test(config): add migration tests for litellm provider

* Implement tests for migrating configuration from v1 to v2 for the litellm provider.
* Validate the structure and values of the migrated configuration.
* Ensure migration rejects newer versions of the configuration.
fix(validate): enhance AI provider validation logic
* Consolidate provider validation into a dedicated method.
* Ensure at least one provider is specified and validate its type.
* Check for required fields based on provider type.
fix(mcpserver): update tool set to use new enrichment tool
* Replace RetryMetadataTool with RetryEnrichmentTool in the ToolSet.
fix(tools): refactor tools to use embedding and metadata runners
* Update tools to utilize EmbeddingRunner and MetadataRunner instead of Provider.
* Adjust method calls to align with the new runner interfaces.

configs/config.example.yaml

@@ -1,3 +1,5 @@
+version: 2
+
 server:
   host: "0.0.0.0"
   port: 8080
@@ -27,7 +29,7 @@ auth:
       - id: "oauth-client"
         client_id: ""
         client_secret: ""
-        description: "used when auth.mode=oauth_client_credentials"
+        description: "optional OAuth client credentials"
 
 database:
   url: "postgres://postgres:postgres@localhost:5432/amcs?sslmode=disable"
@@ -37,33 +39,58 @@ database:
   max_conn_idle_time: "10m"
 
 ai:
-  provider: "litellm"
+  providers:
+    default:
+      type: "litellm"
+      base_url: "http://localhost:4000/v1"
+      api_key: "replace-me"
+      request_headers: {}
+
+    ollama_local:
+      type: "ollama"
+      base_url: "http://localhost:11434/v1"
+      api_key: "ollama"
+      request_headers: {}
+
+    openrouter:
+      type: "openrouter"
+      base_url: "https://openrouter.ai/api/v1"
+      api_key: "replace-me"
+      app_name: "amcs"
+      site_url: ""
+      request_headers: {}
+
   embeddings:
-    model: "openai/text-embedding-3-small"
     dimensions: 1536
+    primary:
+      provider: "default"
+      model: "openai/text-embedding-3-small"
+    fallbacks:
+      - provider: "ollama_local"
+        model: "nomic-embed-text"
+
   metadata:
-    model: "gpt-4o-mini"
-    fallback_models: []
     temperature: 0.1
     log_conversations: false
-  litellm:
-    base_url: "http://localhost:4000/v1"
-    api_key: "replace-me"
-    use_responses_api: false
-    request_headers: {}
-    embedding_model: "openrouter/openai/text-embedding-3-small"
-    metadata_model: "gpt-4o-mini"
-    fallback_metadata_models: []
-  ollama:
-    base_url: "http://localhost:11434/v1"
-    api_key: "ollama"
-    request_headers: {}
-  openrouter:
-    base_url: "https://openrouter.ai/api/v1"
-    api_key: ""
-    app_name: "amcs"
-    site_url: ""
-    extra_headers: {}
+    timeout: "10s"
+    primary:
+      provider: "default"
+      model: "gpt-4o-mini"
+    fallbacks:
+      - provider: "openrouter"
+        model: "openai/gpt-4.1-mini"
+
+  # Optional overrides for background jobs (backfill_embeddings,
+  # retry_failed_metadata, reparse_thought_metadata).
+  background:
+    embeddings:
+      primary:
+        provider: "default"
+        model: "openai/text-embedding-3-small"
+    metadata:
+      primary:
+        provider: "default"
+        model: "gpt-4o-mini"
 
 capture:
   source: "mcp"