pllan 2026.3.47 → 2026.3.49

package/docs/nb/prose.md

@@ -31,7 +31,7 @@ Restart the Gateway after enabling the plugin.
 
 Dev/local checkout: `pllan plugins install ./extensions/open-prose`
 
-Related docs: [Plugins](/tools/plugin), [Plugin manifest](/plugins/manifest), [Skills](/tools/skills).
+Related docs: [Plugins](/nb/tools/plugin), [Plugin manifest](/nb/plugins/manifest), [Skills](/nb/tools/skills).
 
 ## Slash command
 
@@ -125,10 +125,10 @@ OpenProse programs map to Pllan primitives:
 | File read/write           | `read` / `write` |
 | Web fetch                 | `web_fetch`      |
 
-If your tool allowlist blocks these tools, OpenProse programs will fail. See [Skills config](/tools/skills-config).
+If your tool allowlist blocks these tools, OpenProse programs will fail. See [Skills config](/nb/tools/skills-config).
 
 ## Security + approvals
 
 Treat `.prose` files like code. Review before running. Use Pllan tool allowlists and approval gates to control side effects.
 
-For deterministic, approval-gated workflows, compare with [pllan](/tools/pllan).
+For deterministic, approval-gated workflows, compare with [pllan](/nb/tools/pllan).

package/docs/nb/providers/anthropic.md

@@ -150,7 +150,7 @@ The older `cacheControlTtl` parameter is still supported for backwards compatibi
 We recommend migrating to the new `cacheRetention` parameter.
 
 Pllan includes the `extended-cache-ttl-2025-04-11` beta flag for Anthropic API
-requests; keep it if you override provider headers (see [/gateway/configuration](/gateway/configuration)).
+requests; keep it if you override provider headers (see [/gateway/configuration](/nb/gateway/configuration)).
 
 ## 1M context window (Anthropic beta)
 
@@ -228,8 +228,8 @@ pllan onboard --auth-choice setup-token
 ## Notes
 
 - Generate the setup-token with `claude setup-token` and paste it, or run `pllan models auth setup-token` on the gateway host.
-- If you see “OAuth token refresh failed …” on a Claude subscription, re-auth with a setup-token. See [/gateway/troubleshooting](/gateway/troubleshooting).
-- Auth details + reuse rules are in [/concepts/oauth](/concepts/oauth).
+- If you see “OAuth token refresh failed …” on a Claude subscription, re-auth with a setup-token. See [/gateway/troubleshooting](/nb/gateway/troubleshooting).
+- Auth details + reuse rules are in [/concepts/oauth](/nb/concepts/oauth).
 
 ## Troubleshooting
 
@@ -256,4 +256,4 @@ pllan onboard --auth-choice setup-token
 - Check `pllan models status --json` for `auth.unusableProfiles`.
 - Add another Anthropic profile or wait for cooldown.
 
-More: [/gateway/troubleshooting](/gateway/troubleshooting) and [/help/faq](/help/faq).
+More: [/gateway/troubleshooting](/nb/gateway/troubleshooting) and [/help/faq](/nb/help/faq).

package/docs/nb/providers/claude-max-api-proxy.md

@@ -150,5 +150,5 @@ launchctl bootstrap gui/$(id -u) ~/Library/LaunchAgents/com.claude-max-api.plist
 
 ## See Also
 
-- [Anthropic provider](/providers/anthropic) - Native Pllan integration with Claude setup-token or API keys
-- [OpenAI provider](/providers/openai) - For OpenAI/Codex subscriptions
+- [Anthropic provider](/nb/providers/anthropic) - Native Pllan integration with Claude setup-token or API keys
+- [OpenAI provider](/nb/providers/openai) - For OpenAI/Codex subscriptions

package/docs/nb/providers/glm.md

@@ -40,4 +40,4 @@ pllan onboard --auth-choice zai-cn
 
 - GLM versions and availability can change; check Z.AI's docs for the latest.
 - Example model IDs include `glm-5`, `glm-4.7`, and `glm-4.6`.
-- For provider details, see [/providers/zai](/providers/zai).
+- For provider details, see [/providers/zai](/nb/providers/zai).

package/docs/nb/providers/index.md

@@ -11,7 +11,7 @@ title: "Provider Directory"
 Pllan can use many LLM providers. Pick a provider, authenticate, then set the
 default model as `provider/model`.
 
-Looking for chat channel docs (WhatsApp/Telegram/Discord/Slack/Mattermost (plugin)/etc.)? See [Channels](/channels).
+Looking for chat channel docs (WhatsApp/Telegram/Discord/Slack/Mattermost (plugin)/etc.)? See [Channels](/nb/channels).
 
 ## Quick start
 
@@ -26,44 +26,44 @@ Looking for chat channel docs (WhatsApp/Telegram/Discord/Slack/Mattermost (plugi
 
 ## Provider docs
 
-- [Amazon Bedrock](/providers/bedrock)
-- [Anthropic (API + Claude Code CLI)](/providers/anthropic)
-- [Cloudflare AI Gateway](/providers/cloudflare-ai-gateway)
-- [GLM models](/providers/glm)
-- [Google (Gemini)](/providers/google)
-- [Groq (LPU inference)](/providers/groq)
-- [Hugging Face (Inference)](/providers/huggingface)
-- [Kilocode](/providers/kilocode)
-- [LiteLLM (unified gateway)](/providers/litellm)
-- [MiniMax](/providers/minimax)
-- [Mistral](/providers/mistral)
-- [Model Studio (Alibaba Cloud)](/providers/modelstudio)
-- [Moonshot AI (Kimi + Kimi Coding)](/providers/moonshot)
-- [NVIDIA](/providers/nvidia)
-- [Ollama (cloud + local models)](/providers/ollama)
-- [OpenAI (API + Codex)](/providers/openai)
-- [OpenCode (Zen + Go)](/providers/opencode)
-- [OpenRouter](/providers/openrouter)
-- [Perplexity (web search)](/providers/perplexity-provider)
-- [Qianfan](/providers/qianfan)
-- [Qwen (OAuth)](/providers/qwen)
-- [SGLang (local models)](/providers/sglang)
-- [Together AI](/providers/together)
-- [Vercel AI Gateway](/providers/vercel-ai-gateway)
-- [Venice (Venice AI, privacy-focused)](/providers/venice)
-- [vLLM (local models)](/providers/vllm)
-- [Volcengine (Doubao)](/providers/volcengine)
-- [xAI](/providers/xai)
-- [Xiaomi](/providers/xiaomi)
-- [Z.AI](/providers/zai)
+- [Amazon Bedrock](/nb/providers/bedrock)
+- [Anthropic (API + Claude Code CLI)](/nb/providers/anthropic)
+- [Cloudflare AI Gateway](/nb/providers/cloudflare-ai-gateway)
+- [GLM models](/nb/providers/glm)
+- [Google (Gemini)](/nb/providers/google)
+- [Groq (LPU inference)](/nb/providers/groq)
+- [Hugging Face (Inference)](/nb/providers/huggingface)
+- [Kilocode](/nb/providers/kilocode)
+- [LiteLLM (unified gateway)](/nb/providers/litellm)
+- [MiniMax](/nb/providers/minimax)
+- [Mistral](/nb/providers/mistral)
+- [Model Studio (Alibaba Cloud)](/nb/providers/modelstudio)
+- [Moonshot AI (Kimi + Kimi Coding)](/nb/providers/moonshot)
+- [NVIDIA](/nb/providers/nvidia)
+- [Ollama (cloud + local models)](/nb/providers/ollama)
+- [OpenAI (API + Codex)](/nb/providers/openai)
+- [OpenCode (Zen + Go)](/nb/providers/opencode)
+- [OpenRouter](/nb/providers/openrouter)
+- [Perplexity (web search)](/nb/providers/perplexity-provider)
+- [Qianfan](/nb/providers/qianfan)
+- [Qwen (OAuth)](/nb/providers/qwen)
+- [SGLang (local models)](/nb/providers/sglang)
+- [Together AI](/nb/providers/together)
+- [Vercel AI Gateway](/nb/providers/vercel-ai-gateway)
+- [Venice (Venice AI, privacy-focused)](/nb/providers/venice)
+- [vLLM (local models)](/nb/providers/vllm)
+- [Volcengine (Doubao)](/nb/providers/volcengine)
+- [xAI](/nb/providers/xai)
+- [Xiaomi](/nb/providers/xiaomi)
+- [Z.AI](/nb/providers/zai)
 
 ## Transcription providers
 
-- [Deepgram (audio transcription)](/providers/deepgram)
+- [Deepgram (audio transcription)](/nb/providers/deepgram)
 
 ## Community tools
 
-- [Claude Max API Proxy](/providers/claude-max-api-proxy) - Community proxy for Claude subscription credentials (verify Anthropic policy/terms before use)
+- [Claude Max API Proxy](/nb/providers/claude-max-api-proxy) - Community proxy for Claude subscription credentials (verify Anthropic policy/terms before use)
 
 For the full provider catalog (xAI, Groq, Mistral, etc.) and advanced configuration,
-see [Model providers](/concepts/model-providers).
+see [Model providers](/nb/concepts/model-providers).

package/docs/nb/providers/kilocode.md

@@ -70,5 +70,5 @@ kilocode/google/gemini-3-pro-preview
 - Model refs are `kilocode/<model-id>` (e.g., `kilocode/anthropic/claude-sonnet-4`).
 - Default model: `kilocode/kilo/auto`
 - Base URL: `https://api.kilo.ai/api/gateway/`
-- For more model/provider options, see [/concepts/model-providers](/concepts/model-providers).
+- For more model/provider options, see [/concepts/model-providers](/nb/concepts/model-providers).
 - Kilo Gateway uses a Bearer token with your API key under the hood.

package/docs/nb/providers/litellm.md

@@ -151,4 +151,4 @@ curl "http://localhost:4000/spend/logs" \
 ## See also
 
 - [LiteLLM Docs](https://docs.litellm.ai)
-- [Model Providers](/concepts/model-providers)
+- [Model Providers](/nb/concepts/model-providers)

package/docs/nb/providers/minimax.md

@@ -194,7 +194,7 @@ Use the interactive config wizard to set MiniMax without editing JSON:
 - Coding Plan usage API: `https://api.minimaxi.com/v1/api/openplatform/coding_plan/remains` (requires a coding plan key).
 - Update pricing values in `models.json` if you need exact cost tracking.
 - Referral link for MiniMax Coding Plan (10% off): [https://platform.minimax.io/subscribe/coding-plan?code=DbXJTRClnb&source=link](https://platform.minimax.io/subscribe/coding-plan?code=DbXJTRClnb&source=link)
-- See [/concepts/model-providers](/concepts/model-providers) for provider rules.
+- See [/concepts/model-providers](/nb/concepts/model-providers) for provider rules.
 - Use `pllan models list` and `pllan models set minimax/MiniMax-M2.7` to switch.
 
 ## Troubleshooting

package/docs/nb/providers/models.md

@@ -24,22 +24,22 @@ model as `provider/model`.
 
 ## Supported providers (starter set)
 
-- [OpenAI (API + Codex)](/providers/openai)
-- [Anthropic (API + Claude Code CLI)](/providers/anthropic)
-- [OpenRouter](/providers/openrouter)
-- [Vercel AI Gateway](/providers/vercel-ai-gateway)
-- [Cloudflare AI Gateway](/providers/cloudflare-ai-gateway)
-- [Moonshot AI (Kimi + Kimi Coding)](/providers/moonshot)
-- [Mistral](/providers/mistral)
-- [Synthetic](/providers/synthetic)
-- [OpenCode (Zen + Go)](/providers/opencode)
-- [Z.AI](/providers/zai)
-- [GLM models](/providers/glm)
-- [MiniMax](/providers/minimax)
-- [Venice (Venice AI)](/providers/venice)
-- [Amazon Bedrock](/providers/bedrock)
-- [Qianfan](/providers/qianfan)
-- [xAI](/providers/xai)
+- [OpenAI (API + Codex)](/nb/providers/openai)
+- [Anthropic (API + Claude Code CLI)](/nb/providers/anthropic)
+- [OpenRouter](/nb/providers/openrouter)
+- [Vercel AI Gateway](/nb/providers/vercel-ai-gateway)
+- [Cloudflare AI Gateway](/nb/providers/cloudflare-ai-gateway)
+- [Moonshot AI (Kimi + Kimi Coding)](/nb/providers/moonshot)
+- [Mistral](/nb/providers/mistral)
+- [Synthetic](/nb/providers/synthetic)
+- [OpenCode (Zen + Go)](/nb/providers/opencode)
+- [Z.AI](/nb/providers/zai)
+- [GLM models](/nb/providers/glm)
+- [MiniMax](/nb/providers/minimax)
+- [Venice (Venice AI)](/nb/providers/venice)
+- [Amazon Bedrock](/nb/providers/bedrock)
+- [Qianfan](/nb/providers/qianfan)
+- [xAI](/nb/providers/xai)
 
 For the full provider catalog (xAI, Groq, Mistral, etc.) and advanced configuration,
-see [Model providers](/concepts/model-providers).
+see [Model providers](/nb/concepts/model-providers).

package/docs/nb/providers/ollama.md

@@ -347,6 +347,6 @@ ollama serve
 
 ## See Also
 
-- [Model Providers](/concepts/model-providers) - Overview of all providers
-- [Model Selection](/concepts/models) - How to choose models
-- [Configuration](/gateway/configuration) - Full config reference
+- [Model Providers](/nb/concepts/model-providers) - Overview of all providers
+- [Model Selection](/nb/concepts/models) - How to choose models
+- [Configuration](/nb/gateway/configuration) - Full config reference

package/docs/nb/providers/openai.md

@@ -299,5 +299,5 @@ Direct OpenAI Responses models still force `store: true` unless compat sets
 
 ## Notes
 
-- Model refs always use `provider/model` (see [/concepts/models](/concepts/models)).
-- Auth details + reuse rules are in [/concepts/oauth](/concepts/oauth).
+- Model refs always use `provider/model` (see [/concepts/models](/nb/concepts/models)).
+- Auth details + reuse rules are in [/concepts/oauth](/nb/concepts/oauth).

package/docs/nb/providers/opencode-go.md

@@ -8,7 +8,7 @@ title: "OpenCode Go"
 
 # OpenCode Go
 
-OpenCode Go is the Go catalog within [OpenCode](/providers/opencode).
+OpenCode Go is the Go catalog within [OpenCode](/nb/providers/opencode).
 It uses the same `OPENCODE_API_KEY` as the Zen catalog, but keeps the runtime
 provider id `opencode-go` so upstream per-model routing stays correct.
 
@@ -41,5 +41,5 @@ Pllan handles per-model routing automatically when the model ref uses `opencode-
 
 ## Notes
 
-- Use [OpenCode](/providers/opencode) for the shared onboarding and catalog overview.
+- Use [OpenCode](/nb/providers/opencode) for the shared onboarding and catalog overview.
 - Runtime refs stay explicit: `opencode/...` for Zen, `opencode-go/...` for Go.

package/docs/nb/providers/openrouter.md

@@ -33,5 +33,5 @@ pllan onboard --auth-choice apiKey --token-provider openrouter --token "$OPENROU
 ## Notes
 
 - Model refs are `openrouter/<provider>/<model>`.
-- For more model/provider options, see [/concepts/model-providers](/concepts/model-providers).
+- For more model/provider options, see [/concepts/model-providers](/nb/concepts/model-providers).
 - OpenRouter uses a Bearer token with your API key under the hood.

package/docs/nb/providers/perplexity-provider.md

@@ -13,7 +13,7 @@ Search API or Perplexity Sonar via OpenRouter.
 
 <Note>
 This page covers the Perplexity **provider** setup. For the Perplexity
-**tool** (how the agent uses it), see [Perplexity tool](/tools/perplexity-search).
+**tool** (how the agent uses it), see [Perplexity tool](/nb/tools/perplexity-search).
 </Note>
 
 - Type: web search provider (not a model provider)

package/docs/nb/providers/qianfan.md

@@ -32,7 +32,7 @@ pllan onboard --auth-choice qianfan-api-key
 
 ## Related Documentation
 
-- [Pllan Configuration](/gateway/configuration)
-- [Model Providers](/concepts/model-providers)
-- [Agent Setup](/concepts/agent)
+- [Pllan Configuration](/nb/gateway/configuration)
+- [Model Providers](/nb/concepts/model-providers)
+- [Agent Setup](/nb/concepts/agent)
 - [Qianfan API Documentation](https://cloud.baidu.com/doc/qianfan-api/s/3m7of64lb)

package/docs/nb/providers/qwen.md

@@ -50,4 +50,4 @@ from `~/.qwen/oauth_creds.json` when it loads the auth store. You still need a
 - Tokens auto-refresh; re-run the login command if refresh fails or access is revoked.
 - Default base URL: `https://portal.qwen.ai/v1` (override with
   `models.providers.qwen-portal.baseUrl` if Qwen provides a different endpoint).
-- See [Model providers](/concepts/model-providers) for provider-wide rules.
+- See [Model providers](/nb/concepts/model-providers) for provider-wide rules.

package/docs/nb/providers/synthetic.md

@@ -96,4 +96,4 @@ All models below use cost `0` (input/output/cache).
 - Model refs use `synthetic/<modelId>`.
 - If you enable a model allowlist (`agents.defaults.models`), add every model you
   plan to use.
-- See [Model providers](/concepts/model-providers) for provider rules.
+- See [Model providers](/nb/concepts/model-providers) for provider rules.

package/docs/nb/providers/xai.md

@@ -58,4 +58,4 @@ pllan config set tools.web.search.provider grok
 ## Notes
 
 - Pllan applies xAI-specific tool-schema and tool-call compatibility fixes automatically on the shared runner path.
-- For the broader provider overview, see [Model providers](/providers/index).
+- For the broader provider overview, see [Model providers](/nb/providers/index).

package/docs/nb/providers/xiaomi.md

@@ -83,4 +83,4 @@ pllan onboard --auth-choice xiaomi-api-key --xiaomi-api-key "$XIAOMI_API_KEY"
 - Default model ref: `xiaomi/mimo-v2-flash`.
 - Additional built-in models: `xiaomi/mimo-v2-pro`, `xiaomi/mimo-v2-omni`.
 - The provider is injected automatically when `XIAOMI_API_KEY` is set (or an auth profile exists).
-- See [/concepts/model-providers](/concepts/model-providers) for provider rules.
+- See [/concepts/model-providers](/nb/concepts/model-providers) for provider rules.

package/docs/nb/providers/zai.md

@@ -42,5 +42,5 @@ pllan onboard --auth-choice zai-cn
 - GLM models are available as `zai/<model>` (example: `zai/glm-5`).
 - `tool_stream` is enabled by default for Z.AI tool-call streaming. Set
   `agents.defaults.models["zai/<model>"].params.tool_stream` to `false` to disable it.
-- See [/providers/glm](/providers/glm) for the model family overview.
+- See [/providers/glm](/nb/providers/glm) for the model family overview.
 - Z.AI uses Bearer auth with your API key.

package/docs/nb/reference/api-usage-costs.md

@@ -29,7 +29,7 @@ Pllan features that can generate provider usage or paid API calls.
 - `pllan status --usage` and `pllan channels list` show provider **usage windows**
   (quota snapshots, not per-message costs).
 
-See [Token use & costs](/reference/token-use) for details and examples.
+See [Token use & costs](/nb/reference/token-use) for details and examples.
 
 ## How keys are discovered
 
@@ -48,7 +48,7 @@ Pllan can pick up credentials from:
 Every reply or tool call uses the **current model provider** (OpenAI, Anthropic, etc). This is the
 primary source of usage and cost.
 
-See [Models](/providers/models) for pricing config and [Token use & costs](/reference/token-use) for display.
+See [Models](/nb/providers/models) for pricing config and [Token use & costs](/nb/reference/token-use) for display.
 
 ### 2) Media understanding (audio/image/video)
 
@@ -58,7 +58,7 @@ Inbound media can be summarized/transcribed before the reply runs. This uses mod
 - Image: OpenAI / Anthropic / Google.
 - Video: Google.
 
-See [Media understanding](/nodes/media-understanding).
+See [Media understanding](/nb/nodes/media-understanding).
 
 ### 3) Memory embeddings + semantic search
 
@@ -73,7 +73,7 @@ Semantic memory search uses **embedding APIs** when configured for remote provid
 
 You can keep it local with `memorySearch.provider = "local"` (no API usage).
 
-See [Memory](/concepts/memory).
+See [Memory](/nb/concepts/memory).
 
 ### 4) Web search tool
 
@@ -92,7 +92,7 @@ free credit. The Search plan costs \$5 per 1,000 requests, so the credit covers
 1,000 requests/month at no charge. Set your usage limit in the Brave dashboard
 to avoid unexpected charges.
 
-See [Web tools](/tools/web).
+See [Web tools](/nb/tools/web).
 
 ### 5) Web fetch tool (Firecrawl)
 
@@ -102,7 +102,7 @@ See [Web tools](/tools/web).
 
 If Firecrawl isn’t configured, the tool falls back to direct fetch + readability (no paid API).
 
-See [Web tools](/tools/web).
+See [Web tools](/nb/tools/web).
 
 ### 6) Provider usage snapshots (status/health)
 
@@ -112,21 +112,21 @@ These are typically low-volume calls but still hit provider APIs:
 - `pllan status --usage`
 - `pllan models status --json`
 
-See [Models CLI](/cli/models).
+See [Models CLI](/nb/cli/models).
 
 ### 7) Compaction safeguard summarization
 
 The compaction safeguard can summarize session history using the **current model**, which
 invokes provider APIs when it runs.
 
-See [Session management + compaction](/reference/session-management-compaction).
+See [Session management + compaction](/nb/reference/session-management-compaction).
 
 ### 8) Model scan / probe
 
 `pllan models scan` can probe OpenRouter models and uses `OPENROUTER_API_KEY` when
 probing is enabled.
 
-See [Models CLI](/cli/models).
+See [Models CLI](/nb/cli/models).
 
 ### 9) Talk (speech)
 
@@ -134,11 +134,11 @@ Talk mode can invoke **ElevenLabs** when configured:
 
 - `ELEVENLABS_API_KEY` or `talk.apiKey`
 
-See [Talk mode](/nodes/talk).
+See [Talk mode](/nb/nodes/talk).
 
 ### 10) Skills (third-party APIs)
 
 Skills can store `apiKey` in `skills.entries.<name>.apiKey`. If a skill uses that key for external
 APIs, it can incur costs according to the skill’s provider.
 
-See [Skills](/tools/skills).
+See [Skills](/nb/tools/skills).

package/docs/nb/reference/memory-config.md

@@ -12,7 +12,7 @@ read_when:
 
 This page covers the full configuration surface for Pllan memory search. For
 the conceptual overview (file layout, memory tools, when to write memory, and the
-automatic flush), see [Memory](/concepts/memory).
+automatic flush), see [Memory](/nb/concepts/memory).
 
 ## Memory search defaults
 
@@ -126,7 +126,7 @@ out to QMD for retrieval. Key points:
   `commandTimeoutMs`, `updateTimeoutMs`, `embedTimeoutMs`).
 - `limits`: clamp recall payload (`maxResults`, `maxSnippetChars`,
   `maxInjectedChars`, `timeoutMs`).
-- `scope`: same schema as [`session.sendPolicy`](/gateway/configuration-reference#session).
+- `scope`: same schema as [`session.sendPolicy`](/nb/gateway/configuration-reference#session).
   Default is DM-only (`deny` all, `allow` direct chats); loosen it to surface QMD
   hits in groups/channels.
   - `match.keyPrefix` matches the **normalized** session key (lowercased, with any

package/docs/nb/reference/prompt-caching.md

@@ -69,7 +69,7 @@ agents:
       ttl: "1h"
 ```
 
-See [Session Pruning](/concepts/session-pruning) for full behavior.
+See [Session Pruning](/nb/concepts/session-pruning) for full behavior.
 
 ### Heartbeat keep-warm
 
@@ -179,7 +179,7 @@ Defaults:
 
 Related docs:
 
-- [Anthropic](/providers/anthropic)
-- [Token Use and Costs](/reference/token-use)
-- [Session Pruning](/concepts/session-pruning)
-- [Gateway Configuration Reference](/gateway/configuration-reference)
+- [Anthropic](/nb/providers/anthropic)
+- [Token Use and Costs](/nb/reference/token-use)
+- [Session Pruning](/nb/concepts/session-pruning)
+- [Gateway Configuration Reference](/nb/gateway/configuration-reference)

package/docs/nb/reference/rpc.md

@@ -17,11 +17,11 @@ Pllan integrates external CLIs via JSON-RPC. Two patterns are used today.
 - Health probe: `/api/v1/check`.
 - Pllan owns lifecycle when `channels.signal.autoStart=true`.
 
-See [Signal](/channels/signal) for setup and endpoints.
+See [Signal](/nb/channels/signal) for setup and endpoints.
 
 ## Pattern B: stdio child process (legacy: imsg)
 
-> **Note:** For new iMessage setups, use [BlueBubbles](/channels/bluebubbles) instead.
+> **Note:** For new iMessage setups, use [BlueBubbles](/nb/channels/bluebubbles) instead.
 
 - Pllan spawns `imsg rpc` as a child process (legacy iMessage integration).
 - JSON-RPC is line-delimited over stdin/stdout (one JSON object per line).
@@ -34,7 +34,7 @@ Core methods used:
 - `send`
 - `chats.list` (probe/diagnostics)
 
-See [iMessage](/channels/imessage) for legacy setup and addressing (`chat_id` preferred).
+See [iMessage](/nb/channels/imessage) for legacy setup and addressing (`chat_id` preferred).
 
 ## Adapter guidelines
 

package/docs/nb/reference/session-management-compaction.md

@@ -21,10 +21,10 @@ This document explains how Pllan manages sessions end-to-end:
 
 If you want a higher-level overview first, start with:
 
-- [/concepts/session](/concepts/session)
-- [/concepts/compaction](/concepts/compaction)
-- [/concepts/session-pruning](/concepts/session-pruning)
-- [/reference/transcript-hygiene](/reference/transcript-hygiene)
+- [/concepts/session](/nb/concepts/session)
+- [/concepts/compaction](/nb/concepts/compaction)
+- [/concepts/session-pruning](/nb/concepts/session-pruning)
+- [/reference/transcript-hygiene](/nb/reference/transcript-hygiene)
 
 ---
 
@@ -115,7 +115,7 @@ Common patterns:
 - Cron: `cron:<job.id>`
 - Webhook: `hook:<uuid>` (unless overridden)
 
-The canonical rules are documented at [/concepts/session](/concepts/session).
+The canonical rules are documented at [/concepts/session](/nb/concepts/session).
 
 ---
 
@@ -193,7 +193,7 @@ If you’re tuning limits:
 - The context window comes from the model catalog (and can be overridden via config).
 - `contextTokens` in the store is a runtime estimate/reporting value; don’t treat it as a strict guarantee.
 
-For more, see [/token-use](/reference/token-use).
+For more, see [/token-use](/nb/reference/token-use).
 
 ---
 
@@ -206,7 +206,7 @@ After compaction, future turns see:
 - The compaction summary
 - Messages after `firstKeptEntryId`
 
-Compaction is **persistent** (unlike session pruning). See [/concepts/session-pruning](/concepts/session-pruning).
+Compaction is **persistent** (unlike session pruning). See [/concepts/session-pruning](/nb/concepts/session-pruning).
 
 ---
 
@@ -306,7 +306,7 @@ Notes:
 - The flush runs once per compaction cycle (tracked in `sessions.json`).
 - The flush runs only for embedded Pi sessions (CLI backends skip it).
 - The flush is skipped when the session workspace is read-only (`workspaceAccess: "ro"` or `"none"`).
-- See [Memory](/concepts/memory) for the workspace file layout and write patterns.
+- See [Memory](/nb/concepts/memory) for the workspace file layout and write patterns.
 
 Pi also exposes a `session_before_compact` hook in the extension API, but Pllan’s
 flush logic lives on the Gateway side today.
@@ -315,7 +315,7 @@ flush logic lives on the Gateway side today.
 
 ## Troubleshooting checklist
 
-- Session key wrong? Start with [/concepts/session](/concepts/session) and confirm the `sessionKey` in `/status`.
+- Session key wrong? Start with [/concepts/session](/nb/concepts/session) and confirm the `sessionKey` in `/status`.
 - Store vs transcript mismatch? Confirm the Gateway host and the store path from `pllan status`.
 - Compaction spam? Check:
   - model context window (too small)

package/docs/nb/reference/test.md

@@ -7,7 +7,7 @@ title: "Tests"
 
 # Tests
 
-- Full testing kit (suites, live, Docker): [Testing](/help/testing)
+- Full testing kit (suites, live, Docker): [Testing](/nb/help/testing)
 
 - `pnpm test:force`: Kills any lingering gateway process holding the default control port, then runs the full Vitest suite with an isolated gateway port so server tests don’t collide with a running instance. Use this when a prior gateway run left port 18789 occupied.
 - `pnpm test:coverage`: Runs the unit suite with V8 coverage (via `vitest.unit.config.ts`). Global thresholds are 70% lines/branches/functions/statements. Coverage excludes integration-heavy entrypoints (CLI wiring, gateway/telegram bridges, webchat static server) to keep the target focused on unit-testable logic.

package/docs/nb/reference/token-use.md

@@ -23,7 +23,7 @@ Pllan assembles its own system prompt on every run. It includes:
 - Reply tags + heartbeat behavior
 - Runtime metadata (host/OS/model/thinking)
 
-See the full breakdown in [System Prompt](/concepts/system-prompt).
+See the full breakdown in [System Prompt](/nb/concepts/system-prompt).
 
 ## What counts in the context window
 
@@ -42,7 +42,7 @@ Use `agents.defaults.imageMaxDimensionPx` (default: `1200`) to tune this:
 - Lower values usually reduce vision-token usage and payload size.
 - Higher values preserve more visual detail for OCR/UI-heavy screenshots.
 
-For a practical breakdown (per injected file, tools, skills, and system prompt size), use `/context list` or `/context detail`. See [Context](/concepts/context).
+For a practical breakdown (per injected file, tools, skills, and system prompt size), use `/context list` or `/context detail`. See [Context](/nb/concepts/context).
 
 ## How to see current token usage
 
@@ -81,8 +81,8 @@ has expired, then resets the cache window so subsequent requests can re-use the
 freshly cached context instead of re-caching the full history. This keeps cache
 write costs lower when a session goes idle past the TTL.
 
-Configure it in [Gateway configuration](/gateway/configuration) and see the
-behavior details in [Session pruning](/concepts/session-pruning).
+Configure it in [Gateway configuration](/nb/gateway/configuration) and see the
+behavior details in [Session pruning](/nb/concepts/session-pruning).
 
 Heartbeat can keep the cache **warm** across idle gaps. If your model cache TTL
 is `1h`, setting the heartbeat interval just under that (e.g., `55m`) can avoid
@@ -91,7 +91,7 @@ re-caching the full prompt, reducing cache write costs.
 In multi-agent setups, you can keep one shared model config and tune cache behavior
 per agent with `agents.list[].params.cacheRetention`.
 
-For a full knob-by-knob guide, see [Prompt Caching](/reference/prompt-caching).
+For a full knob-by-knob guide, see [Prompt Caching](/nb/reference/prompt-caching).
 
 For Anthropic API pricing, cache reads are significantly cheaper than input
 tokens, while cache writes are billed at a higher multiplier. See Anthropic’s
@@ -172,4 +172,4 @@ rejects that combination with HTTP 401.
 - Keep skill descriptions short (skill list is injected into the prompt).
 - Prefer smaller models for verbose, exploratory work.
 
-See [Skills](/tools/skills) for the exact skill list overhead formula.
+See [Skills](/nb/tools/skills) for the exact skill list overhead formula.

package/docs/nb/reference/transcript-hygiene.md

@@ -28,7 +28,7 @@ Scope includes:
 
 If you need transcript storage details, see:
 
-- [/reference/session-management-compaction](/reference/session-management-compaction)
+- [/reference/session-management-compaction](/nb/reference/session-management-compaction)
 
 ---