### What problem does this PR solve?
Unify reference format of agent completion and OpenAI-compatible
completion API.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
- [x] Documentation Update
- [x] Refactoring
### What problem does this PR solve?
Revert broken agent completion by #9631.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
This PR fixes a critical bug in the session listing endpoint where the
application crashes with an `AttributeError` when processing chunk data
that contains non-dictionary objects.
**Error before fix:**
```json
{
"code": 100,
"data": null,
"message": "AttributeError(\"'str' object has no attribute 'get'\")"
}
```
**Root cause:**
The code assumes all items in the `chunks` array are dictionary objects
and directly calls the `.get()` method on them. However, in some cases,
the chunks array contains string objects or other non-dictionary types,
causing the application to crash when attempting to call `.get()` on a
string.
**Solution:**
Added type validation to ensure each chunk is a dictionary before
processing. Non-dictionary chunks are safely skipped, preventing the
crash while maintaining functionality for valid chunk data.
This fix improves the robustness of the session listing endpoint and
ensures users can retrieve their conversation sessions without
encountering server errors due to data format inconsistencies.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
When create conversation,the prologue hasn't save in conversation.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Fix search app AI summary ERROR: 'dict' object has no attribute 'split'.
#9649
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Resolve#9549 and #9436 , In v0.20.x,Agent completions API changed a
lot,such as without reference and so on
### Type of change
- [x] Refactoring
### What problem does this PR solve?
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
---------
Co-authored-by: Kevin Hu <kevinhu.sh@gmail.com>
### What problem does this PR solve?
When the `dataset_ids` parameter is omitted in the **update assistant**
request, Passing an empty array `[]` triggers a misleading
message"Dataset use different embedding models", while omitting the
field does not.
To fix this, we:
- Provide a default empty list: `ids = req.get("dataset_ids", [])`.
- Replace the `is not None` check with a truthy check: `if ids:`.
**Files changed**
`api/apps/sdk/chat.py`
- L153: `ids = req.get("dataset_ids")` → `ids = req.get("dataset_ids",
[])`
- L156: `if ids is not None:` → `if ids:`
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Refactor OpenAI to enable audio parsing.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
- [x] Refactoring
### What problem does this PR solve?
- Update search_app.py to use SearchService instead of
KnowledgebaseService for duplicate
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Add embedded search functionality.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
---------
Co-authored-by: Kevin Hu <kevinhu.sh@gmail.com>
### What problem does this PR solve?
Add SMTP support for user invitation emails
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
Conversation completion can specify different model
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
Update broken create agent session due to v0.20.0 changes. #9383
**NOTE: A session ID is no longer required to interact with the agent.**
See: #9241, #9309.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Allows set multiple types of default models in service config.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
- Add type and boundary checks for conv["reference"] access
- Prevent KeyError: 0 when reference list is empty or malformed
- Ensure reference is list type before indexing
- Handle cases where reference items are None or missing chunks
- Maintains backward compatibility with existing data structures
This resolves crashes in /api/v1/agents/<agent_id>/sessions endpoint
when conversation reference data is not properly structured.
### What problem does this PR solve?
This PR fixes a critical `KeyError: 0` that occurs in the
`/api/v1/agents/<agent_id>/sessions` endpoint when the system attempts
to access conversation reference data that is not properly structured.
**Background Context:**
The `list_agent_session` method in `api/apps/sdk/session.py` assumes
that `conv["reference"]` is always a properly indexed list with valid
dictionary structures. However, in real-world scenarios, this data can
be:
- Not a list type (could be None, string, or other types)
- An empty list when `chunk_num` tries to access index 0
- Contains None values or malformed dictionary structures
- Missing expected "chunks" keys in reference items
**Impact Before Fix:**
When malformed reference data is encountered, the API crashes with:
```json
{
"code": 100,
"data": null,
"message": "KeyError(0)"
}
```
**Solution:**
Added comprehensive safety checks including type validation, boundary
checking, null safety, and structure validation to ensure the API
gracefully handles all reference data formats while maintaining backward
compatibility.
### Type of change
- [x] 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?
All models pass the mock response tests, which means that if a model can
return the correct response, everything should work as expected.
However, not all models have been fully tested in a real environment,
the real API_KEY. I suggest actively monitoring the refactored models
over the coming period to ensure they work correctly and fixing them
step by step, or waiting to merge until most have been tested in
practical environment.
### Type of change
- [x] Refactoring
- Root cause: accessing req.get("dataset_ids") returns None when the key
is absent, causing KeyError.
- Fix: use req.get("dataset_ids", []) to default to empty list.
### What problem does this PR solve?
Revert token_required decorator of agent_bot completions and inputs.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
- [x] Refactoring
### What problem does this PR solve?
Update broken agent completion due to v0.20.0 changes. #9199
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Fix virtual file cannot be displayed in KB. #9265
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Improve the logic so that it does not decode base 64 for the test image
each time
### Type of change
- [x] Refactoring
- [x] Performance Improvement
---------
Co-authored-by: Kevin Hu <kevinhu.sh@gmail.com>
### What problem does this PR solve?
#9232
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
1. When creating a new session, initialize an empty reference that
includes both the app api and sdk API.
2. Fix the logic when retrieving references for historical messages: the
number of dialogue messages and reference messages may differ, but it
should match the number of assistant messages.
Co-authored-by: Li Ye <liye@unittec.com>
### What problem does this PR solve?
list_document supports range filtering.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
fix#8424 NPE in dify_retrieval.py, add log exception
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
The index name of the tag chunks is generated by the tenant id of the
knowledge base, so it should use the tenant id instead of the current
user id in the listing tags API.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
