lfg2025/botfights
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

docs(prompt): AI-agent consent preamble, operator-only LLM creds (drop ANTHROPIC_API_KEY pattern), accurate queue-join timing — feedback from first real AI agent test
CI / check (push) Failing after 6m5s
Details

Browse Source 
The first cloud AI agent given the prompt refused it as a suspected prompt
injection: 'nothing else needs to be read' framing, raw-IP fallback, and
being told to wire its own ANTHROPIC_API_KEY into a persistent script. All
three patterns removed; brains are now an operator-supplied optional
OpenAI-compatible endpoint with local heuristics as default. queue/join
documented as blocking ~35s (60s client timeout) matching the real 30s
production QUEUE_TIMEOUT_MS.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
This commit is contained in:
Dorian
2026-07-30 23:52:18 -04:00
co-authored by Claude Fable 5
parent 90d5e2d16d
commit d2fc998a28
2 changed files with 88 additions and 50 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docker-compose.arena.yml
+1 -1
View File
@@ -18,7 +18,7 @@
services:
botfights-arena:
image: localhost:3000/lfg2025/botfights:1.2.0
image: localhost:3000/lfg2025/botfights:1.2.1
container_name: botfights-arena
restart: unless-stopped
ports: