Won Park b04a2c2645 Estimate history tokens from content instead of serialized envelopes (#45094) ...

## Why

Serialized response items include message IDs, metadata, and JSON escaping that inflate token estimates without adding model-visible content.

## What changed

- Estimate each response item from its content, retaining JSON syntax for structured tool payloads.
- Apply image estimates to all image inputs, including non-base64 URLs, and count audio and encrypted content through their modality-specific estimates.
- Exclude plaintext reasoning and bookkeeping-only items from replay accounting.

## Testing

Update unit expectations for text, images, audio, and encrypted content. Add a remote compaction regression test showing that equal-length text produces identical token usage estimates despite different message IDs, metadata, and JSON escaping, while preserving the submitted messages.

GitOrigin-RevId: 1c43d5abbcc1668b4ab413901a2b4b6511ca5892

2026-09-12 18:41:47 +00:00

..

common

Make context snapshot text rendering consistent (#44976)

2026-09-12 05:04:11 +00:00

remote_env_windows

Apply remote platform semantics to exec safety checks (#42113)

2026-09-01 18:24:56 +00:00

suite

Estimate history tokens from content instead of serialized envelopes (#45094)

2026-09-12 18:41:47 +00:00

all.rs

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

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

responses_headers.rs

Expose session analytics state in Responses turn metadata (#44628)

2026-09-10 19:41:14 +00:00