Merge pull request #1136 from corbitsdev/cl-8269-extract-prompt-variance-as-a-versioned-package-agent-owned

feat(prompt-variance): extract family prompt variance as a versioned package

Author: TheGreatAxios

bun.lock

@@ -0,0 +1,13 @@
+{
+  "name": "@corbits/prompt-variance",
+  "version": "0.1.0",
+  "private": true,
+  "type": "module",
+  "license": "SEE LICENSE IN LICENSE.md",
+  "exports": {
+    ".": {
+      "types": "./src/index.ts",
+      "default": "./src/index.ts"
+    }
+  }
+}

packages/prompt-variance/package.json

@@ -0,0 +1,36 @@
+import { describe, expect, test } from "bun:test";
+import { assemble } from "./assemble.js";
+import { claudeRow, defaultRow, gptRow, grokRow, museRow } from "./rows.js";
+
+const SECTIONS = ["contract", "Tools (names only): read_file", "context"];
+
+describe("assemble", () => {
+  test("joins sections with the residual as the last section", () => {
+    const out = assemble(SECTIONS, grokRow);
+    expect(out).toContain("contract");
+    expect(out.trimEnd().endsWith(grokRow.residual)).toBe(true);
+  });
+
+  test("a row without residual leaves the sections unchanged", () => {
+    expect(assemble(SECTIONS, defaultRow)).toBe(SECTIONS.join("\n\n"));
+  });
+
+  test("muse residual closes the prompt like the shipped tail append", () => {
+    const out = assemble(SECTIONS, museRow);
+    expect(out.trimEnd().endsWith(museRow.residual)).toBe(true);
+  });
+
+  test("claude and gpt residuals close the prompt the same way", () => {
+    expect(
+      assemble(SECTIONS, claudeRow).trimEnd().endsWith(claudeRow.residual),
+    ).toBe(true);
+    expect(assemble(SECTIONS, gptRow).trimEnd().endsWith(gptRow.residual)).toBe(
+      true,
+    );
+  });
+
+  test("tool mounting is out of scope: assemble returns a string, not tool names", () => {
+    const out = assemble(SECTIONS, grokRow);
+    expect(typeof out).toBe("string");
+  });
+});

packages/prompt-variance/src/assemble.test.ts

@@ -0,0 +1,16 @@
+import type { PromptVarianceRow } from "./rows.js";
+
+/**
+ * Append a family variance row's residual at the tail of the assembled
+ * sections (CL-8269). An empty residual leaves the sections unchanged.
+ * Residuals render last so they cannot disturb the cached prompt prefix.
+ * Tool mounting is out of scope: run.ts applies
+ * ModelFamilyPolicy.advertisedToolDeny at mount time.
+ */
+export function assemble(
+  sections: readonly string[],
+  familyRow: PromptVarianceRow,
+): string {
+  if (familyRow.residual.length === 0) return sections.join("\n\n");
+  return [...sections, familyRow.residual].join("\n\n");
+}

packages/prompt-variance/src/assemble.ts

@@ -0,0 +1,14 @@
+export { assemble } from "./assemble.js";
+export { resolvePromptVariance } from "./resolve.js";
+export {
+  claudeRow,
+  defaultRow,
+  FAMILY_IDS,
+  FAMILY_ROWS,
+  gptRow,
+  grokRow,
+  grokToolBudgetResidual,
+  museRow,
+  type PromptVarianceFamily,
+  type PromptVarianceRow,
+} from "./rows.js";

packages/prompt-variance/src/index.ts

@@ -0,0 +1,54 @@
+import { describe, expect, test } from "bun:test";
+import { resolvePromptVariance } from "./resolve.js";
+import { grokRow } from "./rows.js";
+
+describe("resolvePromptVariance", () => {
+  test("resolves each family to its row", () => {
+    expect(resolvePromptVariance({ family: "default" }).id).toBe("default");
+    expect(resolvePromptVariance({ family: "muse" }).id).toBe("muse");
+    expect(resolvePromptVariance({ family: "grok" }).id).toBe("grok");
+    expect(resolvePromptVariance({ family: "claude" }).id).toBe("claude");
+    expect(resolvePromptVariance({ family: "gpt" }).id).toBe("gpt");
+  });
+
+  test("grok keeps its finish-bias residual on leaves", () => {
+    const row = resolvePromptVariance({ family: "grok", orchestrator: false });
+    expect(row.residual).toBe(grokRow.residual);
+  });
+
+  test("grok on orchestrators falls back to the default row", () => {
+    const row = resolvePromptVariance({ family: "grok", orchestrator: true });
+    expect(row.id).toBe("default");
+    expect(row.residual).toBe("");
+  });
+
+  test("claude keeps its task_guidance block on leaves, not orchestrators", () => {
+    expect(
+      resolvePromptVariance({ family: "claude", orchestrator: false }).residual,
+    ).toContain("<task_guidance>");
+    const orch = resolvePromptVariance({
+      family: "claude",
+      orchestrator: true,
+    });
+    expect(orch.id).toBe("default");
+    expect(orch.residual).toBe("");
+  });
+
+  test("muse keeps its residual on leaves and orchestrators alike", () => {
+    expect(
+      resolvePromptVariance({ family: "muse", orchestrator: false }).residual,
+    ).not.toBe("");
+    expect(
+      resolvePromptVariance({ family: "muse", orchestrator: true }).residual,
+    ).not.toBe("");
+  });
+
+  test("gpt keeps its narrate-before-tools nudge on leaves and orchestrators alike", () => {
+    expect(
+      resolvePromptVariance({ family: "gpt", orchestrator: false }).residual,
+    ).toContain("Narrate before tools");
+    expect(
+      resolvePromptVariance({ family: "gpt", orchestrator: true }).residual,
+    ).toContain("Narrate before tools");
+  });
+});

packages/prompt-variance/src/resolve.test.ts

@@ -0,0 +1,26 @@
+import {
+  defaultRow,
+  FAMILY_ROWS,
+  type PromptVarianceFamily,
+  type PromptVarianceRow,
+} from "./rows.js";
+
+/**
+ * Resolve the variance row for a family, mirroring the leaves-only gates in
+ * the model family policy: the grok finish-bias residual and the claude
+ * task_guidance block only make sense on leaf workers, so orchestrators
+ * fall back to the default row. Muse keeps its residual on both — the
+ * constructors append the same text at the tail either way — and gpt keeps
+ * its narrate-before-tools nudge on primaries and leaves alike.
+ */
+export function resolvePromptVariance(input: {
+  family: PromptVarianceFamily;
+  orchestrator?: boolean;
+}): PromptVarianceRow {
+  if (input.orchestrator === true) {
+    if (input.family === "grok" || input.family === "claude") {
+      return defaultRow;
+    }
+  }
+  return FAMILY_ROWS[input.family];
+}

packages/prompt-variance/src/resolve.ts

@@ -0,0 +1,115 @@
+import { describe, expect, test } from "bun:test";
+import {
+  claudeRow,
+  defaultRow,
+  FAMILY_IDS,
+  FAMILY_ROWS,
+  gptRow,
+  grokRow,
+  grokToolBudgetResidual,
+  museRow,
+  type PromptVarianceFamily,
+} from "./rows.js";
+
+const CEREMONY_LINES = [
+  "Never run git add, git commit, git stash, or any other state-changing git command unless the user asks.",
+  "Do not narrate a plan before acting on a small task; act, then report.",
+  "Verify with the test command once at the end, not after every edit.",
+];
+
+describe("prompt-variance family rows", () => {
+  test("ships exactly the default/muse/grok/claude/gpt families", () => {
+    expect([...FAMILY_IDS]).toEqual([
+      "default",
+      "muse",
+      "grok",
+      "claude",
+      "gpt",
+    ]);
+  });
+
+  test("has no glm row until its eval lands (CL-8265)", () => {
+    for (const id of FAMILY_IDS) {
+      expect(id).not.toBe("glm");
+    }
+  });
+
+  test("every row carries the id/residual shape — residuals-only, no deny fields", () => {
+    for (const row of [defaultRow, museRow, grokRow, claudeRow, gptRow]) {
+      expect(typeof row.id).toBe("string");
+      expect(typeof row.residual).toBe("string");
+      expect("advertisedToolDeny" in row).toBe(false);
+      expect("sectionOmit" in row).toBe(false);
+      expect("overrides" in row).toBe(false);
+    }
+  });
+
+  test("row ids match their family and FAMILY_ROWS covers all five", () => {
+    const ids: PromptVarianceFamily[] = [
+      defaultRow.id,
+      museRow.id,
+      grokRow.id,
+      claudeRow.id,
+      gptRow.id,
+    ];
+    expect(ids).toEqual(["default", "muse", "grok", "claude", "gpt"]);
+    expect(Object.keys(FAMILY_ROWS).sort()).toEqual([
+      "claude",
+      "default",
+      "gpt",
+      "grok",
+      "muse",
+    ]);
+  });
+
+  test("muse row is the shipped CL-7869 tool-discipline text", () => {
+    expect(museRow.residual).toContain("Tool discipline:");
+    expect(museRow.residual).toContain("Batch independent tool calls");
+    expect(museRow.residual).toContain("Never re-read a file");
+    expect(museRow.residual).toContain("Do not narrate; act.");
+  });
+
+  test("grok row is the single finish-bias + ceremony block (CL-8296)", () => {
+    expect(grokRow.residual).toContain("Finish bias (xAI / Grok worker):");
+    expect(grokRow.residual).toContain("prefer the structured report");
+    expect(grokRow.residual).toContain("re-open paths you already read");
+    expect(grokRow.residual).toContain("done-definition is met");
+    expect(grokRow.residual).toContain("never run_shell");
+  });
+
+  test("each ceremony line appears exactly once in the grok row (P2 invariant)", () => {
+    for (const line of CEREMONY_LINES) {
+      const occurrences = grokRow.residual.split(line).length - 1;
+      expect(occurrences).toBe(1);
+    }
+  });
+
+  test("grok tool-budget residual is ceremony-free and budget text appears once (P1 invariant)", () => {
+    expect(grokToolBudgetResidual).toContain("Tool budget:");
+    for (const line of CEREMONY_LINES) {
+      expect(grokToolBudgetResidual).not.toContain(line);
+    }
+    const budgetOccurrences =
+      grokToolBudgetResidual.split("Tool budget:").length - 1;
+    expect(budgetOccurrences).toBe(1);
+  });
+
+  test("default row carries no residual", () => {
+    expect(defaultRow.residual).toBe("");
+  });
+
+  test("claude row is the single XML task_guidance block (CL-8309)", () => {
+    expect(claudeRow.residual).toContain("<task_guidance>");
+    expect(claudeRow.residual).toContain("</task_guidance>");
+    expect(claudeRow.residual).toContain("Follow the dispatch brief exactly");
+    expect(claudeRow.residual).toContain("Batch independent tool calls");
+  });
+
+  test("gpt row is the narrate-before-tools nudge (CL-8310)", () => {
+    expect(gptRow.residual).toContain("Narrate before tools (GPT worker):");
+    expect(gptRow.residual).toContain(
+      "one short line saying what you are doing",
+    );
+    expect(gptRow.residual).toContain("done-definition is met");
+  });
+});