@quantumclaw/quantumclaw 2026.3.22

package/docs/nodes/media-understanding.md

@@ -0,0 +1,394 @@
+---
+summary: "Inbound image/audio/video understanding (optional) with provider + CLI fallbacks"
+read_when:
+  - Designing or refactoring media understanding
+  - Tuning inbound audio/video/image preprocessing
+title: "Media Understanding"
+---
+
+# Media Understanding - Inbound (2026-01-17)
+
+QuantumClaw can **summarize inbound media** (image/audio/video) before the reply pipeline runs. It auto‑detects when local tools or provider keys are available, and can be disabled or customized. If understanding is off, models still receive the original files/URLs as usual.
+
+Vendor-specific media behavior is registered by vendor plugins, while QuantumClaw
+core owns the shared `tools.media` config, fallback order, and reply-pipeline
+integration.
+
+## Goals
+
+- Optional: pre‑digest inbound media into short text for faster routing + better command parsing.
+- Preserve original media delivery to the model (always).
+- Support **provider APIs** and **CLI fallbacks**.
+- Allow multiple models with ordered fallback (error/size/timeout).
+
+## High-level behavior
+
+1. Collect inbound attachments (`MediaPaths`, `MediaUrls`, `MediaTypes`).
+2. For each enabled capability (image/audio/video), select attachments per policy (default: **first**).
+3. Choose the first eligible model entry (size + capability + auth).
+4. If a model fails or the media is too large, **fall back to the next entry**.
+5. On success:
+   - `Body` becomes `[Image]`, `[Audio]`, or `[Video]` block.
+   - Audio sets `{{Transcript}}`; command parsing uses caption text when present,
+     otherwise the transcript.
+   - Captions are preserved as `User text:` inside the block.
+
+If understanding fails or is disabled, **the reply flow continues** with the original body + attachments.
+
+## Config overview
+
+`tools.media` supports **shared models** plus per‑capability overrides:
+
+- `tools.media.models`: shared model list (use `capabilities` to gate).
+- `tools.media.image` / `tools.media.audio` / `tools.media.video`:
+  - defaults (`prompt`, `maxChars`, `maxBytes`, `timeoutSeconds`, `language`)
+  - provider overrides (`baseUrl`, `headers`, `providerOptions`)
+  - Deepgram audio options via `tools.media.audio.providerOptions.deepgram`
+  - audio transcript echo controls (`echoTranscript`, default `false`; `echoFormat`)
+  - optional **per‑capability `models` list** (preferred before shared models)
+  - `attachments` policy (`mode`, `maxAttachments`, `prefer`)
+  - `scope` (optional gating by channel/chatType/session key)
+- `tools.media.concurrency`: max concurrent capability runs (default **2**).
+
+```json5
+{
+  tools: {
+    media: {
+      models: [
+        /* shared list */
+      ],
+      image: {
+        /* optional overrides */
+      },
+      audio: {
+        /* optional overrides */
+        echoTranscript: true,
+        echoFormat: '📝 "{transcript}"',
+      },
+      video: {
+        /* optional overrides */
+      },
+    },
+  },
+}
+```
+
+### Model entries
+
+Each `models[]` entry can be **provider** or **CLI**:
+
+```json5
+{
+  type: "provider", // default if omitted
+  provider: "openai",
+  model: "gpt-5.2",
+  prompt: "Describe the image in <= 500 chars.",
+  maxChars: 500,
+  maxBytes: 10485760,
+  timeoutSeconds: 60,
+  capabilities: ["image"], // optional, used for multi‑modal entries
+  profile: "vision-profile",
+  preferredProfile: "vision-fallback",
+}
+```
+
+```json5
+{
+  type: "cli",
+  command: "gemini",
+  args: [
+    "-m",
+    "gemini-3-flash",
+    "--allowed-tools",
+    "read_file",
+    "Read the media at {{MediaPath}} and describe it in <= {{MaxChars}} characters.",
+  ],
+  maxChars: 500,
+  maxBytes: 52428800,
+  timeoutSeconds: 120,
+  capabilities: ["video", "image"],
+}
+```
+
+CLI templates can also use:
+
+- `{{MediaDir}}` (directory containing the media file)
+- `{{OutputDir}}` (scratch dir created for this run)
+- `{{OutputBase}}` (scratch file base path, no extension)
+
+## Defaults and limits
+
+Recommended defaults:
+
+- `maxChars`: **500** for image/video (short, command‑friendly)
+- `maxChars`: **unset** for audio (full transcript unless you set a limit)
+- `maxBytes`:
+  - image: **10MB**
+  - audio: **20MB**
+  - video: **50MB**
+
+Rules:
+
+- If media exceeds `maxBytes`, that model is skipped and the **next model is tried**.
+- Audio files smaller than **1024 bytes** are treated as empty/corrupt and skipped before provider/CLI transcription.
+- If the model returns more than `maxChars`, output is trimmed.
+- `prompt` defaults to simple “Describe the {media}.” plus the `maxChars` guidance (image/video only).
+- If `<capability>.enabled: true` but no models are configured, QuantumClaw tries the
+  **active reply model** when its provider supports the capability.
+
+### Auto-detect media understanding (default)
+
+If `tools.media.<capability>.enabled` is **not** set to `false` and you haven’t
+configured models, QuantumClaw auto-detects in this order and **stops at the first
+working option**:
+
+1. **Local CLIs** (audio only; if installed)
+   - `sherpa-onnx-offline` (requires `SHERPA_ONNX_MODEL_DIR` with encoder/decoder/joiner/tokens)
+   - `whisper-cli` (`whisper-cpp`; uses `WHISPER_CPP_MODEL` or the bundled tiny model)
+   - `whisper` (Python CLI; downloads models automatically)
+2. **Gemini CLI** (`gemini`) using `read_many_files`
+3. **Provider keys**
+   - Audio: OpenAI → Groq → Deepgram → Google
+   - Image: OpenAI → Anthropic → Google → MiniMax
+   - Video: Google
+
+To disable auto-detection, set:
+
+```json5
+{
+  tools: {
+    media: {
+      audio: {
+        enabled: false,
+      },
+    },
+  },
+}
+```
+
+Note: Binary detection is best-effort across macOS/Linux/Windows; ensure the CLI is on `PATH` (we expand `~`), or set an explicit CLI model with a full command path.
+
+### Proxy environment support (provider models)
+
+When provider-based **audio** and **video** media understanding is enabled, QuantumClaw
+honors standard outbound proxy environment variables for provider HTTP calls:
+
+- `HTTPS_PROXY`
+- `HTTP_PROXY`
+- `https_proxy`
+- `http_proxy`
+
+If no proxy env vars are set, media understanding uses direct egress.
+If the proxy value is malformed, QuantumClaw logs a warning and falls back to direct
+fetch.
+
+## Capabilities (optional)
+
+If you set `capabilities`, the entry only runs for those media types. For shared
+lists, QuantumClaw can infer defaults:
+
+- `openai`, `anthropic`, `minimax`: **image**
+- `moonshot`: **image + video**
+- `google` (Gemini API): **image + audio + video**
+- `mistral`: **audio**
+- `zai`: **image**
+- `groq`: **audio**
+- `deepgram`: **audio**
+
+For CLI entries, **set `capabilities` explicitly** to avoid surprising matches.
+If you omit `capabilities`, the entry is eligible for the list it appears in.
+
+## Provider support matrix (QuantumClaw integrations)
+
+| Capability | Provider integration                               | Notes                                                                   |
+| ---------- | -------------------------------------------------- | ----------------------------------------------------------------------- |
+| Image      | OpenAI, Anthropic, Google, MiniMax, Moonshot, Z.AI | Vendor plugins register image support against core media understanding. |
+| Audio      | OpenAI, Groq, Deepgram, Google, Mistral            | Provider transcription (Whisper/Deepgram/Gemini/Voxtral).               |
+| Video      | Google, Moonshot                                   | Provider video understanding via vendor plugins.                        |
+
+## Model selection guidance
+
+- Prefer the strongest latest-generation model available for each media capability when quality and safety matter.
+- For tool-enabled agents handling untrusted inputs, avoid older/weaker media models.
+- Keep at least one fallback per capability for availability (quality model + faster/cheaper model).
+- CLI fallbacks (`whisper-cli`, `whisper`, `gemini`) are useful when provider APIs are unavailable.
+- `parakeet-mlx` note: with `--output-dir`, QuantumClaw reads `<output-dir>/<media-basename>.txt` when output format is `txt` (or unspecified); non-`txt` formats fall back to stdout.
+
+## Attachment policy
+
+Per‑capability `attachments` controls which attachments are processed:
+
+- `mode`: `first` (default) or `all`
+- `maxAttachments`: cap the number processed (default **1**)
+- `prefer`: `first`, `last`, `path`, `url`
+
+When `mode: "all"`, outputs are labeled `[Image 1/2]`, `[Audio 2/2]`, etc.
+
+## Config examples
+
+### 1) Shared models list + overrides
+
+```json5
+{
+  tools: {
+    media: {
+      models: [
+        { provider: "openai", model: "gpt-5.2", capabilities: ["image"] },
+        {
+          provider: "google",
+          model: "gemini-3-flash-preview",
+          capabilities: ["image", "audio", "video"],
+        },
+        {
+          type: "cli",
+          command: "gemini",
+          args: [
+            "-m",
+            "gemini-3-flash",
+            "--allowed-tools",
+            "read_file",
+            "Read the media at {{MediaPath}} and describe it in <= {{MaxChars}} characters.",
+          ],
+          capabilities: ["image", "video"],
+        },
+      ],
+      audio: {
+        attachments: { mode: "all", maxAttachments: 2 },
+      },
+      video: {
+        maxChars: 500,
+      },
+    },
+  },
+}
+```
+
+### 2) Audio + Video only (image off)
+
+```json5
+{
+  tools: {
+    media: {
+      audio: {
+        enabled: true,
+        models: [
+          { provider: "openai", model: "gpt-4o-mini-transcribe" },
+          {
+            type: "cli",
+            command: "whisper",
+            args: ["--model", "base", "{{MediaPath}}"],
+          },
+        ],
+      },
+      video: {
+        enabled: true,
+        maxChars: 500,
+        models: [
+          { provider: "google", model: "gemini-3-flash-preview" },
+          {
+            type: "cli",
+            command: "gemini",
+            args: [
+              "-m",
+              "gemini-3-flash",
+              "--allowed-tools",
+              "read_file",
+              "Read the media at {{MediaPath}} and describe it in <= {{MaxChars}} characters.",
+            ],
+          },
+        ],
+      },
+    },
+  },
+}
+```
+
+### 3) Optional image understanding
+
+```json5
+{
+  tools: {
+    media: {
+      image: {
+        enabled: true,
+        maxBytes: 10485760,
+        maxChars: 500,
+        models: [
+          { provider: "openai", model: "gpt-5.2" },
+          { provider: "anthropic", model: "claude-opus-4-6" },
+          {
+            type: "cli",
+            command: "gemini",
+            args: [
+              "-m",
+              "gemini-3-flash",
+              "--allowed-tools",
+              "read_file",
+              "Read the media at {{MediaPath}} and describe it in <= {{MaxChars}} characters.",
+            ],
+          },
+        ],
+      },
+    },
+  },
+}
+```
+
+### 4) Multi-modal single entry (explicit capabilities)
+
+```json5
+{
+  tools: {
+    media: {
+      image: {
+        models: [
+          {
+            provider: "google",
+            model: "gemini-3.1-pro-preview",
+            capabilities: ["image", "video", "audio"],
+          },
+        ],
+      },
+      audio: {
+        models: [
+          {
+            provider: "google",
+            model: "gemini-3.1-pro-preview",
+            capabilities: ["image", "video", "audio"],
+          },
+        ],
+      },
+      video: {
+        models: [
+          {
+            provider: "google",
+            model: "gemini-3.1-pro-preview",
+            capabilities: ["image", "video", "audio"],
+          },
+        ],
+      },
+    },
+  },
+}
+```
+
+## Status output
+
+When media understanding runs, `/status` includes a short summary line:
+
+```
+📎 Media: image ok (openai/gpt-5.2) · audio skipped (maxBytes)
+```
+
+This shows per‑capability outcomes and the chosen provider/model when applicable.
+
+## Notes
+
+- Understanding is **best‑effort**. Errors do not block replies.
+- Attachments are still passed to models even when understanding is disabled.
+- Use `scope` to limit where understanding runs (e.g. only DMs).
+
+## Related docs
+
+- [Configuration](/gateway/configuration)
+- [Image & Media Support](/nodes/images)

package/docs/nodes/talk.md

@@ -0,0 +1,92 @@
+---
+summary: "Talk mode: continuous speech conversations with ElevenLabs TTS"
+read_when:
+  - Implementing Talk mode on macOS/iOS/Android
+  - Changing voice/TTS/interrupt behavior
+title: "Talk Mode"
+---
+
+# Talk Mode
+
+Talk mode is a continuous voice conversation loop:
+
+1. Listen for speech
+2. Send transcript to the model (main session, chat.send)
+3. Wait for the response
+4. Speak it via ElevenLabs (streaming playback)
+
+## Behavior (macOS)
+
+- **Always-on overlay** while Talk mode is enabled.
+- **Listening → Thinking → Speaking** phase transitions.
+- On a **short pause** (silence window), the current transcript is sent.
+- Replies are **written to WebChat** (same as typing).
+- **Interrupt on speech** (default on): if the user starts talking while the assistant is speaking, we stop playback and note the interruption timestamp for the next prompt.
+
+## Voice directives in replies
+
+The assistant may prefix its reply with a **single JSON line** to control voice:
+
+```json
+{ "voice": "<voice-id>", "once": true }
+```
+
+Rules:
+
+- First non-empty line only.
+- Unknown keys are ignored.
+- `once: true` applies to the current reply only.
+- Without `once`, the voice becomes the new default for Talk mode.
+- The JSON line is stripped before TTS playback.
+
+Supported keys:
+
+- `voice` / `voice_id` / `voiceId`
+- `model` / `model_id` / `modelId`
+- `speed`, `rate` (WPM), `stability`, `similarity`, `style`, `speakerBoost`
+- `seed`, `normalize`, `lang`, `output_format`, `latency_tier`
+- `once`
+
+## Config (`~/.quantumclaw/quantumclaw.json`)
+
+```json5
+{
+  talk: {
+    voiceId: "elevenlabs_voice_id",
+    modelId: "eleven_v3",
+    outputFormat: "mp3_44100_128",
+    apiKey: "elevenlabs_api_key",
+    silenceTimeoutMs: 1500,
+    interruptOnSpeech: true,
+  },
+}
+```
+
+Defaults:
+
+- `interruptOnSpeech`: true
+- `silenceTimeoutMs`: when unset, Talk keeps the platform default pause window before sending the transcript (`700 ms on macOS and Android, 900 ms on iOS`)
+- `voiceId`: falls back to `ELEVENLABS_VOICE_ID` / `SAG_VOICE_ID` (or first ElevenLabs voice when API key is available)
+- `modelId`: defaults to `eleven_v3` when unset
+- `apiKey`: falls back to `ELEVENLABS_API_KEY` (or gateway shell profile if available)
+- `outputFormat`: defaults to `pcm_44100` on macOS/iOS and `pcm_24000` on Android (set `mp3_*` to force MP3 streaming)
+
+## macOS UI
+
+- Menu bar toggle: **Talk**
+- Config tab: **Talk Mode** group (voice id + interrupt toggle)
+- Overlay:
+  - **Listening**: cloud pulses with mic level
+  - **Thinking**: sinking animation
+  - **Speaking**: radiating rings
+  - Click cloud: stop speaking
+  - Click X: exit Talk mode
+
+## Notes
+
+- Requires Speech + Microphone permissions.
+- Uses `chat.send` against session key `main`.
+- TTS uses ElevenLabs streaming API with `ELEVENLABS_API_KEY` and incremental playback on macOS/iOS/Android for lower latency.
+- `stability` for `eleven_v3` is validated to `0.0`, `0.5`, or `1.0`; other models accept `0..1`.
+- `latency_tier` is validated to `0..4` when set.
+- Android supports `pcm_16000`, `pcm_22050`, `pcm_24000`, and `pcm_44100` output formats for low-latency AudioTrack streaming.

package/docs/nodes/troubleshooting.md

@@ -0,0 +1,114 @@
+---
+summary: "Troubleshoot node pairing, foreground requirements, permissions, and tool failures"
+read_when:
+  - Node is connected but camera/canvas/screen/exec tools fail
+  - You need the node pairing versus approvals mental model
+title: "Node Troubleshooting"
+---
+
+# Node troubleshooting
+
+Use this page when a node is visible in status but node tools fail.
+
+## Command ladder
+
+```bash
+quantumclaw status
+quantumclaw gateway status
+quantumclaw logs --follow
+quantumclaw doctor
+quantumclaw channels status --probe
+```
+
+Then run node specific checks:
+
+```bash
+quantumclaw nodes status
+quantumclaw nodes describe --node <idOrNameOrIp>
+quantumclaw approvals get --node <idOrNameOrIp>
+```
+
+Healthy signals:
+
+- Node is connected and paired for role `node`.
+- `nodes describe` includes the capability you are calling.
+- Exec approvals show expected mode/allowlist.
+
+## Foreground requirements
+
+`canvas.*`, `camera.*`, and `screen.*` are foreground only on iOS/Android nodes.
+
+Quick check and fix:
+
+```bash
+quantumclaw nodes describe --node <idOrNameOrIp>
+quantumclaw nodes canvas snapshot --node <idOrNameOrIp>
+quantumclaw logs --follow
+```
+
+If you see `NODE_BACKGROUND_UNAVAILABLE`, bring the node app to the foreground and retry.
+
+## Permissions matrix
+
+| Capability                   | iOS                                     | Android                                      | macOS node app                | Typical failure code           |
+| ---------------------------- | --------------------------------------- | -------------------------------------------- | ----------------------------- | ------------------------------ |
+| `camera.snap`, `camera.clip` | Camera (+ mic for clip audio)           | Camera (+ mic for clip audio)                | Camera (+ mic for clip audio) | `*_PERMISSION_REQUIRED`        |
+| `screen.record`              | Screen Recording (+ mic optional)       | Screen capture prompt (+ mic optional)       | Screen Recording              | `*_PERMISSION_REQUIRED`        |
+| `location.get`               | While Using or Always (depends on mode) | Foreground/Background location based on mode | Location permission           | `LOCATION_PERMISSION_REQUIRED` |
+| `system.run`                 | n/a (node host path)                    | n/a (node host path)                         | Exec approvals required       | `SYSTEM_RUN_DENIED`            |
+
+## Pairing versus approvals
+
+These are different gates:
+
+1. **Device pairing**: can this node connect to the gateway?
+2. **Exec approvals**: can this node run a specific shell command?
+
+Quick checks:
+
+```bash
+quantumclaw devices list
+quantumclaw nodes status
+quantumclaw approvals get --node <idOrNameOrIp>
+quantumclaw approvals allowlist add --node <idOrNameOrIp> "/usr/bin/uname"
+```
+
+If pairing is missing, approve the node device first.
+If pairing is fine but `system.run` fails, fix exec approvals/allowlist.
+
+## Common node error codes
+
+- `NODE_BACKGROUND_UNAVAILABLE` → app is backgrounded; bring it foreground.
+- `CAMERA_DISABLED` → camera toggle disabled in node settings.
+- `*_PERMISSION_REQUIRED` → OS permission missing/denied.
+- `LOCATION_DISABLED` → location mode is off.
+- `LOCATION_PERMISSION_REQUIRED` → requested location mode not granted.
+- `LOCATION_BACKGROUND_UNAVAILABLE` → app is backgrounded but only While Using permission exists.
+- `SYSTEM_RUN_DENIED: approval required` → exec request needs explicit approval.
+- `SYSTEM_RUN_DENIED: allowlist miss` → command blocked by allowlist mode.
+  On Windows node hosts, shell-wrapper forms like `cmd.exe /c ...` are treated as allowlist misses in
+  allowlist mode unless approved via ask flow.
+
+## Fast recovery loop
+
+```bash
+quantumclaw nodes status
+quantumclaw nodes describe --node <idOrNameOrIp>
+quantumclaw approvals get --node <idOrNameOrIp>
+quantumclaw logs --follow
+```
+
+If still stuck:
+
+- Re-approve device pairing.
+- Re-open node app (foreground).
+- Re-grant OS permissions.
+- Recreate/adjust exec approval policy.
+
+Related:
+
+- [/nodes/index](/nodes/index)
+- [/nodes/camera](/nodes/camera)
+- [/nodes/location-command](/nodes/location-command)
+- [/tools/exec-approvals](/tools/exec-approvals)
+- [/gateway/pairing](/gateway/pairing)

package/docs/nodes/voicewake.md

@@ -0,0 +1,66 @@
+---
+summary: "Global voice wake words (Gateway-owned) and how they sync across nodes"
+read_when:
+  - Changing voice wake words behavior or defaults
+  - Adding new node platforms that need wake word sync
+title: "Voice Wake"
+---
+
+# Voice Wake (Global Wake Words)
+
+QuantumClaw treats **wake words as a single global list** owned by the **Gateway**.
+
+- There are **no per-node custom wake words**.
+- **Any node/app UI may edit** the list; changes are persisted by the Gateway and broadcast to everyone.
+- macOS and iOS keep local **Voice Wake enabled/disabled** toggles (local UX + permissions differ).
+- Android currently keeps Voice Wake off and uses a manual mic flow in the Voice tab.
+
+## Storage (Gateway host)
+
+Wake words are stored on the gateway machine at:
+
+- `~/.quantumclaw/settings/voicewake.json`
+
+Shape:
+
+```json
+{ "triggers": ["quantumclaw", "claude", "computer"], "updatedAtMs": 1730000000000 }
+```
+
+## Protocol
+
+### Methods
+
+- `voicewake.get` → `{ triggers: string[] }`
+- `voicewake.set` with params `{ triggers: string[] }` → `{ triggers: string[] }`
+
+Notes:
+
+- Triggers are normalized (trimmed, empties dropped). Empty lists fall back to defaults.
+- Limits are enforced for safety (count/length caps).
+
+### Events
+
+- `voicewake.changed` payload `{ triggers: string[] }`
+
+Who receives it:
+
+- All WebSocket clients (macOS app, WebChat, etc.)
+- All connected nodes (iOS/Android), and also on node connect as an initial “current state” push.
+
+## Client behavior
+
+### macOS app
+
+- Uses the global list to gate `VoiceWakeRuntime` triggers.
+- Editing “Trigger words” in Voice Wake settings calls `voicewake.set` and then relies on the broadcast to keep other clients in sync.
+
+### iOS node
+
+- Uses the global list for `VoiceWakeManager` trigger detection.
+- Editing Wake Words in Settings calls `voicewake.set` (over the Gateway WS) and also keeps local wake-word detection responsive.
+
+### Android node
+
+- Voice Wake is currently disabled in Android runtime/Settings.
+- Android voice uses manual mic capture in the Voice tab instead of wake-word triggers.