactive edits.
 
-    Docs: [Config](/cli/config), [Configure](/cli/configure), [Doctor](/gateway/doctor).
+    Docs: [Config](/sv/cli/config), [Configure](/sv/cli/configure), [Doctor](/sv/gateway/doctor).
 
   </Accordion>
 
@@ -1464,7 +1464,7 @@ Quick answers plus deeper troubleshooting for real-world setups (local dev, VPS,
     - **Sub-agents:** spawn background work from a main agent when you want parallelism.
     - **TUI:** connect to the Gateway and switch agents/sessions.
 
-    Docs: [Nodes](/nodes), [Remote access](/gateway/remote), [Multi-Agent Routing](/concepts/multi-agent), [Sub-agents](/tools/subagents), [TUI](/web/tui).
+    Docs: [Nodes](/sv/nodes), [Remote access](/sv/gateway/remote), [Multi-Agent Routing](/sv/concepts/multi-agent), [Sub-agents](/sv/tools/subagents), [TUI](/sv/web/tui).
 
   </Accordion>
 
@@ -1482,7 +1482,7 @@ Quick answers plus deeper troubleshooting for real-world setups (local dev, VPS,
     }
     ```
 
-    Default is `false` (headful). Headless is more likely to trigger anti-bot checks on some sites. See [Browser](/tools/browser).
+    Default is `false` (headful). Headless is more likely to trigger anti-bot checks on some sites. See [Browser](/sv/tools/browser).
 
     Headless uses the **same Chromium engine** and works for most automation (forms, clicks, scraping, logins). The main differences:
 
@@ -1494,7 +1494,7 @@ Quick answers plus deeper troubleshooting for real-world setups (local dev, VPS,
 
   <Accordion title="How do I use Brave for browser control?">
     Set `browser.executablePath` to your Brave binary (or any Chromium-based browser) and restart the Gateway.
-    See the full config examples in [Browser](/tools/browser#use-brave-or-another-chromium-based-browser).
+    See the full config examples in [Browser](/sv/tools/browser#use-brave-or-another-chromium-based-browser).
   </Accordion>
 </AccordionGroup>
 
@@ -1532,9 +1532,9 @@ Quick answers plus deeper troubleshooting for real-world setups (local dev, VPS,
     No separate TCP bridge is required; nodes connect over the Gateway WebSocket.
 
     Security reminder: pairing a macOS node allows `system.run` on that machine. Only
-    pair devices you trust, and review [Security](/gateway/security).
+    pair devices you trust, and review [Security](/sv/gateway/security).
 
-    Docs: [Nodes](/nodes), [Gateway protocol](/gateway/protocol), [macOS remote mode](/platforms/mac/remote), [Security](/gateway/security).
+    Docs: [Nodes](/sv/nodes), [Gateway protocol](/sv/gateway/protocol), [macOS remote mode](/sv/platforms/mac/remote), [Security](/sv/gateway/security).
 
   </Accordion>
 
@@ -1551,7 +1551,7 @@ Quick answers plus deeper troubleshooting for real-world setups (local dev, VPS,
     - If you connect via SSH tunnel, confirm the local tunnel is up and points at the right port.
     - Confirm your allowlists (DM or group) include your account.
 
-    Docs: [Tailscale](/gateway/tailscale), [Remote access](/gateway/remote), [Channels](/channels).
+    Docs: [Tailscale](/sv/gateway/tailscale), [Remote access](/sv/gateway/remote), [Channels](/sv/channels).
 
   </Accordion>
 
@@ -1565,7 +1565,7 @@ Quick answers plus deeper troubleshooting for real-world setups (local dev, VPS,
     **CLI bridge (generic):** run a script that calls the other Gateway with
     `pllan agent --message ... --deliver`, targeting a chat where the other bot
     listens. If one bot is on a remote VPS, point your CLI at that remote Gateway
-    via SSH/Tailscale (see [Remote access](/gateway/remote)).
+    via SSH/Tailscale (see [Remote access](/sv/gateway/remote)).
 
     Example pattern (run from a machine that can reach the target Gateway):
 
@@ -1576,7 +1576,7 @@ Quick answers plus deeper troubleshooting for real-world setups (local dev, VPS,
     Tip: add a guardrail so the two bots do not loop endlessly (mention-only, channel
     allowlists, or a "do not reply to bot messages" rule).
 
-    Docs: [Remote access](/gateway/remote), [Agent CLI](/cli/agent), [Agent send](/tools/agent-send).
+    Docs: [Remote access](/sv/gateway/remote), [Agent CLI](/sv/cli/agent), [Agent send](/sv/tools/agent-send).
 
   </Accordion>
 
@@ -1605,14 +1605,14 @@ Quick answers plus deeper troubleshooting for real-world setups (local dev, VPS,
     SSH is fine for ad-hoc shell access, but nodes are simpler for ongoing agent workflows and
     device automation.
 
-    Docs: [Nodes](/nodes), [Nodes CLI](/cli/nodes), [Browser](/tools/browser).
+    Docs: [Nodes](/sv/nodes), [Nodes CLI](/sv/cli/nodes), [Browser](/sv/tools/browser).
 
   </Accordion>
 
   <Accordion title="Do nodes run a gateway service?">
-    No. Only **one gateway** should run per host unless you intentionally run isolated profiles (see [Multiple gateways](/gateway/multiple-gateways)). Nodes are peripherals that connect
+    No. Only **one gateway** should run per host unless you intentionally run isolated profiles (see [Multiple gateways](/sv/gateway/multiple-gateways)). Nodes are peripherals that connect
     to the gateway (iOS/Android nodes, or macOS "node mode" in the menubar app). For headless node
-    hosts and CLI control, see [Node host CLI](/cli/node).
+    hosts and CLI control, see [Node host CLI](/sv/cli/node).
 
     A full restart is required for `gateway`, `discovery`, and `canvasHost` changes.
 
@@ -1658,7 +1658,7 @@ Quick answers plus deeper troubleshooting for real-world setups (local dev, VPS,
     pllan gateway --tailscale serve
     ```
 
-    This keeps the gateway bound to loopback and exposes HTTPS via Tailscale. See [Tailscale](/gateway/tailscale).
+    This keeps the gateway bound to loopback and exposes HTTPS via Tailscale. See [Tailscale](/sv/gateway/tailscale).
 
   </Accordion>
 
@@ -1677,7 +1677,7 @@ Quick answers plus deeper troubleshooting for real-world setups (local dev, VPS,
        pllan devices approve <requestId>
        ```
 
-    Docs: [Gateway protocol](/gateway/protocol), [Discovery](/gateway/discovery), [macOS remote mode](/platforms/mac/remote).
+    Docs: [Gateway protocol](/sv/gateway/protocol), [Discovery](/sv/gateway/discovery), [macOS remote mode](/sv/platforms/mac/remote).
 
   </Accordion>
 
@@ -1688,7 +1688,7 @@ Quick answers plus deeper troubleshooting for real-world setups (local dev, VPS,
 
     Install a second Gateway only when you need **hard isolation** or two fully separate bots.
 
-    Docs: [Nodes](/nodes), [Nodes CLI](/cli/nodes), [Multiple gateways](/gateway/multiple-gateways).
+    Docs: [Nodes](/sv/nodes), [Nodes CLI](/sv/cli/nodes), [Multiple gateways](/sv/gateway/multiple-gateways).
 
   </Accordion>
 </AccordionGroup>
@@ -1715,7 +1715,7 @@ Quick answers plus deeper troubleshooting for real-world setups (local dev, VPS,
     }
     ```
 
-    See [/environment](/help/environment) for full precedence and sources.
+    See [/environment](/sv/help/environment) for full precedence and sources.
 
   </Accordion>
 
@@ -1765,7 +1765,7 @@ Quick answers plus deeper troubleshooting for real-world setups (local dev, VPS,
     ```
 
     Copilot tokens are read from `COPILOT_GITHUB_TOKEN` (also `GH_TOKEN` / `GITHUB_TOKEN`).
-    See [/concepts/model-providers](/concepts/model-providers) and [/environment](/help/environment).
+    See [/concepts/model-providers](/sv/concepts/model-providers) and [/environment](/sv/help/environment).
 
   </Accordion>
 </AccordionGroup>
@@ -1774,7 +1774,7 @@ Quick answers plus deeper troubleshooting for real-world setups (local dev, VPS,
 
 <AccordionGroup>
   <Accordion title="How do I start a fresh conversation?">
-    Send `/new` or `/reset` as a standalone message. See [Session management](/concepts/session).
+    Send `/new` or `/reset` as a standalone message. See [Session management](/sv/concepts/session).
   </Accordion>
 
   <Accordion title="Do sessions reset automatically if I never send /new?">
@@ -1801,7 +1801,7 @@ Quick answers plus deeper troubleshooting for real-world setups (local dev, VPS,
     envision is one bot you talk to, with different sessions for parallel work. That
     bot can also spawn sub-agents when needed.
 
-    Docs: [Multi-agent routing](/concepts/multi-agent), [Sub-agents](/tools/subagents), [Agents CLI](/cli/agents).
+    Docs: [Multi-agent routing](/sv/concepts/multi-agent), [Sub-agents](/sv/tools/subagents), [Agents CLI](/sv/cli/agents).
 
   </Accordion>
 
@@ -1840,7 +1840,7 @@ Quick answers plus deeper troubleshooting for real-world setups (local dev, VPS,
 
     Notes:
 
-    - Onboarding also offers **Reset** if it sees an existing config. See [Onboarding (CLI)](/start/wizard).
+    - Onboarding also offers **Reset** if it sees an existing config. See [Onboarding (CLI)](/sv/start/wizard).
     - If you used profiles (`--profile` / `PLLAN_PROFILE`), reset each state dir (defaults are `~/.pllan-<profile>`).
     - Dev reset: `pllan gateway --dev --reset` (dev-only; wipes dev config + credentials + sessions + workspace).
 
@@ -1869,7 +1869,7 @@ Quick answers plus deeper troubleshooting for real-world setups (local dev, VPS,
     - Enable or tune **session pruning** (`agents.defaults.contextPruning`) to trim old tool output.
     - Use a model with a larger context window.
 
-    Docs: [Compaction](/concepts/compaction), [Session pruning](/concepts/session-pruning), [Session management](/concepts/session).
+    Docs: [Compaction](/sv/concepts/compaction), [Session pruning](/sv/concepts/session-pruning), [Session management](/sv/concepts/session).
 
   </Accordion>
 
@@ -1901,7 +1901,7 @@ Quick answers plus deeper troubleshooting for real-world setups (local dev, VPS,
     headers like `# Heading`), Pllan skips the heartbeat run to save API calls.
     If the file is missing, the heartbeat still runs and the model decides what to do.
 
-    Per-agent overrides use `agents.list[].heartbeat`. Docs: [Heartbeat](/gateway/heartbeat).
+    Per-agent overrides use `agents.list[].heartbeat`. Docs: [Heartbeat](/sv/gateway/heartbeat).
 
   </Accordion>
 
@@ -1940,7 +1940,7 @@ Quick answers plus deeper troubleshooting for real-world setups (local dev, VPS,
     pllan directory groups list --channel whatsapp
     ```
 
-    Docs: [WhatsApp](/channels/whatsapp), [Directory](/cli/directory), [Logs](/cli/logs).
+    Docs: [WhatsApp](/sv/channels/whatsapp), [Directory](/sv/cli/directory), [Logs](/sv/cli/logs).
 
   </Accordion>
 
@@ -1950,12 +1950,12 @@ Quick answers plus deeper troubleshooting for real-world setups (local dev, VPS,
     - Mention gating is on (default). You must @mention the bot (or match `mentionPatterns`).
     - You configured `channels.whatsapp.groups` without `"*"` and the group isn't allowlisted.
 
-    See [Groups](/channels/groups) and [Group messages](/channels/group-messages).
+    See [Groups](/sv/channels/groups) and [Group messages](/sv/channels/group-messages).
 
   </Accordion>
 
   <Accordion title="Do groups/threads share context with DMs?">
-    Direct chats collapse to the main session by default. Groups/channels have their own session keys, and Telegram topics / Discord threads are separate sessions. See [Groups](/channels/groups) and [Group messages](/channels/group-messages).
+    Direct chats collapse to the main session by default. Groups/channels have their own session keys, and Telegram topics / Discord threads are separate sessions. See [Groups](/sv/channels/groups) and [Group messages](/sv/channels/group-messages).
   </Accordion>
 
   <Accordion title="How many workspaces and agents can I create?">
@@ -1988,8 +1988,8 @@ Quick answers plus deeper troubleshooting for real-world setups (local dev, VPS,
     - Slack channel(s) bound to those agents.
     - Local browser via Chrome MCP or a node when needed.
 
-    Docs: [Multi-Agent Routing](/concepts/multi-agent), [Slack](/channels/slack),
-    [Browser](/tools/browser), [Nodes](/nodes).
+    Docs: [Multi-Agent Routing](/sv/concepts/multi-agent), [Slack](/sv/channels/slack),
+    [Browser](/sv/tools/browser), [Nodes](/sv/nodes).
 
   </Accordion>
 </AccordionGroup>
@@ -2013,18 +2013,18 @@ Quick answers plus deeper troubleshooting for real-world setups (local dev, VPS,
     **For tool-enabled or untrusted-input agents:** prioritize model strength over cost.
     **For routine/low-stakes chat:** use cheaper fallback models and route by agent role.
 
-    MiniMax has its own docs: [MiniMax](/providers/minimax) and
-    [Local models](/gateway/local-models).
+    MiniMax has its own docs: [MiniMax](/sv/providers/minimax) and
+    [Local models](/sv/gateway/local-models).
 
     Rule of thumb: use the **best model you can afford** for high-stakes work, and a cheaper
     model for routine chat or summaries. You can route models per agent and use sub-agents to
-    parallelize long tasks (each sub-agent consumes tokens). See [Models](/concepts/models) and
-    [Sub-agents](/tools/subagents).
+    parallelize long tasks (each sub-agent consumes tokens). See [Models](/sv/concepts/models) and
+    [Sub-agents](/sv/tools/subagents).
 
     Strong warning: weaker/over-quantized models are more vulnerable to prompt
-    injection and unsafe behavior. See [Security](/gateway/security).
+    injection and unsafe behavior. See [Security](/sv/gateway/security).
 
-    More context: [Models](/concepts/models).
+    More context: [Models](/sv/concepts/models).
 
   </Accordion>
 
@@ -2041,7 +2041,7 @@ Quick answers plus deeper troubleshooting for real-world setups (local dev, VPS,
     Avoid `config.apply` with a partial object unless you intend to replace the whole config.
     If you did overwrite config, restore from backup or re-run `pllan doctor` to repair.
 
-    Docs: [Models](/concepts/models), [Configure](/cli/configure), [Config](/cli/config), [Doctor](/gateway/doctor).
+    Docs: [Models](/sv/concepts/models), [Configure](/sv/cli/configure), [Config](/sv/cli/config), [Doctor](/sv/gateway/doctor).
 
   </Accordion>
 
@@ -2066,9 +2066,9 @@ Quick answers plus deeper troubleshooting for real-world setups (local dev, VPS,
     injection. We strongly recommend **large models** for any bot that can use tools.
     If you still want small models, enable sandboxing and strict tool allowlists.
 
-    Docs: [Ollama](/providers/ollama), [Local models](/gateway/local-models),
-    [Model providers](/concepts/model-providers), [Security](/gateway/security),
-    [Sandboxing](/gateway/sandboxing).
+    Docs: [Ollama](/sv/providers/ollama), [Local models](/sv/gateway/local-models),
+    [Model providers](/sv/concepts/model-providers), [Security](/sv/gateway/security),
+    [Sandboxing](/sv/gateway/sandboxing).
 
   </Accordion>
 
@@ -2129,7 +2129,7 @@ Quick answers plus deeper troubleshooting for real-world setups (local dev, VPS,
     - **Default + switch:** set `agents.defaults.model.primary` to `openai/gpt-5.2`, then switch to `openai-codex/gpt-5.4` when coding (or the other way around).
     - **Sub-agents:** route coding tasks to sub-agents with a different default model.
 
-    See [Models](/concepts/models) and [Slash commands](/tools/slash-commands).
+    See [Models](/sv/concepts/models) and [Slash commands](/sv/tools/slash-commands).
 
   </Accordion>
 
@@ -2167,7 +2167,7 @@ Quick answers plus deeper troubleshooting for real-world setups (local dev, VPS,
 
        and pick from the list (or `/model list` in chat).
 
-    See [MiniMax](/providers/minimax) and [Models](/concepts/models).
+    See [MiniMax](/sv/providers/minimax) and [Models](/sv/concepts/models).
 
   </Accordion>
 
@@ -2204,7 +2204,7 @@ Quick answers plus deeper troubleshooting for real-world setups (local dev, VPS,
     - Agent B default: OpenAI
     - Route by agent or use `/agent` to switch
 
-    Docs: [Models](/concepts/models), [Multi-Agent Routing](/concepts/multi-agent), [MiniMax](/providers/minimax), [OpenAI](/providers/openai).
+    Docs: [Models](/sv/concepts/models), [Multi-Agent Routing](/sv/concepts/multi-agent), [MiniMax](/sv/providers/minimax), [OpenAI](/sv/providers/openai).
 
   </Accordion>
 
@@ -2361,7 +2361,7 @@ Quick answers plus deeper troubleshooting for real-world setups (local dev, VPS,
 
 ## Auth profiles: what they are and how to manage them
 
-Related: [/concepts/oauth](/concepts/oauth) (OAuth flows, token storage, multi-account patterns)
+Related: [/concepts/oauth](/sv/concepts/oauth) (OAuth flows, token storage, multi-account patterns)
 
 <AccordionGroup>
   <Accordion title="What is an auth profile?">
@@ -2508,7 +2508,7 @@ Related: [/concepts/oauth](/concepts/oauth) (OAuth flows, token storage, multi-a
     - If mismatch persists after the one retry, rotate/re-approve the paired device token:
       - `pllan devices list`
       - `pllan devices rotate --device <id> --role operator`
-    - Still stuck? Run `pllan status --all` and follow [Troubleshooting](/gateway/troubleshooting). See [Dashboard](/web/dashboard) for auth details.
+    - Still stuck? Run `pllan status --all` and follow [Troubleshooting](/sv/gateway/troubleshooting). See [Dashboard](/sv/web/dashboard) for auth details.
 
   </Accordion>
 
@@ -2541,7 +2541,7 @@ Related: [/concepts/oauth](/concepts/oauth) (OAuth flows, token storage, multi-a
     - Install a per-profile service: `pllan --profile <name> gateway install`.
 
     Profiles also suffix service names (`ai.pllan.<profile>`; legacy `com.pllan.*`, `pllan-gateway-<profile>.service`, `Pllan Gateway (<profile>)`).
-    Full guide: [Multiple gateways](/gateway/multiple-gateways).
+    Full guide: [Multiple gateways](/sv/gateway/multiple-gateways).
 
   </Accordion>
 
@@ -2568,7 +2568,7 @@ Related: [/concepts/oauth](/concepts/oauth) (OAuth flows, token storage, multi-a
     pllan tui --url ws://<host>:18789 --token <token>
     ```
 
-    Protocol details: [Gateway protocol](/gateway/protocol).
+    Protocol details: [Gateway protocol](/sv/gateway/protocol).
 
   </Accordion>
 </AccordionGroup>
@@ -2597,7 +2597,7 @@ Related: [/concepts/oauth](/concepts/oauth) (OAuth flows, token storage, multi-a
     - Linux: `journalctl --user -u pllan-gateway[-<profile>].service -n 200 --no-pager`
     - Windows: `schtasks /Query /TN "Pllan Gateway (<profile>)" /V /FO LIST`
 
-    See [Troubleshooting](/gateway/troubleshooting) for more.
+    See [Troubleshooting](/sv/gateway/troubleshooting) for more.
 
   </Accordion>
 
@@ -2609,7 +2609,7 @@ Related: [/concepts/oauth](/concepts/oauth) (OAuth flows, token storage, multi-a
     pllan gateway restart
     ```
 
-    If you run the gateway manually, `pllan gateway --force` can reclaim the port. See [Gateway](/gateway).
+    If you run the gateway manually, `pllan gateway --force` can reclaim the port. See [Gateway](/sv/gateway).
 
   </Accordion>
 
@@ -2647,7 +2647,7 @@ Related: [/concepts/oauth](/concepts/oauth) (OAuth flows, token storage, multi-a
     pllan gateway run
     ```
 
-    Docs: [Windows (WSL2)](/platforms/windows), [Gateway service runbook](/gateway).
+    Docs: [Windows (WSL2)](/sv/platforms/windows), [Gateway service runbook](/sv/gateway).
 
   </Accordion>
 
@@ -2670,7 +2670,7 @@ Related: [/concepts/oauth](/concepts/oauth) (OAuth flows, token storage, multi-a
     If you are remote, confirm the tunnel/Tailscale connection is up and that the
     Gateway WebSocket is reachable.
 
-    Docs: [Channels](/channels), [Troubleshooting](/gateway/troubleshooting), [Remote access](/gateway/remote).
+    Docs: [Channels](/sv/channels), [Troubleshooting](/sv/gateway/troubleshooting), [Remote access](/sv/gateway/remote).
 
   </Accordion>
 
@@ -2688,7 +2688,7 @@ Related: [/concepts/oauth](/concepts/oauth) (OAuth flows, token storage, multi-a
     pllan logs --follow
     ```
 
-    Docs: [Dashboard](/web/dashboard), [Remote access](/gateway/remote), [Troubleshooting](/gateway/troubleshooting).
+    Docs: [Dashboard](/sv/web/dashboard), [Remote access](/sv/gateway/remote), [Troubleshooting](/sv/gateway/troubleshooting).
 
   </Accordion>
 
@@ -2707,7 +2707,7 @@ Related: [/concepts/oauth](/concepts/oauth) (OAuth flows, token storage, multi-a
 
     If the Gateway is remote, make sure you are looking at logs on the Gateway host.
 
-    Docs: [Telegram](/channels/telegram), [Channel troubleshooting](/channels/troubleshooting).
+    Docs: [Telegram](/sv/channels/telegram), [Channel troubleshooting](/sv/channels/troubleshooting).
 
   </Accordion>
 
@@ -2723,7 +2723,7 @@ Related: [/concepts/oauth](/concepts/oauth) (OAuth flows, token storage, multi-a
     In the TUI, use `/status` to see the current state. If you expect replies in a chat
     channel, make sure delivery is enabled (`/deliver on`).
 
-    Docs: [TUI](/web/tui), [Slash commands](/tools/slash-commands).
+    Docs: [TUI](/sv/web/tui), [Slash commands](/sv/tools/slash-commands).
 
   </Accordion>
 
@@ -2744,7 +2744,7 @@ Related: [/concepts/oauth](/concepts/oauth) (OAuth flows, token storage, multi-a
     pllan gateway run
     ```
 
-    Docs: [Gateway service runbook](/gateway).
+    Docs: [Gateway service runbook](/sv/gateway).
 
   </Accordion>
 
@@ -2766,7 +2766,7 @@ Related: [/concepts/oauth](/concepts/oauth) (OAuth flows, token storage, multi-a
 
 <AccordionGroup>
   <Accordion title="My skill generated an image/PDF, but nothing was sent">
-    Outbound attachments from the agent must include a `MEDIA:<path-or-url>` line (on its own line). See [Pllan assistant setup](/start/pllan) and [Agent send](/tools/agent-send).
+    Outbound attachments from the agent must include a `MEDIA:<path-or-url>` line (on its own line). See [Pllan assistant setup](/sv/start/pllan) and [Agent send](/sv/tools/agent-send).
 
     CLI sending:
 
@@ -2779,7 +2779,7 @@ Related: [/concepts/oauth](/concepts/oauth) (OAuth flows, token storage, multi-a
     - The target channel supports outbound media and isn't blocked by allowlists.
     - The file is within the provider's size limits (images are resized to max 2048px).
 
-    See [Images](/nodes/images).
+    See [Images](/sv/nodes/images).
 
   </Accordion>
 </AccordionGroup>
@@ -2813,7 +2813,7 @@ Related: [/concepts/oauth](/concepts/oauth) (OAuth flows, token storage, multi-a
     - keeping `web_search` / `web_fetch` / `browser` off for tool-enabled agents
     - sandboxing and strict tool allowlists
 
-    Details: [Security](/gateway/security).
+    Details: [Security](/sv/gateway/security).
 
   </Accordion>
 
@@ -2825,7 +2825,7 @@ Related: [/concepts/oauth](/concepts/oauth) (OAuth flows, token storage, multi-a
     Start small. Give access only to the tools and accounts you actually need, and expand
     later if required.
 
-    Docs: [Security](/gateway/security), [Pairing](/channels/pairing).
+    Docs: [Security](/sv/gateway/security), [Pairing](/sv/channels/pairing).
 
   </Accordion>
 
@@ -2837,7 +2837,7 @@ Related: [/concepts/oauth](/concepts/oauth) (OAuth flows, token storage, multi-a
     - Let it draft, then **approve before sending**.
 
     If you want to experiment, do it on a dedicated account and keep it isolated. See
-    [Security](/gateway/security).
+    [Security](/sv/gateway/security).
 
   </Accordion>
 
@@ -2845,7 +2845,7 @@ Related: [/concepts/oauth](/concepts/oauth) (OAuth flows, token storage, multi-a
     Yes, **if** the agent is chat-only and the input is trusted. Smaller tiers are
     more susceptible to instruction hijacking, so avoid them for tool-enabled agents
     or when reading untrusted content. If you must use a smaller model, lock down
-    tools and run inside a sandbox. See [Security](/gateway/security).
+    tools and run inside a sandbox. See [Security](/sv/gateway/security).
   </Accordion>
 
   <Accordion title="I ran /start in Telegram but did not get a pairing code">
@@ -2901,7 +2901,7 @@ Related: [/concepts/oauth](/concepts/oauth) (OAuth flows, token storage, multi-a
     to **inherit**. Also confirm you are not using a bot profile with `verboseDefault` set
     to `on` in config.
 
-    Docs: [Thinking and verbose](/tools/thinking), [Security](/gateway/security#reasoning-verbose-output-in-groups).
+    Docs: [Thinking and verbose](/sv/tools/thinking), [Security](/sv/gateway/security#reasoning-verbose-output-in-groups).
 
   </Accordion>
 
@@ -2938,7 +2938,7 @@ Related: [/concepts/oauth](/concepts/oauth) (OAuth flows, token storage, multi-a
     process action:kill sessionId:XXX
     ```
 
-    Slash commands overview: see [Slash commands](/tools/slash-commands).
+    Slash commands overview: see [Slash commands](/sv/tools/slash-commands).
 
     Most commands must be sent as a **standalone** message that starts with `/`, but a few shortcuts (like `/status`) also work inline for allowlisted senders.