[PR #405] docs: add Grok Build integration guide

## 📋 Pull Request Information **Original PR:** https://github.com/deepseek-ai/awesome-deepseek-agent/pull/405 **Author:** [@ChrisAngelo](https://github.com/ChrisAngelo) **Created:** 8/24/2026 **Status:** 🔄 Open **Base:** `main` ← **Head:** `docs/add-grok-build` --- ### 📝 Commits (1) - [`65722c9`](https://github.com/deepseek-ai/awesome-deepseek-agent/commit/65722c9b3bfaf6fe8aa8c2a9ba2f8c6a1de362c6) docs: add Grok Build integration guide ### 📊 Changes **4 files changed** (+256 additions, -0 deletions) <details> <summary>View changed files</summary> 📝 `README.md` (+1 -0) 📝 `README.zh-CN.md` (+1 -0) ➕ `docs/grok_build.md` (+127 -0) ➕ `docs/grok_build.zh-CN.md` (+127 -0) </details> ### 📄 Description ## Summary Adds a bilingual integration guide for **Grok Build** (`grok`), xAI's terminal AI coding agent, so DeepSeek V4 users can find and configure it. ### Why this PR exists next to #314 [#314](https://github.com/deepseek-ai/awesome-deepseek-agent/pull/314) is still open, but it documents config keys that are **not** in Grok's custom-model contract (`provider_alias`, `provider_name`, `supports_reasoning_effort`) and it defaults to OpenAI Chat Completions. CONTRIBUTING.md says only verified fields should ship. This PR rewrites the guide against Grok 1.0.x's actual `config.toml` fields. If you prefer to keep a single Grok Build PR, this one can replace #314. ### What's included - `docs/grok_build.md` and `docs/grok_build.zh-CN.md` - README table entries in both languages, alphabetical order (after GitHub Copilot CLI, before Hermes) ### Agent configuration - Model names: `deepseek-v4-pro` / `deepseek-v4-flash` (current, not v3) - 1M context: Anthropic model ids use the `[1m]` suffix; both backends set `context_window = 1000000` - Max thinking: `[models].default_reasoning_effort = max` plus `/effort max` and `--effort max` - Preferred backend: DeepSeek Anthropic Messages (`api_backend = messages`) so tool-calling turns do not hit the `reasoning_content` 400 that Chat Completions clients often see - Optional OpenAI Chat Completions snippet, with a pointer back to Anthropic if that 400 appears - API key via `DEEPSEEK_API_KEY` (`env_http_headers` / `env_key`), never hardcoded ### Checklist #### Agent Configuration - [x] Model names are current (v4-pro / v4-flash, not v3 names) - [x] 1M context is configured or mentioned - [x] Max thinking effort level is supported - [x] Pricing is current — N/A: this guide does not include a pricing table - [x] Config fields are verified against Grok's published custom-models docs (`model`, `base_url`, `name`, `api_backend`, `context_window`, `env_key`, `env_http_headers`, `extra_headers`, `[models].default` / `default_reasoning_effort`) - [x] No workarounds that disable thinking mode #### Documentation - [x] Both English and Chinese versions included in a single PR - [x] README table entry inserted in alphabetical order - [x] One tool per PR - [x] No screenshots required --- <sub>🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.</sub>

bsakaguchi commented

2026-10-26 09:48:53 +00:00

Owner

📋 Pull Request Information

Original PR: https://github.com/deepseek-ai/awesome-deepseek-agent/pull/405
Author: @ChrisAngelo
Created: 8/24/2026
Status: 🔄 Open

Base: main ← Head: docs/add-grok-build

📝 Commits (1)

65722c9 docs: add Grok Build integration guide

📊 Changes

4 files changed (+256 additions, -0 deletions)

View changed files

📝 README.md (+1 -0)
📝 README.zh-CN.md (+1 -0)
➕ docs/grok_build.md (+127 -0)
➕ docs/grok_build.zh-CN.md (+127 -0)

📄 Description

Summary

Adds a bilingual integration guide for Grok Build (grok), xAI's terminal AI coding agent, so DeepSeek V4 users can find and configure it.

Why this PR exists next to #314

#314 is still open, but it documents config keys that are not in Grok's custom-model contract (provider_alias, provider_name, supports_reasoning_effort) and it defaults to OpenAI Chat Completions. CONTRIBUTING.md says only verified fields should ship. This PR rewrites the guide against Grok 1.0.x's actual config.toml fields.

If you prefer to keep a single Grok Build PR, this one can replace #314.

What's included

docs/grok_build.md and docs/grok_build.zh-CN.md
README table entries in both languages, alphabetical order (after GitHub Copilot CLI, before Hermes)

Agent configuration

Model names: deepseek-v4-pro / deepseek-v4-flash (current, not v3)
1M context: Anthropic model ids use the [1m] suffix; both backends set context_window = 1000000
Max thinking: [models].default_reasoning_effort = max plus /effort max and --effort max
Preferred backend: DeepSeek Anthropic Messages (api_backend = messages) so tool-calling turns do not hit the reasoning_content 400 that Chat Completions clients often see
Optional OpenAI Chat Completions snippet, with a pointer back to Anthropic if that 400 appears
API key via DEEPSEEK_API_KEY (env_http_headers / env_key), never hardcoded

Checklist

Agent Configuration

Model names are current (v4-pro / v4-flash, not v3 names)
1M context is configured or mentioned
Max thinking effort level is supported
Pricing is current — N/A: this guide does not include a pricing table
Config fields are verified against Grok's published custom-models docs (model, base_url, name, api_backend, context_window, env_key, env_http_headers, extra_headers, [models].default / default_reasoning_effort)
No workarounds that disable thinking mode

Documentation

Both English and Chinese versions included in a single PR
README table entry inserted in alphabetical order
One tool per PR
No screenshots required

_{🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.}

bsakaguchi added the

pull-request

label

bsakaguchi referenced this issue

2026-10-26 09:48:55 +00:00

[PR #406] [CLOSED] docs: add dsh-session-recall integration guide #407

Rows
Columns

[PR #405] docs: add Grok Build integration guide #406