docs: describe image input across the three surfaces

`doc/images.md` holds the message shape, how `@path` attaches a file, the
per-surface mapping, the provider limits, what a live probe against DeepSeek
confirmed (`tool_result` and `function_call_output` images work, `detail: low`
is 3.4x cheaper, an assistant-message image is a 400), and why the Files API is
not used.

AGENTS.md gets the invariants and the mention/config keys; `doc/architecture.md`
and the example TOML point at it.
This commit is contained in:
2026-10-21 18:52:14 +08:00
parent 154509b929
commit 029ac47350
4 changed files with 121 additions and 6 deletions
+2
View File
@@ -39,4 +39,6 @@
Plugins (third-party entry points, allowlisted under ``[plugins]``): [plugins.md](./plugins.md).
Conversation units (a *round* = one request→response plus its tool batch, a
*turn* = a user message to the explicit stop): [turns-and-rounds.md](./turns-and-rounds.md).
Images (a turn's pictures, a tool result's pictures, what each wire surface
takes): [images.md](./images.md).