pllan 2026.3.47 → 2026.3.49

package/docs/nb/start/onboarding-overview.md

@@ -45,15 +45,15 @@ pllan onboard
 
 Legg til `--install-daemon` for ogsa a installere bakgrunnstjenesten i ett steg.
 
-Fullstendig referanse: [Introduksjonsveiviser (CLI)](/start/wizard)
-CLI-kommandodokumentasjon: [`pllan onboard`](/cli/onboard)
+Fullstendig referanse: [Introduksjonsveiviser (CLI)](/nb/start/wizard)
+CLI-kommandodokumentasjon: [`pllan onboard`](/nb/cli/onboard)
 
 ## macOS-app-introduksjon
 
 Apne Pllan-appen. Forstekjoringsveiviseren guider deg gjennom de samme stegene
 med et visuelt grensesnitt.
 
-Fullstendig referanse: [Introduksjon (macOS-app)](/start/onboarding)
+Fullstendig referanse: [Introduksjon (macOS-app)](/nb/start/onboarding)
 
 ## Egendefinerte eller ulistede leverandorer
 

package/docs/nb/start/onboarding.md

@@ -12,7 +12,7 @@ sidebarTitle: "Introduksjon: macOS-app"
 Dette dokumentet beskriver den **gjeldende** forstegangskjoringsflyten. Malet er en
 jevn «dag 0»-opplevelse: velg hvor gatewayen kjorer, koble til autentisering, kjor
 veiviseren og la agenten starte seg selv opp.
-For en generell oversikt over introduksjonsstier, se [Introduksjonsoversikt](/start/onboarding-overview).
+For en generell oversikt over introduksjonsstier, se [Introduksjonsoversikt](/nb/start/onboarding-overview).
 
 <Steps>
 <Step title="Godkjenn macOS-advarsel">
@@ -33,7 +33,7 @@ For en generell oversikt over introduksjonsstier, se [Introduksjonsoversikt](/st
 Sikkerhets-tillitsmodell:
 
 - Som standard er Pllan en personlig agent: en betrodd operatorgrense.
-- Delte/flerbrukeroppsett krever nedlasing (delte tillitsgrenser, hold verktoyilgang minimal, og folg [Sikkerhet](/gateway/security)).
+- Delte/flerbrukeroppsett krever nedlasing (delte tillitsgrenser, hold verktoyilgang minimal, og folg [Sikkerhet](/nb/gateway/security)).
 - Lokal introduksjon setter na nye konfigurasjoner til `tools.profile: "coding"` slik at ferske lokale oppsett beholder filsystem-/kjoringsverktoy uten a tvinge den ubegrensede `full`-profilen.
 - Hvis hooks/webhooks eller annet ubetrott innhold er aktivert, bruk en sterk moderne modell og behold strenge verktoyretningslinjer/sandkassing.
 
@@ -85,7 +85,7 @@ Introduksjonen ber om TCC-tillatelser som trengs for:
 <Step title="Introduksjonschat (dedikert sesjon)">
   Etter oppsett apner appen en dedikert introduksjonschat-sesjon slik at agenten kan
   presentere seg selv og veilede videre steg. Dette holder forstegangsveiledning adskilt
-  fra din vanlige samtale. Se [Oppstartsinnlasting](/start/bootstrapping) for
+  fra din vanlige samtale. Se [Oppstartsinnlasting](/nb/start/bootstrapping) for
   hva som skjer pa gateway-verten under forste agentkjoring.
 </Step>
 </Steps>

package/docs/nb/start/pllan.md

@@ -26,7 +26,7 @@ Start konservativt:
 
 ## Forutsetninger
 
-- Pllan installert og introdusert — se [Kom i gang](/start/getting-started) hvis du ikke har gjort dette enna
+- Pllan installert og introdusert — se [Kom i gang](/nb/start/getting-started) hvis du ikke har gjort dette enna
 - Et ekstra telefonnummer (SIM/eSIM/kontantkort) for assistenten
 
 ## Oppsett med to telefoner (anbefalt)
@@ -79,8 +79,8 @@ Tips: behandle denne mappen som Pllans «minne» og gjor den til et git-depot (h
 pllan setup
 ```
 
-Fullstendig arbeidsomradeoppsett + sikkerhetskopieringsguide: [Agentarbeidsomrade](/concepts/agent-workspace)
-Minnearbeidsflyt: [Minne](/concepts/memory)
+Fullstendig arbeidsomradeoppsett + sikkerhetskopieringsguide: [Agentarbeidsomrade](/nb/concepts/agent-workspace)
+Minnearbeidsflyt: [Minne](/nb/concepts/memory)
 
 Valgfritt: velg et annet arbeidsomrade med `agents.defaults.workspace` (stotter `~`).
 
@@ -205,12 +205,12 @@ Logger ligger under `/tmp/pllan/` (standard: `pllan-YYYY-MM-DD.log`).
 
 ## Neste steg
 
-- WebChat: [WebChat](/web/webchat)
-- Gateway-drift: [Gateway-handbok](/gateway)
-- Cron + vekking: [Cron-jobber](/automation/cron-jobs)
-- macOS menylinjefolgsvenn: [Pllan macOS-app](/platforms/macos)
-- iOS-nodeapp: [iOS-app](/platforms/ios)
-- Android-nodeapp: [Android-app](/platforms/android)
-- Windows-status: [Windows (WSL2)](/platforms/windows)
-- Linux-status: [Linux-app](/platforms/linux)
-- Sikkerhet: [Sikkerhet](/gateway/security)
+- WebChat: [WebChat](/nb/web/webchat)
+- Gateway-drift: [Gateway-handbok](/nb/gateway)
+- Cron + vekking: [Cron-jobber](/nb/automation/cron-jobs)
+- macOS menylinjefolgsvenn: [Pllan macOS-app](/nb/platforms/macos)
+- iOS-nodeapp: [iOS-app](/nb/platforms/ios)
+- Android-nodeapp: [Android-app](/nb/platforms/android)
+- Windows-status: [Windows (WSL2)](/nb/platforms/windows)
+- Linux-status: [Linux-app](/nb/platforms/linux)
+- Sikkerhet: [Sikkerhet](/nb/gateway/security)

package/docs/nb/start/quickstart.md

@@ -9,14 +9,14 @@ title: "Hurtigstart"
 # Hurtigstart
 
 <Info>
-Hurtigstart er na en del av [Kom i gang](/start/getting-started).
+Hurtigstart er na en del av [Kom i gang](/nb/start/getting-started).
 </Info>
 
 <Columns>
-  <Card title="Kom i gang" href="/start/getting-started">
+  <Card title="Kom i gang" href="/nb/start/getting-started">
     Installer Pllan og kjor din forste chat pa noen minutter.
   </Card>
-  <Card title="Introduksjonsveiviser (CLI)" href="/start/wizard">
+  <Card title="Introduksjonsveiviser (CLI)" href="/nb/start/wizard">
     Fullstendig CLI-introduksjonsreferanse og avanserte alternativer.
   </Card>
 </Columns>

package/docs/nb/start/setup.md

@@ -9,8 +9,8 @@ title: "Oppsett"
 # Oppsett
 
 <Note>
-Hvis du setter opp for forste gang, start med [Kom i gang](/start/getting-started).
-For introduksjonsdetaljer, se [Introduksjonsveiviser (CLI)](/start/wizard).
+Hvis du setter opp for forste gang, start med [Kom i gang](/nb/start/getting-started).
+For introduksjonsdetaljer, se [Introduksjonsveiviser (CLI)](/nb/start/wizard).
 </Note>
 
 ## Kort oppsummert
@@ -23,7 +23,7 @@ For introduksjonsdetaljer, se [Introduksjonsveiviser (CLI)](/start/wizard).
 
 - Node 24 anbefalt (Node 22 LTS, for oyeblikket `22.16+`, stottes fortsatt)
 - `pnpm`
-- Docker (valgfritt; bare for beholderbasert oppsett/e2e — se [Docker](/install/docker))
+- Docker (valgfritt; bare for beholderbasert oppsett/e2e — se [Docker](/nb/install/docker))
 
 ## Tilpasningsstrategi (slik at oppdateringer ikke skader)
 
@@ -135,7 +135,7 @@ Bruk dette ved feilsoking av autentisering eller ved beslutning om hva som skal
 - **Modell-autentiseringsprofiler**: `~/.pllan/agents/<agentId>/agent/auth-profiles.json`
 - **Filbasert hemmelighetsinnhold (valgfritt)**: `~/.pllan/secrets.json`
 - **Eldre OAuth-import**: `~/.pllan/credentials/oauth.json`
-  Mer detaljer: [Sikkerhet](/gateway/security#credential-storage-map).
+  Mer detaljer: [Sikkerhet](/nb/gateway/security#credential-storage-map).
 
 ## Oppdatering (uten a odelegge oppsettet ditt)
 
@@ -153,12 +153,12 @@ sudo loginctl enable-linger $USER
 ```
 
 For alltid-pa eller flerbrukerservere, vurder en **system**tjeneste i stedet for en
-brukertjeneste (ingen lingering nodvendig). Se [Gateway-handbok](/gateway) for systemd-notatene.
+brukertjeneste (ingen lingering nodvendig). Se [Gateway-handbok](/nb/gateway) for systemd-notatene.
 
 ## Relatert dokumentasjon
 
-- [Gateway-handbok](/gateway) (flagg, overvaking, porter)
-- [Gateway-konfigurasjon](/gateway/configuration) (konfigurasjonsskjema + eksempler)
-- [Discord](/channels/discord) og [Telegram](/channels/telegram) (svar-tagger + replyToMode-innstillinger)
-- [Pllan-assistentoppsett](/start/pllan)
-- [macOS-app](/platforms/macos) (gateway-livssyklus)
+- [Gateway-handbok](/nb/gateway) (flagg, overvaking, porter)
+- [Gateway-konfigurasjon](/nb/gateway/configuration) (konfigurasjonsskjema + eksempler)
+- [Discord](/nb/channels/discord) og [Telegram](/nb/channels/telegram) (svar-tagger + replyToMode-innstillinger)
+- [Pllan-assistentoppsett](/nb/start/pllan)
+- [macOS-app](/nb/platforms/macos) (gateway-livssyklus)

package/docs/nb/start/wizard-cli-automation.md

@@ -210,6 +210,6 @@ Merknader:
 
 ## Relatert dokumentasjon
 
-- Introduksjonshub: [Introduksjonsveiviser (CLI)](/start/wizard)
-- Fullstendig referanse: [CLI-oppsett-referanse](/start/wizard-cli-reference)
-- Kommandoreferanse: [`pllan onboard`](/cli/onboard)
+- Introduksjonshub: [Introduksjonsveiviser (CLI)](/nb/start/wizard)
+- Fullstendig referanse: [CLI-oppsett-referanse](/nb/start/wizard-cli-reference)
+- Kommandoreferanse: [`pllan onboard`](/nb/cli/onboard)

package/docs/nb/start/wizard-cli-reference.md

@@ -10,7 +10,7 @@ sidebarTitle: "CLI reference"
 # CLI Setup Reference
 
 This page is the full reference for `pllan onboard`.
-For the short guide, see [Onboarding (CLI)](/start/wizard).
+For the short guide, see [Onboarding (CLI)](/nb/start/wizard).
 
 ## What the wizard does
 
@@ -46,7 +46,7 @@ It does not install or modify anything on the remote host.
   <Step title="Workspace">
     - Default `~/.pllan/workspace` (configurable).
     - Seeds workspace files needed for first-run bootstrap ritual.
-    - Workspace layout: [Agent workspace](/concepts/agent-workspace).
+    - Workspace layout: [Agent workspace](/nb/concepts/agent-workspace).
   </Step>
   <Step title="Gateway">
     - Prompts for port, bind, auth mode, and tailscale exposure.
@@ -62,14 +62,14 @@ It does not install or modify anything on the remote host.
     - Non-loopback binds still require auth.
   </Step>
   <Step title="Channels">
-    - [WhatsApp](/channels/whatsapp): optional QR login
-    - [Telegram](/channels/telegram): bot token
-    - [Discord](/channels/discord): bot token
-    - [Google Chat](/channels/googlechat): service account JSON + webhook audience
-    - [Mattermost](/channels/mattermost) plugin: bot token + base URL
-    - [Signal](/channels/signal): optional `signal-cli` install + account config
-    - [BlueBubbles](/channels/bluebubbles): recommended for iMessage; server URL + password + webhook
-    - [iMessage](/channels/imessage): legacy `imsg` CLI path + DB access
+    - [WhatsApp](/nb/channels/whatsapp): optional QR login
+    - [Telegram](/nb/channels/telegram): bot token
+    - [Discord](/nb/channels/discord): bot token
+    - [Google Chat](/nb/channels/googlechat): service account JSON + webhook audience
+    - [Mattermost](/nb/channels/mattermost) plugin: bot token + base URL
+    - [Signal](/nb/channels/signal): optional `signal-cli` install + account config
+    - [BlueBubbles](/nb/channels/bluebubbles): recommended for iMessage; server URL + password + webhook
+    - [iMessage](/nb/channels/imessage): legacy `imsg` CLI path + DB access
     - DM security: default is pairing. First DM sends a code; approve via
       `pllan pairing approve <channel> <code>` or use allowlists.
   </Step>
@@ -164,28 +164,28 @@ What you set:
   </Accordion>
   <Accordion title="Vercel AI Gateway">
     Prompts for `AI_GATEWAY_API_KEY`.
-    More detail: [Vercel AI Gateway](/providers/vercel-ai-gateway).
+    More detail: [Vercel AI Gateway](/nb/providers/vercel-ai-gateway).
   </Accordion>
   <Accordion title="Cloudflare AI Gateway">
     Prompts for account ID, gateway ID, and `CLOUDFLARE_AI_GATEWAY_API_KEY`.
-    More detail: [Cloudflare AI Gateway](/providers/cloudflare-ai-gateway).
+    More detail: [Cloudflare AI Gateway](/nb/providers/cloudflare-ai-gateway).
   </Accordion>
   <Accordion title="MiniMax">
     Config is auto-written. Hosted default is `MiniMax-M2.7`; `MiniMax-M2.5` stays available.
-    More detail: [MiniMax](/providers/minimax).
+    More detail: [MiniMax](/nb/providers/minimax).
   </Accordion>
   <Accordion title="Synthetic (Anthropic-compatible)">
     Prompts for `SYNTHETIC_API_KEY`.
-    More detail: [Synthetic](/providers/synthetic).
+    More detail: [Synthetic](/nb/providers/synthetic).
   </Accordion>
   <Accordion title="Ollama (Cloud and local open models)">
     Prompts for base URL (default `http://127.0.0.1:11434`), then offers Cloud + Local or Local mode.
     Discovers available models and suggests defaults.
-    More detail: [Ollama](/providers/ollama).
+    More detail: [Ollama](/nb/providers/ollama).
   </Accordion>
   <Accordion title="Moonshot and Kimi Coding">
     Moonshot (Kimi K2) and Kimi Coding configs are auto-written.
-    More detail: [Moonshot AI (Kimi + Kimi Coding)](/providers/moonshot).
+    More detail: [Moonshot AI (Kimi + Kimi Coding)](/nb/providers/moonshot).
   </Accordion>
   <Accordion title="Custom provider">
     Works with OpenAI-compatible and Anthropic-compatible endpoints.
@@ -294,6 +294,6 @@ Signal setup behavior:
 
 ## Related docs
 
-- Onboarding hub: [Onboarding (CLI)](/start/wizard)
-- Automation and scripts: [CLI Automation](/start/wizard-cli-automation)
-- Command reference: [`pllan onboard`](/cli/onboard)
+- Onboarding hub: [Onboarding (CLI)](/nb/start/wizard)
+- Automation and scripts: [CLI Automation](/nb/start/wizard-cli-automation)
+- Command reference: [`pllan onboard`](/nb/cli/onboard)

package/docs/nb/start/wizard.md

@@ -20,7 +20,7 @@ pllan onboard
 
 <Info>
 Raskeste forste chat: apne kontrollpanelet (ingen kanaloppsett nodvendig). Kjor
-`pllan dashboard` og chat i nettleseren. Dokumentasjon: [Dashbord](/web/dashboard).
+`pllan dashboard` og chat i nettleseren. Dokumentasjon: [Dashbord](/nb/web/dashboard).
 </Info>
 
 For a rekonfigurere senere:
@@ -38,7 +38,7 @@ pllan agents add <navn>
 CLI-introduksjonen inkluderer et nettsoksteg der du kan velge en leverandor
 (Perplexity, Brave, Gemini, Grok eller Kimi) og lime inn API-nokkelen din slik at agenten
 kan bruke `web_search`. Du kan ogsa konfigurere dette senere med
-`pllan configure --section web`. Dokumentasjon: [Nettverktoy](/tools/web).
+`pllan configure --section web`. Dokumentasjon: [Nettverktoy](/nb/tools/web).
 </Tip>
 
 ## Hurtigstart vs. Avansert
@@ -52,7 +52,7 @@ Introduksjonen starter med **Hurtigstart** (standardinnstillinger) vs. **Avanser
     - Gateway-port **18789**
     - Gateway-autentisering **Token** (automatisk generert, selv pa tilbakekobling)
     - Standard verktoyretningslinjer for nye lokale oppsett: `tools.profile: "coding"` (eksisterende eksplisitt profil bevares)
-    - Standard DM-isolasjon: lokal introduksjon skriver `session.dmScope: "per-channel-peer"` nar ikke satt. Detaljer: [CLI-oppsett-referanse](/start/wizard-cli-reference#outputs-and-internals)
+    - Standard DM-isolasjon: lokal introduksjon skriver `session.dmScope: "per-channel-peer"` nar ikke satt. Detaljer: [CLI-oppsett-referanse](/nb/start/wizard-cli-reference#outputs-and-internals)
     - Tailscale-eksponering **Av**
     - Telegram + WhatsApp DM-er standard til **tilgangsliste** (du blir spurt om telefonnummeret ditt)
   </Tab>
@@ -112,14 +112,14 @@ Merknader:
 ## Fullstendig referanse
 
 For detaljerte steg-for-steg-gjennomganger og konfigurasjonsutdata, se
-[CLI-oppsett-referanse](/start/wizard-cli-reference).
-For ikke-interaktive eksempler, se [CLI-automatisering](/start/wizard-cli-automation).
+[CLI-oppsett-referanse](/nb/start/wizard-cli-reference).
+For ikke-interaktive eksempler, se [CLI-automatisering](/nb/start/wizard-cli-automation).
 For den dypere tekniske referansen, inkludert RPC-detaljer, se
-[Introduksjonsreferanse](/reference/wizard).
+[Introduksjonsreferanse](/nb/reference/wizard).
 
 ## Relatert dokumentasjon
 
-- CLI-kommandoreferanse: [`pllan onboard`](/cli/onboard)
-- Introduksjonsoversikt: [Introduksjonsoversikt](/start/onboarding-overview)
-- macOS-app-introduksjon: [Introduksjon](/start/onboarding)
-- Agentens forstekjoringsritual: [Agentoppstart](/start/bootstrapping)
+- CLI-kommandoreferanse: [`pllan onboard`](/nb/cli/onboard)
+- Introduksjonsoversikt: [Introduksjonsoversikt](/nb/start/onboarding-overview)
+- macOS-app-introduksjon: [Introduksjon](/nb/start/onboarding)
+- Agentens forstekjoringsritual: [Agentoppstart](/nb/start/bootstrapping)

package/docs/nb/tools/acp-agents.md

@@ -60,7 +60,7 @@ Use ACP when you want an external harness runtime. Use sub-agents when you want
 | Main commands | `/acp ...`                            | `/subagents ...`                   |
 | Spawn tool    | `sessions_spawn` with `runtime:"acp"` | `sessions_spawn` (default runtime) |
 
-See also [Sub-agents](/tools/subagents).
+See also [Sub-agents](/nb/tools/subagents).
 
 ## Thread-bound sessions (channel-agnostic)
 
@@ -343,7 +343,7 @@ Key flags:
 - `--cwd <absolute-path>`
 - `--label <name>`
 
-See [Slash Commands](/tools/slash-commands).
+See [Slash Commands](/nb/tools/slash-commands).
 
 ## Session target resolution
 
@@ -503,7 +503,7 @@ If thread-bound ACP spawn does not work, verify the adapter feature flag first:
 
 - Discord: `channels.discord.threadBindings.spawnAcpSessions=true`
 
-See [Configuration Reference](/gateway/configuration-reference).
+See [Configuration Reference](/nb/gateway/configuration-reference).
 
 ## Plugin setup for acpx backend
 
@@ -563,7 +563,7 @@ Notes:
 - When `command` points to a custom binary/path, plugin-local auto-install is disabled.
 - Pllan startup remains non-blocking while the backend health check runs.
 
-See [Plugins](/tools/plugin).
+See [Plugins](/nb/tools/plugin).
 
 ## Permission configuration
 

package/docs/nb/tools/brave-search.md

@@ -90,4 +90,4 @@ await web_search({
 - The Search plan includes the LLM Context endpoint and AI inference rights. Storing results to train or tune models requires a plan with explicit storage rights. See the Brave [Terms of Service](https://api-dashboard.search.brave.com/terms-of-service).
 - Results are cached for 15 minutes by default (configurable via `cacheTtlMinutes`).
 
-See [Web tools](/tools/web) for the full web_search configuration.
+See [Web tools](/nb/tools/web) for the full web_search configuration.

package/docs/nb/tools/browser-login.md

@@ -14,7 +14,7 @@ When a site requires login, **sign in manually** in the **host** browser profile
 
 Do **not** give the model your credentials. Automated logins often trigger anti‑bot defenses and can lock the account.
 
-Back to the main browser docs: [Browser](/tools/browser).
+Back to the main browser docs: [Browser](/nb/tools/browser).
 
 ## Which Chrome profile is used?
 

package/docs/nb/tools/browser-wsl2-windows-remote-cdp-troubleshooting.md

@@ -73,7 +73,7 @@ Use:
 
 `http://127.0.0.1:18789/`
 
-Do not default to a LAN IP for the Control UI. Plain HTTP on a LAN or tailnet address can trigger insecure-origin/device-auth behavior that is unrelated to CDP itself. See [Control UI](/web/control-ui).
+Do not default to a LAN IP for the Control UI. Plain HTTP on a LAN or tailnet address can trigger insecure-origin/device-auth behavior that is unrelated to CDP itself. See [Control UI](/nb/web/control-ui).
 
 ## Validate in layers
 
@@ -158,7 +158,7 @@ Then verify:
 
 Helpful page:
 
-- [Control UI](/web/control-ui)
+- [Control UI](/nb/web/control-ui)
 
 ### Layer 5: Verify end-to-end browser control
 

package/docs/nb/tools/browser.md

@@ -471,7 +471,7 @@ docker compose run --rm pllan-cli \
 
 To persist browser downloads, set `PLAYWRIGHT_BROWSERS_PATH` (for example,
 `/home/node/.cache/ms-playwright`) and make sure `/home/node` is persisted via
-`PLLAN_HOME_VOLUME` or a bind mount. See [Docker](/install/docker).
+`PLLAN_HOME_VOLUME` or a bind mount. See [Docker](/nb/install/docker).
 
 ## How it works (internal)
 
@@ -581,7 +581,7 @@ Notes:
   - `--format ai` (default when Playwright is installed): returns an AI snapshot with numeric refs (`aria-ref="<n>"`).
   - `--format aria`: returns the accessibility tree (no refs; inspection only).
   - `--efficient` (or `--mode efficient`): compact role snapshot preset (interactive + compact + depth + lower maxChars).
-  - Config default (tool/CLI only): set `browser.snapshotDefaults.mode: "efficient"` to use efficient snapshots when the caller does not pass a mode (see [Gateway configuration](/gateway/configuration-reference#browser)).
+  - Config default (tool/CLI only): set `browser.snapshotDefaults.mode: "efficient"` to use efficient snapshots when the caller does not pass a mode (see [Gateway configuration](/nb/gateway/configuration-reference#browser)).
   - Role snapshot options (`--interactive`, `--compact`, `--depth`, `--selector`) force a role-based snapshot with refs like `ref=e12`.
   - `--frame "<iframe selector>"` scopes role snapshots to an iframe (pairs with role refs like `e12`).
   - `--interactive` outputs a flat, easy-to-pick list of interactive elements (best for driving actions).
@@ -684,7 +684,7 @@ These are useful for “make the site behave like X” workflows:
 - `browser act kind=evaluate` / `pllan browser evaluate` and `wait --fn`
   execute arbitrary JavaScript in the page context. Prompt injection can steer
   this. Disable it with `browser.evaluateEnabled=false` if you do not need it.
-- For logins and anti-bot notes (X/Twitter, etc.), see [Browser login + X/Twitter posting](/tools/browser-login).
+- For logins and anti-bot notes (X/Twitter, etc.), see [Browser login + X/Twitter posting](/nb/tools/browser-login).
 - Keep the Gateway/node host private (loopback or tailnet-only).
 - Remote CDP endpoints are powerful; tunnel and protect them.
 
@@ -705,10 +705,10 @@ Strict-mode example (block private/internal destinations by default):
 ## Troubleshooting
 
 For Linux-specific issues (especially snap Chromium), see
-[Browser troubleshooting](/tools/browser-linux-troubleshooting).
+[Browser troubleshooting](/nb/tools/browser-linux-troubleshooting).
 
 For WSL2 Gateway + Windows Chrome split-host setups, see
-[WSL2 + Windows + remote Chrome CDP troubleshooting](/tools/browser-wsl2-windows-remote-cdp-troubleshooting).
+[WSL2 + Windows + remote Chrome CDP troubleshooting](/nb/tools/browser-wsl2-windows-remote-cdp-troubleshooting).
 
 ## Agent tools + how control works
 

package/docs/nb/tools/btw.md

@@ -137,6 +137,6 @@ In that case, ask normally in the main session instead of using BTW.
 
 ## Related
 
-- [Slash commands](/tools/slash-commands)
-- [Thinking Levels](/tools/thinking)
-- [Session](/concepts/session)
+- [Slash commands](/nb/tools/slash-commands)
+- [Thinking Levels](/nb/tools/thinking)
+- [Session](/nb/concepts/session)

package/docs/nb/tools/clawhub.md

@@ -69,7 +69,7 @@ pnpm add -g clawhub
 By default, the CLI installs skills into `./skills` under your current working directory. If an Pllan workspace is configured, `clawhub` falls back to that workspace unless you override `--workdir` (or `CLAWHUB_WORKDIR`). Pllan loads workspace skills from `<workspace>/skills` and will pick them up in the **next** session. If you already use `~/.pllan/skills` or bundled skills, workspace skills take precedence.
 
 For more detail on how skills are loaded, shared, and gated, see
-[Skills](/tools/skills).
+[Skills](/nb/tools/skills).
 
 ## Skill system overview
 

package/docs/nb/tools/diffs.md

@@ -381,6 +381,6 @@ Diff rendering engine:
 
 ## Related docs
 
-- [Tools overview](/tools)
-- [Plugins](/tools/plugin)
-- [Browser](/tools/browser)
+- [Tools overview](/nb/tools)
+- [Plugins](/nb/tools/plugin)
+- [Browser](/nb/tools/browser)

package/docs/nb/tools/exec-approvals.md

@@ -253,7 +253,7 @@ must advertise `system.execApprovals.get/set` (macOS app or headless node host).
 If a node does not advertise exec approvals yet, edit its local
 `~/.pllan/exec-approvals.json` directly.
 
-CLI: `pllan approvals` supports gateway or node editing (see [Approvals CLI](/cli/approvals)).
+CLI: `pllan approvals` supports gateway or node editing (see [Approvals CLI](/nb/cli/approvals)).
 
 ## Approval flow
 
@@ -354,8 +354,8 @@ topics, Pllan preserves the topic for the approval prompt and the post-approval
 
 See:
 
-- [Discord](/channels/discord#exec-approvals-in-discord)
-- [Telegram](/channels/telegram#exec-approvals-in-telegram)
+- [Discord](/nb/channels/discord#exec-approvals-in-discord)
+- [Telegram](/nb/channels/telegram#exec-approvals-in-telegram)
 
 ### macOS IPC flow
 
@@ -395,6 +395,6 @@ Approval-gated execs reuse the approval id as the `runId` in these messages for
 
 Related:
 
-- [Exec tool](/tools/exec)
-- [Elevated mode](/tools/elevated)
-- [Skills](/tools/skills)
+- [Exec tool](/nb/tools/exec)
+- [Elevated mode](/nb/tools/elevated)
+- [Skills](/nb/tools/skills)

package/docs/nb/tools/exec.md

@@ -57,7 +57,7 @@ Notes:
 - `tools.exec.ask` (default: `on-miss`)
 - `tools.exec.node` (default: unset)
 - `tools.exec.pathPrepend`: list of directories to prepend to `PATH` for exec runs (gateway + sandbox only).
-- `tools.exec.safeBins`: stdin-only safe binaries that can run without explicit allowlist entries. For behavior details, see [Safe bins](/tools/exec-approvals#safe-bins-stdin-only).
+- `tools.exec.safeBins`: stdin-only safe binaries that can run without explicit allowlist entries. For behavior details, see [Safe bins](/nb/tools/exec-approvals#safe-bins-stdin-only).
 - `tools.exec.safeBinTrustedDirs`: additional explicit directories trusted for `safeBins` path checks. `PATH` entries are never auto-trusted. Built-in defaults are `/bin` and `/usr/bin`.
 - `tools.exec.safeBinProfiles`: optional custom argv policy per safe bin (`minPositional`, `maxPositional`, `allowedValueFlags`, `deniedFlags`).
 
@@ -116,7 +116,7 @@ policy (`tools.deny: ["exec"]` or per-agent). Host approvals still apply unless
 ## Exec approvals (companion app / node host)
 
 Sandboxed agents can require per-request approval before `exec` runs on the gateway or node host.
-See [Exec approvals](/tools/exec-approvals) for the policy, allowlist, and UI flow.
+See [Exec approvals](/nb/tools/exec-approvals) for the policy, allowlist, and UI flow.
 
 When approvals are required, the exec tool returns immediately with
 `status: "approval-pending"` and an approval id. Once approved (or denied / timed out),
@@ -144,7 +144,7 @@ Use the two controls for different jobs:
 Do not treat `safeBins` as a generic allowlist, and do not add interpreter/runtime binaries (for example `python3`, `node`, `ruby`, `bash`). If you need those, use explicit allowlist entries and keep approval prompts enabled.
 `pllan security audit` warns when interpreter/runtime `safeBins` entries are missing explicit profiles, and `pllan doctor --fix` can scaffold missing custom `safeBinProfiles` entries.
 
-For full policy details and examples, see [Exec approvals](/tools/exec-approvals#safe-bins-stdin-only) and [Safe bins versus allowlist](/tools/exec-approvals#safe-bins-versus-allowlist).
+For full policy details and examples, see [Exec approvals](/nb/tools/exec-approvals#safe-bins-stdin-only) and [Safe bins versus allowlist](/nb/tools/exec-approvals#safe-bins-versus-allowlist).
 
 ## Examples
 

package/docs/nb/tools/firecrawl.md

@@ -137,4 +137,4 @@ than basic-only scraping.
 2. Firecrawl (if configured)
 3. Basic HTML cleanup (last fallback)
 
-See [Web tools](/tools/web) for the full web tool setup.
+See [Web tools](/nb/tools/web) for the full web tool setup.

package/docs/nb/tools/index.md

@@ -166,15 +166,15 @@ Example (allow only file tools + browser):
 ## Plugins + tools
 
 Plugins can register **additional tools** (and CLI commands) beyond the core set.
-See [Plugins](/tools/plugin) for install + config, and [Skills](/tools/skills) for how
+See [Plugins](/nb/tools/plugin) for install + config, and [Skills](/nb/tools/skills) for how
 tool usage guidance is injected into prompts. Some plugins ship their own skills
 alongside tools (for example, the voice-call plugin).
 
 Optional plugin tools:
 
-- [pllan](/tools/pllan): typed workflow runtime with resumable approvals (requires the pllan CLI on the gateway host).
-- [LLM Task](/tools/llm-task): JSON-only LLM step for structured workflow output (optional schema validation).
-- [Diffs](/tools/diffs): read-only diff viewer and PNG or PDF file renderer for before/after text or unified patches.
+- [pllan](/nb/tools/pllan): typed workflow runtime with resumable approvals (requires the pllan CLI on the gateway host).
+- [LLM Task](/nb/tools/llm-task): JSON-only LLM step for structured workflow output (optional schema validation).
+- [Diffs](/nb/tools/diffs): read-only diff viewer and PNG or PDF file renderer for before/after text or unified patches.
 
 ## Tool inventory
 
@@ -209,7 +209,7 @@ Notes:
 - `elevated` is gated by `tools.elevated` plus any `agents.list[].tools.elevated` override (both must allow) and is an alias for `host=gateway` + `security=full`.
 - `elevated` only changes behavior when the agent is sandboxed (otherwise it’s a no-op).
 - `host=node` can target a macOS companion app or a headless node host (`pllan node run`).
-- gateway/node approvals and allowlists: [Exec approvals](/tools/exec-approvals).
+- gateway/node approvals and allowlists: [Exec approvals](/nb/tools/exec-approvals).
 
 ### `process`
 
@@ -268,7 +268,7 @@ Notes:
 - Requires an API key for the chosen provider (recommended: `pllan configure --section web`).
 - Enable via `tools.web.search.enabled`.
 - Responses are cached (default 15 min).
-- See [Web tools](/tools/web) for setup.
+- See [Web tools](/nb/tools/web) for setup.
 
 ### `web_fetch`
 
@@ -286,8 +286,8 @@ Notes:
 - `maxChars` is clamped by `tools.web.fetch.maxCharsCap` (default 50000).
 - Responses are cached (default 15 min).
 - For JS-heavy sites, prefer the browser tool.
-- See [Web tools](/tools/web) for setup.
-- See [Firecrawl](/tools/firecrawl) for the optional anti-bot fallback.
+- See [Web tools](/nb/tools/web) for setup.
+- See [Firecrawl](/nb/tools/firecrawl) for the optional anti-bot fallback.
 
 ### `browser`
 
@@ -444,7 +444,7 @@ Native example:
 
 Analyze one or more PDF documents.
 
-For full behavior, limits, config, and examples, see [PDF tool](/tools/pdf).
+For full behavior, limits, config, and examples, see [PDF tool](/nb/tools/pdf).
 
 ### `message`
 
@@ -529,7 +529,7 @@ Notes:
 - Session targeting is controlled by `tools.sessions.visibility` (default `tree`: current session + spawned subagent sessions). If you run a shared agent for multiple users, consider setting `tools.sessions.visibility: "self"` to prevent cross-session browsing.
 - `sessions_send` waits for final completion when `timeoutSeconds > 0`.
 - Delivery/announce happens after completion and is best-effort; `status: "ok"` confirms the agent run finished, not that the announce was delivered.
-- `sessions_spawn` supports `runtime: "subagent" | "acp"` (`subagent` default). For ACP runtime behavior, see [ACP Agents](/tools/acp-agents).
+- `sessions_spawn` supports `runtime: "subagent" | "acp"` (`subagent` default). For ACP runtime behavior, see [ACP Agents](/nb/tools/acp-agents).
 - For ACP runtime, `streamTo: "parent"` routes initial-run progress summaries back to the requester session as system events instead of direct child delivery.
 - `sessions_spawn` starts a sub-agent run and posts an announce reply back to the requester chat.
   - Supports one-shot mode (`mode: "run"`) and persistent thread-bound mode (`mode: "session"` with `thread: true`).
@@ -575,8 +575,8 @@ Browser tool:
 - `target` (`sandbox` | `host` | `node`)
 - `node` (optional; pin a specific node id/name)
 - Troubleshooting guides:
-  - Linux startup/CDP issues: [Browser troubleshooting (Linux)](/tools/browser-linux-troubleshooting)
-  - WSL2 Gateway + Windows remote Chrome CDP: [WSL2 + Windows + remote Chrome CDP troubleshooting](/tools/browser-wsl2-windows-remote-cdp-troubleshooting)
+  - Linux startup/CDP issues: [Browser troubleshooting (Linux)](/nb/tools/browser-linux-troubleshooting)
+  - WSL2 Gateway + Windows remote Chrome CDP: [WSL2 + Windows + remote Chrome CDP troubleshooting](/nb/tools/browser-wsl2-windows-remote-cdp-troubleshooting)
 
 ## Recommended agent flows
 

package/docs/nb/tools/multi-agent-sandbox-tools.md

@@ -11,9 +11,9 @@ Each agent in a multi-agent setup can override the global sandbox and tool
 policy. This page covers per-agent configuration, precedence rules, and
 examples.
 
-- **Sandbox backends and modes**: see [Sandboxing](/gateway/sandboxing).
-- **Debugging blocked tools**: see [Sandbox vs Tool Policy vs Elevated](/gateway/sandbox-vs-tool-policy-vs-elevated) and `pllan sandbox explain`.
-- **Elevated exec**: see [Elevated Mode](/tools/elevated).
+- **Sandbox backends and modes**: see [Sandboxing](/nb/gateway/sandboxing).
+- **Debugging blocked tools**: see [Sandbox vs Tool Policy vs Elevated](/nb/gateway/sandbox-vs-tool-policy-vs-elevated) and `pllan sandbox explain`.
+- **Elevated exec**: see [Elevated Mode](/nb/tools/elevated).
 
 Auth is per-agent: each agent reads from its own `agentDir` auth store at
 `~/.pllan/agents/<agentId>/agent/auth-profiles.json`.
@@ -207,9 +207,9 @@ If `agents.list[].tools.sandbox.tools` is set, it replaces `tools.sandbox.tools`
 If `agents.list[].tools.profile` is set, it overrides `tools.profile` for that agent.
 Provider tool keys accept either `provider` (e.g. `google-antigravity`) or `provider/model` (e.g. `openai/gpt-5.2`).
 
-Tool policies support `group:*` shorthands that expand to multiple tools. See [Tool groups](/gateway/sandbox-vs-tool-policy-vs-elevated#tool-groups-shorthands) for the full list.
+Tool policies support `group:*` shorthands that expand to multiple tools. See [Tool groups](/nb/gateway/sandbox-vs-tool-policy-vs-elevated#tool-groups-shorthands) for the full list.
 
-Per-agent elevated overrides (`agents.list[].tools.elevated`) can further restrict elevated exec for specific agents. See [Elevated Mode](/tools/elevated) for details.
+Per-agent elevated overrides (`agents.list[].tools.elevated`) can further restrict elevated exec for specific agents. See [Elevated Mode](/nb/tools/elevated) for details.
 
 ---
 
@@ -356,9 +356,9 @@ After configuring multi-agent sandbox and tools:
 
 ## See also
 
-- [Sandboxing](/gateway/sandboxing) -- full sandbox reference (modes, scopes, backends, images)
-- [Sandbox vs Tool Policy vs Elevated](/gateway/sandbox-vs-tool-policy-vs-elevated) -- debugging "why is this blocked?"
-- [Elevated Mode](/tools/elevated)
-- [Multi-Agent Routing](/concepts/multi-agent)
-- [Sandbox Configuration](/gateway/configuration-reference#agents-defaults-sandbox)
-- [Session Management](/concepts/session)
+- [Sandboxing](/nb/gateway/sandboxing) -- full sandbox reference (modes, scopes, backends, images)
+- [Sandbox vs Tool Policy vs Elevated](/nb/gateway/sandbox-vs-tool-policy-vs-elevated) -- debugging "why is this blocked?"
+- [Elevated Mode](/nb/tools/elevated)
+- [Multi-Agent Routing](/nb/concepts/multi-agent)
+- [Sandbox Configuration](/nb/gateway/configuration-reference#agents-defaults-sandbox)
+- [Session Management](/nb/concepts/session)