dgf1988/codewhale

Files

T

Hunter Bown e1ac84ae44 release: v0.6.1 — pricing update, remove light theme + theme setting

- V4 cache-hit input prices cut to 1/10th per DeepSeek pricing update:
  Pro promo 0.03625→0.003625, Pro base 0.145→0.0145, Flash 0.028→0.0028
- Remove the 'light' theme variant (Variant::Light, Theme::light(), test)
- Remove the theme setting entirely — hardcode UI_THEME to whale/dark,
  drop the theme field from Settings, ConfigView, and config command
- Bump workspace version 0.6.0 → 0.6.1 (Cargo.toml, npm pkg, CHANGELOG)
- De-cringe the README: drop emojis, marketing fluff, unverified claims

2026-04-26 11:56:41 -05:00

bin

feat: add npm package and update install docs

2026-03-03 09:57:56 -06:00

scripts

feat: DeepSeek V4 support with reasoning-effort control (0.4.0)

2026-04-23 22:53:20 -05:00

.gitignore

feat: add npm package and update install docs

2026-03-03 09:57:56 -06:00

package.json

release: v0.6.1 — pricing update, remove light theme + theme setting

2026-04-26 11:56:41 -05:00

README.md

Fix reasoning replay and context accounting for NIM

2026-04-24 18:42:18 -05:00

README.md

deepseek-tui

Install and run the deepseek and deepseek-tui binaries from GitHub release artifacts.

Install

npm install -g deepseek-tui
# or
pnpm add -g deepseek-tui

For project-local usage:

npm install deepseek-tui
npx deepseek-tui --help

postinstall downloads platform binaries into bin/downloads/ and exposes deepseek and deepseek-tui commands.

First run

deepseek login --api-key "YOUR_DEEPSEEK_API_KEY"
deepseek doctor
deepseek

The deepseek facade and deepseek-tui binary share ~/.deepseek/config.toml for DeepSeek auth and default model settings. Common TUI commands are available directly through the facade, including deepseek doctor, deepseek models, deepseek sessions, and deepseek resume --last.

The app talks to DeepSeek's documented OpenAI-compatible Chat Completions API. Set DEEPSEEK_BASE_URL only if you need the China endpoint or DeepSeek beta features such as strict tool mode, chat prefix completion, or FIM completion.

NVIDIA NIM-hosted DeepSeek V4 Pro is also supported:

deepseek auth set --provider nvidia-nim --api-key "YOUR_NVIDIA_API_KEY"
deepseek --provider nvidia-nim

For a single process, set DEEPSEEK_PROVIDER=nvidia-nim and NVIDIA_API_KEY or NVIDIA_NIM_API_KEY (with DEEPSEEK_API_KEY as a compatibility fallback). The NIM default model is deepseek-ai/deepseek-v4-pro and the default base URL is https://integrate.api.nvidia.com/v1. With --provider nvidia-nim, --model deepseek-v4-flash maps to deepseek-ai/deepseek-v4-flash.

Supported platforms

Linux x64
macOS x64 / arm64
Windows x64

Other platform/architecture combinations are not supported and will fail during install.

Configuration

Default binary version comes from deepseekBinaryVersion in package.json.
Set DEEPSEEK_TUI_VERSION or DEEPSEEK_VERSION to override the release version.
Set DEEPSEEK_TUI_GITHUB_REPO or DEEPSEEK_GITHUB_REPO to override the source repo (defaults to Hmbown/DeepSeek-TUI).
Set DEEPSEEK_TUI_FORCE_DOWNLOAD=1 to force download even when the cached binary is already present.
Set DEEPSEEK_TUI_DISABLE_INSTALL=1 to skip install-time download.

Release integrity

npm publish runs a release-asset check to ensure all required binary assets exist for the target GitHub release before publishing.
Install-time downloads are verified against the release checksum manifest before the wrapper marks them executable.
Set DEEPSEEK_TUI_RELEASE_BASE_URL to point the installer at a local or staged release-asset directory for smoke tests.