diff options
Diffstat (limited to 'GLOSSARY.md')
| -rw-r--r-- | GLOSSARY.md | 2 |
1 files changed, 2 insertions, 0 deletions
diff --git a/GLOSSARY.md b/GLOSSARY.md index 4ca083c..26d3844 100644 --- a/GLOSSARY.md +++ b/GLOSSARY.md @@ -30,6 +30,8 @@ | **vision** (capability) | Whether a model can natively accept image input (multimodal). On the wire as `ModelMetadata.vision?: boolean` (`GET /models` `modelInfo[name].vision`). `true` (e.g. any `kimi/*` model) → image chunks are passed through to the provider natively. Absent/`false` (e.g. `umans/glm-5.2`) → the server's **vision handoff** gives the model a numbered placeholder + the `consult_vision` tool. The FE shows a vision badge in the model picker; it does NOT decide handoff (server-owned). | multimodal, image support | | **vision handoff** | The server-owned mechanism by which a NON-vision model still reasons about a pasted image. A non-vision model gets a NUMBERED PLACEHOLDER text chunk alongside the persisted `image` chunk, then calls the `consult_vision` tool (which opens a NEW conversation tab with a vision-capable model, attaches the image + question, and returns the vision model's answer). The persisted user message keeps the original `image` chunk (the FE renders it) AND the placeholder text. When a vision-capable model has more than `imageLimit` images in history, image **compaction** transcribes the oldest to `[Compacted image]: <description>` text chunks (the `image` chunk stays for rendering). All these are regular `text` chunks — the FE renders them as-is. Distinct from a vision-capable model, which receives the image natively. | image transcription, vision relay | | **consult_vision** | A tool available to all models that defers image analysis to a vision-capable model: it opens a NEW conversation tab (with a vision model, e.g. Kimi), attaches the image (by `imageIds` from a pasted placeholder, or by `path` from disk) + a `question`, and returns the conversation id + the vision model's answer (suggesting the dispatch CLI for follow-ups). Replaces the former `read_image` tool. Rendered generically like any tool call/result (by `toolName`). | read_image (former), vision tool | +| **Named Agent** | A user-curated, persisted model preset: a friendly `name` bound to one canonical `<provider-or-credential>/<model>` identifier (`NamedAgent` = `{ id, name, model }`). NOT a running agent or conversation — it is configuration. Editable in a sidebar view; drives the synthetic "Named Agents" provider in the model picker + the `list_agent_models`/`summon_agent` agent tools. Global user config (not per-workspace). | preset, model shortcut, aliased model | +| **Named Agent snapshot** | The `NamedAgentSelectionSnapshot` (`{ namedAgentId, namedAgentName, model }`) a conversation retains when it was selected via a Named Agent. `model` is the raw provider/model the conversation uses; the id/name freeze HOW it was selected so later edits/removal of the shared Named Agent do NOT retroactively change an existing conversation (plan §7). Absent for a raw-model selection. | frozen selection, selection record | ## Frontend-specific | Term | Meaning | Aliases to avoid | |