Issue LIF-Initiative#747: Fix issue with GraphQL failing due to getting null values… (LIF-Initiative#753)

… for required fields

<!--
Thank you for your pull request. Please review the requirements below.

Bug fixes and new features should be reported on the issue tracker:
https://github.com/lif-initiative/lif-core/issues

Contributing guide:
https://github.com/lif-initiative/lif-core/blob/main/docs/CONTRIBUTING.md
Code of Conduct:
https://github.com/lif-initiative/lif-core/blob/main/CODE_OF_CONDUCT.md
-->

##### Checklist
<!-- Remove items that do not apply. For completed items, change [ ] to
[x]. -->

- [x] commit message follows commit guidelines (see
commitlint.config.mjs)
- [x] tests are included (unit and/or integration tests)
- [x] all tests are successful
- [x] documentation is changed or added (in /docs directory)
- [x] code passes linting checks (`uv run ruff check`)
- [x] code passes formatting checks (`uv run ruff format`)
- [x] code passes type checking (`uv run ty check`)
- [x] pre-commit hooks have been run successfully
- [ ] database schema changes: migration files created and CHANGELOG.md
updated
- [ ] API changes: base (Python code) documentation in `docs/`
      and project README updated
- [ ] configuration changes: relevant folder README updated
- [ ] breaking changes: added to MIGRATION.md with upgrade instructions
      and CHANGELOG.md entry

##### Type of Change
<!-- Check all that apply -->

- [x] Bug fix (non-breaking change which fixes an issue)
- [ ] New feature (non-breaking change which adds functionality)
- [ ] Breaking change (fix or feature that would cause existing
functionality
      to not work as expected)
- [x] Documentation update
- [ ] Infrastructure/deployment change
- [ ] Performance improvement
- [x] Code refactoring

##### Description of Change
<!-- Provide a clear and detailed description of the change below this
comment.
Include:
- What problem does this solve?
- What is the solution?
- Are there any side effects or limitations?
- How should reviewers test this?
-->

##### Related Issues
<!-- Link to related issues using #issue_number -->

Closes LIF-Initiative#747

##### Testing
<!-- Describe the testing you've done -->

- [ ] Manual testing performed
- [ ] Automated tests added/updated
- [ ] Integration testing completed

##### Project Area(s) Affected
<!-- Check all project areas affected by this change -->

- [ ] bases/
- [ ] components/
- [ ] orchestrators/
- [ ] frontends/
- [ ] deployments/
- [ ] CloudFormation/SAM templates
- [ ] Database schema
- [ ] API endpoints
- [ ] Documentation
- [ ] Testing

##### Additional Notes
<!-- Any additional information that reviewers should know -->

Author: bjagg

bases/lif/api_graphql/core.py

@@ -11,27 +11,28 @@
 from fastapi import FastAPI
 from strawberry.fastapi import GraphQLRouter
 
+from lif.lif_schema_config import LIFSchemaConfig
 from lif.logging import get_logger
 from lif.mdr_client import get_openapi_lif_data_model
 from lif.openapi_to_graphql.core import generate_graphql_schema
 
 logger = get_logger(__name__)
 
 
-LIF_QUERY_PLANNER_URL = os.getenv("LIF_QUERY_PLANNER_URL", "http://localhost:8002")
-LIF_GRAPHQL_ROOT_TYPE_NAME = os.getenv("LIF_GRAPHQL_ROOT_TYPE_NAME", "Person")
+# Load centralized configuration from environment
+CONFIG = LIFSchemaConfig.from_environment()
 
-logger.info(f"LIF_QUERY_PLANNER_URL: {LIF_QUERY_PLANNER_URL}")
-logger.info(f"LIF_GRAPHQL_ROOT_TYPE_NAME: {LIF_GRAPHQL_ROOT_TYPE_NAME}")
-logger.info(f"LIF_MDR_API_URL: {os.getenv('LIF_MDR_API_URL')}")
+logger.info(f"LIF_QUERY_PLANNER_URL: {CONFIG.query_planner_base_url}")
+logger.info(f"LIF_GRAPHQL_ROOT_TYPE_NAME: {CONFIG.root_type_name}")
+logger.info(f"LIF_MDR_API_URL: {CONFIG.mdr_api_url}")
 
 
 async def fetch_dynamic_graphql_schema(openapi: dict):
     return await generate_graphql_schema(
         openapi=openapi,
-        root_type_name=LIF_GRAPHQL_ROOT_TYPE_NAME,
-        query_planner_query_url=LIF_QUERY_PLANNER_URL.rstrip("/") + "/query",
-        query_planner_update_url=LIF_QUERY_PLANNER_URL.rstrip("/") + "/update",
+        root_type_name=CONFIG.root_type_name,
+        query_planner_query_url=CONFIG.query_planner_query_url,
+        query_planner_update_url=CONFIG.query_planner_update_url,
     )
 
 

bases/lif/semantic_search_mcp_server/core.py

@@ -9,6 +9,7 @@
 from starlette.requests import Request
 from starlette.responses import PlainTextResponse
 
+from lif.lif_schema_config import LIFSchemaConfig, DEFAULT_ATTRIBUTE_KEYS
 from lif.logging import get_logger
 from lif.mdr_client import get_openapi_lif_data_model_from_file
 from lif.openapi_schema_parser import load_schema_leaves
@@ -23,41 +24,73 @@
 logger = get_logger(__name__)
 
 
-# --------- LOAD ENVIRONMENT VARIABLES ---------
+# --------- LOAD CONFIGURATION ---------
 
-ROOT_NODE = os.getenv("LIF_GRAPHQL_ROOT_NODE", "Person")
+# Load centralized configuration from environment
+CONFIG = LIFSchemaConfig.from_environment()
+
+# Extract values for convenience
+ROOT_NODES = CONFIG.all_root_types
+DEFAULT_ROOT_NODE = CONFIG.root_type_name
 LIF_GRAPHQL_API_URL = os.getenv("LIF_GRAPHQL_API_URL", "http://localhost:8002/graphql")
-TOP_K = int(os.getenv("TOP_K", 200))
-MODEL_NAME = "all-MiniLM-L6-v2"
+TOP_K = CONFIG.semantic_search_top_k
+MODEL_NAME = CONFIG.semantic_search_model_name
 
-ATTRIBUTE_KEYS = ["x-queryable", "x-mutable", "DataType", "Required", "Array", "enum"]  # Add more attributes as needed
+ATTRIBUTE_KEYS = DEFAULT_ATTRIBUTE_KEYS
 
 
 # --------- LOAD VECTOR STORE & EMBEDDINGS ---------
 
 # get the OpenAPI specification for the LIF data model from the MDR
 openapi = get_openapi_lif_data_model_from_file()
 
-try:
-    LEAVES = load_schema_leaves(openapi, ROOT_NODE, attribute_keys=ATTRIBUTE_KEYS)
-except Exception as e:
-    logger.critical(f"Failed to load schema leaves: {e}")
-    sys.exit(1)
-
-try:
-    FILTER = build_dynamic_filter_model(LEAVES)
-    Filter = FILTER[ROOT_NODE]
-    logger.info("Dynamic Filter Schema:\n" + json.dumps(Filter.model_json_schema(), indent=2))
-except Exception as e:
-    logger.critical(f"Failed to load build dynamic filter model: {e}")
-    sys.exit(1)
-
-try:
-    MUTATION_MODELS = build_dynamic_mutation_model(LEAVES)
-    MutationModel = MUTATION_MODELS[ROOT_NODE]
-    logger.info("Dynamic Mutation Schema:\n" + json.dumps(MutationModel.model_json_schema(), indent=2))
-except Exception as e:
-    logger.critical(f"Failed to build dynamic mutation model: {e}")
+# Load schema leaves for all root nodes
+ALL_LEAVES: List = []
+LEAVES_BY_ROOT: dict = {}
+
+for root_node in ROOT_NODES:
+    try:
+        root_leaves = load_schema_leaves(openapi, root_node, attribute_keys=ATTRIBUTE_KEYS)
+        LEAVES_BY_ROOT[root_node] = root_leaves
+        ALL_LEAVES.extend(root_leaves)
+        logger.info(f"Loaded {len(root_leaves)} schema leaves for root '{root_node}'")
+    except Exception as e:
+        # Primary root (Person) is required; additional roots are optional
+        if root_node == DEFAULT_ROOT_NODE:
+            logger.critical(f"Failed to load schema leaves for required root '{root_node}': {e}")
+            sys.exit(1)
+        else:
+            logger.warning(f"Failed to load schema leaves for optional root '{root_node}': {e}")
+
+logger.info(f"Total schema leaves loaded: {len(ALL_LEAVES)}")
+
+# Build filter and mutation models for each root
+FILTER_MODELS: dict = {}
+MUTATION_MODELS: dict = {}
+
+for root_node, root_leaves in LEAVES_BY_ROOT.items():
+    try:
+        filter_model = build_dynamic_filter_model(root_leaves)
+        if root_node in filter_model:
+            FILTER_MODELS[root_node] = filter_model[root_node]
+            logger.info(f"Dynamic Filter Schema for '{root_node}':\n" + json.dumps(filter_model[root_node].model_json_schema(), indent=2))
+    except Exception as e:
+        logger.warning(f"Failed to build dynamic filter model for '{root_node}': {e}")
+
+    try:
+        mutation_model = build_dynamic_mutation_model(root_leaves)
+        if root_node in mutation_model:
+            MUTATION_MODELS[root_node] = mutation_model[root_node]
+            logger.info(f"Dynamic Mutation Schema for '{root_node}':\n" + json.dumps(mutation_model[root_node].model_json_schema(), indent=2))
+    except Exception as e:
+        logger.warning(f"Failed to build dynamic mutation model for '{root_node}': {e}")
+
+# Use default root for backwards compatibility
+Filter = FILTER_MODELS.get(DEFAULT_ROOT_NODE)
+MutationModel = MUTATION_MODELS.get(DEFAULT_ROOT_NODE)
+
+if not Filter:
+    logger.critical(f"Failed to build filter model for default root '{DEFAULT_ROOT_NODE}'")
     sys.exit(1)
 
 try:
@@ -66,15 +99,18 @@
     logger.critical(f"Failed to load SentenceTransformer model: {e}")
     sys.exit(1)
 
-# ------ ALWAYS embed only the descriptions ------
-EMBEDDING_TEXTS = [leaf.description for leaf in LEAVES]
+# ------ ALWAYS embed only the descriptions for ALL leaves (all root entities) ------
+EMBEDDING_TEXTS = [leaf.description for leaf in ALL_LEAVES]
 
 try:
     EMBEDDINGS = build_embeddings(EMBEDDING_TEXTS, MODEL)
 except Exception as e:
     logger.critical(f"EMBEDDINGS failed: {e}")
     sys.exit(1)
 
+# Keep a reference to all leaves for search
+LEAVES = ALL_LEAVES
+
 
 mcp = FastMCP(name="LIF-Query-Server")
 
@@ -99,6 +135,7 @@ async def lif_query(
         leaves=LEAVES,
         top_k=TOP_K,
         graphql_url=LIF_GRAPHQL_API_URL,
+        config=CONFIG,
     )
 
 

cloudformation/lif-semantic-search-taskdef-includes.yml

@@ -17,3 +17,7 @@ Environment:
     Value: "openapi_constrained_with_interactions.json"
   - Name: USE_OPENAPI_DATA_MODEL_FROM_FILE
     Value: "false"
+Secrets:
+  - Name: LIF_MDR_API_AUTH_TOKEN
+    ValueFrom:
+      Fn::Sub: "arn:aws:ssm:${AWS::Region}:${AWS::AccountId}:parameter/${EnvironmentName}/${ServiceName}/MdrApiKey"

components/lif/composer/core.py

@@ -41,8 +41,16 @@ def compose_with_fragment_list(lif_record: LIFRecord, lif_fragments: List[LIFFra
 
 
 def adjust_fragment_path_for_root_person_list(fragment_path: str) -> str:
+    """Adjust fragment path to navigate into the person array.
+
+    Handles both lowercase 'person.' and PascalCase 'Person.' prefixes.
+    The internal LIF record structure uses lowercase 'person'.
+    """
     if fragment_path.startswith("person."):
         return "person.0" + fragment_path[6::]
+    elif fragment_path.startswith("Person."):
+        # Convert PascalCase to lowercase for internal navigation
+        return "person.0" + fragment_path[6:]
     else:
         return fragment_path
 
@@ -80,8 +88,8 @@ def add_fragment_items_to_list(list_to_update: list, new_items: list):
         logger.error(f"Expected a list but got: {type(list_to_update)}")
         raise ValueError("Expected a list to update")
     if not new_items:
-        logger.error("No items to add to the list")
-        raise ValueError("No items to add to the list")
+        logger.warning("No items to add to the list, skipping")
+        return
     for new_item in new_items:
         if isinstance(new_item, dict):
             list_to_update.append(new_item)

components/lif/data_source_adapters/lif_to_lif_adapter/graphql_query_all_fields_org2.graphql

@@ -1,49 +1,33 @@
 query GetPersonByIdentifier($identifier: String!, $identifierType: String!) {
-  person(filter: { identifier: { identifier: $identifier, identifierType: $identifierType } }) {
-    name {
+  person(filter: { Identifier: { identifier: $identifier, identifierType: $identifierType } }) {
+    Name {
       informationSourceId
       lastName
       firstName
     }
-    contact {
-      email {
+    Contact {
+      Email {
         informationSourceId
         emailAddress
       }
     }
-    identifier {
+    Identifier {
       informationSourceId
       identifier
   # identifierType
     }
-    employmentLearningExperience {
+    EmploymentLearningExperience {
       informationSourceId
       name
       startDate
       endDate
-      #refPosition {
-      #  name
-      #  informationSourceId
-      #}
-      #assertedByRefOrganization {
-      #  identificationSystem
-      #  name
-      #  organizationType
-      #  informationSourceId
-      #}
-      #offeredByRefOrganization {
-      #  identificationSystem
-      #  name
-      #  organizationType
-      #  informationSourceId
-      #}
-      #approvedByRefOrganization {
-      #  identificationSystem
-      #  name
-      #  organizationType
-      #  informationSourceId
-      #}
-      refCredentialAward {
+      RefPosition {
+        identifier
+        name
+        informationSourceId
+        informationSourceOrganization
+      }
+      RefCredentialAward {
         identifier
         #awardIssueDate
         #credentialAwardee
@@ -52,34 +36,34 @@ query GetPersonByIdentifier($identifier: String!, $identifierType: String!) {
         name
       }
     }
-    positionPreferences {
+    PositionPreferences {
       # informationSourceId
-      travel {
+      Travel {
         percentage
         willingToTravelIndicator
       }
-      relocation {
+      Relocation {
         willingToRelocateIndicator
       }
-      remoteWork {
+      RemoteWork {
         remoteWorkIndicator
       }
       positionTitles
       positionOfferingTypeCodes
       positionScheduleTypeCodes
-      #offeredByRefRemunerationPackage {
-      #  ranges {
-      #    minimumAmount {
+      #OfferedByRefRemunerationPackage {
+      #  Ranges {
+      #    MinimumAmount {
       #      value
       #      currency
       #    }
       #  }
       #  basisCode
       #}
     }
-    employmentPreferences {
+    EmploymentPreferences {
     #  informationSourceId
-    #  offeredByRefOrganization {
+    #  OfferedByRefOrganization {
     #    informationSourceId
     #    name
     #    identificationSystem
@@ -89,11 +73,34 @@ query GetPersonByIdentifier($identifier: String!, $identifierType: String!) {
       organizationTypes
       organizationNames
     }
-    credentialAward {
+    CredentialAward {
       identifier
       awardIssueDate
       credentialAwardee
       informationSourceId
+      InstanceOfRefCredential {
+        informationSourceId
+        informationSourceOrganization
+        identifier
+        name
+      }
+    }
+    CourseLearningExperience {
+      informationSourceId
+      startDate
+      endDate
+      RefCourse {
+        informationSourceId
+        informationSourceOrganization
+        identifier
+        name
+      }
+      RefCredentialAward {
+        informationSourceId
+        informationSourceOrganization
+        identifier
+        name
+      }
     }
   }
 }