@neurocode-ai/llm 1.18.8

package/test/recorded-websocket.ts

@@ -0,0 +1,26 @@
+import { HttpRecorderInternal } from "@neurocode-ai/http-recorder/internal"
+import { Effect, Layer } from "effect"
+import { WebSocketExecutor } from "../src/route"
+import type { Service as WebSocketExecutorService } from "../src/route/transport/websocket"
+
+const liveWebSocket = WebSocketExecutor.open
+
+export const webSocketCassetteLayer = (
+  cassette: string,
+  input: { readonly metadata?: Record<string, unknown>; readonly mode: HttpRecorderInternal.RecordReplayMode },
+): Layer.Layer<WebSocketExecutorService, never, HttpRecorderInternal.Cassette.Service> =>
+  Layer.effect(
+    WebSocketExecutor.Service,
+    Effect.gen(function* () {
+      const cassetteService = yield* HttpRecorderInternal.Cassette.Service
+      const executor = yield* HttpRecorderInternal.makeWebSocketExecutor({
+        name: cassette,
+        mode: input.mode,
+        metadata: input.metadata,
+        cassette: cassetteService,
+        live: { open: liveWebSocket },
+        compareClientMessagesAsJson: true,
+      })
+      return WebSocketExecutor.Service.of(executor)
+    }),
+  )

package/test/response.test.ts

@@ -0,0 +1,98 @@
+import { describe, expect, test } from "bun:test"
+import { LLMEvent, LLMResponse } from "../src"
+
+const reduce = (events: ReadonlyArray<LLMEvent>) => events.reduce(LLMResponse.reduce, LLMResponse.empty())
+const finishEvents = (events: ReadonlyArray<LLMEvent>) => events.filter(LLMEvent.is.finish)
+
+describe("LLMResponse reducer", () => {
+  test("assembles interleaved reasoning and text with end metadata", () => {
+    const events = [
+      LLMEvent.reasoningStart({ id: "r1" }),
+      LLMEvent.reasoningDelta({ id: "r1", text: "I should " }),
+      LLMEvent.textStart({ id: "t1" }),
+      LLMEvent.reasoningDelta({ id: "r1", text: "compare..." }),
+      LLMEvent.reasoningEnd({ id: "r1", providerMetadata: { anthropic: { signature: "sig" } } }),
+      LLMEvent.textDelta({ id: "t1", text: "Answer" }),
+      LLMEvent.textEnd({ id: "t1" }),
+      LLMEvent.finish({ reason: "stop", usage: { outputTokens: 5 } }),
+    ]
+    const response = LLMResponse.fromEvents(events)
+
+    expect(response?.finishReason).toBe("stop")
+    expect(response?.usage).toMatchObject({ outputTokens: 5 })
+    expect(response?.events).toEqual(events)
+    expect(response?.events.map((event) => event.type)).toEqual([
+      "reasoning-start",
+      "reasoning-delta",
+      "text-start",
+      "reasoning-delta",
+      "reasoning-end",
+      "text-delta",
+      "text-end",
+      "finish",
+    ])
+    expect(finishEvents(response?.events ?? [])).toHaveLength(1)
+    expect(response?.message.content).toEqual([
+      {
+        type: "reasoning",
+        text: "I should compare...",
+        providerMetadata: { anthropic: { signature: "sig" } },
+      },
+      { type: "text", text: "Answer" },
+    ])
+  })
+
+  test("preserves partial content without completing a failed stream", () => {
+    const state = reduce([LLMEvent.textStart({ id: "t1" }), LLMEvent.textDelta({ id: "t1", text: "partial" })])
+
+    expect(LLMResponse.complete(state)).toBeUndefined()
+    expect(state.message.content).toEqual([{ type: "text", text: "partial" }])
+  })
+
+  test("does not complete ended content without a terminal finish", () => {
+    const state = reduce([
+      LLMEvent.textStart({ id: "t1" }),
+      LLMEvent.textDelta({ id: "t1", text: "partial" }),
+      LLMEvent.textEnd({ id: "t1" }),
+    ])
+
+    expect(LLMResponse.complete(state)).toBeUndefined()
+    expect(state.message.content).toEqual([{ type: "text", text: "partial" }])
+  })
+
+  test("uses terminal usage when present and keeps prior usage when finish omits it", () => {
+    const withFinishUsage = LLMResponse.fromEvents([
+      LLMEvent.stepFinish({ index: 0, reason: "stop", usage: { inputTokens: 3 } }),
+      LLMEvent.finish({ reason: "stop", usage: { outputTokens: 2 } }),
+    ])
+    const withoutFinishUsage = LLMResponse.fromEvents([
+      LLMEvent.stepFinish({ index: 0, reason: "stop", usage: { inputTokens: 3 } }),
+      LLMEvent.finish({ reason: "stop" }),
+    ])
+
+    expect(withFinishUsage?.usage).toMatchObject({ outputTokens: 2 })
+    expect(withoutFinishUsage?.usage).toMatchObject({ inputTokens: 3 })
+  })
+
+  test("assembles tool-call content only after the completed tool call event", () => {
+    const pending = reduce([
+      LLMEvent.toolInputStart({ id: "call_1", name: "lookup" }),
+      LLMEvent.toolInputDelta({ id: "call_1", name: "lookup", text: '{"query"' }),
+    ])
+
+    expect(pending.message.content).toEqual([])
+    expect(pending.toolInputs.call_1?.text).toBe('{"query"')
+
+    const response = LLMResponse.fromEvents([
+      ...pending.events,
+      LLMEvent.toolInputDelta({ id: "call_1", name: "lookup", text: ':"weather"}' }),
+      LLMEvent.toolInputEnd({ id: "call_1", name: "lookup" }),
+      LLMEvent.toolCall({ id: "call_1", name: "lookup", input: { query: "weather" } }),
+      LLMEvent.finish({ reason: "tool-calls" }),
+    ])
+
+    expect(response?.message.content).toEqual([
+      { type: "tool-call", id: "call_1", name: "lookup", input: { query: "weather" } },
+    ])
+  })
+})

package/test/route.test.ts

@@ -0,0 +1,43 @@
+import { describe, expect, test } from "bun:test"
+import * as OpenAIChat from "../src/protocols/openai-chat"
+import { Auth } from "../src/route"
+
+describe("Route.with", () => {
+  test("merges endpoint query and header defaults while replacing auth and id", () => {
+    const auth = Auth.headers({ "x-auth": "new" })
+    const route = OpenAIChat.route
+      .with({
+        id: "base-chat",
+        endpoint: {
+          baseURL: "https://api.example.test/v1",
+          query: { keep: "base", base: "1" },
+        },
+        headers: { "x-base": "base", "x-override": "base" },
+        auth: Auth.headers({ "x-auth": "old" }),
+      })
+      .with({
+        id: "patched-chat",
+        endpoint: { query: { keep: "patch", patch: "1" } },
+        headers: { "x-override": "patch", "x-patch": "patch" },
+        auth,
+      })
+
+    expect(route.id).toBe("patched-chat")
+    expect(route.auth).toBe(auth)
+    expect(route.endpoint).toMatchObject({
+      baseURL: "https://api.example.test/v1",
+      path: "/chat/completions",
+      query: { keep: "patch", base: "1", patch: "1" },
+    })
+    expect(route.defaults.headers).toEqual({
+      "x-base": "base",
+      "x-override": "patch",
+      "x-patch": "patch",
+    })
+    expect(route.defaults.http?.headers).toEqual({
+      "x-base": "base",
+      "x-override": "patch",
+      "x-patch": "patch",
+    })
+  })
+})

package/test/schema.test.ts

@@ -0,0 +1,86 @@
+import { describe, expect, test } from "bun:test"
+import { Schema } from "effect"
+import * as OpenAIChat from "../src/protocols/openai-chat"
+import * as OpenAIResponses from "../src/protocols/openai-responses"
+import { ContentPart, LLMEvent, LLMRequest, Model, ModelID, ProviderID, Usage } from "../src/schema"
+import { ProviderShared } from "../src/protocols/shared"
+
+const model = new Model({
+  id: ModelID.make("fake-model"),
+  provider: ProviderID.make("fake-provider"),
+  route: OpenAIChat.route,
+})
+
+const decodeLLMRequest = Schema.decodeUnknownSync(LLMRequest as unknown as Schema.Decoder<LLMRequest>)
+const decodeLLMEvent = Schema.decodeUnknownSync(LLMEvent as unknown as Schema.Decoder<LLMEvent>)
+
+describe("llm schema", () => {
+  test("decodes a minimal request", () => {
+    const input: unknown = {
+      id: "req_1",
+      model,
+      system: [{ type: "text", text: "You are terse." }],
+      messages: [{ role: "user", content: [{ type: "text", text: "hi" }] }],
+      tools: [],
+      generation: {},
+    }
+
+    const decoded = decodeLLMRequest(input)
+
+    expect(decoded.id).toBe("req_1")
+    expect(decoded.messages[0]?.content[0]?.type).toBe("text")
+  })
+
+  test("accepts custom route ids", () => {
+    const decoded = decodeLLMRequest({
+      model: Model.update(model, { route: OpenAIResponses.route }),
+      system: [],
+      messages: [],
+      tools: [],
+      generation: {},
+    })
+
+    expect(decoded.model.route.id).toBe("openai-responses")
+  })
+
+  test("rejects invalid event type", () => {
+    expect(() => decodeLLMEvent({ type: "bogus" })).toThrow()
+  })
+
+  test("finish constructors accept usage input", () => {
+    expect(LLMEvent.stepFinish({ index: 0, reason: "stop", usage: { inputTokens: 1 } }).usage).toBeInstanceOf(Usage)
+    expect(LLMEvent.finish({ reason: "stop", usage: { outputTokens: 2 } }).usage).toBeInstanceOf(Usage)
+  })
+
+  test("content part tagged union exposes guards", () => {
+    expect(ContentPart.guards.text({ type: "text", text: "hi" })).toBe(true)
+    expect(ContentPart.guards.media({ type: "text", text: "hi" })).toBe(false)
+  })
+})
+
+describe("LLM.Usage", () => {
+  test("subtractTokens clamps non-sensical breakdowns to zero", () => {
+    // Defense against a provider reporting cached_tokens > prompt_tokens or
+    // reasoning_tokens > completion_tokens — the negative would otherwise
+    // round-trip through the pipeline and crash strict downstream schemas.
+    expect(ProviderShared.subtractTokens(5, 3)).toBe(2)
+    expect(ProviderShared.subtractTokens(5, 10)).toBe(0)
+    expect(ProviderShared.subtractTokens(5, undefined)).toBe(5)
+    expect(ProviderShared.subtractTokens(undefined, 3)).toBeUndefined()
+    expect(ProviderShared.subtractTokens(undefined, undefined)).toBeUndefined()
+  })
+
+  test("sumTokens returns undefined only when every input is undefined", () => {
+    expect(ProviderShared.sumTokens(1, 2, 3)).toBe(6)
+    expect(ProviderShared.sumTokens(1, undefined, 3)).toBe(4)
+    expect(ProviderShared.sumTokens(undefined, undefined, undefined)).toBeUndefined()
+    expect(ProviderShared.sumTokens()).toBeUndefined()
+  })
+
+  test("visibleOutputTokens clamps reasoning > output to zero", () => {
+    expect(new Usage({ outputTokens: 10, reasoningTokens: 4 }).visibleOutputTokens).toBe(6)
+    expect(new Usage({ outputTokens: 10 }).visibleOutputTokens).toBe(10)
+    expect(new Usage({ outputTokens: 4, reasoningTokens: 10 }).visibleOutputTokens).toBe(0)
+    expect(new Usage({}).visibleOutputTokens).toBe(0)
+  })
+})