wip

data-pipeline/config/batch.ts

@@ -1 +1,2 @@
-export const BATCH_CONFIG = { size: 4, maxRetries: 3 } as const;
+// Runtime-populated by pipeline.ts after CLI initialization
+export const BATCH_CONFIG = { size: 4, maxRetries: 3 };

data-pipeline/config/llm.ts

@@ -1,5 +1,10 @@
+import type { OnlineProvider } from "./providers.js";
+
+export type LlmProvider = "local" | OnlineProvider;
+
+// Runtime-populated by pipeline.ts after CLI initialization
 export const LLM_CONFIG = {
-  provider: "local" as "local" | "openrouter" | "deepseek" | "gemini",
+  provider: "local" as LlmProvider,
   url: "http://127.0.0.1:8080/v1/chat/completions",
   model: undefined as string | undefined,
-} as const;
+};

data-pipeline/config/providers.ts

@@ -0,0 +1,58 @@
+export type ProviderMeta = {
+  name: string;
+  envVar: string;
+  url: string;
+  requiresKey: boolean;
+  models: string[];
+};
+
+// 1. Explicitly define the literal union
+export type OnlineProvider = "gemini" | "deepseek" | "openrouter" | "groq";
+
+// 2. Use the union to type the Record
+export const ONLINE_PROVIDERS: Record<OnlineProvider, ProviderMeta> = {
+  gemini: {
+    name: "Gemini",
+    envVar: "GEMINI_API_KEY",
+    url: "https://generativelanguage.googleapis.com/v1beta",
+    requiresKey: true,
+    models: ["gemini-2.5-flash", "gemini-2.5-pro"],
+  },
+  deepseek: {
+    name: "DeepSeek",
+    envVar: "DEEPSEEK_API_KEY",
+    url: "https://api.deepseek.com/v1/chat/completions",
+    requiresKey: true,
+    models: ["deepseek-chat", "deepseek-reasoner"],
+  },
+  openrouter: {
+    name: "OpenRouter",
+    envVar: "OPENROUTER_API_KEY",
+    url: "https://openrouter.ai/api/v1/chat/completions",
+    requiresKey: true,
+    models: [
+      "openai/gpt-oss-120b:free",
+      "google/gemma-4-31b-it:free",
+      "qwen/qwen3-next-80b-a3b-instruct:free",
+      "meta-llama/llama-3.3-70b-instruct:free",
+      "anthropic/claude-sonnet-4",
+      "google/gemini-2.5-flash",
+      "deepseek/deepseek-chat-v3",
+    ],
+  },
+  groq: {
+    name: "Groq",
+    envVar: "GROQ_API_KEY",
+    url: "https://api.groq.com/openai/v1/chat/completions",
+    requiresKey: true,
+    models: ["llama-3.3-70b-versatile", "gemma2-9b-it", "mixtral-8x7b-32768"],
+  },
+};
+
+export const LOCAL_PROVIDER: ProviderMeta = {
+  name: "Local (llama.cpp / ollama / lm-studio)",
+  envVar: "",
+  url: "http://127.0.0.1:8080/v1/chat/completions",
+  requiresKey: false,
+  models: [],
+};