feat(gsd): add browser-executable and runtime-executable UAT types (#1620)

New UAT types skip human pause, enabling automated browser and script
verification by the engine.

Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

src/resources/extensions/gsd/auto-dispatch.ts

@@ -155,7 +155,7 @@ const DISPATCH_RULES: DispatchRule[] = [
           uatContent ?? "",
           basePath,
         ),
-        pauseAfterDispatch: uatType !== "artifact-driven",
+        pauseAfterDispatch: uatType !== "artifact-driven" && uatType !== "browser-executable" && uatType !== "runtime-executable",
       };
     },
   },

src/resources/extensions/gsd/files.ts

@@ -775,7 +775,7 @@ export function parseTaskPlanIO(content: string): { inputFiles: string[]; output
  * The four UAT classification types recognised by GSD auto-mode.
  * `undefined` is returned (not this union) when no type can be determined.
  */
-export type UatType = 'artifact-driven' | 'live-runtime' | 'human-experience' | 'mixed';
+export type UatType = 'artifact-driven' | 'live-runtime' | 'human-experience' | 'mixed' | 'browser-executable' | 'runtime-executable';
 
 /**
  * Extract the UAT type from a UAT file's raw content.
@@ -799,6 +799,8 @@ export function extractUatType(content: string): UatType | undefined {
   const rawValue = modeBullet.slice('UAT mode:'.length).trim().toLowerCase();
 
   if (rawValue.startsWith('artifact-driven')) return 'artifact-driven';
+  if (rawValue.startsWith('browser-executable')) return 'browser-executable';
+  if (rawValue.startsWith('runtime-executable')) return 'runtime-executable';
   if (rawValue.startsWith('live-runtime')) return 'live-runtime';
   if (rawValue.startsWith('human-experience')) return 'human-experience';
   if (rawValue.startsWith('mixed')) return 'mixed';

src/resources/extensions/gsd/prompts/run-uat.md

@@ -25,6 +25,8 @@ You are the UAT runner. Execute every check defined in `{{uatPath}}` as deeply a
 ### Automation rules by mode
 
 - `artifact-driven` — verify with shell commands, scripts, file reads, and artifact structure checks.
+- `browser-executable` — use browser tools to navigate to the target URL and verify expected behavior. Capture screenshots as evidence. Record pass/fail with specific assertions.
+- `runtime-executable` — execute the specified command or script. Capture stdout/stderr as evidence. Record pass/fail based on exit code and output.
 - `live-runtime` — exercise the real runtime path. Start or connect to the app/service if needed, use browser/runtime/network checks, and verify observable behavior.
 - `mixed` — run all automatable artifact-driven and live-runtime checks. Separate any remaining human-only checks explicitly.
 - `human-experience` — automate setup, preconditions, screenshots, logs, and objective checks, but do **not** invent subjective PASS results. Mark taste-based, experiential, or purely human-judgment checks as `NEEDS-HUMAN` and use an overall verdict of `PARTIAL` unless every required check was objective and passed.