@codilore/llm 1.15.13

package/test/provider/openai-chat.test.ts

@@ -0,0 +1,446 @@
+import { describe, expect } from "bun:test"
+import { Effect, Schema, Stream } from "effect"
+import { HttpClientRequest } from "effect/unstable/http"
+import { LLM, LLMError, Message, Model, ToolCallPart, Usage } from "../../src"
+import * as Azure from "../../src/providers/azure"
+import * as OpenAI from "../../src/providers/openai"
+import * as OpenAIChat from "../../src/protocols/openai-chat"
+import { Auth, LLMClient } from "../../src/route"
+import { it } from "../lib/effect"
+import { dynamicResponse, fixedResponse, truncatedStream } from "../lib/http"
+import { deltaChunk, usageChunk } from "../lib/openai-chunks"
+import { sseEvents } from "../lib/sse"
+
+const TargetJson = Schema.fromJsonString(Schema.Unknown)
+const encodeJson = Schema.encodeSync(TargetJson)
+const decodeJson = Schema.decodeUnknownSync(TargetJson)
+
+const model = OpenAIChat.route
+  .with({ endpoint: { baseURL: "https://api.openai.test/v1/" }, auth: Auth.bearer("test") })
+  .model({ id: "gpt-4o-mini" })
+
+const request = LLM.request({
+  id: "req_1",
+  model,
+  system: "You are concise.",
+  prompt: "Say hello.",
+  generation: { maxTokens: 20, temperature: 0 },
+})
+
+describe("OpenAI Chat route", () => {
+  it.effect("prepares OpenAI Chat payload", () =>
+    Effect.gen(function* () {
+      // Pass the OpenAIChat payload type so `prepared.body` is statically
+      // typed to the route's native shape — the assertions below read field
+      // names without `unknown` casts.
+      const prepared = yield* LLMClient.prepare<OpenAIChat.OpenAIChatBody>(request)
+      const _typed: { readonly model: string; readonly stream: true } = prepared.body
+
+      expect(prepared.body).toEqual({
+        model: "gpt-4o-mini",
+        messages: [
+          { role: "system", content: "You are concise." },
+          { role: "user", content: "Say hello." },
+        ],
+        stream: true,
+        stream_options: { include_usage: true },
+        max_tokens: 20,
+        temperature: 0,
+      })
+    }),
+  )
+
+  it.effect("lowers chronological system updates to escaped user wrappers in order", () =>
+    Effect.gen(function* () {
+      const prepared = yield* LLMClient.prepare<OpenAIChat.OpenAIChatBody>(
+        LLM.request({
+          model,
+          messages: [
+            Message.user("Before."),
+            Message.system("Treat <admin> & data literally."),
+            Message.assistant("After."),
+          ],
+        }),
+      )
+
+      expect(prepared.body.messages).toEqual([
+        {
+          role: "user",
+          content: "Before.\n<system-update>\nTreat &lt;admin&gt; &amp; data literally.\n</system-update>",
+        },
+        { role: "assistant", content: "After." },
+      ])
+    }),
+  )
+
+  it.effect("replays canonical reasoning as OpenAI-compatible reasoning_content", () =>
+    Effect.gen(function* () {
+      const prepared = yield* LLMClient.prepare<OpenAIChat.OpenAIChatBody>(
+        LLM.request({
+          model,
+          messages: [
+            Message.assistant([
+              { type: "reasoning", text: "thinking" },
+              { type: "text", text: "Hello" },
+            ]),
+          ],
+        }),
+      )
+
+      expect(prepared.body.messages).toEqual([{ role: "assistant", content: "Hello", reasoning_content: "thinking" }])
+    }),
+  )
+
+  it.effect("maps OpenAI provider options to Chat options", () =>
+    Effect.gen(function* () {
+      const prepared = yield* LLMClient.prepare<OpenAIChat.OpenAIChatBody>(
+        LLM.request({
+          model: OpenAI.configure({ baseURL: "https://api.openai.test/v1/", apiKey: "test" }).chat("gpt-4o-mini"),
+          prompt: "think",
+          providerOptions: { openai: { reasoningEffort: "low" } },
+        }),
+      )
+
+      expect(prepared.body.store).toBe(false)
+      expect(prepared.body.reasoning_effort).toBe("low")
+    }),
+  )
+
+  it.effect("adds native query params to the Chat Completions URL", () =>
+    LLMClient.generate(
+      LLM.updateRequest(request, {
+        model: Model.update(model, { route: model.route.with({ endpoint: { query: { "api-version": "v1" } } }) }),
+      }),
+    ).pipe(
+      Effect.provide(
+        dynamicResponse((input) =>
+          Effect.gen(function* () {
+            const web = yield* HttpClientRequest.toWeb(input.request).pipe(Effect.orDie)
+            expect(web.url).toBe("https://api.openai.test/v1/chat/completions?api-version=v1")
+            return input.respond(sseEvents(deltaChunk({}, "stop")), {
+              headers: { "content-type": "text/event-stream" },
+            })
+          }),
+        ),
+      ),
+    ),
+  )
+
+  it.effect("uses Azure api-key header for static OpenAI Chat keys", () =>
+    LLMClient.generate(
+      LLM.updateRequest(request, {
+        model: Azure.configure({
+          baseURL: "https://Codilore-test.openai.azure.com/openai/v1/",
+          apiKey: "azure-key",
+          headers: { authorization: "Bearer stale" },
+        }).chat("gpt-4o-mini"),
+      }),
+    ).pipe(
+      Effect.provide(
+        dynamicResponse((input) =>
+          Effect.gen(function* () {
+            const web = yield* HttpClientRequest.toWeb(input.request).pipe(Effect.orDie)
+            expect(web.url).toBe("https://Codilore-test.openai.azure.com/openai/v1/chat/completions?api-version=v1")
+            expect(web.headers.get("api-key")).toBe("azure-key")
+            expect(web.headers.get("authorization")).toBeNull()
+            return input.respond(sseEvents(deltaChunk({}, "stop")), {
+              headers: { "content-type": "text/event-stream" },
+            })
+          }),
+        ),
+      ),
+    ),
+  )
+
+  it.effect("applies serializable HTTP overlays after payload lowering", () =>
+    LLMClient.generate(
+      LLM.updateRequest(request, {
+        model: model.route
+          .with({ auth: Auth.bearer("fresh-key"), headers: { authorization: "Bearer stale" } })
+          .model({ id: model.id }),
+        http: {
+          body: { metadata: { source: "test" } },
+          headers: { authorization: "Bearer request", "x-custom": "yes" },
+          query: { debug: "1" },
+        },
+      }),
+    ).pipe(
+      Effect.provide(
+        dynamicResponse((input) =>
+          Effect.gen(function* () {
+            const web = yield* HttpClientRequest.toWeb(input.request).pipe(Effect.orDie)
+            expect(web.url).toBe("https://api.openai.test/v1/chat/completions?debug=1")
+            expect(web.headers.get("authorization")).toBe("Bearer fresh-key")
+            expect(web.headers.get("x-custom")).toBe("yes")
+            expect(decodeJson(input.text)).toMatchObject({
+              stream: true,
+              stream_options: { include_usage: true },
+              metadata: { source: "test" },
+            })
+            return input.respond(sseEvents(deltaChunk({}, "stop")), {
+              headers: { "content-type": "text/event-stream" },
+            })
+          }),
+        ),
+      ),
+    ),
+  )
+
+  it.effect("prepares assistant tool-call and tool-result messages", () =>
+    Effect.gen(function* () {
+      const prepared = yield* LLMClient.prepare(
+        LLM.request({
+          id: "req_tool_result",
+          model,
+          messages: [
+            Message.user("What is the weather?"),
+            Message.assistant([ToolCallPart.make({ id: "call_1", name: "lookup", input: { query: "weather" } })]),
+            Message.tool({ id: "call_1", name: "lookup", result: { forecast: "sunny" } }),
+          ],
+        }),
+      )
+
+      expect(prepared.body).toEqual({
+        model: "gpt-4o-mini",
+        messages: [
+          { role: "user", content: "What is the weather?" },
+          {
+            role: "assistant",
+            content: null,
+            tool_calls: [
+              {
+                id: "call_1",
+                type: "function",
+                function: { name: "lookup", arguments: encodeJson({ query: "weather" }) },
+              },
+            ],
+          },
+          { role: "tool", tool_call_id: "call_1", content: encodeJson({ forecast: "sunny" }) },
+        ],
+        stream: true,
+        stream_options: { include_usage: true },
+      })
+    }),
+  )
+
+  it.effect("rejects unsupported user media content", () =>
+    Effect.gen(function* () {
+      const error = yield* LLMClient.prepare(
+        LLM.request({
+          id: "req_media",
+          model,
+          messages: [Message.user({ type: "media", mediaType: "image/png", data: "AAECAw==" })],
+        }),
+      ).pipe(Effect.flip)
+
+      expect(error.message).toContain("OpenAI Chat user messages only support text content for now")
+    }),
+  )
+
+  it.effect("lowers reasoning-only assistant history", () =>
+    Effect.gen(function* () {
+      const prepared = yield* LLMClient.prepare<OpenAIChat.OpenAIChatBody>(
+        LLM.request({
+          id: "req_reasoning",
+          model,
+          messages: [Message.assistant({ type: "reasoning", text: "hidden" })],
+        }),
+      )
+
+      expect(prepared.body.messages).toEqual([{ role: "assistant", content: null, reasoning_content: "hidden" }])
+    }),
+  )
+
+  it.effect("parses text and usage stream fixtures", () =>
+    Effect.gen(function* () {
+      const body = sseEvents(
+        deltaChunk({ role: "assistant", content: "Hello" }),
+        deltaChunk({ content: "!" }),
+        deltaChunk({}, "stop"),
+        usageChunk({
+          prompt_tokens: 5,
+          completion_tokens: 2,
+          total_tokens: 7,
+          prompt_tokens_details: { cached_tokens: 1 },
+          completion_tokens_details: { reasoning_tokens: 0 },
+        }),
+      )
+      const response = yield* LLMClient.generate(request).pipe(Effect.provide(fixedResponse(body)))
+      const usage = new Usage({
+        inputTokens: 5,
+        outputTokens: 2,
+        nonCachedInputTokens: 4,
+        cacheReadInputTokens: 1,
+        reasoningTokens: 0,
+        totalTokens: 7,
+        providerMetadata: {
+          openai: {
+            prompt_tokens: 5,
+            completion_tokens: 2,
+            total_tokens: 7,
+            prompt_tokens_details: { cached_tokens: 1 },
+            completion_tokens_details: { reasoning_tokens: 0 },
+          },
+        },
+      })
+
+      expect(response.text).toBe("Hello!")
+      expect(response.events).toEqual([
+        { type: "step-start", index: 0 },
+        { type: "text-start", id: "text-0" },
+        { type: "text-delta", id: "text-0", text: "Hello" },
+        { type: "text-delta", id: "text-0", text: "!" },
+        { type: "text-end", id: "text-0" },
+        { type: "step-finish", index: 0, reason: "stop", usage, providerMetadata: undefined },
+        {
+          type: "finish",
+          reason: "stop",
+          usage,
+        },
+      ])
+    }),
+  )
+
+  it.effect("parses OpenAI-compatible reasoning content deltas", () =>
+    Effect.gen(function* () {
+      const body = sseEvents(
+        { choices: [{ delta: { reasoning_content: "thinking" } }] },
+        { choices: [{ delta: { content: "Hello" } }] },
+        { choices: [{ delta: {}, finish_reason: "stop" }] },
+      )
+
+      const response = yield* LLMClient.generate(request).pipe(Effect.provide(fixedResponse(body)))
+
+      expect(response.reasoning).toBe("thinking")
+      expect(response.text).toBe("Hello")
+      expect(response.events).toMatchObject([
+        { type: "step-start", index: 0 },
+        { type: "reasoning-start", id: "reasoning-0" },
+        { type: "reasoning-delta", id: "reasoning-0", text: "thinking" },
+        { type: "text-start", id: "text-0" },
+        { type: "text-delta", id: "text-0", text: "Hello" },
+        { type: "reasoning-end", id: "reasoning-0" },
+        { type: "text-end", id: "text-0" },
+        { type: "step-finish", index: 0, reason: "stop" },
+        { type: "finish", reason: "stop" },
+      ])
+    }),
+  )
+
+  it.effect("assembles streamed tool call input", () =>
+    Effect.gen(function* () {
+      const body = sseEvents(
+        deltaChunk({
+          role: "assistant",
+          tool_calls: [{ index: 0, id: "call_1", function: { name: "lookup", arguments: '{"query"' } }],
+        }),
+        deltaChunk({ tool_calls: [{ index: 0, function: { arguments: ':"weather"}' } }] }),
+        deltaChunk({}, "tool_calls"),
+      )
+      const response = yield* LLMClient.generate(
+        LLM.updateRequest(request, {
+          tools: [{ name: "lookup", description: "Lookup data", inputSchema: { type: "object" } }],
+        }),
+      ).pipe(Effect.provide(fixedResponse(body)))
+
+      expect(response.events).toEqual([
+        { type: "step-start", index: 0 },
+        { type: "tool-input-start", id: "call_1", name: "lookup", providerMetadata: undefined },
+        { type: "tool-input-delta", id: "call_1", name: "lookup", text: '{"query"' },
+        { type: "tool-input-delta", id: "call_1", name: "lookup", text: ':"weather"}' },
+        { type: "tool-input-end", id: "call_1", name: "lookup", providerMetadata: undefined },
+        {
+          type: "tool-call",
+          id: "call_1",
+          name: "lookup",
+          input: { query: "weather" },
+          providerExecuted: undefined,
+          providerMetadata: undefined,
+        },
+        { type: "step-finish", index: 0, reason: "tool-calls", usage: undefined, providerMetadata: undefined },
+        { type: "finish", reason: "tool-calls", usage: undefined },
+      ])
+    }),
+  )
+
+  it.effect("does not finalize streamed tool calls without a finish reason", () =>
+    Effect.gen(function* () {
+      const body = sseEvents(
+        deltaChunk({
+          role: "assistant",
+          tool_calls: [{ index: 0, id: "call_1", function: { name: "lookup", arguments: '{"query"' } }],
+        }),
+        deltaChunk({ tool_calls: [{ index: 0, function: { arguments: ':"weather"}' } }] }),
+      )
+      const response = yield* LLMClient.generate(
+        LLM.updateRequest(request, {
+          tools: [{ name: "lookup", description: "Lookup data", inputSchema: { type: "object" } }],
+        }),
+      ).pipe(Effect.provide(fixedResponse(body)))
+
+      expect(response.events).toEqual([
+        { type: "step-start", index: 0 },
+        { type: "tool-input-start", id: "call_1", name: "lookup", providerMetadata: undefined },
+        { type: "tool-input-delta", id: "call_1", name: "lookup", text: '{"query"' },
+        { type: "tool-input-delta", id: "call_1", name: "lookup", text: ':"weather"}' },
+      ])
+      expect(response.toolCalls).toEqual([])
+    }),
+  )
+
+  it.effect("fails on malformed stream events", () =>
+    Effect.gen(function* () {
+      const body = sseEvents(deltaChunk({ content: 123 }))
+      const error = yield* LLMClient.generate(request).pipe(Effect.provide(fixedResponse(body)), Effect.flip)
+
+      expect(error.message).toContain("Invalid openai/openai-chat stream event")
+    }),
+  )
+
+  it.effect("surfaces transport errors that occur mid-stream", () =>
+    Effect.gen(function* () {
+      const layer = truncatedStream([
+        `data: ${JSON.stringify(deltaChunk({ role: "assistant", content: "Hello" }))}\n\n`,
+      ])
+      const error = yield* LLMClient.generate(request).pipe(Effect.provide(layer), Effect.flip)
+
+      expect(error.message).toContain("Failed to read openai/openai-chat stream")
+    }),
+  )
+
+  it.effect("fails HTTP provider errors before stream parsing", () =>
+    Effect.gen(function* () {
+      const error = yield* LLMClient.generate(request).pipe(
+        Effect.provide(
+          fixedResponse('{"error":{"message":"Bad request","type":"invalid_request_error"}}', {
+            status: 400,
+            headers: { "content-type": "application/json" },
+          }),
+        ),
+        Effect.flip,
+      )
+
+      expect(error).toBeInstanceOf(LLMError)
+      expect(error.reason).toMatchObject({ _tag: "InvalidRequest" })
+      expect(error.message).toContain("HTTP 400")
+    }),
+  )
+
+  it.effect("short-circuits the upstream stream when the consumer takes a prefix", () =>
+    Effect.gen(function* () {
+      // The body has more chunks than we'll consume. If `Stream.take(1)` did
+      // not interrupt the upstream HTTP body the test would hang waiting for
+      // the rest of the stream to drain.
+      const body = sseEvents(
+        deltaChunk({ role: "assistant", content: "Hello" }),
+        deltaChunk({ content: " world" }),
+        deltaChunk({}, "stop"),
+      )
+
+      const events = Array.from(
+        yield* LLMClient.stream(request).pipe(Stream.take(1), Stream.runCollect, Effect.provide(fixedResponse(body))),
+      )
+      expect(events.map((event) => event.type)).toEqual(["step-start"])
+    }),
+  )
+})

package/test/provider/openai-compatible-chat.test.ts

@@ -0,0 +1,238 @@
+import { describe, expect } from "bun:test"
+import { Effect, Schema } from "effect"
+import { HttpClientRequest } from "effect/unstable/http"
+import { LLM, Message, ToolCallPart } from "../../src"
+import { Auth, LLMClient } from "../../src/route"
+import * as OpenAICompatible from "../../src/providers/openai-compatible"
+import * as OpenAICompatibleChat from "../../src/protocols/openai-compatible-chat"
+import { it } from "../lib/effect"
+import { dynamicResponse } from "../lib/http"
+import { sseEvents } from "../lib/sse"
+
+const Json = Schema.fromJsonString(Schema.Unknown)
+const decodeJson = Schema.decodeUnknownSync(Json)
+
+const model = OpenAICompatibleChat.route
+  .with({
+    provider: "deepseek",
+    endpoint: { baseURL: "https://api.deepseek.test/v1/", query: { "api-version": "2026-01-01" } },
+    auth: Auth.bearer("test-key"),
+  })
+  .model({ id: "deepseek-chat" })
+
+const request = LLM.request({
+  id: "req_1",
+  model,
+  system: "You are concise.",
+  prompt: "Say hello.",
+  generation: { maxTokens: 20, temperature: 0 },
+})
+
+const deltaChunk = (delta: object, finishReason: string | null = null) => ({
+  id: "chatcmpl_fixture",
+  choices: [{ delta, finish_reason: finishReason }],
+  usage: null,
+})
+
+const usageChunk = (usage: object) => ({
+  id: "chatcmpl_fixture",
+  choices: [],
+  usage,
+})
+
+const providerFamilies = [
+  ["baseten", OpenAICompatible.baseten, "https://inference.baseten.co/v1"],
+  ["cerebras", OpenAICompatible.cerebras, "https://api.cerebras.ai/v1"],
+  ["deepinfra", OpenAICompatible.deepinfra, "https://api.deepinfra.com/v1/openai"],
+  ["deepseek", OpenAICompatible.deepseek, "https://api.deepseek.com/v1"],
+  ["fireworks", OpenAICompatible.fireworks, "https://api.fireworks.ai/inference/v1"],
+  ["togetherai", OpenAICompatible.togetherai, "https://api.together.xyz/v1"],
+] as const
+
+describe("OpenAI-compatible Chat route", () => {
+  it.effect("prepares generic Chat target", () =>
+    Effect.gen(function* () {
+      const prepared = yield* LLMClient.prepare(
+        LLM.updateRequest(request, {
+          tools: [{ name: "lookup", description: "Lookup data", inputSchema: { type: "object" } }],
+          toolChoice: { type: "required" },
+        }),
+      )
+
+      expect(prepared.route).toBe("openai-compatible-chat")
+      expect(prepared.model).toMatchObject({
+        id: "deepseek-chat",
+        provider: "deepseek",
+        route: { id: "openai-compatible-chat" },
+      })
+      expect(prepared.model.route.endpoint).toMatchObject({
+        baseURL: "https://api.deepseek.test/v1/",
+        query: { "api-version": "2026-01-01" },
+      })
+      expect(prepared.body).toEqual({
+        model: "deepseek-chat",
+        messages: [
+          { role: "system", content: "You are concise." },
+          { role: "user", content: "Say hello." },
+        ],
+        tools: [
+          {
+            type: "function",
+            function: { name: "lookup", description: "Lookup data", parameters: { type: "object" } },
+          },
+        ],
+        tool_choice: "required",
+        stream: true,
+        stream_options: { include_usage: true },
+        max_tokens: 20,
+        temperature: 0,
+      })
+    }),
+  )
+
+  it.effect("provides model helpers for compatible provider families", () =>
+    Effect.gen(function* () {
+      expect(
+        providerFamilies.map(([provider, family]) => {
+          const model = family.configure({ apiKey: "test-key" }).model(`${provider}-model`)
+          return {
+            id: String(model.id),
+            provider: String(model.provider),
+            route: model.route.id,
+            baseURL: model.route.endpoint.baseURL,
+          }
+        }),
+      ).toEqual(
+        providerFamilies.map(([provider, _, baseURL]) => ({
+          id: `${provider}-model`,
+          provider,
+          route: "openai-compatible-chat",
+          baseURL,
+        })),
+      )
+
+      const custom = OpenAICompatible.deepseek
+        .configure({
+          apiKey: "test-key",
+          baseURL: "https://custom.deepseek.test/v1",
+        })
+        .model("deepseek-chat")
+      expect(custom).toMatchObject({
+        provider: "deepseek",
+        route: { id: "openai-compatible-chat" },
+      })
+      expect(custom.route.endpoint.baseURL).toBe("https://custom.deepseek.test/v1")
+    }),
+  )
+
+  it.effect("matches AI SDK compatible basic request body fixture", () =>
+    Effect.gen(function* () {
+      const prepared = yield* LLMClient.prepare(request)
+
+      expect(prepared.body).toEqual({
+        model: "deepseek-chat",
+        messages: [
+          { role: "system", content: "You are concise." },
+          { role: "user", content: "Say hello." },
+        ],
+        stream: true,
+        stream_options: { include_usage: true },
+        max_tokens: 20,
+        temperature: 0,
+      })
+    }),
+  )
+
+  it.effect("matches AI SDK compatible tool request body fixture", () =>
+    Effect.gen(function* () {
+      const prepared = yield* LLMClient.prepare(
+        LLM.request({
+          id: "req_tool_parity",
+          model,
+          tools: [
+            {
+              name: "lookup",
+              description: "Lookup data",
+              inputSchema: { type: "object", properties: { query: { type: "string" } }, required: ["query"] },
+            },
+          ],
+          toolChoice: "lookup",
+          messages: [
+            Message.user("What is the weather?"),
+            Message.assistant([ToolCallPart.make({ id: "call_1", name: "lookup", input: { query: "weather" } })]),
+            Message.tool({ id: "call_1", name: "lookup", result: { forecast: "sunny" } }),
+          ],
+        }),
+      )
+
+      expect(prepared.body).toEqual({
+        model: "deepseek-chat",
+        messages: [
+          { role: "user", content: "What is the weather?" },
+          {
+            role: "assistant",
+            content: null,
+            tool_calls: [
+              {
+                id: "call_1",
+                type: "function",
+                function: { name: "lookup", arguments: '{"query":"weather"}' },
+              },
+            ],
+          },
+          { role: "tool", tool_call_id: "call_1", content: '{"forecast":"sunny"}' },
+        ],
+        tools: [
+          {
+            type: "function",
+            function: {
+              name: "lookup",
+              description: "Lookup data",
+              parameters: { type: "object", properties: { query: { type: "string" } }, required: ["query"] },
+            },
+          },
+        ],
+        tool_choice: { type: "function", function: { name: "lookup" } },
+        stream: true,
+        stream_options: { include_usage: true },
+      })
+    }),
+  )
+
+  it.effect("posts to the configured compatible endpoint and parses text usage", () =>
+    Effect.gen(function* () {
+      const response = yield* LLMClient.generate(request).pipe(
+        Effect.provide(
+          dynamicResponse((input) =>
+            Effect.gen(function* () {
+              const web = yield* HttpClientRequest.toWeb(input.request).pipe(Effect.orDie)
+              expect(web.url).toBe("https://api.deepseek.test/v1/chat/completions?api-version=2026-01-01")
+              expect(web.headers.get("authorization")).toBe("Bearer test-key")
+              expect(decodeJson(input.text)).toMatchObject({
+                model: "deepseek-chat",
+                stream: true,
+                messages: [
+                  { role: "system", content: "You are concise." },
+                  { role: "user", content: "Say hello." },
+                ],
+              })
+              return input.respond(
+                sseEvents(
+                  deltaChunk({ role: "assistant", content: "Hello" }),
+                  deltaChunk({ content: "!" }),
+                  deltaChunk({}, "stop"),
+                  usageChunk({ prompt_tokens: 5, completion_tokens: 2, total_tokens: 7 }),
+                ),
+                { headers: { "content-type": "text/event-stream" } },
+              )
+            }),
+          ),
+        ),
+      )
+
+      expect(response.text).toBe("Hello!")
+      expect(response.usage).toMatchObject({ inputTokens: 5, outputTokens: 2, totalTokens: 7 })
+      expect(response.events.at(-1)).toMatchObject({ type: "finish", reason: "stop" })
+    }),
+  )
+})