jpmschweitzerandClaude 9d58df85f3 fix(config): default agent model to gemma4:e2b ...

mistral-nemo-large holds ~9.2 GB of the 11 GB card it shares with Speaches,
which starves Whisper and breaks voice transcription. gemma4:e2b holds
1.9 GB and is faster. The deployed stack already overrides this via
OLLAMA_AGENT_MODEL; this aligns the default so a deployment without that
override does not reintroduce the contention.

Co-Authored-By: Claude <noreply@anthropic.com>

2026-08-07 14:58:57 +02:00

..

docs

docs(architecture): registry is git.schweitz.net not git.schweitz.internal

2026-07-19 17:11:08 +02:00

src

fix(config): default agent model to gemma4:e2b

2026-08-07 14:58:57 +02:00

tests

fix(config): use docker hostnames for tatlock and searxng defaults

2026-07-19 12:21:43 +02:00

.env.example

fix(config): default agent model to gemma4:e2b

2026-08-07 14:58:57 +02:00

AGENTS.md

refactor: reorganize into monorepo with separate subprojects

2026-01-10 10:37:47 +01:00

CHANGELOG.md

fix(config): default agent model to gemma4:e2b

2026-08-07 14:58:57 +02:00

Dockerfile

refactor: reorganize into monorepo with separate subprojects

2026-01-10 10:37:47 +01:00

pyproject.toml

chore: release api v1.0.1

2026-07-19 12:32:02 +02:00

requirements-dev.txt

refactor: reorganize into monorepo with separate subprojects

2026-01-10 10:37:47 +01:00

requirements.txt

fix: replace litellm with tiktoken for token counting

2026-01-11 23:05:11 +01:00

wakeup.sh

refactor: reorganize into monorepo with separate subprojects

2026-01-10 10:37:47 +01:00