Testing/CI/tooling consistency (#9,#20,#21,#22,#23,#28) (#59)

Co-authored-by: claude <claude@jpaul.io>
Co-committed-by: claude <claude@jpaul.io>

modules/24-assistive-agents/README.md

@@ -214,6 +214,10 @@ You're reviewing a branch that adds a `clear` command to the tasks-app. The diff
    python reviewer.py apply my-review.json
    ```
 
+   (If your assistant wrapped the JSON in a ```` ```json ```` code fence even though the prompt said
+   "JSON only," don't worry — `apply` tolerates a fenced or prose-wrapped response and reads the JSON
+   out of it.)
+
 4. **Make the human decision.** Open `feature.patch` and check the agent's headline claim: the
    `clear` branch in `cli.py` never calls `save(tlist)`, so it prints "cleared all tasks" while
    `tasks.json` is untouched — a silent no-op, the exact kind of plausibility trap Module 10 trained

modules/24-assistive-agents/lab/reviewer.py

@@ -19,6 +19,24 @@ from pathlib import Path
 
 HERE = Path(__file__).parent
 
+
+def load_json_response(path: Path):
+    """Parse the JSON the AI returned.
+
+    Chat assistants very often wrap their output in a ```json ... ``` code fence (or add a line of
+    prose) even when told to "return only the JSON" — so a strict json.loads on the raw paste fails
+    on the most likely real output. Try a strict parse first; if that fails, fall back to the
+    outermost { ... } block, which survives a code fence or surrounding text. Stdlib only."""
+    raw = path.read_text()
+    try:
+        return json.loads(raw)
+    except json.JSONDecodeError:
+        start, end = raw.find("{"), raw.rfind("}")
+        if start != -1 and end > start:
+            return json.loads(raw[start : end + 1])
+        raise
+
+
 PROMPT_HEADER = """\
 You are an assistive code reviewer. Follow the rubric below exactly, then review the diff that
 follows it. Return ONLY the JSON object the rubric specifies — no prose before or after.
@@ -40,7 +58,7 @@ def cmd_prompt(args: argparse.Namespace) -> int:
 
 def cmd_apply(args: argparse.Namespace) -> int:
     try:
-        review = json.loads(Path(args.response).read_text())
+        review = load_json_response(Path(args.response))
     except (json.JSONDecodeError, FileNotFoundError) as exc:
         print(f"error: could not read a JSON review from {args.response}: {exc}")
         return 1

modules/24-assistive-agents/lab/triage.py

@@ -39,6 +39,23 @@ def allowed_labels(taxonomy_text: str) -> set[str]:
     return set(LABEL_RE.findall(taxonomy_text))
 
 
+def load_json_response(path: Path):
+    """Parse the JSON the AI returned.
+
+    Chat assistants very often wrap their output in a ```json ... ``` code fence (or add a line of
+    prose) even when told to "return only the JSON" — so a strict json.loads on the raw paste fails
+    on the most likely real output. Try a strict parse first; if that fails, fall back to the
+    outermost { ... } block, which survives a code fence or surrounding text. Stdlib only."""
+    raw = path.read_text()
+    try:
+        return json.loads(raw)
+    except json.JSONDecodeError:
+        start, end = raw.find("{"), raw.rfind("}")
+        if start != -1 and end > start:
+            return json.loads(raw[start : end + 1])
+        raise
+
+
 def cmd_prompt(args: argparse.Namespace) -> int:
     taxonomy = Path(args.taxonomy).read_text()
     issue = Path(args.issue).read_text()
@@ -49,7 +66,7 @@ def cmd_prompt(args: argparse.Namespace) -> int:
 def cmd_apply(args: argparse.Namespace) -> int:
     allowed = allowed_labels(Path(args.taxonomy).read_text())
     try:
-        sug = json.loads(Path(args.response).read_text())
+        sug = load_json_response(Path(args.response))
     except (json.JSONDecodeError, FileNotFoundError) as exc:
         print(f"error: could not read a JSON suggestion from {args.response}: {exc}")
         return 1