Benjamin Admin 736ddf647d fix(llm-dedup): use think:false instead of /no_think, restore 30s timeout ...

Ollama API supports "think": false to disable extended thinking mode
on qwen3.5. Reduces response time from 95s to ~3s per comparison.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

2026-04-22 20:31:13 +02:00

.claude

…

.gitea/workflows

…

admin-core

…

backend-core

…

billing-service

…

bpmn-processes

…

consent-service

…

control-pipeline

fix(llm-dedup): use think:false instead of /no_think, restore 30s timeout

2026-04-22 20:31:13 +02:00

docs-src

…

document-templates

…

embedding-service

…

gitea

…

levis-holzbau

…

nginx

…

night-scheduler

…

paddleocr-service

…

pitch-deck

chore: diagnose 1M version data on production

2026-04-22 20:18:24 +02:00

rag-service

…

scripts

…

vault

…

voice-service

…

.env.coolify.example

…

.env.example

…

.gitignore

…

docker-compose.coolify.yml

…

docker-compose.hetzner.yml

…

docker-compose.yml

…

mkdocs.yml

…

update_pitch_deck_maschinenbau.sql

…

Description

No description provided

51 MiB

Languages

TypeScript 36.1%

Python 33.4%

Go 25.4%

HTML 3.2%

Shell 0.8%

Other 1.1%