Synced from monorepo

Synced from monorepo

Changes:
- Temporarily disable session share link creation in the TUI
- Do not approve plan on empty Enter from the revise prompt
- Expose chat product Skills via ACP available_commands_update
- Return immediately from a blocking wait on an already-completed ACP task
- Split headless pager module for clearer structure
- Stop git worktree prune from removing user registrations on resume
- Use compaction sampler tokenizer for item token counts
- Opt-in extra root CAs via GROK_EXTRA_CA_BUNDLE
- Cancel all session subagents when the user stops
- Let the session persistence actor exit when its session ends
- Make fullscreen terminal resize much cheaper on long sessions
- Report honestly from kill_task when an ACP task does not exist
- Hide /usage for external-auth deployments
- Forward the history-load trailer’s computer_reason to the client
- Remove ineffective no-op tool reminder
- Declare slash-command screen-mode support in one place
- Keep settings enum picker on the committed value until Enter
- Reap a PTY’s full process tree
- Stream tool calls from headless mode over ACP
- Bridge gateway task lifecycle to ACP for chat session background tasks
- Don’t warn about truncated history on a suppressed replay
- Fit full-replace summarizer input and recover on context-length errors
- Stop dropping agents over an unrecognized frontmatter color
- Add /undo as a slash alias for /rewind
- Harden sleep/wake token-refresh paths against forced re-login
- Add session/list ACP method
- Give each sampling backend its own conversion module
- Treat an unenrolled child process as a lint error
- Suppress the cancelled marker on send-now wake turns
- Stop tearing down Roslyn on every edit, and read C# diagnostics

Source-Revision: 2a28b4a86cfc4a4c133c35b7fc2a6a9964387c39

crates/codegen/xai-chat-state/src/actor/tests.rs

@@ -468,6 +468,7 @@ async fn record_last_turn_usage_round_trip() {
         total_tokens: 1290,
         reasoning_tokens: 0,
         cached_prompt_tokens: 800,
+        cache_creation_prompt_tokens: 0,
     };
     h.handle.record_last_turn_usage(usage.clone());
 
@@ -483,6 +484,7 @@ async fn record_last_turn_usage_round_trip() {
         total_tokens: 10000,
         reasoning_tokens: 0,
         cached_prompt_tokens: 0,
+        cache_creation_prompt_tokens: 0,
     };
     h.handle.record_last_turn_usage(next);
     let got2 = h
@@ -504,6 +506,7 @@ async fn prompt_usage_ledger_via_handle_resets_and_clears() {
         total_tokens: 12,
         reasoning_tokens: 0,
         cached_prompt_tokens: 0,
+        cache_creation_prompt_tokens: 0,
     };
 
     let h = TestHarness::new();

crates/codegen/xai-chat-state/src/usage.rs

@@ -33,6 +33,7 @@ pub struct UsageTotals {
     pub input_tokens: u64,
     pub output_tokens: u64,
     pub cached_read_tokens: u64,
+    pub cache_creation_tokens: u64,
     pub reasoning_tokens: u64,
     pub model_calls: u64,
     pub api_duration_ms: u64,
@@ -52,6 +53,7 @@ impl UsageTotals {
             input_tokens: u64::from(usage.prompt_tokens),
             output_tokens: u64::from(usage.completion_tokens),
             cached_read_tokens: u64::from(usage.cached_prompt_tokens),
+            cache_creation_tokens: u64::from(usage.cache_creation_prompt_tokens),
             reasoning_tokens: u64::from(usage.reasoning_tokens),
             model_calls: 1,
             api_duration_ms: api_duration_ms.unwrap_or(0),
@@ -73,6 +75,7 @@ impl UsageTotals {
             input_tokens,
             output_tokens,
             cached_read_tokens,
+            cache_creation_tokens,
             reasoning_tokens,
             model_calls,
             api_duration_ms,
@@ -82,6 +85,9 @@ impl UsageTotals {
         self.input_tokens = self.input_tokens.saturating_add(*input_tokens);
         self.output_tokens = self.output_tokens.saturating_add(*output_tokens);
         self.cached_read_tokens = self.cached_read_tokens.saturating_add(*cached_read_tokens);
+        self.cache_creation_tokens = self
+            .cache_creation_tokens
+            .saturating_add(*cache_creation_tokens);
         self.reasoning_tokens = self.reasoning_tokens.saturating_add(*reasoning_tokens);
         self.model_calls = self.model_calls.saturating_add(*model_calls);
         self.api_duration_ms = self.api_duration_ms.saturating_add(*api_duration_ms);
@@ -157,6 +163,7 @@ mod tests {
             total_tokens: 999_999,
             reasoning_tokens: 0,
             cached_prompt_tokens: 0,
+            cache_creation_prompt_tokens: 0,
         }
     }