feat(llm): add Kilo Gateway and OpenCode Go provider support

README.md

@@ -184,15 +184,15 @@ coding = "ollama/qwen3"
 
 ```toml
 [llm.provider.my-provider]
-api_type = "openai_completions"  # or "anthropic"
+api_type = "openai_completions"  # or "openai_chat_completions", "openai_responses", "anthropic"
 base_url = "https://my-llm-host.example.com"
 api_key = "env:MY_PROVIDER_KEY"
 
 [defaults.routing]
 channel = "my-provider/my-model"
 ```
 
-Additional built-in providers include **NVIDIA**, **MiniMax**, **Moonshot AI (Kimi)**, and **Z.AI Coding Plan** — configure with `nvidia_key`, `minimax_key`, `moonshot_key`, or `zai_coding_plan_key` in `[llm]`.
+Additional built-in providers include **Kilo Gateway**, **OpenCode Go**, **NVIDIA**, **MiniMax**, **Moonshot AI (Kimi)**, and **Z.AI Coding Plan** — configure with `kilo_key`, `opencode_go_key`, `nvidia_key`, `minimax_key`, `moonshot_key`, or `zai_coding_plan_key` in `[llm]`.
 
 ### Skills
 
@@ -381,7 +381,7 @@ Read the full vision in the [roadmap](docs/content/docs/(deployment)/roadmap.mdx
 ### Prerequisites
 
 - **Rust** 1.85+ ([rustup](https://rustup.rs/))
-- An LLM API key from any supported provider (Anthropic, OpenAI, OpenRouter, Z.ai, Groq, Together, Fireworks, DeepSeek, xAI, Mistral, NVIDIA, MiniMax, Moonshot AI, OpenCode Zen) — or use `spacebot auth login` for Anthropic OAuth
+- An LLM API key from any supported provider (Anthropic, OpenAI, OpenRouter, Kilo Gateway, Z.ai, Groq, Together, Fireworks, DeepSeek, xAI, Mistral, NVIDIA, MiniMax, Moonshot AI, OpenCode Zen, OpenCode Go) — or use `spacebot auth login` for Anthropic OAuth
 
 ### Build and Run
 

docs/content/docs/(configuration)/config.mdx

@@ -24,6 +24,7 @@ spacebot --config /path/to.toml  # CLI override
 anthropic_key = "env:ANTHROPIC_API_KEY"
 openai_key = "env:OPENAI_API_KEY"
 openrouter_key = "env:OPENROUTER_API_KEY"
+kilo_key = "env:KILO_API_KEY"
 zhipu_key = "env:ZHIPU_API_KEY"
 groq_key = "env:GROQ_API_KEY"
 together_key = "env:TOGETHER_API_KEY"
@@ -32,6 +33,7 @@ deepseek_key = "env:DEEPSEEK_API_KEY"
 xai_key = "env:XAI_API_KEY"
 mistral_key = "env:MISTRAL_API_KEY"
 opencode_zen_key = "env:OPENCODE_ZEN_API_KEY"
+opencode_go_key = "env:OPENCODE_GO_API_KEY"
 
 # Custom LLM providers (alternative to legacy keys)
 [llm.provider.my_anthropic]
@@ -173,7 +175,7 @@ anthropic_key = "env:ANTHROPIC_API_KEY"
 
 This reads `ANTHROPIC_API_KEY` from the environment at startup. If the variable is unset, the value is treated as missing.
 
-LLM keys also have implicit env fallbacks — if no key is set in the TOML, Spacebot checks `ANTHROPIC_API_KEY`, `OPENAI_API_KEY`, and `OPENROUTER_API_KEY` automatically.
+LLM keys also have implicit env fallbacks — if no key is set in the TOML, Spacebot checks `ANTHROPIC_API_KEY`, `OPENAI_API_KEY`, `OPENROUTER_API_KEY`, `KILO_API_KEY`, and `OPENCODE_GO_API_KEY` automatically.
 
 ## Env-Only Mode
 
@@ -208,6 +210,7 @@ Model names include the provider as a prefix:
 | Anthropic | `anthropic/<model>` | `anthropic/claude-sonnet-4-20250514` |
 | OpenAI | `openai/<model>` | `openai/gpt-4o` |
 | OpenRouter | `openrouter/<provider>/<model>` | `openrouter/anthropic/claude-sonnet-4-20250514` |
+| Kilo Gateway | `kilo/<provider>/<model>` | `kilo/anthropic/claude-sonnet-4.5` |
 | Custom provider | `<provider_id>/<model>` | `my_openai/gpt-4o-mini` |
 
 You can mix providers across process types. See [Routing](/docs/routing) for the full routing system.
@@ -329,6 +332,7 @@ If you define a custom provider with the same ID as a legacy key, your custom co
 | `anthropic_key` | string | None | Anthropic API key (or `env:VAR_NAME`) |
 | `openai_key` | string | None | OpenAI API key (or `env:VAR_NAME`) |
 | `openrouter_key` | string | None | OpenRouter API key (or `env:VAR_NAME`) |
+| `kilo_key` | string | None | Kilo Gateway API key (or `env:VAR_NAME`) |
 | `zhipu_key` | string | None | Zhipu AI (GLM) API key (or `env:VAR_NAME`) |
 | `groq_key` | string | None | Groq API key (or `env:VAR_NAME`) |
 | `together_key` | string | None | Together AI API key (or `env:VAR_NAME`) |
@@ -337,31 +341,34 @@ If you define a custom provider with the same ID as a legacy key, your custom co
 | `xai_key` | string | None | XAI API key (or `env:VAR_NAME`) |
 | `mistral_key` | string | None | Mistral API key (or `env:VAR_NAME`) |
 | `opencode_zen_key` | string | None | OpenCode Zen API key (or `env:VAR_NAME`) |
+| `opencode_go_key` | string | None | OpenCode Go API key (or `env:VAR_NAME`) |
 
 #### Custom Providers
 
 Custom providers allow configuring LLM providers with custom endpoints and API types. Use either legacy keys **or** custom providers.
 
 ```toml
 [llm.provider.<id>]
-api_type = "anthropic"          # Required - one of: anthropic, openai_completions, openai_responses
+api_type = "anthropic"          # Required - see supported values below
 base_url = "https://api..."     # Required - valid URL
 api_key = "env:API_KEY"         # Required - API key (supports env:VAR_NAME format)
 name = "My Provider"            # Optional - friendly name for display
 ```
 
 | Field | Type | Required | Description |
 |-------|------|----------|-------------|
-| `api_type` | string | Yes | API protocol type. One of: `anthropic` (Anthropic Messages API), `openai_completions` (OpenAI Chat Completions-compatible API), or `openai_responses` (OpenAI Responses API-compatible) |
+| `api_type` | string | Yes | API protocol type. One of: `anthropic`, `openai_completions`, `openai_chat_completions`, `openai_responses`, `gemini`, or `kilo_gateway` |
 | `base_url` | string | Yes | Base URL of the API endpoint. Must be a valid URL (including protocol) |
 | `api_key` | string | Yes | API key for authentication. Supports `env:VAR_NAME` syntax to reference environment variables |
 | `name` | string | No | Optional friendly name for the provider (displayed in logs and UI) |
 
 > Note:
-> - For `openai_completions` and `openai_responses`, configure `base_url` as the provider root URL (usually without a trailing `/v1`).
+> - For `openai_completions`, `openai_chat_completions`, and `openai_responses`, configure `base_url` as the provider root URL (usually without a trailing `/v1`).
 > - Spacebot appends the endpoint path automatically:
 >   - `openai_completions` -> `/v1/chat/completions`
+>   - `openai_chat_completions` -> `/chat/completions`
 >   - `openai_responses` -> `/v1/responses`
+>   - `kilo_gateway` -> `/chat/completions` plus Kilo-required `HTTP-Referer` / `X-Title` headers
 > - If you include `/v1` in `base_url`, requests can end up with duplicated paths such as `/v1/v1/...`.
 
 **Provider ID Requirements:**

docs/content/docs/(deployment)/roadmap.mdx

@@ -18,7 +18,7 @@ The full message-in → LLM → response-out pipeline is wired end-to-end across
 - **Config** — hierarchical TOML with `Config`, `AgentConfig`, `ResolvedAgentConfig`, `Binding`, `MessagingConfig`. File watcher with event filtering and content hash debounce for hot-reload.
 - **Multi-agent** — per-agent database isolation, `Agent` struct bundles all dependencies
 - **Database connections** — SQLite + LanceDB + redb per-agent, migrations for all tables
-- **LLM** — `SpacebotModel` implements Rig's `CompletionModel`, routes through `LlmManager` via HTTP with retries and fallback chains across 11 providers (Anthropic, OpenAI, OpenRouter, Z.ai, Groq, Together, Fireworks, DeepSeek, xAI, Mistral, OpenCode Zen)
+- **LLM** — `SpacebotModel` implements Rig's `CompletionModel`, routes through `LlmManager` via HTTP with retries and fallback chains across 13 providers (Anthropic, OpenAI, OpenRouter, Kilo Gateway, Z.ai, Groq, Together, Fireworks, DeepSeek, xAI, Mistral, OpenCode Zen, OpenCode Go)
 - **Model routing** — `RoutingConfig` with process-type defaults, task overrides, fallback chains
 - **Memory** — full stack: types, SQLite store (CRUD + graph), LanceDB (embeddings + vector + FTS), fastembed, hybrid search (RRF fusion). `memory_type` filter wired end-to-end through SearchConfig. `total_cmp` for safe sorting.
 - **Memory maintenance** — decay + prune implemented

docs/content/docs/(getting-started)/quickstart.mdx

@@ -47,7 +47,7 @@ You can also manage updates from **Settings → Updates** in the web UI.
 
 - **Rust 1.85+** — `rustup update stable`
 - **Bun** (optional, for the web UI) — `curl -fsSL https://bun.sh/install | bash`
-- **An LLM API key** — Anthropic, OpenAI, or OpenRouter
+- **An LLM API key** — Anthropic, OpenAI, OpenRouter, Kilo Gateway, or OpenCode Go
 
 ### Install
 
@@ -88,6 +88,8 @@ Create `~/.spacebot/config.toml`:
 [llm]
 anthropic_key = "sk-ant-..."
 # or: openrouter_key = "sk-or-..."
+# or: kilo_key = "sk-..."
+# or: opencode_go_key = "..."
 # or: openai_key = "sk-..."
 # Keys also support env references: anthropic_key = "env:ANTHROPIC_API_KEY"
 

interface/src/api/client.ts

@@ -726,6 +726,7 @@ export interface ProviderStatus {
 	openai: boolean;
 	openai_chatgpt: boolean;
 	openrouter: boolean;
+	kilo: boolean;
 	zhipu: boolean;
 	groq: boolean;
 	together: boolean;
@@ -736,6 +737,7 @@ export interface ProviderStatus {
 	gemini: boolean;
 	ollama: boolean;
 	opencode_zen: boolean;
+	opencode_go: boolean;
 	nvidia: boolean;
 	minimax: boolean;
 	minimax_cn: boolean;

interface/src/components/ModelSelect.tsx

@@ -15,6 +15,7 @@ interface ModelSelectProps {
 const PROVIDER_LABELS: Record<string, string> = {
   anthropic: "Anthropic",
   openrouter: "OpenRouter",
+  kilo: "Kilo Gateway",
   openai: "OpenAI",
   "openai-chatgpt": "ChatGPT Plus (OAuth)",
   deepseek: "DeepSeek",
@@ -27,6 +28,7 @@ const PROVIDER_LABELS: Record<string, string> = {
   zhipu: "Z.ai (GLM)",
   ollama: "Ollama",
   "opencode-zen": "OpenCode Zen",
+  "opencode-go": "OpenCode Go",
   minimax: "MiniMax",
   "minimax-cn": "MiniMax CN",
 };
@@ -128,6 +130,7 @@ export function ModelSelect({
 
   const providerOrder = [
     "openrouter",
+    "kilo",
     "anthropic",
     "openai",
     "openai-chatgpt",
@@ -141,12 +144,16 @@ export function ModelSelect({
     "fireworks",
     "zhipu",
     "opencode-zen",
+    "opencode-go",
     "minimax",
     "minimax-cn",
   ];
+  const providerRank = (provider: string) => {
+    const index = providerOrder.indexOf(provider);
+    return index === -1 ? Number.MAX_SAFE_INTEGER : index;
+  };
   const sortedProviders = Object.keys(grouped).sort(
-    (a, b) =>
-      (providerOrder.indexOf(a) ?? 99) - (providerOrder.indexOf(b) ?? 99),
+    (a, b) => providerRank(a) - providerRank(b),
   );
 
   return (

interface/src/lib/providerIcons.tsx

@@ -90,6 +90,26 @@ function OllamaIcon({ size = 24, className }: IconProps) {
 	);
 }
 
+function KiloIcon({ size = 24, className }: IconProps) {
+	return (
+		<svg
+			width={size}
+			height={size}
+			viewBox="0 0 100 100"
+			fill="none"
+			xmlns="http://www.w3.org/2000/svg"
+			className={className}
+			aria-hidden="true"
+			focusable="false"
+		>
+			<path
+				fill="currentColor"
+				d="M0,0v100h100V0H0ZM92.5925926,92.5925926H7.4074074V7.4074074h85.1851852v85.1851852ZM61.1111044,71.9096084h9.2592593v7.4074074h-11.6402116l-5.026455-5.026455v-11.6402116h7.4074074v9.2592593ZM77.7777711,71.9096084h-7.4074074v-9.2592593h-9.2592593v-7.4074074h11.6402116l5.026455,5.026455v11.6402116ZM46.2962963,61.1114207h-7.4074074v-7.4074074h7.4074074v7.4074074ZM22.2222222,53.7040133h7.4074074v16.6666667h16.6666667v7.4074074h-19.047619l-5.026455-5.026455v-19.047619ZM77.7777711,38.8888889v7.4074074h-24.0740741v-7.4074074h8.2781918v-9.2592593h-8.2781918v-7.4074074h10.6591442l5.026455,5.026455v11.6402116h8.3884749ZM29.6296296,30.5555556h9.2592593l7.4074074,7.4074074v8.3333333h-7.4074074v-8.3333333h-9.2592593v8.3333333h-7.4074074v-24.0740741h7.4074074v8.3333333ZM46.2962963,30.5555556h-7.4074074v-8.3333333h7.4074074v8.3333333Z"
+			/>
+		</svg>
+	);
+}
+
 export function ProviderIcon({ provider, className = "text-ink-faint", size = 24 }: ProviderIconProps) {
 	const iconProps: Partial<IconProps> = {
 		size,
@@ -101,6 +121,7 @@ export function ProviderIcon({ provider, className = "text-ink-faint", size = 24
 		openai: OpenAI,
 		"openai-chatgpt": OpenAI,
 		openrouter: OpenRouter,
+		kilo: KiloIcon,
 		groq: Groq,
 		mistral: Mistral,
 		gemini: Google,
@@ -112,6 +133,7 @@ export function ProviderIcon({ provider, className = "text-ink-faint", size = 24
 		"zai-coding-plan": ZAI,
 		ollama: OllamaIcon,
 		"opencode-zen": OpenCodeZenIcon,
+		"opencode-go": OpenCodeZenIcon,
 		nvidia: NvidiaIcon,
 		minimax: Minimax,
 		"minimax-cn": Minimax,

interface/src/routes/Settings.tsx

@@ -78,6 +78,14 @@ const PROVIDERS = [
 		envVar: "OPENROUTER_API_KEY",
 		defaultModel: "openrouter/anthropic/claude-sonnet-4",
 	},
+	{
+		id: "kilo",
+		name: "Kilo Gateway",
+		description: "OpenAI-compatible multi-provider gateway",
+		placeholder: "sk-...",
+		envVar: "KILO_API_KEY",
+		defaultModel: "kilo/anthropic/claude-sonnet-4.5",
+	},
 	{
 		id: "opencode-zen",
 		name: "OpenCode Zen",
@@ -86,6 +94,14 @@ const PROVIDERS = [
 		envVar: "OPENCODE_ZEN_API_KEY",
 		defaultModel: "opencode-zen/kimi-k2.5",
 	},
+	{
+		id: "opencode-go",
+		name: "OpenCode Go",
+		description: "Lite OpenCode model catalog and limits",
+		placeholder: "...",
+		envVar: "OPENCODE_GO_API_KEY",
+		defaultModel: "opencode-go/kimi-k2.5",
+	},
 	{
 		id: "anthropic",
 		name: "Anthropic",
@@ -529,9 +545,9 @@ export function Settings() {
 	};
 
 	return (
-		<div className="flex h-full">
+		<div className="flex h-full min-h-0 overflow-hidden">
 			{/* Sidebar */}
-			<div className="flex w-52 flex-shrink-0 flex-col border-r border-app-line/50 bg-app-darkBox/20 overflow-y-auto">
+			<div className="flex min-h-0 w-52 flex-shrink-0 flex-col overflow-y-auto border-r border-app-line/50 bg-app-darkBox/20">
 				<div className="px-3 pb-1 pt-4">
 					<span className="text-tiny font-medium uppercase tracking-wider text-ink-faint">
 						Settings
@@ -551,13 +567,13 @@ export function Settings() {
 			</div>
 
 			{/* Content */}
-			<div className="flex flex-1 flex-col overflow-hidden">
+			<div className="flex min-h-0 flex-1 flex-col overflow-hidden">
 				<header className="flex h-12 items-center border-b border-app-line bg-app-darkBox/50 px-6">
 					<h1 className="font-plex text-sm font-medium text-ink">
 						{SECTIONS.find((s) => s.id === activeSection)?.label}
 					</h1>
 				</header>
-				<div className="flex-1 overflow-y-auto">
+				<div className="min-h-0 flex-1 overflow-y-auto overscroll-contain">
 					{activeSection === "providers" ? (
 						<div className="mx-auto max-w-2xl px-6 py-6">
 							{/* Section header */}

src/api/cron.rs

@@ -221,21 +221,21 @@ fn validate_cron_request(request: &CreateCronRequest) -> Result<(), (StatusCode,
         ));
     }
 
-    if let Some(start) = request.active_start_hour {
-        if start > 23 {
-            return Err((
-                StatusCode::BAD_REQUEST,
-                "active_start_hour must be 0-23".into(),
-            ));
-        }
+    if let Some(start) = request.active_start_hour
+        && start > 23
+    {
+        return Err((
+            StatusCode::BAD_REQUEST,
+            "active_start_hour must be 0-23".into(),
+        ));
     }
-    if let Some(end) = request.active_end_hour {
-        if end > 23 {
-            return Err((
-                StatusCode::BAD_REQUEST,
-                "active_end_hour must be 0-23".into(),
-            ));
-        }
+    if let Some(end) = request.active_end_hour
+        && end > 23
+    {
+        return Err((
+            StatusCode::BAD_REQUEST,
+            "active_end_hour must be 0-23".into(),
+        ));
     }
 
     Ok(())
@@ -248,24 +248,39 @@ pub(super) async fn create_or_update_cron(
 ) -> Result<Json<CronActionResponse>, (StatusCode, Json<CronActionResponse>)> {
     if let Err((status, message)) = validate_cron_request(&request) {
         tracing::warn!(agent_id = %request.agent_id, cron_id = %request.id, %message, "cron validation failed");
-        return Err((status, Json(CronActionResponse {
-            success: false,
-            message,
-        })));
+        return Err((
+            status,
+            Json(CronActionResponse {
+                success: false,
+                message,
+            }),
+        ));
     }
 
     let stores = state.cron_stores.load();
     let schedulers = state.cron_schedulers.load();
 
     let cron_err = |status: StatusCode, message: String| {
-        (status, Json(CronActionResponse { success: false, message }))
+        (
+            status,
+            Json(CronActionResponse {
+                success: false,
+                message,
+            }),
+        )
     };
 
     let store = stores.get(&request.agent_id).ok_or_else(|| {
-        cron_err(StatusCode::NOT_FOUND, format!("agent '{}' not found", request.agent_id))
+        cron_err(
+            StatusCode::NOT_FOUND,
+            format!("agent '{}' not found", request.agent_id),
+        )
     })?;
     let scheduler = schedulers.get(&request.agent_id).ok_or_else(|| {
-        cron_err(StatusCode::NOT_FOUND, format!("agent '{}' not found", request.agent_id))
+        cron_err(
+            StatusCode::NOT_FOUND,
+            format!("agent '{}' not found", request.agent_id),
+        )
     })?;
 
     let active_hours = match (request.active_start_hour, request.active_end_hour) {