feat: automatic error feedback loop with bug report tracker (#80)

Errors and uncaught exceptions are now automatically captured, deduplicated,
persisted to a rotating log file, and filed as bug report tasks in the
existing task queue — giving Timmy a sovereign, local issue tracker with
zero new dependencies.

- Add RotatingFileHandler writing errors to logs/errors.log (5MB rotate, 5 backups)
- Add error capture module with stack-trace hashing and 5-min dedup window
- Add FastAPI exception middleware + global exception handler
- Instrument all background loops (briefing, thinking, task processor) with capture_error()
- Extend task queue with bug_report task type and auto-approve rule
- Fix auto-approve type matching (was ignoring task_type field entirely)
- Add /bugs dashboard page and /api/bugs JSON endpoints
- Add ERROR_CAPTURED and BUG_REPORT_CREATED event types for real-time feed
- Add BUGS nav link to desktop and mobile navigation
- Add 16 tests covering error capture, deduplication, and bug report routes

Co-authored-by: Alexander Payne <apayne@MM.local>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>

src/swarm/task_queue/models.py

@@ -74,8 +74,11 @@ class QueueTask:
 
 AUTO_APPROVE_RULES = [
     {"assigned_to": "timmy", "type": "chat_response"},
+    {"assigned_to": "timmy", "type": "thought"},
+    {"assigned_to": "timmy", "type": "internal"},
     {"assigned_to": "forge", "type": "run_tests"},
     {"priority": "urgent", "created_by": "timmy"},
+    {"type": "bug_report", "created_by": "system"},
 ]
 
 
@@ -87,7 +90,10 @@ def should_auto_approve(task: QueueTask) -> bool:
         match = True
         for key, val in rule.items():
             if key == "type":
-                continue  # type matching is informational for now
+                if task.task_type != val:
+                    match = False
+                    break
+                continue
             task_val = getattr(task, key, None)
             if isinstance(task_val, Enum):
                 task_val = task_val.value