feat: add custom/other OpenAI-compatible LLM providers

Allow Settings → Providers to define custom providers (id, name, base URL,
API key, models, headers) without code changes. Persist config via OpenCode
layers, store keys through auth.set, and keep web/VS Code parity.

Co-authored-by: Serhii Dziupin <makeittech@users.noreply.github.com>

packages/web/server/lib/opencode/feature-routes-runtime.js

@@ -18,7 +18,7 @@ import { registerPluginRoutes } from './plugin-routes.js';
 import { getNpmInfo, clearCache as clearNpmCache } from './npm-registry.js';
 import { parseNpmSpec, parsePathSpec, isExactSemver } from './plugin-spec.js';
 import { registerOpenCodeRoutes } from './routes.js';
-import { getProviderSources, removeProviderConfig } from './providers.js';
+import { getProviderSources, removeProviderConfig, upsertProviderConfig } from './providers.js';
 import { getAgentSources, getAgentConfig, createAgent, updateAgent, deleteAgent } from './agents.js';
 import { getCommandSources, createCommand, updateCommand, deleteCommand } from './commands.js';
 import { listMcpConfigs, getMcpConfig, createMcpConfig, updateMcpConfig, deleteMcpConfig } from './mcp.js';
@@ -132,6 +132,7 @@ export const createFeatureRoutesRuntime = (dependencies) => {
       resolveProjectDirectory,
       getProviderSources,
       removeProviderConfig,
+      upsertProviderConfig,
       refreshOpenCodeAfterConfigChange,
       buildOpenCodeUrl,
       getOpenCodeAuthHeaders,