[PR #370] docs: use the supported Claude Code Flash model ID #376

New issue

Open

opened 2026-10-26 09:48:35 +00:00 by bsakaguchi · 0 comments

bsakaguchi commented

2026-10-26 09:48:35 +00:00

Owner

📋 Pull Request Information

Original PR: https://github.com/deepseek-ai/awesome-deepseek-agent/pull/370
Author: @morluto
Created: 8/12/2026
Status: 🔄 Open

Base: main ← Head: agent/fix-claude-code-flash-model

📝 Commits (1)

e57e034 docs: use the supported Claude Code Flash model ID

📊 Changes

3 files changed (+7 additions, -7 deletions)

View changed files

📝 CONTRIBUTING.md (+1 -1)
📝 docs/claude_code.md (+3 -3)
📝 docs/claude_code.zh-CN.md (+3 -3)

📄 Description

Summary

Remove the unsupported [1m] suffix from deepseek-v4-flash in the Claude Code English and Simplified Chinese guides.
Narrow the contributor guidance so [1m] is documented for Pro while Flash uses its plain API model ID.
Keep the existing deepseek-v4-pro[1m] configuration unchanged.

The current DeepSeek Claude Code integration guide uses deepseek-v4-flash without [1m]. The affected repository guidance showed deepseek-v4-flash[1m] in all three Claude Code configuration examples, which could lead users to an invalid or unsupported model name. Related user report: #96.

Validation

git diff --check
Confirmed no deepseek-v4-flash[1m] remains in the affected documentation.
npx --yes markdownlint-cli --disable MD001 MD013 MD041 MD060 -- CONTRIBUTING.md docs/claude_code.md docs/claude_code.zh-CN.md — existing lint findings remain for unlabeled fences, list spacing, inline HTML, and missing image alt text; none were introduced by this change.

Reference: https://api-docs.deepseek.com/quick_start/agent_integrations/claude_code

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

## 📋 Pull Request Information **Original PR:** https://github.com/deepseek-ai/awesome-deepseek-agent/pull/370 **Author:** [@morluto](https://github.com/morluto) **Created:** 8/12/2026 **Status:** 🔄 Open **Base:** `main` ← **Head:** `agent/fix-claude-code-flash-model` --- ### 📝 Commits (1) - [`e57e034`](https://github.com/deepseek-ai/awesome-deepseek-agent/commit/e57e034ebdbd184239ead6539351d6f72b904ef8) docs: use the supported Claude Code Flash model ID ### 📊 Changes **3 files changed** (+7 additions, -7 deletions) <details> <summary>View changed files</summary> 📝 `CONTRIBUTING.md` (+1 -1) 📝 `docs/claude_code.md` (+3 -3) 📝 `docs/claude_code.zh-CN.md` (+3 -3) </details> ### 📄 Description ## Summary - Remove the unsupported `[1m]` suffix from `deepseek-v4-flash` in the Claude Code English and Simplified Chinese guides. - Narrow the contributor guidance so `[1m]` is documented for Pro while Flash uses its plain API model ID. - Keep the existing `deepseek-v4-pro[1m]` configuration unchanged. The current DeepSeek Claude Code integration guide uses `deepseek-v4-flash` without `[1m]`. The affected repository guidance showed `deepseek-v4-flash[1m]` in all three Claude Code configuration examples, which could lead users to an invalid or unsupported model name. Related user report: #96. ## Validation - `git diff --check` - Confirmed no `deepseek-v4-flash[1m]` remains in the affected documentation. - `npx --yes markdownlint-cli --disable MD001 MD013 MD041 MD060 -- CONTRIBUTING.md docs/claude_code.md docs/claude_code.zh-CN.md` — existing lint findings remain for unlabeled fences, list spacing, inline HTML, and missing image alt text; none were introduced by this change. Reference: https://api-docs.deepseek.com/quick_start/agent_integrations/claude_code --- <sub>🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.</sub>

bsakaguchi added the

pull-request

label

2026-10-26 09:48:35 +00:00

bsakaguchi referenced this issue

2026-10-26 09:48:38 +00:00

[PR #376] docs: add Kimi Code integration guide #381