gsd-pi 2.41.0 → 2.42.0-dev.1df898f

package/src/resources/extensions/gsd/tests/custom-workflow-engine.test.ts

@@ -0,0 +1,339 @@
+/**
+ * custom-workflow-engine.test.ts — Tests for CustomWorkflowEngine and CustomExecutionPolicy.
+ *
+ * Uses real temp directories with actual GRAPH.yaml files — no mocks.
+ * Tests the full engine lifecycle: deriveState → resolveDispatch → reconcile.
+ */
+
+import { describe, it, afterEach } from "node:test";
+import assert from "node:assert/strict";
+import { mkdtempSync, rmSync, readFileSync, writeFileSync } from "node:fs";
+import { join } from "node:path";
+import { tmpdir } from "node:os";
+import { parse } from "yaml";
+
+import { CustomWorkflowEngine } from "../custom-workflow-engine.ts";
+import { CustomExecutionPolicy } from "../custom-execution-policy.ts";
+import { writeGraph, readGraph, type WorkflowGraph, type GraphStep } from "../graph.ts";
+import { stringify } from "yaml";
+
+// ─── Helpers ─────────────────────────────────────────────────────────────
+
+const tmpDirs: string[] = [];
+
+function makeTmpDir(): string {
+  const dir = mkdtempSync(join(tmpdir(), "engine-test-"));
+  tmpDirs.push(dir);
+  return dir;
+}
+
+afterEach(() => {
+  for (const d of tmpDirs) {
+    try { rmSync(d, { recursive: true, force: true, maxRetries: 3, retryDelay: 100 }); } catch { /* Windows EPERM */ }
+  }
+  tmpDirs.length = 0;
+});
+
+function makeStep(overrides: Partial<GraphStep> & { id: string }): GraphStep {
+  return {
+    title: overrides.id,
+    status: "pending",
+    prompt: `Do ${overrides.id}`,
+    dependsOn: [],
+    ...overrides,
+  };
+}
+
+function makeGraph(steps: GraphStep[], name = "test-wf"): WorkflowGraph {
+  return {
+    steps,
+    metadata: { name, createdAt: "2026-01-01T00:00:00.000Z" },
+  };
+}
+
+/** Write a graph to a temp dir and return engine + dir. Also writes a minimal DEFINITION.yaml so resolveDispatch/injectContext can read it. */
+function setupEngine(
+  steps: GraphStep[],
+  name = "test-wf",
+): { engine: CustomWorkflowEngine; runDir: string } {
+  const runDir = makeTmpDir();
+  const graph = makeGraph(steps, name);
+  writeGraph(runDir, graph);
+
+  // Write a minimal DEFINITION.yaml matching the graph steps
+  const def = {
+    version: 1,
+    name,
+    steps: steps.map((s) => ({
+      id: s.id,
+      name: s.title,
+      prompt: s.prompt,
+      requires: s.dependsOn,
+      produces: [],
+    })),
+  };
+  writeFileSync(join(runDir, "DEFINITION.yaml"), stringify(def), "utf-8");
+
+  return { engine: new CustomWorkflowEngine(runDir), runDir };
+}
+
+// ─── deriveState ─────────────────────────────────────────────────────────
+
+describe("CustomWorkflowEngine.deriveState", () => {
+  it("returns running phase when steps are pending", async () => {
+    const { engine } = setupEngine([
+      makeStep({ id: "a" }),
+      makeStep({ id: "b", dependsOn: ["a"] }),
+    ]);
+
+    const state = await engine.deriveState("/unused");
+
+    assert.equal(state.phase, "running");
+    assert.equal(state.isComplete, false);
+    assert.ok(state.raw, "raw should contain the graph");
+  });
+
+  it("returns complete phase when all steps are complete", async () => {
+    const { engine } = setupEngine([
+      makeStep({ id: "a", status: "complete" }),
+      makeStep({ id: "b", status: "complete" }),
+    ]);
+
+    const state = await engine.deriveState("/unused");
+
+    assert.equal(state.phase, "complete");
+    assert.equal(state.isComplete, true);
+  });
+
+  it("treats expanded steps as done for completion check", async () => {
+    const { engine } = setupEngine([
+      makeStep({ id: "a", status: "expanded" }),
+      makeStep({ id: "a--001", status: "complete", parentStepId: "a" }),
+      makeStep({ id: "b", status: "complete" }),
+    ]);
+
+    const state = await engine.deriveState("/unused");
+
+    assert.equal(state.phase, "complete");
+    assert.equal(state.isComplete, true);
+  });
+});
+
+// ─── resolveDispatch ─────────────────────────────────────────────────────
+
+describe("CustomWorkflowEngine.resolveDispatch", () => {
+  it("returns dispatch for first pending step", async () => {
+    const { engine } = setupEngine([
+      makeStep({ id: "step-1", prompt: "Do the first thing" }),
+      makeStep({ id: "step-2", dependsOn: ["step-1"] }),
+    ], "my-workflow");
+
+    const state = await engine.deriveState("/unused");
+    const dispatch = await engine.resolveDispatch(state, { basePath: "/unused" });
+
+    assert.equal(dispatch.action, "dispatch");
+    if (dispatch.action === "dispatch") {
+      assert.equal(dispatch.step.unitType, "custom-step");
+      assert.equal(dispatch.step.unitId, "my-workflow/step-1");
+      assert.equal(dispatch.step.prompt, "Do the first thing");
+    }
+  });
+
+  it("returns stop when all steps are complete", async () => {
+    const { engine } = setupEngine([
+      makeStep({ id: "a", status: "complete" }),
+      makeStep({ id: "b", status: "complete" }),
+    ]);
+
+    const state = await engine.deriveState("/unused");
+    const dispatch = await engine.resolveDispatch(state, { basePath: "/unused" });
+
+    assert.equal(dispatch.action, "stop");
+    if (dispatch.action === "stop") {
+      assert.equal(dispatch.reason, "All steps complete");
+      assert.equal(dispatch.level, "info");
+    }
+  });
+
+  it("respects dependency ordering", async () => {
+    const { engine } = setupEngine([
+      makeStep({ id: "a" }),
+      makeStep({ id: "b", dependsOn: ["a"] }),
+      makeStep({ id: "c", dependsOn: ["b"] }),
+    ], "dep-wf");
+
+    const state = await engine.deriveState("/unused");
+    const dispatch = await engine.resolveDispatch(state, { basePath: "/unused" });
+
+    // Should pick "a" (no deps), not "b" or "c"
+    assert.equal(dispatch.action, "dispatch");
+    if (dispatch.action === "dispatch") {
+      assert.equal(dispatch.step.unitId, "dep-wf/a");
+    }
+  });
+
+  it("picks next eligible step when earlier deps are complete", async () => {
+    const { engine } = setupEngine([
+      makeStep({ id: "a", status: "complete" }),
+      makeStep({ id: "b", dependsOn: ["a"] }),
+      makeStep({ id: "c", dependsOn: ["b"] }),
+    ], "dep-wf");
+
+    const state = await engine.deriveState("/unused");
+    const dispatch = await engine.resolveDispatch(state, { basePath: "/unused" });
+
+    // "a" is done, "b" deps met, should pick "b"
+    assert.equal(dispatch.action, "dispatch");
+    if (dispatch.action === "dispatch") {
+      assert.equal(dispatch.step.unitId, "dep-wf/b");
+    }
+  });
+});
+
+// ─── reconcile ───────────────────────────────────────────────────────────
+
+describe("CustomWorkflowEngine.reconcile", () => {
+  it("marks step complete in GRAPH.yaml on disk", async () => {
+    const { engine, runDir } = setupEngine([
+      makeStep({ id: "step-1" }),
+      makeStep({ id: "step-2", dependsOn: ["step-1"] }),
+    ], "wf");
+
+    const state = await engine.deriveState("/unused");
+    const result = await engine.reconcile(state, {
+      unitType: "custom-step",
+      unitId: "wf/step-1",
+      startedAt: Date.now() - 1000,
+      finishedAt: Date.now(),
+    });
+
+    assert.equal(result.outcome, "continue");
+
+    // Verify on-disk state
+    const graph = readGraph(runDir);
+    assert.equal(graph.steps[0].status, "complete");
+    assert.ok(graph.steps[0].finishedAt, "finishedAt should be set");
+    assert.equal(graph.steps[1].status, "pending");
+  });
+
+  it("returns milestone-complete when all steps done", async () => {
+    const { engine } = setupEngine([
+      makeStep({ id: "only-step" }),
+    ], "wf");
+
+    const state = await engine.deriveState("/unused");
+    const result = await engine.reconcile(state, {
+      unitType: "custom-step",
+      unitId: "wf/only-step",
+      startedAt: Date.now() - 1000,
+      finishedAt: Date.now(),
+    });
+
+    assert.equal(result.outcome, "milestone-complete");
+  });
+
+  it("handles multi-segment unitId correctly", async () => {
+    const { engine, runDir } = setupEngine([
+      makeStep({ id: "deep-step" }),
+    ], "nested/workflow");
+
+    const state = await engine.deriveState("/unused");
+    const result = await engine.reconcile(state, {
+      unitType: "custom-step",
+      unitId: "nested/workflow/deep-step",
+      startedAt: Date.now() - 1000,
+      finishedAt: Date.now(),
+    });
+
+    assert.equal(result.outcome, "milestone-complete");
+    const graph = readGraph(runDir);
+    assert.equal(graph.steps[0].status, "complete");
+  });
+});
+
+// ─── getDisplayMetadata ──────────────────────────────────────────────────
+
+describe("CustomWorkflowEngine.getDisplayMetadata", () => {
+  it("returns correct progress summary", async () => {
+    const { engine } = setupEngine([
+      makeStep({ id: "a", status: "complete" }),
+      makeStep({ id: "b" }),
+      makeStep({ id: "c" }),
+    ]);
+
+    const state = await engine.deriveState("/unused");
+    const meta = engine.getDisplayMetadata(state);
+
+    assert.equal(meta.engineLabel, "WORKFLOW");
+    assert.equal(meta.currentPhase, "running");
+    assert.equal(meta.progressSummary, "Step 1/3");
+    assert.deepStrictEqual(meta.stepCount, { completed: 1, total: 3 });
+  });
+
+  it("shows 0/N when no steps complete", async () => {
+    const { engine } = setupEngine([
+      makeStep({ id: "a" }),
+      makeStep({ id: "b" }),
+    ]);
+
+    const state = await engine.deriveState("/unused");
+    const meta = engine.getDisplayMetadata(state);
+
+    assert.equal(meta.progressSummary, "Step 0/2");
+  });
+
+  it("shows N/N when all steps complete", async () => {
+    const { engine } = setupEngine([
+      makeStep({ id: "a", status: "complete" }),
+      makeStep({ id: "b", status: "complete" }),
+    ]);
+
+    const state = await engine.deriveState("/unused");
+    const meta = engine.getDisplayMetadata(state);
+
+    assert.equal(meta.progressSummary, "Step 2/2");
+    assert.equal(meta.currentPhase, "complete");
+  });
+});
+
+// ─── CustomExecutionPolicy ───────────────────────────────────────────────
+
+describe("CustomExecutionPolicy", () => {
+  it("verify returns continue", async () => {
+    // verify() reads DEFINITION.yaml from runDir to find step's verify policy
+    const runDir = makeTmpDir();
+    writeFileSync(join(runDir, "DEFINITION.yaml"), stringify({
+      version: 1, name: "wf", description: "test",
+      steps: [{ id: "step-1", name: "Step 1", prompt: "do it", produces: "step-1/output.md" }],
+    }));
+    const policy = new CustomExecutionPolicy(runDir);
+    const result = await policy.verify("custom-step", "wf/step-1", { basePath: runDir });
+    assert.equal(result, "continue");
+  });
+
+  it("selectModel returns null", async () => {
+    const policy = new CustomExecutionPolicy("/tmp/run");
+    const result = await policy.selectModel("custom-step", "wf/step-1", { basePath: "/tmp" });
+    assert.equal(result, null);
+  });
+
+  it("recover returns retry", async () => {
+    const policy = new CustomExecutionPolicy("/tmp/run");
+    const result = await policy.recover("custom-step", "wf/step-1", { basePath: "/tmp" });
+    assert.deepStrictEqual(result, { outcome: "retry", reason: "Default retry" });
+  });
+
+  it("closeout returns no artifacts", async () => {
+    const policy = new CustomExecutionPolicy("/tmp/run");
+    const result = await policy.closeout("custom-step", "wf/step-1", {
+      basePath: "/tmp",
+      startedAt: Date.now(),
+    });
+    assert.deepStrictEqual(result, { committed: false, artifacts: [] });
+  });
+
+  it("prepareWorkspace resolves without error", async () => {
+    const policy = new CustomExecutionPolicy("/tmp/run");
+    await policy.prepareWorkspace("/tmp", "M001"); // Should not throw
+  });
+});

package/src/resources/extensions/gsd/tests/dashboard-custom-engine.test.ts

@@ -0,0 +1,87 @@
+/**
+ * dashboard-custom-engine.test.ts — Tests that the custom engine path
+ * calls updateProgressWidget and that unitLabel handles "custom-step".
+ *
+ * Uses source-level assertions for the non-exported unitLabel function
+ * and the updateProgressWidget call placement. Tests exported helpers
+ * (unitVerb, unitPhaseLabel) directly.
+ */
+
+import { describe, it } from "node:test";
+import assert from "node:assert/strict";
+import { readFileSync } from "node:fs";
+import { resolve } from "node:path";
+import { fileURLToPath } from "node:url";
+
+import { unitVerb, unitPhaseLabel } from "../auto-dashboard.js";
+
+// ─── Tests ───────────────────────────────────────────────────────────────
+
+describe("Dashboard custom-engine: unitLabel and related helpers", () => {
+  it('unitVerb("custom-step") returns "executing workflow step"', () => {
+    assert.equal(unitVerb("custom-step"), "executing workflow step");
+  });
+
+  it('unitPhaseLabel("custom-step") returns "WORKFLOW"', () => {
+    assert.equal(unitPhaseLabel("custom-step"), "WORKFLOW");
+  });
+
+  it('dashboard-overlay.ts contains a case for "custom-step" returning "Workflow Step"', () => {
+    const __filename = fileURLToPath(import.meta.url);
+    const overlayPath = resolve(__filename, "../../dashboard-overlay.ts");
+    const source = readFileSync(overlayPath, "utf-8");
+    assert.ok(
+      source.includes('"custom-step"') && source.includes('"Workflow Step"'),
+      'dashboard-overlay.ts should contain case "custom-step": return "Workflow Step"',
+    );
+  });
+});
+
+describe("Dashboard custom-engine: updateProgressWidget in custom engine path", () => {
+  it("loop.ts custom engine path includes updateProgressWidget call before runGuards", () => {
+    const __filename = fileURLToPath(import.meta.url);
+    const loopPath = resolve(__filename, "../../auto/loop.ts");
+    const source = readFileSync(loopPath, "utf-8");
+
+    // Find the custom engine block
+    const customEngineStart = source.indexOf('s.activeEngineId !== "dev"');
+    assert.ok(customEngineStart > -1, "Should find custom engine path in loop.ts");
+
+    // The updateProgressWidget call should appear after the custom engine block start
+    // and before the runGuards call in that block
+    const afterCustomEngine = source.slice(customEngineStart);
+    const widgetCallIndex = afterCustomEngine.indexOf(
+      "deps.updateProgressWidget(ctx, iterData.unitType, iterData.unitId, iterData.state)",
+    );
+    const guardsCallIndex = afterCustomEngine.indexOf("runGuards(ic,");
+    assert.ok(widgetCallIndex > -1, "updateProgressWidget should be called in custom engine path");
+    assert.ok(
+      widgetCallIndex < guardsCallIndex,
+      "updateProgressWidget should be called before runGuards in custom engine path",
+    );
+  });
+
+  it("updateProgressWidget call is placed after iterData is built", () => {
+    const __filename = fileURLToPath(import.meta.url);
+    const loopPath = resolve(__filename, "../../auto/loop.ts");
+    const source = readFileSync(loopPath, "utf-8");
+
+    const customEngineStart = source.indexOf('s.activeEngineId !== "dev"');
+    const afterCustomEngine = source.slice(customEngineStart);
+
+    // Verify custom engine path has iterData built before the widget call
+    const iterDataIndex = afterCustomEngine.indexOf("iterData = {");
+    const widgetIndex = afterCustomEngine.indexOf("deps.updateProgressWidget");
+    assert.ok(iterDataIndex > -1 && widgetIndex > -1, "Both iterData and widget call should exist");
+    assert.ok(
+      iterDataIndex < widgetIndex,
+      "iterData should be built before updateProgressWidget is called",
+    );
+
+    // Verify the call uses iterData.state (which holds the derived GSD state)
+    assert.ok(
+      afterCustomEngine.includes("iterData.state"),
+      "Custom engine updateProgressWidget should reference iterData.state",
+    );
+  });
+});

package/src/resources/extensions/gsd/tests/db-writer.test.ts

@@ -59,6 +59,7 @@ const SAMPLE_DECISIONS: Decision[] = [
     choice: 'better-sqlite3',
     rationale: 'Sync API',
     revisable: 'No',
+    made_by: 'collaborative',
     superseded_by: null,
   },
   {
@@ -70,6 +71,7 @@ const SAMPLE_DECISIONS: Decision[] = [
     choice: '.gsd/gsd.db',
     rationale: 'Derived state',
     revisable: 'No',
+    made_by: 'agent',
     superseded_by: null,
   },
   {
@@ -81,6 +83,7 @@ const SAMPLE_DECISIONS: Decision[] = [
     choice: 'node:sqlite fallback',
     rationale: 'Zero deps',
     revisable: 'Yes',
+    made_by: 'human',
     superseded_by: null,
   },
 ];
@@ -166,6 +169,7 @@ console.log('\n── generateDecisionsMd round-trip ──');
     assertEq(rt.choice, orig.choice, `decision ${orig.id} choice round-trips`);
     assertEq(rt.rationale, orig.rationale, `decision ${orig.id} rationale round-trips`);
     assertEq(rt.revisable, orig.revisable, `decision ${orig.id} revisable round-trips`);
+    assertEq(rt.made_by, orig.made_by, `decision ${orig.id} made_by round-trips`);
   }
 }
 
@@ -177,6 +181,7 @@ console.log('\n── generateDecisionsMd format ──');
   assertTrue(md.includes('<!-- Append-only'), 'contains HTML comment block');
   assertTrue(md.includes('| # | When | Scope'), 'contains table header');
   assertTrue(md.includes('|---|------|-------'), 'contains separator row');
+  assertTrue(md.includes('| Made By |'), 'contains Made By column header');
 }
 
 console.log('\n── generateDecisionsMd empty input ──');
@@ -200,6 +205,7 @@ console.log('\n── generateDecisionsMd pipe escaping ──');
     choice: 'A',
     rationale: 'Better',
     revisable: 'No',
+    made_by: 'agent',
     superseded_by: null,
   };
   const md = generateDecisionsMd([withPipe]);
@@ -291,6 +297,7 @@ console.log('\n── nextDecisionId ──');
     choice: 'test choice',
     rationale: 'test',
     revisable: 'No',
+    made_by: 'agent',
     superseded_by: null,
   });
   upsertDecision({
@@ -301,6 +308,7 @@ console.log('\n── nextDecisionId ──');
     choice: 'test choice',
     rationale: 'test',
     revisable: 'No',
+    made_by: 'agent',
     superseded_by: null,
   });
 
@@ -520,6 +528,7 @@ console.log('\n── Full DB round-trip: decisions ──');
       choice: d.choice,
       rationale: d.rationale,
       revisable: d.revisable,
+      made_by: d.made_by,
       superseded_by: d.superseded_by,
     });
   }
@@ -536,6 +545,7 @@ console.log('\n── Full DB round-trip: decisions ──');
     choice: row['choice'] as string,
     rationale: row['rationale'] as string,
     revisable: row['revisable'] as string,
+    made_by: (row['made_by'] as string as import('../types.js').DecisionMadeBy) ?? 'agent',
     superseded_by: (row['superseded_by'] as string) ?? null,
   }));