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>
2026-06-12 18:08:54 +00:00 · 2026-04-30 11:08:00 +08:00
parent a36472b55f
commit cb1e1a3595
9 changed files with 625 additions and 122 deletions
@@ -64,6 +64,62 @@ func extractJSONStringField(content, field string) string {
 // 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") }