refactor: rename ingestor to source throughout codebase

Justfile

@@ -58,6 +58,10 @@ cli *ARGS:
 init FIELD:
     uv run osa field init {{FIELD}}
 
+# Wipe all local OSA data (database, vectors, cache)
+wipe:
+    uv run osa local clean --force
+
 # === Complete Workflow ===
 
 # Set up everything for first time (start DB + run migrations)

osa/application/api/rest/app.py

@@ -11,7 +11,7 @@
 from osa.config import Config, configure_logging
 from osa.domain.shared.error import OSAError
 from osa.infrastructure.event.worker import BackgroundWorker
-from osa.infrastructure.ingest.discovery import validate_ingestors_at_startup
+from osa.infrastructure.source.discovery import validate_sources_at_startup
 from osa.util.di.fastapi import setup_dishka
 
 logger = logging.getLogger(__name__)
@@ -37,8 +37,8 @@ def create_app() -> FastAPI:
     configure_logging(config.logging)
     logger.info("Starting OSA server: %s v%s", config.server.name, config.server.version)
 
-    # Validate ingestor configs at startup (fail fast with clear errors)
-    validate_ingestors_at_startup(config.ingestors)
+    # Validate source configs at startup (fail fast with clear errors)
+    validate_sources_at_startup(config.sources)
 
     app_instance = FastAPI(
         title=config.server.name,

osa/application/di.py

@@ -6,7 +6,7 @@
 from osa.domain.validation.util.di import ValidationProvider
 from osa.infrastructure.event.di import EventProvider
 from osa.infrastructure.index.di import IndexProvider
-from osa.infrastructure.ingest.di import IngestProvider
+from osa.infrastructure.source.di import SourceProvider
 from osa.infrastructure.oci import OciProvider
 from osa.infrastructure.persistence import PersistenceProvider
 from osa.util.di.scope import Scope
@@ -22,7 +22,7 @@ def create_container() -> AsyncContainer:
         PersistenceProvider(),
         OciProvider(),
         IndexProvider(),
-        IngestProvider(),
+        SourceProvider(),
         EventProvider(),
         DepositionProvider(),
         ValidationProvider(),

osa/cli/commands/local.py

@@ -37,9 +37,9 @@
 # logging:
 #   level: "INFO"
 
-# GEO Ingestor - pulls from NCBI Gene Expression Omnibus via Entrez API
-ingestors:
-  - ingestor: geo-entrez
+# GEO Source - pulls from NCBI Gene Expression Omnibus via Entrez API
+sources:
+  - source: geo-entrez
     config:
       record_type: gse  # gse (~250k all) or gds (~5k curated)
       email: your@email.com  # Required by NCBI - please update this
@@ -77,9 +77,9 @@
 # logging:
 #   level: "INFO"
 
-# Add your ingestors here:
-# ingestors:
-#   - ingestor: geo-entrez
+# Add your sources here:
+# sources:
+#   - source: geo-entrez
 #     config:
 #       email: your@email.com
 

osa/config.py

@@ -34,41 +34,41 @@ class IndexConfig(BaseModel):
 
 
 # =============================================================================
-# Ingest Configuration
+# Source Configuration
 # =============================================================================
 
 
-class IngestSchedule(BaseModel):
-    """Schedule configuration for an ingestor."""
+class SourceSchedule(BaseModel):
+    """Schedule configuration for a source."""
 
     cron: str  # Cron expression (e.g., "0 * * * *" for hourly)
     limit: int | None = None  # Optional limit per scheduled run
 
 
 class InitialRun(BaseModel):
-    """Initial run configuration for an ingestor."""
+    """Initial run configuration for a source."""
 
     enabled: bool = False
     limit: int | None = 10  # Limit records for initial run
     since: datetime | None = None  # Optional: bootstrap from specific date
 
 
-class IngestConfig(BaseModel):
-    """Configuration for an ingestor.
+class SourceConfig(BaseModel):
+    """Configuration for a source.
 
-    The `config` field is validated at runtime based on the ingestor type,
-    allowing external ingestors to define their own config schemas.
+    The `config` field is validated at runtime based on the source type,
+    allowing external sources to define their own config schemas.
     """
 
-    ingestor: str  # "geo-entrez", etc. - matches entry point name
-    config: dict[str, Any] = {}  # Validated at runtime by ingestor's config_class
-    schedule: IngestSchedule | None = None  # Optional: if set, runs on schedule
+    source: str  # "geo-entrez", etc. - matches entry point name
+    config: dict[str, Any] = {}  # Validated at runtime by source's config_class
+    schedule: SourceSchedule | None = None  # Optional: if set, runs on schedule
     initial_run: InitialRun | None = None  # Optional: if set, runs on startup
 
     @property
     def name(self) -> str:
-        """The ingestor name (same as ingestor type for now)."""
-        return self.ingestor
+        """The source name (same as source type for now)."""
+        return self.source
 
 
 # =============================================================================
@@ -147,7 +147,7 @@ class Config(BaseSettings):
     database: DatabaseConfig = DatabaseConfig()
     logging: LoggingConfig = LoggingConfig()
     indexes: list[IndexConfig] = []  # list of index configs
-    ingestors: list[IngestConfig] = []  # list of ingestor configs
+    sources: list[SourceConfig] = []  # list of source configs
 
     model_config = {
         "env_prefix": "OSA_",

osa/domain/deposition/command/submit.py

@@ -30,7 +30,7 @@ async def run(self, cmd: SubmitDeposition) -> DepositionSubmitted:
             event = DepositionSubmittedEvent(
                 id=EventId(uuid4()),
                 deposition_id=cmd.srn,
-                metadata={},  # Empty metadata for direct submission (not from ingest)
+                metadata={},  # Empty metadata for direct submission (not from source)
             )
             await self.outbox.append(event)
 

osa/domain/deposition/model/aggregate.py

@@ -13,7 +13,7 @@ class Deposition(Aggregate, Generic[T]):
     metadata: T
     files: list[DepositionFile] = []
     record_srn: RecordSRN | None = None
-    provenance: dict[str, Any] = {}  # Ingestor info, source tracking
+    provenance: dict[str, Any] = {}  # Source info, provenance tracking
 
     def remove_all_files(self) -> None:
         self.files = []