busya ff4804164a feat(translate): universal reasoning suppression for DeepSeek/Qwen/MiniMax/Kimi ...

Added disable_reasoning toggle that works via:
1. API parameter: reasoning_effort: 'none' (DeepSeek, Qwen)
2. System prompt instruction: 'Respond directly with ONLY the JSON.
   Do NOT include any reasoning, thinking, or chain-of-thought'
   (works for ALL models universally)

Backend: model column, schema, preview+executor payload
Frontend: checkbox in LLM settings, i18n en+ru

2026-05-15 10:13:37 +03:00

..

api

fix(translate): add EXPLORE logging for LLM JSON parse failures

2026-05-15 09:15:36 +03:00

core

chore(lint): apply ruff --fix (4443 auto-fixes)

2026-05-14 11:20:17 +03:00

models

feat(translate): universal reasoning suppression for DeepSeek/Qwen/MiniMax/Kimi

2026-05-15 10:13:37 +03:00

plugins

feat(translate): universal reasoning suppression for DeepSeek/Qwen/MiniMax/Kimi

2026-05-15 10:13:37 +03:00

schemas

feat(translate): universal reasoning suppression for DeepSeek/Qwen/MiniMax/Kimi

2026-05-15 10:13:37 +03:00

scripts

chore: remove legacy SQLite migration script + fix stale comments

2026-05-14 23:48:13 +03:00

services

chore(lint): apply ruff --fix (4443 auto-fixes)

2026-05-14 11:20:17 +03:00

__init__.py

fix(llm): add fetch-models endpoint, fix SQL Lab INSERT (client_id truncation, sync mode, target_column, timestamp normalization)

2026-05-13 20:06:15 +03:00

app.py

chore: update semantic index, agent configs, and app startup

2026-05-14 21:33:26 +03:00

dependencies.py

chore(lint): apply ruff --fix (4443 auto-fixes)

2026-05-14 11:20:17 +03:00