feat: Budget skill metadata and surface trimming as a warning (#18298)

Cap the model-visible skills section to a small share of the context
window, with a fallback character budget, and keep only as many implicit
skills as fit within that budget.

Emit a non-fatal warning when enabled skills are omitted, and add a new
app-server warning notification

Record thread-start skill metrics for total enabled skills, kept skills,
and whether truncation happened

---------

Co-authored-by: Matthew Zeng <mzeng@openai.com>
Co-authored-by: Codex <noreply@openai.com>

codex-rs/app-server-protocol/src/protocol/common.rs

@@ -1029,6 +1029,7 @@ server_notification_definitions! {
     /// Deprecated: Use `ContextCompaction` item type instead.
     ContextCompacted => "thread/compacted" (v2::ContextCompactedNotification),
     ModelRerouted => "model/rerouted" (v2::ModelReroutedNotification),
+    Warning => "warning" (v2::WarningNotification),
     DeprecationNotice => "deprecationNotice" (v2::DeprecationNoticeNotification),
     ConfigWarning => "configWarning" (v2::ConfigWarningNotification),
     FuzzyFileSearchSessionUpdated => "fuzzyFileSearch/sessionUpdated" (FuzzyFileSearchSessionUpdatedNotification),