Fix: UserFillUp interactive forms not working in agent explore mode (#14589)

## Summary

- **Backend**: `_iter_session_completion_events` in `agent_api.py` was
filtering out `user_inputs` and `workflow_finished` SSE events, causing
agents with UserFillUp components to silently fail in explore mode — the
interactive form never appeared, while the same agent worked correctly
in run (editor) mode.
- **Frontend**: `SessionChat` component in explore mode was missing
`DebugContent` children rendering inside `MessageItem`, so even if the
backend forwarded the events, the form UI would not render. Added
`DebugContent`, `MarkdownContent`, `useAwaitCompentData` hook, and
input-disabling logic to match the run mode's `chat/box.tsx` behavior.

## What was changed

### Backend (`api/apps/restful_apis/agent_api.py`)
- Line 266: Added `"user_inputs"` and `"workflow_finished"` to the
allowed event filter in `_iter_session_completion_events`

### Frontend (`web/src/pages/agent/explore/components/session-chat.tsx`)
- Added imports: `DebugContent`, `MarkdownContent`,
`useAwaitCompentData`, `useParams`
- Added `sendFormMessage` from `useSendSessionMessage()` hook
- Added `useAwaitCompentData` hook for form state management
- Added `DebugContent` as `MessageItem` children for the latest
assistant message (renders UserFillUp form)
- Added `MarkdownContent` + submitted values display for previous
assistant messages
- Updated `NextMessageInput` disabled states to respect `isWaitting`
(form submission in progress)

## Test plan

- [x] Agent with UserFillUp component (e.g., email draft with
send/edit/cancel options) shows interactive form in **explore mode**
- [x] Same agent continues to work correctly in **run (editor) mode**
- [x] Form submission sends data back to the agent and workflow
continues
- [x] Input field is disabled while waiting for form submission
- [ ] Agents without UserFillUp components are unaffected in explore
mode

🤖 Generated with [Claude Code](https://claude.com/claude-code)

---------

Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Co-authored-by: Zhichang Yu <yuzhichang@gmail.com>

common/file_utils.py

@@ -16,21 +16,30 @@
 
 import os
 
-PROJECT_BASE = os.getenv("RAG_PROJECT_BASE") or os.getenv("RAG_DEPLOY_BASE")
+PROJECT_BASE = None
+
+
+def _default_project_base_directory():
+    return os.path.abspath(
+        os.path.join(
+            os.path.dirname(os.path.realpath(__file__)),
+            os.pardir,
+        )
+    )
+
 
 def get_project_base_directory(*args):
     global PROJECT_BASE
-    if PROJECT_BASE is None:
-        PROJECT_BASE = os.path.abspath(
-            os.path.join(
-                os.path.dirname(os.path.realpath(__file__)),
-                os.pardir,
-            )
-        )
+
+    project_base = os.getenv("RAG_PROJECT_BASE") or os.getenv("RAG_DEPLOY_BASE")
+    if not project_base:
+        if PROJECT_BASE is None:
+            PROJECT_BASE = _default_project_base_directory()
+        project_base = PROJECT_BASE
 
     if args:
-        return os.path.join(PROJECT_BASE, *args)
-    return PROJECT_BASE
+        return os.path.join(project_base, *args)
+    return project_base
 
 def traversal_files(base):
     for root, ds, fs in os.walk(base):

common/token_utils.py

@@ -14,13 +14,27 @@
 #  limitations under the License.
 #
 
-
 import os
+import shutil
 import tiktoken
 
 from common.file_utils import get_project_base_directory
 
-tiktoken_cache_dir = get_project_base_directory()
+
+def _ensure_tiktoken_cache() -> str:
+    cache_dir = get_project_base_directory()
+    os.environ["TIKTOKEN_CACHE_DIR"] = cache_dir
+
+    bundled_encoding_path = get_project_base_directory("ragflow_deps", "cl100k_base.tiktoken")
+    cached_encoding_path = os.path.join(cache_dir, "9b5ad71b2ce5302211f9c61530b329a4922fc6a4")
+
+    if os.path.exists(bundled_encoding_path) and not os.path.exists(cached_encoding_path):
+        shutil.copyfile(bundled_encoding_path, cached_encoding_path)
+
+    return cache_dir
+
+
+tiktoken_cache_dir = _ensure_tiktoken_cache()
 os.environ["TIKTOKEN_CACHE_DIR"] = tiktoken_cache_dir
 # encoder = tiktoken.encoding_for_model("gpt-3.5-turbo")
 encoder = tiktoken.get_encoding("cl100k_base")