X-Git-Url: https://git.giacomolli.uk/onechat/blobdiff_plain/522d7fd117285e4e4ce3ea5ec9b5a1722521b681..59948b44c0fe2165b90e3aa0d18646f6c3d74af3:/model.go?ds=inline

diff --git a/model.go b/model.go
index 507fbb1..cc77f9a 100644
--- a/model.go
+++ b/model.go
@@ -41,9 +41,9 @@ const (
 var errModelCallLimit = errors.New("call limit reached")
 
 // modelEndpoint returns the URL and the authorizer of the endpoint in config.
-// The ChatGPT backend uses the token file in dir. The OpenAI API uses the key in
-// OPENAI_API_KEY, and there is no fallback from one to the other. All clients
-// share the authorizer, so one refresh runs at a time.
+// The ChatGPT backend uses the token file in dir. The OpenAI API uses the key
+// in OPENAI_API_KEY, and there is no fallback from one to the other. All
+// clients share the authorizer, so one refresh runs at a time.
 func modelEndpoint(config Config, dir string) (string, ModelAuthorizer, error) {
 	if config.Endpoint == configEndpointAPI {
 		key := os.Getenv("OPENAI_API_KEY")
@@ -73,22 +73,22 @@ func newModelClient(url string, auth ModelAuthorizer, cacheKey, usagePath string
 
 // modelUserMessage returns a user input item with one text part for each text.
 func modelUserMessage(texts ...string) any {
-	type part struct {
-		Type string `json:"type"`
-		Text string `json:"text"`
-	}
-
-	content := make([]part, len(texts))
+	content := make([]ModelInputPart, len(texts))
 	for n, text := range texts {
-		content[n] = part{
+		content[n] = ModelInputPart{
 			Type: "input_text",
 			Text: text,
 		}
 	}
 
+	return modelUserParts(content)
+}
+
+// modelUserParts keeps text and image parts in one user message.
+func modelUserParts(content []ModelInputPart) any {
 	return struct {
-		Role    string `json:"role"`
-		Content []part `json:"content"`
+		Role    string           `json:"role"`
+		Content []ModelInputPart `json:"content"`
 	}{
 		Role:    "user",
 		Content: content,
@@ -321,6 +321,13 @@ type ModelOutputItem struct {
 	} `json:"content"`
 }
 
+// ModelInputPart is a text or image part in a user message or tool result.
+type ModelInputPart struct {
+	Type     string `json:"type"`
+	Text     string `json:"text,omitempty"`
+	ImageURL string `json:"image_url,omitempty"`
+}
+
 // ModelRequest is one model call. Input holds the input items in order, such as
 // modelUserMessage values or output items of an earlier response. Node names
 // the node that a compaction builds, or is nil. Turn names the request of a