bot/docs/nodes/media-understanding.md

summary, read_when, title

summary	read_when	title
Inbound image/audio/video understanding (optional) with provider + CLI fallbacks	Designing or refactoring media understanding Tuning inbound audio/video/image preprocessing	Media Understanding

Media Understanding (Inbound) — 2026-01-17

HanzoBot 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.

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).

{
  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:

{
  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",
}

{
  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, HanzoBot 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, HanzoBot 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:

{
  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, HanzoBot 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, HanzoBot 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, HanzoBot can infer defaults:

• openai, anthropic, minimax: image
• google (Gemini API): image + audio + video
• 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 (HanzoBot integrations)

Capability	Provider integration	Notes
Image	OpenAI / Anthropic / Google / others via pi-ai	Any image-capable model in the registry works.
Audio	OpenAI, Groq, Deepgram, Google, Mistral	Provider transcription (Whisper/Deepgram/Gemini/Voxtral).
Video	Google (Gemini API)	Provider video understanding.

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, HanzoBot 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

{
  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)

{
  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

{
  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)

{
  tools: {
    media: {
      image: {
        models: [
          {
            provider: "google",
            model: "gemini-3-pro-preview",
            capabilities: ["image", "video", "audio"],
          },
        ],
      },
      audio: {
        models: [
          {
            provider: "google",
            model: "gemini-3-pro-preview",
            capabilities: ["image", "video", "audio"],
          },
        ],
      },
      video: {
        models: [
          {
            provider: "google",
            model: "gemini-3-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
• Image & Media Support