@asterxsk/kiln 0.1.0

package/agent/extensions/subagents/claude.test.ts

@@ -0,0 +1,119 @@
+import assert from "node:assert/strict";
+import test from "node:test";
+import { Effect } from "effect";
+import { SubagentManager } from "./src/manager.ts";
+import { claudeBackend } from "./src/backends/claude.ts";
+import type { ParentContext, SpawnTask } from "./src/domain.ts";
+import { createSubagentRuntime, runTool } from "./src/runtime.ts";
+
+const parent: ParentContext = {
+  parentCwd: process.cwd(),
+  projectTrusted: false,
+};
+
+function task(prompt: string): SpawnTask {
+  return {
+    prompt,
+    title: "live Claude test",
+    cwd: process.cwd(),
+    model: "haiku",
+    reasoningEffort: "off",
+    parent,
+  };
+}
+
+async function claudeAvailable() {
+  return Effect.runPromise(claudeBackend.available);
+}
+
+/** Rejecting deadline so a hung wait still reaches finally() and disposes. */
+function deadline<A>(operation: Promise<A>, timeoutMs: number) {
+  let timer: ReturnType<typeof setTimeout> | undefined;
+  const timeout = new Promise<never>((_resolve, reject) => {
+    timer = setTimeout(
+      () => reject(new Error(`Live Claude test exceeded ${timeoutMs}ms`)),
+      timeoutMs,
+    );
+  });
+  return Promise.race([operation, timeout]).finally(() => {
+    if (timer) clearTimeout(timer);
+  });
+}
+
+test(
+  "Claude backend completes a live manager run",
+  { timeout: 60_000 },
+  async (t) => {
+    if (!(await claudeAvailable())) {
+      t.skip("Claude Code executable is unavailable");
+      return;
+    }
+
+    const runtime = createSubagentRuntime();
+    try {
+      const manager = await runtime.runPromise(SubagentManager);
+      const started = await runTool(
+        runtime,
+        manager.spawn("claude", task("Reply with exactly: hello claude")),
+      );
+      await deadline(runTool(runtime, manager.waitFor([started.id])), 45_000);
+
+      const done = manager.view.get(started.id);
+      assert.equal(done?.status, "done");
+      assert.match(done?.finalText ?? "", /hello claude/i);
+      assert.ok(done?.meta.nativeSessionId);
+      assert.ok(done?.meta.sessionFilePath?.endsWith(".jsonl"));
+    } finally {
+      await runtime.dispose();
+    }
+  },
+);
+
+test(
+  "Claude backend interrupt settles a live run as aborted",
+  { timeout: 60_000 },
+  async (t) => {
+    if (!(await claudeAvailable())) {
+      t.skip("Claude Code executable is unavailable");
+      return;
+    }
+
+    const runtime = createSubagentRuntime();
+    try {
+      const manager = await runtime.runPromise(SubagentManager);
+      const started = await runTool(
+        runtime,
+        manager.spawn(
+          "claude",
+          task(
+            "Write a detailed 10,000-word essay about the history of computing.",
+          ),
+        ),
+      );
+
+      // Wait for streamed output so cancellation definitely lands mid-run and
+      // exercises the SDK's normal interrupt receipt/result path.
+      const streamDeadline = Date.now() + 15_000;
+      while (
+        manager.view.get(started.id)?.status === "running" &&
+        !manager.view.get(started.id)?.liveAssistant?.text &&
+        Date.now() < streamDeadline
+      ) {
+        await new Promise((resolve) => setTimeout(resolve, 20));
+      }
+      assert.equal(manager.view.get(started.id)?.status, "running");
+      assert.ok(manager.view.get(started.id)?.liveAssistant?.text);
+
+      const report = await deadline(
+        runTool(runtime, manager.cancel([started.id])),
+        20_000,
+      );
+
+      assert.equal(report[0]?.cancelled, true);
+      assert.equal(manager.view.get(started.id)?.status, "error");
+      assert.equal(manager.view.get(started.id)?.errorText, "Run was aborted");
+    } finally {
+      await runtime.dispose();
+    }
+  },
+);

package/agent/extensions/subagents/codex.test.ts

@@ -0,0 +1,102 @@
+import assert from "node:assert/strict";
+import test from "node:test";
+import { Effect } from "effect";
+import { codexBackend } from "./src/backends/codex.ts";
+import type { ParentContext, SpawnTask } from "./src/domain.ts";
+import { SubagentManager } from "./src/manager.ts";
+import { createSubagentRuntime, runTool } from "./src/runtime.ts";
+
+const parent: ParentContext = {
+  parentCwd: process.cwd(),
+  projectTrusted: false,
+};
+
+function task(prompt: string): SpawnTask {
+  return {
+    prompt,
+    title: "live Codex test",
+    cwd: process.cwd(),
+    parent,
+  };
+}
+
+function deadline<A>(operation: Promise<A>, timeoutMs: number) {
+  let timer: ReturnType<typeof setTimeout> | undefined;
+  const timeout = new Promise<never>((_resolve, reject) => {
+    timer = setTimeout(
+      () => reject(new Error(`Live Codex test exceeded ${timeoutMs}ms`)),
+      timeoutMs,
+    );
+  });
+  return Promise.race([operation, timeout]).finally(() => {
+    if (timer) clearTimeout(timer);
+  });
+}
+
+async function codexAvailable() {
+  return Effect.runPromise(codexBackend.available);
+}
+
+test(
+  "Codex backend completes a live manager run",
+  { timeout: 75_000 },
+  async (t) => {
+    if (!(await codexAvailable())) {
+      t.skip("codex executable is unavailable");
+      return;
+    }
+
+    const runtime = createSubagentRuntime();
+    try {
+      const manager = await runtime.runPromise(SubagentManager);
+      const spawned = await runTool(
+        runtime,
+        manager.spawn("codex", task("Reply with exactly: hello codex")),
+      );
+
+      await deadline(runTool(runtime, manager.waitFor([spawned.id])), 60_000);
+      const done = manager.view.get(spawned.id);
+      assert.equal(done?.status, "done");
+      assert.match(done?.finalText ?? "", /hello codex/i);
+      assert.equal(done?.meta.backend, "codex");
+      assert.ok(done?.meta.nativeSessionId);
+      assert.ok(done?.meta.sessionFilePath);
+    } finally {
+      await runtime.dispose();
+    }
+  },
+);
+
+test(
+  "Codex backend interrupt settles a live manager run",
+  { timeout: 30_000 },
+  async (t) => {
+    if (!(await codexAvailable())) {
+      t.skip("codex executable is unavailable");
+      return;
+    }
+
+    const runtime = createSubagentRuntime();
+    try {
+      const manager = await runtime.runPromise(SubagentManager);
+      const spawned = await runTool(
+        runtime,
+        manager.spawn(
+          "codex",
+          task("Run `sleep 30`, then reply with the word finished."),
+        ),
+      );
+
+      await new Promise((resolve) => setTimeout(resolve, 250));
+      const result = await deadline(
+        runTool(runtime, manager.cancel([spawned.id])),
+        10_000,
+      );
+      assert.equal(result[0]?.cancelled, true);
+      assert.equal(manager.view.get(spawned.id)?.status, "error");
+      assert.equal(manager.view.get(spawned.id)?.errorText, "Run was aborted");
+    } finally {
+      await runtime.dispose();
+    }
+  },
+);

package/agent/extensions/subagents/context-usage.test.ts

@@ -0,0 +1,107 @@
+import assert from "node:assert/strict";
+import test from "node:test";
+import { contextOccupancyTokens } from "./src/backends/claude.ts";
+import { parseThreadTokenUsage } from "./src/backends/codex.ts";
+
+// --- Claude: per-request occupancy, never the run aggregate ------------------
+
+test("Claude occupancy sums one request's input, cache, and output tokens", () => {
+  assert.equal(
+    contextOccupancyTokens({
+      input_tokens: 12,
+      cache_read_input_tokens: 45_000,
+      cache_creation_input_tokens: 3_000,
+      output_tokens: 700,
+    }),
+    48_712,
+  );
+});
+
+test("Claude occupancy treats null cache/output counts as zero", () => {
+  assert.equal(
+    contextOccupancyTokens({
+      input_tokens: 9_000,
+      cache_read_input_tokens: null,
+      cache_creation_input_tokens: null,
+      output_tokens: 250,
+    }),
+    9_250,
+  );
+});
+
+test("Claude occupancy is unknown without a usable per-request usage", () => {
+  assert.equal(contextOccupancyTokens(undefined), undefined);
+  assert.equal(contextOccupancyTokens(null), undefined);
+  assert.equal(
+    contextOccupancyTokens({ input_tokens: null, output_tokens: 5 }),
+    undefined,
+  );
+});
+
+test("Claude occupancy from the last request stays below the window where the run aggregate would not", () => {
+  // A 10-request tool loop over a mostly-cached 150k prompt: the aggregate
+  // usage (what SDKResultMessage.usage reports) re-counts the cache per
+  // request and blows past the 200k window; the final request's usage is the
+  // true occupancy.
+  const perRequest = {
+    input_tokens: 500,
+    cache_read_input_tokens: 150_000,
+    cache_creation_input_tokens: 0,
+    output_tokens: 400,
+  };
+  const aggregate = {
+    input_tokens: 500 * 10,
+    cache_read_input_tokens: 150_000 * 10,
+    cache_creation_input_tokens: 0,
+    output_tokens: 400 * 10,
+  };
+  const occupancy = contextOccupancyTokens(perRequest);
+  assert.ok(occupancy !== undefined && occupancy < 200_000);
+  const misleading = contextOccupancyTokens(aggregate);
+  assert.ok(misleading !== undefined && misleading > 200_000);
+});
+
+// --- Codex: last request's total, never the thread-cumulative total ----------
+
+const codexParams = (tokenUsage: unknown) => ({
+  threadId: "t",
+  turnId: "u",
+  tokenUsage,
+});
+
+test("Codex occupancy uses tokenUsage.last.totalTokens, not the cumulative total", () => {
+  const { tokens, contextWindow } = parseThreadTokenUsage(
+    codexParams({
+      total: {
+        totalTokens: 1_450_000,
+        inputTokens: 1_400_000,
+        cachedInputTokens: 1_300_000,
+        outputTokens: 50_000,
+        reasoningOutputTokens: 20_000,
+      },
+      last: {
+        totalTokens: 61_000,
+        inputTokens: 60_000,
+        cachedInputTokens: 55_000,
+        outputTokens: 1_000,
+        reasoningOutputTokens: 400,
+      },
+      modelContextWindow: 272_000,
+    }),
+  );
+  assert.equal(tokens, 61_000);
+  assert.equal(contextWindow, 272_000);
+});
+
+test("Codex occupancy is unknown when last usage or window is absent", () => {
+  assert.deepEqual(
+    parseThreadTokenUsage(
+      codexParams({ total: { totalTokens: 10 }, modelContextWindow: null }),
+    ),
+    { tokens: undefined, contextWindow: undefined },
+  );
+  assert.deepEqual(parseThreadTokenUsage({ threadId: "t" }), {
+    tokens: undefined,
+    contextWindow: undefined,
+  });
+});