Non-autoregressive System 1 decision engine. Typed choice, score and yes/no decisions over any text in a single forward pass, in 100+ languages, with a router that picks the right checkpoint per request.
Python calibrationclassificationdecision-modelhuggingfacejevmodernbertmultilingualnlppythonpytorchroutingtyped-decisionszero-shot
docs(hooks): remove_hook takes the installed instance, so the example must keep it
Adeshina Lasisi1fa4458febae
diff --git a/docs/hooks/examples.md b/docs/hooks/examples.mdindex 6222708f..96d49e1e 100644--- a/docs/hooks/examples.md+++ b/docs/hooks/examples.md@@ -322,13 +322,17 @@ agent.system_one(state, questions)Attach, detach or scope hooks after construction.```python-agent.add_hook(Metrics()) # attach at runtime-agent.remove_hook(Metrics()) # by identity+metrics = Metrics()+agent.add_hook(metrics) # attach at runtime+agent.remove_hook(metrics) # by identity: keep the instance to remove itwith agent.hooks_installed(DebugDump()):agent.system_one(state, questions) # DebugDump only here```+`remove_hook` compares with `is`, so a fresh `Metrics()` matches nothing: it returns `False` and+the installed hook keeps running.+## Base class and process-wide defaultsSubclass `BaseHook` to override only what you need, and register something once for the whole