Files
nisse/nisse-dev/tests/test_llm.py
T
dongarandClaude Opus 5 cf85648719
CI / checks (push) Successful in 12s
CI / checks (pull_request) Successful in 11s
Add LLM-backed planning agent (A4/A11/A13) — step 5a
- planner.py: LLMPlanningAgent offers exactly two tools, submit_plan
  and ask_human, so gating stays structural at the tool layer; no
  proceed tool exists. System prompt requires explicit, low-inference
  plans because a weaker model executes them (A13)
- Model output is appended to the canonical log as it arrives, before
  being interpreted, so a crash mid-planning leaves a truthful
  transcript
- A bad turn (prose instead of a tool call, malformed arguments, or a
  failed call) retries once, then raises PlanningError; the
  orchestrator gates to AWAIT_INPUT rather than inventing a plan
- Orchestrator: appends every operator message, plan_submitted, and
  gate_opened to the transcript, so re-planning sees rejection
  feedback as conversation rather than out-of-band parameters; pins
  the A11 role mapping at task start
- llm.py: non-JSON or non-object tool arguments now raise LLMError
  instead of escaping as JSONDecodeError — observed from llama3.2,
  which emits truncated argument strings
- Live planning test is opt-in on NISSE_LIVE_PLANNER_MODEL: planning
  escalates unconditionally (A12) and the local model does not hold
  the tool-call contract, so it awaits a frontier route

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-09-07 14:47:12 +00:00

180 lines
5.8 KiB
Python

import json
from pathlib import Path
import httpx
import pytest
from nisse_dev.canonical import (
AssistantText,
StoredEvent,
ToolCall,
UserMessage,
)
from nisse_dev.envfile import load_env_file
from nisse_dev.llm import LiteLLMClient, LLMError, RoleMap
EVENTS = [StoredEvent(id=1, ts="t", event=UserMessage(text="hi", source="m:1"))]
def make_client(handler) -> LiteLLMClient:
return LiteLLMClient(
"http://litellm.test/v1",
"sk-test",
transport=httpx.MockTransport(handler),
)
def completion(message: dict) -> httpx.Response:
return httpx.Response(
200, json={"model": "gpt-test-1", "choices": [{"message": message}]}
)
def test_request_shape_and_auth() -> None:
seen: dict = {}
def handler(request: httpx.Request) -> httpx.Response:
seen["url"] = str(request.url)
seen["auth"] = request.headers.get("authorization")
seen["body"] = json.loads(request.content)
return completion({"content": "hello"})
make_client(handler).complete(EVENTS, tools=None, model="local/qwen", system="s")
assert seen["url"] == "http://litellm.test/v1/chat/completions"
assert seen["auth"] == "Bearer sk-test"
assert seen["body"]["model"] == "local/qwen"
assert seen["body"]["messages"][0] == {"role": "system", "content": "s"}
assert seen["body"]["messages"][1] == {"role": "user", "content": "hi"}
def test_assistant_text_parsed_with_producing_model() -> None:
client = make_client(lambda request: completion({"content": "hello"}))
[event] = client.complete(EVENTS, tools=None, model="local/qwen")
assert event == AssistantText(text="hello", model="gpt-test-1")
def test_tool_calls_get_locally_minted_canonical_ids() -> None:
message = {
"content": None,
"tool_calls": [
{
"id": "call_provider_abc",
"type": "function",
"function": {
"name": "run_tests",
"arguments": '{"path": "tests/"}',
},
}
],
}
client = make_client(lambda request: completion(message))
[event] = client.complete(EVENTS, tools=None, model="local/qwen")
assert isinstance(event, ToolCall)
assert event.tool == "run_tests"
assert event.arguments == {"path": "tests/"}
assert event.call_id != "call_provider_abc" # provider ID never a join key
assert event.call_id.startswith("call-")
def test_truncated_tool_arguments_raise_llm_error() -> None:
message = {
"content": None,
"tool_calls": [
{
"id": "c",
"type": "function",
"function": {"name": "submit_plan", "arguments": '{"content": "'},
}
],
}
client = make_client(lambda request: completion(message))
with pytest.raises(LLMError, match="non-JSON arguments"):
client.complete(EVENTS, tools=None, model="local/qwen")
def test_non_object_tool_arguments_raise_llm_error() -> None:
message = {
"content": None,
"tool_calls": [
{
"id": "c",
"type": "function",
"function": {"name": "submit_plan", "arguments": '"just a string"'},
}
],
}
client = make_client(lambda request: completion(message))
with pytest.raises(LLMError, match="expected object"):
client.complete(EVENTS, tools=None, model="local/qwen")
def test_http_error_status_raises_llm_error() -> None:
client = make_client(lambda request: httpx.Response(429, text="rate limited"))
with pytest.raises(LLMError, match="429"):
client.complete(EVENTS, tools=None, model="local/qwen")
def test_connection_failure_raises_llm_error() -> None:
def handler(request: httpx.Request) -> httpx.Response:
raise httpx.ConnectError("refused")
with pytest.raises(LLMError, match="request failed"):
make_client(handler).complete(EVENTS, tools=None, model="local/qwen")
def test_malformed_response_raises_llm_error() -> None:
client = make_client(lambda request: httpx.Response(200, json={"oops": True}))
with pytest.raises(LLMError, match="malformed"):
client.complete(EVENTS, tools=None, model="local/qwen")
ROLE_ENV = {
"NISSE_ROLE_EXECUTOR": "local/qwen",
"NISSE_ROLE_PLANNER": "anthropic/claude-opus-5",
"NISSE_ROLE_DELEGATE": "anthropic/claude-opus-5",
"NISSE_ROLE_CONSULTANT": "anthropic/claude-opus-5",
}
def test_role_map_resolves_and_pins() -> None:
roles = RoleMap.from_env(ROLE_ENV)
assert roles.resolve("executor") == "local/qwen"
assert roles.pinned() == {
"executor": "local/qwen",
"planner": "anthropic/claude-opus-5",
"delegate": "anthropic/claude-opus-5",
"consultant": "anthropic/claude-opus-5",
}
def test_role_map_missing_env_raises() -> None:
with pytest.raises(LLMError, match="NISSE_ROLE_PLANNER"):
RoleMap.from_env({"NISSE_ROLE_EXECUTOR": "local/qwen"})
def test_unknown_role_raises() -> None:
with pytest.raises(LLMError, match="unknown role"):
RoleMap.from_env(ROLE_ENV).resolve("boss")
def test_client_from_env_requires_config() -> None:
with pytest.raises(LLMError, match="NISSE_LLM_BASE_URL"):
LiteLLMClient.from_env({})
def test_load_env_file(tmp_path: Path) -> None:
envfile = tmp_path / ".env"
envfile.write_text(
"# comment\n\nNISSE_LLM_TOKEN=sk-abc\nNISSE_LLM_BASE_URL = http://x \n"
)
env: dict[str, str] = {"NISSE_LLM_TOKEN": "sk-already-set"}
load_env_file(envfile, env)
assert env["NISSE_LLM_TOKEN"] == "sk-already-set" # real env wins
assert env["NISSE_LLM_BASE_URL"] == "http://x"
def test_load_env_file_missing_is_noop(tmp_path: Path) -> None:
env: dict[str, str] = {}
load_env_file(tmp_path / "nope.env", env)
assert env == {}