### Related issues
Closes#14781
### What problem does this PR solve?
Some retrieval endpoints accepted caller-supplied `tenant_rerank_id` and
resolved it through `get_model_config_by_id(...)`. That helper loaded
`TenantLLM` rows by global database id and returned decoded model
configuration without checking whether the model belonged to the
authenticated tenant or the dataset owner tenant.
This meant dataset access was validated, but rerank-model selection was
not. A caller who knew or could guess another tenant's
`tenant_rerank_id` could attempt retrieval with a foreign rerank model
config, creating a cross-tenant authorization gap for model usage.
This PR closes that gap by making `tenant_rerank_id` resolution
tenant-aware across the retrieval paths that accept it.
### 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):
### Solution
- Extend `get_model_config_by_id(...)` to accept an optional
`allowed_tenant_ids` set and reject `TenantLLM` rows whose `tenant_id`
is outside that set.
- Pass the allowed tenant scope from retrieval endpoints that accept
`tenant_rerank_id`:
- `api/apps/sdk/doc.py`
- `api/apps/sdk/session.py`
- `api/apps/services/dataset_api_service.py`
- Use the authenticated tenant plus dataset-owner tenant ids already
derived by each retrieval flow as the authorization boundary for rerank
model selection.
- Add focused unit coverage to assert unauthorized `tenant_rerank_id`
values are rejected and that the allowed tenant set is propagated
correctly.
### Testing
- `python -m py_compile` on:
- `api/db/joint_services/tenant_model_service.py`
- `api/apps/services/dataset_api_service.py`
- `api/apps/sdk/doc.py`
- `api/apps/sdk/session.py`
- Added unit tests in:
-
`test/testcases/test_http_api/test_file_management_within_dataset/test_doc_sdk_routes_unit.py`
-
`test/testcases/test_http_api/test_session_management/test_session_sdk_routes_unit.py`
### Notes for reviewers
- This change is intentionally narrow: it affects only the
`tenant_rerank_id` path, not the normal `rerank_id` name-based
resolution path.
- Local lint/syntax checks passed.
- Full pytest execution could not be completed in this environment
because the local test runtime is missing `strenum`, so the route-test
files fail during collection before exercising the updated cases.
---------
Co-authored-by: jony376 <jony376@gmail.com>
## Summary
- When a model is registered as `chat` in `tenant_llm` but has the
`IMAGE2TEXT` tag in `llm_factories.json`, requesting it as `image2text`
(e.g. PDF parser) fails with `Tenant Model with name <model> and type
image2text not found`.
- After resolution via the new fallback, the returned
`config_dict["model_type"]` was still `"chat"`, causing
`tenant_llm_service.model_instance()` to instantiate `ChatModel` instead
of `CvModel` — breaking `describe_with_prompt` at ingestion time.
## What problem does this PR solve?
RAGFlow already has a `CHAT→IMAGE2TEXT` fallback: when a chat model is
not found, it retries with `image2text`. The symmetric fallback
(`IMAGE2TEXT→CHAT`) was missing.
This matters for multimodal models declared as `model_type: "chat"` with
an `IMAGE2TEXT` tag in `llm_factories.json` (e.g. models added after
tenant creation, or providers where a single model serves both
purposes). The frontend PDF parser selector correctly surfaces these
models via the `IMAGE2TEXT` tag, but the backend fails to resolve them
at runtime.
## Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
## Changes
**`api/db/joint_services/tenant_model_service.py`**
1. Add `IMAGE2TEXT→CHAT` fallback in
`get_model_config_by_type_and_name`: when an `image2text` model is not
found in `tenant_llm`, retry with `chat` — but only if the `llm` table
confirms `IMAGE2TEXT` capability via the `tags` field. This mirrors the
philosophy of the existing `CHAT→IMAGE2TEXT` fallback: substitution is
only allowed when the model has declared the required capability.
2. Normalize `config_dict["model_type"]` to `image2text` after the
fallback, so the caller (`model_instance`) correctly routes to `CvModel`
instead of `ChatModel`.
3. Extend the type validation guard to allow `(requested=image2text,
found=chat)` alongside the existing `(requested=chat, found=image2text)`
exception.
## Test plan
- [ ] Add a model with `model_type=chat` and `tags` containing
`IMAGE2TEXT` to a tenant
- [ ] Select it as PDF parser in a knowledge base
- [ ] Verify ingestion succeeds without `image2text not found` or
`describe_with_prompt` errors
- [ ] Verify the same model still works correctly in chat context
🤖 Generated with [Claude Code](https://claude.ai/claude-code)
---------
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
### What problem does this PR solve?
Allow image2text models (multimodal) to be used as chat models.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
using builtin model when parsing gave an error because it expects
fid==builtin. split_model_name_and_factory returns id=None. pr allows
the model to be accepted wheter with or without @Builtin
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Fix: model selecton rule in get_model_config_by_type_and_name
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Add id for table tenant_llm and apply in LLMBundle.
### Type of change
- [x] Refactoring
---------
Co-authored-by: Yingfeng <yingfeng.zhang@gmail.com>
Co-authored-by: Liu An <asiro@qq.com>
