dgf1988/codewhale

Files

T

Hunter Bown 06612495fc chore(release): prep v0.8.51 — Arcee provider, cycle removal, UI fixes

Release-preparation checkpoint for v0.8.51 (workspace + npm bumped to 0.8.51).

Added:
- Arcee AI direct provider: [providers.arcee], ARCEE_API_KEY/BASE_URL/MODEL,
  CLI auth, provider + model picker, registry. Default direct-API model is
  trinity-large-thinking (reasoning, 262K ctx/out); preview + mini selectable.
  Cloudflare-WAF-safe opening turn (benign read-only tool surface, system-prompt
  payload splitting) and reasoning_content replay on tool-call turns.
- Expanded model catalog (qwen3.6 flash/plus/max-preview, Xiaomi MiMo v2.5
  chat/ASR/TTS); provider-aware model picker with per-provider saved models.

Changed:
- Auto-compaction is percentage- and model-aware
  (compaction_threshold_for_model_at_percent; default 80%; auto-enable for
  <=256K windows, opt-in for 1M models).
- Provider/gateway HTTP errors sanitized (HTML/WAF interstitials collapsed,
  401/403 split into authentication vs authorization).

Removed:
- The session cycle / checkpoint-restart system: /cycles, /cycle, /recall,
  recall_archive tool, cycle_manager, cycle-handoff prompt, sidebar cycle lines,
  EngineConfig.cycle / Event::CycleAdvanced / seam cycle thresholds.

Fixed:
- Orphaned assistant 'blue dot' role glyph on whitespace-only turns.
- Sidebar mouse-wheel scroll leaking into the transcript.
- Sidebar hover tooltip overlap + warning-orange styling.
- README Constitution description corrected to match prompts/base.md.
- Repaired release-blocking unit/integration tests after the refactors.

Preflight: cargo fmt clean, workspace builds, 3903 tui tests pass (1 known
flaky MCP SSE test under parallel load, passes in isolation).

2026-06-02 17:36:18 -07:00

bin

feat(v0.8.44): npm codew alias binary wrapper

2026-05-24 15:09:49 -05:00

scripts

fix(npm): prefer binary version output

2026-06-01 19:17:58 -07:00

test

fix(npm): prefer binary version output

2026-06-01 19:17:58 -07:00

.gitignore

feat(npm): publish as codewhale; keep deepseek-tui as deprecation shim

2026-05-23 11:11:53 -05:00

package.json

chore(release): prep v0.8.51 — Arcee provider, cycle removal, UI fixes

2026-06-02 17:36:18 -07:00

README.md

chore(release): harden deepseek-tui deprecation path

2026-06-01 06:01:03 -07:00

README.md

codewhale

Install and run CodeWhale, the agentic terminal for open-source and open-weight coding models, from GitHub release artifacts.

Previously published as deepseek-tui. See docs/REBRAND.md in the upstream repository for the migration notes; the legacy deepseek-tui npm package is deprecated and receives no further releases.

Install

npm install -g codewhale
# or
pnpm add -g codewhale

For project-local usage:

npm install codewhale
npx codewhale --help

postinstall tries to download platform binaries into bin/downloads/ and exposes codewhale and codewhale-tui commands. If GitHub release assets are temporarily unreachable, install continues and the wrapper retries the download on first run.

First run

codewhale login --api-key "YOUR_DEEPSEEK_API_KEY"
codewhale doctor
codewhale

The codewhale facade and codewhale-tui binary share ~/.codewhale/config.toml for DeepSeek auth and default model settings. Legacy ~/.deepseek/config.toml installs are still read as a compatibility fallback. Common TUI commands are available directly through the facade, including codewhale doctor, codewhale models, codewhale sessions, and codewhale 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:

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

Prebuilt binaries for the GitHub release are downloaded automatically:

Linux x64
Linux arm64 (v0.8.8+)
macOS x64 / arm64
Windows x64

Other platform/architecture combinations (musl, riscv64, FreeBSD, …) aren't shipped as prebuilts. Unsupported platforms, checksum failures, and glibc compatibility problems still fail with a clear error pointing you at cargo install codewhale-cli codewhale-tui --locked and the full docs/INSTALL.md build-from-source guide.

Configuration

Default binary version comes from codewhaleBinaryVersion in package.json (with deepseekBinaryVersion as a backward-compat fallback).
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/CodeWhale).
Set DEEPSEEK_TUI_RELEASE_BASE_URL to use an internal or mirrored release-asset directory when GitHub Releases is unavailable. The directory must contain codewhale-artifacts-sha256.txt and the platform binaries.
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.
Set DEEPSEEK_TUI_OPTIONAL_INSTALL=1 to make install-time retryable download failures warn and exit 0 instead of failing npm install.

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.