fix(hub): close seven bugs found in the refactor review

The PermissionRequest hook posted asks cut to the hub's field limits, so a signature covered less than Claude Code would run; it now posts nothing it cannot sign in full and leaves the decision to Claude Code with a reason on stderr. fields.seconds names the field the caller used in its error. Serving a stored page maps an OSError to 500 instead of a dropped connection. The natural-language line marks the register as seen before it builds the inbox, like the page does. do_POST runs every header guard (host, origin, client, content type, MCP) before it reads the body, so a refused request never costs its upload. The runner's reader closes stdout at EOF, because a close from the executing thread blocked on the buffer lock and could SIGPIPE a command still running. The page title counts only inbox items that are not snoozed.

Committed on the operator's word despite the gate: cost and time are estimates under 98 % other load and include eight new test cases.

🎯 Fix: 88 %
💥 Break: 3 %
💸 Cost: 106 %
⏱️ Time: 113 %
🛡️ Security: 100 %
🏆 Score: 71
🚦 Gate: ⛔ fix 88 % < 90; cost 106 % > 100, time 113 % > 100: ask the operator before the commit

```
/home/kevinveenbirkenbach/Repositories/github.com/kevinveenbirkenbach/skills/.worktrees/feature/kvb-hub
```

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

hub/kvb_hub/language.py

@@ -180,7 +180,9 @@ class Language:
         now = time.time()
         claims = read_claims(self.council)
         tasks = read_register(self.council / REGISTER)
-        items = self.inbox(now, tasks, self.directory(claims, read_jsonl(self.council / NEWS), now))
+        directory = self.directory(claims, read_jsonl(self.council / NEWS), now)
+        self.watch.see(tasks, now)
+        items = self.inbox(now, tasks, directory)
         agents = ordered({claim["agent"] for claim in claims if claim["agent"]} | set(priority(tasks)))
         shown_items = [{"id": item["id"], "kind": item["kind"], "title": item["title"][:200]} for item in items]
         return nl_actions(self.model.complete(nl_messages(text, shown_items, agents)), items, agents)