ENG-2071: stop naming Picker-granted Drive files in anton's prompt

anton/utils/datasources.py

@@ -268,10 +268,18 @@ def build_datasource_context(vault: DataVault, active_only: str | None = None) -
     )
     # Google Drive's drive.file OAuth scope only covers files the app created
     # itself, plus files explicitly granted via the Google Picker (persisted
-    # as a `_picked_files` vault field) — these must be named explicitly here
-    # since a plain files.list()/files.search() call won't return them.
+    # as a `_picked_files` vault field).
+    #
+    # Those granted files are deliberately NOT listed here (ENG-2071). Listing
+    # them needs the *current project* to scope by, and `projects` is a cowork
+    # concept this function has no access to — so the list rendered here was
+    # unscoped, and named files from other projects. cowork-server renders the
+    # scoped list itself, via ConnectionsService.picked_files_by_project() ->
+    # the harness prompt suffix, which is the single renderer. All we track
+    # here is *whether* any exist, so the availability paragraph below still
+    # fires for a Picker-only connection exactly as it always has.
     google_drive_oauth_connected = False
-    google_drive_picked_files: dict[str, list[dict]] = {}
+    google_drive_has_picked_files = False
     # Hoisted out of the loop below: this function is rebuilt on every chat
     # turn, and DatasourceRegistry() parses the full built-in + user
     # datasources.md on every construction (no caching) — with N
@@ -323,36 +331,17 @@ def build_datasource_context(vault: DataVault, active_only: str | None = None) -
         if c["engine"] == "google_drive":
             if fields.get("auth_type") == "oauth":
                 google_drive_oauth_connected = True
-            picked = _parse_picked_files(fields.get("_picked_files"))
-            if picked:
-                google_drive_picked_files[c["name"]] = picked
-    if google_drive_oauth_connected or google_drive_picked_files:
+            # Parsed, not merely truthy-checked: a `_picked_files` holding only
+            # malformed entries must read as "none", the same way it did when
+            # this drove the (now removed) listing.
+            if _parse_picked_files(fields.get("_picked_files")):
+                google_drive_has_picked_files = True
+    if google_drive_oauth_connected or google_drive_has_picked_files:
         lines.append(
             "\nConnected Google Drive accounts are available through Google OAuth credentials "
             "in the injected `DS_GOOGLE_DRIVE_<CONNECTION>__...` environment variables. "
             "Only claim Google Drive access if you can actually use those credentials successfully."
         )
-    if google_drive_picked_files:
-        picked_lines = [
-            f"- {f.get('name', 'untitled')} (id: {f.get('id')}, connection: {conn_name})"
-            for conn_name, files in google_drive_picked_files.items()
-            for f in files
-        ]
-        # Imperative and structurally separate from the paragraph above — a
-        # softer prose mention got silently dropped by the agent when
-        # reporting files.list() results verbatim.
-        lines.append(
-            "\nIMPORTANT — additional Drive files the user has explicitly granted access to "
-            "via the Google Picker, which a plain files.list() or files.search() call will NOT "
-            "return (the google_drive scope only covers files this app created itself, plus "
-            "these specifically granted ones):\n"
-            + "\n".join(picked_lines)
-            + "\nWhenever you list, search, or enumerate Drive files for the user, you MUST "
-            "include every file above IN ADDITION to whatever files.list()/files.search() "
-            "returns — do not report only the API call's results. To read one of these files' "
-            "content, call files.get(fileId=...) directly with its id above; do not expect it "
-            "to appear in a files.list() response first."
-        )
     return "\n".join(lines)
 
 

tests/test_build_chat_session_google_drive.py

@@ -1,5 +1,5 @@
-"""End-to-end: build_chat_session() -> ChatSession._build_system_prompt() actually
-surfaces Google Drive Picker guidance in the real assembled system prompt.
+"""End-to-end: build_chat_session() -> ChatSession._build_system_prompt() and what
+Google Drive guidance really reaches the assembled system prompt.
 
 ENG-687 review (PR #241): the picked-files/OAuth guidance moved out of
 build_chat_session (anton/core/runtime.py) into build_datasource_context
@@ -38,7 +38,7 @@ def workspace_path(tmp_path):
     return p
 
 
-async def test_picked_files_reach_the_real_system_prompt(workspace_path):
+async def test_drive_availability_reaches_prompt_without_naming_picked_files(workspace_path):
     from anton.core.datasources.data_vault import LocalDataVault
     from anton.core.runtime import build_chat_session
 
@@ -53,8 +53,12 @@ async def test_picked_files_reach_the_real_system_prompt(workspace_path):
     prompt = await session._build_system_prompt()
 
     assert "Connected Google Drive accounts are available" in prompt
-    assert "IMPORTANT — additional Drive files" in prompt
-    assert "Roadmap.gdoc" in prompt
+    # ENG-2071: the availability paragraph reaches the real prompt, but the
+    # Picker-granted files themselves must not — this function has no project
+    # to scope them by, so it named files from every project. cowork-server
+    # renders the scoped list instead (ConnectionsService.picked_files_by_project).
+    assert "IMPORTANT — additional Drive files" not in prompt
+    assert "Roadmap.gdoc" not in prompt
 
 
 async def test_no_connections_and_no_suffix_does_not_crash(workspace_path):

tests/test_datasource_context_identity.py

@@ -167,10 +167,11 @@ def test_empty_or_none_returns_empty(self):
 
 
 class TestGoogleDrivePickerContext:
-    """ENG-687: google_drive's drive.file OAuth scope only covers files the
-    app created itself, plus files explicitly granted via the Google
-    Picker — the agent needs those named by id or a plain files.list()/
-    files.search() call won't surface them at all."""
+    """ENG-687 gave google_drive's Picker-granted files their own prompt block
+    here. ENG-2071 removed the *listing* again: it had no project to scope by,
+    so it named files the user granted in other projects, re-opening the leak
+    ConnectionsService.picked_files_by_project() closes on the cowork-server
+    side. What stays here is the availability paragraph — no file ids."""
 
     def test_oauth_connection_without_picked_files_shows_availability_only(self, tmp_path):
         v = LocalDataVault(tmp_path)
@@ -179,34 +180,56 @@ def test_oauth_connection_without_picked_files_shows_availability_only(self, tmp
         assert "Connected Google Drive accounts are available" in ctx
         assert "IMPORTANT" not in ctx
 
-    def test_picked_files_surfaced_with_id_and_connection(self, tmp_path):
+    def test_picked_files_are_never_named_here(self, tmp_path):
+        """ENG-2071: the availability paragraph still fires, but no file
+        identity reaches the prompt from this function."""
         v = LocalDataVault(tmp_path)
         v.save("google_drive", "work", {
             "auth_type": "oauth",
             "_picked_files": json.dumps([{"id": "f1", "name": "Roadmap.gdoc"}]),
         })
         ctx = build_datasource_context(v)
-        assert "IMPORTANT — additional Drive files" in ctx
-        assert "Roadmap.gdoc" in ctx
-        assert "id: f1" in ctx
-        assert "connection: work" in ctx
+        assert "Connected Google Drive accounts are available" in ctx
+        assert "Roadmap.gdoc" not in ctx
+        assert "f1" not in ctx
+        assert "IMPORTANT — additional Drive files" not in ctx
+
+    def test_file_granted_in_another_project_is_not_named(self, tmp_path):
+        """The leak itself. A file tagged to Project A must not surface at all
+        from here — this function cannot tell which project is active, which is
+        exactly why it no longer lists any of them."""
+        v = LocalDataVault(tmp_path)
+        v.save("google_drive", "work", {
+            "auth_type": "oauth",
+            "_picked_files": json.dumps([
+                {"id": "secret-a", "name": "ProjectA-Salaries.gsheet", "projects": ["Project A"]},
+            ]),
+        })
+        ctx = build_datasource_context(v)
+        assert "ProjectA-Salaries.gsheet" not in ctx
+        assert "secret-a" not in ctx
 
-    def test_resource_key_not_required_but_included_when_present(self, tmp_path):
+    def test_picker_only_connection_still_shows_availability(self, tmp_path):
+        """A Picker-granted connection with no `auth_type` still triggers the
+        paragraph — unchanged from before ENG-2071, which is why presence is
+        still tracked even though the list is gone."""
         v = LocalDataVault(tmp_path)
         v.save("google_drive", "work", {
-            "_picked_files": json.dumps([{"id": "f1", "name": "Shared.gdoc", "resourceKey": "rk123"}]),
+            "_picked_files": json.dumps([{"id": "f1", "name": "Roadmap.gdoc"}]),
         })
         ctx = build_datasource_context(v)
-        assert "Roadmap.gdoc" not in ctx  # sanity: not leaking the other test's fixture
-        assert "Shared.gdoc" in ctx
+        assert "Connected Google Drive accounts are available" in ctx
+        assert "Roadmap.gdoc" not in ctx
 
     def test_malformed_picked_file_entries_are_dropped_not_crashed(self, tmp_path):
         v = LocalDataVault(tmp_path)
         v.save("google_drive", "work", {
             "_picked_files": json.dumps(["not-a-dict", {"name": "missing-id"}]),
         })
         ctx = build_datasource_context(v)  # must not raise
-        assert "IMPORTANT" not in ctx  # nothing well-formed survived, so no block at all
+        # Nothing well-formed survived and there is no oauth marker, so the
+        # connection reads as "no Picker grant" and no paragraph appears.
+        assert "Connected Google Drive accounts are available" not in ctx
 
     def test_no_google_drive_connection_no_guidance(self, tmp_path):
         v = LocalDataVault(tmp_path)
@@ -215,13 +238,14 @@ def test_no_google_drive_connection_no_guidance(self, tmp_path):
         assert "Google Drive" not in ctx
         assert "IMPORTANT" not in ctx
 
-    def test_multiple_google_drive_connections_each_listed_separately(self, tmp_path):
+    def test_multiple_google_drive_connections_name_no_files(self, tmp_path):
         v = LocalDataVault(tmp_path)
         v.save("google_drive", "work", {"_picked_files": json.dumps([{"id": "1", "name": "Work.gdoc"}])})
         v.save("google_drive", "personal", {"_picked_files": json.dumps([{"id": "2", "name": "Personal.gdoc"}])})
         ctx = build_datasource_context(v)
-        assert "Work.gdoc" in ctx and "connection: work" in ctx
-        assert "Personal.gdoc" in ctx and "connection: personal" in ctx
+        assert "Connected Google Drive accounts are available" in ctx
+        assert "Work.gdoc" not in ctx
+        assert "Personal.gdoc" not in ctx
 
     def test_active_only_suppresses_other_connections_guidance(self, tmp_path):
         v = LocalDataVault(tmp_path)
@@ -235,10 +259,11 @@ def test_active_only_suppresses_other_connections_guidance(self, tmp_path):
         assert "Google Drive" not in ctx
         assert "Roadmap.gdoc" not in ctx
 
-    def test_active_only_on_google_drive_still_shows_its_guidance(self, tmp_path):
+    def test_active_only_on_google_drive_still_shows_availability(self, tmp_path):
         v = LocalDataVault(tmp_path)
         v.save("google_drive", "work", {
             "_picked_files": json.dumps([{"id": "1", "name": "Roadmap.gdoc"}]),
         })
         ctx = build_datasource_context(v, active_only="google_drive-work")
-        assert "Roadmap.gdoc" in ctx
+        assert "Connected Google Drive accounts are available" in ctx
+        assert "Roadmap.gdoc" not in ctx