fix(server): retry Cursor text generation without sandboxing

[Yash-Singh1]

What Changed

Retry Cursor text generation without sandboxing when the sandboxed attempt fails.

Why

Cursor can fail to generate text in a sandboxed run. Retrying without sandboxing lets the run recover from that failure.

UI Changes

Not applicable.

Checklist

• This PR is small and focused
• I explained what changed and why
• I included before/after screenshots for any UI changes
• I included a video for animation/interaction changes

[macroscopeapp]

Macroscope has since reviewed this pull request. An earlier review was skipped by a cost limit; a review has now completed, so that notice no longer applies.

[macroscopeapp]

Approvability

Verdict: Not approved

Macroscope's review found this PR not approvable — The production text-generation path now falls back to disabling Cursor's OS sandbox, so a temporary working directory does not prevent access to the host filesystem, network, shell, or environment. This materially changes the security posture and has an unresolved critical concern requiring human review.

^{Adjust the Minimum Blocking Severity for this repo — including turning it Off — in Settings. You can add or adjust custom eligibility rules. Learn more.}

[Yash-Singh1]

Reopening so CI runs against t3code/codex-turn-mapping. The pull request was opened against main, which skipped pull_request workflows while the merge was conflicted.

[github-actions]

Thread transfer impact

✅ Thread transfer remains within every enforced ceiling.

ℹ️ No successful main baseline artifact is available yet. This run establishes the initial measurement.

Provider	Metric	Main baseline	This PR	Impact	PR ceiling
Codex	Total thread wire	—	4.9 KiB	—	6.8 KiB	✅
Codex	Thread snapshot wire	—	3.7 KiB	—	4.9 KiB	✅
Codex	Live turn WebSocket wire	—	1.1 KiB	—	2.0 KiB	✅
Codex	Live turn WebSocket decoded	—	20.4 KiB	—	29.3 KiB	✅
Codex	Live turn messages	—	1	—	8	✅
Claude	Total thread wire	—	4.9 KiB	—	6.8 KiB	✅
Claude	Thread snapshot wire	—	3.7 KiB	—	4.9 KiB	✅
Claude	Live turn WebSocket wire	—	1.2 KiB	—	2.0 KiB	✅
Claude	Live turn WebSocket decoded	—	20.8 KiB	—	29.3 KiB	✅
Claude	Live turn messages	—	2	—	8	✅

Baseline: unavailable · PR result: 3cc4835 · 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: 106.1 KiB
• Claude decoded thread snapshot: 106.4 KiB

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