### What problem does this PR solve?

Change mcp_client module to rag/utils/conn.

### Type of change

- [x] Refactoring

### What problem does this PR solve?

Feat: In a dialog message, users can enter different types of data #3221

### Type of change


- [x] New Feature (non-breaking change which adds functionality)

### What problem does this PR solve?

Switching threading.Lock() to asyncio.Lock(), since threading.Lock() is
blocking.

### Type of change

- [x] Performance Improvement

### What problem does this PR solve?

Feat: Fixed the issue that the top toolbar disappears when opening the
agent operator form #3221

### Type of change


- [x] New Feature (non-breaking change which adds functionality)

### What problem does this PR solve?

#1853

### Type of change

- [x] New Feature (non-breaking change which adds functionality)

### What problem does this PR solve?

Feat: Support GiteeAI model  #1853

### Type of change


- [x] New Feature (non-breaking change which adds functionality)

### What problem does this PR solve?

Feat: Allow users to enter text in the middle of a chat #3221
### Type of change


- [x] New Feature (non-breaking change which adds functionality)

### What problem does this PR solve?


### Type of change

- [x] New Feature (non-breaking change which adds functionality)

### What problem does this PR solve?

#8538

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
- [x] Refactoring

### What problem does this PR solve?

Feat: Fixed the issue where the begin operator parameters could not be
submitted during debugging #3221

### Type of change


- [x] New Feature (non-breaking change which adds functionality)

### What problem does this PR solve?
Feat: Display sub-agents in agent form #3221
### Type of change


- [x] New Feature (non-breaking change which adds functionality)

### What problem does this PR solve?

Feat: Fixed the issue where the prompt menu content was hidden #3221

### Type of change


- [x] New Feature (non-breaking change which adds functionality)

### What problem does this PR solve?


### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)

### What problem does this PR solve?

Allow users to choose which MCP tools are enabled.

### Type of change

- [x] New Feature (non-breaking change which adds functionality)

### What problem does this PR solve?
This PR addresses critical memory leaks in the task executor's image
processing pipeline. The current implementation fails to properly
dispose of PIL Image objects and BytesIO buffers during chunk
processing, leading to progressive memory accumulation that can cause
the task executor to consume excessive memory over time.

### Background context
- The `upload_to_minio` function processes images from document chunks
and converts them to JPEG format for storage.
- PIL Image objects hold significant memory resources that must be
explicitly closed to prevent memory leaks.
- BytesIO objects also consume memory and should be properly disposed of
after use.
- In high-throughput scenarios with many image-containing documents,
these memory leaks can lead to out-of-memory errors and degraded
performance.

### Specific issues fixed
- PIL Image objects were not being explicitly closed after processing.
- BytesIO buffers lacked proper cleanup in all code paths.
- Converted images (RGBA/P to RGB) were not disposing of the original
image object.
- Memory references to large image data were not being cleared promptly.

### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
- [x] Performance Improvement


### Changes made
- Added explicit `d["image"].close()` calls after image processing
operations.
- Implemented proper cleanup of converted images when changing formats
from RGBA/P to RGB.
- Enhanced BytesIO cleanup with `try/finally` blocks to ensure disposal
in all code paths.
- Added explicit `del d["image"]` to clear memory references after
processing.

This fix ensures stable memory usage during long-running document
processing tasks and prevents potential out-of-memory conditions in
production environments.

### What problem does this PR solve?

Remove useless logic in a loop for list_doc

### Type of change

- [x] Refactoring
- [x] Performance Improvement

### What problem does this PR solve?

improve the logic to check cancel

### Type of change

- [x] Refactoring

---------

Co-authored-by: Kevin Hu <kevinhu.sh@gmail.com>

### What problem does this PR solve?

https://github.com/infiniflow/ragflow/issues/8467
when add llm the llm_name will like "llm1___OpenAI-API"
f09ca8e795/api/apps/llm_app.py (L173)
so we should not use llm1 to query


### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)

### What problem does this PR solve?

stack：

```
2025-06-26 17:22:24,739 ERROR    1609 list index out of range
Traceback (most recent call last):
  File "/ragflow/.venv/lib/python3.10/site-packages/flask/app.py", line 880, in full_dispatch_request
    rv = self.dispatch_request()
  File "/ragflow/.venv/lib/python3.10/site-packages/flask/app.py", line 865, in dispatch_request
    return self.ensure_sync(self.view_functions[rule.endpoint])(**view_args)  # type: ignore[no-any-return]
  File "/ragflow/api/utils/api_utils.py", line 298, in decorated_function
    return func(*args, **kwargs)
  File "/ragflow/api/apps/sdk/session.py", line 472, in list_session
    print(conv["reference"][message_num])
IndexError: list index out of range

```


![图片](https://github.com/user-attachments/assets/93fe90a8-0434-4842-ba9f-bb5a995b498a)


### Type of change

- [ ] Bug Fix (non-breaking change which fixes an issue)
- [ ] New Feature (non-breaking change which adds functionality)
- [ ] Documentation Update
- [ ] Refactoring
- [ ] Performance Improvement
- [ ] Other (please describe):

### What problem does this PR solve?

Feat: Add StringTransform operator #3221

### Type of change


- [x] New Feature (non-breaking change which adds functionality)

### What problem does this PR solve?

In web folder's prompt-editor component, when entering content for the
first time, the cursor position is abnormal and it will automatically
wrap

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)

Co-authored-by: leonlai <owllai123456>

### What problem does this PR solve?

Fix chunk number error after re-parsing. #8503.

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)

### What problem does this PR solve?

Feat: Displays the output variable type selected by the loop operator
#3221

### Type of change


- [x] New Feature (non-breaking change which adds functionality)

### What problem does this PR solve?

- Include optional `tag_feas` field if present in request
- Add input validation for `important_kwd` and `question_kwd` to ensure
they are lists
- #8462

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)

### What problem does this PR solve?

Feat: Customize the output variable name of the loop operator #3221

### Type of change


- [x] New Feature (non-breaking change which adds functionality)

### What problem does this PR solve?

Feat: Add UserFillUpForm component #3221

### Type of change


- [x] New Feature (non-breaking change which adds functionality)

### What problem does this PR solve?


### Type of change

- [x] Performance Improvement

### What problem does this PR solve?

Add MCP dashboard functionalities list_tools and test_tool.

### Type of change

- [x] New Feature (non-breaking change which adds functionality)

### What problem does this PR solve?
This PR addresses an issue in the presentation parser where the
`layout_recognize` configuration was incorrectly retrieved from
`kwargs.get("layout_recognize", "DeepDOC")`. Instead, it should be
sourced from the `parser_config` parameter, specifically
`parser_config.get("layout_recognize", "DeepDOC")`.

This mismatch could cause the parser to default to the "DeepDOC" layout
recognizer, ignoring any alternative recognition method specified in the
parser configuration. As a result, PDF document parsing might use an
incorrect recognition engine.

The fix ensures the presentation parser consistently uses the
`layout_recognize` setting from `parser_config`, aligning with the
configuration access patterns used elsewhere in the codebase.

### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)

### What problem does this PR solve?

Feat: Allow operators inside the loop operator to reference the output
parameters of external operators #3221

### Type of change


- [x] New Feature (non-breaking change which adds functionality)

### What problem does this PR solve?

Feat: Add retrieval tool #3221

### Type of change


- [x] New Feature (non-breaking change which adds functionality)

### What problem does this PR solve?

This PR adds fields to the `Chunk` class to store retrieval results like
similarity scores, term similarity, vector similarity, positions, and
document type. This allows the chunk object to hold all the information
needed when returning search results from the vector database.

### Type of change

- [x] New Feature (non-breaking change which adds functionality)

### What problem does this PR solve?

Previous:
- Defaulted to hardcoded model 'BAAI/bge-large-zh-v1.5@BAAI'
- Did not respect user-configured default embedding_model

Now:
- Correctly prioritizes user-configured default embedding_model

Other:
- Make embedding_model optional in CreateDatasetReq with proper None
handling
- Add default embedding model fallback in dataset update when empty
- Enhance validation utils to handle None values and string
normalization
- Update SDK default embedding model to None to match API changes
- Adjust related test cases to reflect new validation rules

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)

### What problem does this PR solve?
[https://github.com/infiniflow/ragflow/issues/8324](url)

docker image version: v0.19.1

The `_clean_conf` function was not implemented in the `_chat` and
`chat_streamly` methods of the `GeminiChat` class, causing the error
"Unknown field for GenerationConfig: max_tokens" when the default LLM
config includes the "max_tokens" parameter.

**Buggy Code(ragflow/rag/llm/chat_model.py)**
```python
class GeminiChat(Base):
    def __init__(self, key, model_name, base_url=None, **kwargs):
        super().__init__(key, model_name, base_url=base_url, **kwargs)

        from google.generativeai import GenerativeModel, client

        client.configure(api_key=key)
        _client = client.get_default_generative_client()
        self.model_name = "models/" + model_name
        self.model = GenerativeModel(model_name=self.model_name)
        self.model._client = _client

    def _clean_conf(self, gen_conf):
        for k in list(gen_conf.keys()):
            if k not in ["temperature", "top_p"]:
                del gen_conf[k]
        return gen_conf

    def _chat(self, history, gen_conf):
        from google.generativeai.types import content_types

        system = history[0]["content"] if history and history[0]["role"] == "system" else ""
        hist = []
        for item in history:
            if item["role"] == "system":
                continue
            hist.append(deepcopy(item))
            item = hist[-1]
            if "role" in item and item["role"] == "assistant":
                item["role"] = "model"
            if "role" in item and item["role"] == "system":
                item["role"] = "user"
            if "content" in item:
                item["parts"] = item.pop("content")

        if system:
            self.model._system_instruction = content_types.to_content(system)
        response = self.model.generate_content(hist, generation_config=gen_conf)
        ans = response.text
        return ans, response.usage_metadata.total_token_count

    def chat_streamly(self, system, history, gen_conf):
        from google.generativeai.types import content_types

        if system:
            self.model._system_instruction = content_types.to_content(system)
        #❌_clean_conf was not implemented 
        for k in list(gen_conf.keys()):
            if k not in ["temperature", "top_p", "max_tokens"]:
                del gen_conf[k]
        for item in history:
            if "role" in item and item["role"] == "assistant":
                item["role"] = "model"
            if "content" in item:
                item["parts"] = item.pop("content")
        ans = ""
        try:
            response = self.model.generate_content(history, generation_config=gen_conf, stream=True)
            for resp in response:
                ans = resp.text
                yield ans

            yield response._chunks[-1].usage_metadata.total_token_count
        except Exception as e:
            yield ans + "\n**ERROR**: " + str(e)

        yield 0
```
**Implement the _clean_conf function**
```python
class GeminiChat(Base):
    def __init__(self, key, model_name, base_url=None, **kwargs):
        super().__init__(key, model_name, base_url=base_url, **kwargs)

        from google.generativeai import GenerativeModel, client

        client.configure(api_key=key)
        _client = client.get_default_generative_client()
        self.model_name = "models/" + model_name
        self.model = GenerativeModel(model_name=self.model_name)
        self.model._client = _client

    def _clean_conf(self, gen_conf):
        for k in list(gen_conf.keys()):
            if k not in ["temperature", "top_p"]:
                del gen_conf[k]
        return gen_conf

    def _chat(self, history, gen_conf):
        from google.generativeai.types import content_types
        #✅ implement _clean_conf to remove the wrong parameters
        gen_conf = self._clean_conf(gen_conf)

        system = history[0]["content"] if history and history[0]["role"] == "system" else ""
        hist = []
        for item in history:
            if item["role"] == "system":
                continue
            hist.append(deepcopy(item))
            item = hist[-1]
            if "role" in item and item["role"] == "assistant":
                item["role"] = "model"
            if "role" in item and item["role"] == "system":
                item["role"] = "user"
            if "content" in item:
                item["parts"] = item.pop("content")

        if system:
            self.model._system_instruction = content_types.to_content(system)
        response = self.model.generate_content(hist, generation_config=gen_conf)
        ans = response.text
        return ans, response.usage_metadata.total_token_count

    def chat_streamly(self, system, history, gen_conf):
        from google.generativeai.types import content_types
        #✅ implement _clean_conf to remove the wrong parameters
        gen_conf = self._clean_conf(gen_conf)

        if system:
            self.model._system_instruction = content_types.to_content(system)
        #✅Removed duplicate parameter filtering logic "for k in list(gen_conf.keys()):"
        for item in history:
            if "role" in item and item["role"] == "assistant":
                item["role"] = "model"
            if "content" in item:
                item["parts"] = item.pop("content")
        ans = ""
        try:
            response = self.model.generate_content(history, generation_config=gen_conf, stream=True)
            for resp in response:
                ans = resp.text
                yield ans

            yield response._chunks[-1].usage_metadata.total_token_count
        except Exception as e:
            yield ans + "\n**ERROR**: " + str(e)

        yield 0
```

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)

---------

Co-authored-by: Kevin Hu <kevinhu.sh@gmail.com>

### What problem does this PR solve?

Feat: Filter the query variable drop-down box options by type #3221

### Type of change


- [x] New Feature (non-breaking change which adds functionality)

### What problem does this PR solve?

Improve GraphRAG similarity sensitivity to numeric differences. #8444.

### Type of change

- [x] Refactoring

### What problem does this PR solve?

This PR fixes a typo in the variable name `succesfulFilenames`,
correcting it to `successfulFilenames`. This ensures consistency and
avoids potential errors due to the misspelled variable.

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)

### What problem does this PR solve?
Fix: when using external components, it is impossible to specify the
port, because the variables in the `docker/.env` variable were not
referenced by `docker/service_conf.yaml.template`.

382d2d0373/docker/.env (L85)

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)

### What problem does this PR solve?

Feat: Insert the node data of the bottom subagent into the tool array of
the head agent #3221

### Type of change


- [x] New Feature (non-breaking change which adds functionality)

### What problem does this PR solve?

Using the QA chunking method with a large PDF (e.g., 300+ pages) may
lead to OOM in the ragflow-worker module.


### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)

### What problem does this PR solve?

Add MCP treamable-http transport.

### Type of change

- [x] New Feature (non-breaking change which adds functionality)

### What problem does this PR solve?
https://github.com/infiniflow/ragflow/issues/8466
I go through the codes, current logic:
When do_handle_task raises an exception, handle_task will set the
progress, but for some cases do_handle_task internal will just return
but not set the right progress, at this cases the redis stream will been
acked but the task is running.

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)

---------

Co-authored-by: Kevin Hu <kevinhu.sh@gmail.com>

### What problem does this PR solve?

Add MCP server dashboard operations.

### Type of change

- [x] New Feature (non-breaking change which adds functionality)

### What problem does this PR solve?

_Briefly describe what this PR aims to solve. Include background context
that will help reviewers understand the purpose of the PR._

### Type of change

- [ ] Bug Fix (non-breaking change which fixes an issue)
- [ ] New Feature (non-breaking change which adds functionality)
- [x] Documentation Update
- [ ] Refactoring
- [ ] Performance Improvement
- [ ] Other (please describe):

### What problem does this PR solve?

This PR will fix the #8271 by extending int type to float type when
there is any value out of long type range in a column.
### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)

### What problem does this PR solve?

Feat: Add IterationNode component #3221
### Type of change


- [x] New Feature (non-breaking change which adds functionality)

Saving an RGBA image directly as JPEG will cause an error. If the image
is in RGBA mode, convert it to RGB mode before saving it in JPG format.

### What problem does this PR solve?

During document parsing in the knowledge base, we occasionally encounter
the error 'cannot write mode RGBA as JPEG.' This occurs because images
in RGBA mode cannot be directly saved as JPEG. They must be converted
first before saving.

### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)

### What problem does this PR solve?

- Add new test suite for document app with
create/list/parse/upload/remove tests
- Update API URLs to use version variable from config in HTTP and web
API tests

### Type of change

- [x] Add test cases

### What problem does this PR solve?

before refactor
1. create file record
2. Add to blob

if have some execption at 2 the system db will have a file record but
not have related blob, which will introduce some bug.

after refactor
1. add to blob
2. create file record.

if 1 success but 2 failed just have a dirty blob in blob system, user
will not feel that



### Type of change


- [x] Refactoring

### What problem does this PR solve?

Feat: Delete the agent and tool nodes downstream of the agent node #3221

### Type of change


- [x] New Feature (non-breaking change which adds functionality)