Phillip Tarrant 1ed863d3fe docs(spec): Narrator streaming (M2) design ...

Real token streaming to hide the ~2s call (§14). Proxy emits its own minimal
NDJSON (delta/done/error); /dm/narrate becomes a 200 stream (422 stays sync,
model errors become an in-stream frame). Client reworks to an HTTPClient
poll-loop StreamTransport behind a testable seam; hold-back tag filter;
keep-partial mid-stream degrade; folds in the HttpTransport timeout fix.
Narrator first; NPC fast-follow.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

2026-07-10 14:23:32 -05:00

..

plans

docs(plan): bounded NPC conversation implementation plan

2026-07-10 12:03:58 -05:00

specs

docs(spec): Narrator streaming (M2) design

2026-07-10 14:23:32 -05:00