feat: multimodal image clients, workspaces, Tushare skill, test fixes

- Replace monolithic image_message_client with HTTP/OCR/legacy modules; tighten OpenAI transport + tool schemas for multimodal downgrade to OCR specialist path.
- Add image/stock workspace prompts (META/SOUL/ROLE_SYSTEM); register experts; tweak specialist agent/direct loop/query_image_attachment.
- Add bundled runtime/skills/tushare-finance (references, api_client, SKILL metadata).
- Document OCR-related env vars; admin chat tweaks; README; weixin_install Ensure-OfficialPluginRuntimeDeps helper.
- Tests: multimodal downgrade + OCR coverage, strict tool pairing in attachment replay guard, workspace contract skips _internal/_system dirs, router/trace/prompt guards.

Co-authored-by: Cursor <cursoragent@cursor.com>

_local/system.env.example

@@ -271,15 +271,16 @@ AIA_REPLAY_TOOL_FULL_ROUNDS=
 AIA_REPLAY_REASONING_SIGNATURE_POLICY=
 
 # -----------------------------------------------------------------------------
-# 十六、图片 / 音视频工具（OpenAI、DashScope）
+# 十六、图片 / OCR 多模态通道（OpenAI-compatible；preferred 名称）
 # -----------------------------------------------------------------------------
 OPENAI_IMAGE_MODEL=
 OPENAI_AUDIO_TRANSCRIPTION_MODEL=
 
-AIA_IMAGE_MODEL=
-AIA_IMAGE_BASE_URL=
-AIA_IMAGE_API_KEY=
-AIA_IMAGE_CHAT_ENDPOINT=
+# query_image_attachment / send_ocr_image_messages（三项必填，无缺省模型 id）
+AIA_OCR_MODEL=
+AIA_OCR_BASE_URL=
+AIA_OCR_API_KEY=
+AIA_OCR_CHAT_ENDPOINT=
 
 DASHSCOPE_IMAGE_N=
 DASHSCOPE_IMAGE_WATERMARK=
@@ -288,11 +289,6 @@ DASHSCOPE_IMAGE_PROMPT_EXTEND=
 DASHSCOPE_IMAGE_SIZE=
 DASHSCOPE_IMAGE_MODEL=
 
-AIA_IMAGE_RETRIES=
-AIA_IMAGE_RETRY_BACKOFF_SEC=
-AIA_IMAGE_STATUS_RETRIES=
-AIA_IMAGE_STATUS_RETRY_BACKOFF_SEC=
-
 CLOUDFLARE_ACCOUNT_ID=
 CLOUDFLARE_API_TOKEN=