Mostly cron-related fixes and bug report; one unrelated model metadata PR

Fixes on record

Merged to main. A stamp counts the issues a fix is linked to.

• #7453 fix(cron): salvage cron fix PRs #6917 #6810

  merged to main

  files: cron/jobs.py, cron/scheduler.py

  Show the diff

  • cron/jobs.py

    @@ -31,7 +31,7 @@
     # Configuration
     # =============================================================================
     
    -HERMES_DIR = get_hermes_home()
    +HERMES_DIR = get_hermes_home().resolve()
     CRON_DIR = HERMES_DIR / "cron"
     JOBS_FILE = CRON_DIR / "jobs.json"
     OUTPUT_DIR = CRON_DIR / "output"
    @@ -338,10 +338,12 @@ def load_jobs() -> List[Dict[str, Any]]:
                         save_jobs(jobs)
                         logger.warning("Auto-repaired jobs.json (had invalid control characters)")
                     return jobs
    -        except Exception:
    -            return []
    -    except IOError:
    -        return []
    +        except Exception as e:
    +            logger.error("Failed to auto-repair jobs.json: %s", e)
    +            raise RuntimeError(f"Cron database corrupted and unrepairable: {e}") from e
    +    except IOError as e:
    +        logger.error("IOError reading jobs.json: %s", e)
    +        raise RuntimeError(f"Failed to read cron database: {e}") from e
     
     
     def save_jobs(jobs: List[Dict[str, Any]]):
    @@ -452,6 +454,7 @@ def create_job(
             "last_run_at": None,
             "last_status": None,
             "last_error": None,
    +        "last_delivery_error": None,
             # Delivery configuration
             "deliver": deliver,
             "origin": origin,  # Tracks where job was created for "origin" delivery
    @@ -620,8 +623,8 @@ def mark_job_run(job_id: str, success: bool, error: Optional[str] = None,
     
                 save_jobs(jobs)
                 return
    -    
    -    save_jobs(jobs)
    +
    +    logger.warning("mark_job_run: job_id %s not found, skipping save", job_id)
     
     
     def advance_next_run(job_id: str) -> bool:

  • cron/scheduler.py

    @@ -769,7 +769,7 @@ def run_job(job: dict) -> tuple[bool, str, str, Optional[str]]:
                 _cron_pool.shutdown(wait=False, cancel_futures=True)
                 raise
             finally:
    -            _cron_pool.shutdown(wait=False)
    +            _cron_pool.shutdown(wait=False, cancel_futures=True)
     
             if _inactivity_timeout:
                 # Build diagnostic summary from the agent's activity tracker.