Fix --walltime CLI precedence over input.py settings

Previously, `--walltime` defaulted to `'00:00:00:00'` and was always
passed as a kwarg to `RMG.execute()`, silently overriding any `wallTime`
set in `input.py`. This meant users who set `wallTime` in their input
file and ran without `-t` would have their setting clobbered, giving an
effective wall time of zero (no limit).

Changes:
- Change `--walltime` default to `None`; only add `walltime` and
  `max_iterations` to the kwargs dict when they are explicitly provided
  on the command line. Input-file values are now respected by default.
- Move walltime/max_iterations override logic earlier in `execute()`
  (before database loading), so bad values produce an error immediately
  rather than after a potentially long setup phase.
- Extract walltime parsing into a `_parse_walltime_to_seconds()` static
  method for clarity and testability; improve the error message to
  include the invalid value.
- Log an explicit "Overriding walltime/max_iterations from input file
  (...) with command-line value (...)" message whenever the CLI does
  override the input file, making precedence visible in the run log.
- Replace bare `return` statements inside nested loops (walltime/maxiter
  termination paths) with an `end_early` flag + `break`, so that
  `make_seed_mech()`, `check_model()`, and `finish()` are still called
  on early termination. Suppress the "MODEL GENERATION COMPLETED" banner
  when ending early to avoid misleading output.
- Update docs (`running.rst`) and example input files to document CLI
  override behaviour and clarify that `wallTime` can be set in
  `input.py` while `--maxiter` is CLI-only.
- Update test for the new `None` default.

Author: rwest

documentation/source/users/rmg/running.rst

@@ -48,9 +48,9 @@ at the command line will print the documentation from ``util.py``, which is repr
 	  -P, --postprocess     postprocess profiling statistics from previous
 	                        [failed] run; does not run the simulation
 	  -t DD:HH:MM:SS, --walltime DD:HH:MM:SS
-	                        set the maximum execution time
+	                        set the maximum execution time (overrides input.py if provided)
 	  -i MAXITER, --maxiter MAXITER
-	                        set the maximum number of RMG iterations
+	                        set the maximum number of RMG iterations (overrides input.py if provided)
 	  -n MAXPROC, --maxproc MAXPROC
 	                        max number of processes used during reaction
 	                        generation
@@ -73,7 +73,7 @@ Run with multiprocessing for reaction generation and QMTP::
 
     python rmg.py -n <Max number of processes allowed> input.py 
 
-Run with setting a limit on the maximum execution time::
+Run with setting a limit on the maximum execution time (if specified, then the command-line value overrides any value read from ``input.py``)::
 
 	python rmg.py -t <DD:HH:MM:SS> input.py
 

examples/rmg/MR_test/input.py

@@ -260,9 +260,9 @@
     #Sets a time limit in the form DD:HH:MM:SS after which the RMG job will stop. Useful for profiling on jobs that
     #do not converge.
     #wallTime = '00:00:00', 
+    #When keepIrreversible=False (default), forces RMG to import library reactions as reversible. 
+    #Otherwise, if set to True, RMG will import library reactions while keeping the reversibility as specified.
     keepIrreversible=False,
-    #Forces RMG to import library reactions as reversible (default). Otherwise, if set to True, RMG will import library
-    #reactions while keeping the reversibility as as.
 )
 
 # optional module allows for correction to unimolecular reaction rates at low pressures and/or temperatures.

examples/rmg/commented/input.py

@@ -229,11 +229,11 @@
     # Helpful for seeing why some reactions are not appearing in the core model.
     # Individual writers can override this with their own saveEdge key.
     saveEdgeSpecies=False,
-    # Sets a time limit in the form DD:HH:MM:SS after which the RMG job will stop. Useful for profiling on jobs that
-    # do not converge.
-    # wallTime = '00:00:00',
-    # Forces RMG to import library reactions as reversible (default). Otherwise, if set to True, RMG will import library
-    # reactions while keeping the reversibility as as.
+    # Sets a time limit in the form DD:HH:MM:SS after (or shortly before) which the RMG job will stop.
+    # Useful for profiling on jobs that do not converge.
+    wallTime = '00:00:00:00',
+    # If keepIrreversible=False (default) forces RMG to import library reactions as reversible.
+    # If set to True, RMG will import library reactions while keeping the reversibility as specified.
     keepIrreversible=False,
     # Allows families with three products to react in the diverse direction (default).
     trimolecularProductReversible=True,

rmgpy/__main__.py

@@ -62,11 +62,13 @@ def main():
 
     kwargs = {
         'restart': args.restart,
-        'walltime': args.walltime,
         'maxproc': args.maxproc,
         'kineticsdatastore': args.kineticsdatastore,
-        'max_iterations': args.maxiter,
     }
+    if args.walltime is not None:
+        kwargs['walltime'] = args.walltime
+    if args.maxiter is not None:
+        kwargs['max_iterations'] = args.maxiter
 
     if args.profile:
         import cProfile

rmgpy/rmg/main.py

@@ -271,6 +271,19 @@ def clear(self):
         self.exec_time = []
         self.liquid_volumetric_mass_transfer_coefficient_power_law = None
 
+    @staticmethod
+    def _parse_walltime_to_seconds(walltime):
+        """
+        Convert walltime string DD:HH:MM:SS to seconds.
+        """
+        data = walltime.split(":")
+        if len(data) != 4:
+            raise ValueError("Invalid format for wall time {0}; should be DD:HH:MM:SS.".format(walltime))
+        try:
+            return int(data[-1]) + 60 * int(data[-2]) + 3600 * int(data[-3]) + 86400 * int(data[-4])
+        except ValueError as exc:
+            raise ValueError("Invalid format for wall time {0}; should be DD:HH:MM:SS.".format(walltime)) from exc
+
     def load_input(self, path=None):
         """
         Load an RMG job from the input file located at `input_file`, or
@@ -582,6 +595,24 @@ def initialize(self, **kwargs):
                 )
             )
 
+        if "walltime" in kwargs:
+            logging.info(
+                "Overriding walltime from input file (%s) with command-line value (%s).",
+                self.walltime,
+                kwargs["walltime"],
+            )
+            self.walltime = kwargs["walltime"]
+
+        if "max_iterations" in kwargs:
+            logging.info(
+                "Overriding max_iterations from input file (%s) with command-line value (%s).",
+                self.max_iterations,
+                kwargs["max_iterations"],
+            )
+            self.max_iterations = kwargs["max_iterations"]
+
+        self.walltime = self._parse_walltime_to_seconds(self.walltime)
+
         # Auto-select libraries if any field uses 'auto' or '<PAH_libs>'
         auto_select_libraries(self)
 
@@ -659,21 +690,6 @@ def initialize(self, **kwargs):
                 if reaction_system.T:
                     reaction_system.viscosity = solvent_data.get_solvent_viscosity(reaction_system.T.value_si)
 
-        try:
-            self.walltime = kwargs["walltime"]
-        except KeyError:
-            pass
-
-        try:
-            self.max_iterations = kwargs["max_iterations"]
-        except KeyError:
-            pass
-
-        data = self.walltime.split(":")
-        if not len(data) == 4:
-            raise ValueError("Invalid format for wall time {0}; should be DD:HH:MM:SS.".format(self.walltime))
-        self.walltime = int(data[-1]) + 60 * int(data[-2]) + 3600 * int(data[-3]) + 86400 * int(data[-4])
-
         # Initialize reaction model
 
         for spec in self.initial_species:
@@ -931,6 +947,7 @@ def execute(self, initialize=True, **kwargs):
             self.make_seed_mech()
 
         max_num_spcs_hit = False  # default
+        end_early = False
 
         for q, model_settings in enumerate(self.model_settings_list):
             if len(self.simulator_settings_list) > 1:
@@ -940,7 +957,7 @@ def execute(self, initialize=True, **kwargs):
 
             self.filter_reactions = model_settings.filter_reactions
 
-            logging.info("Beginning model generation stage {0}...\n".format(q + 1))
+            logging.info(f"Beginning model generation stage {q + 1} of {len(self.model_settings_list)}.\n")
 
             self.done = False
 
@@ -1235,7 +1252,8 @@ def execute(self, initialize=True, **kwargs):
                         core_spec, core_reac, edge_spec, edge_reac = self.reaction_model.get_model_size()
                         logging.info("The current model core has %s species and %s reactions" % (core_spec, core_reac))
                         logging.info("The current model edge has %s species and %s reactions" % (edge_spec, edge_reac))
-                        return
+                        end_early = True
+                        break
 
                 if self.max_iterations and (self.reaction_model.iteration_num >= self.max_iterations):
                     logging.info("MODEL GENERATION TERMINATED")
@@ -1246,12 +1264,16 @@ def execute(self, initialize=True, **kwargs):
                     core_spec, core_reac, edge_spec, edge_reac = self.reaction_model.get_model_size()
                     logging.info("The current model core has %s species and %s reactions" % (core_spec, core_reac))
                     logging.info("The current model edge has %s species and %s reactions" % (edge_spec, edge_reac))
-                    return
+                    end_early = True
+                    break
 
             if max_num_spcs_hit:  # resets maxNumSpcsHit and continues the settings for loop
                 logging.info("The maximum number of species ({0}) has been hit, Exiting stage {1} ...".format(model_settings.max_num_species, q + 1))
                 max_num_spcs_hit = False
 
+            if end_early:  # breaks the settings for loop
+                break
+
         # Save the final seed mechanism
         self.make_seed_mech()
 
@@ -1333,12 +1355,14 @@ def execute(self, initialize=True, **kwargs):
 
         self.check_model()
         # Write output file
-        logging.info("")
-        logging.info("MODEL GENERATION COMPLETED")
-        logging.info("")
-        core_spec, core_reac, edge_spec, edge_reac = self.reaction_model.get_model_size()
-        logging.info("The final model core has %s species and %s reactions" % (core_spec, core_reac))
-        logging.info("The final model edge has %s species and %s reactions" % (edge_spec, edge_reac))
+
+        if not end_early:
+            logging.info("")
+            logging.info("MODEL GENERATION COMPLETED")
+            logging.info("")
+            core_spec, core_reac, edge_spec, edge_reac = self.reaction_model.get_model_size()
+            logging.info("The final model core has %s species and %s reactions" % (core_spec, core_reac))
+            logging.info("The final model edge has %s species and %s reactions" % (edge_spec, edge_reac))
 
         self.finish()
 

rmgpy/util.py

@@ -173,7 +173,7 @@ def parse_command_line_arguments(command_line_args=None):
     parser.add_argument('-P', '--postprocess', action='store_true',
                         help='postprocess profiling statistics from previous [failed] run; does not run the simulation')
 
-    parser.add_argument('-t', '--walltime', type=str, nargs=1, default='00:00:00:00',
+    parser.add_argument('-t', '--walltime', type=str, nargs=1, default=None,
                         metavar='DD:HH:MM:SS', help='set the maximum execution time')
 
     parser.add_argument('-i', '--maxiter', type=int, nargs=1, default=None,
@@ -197,7 +197,7 @@ def parse_command_line_arguments(command_line_args=None):
     args.file = args.file[0]
 
     # If walltime was specified, retrieve this string from the element 1 list
-    if args.walltime != '00:00:00:00':
+    if args.walltime:
         args.walltime = args.walltime[0]
 
     if args.restart:

test/rmgpy/rmg/rmgTest.py

@@ -206,7 +206,7 @@ def test_parse_command_line_arguments_defaults(self):
         args = parse_command_line_arguments(["input.py"])
 
         # Test default values
-        assert args.walltime == "00:00:00:00"
+        assert args.walltime is None
         assert args.output_directory == os.path.abspath(os.path.dirname("./"))
         assert args.debug == False
         assert args.file == "input.py"