docs(custom-model): say a PUT clears defaultContextLength and a learned figure wins

Round-four review smaller items: api-reference now states the opposite-of-apiKey behaviour for an omitted defaultContextLength, and the wiki sentence follows the code, modelContextLengths[id] ?? defaultContextLength: any stored figure beats the default.

docs/api-reference.md

@@ -1220,7 +1220,9 @@ authStyle?, defaultModelId?, defaultContextLength? }` creates one. `id`
   keeps the stored one rather than clearing it — the client never receives
   the real value to resend deliberately unchanged, so omission is the only
   way to say "leave it alone"; there is no way to clear a key back to unset
-  this way. `defaultModelId`, when set, must be one of that endpoint's own
+  this way. `defaultContextLength` behaves the opposite way: a PUT without
+  it clears the stored value, so send the field back to keep it.
+  `defaultModelId`, when set, must be one of that endpoint's own
   `models` (`400 INVALID_INPUT` otherwise).
 - `DELETE /api/v1/model-endpoints/:id` removes one.
 - `POST /api/v1/model-endpoints/:id/discover-models` fetches the endpoint's

docs/wiki/Custom-Model-Endpoints.md

@@ -33,10 +33,11 @@ which current llama.cpp, llama-swap and gateway-style servers state to varying d
 against a llama-swap server the stronger figures from its launch command and from llama.cpp's
 `/props` probe win where they exist, and those probes only ever run for a model the server
 already reports loaded, since asking about an unloaded model can trigger an actual, slow model
-swap as a side effect. A model that states no figure and was never loaded falls back to the
-endpoint's **Default context length** field (that number is the model's whole window, never a
-per-slot figure), and a model neither covers keeps whatever an earlier cycle learned or simply
-gets no override, never a guess. The window is applied to the launched session by the harnesses
+swap as a side effect. A model that states no figure keeps whatever an earlier cycle learned:
+the stored figure always beats the endpoint's **Default context length** field
+(`modelContextLengths[id] ?? defaultContextLength`), which only applies where no figure was
+ever learned (that number is the model's whole window, never a per-slot figure). A model
+neither covers simply gets no override, never a guess. The window is applied to the launched session by the harnesses
 that can take it: Claude Code today (see below), OpenCode as the model's context limit, and
 Codex as a `model_context_window` entry in its generated config file, which also sets Codex's
 own auto-compact point via `model_auto_compact_token_limit` at 75% of the window.