feat(kanban): let a task pin its own thinking depth

A task could already pin a model and provider, but not how hard the worker
thinks: reasoning effort came from the assigned profile's config and nothing
per-task could reach it. Pairing a small model with high effort, or a big one
with thinking off, meant editing the worker profile itself.

Adds a tasks.reasoning_effort column (migrated, NULL = inherit the profile)
with set_reasoning_effort(), a create_task kwarg, and a --reasoning spawn flag.
Kept deliberately independent of model_override: a task may run the profile's
own model at a different depth, and clearing a model override no longer resets
the depth the operator chose. "none" is a value (thinking off), not a clear.

--reasoning is new on the CLI too — the level was only reachable through the
/reasoning slash command, so the dispatcher had no flag to pass. It overrides
agent.reasoning_effort for one run and is never persisted.

hermes_cli/_parser.py

@@ -147,6 +147,18 @@ def build_top_level_parser():
             "under model.provider — use `hermes setup` or edit the file to change it."
         ),
     )
+    _inherited_flag(
+        parser,
+        "--reasoning",
+        default=None,
+        metavar="LEVEL",
+        help=(
+            "Reasoning effort for this invocation: none, minimal, low, medium, "
+            "high, xhigh, max, or ultra. Overrides agent.reasoning_effort in "
+            "config.yaml for this run only; the persistent level lives there "
+            "(or per-model under agent.reasoning_overrides)."
+        ),
+    )
     parser.add_argument(
         "-t",
         "--toolsets",
@@ -299,6 +311,17 @@ def build_top_level_parser():
         default=argparse.SUPPRESS,
         help="Comma-separated toolsets to enable",
     )
+    _inherited_flag(
+        chat_parser,
+        "--reasoning",
+        default=argparse.SUPPRESS,
+        metavar="LEVEL",
+        help=(
+            "Reasoning effort for this session: none, minimal, low, medium, "
+            "high, xhigh, max, or ultra. Overrides agent.reasoning_effort for "
+            "this run only (same levels as the /reasoning slash command)."
+        ),
+    )
     _inherited_flag(
         chat_parser,
         "-s",