feat(cmf): per-model generation defaults; safer delete-file default

- Each Local-models row gains default generation params — temperature, top-p,
  max tokens — applied by the gateway when the incoming request doesn't set
  them (an explicit request value always wins). Works for both the plain and
  streaming paths; top_p is now forwarded to OpenAI-compatible providers.
- The "also delete the model file from disk" checkbox in the delete dialog now
  defaults to UNCHECKED — deleting a pool entry no longer silently costs a
  multi-GB re-download/conversion.

web/js/i18n/en.js

@@ -264,7 +264,10 @@ export default {
   "settings.cmf.pick": "select a model",
   "settings.cmf.models": "Local models",
   "settings.cmf.modelsHelp": "Each row is one model the gateway runs (its own cortiq serve on its own port) and registers in the pool. Add as many as you have .cmf files and free ports.",
-  "settings.cmf.rowHint": "id · .cmf file · port · threads · GPU · O(1). Applied on save: a removed row stops its server (memory freed), a new row starts one.",
+  "settings.cmf.rowHint": "id · .cmf file · port · threads · GPU · O(1) · T°/top-p/max tok. Applied on save: a removed row stops its server (memory freed), a new row starts one.",
+  "settings.cmf.tempHelp": "Default temperature for this model (0 = deterministic, 0.7 = balanced, >1 = creative). Used when the request doesn't set one; a request value always wins. Empty = provider default.",
+  "settings.cmf.topPHelp": "Default nucleus sampling (top-p) for this model: only tokens within this cumulative probability are sampled (0.9 typical). Empty = provider default.",
+  "settings.cmf.maxTokHelp": "Default max output tokens for this model when the request doesn't set one. Protects against runaway long generations. Empty = provider default.",
   "settings.cmf.o1Auto": "O(1): auto",
   "settings.cmf.o1Help": "O(1) attention at serve time: auto — follow the hint recorded in the .cmf; off — force exact attention (fixes incoherent output after a too-aggressive --o1 conversion, no re-convert needed); all/deepN — force-enable on those layers.",
   "settings.cmf.addServer": "+ Add local model",