From 3113ff3aa330be6bbcd2c686d55cd5c61e56303c Mon Sep 17 00:00:00 2001
From: mason5052 <ehehwnwjs5052@gmail.com>
Date: Thu, 21 May 2026 15:44:30 -0400
Subject: [PATCH] fix(deepseek): update default model names to DeepSeek V4

The DeepSeek provider config still defaulted to the legacy
`deepseek-chat` and `deepseek-reasoner` model names, which the
upstream DeepSeek API has announced for deprecation on 2026-07-24.
A first-run install therefore breaks once the legacy names are
removed.

Swap the defaults to the current DeepSeek V4 family:

- non-thinking roles use `deepseek-v4-flash`
- reasoning-heavy roles use `deepseek-v4-pro`

The change is limited to the embedded `config.yml` / `models.yml`
inside `backend/pkg/providers/deepseek`, the matching example at
`examples/configs/deepseek.provider.yml`, the `DeepSeekAgentModel`
fallback constant in `deepseek.go`, and three doc references
(README.md, backend/docs/config.md, backend/docs/llms_how_to.md)
plus one installer help string in
`backend/cmd/installer/wizard/locale/locale.go`. LiteLLM prefix
behavior is untouched.
---
 README.md                                     | 23 +++++++++-------
 backend/cmd/installer/wizard/locale/locale.go |  2 +-
 backend/docs/config.md                        |  2 +-
 backend/docs/llms_how_to.md                   |  2 +-
 backend/pkg/providers/deepseek/config.yml     | 26 +++++++++----------
 backend/pkg/providers/deepseek/deepseek.go    |  2 +-
 backend/pkg/providers/deepseek/models.yml     |  8 +++---
 examples/configs/deepseek.provider.yml        | 26 +++++++++----------
 8 files changed, 48 insertions(+), 43 deletions(-)

diff --git a/README.md b/README.md
index 7ddc15ba..8eb74422 100644
--- a/README.md
+++ b/README.md
@@ -1845,23 +1845,28 @@ DEEPSEEK_SERVER_URL=https://api.deepseek.com
 # With LiteLLM proxy
 DEEPSEEK_API_KEY=your_litellm_key
 DEEPSEEK_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 model
 
 When 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 prefixing
 DEEPSEEK_API_KEY=your_litellm_proxy_key
 DEEPSEEK_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_key
diff --git a/backend/cmd/installer/wizard/locale/locale.go b/backend/cmd/installer/wizard/locale/locale.go
index 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 usage
 
 Best for: Teams requiring multilingual support, cost-conscious deployments, Chinese language security testing
diff --git a/backend/docs/config.md b/backend/docs/config.md
index 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 Provider
 
diff --git a/backend/docs/llms_how_to.md b/backend/docs/llms_how_to.md
index 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 automatically
diff --git a/backend/pkg/providers/deepseek/config.yml b/backend/pkg/providers/deepseek/config.yml
index 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-flash
   temperature: 0.5
   top_p: 0.5
   n: 1
@@ -10,7 +10,7 @@ simple:
     cache_read: 0.028
 
 simple_json:
-  model: deepseek-chat
+  model: deepseek-v4-flash
   temperature: 0.5
   top_p: 0.5
   n: 1
@@ -22,7 +22,7 @@ simple_json:
     cache_read: 0.028
 
 primary_agent:
-  model: deepseek-reasoner
+  model: deepseek-v4-pro
   n: 1
   max_tokens: 16384
   price:
@@ -31,7 +31,7 @@ primary_agent:
     cache_read: 0.028
 
 assistant:
-  model: deepseek-reasoner
+  model: deepseek-v4-pro
   n: 1
   max_tokens: 16384
   price:
@@ -40,7 +40,7 @@ assistant:
     cache_read: 0.028
 
 generator:
-  model: deepseek-reasoner
+  model: deepseek-v4-pro
   n: 1
   max_tokens: 32768
   price:
@@ -49,7 +49,7 @@ generator:
     cache_read: 0.028
 
 refiner:
-  model: deepseek-reasoner
+  model: deepseek-v4-pro
   n: 1
   max_tokens: 20480
   price:
@@ -58,7 +58,7 @@ refiner:
     cache_read: 0.028
 
 adviser:
-  model: deepseek-chat
+  model: deepseek-v4-flash
   temperature: 0.7
   top_p: 0.8
   n: 1
@@ -69,7 +69,7 @@ adviser:
     cache_read: 0.028
 
 reflector:
-  model: deepseek-reasoner
+  model: deepseek-v4-pro
   n: 1
   max_tokens: 4096
   price:
@@ -78,7 +78,7 @@ reflector:
     cache_read: 0.028
 
 searcher:
-  model: deepseek-chat
+  model: deepseek-v4-flash
   temperature: 0.7
   top_p: 0.8
   n: 1
@@ -89,7 +89,7 @@ searcher:
     cache_read: 0.028
 
 enricher:
-  model: deepseek-chat
+  model: deepseek-v4-flash
   temperature: 0.7
   top_p: 0.8
   n: 1
@@ -100,7 +100,7 @@ enricher:
     cache_read: 0.028
 
 coder:
-  model: deepseek-reasoner
+  model: deepseek-v4-pro
   n: 1
   max_tokens: 20480
   price:
@@ -109,7 +109,7 @@ coder:
     cache_read: 0.028
 
 installer:
-  model: deepseek-reasoner
+  model: deepseek-v4-pro
   n: 1
   max_tokens: 16384
   price:
@@ -118,7 +118,7 @@ installer:
     cache_read: 0.028
 
 pentester:
-  model: deepseek-reasoner
+  model: deepseek-v4-pro
   n: 1
   max_tokens: 16384
   price:
diff --git a/backend/pkg/providers/deepseek/deepseek.go b/backend/pkg/providers/deepseek/deepseek.go
index 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.yml
 var 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.yml
index 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: false
   price:
     input: 0.28
     output: 0.42
     cache_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: true
   price:
     input: 0.28
diff --git a/examples/configs/deepseek.provider.yml b/examples/configs/deepseek.provider.yml
index 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-flash
   temperature: 0.5
   top_p: 0.5
   n: 1
@@ -10,7 +10,7 @@ simple:
     cache_read: 0.028
 
 simple_json:
-  model: deepseek-chat
+  model: deepseek-v4-flash
   temperature: 0.5
   top_p: 0.5
   n: 1
@@ -22,7 +22,7 @@ simple_json:
     cache_read: 0.028
 
 primary_agent:
-  model: deepseek-reasoner
+  model: deepseek-v4-pro
   n: 1
   max_tokens: 8000
   price:
@@ -31,7 +31,7 @@ primary_agent:
     cache_read: 0.028
 
 assistant:
-  model: deepseek-reasoner
+  model: deepseek-v4-pro
   n: 1
   max_tokens: 8000
   price:
@@ -40,7 +40,7 @@ assistant:
     cache_read: 0.028
 
 generator:
-  model: deepseek-reasoner
+  model: deepseek-v4-pro
   n: 1
   max_tokens: 8000
   price:
@@ -49,7 +49,7 @@ generator:
     cache_read: 0.028
 
 refiner:
-  model: deepseek-reasoner
+  model: deepseek-v4-pro
   n: 1
   max_tokens: 8000
   price:
@@ -58,7 +58,7 @@ refiner:
     cache_read: 0.028
 
 adviser:
-  model: deepseek-chat
+  model: deepseek-v4-flash
   temperature: 0.7
   top_p: 0.8
   n: 1
@@ -69,7 +69,7 @@ adviser:
     cache_read: 0.028
 
 reflector:
-  model: deepseek-reasoner
+  model: deepseek-v4-pro
   n: 1
   max_tokens: 4000
   price:
@@ -78,7 +78,7 @@ reflector:
     cache_read: 0.028
 
 searcher:
-  model: deepseek-chat
+  model: deepseek-v4-flash
   temperature: 0.7
   top_p: 0.8
   n: 1
@@ -89,7 +89,7 @@ searcher:
     cache_read: 0.028
 
 enricher:
-  model: deepseek-chat
+  model: deepseek-v4-flash
   temperature: 0.7
   top_p: 0.8
   n: 1
@@ -100,7 +100,7 @@ enricher:
     cache_read: 0.028
 
 coder:
-  model: deepseek-reasoner
+  model: deepseek-v4-pro
   n: 1
   max_tokens: 16384
   price:
@@ -109,7 +109,7 @@ coder:
     cache_read: 0.028
 
 installer:
-  model: deepseek-reasoner
+  model: deepseek-v4-pro
   n: 1
   max_tokens: 8192
   price:
@@ -118,7 +118,7 @@ installer:
     cache_read: 0.028
 
 pentester:
-  model: deepseek-reasoner
+  model: deepseek-v4-pro
   n: 1
   max_tokens: 8192
   price: