skykoi 2026.3.11 → 2026.3.13

package/docs/providers/anthropic.md

@@ -1,7 +1,7 @@
 ---
-summary: "Use Anthropic Claude via API keys or setup-token in SkyKoi"
+summary: "Use Anthropic Claude via API keys or setup-token in SKYKOI"
 read_when:
-  - You want to use Anthropic models in SkyKoi
+  - You want to use Anthropic models in SKYKOI
   - You want setup-token instead of API keys
 title: "Anthropic"
 ---
@@ -9,7 +9,7 @@ title: "Anthropic"
 # Anthropic (Claude)
 
 Anthropic builds the **Claude** model family and provides access via an API.
-In SkyKoi you can authenticate with an API key or a **setup-token**.
+In SKYKOI you can authenticate with an API key or a **setup-token**.
 
 ## Option A: Anthropic API key
 
@@ -19,11 +19,11 @@ Create your API key in the Anthropic Console.
 ### CLI setup
 
 ```bash
-SkyKoi onboard
+SKYKOI onboard
 # choose: Anthropic API key
 
 # or non-interactive
-SkyKoi onboard --anthropic-api-key "$ANTHROPIC_API_KEY"
+SKYKOI onboard --anthropic-api-key "$ANTHROPIC_API_KEY"
 ```
 
 ### Config snippet
@@ -37,7 +37,7 @@ SkyKoi onboard --anthropic-api-key "$ANTHROPIC_API_KEY"
 
 ## Prompt caching (Anthropic API)
 
-SkyKoi supports Anthropic's prompt caching feature. This is **API-only**; subscription auth does not honor cache settings.
+SKYKOI supports Anthropic's prompt caching feature. This is **API-only**; subscription auth does not honor cache settings.
 
 ### Configuration
 
@@ -65,7 +65,7 @@ Use the `cacheRetention` parameter in your model config:
 
 ### Defaults
 
-When using Anthropic API Key authentication, SkyKoi automatically applies `cacheRetention: "short"` (5-minute cache) for all Anthropic models. You can override this by explicitly setting `cacheRetention` in your config.
+When using Anthropic API Key authentication, SKYKOI automatically applies `cacheRetention: "short"` (5-minute cache) for all Anthropic models. You can override this by explicitly setting `cacheRetention` in your config.
 
 ### Legacy parameter
 
@@ -76,7 +76,7 @@ The older `cacheControlTtl` parameter is still supported for backwards compatibi
 
 We recommend migrating to the new `cacheRetention` parameter.
 
-SkyKoi includes the `extended-cache-ttl-2025-04-11` beta flag for Anthropic API
+SKYKOI includes the `extended-cache-ttl-2025-04-11` beta flag for Anthropic API
 requests; keep it if you override provider headers (see [/gateway/configuration](/gateway/configuration)).
 
 ## Option B: Claude setup-token
@@ -91,23 +91,23 @@ Setup-tokens are created by the **Claude Code CLI**, not the Anthropic Console.
 claude setup-token
 ```
 
-Paste the token into SkyKoi (wizard: **Anthropic token (paste setup-token)**), or run it on the gateway host:
+Paste the token into SKYKOI (wizard: **Anthropic token (paste setup-token)**), or run it on the gateway host:
 
 ```bash
-SkyKoi models auth setup-token --provider anthropic
+SKYKOI models auth setup-token --provider anthropic
 ```
 
 If you generated the token on a different machine, paste it:
 
 ```bash
-SkyKoi models auth paste-token --provider anthropic
+SKYKOI models auth paste-token --provider anthropic
 ```
 
 ### CLI setup (setup-token)
 
 ```bash
 # Paste a setup-token during onboarding
-SkyKoi onboard --auth-choice setup-token
+SKYKOI onboard --auth-choice setup-token
 ```
 
 ### Config snippet (setup-token)
@@ -120,7 +120,7 @@ SkyKoi onboard --auth-choice setup-token
 
 ## Notes
 
-- Generate the setup-token with `claude setup-token` and paste it, or run `SkyKoi models auth setup-token` on the gateway host.
+- Generate the setup-token with `claude setup-token` and paste it, or run `SKYKOI models auth setup-token` on the gateway host.
 - If you see “OAuth token refresh failed …” on a Claude subscription, re-auth with a setup-token. See [/gateway/troubleshooting#oauth-token-refresh-failed-anthropic-claude-subscription](/gateway/troubleshooting#oauth-token-refresh-failed-anthropic-claude-subscription).
 - Auth details + reuse rules are in [/concepts/oauth](/concepts/oauth).
 
@@ -131,22 +131,22 @@ SkyKoi onboard --auth-choice setup-token
 - Claude subscription auth can expire or be revoked. Re-run `claude setup-token`
   and paste it into the **gateway host**.
 - If the Claude CLI login lives on a different machine, use
-  `SkyKoi models auth paste-token --provider anthropic` on the gateway host.
+  `SKYKOI models auth paste-token --provider anthropic` on the gateway host.
 
 **No API key found for provider "anthropic"**
 
 - Auth is **per agent**. New agents don’t inherit the main agent’s keys.
 - Re-run onboarding for that agent, or paste a setup-token / API key on the
-  gateway host, then verify with `SkyKoi models status`.
+  gateway host, then verify with `SKYKOI models status`.
 
 **No credentials found for profile `anthropic:default`**
 
-- Run `SkyKoi models status` to see which auth profile is active.
+- Run `SKYKOI models status` to see which auth profile is active.
 - Re-run onboarding, or paste a setup-token / API key for that profile.
 
 **No available auth profile (all in cooldown/unavailable)**
 
-- Check `SkyKoi models status --json` for `auth.unusableProfiles`.
+- Check `SKYKOI models status --json` for `auth.unusableProfiles`.
 - Add another Anthropic profile or wait for cooldown.
 
 More: [/gateway/troubleshooting](/gateway/troubleshooting) and [/help/faq](/help/faq).

package/docs/providers/bedrock.md

@@ -1,14 +1,14 @@
 ---
-summary: "Use Amazon Bedrock (Converse API) models with SkyKoi"
+summary: "Use Amazon Bedrock (Converse API) models with SKYKOI"
 read_when:
-  - You want to use Amazon Bedrock models with SkyKoi
+  - You want to use Amazon Bedrock models with SKYKOI
   - You need AWS credential/region setup for model calls
 title: "Amazon Bedrock"
 ---
 
 # Amazon Bedrock
 
-SkyKoi can use **Amazon Bedrock** models via pi‑ai’s **Bedrock Converse**
+SKYKOI can use **Amazon Bedrock** models via pi‑ai’s **Bedrock Converse**
 streaming provider. Bedrock auth uses the **AWS SDK default credential chain**,
 not an API key.
 
@@ -21,7 +21,7 @@ not an API key.
 
 ## Automatic model discovery
 
-If AWS credentials are detected, SkyKoi can automatically discover Bedrock
+If AWS credentials are detected, SKYKOI can automatically discover Bedrock
 models that support **streaming** and **text output**. Discovery uses
 `bedrock:ListFoundationModels` and is cached (default: 1 hour).
 
@@ -100,9 +100,9 @@ export AWS_BEARER_TOKEN_BEDROCK="..."
 
 ## EC2 Instance Roles
 
-When running SkyKoi on an EC2 instance with an IAM role attached, the AWS SDK
+When running SKYKOI on an EC2 instance with an IAM role attached, the AWS SDK
 will automatically use the instance metadata service (IMDS) for authentication.
-However, SkyKoi's credential detection currently only checks for environment
+However, SKYKOI's credential detection currently only checks for environment
 variables, not IMDS credentials.
 
 **Workaround:** Set `AWS_PROFILE=default` to signal that AWS credentials are
@@ -150,8 +150,8 @@ aws ec2 associate-iam-instance-profile \
   --iam-instance-profile Name=EC2-Bedrock-Access
 
 # 3. On the EC2 instance, enable discovery
-SkyKoi config set models.bedrockDiscovery.enabled true
-SkyKoi config set models.bedrockDiscovery.region us-east-1
+SKYKOI config set models.bedrockDiscovery.enabled true
+SKYKOI config set models.bedrockDiscovery.region us-east-1
 
 # 4. Set the workaround env vars
 echo 'export AWS_PROFILE=default' >> ~/.bashrc
@@ -159,7 +159,7 @@ echo 'export AWS_REGION=us-east-1' >> ~/.bashrc
 source ~/.bashrc
 
 # 5. Verify models are discovered
-SkyKoi models list
+SKYKOI models list
 ```
 
 ## Notes
@@ -167,7 +167,7 @@ SkyKoi models list
 - Bedrock requires **model access** enabled in your AWS account/region.
 - Automatic discovery needs the `bedrock:ListFoundationModels` permission.
 - If you use profiles, set `AWS_PROFILE` on the gateway host.
-- SkyKoi surfaces the credential source in this order: `AWS_BEARER_TOKEN_BEDROCK`,
+- SKYKOI surfaces the credential source in this order: `AWS_BEARER_TOKEN_BEDROCK`,
   then `AWS_ACCESS_KEY_ID` + `AWS_SECRET_ACCESS_KEY`, then `AWS_PROFILE`, then the
   default AWS SDK chain.
 - Reasoning support depends on the model; check the Bedrock model card for

package/docs/providers/claude-max-api-proxy.md

@@ -70,9 +70,9 @@ curl http://localhost:3456/v1/chat/completions \
   }'
 ```
 
-### With SkyKoi
+### With SKYKOI
 
-You can point SkyKoi at the proxy as a custom OpenAI-compatible endpoint:
+You can point SKYKOI at the proxy as a custom OpenAI-compatible endpoint:
 
 ```json5
 {
@@ -137,12 +137,12 @@ launchctl bootstrap gui/$(id -u) ~/Library/LaunchAgents/com.claude-max-api.plist
 
 ## Notes
 
-- This is a **community tool**, not officially supported by Anthropic or SkyKoi
+- This is a **community tool**, not officially supported by Anthropic or SKYKOI
 - Requires an active Claude Max/Pro subscription with Claude Code CLI authenticated
 - The proxy runs locally and does not send data to any third-party servers
 - Streaming responses are fully supported
 
 ## See Also
 
-- [Anthropic provider](/providers/anthropic) - Native SkyKoi integration with Claude setup-token or API keys
+- [Anthropic provider](/providers/anthropic) - Native SKYKOI integration with Claude setup-token or API keys
 - [OpenAI provider](/providers/openai) - For OpenAI/Codex subscriptions

package/docs/providers/cloudflare-ai-gateway.md

@@ -2,13 +2,13 @@
 title: "Cloudflare AI Gateway"
 summary: "Cloudflare AI Gateway setup (auth + model selection)"
 read_when:
-  - You want to use Cloudflare AI Gateway with SkyKoi
+  - You want to use Cloudflare AI Gateway with SKYKOI
   - You need the account ID, gateway ID, or API key env var
 ---
 
 # Cloudflare AI Gateway
 
-Cloudflare AI Gateway sits in front of provider APIs and lets you add analytics, caching, and controls. For Anthropic, SkyKoi uses the Anthropic Messages API through your Gateway endpoint.
+Cloudflare AI Gateway sits in front of provider APIs and lets you add analytics, caching, and controls. For Anthropic, SKYKOI uses the Anthropic Messages API through your Gateway endpoint.
 
 - Provider: `cloudflare-ai-gateway`
 - Base URL: `https://gateway.ai.cloudflare.com/v1/<account_id>/<gateway_id>/anthropic`
@@ -22,7 +22,7 @@ For Anthropic models, use your Anthropic API key.
 1. Set the provider API key and Gateway details:
 
 ```bash
-SkyKoi onboard --auth-choice cloudflare-ai-gateway-api-key
+SKYKOI onboard --auth-choice cloudflare-ai-gateway-api-key
 ```
 
 2. Set a default model:
@@ -40,7 +40,7 @@ SkyKoi onboard --auth-choice cloudflare-ai-gateway-api-key
 ## Non-interactive example
 
 ```bash
-SkyKoi onboard --non-interactive \
+SKYKOI onboard --non-interactive \
   --mode local \
   --auth-choice cloudflare-ai-gateway-api-key \
   --cloudflare-ai-gateway-account-id "your-account-id" \
@@ -68,4 +68,4 @@ If you enabled Gateway authentication in Cloudflare, add the `cf-aig-authorizati
 
 ## Environment note
 
-If the Gateway runs as a daemon (launchd/systemd), make sure `CLOUDFLARE_AI_GATEWAY_API_KEY` is available to that process (for example, in `~/.skykoi/.env` or via `env.shellEnv`).
+If the Gateway runs as a daemon (launchd/systemd), make sure `CLOUDFLARE_AI_GATEWAY_API_KEY` is available to that process (for example, in `~/.SKYKOI/.env` or via `env.shellEnv`).

package/docs/providers/deepgram.md

@@ -8,10 +8,10 @@ title: "Deepgram"
 
 # Deepgram (Audio Transcription)
 
-Deepgram is a speech-to-text API. In SkyKoi it is used for **inbound audio/voice note
+Deepgram is a speech-to-text API. In SKYKOI it is used for **inbound audio/voice note
 transcription** via `tools.media.audio`.
 
-When enabled, SkyKoi uploads the audio file to Deepgram and injects the transcript
+When enabled, SKYKOI uploads the audio file to Deepgram and injects the transcript
 into the reply pipeline (`{{Transcript}}` + `[Audio]` block). This is **not streaming**;
 it uses the pre-recorded transcription endpoint.
 

package/docs/providers/github-copilot.md

@@ -1,8 +1,8 @@
 ---
-summary: "Sign in to GitHub Copilot from SkyKoi using the device flow"
+summary: "Sign in to GitHub Copilot from SKYKOI using the device flow"
 read_when:
   - You want to use GitHub Copilot as a model provider
-  - You need the `SkyKoi models auth login-github-copilot` flow
+  - You need the `SKYKOI models auth login-github-copilot` flow
 title: "GitHub Copilot"
 ---
 
@@ -11,20 +11,20 @@ title: "GitHub Copilot"
 ## What is GitHub Copilot?
 
 GitHub Copilot is GitHub's AI coding assistant. It provides access to Copilot
-models for your GitHub account and plan. SkyKoi can use Copilot as a model
+models for your GitHub account and plan. SKYKOI can use Copilot as a model
 provider in two different ways.
 
-## Two ways to use Copilot in SkyKoi
+## Two ways to use Copilot in SKYKOI
 
 ### 1) Built-in GitHub Copilot provider (`github-copilot`)
 
 Use the native device-login flow to obtain a GitHub token, then exchange it for
-Copilot API tokens when SkyKoi runs. This is the **default** and simplest path
+Copilot API tokens when SKYKOI runs. This is the **default** and simplest path
 because it does not require VS Code.
 
 ### 2) Copilot Proxy plugin (`copilot-proxy`)
 
-Use the **Copilot Proxy** VS Code extension as a local bridge. SkyKoi talks to
+Use the **Copilot Proxy** VS Code extension as a local bridge. SKYKOI talks to
 the proxy’s `/v1` endpoint and uses the model list you configure there. Choose
 this when you already run Copilot Proxy in VS Code or need to route through it.
 You must enable the plugin and keep the VS Code extension running.
@@ -36,7 +36,7 @@ profile.
 ## CLI setup
 
 ```bash
-SkyKoi models auth login-github-copilot
+SKYKOI models auth login-github-copilot
 ```
 
 You'll be prompted to visit a URL and enter a one-time code. Keep the terminal
@@ -45,14 +45,14 @@ open until it completes.
 ### Optional flags
 
 ```bash
-SkyKoi models auth login-github-copilot --profile-id github-copilot:work
-SkyKoi models auth login-github-copilot --yes
+SKYKOI models auth login-github-copilot --profile-id github-copilot:work
+SKYKOI models auth login-github-copilot --yes
 ```
 
 ## Set a default model
 
 ```bash
-SkyKoi models set github-copilot/gpt-4o
+SKYKOI models set github-copilot/gpt-4o
 ```
 
 ### Config snippet
@@ -69,4 +69,4 @@ SkyKoi models set github-copilot/gpt-4o
 - Copilot model availability depends on your plan; if a model is rejected, try
   another ID (for example `github-copilot/gpt-4.1`).
 - The login stores a GitHub token in the auth profile store and exchanges it for a
-  Copilot API token when SkyKoi runs.
+  Copilot API token when SKYKOI runs.

package/docs/providers/glm.md

@@ -1,20 +1,20 @@
 ---
-summary: "GLM model family overview + how to use it in SkyKoi"
+summary: "GLM model family overview + how to use it in SKYKOI"
 read_when:
-  - You want GLM models in SkyKoi
+  - You want GLM models in SKYKOI
   - You need the model naming convention and setup
 title: "GLM Models"
 ---
 
 # GLM models
 
-GLM is a **model family** (not a company) available through the Z.AI platform. In SkyKoi, GLM
+GLM is a **model family** (not a company) available through the Z.AI platform. In SKYKOI, GLM
 models are accessed via the `zai` provider and model IDs like `zai/glm-4.7`.
 
 ## CLI setup
 
 ```bash
-SkyKoi onboard --auth-choice zai-api-key
+SKYKOI onboard --auth-choice zai-api-key
 ```
 
 ## Config snippet

package/docs/providers/index.md

@@ -1,5 +1,5 @@
 ---
-summary: "Model providers (LLMs) supported by SkyKoi"
+summary: "Model providers (LLMs) supported by SKYKOI"
 read_when:
   - You want to choose a model provider
   - You need a quick overview of supported LLM backends
@@ -8,7 +8,7 @@ title: "Model Providers"
 
 # Model Providers
 
-SkyKoi can use many LLM providers. Pick a provider, authenticate, then set the
+SKYKOI can use many LLM providers. Pick a provider, authenticate, then set the
 default model as `provider/model`.
 
 Looking for chat channel docs (WhatsApp/Telegram/Discord/Slack/Mattermost (plugin)/etc.)? See [Channels](/channels).
@@ -24,7 +24,7 @@ See [Venice AI](/providers/venice).
 
 ## Quick start
 
-1. Authenticate with the provider (usually via `SkyKoi onboard`).
+1. Authenticate with the provider (usually via `SKYKOI onboard`).
 2. Set the default model:
 
 ```json5

package/docs/providers/minimax.md

@@ -1,7 +1,7 @@
 ---
-summary: "Use MiniMax M2.1 in SkyKoi"
+summary: "Use MiniMax M2.1 in SKYKOI"
 read_when:
-  - You want MiniMax models in SkyKoi
+  - You want MiniMax models in SKYKOI
   - You need MiniMax setup guidance
 title: "MiniMax"
 ---
@@ -44,9 +44,9 @@ MiniMax highlights these improvements in M2.1:
 Enable the bundled OAuth plugin and authenticate:
 
 ```bash
-SkyKoi plugins enable minimax-portal-auth  # skip if already loaded.
-SkyKoi gateway restart  # restart if gateway is already running
-SkyKoi onboard --auth-choice minimax-portal
+SKYKOI plugins enable minimax-portal-auth  # skip if already loaded.
+SKYKOI gateway restart  # restart if gateway is already running
+SKYKOI onboard --auth-choice minimax-portal
 ```
 
 You will be prompted to select an endpoint:
@@ -54,7 +54,7 @@ You will be prompted to select an endpoint:
 - **Global** - International users (`api.minimax.io`)
 - **CN** - Users in China (`api.minimaxi.com`)
 
-See [MiniMax OAuth plugin README](https://github.com/SkyKoi/SkyKoi/tree/main/extensions/minimax-portal-auth) for details.
+See [MiniMax OAuth plugin README](https://github.com/SKYKOI/SKYKOI/tree/main/extensions/minimax-portal-auth) for details.
 
 ### MiniMax M2.1 (API key)
 
@@ -62,7 +62,7 @@ See [MiniMax OAuth plugin README](https://github.com/SkyKoi/SkyKoi/tree/main/ext
 
 Configure via CLI:
 
-- Run `SkyKoi configure`
+- Run `SKYKOI configure`
 - Select **Model/auth**
 - Choose **MiniMax M2.1**
 
@@ -122,7 +122,7 @@ Configure via CLI:
 We have seen strong results with MiniMax M2.1 on powerful hardware (e.g. a
 desktop/server) using LM Studio's local server.
 
-Configure manually via `skykoi.json`:
+Configure manually via `SKYKOI.json`:
 
 ```json5
 {
@@ -156,11 +156,11 @@ Configure manually via `skykoi.json`:
 }
 ```
 
-## Configure via `SkyKoi configure`
+## Configure via `SKYKOI configure`
 
 Use the interactive config wizard to set MiniMax without editing JSON:
 
-1. Run `SkyKoi configure`.
+1. Run `SKYKOI configure`.
 2. Select **Model/auth**.
 3. Choose **MiniMax M2.1**.
 4. Pick your default model when prompted.
@@ -181,7 +181,7 @@ Use the interactive config wizard to set MiniMax without editing JSON:
 - Update pricing values in `models.json` if you need exact cost tracking.
 - Referral link for MiniMax Coding Plan (10% off): [https://platform.minimax.io/subscribe/coding-plan?code=DbXJTRClnb&source=link](https://platform.minimax.io/subscribe/coding-plan?code=DbXJTRClnb&source=link)
 - See [/concepts/model-providers](/concepts/model-providers) for provider rules.
-- Use `SkyKoi models list` and `SkyKoi models set minimax/MiniMax-M2.1` to switch.
+- Use `SKYKOI models list` and `SKYKOI models set minimax/MiniMax-M2.1` to switch.
 
 ## Troubleshooting
 
@@ -192,7 +192,7 @@ and no MiniMax auth profile/env key found). A fix for this detection is in
 **2026.1.12** (unreleased at the time of writing). Fix by:
 
 - Upgrading to **2026.1.12** (or run from source `main`), then restarting the gateway.
-- Running `SkyKoi configure` and selecting **MiniMax M2.1**, or
+- Running `SKYKOI configure` and selecting **MiniMax M2.1**, or
 - Adding the `models.providers.minimax` block manually, or
 - Setting `MINIMAX_API_KEY` (or a MiniMax auth profile) so the provider can be injected.
 
@@ -204,5 +204,5 @@ Make sure the model id is **case‑sensitive**:
 Then recheck with:
 
 ```bash
-SkyKoi models list
+SKYKOI models list
 ```

package/docs/providers/models.md

@@ -1,5 +1,5 @@
 ---
-summary: "Model providers (LLMs) supported by SkyKoi"
+summary: "Model providers (LLMs) supported by SKYKOI"
 read_when:
   - You want to choose a model provider
   - You want quick setup examples for LLM auth + model selection
@@ -8,7 +8,7 @@ title: "Model Provider Quickstart"
 
 # Model Providers
 
-SkyKoi can use many LLM providers. Pick one, authenticate, then set the default
+SKYKOI can use many LLM providers. Pick one, authenticate, then set the default
 model as `provider/model`.
 
 ## Highlight: Venice (Venice AI)
@@ -22,7 +22,7 @@ See [Venice AI](/providers/venice).
 
 ## Quick start (two steps)
 
-1. Authenticate with the provider (usually via `SkyKoi onboard`).
+1. Authenticate with the provider (usually via `SKYKOI onboard`).
 2. Set the default model:
 
 ```json5

package/docs/providers/moonshot.md

@@ -25,13 +25,13 @@ Current Kimi K2 model IDs:
   {/_moonshot-kimi-k2-ids:end_/ && null}
 
 ```bash
-SkyKoi onboard --auth-choice moonshot-api-key
+SKYKOI onboard --auth-choice moonshot-api-key
 ```
 
 Kimi Coding:
 
 ```bash
-SkyKoi onboard --auth-choice kimi-code-api-key
+SKYKOI onboard --auth-choice kimi-code-api-key
 ```
 
 Note: Moonshot and Kimi Coding are separate providers. Keys are not interchangeable, endpoints differ, and model refs differ (Moonshot uses `moonshot/...`, Kimi Coding uses `kimi-coding/...`).

package/docs/providers/ollama.md

@@ -1,14 +1,14 @@
 ---
-summary: "Run SkyKoi with Ollama (local LLM runtime)"
+summary: "Run SKYKOI with Ollama (local LLM runtime)"
 read_when:
-  - You want to run SkyKoi with local models via Ollama
+  - You want to run SKYKOI with local models via Ollama
   - You need Ollama setup and configuration guidance
 title: "Ollama"
 ---
 
 # Ollama
 
-Ollama is a local LLM runtime that makes it easy to run open-source models on your machine. SkyKoi integrates with Ollama's OpenAI-compatible API and can **auto-discover tool-capable models** when you opt in with `OLLAMA_API_KEY` (or an auth profile) and do not define an explicit `models.providers.ollama` entry.
+Ollama is a local LLM runtime that makes it easy to run open-source models on your machine. SKYKOI integrates with Ollama's OpenAI-compatible API and can **auto-discover tool-capable models** when you opt in with `OLLAMA_API_KEY` (or an auth profile) and do not define an explicit `models.providers.ollama` entry.
 
 ## Quick start
 
@@ -26,14 +26,14 @@ ollama pull qwen2.5-coder:32b
 ollama pull deepseek-r1:32b
 ```
 
-3. Enable Ollama for SkyKoi (any value works; Ollama doesn't require a real key):
+3. Enable Ollama for SKYKOI (any value works; Ollama doesn't require a real key):
 
 ```bash
 # Set environment variable
 export OLLAMA_API_KEY="ollama-local"
 
 # Or configure in your config file
-SkyKoi config set models.providers.ollama.apiKey "ollama-local"
+SKYKOI config set models.providers.ollama.apiKey "ollama-local"
 ```
 
 4. Use Ollama models:
@@ -50,7 +50,7 @@ SkyKoi config set models.providers.ollama.apiKey "ollama-local"
 
 ## Model discovery (implicit provider)
 
-When you set `OLLAMA_API_KEY` (or an auth profile) and **do not** define `models.providers.ollama`, SkyKoi discovers models from the local Ollama instance at `http://127.0.0.1:11434`:
+When you set `OLLAMA_API_KEY` (or an auth profile) and **do not** define `models.providers.ollama`, SKYKOI discovers models from the local Ollama instance at `http://127.0.0.1:11434`:
 
 - Queries `/api/tags` and `/api/show`
 - Keeps only models that report `tools` capability
@@ -65,7 +65,7 @@ To see what models are available:
 
 ```bash
 ollama list
-SkyKoi models list
+SKYKOI models list
 ```
 
 To add a new model, simply pull it with Ollama:
@@ -122,7 +122,7 @@ Use explicit config when:
 }
 ```
 
-If `OLLAMA_API_KEY` is set, you can omit `apiKey` in the provider entry and SkyKoi will fill it for availability checks.
+If `OLLAMA_API_KEY` is set, you can omit `apiKey` in the provider entry and SKYKOI will fill it for availability checks.
 
 ### Custom base URL (explicit config)
 
@@ -162,7 +162,7 @@ Once configured, all your Ollama models are available:
 
 ### Reasoning models
 
-SkyKoi marks models as reasoning-capable when Ollama reports `thinking` in `/api/show`:
+SKYKOI marks models as reasoning-capable when Ollama reports `thinking` in `/api/show`:
 
 ```bash
 ollama pull deepseek-r1:32b
@@ -216,7 +216,7 @@ You can also disable streaming for any provider if needed:
 
 ### Context windows
 
-For auto-discovered models, SkyKoi uses the context window reported by Ollama when available, otherwise it defaults to `8192`. You can override `contextWindow` and `maxTokens` in explicit provider config.
+For auto-discovered models, SKYKOI uses the context window reported by Ollama when available, otherwise it defaults to `8192`. You can override `contextWindow` and `maxTokens` in explicit provider config.
 
 ## Troubleshooting
 
@@ -236,7 +236,7 @@ curl http://localhost:11434/api/tags
 
 ### No models available
 
-SkyKoi only auto-discovers models that report tool support. If your model isn't listed, either:
+SKYKOI only auto-discovers models that report tool support. If your model isn't listed, either:
 
 - Pull a tool-capable model, or
 - Define the model explicitly in `models.providers.ollama`.
@@ -263,7 +263,7 @@ ollama serve
 
 ### Corrupted responses or tool names in output
 
-If you see garbled responses containing tool names (like `sessions_send`, `memory_get`) or fragmented text when using Ollama models, this is due to an upstream SDK issue with streaming responses. **This is fixed by default** in the latest SkyKoi version by disabling streaming for Ollama models.
+If you see garbled responses containing tool names (like `sessions_send`, `memory_get`) or fragmented text when using Ollama models, this is due to an upstream SDK issue with streaming responses. **This is fixed by default** in the latest SKYKOI version by disabling streaming for Ollama models.
 
 If you manually enabled streaming and experience this issue:
 

package/docs/providers/openai.md

@@ -1,7 +1,7 @@
 ---
-summary: "Use OpenAI via API keys or Codex subscription in SkyKoi"
+summary: "Use OpenAI via API keys or Codex subscription in SKYKOI"
 read_when:
-  - You want to use OpenAI models in SkyKoi
+  - You want to use OpenAI models in SKYKOI
   - You want Codex subscription auth instead of API keys
 title: "OpenAI"
 ---
@@ -19,9 +19,9 @@ Get your API key from the OpenAI dashboard.
 ### CLI setup
 
 ```bash
-SkyKoi onboard --auth-choice openai-api-key
+SKYKOI onboard --auth-choice openai-api-key
 # or non-interactive
-SkyKoi onboard --openai-api-key "$OPENAI_API_KEY"
+SKYKOI onboard --openai-api-key "$OPENAI_API_KEY"
 ```
 
 ### Config snippet
@@ -42,10 +42,10 @@ Codex cloud requires ChatGPT sign-in, while the Codex CLI supports ChatGPT or AP
 
 ```bash
 # Run Codex OAuth in the wizard
-SkyKoi onboard --auth-choice openai-codex
+SKYKOI onboard --auth-choice openai-codex
 
 # Or run OAuth directly
-SkyKoi models auth login --provider openai-codex
+SKYKOI models auth login --provider openai-codex
 ```
 
 ### Config snippet (Codex subscription)

package/docs/providers/opencode.md

@@ -1,5 +1,5 @@
 ---
-summary: "Use OpenCode Zen (curated models) with SkyKoi"
+summary: "Use OpenCode Zen (curated models) with SKYKOI"
 read_when:
   - You want OpenCode Zen for model access
   - You want a curated list of coding-friendly models
@@ -15,9 +15,9 @@ Zen is currently in beta.
 ## CLI setup
 
 ```bash
-SkyKoi onboard --auth-choice opencode-zen
+SKYKOI onboard --auth-choice opencode-zen
 # or non-interactive
-SkyKoi onboard --opencode-zen-api-key "$OPENCODE_API_KEY"
+SKYKOI onboard --opencode-zen-api-key "$OPENCODE_API_KEY"
 ```
 
 ## Config snippet