Receive images in WhatsApp batches

[onechat] / compactor.go

diff --git a/compactor.go b/compactor.go
index 8a16c6e8da18d3ff39ea07eed762e7bc57ee7f4d..2b239015ce763f56d1a23a4621647f056023b07b 100644 (file)
--- a/compactor.go
+++ b/compactor.go
@@ -4,7 +4,6 @@ import (
        "context"
        "errors"
        "fmt"
-       "slices"
        "strings"
        "unicode/utf8"
 )
@@ -20,12 +19,13 @@ var compactorRuler = strings.Repeat("-", nodeBytes)
 // client with model. instructions gives the system prompt of the agent at each
 // build. tools are the tools of that agent, so a build sends the same prompt
 // and tools as its turns.
-func newCompactor(client *ModelClient, instructions func() (string, error), model ModelConfig, tools []ModelTool) *Compactor {
+func newCompactor(client *ModelClient, instructions func() (string, error), model ModelConfig, tools []ModelTool, images *ImageStore) *Compactor {
        return &Compactor{
                client:       client,
                model:        model,
                instructions: instructions,
                tools:        tools,
+               images:       images,
        }
 }
 
@@ -37,17 +37,19 @@ func newCompactor(client *ModelClient, instructions func() (string, error), mode
 //
 // When the line is over nodeBytes, the next try sends the same message, plus
 // one more user message with a note with the size of the newest line and its
-// cut at the limit. A try never sends the model's earlier reply or reasoning
-// back, so every try begins with the same view and task and has about the same
-// size. After at most compactorTries tries, the shortest line is the node. A
-// few bytes over the limit is fine, because the view measures the real sizes. A
-// call that fails before any line fails the build, and the core tries it again
-// at the next message.
+// cut at the limit. Only the first call of an image leaf sends its pixels. A
+// try never sends the model's earlier reply or reasoning back, so every try
+// begins with the same view and task and has about the same size. After at most
+// compactorTries tries, the shortest line is the node. A few bytes over the
+// limit is fine, because the view measures the real sizes. A call that fails
+// before any line fails the build, and the core tries it again at the next
+// message.
 type Compactor struct {
        client       *ModelClient
        model        ModelConfig
        instructions func() (string, error)
        tools        []ModelTool
+       images       *ImageStore
 }
 
 // Summarize returns the line of the node of task.
@@ -62,7 +64,13 @@ func (c *Compactor) Summarize(ctx context.Context, task Task) (string, error) {
                return "", err
        }
 
-       first := []any{modelUserMessage(task.Context + "\n" + text)}
+       source := task.Context + "\n" + text
+       parts, err := imageParts(c.images, source, task.Images)
+       if err != nil {
+               return "", fmt.Errorf("read compaction images: %w", err)
+       }
+
+       first := []any{modelUserParts(parts)}
 
        var lines []string
 
@@ -70,7 +78,7 @@ func (c *Compactor) Summarize(ctx context.Context, task Task) (string, error) {
        for len(lines) < compactorTries {
                input := first
                if note != "" {
-                       input = append(slices.Clip(first), modelUserMessage(note))
+                       input = []any{modelUserMessage(source), modelUserMessage(note)}
                }
 
                var response ModelResponse
@@ -111,12 +119,17 @@ func (c *Compactor) Summarize(ctx context.Context, task Task) (string, error) {
 // compactorTask returns the task of a build, with its input.
 func compactorTask(task Task) (string, error) {
        if task.Level == 0 && len(task.Input) == 1 {
-               return fmt.Sprintf(`Compaction: compress message %d into one line of at most %d bytes
+               text := fmt.Sprintf(`Compaction: compress message %d into one line of at most %d bytes
 (about 70 words), the length of this ruler:
 %s
 <input>
 %s
-</input>`, task.Index, nodeBytes, compactorRuler, task.Input[0]), nil
+</input>`, task.Index, nodeBytes, compactorRuler, task.Input[0])
+               if len(task.Images) > 0 {
+                       text += "\nKeep each [image FILE] name and describe its kind, visible text, amounts, names, and context."
+               }
+
+               return text, nil
        }
 
        if task.Level > 0 && len(task.Input) == 2 {