pllan 2026.3.47 → 2026.3.49

package/docs/nb/concepts/architecture.md

@@ -46,7 +46,7 @@ title: "Gateway-arkitektur"
 
 Protokolldetaljer:
 
-- [Gateway-protokoll](/gateway/protocol)
+- [Gateway-protokoll](/nb/gateway/protocol)
 
 ### WebChat
 
@@ -100,8 +100,8 @@ sequenceDiagram
 - Gateway-autentisering (`gateway.auth.*`) gjelder fortsatt for **alle** tilkoblinger, lokale eller
   fjerne.
 
-Detaljer: [Gateway-protokoll](/gateway/protocol), [Sammenkobling](/channels/pairing),
-[Sikkerhet](/gateway/security).
+Detaljer: [Gateway-protokoll](/nb/gateway/protocol), [Sammenkobling](/nb/channels/pairing),
+[Sikkerhet](/nb/gateway/security).
 
 ## Fjerntilgang
 

package/docs/nb/concepts/compaction.md

@@ -64,7 +64,7 @@ You’ll see:
 - `/status` showing `🧹 Compactions: <count>`
 
 Before compaction, Pllan can run a **silent memory flush** turn to store
-durable notes to disk. See [Memory](/concepts/memory) for details and config.
+durable notes to disk. See [Memory](/nb/concepts/memory) for details and config.
 
 ## Manual compaction
 
@@ -83,7 +83,7 @@ Context window is model-specific. Pllan uses the model definition from the confi
 - **Compaction**: summarises and **persists** in JSONL.
 - **Session pruning**: trims old **tool results** only, **in-memory**, per request.
 
-See [/concepts/session-pruning](/concepts/session-pruning) for pruning details.
+See [/concepts/session-pruning](/nb/concepts/session-pruning) for pruning details.
 
 ## OpenAI server-side compaction
 
@@ -95,12 +95,12 @@ compaction and can run alongside it.
 - Server-side compaction: OpenAI compacts context on the provider side when
   `store` + `context_management` are enabled.
 
-See [OpenAI provider](/providers/openai) for model params and overrides.
+See [OpenAI provider](/nb/providers/openai) for model params and overrides.
 
 ## Custom context engines
 
 Compaction behavior is owned by the active
-[context engine](/concepts/context-engine). The legacy engine uses the built-in
+[context engine](/nb/concepts/context-engine). The legacy engine uses the built-in
 summarization described above. Plugin engines (selected via
 `plugins.slots.contextEngine`) can implement any compaction strategy — DAG
 summaries, vector retrieval, incremental condensation, etc.

package/docs/nb/concepts/context-engine.md

@@ -264,5 +264,5 @@ Pllan resolves when it needs a context engine.
 - For development, use `pllan plugins install -l ./my-engine` to link a
   local plugin directory without copying.
 
-See also: [Compaction](/concepts/compaction), [Context](/concepts/context),
-[Plugins](/tools/plugin), [Plugin manifest](/plugins/manifest).
+See also: [Compaction](/nb/concepts/compaction), [Context](/nb/concepts/context),
+[Plugins](/nb/tools/plugin), [Plugin manifest](/nb/plugins/manifest).

package/docs/nb/concepts/context.md

@@ -27,7 +27,7 @@ Context is _not the same thing_ as “memory”: memory can be stored on disk an
 - `/usage tokens` → append per-reply usage footer to normal replies.
 - `/compact` → summarize older history into a compact entry to free window space.
 
-See also: [Slash commands](/tools/slash-commands), [Token use & costs](/reference/token-use), [Compaction](/concepts/compaction).
+See also: [Slash commands](/nb/tools/slash-commands), [Token use & costs](/nb/reference/token-use), [Compaction](/nb/concepts/compaction).
 
 ## Example output
 
@@ -98,7 +98,7 @@ The system prompt is **Pllan-owned** and rebuilt each run. It includes:
 - Runtime metadata (host/OS/model/thinking).
 - Injected workspace bootstrap files under **Project Context**.
 
-Full breakdown: [System Prompt](/concepts/system-prompt).
+Full breakdown: [System Prompt](/nb/concepts/system-prompt).
 
 ## Injected workspace files (Project Context)
 
@@ -141,7 +141,7 @@ Slash commands are handled by the Gateway. There are a few different behaviors:
   - Inline directives in a normal message act as per-message hints.
 - **Inline shortcuts** (allowlisted senders only): certain `/...` tokens inside a normal message can run immediately (example: “hey /status”), and are stripped before the model sees the remaining text.
 
-Details: [Slash commands](/tools/slash-commands).
+Details: [Slash commands](/nb/tools/slash-commands).
 
 ## Sessions, compaction, and pruning (what persists)
 
@@ -151,7 +151,7 @@ What persists across messages depends on the mechanism:
 - **Compaction** persists a summary into the transcript and keeps recent messages intact.
 - **Pruning** removes old tool results from the _in-memory_ prompt for a run, but does not rewrite the transcript.
 
-Docs: [Session](/concepts/session), [Compaction](/concepts/compaction), [Session pruning](/concepts/session-pruning).
+Docs: [Session](/nb/concepts/session), [Compaction](/nb/concepts/compaction), [Session pruning](/nb/concepts/session-pruning).
 
 By default, Pllan uses the built-in `legacy` context engine for assembly and
 compaction. If you install a plugin that provides `kind: "context-engine"` and
@@ -159,7 +159,7 @@ select it with `plugins.slots.contextEngine`, Pllan delegates context
 assembly, `/compact`, and related subagent context lifecycle hooks to that
 engine instead. `ownsCompaction: false` does not auto-fallback to the legacy
 engine; the active engine must still implement `compact()` correctly. See
-[Context Engine](/concepts/context-engine) for the full
+[Context Engine](/nb/concepts/context-engine) for the full
 pluggable interface, lifecycle hooks, and configuration.
 
 ## What `/context` actually reports

package/docs/nb/concepts/markdown-formatting.md

@@ -94,7 +94,7 @@ channels:
   chunks; the renderer reopens styles inside each chunk.
 
 If you need more on chunking behavior across channels, see
-[Streaming + chunking](/concepts/streaming).
+[Streaming + chunking](/nb/concepts/streaming).
 
 ## Link policy
 

package/docs/nb/concepts/memory.md

@@ -28,7 +28,7 @@ The default workspace layout uses two memory layers:
   - **Only load in the main, private session** (never in group contexts).
 
 These files live under the workspace (`agents.defaults.workspace`, default
-`~/.pllan/workspace`). See [Agent workspace](/concepts/agent-workspace) for the full layout.
+`~/.pllan/workspace`). See [Agent workspace](/nb/concepts/agent-workspace) for the full layout.
 
 ## Memory tools
 
@@ -89,7 +89,7 @@ Details:
   `workspaceAccess: "ro"` or `"none"`, the flush is skipped.
 
 For the full compaction lifecycle, see
-[Session management + compaction](/reference/session-management-compaction).
+[Session management + compaction](/nb/reference/session-management-compaction).
 
 ## Vector memory search
 
@@ -105,4 +105,4 @@ and temporal decay.
 
 For the full configuration reference -- including embedding provider setup, QMD
 backend, hybrid search tuning, multimodal memory, and all config knobs -- see
-[Memory configuration reference](/reference/memory-config).
+[Memory configuration reference](/nb/reference/memory-config).

package/docs/nb/concepts/messages.md

@@ -28,7 +28,7 @@ Key knobs live in configuration:
 - `agents.defaults.*` for block streaming and chunking defaults.
 - Channel overrides (`channels.whatsapp.*`, `channels.telegram.*`, etc.) for caps and streaming toggles.
 
-See [Configuration](/gateway/configuration) for full schema.
+See [Configuration](/nb/gateway/configuration) for full schema.
 
 ## Inbound dedupe
 
@@ -77,7 +77,7 @@ synced back to every client. Recommendation: use one primary device for long
 conversations to avoid divergent context. The Control UI and TUI always show the
 gateway-backed session transcript, so they are the source of truth.
 
-Details: [Session management](/concepts/session).
+Details: [Session management](/nb/concepts/session).
 
 ## Inbound bodies and history context
 
@@ -116,7 +116,7 @@ current run, or collected for a followup turn.
 - Configure via `messages.queue` (and `messages.queue.byChannel`).
 - Modes: `interrupt`, `steer`, `followup`, `collect`, plus backlog variants.
 
-Details: [Queueing](/concepts/queue).
+Details: [Queueing](/nb/concepts/queue).
 
 ## Streaming, chunking, and batching
 
@@ -132,7 +132,7 @@ Key settings:
 - `agents.defaults.humanDelay` (human-like pause between block replies)
 - Channel overrides: `*.blockStreaming` and `*.blockStreamingCoalesce` (non-Telegram channels require explicit `*.blockStreaming: true`)
 
-Details: [Streaming + chunking](/concepts/streaming).
+Details: [Streaming + chunking](/nb/concepts/streaming).
 
 ## Reasoning visibility and tokens
 
@@ -142,7 +142,7 @@ Pllan can expose or hide model reasoning:
 - Reasoning content still counts toward token usage when produced by the model.
 - Telegram supports reasoning stream into the draft bubble.
 
-Details: [Thinking + reasoning directives](/tools/thinking) and [Token use](/reference/token-use).
+Details: [Thinking + reasoning directives](/nb/tools/thinking) and [Token use](/nb/reference/token-use).
 
 ## Prefixes, threading, and replies
 
@@ -151,4 +151,4 @@ Outbound message formatting is centralized in `messages`:
 - `messages.responsePrefix`, `channels.<channel>.responsePrefix`, and `channels.<channel>.accounts.<id>.responsePrefix` (outbound prefix cascade), plus `channels.whatsapp.messagePrefix` (WhatsApp inbound prefix)
 - Reply threading via `replyToMode` and per-channel defaults
 
-Details: [Configuration](/gateway/configuration-reference#messages) and channel docs.
+Details: [Configuration](/nb/gateway/configuration-reference#messages) and channel docs.

package/docs/nb/concepts/model-failover.md

@@ -23,7 +23,7 @@ Pllan uses **auth profiles** for both API keys and OAuth tokens.
 - Config `auth.profiles` / `auth.order` are **metadata + routing only** (no secrets).
 - Legacy import-only OAuth file: `~/.pllan/credentials/oauth.json` (imported into `auth-profiles.json` on first use).
 
-More detail: [/concepts/oauth](/concepts/oauth)
+More detail: [/concepts/oauth](/nb/concepts/oauth)
 
 Credential types:
 
@@ -141,7 +141,7 @@ When a run starts with a model override (hooks or CLI), fallbacks still end at
 
 ## Related config
 
-See [Gateway configuration](/gateway/configuration) for:
+See [Gateway configuration](/nb/gateway/configuration) for:
 
 - `auth.profiles` / `auth.order`
 - `auth.cooldowns.billingBackoffHours` / `auth.cooldowns.billingBackoffHoursByProvider`
@@ -149,4 +149,4 @@ See [Gateway configuration](/gateway/configuration) for:
 - `agents.defaults.model.primary` / `agents.defaults.model.fallbacks`
 - `agents.defaults.imageModel` routing
 
-See [Models](/concepts/models) for the broader model selection and fallback overview.
+See [Models](/nb/concepts/models) for the broader model selection and fallback overview.

package/docs/nb/concepts/model-providers.md

@@ -9,7 +9,7 @@ title: "Model Providers"
 # Model providers
 
 This page covers **LLM/model providers** (not chat channels like WhatsApp/Telegram).
-For model selection rules, see [/concepts/models](/concepts/models).
+For model selection rules, see [/concepts/models](/nb/concepts/models).
 
 ## Quick rules
 
@@ -34,7 +34,7 @@ For model selection rules, see [/concepts/models](/concepts/models).
   `fetchUsageSnapshot`.
 - Note: provider runtime `capabilities` is shared runner metadata (provider
   family, transcript/tooling quirks, transport/cache hints). It is not the
-  same as the [public capability model](/plugins/architecture#public-capability-model)
+  same as the [public capability model](/nb/plugins/architecture#public-capability-model)
   which describes what a plugin registers (text inference, speech, etc.).
 
 ## Plugin-owned provider behavior
@@ -250,7 +250,7 @@ Pllan ships with the pi‑ai catalog. These providers require **no**
 - Base URL: `https://api.kilo.ai/api/gateway/`
 - Expanded built-in catalog includes GLM-5 Free, MiniMax M2.5 Free, GPT-5.2, Gemini 3 Pro Preview, Gemini 3 Flash Preview, Grok Code Fast 1, and Kimi K2.5.
 
-See [/providers/kilocode](/providers/kilocode) for setup details.
+See [/providers/kilocode](/nb/providers/kilocode) for setup details.
 
 ### Other bundled provider plugins
 
@@ -281,7 +281,7 @@ See [/providers/kilocode](/providers/kilocode) for setup details.
   - GLM models on Cerebras use ids `zai-glm-4.7` and `zai-glm-4.6`.
   - OpenAI-compatible base URL: `https://api.cerebras.ai/v1`.
 - GitHub Copilot: `github-copilot` (`COPILOT_GITHUB_TOKEN` / `GH_TOKEN` / `GITHUB_TOKEN`)
-- Hugging Face Inference example model: `huggingface/deepseek-ai/DeepSeek-R1`; CLI: `pllan onboard --auth-choice huggingface-api-key`. See [Hugging Face (Inference)](/providers/huggingface).
+- Hugging Face Inference example model: `huggingface/deepseek-ai/DeepSeek-R1`; CLI: `pllan onboard --auth-choice huggingface-api-key`. See [Hugging Face (Inference)](/nb/providers/huggingface).
 
 ## Providers via `models.providers` (custom/base URL)
 
@@ -362,7 +362,7 @@ Model refs:
 - `qwen-portal/coder-model`
 - `qwen-portal/vision-model`
 
-See [/providers/qwen](/providers/qwen) for setup details and notes.
+See [/providers/qwen](/nb/providers/qwen) for setup details and notes.
 
 ### Volcano Engine (Doubao)
 
@@ -463,7 +463,7 @@ MiniMax is configured via `models.providers` because it uses custom endpoints:
 - MiniMax (Anthropic‑compatible): `--auth-choice minimax-api`
 - Auth: `MINIMAX_API_KEY`
 
-See [/providers/minimax](/providers/minimax) for setup details, model options, and config snippets.
+See [/providers/minimax](/nb/providers/minimax) for setup details, model options, and config snippets.
 
 ### Ollama
 
@@ -489,7 +489,7 @@ ollama pull llama3.3
 
 Ollama is detected locally at `http://127.0.0.1:11434` when you opt in with
 `OLLAMA_API_KEY`, and the bundled provider plugin adds Ollama directly to
-`pllan onboard` and the model picker. See [/providers/ollama](/providers/ollama)
+`pllan onboard` and the model picker. See [/providers/ollama](/nb/providers/ollama)
 for onboarding, cloud/local mode, and custom configuration.
 
 ### vLLM
@@ -517,7 +517,7 @@ Then set a model (replace with one of the IDs returned by `/v1/models`):
 }
 ```
 
-See [/providers/vllm](/providers/vllm) for details.
+See [/providers/vllm](/nb/providers/vllm) for details.
 
 ### SGLang
 
@@ -545,7 +545,7 @@ Then set a model (replace with one of the IDs returned by `/v1/models`):
 }
 ```
 
-See [/providers/sglang](/providers/sglang) for details.
+See [/providers/sglang](/nb/providers/sglang) for details.
 
 ### Local proxies (LM Studio, vLLM, LiteLLM, etc.)
 
@@ -604,4 +604,4 @@ pllan models set opencode/claude-opus-4-6
 pllan models list
 ```
 
-See also: [/gateway/configuration](/gateway/configuration) for full configuration examples.
+See also: [/gateway/configuration](/nb/gateway/configuration) for full configuration examples.

package/docs/nb/concepts/models.md

@@ -9,9 +9,9 @@ title: "Models CLI"
 
 # Models CLI
 
-See [/concepts/model-failover](/concepts/model-failover) for auth profile
+See [/concepts/model-failover](/nb/concepts/model-failover) for auth profile
 rotation, cooldowns, and how that interacts with fallbacks.
-Quick provider overview + examples: [/concepts/model-providers](/concepts/model-providers).
+Quick provider overview + examples: [/concepts/model-providers](/nb/concepts/model-providers).
 
 ## How model selection works
 
@@ -27,7 +27,7 @@ Related:
 - `agents.defaults.models` is the allowlist/catalog of models Pllan can use (plus aliases).
 - `agents.defaults.imageModel` is used **only when** the primary model can’t accept images.
 - `agents.defaults.imageGenerationModel` is used by the shared image-generation capability. If omitted, `image_generate` can still infer a provider default from compatible auth-backed image-generation plugins.
-- Per-agent defaults can override `agents.defaults.model` via `agents.list[].model` plus bindings (see [/concepts/multi-agent](/concepts/multi-agent)).
+- Per-agent defaults can override `agents.defaults.model` via `agents.list[].model` plus bindings (see [/concepts/multi-agent](/nb/concepts/multi-agent)).
 
 ## Quick model policy
 
@@ -58,7 +58,7 @@ Model refs are normalized to lowercase. Provider aliases like `z.ai/*` normalize
 to `zai/*`.
 
 Provider configuration examples (including OpenCode) live in
-[/providers/opencode](/providers/opencode).
+[/providers/opencode](/nb/providers/opencode).
 
 ## "Model is not allowed" (and why replies stop)
 
@@ -113,7 +113,7 @@ Notes:
 - If the model ID itself contains `/` (OpenRouter-style), you must include the provider prefix (example: `/model openrouter/moonshotai/kimi-k2`).
 - If you omit the provider, Pllan treats the input as an alias or a model for the **default provider** (only works when there is no `/` in the model ID).
 
-Full command behavior/config: [Slash commands](/tools/slash-commands).
+Full command behavior/config: [Slash commands](/nb/tools/slash-commands).
 
 ## CLI commands
 
@@ -199,7 +199,7 @@ Scan results are ranked by:
 Input
 
 - OpenRouter `/models` list (filter `:free`)
-- Requires OpenRouter API key from auth profiles or `OPENROUTER_API_KEY` (see [/environment](/help/environment))
+- Requires OpenRouter API key from auth profiles or `OPENROUTER_API_KEY` (see [/environment](/nb/help/environment))
 - Optional filters: `--max-age-days`, `--min-params`, `--provider`, `--max-candidates`
 - Probe controls: `--timeout`, `--concurrency`
 

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

@@ -28,14 +28,14 @@ across agents (it causes auth/session collisions). If you want to share creds,
 copy `auth-profiles.json` into the other agent's `agentDir`.
 
 Skills are per-agent via each workspace’s `skills/` folder, with shared skills
-available from `~/.pllan/skills`. See [Skills: per-agent vs shared](/tools/skills#per-agent-vs-shared-skills).
+available from `~/.pllan/skills`. See [Skills: per-agent vs shared](/nb/tools/skills#per-agent-vs-shared-skills).
 
 The Gateway can host **one agent** (default) or **many agents** side-by-side.
 
 **Workspace note:** each agent’s workspace is the **default cwd**, not a hard
 sandbox. Relative paths resolve inside the workspace, but absolute paths can
 reach other host locations unless sandboxing is enabled. See
-[Sandboxing](/gateway/sandboxing).
+[Sandboxing](/nb/gateway/sandboxing).
 
 ## Paths (quick map)
 
@@ -98,7 +98,7 @@ Create one account per agent on your preferred channels:
 pllan channels login --channel whatsapp --account work
 ```
 
-See channel guides: [Discord](/channels/discord), [Telegram](/channels/telegram), [WhatsApp](/channels/whatsapp).
+See channel guides: [Discord](/nb/channels/discord), [Telegram](/nb/channels/telegram), [WhatsApp](/nb/channels/whatsapp).
 
   </Step>
 
@@ -167,7 +167,7 @@ Example:
 Notes:
 
 - DM access control is **global per WhatsApp account** (pairing/allowlist), not per agent.
-- For shared groups, bind the group to one agent or use [Broadcast groups](/channels/broadcast-groups).
+- For shared groups, bind the group to one agent or use [Broadcast groups](/nb/channels/broadcast-groups).
 
 ## Routing rules (how messages pick an agent)
 
@@ -549,4 +549,4 @@ Note: `tools.elevated` is **global** and sender-based; it is not configurable pe
 If you need per-agent boundaries, use `agents.list[].tools` to deny `exec`.
 For group targeting, use `agents.list[].groupChat.mentionPatterns` so @mentions map cleanly to the intended agent.
 
-See [Multi-Agent Sandbox & Tools](/tools/multi-agent-sandbox-tools) for detailed examples.
+See [Multi-Agent Sandbox & Tools](/nb/tools/multi-agent-sandbox-tools) for detailed examples.

package/docs/nb/concepts/oauth.md

@@ -50,9 +50,9 @@ Legacy import-only file (still supported, but not the main store):
 
 - `~/.pllan/credentials/oauth.json` (imported into `auth-profiles.json` on first use)
 
-All of the above also respect `$PLLAN_STATE_DIR` (state dir override). Full reference: [/gateway/configuration](/gateway/configuration-reference#auth-storage)
+All of the above also respect `$PLLAN_STATE_DIR` (state dir override). Full reference: [/gateway/configuration](/nb/gateway/configuration-reference#auth-storage)
 
-For static secret refs and runtime snapshot activation behavior, see [Secrets Management](/gateway/secrets).
+For static secret refs and runtime snapshot activation behavior, see [Secrets Management](/nb/gateway/secrets).
 
 ## Anthropic setup-token (subscription auth)
 
@@ -154,5 +154,5 @@ How to see what profile IDs exist:
 
 Related docs:
 
-- [/concepts/model-failover](/concepts/model-failover) (rotation + cooldown rules)
-- [/tools/slash-commands](/tools/slash-commands) (command surface)
+- [/concepts/model-failover](/nb/concepts/model-failover) (rotation + cooldown rules)
+- [/tools/slash-commands](/nb/tools/slash-commands) (command surface)

package/docs/nb/concepts/session-pruning.md

@@ -73,7 +73,7 @@ If `agents.defaults.contextTokens` is set, it is treated as a cap (min) on the r
 ## Interaction with other limits
 
 - Built-in tools already truncate their own output; session pruning is an extra layer that prevents long-running chats from accumulating too much tool output in the model context.
-- Compaction is separate: compaction summarizes and persists, pruning is transient per request. See [/concepts/compaction](/concepts/compaction).
+- Compaction is separate: compaction summarizes and persists, pruning is transient per request. See [/concepts/compaction](/nb/concepts/compaction).
 
 ## Defaults (when enabled)
 
@@ -118,4 +118,4 @@ Restrict pruning to specific tools:
 }
 ```
 
-See config reference: [Gateway Configuration](/gateway/configuration)
+See config reference: [Gateway Configuration](/nb/gateway/configuration)

package/docs/nb/concepts/session.md

@@ -52,7 +52,7 @@ Notes:
 - Local CLI onboarding writes `session.dmScope: "per-channel-peer"` by default when unset (existing explicit values are preserved).
 - For multi-account inboxes on the same channel, prefer `per-account-channel-peer`.
 - If the same person contacts you on multiple channels, use `session.identityLinks` to collapse their DM sessions into one canonical identity.
-- You can verify your DM settings with `pllan security audit` (see [security](/cli/security)).
+- You can verify your DM settings with `pllan security audit` (see [security](/nb/cli/security)).
 
 ## Gateway is the source of truth
 
@@ -177,14 +177,14 @@ pllan sessions cleanup --enforce
 ## Session pruning
 
 Pllan trims **old tool results** from the in-memory context right before LLM calls by default.
-This does **not** rewrite JSONL history. See [/concepts/session-pruning](/concepts/session-pruning).
+This does **not** rewrite JSONL history. See [/concepts/session-pruning](/nb/concepts/session-pruning).
 
 ## Pre-compaction memory flush
 
 When a session nears auto-compaction, Pllan can run a **silent memory flush**
 turn that reminds the model to write durable notes to disk. This only runs when
-the workspace is writable. See [Memory](/concepts/memory) and
-[Compaction](/concepts/compaction).
+the workspace is writable. See [Memory](/nb/concepts/memory) and
+[Compaction](/nb/concepts/compaction).
 
 ## Mapping transports → session keys
 
@@ -284,7 +284,7 @@ Runtime override (owner only):
 - Send `/status` as a standalone message in chat to see whether the agent is reachable, how much of the session context is used, current thinking/fast/verbose toggles, and when your WhatsApp web creds were last refreshed (helps spot relink needs).
 - Send `/context list` or `/context detail` to see what’s in the system prompt and injected workspace files (and the biggest context contributors).
 - Send `/stop` (or standalone abort phrases like `stop`, `stop action`, `stop run`, `stop pllan`) to abort the current run, clear queued followups for that session, and stop any sub-agent runs spawned from it (the reply includes the stopped count).
-- Send `/compact` (optional instructions) as a standalone message to summarize older context and free up window space. See [/concepts/compaction](/concepts/compaction).
+- Send `/compact` (optional instructions) as a standalone message to summarize older context and free up window space. See [/concepts/compaction](/nb/concepts/compaction).
 - JSONL transcripts can be opened directly to review full turns.
 
 ## Tips

package/docs/nb/concepts/system-prompt.md

@@ -84,7 +84,7 @@ are filtered out to keep the sub-agent context small).
 Internal hooks can intercept this step via `agent:bootstrap` to mutate or replace
 the injected bootstrap files (for example swapping `SOUL.md` for an alternate persona).
 
-To inspect how much each injected file contributes (raw vs injected, truncation, plus tool schema overhead), use `/context list` or `/context detail`. See [Context](/concepts/context).
+To inspect how much each injected file contributes (raw vs injected, truncation, plus tool schema overhead), use `/context list` or `/context detail`. See [Context](/nb/concepts/context).
 
 ## Time handling
 
@@ -100,7 +100,7 @@ Configure with:
 - `agents.defaults.userTimezone`
 - `agents.defaults.timeFormat` (`auto` | `12` | `24`)
 
-See [Date & Time](/date-time) for full behavior details.
+See [Date & Time](/nb/date-time) for full behavior details.
 
 ## Skills
 

package/docs/nb/concepts/timezone.md

@@ -88,4 +88,4 @@ The system prompt includes:
 
 You can control the prompt format with `agents.defaults.timeFormat` (`auto` | `12` | `24`).
 
-See [Date & Time](/date-time) for the full behavior and examples.
+See [Date & Time](/nb/date-time) for the full behavior and examples.

package/docs/nb/concepts/typebox.md

@@ -15,7 +15,7 @@ drive **runtime validation**, **JSON Schema export**, and **Swift codegen** for
 the macOS app. One source of truth; everything else is generated.
 
 If you want the higher-level protocol context, start with
-[Gateway architecture](/concepts/architecture).
+[Gateway architecture](/nb/concepts/architecture).
 
 ## Mental model (30 seconds)
 

package/docs/nb/date-time.md

@@ -123,6 +123,6 @@ If you need local time, convert it downstream using the known timezone.
 
 ## Related docs
 
-- [System Prompt](/concepts/system-prompt)
-- [Timezones](/concepts/timezone)
-- [Messages](/concepts/messages)
+- [System Prompt](/nb/concepts/system-prompt)
+- [Timezones](/nb/concepts/timezone)
+- [Messages](/nb/concepts/messages)

package/docs/nb/diagnostics/flags.md

@@ -82,10 +82,10 @@ Or tail while reproducing:
 tail -f /tmp/pllan/pllan-$(date +%F).log | rg "telegram http error"
 ```
 
-For remote gateways, you can also use `pllan logs --follow` (see [/cli/logs](/cli/logs)).
+For remote gateways, you can also use `pllan logs --follow` (see [/cli/logs](/nb/cli/logs)).
 
 ## Notes
 
 - If `logging.level` is set higher than `warn`, these logs may be suppressed. Default `info` is fine.
 - Flags are safe to leave enabled; they only affect log volume for the specific subsystem.
-- Use [/logging](/logging) to change log destinations, levels, and redaction.
+- Use [/logging](/nb/logging) to change log destinations, levels, and redaction.

package/docs/nb/gateway/authentication.md

@@ -12,11 +12,11 @@ Pllan supports OAuth and API keys for model providers. For always-on gateway
 hosts, API keys are usually the most predictable option. Subscription/OAuth
 flows are also supported when they match your provider account model.
 
-See [/concepts/oauth](/concepts/oauth) for the full OAuth flow and storage
+See [/concepts/oauth](/nb/concepts/oauth) for the full OAuth flow and storage
 layout.
-For SecretRef-based auth (`env`/`file`/`exec` providers), see [Secrets Management](/gateway/secrets).
+For SecretRef-based auth (`env`/`file`/`exec` providers), see [Secrets Management](/nb/gateway/secrets).
 For credential eligibility/reason-code rules used by `models status --probe`, see
-[Auth Credential Semantics](/auth-credential-semantics).
+[Auth Credential Semantics](/nb/auth-credential-semantics).
 
 ## Recommended setup (API key, any provider)
 
@@ -52,7 +52,7 @@ pllan doctor
 If you’d rather not manage env vars yourself, onboarding can store
 API keys for daemon use: `pllan onboard`.
 
-See [Help](/help) for details on env inheritance (`env.shellEnv`,
+See [Help](/nb/help) for details on env inheritance (`env.shellEnv`,
 `~/.pllan/.env`, systemd/launchd).
 
 ## Anthropic: setup-token (subscription auth)
@@ -109,7 +109,7 @@ pllan models status --check
 ```
 
 Optional ops scripts (systemd/Termux) are documented here:
-[/automation/auth-monitoring](/automation/auth-monitoring)
+[/automation/auth-monitoring](/nb/automation/auth-monitoring)
 
 > `claude setup-token` requires an interactive TTY.
 

package/docs/nb/gateway/bonjour.md

@@ -173,5 +173,5 @@ sequences (e.g. spaces become `\032`).
 
 ## Related docs
 
-- Discovery policy and transport selection: [Discovery](/gateway/discovery)
-- Node pairing + approvals: [Gateway pairing](/gateway/pairing)
+- Discovery policy and transport selection: [Discovery](/nb/gateway/discovery)
+- Node pairing + approvals: [Gateway pairing](/nb/gateway/pairing)

package/docs/nb/gateway/bridge-protocol.md

@@ -13,7 +13,7 @@ The Bridge protocol is a **legacy** node transport (TCP JSONL). New node clients
 should use the unified Gateway WebSocket protocol instead.
 
 If you are building an operator or node client, use the
-[Gateway protocol](/gateway/protocol).
+[Gateway protocol](/nb/gateway/protocol).
 
 **Note:** Current Pllan builds no longer ship the TCP bridge listener; this document is kept for historical reference.
 Legacy `bridge.*` config keys are no longer part of the config schema.

package/docs/nb/gateway/configuration-examples.md

@@ -9,7 +9,7 @@ title: "Configuration Examples"
 
 # Configuration Examples
 
-Examples below are aligned with the current config schema. For the exhaustive reference and per-field notes, see [Configuration](/gateway/configuration).
+Examples below are aligned with the current config schema. For the exhaustive reference and per-field notes, see [Configuration](/nb/gateway/configuration).
 
 ## Quick start
 
@@ -634,4 +634,4 @@ terms before depending on subscription auth.
 - If you set `dmPolicy: "open"`, the matching `allowFrom` list must include `"*"`.
 - Provider IDs differ (phone numbers, user IDs, channel IDs). Use the provider docs to confirm the format.
 - Optional sections to add later: `web`, `browser`, `ui`, `discovery`, `canvasHost`, `talk`, `signal`, `imessage`.
-- See [Providers](/providers) and [Troubleshooting](/gateway/troubleshooting) for deeper setup notes.
+- See [Providers](/nb/providers) and [Troubleshooting](/nb/gateway/troubleshooting) for deeper setup notes.