fix(cli): the concepts paragraph no longer claims run writes documents

The shipped wording lifted #319's loose "quintet is pure translation"
phrasing into "the research verbs (run, sweep, ...) are sugar — each writes
registered process/campaign documents". Source check (dispatch_run): only
the four verb_sugar bridges (sweep, walkforward, mc, generalize) generate
and register documents; `run` is a direct single backtest, exactly why its
own long help already avoided the desugaring claim. The paragraph now names
the four document-bridged verbs and places run as their single-backtest
sibling — consistent with `run --help`.

Found by re-auditing the shipped prose claims against the source after the
owner asked how I know no error was made (skills-less-cycle experiment,
refs #315): prose claims in help text are exactly the class the green test
suite cannot semantically verify.

crates/aura-cli/src/main.rs

@@ -1031,11 +1031,12 @@ fn version_string() -> &'static str {
 const CONCEPTS_HELP: &str = "\
 Author, backtest, and validate trading strategies — research CLI.
 
-Two layers, one vocabulary: the research verbs (run, sweep, walkforward, mc,
-generalize) are sugar — each writes registered process/campaign documents and
-executes them. That document data plane is directly authorable: `aura process`
-/ `aura campaign` (validate | introspect | register | run), growing a document
-from a bare {} via `introspect --unwired`.
+Two layers, one vocabulary: the research verbs are the convenience surface —
+sweep, walkforward, mc, and generalize each write registered process/campaign
+documents and execute them (run is their single-backtest sibling). That
+document data plane is directly authorable: `aura process` / `aura campaign`
+(validate | introspect | register | run), growing a document from a bare {}
+via `introspect --unwired`.
 
 Execution model: a strategy emits a bias in [-1,+1] per cycle, held as the
 continuously-tracked target position; a protective stop defines the risk unit