Cor-Incorporated · terisuke · May 3, 2026 · May 2, 2026 · May 2, 2026 · May 2, 2026
diff --git a/.env.evo-x2.example b/.env.evo-x2.example
@@ -1,20 +1,28 @@
 PORT=8080
 WORKFLOW_STORE_PATH=data/workflow_store.json
 LLM_RUNTIME=remote
-LLM_BASE_URL=http://evo-x2:11434/v1
+EVO_X2_TAILNET_HOST=evo-x2.tailb30e58.ts.net
+EVO_X2_SSH_HOST=evo-x2
+EVO_X2_SSH_LOCAL_PORT=21434
+LLM_BASE_URL=http://evo-x2.tailb30e58.ts.net/v1
 LLM_MODEL=gemma4:31b
 LLM_TIMEOUT_SECONDS=900
 
-# Use smaller models for quick tests, and larger models for final drafts.
-STYLE_LLM_MODEL=gemma4:latest
-BRIEF_LLM_MODEL=gemma4:e2b
-ARTICLE_LLM_MODEL=gemma4:latest
+# Primary route is Evo X2 Ollama's OpenAI-compatible API.
+# Use smaller models for source summarization, a stronger reasoning model for
+# questions, and the high-quality Japanese draft model for final output.
+STYLE_LLM_MODEL=gemma4:e2b
+BRIEF_LLM_MODEL=qwen3.6:27b
+ARTICLE_LLM_MODEL=gemma4:e2b
 DRAFT_LLM_MODEL=gemma4:31b
+VERIFY_LLM_MODEL=gemma4:latest
 
-# Used only if Evo X2 is unavailable and a local llama.cpp server is already running.
-FALLBACK_LLM_BASE_URL=http://127.0.0.1:8081/v1
-# The fallback client reuses the selected model name for each phase.
-# STYLE_FALLBACK_LLM_MODEL=gemma4:latest
-# BRIEF_FALLBACK_LLM_MODEL=gemma4:e2b
-# ARTICLE_FALLBACK_LLM_MODEL=gemma4:latest
-# DRAFT_FALLBACK_LLM_MODEL=gemma4:31b
+# Ordered fallback chain:
+# 1. Evo X2 llama.cpp over Tailnet/Caddy.
+# 2. Last-resort local llama.cpp on this workstation.
+LLM_FALLBACK_BASE_URLS=http://evo-x2.tailb30e58.ts.net/llama/v1,http://127.0.0.1:8081/v1
+STYLE_LLM_FALLBACK_MODELS=gemma-4-E2B-it-Q8_0.gguf,gemma4:e2b
+BRIEF_LLM_FALLBACK_MODELS=gemma-4-E2B-it-Q8_0.gguf,qwen3:30b-a3b
+ARTICLE_LLM_FALLBACK_MODELS=gemma-4-E2B-it-Q8_0.gguf,gemma4:e2b
+DRAFT_LLM_FALLBACK_MODELS=gemma-4-E2B-it-Q8_0.gguf,qwen3:30b-a3b
+VERIFY_LLM_FALLBACK_MODELS=gemma-4-E2B-it-Q8_0.gguf,gemma4:e2b
diff --git a/.env.example b/.env.example
@@ -5,13 +5,21 @@ LLM_BASE_URL=http://127.0.0.1:8081/v1
 LLM_MODEL=gemma4:31b
 LLM_TIMEOUT_SECONDS=180
 # Optional per-phase overrides:
-# STYLE_LLM_MODEL=gemma4:latest
-# BRIEF_LLM_MODEL=gemma4:e2b
-# ARTICLE_LLM_MODEL=gemma4:latest
+# STYLE_LLM_MODEL=gemma4:e2b
+# BRIEF_LLM_MODEL=qwen3.6:27b
+# ARTICLE_LLM_MODEL=gemma4:e2b
 # DRAFT_LLM_MODEL=gemma4:31b
+# VERIFY_LLM_MODEL=gemma4:latest
+# Ordered fallback chain. Use comma-separated OpenAI-compatible base URLs.
+# LLM_FALLBACK_BASE_URLS=http://remote-llama/v1,http://127.0.0.1:8081/v1
+# Optional comma-separated per-phase fallback model names:
+# STYLE_LLM_FALLBACK_MODELS=gemma-4-E2B-it-Q8_0.gguf,gemma4:e2b
+# BRIEF_LLM_FALLBACK_MODELS=gemma-4-E2B-it-Q8_0.gguf,qwen3:30b-a3b
+# ARTICLE_LLM_FALLBACK_MODELS=gemma-4-E2B-it-Q8_0.gguf,gemma4:e2b
+# DRAFT_LLM_FALLBACK_MODELS=gemma-4-E2B-it-Q8_0.gguf,qwen3:30b-a3b
+# VERIFY_LLM_FALLBACK_MODELS=gemma-4-E2B-it-Q8_0.gguf,gemma4:e2b
+# Legacy single fallback remains supported:
 # FALLBACK_LLM_BASE_URL=http://127.0.0.1:8081/v1
-# フォールバック時のモデル名は選択中のフェーズ別モデルを引き継ぎます。
-# 明示的に変える場合だけ STYLE_FALLBACK_LLM_MODEL などを設定してください。
 LLAMACPP_HOST=127.0.0.1
 LLAMACPP_PORT=8081
 LLAMACPP_BASE_URL=http://127.0.0.1:8081/v1

diff --git a/.gitignore b/.gitignore
@@ -28,7 +28,7 @@ Thumbs.db
 bin/
 dist/
 tmp/
-server
+/server
 data/
 
 # ログ関連
@@ -39,6 +39,11 @@ logs/
 vendor/
 node_modules/
 
+# Python/E2E
+__pycache__/
+*.py[cod]
+.pytest_cache/
+
 # その他
 *.bak
 *.tmp

diff --git a/Makefile b/Makefile
@@ -6,41 +6,122 @@ export
 endif
 
 PORT ?= 8080
-LLM_RUNTIME ?= local
-LLM_BASE_URL ?= http://$(LLAMACPP_HOST):$(LLAMACPP_PORT)/v1
+EVO_X2_TAILNET_HOST ?= evo-x2.tailb30e58.ts.net
+EVO_X2_SSH_HOST ?= evo-x2
+EVO_X2_SSH_LOCAL_PORT ?= 21434
+EVO_X2_OLLAMA_LLM_BASE_URL ?= http://$(EVO_X2_TAILNET_HOST)/v1
+EVO_X2_LLAMA_CPP_LLM_BASE_URL ?= http://$(EVO_X2_TAILNET_HOST)/llama/v1
+EVO_X2_LLAMA_CPP_SERVICE ?= note-maker-llama-cpp.service
+EVO_X2_LLAMA_CPP_PROFILE ?= fallback-gemma-e2b
+EVO_X2_LLAMA_CPP_APPLY ?= 0
+EVO_X2_LLAMA_CPP_ALLOW_RESTART ?= 0
+EVO_X2_LLM_BASE_URL ?= $(EVO_X2_OLLAMA_LLM_BASE_URL)
+EVO_X2_SSH_LLM_BASE_URL ?= http://127.0.0.1:$(EVO_X2_SSH_LOCAL_PORT)/v1
+LLM_RUNTIME ?= remote
+LLM_BASE_URL ?= $(EVO_X2_LLM_BASE_URL)
 LLM_MODEL ?= gemma4:31b
-EVO_X2_LLM_BASE_URL ?= http://evo-x2:11434/v1
 EVO_X2_LLM_MODEL ?= gemma4:31b
-EVO_X2_BRIEF_LLM_MODEL ?= gemma4:e2b
-EVO_X2_STYLE_LLM_MODEL ?= gemma4:latest
-EVO_X2_ARTICLE_LLM_MODEL ?= gemma4:latest
+EVO_X2_BRIEF_LLM_MODEL ?= qwen3.6:27b
+EVO_X2_STYLE_LLM_MODEL ?= gemma4:e2b
+EVO_X2_ARTICLE_LLM_MODEL ?= gemma4:e2b
 EVO_X2_DRAFT_LLM_MODEL ?= gemma4:31b
+EVO_X2_VERIFY_LLM_MODEL ?= gemma4:latest
 FALLBACK_LLM_BASE_URL ?= http://127.0.0.1:8081/v1
+LLM_FALLBACK_BASE_URLS ?= $(EVO_X2_LLAMA_CPP_LLM_BASE_URL),$(FALLBACK_LLM_BASE_URL)
+EVO_X2_LLAMA_CPP_MODEL ?= gemma-4-E2B-it-Q8_0.gguf
+EVO_X2_LLAMA_CPP_STYLE_MODEL ?= $(EVO_X2_LLAMA_CPP_MODEL)
+EVO_X2_LLAMA_CPP_BRIEF_MODEL ?= $(EVO_X2_LLAMA_CPP_MODEL)
+EVO_X2_LLAMA_CPP_ARTICLE_MODEL ?= $(EVO_X2_LLAMA_CPP_MODEL)
+EVO_X2_LLAMA_CPP_DRAFT_MODEL ?= $(EVO_X2_LLAMA_CPP_MODEL)
+EVO_X2_LLAMA_CPP_VERIFY_MODEL ?= $(EVO_X2_LLAMA_CPP_MODEL)
+STYLE_LLM_FALLBACK_MODELS ?= $(EVO_X2_LLAMA_CPP_MODEL),gemma4:e2b
+BRIEF_LLM_FALLBACK_MODELS ?= $(EVO_X2_LLAMA_CPP_MODEL),qwen3:30b-a3b
+ARTICLE_LLM_FALLBACK_MODELS ?= $(EVO_X2_LLAMA_CPP_MODEL),gemma4:e2b
+DRAFT_LLM_FALLBACK_MODELS ?= $(EVO_X2_LLAMA_CPP_MODEL),qwen3:30b-a3b
+VERIFY_LLM_FALLBACK_MODELS ?= $(EVO_X2_LLAMA_CPP_MODEL),gemma4:e2b
+LLM_STREAM_FIRST_BYTE_TIMEOUT_SECONDS ?= 45
+LLM_STREAM_IDLE_TIMEOUT_SECONDS ?= 45
 LLAMACPP_HOST ?= 127.0.0.1
 LLAMACPP_PORT ?= 8081
 LLAMACPP_BASE_URL ?= $(LLM_BASE_URL)
 LLAMACPP_MODEL ?= gemma4:31b
 LLAMACPP_HF_REPO ?= ggml-org/gemma-4-31B-it-GGUF
 LLAMACPP_HF_FILE ?= gemma-4-31B-it-Q4_K_M.gguf
+LOCAL_LLAMACPP_FALLBACK_BASE_URL ?= http://127.0.0.1:8081/v1
+LOCAL_LLAMACPP_FALLBACK_MODEL ?= qwen3:30b-a3b
+LOCAL_LLAMACPP_FALLBACK_VERIFY_MODEL ?= $(LOCAL_LLAMACPP_FALLBACK_MODEL)
+LOCAL_LLAMACPP_FALLBACK_LOAD_FLAGS ?=
+LOCAL_LLAMACPP_FALLBACK_OUTPUT_DIR ?= tmp/local_llamacpp_fallback
+LOCAL_LLAMACPP_FALLBACK_MIN_STYLE_SCORE ?= 82
+LOCAL_LLAMACPP_FALLBACK_MIN_KEYWORD_OVERLAP ?= 70
+LOCAL_LLAMACPP_FALLBACK_MIN_DRAFT_RUNES ?= 2800
+LOCAL_LLAMACPP_FALLBACK_TIMEOUT_SECONDS ?= 900
+LOCAL_LLAMACPP_FALLBACK_MAX_ATTEMPTS ?= 2
 LLAMA_SERVER ?= llama-server
 
-.PHONY: app dev evo-x2 remote evo-x2-models scenario-evo-x2 server llama check
+.PHONY: app launcher launcher-local launcher-status launcher-check dev evo-x2 remote evo-x2-preflight evo-x2-models evo-x2-ssh-models evo-x2-llama-status evo-x2-llama-plan evo-x2-llama-start evo-x2-llama-swap evo-x2-llama-check scenario-evo-x2 scenario-evo-x2-llama-brief-draft scenario-local-llamacpp-fallback scenario-media-matrix-live server llama check e2e
 
-app: dev
+app: launcher
+
+launcher:
+	./scripts/launcher.sh
+
+launcher-local:
+	NOTE_MAKER_START_LOCAL_LLM=1 ./scripts/launcher.sh --local-llm
+
+launcher-status:
+	./scripts/launcher.sh --status
+
+launcher-check:
+	./scripts/check-launcher.sh
 
 dev:
 	./scripts/dev.sh
 
 evo-x2: remote
 
-remote:
-	NOTE_MAKER_SKIP_ENV=1 LLM_RUNTIME=remote LLM_BASE_URL="$(EVO_X2_LLM_BASE_URL)" LLM_MODEL="$(EVO_X2_LLM_MODEL)" STYLE_LLM_MODEL="$(EVO_X2_STYLE_LLM_MODEL)" BRIEF_LLM_MODEL="$(EVO_X2_BRIEF_LLM_MODEL)" ARTICLE_LLM_MODEL="$(EVO_X2_ARTICLE_LLM_MODEL)" DRAFT_LLM_MODEL="$(EVO_X2_DRAFT_LLM_MODEL)" FALLBACK_LLM_BASE_URL="$(FALLBACK_LLM_BASE_URL)" ./scripts/dev.sh
+remote: evo-x2-preflight
+	NOTE_MAKER_SKIP_ENV=1 LLM_RUNTIME=remote LLM_BASE_URL="$(EVO_X2_LLM_BASE_URL)" LLM_MODEL="$(EVO_X2_LLM_MODEL)" STYLE_LLM_MODEL="$(EVO_X2_STYLE_LLM_MODEL)" BRIEF_LLM_MODEL="$(EVO_X2_BRIEF_LLM_MODEL)" ARTICLE_LLM_MODEL="$(EVO_X2_ARTICLE_LLM_MODEL)" DRAFT_LLM_MODEL="$(EVO_X2_DRAFT_LLM_MODEL)" VERIFY_LLM_MODEL="$(EVO_X2_VERIFY_LLM_MODEL)" LLM_FALLBACK_BASE_URLS="$(LLM_FALLBACK_BASE_URLS)" STYLE_LLM_FALLBACK_MODELS="$(STYLE_LLM_FALLBACK_MODELS)" BRIEF_LLM_FALLBACK_MODELS="$(BRIEF_LLM_FALLBACK_MODELS)" ARTICLE_LLM_FALLBACK_MODELS="$(ARTICLE_LLM_FALLBACK_MODELS)" DRAFT_LLM_FALLBACK_MODELS="$(DRAFT_LLM_FALLBACK_MODELS)" VERIFY_LLM_FALLBACK_MODELS="$(VERIFY_LLM_FALLBACK_MODELS)" ./scripts/dev.sh
 
-evo-x2-models:
+evo-x2-preflight:
+	EVO_X2_TAILNET_HOST="$(EVO_X2_TAILNET_HOST)" EVO_X2_LLM_BASE_URL="$(EVO_X2_LLM_BASE_URL)" ./scripts/evo-x2-tailnet-preflight.sh
+
+evo-x2-models: evo-x2-preflight
 	curl -s "$(EVO_X2_LLM_BASE_URL)/models"
 
-scenario-evo-x2:
-	RUN_NOTE_SCENARIO=1 RUN_LOCAL_LLM_SCENARIO=1 LLM_BASE_URL="$(EVO_X2_LLM_BASE_URL)" LLM_MODEL="$(EVO_X2_LLM_MODEL)" STYLE_LLM_MODEL="$(EVO_X2_STYLE_LLM_MODEL)" BRIEF_LLM_MODEL="$(EVO_X2_BRIEF_LLM_MODEL)" ARTICLE_LLM_MODEL="$(EVO_X2_ARTICLE_LLM_MODEL)" DRAFT_LLM_MODEL="$(EVO_X2_DRAFT_LLM_MODEL)" LLM_TIMEOUT_SECONDS=900 FALLBACK_LLM_BASE_URL="$(FALLBACK_LLM_BASE_URL)" SCENARIO_MIN_STYLE_SCORE=80 SCENARIO_MIN_DRAFT_RUNES=2800 DRAFT_MAX_ATTEMPTS=2 go run ./cmd/scenario/full_workflow
+evo-x2-ssh-models:
+	EVO_X2_SSH_HOST="$(EVO_X2_SSH_HOST)" EVO_X2_SSH_LOCAL_PORT="$(EVO_X2_SSH_LOCAL_PORT)" EVO_X2_LLM_BASE_URL="$(EVO_X2_SSH_LLM_BASE_URL)" ./scripts/evo-x2-ssh-preflight.sh
+	curl -s "$(EVO_X2_SSH_LLM_BASE_URL)/models"
+
+evo-x2-llama-status:
+	EVO_X2_TAILNET_HOST="$(EVO_X2_TAILNET_HOST)" EVO_X2_SSH_HOST="$(EVO_X2_SSH_HOST)" EVO_X2_OLLAMA_LLM_BASE_URL="$(EVO_X2_OLLAMA_LLM_BASE_URL)" EVO_X2_LLAMA_CPP_LLM_BASE_URL="$(EVO_X2_LLAMA_CPP_LLM_BASE_URL)" EVO_X2_LLAMA_CPP_SERVICE="$(EVO_X2_LLAMA_CPP_SERVICE)" EVO_X2_LLAMA_CPP_PROFILE="$(EVO_X2_LLAMA_CPP_PROFILE)" EVO_X2_LLAMA_CPP_APPLY="$(EVO_X2_LLAMA_CPP_APPLY)" EVO_X2_LLAMA_CPP_ALLOW_RESTART="$(EVO_X2_LLAMA_CPP_ALLOW_RESTART)" ./scripts/evo-x2-llama-swap.sh inspect
+
+evo-x2-llama-plan:
+	EVO_X2_TAILNET_HOST="$(EVO_X2_TAILNET_HOST)" EVO_X2_SSH_HOST="$(EVO_X2_SSH_HOST)" EVO_X2_OLLAMA_LLM_BASE_URL="$(EVO_X2_OLLAMA_LLM_BASE_URL)" EVO_X2_LLAMA_CPP_LLM_BASE_URL="$(EVO_X2_LLAMA_CPP_LLM_BASE_URL)" EVO_X2_LLAMA_CPP_SERVICE="$(EVO_X2_LLAMA_CPP_SERVICE)" EVO_X2_LLAMA_CPP_PROFILE="$(EVO_X2_LLAMA_CPP_PROFILE)" EVO_X2_LLAMA_CPP_APPLY="$(EVO_X2_LLAMA_CPP_APPLY)" EVO_X2_LLAMA_CPP_ALLOW_RESTART="$(EVO_X2_LLAMA_CPP_ALLOW_RESTART)" ./scripts/evo-x2-llama-swap.sh plan
+
+evo-x2-llama-start:
+	EVO_X2_TAILNET_HOST="$(EVO_X2_TAILNET_HOST)" EVO_X2_SSH_HOST="$(EVO_X2_SSH_HOST)" EVO_X2_OLLAMA_LLM_BASE_URL="$(EVO_X2_OLLAMA_LLM_BASE_URL)" EVO_X2_LLAMA_CPP_LLM_BASE_URL="$(EVO_X2_LLAMA_CPP_LLM_BASE_URL)" EVO_X2_LLAMA_CPP_SERVICE="$(EVO_X2_LLAMA_CPP_SERVICE)" EVO_X2_LLAMA_CPP_PROFILE="$(EVO_X2_LLAMA_CPP_PROFILE)" EVO_X2_LLAMA_CPP_APPLY="$(EVO_X2_LLAMA_CPP_APPLY)" EVO_X2_LLAMA_CPP_ALLOW_RESTART="$(EVO_X2_LLAMA_CPP_ALLOW_RESTART)" ./scripts/evo-x2-llama-swap.sh start
+
+evo-x2-llama-swap:
+	EVO_X2_TAILNET_HOST="$(EVO_X2_TAILNET_HOST)" EVO_X2_SSH_HOST="$(EVO_X2_SSH_HOST)" EVO_X2_OLLAMA_LLM_BASE_URL="$(EVO_X2_OLLAMA_LLM_BASE_URL)" EVO_X2_LLAMA_CPP_LLM_BASE_URL="$(EVO_X2_LLAMA_CPP_LLM_BASE_URL)" EVO_X2_LLAMA_CPP_SERVICE="$(EVO_X2_LLAMA_CPP_SERVICE)" EVO_X2_LLAMA_CPP_PROFILE="$(EVO_X2_LLAMA_CPP_PROFILE)" EVO_X2_LLAMA_CPP_APPLY="$(EVO_X2_LLAMA_CPP_APPLY)" EVO_X2_LLAMA_CPP_ALLOW_RESTART="$(EVO_X2_LLAMA_CPP_ALLOW_RESTART)" ./scripts/evo-x2-llama-swap.sh swap
+
+evo-x2-llama-check:
+	bash -n scripts/dev.sh scripts/evo-x2-tailnet-preflight.sh scripts/evo-x2-ssh-preflight.sh scripts/evo-x2-llama-swap.sh
+
+scenario-evo-x2: evo-x2-preflight
+	RUN_NOTE_SCENARIO=1 RUN_LOCAL_LLM_SCENARIO=1 SCENARIO_STREAM_DRAFT=1 LLM_BASE_URL="$(EVO_X2_LLM_BASE_URL)" LLM_MODEL="$(EVO_X2_LLM_MODEL)" STYLE_LLM_MODEL="$(EVO_X2_STYLE_LLM_MODEL)" BRIEF_LLM_MODEL="$(EVO_X2_BRIEF_LLM_MODEL)" ARTICLE_LLM_MODEL="$(EVO_X2_ARTICLE_LLM_MODEL)" DRAFT_LLM_MODEL="$(EVO_X2_DRAFT_LLM_MODEL)" VERIFY_LLM_MODEL="$(EVO_X2_VERIFY_LLM_MODEL)" LLM_TIMEOUT_SECONDS=900 LLM_STREAM_FIRST_BYTE_TIMEOUT_SECONDS="$(LLM_STREAM_FIRST_BYTE_TIMEOUT_SECONDS)" LLM_STREAM_IDLE_TIMEOUT_SECONDS="$(LLM_STREAM_IDLE_TIMEOUT_SECONDS)" LLM_FALLBACK_BASE_URLS="$(LLM_FALLBACK_BASE_URLS)" STYLE_LLM_FALLBACK_MODELS="$(STYLE_LLM_FALLBACK_MODELS)" BRIEF_LLM_FALLBACK_MODELS="$(BRIEF_LLM_FALLBACK_MODELS)" ARTICLE_LLM_FALLBACK_MODELS="$(ARTICLE_LLM_FALLBACK_MODELS)" DRAFT_LLM_FALLBACK_MODELS="$(DRAFT_LLM_FALLBACK_MODELS)" VERIFY_LLM_FALLBACK_MODELS="$(VERIFY_LLM_FALLBACK_MODELS)" SCENARIO_MIN_STYLE_SCORE=80 SCENARIO_MIN_DRAFT_RUNES=2800 DRAFT_MAX_ATTEMPTS=2 go run ./cmd/scenario/full_workflow
+
+scenario-evo-x2-llama-brief-draft:
+	@if [ "$${RUN_EVO_X2_LLAMA_CPP_SCENARIO:-0}" != "1" ]; then echo "Set RUN_EVO_X2_LLAMA_CPP_SCENARIO=1 to run the live Evo X2 llama.cpp brief/draft validation."; exit 2; fi
+	EVO_X2_TAILNET_HOST="$(EVO_X2_TAILNET_HOST)" EVO_X2_LLM_BASE_URL="$(EVO_X2_LLAMA_CPP_LLM_BASE_URL)" ./scripts/evo-x2-tailnet-preflight.sh
+	RUN_NOTE_SCENARIO=1 RUN_LOCAL_LLM_SCENARIO=1 SCENARIO_STREAM_DRAFT=1 LLM_BASE_URL="$(EVO_X2_LLAMA_CPP_LLM_BASE_URL)" LLM_MODEL="$(EVO_X2_LLAMA_CPP_MODEL)" STYLE_LLM_MODEL="$(EVO_X2_LLAMA_CPP_STYLE_MODEL)" BRIEF_LLM_MODEL="$(EVO_X2_LLAMA_CPP_BRIEF_MODEL)" ARTICLE_LLM_MODEL="$(EVO_X2_LLAMA_CPP_ARTICLE_MODEL)" DRAFT_LLM_MODEL="$(EVO_X2_LLAMA_CPP_DRAFT_MODEL)" VERIFY_LLM_MODEL="$(EVO_X2_LLAMA_CPP_VERIFY_MODEL)" LLM_TIMEOUT_SECONDS=900 LLM_STREAM_FIRST_BYTE_TIMEOUT_SECONDS="$(LLM_STREAM_FIRST_BYTE_TIMEOUT_SECONDS)" LLM_STREAM_IDLE_TIMEOUT_SECONDS="$(LLM_STREAM_IDLE_TIMEOUT_SECONDS)" LLM_FALLBACK_BASE_URLS="" STYLE_LLM_FALLBACK_MODELS="" BRIEF_LLM_FALLBACK_MODELS="" ARTICLE_LLM_FALLBACK_MODELS="" DRAFT_LLM_FALLBACK_MODELS="" VERIFY_LLM_FALLBACK_MODELS="" SCENARIO_MIN_STYLE_SCORE=80 SCENARIO_MIN_DRAFT_RUNES=2800 DRAFT_MAX_ATTEMPTS=2 go run ./cmd/scenario/full_workflow
+
+scenario-local-llamacpp-fallback:
+	LOCAL_LLAMACPP_FALLBACK_BASE_URL="$(LOCAL_LLAMACPP_FALLBACK_BASE_URL)" LOCAL_LLAMACPP_FALLBACK_MODEL="$(LOCAL_LLAMACPP_FALLBACK_MODEL)" LOCAL_LLAMACPP_FALLBACK_VERIFY_MODEL="$(LOCAL_LLAMACPP_FALLBACK_VERIFY_MODEL)" LOCAL_LLAMACPP_FALLBACK_LOAD_FLAGS="$(LOCAL_LLAMACPP_FALLBACK_LOAD_FLAGS)" LOCAL_LLAMACPP_FALLBACK_OUTPUT_DIR="$(LOCAL_LLAMACPP_FALLBACK_OUTPUT_DIR)" LOCAL_LLAMACPP_FALLBACK_MIN_STYLE_SCORE="$(LOCAL_LLAMACPP_FALLBACK_MIN_STYLE_SCORE)" LOCAL_LLAMACPP_FALLBACK_MIN_KEYWORD_OVERLAP="$(LOCAL_LLAMACPP_FALLBACK_MIN_KEYWORD_OVERLAP)" LOCAL_LLAMACPP_FALLBACK_MIN_DRAFT_RUNES="$(LOCAL_LLAMACPP_FALLBACK_MIN_DRAFT_RUNES)" LOCAL_LLAMACPP_FALLBACK_TIMEOUT_SECONDS="$(LOCAL_LLAMACPP_FALLBACK_TIMEOUT_SECONDS)" LOCAL_LLAMACPP_FALLBACK_MAX_ATTEMPTS="$(LOCAL_LLAMACPP_FALLBACK_MAX_ATTEMPTS)" go run ./cmd/scenario/local_llamacpp_fallback
+
+scenario-media-matrix-live: evo-x2-preflight
+	SCENARIO_OUTPUT_DIR=tmp/media_matrix go run ./cmd/scenario/media_matrix
+	RUN_LIVE_MEDIA_MATRIX=1 SCENARIO_STREAM_DRAFT=1 SCENARIO_OUTPUT_DIR=tmp/media_matrix LIVE_MEDIA_MATRIX_OUTPUT_DIR=tmp/media_matrix/live LLM_BASE_URL="$(EVO_X2_LLM_BASE_URL)" LLM_MODEL="$(EVO_X2_LLM_MODEL)" STYLE_LLM_MODEL="$(EVO_X2_STYLE_LLM_MODEL)" BRIEF_LLM_MODEL="$(EVO_X2_BRIEF_LLM_MODEL)" ARTICLE_LLM_MODEL="$(EVO_X2_ARTICLE_LLM_MODEL)" DRAFT_LLM_MODEL="$(EVO_X2_DRAFT_LLM_MODEL)" VERIFY_LLM_MODEL="$(EVO_X2_VERIFY_LLM_MODEL)" LLM_TIMEOUT_SECONDS=900 LLM_STREAM_FIRST_BYTE_TIMEOUT_SECONDS="$(LLM_STREAM_FIRST_BYTE_TIMEOUT_SECONDS)" LLM_STREAM_IDLE_TIMEOUT_SECONDS="$(LLM_STREAM_IDLE_TIMEOUT_SECONDS)" LLM_FALLBACK_BASE_URLS="$(LLM_FALLBACK_BASE_URLS)" STYLE_LLM_FALLBACK_MODELS="$(STYLE_LLM_FALLBACK_MODELS)" BRIEF_LLM_FALLBACK_MODELS="$(BRIEF_LLM_FALLBACK_MODELS)" ARTICLE_LLM_FALLBACK_MODELS="$(ARTICLE_LLM_FALLBACK_MODELS)" DRAFT_LLM_FALLBACK_MODELS="$(DRAFT_LLM_FALLBACK_MODELS)" VERIFY_LLM_FALLBACK_MODELS="$(VERIFY_LLM_FALLBACK_MODELS)" SCENARIO_MIN_STYLE_SCORE=80 SCENARIO_MIN_DRAFT_RUNES=1400 DRAFT_MAX_ATTEMPTS=2 go run ./cmd/scenario/live_media_matrix
 
 server:
 	go run ./cmd/server
@@ -55,3 +136,6 @@ llama:
 
 check:
 	go test ./...
+
+e2e:
+	python3 -m pytest tests/e2e