Synced from monorepo

Synced from monorepo

Changes:
- Workspace server: surface preview-proxy metrics through the hub metric pump
- Shell: reclaim a session’s retained state in one entry
- Shell: reclaim a session’s resident state in one entry
- Pager: withhold key event types from Alacritty builds that double keys
- Tools: cancel a session’s subagents when it closes
- Pager: keep the whole plan in scrollback and separate reasoning from output in minimal mode
- Pager: probe terminal version over DA2 and include it with feedback
- SuperGrok Plus: identity, CLI, and analytics tier surfaces
- Shell: inherit the session process scope into subagents
- Pager: build @-file-search matcher lazily on first use
- Tools: fix description and output contradictions in tool definitions
- Workspace: degrade @-file-search instead of aborting on thread exhaustion
- Tools: reap a session’s LSP servers when it closes
- Tools: fix contradictions and defects in tool descriptions, schemas, and harness pools
- MCP: reap stdio MCP children on session close
- Shell: reuse spawn-time skill discovery for session telemetry
- Tools: stop leaking shell-wrapper positional params into sourced scripts (fixes activate_conda under persistent/static shell)
- Shell: self-heal corrupt session-search SQLite cache
- Workspace: cap workspace-server tokio workers on many-core hosts
- Shell: reap a session’s child processes when it closes
- Crash handler: capture SIGABRT so panic-aborts leave crash reports
- CLI chat proxy: team-scoped Grok Code managed-config admin routes
- MCP: add CLI enable/disable for MCP servers
- Shell: cap tokio worker threads for startup thread demand
- Workspace: harden git_commit and add git_sync_base operation
- Circuit breaker: add feature-gated gRPC retry policy

Source-Revision: 2a818575225183d8ca915f5632a09b8067b5156a

crates/codegen/xai-tty-utils/src/runtime.rs

@@ -0,0 +1,55 @@
+//! Worker-thread policy for multi-thread tokio runtimes.
+//!
+//! Tokio defaults to one worker per core. On many-core shared hosts (100+-core
+//! HPC login nodes) that pins 100+ thread slots per grok process against
+//! per-user ceilings — systemd user-slice `pids.max` (commonly 1000) or
+//! `RLIMIT_NPROC` — and later thread spawns die with EAGAIN. Grok's runtimes
+//! are I/O-bound, so throughput does not scale with workers past a small
+//! count.
+//!
+//! This is the single home for the cap policy; every multi-thread runtime in
+//! the workspace (the `grok` binary, the `workspace_server` daemon) derives
+//! its worker count from here so the policy cannot drift across crates.
+
+use std::num::NonZeroUsize;
+
+/// Maximum runtime worker threads for any grok process.
+pub const MAX_WORKER_THREADS: NonZeroUsize = NonZeroUsize::new(8).unwrap();
+
+/// Pure, testable: `min(cores, MAX_WORKER_THREADS)`.
+pub fn cap_worker_threads(cores: NonZeroUsize) -> NonZeroUsize {
+    cores.min(MAX_WORKER_THREADS)
+}
+
+/// Reads the host: `min(available_parallelism, MAX_WORKER_THREADS)`.
+pub fn capped_worker_threads() -> NonZeroUsize {
+    cap_worker_threads(std::thread::available_parallelism().unwrap_or(NonZeroUsize::MIN))
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+
+    fn nz(n: usize) -> NonZeroUsize {
+        NonZeroUsize::new(n).unwrap()
+    }
+
+    #[test]
+    fn cap_is_identity_at_or_below_max() {
+        assert_eq!(cap_worker_threads(nz(1)), nz(1));
+        assert_eq!(cap_worker_threads(nz(4)), nz(4));
+        assert_eq!(cap_worker_threads(nz(8)), nz(8));
+    }
+
+    #[test]
+    fn cap_clamps_many_core_hosts() {
+        assert_eq!(cap_worker_threads(nz(9)), nz(8));
+        assert_eq!(cap_worker_threads(nz(360)), nz(8));
+    }
+
+    #[test]
+    fn capped_worker_threads_stays_in_bounds() {
+        let n = capped_worker_threads();
+        assert!(n <= MAX_WORKER_THREADS, "got {n}");
+    }
+}