feat: add API key and custom provider configuration (#4)

* feat: add API key and custom provider configuration

Previously, model setup only offered OAuth login. This adds:

- API key configuration for 17 built-in providers (OpenAI, Anthropic,
  Google, Mistral, Groq, xAI, OpenRouter, etc.)
- Custom provider setup via models.json (for Ollama, vLLM, LM Studio,
  proxies, or any OpenAI/Anthropic/Google-compatible endpoint)
- Interactive prompts with smart defaults and auto-detection of models
- Verification flow that probes endpoints and provides actionable tips
- Doctor diagnostics for models.json path and missing apiKey warnings
- Dev environment fallback for running without dist/ build artifacts
- Unified auth flow: `feynman model login` now offers both API key
  and OAuth options (OAuth-only when a specific provider is given)

New files:
- src/model/models-json.ts: Read/write models.json with proper merging
- src/model/registry.ts: Centralized ModelRegistry creation with modelsJsonPath
- tests/models-json.test.ts: Unit tests for provider config upsert

* fix: harden runtime env and custom provider auth

---------

Co-authored-by: Advait Paliwal <advaitspaliwal@gmail.com>

src/model/registry.ts

@@ -0,0 +1,12 @@
+import { dirname, resolve } from "node:path";
+
+import { AuthStorage, ModelRegistry } from "@mariozechner/pi-coding-agent";
+
+export function getModelsJsonPath(authPath: string): string {
+	return resolve(dirname(authPath), "models.json");
+}
+
+export function createModelRegistry(authPath: string): ModelRegistry {
+	return new ModelRegistry(AuthStorage.create(authPath), getModelsJsonPath(authPath));
+}
+