let5see/clawdbot

Fork 0

Files

Peter Steinberger c69947dff8 feat: auto-enable audio understanding when keys exist

2026-01-18 14:55:09 +00:00

9.1 KiB

Raw Blame History

summary, read_when

summary

read_when

Inbound image/audio/video understanding (optional) with provider + CLI fallbacks

Designing or refactoring media understanding

Tuning inbound audio/video/image preprocessing

Media Understanding (Inbound) — 2026-01-17

Clawdbot can optionally summarize inbound media (image/audio/video) before the reply pipeline runs. This is opt-in and separate from the base attachment flow—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

Collect inbound attachments (MediaPaths, MediaUrls, MediaTypes).
For each enabled capability (image/audio/video), select attachments per policy (default: first).
Choose the first eligible model entry (size + capability + auth).
If a model fails or the media is too large, fall back to the next entry.
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
- 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 */ },
      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"]
}

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.
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, Clawdbot tries the active reply model when its provider supports the capability.

Auto-enable audio (when keys exist)

If tools.media.audio.enabled is not set to false and you have any supported audio provider keys configured, Clawdbot will auto-enable audio transcription even when you haven’t listed models explicitly.

Providers checked (in order):

OpenAI
Groq
Deepgram

To disable this behavior, set:

{
  tools: {
    media: {
      audio: {
        enabled: false
      }
    }
  }
}

Capabilities (optional)

If you set capabilities, the entry only runs for those media types. For shared lists, Clawdbot 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 (Clawdbot 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	Provider transcription (Whisper/Deepgram).
Video	Google (Gemini API)	Provider video understanding.

Recommended providers

Image

Prefer your active model if it supports images.
Good defaults: openai/gpt-5.2, anthropic/claude-opus-4-5, google/gemini-3-pro-preview.

Audio

openai/whisper-1, groq/whisper-large-v3-turbo, or deepgram/nova-3.
CLI fallback: whisper binary.
Deepgram setup: Deepgram (audio transcription).

Video

google/gemini-3-flash-preview (fast), google/gemini-3-pro-preview (richer).
CLI fallback: gemini CLI (supports read_file on video/audio).

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: "whisper-1" },
          {
            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-4-5" },
          {
            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).

9.1 KiB Raw Blame History Unescape Escape