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>

tests/test_workspaces_prompt_contract.py

@@ -38,6 +38,9 @@ def test_every_workspace_has_role_system() -> None:
             continue
         if item.name.startswith("__"):
             continue
+        # `_system` holds template fragments/snippets, not routed specialist workspaces.
+        if item.name.startswith("_"):
+            continue
         assert (item / "ROLE_SYSTEM.md").exists(), f"missing ROLE_SYSTEM.md for {item.name}"
 
 
@@ -49,5 +52,7 @@ def test_workspace_legacy_prompt_files_removed() -> None:
             continue
         if item.name.startswith("__"):
             continue
+        if item.name.startswith("_"):
+            continue
         for name in legacy:
             assert not (item / name).exists(), f"legacy prompt file still exists: {item.name}/{name}"