fix: unknown single-word subcommand emits command_not_found (#825/#826)

Single-word all-alpha/dash tokens that don't match any known subcommand
now always emit command_not_found (with or without fuzzy suggestions).

Multi-word cases fall through to CliAction::Prompt (natural language
prompt passthrough like 'claw explain this' must still work). The
multi-word gap is documented as ROADMAP #826 (known limitation).

Tests:
- unknown_subcommand_json_emits_command_not_found (new)
- unknown_subcommand_text_emits_command_not_found_on_stderr (new)
- unknown_subcommand_typo_with_suggestions_json_emits_command_not_found (new)
- multi_word_unknown_subcommand_falls_through_to_prompt_826 (documents gap)

572 tests pass, 1 pre-existing worker_boot failure unrelated.

rust/crates/rusty-claude-cli/src/main.rs

@@ -1381,9 +1381,9 @@ fn parse_args(args: &[String]) -> Result<CliAction, String> {
                 // #825: always emit a command_not_found error for
                 // single-word all-alpha/dash tokens that don't match any
                 // known subcommand — with or without close suggestions.
-                // Previously, no-suggestion cases fell through silently to
-                // CliAction::Prompt and triggered a misleading
-                // `missing_credentials` error after provider startup.
+                // Multi-word cases fall through to CliAction::Prompt so
+                // natural language prompts like `claw explain this` work.
+                // (#826 documents the multi-word gap as a known limitation.)
                 let mut message = format!("command_not_found: unknown subcommand: {other}.");
                 if let Some(suggestions) = suggest_similar_subcommand(other) {
                     if let Some(line) = render_suggestion_line("Did you mean", &suggestions) {

rust/crates/rusty-claude-cli/tests/output_format_contract.rs

@@ -3939,3 +3939,31 @@ fn unknown_subcommand_typo_with_suggestions_json_emits_command_not_found() {
     );
     assert!(stderr.is_empty(), "typo JSON must have empty stderr (#825)");
 }
+
+// #826: multi-word unknown subcommand is a known gap — falls through to
+// CliAction::Prompt (natural language prompt passthrough like `claw explain this`).
+// Single-word typos (#825) are caught; multi-word is documented as backlog.
+// This test documents the current behaviour (not the desired fix).
+#[test]
+fn multi_word_unknown_subcommand_falls_through_to_prompt_826() {
+    let root = unique_temp_dir("multi-word-gap-826");
+    std::fs::create_dir_all(&root).expect("create temp dir");
+    // "foobar baz" has no fuzzy suggestion → falls through to Prompt path
+    // (hits missing_credentials since no API key is set, rc=1)
+    let output = run_claw(&root, &["--output-format", "json", "foobar", "baz"], &[]);
+    assert_eq!(output.status.code(), Some(1));
+    let stdout = String::from_utf8_lossy(&output.stdout);
+    let stderr = String::from_utf8_lossy(&output.stderr);
+    // Currently emits missing_credentials (fallthrough gap documented in #826)
+    let j: serde_json::Value =
+        serde_json::from_str(stdout.trim()).expect("multi-word fallthrough must emit JSON");
+    assert_eq!(
+        j["status"], "error",
+        "multi-word fallthrough must be an error: {j}"
+    );
+    // stderr must be empty regardless (JSON mode)
+    assert!(
+        stderr.is_empty(),
+        "multi-word fallthrough JSON must have empty stderr: {stderr:?}"
+    );
+}