{"version":"2.1.286","anchor":"startupturn-timing-phases-expanded","canonical_anchor":"startupturn-timing-phases-expanded","heading":"Turn-latency timing gains new phases, token count and server-receipt time","tier":"internal","area":"API Requests","url":"https:\/\/changelogs.core-directive.com\/v\/2.1.286\/e\/startupturn-timing-phases-expanded","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.286","markdown":"### Turn-latency timing gains new phases, token count and server-receipt time\n\nTurn timing now splits out tool_pool_refresh, model_gates, request_build and redrive phases, and result messages carry new timing fields\n\n**Unclear.** It is unclear whether these timings are sent anywhere or only kept locally.\n\n**What**\n\nClaude Code times each turn in named phases so the time before a request goes out can be broken down. The list of phases used to end at `client_creation`. It now adds:\n\n- `tool_pool_refresh`, `model_gates` and `request_build`.\n\n- Four retry phases: `redrive_reactive_compact`, `redrive_fallback_model`, `redrive_non_streaming` and `redrive_other`. A redrive is a request sent again after the first attempt. A new `noteRedrive` records it, and the time after the first send goes into `redrive_<cause>`, or `redrive_other` when the cause has no name of its own.\n\n- The documentation for `time_to_request_phases_ms` lists the new phases.\n\nResult messages, sent at the end of a turn, also gain two fields. Both are marked internal and appear only together with `request_sent_wall_ms`:\n\n- `first_request_input_tokens`: the first request's input tokens plus cache-read and cache-creation tokens.\n\n- `user_message_server_received_wall_ms`: when the server received the user's message.\n\nThe SDK's process transport, the part that starts Claude Code as a separate program, now calls `options.onProcessSpawned(pid)` once that program has started.\n\n**Why**\n\nThis is timing data for programs that host Claude Code sessions, with no visible effect in normal use. It shows more precisely where the time before a response goes, including time lost to retries.\n\n- Area: API Requests\n- Tier: Under the hood\n- Useful: 1\/5\n- Signal: 1\/5"}