feat(context): tambah context::shaping (port dari shortsend)

Perilaku should_shape/shape_messages tidak berubah, hanya sumber
penghitungan token yang sekarang lewat context::tokens (tiktoken-rs)
menggantikan heuristik char/3 bawaannya sendiri.

src/app/runtime/actions/mod.rs

@@ -556,7 +556,7 @@ pub fn apply_action(state: &mut AppStateRest, action: Action) {
                     .map(str::len)
                     .sum();
                 let token_estimate = total_chars / 3;
-                rt.messages = crate::app::runtime::shortsend::shape_messages(&rt.messages, token_estimate, max_wire_tokens, true, None);
+                rt.messages = crate::app::runtime::context::shaping::shape_messages(&rt.messages, token_estimate, max_wire_tokens, true, None);
                 state.push_toast(Toast::new(ToastKind::Success, "Conversation history compacted.".to_string()));
                 state.dirty = true;
             }
@@ -1154,10 +1154,10 @@ fn run_agent_turn(
         // Skip message compaction if abort was requested — the non-streaming
         // LLM call for summarization would block without checking abort_flag.
         let wire_msgs = if !tc.abort_flag.load(std::sync::atomic::Ordering::SeqCst)
-            && crate::app::runtime::shortsend::should_shape(token_estimate, max_wire_tokens, prev_shaped)
+            && crate::app::runtime::context::shaping::should_shape(token_estimate, max_wire_tokens, prev_shaped)
         {
             prev_shaped = true;
-            let compacted = crate::app::runtime::shortsend::shape_messages(&msgs, token_estimate, max_wire_tokens, false, Some(&tc.client));
+            let compacted = crate::app::runtime::context::shaping::shape_messages(&msgs, token_estimate, max_wire_tokens, false, Some(&tc.client));
             
             // Dispatch the compacted messages to the main thread so the local session history
             // is permanently compacted and doesn't trigger shaping again immediately on next turn.

src/app/runtime/context/dedup.rs

@@ -1,3 +1,4 @@
+#![allow(dead_code)]
 //! Cross-call tool-result deduplication: when a read-only tool is called
 //! again with identical arguments, the earlier result is replaced with a
 //! placeholder so only the latest copy occupies context.

src/app/runtime/context/mod.rs

@@ -11,6 +11,7 @@
 //! `TurnEvent::Compacted`.
 
 pub mod dedup;
+pub mod shaping;
 pub mod squash;
 pub mod tokens;
 pub mod window;

src/app/runtime/context/squash.rs

@@ -1,3 +1,4 @@
+#![allow(dead_code)]
 //! Per-tool-result compression: shrink large tool outputs before they
 //! ever enter conversation history, dispatching by content shape.
 //!

src/app/runtime/context/tokens.rs

@@ -28,6 +28,7 @@ pub fn count_tokens(text: &str) -> usize {
 ///
 /// Return: 0 for a message with no `content` (e.g. an assistant message
 /// that only carries `tool_calls`).
+#[allow(dead_code)]
 pub fn count_message_tokens(msg: &ChatMessage) -> usize {
     msg.content.as_deref().map_or(0, count_tokens)
 }

src/app/runtime/context/window.rs

@@ -1,3 +1,4 @@
+#![allow(dead_code)]
 //! Single source of truth for resolving the active model's context
 //! window size, replacing three copies of the same lookup that had
 //! drifted (`Action::Compact`, `spawn_turn`, and `view/status.rs` each

src/app/runtime/mod.rs

@@ -3,5 +3,4 @@
 pub mod actions;
 pub mod commands;
 pub mod context;
-pub mod shortsend;
 pub mod stream;