jif 816fa702ec Account for token usage from incomplete responses (#53670) ...

## Why

Terminal `response.incomplete` errors discard reported token usage. Counting that usage as a new context baseline can also double-count input and trigger unnecessary compaction on the next turn.

## What changed

- Carry the response ID and valid reported usage with incomplete-response errors.
- Record usage for sampling and foreground compaction in cumulative totals, rollout records, budgets, and token-usage contributors without replacing the context baseline. Preserve the original terminal error, including when accounting exhausts the budget or cancellation races the error.
- Charge incomplete background compaction requests to the rollout budget without publishing foreground token usage.
- Ignore missing or malformed usage rather than estimating it.

## Testing

Extend coverage for SSE and WebSocket incomplete responses, rollout usage records, compaction accounting, deferred token-count events, and token-usage contributors. Add regressions for unnecessary compaction on the next turn and background compaction publishing foreground usage.

GitOrigin-RevId: bf1ee6df3912052ab7c19e1c6af8ad3dc4b07675

2026-10-13 13:36:24 +00:00

..

common

Add opt-in output token replay for OpenAI requests (#52742)

2026-10-10 01:25:00 +00:00

remote_env_windows

Bind capability roots to environment selections (#51493)

2026-10-06 22:39:32 +00:00

suite

Account for token usage from incomplete responses (#53670)

2026-10-13 13:36:24 +00:00

all.rs

[codex] Use expect in integration tests (#28441)

2026-06-15 21:53:47 -07:00

mcp_trace_propagation.rs

Preserve MCP request trace context across transport workers (#47212)

2026-09-22 06:47:07 +00:00

responses_headers.rs

Add opt-in output token replay for OpenAI requests (#52742)

2026-10-10 01:25:00 +00:00

windows_sandbox.rs

Move Windows sandbox tests into a dedicated integration binary (#51678)

2026-10-07 12:47:04 +00:00