Fix missing ClickUp comments on error status transitions and add pipeline error audit log

- File handler now captures DEBUG+ (was WARNING) for full pipeline visibility
- Add ClickUp comments at every error status transition (missing IMSURL, pipeline crash, content crash)
- Content watcher exception now also sets error status (was silently failing)
- Cora distributor resets matched error tasks to "running cora" when new XLSX arrives
- Add dedicated logs/pipeline_errors.log for tool-handled errors (audit trail)

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

cheddahbot/__main__.py

@@ -17,13 +17,13 @@ logging.basicConfig(
     datefmt="%H:%M:%S",
 )
 
-# Warnings and errors to rotating log file
+# All levels to rotating log file (DEBUG+)
 _log_dir = Path(__file__).resolve().parent.parent / "logs"
 _log_dir.mkdir(exist_ok=True)
 _file_handler = RotatingFileHandler(
     _log_dir / "cheddahbot.log", maxBytes=5 * 1024 * 1024, backupCount=5
 )
-_file_handler.setLevel(logging.WARNING)
+_file_handler.setLevel(logging.DEBUG)
 _file_handler.setFormatter(
     logging.Formatter("%(asctime)s [%(name)s] %(levelname)s: %(message)s")
 )

cheddahbot/scheduler.py

@@ -23,6 +23,19 @@ if TYPE_CHECKING:
 
 log = logging.getLogger(__name__)
 
+# Dedicated logger for "tool returned error but likely handled it" cases.
+# Writes to logs/pipeline_errors.log for manual review.
+_pipeline_err_log = logging.getLogger("cheddahbot.pipeline_errors")
+_pipeline_err_log.propagate = False
+_pe_dir = Path(__file__).resolve().parent.parent / "logs"
+_pe_dir.mkdir(exist_ok=True)
+_pe_handler = logging.FileHandler(_pe_dir / "pipeline_errors.log", encoding="utf-8")
+_pe_handler.setFormatter(
+    logging.Formatter("%(asctime)s | %(message)s")
+)
+_pipeline_err_log.addHandler(_pe_handler)
+_pipeline_err_log.setLevel(logging.INFO)
+
 HEARTBEAT_OK = "HEARTBEAT_OK"
 
 # Only tasks in these statuses are eligible for xlsx → ClickUp matching.
@@ -789,6 +802,11 @@ class Scheduler:
         money_site_url = matched_task.custom_fields.get("IMSURL", "") or ""
         if not money_site_url:
             log.warning("Task %s (%s) missing IMSURL — skipping", task_id, matched_task.name)
+            client.add_comment(
+                task_id,
+                "❌ Link building skipped — IMSURL field is empty. "
+                "Set the IMSURL field in ClickUp so the pipeline knows where to build links.",
+            )
             client.update_task_status(task_id, self.config.clickup.error_status)
             self._notify(
                 f"Folder watcher: **{filename}** matched task **{matched_task.name}** "
@@ -823,6 +841,10 @@ class Scheduler:
 
             if "Error" in result and "## Step" not in result:
                 # Pipeline failed — tool handles its own ClickUp error status
+                _pipeline_err_log.info(
+                    "LINKBUILDING | task=%s | file=%s | result=%s",
+                    task_id, filename, result[:500],
+                )
                 self._notify(
                     f"Folder watcher: pipeline **failed** for **{filename}**.\n"
                     f"Error: {result[:200]}",
@@ -847,6 +869,10 @@ class Scheduler:
 
         except Exception as e:
             log.error("Folder watcher pipeline error for %s: %s", filename, e)
+            client.add_comment(
+                task_id,
+                f"❌ Link building pipeline crashed.\n\nError: {str(e)[:2000]}",
+            )
             client.update_task_status(task_id, self.config.clickup.error_status)
         finally:
             self._unregister_execution(task_id)
@@ -990,6 +1016,10 @@ class Scheduler:
                 result = "Error: tool registry not available"
 
             if result.startswith("Error:"):
+                _pipeline_err_log.info(
+                    "CONTENT | task=%s | file=%s | result=%s",
+                    task_id, filename, result[:500],
+                )
                 self._notify(
                     f"Content watcher: pipeline **failed** for **{filename}**.\n"
                     f"Error: {result[:200]}",
@@ -1014,6 +1044,11 @@ class Scheduler:
 
         except Exception as e:
             log.error("Content watcher pipeline error for %s: %s", filename, e)
+            client.add_comment(
+                task_id,
+                f"❌ Content pipeline crashed.\n\nError: {str(e)[:2000]}",
+            )
+            client.update_task_status(task_id, self.config.clickup.error_status)
         finally:
             self._unregister_execution(task_id)
 
@@ -1125,6 +1160,7 @@ class Scheduler:
         has_lb = False
         has_content = False
         matched_names = []
+        matched_error_tasks = []
 
         for task in tasks:
             if task.status not in _CORA_ELIGIBLE_STATUSES:
@@ -1138,6 +1174,8 @@ class Scheduler:
                 continue
 
             matched_names.append(task.name)
+            if task.status == self.config.clickup.error_status:
+                matched_error_tasks.append(task)
             if task.task_type == "Link Building":
                 has_lb = True
             elif task.task_type in ("Content Creation", "On Page Optimization"):
@@ -1174,6 +1212,19 @@ class Scheduler:
             )
             return
 
+        # Reset any matched tasks that were in "error" back to "running cora"
+        # so the pipeline picks them up again.
+        for task in matched_error_tasks:
+            try:
+                client.update_task_status(task.id, "running cora")
+                client.add_comment(
+                    task.id,
+                    f"New Cora XLSX distributed — resetting from error to running cora.",
+                )
+                log.info("Distributor: reset task %s (%s) from error → running cora", task.id, task.name)
+            except Exception as e:
+                log.warning("Distributor: failed to reset task %s: %s", task.id, e)
+
         # Move original to processed/
         processed_dir = xlsx_path.parent / "processed"
         processed_dir.mkdir(exist_ok=True)