tts-voice-creator-clone-and.../routes
mARTin-B78 3503f5bda6 Live LLM-thinking stream, fix resolver garbage names, safer rules (v1.12.95)
The LLM Reading card splits into thinking-stream (left) and passage
(right), fed by a new SSE endpoint that shares prompt-building and
parsing with the blocking one and falls back to it on any stream
failure (inactivity timeout, not overall). The deterministic resolver
no longer invents speakers from scenery nouns (PLATZ/GESICHTER/
KLEINIGKEIT) — person-noun whitelist plus a clause-subject pattern —
and gains the impersonal post-quote formula and strict two-person
alternation with colon/page/window guards. All reported failure cases
verified against the exact book sentences.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-07-05 10:50:34 +02:00
..
__init__.py Security audit, modular refactor, and container-name field 2026-05-29 12:13:07 +02:00
admin.py Release v1.6.0: a11y (WCAG AA), i18n (DE), PWA, perf, tests, Cast UX 2026-06-03 14:23:35 +02:00
characters.py release: v1.12.52 2026-06-30 13:53:08 +02:00
conversation.py Live LLM-thinking stream, fix resolver garbage names, safer rules (v1.12.95) 2026-07-05 10:50:34 +02:00
docker.py release: v1.12.52 2026-06-30 13:53:08 +02:00
library.py Back user state with SQLite voice index 2026-06-30 15:06:43 +02:00
reader.py Fix casting-feed freeze, zip cast export, character generation prompts (v1.12.90) 2026-07-04 12:48:00 +02:00
rehearsals_db.py release: v1.12.52 2026-06-30 13:53:08 +02:00
settings.py Security audit, modular refactor, and container-name field 2026-05-29 12:13:07 +02:00
sources.py Back user state with SQLite voice index 2026-06-30 15:06:43 +02:00
stt.py Release v1.8.1 2026-06-25 18:48:42 +02:00
tts.py Merge Reader/Casting/Rehearser pipeline into one guided workflow (v1.12.84) 2026-07-03 17:45:38 +02:00