Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.decepticon.red/llms.txt

Use this file to discover all available pages before exploring further.

​
Overview

Not every agent task requires the most powerful model. Decepticon uses LiteLLM as a proxy layer to route different agent roles to different model tiers — balancing cost, speed, and capability.

​
Model Profiles

Three built-in profiles optimize for different use cases:
ProfileOrchestratorExploitReconUse Case
ecoOpus 4.7Sonnet 4.6Haiku 4.5Production — best cost/performance ratio (default)
maxOpus 4.7Opus 4.7Sonnet 4.6High-value targets — maximum capability
testHaiku 4.5Haiku 4.5Haiku 4.5Development/CI — fast iteration
The full per-tier model matrix across providers is:
TierAnthropic APIAnthropic OAuthOpenAIGoogleMiniMax
HIGHclaude-opus-4-7auth/claude-opus-4-7gpt-5.5gemini-2.5-proMiniMax-M2.5
MIDclaude-sonnet-4-6auth/claude-sonnet-4-6gpt-5.4gemini-2.5-flashMiniMax-M2.5-lightning
LOWclaude-haiku-4-5auth/claude-haiku-4-5gpt-5-nanogemini-2.5-flash-lite—
The eco profile is recommended for most engagements. The orchestrator needs deep reasoning (Opus), but reconnaissance tasks work well with faster, cheaper models.

​
Role-Based Routing

Each agent role has different cognitive demands:

Orchestrator

Needs deep reasoning for objective sequencing, dependency resolution, and attack path adaptation. Routes to the most capable model.

Exploit Agent

Requires strong technical reasoning for vulnerability exploitation and tool operation. Routes to mid-high tier.

Recon Agent

Handles structured tasks — port scanning, service enumeration, output parsing. Works well with faster models.

Post-Exploit Agent

Complex post-exploitation through C2 sessions. Routes similarly to exploit tier.

​
Automatic Fallback

Each tier has a fallback chain across providers. If the primary provider hits a rate limit or experiences an outage, Decepticon seamlessly switches to the next provider in the chain: 
HIGH:  Opus 4.7   → GPT-5.5    → Gemini 2.5 Pro        → MiniMax-M2.5
MID:   Sonnet 4.6 → GPT-5.4    → Gemini 2.5 Flash      → MiniMax-M2.5-lightning
LOW:   Haiku 4.5  → GPT-5-nano → Gemini 2.5 Flash-Lite
Provider order is configurable via the DECEPTICON_AUTH_PRIORITY environment variable (e.g., anthropic_oauth,anthropic_api,openai_api,google_api,minimax_api). The switch is transparent — no manual intervention, no interrupted operations.

​
Provider Support

Any LiteLLM-compatible backend works:
  • Anthropic — Claude Opus 4.7, Sonnet 4.6, Haiku 4.5 (API key or Claude OAuth subscription)
  • OpenAI — GPT-5.5, GPT-5.4, GPT-5-nano
  • Google — Gemini 2.5 Pro / Flash / Flash-Lite
  • MiniMax — MiniMax-M2.5 and M2.5-lightning
  • Self-hosted — vLLM, Ollama, or any OpenAI-compatible endpoint
Configure via decepticon onboard or environment variables. See Configuration for details.