Skip to content

Place T3 control and workload processes in verified CPU roles - #21

Open
Mjones13 wants to merge 2 commits into
mainfrom
work/cpu-capacity-placement
Open

Mjones13 wants to merge 2 commits into
mainfrom
work/cpu-capacity-placement

Conversation

@Mjones13

@Mjones13 Mjones13 commented Oct 4, 2026 •

Copy link
Copy Markdown
Collaborator

Adds opt-in Linux CPU placement so the T3 control process and launched workloads can enter verified cgroup roles before payload execution. The helper verifies immutable bindings and group identity, and required placement fails closed. Launcher replacement, shared spawning, both PTYs, Claude SDK launches and telemetry use the same placement contract; an absent configuration preserves existing behavior.

Source is synchronized with canonical main e1f3015 through ordinary merge 728a8a9. PR #5 covers unrelated sidebar inventory; it supplies no dependency.

Validation: current merged candidate passed 199 tests across 12 placement/usage files, 163 NativeTelemetryClient/server tests, and server typecheck. Original placement source additionally passed targeted lint, native bundle compilation and five native-build lifecycle checks on each declared Node engine floor. Those build checks remain bound to d58857e; no unchanged native build was repeated.

This PR publishes source only. No shared service, scheduler, cgroup or release was activated. Repository package version 0.0.38 differs from live 0.0.46-nightly.20261003.2638; activation requires the owning release process to reconcile exact installed source, runtime closure, CPU delegation and a separately approved cold window. Positive native placement and response improvement remain unproved.


View with [code]smith Autofix with [code]smith
Need help on this PR? Tag @codesmith-bot with what you need. Autofix is disabled.

@github-actions github-actions Bot added vouch:trusted PR author is trusted by repo permissions or the VOUCHED list. size:XXL labels Oct 4, 2026
@github-actions

github-actions Bot commented Oct 4, 2026

Copy link
Copy Markdown

Thread transfer impact

✅ Thread transfer remains within every enforced ceiling.

Provider Metric Main baseline This PR Impact PR ceiling
Codex Total thread wire 13.6 KiB 13.5 KiB −29 B (−0.2%) 15.1 KiB ✅
Codex Thread snapshot wire 7.0 KiB 7.0 KiB −6 B (−0.1%) 7.3 KiB ✅
Codex Live turn WebSocket wire 6.5 KiB 6.5 KiB −23 B (−0.3%) 7.8 KiB ✅
Codex Live turn WebSocket decoded 57.0 KiB 57.0 KiB −44 B (−0.1%) 66.4 KiB ✅
Codex Live turn messages 9 8 −1 (−11.1%) 21 ✅
Claude Total thread wire 13.6 KiB 13.6 KiB −16 B (−0.1%) 15.1 KiB ✅
Claude Thread snapshot wire 7.0 KiB 7.0 KiB +1 B (+0.0%) 7.3 KiB ✅
Claude Live turn WebSocket wire 6.5 KiB 6.5 KiB −17 B (−0.3%) 7.8 KiB ✅
Claude Live turn WebSocket decoded 57.8 KiB 57.8 KiB 0 B (0.0%) 66.4 KiB ✅
Claude Live turn messages 9 9 0 (0.0%) 21 ✅

Baseline: e1f3015 · PR result: 728a8a9 · Source CI: success

Scenario and decoded snapshot size

10 historical turns, 5 command tools per turn, 878.9 KiB retained MCP result per historical turn, and a 1.05 MiB retained result in the measured turn.

  • Codex decoded thread snapshot: 113.8 KiB
  • Claude decoded thread snapshot: 114.5 KiB

Updated in place by a trusted workflow. PR artifacts are strictly validated and never executed.

This branch has not been deployed

No deployments
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

size:XXL vouch:trusted PR author is trusted by repo permissions or the VOUCHED list.

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant