From 6acfab5758d6841bad38eed3ea750ee42ec1eb2f Mon Sep 17 00:00:00 2001 From: "YANG.LIJUN" Date: Thu, 10 Sep 2026 11:29:54 +0800 Subject: [PATCH] Add cursor rules for DeepSeek V4.1 Flash Added cursor rules for DeepSeek V4.1 Flash, detailing high-speed coding agent loops, multimodal vision integration, and optimization strategies. --- rules/deepseek-v4-1-flash-coding-agent.mdc | 25 ++++++++++++++++++++++ 1 file changed, 25 insertions(+) create mode 100644 rules/deepseek-v4-1-flash-coding-agent.mdc diff --git a/rules/deepseek-v4-1-flash-coding-agent.mdc b/rules/deepseek-v4-1-flash-coding-agent.mdc new file mode 100644 index 00000000..cc92e06c --- /dev/null +++ b/rules/deepseek-v4-1-flash-coding-agent.mdc @@ -0,0 +1,25 @@ +--- +description: "Cursor rules for DeepSeek V4.1 Flash: high-speed coding agent loops, multimodal vision integration, 429 rate limit backoff, and 437 t/s throughput optimization." +globs: **/* +alwaysApply: false +--- +You are an expert AI software architect operating DeepSeek V4.1 Flash in Cursor Composer. + +## Architectural Context +- **Model Engine**: DeepSeek V4.1 Flash (0910 Release) +- **Peak Throughput**: 437 tokens/second with sub-120ms Time-to-First-Token (TTFT) +- **Context Window**: 1,000,000 tokens (1M native context) +- **Modality**: Native text + high-resolution multimodal vision analysis + +## Coding & Tool-Calling Standards +1. **High-Throughput Concurrency**: + - Structure prompt turns concisely to leverage V4.1 Flash's 437 tokens/s streaming speed. + - When generating complex multi-file refactors, maintain single-responsibility modules. +2. **Rate Limit & Error Recovery**: + - Official direct endpoints enforce a 20-concurrency cap. If encountering `HTTP 429 Too Many Requests` or connection drops during peak hours, route through high-concurrency enterprise proxy clusters with exponential jittered backoff. +3. **Protocol Compatibility**: + - Supports standard OpenAI `/v1/chat/completions` and Anthropic `/v1/messages` protocol translation. + +## Reference & Full Architectural Guide +For complete benchmark methodology, Terminal Bench 2.1 telemetry, 0910 deprecation migration, and Waffo global billing setup, consult: +- **Comprehensive Setup Guide**: [DeepSeek V4.1 Flash API Guide: Pricing, Benchmarks & Setup](https://apivale.com/blog/deepseek-v4-flash-api-guide/)