[PR #430] docs: add Dassi integration guide (EN + zh-CN)

## 📋 Pull Request Information **Original PR:** https://github.com/deepseek-ai/awesome-deepseek-agent/pull/430 **Author:** [@weihao-m](https://github.com/weihao-m) **Created:** 9/26/2026 **Status:** 🔄 Open **Base:** `main` ← **Head:** `docs/add-dassi-guide` --- ### 📝 Commits (1) - [`f8c8402`](https://github.com/deepseek-ai/awesome-deepseek-agent/commit/f8c84025484d9c1f397d991bba8c06367f410100) docs: add Dassi DeepSeek integration guide ### 📊 Changes **4 files changed** (+124 additions, -0 deletions) <details> <summary>View changed files</summary> 📝 `README.md` (+1 -0) 📝 `README.zh-CN.md` (+1 -0) ➕ `docs/dassi.md` (+61 -0) ➕ `docs/dassi.zh-CN.md` (+61 -0) </details> ### 📄 Description Adds [Dassi](https://dassi.ai/), an AI agent for Chrome, with English and Simplified Chinese guides covering installation, the built-in DeepSeek API key connection, model selection, and first tasks. Both README tables include Dassi in alphabetical order. The browser walkthrough uses vision-capable Flash. The guide explains that current `deepseek-flash` supports vision and that DeepSeek still accepts the older Flash aliases shown by some Dassi catalogs. It also covers V4 Pro for text tasks and the 1M context window. **Known limitation:** Dassi currently uses `high` reasoning and does not expose a user-facing `max` control. Both guides state this explicitly; the max-effort checklist item is intentionally left unchecked. Validation: checked configuration steps against Dassi's provider/model UI and bundled model catalog; checked current model aliases and vision support against the [official model details](https://api-docs.deepseek.com/quick_start/pricing/) and [vision guide](https://api-docs.deepseek.com/guides/vision/). Local links, alphabetical ordering, bilingual structure, code fences, and `git diff --check` pass. A live API/browser run was not performed for this documentation change. ## Checklist ### Agent Configuration - [x] Model names are current; accepted legacy Flash aliases are explained using current API documentation - [x] 1M context is configured or mentioned - [ ] Max thinking effort level is supported — Dassi currently exposes no `max` control; limitation documented - [x] Pricing is current — no numeric pricing copied; links point to current official pages - [x] Config fields checked against the agent's implementation; live API verification not performed - [x] No workarounds for already-fixed upstream bugs ### 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; unrelated tools not combined - [x] Images placed in `docs/assets/` with descriptive filenames and reasonable sizes — no images added --- <sub>🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.</sub>

bsakaguchi commented

2026-10-26 09:49:10 +00:00

Owner

📋 Pull Request Information

Original PR: https://github.com/deepseek-ai/awesome-deepseek-agent/pull/430
Author: @weihao-m
Created: 9/26/2026
Status: 🔄 Open

Base: main ← Head: docs/add-dassi-guide

📝 Commits (1)

f8c8402 docs: add Dassi DeepSeek integration guide

📊 Changes

4 files changed (+124 additions, -0 deletions)

View changed files

📝 README.md (+1 -0)
📝 README.zh-CN.md (+1 -0)
➕ docs/dassi.md (+61 -0)
➕ docs/dassi.zh-CN.md (+61 -0)

📄 Description

Adds Dassi, an AI agent for Chrome, with English and Simplified Chinese guides covering installation, the built-in DeepSeek API key connection, model selection, and first tasks. Both README tables include Dassi in alphabetical order.

The browser walkthrough uses vision-capable Flash. The guide explains that current deepseek-flash supports vision and that DeepSeek still accepts the older Flash aliases shown by some Dassi catalogs. It also covers V4 Pro for text tasks and the 1M context window.

Known limitation: Dassi currently uses high reasoning and does not expose a user-facing max control. Both guides state this explicitly; the max-effort checklist item is intentionally left unchecked.

Validation: checked configuration steps against Dassi's provider/model UI and bundled model catalog; checked current model aliases and vision support against the official model details and vision guide. Local links, alphabetical ordering, bilingual structure, code fences, and git diff --check pass. A live API/browser run was not performed for this documentation change.

Checklist

Agent Configuration

Model names are current; accepted legacy Flash aliases are explained using current API documentation
1M context is configured or mentioned
Max thinking effort level is supported — Dassi currently exposes no max control; limitation documented
Pricing is current — no numeric pricing copied; links point to current official pages
Config fields checked against the agent's implementation; live API verification not performed
No workarounds for already-fixed upstream bugs

Documentation

Both English and Chinese versions included in a single PR
README table entry inserted in alphabetical order
One tool per PR; unrelated tools not combined
Images placed in docs/assets/ with descriptive filenames and reasonable sizes — no images added

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

bsakaguchi added the

pull-request

label

Rows
Columns

[PR #430] docs: add Dassi integration guide (EN + zh-CN) #428