Fix: IMAGE2TEXT→CHAT fallback with model_type normalization in tenant_model_service (#14704)

## 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>

api/db/joint_services/tenant_model_service.py

@@ -13,6 +13,7 @@
 #  See the License for the specific language governing permissions and
 #  limitations under the License.
 #
+import logging
 import os
 import enum
 from common import settings
@@ -20,6 +21,8 @@ from common.constants import LLMType
 from api.db.services.llm_service import LLMService
 from api.db.services.tenant_llm_service import TenantLLMService, TenantService
 
+logger = logging.getLogger(__name__)
+
 
 def get_model_config_by_id(tenant_model_id: int) -> dict:
     found, model_config = TenantLLMService.get_by_id(tenant_model_id)
@@ -71,6 +74,23 @@ def get_model_config_by_type_and_name(tenant_id: str, model_type: str, model_nam
             if not model_config:
                 raise LookupError(f"Tenant Model with name {model_name} and type {model_type_val} not found")
             config_dict = model_config.to_dict()
+        elif model_type_val == LLMType.IMAGE2TEXT.value:
+            model_config = TenantLLMService.get_api_key(tenant_id, pure_model_name, LLMType.IMAGE2TEXT.value)
+            if not model_config:
+                # Fall back to a chat model only if it has declared IMAGE2TEXT capability (tag check via llm table)
+                chat_config = TenantLLMService.get_api_key(tenant_id, pure_model_name, LLMType.CHAT.value)
+                logger.debug("IMAGE2TEXT config not found for %s; chat_config found: %s", pure_model_name, chat_config is not None)
+                if chat_config:
+                    llm_entry = LLMService.query(fid=chat_config.llm_factory, llm_name=chat_config.llm_name)
+                    tags = [t.strip() for t in (llm_entry[0].tags or "").split(",")] if llm_entry else []
+                    logger.debug("LLM tags for %s/%s: %s", chat_config.llm_factory, chat_config.llm_name, tags)
+                    if "IMAGE2TEXT" in tags:
+                        logger.debug("Promoting chat config to IMAGE2TEXT for %s", pure_model_name)
+                        model_config = chat_config
+            if not model_config:
+                raise LookupError(f"Tenant Model with name {model_name} and type {model_type_val} not found")
+            config_dict = model_config.to_dict()
+            config_dict["model_type"] = LLMType.IMAGE2TEXT.value
         else:
             model_config = TenantLLMService.get_api_key(tenant_id, pure_model_name, model_type_val)
             if not model_config:
@@ -90,6 +110,9 @@ def get_model_config_by_type_and_name(tenant_id: str, model_type: str, model_nam
     if config_model_type != model_type_val and not (
             model_type_val == LLMType.CHAT.value
             and config_model_type == LLMType.IMAGE2TEXT.value
+    ) and not (
+            model_type_val == LLMType.IMAGE2TEXT.value
+            and config_model_type == LLMType.CHAT.value
     ):
         raise LookupError(
             f"Tenant Model with name {model_name} has type {config_model_type}, expected {model_type_val}"