lsd-pi 1.0.0 → 1.1.0

package/src/resources/extensions/gsd/tests/prompt-cache-optimizer.test.ts

@@ -1,314 +0,0 @@
-/**
- * Unit tests for prompt-cache-optimizer.ts — cache-aware prompt reordering.
- */
-
-import { describe, it } from "node:test";
-import assert from "node:assert/strict";
-
-import {
-  type ContentRole,
-  type PromptSection,
-  classifySection,
-  section,
-  optimizeForCaching,
-  estimateCacheSavings,
-  computeCacheHitRate,
-} from "../prompt-cache-optimizer.js";
-
-// ─── classifySection ─────────────────────────────────────────────────────────
-
-describe("prompt-cache-optimizer: classifySection", () => {
-  it("classifies system-prompt as static", () => {
-    assert.equal(classifySection("system-prompt"), "static");
-  });
-
-  it("classifies base-instructions as static", () => {
-    assert.equal(classifySection("base-instructions"), "static");
-  });
-
-  it("classifies executor-constraints as static", () => {
-    assert.equal(classifySection("executor-constraints"), "static");
-  });
-
-  it("classifies template-* prefixed labels as static", () => {
-    assert.equal(classifySection("template-code"), "static");
-    assert.equal(classifySection("template-review"), "static");
-    assert.equal(classifySection("template-"), "static");
-  });
-
-  it("classifies slice-plan as semi-static", () => {
-    assert.equal(classifySection("slice-plan"), "semi-static");
-  });
-
-  it("classifies decisions as semi-static", () => {
-    assert.equal(classifySection("decisions"), "semi-static");
-  });
-
-  it("classifies requirements as semi-static", () => {
-    assert.equal(classifySection("requirements"), "semi-static");
-  });
-
-  it("classifies roadmap as semi-static", () => {
-    assert.equal(classifySection("roadmap"), "semi-static");
-  });
-
-  it("classifies prior-summaries as semi-static", () => {
-    assert.equal(classifySection("prior-summaries"), "semi-static");
-  });
-
-  it("classifies project-context as semi-static", () => {
-    assert.equal(classifySection("project-context"), "semi-static");
-  });
-
-  it("classifies overrides as semi-static", () => {
-    assert.equal(classifySection("overrides"), "semi-static");
-  });
-
-  it("classifies task-plan as dynamic", () => {
-    assert.equal(classifySection("task-plan"), "dynamic");
-  });
-
-  it("classifies task-instructions as dynamic", () => {
-    assert.equal(classifySection("task-instructions"), "dynamic");
-  });
-
-  it("classifies task-context as dynamic", () => {
-    assert.equal(classifySection("task-context"), "dynamic");
-  });
-
-  it("classifies file-contents as dynamic", () => {
-    assert.equal(classifySection("file-contents"), "dynamic");
-  });
-
-  it("classifies diff-context as dynamic", () => {
-    assert.equal(classifySection("diff-context"), "dynamic");
-  });
-
-  it("classifies verification-commands as dynamic", () => {
-    assert.equal(classifySection("verification-commands"), "dynamic");
-  });
-
-  it("defaults unknown labels to dynamic", () => {
-    assert.equal(classifySection("something-unknown"), "dynamic");
-    assert.equal(classifySection(""), "dynamic");
-    assert.equal(classifySection("random-label"), "dynamic");
-  });
-});
-
-// ─── section() helper ────────────────────────────────────────────────────────
-
-describe("prompt-cache-optimizer: section()", () => {
-  it("auto-classifies based on label", () => {
-    const s = section("system-prompt", "You are an assistant.");
-    assert.equal(s.label, "system-prompt");
-    assert.equal(s.content, "You are an assistant.");
-    assert.equal(s.role, "static");
-  });
-
-  it("auto-classifies semi-static labels", () => {
-    const s = section("slice-plan", "Plan content here.");
-    assert.equal(s.role, "semi-static");
-  });
-
-  it("auto-classifies dynamic labels", () => {
-    const s = section("task-instructions", "Do this task.");
-    assert.equal(s.role, "dynamic");
-  });
-
-  it("allows manual role override", () => {
-    const s = section("unknown-label", "content", "static");
-    assert.equal(s.role, "static");
-  });
-
-  it("override takes precedence over auto-classification", () => {
-    const s = section("system-prompt", "content", "dynamic");
-    assert.equal(s.role, "dynamic");
-  });
-});
-
-// ─── optimizeForCaching ──────────────────────────────────────────────────────
-
-describe("prompt-cache-optimizer: optimizeForCaching", () => {
-  it("orders static before semi-static before dynamic", () => {
-    const sections: PromptSection[] = [
-      { label: "task", content: "DYNAMIC", role: "dynamic" },
-      { label: "plan", content: "SEMI", role: "semi-static" },
-      { label: "sys", content: "STATIC", role: "static" },
-    ];
-
-    const result = optimizeForCaching(sections);
-    const parts = result.prompt.split("\n\n");
-    assert.equal(parts[0], "STATIC");
-    assert.equal(parts[1], "SEMI");
-    assert.equal(parts[2], "DYNAMIC");
-  });
-
-  it("preserves relative order within the same role group", () => {
-    const sections: PromptSection[] = [
-      { label: "d1", content: "D-first", role: "dynamic" },
-      { label: "d2", content: "D-second", role: "dynamic" },
-      { label: "s1", content: "S-first", role: "static" },
-      { label: "s2", content: "S-second", role: "static" },
-    ];
-
-    const result = optimizeForCaching(sections);
-    const parts = result.prompt.split("\n\n");
-    assert.equal(parts[0], "S-first");
-    assert.equal(parts[1], "S-second");
-    assert.equal(parts[2], "D-first");
-    assert.equal(parts[3], "D-second");
-  });
-
-  it("calculates cacheEfficiency correctly", () => {
-    const sections: PromptSection[] = [
-      { label: "sys", content: "AAAA", role: "static" },     // 4 chars
-      { label: "plan", content: "BBBB", role: "semi-static" }, // 4 chars
-      { label: "task", content: "CCCC", role: "dynamic" },    // 4 chars
-    ];
-
-    const result = optimizeForCaching(sections);
-    // Cacheable prefix = "AAAA" + "\n\n" + "BBBB" = 10 chars
-    // Total = "AAAA\n\nBBBB\n\nCCCC" = 16 chars
-    assert.equal(result.cacheablePrefixChars, 10);
-    assert.equal(result.totalChars, 16);
-    assert.ok(Math.abs(result.cacheEfficiency - 10 / 16) < 0.001);
-  });
-
-  it("returns correct section counts", () => {
-    const sections: PromptSection[] = [
-      { label: "a", content: "x", role: "static" },
-      { label: "b", content: "y", role: "static" },
-      { label: "c", content: "z", role: "semi-static" },
-      { label: "d", content: "w", role: "dynamic" },
-    ];
-
-    const result = optimizeForCaching(sections);
-    assert.deepEqual(result.sectionCounts, {
-      static: 2,
-      "semi-static": 1,
-      dynamic: 1,
-    });
-  });
-
-  it("handles empty sections array", () => {
-    const result = optimizeForCaching([]);
-    assert.equal(result.prompt, "");
-    assert.equal(result.cacheablePrefixChars, 0);
-    assert.equal(result.totalChars, 0);
-    assert.equal(result.cacheEfficiency, 0);
-    assert.deepEqual(result.sectionCounts, {
-      static: 0,
-      "semi-static": 0,
-      dynamic: 0,
-    });
-  });
-
-  it("handles only static sections (100% cacheable)", () => {
-    const sections: PromptSection[] = [
-      { label: "sys", content: "Hello", role: "static" },
-    ];
-
-    const result = optimizeForCaching(sections);
-    assert.equal(result.cacheEfficiency, 1);
-    assert.equal(result.cacheablePrefixChars, result.totalChars);
-  });
-
-  it("handles only dynamic sections (0% cacheable)", () => {
-    const sections: PromptSection[] = [
-      { label: "task", content: "Do something", role: "dynamic" },
-    ];
-
-    const result = optimizeForCaching(sections);
-    assert.equal(result.cacheablePrefixChars, 0);
-    assert.equal(result.cacheEfficiency, 0);
-  });
-});
-
-// ─── estimateCacheSavings ────────────────────────────────────────────────────
-
-describe("prompt-cache-optimizer: estimateCacheSavings", () => {
-  it("returns 90% of cache efficiency for anthropic", () => {
-    const result = optimizeForCaching([
-      { label: "sys", content: "AAAA", role: "static" },
-      { label: "task", content: "CCCC", role: "dynamic" },
-    ]);
-    // cacheEfficiency = 4 / 10 = 0.4
-    const savings = estimateCacheSavings(result, "anthropic");
-    assert.ok(Math.abs(savings - result.cacheEfficiency * 0.9) < 0.001);
-  });
-
-  it("returns 50% of cache efficiency for openai", () => {
-    const result = optimizeForCaching([
-      { label: "sys", content: "AAAA", role: "static" },
-      { label: "task", content: "CCCC", role: "dynamic" },
-    ]);
-    const savings = estimateCacheSavings(result, "openai");
-    assert.ok(Math.abs(savings - result.cacheEfficiency * 0.5) < 0.001);
-  });
-
-  it("returns 0 for other providers", () => {
-    const result = optimizeForCaching([
-      { label: "sys", content: "AAAA", role: "static" },
-    ]);
-    assert.equal(estimateCacheSavings(result, "other"), 0);
-  });
-
-  it("returns 0 when cache efficiency is 0", () => {
-    const result = optimizeForCaching([
-      { label: "task", content: "CCCC", role: "dynamic" },
-    ]);
-    assert.equal(estimateCacheSavings(result, "anthropic"), 0);
-    assert.equal(estimateCacheSavings(result, "openai"), 0);
-  });
-});
-
-// ─── computeCacheHitRate ─────────────────────────────────────────────────────
-
-describe("prompt-cache-optimizer: computeCacheHitRate", () => {
-  it("computes hit rate as percentage", () => {
-    const rate = computeCacheHitRate({
-      cacheRead: 800,
-      cacheWrite: 200,
-      input: 200,
-    });
-    // 800 / (800 + 200) * 100 = 80%
-    assert.equal(rate, 80);
-  });
-
-  it("returns 0 when no cache activity", () => {
-    const rate = computeCacheHitRate({
-      cacheRead: 0,
-      cacheWrite: 0,
-      input: 0,
-    });
-    assert.equal(rate, 0);
-  });
-
-  it("returns 100 when everything is from cache", () => {
-    const rate = computeCacheHitRate({
-      cacheRead: 1000,
-      cacheWrite: 0,
-      input: 0,
-    });
-    assert.equal(rate, 100);
-  });
-
-  it("returns 0 when nothing is from cache", () => {
-    const rate = computeCacheHitRate({
-      cacheRead: 0,
-      cacheWrite: 500,
-      input: 1000,
-    });
-    assert.equal(rate, 0);
-  });
-
-  it("ignores cacheWrite in hit rate calculation", () => {
-    const rate = computeCacheHitRate({
-      cacheRead: 500,
-      cacheWrite: 9999,
-      input: 500,
-    });
-    // 500 / (500 + 500) * 100 = 50%
-    assert.equal(rate, 50);
-  });
-});

package/src/resources/extensions/gsd/tests/prompt-contracts.test.ts

@@ -1,239 +0,0 @@
-import test from "node:test";
-import assert from "node:assert/strict";
-import { readFileSync } from "node:fs";
-import { join } from "node:path";
-
-const promptsDir = join(process.cwd(), "src/resources/extensions/gsd/prompts");
-
-function readPrompt(name: string): string {
-  return readFileSync(join(promptsDir, `${name}.md`), "utf-8");
-}
-
-test("reactive-execute prompt keeps task summaries with subagents and avoids batch commits", () => {
-  const prompt = readPrompt("reactive-execute");
-  assert.match(prompt, /subagent-written summary as authoritative/i);
-  assert.match(prompt, /Do NOT create a batch commit/i);
-  assert.doesNotMatch(prompt, /\*\*Write task summaries\*\*/i);
-  assert.doesNotMatch(prompt, /\*\*Commit\*\* all changes/i);
-});
-
-test("run-uat prompt branches on dynamic UAT mode and supports runtime evidence", () => {
-  const prompt = readPrompt("run-uat");
-  assert.match(prompt, /\*\*Detected UAT mode:\*\*\s*`\{\{uatType\}\}`/);
-  assert.match(prompt, /uatType:\s*\{\{uatType\}\}/);
-  assert.match(prompt, /live-runtime/);
-  assert.match(prompt, /browser\/runtime\/network/i);
-  assert.match(prompt, /NEEDS-HUMAN/);
-  assert.doesNotMatch(prompt, /uatType:\s*artifact-driven/);
-});
-
-test("workflow-start prompt defaults to autonomy instead of per-phase confirmation", () => {
-  const prompt = readPrompt("workflow-start");
-  assert.match(prompt, /Keep moving by default/i);
-  assert.match(prompt, /Decision gates, not ceremony/i);
-  assert.doesNotMatch(prompt, /confirm with the user before proceeding/i);
-  assert.doesNotMatch(prompt, /Gate between phases/i);
-});
-
-test("discuss prompt allows implementation questions when they materially matter", () => {
-  const prompt = readPrompt("discuss");
-  assert.match(prompt, /Lead with experience, but ask implementation when it materially matters/i);
-  assert.match(prompt, /one gate, not two/i);
-  assert.doesNotMatch(prompt, /Questions must be about the experience, not the implementation/i);
-});
-
-test("guided discussion prompts avoid wrap-up prompts after every round", () => {
-  const milestonePrompt = readPrompt("guided-discuss-milestone");
-  const slicePrompt = readPrompt("guided-discuss-slice");
-  assert.match(milestonePrompt, /Do \*\*not\*\* ask a meta "ready to wrap up\?" question after every round/i);
-  assert.match(slicePrompt, /Do \*\*not\*\* ask a meta "ready to wrap up\?" question after every round/i);
-  assert.doesNotMatch(milestonePrompt, /I think I have a solid picture of this milestone\. Ready to wrap up/i);
-  assert.doesNotMatch(slicePrompt, /I think I have a solid picture of this slice\. Ready to wrap up/i);
-});
-
-test("guided-resume-task prompt preserves recovery state until work is superseded", () => {
-  const prompt = readPrompt("guided-resume-task");
-  assert.match(prompt, /Do \*\*not\*\* delete the continue file immediately/i);
-  assert.match(prompt, /successfully completed or you have written a newer summary\/continue artifact/i);
-  assert.doesNotMatch(prompt, /Delete the continue file after reading it/i);
-});
-
-// ─── Prompt migration: execute-task → gsd_complete_task ───────────────
-
-test("execute-task prompt references gsd_complete_task tool", () => {
-  const prompt = readPrompt("execute-task");
-  assert.match(prompt, /gsd_complete_task/);
-});
-
-test("execute-task prompt instructs writing task summary before tool call", () => {
-  const prompt = readPrompt("execute-task");
-  // The prompt instructs writing the summary file AND calling the tool
-  assert.match(prompt, /\{\{taskSummaryPath\}\}/);
-  assert.match(prompt, /gsd_complete_task/);
-});
-
-test("execute-task prompt does not instruct LLM to toggle checkboxes manually", () => {
-  const prompt = readPrompt("execute-task");
-  assert.doesNotMatch(prompt, /change \[ \] to \[x\]/);
-  assert.doesNotMatch(prompt, /Mark \{\{taskId\}\} done in/);
-});
-
-test("execute-task prompt still contains template variables for context", () => {
-  const prompt = readPrompt("execute-task");
-  assert.match(prompt, /\{\{taskSummaryPath\}\}/);
-  assert.match(prompt, /\{\{planPath\}\}/);
-});
-
-test("guided-execute-task prompt references gsd_task_complete tool", () => {
-  const prompt = readPrompt("guided-execute-task");
-  assert.match(prompt, /gsd_task_complete/);
-});
-
-test("guided-execute-task prompt does not instruct manual file write", () => {
-  const prompt = readPrompt("guided-execute-task");
-  assert.doesNotMatch(prompt, /Write `?\{\{taskId\}\}-SUMMARY\.md`?.*mark it done/i);
-});
-
-// ─── Prompt migration: complete-slice → gsd_complete_slice ────────────
-
-test("complete-slice prompt references gsd_complete_slice tool", () => {
-  const prompt = readPrompt("complete-slice");
-  assert.match(prompt, /gsd_complete_slice/);
-});
-
-test("complete-slice prompt does not instruct LLM to toggle checkboxes manually", () => {
-  const prompt = readPrompt("complete-slice");
-  assert.doesNotMatch(prompt, /change \[ \] to \[x\]/);
-});
-
-test("guided-complete-slice prompt references gsd_slice_complete tool", () => {
-  const prompt = readPrompt("guided-complete-slice");
-  assert.match(prompt, /gsd_slice_complete/);
-});
-
-test("complete-slice prompt instructs writing summary and UAT files before tool call", () => {
-  const prompt = readPrompt("complete-slice");
-  // The prompt instructs writing the summary AND UAT files, then calling the tool
-  assert.match(prompt, /\{\{sliceSummaryPath\}\}/);
-  assert.match(prompt, /\{\{sliceUatPath\}\}/);
-  assert.match(prompt, /gsd_complete_slice/);
-});
-
-test("complete-slice prompt preserves decisions and knowledge review steps", () => {
-  const prompt = readPrompt("complete-slice");
-  assert.match(prompt, /DECISIONS\.md/);
-  assert.match(prompt, /KNOWLEDGE\.md/);
-});
-
-test("complete-slice prompt still contains template variables for context", () => {
-  const prompt = readPrompt("complete-slice");
-  assert.match(prompt, /\{\{sliceSummaryPath\}\}/);
-  assert.match(prompt, /\{\{sliceUatPath\}\}/);
-});
-
-test("plan-milestone prompt references DB-backed planning tool and explicitly forbids manual roadmap writes", () => {
-  const prompt = readPrompt("plan-milestone");
-  assert.match(prompt, /gsd_plan_milestone/);
-  assert.match(prompt, /Do \*\*not\*\* write `?\{\{outputPath\}\}`?, `?ROADMAP\.md`?, or other planning artifacts manually/i);
-});
-
-test("guided-plan-milestone prompt references DB-backed planning tool and explicitly forbids manual roadmap writes", () => {
-  const prompt = readPrompt("guided-plan-milestone");
-  assert.match(prompt, /gsd_plan_milestone/);
-  assert.match(prompt, /Do \*\*not\*\* write `?\{\{milestoneId\}\}-ROADMAP\.md`?, `?ROADMAP\.md`?, or other planning artifacts manually/i);
-});
-
-test("plan-slice prompt no longer frames direct PLAN writes as the source of truth", () => {
-  const prompt = readPrompt("plan-slice");
-  assert.match(prompt, /Do \*\*not\*\* rely on direct `PLAN\.md` writes as the source of truth/i);
-});
-
-test("plan-slice prompt explicitly names gsd_plan_slice as DB-backed planning tool", () => {
-  const prompt = readPrompt("plan-slice");
-  assert.match(prompt, /gsd_plan_slice/);
-  assert.match(prompt, /gsd_plan_task/);
-  // The prompt should describe the DB-backed tool as the canonical write path
-  assert.match(prompt, /DB-backed tool is the canonical write path/i);
-});
-
-test("plan-slice prompt does not instruct direct file writes as a primary step", () => {
-  const prompt = readPrompt("plan-slice");
-  // Should not instruct to "Write {{outputPath}}" as a primary step — tools handle rendering
-  assert.doesNotMatch(prompt, /^\d+\.\s+Write `?\{\{outputPath\}\}`?\s*$/m);
-});
-
-test("plan-slice prompt clarifies gsd_plan_slice handles task persistence", () => {
-  const prompt = readPrompt("plan-slice");
-  // gsd_plan_slice persists tasks in its transaction — no separate gsd_plan_task calls needed
-  assert.match(prompt, /gsd_plan_task/);
-  assert.match(prompt, /gsd_plan_slice` handles task persistence/i);
-});
-
-test("replan-slice prompt uses gsd_replan_slice as canonical DB-backed tool", () => {
-  const prompt = readPrompt("replan-slice");
-  assert.match(prompt, /gsd_replan_slice/);
-  // Degraded fallback (direct file writes) was removed — DB tools are always available
-  assert.doesNotMatch(prompt, /Degraded fallback/i);
-});
-
-test("reassess-roadmap prompt references gsd_reassess_roadmap tool", () => {
-  const prompt = readPrompt("reassess-roadmap");
-  assert.match(prompt, /gsd_reassess_roadmap/);
-});
-
-test("validate-milestone prompt persists verification classes through gsd_validate_milestone", () => {
-  const prompt = readPrompt("validate-milestone");
-  assert.match(prompt, /verification classes section/i);
-  assert.match(prompt, /verificationClasses/);
-  assert.match(prompt, /gsd_validate_milestone/);
-});
-
-// ─── Prompt migration: replan-slice → gsd_replan_slice ────────────────
-
-test("replan-slice prompt names gsd_replan_slice as the tool to use", () => {
-  const prompt = readPrompt("replan-slice");
-  assert.match(prompt, /gsd_replan_slice/);
-});
-
-// ─── Prompt migration: reassess-roadmap → gsd_reassess_roadmap ───────
-
-test("reassess-roadmap prompt names gsd_reassess_roadmap as the tool to use", () => {
-  const prompt = readPrompt("reassess-roadmap");
-  assert.match(prompt, /gsd_reassess_roadmap/);
-});
-
-// ─── Bug #2933: prompt parameter names must match camelCase TypeBox schema ───
-
-test("execute-task prompt uses camelCase parameter names matching TypeBox schema", () => {
-  const prompt = readPrompt("execute-task");
-  // The gsd_complete_task tool schema uses camelCase: milestoneId, sliceId, taskId
-  // Prompts must NOT tell the LLM to use snake_case (milestone_id, slice_id, task_id)
-  const toolCallLine = prompt.split("\n").find((l) => /gsd_complete_task/.test(l) || /gsd_task_complete/.test(l));
-  assert.ok(toolCallLine, "prompt must contain a gsd_complete_task or gsd_task_complete tool call line");
-  assert.doesNotMatch(toolCallLine!, /milestone_id/, "must use milestoneId, not milestone_id");
-  assert.doesNotMatch(toolCallLine!, /slice_id/, "must use sliceId, not slice_id");
-  assert.doesNotMatch(toolCallLine!, /task_id/, "must use taskId, not task_id");
-  // Positive: must mention the camelCase names
-  assert.match(toolCallLine!, /milestoneId/);
-  assert.match(toolCallLine!, /sliceId/);
-  assert.match(toolCallLine!, /taskId/);
-});
-
-test("complete-slice prompt uses camelCase parameter names matching TypeBox schema", () => {
-  const prompt = readPrompt("complete-slice");
-  // The gsd_complete_slice tool schema uses camelCase: milestoneId, sliceId
-  const toolCallLine = prompt.split("\n").find((l) => /gsd_complete_slice/.test(l) || /gsd_slice_complete/.test(l));
-  assert.ok(toolCallLine, "prompt must contain a gsd_complete_slice or gsd_slice_complete tool call line");
-  assert.doesNotMatch(toolCallLine!, /milestone_id/, "must use milestoneId, not milestone_id");
-  assert.doesNotMatch(toolCallLine!, /slice_id/, "must use sliceId, not slice_id");
-  // Positive: must mention the camelCase names
-  assert.match(toolCallLine!, /milestoneId/);
-  assert.match(toolCallLine!, /sliceId/);
-});
-
-test("reactive-execute prompt references tool calls instead of checkbox updates", () => {
-  const prompt = readPrompt("reactive-execute");
-  assert.doesNotMatch(prompt, /checkbox updates/);
-  assert.doesNotMatch(prompt, /checkbox edits/);
-  assert.match(prompt, /completion tool calls/);
-});