Files
ai-novel-engine/automation/next_lots.toml
T
2026-03-09 09:22:27 +01:00

71 lines
1.9 KiB
TOML

[paths]
mascarade_repo = "/Users/electron/mascarade"
core_base_url = "http://127.0.0.1:8100"
apple_runtime_url = "http://127.0.0.1:8201"
ollama_tags_url = "http://127.0.0.1:11435/api/tags"
apple_model_ready_timeout_seconds = 30
apple_model_poll_interval_seconds = 2
[smoke]
chapter = "02"
intention = "Chapitre court. Une femme arrive dans une ville de nuit, trouve un indice simple, et finit sur une decision risquee. Style direct, phrases courtes, ton sobre."
timeout_seconds = 300
[preset]
ANE_PROVIDER = "openai_compatible"
ANE_BASE_URL = "http://127.0.0.1:8100"
ANE_TIMEOUT = "300"
ANE_MAX_TOKENS_STRUCTURE = "256"
ANE_MAX_TOKENS_DRAFT = "768"
ANE_MAX_TOKENS_CRITIQUE = "512"
ANE_MAX_TOKENS_REWRITE = "768"
ANE_MAX_TOKENS_GATE = "384"
ANE_MAX_TOKENS_REPAIR = "512"
ANE_MAX_TOKENS_MEMORY = "320"
ANE_REPAIR_MAX_PASSES = "2"
[ensure_models]
apple_models = [
"qwen2.5-0.5b-instruct-onnx",
"qwen3.5-4b-onnx-q4f16",
"stateful-mistral7b-instruct-int4-coreml",
]
ollama_models = [
"qwen2.5:7b",
"qwen2.5:1.5b",
]
[lots.priority_models]
models = [
"apple-coreml:qwen3.5-4b-onnx-q4f16",
"ollama:qwen2.5:7b",
]
[lots.baselines]
models = [
"apple-coreml:qwen2.5-0.5b-instruct-onnx",
"ollama:qwen2.5:1.5b",
]
[lots.preflight_only]
models = [
"apple-coreml:stateful-mistral7b-instruct-int4-coreml",
]
[tracking.ane]
todo_active = "TODO_ACTIVE.md"
todo_done = "TODO_IMPLEMENTE.md"
plan = "docs/EXECUTION_PLAN_2026-03-08.md"
comparison = "docs/MODEL_COMPARISON_2026-03-08.md"
readme = "README.md"
runbook = "docs/runbooks/LOCAL_GENERATION.md"
[tracking.mascarade]
todo = "TODO_AI_NOVEL_ENGINE.md"
plan = "docs/EXECUTION_PLAN_2026-03-08.md"
readme = "README.md"
runbook = "docs/RUNBOOK_APPLE_LLM_LOCAL.md"
[next_actions]
rewrite_compaction = "Compacter ou reduire `rewrite_v1` et ses budgets pour faire passer au moins `apple-coreml:qwen3.5-4b-onnx-q4f16` ou `ollama:qwen2.5:7b` jusqu'a `gate`."