feat: add DeepSeek + GLM Coding Plan providers, fix DeepSeek reasonin…

README.md

@@ -34,7 +34,7 @@ Or download our self-hosted PDF version of the paper [here](https://byterover.de
 - 🖥️ Interactive TUI with REPL interface (React/Ink)
 - 🧠 Context tree and knowledge storage management
 - 🔀 Git-like version control for the context tree (branch, commit, merge, push/pull)
-- 🤖 18 LLM providers (Anthropic, OpenAI, Google, Groq, Mistral, xAI, and more)
+- 🤖 20 LLM providers (Anthropic, OpenAI, Google, Groq, Mistral, xAI, DeepSeek, and more)
 - 🛠️ 24 built-in agent tools (code exec, file ops, knowledge search, memory management)
 - 🔄 Cloud sync with push/pull
 - 👀 Review workflow for curate operations (approve/reject pending changes)
@@ -220,7 +220,7 @@ Run `brv --help` for the full command reference.
 <details>
 <summary><h2>Supported LLM Providers</h2></summary>
 
-ByteRover CLI supports 18 LLM providers out of the box. Connect and switch providers from the dashboard, or use `brv providers connect` / `brv providers switch`.
+ByteRover CLI supports 20 LLM providers out of the box. Connect and switch providers from the dashboard, or use `brv providers connect` / `brv providers switch`.
 
 | Provider | Description |
 |----------|-------------|
@@ -233,13 +233,15 @@ ByteRover CLI supports 18 LLM providers out of the box. Connect and switch provi
 | Cerebras | Fast inference |
 | Cohere | Command models |
 | DeepInfra | Open-source model hosting |
+| DeepSeek | DeepSeek V3 and R1 reasoning models |
 | OpenRouter | Multi-provider gateway |
 | Perplexity | Search-augmented models |
 | TogetherAI | Open-source model hosting |
 | Vercel | AI SDK provider |
 | Minimax | Minimax models |
 | Moonshot | Kimi models |
 | GLM | GLM models |
+| GLM Coding Plan | GLM models on Z.AI Coding Plan subscription |
 | OpenAI-Compatible | Any OpenAI-compatible API |
 | ByteRover | ByteRover's hosted models |
 

src/agent/infra/llm/model-capabilities.ts

@@ -9,7 +9,8 @@
  * - Grok: `reasoning_content` or `reasoning_details` fields
  * - Gemini via OpenRouter: `reasoning_details` array or `thoughts` field
  * - GLM (Zhipu AI): `reasoning_content` field in API response
- * - Claude/DeepSeek/MiniMax: `<think>...</think>` XML tags in content
+ * - DeepSeek (R1/Reasoner): `reasoning_content` field in API response (OpenAI-compatible)
+ * - Claude/MiniMax: `<think>...</think>` XML tags in content
  */
 
 /**
@@ -54,7 +55,7 @@
  * // { reasoning: true, reasoningFormat: 'think-tags' }
  * ```
  */
 export function getModelCapabilities(modelId: string): ModelCapabilities {
   const id = modelId.toLowerCase()
 
   // OpenAI reasoning models (o1, o3, gpt-5 series)
@@ -132,13 +133,14 @@
     }
   }
 
-  // DeepSeek models use think tags
+  // DeepSeek models — reasoning models stream `reasoning_content` natively
+  // (OpenAI-compatible field), not <think> tags.
   if (id.includes('deepseek')) {
-    // DeepSeek-R1 and reasoning models
     if (id.includes('r1') || id.includes('reasoner')) {
       return {
         reasoning: true,
-        reasoningFormat: 'think-tags',
+        reasoningField: 'reasoning_content',
+        reasoningFormat: 'native-field',
       }
     }
 

src/agent/infra/llm/providers/deepseek.ts

@@ -0,0 +1,40 @@
+/**
+ * DeepSeek Provider Module
+ *
+ * Access to DeepSeek V3 (deepseek-chat) and R1 (deepseek-reasoner) via their
+ * OpenAI-compatible API. The reasoner model streams thinking through the
+ * native `reasoning_content` field rather than `<think>` tags — see
+ * model-capabilities.ts for the parser routing.
+ */
+
+import {createOpenAICompatible} from '@ai-sdk/openai-compatible'
+
+import type {GeneratorFactoryConfig, ProviderModule} from './types.js'
+
+import {AiSdkContentGenerator} from '../generators/ai-sdk-content-generator.js'
+
+export const deepseekProvider: ProviderModule = {
+  apiKeyUrl: 'https://platform.deepseek.com/api_keys',
+  authType: 'api-key',
+  baseUrl: 'https://api.deepseek.com/v1',
+  category: 'other',
+  createGenerator(config: GeneratorFactoryConfig) {
+    const provider = createOpenAICompatible({
+      apiKey: config.apiKey!,
+      baseURL: 'https://api.deepseek.com/v1',
+      name: 'deepseek',
+    })
+
+    return new AiSdkContentGenerator({
+      model: provider.chatModel(config.model),
+    })
+  },
+  defaultModel: 'deepseek-chat',
+  description: 'DeepSeek V3 and R1 reasoning models',
+  envVars: ['DEEPSEEK_API_KEY'],
+  id: 'deepseek',
+  name: 'DeepSeek',
+  priority: 19,
+
+  providerType: 'openai',
+}

src/agent/infra/llm/providers/glm-coding-plan.ts

@@ -0,0 +1,39 @@
+/**
+ * GLM Coding Plan (Z.AI) Provider Module
+ *
+ * Same Z.AI account as the standard `glm` provider but routes through the
+ * coding-plan endpoint so subscription quota is consumed instead of
+ * pay-per-token billing.
+ */
+
+import {createOpenAICompatible} from '@ai-sdk/openai-compatible'
+
+import type {GeneratorFactoryConfig, ProviderModule} from './types.js'
+
+import {AiSdkContentGenerator} from '../generators/ai-sdk-content-generator.js'
+
+export const glmCodingPlanProvider: ProviderModule = {
+  apiKeyUrl: 'https://docs.z.ai/devpack/overview',
+  authType: 'api-key',
+  baseUrl: 'https://api.z.ai/api/coding/paas/v4',
+  category: 'other',
+  createGenerator(config: GeneratorFactoryConfig) {
+    const provider = createOpenAICompatible({
+      apiKey: config.apiKey!,
+      baseURL: 'https://api.z.ai/api/coding/paas/v4',
+      name: 'glm-coding-plan',
+    })
+
+    return new AiSdkContentGenerator({
+      model: provider.chatModel(config.model),
+    })
+  },
+  defaultModel: 'glm-4.7',
+  description: 'GLM models on the Z.AI Coding Plan subscription',
+  envVars: ['ZHIPU_API_KEY'],
+  id: 'glm-coding-plan',
+  name: 'GLM Coding Plan (Z.AI)',
+  priority: 17.5,
+
+  providerType: 'openai',
+}

src/agent/infra/llm/providers/index.ts

@@ -14,6 +14,8 @@ import {byteroverProvider} from './byterover.js'
 import {cerebrasProvider} from './cerebras.js'
 import {cohereProvider} from './cohere.js'
 import {deepinfraProvider} from './deepinfra.js'
+import {deepseekProvider} from './deepseek.js'
+import {glmCodingPlanProvider} from './glm-coding-plan.js'
 import {glmProvider} from './glm.js'
 import {googleProvider} from './google.js'
 import {groqProvider} from './groq.js'
@@ -38,7 +40,9 @@ const PROVIDER_MODULES: Readonly<Record<string, ProviderModule>> = {
   cerebras: cerebrasProvider,
   cohere: cohereProvider,
   deepinfra: deepinfraProvider,
+  deepseek: deepseekProvider,
   glm: glmProvider,
+  'glm-coding-plan': glmCodingPlanProvider,
   google: googleProvider,
   groq: groqProvider,
   minimax: minimaxProvider,

src/server/core/domain/entities/provider-registry.ts

@@ -144,6 +144,19 @@ export const PROVIDER_REGISTRY: Readonly<Record<string, ProviderDefinition>> = {
     name: 'DeepInfra',
     priority: 10,
   },
+  deepseek: {
+    apiKeyUrl: 'https://platform.deepseek.com/api_keys',
+    baseUrl: 'https://api.deepseek.com/v1',
+    category: 'other',
+    defaultModel: 'deepseek-chat',
+    description: 'DeepSeek V3 and R1 reasoning models',
+    envVars: ['DEEPSEEK_API_KEY'],
+    headers: {},
+    id: 'deepseek',
+    modelsEndpoint: '/models',
+    name: 'DeepSeek',
+    priority: 19,
+  },
   glm: {
     apiKeyUrl: 'https://open.z.ai',
     baseUrl: 'https://api.z.ai/api/paas/v4',
@@ -157,6 +170,19 @@ export const PROVIDER_REGISTRY: Readonly<Record<string, ProviderDefinition>> = {
     name: 'GLM (Z.AI)',
     priority: 17,
   },
+  'glm-coding-plan': {
+    apiKeyUrl: 'https://docs.z.ai/devpack/overview',
+    baseUrl: 'https://api.z.ai/api/coding/paas/v4',
+    category: 'other',
+    defaultModel: 'glm-4.7',
+    description: 'GLM models on the Z.AI Coding Plan subscription',
+    envVars: ['ZHIPU_API_KEY'],
+    headers: {},
+    id: 'glm-coding-plan',
+    modelsEndpoint: '',
+    name: 'GLM Coding Plan (Z.AI)',
+    priority: 17.5,
+  },
   google: {
     apiKeyUrl: 'https://aistudio.google.com/apikey',
     baseUrl: '',

src/server/infra/http/provider-model-fetcher-registry.ts

@@ -63,6 +63,7 @@ export async function getModelFetcher(providerId: string): Promise<IProviderMode
     case 'cerebras': // falls through
     case 'cohere': // falls through
     case 'deepinfra': // falls through
+    case 'deepseek': // falls through
     case 'groq': // falls through
     case 'mistral': // falls through
     case 'togetherai': // falls through
@@ -85,6 +86,16 @@ export async function getModelFetcher(providerId: string): Promise<IProviderMode
       break
     }
 
+    case 'glm-coding-plan': {
+      fetcher = new ChatBasedModelFetcher(
+        'https://api.z.ai/api/coding/paas/v4',
+        'GLM Coding Plan (Z.AI)',
+        ['glm-4.7', 'glm-4.7-flash', 'glm-4.7-flashx', 'glm-5-turbo', 'glm-4.5', 'glm-4.5-flash'],
+      )
+
+      break
+    }
+
     case 'google': {
       fetcher = new GoogleModelFetcher()
 

src/webui/features/provider/components/provider-flow/provider-icons.ts

@@ -3,6 +3,7 @@ import byterover from '../../../../assets/providers/byterover-provider.svg'
 import cerebras from '../../../../assets/providers/cerebras-provider.svg'
 import cohere from '../../../../assets/providers/cohere-provider.svg'
 import deepinfra from '../../../../assets/providers/deepinfra-provider.svg'
+import deepseek from '../../../../assets/providers/deepseek-provider.svg'
 import gemini from '../../../../assets/providers/gemini-provider.svg'
 import groq from '../../../../assets/providers/groq-provider.svg'
 import kimi from '../../../../assets/providers/kimi-provider.svg'
@@ -23,7 +24,9 @@ export const providerIcons: Record<string, string> = {
   cerebras,
   cohere,
   deepinfra,
+  deepseek,
   glm: zai,
+  'glm-coding-plan': zai,
   google: gemini,
   groq,
   minimax,

test/unit/agent/llm/model-capabilities.test.ts

@@ -0,0 +1,25 @@
+import {expect} from 'chai'
+
+import {getModelCapabilities} from '../../../../src/agent/infra/llm/model-capabilities.js'
+
+describe('getModelCapabilities — DeepSeek', () => {
+  it('reports native reasoning_content for deepseek-reasoner', () => {
+    const caps = getModelCapabilities('deepseek-reasoner')
+    expect(caps.reasoning).to.equal(true)
+    expect(caps.reasoningField).to.equal('reasoning_content')
+    expect(caps.reasoningFormat).to.equal('native-field')
+  })
+
+  it('reports native reasoning_content for deepseek-r1', () => {
+    const caps = getModelCapabilities('deepseek-r1')
+    expect(caps.reasoning).to.equal(true)
+    expect(caps.reasoningField).to.equal('reasoning_content')
+    expect(caps.reasoningFormat).to.equal('native-field')
+  })
+
+  it('reports no reasoning for deepseek-chat', () => {
+    const caps = getModelCapabilities('deepseek-chat')
+    expect(caps.reasoning).to.equal(false)
+    expect(caps.reasoningFormat).to.equal('none')
+  })
+})

test/unit/agent/llm/providers/deepseek.test.ts

@@ -0,0 +1,31 @@
+import {expect} from 'chai'
+
+import {getProviderModule} from '../../../../../src/agent/infra/llm/providers/index.js'
+
+describe('deepseek provider module', () => {
+  const mod = getProviderModule('deepseek')
+
+  it('is registered', () => {
+    expect(mod).to.not.be.undefined
+  })
+
+  it('uses api-key auth', () => {
+    expect(mod?.authType).to.equal('api-key')
+  })
+
+  it('uses the openai provider type for formatter/tokenizer selection', () => {
+    expect(mod?.providerType).to.equal('openai')
+  })
+
+  it('defaults to deepseek-chat', () => {
+    expect(mod?.defaultModel).to.equal('deepseek-chat')
+  })
+
+  it('points at the official DeepSeek API base URL', () => {
+    expect(mod?.baseUrl).to.equal('https://api.deepseek.com/v1')
+  })
+
+  it('exposes DEEPSEEK_API_KEY for env detection', () => {
+    expect(mod?.envVars).to.include('DEEPSEEK_API_KEY')
+  })
+})

test/unit/agent/llm/providers/glm-coding-plan.test.ts

@@ -0,0 +1,37 @@
+import {expect} from 'chai'
+
+import {getProviderModule} from '../../../../../src/agent/infra/llm/providers/index.js'
+
+describe('glm-coding-plan provider module', () => {
+  const mod = getProviderModule('glm-coding-plan')
+
+  it('is registered', () => {
+    expect(mod).to.not.be.undefined
+  })
+
+  it('uses api-key auth', () => {
+    expect(mod?.authType).to.equal('api-key')
+  })
+
+  it('uses the openai provider type for formatter/tokenizer selection', () => {
+    expect(mod?.providerType).to.equal('openai')
+  })
+
+  it('defaults to glm-4.7', () => {
+    expect(mod?.defaultModel).to.equal('glm-4.7')
+  })
+
+  it('points at the Z.AI Coding Plan endpoint', () => {
+    expect(mod?.baseUrl).to.equal('https://api.z.ai/api/coding/paas/v4')
+  })
+
+  it('exposes ZHIPU_API_KEY for env detection', () => {
+    expect(mod?.envVars).to.include('ZHIPU_API_KEY')
+  })
+
+  it('coexists with the standard glm provider', () => {
+    const standard = getProviderModule('glm')
+    expect(standard).to.not.be.undefined
+    expect(standard?.baseUrl).to.not.equal(mod?.baseUrl)
+  })
+})