Phase 4 ingestion: exclusion/provenance/incremental/graph tests

Makefile

@@ -23,7 +23,8 @@ BIN := bin
 DIST := dist
 
 .PHONY: build dist generate dev test validate validate-self-test fmt vet clean help \
-        corpus corpus-sync corpus-rebuild corpus-audit corpus-verify corpus-demo corpus-test
+        corpus corpus-sync corpus-rebuild corpus-offline corpus-audit corpus-verify \
+        corpus-demo corpus-test corpus-graph corpus-scan corpus-sources
 
 help:
 	@echo "make build            templ generate, compile bin/, no dist"
@@ -36,11 +37,15 @@ help:
 	@echo "make clean            remove bin/ and dist/"
 	@echo ""
 	@echo "corpus (Phase 4, python3 -m corpus.cli):"
-	@echo "make corpus           rebuild the corpus from content/ (drops the collection)"
+	@echo "make corpus           rebuild the pool from the estate (drops both collections)"
+	@echo "make corpus-offline   rebuild content/ only, no Gitea (recovery and CI)"
 	@echo "make corpus-sync      incremental update; only changed documents are re-embedded"
 	@echo "make corpus-audit     freshness + drift audit (exit 1 on findings)"
 	@echo "make corpus-verify    check the index against content/ and Qdrant"
 	@echo "make corpus-demo      same query with and without an area filter"
+	@echo "make corpus-graph Q=  query graph nodes and edges (with their source note)"
+	@echo "make corpus-scan      search the pool for credential-shaped content"
+	@echo "make corpus-sources   show the platform guides and the last harvest"
 	@echo "make corpus-test      corpus unit tests (no container, no network)"
 
 build: generate
@@ -87,6 +92,9 @@ corpus: corpus-rebuild
 corpus-rebuild:
 	@$(CORPUS) rebuild
 
+corpus-offline:
+	@$(CORPUS) --offline rebuild
+
 corpus-sync:
 	@$(CORPUS) sync
 
@@ -99,6 +107,16 @@ corpus-verify:
 corpus-demo:
 	@$(CORPUS) demo-filter --query "distributed audio endpoints" --area edge
 
+corpus-graph:
+	@test -n "$(Q)" || { echo "usage: make corpus-graph Q='photo pipeline'"; exit 2; }
+	@$(CORPUS) graph --query "$(Q)"
+
+corpus-scan:
+	@$(CORPUS) scan
+
+corpus-sources:
+	@$(CORPUS) sources
+
 corpus-test:
 	@$(PYTHON) -m unittest discover -s corpus/tests -t .