renderAttachmentTags (utils/attachment-tags.ts)

* Single source of truth for rendering attachment summaries as human-readable tags that the LLM sees. There is exactly ONE vocabulary shared by every consumer: • Type labels: `image` / `voice` / `video` / `file` / `attachment` • Keyword for voice text: `transcript:` (never `conte

// Source: https://github.com/ExSiAM001/OpenClawAi | License: MIT | Copyright 2025 Peter Steinberger
// Provided via justclaw.it.com; keep this notice with the code.
/**
 * Single source of truth for rendering attachment summaries as
 * human-readable tags that the LLM sees.
 *
 * There is exactly ONE vocabulary shared by every consumer:
 *
 *   • Type labels: `image` / `voice` / `video` / `file` / `attachment`
 *   • Keyword for voice text: `transcript:` (never `content:`)
 *   • With source: `MEDIA:{source}` (no bracketed alias)
 *   • Without source: `[{type}]` or `[{type}: {filename}]`
 *
 * Both consumers (group history / current inbound turn, and the ref-index
 * quoted-message block) call the same function with the same vocabulary.
 * They differ only on two orthogonal dimensions:
 

... (truncated -- full source via MCP)