chore: housekeeping from the runs of 2026-10-09
Some checks failed
validation / verify (push) Failing after 12s

- An Execution's files are written as each Deliverable is submitted, marked
  in_progress, so a killed process or one waiting for its user leaves them on
  disk. A write removes files an earlier write left that it no longer has.
- A question about delivered work is answered from that Execution's solution
  guide by the reply writer; a question about the service is answered as
  before. Nothing is started for either.
- Lessons: prove writes only for lessons the Skill holds; the Skill records
  the vendored Skill versions the lessons were read against, status names any
  that changed, and a test fails until they are reviewed.
- Four more code patterns: Firestore, BigQuery, Eventarc and GKE.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
2026-10-10 11:44:38 +01:00
parent 10d23a5f91
commit 71da0ed504
24 changed files with 1109 additions and 43 deletions

View File

@@ -75,7 +75,7 @@ def complete_run_turns() -> dict:
def client_for(
tmp_path: Path, turns: dict, decider=None
tmp_path: Path, turns: dict, decider=None, answers=None
) -> tuple[TestClient, FakeAgentRuntime]:
bundle = load_provider("gcp")
roles = load_roles(AGENTS_DIR, bundle)
@@ -96,6 +96,7 @@ def client_for(
roles,
{"compute": "API not enabled"},
intake=Intake(decider, tmp_path) if decider else None,
answers=answers,
)
return TestClient(create_app(get_settings(), fake_assembly)), runtime
@@ -398,6 +399,74 @@ def delivered_case(tmp_path: Path, case: str = "acme") -> None:
)
class Answers:
"""Stands in for the reply writer answering from delivered files."""
def __init__(self, reply):
self.reply = reply
self.asked: list[tuple[str, str, str]] = []
async def answer(self, question, customer_case, execution_id):
self.asked.append((question, customer_case, execution_id))
return self.reply
ABOUT_DELIVERED = {
"intake": Answer("question", 0.98),
"about_delivered": Answer(0.92, 0.9),
}
def test_a_question_about_delivered_work_is_answered_from_it(tmp_path):
delivered_case(tmp_path)
answers = Answers("Cloud SQL, because bookings are relational.")
client, runtime = client_for(tmp_path, {}, FakeDecider(ABOUT_DELIVERED), answers)
with client:
task = send(
client,
[{"text": "Why did you choose Cloud SQL?"}],
metadata={"customer_case": "acme"},
)
text, data = status_parts(task)
assert task["status"]["state"] == "TASK_STATE_COMPLETED"
assert text == "Cloud SQL, because bookings are relational."
assert data == {"status": "answered", "intake": "question", "about": "v1"}
assert answers.asked == [("Why did you choose Cloud SQL?", "acme", "v1")]
assert runtime.runs == []
def test_a_question_that_could_not_be_answered_says_where_to_look(tmp_path):
delivered_case(tmp_path)
client, _ = client_for(tmp_path, {}, FakeDecider(ABOUT_DELIVERED), Answers(None))
with client:
task = send(
client, [{"text": "Why Cloud SQL?"}], metadata={"customer_case": "acme"}
)
text, data = status_parts(task)
assert "could not answer that from the documents delivered in Execution v1" in text
assert data["about"] == "v1"
def test_a_question_about_the_service_is_still_answered_in_general(tmp_path):
delivered_case(tmp_path)
decider = FakeDecider(
{"intake": Answer("question", 0.98), "about_delivered": Answer(0.08, 0.9)}
)
answers = Answers("unused")
client, _ = client_for(tmp_path, {}, decider, answers)
with client:
task = send(
client, [{"text": "What can you do?"}], metadata={"customer_case": "acme"}
)
text, data = status_parts(task)
assert text.startswith("I design cloud solution architectures.")
assert data == {"status": "answered", "intake": "question"}
assert answers.asked == []
def test_a_change_to_delivered_work_names_the_baseline_and_starts_nothing(tmp_path):
delivered_case(tmp_path)
decider = FakeDecider({"intake": Answer("change_request", 0.98)})