### What problem does this PR solve?
Support model list for VolcEngine.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
Fix LM-Studio provider connection verification so embedding checks await
the async wrapper correctly and log the full traceback on failures.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Normalize agent session chunk references so they are mapped through a
dedicated helper instead of duplicating the field extraction inline.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Feat：
- Get model list from remote provider.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
## Summary
- Infer `Content-Type` from the stored document filename on SDK download
routes.
- Covers `GET /api/v1/datasets/<dataset_id>/documents/<document_id>` and
`GET /api/v1/documents/<document_id>`.
- Aligns with REST preview/download via `CONTENT_TYPE_MAP`.
## Test plan
- [x] `pytest
test/testcases/test_http_api/test_file_management_within_dataset/test_doc_sdk_routes_unit.py::TestDocRoutesUnit::test_download_mimetype_from_filename`
- [x] Manual: `curl -sSI` on SDK dataset document download for a PDF;
expect `Content-Type: application/pdf`
Fixes#15112.
### What problem does this PR solve?
Fix:
- VolcEngine adapt to new api_key format
- Save dict api_key as json
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
When a document is rerun or updated concurrently, the previous
unconditional update could overwrite a newer task state.
This change adds an `update_time`-based optimistic lock so the update
only succeeds if the record has not been modified by another flow in the
meantime.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Not display `success` when check not passed.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
remove duplicate document preview access check
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Fix:
- Verify provider with empty llm list in llm_factories.json
- Set search bot's chat_llm_name, use tenant default chat model as
default
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
Restore `DocumentService.accessible` on `GET
/api/v1/documents/{doc_id}/preview` so cross-tenant users cannot stream
documents by UUID.
Fixes#15501
### What problem does this PR solve?
PR #15146 (`71a52d579`) moved the agent attachment download route and
accidentally removed the `DocumentService.accessible(doc_id,
current_user.id)` guard from the REST preview handler. The endpoint
still requires login, but any authenticated user who knows another
tenant's `doc_id` can download the raw file bytes.
This restores the same authorization check that existed before #15146,
returning a generic `"Document not found!"` when access is denied (no
cross-tenant ID enumeration). SDK download routes tracked in #15125 are
unchanged.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
## Summary
Restore the `DocumentService.accessible(doc_id, current_user.id)` check
that PR #15146 dropped from the REST document preview handler. Any
authenticated caller could download any tenant's document bytes by
guessing/knowing the `doc_id`.
## Root cause
`api/apps/restful_apis/document_api.py` — the `GET
/documents/<doc_id>/preview` handler called `DocumentService.get_by_id`
and went straight to `File2DocumentService.get_storage_address` +
`STORAGE_IMPL.get`, with no tenant check between the lookup and the
read. The handler's docstring even promises "user must belong to the
tenant that owns the document's knowledge base" — the code didn't
enforce it.
## Fix
- Add `current_user` to the existing `api.apps` import.
- Immediately after `get_by_id`, call
`DocumentService.accessible(doc_id, current_user.id)`; on denial, return
the **same** `get_data_error_result(message="Document not found!")`
shape used for the missing-doc branch. That makes a cross-tenant probe
indistinguishable from a missing-doc probe, preventing ID enumeration
(the issue body calls this out explicitly).
- Emit `logging.warning` with caller user + doc_id for audit.
- Restores symmetry with peer routes that already call
`accessible(doc_id, user_id)` (e.g. `_run_sync` at
`document_api.py:1380`).
## Test plan
Adds
`test/unit_test/api/apps/restful_apis/test_document_preview_accessible.py`:
- **`test_cross_tenant_preview_is_denied`** — owner tenant ≠ caller
tenant; asserts the response shape is `Document not found!` and the
storage backend (`thread_pool_exec(STORAGE_IMPL.get, ...)`) is **never**
invoked.
- **`test_missing_doc_returns_not_found`** — missing-doc behaviour
unchanged.
Stub-loader pattern mirrors
`test/unit_test/api/apps/sdk/test_dify_retrieval.py` (added in #15028,
passing in CI).
## Provenance — how this fix was produced
This PR was authored against a small cited knowledge base committed in
the working tree as a `.vouch/` (see
[vouchdev/vouch](https://github.com/vouchdev/vouch)). The loop used
here:
1. **Grounding first.** Before reading the handler, queried the KB for
prior context: `vouch context "tenant scoped accessible authorization"`
→ retrieved a cited claim distilled from PR #15028 (which restored the
same `accessible()` check on `/dify/retrieval`). The retrieved rule:
> *ragflow REST endpoints that load by tenant-scoped id must call
`<Service>.accessible(id, tenant_id)` after `get_by_id` and before
storage/DB read; deny with code 109 'No authorization.' and log a
warning. Established by PR #15028.*
2. **Applied the pattern with a domain refinement.** For an API/JSON
endpoint, `No authorization.` is the right denial shape. For a
**byte-streaming, browser-facing** endpoint like `/preview`, leaking
*existence* itself enables enumeration — so per the issue's expected
behaviour, this PR denies with `Document not found!` (indistinguishable
from missing) instead. Same auth check, narrower response.
3. **Recorded the refinement back into the KB** as a new cited claim, so
the next IDOR-class issue starts already grounded in both the general
pattern and the byte-route nuance.
Net effect of the workflow: the fix replicates a known-good pattern
instead of reinventing it, *and* the place where the pattern was nuanced
is now retrievable for the next pass. Mechanism is fully independent of
this PR — it's not a runtime dependency, just process discipline.
Closes#15501
### What problem does this PR solve?
### Problem
On the Model Providers page, the Embedding Model dropdown in System
Model Settings shows empty (no default selected), even though a default
embedding model is configured in `service_conf.yaml`.
### Root Cause
Two issues were identified:
1. **Backend: `_get_model_info` fails for unregistered providers**
The tenant's `embd_id` is set to `bge-m3@xxxx` during initialization
(from the placeholder config `factory: 'xxxx'`). The `_get_model_info`
function requires the provider to exist in `tenant_model_provider`
table, but `xxxx` is never a real provider. Even after the user adds a
real provider (e.g., ZHIPU-AI), the stale `embd_id` still references the
non-existent one, causing the function to return `None`.
2. **Frontend: default models cache not invalidated after adding
provider**
`useAddProviderInstance` only invalidates `addedProviders` and
`allModels` caches after adding a provider instance, but does **not**
invalidate the `defaultModels` cache. This means the default model list
is not re-fetched until the user manually refreshes the page.
### Fix
**`api/apps/services/models_api_service.py`**
- Added `_resolve_model_from_tenant_providers()` helper: when the
default model's provider doesn't exist (e.g., placeholder `xxxx`), it
searches through the tenant's actually registered providers for a model
of the same type and returns the first match.
- When an instance name doesn't match (e.g., `"default"` vs actual name
`"1"`), the function now auto-resolves to the first real instance under
that provider.
- Falls back to `FACTORY_LLM_INFOS` validation when neither provider nor
instance exists.
**`web/src/hooks/use-llm-request.tsx`**
- Added `queryClient.invalidateQueries({ queryKey:
LlmKeys.defaultModels() })` to `useAddProviderInstance` so that the
default model list is re-fetched immediately after a provider instance
is added, eliminating the need for a manual page refresh.
### Testing
- Verified with a tenant whose `embd_id=bge-m3@xxxx` and only provider
is ZHIPU-AI (instance `1`): `_resolve_model_from_tenant_providers`
correctly resolves to `embedding-2@1@ZHIPU-AI`.
- After adding a provider via the UI, the embedding model dropdown now
immediately shows the resolved default without requiring a page refresh.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
---------
Signed-off-by: noob <yixiao121314@outlook.com>
## Summary
Fixes#15534 — `update_document_name_only()` crashes with
`AttributeError` when `File2Document` exists but the linked `File` row
was deleted.
`update_document_name_only()` in `document_api_service.py` called
`FileService.get_by_id()` when a `File2Document` row existed, then
accessed `file.id` without checking the lookup result. An orphan
`File2Document` link (file deleted, mapping left behind) caused document
rename via `PATCH /api/v1/datasets/{dataset_id}/documents/{document_id}`
to return HTTP 500.
This PR mirrors guards used in `file2document_api.py` and
`file_api_service.py`: skip the optional file rename when the file is
missing, and still update the document record and search index.
## Changes
- `api/apps/services/document_api_service.py` — check `e and file`
before `FileService.update_by_id`
- `test/unit_test/api/apps/services/test_update_document_name_only.py` —
regression tests (orphan link + happy path)
## Test plan
- [x] `pytest
test/unit_test/api/apps/services/test_update_document_name_only.py -v`
- [ ] Manual: PATCH document `name` when `File2Document` points to a
non-existent `file_id` → 200, document/index renamed, no 500
### What problem does this PR solve?
Closes#15388.
Chat completion routes did not reliably honor per-request generation
settings:
- `/api/v1/chat/completions` copied generation settings with a
truthiness check, so valid zero values such as `temperature: 0`, `top_p:
0`, `frequency_penalty: 0`, `presence_penalty: 0`, and `max_tokens: 0`
were dropped.
- `/api/v1/openai/{chat_id}/chat/completions` did not forward standard
generation settings into the request-specific dialog LLM settings before
calling `async_chat`.
This PR preserves explicitly supplied generation parameters, including
zero values, and merges request-level overrides into existing dialog
settings where appropriate.
The supported generation parameter keys and merge behavior live in a
shared REST API helper to keep both completion routes aligned.
Validation:
- `git diff --check`
- `python3 -m py_compile api/apps/restful_apis/_generation_params.py
api/apps/restful_apis/chat_api.py api/apps/restful_apis/openai_api.py
test/testcases/test_http_api/test_session_management/test_session_sdk_routes_unit.py`
- `uv run ruff check api/apps/restful_apis/_generation_params.py
api/apps/restful_apis/chat_api.py api/apps/restful_apis/openai_api.py
test/testcases/test_http_api/test_session_management/test_session_sdk_routes_unit.py`
- `ZHIPU_AI_API_KEY=dummy uv run pytest
test/testcases/test_http_api/test_session_management/test_session_sdk_routes_unit.py
-q -k generation_params`
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Fix:
- Handle siliconflow and siliconflow_intl api_key
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Fix:
- Use @ to avoid split by `_` in model_name.
- Verify api_key when add instance.
- Pop api_key in list intances response.
- Remove useless index.
- Sort providers, instances and models by name.
- Get `is_tools` from llm_factories.json
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Fixes#15286.
When calling `/api/v1/openai/<chat_id>/chat/completions` with `"stream":
true`, the response contains the answer **twice** — the final message
repeats everything that was already streamed.
#### Root cause
RAGFlow's `async_chat` streams the body as incremental `delta.content`
chunks, then emits a terminating `final` event whose `answer` is the
**complete** (decorated) message. The handler re-emitted that full
answer as one more `delta.content` chunk:
```python
if ans.get("final"):
if ans.get("answer"):
full_content = ans["answer"]
response["choices"][0]["delta"]["content"] = full_content # <-- whole answer again
yield ...
```
So a client accumulating `delta.content` ends up with the message
duplicated.
#### Fix
Drop the re-emission. The complete answer from the `final` event is now
surfaced **only** through the trailing chunk's `final_content` and
`reference` fields, which matches OpenAI streaming semantics: deltas are
incremental, and the final chunk carries only `finish_reason` / `usage`
(plus RAGFlow's `reference` / `final_content` extensions).
This matches the expected behavior described in the issue: "The stream
should only yield content chunks once, and the final message should only
contain reference, usage, and finish_reason."
#### Testability refactor
The streaming SSE assembly was a closure inside the request handler, so
it could only be exercised against a live server + real LLM. I extracted
it into a module-level `_stream_chat_completion_sse` async generator
(behavior-preserving) so it can be unit-tested with a fake event stream.
#### Tests
Adds
`test/unit_test/api/apps/restful_apis/test_openai_stream_no_duplicate.py`
(same import-stub pattern as the existing `test_get_agent_session.py`):
- body is streamed exactly once (the regression);
- the complete answer is never re-emitted as a content chunk;
- the terminating chunk has `finish_reason="stop"`, `content=None`, and
correct `usage`;
- `final_content` / `reference` are present on the trailing chunk;
- reasoning (`think`) deltas stream separately and are not duplicated.
> Note: this is unrelated to #15442, which only changes the `stream`
default — it does not touch the duplication logic.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
- [x] Added test cases
---------
Co-authored-by: Wang Qi <wangq8@outlook.com>
### What problem does this PR solve?
Fixes#15115.
`GET /api/v1/documents/images/<image_id>` returned **Image not found**
when the thumbnail storage object key contained hyphens (e.g.
`page-1.png`). Document APIs build URLs as `{dataset_id}-{thumbnail}`,
but `get_document_image()` used `image_id.split("-")` and required
exactly two segments, so keys like `<kb_id>-page-1.png` were rejected
even though the blob existed.
This PR splits only on the first hyphen (`split("-", 1)`) and sets
`Content-Type` from the object key extension via `CONTENT_TYPE_MAP`
instead of hardcoding `image/JPEG`.
### Related issues
Closes#15358
<!-- After filing upstream, replace XXXX with your issue number. -->
---
### What problem does this PR solve?
`POST /api/v1/openai/<chat_id>/chat/completions` forwards `messages` to
`async_chat` without normalizing `content`. Downstream, `dialog_service`
assumes string content:
```python
re.sub(r"##\d+\$\$", "", m["content"])
```
OpenAI-compatible clients may send `content` as an **array** of parts
(text, `image_url`, etc.), including text-only arrays. That causes
`TypeError` and HTTP **500** instead of a valid response or a clear
**400**.
`openai_api.py` also reads `messages[-1]["content"]` directly for
`prompt` without handling list-shaped content.
This PR normalizes array `content` to a string (concatenating `type:
text` parts) before calling `async_chat`, matching a minimal
OpenAI-compat path. Image parts can be documented as unsupported or
handled in a follow-up if vision integration is required.
## Summary
Fixes#15245 — `POST /api/v1/chat/completions` with `stream=true`
intermittently returns 500:
```
data:{"code": 500, "message": "failed to encode response: json:
unsupported value: NaN (status code: 500)", "data": {...}}
```
…even though "the same question" works on retry.
## Root cause
The streaming path serialized the answer with bare `json.dumps(...)`
(`api/apps/restful_apis/chat_api.py:1221`). `json.dumps` defaults to
`allow_nan=True` and emits the literal token `NaN` for NaN /
Infinity float values. That is valid Python-flavored JSON but
**invalid per RFC 8259**, so downstream consumers reject it. The
reporter's gateway is Go-based and the error wording
(`failed to encode response: json: unsupported value: NaN`) is
straight from Go's `encoding/json`.
How NaN gets into the payload: retrieval scoring in
`rag/nlp/search.py` runs `np.mean(...)` over aggregations that can
be empty, and similarity denominators can be zero. Reference chunk
fields like `similarity`, `vector_similarity`, `term_similarity`
can therefore be NaN depending on which chunks a given query
retrieves — which is exactly why the failure is intermittent for
the same question.
The non-streaming branch (`get_json_result(data=answer)`,
`chat_api.py:1243`) has the same vulnerability — Quart's `jsonify`
also defaults to `allow_nan=True` and the same retrieval pipeline
feeds both branches.
`agent/tools/exesql.py:88-102` already has the same NaN/Inf guard
for SQL results. This PR brings the chat completions path up to
parity.
## Fix
Add a small `_sanitize_json_floats(obj)` helper near the top of
`api/apps/restful_apis/chat_api.py`. It walks `dict` / `list` /
`tuple` and replaces any `float` that is `NaN` or `±Infinity` with
`None`. Apply it at the two serialization boundaries:
- **Streaming branch** (`stream()`): sanitize the SSE payload before
`json.dumps`.
- **Non-streaming branch**: sanitize the `answer` dict before
`get_json_result(data=...)`.
The terminal `data:True` frame and the `code:500` error frame carry
no scores and are left untouched.
Added `import math` to the existing alphabetical import block.
No change to retrieval logic — replacing NaN with `null` at the
serialization boundary is conservative: clients still parse the
JSON, a missing-score chunk is a strictly better failure mode than
a 500 that kills the whole reply.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### Related issues
Closes#15310
### What problem does this PR solve?
`/api/v1/dify/retrieval` had duplicate `GET` route registrations in
`dify_retrieval_api.py`: one for authenticated retrieval and another for
unauthenticated health checks. Sharing the same path and method created
ambiguous routing behavior and an unstable API contract for Dify
external knowledge base integration.
This PR separates concerns by moving the health-check endpoint to `GET
/api/v1/dify/retrieval/health`, while keeping retrieval on
`/api/v1/dify/retrieval`. This makes auth behavior deterministic and
prevents route shadowing/conflicts.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Closes#15180.
`OIDCClient.parse_id_token` in `api/apps/auth/oidc.py` read the JWT
signing
algorithm from the **unverified** JWT header and passed it through to
`jwt.decode(..., algorithms=[alg], ...)` as the trust anchor. This is
the
textbook JWT algorithm-confusion vulnerability (CWE-345 / CWE-347). Any
unauthenticated client capable of reaching the OIDC callback could take
over
an arbitrary account on any RAGFlow deployment with OIDC login enabled:
1. **`alg: "none"`** — present a JWT with `{"alg": "none"}` and no
signature segment → `jwt.decode(..., algorithms=["none"])` → PyJWT's
`NoneAlgorithm` accepts the token without verification → login as any
user.
2. **RSA / HMAC confusion** — fetch the public RSA key from the
provider's
JWKS (it's public), forge a JWT with `{"alg": "HS256"}` HMAC-signed
using the public-key bytes as the secret → `jwt.decode(...,
algorithms=["HS256"], key=public_key)` → verifier accepts → login as
any user. (Modern PyJWT independently refuses to use a PEM-formatted
key as an HMAC secret, which mitigates this leg for PEM key formats;
the fix here is the only mitigation for raw / DER / JWK octet keys and
for older PyJWT versions.)
### What changed
**`api/apps/auth/oidc.py`:**
- New module constants `_ALLOWED_OIDC_SIGNING_ALGS` (asymmetric-only:
`RS*`, `ES*`, `PS*`, `EdDSA` — explicitly excludes `none` and `HS*`)
and `_DEFAULT_OIDC_SIGNING_ALGS = ("RS256",)` (the OIDC Core 1.0 §2
spec default).
- New helper `_resolve_id_token_signing_algs(metadata)` — intersects the
provider's advertised `id_token_signing_alg_values_supported` from
`/.well-known/openid-configuration` with the safe allowlist; falls back
to RS256 when the field is missing or contains only unsafe values.
- `OIDCClient.__init__` now stores the resolved allowlist on
`self.id_token_signing_algs` — pinned once, from a trusted source, at
construction time.
- `parse_id_token` no longer calls `jwt.get_unverified_header` and no
longer reads `alg` from the JWT header. It passes
`self.id_token_signing_algs` to `jwt.decode(..., algorithms=...)`.
`PyJWKClient.get_signing_key_from_jwt` still reads the `kid` from the
header internally for JWKS lookup — that's fine, `kid` is not a
security decision; the signature still proves which key was actually
used.
**`test/testcases/test_web_api/test_auth_app/test_oidc_client_unit.py`:**
- Existing `test_parse_id_token_success_and_error` drops its
`jwt.get_unverified_header` mock (no longer called by `parse_id_token`).
- `_metadata` and `_make_client` helpers grew an optional `signing_algs`
parameter so tests can configure what the discovery document advertises.
- New `TestSSRFValidation` / algorithm-confusion regression block (7
tests):
- `test_id_token_signing_algs_default_to_rs256_when_metadata_missing`
- `test_id_token_signing_algs_intersect_metadata_with_safe_allowlist`
- `test_id_token_signing_algs_fall_back_when_only_unsafe_advertised`
- `test_id_token_signing_algs_ignores_non_string_entries`
- `test_id_token_signing_algs_handles_non_list_metadata_field`
- `test_parse_id_token_passes_pinned_algorithms_to_jwt_decode` —
sabotages `jwt.get_unverified_header` to raise on call, proving the
verification path never consults the unverified header.
- `test_parse_id_token_rejects_alg_none` — uses real PyJWT to encode an
`alg: "none"` token; `parse_id_token` raises `ValueError("Error
parsing ID Token: …")` instead of accepting it.
- `test_parse_id_token_rejects_hs256_when_allowlist_is_asymmetric` —
uses real PyJWT to forge an `alg: "HS256"` token with a non-PEM
shared secret (so PyJWT's incidental PEM-as-HMAC refusal isn't what
blocks it); `parse_id_token` raises because `HS256` is not in the
pinned allowlist.
Sanity-checked end-to-end with real PyJWT outside the project test
runner:
- `alg=none` forged token + `algorithms=["RS256"]` →
`InvalidAlgorithmError` ✓
- `alg=HS256` forged token + `algorithms=["RS256"]` →
`InvalidAlgorithmError` ✓
- Same `alg=HS256` token + `algorithms=["HS256"]` → **accepted**
({'sub': 'admin'})
— confirming the attack path was real before the fix.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
Co-authored-by: galuis116 <contact@duerrimports.com>
### What this PR fixes
This PR fixes an issue in the Python backend where user logout did not
reliably persist the invalidated access_token to the database.
Although the logout endpoint returned success and logged that the token
had been invalidated, the user.access_token value could remain
unchanged in the database, which meant the previous login token could
stay valid longer than expected.
### What changed
- Resolve the real user object before updating the token
- Persist the invalidated access_token before calling logout_user()
- Return a server error if the token update is not written successfully
### Impact
- Logging out now correctly replaces the stored access_token with an
INVALID_... value
- The previous login session is properly invalidated
- The change is limited to the logout flow and is intentionally small in
scope
### What problem does this PR solve?
default OpenAI chat completions to non-stream when `stream` is omitted
https://github.com/infiniflow/ragflow/issues/15356
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Python implementation of the Go-based model_provider API suite.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
---------
Co-authored-by: bill <yibie_jingnian@163.com>
### What problem does this PR solve?
Creating or updating an agent via `POST /api/v1/agents` and `PUT
/api/v1/agents/{agent_id}` did not persist `canvas_type` because the
handler `req` dict never assigned the field before
`UserCanvasService.save` / `update_by_id`.
### 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):
Co-authored-by: Cursor <cursoragent@cursor.com>
## Summary
Fixes the confirmed asyncio anti-patterns from #14755. Only the three
verified bugs are addressed; patterns already correctly using
`asyncio.new_event_loop()` in a fresh thread are left untouched.
### Changes
**`api/apps/restful_apis/tenant_api.py` — fire-and-forget
`send_invite_email`**
`asyncio.create_task()` was called without storing the `Task` reference.
CPython's GC can collect an unfinished task, silently cancelling it and
swallowing exceptions. Fixed by storing the task in a module-level
`_background_tasks: set[Task]` with a `done_callback` to discard it on
completion — the standard Python idiom for safe background tasks.
**`api/apps/restful_apis/agent_api.py` — fire-and-forget
`background_run`**
Same root cause in the webhook "Immediately" execution path. Same fix
applied.
**`rag/llm/chat_model.py` (`LocalLLM._stream_response`) —
`asyncio.get_event_loop()` on running loop**
`asyncio.get_event_loop()` returns Quart's running event loop when
called from an async context.
Calling `loop.run_until_complete()` on it raises `RuntimeError`.
Replaced with `asyncio.new_event_loop()` so the generator
uses a dedicated fresh loop, closed in a `finally` block.
## What was NOT changed
- `llm_service._sync_from_async_stream` and
`evaluation_service._sync_from_async_gen`: both already correctly use
`asyncio.new_event_loop()` inside a fresh thread.
- `llm_service._run_coroutine_sync`: only caller is `rag/app/resume.py`
(sync context), so `thread.join()` is correct there.
- `requests` in agent tools: sync methods dispatched through thread
pools; httpx migration is a separate, larger refactor.
## Test plan
- [ ] Invite a team member and confirm the email is sent with no task
warnings in logs.
- [ ] Trigger a webhook agent in "Immediately" mode; confirm canvas
state is persisted after background run.
- [ ] Verify `LocalLLM` (Jina backend) chat and streaming work
end-to-end.
Closes#14755
---------
Co-authored-by: Zhichang Yu <yuzhichang@gmail.com>
Follow on PR #15146 to reslove the backwad compatability issue.
1. /agents/<attachment_id>/download ->
/agents/attachments/<attachment_id>/download
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
## Summary
This change fixes ingestion quality issues where MinerU parser output
may contain HTML fragments (for example, table-related tags like `<tr>`,
`<td>`, `<br>`), which were previously passed directly into
chunking/tokenization and degraded chunk quality.
The fix adds a sanitization step in the MinerU parser path so parsed
sections are normalized to clean text before chunking.
## Change Type (select all)
- [x] Bug fix
- [x] Ingestion pipeline improvement
- [x] Parser/chunking quality fix
## Related Issue
- https://github.com/infiniflow/ragflow/issues/14831
### What problem does this PR solve?
This PR improves the table upload flow for CSV/Excel files by allowing
table column role configuration at upload time.
Previously, users had to:
1. Upload and parse a table file.
2. Open parser settings and manually set table column roles.
3. Re-parse the file for the roles to take effect.
This was inefficient and required an unnecessary second parse.
With this change:
1. When the knowledge base uses table parsing, the upload dialog
extracts CSV/Excel headers client-side.
2. Users can choose Auto mode or Manual mode.
3. In Manual mode, users can assign per-column roles before upload.
4. The selected parser config is sent with the upload request and
applied server-side during document creation.
Result: configured table column roles are applied from the first parse.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
Co-authored-by: Ahmad Intisar <ahmadintisar@Ahmads-MacBook-M4-Pro.local>
### What problem does this PR solve?
1. Fix /chat/completions to send only the latest message
2. Allo chat stream=False
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
