fix(skills): prevent empty responses after load_skill

The skill system instruction does not tell the model what to do after a
load_skill call returns. Some models (notably Gemini) treat the load_skill
tool call as the entire turn and stop with no visible output, producing
empty responses. This is most acute for tool-heavy skills, whose next
correct action after load_skill is to call more tools rather than reply.

Add rule 7 to _build_skill_system_instruction: load_skill only retrieves
instructions and does NOT complete the turn; the model must continue in the
same turn (calling whatever tools the skill requires) and never end with an
empty response right after loading a skill. The rule uses the {prefix}
substitution like the other rules, so both the default and prefixed system
instructions carry it.

Verified in a production environment: appending this guidance dropped the
empty-response rate for Gemini after skill loading substantially.

Adds tests asserting rule 7 is present in both the default and prefixed
system instruction.

Author: lwangverizon

src/google/adk/tools/skill_toolset.py

@@ -97,6 +97,11 @@ def _build_skill_system_instruction(prefix: str | None = None) -> str:
       f"6. If `{p}run_skill_script` returns an error (for example "
       f"`SCRIPT_NOT_FOUND`), do not retry the same script or guess a "
       "different script path. Report the error to the user and stop.\n"
+      f"7. Loading a skill only retrieves its instructions; it does NOT "
+      f"complete your turn. After a `{p}load_skill` call returns, continue "
+      "in the SAME turn: call whatever tools the skill's steps require "
+      "(search, data retrieval, render), then write your reply. Never end "
+      "your turn with an empty response right after loading a skill.\n"
   )
 
 

tests/unittests/tools/test_skill_toolset.py

@@ -1758,6 +1758,24 @@ def test_system_instruction_references_run_skill_script():
   )
 
 
+def test_system_instruction_marks_load_skill_as_non_terminal():
+  """Rule 7 must tell the model load_skill does not complete the turn.
+
+  Without it, some models (notably Gemini) treat the load_skill tool call as
+  the entire turn and stop with no visible output, producing empty responses.
+  """
+  instruction = skill_toolset.DEFAULT_SKILL_SYSTEM_INSTRUCTION
+  assert "does NOT complete your turn" in instruction
+  assert "empty response" in instruction
+
+
+def test_prefixed_system_instruction_includes_continue_after_load_rule():
+  """The prefixed builder variant must also carry rule 7 (with the prefix)."""
+  instruction = skill_toolset._build_skill_system_instruction(prefix="my")
+  assert "does NOT complete your turn" in instruction
+  assert "my_load_skill" in instruction
+
+
 # ── Finding 2: empty files are mounted (not silently dropped) ──