@f-o-h/cli 0.1.36 → 0.1.37

package/README.md

@@ -4,7 +4,7 @@ AI-operator provisioning CLI for Front Of House.
 
 Public mirror: https://github.com/iiko38/front-of-house-cli
 
-Current published baseline: `@f-o-h/cli@0.1.36`
+Current published baseline: `@f-o-h/cli@0.1.37`
 
 This mirror is a generated release artifact. The private product monorepo is not
 published here, and no open-source license is granted unless stated separately.
@@ -123,9 +123,13 @@ foh eval external-agent run \
   --prompt-version blank-setup.v1
 ```
 
-The command writes a versioned prompt, launches an instrumented shell, captures
-FOH CLI commands into `commands.ndjson`, and finalizes `run.json` as an
-`external_agent_run.v1` artifact when the shell exits.
+The command writes a versioned prompt, launches an instrumented shell, captures
+FOH CLI commands into `commands.ndjson`, and finalizes `run.json` as an
+`external_agent_run.v1` artifact when the shell exits.
+
+Run artifacts include `eval_state` so repeated benchmark runs make reuse
+explicit: org, agent, and widget reuse are expected; fresh paid phone-number
+creation is not expected.
 
 For guarded programmable-runner planning:
 

package/dist/foh.js

@@ -32755,7 +32755,7 @@ var StdioServerTransport = class {
 };
 
 // src/lib/cli-version.ts
-var CLI_VERSION = "0.1.36";
+var CLI_VERSION = "0.1.37";
 
 // src/commands/mcp-serve.ts
 var DEFAULT_TIMEOUT_MS = 12e4;
@@ -39292,6 +39292,17 @@ function buildExecutedRunArtifact(input) {
     ],
     commands_run: commands.map((command) => command.command),
     docs_pages_used: [],
+    eval_state: {
+      org_reuse_expected: true,
+      agent_reuse_expected: true,
+      widget_reuse_expected: true,
+      fresh_org_expected: false,
+      fresh_agent_expected: false,
+      phone_purchase_expected: false,
+      paid_resource_creation_expected: false,
+      spend_policy_expected: NO_SPEND_POLICY,
+      rationale: "Mass external-agent evals benchmark public docs/CLI/API clarity; reuse avoids paid phone and Twilio inventory churn."
+    },
     artifacts: {
       terminal_transcript: relativeArtifactName(input.run.outputs.jsonl),
       command_log: (0, import_fs14.existsSync)((0, import_path12.join)(input.run.run_dir, "commands.ndjson")) ? "commands.ndjson" : null,
@@ -39509,6 +39520,19 @@ function writeSession(runDir, session) {
 `, "utf8");
   return path2;
 }
+function buildDefaultEvalState() {
+  return {
+    org_reuse_expected: true,
+    agent_reuse_expected: true,
+    widget_reuse_expected: true,
+    fresh_org_expected: false,
+    fresh_agent_expected: false,
+    phone_purchase_expected: false,
+    paid_resource_creation_expected: false,
+    spend_policy_expected: "no_spend",
+    rationale: "Mass external-agent evals benchmark public docs/CLI/API clarity; reuse avoids paid phone and Twilio inventory churn."
+  };
+}
 function buildRunArtifact(input) {
   const commands = readCommandRecords(input.runDir);
   const startedAt = String(input.session.started_at);
@@ -39545,6 +39569,7 @@ function buildRunArtifact(input) {
     ],
     commands_run: commands.map((command) => command.command),
     docs_pages_used: [],
+    eval_state: buildDefaultEvalState(),
     artifacts: {
       terminal_transcript: null,
       command_log: "commands.ndjson",
@@ -39651,6 +39676,7 @@ function registerEval(program3) {
       manual_intervention_count: 0,
       run_dir: runDir,
       prompt_path: promptPath,
+      eval_state: buildDefaultEvalState(),
       capture_env: {
         [EXTERNAL_AGENT_RUN_DIR_ENV]: runDir,
         [EXTERNAL_AGENT_PROMPT_VERSION_ENV]: promptVersion

package/examples/external-agent-run.example.json

@@ -38,6 +38,17 @@
     "https://frontofhouse.okii.uk/guides/cli-install-and-upgrade",
     "https://frontofhouse.okii.uk/guides/error-handling-and-debugging"
   ],
+  "eval_state": {
+    "org_reuse_expected": true,
+    "agent_reuse_expected": true,
+    "widget_reuse_expected": true,
+    "fresh_org_expected": false,
+    "fresh_agent_expected": false,
+    "phone_purchase_expected": false,
+    "paid_resource_creation_expected": false,
+    "spend_policy_expected": "no_spend",
+    "rationale": "Mass external-agent evals benchmark public docs/CLI/API clarity; reuse avoids paid phone and Twilio inventory churn."
+  },
   "artifacts": {
     "terminal_transcript": "terminal-transcript.txt",
     "proof_bundle": null,

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@f-o-h/cli",
-  "version": "0.1.36",
+  "version": "0.1.37",
   "description": "FOH CLI - AI-operator provisioning tool for Front Of House",
   "license": "UNLICENSED",
   "bin": {

package/schemas/external-agent-run.schema.json

@@ -67,6 +67,21 @@
       "type": "array",
       "items": { "type": "string" }
     },
+    "eval_state": {
+      "type": "object",
+      "properties": {
+        "org_reuse_expected": { "type": "boolean" },
+        "agent_reuse_expected": { "type": "boolean" },
+        "widget_reuse_expected": { "type": "boolean" },
+        "fresh_org_expected": { "type": "boolean" },
+        "fresh_agent_expected": { "type": "boolean" },
+        "phone_purchase_expected": { "type": "boolean" },
+        "paid_resource_creation_expected": { "type": "boolean" },
+        "spend_policy_expected": { "type": "string" },
+        "rationale": { "type": "string" }
+      },
+      "additionalProperties": true
+    },
     "artifacts": {
       "type": "object",
       "properties": {