Add Windows unified exec yield floor

[iceweasel-oai]

Why

The Windows unified_exec experiment regressed at the turn level in a way that points to premature backgrounding / extra command cycles rather than individual responses getting heavier:

• codex_local_tool_calls_per_turn was up about 20.7%.
• codex_local_blended_tokens_per_turn was up about 4.1%, and codex_local_output_tokens_per_turn was up about 4.0%.
• codex_local_response_latency_per_turn was up about 8.3%.
• The primary activity metrics also moved down: codex_turns about -6.6%, codex_dau about -1.0%, and codex_local_hourly_active_users about -3.0%.

At the same time, the per-response metrics moved in the other direction: blended tokens per response, output tokens per response, and latency per response were all lower in test. That suggests the bad turn-level shape is largely about extra tool/model cycles, not each response being slower or more expensive on its own.

Local Windows benchmarking showed the likely mechanism: shell-wrapped commands pay a large PowerShell startup/teardown tax before the actual command has much time to run. In the benchmark, the PowerShell wrapper added roughly 0.7-1.0s versus direct exec:

• Windows PowerShell: about 740ms p50 / 800ms p90 overhead versus direct exec.
• PowerShell 7 (pwsh): about 930ms p50 / 980ms p90 overhead versus direct exec.

The model commonly asks for a 1s initial yield. On Windows, that can spend nearly the whole window waiting on PowerShell machinery, so otherwise-short commands are more likely to return as background sessions and require follow-up polling/tool calls.

This is intentionally a temporary unlock. It gives Windows closer to the same useful post-shell command window as other platforms while we work on reducing the PowerShell tax directly, for example with persistent PowerShell workers or conservative direct-exec paths for commands that do not need shell semantics.

What changed

• Adds a Windows-only 2s floor to unified_exec's initial yield_time_ms clamp.
• Keeps larger model-requested waits unchanged, including the existing 10s default.
• Keeps the existing 30s max clamp.
• Leaves non-Windows behavior unchanged.
• Adds platform-gated tests for both the Windows floor and the non-Windows clamp behavior.

Verification

• just test -p codex-core unified_exec

[jif-oai]

This is very hacky so I would like to see concrete numbers that proves that this will drastically improve the A/B result