Fully autonomous AI Agents system capable of performing complex penetration testing tasks
Go ai-agentsai-security-toolanthropicautonomous-agentsgolanggptgraphqlmulti-agent-systemoffensive-securityopen-sourceopenaipenetration-testingpenetration-testing-toolsreactsecurity-automationsecurity-testingsecurity-toolsself-hosted
fix(deepseek): update default model names to DeepSeek V4
mason50523113ff3aa330
diff --git a/README.md b/README.mdindex 7ddc15ba..8eb74422 100644--- a/README.md+++ b/README.md@@ -1845,23 +1845,28 @@ DEEPSEEK_SERVER_URL=https://api.deepseek.com# With LiteLLM proxyDEEPSEEK_API_KEY=your_litellm_keyDEEPSEEK_SERVER_URL=http://litellm-proxy:4000-DEEPSEEK_PROVIDER=deepseek # Adds prefix to model names (deepseek/deepseek-chat) for LiteLLM+DEEPSEEK_PROVIDER=deepseek # Adds prefix to model names (deepseek/deepseek-v4-flash) for LiteLLM```#### Supported Models-PentAGI supports 2 DeepSeek-V3.2 models with tool calling, streaming, thinking modes, and context caching. Both models are used in default configuration.+PentAGI supports 2 DeepSeek V4 models with tool calling, streaming, thinking modes, and context caching. Both models are used in default configuration.-| Model ID | Thinking | Context | Max Output | Price (Input/Output/Cache) | Use Case |-| --------------------- | -------- | ------- | ---------- | -------------------------- | ----------------------------------------------- |-| `deepseek-chat`* | ❌ | 128K | 8K | $0.28/$0.42/$0.03 | General dialogue, code generation, tool calling |-| `deepseek-reasoner`* | ✅ | 128K | 64K | $0.28/$0.42/$0.03 | Advanced reasoning, complex logic, security analysis |+| Model ID | Thinking | Context | Price (Input/Output/Cache) | Use Case |+| --------------------- | -------- | ------- | -------------------------- | ---------------------------------------------------- |+| `deepseek-v4-flash`* | ❌ | 128K | $0.28/$0.42/$0.03 | General dialogue, code generation, tool calling |+| `deepseek-v4-pro`* | ✅ | 128K | $0.28/$0.42/$0.03 | Advanced reasoning, complex logic, security analysis |**Prices**: Per 1M tokens. Cache pricing is for prompt caching (10% of input cost). Models with thinking support include reinforcement learning chain-of-thought reasoning.+> The legacy model names `deepseek-chat` and `deepseek-reasoner` are scheduled+> for deprecation by DeepSeek on 2026-07-24. Existing user configurations+> referencing the legacy names continue to work until then; the defaults above+> use the current V4 names.+**Key Features**:- **Automatic Prompt Caching**: 40-60% cost reduction on repeated context (10% of input price)-- **Extended Thinking**: Reinforcement learning CoT for complex security analysis (deepseek-reasoner)+- **Extended Thinking**: Reinforcement learning CoT for complex security analysis (deepseek-v4-pro)- **Strong Coding**: Optimized for code generation and exploit development- **Tool Calling**: Seamless integration with 20+ pentesting tools via function calling- **Streaming**: Real-time response streaming for interactive workflows@@ -2715,7 +2720,7 @@ With `LLM_SERVER_PROVIDER=moonshot`, the system automatically prefixes all modelWhen using LiteLLM proxy, set the corresponding `*_PROVIDER` variable to enable model prefixing:-- `deepseek` - for DeepSeek models (`DEEPSEEK_PROVIDER=deepseek` → `deepseek/deepseek-chat`)+- `deepseek` - for DeepSeek models (`DEEPSEEK_PROVIDER=deepseek` → `deepseek/deepseek-v4-flash`)- `zai` - for GLM models (`GLM_PROVIDER=zai` → `zai/glm-4`)- `moonshot` - for Kimi models (`KIMI_PROVIDER=moonshot` → `moonshot/kimi-k2.5`)- `dashscope` - for Qwen models (`QWEN_PROVIDER=dashscope` → `dashscope/qwen-plus`)@@ -2730,7 +2735,7 @@ When using LiteLLM proxy, set the corresponding `*_PROVIDER` variable to enable# Use DeepSeek models via LiteLLM proxy with model prefixingDEEPSEEK_API_KEY=your_litellm_proxy_keyDEEPSEEK_SERVER_URL=http://litellm-proxy:4000-DEEPSEEK_PROVIDER=deepseek # Models become deepseek/deepseek-chat, deepseek/deepseek-reasoner for LiteLLM+DEEPSEEK_PROVIDER=deepseek # Models become deepseek/deepseek-v4-flash, deepseek/deepseek-v4-pro for LiteLLM# Direct DeepSeek API usage (no prefix needed)DEEPSEEK_API_KEY=your_deepseek_api_keydiff --git a/backend/cmd/installer/wizard/locale/locale.go b/backend/cmd/installer/wizard/locale/locale.goindex b7c7f360..c9f04084 100644--- a/backend/cmd/installer/wizard/locale/locale.go+++ b/backend/cmd/installer/wizard/locale/locale.go@@ -504,7 +504,7 @@ Key Advantages:LiteLLM Integration:• Set Provider Name to 'deepseek' when using LiteLLM proxy-• Enables model prefix (e.g., deepseek/deepseek-chat) without modifying config.yml+• Enables model prefix (e.g., deepseek/deepseek-v4-flash) without modifying config.yml• Optional for direct DeepSeek API usageBest for: Teams requiring multilingual support, cost-conscious deployments, Chinese language security testingdiff --git a/backend/docs/config.md b/backend/docs/config.mdindex 26b2c342..79370f99 100644--- a/backend/docs/config.md+++ b/backend/docs/config.md@@ -537,7 +537,7 @@ These settings control the integration with various Large Language Model (LLM) p| DeepSeekServerURL | `DEEPSEEK_SERVER_URL` | `https://api.deepseek.com` | DeepSeek API endpoint URL || DeepSeekProvider | `DEEPSEEK_PROVIDER` | *(none)* | Provider name prefix for LiteLLM integration (optional) |-**LiteLLM Integration**: Set `DEEPSEEK_PROVIDER=deepseek` to enable model prefixing (e.g., `deepseek/deepseek-chat`) when using LiteLLM proxy with default PentAGI configs.+**LiteLLM Integration**: Set `DEEPSEEK_PROVIDER=deepseek` to enable model prefixing (e.g., `deepseek/deepseek-v4-flash`) when using LiteLLM proxy with default PentAGI configs.### GLM LLM Providerdiff --git a/backend/docs/llms_how_to.md b/backend/docs/llms_how_to.mdindex e79639fe..d54c8161 100644--- a/backend/docs/llms_how_to.md+++ b/backend/docs/llms_how_to.md@@ -1196,7 +1196,7 @@ llm, _ := openai.New()resp, _ := llm.GenerateContent(ctx, messages,- llms.WithModel("deepseek-reasoner"),+ llms.WithModel("deepseek-v4-pro"),)// Reasoning extracted from <think>...</think> tags automaticallydiff --git a/backend/pkg/providers/deepseek/config.yml b/backend/pkg/providers/deepseek/config.ymlindex 95512ade..4f95bf6a 100644--- a/backend/pkg/providers/deepseek/config.yml+++ b/backend/pkg/providers/deepseek/config.yml@@ -1,5 +1,5 @@simple:- model: deepseek-chat+ model: deepseek-v4-flashtemperature: 0.5top_p: 0.5n: 1@@ -10,7 +10,7 @@ simple:cache_read: 0.028simple_json:- model: deepseek-chat+ model: deepseek-v4-flashtemperature: 0.5top_p: 0.5n: 1@@ -22,7 +22,7 @@ simple_json:cache_read: 0.028primary_agent:- model: deepseek-reasoner+ model: deepseek-v4-pron: 1max_tokens: 16384price:@@ -31,7 +31,7 @@ primary_agent:cache_read: 0.028assistant:- model: deepseek-reasoner+ model: deepseek-v4-pron: 1max_tokens: 16384price:@@ -40,7 +40,7 @@ assistant:cache_read: 0.028generator:- model: deepseek-reasoner+ model: deepseek-v4-pron: 1max_tokens: 32768price:@@ -49,7 +49,7 @@ generator:cache_read: 0.028refiner:- model: deepseek-reasoner+ model: deepseek-v4-pron: 1max_tokens: 20480price:@@ -58,7 +58,7 @@ refiner:cache_read: 0.028adviser:- model: deepseek-chat+ model: deepseek-v4-flashtemperature: 0.7top_p: 0.8n: 1@@ -69,7 +69,7 @@ adviser:cache_read: 0.028reflector:- model: deepseek-reasoner+ model: deepseek-v4-pron: 1max_tokens: 4096price:@@ -78,7 +78,7 @@ reflector:cache_read: 0.028searcher:- model: deepseek-chat+ model: deepseek-v4-flashtemperature: 0.7top_p: 0.8n: 1@@ -89,7 +89,7 @@ searcher:cache_read: 0.028enricher:- model: deepseek-chat+ model: deepseek-v4-flashtemperature: 0.7top_p: 0.8n: 1@@ -100,7 +100,7 @@ enricher:cache_read: 0.028coder:- model: deepseek-reasoner+ model: deepseek-v4-pron: 1max_tokens: 20480price:@@ -109,7 +109,7 @@ coder:cache_read: 0.028installer:- model: deepseek-reasoner+ model: deepseek-v4-pron: 1max_tokens: 16384price:@@ -118,7 +118,7 @@ installer:cache_read: 0.028pentester:- model: deepseek-reasoner+ model: deepseek-v4-pron: 1max_tokens: 16384price:diff --git a/backend/pkg/providers/deepseek/deepseek.go b/backend/pkg/providers/deepseek/deepseek.goindex a5c2a071..915397cf 100644--- a/backend/pkg/providers/deepseek/deepseek.go+++ b/backend/pkg/providers/deepseek/deepseek.go@@ -19,7 +19,7 @@ import (//go:embed config.yml models.ymlvar configFS embed.FS-const DeepSeekAgentModel = "deepseek-chat"+const DeepSeekAgentModel = "deepseek-v4-flash"const DeepSeekToolCallIDTemplate = "call_{r:2:d}_{r:24:b}"diff --git a/backend/pkg/providers/deepseek/models.yml b/backend/pkg/providers/deepseek/models.ymlindex 3fdadaca..79aae7ed 100644--- a/backend/pkg/providers/deepseek/models.yml+++ b/backend/pkg/providers/deepseek/models.yml@@ -1,13 +1,13 @@-- name: deepseek-chat- description: DeepSeek-V3.2 (Non-thinking Mode) - Suitable for general dialogue, code generation, and tool calling tasks. Supports JSON Output, Tool Calls, Chat Prefix Completion, and FIM Completion. 128K context, max output 8K+- name: deepseek-v4-flash+ description: DeepSeek V4 Flash - Cost-efficient general-purpose model suitable for dialogue, code generation, and tool calling. Supports JSON output and tool calls. 128K context.thinking: falseprice:input: 0.28output: 0.42cache_read: 0.028-- name: deepseek-reasoner- description: DeepSeek-V3.2 (Thinking Mode) - Advanced reasoning model with reinforcement learning chain-of-thought capabilities, suitable for complex logic, mathematical reasoning, and security analysis tasks. 128K context, max output 64K+- name: deepseek-v4-pro+ description: DeepSeek V4 Pro - Higher-tier reasoning model suitable for complex logic, mathematical reasoning, and security analysis. 128K context.thinking: trueprice:input: 0.28diff --git a/examples/configs/deepseek.provider.yml b/examples/configs/deepseek.provider.ymlindex 91b5a535..6c2cb6f4 100644--- a/examples/configs/deepseek.provider.yml+++ b/examples/configs/deepseek.provider.yml@@ -1,5 +1,5 @@simple:- model: deepseek-chat+ model: deepseek-v4-flashtemperature: 0.5top_p: 0.5n: 1@@ -10,7 +10,7 @@ simple:cache_read: 0.028simple_json:- model: deepseek-chat+ model: deepseek-v4-flashtemperature: 0.5top_p: 0.5n: 1@@ -22,7 +22,7 @@ simple_json:cache_read: 0.028primary_agent:- model: deepseek-reasoner+ model: deepseek-v4-pron: 1max_tokens: 8000price:@@ -31,7 +31,7 @@ primary_agent:cache_read: 0.028assistant:- model: deepseek-reasoner+ model: deepseek-v4-pron: 1max_tokens: 8000price:@@ -40,7 +40,7 @@ assistant:cache_read: 0.028generator:- model: deepseek-reasoner+ model: deepseek-v4-pron: 1max_tokens: 8000price:@@ -49,7 +49,7 @@ generator:cache_read: 0.028refiner:- model: deepseek-reasoner+ model: deepseek-v4-pron: 1max_tokens: 8000price:@@ -58,7 +58,7 @@ refiner:cache_read: 0.028adviser:- model: deepseek-chat+ model: deepseek-v4-flashtemperature: 0.7top_p: 0.8n: 1@@ -69,7 +69,7 @@ adviser:cache_read: 0.028reflector:- model: deepseek-reasoner+ model: deepseek-v4-pron: 1max_tokens: 4000price:@@ -78,7 +78,7 @@ reflector:cache_read: 0.028searcher:- model: deepseek-chat+ model: deepseek-v4-flashtemperature: 0.7top_p: 0.8n: 1@@ -89,7 +89,7 @@ searcher:cache_read: 0.028enricher:- model: deepseek-chat+ model: deepseek-v4-flashtemperature: 0.7top_p: 0.8n: 1@@ -100,7 +100,7 @@ enricher:cache_read: 0.028coder:- model: deepseek-reasoner+ model: deepseek-v4-pron: 1max_tokens: 16384price:@@ -109,7 +109,7 @@ coder:cache_read: 0.028installer:- model: deepseek-reasoner+ model: deepseek-v4-pron: 1max_tokens: 8192price:@@ -118,7 +118,7 @@ installer:cache_read: 0.028pentester:- model: deepseek-reasoner+ model: deepseek-v4-pron: 1max_tokens: 8192price: