dgf1988/codewhale
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

fix: DeepSeek-first v0.8.45 — CODEWHALE_* env aliases, remove public Kimi/Moonshot promotion

Browse Source 
Closes #2164 (superseded).
This commit is contained in:
Hunter Bown
2026-05-26 06:03:10 -05:00
committed by GitHub
parent 6011888cfd
commit c47ed896dc
6 changed files with 494 additions and 69 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/CONFIGURATION.md
+19 -13
View File
@@ -63,15 +63,14 @@ provider's keyring entry.
For hosted, generic OpenAI-compatible, or self-hosted providers, set
`provider = "nvidia-nim"`, `"openai"`, `"atlascloud"`, `"wanjie-ark"`, `"fireworks"`,
`"moonshot"`, `"sglang"`, `"vllm"`, or `"ollama"` or pass `codewhale --provider <name>`.
`"sglang"`, `"vllm"`, or `"ollama"` or pass `codewhale --provider <name>`.
The facade saves provider credentials to the shared user config and forwards
the resolved key, base URL, provider, and model to the TUI process. Use
`codewhale auth set --provider nvidia-nim --api-key "YOUR_NVIDIA_API_KEY"` or
`codewhale auth set --provider openai --api-key "YOUR_OPENAI_COMPATIBLE_API_KEY"` or
`codewhale auth set --provider atlascloud --api-key "YOUR_ATLASCLOUD_API_KEY"` or
`codewhale auth set --provider wanjie-ark --api-key "YOUR_WANJIE_API_KEY"` or
`codewhale auth set --provider fireworks --api-key "YOUR_FIREWORKS_API_KEY"` or
`codewhale auth set --provider moonshot --api-key "YOUR_MOONSHOT_OR_KIMI_API_KEY"`
`codewhale auth set --provider fireworks --api-key "YOUR_FIREWORKS_API_KEY"`
to save provider keys through the facade. The generic `openai` provider defaults
to `https://api.openai.com/v1`, accepts `OPENAI_BASE_URL`, and defaults to
`deepseek-v4-pro` for OpenAI-compatible gateways. `atlascloud` defaults to
@@ -80,9 +79,7 @@ to `https://api.openai.com/v1`, accepts `OPENAI_BASE_URL`, and defaults to
Wanjie Ark's OpenAI-compatible endpoint at
`https://maas-openapi.wanjiedata.com/api/v1`, defaults to `deepseek-reasoner`,
and passes model IDs through unchanged because Wanjie model access is
account-scoped. `moonshot` targets Moonshot/Kimi, defaults to `kimi-k2.6`,
and can use `KIMI_API_KEY` or `auth_mode = "kimi_oauth"` with local Kimi CLI
credentials. SGLang, vLLM, and Ollama are
account-scoped. SGLang, vLLM, and Ollama are
self-hosted and can run without an API key by default. Ollama defaults to
`http://localhost:11434/v1` and sends model tags such as `codewhale-coder:1.3b`
or `qwen2.5-coder:7b` unchanged. Self-hosted providers and loopback custom
@@ -200,13 +197,22 @@ If a profile is selected but missing, codewhale exits with an error listing avai
## Environment Variables
Most runtime environment variables override config values. API-key variables are
fallbacks after saved config and keyring credentials:
fallbacks after saved config and keyring credentials.
The three user-facing slots — provider, model, base URL — expose `CODEWHALE_*`
aliases. When both forms are set the `CODEWHALE_*` value wins; the
`DEEPSEEK_*` form is kept for older shells:
- `CODEWHALE_PROVIDER` (preferred) / `DEEPSEEK_PROVIDER` (legacy alias) —
`deepseek|nvidia-nim|openai|atlascloud|wanjie-ark|openrouter|novita|fireworks|sglang|vllm|ollama`
- `CODEWHALE_MODEL` (preferred) / `DEEPSEEK_MODEL` (legacy alias) — default model for the active provider
- `CODEWHALE_BASE_URL` (preferred) / `DEEPSEEK_BASE_URL` (legacy alias) — base URL for the active provider
Remaining variables:
- `DEEPSEEK_API_KEY`
- `DEEPSEEK_BASE_URL`
- `DEEPSEEK_HTTP_HEADERS` (custom model request headers, comma-separated `name=value` pairs)
- `DEEPSEEK_PROVIDER` (`codewhale|nvidia-nim|openai|atlascloud|wanjie-ark|openrouter|novita|fireworks|moonshot|sglang|vllm|ollama`)
- `DEEPSEEK_MODEL` or `DEEPSEEK_DEFAULT_TEXT_MODEL`
- `DEEPSEEK_DEFAULT_TEXT_MODEL` (extra legacy alias of `DEEPSEEK_MODEL`)
- `DEEPSEEK_STREAM_IDLE_TIMEOUT_SECS` (stream idle timeout in seconds; default `300`, clamped to `1..=3600`)
- `DEEPSEEK_STREAM_OPEN_TIMEOUT_SECS` (connection setup + response-header wait in seconds; default `45`, clamped to `5..=300`; distinct from the per-chunk idle timeout)
- `NVIDIA_API_KEY` or `NVIDIA_NIM_API_KEY` (preferred when provider is `nvidia-nim`; falls back to `DEEPSEEK_API_KEY`)
@@ -429,10 +435,10 @@ If you are upgrading from older releases:
### Core keys (used by the TUI/engine)
- `provider` (string, optional): `codewhale` (default), `nvidia-nim`, `openai`, `atlascloud`, `wanjie-ark`, `openrouter`, `novita`, `fireworks`, `moonshot`, `sglang`, `vllm`, or `ollama`. Legacy `deepseek-cn` configs are still accepted as an alias for `codewhale`; DeepSeek uses the same official host [`https://api.deepseek.com`](https://api-docs.deepseek.com/) worldwide. `nvidia-nim` targets NVIDIA's NIM-hosted DeepSeek endpoints through `https://integrate.api.nvidia.com/v1`; `openai` targets a generic OpenAI-compatible endpoint, defaulting to `https://api.openai.com/v1`; `atlascloud` targets AtlasCloud's OpenAI-compatible endpoint at `https://api.atlascloud.ai/v1`; `wanjie-ark` targets Wanjie Ark's OpenAI-compatible endpoint at `https://maas-openapi.wanjiedata.com/api/v1`; `fireworks` targets `https://api.fireworks.ai/inference/v1`; `moonshot` targets `https://api.moonshot.ai/v1` by default, with Kimi CLI OAuth mode using `https://api.kimi.com/coding/v1`; `sglang` targets a self-hosted OpenAI-compatible endpoint, defaulting to `http://localhost:30000/v1`; `vllm` targets a self-hosted vLLM OpenAI-compatible endpoint, defaulting to `http://localhost:8000/v1`; `ollama` targets Ollama's OpenAI-compatible endpoint, defaulting to `http://localhost:11434/v1`.
- `provider` (string, optional): `codewhale` (default), `nvidia-nim`, `openai`, `atlascloud`, `wanjie-ark`, `openrouter`, `novita`, `fireworks`, `sglang`, `vllm`, or `ollama`. Legacy `deepseek-cn` configs are still accepted as an alias for `codewhale`; DeepSeek uses the same official host [`https://api.deepseek.com`](https://api-docs.deepseek.com/) worldwide. `nvidia-nim` targets NVIDIA's NIM-hosted DeepSeek endpoints through `https://integrate.api.nvidia.com/v1`; `openai` targets a generic OpenAI-compatible endpoint, defaulting to `https://api.openai.com/v1`; `atlascloud` targets AtlasCloud's OpenAI-compatible endpoint at `https://api.atlascloud.ai/v1`; `wanjie-ark` targets Wanjie Ark's OpenAI-compatible endpoint at `https://maas-openapi.wanjiedata.com/api/v1`; `fireworks` targets `https://api.fireworks.ai/inference/v1`; `sglang` targets a self-hosted OpenAI-compatible endpoint, defaulting to `http://localhost:30000/v1`; `vllm` targets a self-hosted vLLM OpenAI-compatible endpoint, defaulting to `http://localhost:8000/v1`; `ollama` targets Ollama's OpenAI-compatible endpoint, defaulting to `http://localhost:11434/v1`.
- `api_key` (string, required for hosted providers): must be non-empty for DeepSeek/hosted providers (or set the provider API key env var). Self-hosted SGLang, vLLM, and Ollama can omit it.
- `base_url` (string, optional): defaults to `https://api.deepseek.com/beta` for DeepSeek's OpenAI-compatible Chat Completions API, including legacy `provider = "deepseek-cn"` configs, `https://api.openai.com/v1` for `provider = "openai"`, `https://api.atlascloud.ai/v1` for `provider = "atlascloud"`, `https://maas-openapi.wanjiedata.com/api/v1` for `provider = "wanjie-ark"`, `https://api.moonshot.ai/v1` for `provider = "moonshot"` API-key mode, or the provider-specific endpoint for hosted/self-hosted providers. Set `https://api.deepseek.com` or `https://api.deepseek.com/v1` explicitly to opt out of DeepSeek beta features.
- `default_text_model` (string, optional): defaults to `deepseek-v4-pro` for DeepSeek and generic OpenAI-compatible endpoints, `deepseek-ai/deepseek-v4-pro` for NVIDIA NIM, `deepseek-ai/deepseek-v4-flash` for AtlasCloud, `deepseek-reasoner` for Wanjie Ark, `accounts/fireworks/models/deepseek-v4-pro` for Fireworks, `kimi-k2.6` for Moonshot/Kimi API-key mode, `deepseek-ai/DeepSeek-V4-Pro` for SGLang/vLLM, and `codewhale-coder:1.3b` for Ollama. Current public DeepSeek IDs are `deepseek-v4-pro` and `deepseek-v4-flash`, both with 1M context windows, 384K max output, and thinking mode enabled by default. Legacy `deepseek-chat` and `deepseek-reasoner` remain compatibility aliases for `deepseek-v4-flash` until July 24, 2026. Provider-specific mappings translate `deepseek-v4-pro` / `deepseek-v4-flash` to each provider's model ID where supported. Generic `openai`, `atlascloud`, `wanjie-ark`, and Ollama model IDs are passed through unchanged. OpenRouter provider configs with a custom `base_url` also preserve explicit model values, which lets OpenAI-compatible gateways accept bare model IDs. Use `/models` or `codewhale models` to discover live IDs from your configured endpoint. `DEEPSEEK_MODEL` overrides this for a single process.
- `base_url` (string, optional): defaults to `https://api.deepseek.com/beta` for DeepSeek's OpenAI-compatible Chat Completions API, including legacy `provider = "deepseek-cn"` configs, `https://api.openai.com/v1` for `provider = "openai"`, `https://api.atlascloud.ai/v1` for `provider = "atlascloud"`, `https://maas-openapi.wanjiedata.com/api/v1` for `provider = "wanjie-ark"`, or the provider-specific endpoint for hosted/self-hosted providers. Set `https://api.deepseek.com` or `https://api.deepseek.com/v1` explicitly to opt out of DeepSeek beta features.
- `default_text_model` (string, optional): defaults to `deepseek-v4-pro` for DeepSeek and generic OpenAI-compatible endpoints, `deepseek-ai/deepseek-v4-pro` for NVIDIA NIM, `deepseek-ai/deepseek-v4-flash` for AtlasCloud, `deepseek-reasoner` for Wanjie Ark, `accounts/fireworks/models/deepseek-v4-pro` for Fireworks, `deepseek-ai/DeepSeek-V4-Pro` for SGLang/vLLM, and `codewhale-coder:1.3b` for Ollama. Current public DeepSeek IDs are `deepseek-v4-pro` and `deepseek-v4-flash`, both with 1M context windows, 384K max output, and thinking mode enabled by default. Legacy `deepseek-chat` and `deepseek-reasoner` remain compatibility aliases for `deepseek-v4-flash` until July 24, 2026. Provider-specific mappings translate `deepseek-v4-pro` / `deepseek-v4-flash` to each provider's model ID where supported. Generic `openai`, `atlascloud`, `wanjie-ark`, and Ollama model IDs are passed through unchanged. OpenRouter provider configs with a custom `base_url` also preserve explicit model values, which lets OpenAI-compatible gateways accept bare model IDs. Use `/models` or `codewhale models` to discover live IDs from your configured endpoint. `DEEPSEEK_MODEL` overrides this for a single process.
- `reasoning_effort` (string, optional): `off`, `low`, `medium`, `high`, or `max`; defaults to the configured UI tier. DeepSeek Platform receives top-level `thinking` / `reasoning_effort` fields. NVIDIA NIM receives equivalent settings through `chat_template_kwargs`.
- `allow_shell` (bool, optional): defaults to `true` (sandboxed).
- `approval_policy` (string, optional): `on-request`, `untrusted`, or `never`. Runtime `approval_mode` editing in `/config` also accepts `on-request` and `untrusted` aliases.