Files
dsh-context/tests/client/components
bowenliang123 ffc89ff197 feat(host,client): split the timing model call into TTFT and LLM generation
The step-start → assistant-message slice reads off the stream now: the
model wait (TTFT, step start → first token) and the generation (first
token → message), folded from assistant/chunk — only the open step's
first non-empty text/reasoning/tool-call delta stamps the slot (the
session-stats rule). Calls with no recorded token stay unattributed in
the overhead residue. `lmMs` leaves TimingTotals for `ttftMs` + `genMs`,
the stepStart slot gains the stamp — stateVersion 12, rows refold.
2026-09-02 18:05:27 +08:00
..