XY-900: Add graph/RAG scored smoke adapter evidence

Makefile.toml

@@ -811,7 +811,7 @@ workspace = false
 command = "bash"
 args = [
 	"-lc",
-	"set -euo pipefail; docker compose -f docker-compose.baseline.yml run --build --rm baseline-runner bash scripts/real-world-live-adapters.sh",
+	"set -euo pipefail; lightrag_start=\"$(printenv ELF_LIGHTRAG_CONTEXT_START || true)\"; graphiti_start=\"$(printenv ELF_GRAPHITI_ZEP_SMOKE_START || true)\"; status=0; if [ \"$lightrag_start\" = \"1\" ]; then docker compose -f docker-compose.baseline.yml --profile lightrag up -d lightrag; fi; if [ \"$graphiti_start\" = \"1\" ]; then docker compose -f docker-compose.baseline.yml --profile graphiti-zep up -d graphiti-falkordb; fi; docker compose -f docker-compose.baseline.yml run --build --rm -e ELF_REAL_WORLD_LIVE_ENABLE_RAGFLOW -e ELF_REAL_WORLD_LIVE_ENABLE_LIGHTRAG -e ELF_REAL_WORLD_LIVE_ENABLE_GRAPHRAG -e ELF_REAL_WORLD_LIVE_ENABLE_GRAPHITI_ZEP -e ELF_REAL_WORLD_LIVE_ENABLE_GRAPHIFY -e ELF_RAGFLOW_SMOKE_START -e ELF_RAGFLOW_SMOKE_ACCEPT_RESOURCE_ENVELOPE -e ELF_RAGFLOW_SMOKE_ALLOW_ARM -e ELF_RAGFLOW_SMOKE_PULL_IMAGE -e ELF_RAGFLOW_SMOKE_CLEANUP -e ELF_RAGFLOW_SMOKE_DEVICE -e ELF_RAGFLOW_API_PORT -e ELF_RAGFLOW_API_BASE -e ELF_RAGFLOW_API_KEY -e RAGFLOW_API_KEY -e ELF_RAGFLOW_SMOKE_STARTUP_ATTEMPTS -e ELF_RAGFLOW_SMOKE_STARTUP_INTERVAL_SECONDS -e ELF_RAGFLOW_SMOKE_COMPOSE_TIMEOUT_SECONDS -e ELF_RAGFLOW_REPO_URL -e ELF_RAGFLOW_REF -e ELF_RAGFLOW_IMAGE -e ELF_RAGFLOW_COMPOSE_PROJECT -e ELF_LIGHTRAG_CONTEXT_START -e ELF_LIGHTRAG_API_BASE -e ELF_LIGHTRAG_ADAPTER_ID -e ELF_LIGHTRAG_ADAPTER_NAME -e ELF_LIGHTRAG_STARTUP_ATTEMPTS -e ELF_LIGHTRAG_STARTUP_INTERVAL_SECONDS -e ELF_LIGHTRAG_INDEX_ATTEMPTS -e ELF_LIGHTRAG_INDEX_INTERVAL_SECONDS -e ELF_GRAPHRAG_SMOKE_RUN -e ELF_GRAPHRAG_SMOKE_WORK_DIR -e ELF_GRAPHRAG_SMOKE_INSTALL -e ELF_GRAPHRAG_VERSION -e ELF_GRAPHRAG_PACKAGE -e ELF_GRAPHRAG_REF -e ELF_GRAPHRAG_CHAT_MODEL -e ELF_GRAPHRAG_EMBEDDING_MODEL -e ELF_GRAPHRAG_API_BASE -e ELF_GRAPHRAG_API_KEY -e ELF_GRAPHRAG_INDEX_METHOD -e ELF_GRAPHRAG_QUERY_METHOD -e ELF_GRAPHRAG_TIMEOUT_SECONDS -e ELF_GRAPHRAG_MAX_DOCS -e ELF_GRAPHRAG_MAX_INPUT_CHARS -e ELF_GRAPHITI_ZEP_SMOKE_START -e ELF_GRAPHITI_ZEP_SMOKE_RUN -e ELF_GRAPHITI_ZEP_SMOKE_WORK_DIR -e ELF_GRAPHITI_ZEP_SMOKE_INSTALL -e ELF_GRAPHITI_ZEP_VERSION -e ELF_GRAPHITI_ZEP_PACKAGE -e ELF_GRAPHITI_ZEP_REF -e ELF_GRAPHITI_ZEP_API_BASE -e ELF_GRAPHITI_ZEP_API_KEY -e ELF_GRAPHITI_ZEP_LLM_MODEL -e ELF_GRAPHITI_ZEP_EMBEDDING_MODEL -e ELF_GRAPHITI_ZEP_FALKORDB_HOST -e ELF_GRAPHITI_ZEP_FALKORDB_PORT -e ELF_GRAPHITI_ZEP_FALKORDB_DATABASE -e ELF_GRAPHITI_ZEP_TIMEOUT_SECONDS -e ELF_GRAPHITI_ZEP_STARTUP_ATTEMPTS -e ELF_GRAPHITI_ZEP_STARTUP_INTERVAL_SECONDS -e ELF_GRAPHIFY_SMOKE_RUN -e ELF_GRAPHIFY_SMOKE_WORK_DIR -e ELF_GRAPHIFY_SMOKE_INSTALL -e ELF_GRAPHIFY_PACKAGE -e ELF_GRAPHIFY_REF -e ELF_GRAPHIFY_TIMEOUT_SECONDS -e ELF_GRAPHIFY_QUERY_BUDGET baseline-runner bash scripts/real-world-live-adapters.sh || status=$?; if [ \"$lightrag_start\" = \"1\" ]; then docker compose -f docker-compose.baseline.yml --profile lightrag stop lightrag lightrag-mock-provider >/dev/null 2>&1 || true; fi; if [ \"$graphiti_start\" = \"1\" ]; then docker compose -f docker-compose.baseline.yml --profile graphiti-zep stop graphiti-falkordb >/dev/null 2>&1 || true; fi; exit \"$status\"",
 ]
 
 

README.md

@@ -161,10 +161,18 @@ provider-backed ELF evidence was required.
   1 incomplete, 2 blocked, and 12 not_encoded jobs.
 - Expanded adapter-pack coverage after XY-834: the real-world external adapter
   manifest now includes `research_gate` records for RAGFlow, LightRAG, GraphRAG,
-  Graphiti/Zep, Letta, LangGraph, nanograph, llm-wiki, gbrain, graphify, and deeper
-  qmd/OpenViking profiles. These records carry source/setup/runtime/resource/retry
-  metadata and typed `blocked`, `incomplete`, `wrong_result`, or `not_encoded` states;
-  they are not fixture-backed or live adapter pass evidence.
+  Graphiti/Zep, Letta, LangGraph, nanograph, llm-wiki, gbrain, and deeper
+  qmd/OpenViking profiles, while graphify now has a scored tiny Docker smoke record.
+  These records carry source/setup/runtime/resource/retry metadata and typed
+  `blocked`, `incomplete`, `wrong_result`, or `not_encoded` states; they are not
+  fixture-backed or live adapter pass evidence.
+- Graph/RAG scored-smoke promotion after XY-900: RAGFlow, LightRAG, GraphRAG,
+  Graphiti/Zep, and graphify smokes now emit scored or typed non-pass
+  `real_world_job` adapter reports when run. graphify currently reaches a tiny Docker
+  graph/report smoke and scores `wrong_result`; the other in-scope projects remain
+  typed blocked or incomplete without explicit service, resource, or provider setup.
+  These reports preserve the smoke-only boundary and do not create an ELF win claim
+  against graph/RAG strengths.
 - The benchmark runner and report publisher are checked in and Docker-isolated:
   `cargo make baseline-live-docker`, `cargo make baseline-backfill-docker`,
   `cargo make baseline-production-private-addendum`,
@@ -183,6 +191,7 @@ Detailed evidence and interpretation:
 - [Real-World Comparison Report - June 10, 2026](docs/guide/benchmarking/2026-06-10-real-world-comparison-report.md)
 - [Live Real-World Adapter Sweep Report - June 10, 2026](docs/guide/benchmarking/2026-06-10-live-real-world-sweep-report.md)
 - [Post-Adapter Production Adoption Refresh - June 10, 2026](docs/guide/benchmarking/2026-06-10-production-adoption-refresh.md)
+- [Graph/RAG Scored Smoke Adapter Report - June 11, 2026](docs/guide/benchmarking/2026-06-11-graph-rag-scored-smoke-adapter-report.md)
 - [Live Baseline Benchmark Runbook](docs/guide/benchmarking/live_baseline_benchmark.md)
 - [Single-User Production Runbook](docs/guide/single_user_production.md)
 - Benchmark contract:
@@ -254,6 +263,9 @@ Detailed comparison, mechanism-level analysis, and source map:
 - [Real-World Comparison Report - June 10, 2026](docs/guide/benchmarking/2026-06-10-real-world-comparison-report.md)
 - [Live Real-World Adapter Sweep Report - June 10, 2026](docs/guide/benchmarking/2026-06-10-live-real-world-sweep-report.md)
 - [Post-Adapter Production Adoption Refresh - June 10, 2026](docs/guide/benchmarking/2026-06-10-production-adoption-refresh.md)
+- [Competitor Strength Evidence Matrix - June 11, 2026](docs/guide/benchmarking/2026-06-11-competitor-strength-evidence-matrix.md)
+- [Temporal History Competitor Gap Report - June 11, 2026](docs/guide/benchmarking/2026-06-11-temporal-history-competitor-gap-report.md)
+- [Graph/RAG Scored Smoke Adapter Report - June 11, 2026](docs/guide/benchmarking/2026-06-11-graph-rag-scored-smoke-adapter-report.md)
 - [Live Baseline Benchmark Runbook](docs/guide/benchmarking/live_baseline_benchmark.md)
 - [Real-World Agent Memory Benchmark](docs/guide/benchmarking/real_world_agent_memory_benchmark.md)
 - [External Memory Improvement Plan](docs/guide/research/external_memory_improvement_plan.md)
@@ -263,7 +275,7 @@ Detailed comparison, mechanism-level analysis, and source map:
 - [Real-World Benchmark Dimension Research Run](docs/research/2026-06-09-xy-841-external-memory-benchmark-dimensions.json)
 - [RAG/Graph Adapter Feasibility Research Run](docs/research/2026-06-10-xy-882-rag-graph-adapter-feasibility.json)
 
-Latest real-world benchmark report: June 10, 2026. Latest external research refresh:
+Latest real-world benchmark report: June 11, 2026. Latest external research refresh:
 June 10, 2026.
 
 ## Documentation