Andrei Eternal c8a8295e79 Attribute turn metrics to the models used during the turn (#44656) ...

## Why

Turn completion metrics used session-level telemetry, which could label usage with the wrong model after a model switch. A turn can also include compaction and responses from different models, so a single token total cannot attribute usage correctly.

## What changed

- Accumulate token usage by model using each response's resolved step settings, and emit one histogram sample per model and token type per turn.
- Preserve zero-valued samples when no usage is reported, without adding a sample for an unused selected model when only compaction ran.
- Use turn telemetry for tool-call, memory, network-proxy, and running-process metrics.

## Testing

Add regression tests for model switches, step-level model changes, compaction followed by a response or an aborted turn, and turns without responses. Verify repeated requests aggregate into one sample per model and earlier session usage is excluded.

GitOrigin-RevId: 03ab1dcde7da0b16b3a500a9a05e4c86583ee585

2026-09-10 21:58:58 +00:00

..

compact.rs

Always use streamed remote compaction for supported providers (#44255)

2026-09-09 18:04:04 +00:00

lifecycle.rs

Add experimental thread queue APIs to app server (#38456)

2026-08-13 23:38:02 +00:00

mod_tests.rs

Attribute turn metrics to the models used during the turn (#44656)

2026-09-10 21:58:58 +00:00

mod.rs

Attribute turn metrics to the models used during the turn (#44656)

2026-09-10 21:58:58 +00:00

regular.rs

Preserve root turn attribution in turn-start events (#44611)

2026-09-10 18:24:13 +00:00

review.rs

Use the originating model when recording conversation history (#44243)

2026-09-09 17:46:00 +00:00

user_shell_tests.rs

[codex] simplify shell snapshot ownership (#27756)

2026-06-15 08:18:13 -07:00

user_shell.rs

Preserve root turn attribution in turn-start events (#44611)

2026-09-10 18:24:13 +00:00