dongarandClaude Opus 5.5
6ae2375194
nisse-dev now runs only the conversational loop. The gated state machine it was built alongside is gone: - Removed control.py, planner.py, executor.py, approvals.py, gates.py (command_form moves to loop/reader.py), publish.py and poller.py, the old assembly in agent.py (its shared helpers move to loop/build.py), the store's state-machine view (get_state, transition), their tests, the old end-to-end and live planning/milestone/gate tests, and specs/orchestrator.qnt with its scenarios. - Roles are driver, helper, expert and classifier; driver is required. loop:, roles.planner, roles.executor and tuning.executor are refused with what to use instead; tuning.driver takes the turn cap and failure limit. - The benchmark and the capability matrix measure the driver: the loop's own system prompt and tools, the task's plan as the agreed restatement. Task plans end with finish_milestone, so earlier runs show as (old); stored runs' executor tuning reads as the driver's. - A delegation on the loop records what its helper's alias resolved to (L9), as the old path's did. - The dump shows a work item's revision and what it waits for. - Behaviour the old tests covered and the loop shares stays covered: driver runs that fail on a model call, stop mid-turn, reset the failure count; go-aheads ignoring case and punctuation; a request too big to fit is never sent; the assembly tests, now on build_loop_agent. Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01PPQ14L3LikyefCMFBqEbKE
65 lines
2.3 KiB
Python
65 lines
2.3 KiB
Python
"""Live smoke test against the real LiteLLM proxy."""
|
|
|
|
import pytest
|
|
|
|
from nisse_dev.canonical import AssistantText, StoredEvent, UserMessage
|
|
from nisse_dev.catalog import ModelCatalog
|
|
from nisse_dev.config import AgentConfig
|
|
from nisse_dev.context import BudgetedClient
|
|
from nisse_dev.llm import LiteLLMClient
|
|
|
|
pytestmark = pytest.mark.integration
|
|
|
|
|
|
def test_the_driver_model_completes_via_litellm(
|
|
litellm: LiteLLMClient, live_config: AgentConfig
|
|
) -> None:
|
|
events = [
|
|
StoredEvent(
|
|
id=1,
|
|
ts="t",
|
|
event=UserMessage(
|
|
text="Reply with exactly one word: pong", source="smoke-test"
|
|
),
|
|
)
|
|
]
|
|
result = litellm.complete(events, tools=None, model=live_config.roles.driver)
|
|
texts = [e.text for e in result if isinstance(e, AssistantText)]
|
|
assert texts, f"no assistant text in {result!r}"
|
|
# A plumbing check, so any answer will do: what the model chooses to say
|
|
# is not under test, and asserting the word made CI flaky (it once
|
|
# replied "ping").
|
|
assert texts[0].strip(), f"empty assistant text in {result!r}"
|
|
|
|
|
|
def test_declared_limits_reach_a_budgeted_request(
|
|
litellm: LiteLLMClient, live_config: AgentConfig
|
|
) -> None:
|
|
"""The whole chain: LiteLLM's model_info, the catalog, the budget, and a
|
|
real request through the proxy with the ceiling the budget chose."""
|
|
catalog = ModelCatalog.discover(live_config.llm_base_url, live_config.llm_token)
|
|
roles = live_config.roles.pinned()
|
|
catalog.require_limits(roles) # every test role has a declared window
|
|
|
|
model = live_config.roles.driver
|
|
facts = catalog.facts(model)
|
|
client = BudgetedClient(
|
|
litellm,
|
|
lambda m: (
|
|
catalog.facts(m).max_input_tokens,
|
|
catalog.facts(m).max_output_tokens,
|
|
),
|
|
max_output_tokens=live_config.max_output_tokens,
|
|
)
|
|
assert client.budget_for(model).window == facts.max_input_tokens
|
|
|
|
events = [
|
|
StoredEvent(
|
|
id=1, ts="t", event=UserMessage(text="Reply with exactly: pong", source="t")
|
|
)
|
|
]
|
|
produced = client.complete(events, None, model, system="Be terse.")
|
|
texts = [e.text for e in produced if isinstance(e, AssistantText)]
|
|
assert texts and "pong" in texts[0].lower()
|
|
assert client.last_usage.get("input", 0) > 0
|