chore: bump eval to 0.1.4

小橘 🍊（NEKO Team）

.changeset/inject-thread-progress.md

@@ -1,12 +0,0 @@
----
-"@united-workforce/agent-hermes": patch
-"@united-workforce/agent-claude-code": patch
-"@united-workforce/util-agent": patch
----
-
-feat: inject thread progress into agent prompt (#127)
-
-Agents now receive a "Thread Progress" section in their prompt showing the
-current step number and how many times the current role has spoken before.
-This eliminates the need for agents to make tool calls (terminal, delegate_task)
-just to count their own turn history.

examples/debate.yaml

@@ -1,63 +1,131 @@
-name: "debate"
+name: debate
-description: "Structured debate between two sides. Tests cross-process session resume."
+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:
+  proponent:
-    description: "Argues against the proposition"
+    description: "Argues FOR the proposition"
-    goal: |
+    goal: "Build a compelling case for the proposition through logical reasoning and evidence"
-      You are a skilled debater arguing AGAINST the proposition.
+    capabilities: []
-      Be logical, cite evidence, and directly address your opponent's points.
-      Keep each argument concise (under 200 words).
-    capabilities:
-      - argumentation
-      - critical-thinking
     procedure: |
-      1. If this is the opening, present your strongest argument against the proposition.
+      You are an experienced scholar arguing FOR 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.
+      ## Critical Thinking Framework (execute before every speech)
-    output: |
+
-      Provide your argument in the frontmatter.
+      ### A. Pre-speech reflection (internal, do not output)
-      Set status to "conceded" ONLY if you are genuinely convinced and wish to stop debating.
+      - Does every step in my argument chain hold? Any hidden assumptions or logical gaps?
-      Otherwise set status to "continue".
+      - 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:
+        $status: { const: done }
-          enum: ["continue", "conceded"]
+        summary: { type: string }
-        argument:
+        highlights: { type: string }
-          type: string
+        verdict: { type: string }
-      required: [$status, argument]
+      required: [$status, summary, highlights, verdict]
-  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]
 graph:
   $START:
-    new: { role: "against", prompt: "Present your opening argument against the proposition." }
+    new: { role: proponent, prompt: "The debate begins. You are arguing FOR the proposition. Present your opening argument." }
-    resume: { role: "against", prompt: "Review the previous debate output and continue the argument against the proposition." }
+    resume: { role: proponent, prompt: "The debate continues." }
-  against:
+
-    conceded: { role: "$END", prompt: "The against side conceded. Debate over." }
+  proponent:
-    continue: { role: "for", prompt: "Counter the opposing argument: {{{argument}}}" }
+    speak: { role: opponent, prompt: "Proponent argues:\n\n{{{argument}}}\n\nYou are the opponent. Counter this argument." }
-  for:
+    conceded: { role: host, prompt: "The proponent conceded: {{{reason}}}\n\nPlease summarize the debate." }
-    conceded: { role: "$END", prompt: "The for side conceded. Debate over." }
+    final: { role: opponent, prompt: "Proponent's closing statement:\n\n{{{closing}}}\n\nYou are the opponent. Deliver your final response." }
-    continue: { role: "against", prompt: "Counter the opposing argument: {{{argument}}}" }
+
+  opponent:
+    speak: { role: proponent, prompt: "Opponent argues:\n\n{{{argument}}}\n\nYou are the proponent. Counter this argument." }
+    conceded: { role: host, prompt: "The opponent conceded: {{{reason}}}\n\nPlease summarize the debate." }
+    final: { role: host, prompt: "Opponent's closing statement:\n\n{{{closing}}}\n\nThe debate is over. Please summarize." }
+
+  host:
+    done: { role: "$END", prompt: "Summary complete." }

packages/agent-claude-code/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@united-workforce/agent-claude-code",
-  "version": "0.1.2",
+  "version": "0.1.3",
   "files": [
     "src",
     "dist",

packages/agent-hermes/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@united-workforce/agent-hermes",
-  "version": "0.1.3",
+  "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/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

@@ -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/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/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@united-workforce/util",
-  "version": "0.1.3",
+  "version": "0.1.4",
   "files": [
     "src",
     "dist",