Files
picoclaw/pkg/tools/fs/load_image_test.go
T
Guoguo cb1e1a3595 fix(feishu): fix image download with API fallback and post image support (#2708)
* fix(feishu): fix image download with API fallback and post image support

- Add Image.Get API fallback when MessageResource.Get fails (different
  permission scope: im:resource vs im:message:readonly)
- Extract and download images from post (rich text) messages
- Extract images from interactive card messages
- Deduplicate post image keys across locales
- Add comprehensive tests for new helpers

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* feat(media): add image path tags alongside base64 for LLM file access

Images are still base64-encoded into msg.Media for multimodal LLMs,
but now also get [image:path] tags injected into message content so
the LLM knows the local file path for save/forward operations.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* refactor(media): only auto-inject images for tool results, not user messages

Channel-received images (role=user) now get path tags only, letting
the LLM decide whether to view via load_image or just operate on
the file. Tool result images (role=tool, e.g. load_image) are
base64-encoded into a synthetic user message appended after the tool
message, since many LLM APIs don't support image_url in tool messages.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* fix(media): preserve tool-message ordering for multi-tool-call scenarios

Move synthetic user message (carrying base64 tool images) to after the
entire contiguous tool-message block instead of immediately after each
tool message. This preserves the assistant→tool→tool ordering required
by OpenAI-compatible APIs.

Also fix load_image to use generic [image: photo] placeholder so
injectPathTags can properly replace it with the actual path.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* fix(test): update load_image test for [image: photo] placeholder

The test was checking ForLLM for the media:// ref, but load_image now
emits the generic [image: photo] placeholder instead.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* fix(media): match all channel image placeholders in injectPathTags

Different channels emit different placeholder formats — Telegram/Feishu
use [image: photo], WeCom/WeChat/Line use bare [image], QQ/Discord use
[image: <filename>]. The previous string-match code only handled
[image: photo], so for the other channels the path tag was appended as
a duplicate, producing content like "[image] [image:/path]".

Switch to per-type regex that matches all generic placeholder shapes
while leaving path tags ([image:/path]) untouched. Also fixes the same
issue for [audio], [video], [file] tags. Added test coverage for the
various placeholder shapes.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* fix(media): skip path tag append for JSON content (Feishu cards/posts)

When content is structured JSON (interactive cards, post messages),
injectPathTags now skips the fallback append — only placeholder
replacement is attempted. This prevents corrupting JSON payloads
like {"schema":"2.0",...} with appended [image:/path] tags.

Adds looksLikeJSON() helper and three test cases covering JSON
objects, arrays, and an end-to-end resolveMediaRefs scenario with
Feishu card content.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* fix(media): prepend path tags for JSON content, narrow looksLikeJSON

Two fixes from code review:

1. looksLikeJSON now only checks for '{' prefix (not '['), avoiding
   false positives on regular text like "[update] see attached".

2. For JSON content (Feishu cards/posts), path tags are prepended
   before the JSON instead of being silently dropped. This ensures
   the LLM can discover attached images via the path tag while the
   JSON payload stays valid for downstream parsing.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
2026-04-30 11:08:00 +08:00

153 lines
5.0 KiB
Go

package fstools
import (
"context"
"os"
"path/filepath"
"strings"
"testing"
"github.com/sipeed/picoclaw/pkg/config"
"github.com/sipeed/picoclaw/pkg/media"
)
func TestLoadImage_PathRequired(t *testing.T) {
tool := NewLoadImageTool("/tmp", false, 0, nil)
ctx := WithToolContext(context.Background(), "test", "chat1")
result := tool.Execute(ctx, map[string]any{})
if !result.IsError {
t.Fatal("expected error for missing path")
}
}
func TestLoadImage_NilMediaStore(t *testing.T) {
tool := NewLoadImageTool("/tmp", false, 0, nil)
ctx := WithToolContext(context.Background(), "test", "chat1")
result := tool.Execute(ctx, map[string]any{"path": "test.png"})
if !result.IsError || result.ForLLM != "media store not configured" {
t.Fatalf("expected media store error, got: %s", result.ForLLM)
}
}
func TestLoadImage_NoChannelContext(t *testing.T) {
store := media.NewFileMediaStore()
tool := NewLoadImageTool("/tmp", false, 0, store)
// No WithToolContext — should fail
result := tool.Execute(context.Background(), map[string]any{"path": "test.png"})
if !result.IsError || result.ForLLM != "no target channel/chat available" {
t.Fatalf("expected channel error, got: %s", result.ForLLM)
}
}
func TestLoadImage_NonImageFile(t *testing.T) {
dir := t.TempDir()
txtFile := filepath.Join(dir, "readme.txt")
os.WriteFile(txtFile, []byte("hello"), 0o644)
store := media.NewFileMediaStore()
tool := NewLoadImageTool(dir, false, 0, store)
ctx := WithToolContext(context.Background(), "test", "chat1")
result := tool.Execute(ctx, map[string]any{"path": txtFile})
if !result.IsError {
t.Fatal("expected error for non-image file")
}
}
func TestLoadImage_DefaultMaxSize(t *testing.T) {
tool := NewLoadImageTool("/tmp", false, 0, nil)
if tool.maxFileSize != config.DefaultMaxMediaSize {
t.Errorf("expected default max size %d, got %d", config.DefaultMaxMediaSize, tool.maxFileSize)
}
}
func TestLoadImage_FileTooLarge(t *testing.T) {
dir := t.TempDir()
bigFile := filepath.Join(dir, "big.png")
// Create a file with PNG header but exceeding max size
data := make([]byte, 1024)
copy(data, []byte{0x89, 0x50, 0x4E, 0x47}) // PNG magic bytes
os.WriteFile(bigFile, data, 0o644)
store := media.NewFileMediaStore()
tool := NewLoadImageTool(dir, false, 512, store) // maxSize = 512
ctx := WithToolContext(context.Background(), "test", "chat1")
result := tool.Execute(ctx, map[string]any{"path": bigFile})
if !result.IsError {
t.Fatal("expected error for oversized file")
}
}
func TestLoadImage_SuccessPath(t *testing.T) {
dir := t.TempDir()
// Create a minimal valid PNG file (8-byte signature + minimal IHDR + IEND).
// The PNG spec requires the 8-byte magic header: 0x89 P N G \r \n 0x1a \n
pngSignature := []byte{0x89, 0x50, 0x4E, 0x47, 0x0D, 0x0A, 0x1A, 0x0A}
// IHDR chunk: length(13) + "IHDR" + 1x1 px, 8-bit RGB, no interlace + CRC
ihdr := []byte{
0x00, 0x00, 0x00, 0x0D, // chunk length = 13
0x49, 0x48, 0x44, 0x52, // "IHDR"
0x00, 0x00, 0x00, 0x01, // width = 1
0x00, 0x00, 0x00, 0x01, // height = 1
0x08, // bit depth = 8
0x02, // color type = RGB
0x00, 0x00, 0x00, // compression, filter, interlace
0x90, 0x77, 0x53, 0xDE, // CRC (valid for this IHDR)
}
// IEND chunk
iend := []byte{
0x00, 0x00, 0x00, 0x00, // chunk length = 0
0x49, 0x45, 0x4E, 0x44, // "IEND"
0xAE, 0x42, 0x60, 0x82, // CRC
}
pngData := make([]byte, 0, len(pngSignature)+len(ihdr)+len(iend))
pngData = append(pngData, pngSignature...)
pngData = append(pngData, ihdr...)
pngData = append(pngData, iend...)
imgPath := filepath.Join(dir, "test_image.png")
if err := os.WriteFile(imgPath, pngData, 0o644); err != nil {
t.Fatalf("failed to create test PNG: %v", err)
}
store := media.NewFileMediaStore()
tool := NewLoadImageTool(dir, false, 0, store)
ctx := WithToolContext(context.Background(), "test", "chat1")
result := tool.Execute(ctx, map[string]any{"path": imgPath})
// 1. Must not be an error
if result.IsError {
t.Fatalf("expected success, got error: %s", result.ForLLM)
}
// 2. Media must contain exactly one media:// ref
if len(result.Media) != 1 {
t.Fatalf("expected 1 media ref, got %d", len(result.Media))
}
if !strings.HasPrefix(result.Media[0], "media://") {
t.Errorf("expected media ref to start with 'media://', got: %s", result.Media[0])
}
// 3. ForLLM must contain the [image: marker
if !strings.Contains(result.ForLLM, "[image:") {
t.Errorf("expected ForLLM to contain '[image:' marker, got: %s", result.ForLLM)
}
// 4. ForLLM should contain the generic [image: photo] placeholder
// (resolveMediaRefs will replace it with the actual path later)
if !strings.Contains(result.ForLLM, "[image: photo]") {
t.Errorf("expected ForLLM to contain '[image: photo]' placeholder, got: %s", result.ForLLM)
}
// 5. Verify the ref is resolvable in the store
resolved, err := store.Resolve(result.Media[0])
if err != nil {
t.Fatalf("media ref not resolvable: %v", err)
}
if resolved != imgPath {
t.Errorf("expected resolved path %q, got %q", imgPath, resolved)
}
}