chore: bump eval to 0.1.4

小橘 🍊（NEKO Team）

.changeset/bootstrap-onboarding.md

@@ -1,9 +0,0 @@
----
-"@united-workforce/cli": patch
----
-
-fix: expand bootstrap prompt with full onboarding and upgrade guide
-
-Bootstrap now covers two scenarios:
-- Fresh install: CLI + adapter installation, `uwf setup` configuration, skill installation, end-to-end verification
-- Upgrade: package update, skill regeneration, breaking change migrations (e.g. $START new/resume)

.changeset/bootstrap-preflight.md

@@ -1,8 +0,0 @@
----
-"@united-workforce/cli": patch
----
-
-fix: bootstrap adds Step 0 environment pre-flight check
-
-- Pre-flight checks for node, pnpm/npm, global bin PATH, hermes CLI with FIX instructions (#112)
-- Install commands changed from npm to pnpm (with npm fallback)

.changeset/bootstrap-schema-path.md

@@ -1,9 +0,0 @@
----
-"@united-workforce/cli": patch
-"@united-workforce/util": patch
----
-
-fix: workflow-authoring flat schema example uses enum, bootstrap adds PATH guidance
-
-- workflow-authoring: flat schema example uses `enum: [done]` instead of bare `const` (#110.3)
-- bootstrap: adds `which hermes` check and PATH guidance for venv installs (#110.4)

.changeset/bootstrap-ux-fixes.md

@@ -1,10 +0,0 @@
----
-"@united-workforce/cli": patch
----
-
-fix: preset provider base-url auto-fill, bootstrap ACP docs, friendlier name mismatch error
-
-- `uwf setup --provider dashscope` now auto-fills `--base-url` from preset list (#106)
-- Bootstrap guide documents uwf-hermes ACP dependency (`pip install hermes-agent[acp]`) (#107)
-- Bootstrap verify step uses inline workflow instead of missing `examples/eval-simple.yaml` (#107)
-- Workflow filename mismatch error now suggests how to fix it (#108)

.changeset/setup-ux-improvements.md

@@ -1,12 +0,0 @@
----
-"@united-workforce/cli": patch
----
-
-fix: setup UX improvements (#114)
-
-- Setup validates adapter availability and prints install command if missing
-- Setup prints "Config saved to <path> ✓" on success
-- Spawn ENOENT gives actionable error ("not found in PATH" + which command)
-- SQLite ExperimentalWarning suppressed via NODE_OPTIONS in spawned processes
-- Bootstrap VERSION reads cli package version (was reading util version)
-- Bootstrap PATH guidance is shell-agnostic (no hardcoded .bashrc/.profile)

.changeset/start-new-resume.md

@@ -1,9 +0,0 @@
----
-"@united-workforce/cli": minor
-"@united-workforce/util": patch
----
-
-feat: replace $START `_` status with `new`/`resume` semantics
-
-BREAKING: All workflow YAML files must update `$START._` to `$START.new` + `$START.resume`.
-The `resume` edge prompt replaces the previously hardcoded resume message in the CLI.

examples/debate.yaml

@@ -1,63 +1,131 @@
-name: "debate"
-description: "Structured debate between two sides. Tests cross-process session resume."
+name: debate
+description: "Multi-role structured debate with critical thinking framework and host summary."
+
+# Shared frontmatter schema for debater roles (YAML anchor)
+x-debater-frontmatter: &debater-frontmatter
+  type: object
+  oneOf:
+    - properties:
+        $status: { const: speak }
+        argument: { type: string }
+      required: [$status, argument]
+    - properties:
+        $status: { const: conceded }
+        reason: { type: string }
+      required: [$status, reason]
+    - properties:
+        $status: { const: final }
+        closing: { type: string }
+      required: [$status, closing]
+
 roles:
-  against:
-    description: "Argues against the proposition"
-    goal: |
-      You are a skilled debater arguing AGAINST the proposition.
-      Be logical, cite evidence, and directly address your opponent's points.
-      Keep each argument concise (under 200 words).
-    capabilities:
-      - argumentation
-      - critical-thinking
+  proponent:
+    description: "Argues FOR the proposition"
+    goal: "Build a compelling case for the proposition through logical reasoning and evidence"
+    capabilities: []
     procedure: |
-      1. If this is the opening, present your strongest argument against the proposition.
-      2. If responding to the other side, directly counter their points with evidence and logic.
-      3. If you find yourself genuinely convinced by the other side, you may concede.
-    output: |
-      Provide your argument in the frontmatter.
-      Set status to "conceded" ONLY if you are genuinely convinced and wish to stop debating.
-      Otherwise set status to "continue".
+      You are an experienced scholar arguing FOR the proposition.
+
+      ## Critical Thinking Framework (execute before every speech)
+
+      ### A. Pre-speech reflection (internal, do not output)
+      - Does every step in my argument chain hold? Any hidden assumptions or logical gaps?
+      - If I were my opponent, how would I attack this? Where am I weakest?
+      - Does my evidence actually support my claim, or could it backfire?
+      - Should I go on offense or defense this round?
+
+      ### B. Evidence discipline
+      - Verify key numbers — watch for order-of-magnitude errors
+      - Assess data freshness — fast-moving fields have short half-lives
+      - Distinguish primary data from secondary citations, expert opinion, and common assumptions
+
+      ### C. Anti-fragility
+      - Anticipate counterarguments; preemptively strengthen or strategically abandon weak points
+      - Catch logical gaps, data misuse, or outdated claims in your opponent's reasoning
+
+      ## Rules
+      1. Check Thread Progress to see how many times you have spoken.
+      2. On your 3rd speech, you MUST output $status: final (closing statement).
+      3. If genuinely convinced by the opponent, output $status: conceded.
+      4. Otherwise output $status: speak and counter the opponent's points.
+      5. Be rigorous, cite evidence, stay concise.
+    output: "Debate argument"
+    frontmatter: *debater-frontmatter
+
+  opponent:
+    description: "Argues AGAINST the proposition"
+    goal: "Build a compelling case against the proposition through logical reasoning and evidence"
+    capabilities: []
+    procedure: |
+      You are an experienced scholar arguing AGAINST the proposition.
+
+      ## Critical Thinking Framework (execute before every speech)
+
+      ### A. Pre-speech reflection (internal, do not output)
+      - Does every step in my argument chain hold? Any hidden assumptions or logical gaps?
+      - If I were my opponent, how would I attack this? Where am I weakest?
+      - Does my evidence actually support my claim, or could it backfire?
+      - Should I go on offense or defense this round?
+
+      ### B. Evidence discipline
+      - Verify key numbers — watch for order-of-magnitude errors
+      - Assess data freshness — fast-moving fields have short half-lives
+      - Distinguish primary data from secondary citations, expert opinion, and common assumptions
+
+      ### C. Anti-fragility
+      - Anticipate counterarguments; preemptively strengthen or strategically abandon weak points
+      - Catch logical gaps, data misuse, or outdated claims in your opponent's reasoning
+
+      ## Rules
+      1. Check Thread Progress to see how many times you have spoken.
+      2. On your 3rd speech, or when the proponent has issued a final statement, you MUST output $status: final.
+      3. If genuinely convinced by the proponent, output $status: conceded.
+      4. Otherwise output $status: speak and counter the proponent's points.
+      5. Be rigorous, cite evidence, stay concise.
+    output: "Debate argument"
+    frontmatter: *debater-frontmatter
+
+  host:
+    description: "Debate moderator — delivers impartial summary and verdict"
+    goal: "Objectively review the debate, analyze both sides, and deliver a verdict"
+    capabilities: []
+    procedure: |
+      You are an experienced academic debate moderator.
+
+      ## Task
+      1. Outline each side's core arguments
+      2. Evaluate reasoning quality and evidence use
+      3. Highlight the most impactful exchanges
+      4. Analyze the deeper significance of the topic
+      5. Deliver an overall verdict
+
+      ## Style
+      - Impartial but with independent judgment
+      - Substantive, not superficial
+    output: "Debate summary report"
     frontmatter:
       type: object
       properties:
-        $status:
-          enum: ["continue", "conceded"]
-        argument:
-          type: string
-      required: [$status, argument]
-  for:
-    description: "Argues for the proposition"
-    goal: |
-      You are a skilled debater arguing FOR the proposition.
-      Be logical, cite evidence, and directly address your opponent's points.
-      Keep each argument concise (under 200 words).
-    capabilities:
-      - argumentation
-      - critical-thinking
-    procedure: |
-      1. Read the opposing side's latest argument carefully.
-      2. Counter their points with evidence and logic.
-      3. If you find yourself genuinely convinced by the other side, you may concede.
-    output: |
-      Provide your argument in the frontmatter.
-      Set status to "conceded" ONLY if you are genuinely convinced and wish to stop debating.
-      Otherwise set status to "continue".
-    frontmatter:
-      type: object
-      properties:
-        $status:
-          enum: ["continue", "conceded"]
-        argument:
-          type: string
-      required: [$status, argument]
+        $status: { const: done }
+        summary: { type: string }
+        highlights: { type: string }
+        verdict: { type: string }
+      required: [$status, summary, highlights, verdict]
+
 graph:
   $START:
-    new: { role: "against", prompt: "Present your opening argument against the proposition." }
-    resume: { role: "against", prompt: "Review the previous debate output and continue the argument against the proposition." }
-  against:
-    conceded: { role: "$END", prompt: "The against side conceded. Debate over." }
-    continue: { role: "for", prompt: "Counter the opposing argument: {{{argument}}}" }
-  for:
-    conceded: { role: "$END", prompt: "The for side conceded. Debate over." }
-    continue: { role: "against", prompt: "Counter the opposing argument: {{{argument}}}" }
+    new: { role: proponent, prompt: "The debate begins. You are arguing FOR the proposition. Present your opening argument." }
+    resume: { role: proponent, prompt: "The debate continues." }
+
+  proponent:
+    speak: { role: opponent, prompt: "Proponent argues:\n\n{{{argument}}}\n\nYou are the opponent. Counter this argument." }
+    conceded: { role: host, prompt: "The proponent conceded: {{{reason}}}\n\nPlease summarize the debate." }
+    final: { role: opponent, prompt: "Proponent's closing statement:\n\n{{{closing}}}\n\nYou are the opponent. Deliver your final response." }
+
+  opponent:
+    speak: { role: proponent, prompt: "Opponent argues:\n\n{{{argument}}}\n\nYou are the proponent. Counter this argument." }
+    conceded: { role: host, prompt: "The opponent conceded: {{{reason}}}\n\nPlease summarize the debate." }
+    final: { role: host, prompt: "Opponent's closing statement:\n\n{{{closing}}}\n\nThe debate is over. Please summarize." }
+
+  host:
+    done: { role: "$END", prompt: "Summary complete." }

packages/agent-builtin/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@united-workforce/agent-builtin",
-  "version": "0.1.1",
+  "version": "0.1.2",
   "files": [
     "src",
     "dist",

packages/agent-builtin/src/cli.ts

@@ -1,4 +1,4 @@
-#!/usr/bin/env node
+#!/usr/bin/env -S node --disable-warning=ExperimentalWarning
 
 // eslint-disable-next-line -- dynamic import for version
 const pkg = await import("../package.json", { with: { type: "json" } });

packages/agent-claude-code/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@united-workforce/agent-claude-code",
-  "version": "0.1.1",
+  "version": "0.1.3",
   "files": [
     "src",
     "dist",

packages/agent-claude-code/src/claude-code.ts

@@ -7,6 +7,7 @@ import {
   type AgentRunResult,
   buildContinuationPrompt,
   buildRolePrompt,
+  buildThreadProgress,
   createAgent,
   getCachedSessionId,
   setCachedSessionId,
@@ -27,6 +28,10 @@ export function buildClaudeCodePrompt(ctx: AgentContext): string {
   if (ctx.outputFormatInstruction !== undefined && ctx.outputFormatInstruction !== "") {
     parts.push(ctx.outputFormatInstruction, "");
   }
+
+  // Inject thread progress so the agent knows step count and role visit count
+  parts.push(buildThreadProgress(ctx.steps, ctx.role), "");
+
   parts.push(rolePrompt, "", "## Task", ctx.start.prompt);
 
   if (!ctx.isFirstVisit) {

packages/agent-claude-code/src/cli.ts

@@ -1,4 +1,4 @@
-#!/usr/bin/env node
+#!/usr/bin/env -S node --disable-warning=ExperimentalWarning
 
 // eslint-disable-next-line -- dynamic import for version
 const pkg = await import("../package.json", { with: { type: "json" } });

packages/agent-hermes/__tests__/issue-551.test.ts

@@ -15,7 +15,8 @@ describe("Issue #551 — bin entry & engines", () => {
     const pkg = JSON.parse(readFileSync(join(PKG_ROOT, "package.json"), "utf-8"));
     const binPath = pkg.bin["uwf-hermes"];
     const content = readFileSync(join(PKG_ROOT, binPath), "utf-8");
-    expect(content.startsWith("#!/usr/bin/env node")).toBe(true);
+    expect(content.startsWith("#!/usr/bin/env")).toBe(true);
+    expect(content).toContain("node");
   });
 
   test("README.md explains uwf-hermes is an adapter", () => {

packages/agent-hermes/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@united-workforce/agent-hermes",
-  "version": "0.1.2",
+  "version": "0.1.4",
   "files": [
     "src",
     "dist",

packages/agent-hermes/src/acp-client.ts

@@ -12,7 +12,11 @@ const OWN_VERSION = (
   }
 ).version;
 
-const HERMES_COMMAND = "hermes";
+/** Resolve hermes binary: `UWF_HERMES_BIN` override → default `"hermes"` via PATH. */
+function resolveHermesCommand(): string {
+  const override = process.env.UWF_HERMES_BIN;
+  return override !== undefined && override !== "" ? override : "hermes";
+}
 const PROTOCOL_VERSION = 1;
 
 type JsonRpcResponse = {
@@ -271,7 +275,8 @@ export class HermesAcpClient {
       return;
     }
 
-    const child = spawn(HERMES_COMMAND, ["acp"], {
+    const hermesCommand = resolveHermesCommand();
+    const child = spawn(hermesCommand, ["acp"], {
       env: process.env,
       shell: false,
       stdio: ["pipe", "pipe", "pipe"],

packages/agent-hermes/src/cli.ts

@@ -1,4 +1,4 @@
-#!/usr/bin/env node
+#!/usr/bin/env -S node --disable-warning=ExperimentalWarning
 
 // eslint-disable-next-line -- dynamic import for version
 const pkg = await import("../package.json", { with: { type: "json" } });

packages/agent-hermes/src/hermes.ts

@@ -6,6 +6,7 @@ import {
   type AgentRunResult,
   buildContinuationPrompt,
   buildRolePrompt,
+  buildThreadProgress,
   createAgent,
 } from "@united-workforce/util-agent";
 import type { AcpUsage } from "./acp-client.js";
@@ -60,6 +61,9 @@ export function buildHermesPrompt(ctx: AgentContext): string {
     parts.push(ctx.outputFormatInstruction, "");
   }
 
+  // Inject thread progress so the agent knows step count and role visit count
+  parts.push(buildThreadProgress(ctx.steps, ctx.role), "");
+
   if (!ctx.isFirstVisit) {
     // Re-entry: show only steps since last visit, meta only
     parts.push(buildContinuationPrompt(ctx.steps, ctx.role, ctx.edgePrompt));

packages/agent-mock/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@united-workforce/agent-mock",
-  "version": "0.1.1",
+  "version": "0.1.2",
   "files": [
     "src",
     "dist",

packages/agent-mock/src/cli.ts

@@ -1,4 +1,4 @@
-#!/usr/bin/env node
+#!/usr/bin/env -S node --disable-warning=ExperimentalWarning
 
 // eslint-disable-next-line -- dynamic import for version
 const pkg = await import("../package.json", { with: { type: "json" } });

packages/cli/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@united-workforce/cli",
-  "version": "0.2.0",
+  "version": "0.3.0",
   "files": [
     "src",
     "dist",

packages/cli/src/__tests__/current-role.test.ts

@@ -28,9 +28,13 @@ roles:
       $status: "ready"
     frontmatter:
       type: object
-      required: ["$status"]
-      properties:
-        $status: { type: string, enum: ["ready", "not-ready"] }
+      oneOf:
+        - properties:
+            $status: { const: "ready" }
+          required: ["$status"]
+        - properties:
+            $status: { const: "not-ready" }
+          required: ["$status"]
   roleB:
     description: Second role
     goal: Do B
@@ -42,7 +46,7 @@ roles:
       type: object
       required: ["$status"]
       properties:
-        $status: { type: string, enum: ["done"] }
+        $status: { const: "done" }
 graph:
   $START:
     new:
@@ -82,9 +86,13 @@ roles:
       $status: "pass"
     frontmatter:
       type: object
-      required: ["$status"]
-      properties:
-        $status: { type: string, enum: ["pass", "fail"] }
+      oneOf:
+        - properties:
+            $status: { const: "pass" }
+          required: ["$status"]
+        - properties:
+            $status: { const: "fail" }
+          required: ["$status"]
   roleB:
     description: Pass role
     goal: Do B
@@ -96,7 +104,7 @@ roles:
       type: object
       required: ["$status"]
       properties:
-        $status: { type: string, enum: ["done"] }
+        $status: { const: "done" }
   roleC:
     description: Fail role
     goal: Do C
@@ -108,7 +116,7 @@ roles:
       type: object
       required: ["$status"]
       properties:
-        $status: { type: string, enum: ["done"] }
+        $status: { const: "done" }
 graph:
   $START:
     new:
@@ -155,7 +163,7 @@ roles:
       type: object
       required: ["$status"]
       properties:
-        $status: { type: string, enum: ["done"] }
+        $status: { const: "done" }
 graph:
   $START:
     new:

packages/cli/src/__tests__/thread-location.test.ts

@@ -54,7 +54,7 @@ roles:
       type: object
       required: ["$status"]
       properties:
-        $status: { type: string, enum: ["ready"] }
+        $status: { const: "ready" }
 graph:
   $START:
     new:
@@ -114,7 +114,7 @@ roles:
       type: object
       required: ["$status"]
       properties:
-        $status: { type: string, enum: ["ready"] }
+        $status: { const: "ready" }
 graph:
   $START:
     new:
@@ -161,7 +161,7 @@ roles:
       type: object
       required: ["$status"]
       properties:
-        $status: { type: string, enum: ["ready"] }
+        $status: { const: "ready" }
 graph:
   $START:
     new:

packages/cli/src/__tests__/thread-show-status.test.ts

@@ -31,7 +31,7 @@ roles:
       type: object
       required: ["$status"]
       properties:
-        $status: { type: string, enum: ["ready"] }
+        $status: { const: "ready" }
 graph:
   $START:
     new:

packages/cli/src/__tests__/thread-start-cwd-cli.test.ts

@@ -54,7 +54,7 @@ roles:
       type: object
       required: ["$status"]
       properties:
-        $status: { type: string, enum: ["ready"] }
+        $status: { const: "ready" }
 graph:
   $START:
     new:

packages/cli/src/__tests__/validate-semantic.test.ts

@@ -17,7 +17,7 @@ function makeWorkflow(overrides?: Partial<WorkflowPayload>): WorkflowPayload {
         frontmatter: {
           type: "object",
           properties: {
-            $status: { enum: ["done"] },
+            $status: { const: "done" },
             plan: { type: "string" },
           },
           required: ["$status", "plan"],
@@ -85,7 +85,7 @@ describe("Suite 1: Role Reference Integrity", () => {
       output: "None",
       frontmatter: {
         type: "object",
-        properties: { $status: { enum: ["done"] } },
+        properties: { $status: { const: "done" } },
         required: ["$status"],
       } as unknown as string,
     };
@@ -187,7 +187,7 @@ describe("Suite 2: Graph Structure", () => {
       output: "Isolated",
       frontmatter: {
         type: "object",
-        properties: { $status: { enum: ["done"] } },
+        properties: { $status: { const: "done" } },
         required: ["$status"],
       } as unknown as string,
     };
@@ -272,8 +272,8 @@ describe("Suite 3: Status-Edge Consistency", () => {
   });
 });
 
-describe("Suite 3b: Enum-Based Multi-Exit", () => {
-  test("3b.1 enum multi-exit passes with matching graph keys", () => {
+describe("Suite 3b: Enum-Based $status is Rejected", () => {
+  test("3b.1 enum multi-exit is rejected (must use oneOf + const)", () => {
     const wf = makeWorkflow();
     wf.roles.reviewer = {
       ...wf.roles.reviewer,
@@ -291,52 +291,10 @@ describe("Suite 3b: Enum-Based Multi-Exit", () => {
       rejected: { role: "writer", prompt: "Fix: {{{comments}}}", location: null },
     };
     const errors = validateWorkflow(wf);
-    expect(errors).toEqual([]);
+    expect(errors.some((e) => e.includes("must define") && e.includes("const"))).toBe(true);
   });
 
-  test("3b.2 enum multi-exit with extra graph key", () => {
-    const wf = makeWorkflow();
-    wf.roles.reviewer = {
-      ...wf.roles.reviewer,
-      frontmatter: {
-        type: "object",
-        properties: {
-          $status: { enum: ["approved", "rejected"] },
-          comments: { type: "string" },
-        },
-        required: ["$status", "comments"],
-      } as unknown as string,
-    };
-    wf.graph.reviewer = {
-      approved: { role: "$END", prompt: "Done", location: null },
-      rejected: { role: "writer", prompt: "Fix", location: null },
-      timeout: { role: "$END", prompt: "Timed out", location: null },
-    };
-    const errors = validateWorkflow(wf);
-    expect(errors.some((e) => e.includes("extra status keys: timeout"))).toBe(true);
-  });
-
-  test("3b.3 enum multi-exit with missing graph key", () => {
-    const wf = makeWorkflow();
-    wf.roles.reviewer = {
-      ...wf.roles.reviewer,
-      frontmatter: {
-        type: "object",
-        properties: {
-          $status: { enum: ["approved", "rejected"] },
-          comments: { type: "string" },
-        },
-        required: ["$status", "comments"],
-      } as unknown as string,
-    };
-    wf.graph.reviewer = {
-      approved: { role: "$END", prompt: "Done", location: null },
-    };
-    const errors = validateWorkflow(wf);
-    expect(errors.some((e) => e.includes("missing status keys: rejected"))).toBe(true);
-  });
-
-  test("3b.4 enum with single explicit value passes", () => {
+  test("3b.2 enum single-exit is rejected (must use const)", () => {
     const wf = makeWorkflow();
     wf.roles.writer = {
       ...wf.roles.writer,
@@ -351,28 +309,71 @@ describe("Suite 3b: Enum-Based Multi-Exit", () => {
     };
     wf.graph.writer = { ready: { role: "reviewer", prompt: "Review: {{{plan}}}", location: null } };
     const errors = validateWorkflow(wf);
-    expect(errors).toEqual([]);
+    expect(errors.some((e) => e.includes("must define") && e.includes("const"))).toBe(true);
   });
+});
 
-  test("3b.5 enum multi-exit mustache var not in frontmatter", () => {
+describe("Suite 3c: Const-Based Flat Schema", () => {
+  test("3c.1 flat schema with const $status passes validation", () => {
     const wf = makeWorkflow();
-    wf.roles.reviewer = {
-      ...wf.roles.reviewer,
+    wf.roles.writer = {
+      ...wf.roles.writer,
       frontmatter: {
         type: "object",
         properties: {
-          $status: { enum: ["approved", "rejected"] },
-          comments: { type: "string" },
+          $status: { const: "done" },
+          plan: { type: "string" },
         },
-        required: ["$status", "comments"],
+        required: ["$status", "plan"],
       } as unknown as string,
     };
-    wf.graph.reviewer = {
-      approved: { role: "$END", prompt: "Done: {{{nonexistent}}}", location: null },
-      rejected: { role: "writer", prompt: "Fix: {{{comments}}}", location: null },
+    const errors = validateWorkflow(wf);
+    expect(errors).toEqual([]);
+  });
+
+  test("3c.2 flat schema with const $status detects extra graph key", () => {
+    const wf = makeWorkflow();
+    wf.roles.writer = {
+      ...wf.roles.writer,
+      frontmatter: {
+        type: "object",
+        properties: {
+          $status: { const: "done" },
+          plan: { type: "string" },
+        },
+        required: ["$status", "plan"],
+      } as unknown as string,
+    };
+    wf.graph.writer = {
+      done: { role: "reviewer", prompt: "Review.", location: null },
+      extra: { role: "$END", prompt: "Nope.", location: null },
     };
     const errors = validateWorkflow(wf);
-    expect(errors.some((e) => e.includes("nonexistent") && e.includes("not found"))).toBe(true);
+    expect(errors.some((e) => e.includes("extra status keys") && e.includes("extra"))).toBe(true);
+  });
+
+  test("3c.3 flat schema with const $status validates mustache vars", () => {
+    const wf = makeWorkflow();
+    wf.roles.writer = {
+      ...wf.roles.writer,
+      frontmatter: {
+        type: "object",
+        properties: {
+          $status: { const: "done" },
+          plan: { type: "string" },
+        },
+        required: ["$status", "plan"],
+      } as unknown as string,
+    };
+    wf.graph.writer = {
+      done: { role: "reviewer", prompt: "Review: {{{nonexistent}}}", location: null },
+    };
+    const errors = validateWorkflow(wf);
+    expect(
+      errors.some(
+        (e) => e.includes('prompt variable "nonexistent"') && e.includes('role "writer"'),
+      ),
+    ).toBe(true);
   });
 });
 
@@ -480,7 +481,7 @@ describe("Suite 6: Multiple Errors Collection", () => {
       output: "None",
       frontmatter: {
         type: "object",
-        properties: { $status: { enum: ["done"] } },
+        properties: { $status: { const: "done" } },
         required: ["$status"],
       } as unknown as string,
     };

packages/cli/src/__tests__/workflow-resolution.test.ts

@@ -31,7 +31,7 @@ function makeMinimalPayload(name: string, description: string): WorkflowPayload
         frontmatter: {
           type: "object",
           properties: {
-            $status: { type: "string", enum: ["done"] },
+            $status: { const: "done" },
           },
           required: ["$status"],
         } as unknown as CasRef,

packages/cli/src/cli.ts

@@ -1,4 +1,4 @@
-#!/usr/bin/env node
+#!/usr/bin/env -S node --disable-warning=ExperimentalWarning
 
 import type { CasRef, ThreadId, ThreadStatus } from "@united-workforce/protocol";
 import { Command } from "commander";
@@ -542,7 +542,7 @@ prompt
 
 program
   .command("setup")
-  .description("Configure provider, model, and agent")
+  .description("Configure provider, model, and agent. Run without options for interactive wizard.")
   .option("--provider <name>", "Provider name")
   .option("--base-url <url>", "OpenAI-compatible API base URL")
   .option("--api-key <key>", "API key")

packages/cli/src/commands/prompt.ts

@@ -78,48 +78,105 @@ npm prefix -g     # global prefix; bin is <prefix>/bin
 # FIX: add the missing directory to your shell's startup file
 #   (e.g. ~/.bashrc, ~/.zshrc, ~/.profile, or fish config):
 #   export PATH="<global-bin-dir>:$PATH"
-
-# 4. (uwf-hermes only) hermes CLI
-which hermes
-# FIX: if hermes is in a virtualenv, add it to PATH:
-#   export PATH="$HOME/.hermes/hermes-agent/.venv/bin:$PATH"
-#   or create a symlink: ln -s ~/.hermes/hermes-agent/.venv/bin/hermes ~/.local/bin/hermes
 \`\`\`
 
 **All checks must pass before continuing.** If you had to modify PATH, verify the change persists by opening a new shell or sourcing your shell config.
 
-### Step 1 — Install CLI and agent adapter
+### Step 1 — Discover agents and install adapter
+
+**First, detect which supported agents are already installed on the user's machine:**
 
 \`\`\`bash
-pnpm add -g @united-workforce/cli    # or: npm install -g @united-workforce/cli
-uwf --version   # should print ${CLI_VERSION}
+# Check for Hermes Agent
+which hermes 2>/dev/null && hermes --version
+
+# Check for Claude Code
+which claude 2>/dev/null && claude --version   # should show "X.Y.Z (Claude Code)"
 \`\`\`
 
-Install an agent adapter (at least one is required):
+**Based on the results:**
 
-| Adapter | Install | When to use |
-|---------|---------|-------------|
-| uwf-hermes | \`pnpm add -g @united-workforce/agent-hermes\` | When your agent framework is Hermes Agent |
-| uwf-claude-code | \`pnpm add -g @united-workforce/agent-claude-code\` | When using Claude Code CLI directly |
-| uwf-builtin | \`pnpm add -g @united-workforce/agent-builtin\` | Lightweight built-in agent (no external dependency) |
+- **Only hermes found** → install \`uwf-hermes\` adapter
+- **Only claude found** → install \`uwf-claude-code\` adapter
+- **Both found** → ask the user which agent they want uwf to use as default
+- **Neither found** → the user must install at least one agent first:
+  - Hermes Agent: https://hermes-agent.nousresearch.com/docs
+  - Claude Code: \`npm install -g @anthropic-ai/claude-code\`
+
+**Install the uwf CLI and the chosen adapter** using pnpm or npm:
 
-**uwf-hermes** also requires the Hermes ACP plugin. After installing \`hermes-agent\`, run:
 \`\`\`bash
-pip install hermes-agent[acp]   # or: pip install -e .[acp] if installed from source
+# CLI (required)
+pnpm add -g @united-workforce/cli       # or: npm install -g @united-workforce/cli
+
+# Adapter — install the one matching the detected agent:
+pnpm add -g @united-workforce/agent-hermes       # or: npm i -g @united-workforce/agent-hermes
+pnpm add -g @united-workforce/agent-claude-code   # or: npm i -g @united-workforce/agent-claude-code
 \`\`\`
 
-Verify the adapter is installed: \`uwf-hermes --version\` (or whichever you chose).
+**⚠ Adapter versions are independent from CLI versions.** Do NOT try to match adapter version to CLI version. Just install \`@latest\` (the default).
+
+**After installing, verify that \`uwf\` and the adapter are available in PATH:**
+
+\`\`\`bash
+uwf --version          # should print ${CLI_VERSION}
+uwf-hermes --version   # or: uwf-claude-code --version
+\`\`\`
+
+If either command is not found, the global bin directory is not in the current shell's PATH. **You must fix this before continuing:**
+
+1. Find where the binary was installed:
+   \`\`\`bash
+   find ~/.local ~/.hermes /usr/local -name uwf -type f 2>/dev/null
+   npm prefix -g    # global prefix — bin is <prefix>/bin
+   \`\`\`
+2. Add the directory to PATH permanently by appending to the user's shell config (e.g. \`~/.bashrc\`, \`~/.zshrc\`, \`~/.profile\`, or fish config):
+   \`\`\`bash
+   export PATH="<global-bin-dir>:$PATH"
+   \`\`\`
+3. Source the updated config or open a new shell, then re-verify the commands work.
+
+**uwf-hermes** also requires the Hermes ACP plugin. Verify with \`hermes acp --help\`. If not available, install it:
+\`\`\`bash
+# Option A: install into hermes venv (recommended)
+source ~/.hermes/hermes-agent/.venv/bin/activate && pip install hermes-agent[acp]
+
+# Option B: pipx
+pipx install 'hermes-agent[acp]'
+
+# Option C: if installed from source
+pip install -e '.[acp]'
+\`\`\`
 
 ### Step 2 — Configure provider and model
 
 uwf needs an LLM provider to run agents. **Ask the user** for their provider, API key, and model, then run:
 
 \`\`\`bash
-uwf setup --provider <name> --base-url <url> --api-key <key> --model <model> [--agent <adapter>]
+uwf setup --provider <name> --api-key <key> --model <model> --agent <adapter-command>
 \`\`\`
 
-Preset providers (base-url is auto-filled when using a preset name):
-openai, xai, openrouter, venice, dashscope, deepseek, siliconflow, volcengine, kimi, glm, stepfun, minimax, ollama
+**Note:** \`--agent\` takes the adapter **command name** (e.g. \`uwf-hermes\`), not the npm package name.
+
+**Preset providers** — when using a preset name, \`--base-url\` is auto-filled and can be omitted:
+
+| Provider | Name | Default base URL |
+|----------|------|-----------------|
+| OpenAI | \`openai\` | https://api.openai.com/v1 |
+| xAI | \`xai\` | https://api.x.ai/v1 |
+| OpenRouter | \`openrouter\` | https://openrouter.ai/api/v1 |
+| Venice | \`venice\` | https://api.venice.ai/api/v1 |
+| Dashscope | \`dashscope\` | https://dashscope.aliyuncs.com/compatible-mode/v1 |
+| DeepSeek | \`deepseek\` | https://api.deepseek.com/v1 |
+| SiliconFlow | \`siliconflow\` | https://api.siliconflow.cn/v1 |
+| VolcEngine | \`volcengine\` | https://ark.cn-beijing.volces.com/api/v3 |
+| Kimi (Moonshot) | \`kimi\` | https://api.moonshot.cn/v1 |
+| GLM (Zhipu AI) | \`glm\` | https://open.bigmodel.cn/api/paas/v4 |
+| StepFun | \`stepfun\` | https://api.stepfun.com/v1 |
+| MiniMax | \`minimax\` | https://api.minimax.io/v1 |
+| Ollama (local) | \`ollama\` | http://localhost:11434/v1 |
+
+For **non-preset providers**, you must specify \`--base-url\` manually.
 
 Example:
 \`\`\`bash
@@ -144,6 +201,8 @@ Each command outputs a complete SKILL.md with YAML frontmatter. Use your agent f
 
 Verify skills are installed by listing them (e.g. \`skills_list()\`) and confirming all three appear.
 
+**⚠ After saving all skills, start a new session** so the agent loads the updated skill content. Skills saved in the current session are not active until the next session.
+
 ### Step 4 — Verify end-to-end
 
 Create a minimal workflow file to test your setup:
@@ -162,7 +221,7 @@ roles:
     frontmatter:
       type: object
       properties:
-        $status: { enum: [done] }
+        $status: { const: done }
         message: { type: string }
       required: [$status, message]
 graph:
@@ -189,11 +248,25 @@ If the thread reaches \`$END\` with status \`completed\`, the setup is working.
 ### Step 1 — Update packages
 
 \`\`\`bash
-pnpm add -g @united-workforce/cli@latest    # or: npm install -g @united-workforce/cli@latest
-uwf --version   # should print ${CLI_VERSION}
+# Using pnpm
+pnpm add -g @united-workforce/cli@latest
 
-# Also update your adapter(s)
+# Using npm
+npm install -g @united-workforce/cli@latest
+\`\`\`
+
+\`\`\`bash
+uwf --version   # should print ${CLI_VERSION}
+\`\`\`
+
+Also update your adapter(s):
+
+\`\`\`bash
+# pnpm
 pnpm add -g @united-workforce/agent-hermes@latest
+
+# npm
+npm install -g @united-workforce/agent-hermes@latest
 \`\`\`
 
 ### Step 2 — Regenerate skills
@@ -206,6 +279,8 @@ uwf prompt workflow-authoring  # → update skill "uwf-workflow-authoring"
 uwf prompt adapter-developing  # → update skill "uwf-adapter-developing"
 \`\`\`
 
+**⚠ After updating skills, start a new session** to load the new skill content.
+
 ### Step 3 — Migrate workflow YAML files (if needed)
 
 Check the changelog for breaking changes. Known migrations:
@@ -224,6 +299,17 @@ Check the changelog for breaking changes. Known migrations:
 
 Update all \`.workflow/\` and \`.workflows/\` YAML files in your projects. \`uwf workflow add\` will reject files with the old \`_\` syntax.
 
+- **v0.2.1**: \`$status: { enum: [value] }\` → \`$status: { const: "value" }\`. The validator no longer accepts \`enum\` for \`$status\`. Update all workflow YAML files:
+  \`\`\`yaml
+  # Before (v0.2.0)
+  $status: { enum: [done] }
+  $status: { type: string, enum: ["ready", "failed"] }
+
+  # After (v0.2.1+)
+  $status: { const: "done" }
+  # For multi-exit, use oneOf with const (unchanged)
+  \`\`\`
+
 ### Step 4 — Verify
 
 \`\`\`bash

packages/cli/src/commands/thread.ts

@@ -1001,12 +1001,6 @@ function spawnAgent(
       stdio: ["ignore", "pipe", "pipe"],
       maxBuffer: 50 * 1024 * 1024, // 50 MB — stream-json output can be large
       cwd,
-      env: {
-        ...process.env,
-        NODE_OPTIONS: [process.env.NODE_OPTIONS, "--disable-warning=ExperimentalWarning"]
-          .filter(Boolean)
-          .join(" "),
-      },
     });
   } catch (e) {
     const err = e as NodeJS.ErrnoException & { stderr?: Buffer | string | null };
@@ -1254,12 +1248,6 @@ async function cmdThreadStepBackground(
   const child = spawn(scriptPath, args, {
     detached: true,
     stdio: "ignore",
-    env: {
-      ...process.env,
-      NODE_OPTIONS: [process.env.NODE_OPTIONS, "--disable-warning=ExperimentalWarning"]
-        .filter(Boolean)
-        .join(" "),
-    },
   });
 
   child.unref();

packages/cli/src/validate-semantic.ts

@@ -24,22 +24,22 @@ function isOneOfSchema(fm: unknown): fm is SchemaObj & { oneOf: SchemaObj[] } {
   return Array.isArray(obj.oneOf);
 }
 
-/** Check if a frontmatter schema declares "$status" as an enum (the required form for user roles). */
-function hasStatusEnum(fm: unknown): boolean {
+/** Check if a frontmatter schema declares "$status" as const (flat schema form). */
+function hasStatusConst(fm: unknown): boolean {
   if (typeof fm !== "object" || fm === null) return false;
   const obj = fm as SchemaObj;
   const props = obj.properties as Record<string, SchemaObj> | undefined;
   if (!props?.$status) return false;
-  return Array.isArray(props.$status.enum);
+  return typeof props.$status.const === "string";
 }
 
-/** Extract status values from an enum-based $status field. */
-function getEnumStatuses(fm: SchemaObj): string[] {
+/** Extract status values from a const-based $status field. */
+function getConstStatuses(fm: SchemaObj): string[] {
   const props = fm.properties as Record<string, SchemaObj> | undefined;
   if (!props?.$status) return [];
   const statusDef = props.$status;
-  if (!Array.isArray(statusDef.enum)) return [];
-  return statusDef.enum as string[];
+  if (typeof statusDef.const === "string") return [statusDef.const];
+  return [];
 }
 
 /** Get property names from a schema object. */
@@ -248,21 +248,21 @@ function checkRoleConsistency(payload: WorkflowPayload, errors: string[]): void
       checkOneOfDiscriminant(roleName, variants, statuses, errors);
       checkStatusEdges(roleName, graphKeys, new Set(statuses), errors);
       checkMultiExitMustache(roleName, graphEntry, variants, errors);
-    } else if (hasStatusEnum(fm)) {
-      const statuses = getEnumStatuses(fm as SchemaObj);
+    } else if (hasStatusConst(fm)) {
+      const statuses = getConstStatuses(fm as SchemaObj);
       checkStatusEdges(roleName, graphKeys, new Set(statuses), errors);
-      // For enum-based schemas, mustache vars come from the flat properties
-      checkEnumMustache(roleName, graphEntry, fm as SchemaObj, errors);
+      // For const-based flat schemas, mustache vars come from the flat properties
+      checkFlatMustache(roleName, graphEntry, fm as SchemaObj, errors);
     } else {
       errors.push(
-        `role "${roleName}" must define "$status" as an enum (or oneOf const) in frontmatter`,
+        `role "${roleName}" must define "$status" as const (or oneOf with const) in frontmatter`,
       );
     }
   }
 }
 
 /** Check mustache vars in all edge prompts against flat schema properties. */
-function checkEnumMustache(
+function checkFlatMustache(
   roleName: string,
   graphEntry: Record<string, { role: string; prompt: string }>,
   fm: SchemaObj,

packages/eval/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@united-workforce/eval",
-  "version": "0.1.3",
+  "version": "0.1.4",
   "private": false,
   "files": [
     "src",

packages/eval/src/commands/list.ts

@@ -6,7 +6,7 @@ import { formatList, selectEntries } from "./format.js";
 import { readEvalEntries } from "./read.js";
 
 const log = createLogger({ sink: { kind: "stderr" } });
-const LOG_LIST = "L5KX9R2B";
+const LOG_LIST = "H5KX9R2B";
 
 type ListCliOptions = {
   task: string | undefined;

packages/util-agent/__tests__/build-output-format-instruction.test.ts

@@ -143,7 +143,7 @@ describe("buildOutputFormatInstruction", () => {
         {
           type: "object",
           properties: {
-            $status: { type: "string", enum: ["approved"] },
+            $status: { const: "approved" },
             branch: { type: "string" },
           },
           required: ["$status"],
@@ -151,7 +151,7 @@ describe("buildOutputFormatInstruction", () => {
         {
           type: "object",
           properties: {
-            $status: { type: "string", enum: ["rejected"] },
+            $status: { const: "rejected" },
             comments: { type: "string" },
           },
           required: ["$status"],
@@ -225,4 +225,34 @@ describe("buildOutputFormatInstruction", () => {
     const result = buildOutputFormatInstruction({});
     expect(result).toContain("Focus exclusively on YOUR role");
   });
+
+  test("renders const value as literal in flat schema example", () => {
+    const schema = {
+      type: "object",
+      properties: {
+        $status: { type: "string", const: "greeted" },
+        message: { type: "string" },
+      },
+      required: ["$status", "message"],
+    };
+    const result = buildOutputFormatInstruction(schema);
+    expect(result).toContain("$status: greeted");
+    expect(result).toContain("fixed value");
+    expect(result).not.toContain("$status: <string>");
+  });
+
+  test("renders const value for non-string types", () => {
+    const schema = {
+      type: "object",
+      properties: {
+        count: { type: "number", const: 42 },
+        done: { type: "boolean", const: true },
+      },
+      required: ["count", "done"],
+    };
+    const result = buildOutputFormatInstruction(schema);
+    expect(result).toContain("count: 42");
+    expect(result).toContain("done: true");
+    expect(result).toContain("fixed value");
+  });
 });

packages/util-agent/__tests__/build-thread-progress.test.ts

@@ -0,0 +1,59 @@
+import type { StepContext } from "@united-workforce/protocol";
+import { describe, expect, test } from "vitest";
+import { buildThreadProgress } from "../src/build-thread-progress.js";
+
+function makeStep(role: string): StepContext {
+  return {
+    role,
+    output: {},
+    detail: "0000000000000" as string,
+    agent: "uwf-mock",
+    edgePrompt: "",
+    startedAtMs: 0,
+    completedAtMs: 0,
+    cwd: "",
+    assembledPrompt: null,
+    usage: null,
+    content: null,
+  };
+}
+
+describe("buildThreadProgress", () => {
+  test("first step of thread", () => {
+    const result = buildThreadProgress([], "proponent");
+    expect(result).toContain("## Thread Progress");
+    expect(result).toContain("first step");
+    expect(result).toContain("first time");
+    expect(result).toContain("proponent");
+  });
+
+  test("second step, role not seen before", () => {
+    const steps = [makeStep("opponent")];
+    const result = buildThreadProgress(steps, "proponent");
+    expect(result).toContain("Thread step 2");
+    expect(result).toContain("spoken 0 times");
+  });
+
+  test("role has spoken once before", () => {
+    const steps = [makeStep("proponent"), makeStep("opponent")];
+    const result = buildThreadProgress(steps, "proponent");
+    expect(result).toContain("Thread step 3");
+    expect(result).toContain("spoken 1 time before");
+    // singular "time" not "times"
+    expect(result).not.toContain("1 times");
+  });
+
+  test("role has spoken multiple times", () => {
+    const steps = [
+      makeStep("proponent"),
+      makeStep("opponent"),
+      makeStep("proponent"),
+      makeStep("opponent"),
+      makeStep("proponent"),
+      makeStep("opponent"),
+    ];
+    const result = buildThreadProgress(steps, "proponent");
+    expect(result).toContain("Thread step 7");
+    expect(result).toContain("spoken 3 times");
+  });
+});

packages/util-agent/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@united-workforce/util-agent",
-  "version": "0.1.0",
+  "version": "0.1.1",
   "files": [
     "src",
     "dist",

packages/util-agent/src/build-output-format-instruction.ts

@@ -74,6 +74,10 @@ function collectObjectSchemas(schema: JSONSchema): JSONSchema[] {
 }
 
 function resolvePropertySchema(prop: JSONSchema): JSONSchema {
+  if (prop.const !== undefined) {
+    return prop;
+  }
+
   if (Array.isArray(prop.enum) && prop.enum.length > 0) {
     return prop;
   }
@@ -113,6 +117,11 @@ function buildPropertyExampleLine(prop: SchemaProperty): string {
     commentParts.push("required");
   }
 
+  if (resolved.const !== undefined) {
+    commentParts.push("fixed value");
+    return `${prop.name}: ${formatYamlScalar(resolved.const)}${buildPropertyComment(commentParts)}`;
+  }
+
   if (Array.isArray(resolved.enum) && resolved.enum.length > 0) {
     const enumValues = resolved.enum.map((v) => String(v));
     commentParts.push(...enumValues);

packages/util-agent/src/build-thread-progress.ts

@@ -0,0 +1,27 @@
+import type { StepContext } from "@united-workforce/protocol";
+
+/**
+ * Build a compact thread-progress summary so the agent knows where it is
+ * in the conversation without making tool calls to count steps.
+ *
+ * Example output:
+ *   ## Thread Progress
+ *   Thread step 6. You (proponent) have spoken 2 times before this turn.
+ */
+export function buildThreadProgress(steps: StepContext[], role: string): string {
+  const totalSteps = steps.length;
+  const roleVisits = steps.filter((s) => s.role === role).length;
+
+  const parts = [`## Thread Progress`];
+  if (totalSteps === 0) {
+    parts.push(
+      `This is the first step of the thread. You (${role}) are speaking for the first time.`,
+    );
+  } else {
+    parts.push(
+      `Thread step ${totalSteps + 1}. You (${role}) have spoken ${roleVisits} time${roleVisits === 1 ? "" : "s"} before this turn.`,
+    );
+  }
+
+  return parts.join("\n");
+}

packages/util-agent/src/index.ts

@@ -1,6 +1,7 @@
 export { buildContinuationPrompt } from "./build-continuation-prompt.js";
 export { buildOutputFormatInstruction } from "./build-output-format-instruction.js";
 export { buildRolePrompt } from "./build-role-prompt.js";
+export { buildThreadProgress } from "./build-thread-progress.js";
 export type { BuildContextMeta } from "./context.js";
 export { buildContext, buildContextWithMeta } from "./context.js";
 export type { ExtractResult, ResolvedLlmProvider } from "./extract.js";

packages/util/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@united-workforce/util",
-  "version": "0.1.2",
+  "version": "0.1.4",
   "files": [
     "src",
     "dist",

packages/util/src/usage-reference.ts

@@ -140,5 +140,18 @@ For specific scenarios, run the corresponding \`uwf prompt\` command:
 |----------|---------|-------------|
 | Writing workflow YAML | \`uwf prompt workflow-authoring\` | Designing roles, conditions, graphs, and edge prompts |
 | Building a new agent adapter | \`uwf prompt adapter-developing\` | Creating a new \`uwf-<name>\` CLI adapter |
+
+## Upgrading
+
+\`\`\`bash
+# Install the latest version
+pnpm add -g @united-workforce/cli@latest @united-workforce/agent-hermes@latest
+# or: npm install -g @united-workforce/cli@latest @united-workforce/agent-hermes@latest
+
+# Verify
+uwf --version
+
+# Then run uwf prompt bootstrap and follow the upgrade instructions
+\`\`\`
 `;
 }

packages/util/src/workflow-authoring-reference.ts

@@ -28,6 +28,7 @@ roles:                         # named actors
       2. Do that
     output: "..."              # what the agent should produce
     frontmatter:               # JSON Schema for structured output
+      type: object
       oneOf:
         - properties:
             $status: { const: "ready" }
@@ -71,10 +72,13 @@ The \`frontmatter\` field is a standard JSON Schema. It defines the structured f
 
 ### \`$status\` Field
 
-\`$status\` is the only standard field. Its value determines which graph edge the moderator follows. Use \`const\` to constrain each variant:
+\`$status\` is the only standard field. Its value determines which graph edge the moderator follows.
+
+**Multi-exit (oneOf)** — use \`const\` to constrain each variant:
 
 \`\`\`yaml
 frontmatter:
+  type: object
   oneOf:
     - properties:
         $status: { const: "done" }
@@ -86,26 +90,25 @@ frontmatter:
       required: [$status, error]
 \`\`\`
 
-### Custom Fields
-
-Add any fields you need for data passing between roles. These are available in edge prompts via Mustache templates.
-
-### Flat Schema (Single Status)
-
-When a role has only one outcome, use \`enum\` with a single value:
+**Single-exit (flat schema)** — same syntax, just no \`oneOf\` wrapper:
 
 \`\`\`yaml
 frontmatter:
   type: object
   properties:
-    $status:
-      type: string
-      enum: [done]
+    $status: { const: "done" }
     summary: { type: string }
   required: [$status, summary]
 \`\`\`
 
-Note: \`$status: { const: "done" }\` is **not** valid in flat schemas — the validator requires \`enum\` or \`oneOf\` with \`const\`. Use \`const\` only inside \`oneOf\` variants.
+**Important rules:**
+- \`type: object\` is **required** at the top level of frontmatter (both flat and oneOf)
+- \`$status\` always uses \`const: "value"\` — simple and consistent
+- \`enum\` is **not supported** for \`$status\` — the validator will reject it
+
+### Custom Fields
+
+Add any fields you need for data passing between roles. These are available in edge prompts via Mustache templates.
 
 ## Graph Routing