auto_routerlisted

# auto_router — effort-based local↔cloud routing + fusion Decides *for you* how much model muscle a task needs, then sends it to the cheapest capable backend — local first, cloud when it's worth it. Extends `tiered_router` (cost tiers) and `llm_backends` (local discovery) with a cloud catalog and ensemble strategies. ## When to use - "Pick local or cloud automatically based on how hard the task is." - "Use DeepSeek / GLM / Nemotron / Grok / Gemma alongside my local models." - "Have a local model draft and a stronger model refine" (fusion). - The user mentions effort routing, model fusion/ensemble, OpenRouter, or any of the cloud providers above. ## Auto-decision ```bash python -m skills.auto_router.cli route "classify: bug or feature?" # → LOCAL python -m skills.auto_router.cli route "design a distributed cache and prove correctness" python -m skills.auto_router.cli run "summarize this PR in 2 lines" --max-tokens 200 ``` Effort is scored from prompt signals (length, code, stack traces, reasoning vs trivial vocabulary, multi-file scope) → a `Tier`. `Tier ≤ LOCAL` with a local backend runs local (0 cloud tokens); higher tiers pick the cheapest available cloud model, budget-aware, and **fall back to local** when no cloud key is set. When a non-forced route has both local and cloud as meaningful options, the NN belt records its raw prediction in shadow mode even if the heuristic remains in control. Executed local and cloud routes then include a `feedback_id`. Verify i