mirror of
https://github.com/infiniflow/ragflow.git
synced 2026-07-08 04:22:20 +08:00
0536233f50
## 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>
102 lines
3.4 KiB
Python
102 lines
3.4 KiB
Python
#
|
|
# Copyright 2025 The InfiniFlow Authors. All Rights Reserved.
|
|
#
|
|
# Licensed under the Apache License, Version 2.0 (the "License");
|
|
# you may not use this file except in compliance with the License.
|
|
# You may obtain a copy of the License at
|
|
#
|
|
# http://www.apache.org/licenses/LICENSE-2.0
|
|
#
|
|
# Unless required by applicable law or agreed to in writing, software
|
|
# distributed under the License is distributed on an "AS IS" BASIS,
|
|
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
# See the License for the specific language governing permissions and
|
|
# limitations under the License.
|
|
#
|
|
|
|
import os
|
|
import shutil
|
|
import tiktoken
|
|
|
|
from common.file_utils import 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")
|
|
|
|
|
|
def num_tokens_from_string(string: str) -> int:
|
|
"""Returns the number of tokens in a text string."""
|
|
try:
|
|
code_list = encoder.encode(string)
|
|
return len(code_list)
|
|
except Exception:
|
|
return 0
|
|
|
|
def total_token_count_from_response(resp):
|
|
"""
|
|
Extract token count from LLM response in various formats.
|
|
|
|
Handles None responses and different response structures from various LLM providers.
|
|
Returns 0 if token count cannot be determined.
|
|
"""
|
|
if resp is None:
|
|
return 0
|
|
|
|
try:
|
|
if hasattr(resp, "usage") and hasattr(resp.usage, "total_tokens"):
|
|
return resp.usage.total_tokens
|
|
except Exception:
|
|
pass
|
|
|
|
try:
|
|
if hasattr(resp, "usage_metadata") and hasattr(resp.usage_metadata, "total_tokens"):
|
|
return resp.usage_metadata.total_tokens
|
|
except Exception:
|
|
pass
|
|
|
|
try:
|
|
if hasattr(resp, "meta") and hasattr(resp.meta, "billed_units") and hasattr(resp.meta.billed_units, "input_tokens"):
|
|
return resp.meta.billed_units.input_tokens
|
|
except Exception:
|
|
pass
|
|
|
|
if isinstance(resp, dict) and 'usage' in resp and 'total_tokens' in resp['usage']:
|
|
try:
|
|
return resp["usage"]["total_tokens"]
|
|
except Exception:
|
|
pass
|
|
|
|
if isinstance(resp, dict) and 'usage' in resp and 'input_tokens' in resp['usage'] and 'output_tokens' in resp['usage']:
|
|
try:
|
|
return resp["usage"]["input_tokens"] + resp["usage"]["output_tokens"]
|
|
except Exception:
|
|
pass
|
|
|
|
if isinstance(resp, dict) and 'meta' in resp and 'tokens' in resp['meta'] and 'input_tokens' in resp['meta']['tokens'] and 'output_tokens' in resp['meta']['tokens']:
|
|
try:
|
|
return resp["meta"]["tokens"]["input_tokens"] + resp["meta"]["tokens"]["output_tokens"]
|
|
except Exception:
|
|
pass
|
|
return 0
|
|
|
|
|
|
def truncate(string: str, max_len: int) -> str:
|
|
"""Returns truncated text if the length of text exceed max_len."""
|
|
return encoder.decode(encoder.encode(string)[:max_len])
|