rename: braindump → coopertron (Coopertron 5000)

The tool names the whole experiment, not just this script, so it gets a
name with some personality. Repo, directory and command are `coopertron`;
"Coopertron 5000" is the display name in the README and the report title.
The activity the form captures is still a braindump.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>

synthesize.py

@@ -1,5 +1,5 @@
 #!/usr/bin/env python3
-"""braindump synthesize: turn an anonymous survey export into a review document.
+"""Coopertron 5000: turn an anonymous survey export into a review document.
 
 Pipeline (deterministic Python around two model stages):
 
@@ -162,7 +162,7 @@ class Gateway:
             f"{self.base}/chat/completions",
             data=json.dumps(body).encode("utf-8"),
             headers={"Authorization": f"Bearer {key}", "Content-Type": "application/json",
-                     "User-Agent": "braindump-synthesize/0.1"},
+                     "User-Agent": "coopertron/0.1"},
             method="POST",
         )
         try:
@@ -463,7 +463,7 @@ def render(loaded: dict, items: list[dict], clusters: dict, meta: dict) -> str:
         return f'> "{it["quote"]}" ({it["rid"]}, {it["q"]})'
 
     out: list[str] = []
-    out.append(f"# Braindump synthesis\n")
+    out.append(f"# Coopertron 5000 report\n")
     out.append(f"_Generated {meta['date']} from {meta['source']} · {n_resp} responses · "
                f"{len(items)} points · {len(clusters['themes'])} themes · model `{meta['model']}`_\n")
     out.append("Counts below are computed from the extracted points, not estimated by the model. "