nova/DungeonsDragons
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Compare commits

base: nova/DungeonsDragons:cc680dc392b74f74d9aac10737555abc32eeb7c5
Branches Tags
nova/DungeonsDragons:master
...
compare: nova/DungeonsDragons:1b64010280c12fbfcd7385a71076fd23efb7b695
Branches Tags
nova/DungeonsDragons:master

2 Commits
cc680dc392 ... 1b64010280

Author SHA1 Message Date
Thorsten 1b64010280 Fix stale DM_MODEL default in .env.example 
grok-4.6 was never a real x.ai model id; the live .env has used
grok-4.3 for a while, .env.example just hadn't caught up.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
 2026-09-06 21:26:10 +02:00
Thorsten d62970ee1b Fix backend dependency vulnerabilities (36 CVEs across 6 packages) 
Upgrades fastapi (0.115.6->0.141.1, pulling starlette to 1.6.0),
fastapi-users (14.0.1->15.0.5), aiosmtplib (3.0.2->5.1.2),
python-multipart (0.0.20->0.0.32), and sentence-transformers
(3.3.1->6.0.1, pulling transformers and pyjwt to patched versions).

Verified via pip-audit (zero remaining findings across all 97
resolved dependencies) and functional smoke tests: auth flow, RAG
embedding/retrieval (dimension still 384, similarity still sane),
DM-turn tool-calling (roll_dice still fires correctly), and a live
WebSocket handshake/send/broadcast round trip against the upgraded
Starlette.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
 2026-09-06 21:26:10 +02:00
2 changed files with 6 additions and 6 deletions
Expand all files Collapse all files
.env.example
+1 -1
View File
@@ -5,7 +5,7 @@ LLM_PROVIDER=xai
# x.ai API (Grok) — used when LLM_PROVIDER=xai. Get a key at https://console.x.ai # x.ai API (Grok) — used when LLM_PROVIDER=xai. Get a key at https://console.x.ai
XAI_API_KEY= XAI_API_KEY=
DM_MODEL=grok-4.6 DM_MODEL=grok-4.3
# LM Studio local server — used when LLM_PROVIDER=lmstudio. Use host.docker.internal, not a # LM Studio local server — used when LLM_PROVIDER=lmstudio. Use host.docker.internal, not a
# LAN IP — the backend runs inside Docker and can't necessarily reach the host's LAN address # LAN IP — the backend runs inside Docker and can't necessarily reach the host's LAN address
backend/requirements.txt
+5 -5
View File
@@ -1,13 +1,13 @@
fastapi==0.115.6 fastapi==0.141.1
uvicorn[standard]==0.34.0 uvicorn[standard]==0.34.0
sqlalchemy[asyncio]==2.0.36 sqlalchemy[asyncio]==2.0.36
asyncpg==0.30.0 asyncpg==0.30.0
alembic==1.14.0 alembic==1.14.0
pydantic-settings==2.7.0 pydantic-settings==2.7.0
fastapi-users[sqlalchemy]==14.0.1 fastapi-users[sqlalchemy]==15.0.5
openai>=1.50.0,<2.0.0 openai>=1.50.0,<2.0.0
aiosmtplib==3.0.2 aiosmtplib==5.1.2
python-multipart==0.0.20 python-multipart==0.0.32
websockets==14.1 websockets==14.1
pgvector==0.3.6 pgvector==0.3.6
sentence-transformers==3.3.1 sentence-transformers==6.0.1