dongarandClaude Opus 5.5
15d69799bf
CI / checks (push) Skipped
CI / checks (pull_request) Successful in 51s
With no production instance yet, there is no reason to carry two ways
of configuring the agent. Every environment variable that duplicated a
config key is gone; the environment now supplies only the secrets the
file references by ${…}, plus NISSE_CONFIG and NISSE_ENV to find the
files.
- AgentConfig loads from a file (load, from_file) or a parsed tree
(from_tree, for tests); a missing file is an error naming the example
- The from_env constructors on LiteLLMClient, AnthropicPassthroughClient,
GiteaClient, MatrixConfig and RoleMap are removed, with the env
reading for max output tokens; clients take their settings from config
- The live integration tests share a committed agent config,
tests/integration/nisse-test.yaml, aimed at test resources, and one
conftest that loads it and builds clients. NISSE_LIVE_PLANNER_MODEL
becomes its planner role; NISSE_CAPABILITY_MODELS stays as a per-run
switch
- A missing secret now fails the live tests instead of skipping them
- CI passes only the three tokens
- .env.example is secrets only; spec A5 says config comes from the file
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
55 lines
1.7 KiB
Python
55 lines
1.7 KiB
Python
"""A real consult over the normalized route (A14).
|
|
|
|
The point is the prompt-level contract: a live model must produce something
|
|
that parses against our local schema, since no API-level enforcement exists.
|
|
"""
|
|
|
|
import io
|
|
from pathlib import Path
|
|
|
|
import pytest
|
|
|
|
from nisse_dev.evals import collect
|
|
from nisse_dev.expert import BudgetExhausted, ExpertDesk
|
|
from nisse_dev.llm import LiteLLMClient, RoleMap
|
|
from nisse_dev.oplog import OpLog
|
|
from nisse_dev.state import StateStore
|
|
|
|
pytestmark = pytest.mark.integration
|
|
|
|
|
|
@pytest.fixture
|
|
def desk(tmp_path: Path, litellm: LiteLLMClient, live_model: str):
|
|
def make(budget: int = 2) -> tuple[ExpertDesk, StateStore]:
|
|
model = live_model
|
|
roles = RoleMap(executor=model, planner=model, delegate=model, consultant=model)
|
|
store = StateStore(
|
|
tmp_path / "state.db", oplog=OpLog("nisse-dev", io.StringIO())
|
|
)
|
|
return ExpertDesk(litellm, store, roles, budget=budget), store
|
|
|
|
return make
|
|
|
|
|
|
def test_live_consult_parses_against_the_local_schema(desk) -> None:
|
|
expert, store = desk()
|
|
|
|
answer = expert.ask(
|
|
"For a single-process agent storing a few thousand rows of task state, "
|
|
"is SQLite sufficient, or is PostgreSQL warranted? Answer briefly."
|
|
)
|
|
|
|
assert answer.confidence in {"high", "medium", "low"}
|
|
assert len(answer.answer) > 20
|
|
# The consult is captured for A16 without any extra bookkeeping.
|
|
[record] = collect(store)
|
|
assert record.role == "consultant"
|
|
assert record.exit_status == "answered"
|
|
|
|
|
|
def test_live_budget_stops_a_circling_caller(desk) -> None:
|
|
expert, _ = desk(budget=1)
|
|
expert.ask("Name one advantage of WAL mode in SQLite. Be brief.")
|
|
with pytest.raises(BudgetExhausted):
|
|
expert.ask("And another?")
|