v0.7.0: image input, model registry, prefix-cache savings

Images
- vision gate: text-only models get a note instead of image parts and no
  view_image tool; unknown models retry once without images on HTTP 400
- paste: Ctrl+V and /attach paste read the clipboard (wl-paste, xclip,
  pngpaste/osascript, Win32 PNG or CF_DIB converted to PNG); pasting image
  file paths attaches them
- MCP image content is stored in the session and sent with the tool result
- attach: rel path validation, base64 decode, /retry keeps images

Model registry
- built-in src/models_builtin.json embedded at build time, merged with
  <config>/models.json and cached GET /models metadata (context, vision,
  pricing); most specific rule wins per field
- /model labels, /status source, --list-models [provider]

Cache and cost
- stable request prefix (frozen tools, notes as messages), DeepSeek prefix
  completion, OpenAI/Anthropic cache hints, /cost and hit rate in the status

src/tools/tools_internal.h

@@ -48,6 +48,8 @@ int cst_tool_ask_user(const cst_tool_ctx_t *ctx, const ctl_tool_call_t *c,
                       cst_tool_result_t *r);
 int cst_tool_web_fetch(const cst_tool_ctx_t *ctx, const ctl_tool_call_t *c,
                        cst_tool_result_t *r);
+int cst_tool_view_image(const cst_tool_ctx_t *ctx, const ctl_tool_call_t *c,
+                        cst_tool_result_t *r);
 
 int cst_preview_write_file(const cst_tool_ctx_t *ctx,
                            const ctl_tool_call_t *c, char **out);