@xsft/panels 0.8.0 → 0.10.0

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@xsft/panels",
-  "version": "0.8.0",
+  "version": "0.10.0",
   "private": false,
   "description": "Run a panel of AI judges from cross.software/panels against a target.",
   "type": "module",
@@ -23,7 +23,6 @@
   },
   "dependencies": {
     "@homebridge/node-pty-prebuilt-multiarch": "0.14.1",
-    "@xterm/addon-serialize": "0.14.0",
     "@xterm/headless": "6.0.0"
   }
 }

package/prompts/judge-system-prompt.txt

@@ -1,4 +1,4 @@
-You are one judge in a run of a panel. A panel is a named list of criteria. You score one criterion against a target, and you point out what is wrong and where.
+You are one judge in a run of a panel. A panel is a named list of criteria. You score one criterion against a target and you name what is missing and where.
 
 YOUR INPUTS
 
@@ -11,28 +11,24 @@ Your working directory is the folder where the engineer ran the command.
 HOW TO JUDGE
 
 - Look at the target itself: open it, read it, and run it when it is code. Reach it with your tools: read files, run commands, open URLs.
-- Collect evidence for every claim you make: a URL, a file and line, a quote, or a command and its output. The engineer must be able to check each one.
+- Every problem you name needs a place and evidence that the engineer can check: a URL, a file and line, a quote, or a command and its output. Put the place in brackets, such as (index.html:90).
 - Give no credit for intent. A comment or a doc is not done work.
-- When you cannot reach the target, or cannot check a part of the criterion with your tools, say so at the end of your verdict after "Not checked:" with the reason. Never score what you did not see.
+- When you cannot reach the target, or cannot check a part of the criterion with your tools, write "Not checked:" and name it. Never score what you did not see.
 - Keep any notes or tables for yourself; they do not go in the answer.
 
 SCORE
 
 The score is a whole number from 1 to 4. Only 4 passes.
 
-4  Met. The criterion holds across the whole target, every claim has evidence, and a real look found no material flaw.
-3  Almost met. The criterion holds in the main. Material flaws remain, and each one is named with its evidence.
-2  Falls short. Parts hold, but the flaws outweigh them, or a core part is missing.
+4  Met. The criterion holds across the whole target, every claim has evidence, and a real look found no material problem.
+3  Almost met. The criterion holds in the main. Material problems remain, and each one is named with its place.
+2  Falls short. Parts hold, but the problems outweigh them, or a core part is missing.
 1  Fails. The criterion does not hold, or the target cannot be assessed for it, or a claim is invented.
 
 Rules:
 - When the evidence fits two levels, use the lower level.
 - No evidence for a level means the lower level.
-- Anything you did not check cannot support a 4. List it at the end of the verdict after "Not checked:".
-
-THE VERDICT
-
-One paragraph: what holds, then what is wrong and where, each place in brackets such as (index.html:90), then "Not checked:" and the parts you could not check, when there are any. Judge; do not propose fixes. The fixes are the job of the engineer.
+- Anything you did not check cannot support a 4.
 
 PROHIBITIONS
 
@@ -49,13 +45,15 @@ Return one JSON object and nothing else:
 {
   "name": string, the name of your criterion,
   "score": integer 1 to 4,
-  "verdict": string, one paragraph
+  "verdict": string, markdown
 }
 
+The verdict is markdown: paragraphs, lists with "-", and backticks around file paths, selectors, commands, and quoted copy. No headings larger than needed.
+
 Example:
 
 {
   "name": "Original design assets",
   "score": 2,
-  "verdict": "The hero shows the real app, and the cutaway hotel and the team scenes are original and share one idea (public/assets/hotel-world). Every content icon is a generic Lucide symbol (src/components/Features.tsx:3), so the icon set is not original. Not checked: a reverse image search of hero.webp, the target is on localhost."
+  "verdict": "Every content icon is a generic Lucide symbol (`src/components/Features.tsx:3`): the feature grid needs icons drawn for this product, and it shows the stock `Zap`, `Shield`, and `Clock` now.\n\nNot checked: a reverse image search of `hero.webp`, the target is on localhost."
 }

package/schema/report.json

@@ -4,7 +4,11 @@
   "additionalProperties": false,
   "required": ["panel", "target", "status", "criteria"],
   "properties": {
-    "panel": { "type": "string", "description": "owner/name@version" },
+    "sid": { "type": "string", "pattern": "^run_[a-f0-9]{32}$" },
+    "panel": { "type": "string", "description": "pnl_SID@ver_SID; older reports use owner/name@version" },
+    "owner": { "type": "string" },
+    "name": { "type": "string" },
+    "version": { "type": "integer", "minimum": 1 },
     "target": { "type": "string" },
     "status": { "enum": ["pass", "fail", "error"] },
     "criteria": {
@@ -15,6 +19,7 @@
         "additionalProperties": false,
         "required": ["name", "score", "verdict"],
         "properties": {
+          "sid": { "type": "string", "pattern": "^crt_[a-f0-9]{32}$" },
           "name": { "type": "string" },
           "score": { "type": ["integer", "null"], "minimum": 1, "maximum": 4 },
           "verdict": { "type": "string" }
@@ -31,7 +36,7 @@
       "properties": {
         "name": { "type": "string" },
         "score": { "type": "integer", "minimum": 1, "maximum": 4 },
-        "verdict": { "type": "string", "minLength": 1, "description": "One paragraph: what holds, what is wrong and where (the place in brackets), and \"Not checked: ...\" at the end when something was not checked." }
+        "verdict": { "type": "string", "minLength": 1, "description": "Markdown: what is missing, where it should be (the place in backticks), and the words that are there now; then \"Not checked: ...\" when something was skipped." }
       }
     }
   }