Synced from monorepo

Synced from monorepo

Changes:
- Release a shell session's resources in one drop
- Make the tools blocking-wait cap client-configurable and self-describing
- Recognize API "exceeds budget" errors as context overflow
- Retry /btw on model overload
- Carry running background tasks and subagents across compaction
- Require round-trip time for SDK liveness checks
- Background-subagent completion reminders with a selectable delivery surface
- Make a PTY shell reap itself until it reaches the registry
- Recover the OS error code from a TLS-phase connection reset
- Consume the attached-client signal and report why idle is withheld
- Treat `.grok/sandbox.toml` edits as protected so auto mode prompts before writing
- Surface history/search in the Ctrl+. cheatsheet and keep it working in history view
- Delete sessions from the dashboard and welcome list
- Release a session's activity record when the session ends
- Stop charging auth-retry budget for fail-closed 401s; reset it across suspends
- Scope skills watches on project vendor roots
- Make [stop] cancel in-flight compaction
- Make the leader soak measure the leader, not its harness

Source-Revision: 8d69c91f02bcacf01e98d5aebbf2f92547c45738

crates/common/xai-grok-compaction/src/code_compaction/failure.rs

@@ -33,6 +33,7 @@ pub fn is_context_length_error(message: &str) -> bool {
         || m.contains("maximum prompt length")
         || m.contains("maximum context length")
         || m.contains("context_length_exceeded")
+        || (m.contains("current message") && m.contains("exceeds budget"))
 }
 
 /// Classify an HTTP API failure (status + message) for the compaction retry
@@ -183,6 +184,9 @@ mod tests {
             "exceeds the maximum prompt length",
             "This model's maximum context length is 128000 tokens",
             "error code: context_length_exceeded",
+            "Failed to start sampling: [conversation] Current message (1000000 tokens) exceeds budget (500000 tokens)",
+            "compact failed: API error (status 400 Bad Request): invalid-argument: Failed to start sampling: [conversation] Current message (1000000 tokens) exceeds budget (500000 tokens)",
+            "Current message (600000) exceeds budget (500000)",
         ] {
             assert!(is_context_length_error(msg), "should match: {msg}");
         }
@@ -190,6 +194,8 @@ mod tests {
             "internal server error",
             "rate limited",
             "connection reset by peer",
+            "Attached file content (300000 tokens) causes message to exceed budget",
+            "compact index estimate 2.0 GB exceeds budget 1.0 GB",
         ] {
             assert!(!is_context_length_error(msg), "should not match: {msg}");
         }

crates/common/xai-grok-compaction/src/code_compaction/sample.rs

@@ -319,6 +319,26 @@ mod tests {
         assert_eq!(sampler.call_count(), 1, "overflow must not retry");
     }
 
+    #[tokio::test]
+    async fn conversation_exceeds_budget_is_context_overflow() {
+        let sampler =
+            MockSampler::scripted(vec![Err(CompactionSampleError::Other(anyhow::anyhow!(
+                "API error (status 400 Bad Request): invalid-argument: \
+                 Failed to start sampling: [conversation] Current message \
+                 (1000000 tokens) exceeds budget (500000 tokens)"
+            )))]);
+        let err = run(&sampler, 3).await.expect_err("should fail");
+        assert!(matches!(
+            err,
+            SampleRetryError::Failure {
+                deterministic: true,
+                context_overflow: true,
+                ..
+            }
+        ));
+        assert_eq!(sampler.call_count(), 1, "overflow must not retry");
+    }
+
     #[tokio::test]
     async fn transient_exhausted_is_non_deterministic_failure() {
         let sampler = MockSampler::scripted(vec![

crates/common/xai-grok-compaction/src/reminder.rs

@@ -16,6 +16,12 @@
 //! sections (files, AGENTS.md, skills, MCP, memory). Callers pass **borrowed
 //! views** (`&str` over live state) so long fields (commands, todo content,
 //! descriptions, ids) are not cloned just to format.
+//!
+//! KEEP IN SYNC: the exact wording of these sections is a compatibility
+//! surface — downstream mirrors reproduce it verbatim (grep for
+//! `format_section_running_subagents` / `format_section_background_tasks`
+//! and `section_todo_list` mirrors). Update them when changing any wording
+//! here.
 
 // ---------------------------------------------------------------------------
 // Borrowed views over harness live state (no long-string clones)