avi/S.H.O.N.A.R._Desktop_Companion
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Summarize tone: re-summarize in a chosen voice (backend)

Browse source 
POST /reprocess?job=summarize&tone=<voice> persists the voice on the job
row (queue carries only ids, so a sweep re-enqueue keeps it), the LLM
prompt appends 'write every field in a <tone> tone — the tone colors
the wording, never the facts', and the resulting summary records its
tone (SummaryOut.tone). Plain re-summarize clears a previous tone.
Migration tone0000000001 (summaries.tone, processing_jobs.tone).
78 passed, 1 skipped; ruff clean.
This commit is contained in:
avi 2026-09-15 14:24:36 -05:00
commit b63f49241d
11 changed files with 82 additions and 13 deletions
Download patch file Download diff file Expand all files Collapse all files

3
backend/shonar/services/ai/__init__.py
View file

@ -112,7 +112,8 @@ class SummaryResult:
class LlmProvider(Protocol):
name: str
async def summarize(self, transcript: str, *, title: str | None = None) -> SummaryResult: ...
async def summarize(self, transcript: str, *, title: str | None = None,
tone: str | None = None) -> SummaryResult: ...
def get_transcription_provider(settings: Settings) -> TranscriptionProvider | None: