fix(sdk): infer ToolResponse.Type for binary data in NewTool/NewParallelTool

- Infer Type="image" for image/* MIME types and Type="media" for all
  other binary content so the downstream framework creates a media
  content block instead of silently discarding Data bytes (#17)
- Extract shared toolOutputToResponse() helper to eliminate duplication
- Add ImageResult() and MediaResult() convenience constructors
- Add LLMToolCall and LLMToolResponse type aliases so SDK consumers
  can call Tool.Run() without importing the underlying framework
- Add 6 regression tests covering image, media, and text responses

Closes #17
This commit is contained in:
Ed Zynda
2026-04-22 16:58:07 +03:00
parent 3cfb6437f9
commit 61408ed490
6 changed files with 239 additions and 24 deletions
+22 -1
View File
@@ -646,7 +646,28 @@ host, _ := kit.New(ctx, &kit.Options{
})
```
Use `kit.NewParallelTool` for tools safe to run concurrently. See the [SDK docs](/sdk/overview) for full details on struct tags, `ToolOutput` fields, and `ToolCallIDFromContext`.
Use `kit.NewParallelTool` for tools safe to run concurrently. Binary data (images, audio, etc.) in `ToolOutput.Data` is automatically forwarded to the LLM when `MediaType` is set. See the [SDK docs](/sdk/overview) for full details on struct tags, `ToolOutput` fields, and `ToolCallIDFromContext`.
#### Return Helpers
| Helper | Description |
| --- | --- |
| `kit.TextResult(content)` | Successful text result |
| `kit.ErrorResult(content)` | Error result (LLM sees it as a tool error) |
| `kit.ImageResult(content, data, mediaType)` | Image result with binary data (e.g. `"image/png"`) |
| `kit.MediaResult(content, data, mediaType)` | Non-image media result (e.g. `"audio/mpeg"`) |
#### ToolOutput Fields
```go
kit.ToolOutput{
Content: "result text", // text returned to the LLM
IsError: false, // true = LLM sees this as an error
Data: pngBytes, // optional binary data (images, audio)
MediaType: "image/png", // MIME type for binary Data
Metadata: map[string]any{}, // opaque metadata for hooks/UI (not sent to LLM)
}
```
### With Callbacks
+52 -22
View File
@@ -2,6 +2,7 @@ package kit
import (
"context"
"strings"
"charm.land/fantasy"
@@ -52,6 +53,22 @@ func ErrorResult(content string) ToolOutput {
return ToolOutput{Content: content, IsError: true}
}
// ImageResult creates a [ToolOutput] that returns an image to the LLM.
// The data is the raw image bytes and mediaType is the MIME type
// (e.g. "image/png", "image/jpeg"). The optional text content accompanies
// the image and is visible to the LLM alongside it.
func ImageResult(content string, data []byte, mediaType string) ToolOutput {
return ToolOutput{Content: content, Data: data, MediaType: mediaType}
}
// MediaResult creates a [ToolOutput] that returns non-image binary media
// (e.g. audio, video) to the LLM. The data is the raw bytes and mediaType
// is the MIME type (e.g. "audio/wav", "video/mp4"). The optional text
// content accompanies the media.
func MediaResult(content string, data []byte, mediaType string) ToolOutput {
return ToolOutput{Content: content, Data: data, MediaType: mediaType}
}
// toolCallIDKey is the context key for the tool call ID.
type toolCallIDKey struct{}
@@ -63,9 +80,35 @@ func ToolCallIDFromContext(ctx context.Context) string {
return s
}
// toolOutputToResponse converts a [ToolOutput] into the underlying
// framework's ToolResponse, inferring the response Type from Data/MediaType
// so that binary content (images, audio, etc.) is forwarded to the LLM
// instead of being silently dropped.
func toolOutputToResponse(result ToolOutput) fantasy.ToolResponse {
resp := fantasy.ToolResponse{
Content: result.Content,
IsError: result.IsError,
Data: result.Data,
MediaType: result.MediaType,
}
// Infer response type from binary data so the downstream framework
// creates a media content block instead of a plain-text one.
if len(result.Data) > 0 && result.MediaType != "" {
if strings.HasPrefix(result.MediaType, "image/") {
resp.Type = "image"
} else {
resp.Type = "media"
}
}
if result.Metadata != nil {
resp = fantasy.WithResponseMetadata(resp, result.Metadata)
}
return resp
}
// NewTool creates a custom [Tool] with automatic JSON schema generation from
// the TInput struct type. The handler receives a typed input (deserialized
// from the LLM's JSON arguments) and returns a [ToolResult].
// from the LLM's JSON arguments) and returns a [ToolOutput].
//
// Struct tags on TInput control the generated schema:
//
@@ -77,6 +120,11 @@ func ToolCallIDFromContext(ctx context.Context) string {
// The tool call ID is injected into the context and can be retrieved with
// [ToolCallIDFromContext].
//
// Binary results: When [ToolOutput.Data] and [ToolOutput.MediaType] are set,
// the response type is automatically inferred so the LLM receives the binary
// content (e.g. an image) instead of only the text. Use [ImageResult] or
// [MediaResult] for convenience.
//
// Example:
//
// type WeatherInput struct {
@@ -84,7 +132,7 @@ func ToolCallIDFromContext(ctx context.Context) string {
// }
//
// tool := kit.NewTool("get_weather", "Get weather for a city",
// func(ctx context.Context, input WeatherInput) (kit.ToolResult, error) {
// func(ctx context.Context, input WeatherInput) (kit.ToolOutput, error) {
// return kit.TextResult("72°F, sunny in " + input.City), nil
// },
// )
@@ -96,16 +144,7 @@ func NewTool[TInput any](name, description string, fn func(ctx context.Context,
if err != nil {
return fantasy.NewTextErrorResponse(err.Error()), nil
}
resp := fantasy.ToolResponse{
Content: result.Content,
IsError: result.IsError,
Data: result.Data,
MediaType: result.MediaType,
}
if result.Metadata != nil {
resp = fantasy.WithResponseMetadata(resp, result.Metadata)
}
return resp, nil
return toolOutputToResponse(result), nil
},
)
}
@@ -121,16 +160,7 @@ func NewParallelTool[TInput any](name, description string, fn func(ctx context.C
if err != nil {
return fantasy.NewTextErrorResponse(err.Error()), nil
}
resp := fantasy.ToolResponse{
Content: result.Content,
IsError: result.IsError,
Data: result.Data,
MediaType: result.MediaType,
}
if result.Metadata != nil {
resp = fantasy.WithResponseMetadata(resp, result.Metadata)
}
return resp, nil
return toolOutputToResponse(result), nil
},
)
}
+146
View File
@@ -117,3 +117,149 @@ func TestToolOutput_BinaryData(t *testing.T) {
t.Errorf("MediaType = %q, want %q", r.MediaType, "image/png")
}
}
// TestImageResult verifies the ImageResult convenience constructor.
func TestImageResult(t *testing.T) {
data := []byte{0x89, 0x50, 0x4E, 0x47}
r := kit.ImageResult("here is the image", data, "image/png")
if r.Content != "here is the image" {
t.Errorf("Content = %q, want %q", r.Content, "here is the image")
}
if len(r.Data) != 4 {
t.Errorf("Data len = %d, want 4", len(r.Data))
}
if r.MediaType != "image/png" {
t.Errorf("MediaType = %q, want %q", r.MediaType, "image/png")
}
if r.IsError {
t.Error("ImageResult should not set IsError")
}
}
// TestMediaResult verifies the MediaResult convenience constructor.
func TestMediaResult(t *testing.T) {
data := []byte{0xFF, 0xFB, 0x90, 0x00}
r := kit.MediaResult("audio clip", data, "audio/mpeg")
if r.Content != "audio clip" {
t.Errorf("Content = %q, want %q", r.Content, "audio clip")
}
if len(r.Data) != 4 {
t.Errorf("Data len = %d, want 4", len(r.Data))
}
if r.MediaType != "audio/mpeg" {
t.Errorf("MediaType = %q, want %q", r.MediaType, "audio/mpeg")
}
if r.IsError {
t.Error("MediaResult should not set IsError")
}
}
// TestNewTool_BinaryImageResponse verifies that NewTool correctly infers the
// response type for image data so binary content is forwarded to the LLM
// (issue #17).
func TestNewTool_BinaryImageResponse(t *testing.T) {
type Input struct {
Path string `json:"path"`
}
imgData := []byte{0x89, 0x50, 0x4E, 0x47} // PNG magic bytes
tool := kit.NewTool("read_image", "Read an image file",
func(ctx context.Context, input Input) (kit.ToolOutput, error) {
return kit.ImageResult("Here is the image", imgData, "image/png"), nil
},
)
// Run the tool and inspect the raw ToolResponse via the AgentTool interface.
resp, err := tool.Run(context.Background(), kit.LLMToolCall{
ID: "call_1",
Name: "read_image",
Input: `{"path": "test.png"}`,
})
if err != nil {
t.Fatalf("Run() error: %v", err)
}
// The Type field must be "image" so the downstream framework creates a
// media content block instead of discarding the binary data.
if resp.Type != "image" {
t.Errorf("ToolResponse.Type = %q, want %q", resp.Type, "image")
}
if len(resp.Data) != 4 {
t.Errorf("ToolResponse.Data len = %d, want 4", len(resp.Data))
}
if resp.MediaType != "image/png" {
t.Errorf("ToolResponse.MediaType = %q, want %q", resp.MediaType, "image/png")
}
if resp.Content != "Here is the image" {
t.Errorf("ToolResponse.Content = %q, want %q", resp.Content, "Here is the image")
}
}
// TestNewTool_BinaryMediaResponse verifies type inference for non-image media.
func TestNewTool_BinaryMediaResponse(t *testing.T) {
type Input struct{}
tool := kit.NewTool("get_audio", "Get audio",
func(ctx context.Context, input Input) (kit.ToolOutput, error) {
return kit.MediaResult("audio clip", []byte{0xFF, 0xFB}, "audio/mpeg"), nil
},
)
resp, err := tool.Run(context.Background(), kit.LLMToolCall{
ID: "call_2",
Name: "get_audio",
Input: `{}`,
})
if err != nil {
t.Fatalf("Run() error: %v", err)
}
if resp.Type != "media" {
t.Errorf("ToolResponse.Type = %q, want %q", resp.Type, "media")
}
}
// TestNewTool_TextResponseTypeNotSet verifies that text-only responses do NOT
// get an inferred type (preserving existing behavior).
func TestNewTool_TextResponseTypeNotSet(t *testing.T) {
type Input struct{}
tool := kit.NewTool("echo", "Echo",
func(ctx context.Context, input Input) (kit.ToolOutput, error) {
return kit.TextResult("hello"), nil
},
)
resp, err := tool.Run(context.Background(), kit.LLMToolCall{
ID: "call_3", Name: "echo", Input: `{}`,
})
if err != nil {
t.Fatalf("Run() error: %v", err)
}
// Text responses should not have Type set (the framework treats "" as text).
if resp.Type != "" {
t.Errorf("ToolResponse.Type = %q, want empty string for text responses", resp.Type)
}
}
// TestNewParallelTool_BinaryImageResponse mirrors the NewTool binary test for
// NewParallelTool.
func TestNewParallelTool_BinaryImageResponse(t *testing.T) {
type Input struct{}
tool := kit.NewParallelTool("snap", "Take a snapshot",
func(ctx context.Context, input Input) (kit.ToolOutput, error) {
return kit.ImageResult("snapshot", []byte{0xFF, 0xD8}, "image/jpeg"), nil
},
)
resp, err := tool.Run(context.Background(), kit.LLMToolCall{
ID: "call_4", Name: "snap", Input: `{}`,
})
if err != nil {
t.Fatalf("Run() error: %v", err)
}
if resp.Type != "image" {
t.Errorf("ToolResponse.Type = %q, want %q", resp.Type, "image")
}
}
+12
View File
@@ -157,6 +157,18 @@ type LLMTextPart = fantasy.TextPart
// LLMReasoningPart is a reasoning/chain-of-thought content part.
type LLMReasoningPart = fantasy.ReasoningPart
// LLMToolCall represents the raw tool invocation passed to a [Tool]'s Run
// method. It carries the call ID, tool name, and the JSON-encoded input
// arguments from the LLM. This is the execution-layer call object — distinct
// from [ToolCall] (a message content part).
type LLMToolCall = fantasy.ToolCall
// LLMToolResponse represents the raw response returned from a [Tool]'s Run
// method. Most SDK consumers should use [ToolOutput] with [NewTool] /
// [NewParallelTool] instead — this alias is provided for advanced use cases
// that need to call Tool.Run() directly (e.g. testing).
type LLMToolResponse = fantasy.ToolResponse
// LLMToolCallPart represents an LLM-initiated tool invocation within a message.
type LLMToolCallPart = fantasy.ToolCallPart
+4
View File
@@ -493,6 +493,8 @@ host, _ := kit.New(ctx, &kit.Options{
|----------|-------------|
| `kit.TextResult(content)` | Successful text result |
| `kit.ErrorResult(content)` | Error result (LLM sees it as a tool error) |
| `kit.ImageResult(content, data, mediaType)` | Image result with binary data (e.g. `"image/png"`) |
| `kit.MediaResult(content, data, mediaType)` | Non-image media result (e.g. `"audio/mpeg"`) |
**ToolOutput fields** (for advanced use):
@@ -1095,6 +1097,8 @@ kit.LLMUsage // {InputTokens, OutputTokens, TotalTokens, ReasoningTokens,
// CacheCreationTokens, CacheReadTokens}
kit.LLMResponse // {Content, FinishReason, Usage}
kit.LLMFilePart // {Filename, Data []byte, MediaType}
kit.LLMToolCall // {ID, Name, Input string} — execution-layer tool call (for Tool.Run)
kit.LLMToolResponse // {Type, Content, Data, MediaType, IsError, ...} — raw tool response
// Compaction types
kit.CompactionResult, kit.CompactionOptions
+3 -1
View File
@@ -101,8 +101,10 @@ Return values:
|--------|-------------|
| `kit.TextResult(s)` | Successful text result |
| `kit.ErrorResult(s)` | Error result (LLM sees it as a tool error) |
| `kit.ImageResult(s, data, mediaType)` | Image result with binary data (e.g. `"image/png"`) |
| `kit.MediaResult(s, data, mediaType)` | Non-image media result (e.g. `"audio/mpeg"`) |
For advanced use, return a `kit.ToolOutput` struct directly with `Data`, `MediaType`, and `Metadata` fields.
Binary data (images, audio, etc.) in `ToolOutput.Data` is automatically forwarded to the LLM when `MediaType` is set. For advanced use, return a `kit.ToolOutput` struct directly with `Data`, `MediaType`, and `Metadata` fields.
Use `kit.NewParallelTool` for tools that are safe to run concurrently. Use `kit.ToolCallIDFromContext(ctx)` to retrieve the LLM-assigned call ID for logging or tracing.