pllan 2026.3.47 → 2026.3.49

package/docs/nb/cli/index.md

@@ -12,52 +12,52 @@ This page describes the current CLI behavior. If commands change, update this do
 
 ## Command pages
 
-- [`setup`](/cli/setup)
-- [`onboard`](/cli/onboard)
-- [`configure`](/cli/configure)
-- [`config`](/cli/config)
-- [`completion`](/cli/completion)
-- [`doctor`](/cli/doctor)
-- [`dashboard`](/cli/dashboard)
-- [`backup`](/cli/backup)
-- [`reset`](/cli/reset)
-- [`uninstall`](/cli/uninstall)
-- [`update`](/cli/update)
-- [`message`](/cli/message)
-- [`agent`](/cli/agent)
-- [`agents`](/cli/agents)
-- [`acp`](/cli/acp)
-- [`status`](/cli/status)
-- [`health`](/cli/health)
-- [`sessions`](/cli/sessions)
-- [`gateway`](/cli/gateway)
-- [`logs`](/cli/logs)
-- [`system`](/cli/system)
-- [`models`](/cli/models)
-- [`memory`](/cli/memory)
-- [`directory`](/cli/directory)
-- [`nodes`](/cli/nodes)
-- [`devices`](/cli/devices)
-- [`node`](/cli/node)
-- [`approvals`](/cli/approvals)
-- [`sandbox`](/cli/sandbox)
-- [`tui`](/cli/tui)
-- [`browser`](/cli/browser)
-- [`cron`](/cli/cron)
-- [`dns`](/cli/dns)
-- [`docs`](/cli/docs)
-- [`hooks`](/cli/hooks)
-- [`webhooks`](/cli/webhooks)
-- [`pairing`](/cli/pairing)
-- [`qr`](/cli/qr)
-- [`plugins`](/cli/plugins) (plugin commands)
-- [`channels`](/cli/channels)
-- [`security`](/cli/security)
-- [`secrets`](/cli/secrets)
-- [`skills`](/cli/skills)
-- [`daemon`](/cli/daemon) (legacy alias for gateway service commands)
-- [`clawbot`](/cli/clawbot) (legacy alias namespace)
-- [`voicecall`](/cli/voicecall) (plugin; if installed)
+- [`setup`](/nb/cli/setup)
+- [`onboard`](/nb/cli/onboard)
+- [`configure`](/nb/cli/configure)
+- [`config`](/nb/cli/config)
+- [`completion`](/nb/cli/completion)
+- [`doctor`](/nb/cli/doctor)
+- [`dashboard`](/nb/cli/dashboard)
+- [`backup`](/nb/cli/backup)
+- [`reset`](/nb/cli/reset)
+- [`uninstall`](/nb/cli/uninstall)
+- [`update`](/nb/cli/update)
+- [`message`](/nb/cli/message)
+- [`agent`](/nb/cli/agent)
+- [`agents`](/nb/cli/agents)
+- [`acp`](/nb/cli/acp)
+- [`status`](/nb/cli/status)
+- [`health`](/nb/cli/health)
+- [`sessions`](/nb/cli/sessions)
+- [`gateway`](/nb/cli/gateway)
+- [`logs`](/nb/cli/logs)
+- [`system`](/nb/cli/system)
+- [`models`](/nb/cli/models)
+- [`memory`](/nb/cli/memory)
+- [`directory`](/nb/cli/directory)
+- [`nodes`](/nb/cli/nodes)
+- [`devices`](/nb/cli/devices)
+- [`node`](/nb/cli/node)
+- [`approvals`](/nb/cli/approvals)
+- [`sandbox`](/nb/cli/sandbox)
+- [`tui`](/nb/cli/tui)
+- [`browser`](/nb/cli/browser)
+- [`cron`](/nb/cli/cron)
+- [`dns`](/nb/cli/dns)
+- [`docs`](/nb/cli/docs)
+- [`hooks`](/nb/cli/hooks)
+- [`webhooks`](/nb/cli/webhooks)
+- [`pairing`](/nb/cli/pairing)
+- [`qr`](/nb/cli/qr)
+- [`plugins`](/nb/cli/plugins) (plugin commands)
+- [`channels`](/nb/cli/channels)
+- [`security`](/nb/cli/security)
+- [`secrets`](/nb/cli/secrets)
+- [`skills`](/nb/cli/skills)
+- [`daemon`](/nb/cli/daemon) (legacy alias for gateway service commands)
+- [`clawbot`](/nb/cli/clawbot) (legacy alias namespace)
+- [`voicecall`](/nb/cli/voicecall) (plugin; if installed)
 
 ## Global flags
 
@@ -291,7 +291,7 @@ Manage extensions and their config:
 - `pllan plugins enable <id>` / `disable <id>` — toggle `plugins.entries.<id>.enabled`.
 - `pllan plugins doctor` — report plugin load errors.
 
-Most plugin changes require a gateway restart. See [/plugin](/tools/plugin).
+Most plugin changes require a gateway restart. See [/plugin](/nb/tools/plugin).
 
 ## Memory
 
@@ -303,7 +303,7 @@ Vector search over `MEMORY.md` + `memory/*.md`:
 
 ## Chat slash commands
 
-Chat messages support `/...` commands (text and native). See [/tools/slash-commands](/tools/slash-commands).
+Chat messages support `/...` commands (text and native). See [/tools/slash-commands](/nb/tools/slash-commands).
 
 Highlights:
 
@@ -467,7 +467,7 @@ Common options:
 - `--lines <n>` (default `200`)
 - `--json`
 
-More detail: [/concepts/oauth](/concepts/oauth)
+More detail: [/concepts/oauth](/nb/concepts/oauth)
 
 Examples:
 
@@ -523,7 +523,7 @@ Subcommands:
 
 ### `webhooks gmail`
 
-Gmail Pub/Sub hook setup + runner. See [/automation/gmail-pubsub](/automation/gmail-pubsub).
+Gmail Pub/Sub hook setup + runner. See [/automation/gmail-pubsub](/nb/automation/gmail-pubsub).
 
 Subcommands:
 
@@ -532,7 +532,7 @@ Subcommands:
 
 ### `dns setup`
 
-Wide-area discovery DNS helper (CoreDNS + Tailscale). See [/gateway/discovery](/gateway/discovery).
+Wide-area discovery DNS helper (CoreDNS + Tailscale). See [/gateway/discovery](/nb/gateway/discovery).
 
 Options:
 
@@ -544,7 +544,7 @@ Options:
 
 Unified outbound messaging + channel actions.
 
-See: [/cli/message](/cli/message)
+See: [/cli/message](/nb/cli/message)
 
 Subcommands:
 
@@ -654,7 +654,7 @@ Options:
 
 Run the ACP bridge that connects IDEs to the Gateway.
 
-See [`acp`](/cli/acp) for full options and examples.
+See [`acp`](/nb/cli/acp) for full options and examples.
 
 ### `status`
 
@@ -689,7 +689,7 @@ Notes:
 - Data comes directly from provider usage endpoints (no estimates).
 - Providers: Anthropic, GitHub Copilot, OpenAI Codex OAuth, plus Gemini CLI via the bundled `google` plugin and Antigravity where configured.
 - If no matching credentials exist, usage is hidden.
-- Details: see [Usage tracking](/concepts/usage-tracking).
+- Details: see [Usage tracking](/nb/concepts/usage-tracking).
 
 ### `health`
 
@@ -846,7 +846,7 @@ Tip: when calling `config.set`/`config.apply`/`config.patch` directly, pass `bas
 
 ## Models
 
-See [/concepts/models](/concepts/models) for fallback behavior and scanning strategy.
+See [/concepts/models](/nb/concepts/models) for fallback behavior and scanning strategy.
 
 Anthropic setup-token (supported):
 
@@ -999,7 +999,7 @@ Options:
 
 ## Cron
 
-Manage scheduled jobs (Gateway RPC). See [/automation/cron-jobs](/automation/cron-jobs).
+Manage scheduled jobs (Gateway RPC). See [/automation/cron-jobs](/nb/automation/cron-jobs).
 
 Subcommands:
 
@@ -1018,7 +1018,7 @@ All `cron` commands accept `--url`, `--token`, `--timeout`, `--expect-final`.
 ## Node host
 
 `node` runs a **headless node host** or manages it as a background service. See
-[`pllan node`](/cli/node).
+[`pllan node`](/nb/cli/node).
 
 Subcommands:
 
@@ -1036,7 +1036,7 @@ Auth notes:
 
 ## Nodes
 
-`nodes` talks to the Gateway and targets paired nodes. See [/nodes](/nodes).
+`nodes` talks to the Gateway and targets paired nodes. See [/nodes](/nb/nodes).
 
 Common options:
 
@@ -1078,7 +1078,7 @@ Location:
 
 ## Browser
 
-Browser control CLI (dedicated Chrome/Brave/Edge/Chromium). See [`pllan browser`](/cli/browser) and the [Browser tool](/tools/browser).
+Browser control CLI (dedicated Chrome/Brave/Edge/Chromium). See [`pllan browser`](/nb/cli/browser) and the [Browser tool](/nb/tools/browser).
 
 Common options:
 

package/docs/nb/cli/logs.md

@@ -12,7 +12,7 @@ Tail Gateway file logs over RPC (works in remote mode).
 
 Related:
 
-- Logging overview: [Logging](/logging)
+- Logging overview: [Logging](/nb/logging)
 
 ## Examples
 

package/docs/nb/cli/memory.md

@@ -13,8 +13,8 @@ Provided by the active memory plugin (default: `memory-core`; set `plugins.slots
 
 Related:
 
-- Memory concept: [Memory](/concepts/memory)
-- Plugins: [Plugins](/tools/plugin)
+- Memory concept: [Memory](/nb/concepts/memory)
+- Plugins: [Plugins](/nb/tools/plugin)
 
 ## Examples
 

package/docs/nb/cli/message.md

@@ -210,7 +210,7 @@ pllan message send --channel discord \
   --components '{"text":"Choose a path","blocks":[{"type":"actions","buttons":[{"label":"Approve","style":"success"},{"label":"Decline","style":"danger"}]}]}'
 ```
 
-See [Discord components](/channels/discord#interactive-components) for the full schema.
+See [Discord components](/nb/channels/discord#interactive-components) for the full schema.
 
 Create a Discord poll:
 

package/docs/nb/cli/models.md

@@ -12,8 +12,8 @@ Model discovery, scanning, and configuration (default model, fallbacks, auth pro
 
 Related:
 
-- Providers + models: [Models](/providers/models)
-- Provider auth setup: [Getting started](/start/getting-started)
+- Providers + models: [Models](/nb/providers/models)
+- Provider auth setup: [Getting started](/nb/start/getting-started)
 
 ## Common commands
 

package/docs/nb/cli/node.md

@@ -123,5 +123,5 @@ The node host stores its node id, token, display name, and gateway connection in
 `system.run` is gated by local exec approvals:
 
 - `~/.pllan/exec-approvals.json`
-- [Exec approvals](/tools/exec-approvals)
+- [Exec approvals](/nb/tools/exec-approvals)
 - `pllan approvals --node <id|name|ip>` (edit from the Gateway)

package/docs/nb/cli/nodes.md

@@ -12,9 +12,9 @@ Manage paired nodes (devices) and invoke node capabilities.
 
 Related:
 
-- Nodes overview: [Nodes](/nodes)
-- Camera: [Camera nodes](/nodes/camera)
-- Images: [Image nodes](/nodes/images)
+- Nodes overview: [Nodes](/nb/nodes)
+- Camera: [Camera nodes](/nb/nodes/camera)
+- Images: [Image nodes](/nb/nodes/images)
 
 Common options:
 

package/docs/nb/cli/onboard.md

@@ -11,11 +11,11 @@ Interactive onboarding for local or remote Gateway setup.
 
 ## Related guides
 
-- CLI onboarding hub: [Onboarding (CLI)](/start/wizard)
-- Onboarding overview: [Onboarding Overview](/start/onboarding-overview)
-- CLI onboarding reference: [CLI Setup Reference](/start/wizard-cli-reference)
-- CLI automation: [CLI Automation](/start/wizard-cli-automation)
-- macOS onboarding: [Onboarding (macOS App)](/start/onboarding)
+- CLI onboarding hub: [Onboarding (CLI)](/nb/start/wizard)
+- Onboarding overview: [Onboarding Overview](/nb/start/onboarding-overview)
+- CLI onboarding reference: [CLI Setup Reference](/nb/start/wizard-cli-reference)
+- CLI automation: [CLI Automation](/nb/start/wizard-cli-automation)
+- macOS onboarding: [Onboarding (macOS App)](/nb/start/onboarding)
 
 ## Examples
 
@@ -140,7 +140,7 @@ Flow notes:
 
 - `quickstart`: minimal prompts, auto-generates a gateway token.
 - `manual`: full prompts for port/bind/auth (alias of `advanced`).
-- Local onboarding DM scope behavior: [CLI Setup Reference](/start/wizard-cli-reference#outputs-and-internals).
+- Local onboarding DM scope behavior: [CLI Setup Reference](/nb/start/wizard-cli-reference#outputs-and-internals).
 - Fastest first chat: `pllan dashboard` (Control UI, no channel setup).
 - Custom Provider: connect any OpenAI or Anthropic compatible endpoint,
   including hosted providers not listed. Use Unknown to auto-detect.

package/docs/nb/cli/pairing.md

@@ -11,7 +11,7 @@ Approve or inspect DM pairing requests (for channels that support pairing).
 
 Related:
 
-- Pairing flow: [Pairing](/channels/pairing)
+- Pairing flow: [Pairing](/nb/channels/pairing)
 
 ## Commands
 

package/docs/nb/cli/plugins.md

@@ -12,10 +12,10 @@ Manage Gateway plugins/extensions and compatible bundles.
 
 Related:
 
-- Plugin system: [Plugins](/tools/plugin)
-- Bundle compatibility: [Plugin bundles](/plugins/bundles)
-- Plugin manifest + schema: [Plugin manifest](/plugins/manifest)
-- Security hardening: [Security](/gateway/security)
+- Plugin system: [Plugins](/nb/tools/plugin)
+- Bundle compatibility: [Plugin bundles](/nb/plugins/bundles)
+- Plugin manifest + schema: [Plugin manifest](/nb/plugins/manifest)
+- Security hardening: [Security](/nb/gateway/security)
 
 ## Commands
 
@@ -178,7 +178,7 @@ Each plugin is classified by what it actually registers at runtime:
 - **hook-only** — only hooks, no capabilities or surfaces
 - **non-capability** — tools/commands/services but no capabilities
 
-See [Plugin shapes](/plugins/architecture#plugin-shapes) for more on the capability model.
+See [Plugin shapes](/nb/plugins/architecture#plugin-shapes) for more on the capability model.
 
 The `--json` flag outputs a machine-readable report suitable for scripting and
 auditing.

package/docs/nb/cli/sandbox.md

@@ -192,6 +192,6 @@ Sandbox settings live in `~/.pllan/pllan.json` under `agents.defaults.sandbox` (
 
 ## See Also
 
-- [Sandbox Documentation](/gateway/sandboxing)
-- [Agent Configuration](/concepts/agent-workspace)
-- [Doctor Command](/gateway/doctor) - Check sandbox setup
+- [Sandbox Documentation](/nb/gateway/sandboxing)
+- [Agent Configuration](/nb/concepts/agent-workspace)
+- [Doctor Command](/nb/gateway/doctor) - Check sandbox setup

package/docs/nb/cli/secrets.md

@@ -38,9 +38,9 @@ Exit code note for CI/gates:
 
 Related:
 
-- Secrets guide: [Secrets Management](/gateway/secrets)
-- Credential surface: [SecretRef Credential Surface](/reference/secretref-credential-surface)
-- Security guide: [Security](/gateway/security)
+- Secrets guide: [Secrets Management](/nb/gateway/secrets)
+- Credential surface: [SecretRef Credential Surface](/nb/reference/secretref-credential-surface)
+- Security guide: [Security](/nb/gateway/security)
 
 ## Reload runtime snapshot
 
@@ -127,7 +127,7 @@ Notes:
 - You cannot combine `--providers-only` with `--skip-provider-setup`.
 - `configure` targets secret-bearing fields in `pllan.json` plus `auth-profiles.json` for the selected agent scope.
 - `configure` supports creating new `auth-profiles.json` mappings directly in the picker flow.
-- Canonical supported surface: [SecretRef Credential Surface](/reference/secretref-credential-surface).
+- Canonical supported surface: [SecretRef Credential Surface](/nb/reference/secretref-credential-surface).
 - It performs preflight resolution before apply.
 - If preflight/apply includes exec refs, keep `--allow-exec` set for both steps.
 - Generated plans default to scrub options (`scrubEnv`, `scrubAuthProfilesForProviderTargets`, `scrubLegacyAuthJson` all enabled).
@@ -162,7 +162,7 @@ Exec behavior:
 
 Plan contract details (allowed target paths, validation rules, and failure semantics):
 
-- [Secrets Apply Plan Contract](/gateway/secrets-plan-contract)
+- [Secrets Apply Plan Contract](/nb/gateway/secrets-plan-contract)
 
 What `apply` may update:
 

package/docs/nb/cli/security.md

@@ -12,7 +12,7 @@ Security tools (audit + optional fixes).
 
 Related:
 
-- Security guide: [Security](/gateway/security)
+- Security guide: [Security](/nb/gateway/security)
 
 ## Audit
 
@@ -40,7 +40,7 @@ It also warns when npm-based plugin/hook install records are unpinned, missing i
 It warns when channel allowlists rely on mutable names/emails/tags instead of stable IDs (Discord, Slack, Google Chat, Microsoft Teams, Mattermost, IRC scopes where applicable).
 It warns when `gateway.auth.mode="none"` leaves Gateway HTTP APIs reachable without a shared secret (`/tools/invoke` plus any enabled `/v1/*` endpoint).
 Settings prefixed with `dangerous`/`dangerously` are explicit break-glass operator overrides; enabling one is not, by itself, a security vulnerability report.
-For the complete dangerous-parameter inventory, see the "Insecure or dangerous flags summary" section in [Security](/gateway/security).
+For the complete dangerous-parameter inventory, see the "Insecure or dangerous flags summary" section in [Security](/nb/gateway/security).
 
 SecretRef behavior:
 

package/docs/nb/cli/sessions.md

@@ -66,7 +66,7 @@ pllan sessions cleanup --json
 
 `pllan sessions cleanup` uses `session.maintenance` settings from config:
 
-- Scope note: `pllan sessions cleanup` maintains session stores/transcripts only. It does not prune cron run logs (`cron/runs/<jobId>.jsonl`), which are managed by `cron.runLog.maxBytes` and `cron.runLog.keepLines` in [Cron configuration](/automation/cron-jobs#configuration) and explained in [Cron maintenance](/automation/cron-jobs#maintenance).
+- Scope note: `pllan sessions cleanup` maintains session stores/transcripts only. It does not prune cron run logs (`cron/runs/<jobId>.jsonl`), which are managed by `cron.runLog.maxBytes` and `cron.runLog.keepLines` in [Cron configuration](/nb/automation/cron-jobs#configuration) and explained in [Cron maintenance](/nb/automation/cron-jobs#maintenance).
 
 - `--dry-run`: preview how many entries would be pruned/capped without writing.
   - In text mode, dry-run prints a per-session action table (`Action`, `Key`, `Age`, `Model`, `Flags`) so you can see what would be kept vs removed.
@@ -107,4 +107,4 @@ pllan sessions cleanup --json
 
 Related:
 
-- Session config: [Configuration reference](/gateway/configuration-reference#session)
+- Session config: [Configuration reference](/nb/gateway/configuration-reference#session)

package/docs/nb/cli/setup.md

@@ -12,8 +12,8 @@ Initialize `~/.pllan/pllan.json` and the agent workspace.
 
 Related:
 
-- Getting started: [Getting started](/start/getting-started)
-- CLI onboarding: [Onboarding (CLI)](/start/wizard)
+- Getting started: [Getting started](/nb/start/getting-started)
+- CLI onboarding: [Onboarding (CLI)](/nb/start/wizard)
 
 ## Examples
 

package/docs/nb/cli/skills.md

@@ -12,9 +12,9 @@ Inspect skills (bundled + workspace + managed overrides) and see what’s eligib
 
 Related:
 
-- Skills system: [Skills](/tools/skills)
-- Skills config: [Skills config](/tools/skills-config)
-- ClawHub installs: [ClawHub](/tools/clawhub)
+- Skills system: [Skills](/nb/tools/skills)
+- Skills config: [Skills config](/nb/tools/skills-config)
+- ClawHub installs: [ClawHub](/nb/tools/clawhub)
 
 ## Commands
 

package/docs/nb/cli/status.md

@@ -23,7 +23,7 @@ Notes:
 - Output includes per-agent session stores when multiple agents are configured.
 - Overview includes Gateway + node host service install/runtime status when available.
 - Overview includes update channel + git SHA (for source checkouts).
-- Update info surfaces in the Overview; if an update is available, status prints a hint to run `pllan update` (see [Updating](/install/updating)).
+- Update info surfaces in the Overview; if an update is available, status prints a hint to run `pllan update` (see [Updating](/nb/install/updating)).
 - Read-only status surfaces (`status`, `status --json`, `status --all`) resolve supported SecretRefs for their targeted config paths when possible.
 - If a supported channel SecretRef is configured but unavailable in the current command path, status stays read-only and reports degraded output instead of crashing. Human output shows warnings such as “configured token unavailable in this command path”, and JSON output includes `secretDiagnostics`.
 - When command-local SecretRef resolution succeeds, status prefers the resolved snapshot and clears transient “secret unavailable” channel markers from the final output.

package/docs/nb/cli/tui.md

@@ -12,7 +12,7 @@ Open the terminal UI connected to the Gateway.
 
 Related:
 
-- TUI guide: [TUI](/web/tui)
+- TUI guide: [TUI](/nb/web/tui)
 
 Notes:
 

package/docs/nb/cli/update.md

@@ -10,7 +10,7 @@ title: "update"
 
 Safely update Pllan and switch between stable/beta/dev channels.
 
-If you installed via **npm/pnpm** (global install, no git metadata), updates happen via the package manager flow in [Updating](/install/updating).
+If you installed via **npm/pnpm** (global install, no git metadata), updates happen via the package manager flow in [Updating](/nb/install/updating).
 
 ## Usage
 
@@ -98,6 +98,6 @@ High-level:
 ## See also
 
 - `pllan doctor` (offers to run update first on git checkouts)
-- [Development channels](/install/development-channels)
-- [Updating](/install/updating)
-- [CLI reference](/cli)
+- [Development channels](/nb/install/development-channels)
+- [Updating](/nb/install/updating)
+- [CLI reference](/nb/cli)

package/docs/nb/cli/voicecall.md

@@ -12,7 +12,7 @@ title: "voicecall"
 
 Primary doc:
 
-- Voice-call plugin: [Voice Call](/plugins/voice-call)
+- Voice-call plugin: [Voice Call](/nb/plugins/voice-call)
 
 ## Common commands
 

package/docs/nb/cli/webhooks.md

@@ -12,8 +12,8 @@ Webhook helpers and integrations (Gmail Pub/Sub, webhook helpers).
 
 Related:
 
-- Webhooks: [Webhook](/automation/webhook)
-- Gmail Pub/Sub: [Gmail Pub/Sub](/automation/gmail-pubsub)
+- Webhooks: [Webhook](/nb/automation/webhook)
+- Gmail Pub/Sub: [Gmail Pub/Sub](/nb/automation/gmail-pubsub)
 
 ## Gmail
 
@@ -22,4 +22,4 @@ pllan webhooks gmail setup --account you@example.com
 pllan webhooks gmail run
 ```
 
-See [Gmail Pub/Sub documentation](/automation/gmail-pubsub) for details.
+See [Gmail Pub/Sub documentation](/nb/automation/gmail-pubsub) for details.

package/docs/nb/concepts/agent-loop.md

@@ -47,7 +47,7 @@ wired end-to-end.
 - Runs are serialized per session key (session lane) and optionally through a global lane.
 - This prevents tool/session races and keeps session history consistent.
 - Messaging channels can choose queue modes (collect/steer/followup) that feed this lane system.
-  See [Command Queue](/concepts/queue).
+  See [Command Queue](/nb/concepts/queue).
 
 ## Session + workspace preparation
 
@@ -60,7 +60,7 @@ wired end-to-end.
 
 - System prompt is built from Pllan’s base prompt, skills prompt, bootstrap context, and per-run overrides.
 - Model-specific limits and compaction reserve tokens are enforced.
-- See [System prompt](/concepts/system-prompt) for what the model sees.
+- See [System prompt](/nb/concepts/system-prompt) for what the model sees.
 
 ## Hook points (where you can intercept)
 
@@ -75,7 +75,7 @@ Pllan has two hook systems:
   Use this to add/remove bootstrap context files.
 - **Command hooks**: `/new`, `/reset`, `/stop`, and other command events (see Hooks doc).
 
-See [Hooks](/automation/hooks) for setup and examples.
+See [Hooks](/nb/automation/hooks) for setup and examples.
 
 ### Plugin hooks (agent + gateway lifecycle)
 
@@ -92,14 +92,14 @@ These run inside the agent loop or gateway pipeline:
 - **`session_start` / `session_end`**: session lifecycle boundaries.
 - **`gateway_start` / `gateway_stop`**: gateway lifecycle events.
 
-See [Plugin hooks](/plugins/architecture#provider-runtime-hooks) for the hook API and registration details.
+See [Plugin hooks](/nb/plugins/architecture#provider-runtime-hooks) for the hook API and registration details.
 
 ## Streaming + partial replies
 
 - Assistant deltas are streamed from pi-agent-core and emitted as `assistant` events.
 - Block streaming can emit partial replies either on `text_end` or `message_end`.
 - Reasoning streaming can be emitted as a separate stream or as block replies.
-- See [Streaming](/concepts/streaming) for chunking and block reply behavior.
+- See [Streaming](/nb/concepts/streaming) for chunking and block reply behavior.
 
 ## Tool execution + messaging tools
 
@@ -122,7 +122,7 @@ See [Plugin hooks](/plugins/architecture#provider-runtime-hooks) for the hook AP
 
 - Auto-compaction emits `compaction` stream events and can trigger a retry.
 - On retry, in-memory buffers and tool summaries are reset to avoid duplicate output.
-- See [Compaction](/concepts/compaction) for the compaction pipeline.
+- See [Compaction](/nb/concepts/compaction) for the compaction pipeline.
 
 ## Event streams (today)
 

package/docs/nb/concepts/agent-workspace.md

@@ -17,7 +17,7 @@ sessions.
 **Important:** the workspace is the **default cwd**, not a hard sandbox. Tools
 resolve relative paths against the workspace, but absolute paths can still reach
 elsewhere on the host unless sandboxing is enabled. If you need isolation, use
-[`agents.defaults.sandbox`](/gateway/sandboxing) (and/or per‑agent sandbox config).
+[`agents.defaults.sandbox`](/nb/gateway/sandboxing) (and/or per‑agent sandbox config).
 When sandboxing is enabled and `workspaceAccess` is not `"rw"`, tools operate
 inside a sandbox workspace under `~/.pllan/sandboxes`, not your host workspace.
 
@@ -107,7 +107,7 @@ These are the standard files Pllan expects inside the workspace:
   - Curated long-term memory.
   - Only load in the main, private session (not shared/group contexts).
 
-See [Memory](/concepts/memory) for the workflow and automatic memory flush.
+See [Memory](/nb/concepts/memory) for the workflow and automatic memory flush.
 
 - `skills/` (optional)
   - Workspace-specific skills.
@@ -231,6 +231,6 @@ Suggested `.gitignore` starter:
 ## Advanced notes
 
 - Multi-agent routing can use different workspaces per agent. See
-  [Channel routing](/channels/channel-routing) for routing configuration.
+  [Channel routing](/nb/channels/channel-routing) for routing configuration.
 - If `agents.defaults.sandbox` is enabled, non-main sessions can use per-session sandbox
   workspaces under `agents.defaults.sandbox.workspaceRoot`.

package/docs/nb/concepts/agent.md

@@ -15,11 +15,11 @@ Pllan uses a single agent workspace directory (`agents.defaults.workspace`) as t
 
 Recommended: use `pllan setup` to create `~/.pllan/pllan.json` if missing and initialize the workspace files.
 
-Full workspace layout + backup guide: [Agent workspace](/concepts/agent-workspace)
+Full workspace layout + backup guide: [Agent workspace](/nb/concepts/agent-workspace)
 
 If `agents.defaults.sandbox` is enabled, non-main sessions can override this with
 per-session workspaces under `agents.defaults.sandbox.workspaceRoot` (see
-[Gateway configuration](/gateway/configuration)).
+[Gateway configuration](/nb/gateway/configuration)).
 
 ## Bootstrap files (injected)
 
@@ -61,7 +61,7 @@ Pllan loads skills from three locations (workspace wins on name conflict):
 - Managed/local: `~/.pllan/skills`
 - Workspace: `<workspace>/skills`
 
-Skills can be gated by config/env (see `skills` in [Gateway configuration](/gateway/configuration)).
+Skills can be gated by config/env (see `skills` in [Gateway configuration](/nb/gateway/configuration)).
 
 ## Runtime boundaries
 
@@ -88,7 +88,7 @@ message is injected before the next assistant response.
 
 When queue mode is `followup` or `collect`, inbound messages are held until the
 current turn ends, then a new agent turn starts with the queued payloads. See
-[Queue](/concepts/queue) for mode + debounce/cap behavior.
+[Queue](/nb/concepts/queue) for mode + debounce/cap behavior.
 
 Block streaming sends completed assistant blocks as soon as they finish; it is
 **off by default** (`agents.defaults.blockStreamingDefault: "off"`).
@@ -100,7 +100,7 @@ single-line spam (idle-based merging before send). Non-Telegram channels require
 explicit `*.blockStreaming: true` to enable block replies.
 Verbose tool summaries are emitted at tool start (no debounce); Control UI
 streams tool output via agent events when available.
-More details: [Streaming + chunking](/concepts/streaming).
+More details: [Streaming + chunking](/nb/concepts/streaming).
 
 ## Model refs
 
@@ -119,4 +119,4 @@ At minimum, set:
 
 ---
 
-_Next: [Group Chats](/channels/group-messages)_ 
+_Next: [Group Chats](/nb/channels/group-messages)_