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

docs: add provider registry reference and refresh provider lists (#2201)

Browse Source 
- Add docs/PROVIDERS.md placeholder reference in README and CONFIGURATION.md
- Update provider lists to include moonshot, openrouter, novita
- Add MOONSHOT_API_KEY/KIMI_API_KEY env var docs
- Update default_text_model entries for all providers
- Change legacy deepseek-cn alias to deepseek
- Add CODEWHALE_PROVIDER as preferred env var name
This commit is contained in:
Hunter Bown
2026-05-26 16:37:33 -05:00
parent aa83446d6b
commit 2b8f3bf3dd
3 changed files with 176 additions and 8 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/CONFIGURATION.md
+12 -6
View File
@@ -62,8 +62,11 @@ label without printing the key itself. The command only probes the active
provider's keyring entry.
For hosted, generic OpenAI-compatible, or self-hosted providers, set
`provider = "nvidia-nim"`, `"openai"`, `"atlascloud"`, `"wanjie-ark"`, `"fireworks"`,
`"sglang"`, `"vllm"`, or `"ollama"` or pass `codewhale --provider <name>`.
`provider = "nvidia-nim"`, `"openai"`, `"atlascloud"`, `"wanjie-ark"`,
`"openrouter"`, `"novita"`, `"fireworks"`, `"moonshot"`, `"sglang"`,
`"vllm"`, or `"ollama"` or pass `codewhale --provider <name>`.
For the provider-by-provider registry, including auth variables, default base
URLs, model IDs, and capability metadata, see [PROVIDERS.md](PROVIDERS.md).
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
@@ -204,7 +207,7 @@ 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`
`deepseek|nvidia-nim|openai|atlascloud|wanjie-ark|openrouter|novita|fireworks|moonshot|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
@@ -233,6 +236,9 @@ Remaining variables:
- `NOVITA_BASE_URL`
- `FIREWORKS_API_KEY`
- `FIREWORKS_BASE_URL`
- `MOONSHOT_API_KEY` or `KIMI_API_KEY`
- `MOONSHOT_BASE_URL` or `KIMI_BASE_URL`
- `MOONSHOT_MODEL`, `KIMI_MODEL_NAME`, or `KIMI_MODEL`
- `SGLANG_BASE_URL`
- `SGLANG_MODEL`
- `SGLANG_API_KEY` (optional; many localhost SGLang servers do not require auth)
@@ -435,10 +441,10 @@ 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`, `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`.
- `provider` (string, optional): `deepseek` (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 `deepseek`; 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`; `openrouter` targets `https://openrouter.ai/api/v1`; `novita` targets `https://api.novita.ai/v1`; `fireworks` targets `https://api.fireworks.ai/inference/v1`; `moonshot` targets Moonshot/Kimi, defaulting to `https://api.moonshot.ai/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"`, 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.
- `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. Other defaults are `https://integrate.api.nvidia.com/v1` for `nvidia-nim`, `https://api.openai.com/v1` for `openai`, `https://api.atlascloud.ai/v1` for `atlascloud`, `https://maas-openapi.wanjiedata.com/api/v1` for `wanjie-ark`, `https://openrouter.ai/api/v1` for `openrouter`, `https://api.novita.ai/v1` for `novita`, `https://api.fireworks.ai/inference/v1` for `fireworks`, `https://api.moonshot.ai/v1` for `moonshot`, `http://localhost:30000/v1` for `sglang`, `http://localhost:8000/v1` for `vllm`, and `http://localhost:11434/v1` for `ollama`. 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, `deepseek/deepseek-v4-pro` for OpenRouter and Novita, `accounts/fireworks/models/deepseek-v4-pro` for Fireworks, `kimi-k2.6` for Moonshot, `deepseek-ai/DeepSeek-V4-Pro` for SGLang/vLLM, and `deepseek-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. `CODEWHALE_MODEL` overrides this for a single process; `DEEPSEEK_MODEL` is the legacy alias.
- `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.
docs/PROVIDERS.md
+159
View File
@@ -0,0 +1,159 @@
# Provider Registry
This registry describes provider behavior that is wired into the current
CodeWhale codebase. It is intentionally conservative: shipped entries are
limited to provider IDs, config keys, auth paths, base URLs, model resolution,
and capability metadata that the code already knows about.
DeepSeek remains the first-class default provider. NVIDIA NIM, OpenRouter,
Novita, Fireworks, generic OpenAI-compatible endpoints, self-hosted runtimes,
and Moonshot/Kimi are additive routes for running the same terminal harness
against other hosted or local model endpoints. Hugging Face Inference Providers
are a planned additive open-model routing layer; they are not a native provider
in this checkout yet.
Sources to keep in sync:
- `crates/config/src/lib.rs` - shared provider IDs, defaults, env precedence.
- `crates/tui/src/config.rs` - TUI provider IDs, provider capability metadata,
and provider-specific env handling.
- `crates/agent/src/lib.rs` - static `ModelRegistry` used by
`codewhale model list` and `codewhale model resolve`.
- `config.example.toml` and `docs/CONFIGURATION.md` - user-facing config
examples and environment variable reference.
## Provider Selection
The canonical provider IDs are:
`deepseek`, `nvidia-nim`, `openai`, `atlascloud`, `wanjie-ark`, `openrouter`,
`novita`, `fireworks`, `moonshot`, `sglang`, `vllm`, and `ollama`.
Use any of these surfaces to select a provider:
- CLI: `codewhale --provider <id>`
- TUI: `/provider <id>` or the provider picker
- Env: `CODEWHALE_PROVIDER=<id>`; `DEEPSEEK_PROVIDER=<id>` is the legacy alias
- Config: `provider = "<id>"`
`deepseek-cn`, `deepseek_china`, `deepseekcn`, and `deepseek-china` are accepted
as legacy aliases for `deepseek`. They do not select a different official host;
DeepSeek uses the same official API host worldwide.
Fresh shared config writes to `~/.codewhale/config.toml`. Existing
`~/.deepseek/config.toml` files are still read for compatibility.
## Auth And Env Rules
For hosted providers, `codewhale auth set --provider <id>` saves an API key for
that provider. API-key environment variables are fallback inputs after saved
config and keyring credentials; an explicit process-level `--api-key` still
wins for that launch.
For base URL and model selection, prefer:
- `CODEWHALE_BASE_URL` / `CODEWHALE_MODEL` for the active provider.
- Provider-specific base URL/model env vars when listed below.
- `DEEPSEEK_BASE_URL`, `DEEPSEEK_MODEL`, and `DEEPSEEK_DEFAULT_TEXT_MODEL` as
legacy aliases.
Non-local `http://` base URLs are rejected unless
`DEEPSEEK_ALLOW_INSECURE_HTTP=1` is set. Loopback HTTP URLs are allowed for
self-hosted runtimes.
## Shipped Providers
| Provider ID | TOML table | Auth env | Base URL env and default | Default or static models | Notes |
| --- | --- | --- | --- | --- | --- |
| `deepseek` | `[providers.deepseek]` | `DEEPSEEK_API_KEY` | `CODEWHALE_BASE_URL` / `DEEPSEEK_BASE_URL`; default `https://api.deepseek.com/beta` | `deepseek-v4-pro`, `deepseek-v4-flash`; compatibility aliases `deepseek-chat`, `deepseek-reasoner` | First-class default. Beta URL enables strict tool mode, chat prefix completion, and FIM completion. Set `https://api.deepseek.com` or `/v1` explicitly to opt out of beta-only features. |
| `nvidia-nim` | `[providers.nvidia_nim]` | `NVIDIA_API_KEY`, `NVIDIA_NIM_API_KEY`, fallback `DEEPSEEK_API_KEY` | `NVIDIA_NIM_BASE_URL`, `NIM_BASE_URL`, `NVIDIA_BASE_URL`; default `https://integrate.api.nvidia.com/v1` | `deepseek-ai/deepseek-v4-pro`, `deepseek-ai/deepseek-v4-flash` | Hosted DeepSeek V4 through NVIDIA NIM. `NVIDIA_NIM_MODEL` is accepted by the TUI config path. |
| `openai` | `[providers.openai]` | `OPENAI_API_KEY` | `OPENAI_BASE_URL`; default `https://api.openai.com/v1` | Registry entries: `deepseek-v4-pro`, `deepseek-v4-flash`; default config model `deepseek-v4-pro` | Generic OpenAI-compatible route for gateways and custom endpoints. Use this for explicit third-party OpenAI-compatible routes instead of inventing a new provider ID. `OPENAI_MODEL` is accepted. |
| `atlascloud` | `[providers.atlascloud]` | `ATLASCLOUD_API_KEY` | `ATLASCLOUD_BASE_URL`; default `https://api.atlascloud.ai/v1` | Default config model `deepseek-ai/deepseek-v4-flash` | OpenAI-compatible hosted route. `ATLASCLOUD_MODEL` is accepted by the TUI config path. The static `ModelRegistry` does not currently list AtlasCloud rows. |
| `wanjie-ark` | `[providers.wanjie_ark]` | `WANJIE_ARK_API_KEY`, `WANJIE_API_KEY`, `WANJIE_MAAS_API_KEY` | `WANJIE_ARK_BASE_URL`, `WANJIE_BASE_URL`, `WANJIE_MAAS_BASE_URL`; default `https://maas-openapi.wanjiedata.com/api/v1` | `deepseek-reasoner` | OpenAI-compatible hosted route. `WANJIE_ARK_MODEL`, `WANJIE_MODEL`, and `WANJIE_MAAS_MODEL` are accepted. |
| `openrouter` | `[providers.openrouter]` | `OPENROUTER_API_KEY` | `OPENROUTER_BASE_URL`; default `https://openrouter.ai/api/v1` | `deepseek/deepseek-v4-pro`, `deepseek/deepseek-v4-flash` | Additive open-model routing layer. It does not replace DeepSeek; it lets users route supported model IDs through OpenRouter when they choose it. |
| `novita` | `[providers.novita]` | `NOVITA_API_KEY` | `NOVITA_BASE_URL`; default `https://api.novita.ai/v1` | `deepseek/deepseek-v4-pro`, `deepseek/deepseek-v4-flash` | OpenAI-compatible hosted route for DeepSeek model IDs. Use config or `CODEWHALE_MODEL` / `DEEPSEEK_MODEL` for model overrides. |
| `fireworks` | `[providers.fireworks]` | `FIREWORKS_API_KEY` | `FIREWORKS_BASE_URL`; default `https://api.fireworks.ai/inference/v1` | `accounts/fireworks/models/deepseek-v4-pro` | OpenAI-compatible hosted route. Use config or `CODEWHALE_MODEL` / `DEEPSEEK_MODEL` for model overrides. |
| `moonshot` | `[providers.moonshot]` | `MOONSHOT_API_KEY`, `KIMI_API_KEY` | `MOONSHOT_BASE_URL`, `KIMI_BASE_URL`; default `https://api.moonshot.ai/v1` | `kimi-k2.6`; Kimi Code path uses `kimi-for-coding` at `https://api.kimi.com/coding/v1` | Moonshot/Kimi route. `MOONSHOT_MODEL`, `KIMI_MODEL_NAME`, and `KIMI_MODEL` are accepted. `[providers.moonshot] auth_mode = "kimi_oauth"` reads Kimi CLI OAuth credentials when present. |
| `sglang` | `[providers.sglang]` | Optional `SGLANG_API_KEY` | `SGLANG_BASE_URL`; default `http://localhost:30000/v1` | `deepseek-ai/DeepSeek-V4-Pro`, `deepseek-ai/DeepSeek-V4-Flash` | Self-hosted OpenAI-compatible route. Localhost deployments commonly omit auth. `SGLANG_MODEL` is accepted. |
| `vllm` | `[providers.vllm]` | Optional `VLLM_API_KEY` | `VLLM_BASE_URL`; default `http://localhost:8000/v1` | `deepseek-ai/DeepSeek-V4-Pro`, `deepseek-ai/DeepSeek-V4-Flash` | Self-hosted vLLM OpenAI-compatible route. Localhost deployments commonly omit auth. `VLLM_MODEL` is accepted. |
| `ollama` | `[providers.ollama]` | Optional `OLLAMA_API_KEY` | `OLLAMA_BASE_URL`; default `http://localhost:11434/v1` | `deepseek-coder:1.3b`; provider-hinted custom tags pass through | Self-hosted Ollama OpenAI-compatible route. Localhost deployments commonly omit auth. `OLLAMA_MODEL` is accepted. |
## Static Model Registry
`codewhale model list` and `codewhale model resolve` use the static registry in
`crates/agent/src/lib.rs`. This is not the same as live `/models` discovery.
Use `/models` or `codewhale models` to fetch model IDs from the active API
endpoint when the endpoint supports model listing.
| Provider | Static registry entries | Tool calls | Registry reasoning flag |
| --- | --- | --- | --- |
| `deepseek` | `deepseek-v4-pro`, `deepseek-v4-flash` | yes | yes |
| `nvidia-nim` | `deepseek-ai/deepseek-v4-pro`, `deepseek-ai/deepseek-v4-flash` | yes | yes |
| `openai` | `deepseek-v4-pro`, `deepseek-v4-flash` | yes | yes |
| `wanjie-ark` | `deepseek-reasoner` | yes | yes |
| `openrouter` | `deepseek/deepseek-v4-pro`, `deepseek/deepseek-v4-flash` | yes | yes |
| `novita` | `deepseek/deepseek-v4-pro`, `deepseek/deepseek-v4-flash` | yes | yes |
| `fireworks` | `accounts/fireworks/models/deepseek-v4-pro` | yes | yes |
| `moonshot` | `kimi-k2.6` | yes | yes |
| `sglang` | `deepseek-ai/DeepSeek-V4-Pro`, `deepseek-ai/DeepSeek-V4-Flash` | yes | yes |
| `vllm` | `deepseek-ai/DeepSeek-V4-Pro`, `deepseek-ai/DeepSeek-V4-Flash` | yes | yes |
| `ollama` | `deepseek-coder:1.3b`; custom tags pass through when provider hint is `ollama` | yes | no |
The registry currently has no AtlasCloud entry even though AtlasCloud is a
supported provider in config and TUI selection. AtlasCloud should use the
configured model or live model listing.
## Capability Metadata
`codewhale-tui doctor --json` exposes the `capability` object. It is static
metadata, not a live API probe. Current fields are:
`resolved_provider`, `resolved_model`, `context_window`, `max_output`,
`thinking_supported`, `cache_telemetry_supported`, and `request_payload_mode`.
All shipped providers use the Chat Completions request payload mode today.
| Provider/model class | Context window | Max output metadata | Thinking support | Cache telemetry | FIM endpoint |
| --- | --- | --- | --- | --- | --- |
| DeepSeek V4 (`deepseek-v4-pro`, `deepseek-v4-flash`) | 1,000,000 | 384,000 | yes | yes | DeepSeek beta only |
| DeepSeek compatibility aliases (`deepseek-chat`, `deepseek-reasoner`) | 1,000,000 | 384,000 | yes | yes | DeepSeek beta only |
| NVIDIA NIM V4 registry models | 1,000,000 | 384,000 | yes | yes | not documented in code |
| OpenRouter, Novita, Fireworks, SGLang, and vLLM V4 model IDs | 1,000,000 | 384,000 | yes | no | not documented in code |
| Wanjie Ark `reasoner` / `r1` model IDs | 128,000 | 4,096 | yes | no | not documented in code |
| Generic `openai`, AtlasCloud, and Moonshot/Kimi | 128,000 | 4,096 | no in doctor capability metadata | no | not documented in code |
| Ollama | 8,192 | 4,096 | no | no | not documented in code |
| Other recognized DeepSeek model IDs | 128,000 unless the model name carries an explicit `Nk` hint | 4,096 | no unless V4/reasoner logic matches | DeepSeek/NIM only | DeepSeek beta only |
Tool-call support is tracked separately by the static `ModelRegistry` and by
the endpoint's ability to accept OpenAI-compatible `tools` payloads. A custom
OpenAI-compatible or local endpoint can still reject tool calls even if
CodeWhale can send the schema.
DeepSeek compatibility aliases `deepseek-chat` and `deepseek-reasoner` map to
`deepseek-v4-flash` capability metadata and are scheduled to retire on
2026-07-24 at 2026-07-24T15:59:00Z.
## Planned, Not Shipped Yet
These items belong to the v0.8.47 provider-abstraction milestone or related
provider docs work, but they are not native shipped behavior in this checkout:
- A unified `Provider` trait in `codewhale-agent` that owns env precedence,
secret resolution, base URL normalization, auth-header construction, and
provider metadata. Those responsibilities are still split across
`crates/config`, `crates/secrets`, and `crates/tui/src/client.rs`.
- A native Hugging Face provider such as `[providers.huggingface]`.
- Native Hugging Face auth envs such as `HF_TOKEN` or `HUGGINGFACE_API_KEY`.
- A default Hugging Face router base URL such as
`https://router.huggingface.co/v1`.
- Hugging Face model passport metadata in the picker, including license, base
model, context length, chat template, tool-call support, reasoning support,
and gated/private status.
- A generated drift-check script that fails when this file diverges from the
provider registry. Until that exists, update this file with a source read of
the files listed at the top.
Until native Hugging Face support lands, users can only reach an explicitly
configured Hugging Face-compatible OpenAI route through the generic `openai`
provider. That is an explicit user-selected route, not built-in Hub discovery
or a replacement for DeepSeek.