feat(ai): add packages/ai provider layer (Chunk #8)

Self-contained SSE-based provider layer for OpenAI-compatible endpoints (Ollama/llama.cpp/LM Studio/vLLM), Anthropic, Gemini, and OpenRouter. - budget.ts: re-export core token-budget engine (countTokens, allocateBudget, DEFAULT_BUDGET) - client.ts: streamCompletion/collectStream/complete with budget enforcement via enforceBudget + measureBudget - discover.ts: auto-detect local providers by probing common /v1/models - adapters.ts: per-provider param mapping + streaming adapters + factory - thinking.ts: thinking/reasoning-param normalization per provider - http.ts: SSE parsing + 429 retry - errors.ts: BudgetExceededError 35 unit/integration tests pass; typecheck and lint clean.
2026-10-28 18:59:54 -05:00
parent 5c28a94813
commit 4c4b83bb68
16 changed files with 1795 additions and 0 deletions
@@ -0,0 +1,81 @@
+import { describe, expect, it } from "vitest";
+
+import { discoverLocalProviders } from "./index.js";
+
+/** Build a mock fetch that returns a models catalog for a given URL. */
+function mockFetch(
+  catalog: Record<string, unknown>,
+): typeof fetch {
+  return ((url: string) => {
+    if (catalog[url]) {
+      return Promise.resolve(
+        new Response(JSON.stringify(catalog[url]), {
+          status: 200,
+          headers: { "content-type": "application/json" },
+        }),
+      );
+    }
+    return Promise.reject(new Error("not found"));
+  }) as unknown as typeof fetch;
+}
+
+describe("discoverLocalProviders", () => {
+  it("detects a running Ollama server", async () => {
+    const results = await discoverLocalProviders({
+      timeoutMs: 200,
+      fetchImpl: mockFetch({
+        "http://localhost:11434/v1/models": {
+          object: "list",
+          data: [
+            { id: "llama3.1", owned_by: "ollama" },
+            { id: "mistral", owned_by: "ollama" },
+          ],
+        },
+      }),
+    });
+
+    expect(results).toHaveLength(1);
+    expect(results[0]!.endpoint).toBe("http://localhost:11434/v1/models");
+    expect(results[0]!.kind).toBe("openai-compatible");
+    expect(results[0]!.models.map((m) => m.id)).toEqual(["llama3.1", "mistral"]);
+  });
+
+  it("returns an empty array when no endpoints respond", async () => {
+    const results = await discoverLocalProviders({
+      timeoutMs: 100,
+      fetchImpl: mockFetch({}),
+    });
+    expect(results).toEqual([]);
+  });
+
+  it("ignores endpoints that return no models", async () => {
+    const results = await discoverLocalProviders({
+      timeoutMs: 200,
+      fetchImpl: mockFetch({
+        "http://localhost:1234/v1/models": { object: "list", data: [] },
+      }),
+    });
+    expect(results).toEqual([]);
+  });
+
+  it("probes multiple endpoints and collects all responders", async () => {
+    const results = await discoverLocalProviders({
+      timeoutMs: 200,
+      fetchImpl: mockFetch({
+        "http://localhost:11434/v1/models": {
+          object: "list",
+          data: [{ id: "llama3.1" }],
+        },
+        "http://localhost:1234/v1/models": {
+          object: "list",
+          data: [{ id: "qwen2.5" }],
+        },
+      }),
+    });
+
+    expect(results).toHaveLength(2);
+    const ids = results.flatMap((r) => r.models.map((m) => m.id));
+    expect(ids).toContain("llama3.1");
+    expect(ids).toContain("qwen2.5");
+  });
+});