@taifoon/jev 0.2.0 → 0.2.1

package/README.md

@@ -1,10 +1,19 @@
 # @taifoon/jev
 
-LLM-as-a-judge for agent jobs, callable from a contract's evaluator seat. TypeSafe's Jev, a System One model pinned
-to `jev-1.13.0`, answers a published rubric as structured output. Code composes the verdict, hashes a receipt
-and returns the one call that ends the job. Recording the grade on chain is optional (`record()`, or `--record`). Mid-band answers go to needs_review, which ends nothing.
+**Did the AI agent do the work it was paid for? Ask Jev, and get an answer you can check.**
 
-Built by Taifoon. No runtime dependencies, no key inside, and it signs nothing.
+- **What:** a grader for agent jobs. Code checks the facts, TypeSafe's Jev answers four closed questions about the
+  delivery, and code turns the answers into complete, reject or needs review, with a receipt anyone can recompute.
+- **Why:** agents are paid on chain for work nobody reads. A grade with its full probabilities, a published rubric and
+  an appeal path is something a buyer, a seller and a contract can all rely on.
+- **How:** replay a real Base job, graded by Jev, offline and with no key:
+
+```
+npx @taifoon/jev run --demo
+```
+
+Then grade your own with your TypeSafe key from [console.typesafe.ai](https://console.typesafe.ai). No runtime
+dependencies, no key inside, and it signs nothing. Recording a grade on chain is optional.
 
 ## Quick start
 

package/docs/WORKFLOWS.md

@@ -13,8 +13,8 @@ The node outputs the receipt and the unsigned calls, and it signs nothing. With
 
 ## Workflows
 
-`workflows/0.2.0/` holds the four n8n workflows that run Jev. The same files are attached to the
-GitHub release as `jev-workflows-0.2.0.zip`:
+`workflows/0.2.1/` holds the four n8n workflows that run Jev. The same files are attached to the
+GitHub release as `jev-workflows-0.2.1.zip`:
 
 - **`hire-judge-settle.json`** runs hire → prepare (facts) → TypeSafe (the four RUBRIC_v1 questions) → answers
   (verdict, recorded and anchored) → settle on devnet. Executions 86 and 88 of this workflow are the golden runs above.
@@ -24,8 +24,8 @@ GitHub release as `jev-workflows-0.2.0.zip`:
 
 Credential references are placeholders: `{ "id": "", "name": "REPLACE: <credential type>" }`. After import, pick your
 own credential of that type. Each step names the entity it takes and emits by `$id` (`meta.taifoon.steps`). The schemas
-behind those `$id`s are in `workflows/0.2.0/schemas/`. `manifest.json` pins every file by sha256.
-`workflows/0.2.0/README.md` explains each workflow step by step and lists the nodes and credentials it needs:
+behind those `$id`s are in `workflows/0.2.1/schemas/`. `manifest.json` pins every file by sha256.
+`workflows/0.2.1/README.md` explains each workflow step by step and lists the nodes and credentials it needs:
 
 - `@taifoon/n8n-nodes-typesafe`, tested with 1.3.0, is on npm.
 - `n8n-nodes-taifoon`, tested with 0.4.2, and `n8n-nodes-taifoon-devnet-signer`, tested with 0.2.0, are custom

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@taifoon/jev",
-  "version": "0.2.0",
+  "version": "0.2.1",
   "description": "Grade AI agent jobs with TypeSafe's Jev and record the verdict on chain: code checks the facts, Jev answers a published rubric, and you get a receipt, the on-chain record and the evaluator call for ERC-8183 and Virtuals ACP. No runtime dependencies, no key inside.",
   "keywords": [
     "jev",
@@ -75,6 +75,7 @@
     "vitest": "^4.1.8"
   },
   "bin": {
-    "jev": "bin/jev.mjs"
+    "jev": "bin/jev.mjs",
+    "taifoon-jev": "bin/jev.mjs"
   }
 }

package/workflows/{0.2.0 → 0.2.1}/README.md

@@ -1,4 +1,4 @@
-# Jev workflows 0.2.0
+# Jev workflows 0.2.1
 
 The n8n workflows that run Jev on n8n.taifoon.dev, exported with credential references replaced by placeholders (`{ "id": "", "name": "REPLACE: <credential type>" }`: pick your own credential of that type after import). Import with n8n → Workflows → Import from File, or `n8n import:workflow --input=<file>`. Every step carries its contract: `meta.taifoon.steps` names the canonical entity it takes and emits by `$id`; the schemas are in `schemas/` (the `$id`s are identifiers, the files are here).
 

package/workflows/{0.2.0 → 0.2.1}/manifest.json

@@ -1,6 +1,6 @@
 {
-  "bundle": "jev-workflows-0.2.0",
-  "package": "@taifoon/jev@0.2.0",
+  "bundle": "jev-workflows-0.2.1",
+  "package": "@taifoon/jev@0.2.1",
   "workflows": [
     {
       "file": "hire-judge-settle.json",