feat(agentswarm): optional c0mpute.com inference backend

createC0mputeModel() turns a connected c0mpute.com account (apiKey + OpenAI-
compatible base URL) into a LangChain chat model, usable as the model for
createDeepAgentRunner or the chatModel for the judge/router — so agent inference
can run on community-shared GPUs. Opt-in; default stays the hosted provider.
agentswarm performs no OAuth: the host's c0mpute connector supplies credentials
(resolveC0mputeConnector / c0mputeConnectorFromEnv normalize them). DeepAgent
runner now accepts a model instance, not just a provider string.

7 new tests (defaults, env mapping, not-connected + missing-peer errors); 34/34 pass.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

packages/agentswarm/src/index.ts

@@ -17,6 +17,14 @@ export type {
   SwarmOptions,
   LLMRouterOptions
 } from "./swarm.js";
+export {
+  createC0mputeModel,
+  resolveC0mputeConnector,
+  c0mputeConnectorFromEnv,
+  C0MPUTE_DEFAULT_BASE_URL,
+  C0MPUTE_DEFAULT_MODEL
+} from "./compute.js";
+export type { C0mputeConnector, ResolvedC0mputeConnector } from "./compute.js";
 export { InMemoryBudgetLedger, withBudget } from "./budget.js";
 export type { AgentIdentity, BudgetLedger, BudgetRunnerOptions } from "./budget.js";
 export { createRubricRunner, createLLMJudge } from "./rubric.js";