Files
picoclaw/pkg/channels/feishu/common.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

211 lines
6.1 KiB
Go

package feishu
import (
"encoding/json"
"regexp"
"strings"
larkim "github.com/larksuite/oapi-sdk-go/v3/service/im/v1"
"github.com/sipeed/picoclaw/pkg/channels"
)
// mentionPlaceholderRegex matches @_user_N placeholders inserted by Feishu for mentions.
var mentionPlaceholderRegex = regexp.MustCompile(`@_user_\d+`)
// stringValue safely dereferences a *string pointer.
func stringValue(v *string) string {
if v == nil {
return ""
}
return *v
}
// buildMarkdownCard builds a Feishu Interactive Card JSON 2.0 string with markdown content.
// JSON 2.0 cards support full CommonMark standard markdown syntax.
func buildMarkdownCard(content string) (string, error) {
card := map[string]any{
"schema": "2.0",
"body": map[string]any{
"elements": []map[string]any{
{
"tag": "markdown",
"content": content,
},
},
},
}
data, err := json.Marshal(card)
if err != nil {
return "", err
}
return string(data), nil
}
// extractJSONStringField unmarshals content as JSON and returns the value of the given string field.
// Returns "" if the content is invalid JSON or the field is missing/empty.
func extractJSONStringField(content, field string) string {
var m map[string]json.RawMessage
if err := json.Unmarshal([]byte(content), &m); err != nil {
return ""
}
raw, ok := m[field]
if !ok {
return ""
}
var s string
if err := json.Unmarshal(raw, &s); err != nil {
return ""
}
return s
}
// extractImageKey extracts the image_key from a Feishu image message content JSON.
// Format: {"image_key": "img_xxx"}
func extractImageKey(content string) string { return extractJSONStringField(content, "image_key") }
// extractPostImageKeys extracts all image_key values from a Feishu post (rich text)
// message. Post messages have nested arrays of elements where images appear as
// {"tag":"img","image_key":"img_xxx"}.
func extractPostImageKeys(rawContent string) []string {
if rawContent == "" {
return nil
}
var post map[string]json.RawMessage
if err := json.Unmarshal([]byte(rawContent), &post); err != nil {
return nil
}
var keys []string
seen := make(map[string]struct{})
collectFromRows := func(contentRaw json.RawMessage) {
var rows [][]map[string]any
if err := json.Unmarshal(contentRaw, &rows); err != nil {
return
}
for _, row := range rows {
for _, elem := range row {
if tag, _ := elem["tag"].(string); tag == "img" {
if ik, _ := elem["image_key"].(string); ik != "" {
if _, dup := seen[ik]; !dup {
seen[ik] = struct{}{}
keys = append(keys, ik)
}
}
}
}
}
}
// Flat format: {"title":"...", "content":[[...]]}
if contentRaw, ok := post["content"]; ok {
collectFromRows(contentRaw)
}
// Localized format: {"zh_cn": {"title":"...", "content":[[...]]}, ...}
for _, raw := range post {
var locale map[string]json.RawMessage
if err := json.Unmarshal(raw, &locale); err != nil {
continue
}
contentRaw, ok := locale["content"]
if !ok {
continue
}
collectFromRows(contentRaw)
}
return keys
}
// extractFileKey extracts the file_key from a Feishu file/audio message content JSON.
// Format: {"file_key": "file_xxx", "file_name": "...", ...}
func extractFileKey(content string) string { return extractJSONStringField(content, "file_key") }
// extractFileName extracts the file_name from a Feishu file message content JSON.
func extractFileName(content string) string { return extractJSONStringField(content, "file_name") }
// stripMentionPlaceholders removes @_user_N placeholders from the text content.
// These are inserted by Feishu when users @mention someone in a message.
func stripMentionPlaceholders(content string, mentions []*larkim.MentionEvent) string {
if len(mentions) == 0 {
return content
}
for _, m := range mentions {
if m.Key != nil && *m.Key != "" {
content = strings.ReplaceAll(content, *m.Key, "")
}
}
// Also clean up any remaining @_user_N patterns
content = mentionPlaceholderRegex.ReplaceAllString(content, "")
return strings.TrimSpace(content)
}
// extractCardImageKeys recursively extracts all image keys from a Feishu interactive card.
// Image keys are used to download images from Feishu API.
// Returns two slices: Feishu-hosted keys and external URLs.
func extractCardImageKeys(rawContent string) (feishuKeys []string, externalURLs []string) {
if rawContent == "" {
return nil, nil
}
var card map[string]any
if err := json.Unmarshal([]byte(rawContent), &card); err != nil {
return nil, nil
}
extractImageKeysRecursive(card, &feishuKeys, &externalURLs)
return feishuKeys, externalURLs
}
// isExternalURL returns true if the string is an external HTTP/HTTPS URL.
func isExternalURL(s string) bool {
return strings.HasPrefix(s, "http://") || strings.HasPrefix(s, "https://")
}
// extractImageKeysRecursive traverses card structure to find all image keys.
// Collects both Feishu-hosted keys and external URLs separately.
func extractImageKeysRecursive(v any, feishuKeys, externalURLs *[]string) {
switch val := v.(type) {
case map[string]any:
// Check if this is an img element
if tag, ok := val["tag"].(string); ok {
switch tag {
case "img":
// Try img_key first (always Feishu-hosted)
if imgKey, ok := val["img_key"].(string); ok && imgKey != "" {
*feishuKeys = append(*feishuKeys, imgKey)
}
// Check src - could be Feishu key or external URL
if src, ok := val["src"].(string); ok && src != "" {
if isExternalURL(src) {
*externalURLs = append(*externalURLs, src)
} else {
*feishuKeys = append(*feishuKeys, src)
}
}
case "icon":
// Icon elements use icon_key
if iconKey, ok := val["icon_key"].(string); ok && iconKey != "" {
*feishuKeys = append(*feishuKeys, iconKey)
}
}
}
// Recurse into all nested structures
for _, child := range val {
extractImageKeysRecursive(child, feishuKeys, externalURLs)
}
case []any:
for _, item := range val {
extractImageKeysRecursive(item, feishuKeys, externalURLs)
}
}
}
// VoiceCapabilities returns the voice capabilities of the channel.
func (c *FeishuChannel) VoiceCapabilities() channels.VoiceCapabilities {
return channels.VoiceCapabilities{ASR: true, TTS: true}
}