2026-04-19 16:16:13 +02:00
|
|
|
# Festinger Proxy Configuration
|
|
|
|
|
|
|
|
|
|
# Where the real Ollama is running (for /api/chat, /api/generate, /api/*)
|
|
|
|
|
upstream_ollama: "http://host.docker.internal:11434"
|
|
|
|
|
|
|
|
|
|
# Where the real Anthropic API is running (for /v1/messages)
|
|
|
|
|
# Override via UPSTREAM_ANTHROPIC env var if needed
|
|
|
|
|
upstream_anthropic: "https://api.anthropic.com"
|
|
|
|
|
|
2026-04-21 19:17:51 +02:00
|
|
|
# Where the real OpenAI-compatible API is running (for /v1/chat/completions).
|
|
|
|
|
# For LM Studio set this to its local address, e.g. "http://host.docker.internal:1234"
|
2026-04-19 16:16:13 +02:00
|
|
|
# Override via UPSTREAM_OPENAI env var if needed
|
2026-04-21 19:17:51 +02:00
|
|
|
upstream_openai: "http://host.docker.internal:1234"
|
2026-04-19 16:16:13 +02:00
|
|
|
|
|
|
|
|
# Port this proxy listens on inside the container (exposed as 11434 on the docker network)
|
|
|
|
|
proxy_port: 11434
|
|
|
|
|
|
|
|
|
|
# Postgres connection string (overridable via POSTGRES_DSN env var)
|
|
|
|
|
postgres_dsn: "postgresql://festinger:festinger@postgres:5432/festinger"
|
|
|
|
|
|
|
|
|
|
detection:
|
|
|
|
|
# How many recent completions to keep per session
|
|
|
|
|
window_size: 5
|
|
|
|
|
# Minimum response length to bother checking (ignore trivial one-liners)
|
|
|
|
|
min_length: 20
|
|
|
|
|
|
|
|
|
|
mitigations:
|
|
|
|
|
# Applied in order. circuit_breaker short-circuits all others.
|
|
|
|
|
|
|
|
|
|
- strategy: temperature_boost
|
|
|
|
|
enabled: true
|
|
|
|
|
trigger_count: 2 # kick in after this many identical responses in a row
|
|
|
|
|
boost_amount: 0.35 # added to whatever temperature the request specified
|
|
|
|
|
max_temperature: 1.4 # ceiling
|
|
|
|
|
|
|
|
|
|
- strategy: forbidden_action
|
|
|
|
|
enabled: true
|
|
|
|
|
trigger_count: 2
|
|
|
|
|
# {count} is replaced with the consecutive repeat count
|
|
|
|
|
injection_message: >
|
|
|
|
|
STOP. You have produced the exact same response {count} times in a row.
|
|
|
|
|
You are FORBIDDEN from generating that response again.
|
|
|
|
|
You MUST try a completely different approach: either use a different tool,
|
|
|
|
|
break the task into smaller steps, or write a note explaining why you are
|
|
|
|
|
stuck and then stop.
|
|
|
|
|
|
|
|
|
|
- strategy: history_truncation
|
|
|
|
|
enabled: true
|
|
|
|
|
trigger_count: 3 # more aggressive — only after 3 repeats
|
|
|
|
|
truncate_turns: 6 # drop this many turns from the tail of the message history
|
|
|
|
|
|
|
|
|
|
- strategy: circuit_breaker
|
|
|
|
|
enabled: true
|
|
|
|
|
trigger_count: 5 # hard stop after 5 identical responses
|
|
|
|
|
response_message: >
|
|
|
|
|
[LOOP DETECTOR] This agent has produced the same response 5 times in a row.
|
|
|
|
|
The task has been halted to prevent an infinite loop.
|
|
|
|
|
A human operator should review the task state and restart with fresh context.
|
