X-Git-Url: https://git.giacomolli.uk/onechat/blobdiff_plain/723f6e18adc6482ed913e1618c8a76e981720c2b..c781f79f3c8cb9a7577ee1574d196988da2719b3:/prompt.go?ds=sidebyside

diff --git a/prompt.go b/prompt.go
index 36fda32..0571ecf 100644
--- a/prompt.go
+++ b/prompt.go
@@ -34,17 +34,14 @@ const (
 	promptInstructionsHeading = "\n\n# The user's instructions\n\n"
 )
 
-// promptEfforts are the reasoning efforts that spawn can give a subagent.
-var promptEfforts = []string{"low", "medium", "high", "xhigh"}
-
 // promptText is the system prompt of the reference, nearly word for word, with
 // one added paragraph on the user's instructions file. The reference names its
 // own agent, so promptText has the name of the agent and the kind reply in its
 // place. It describes only what OneChat can do, so it leaves out the spec text
-// on images, computers, and computer tasks. Its paragraph on persistent mode
-// tells the model that a final answer ends the turn. prompt adds the clause on
-// the instructions of the user only when there are instructions. It holds no
-// date and no state, so turns and compactions share its prompt cache.
+// on computers and computer tasks. Its paragraph on persistent mode tells the
+// model that a final answer ends the turn. prompt adds the clause on the
+// instructions of the user only when there are instructions. It holds no date
+// and no state, so turns and compactions share its prompt cache.
 const promptText = `You are {name}, an AI agent that works for one user in a single chat that never
 ends. Each call to you is a turn or a compaction: the view below is followed by
 the user's new message, or by a task starting "Compaction:".
@@ -76,6 +73,9 @@ Tools:
 - zoom("Name") gives an agent's whole chat
 - date(id) gives the date and time of message id
 
+An [image FILE] line names a stored image. New images include pixels for this
+turn only. Use zoom(id, 1) to see an older image again.
+
 # Turns
 
 Do the user's tasks yourself, with your tools.
@@ -151,14 +151,16 @@ Pass area messages from mixed chats to the right child with sender, date, and
 words. Never send a WhatsApp reply drafted by a child without the user's
 agreement.
 Propose routing a source that talks only about one area to its child.
-Set or remove a route only after the user agrees.`
+Set or remove a route only after the user agrees.
+Use image_show or whatsapp_send with an image only on the user's request.
+Pass an image to a child with an [image FILE] line in tell.`
 
 // promptSubagentText is the system prompt of a subagent, from the subagent
 // prompt of the reference design: its head, then the doc of the view, without
-// the parts on devices and images. A subagent gets the view of the agent, then
-// its whole log, so it goes on from its log after a tell or a restart.
-// promptSubagent adds the clause on the instructions of the user only when
-// there are instructions.
+// the parts on devices. A subagent gets the view of the agent, then its whole
+// log, so it goes on from its log after a tell or a restart. promptSubagent
+// adds the clause on the instructions of the user only when there are
+// instructions.
 const promptSubagentText = `You are a subagent of {name}, an AI agent that works for one user in a single
 chat that never ends. {name} gave you a task. Do it yourself, with your tools.
 
@@ -189,7 +191,11 @@ was made from; zoom(id, 1) gives message id in full. Zoom whenever a summary
 only mentions something you need, such as what your last reply said, a
 decision, a past attempt or where a file is, before you act, guess or ask.
 date(id) gives the date and time of message id. zoom("Name") gives an agent's
-whole chat.`
+whole chat. An [image FILE] line names a stored image. Use zoom(id, 1)
+to see its pixels.`
+
+// promptEfforts are the reasoning efforts that spawn can give a subagent.
+var promptEfforts = []string{"low", "medium", "high", "xhigh"}
 
 // prompt returns the system prompt of the reference with one added paragraph on
 // the user's instructions file at instructionsPath. It uses the agent name and
@@ -217,6 +223,7 @@ message outside your area. Your final reply is your report to the parent.
 End your turn with an empty reply when nothing needs the parent or the user.
 Send nothing to WhatsApp. Draft replies in your report instead, so the parent
 can ask the user before sending.`, 1)
+
 	text = strings.Replace(text, promptChildrenText, "", 1)
 
 	return promptWithInstructions(text, "Do the tasks of your area yourself, with your tools.", promptInstructionsClause, instructions)
@@ -270,6 +277,15 @@ func promptTools() []ModelTool {
 			"message": promptStringSchema("The message."),
 		}),
 		Strict: true,
+	}, ModelTool{
+		Type:        "function",
+		Name:        "image_show",
+		Description: "Show a stored image to the user, only when the user asks to see it. Give its stored filename, not a path.",
+		Parameters: promptObjectSchema(map[string]any{
+			"image":   promptStringSchema("The stored image filename from an [image FILE] line."),
+			"caption": promptStringSchema("The caption, or an empty string."),
+		}),
+		Strict: true,
 	}, ModelTool{
 		Type:        "function",
 		Name:        "whatsapp_find",
@@ -281,11 +297,12 @@ func promptTools() []ModelTool {
 	}, ModelTool{
 		Type:        "function",
 		Name:        "whatsapp_send",
-		Description: "Send a text message to a WhatsApp chat. Send only a message that the user asked you to send, to the chat that the user named. Give a new id for each message: a call with an id that was used gives the answer of the first call and sends nothing.",
+		Description: "Send text or a stored image with text as its caption to a WhatsApp chat. Send only a message that the user asked you to send, to the chat that the user named. Give a new id for each message: a call with an id that was used gives the answer of the first call and sends nothing.",
 		Parameters: promptObjectSchema(map[string]any{
-			"id":   promptStringSchema("A new id for this message, such as a short random word."),
-			"chat": promptStringSchema("The ID of the chat, from whatsapp_find or from a [WhatsApp] message."),
-			"text": promptStringSchema("The text of the message."),
+			"id":    promptStringSchema("A new id for this message, such as a short random word."),
+			"chat":  promptStringSchema("The ID of the chat, from whatsapp_find or from a [WhatsApp] message."),
+			"text":  promptStringSchema("The text, or the caption when sending an image. Can be empty with an image."),
+			"image": promptNullableStringSchema("The stored image filename from an [image FILE] line, or null for text only."),
 		}),
 		Strict: true,
 	}, ModelTool{