feat(connectors): add Ollama and LM Studio as a local auth kind

Both servers expose OpenAI-compatible /v1/chat/completions and /v1/models,
so we route them through pi-ai's `openai-completions` API the same way
Fireworks does — but with a per-installation base URL the user enters
during onboarding instead of a hardcoded one. The shared schemas grow a
`local` credential payload carrying just the baseUrl; the credential
resolver surfaces it on `ResolvedCredential.baseUrl`, the runtime bridge
forwards it through `prepareRun`, and the worker plumbs it into
`resolveModel` so the streamed Model<openai-completions> targets the
user's server. The local-cost path short-circuits to zero in cost-writer
since users bill their own hardware, and the live model list is fetched
from the saved baseUrl by `fetchLocalConnectorModels` (Ollama and LM
Studio both speak the standard OpenAI catalog shape). Onboarding ships
a new LocalProviderCard and the Settings panel a LocalForm; both default
to the catalog's per-connector localhost URL and accept any custom URL.

src/main/main-runtime-support.ts

@@ -184,8 +184,18 @@ export function createMainRuntimeSupport(state: MainRuntimeState) {
         // user has selected a company; the onboarding path uses this
         // catalog directly because no company exists yet.
         const { getConnectorDefinition } = await import("./connectors");
-        const { resolveModels } = await import("./model-resolver");
+        const { resolveModels, fetchLocalConnectorModels } = await import("./model-resolver");
         const definition = getConnectorDefinition(connectorId as ConnectorId);
+        if (definition.auth.type === "local") {
+          // Local servers' catalogs depend on the user's installed/loaded
+          // models. Read the saved baseUrl and ask the server directly.
+          const piRuntime = requireServiceGraph().getPiRuntime();
+          const credentials = piRuntime?.credentialStore.read(connectorId);
+          const baseUrl = credentials?.kind === "local" ? credentials.value.baseUrl : null;
+          if (!baseUrl) return [];
+          const models = await fetchLocalConnectorModels(baseUrl);
+          return models.map((m) => ({ id: m.id, label: m.name }));
+        }
         return resolveModels(definition.provider).map((m) => ({ id: m.id, label: m.name }));
       },
       logger: log,