test: add deterministic Moonshine integration and enforce session resume identity (#3)

* test: add Moonshine runtime integration and session identity coverage

Replays the completed deterministic Moonshine runtime integration harness and the session resume identity fix onto the latest upstream-synced main.

* ci: separate offline and Moonshine integration test layers

Author: Charlie-Wang-03

.github/workflows/moonshine-integration-tests.yml

@@ -0,0 +1,45 @@
+name: Moonshine runtime integration tests
+
+on:
+  push:
+    paths:
+      - "run_archive.py"
+      - "archive-format-specification.md"
+      - "skills/**"
+      - "tests/integration_run_archive_moonshine.py"
+      - ".github/workflows/moonshine-integration-tests.yml"
+  pull_request:
+    paths:
+      - "run_archive.py"
+      - "archive-format-specification.md"
+      - "skills/**"
+      - "tests/integration_run_archive_moonshine.py"
+      - ".github/workflows/moonshine-integration-tests.yml"
+
+permissions:
+  contents: read
+
+env:
+  MOONSHINE_COMMIT: 72a64f8984e0e7e1b0a50f6e53e4d00e4fffbb7d
+
+jobs:
+  moonshine-integration:
+    runs-on: ubuntu-latest
+    timeout-minutes: 10
+
+    steps:
+      - name: Check out Creative-Intelligence
+        uses: actions/checkout@v7
+
+      - name: Set up Python 3.11
+        uses: actions/setup-python@v7
+        with:
+          python-version: "3.11"
+
+      - name: Install pinned Moonshine runtime
+        run: |
+          python -m pip install --upgrade pip
+          python -m pip install --no-deps "git+https://github.com/DeepMathLLM/Moonshine.git@${MOONSHINE_COMMIT}"
+
+      - name: Run deterministic Moonshine integration tests
+        run: python -m unittest -v tests.integration_run_archive_moonshine

run_archive.py

@@ -857,13 +857,22 @@ def _render_material_paths(staged: Sequence[Dict[str, object]]) -> str:
 def _open_or_create_session(app: MoonshineApp, object_job: ObjectJob, item_state: Dict[str, object]) -> ShellState:
     session_id = str(item_state.get("session_id") or "").strip()
     if session_id:
-        shell_state = app.start_shell_state(session_id=session_id)
-        if shell_state.project_slug != object_job.project_slug:
-            raise RunnerError(
-                "session %s belongs to project %s, expected %s"
-                % (session_id, shell_state.project_slug, object_job.project_slug)
+        try:
+            return app.start_shell_state(
+                session_id=session_id,
+                mode="chat",
+                project_slug=object_job.project_slug,
+                agent_slug=AGENT_SLUG,
             )
-        return shell_state
+        except ValueError as exc:
+            session_meta = app.session_store.get_session_meta(session_id) or {}
+            actual_project = str(session_meta.get("project_slug") or "")
+            if actual_project and actual_project != object_job.project_slug:
+                raise RunnerError(
+                    "session %s belongs to project %s, expected %s"
+                    % (session_id, actual_project, object_job.project_slug)
+                ) from exc
+            raise RunnerError("session %s is incompatible with archive runner: %s" % (session_id, exc)) from exc
     return app.start_shell_state(
         mode="chat",
         project_slug=object_job.project_slug,