dongarandClaude Opus 5.5
83804fe02a
CI / checks (push) Skipped
CI / checks (pull_request) Successful in 1m14s
Development Plan M1.1, as discussed. - Schema v4: a work_items table (id, scope, title, status, outcome, position, data) and an agent row whose active_item points at one (NULL: idle). Canonical events and intents carry their work item, and events their actor. Older stores are refused with a clear message: there was no production data, so no migration (the mechanism stays). - The log is reached through a Transcript bound to one work item and one actor: store.transcript(item, actor) reads only that item and writes with both. The planner, executor, delegation and expert desk get one per call from the orchestrator instead of holding the store, so a component can neither read another task's events (the planner read every earlier task's, #78) nor write without attribution. store.all_events() is kept for readers that span items (evaluation capture, dumps). Intents are begun through the transcript or with work_item=, so each belongs to its item. - The orchestrator opens a work item on 'use', closes it with its outcome (completed or abandoned), and carries what the operator said while idle into the new item as copies with their origin, so a task sent before 'use' is still planned from (D1). control.py keeps its state machine through get_state()/transition(), now over the active work item, until M2.6 retires it. - nisse_dev.dump shows work items and each event's item and actor. Tests: test_work_items.py (scoping, attribution, intent ownership, restart, outcomes, carried messages, a second task never seeing the first); the suites updated for the per-call transcript. Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01PPQ14L3LikyefCMFBqEbKE
48 lines
1.7 KiB
Python
48 lines
1.7 KiB
Python
"""Live planning turn: a real model must answer with a submit_plan or
|
|
ask_human tool call, not prose.
|
|
|
|
Plans with the test config's planner role. The planner role is a frontier
|
|
model today (Development Plan §2), and small local models do not hold the tool-call
|
|
contract reliably, so that role must be one that does.
|
|
"""
|
|
|
|
import io
|
|
from pathlib import Path
|
|
|
|
import pytest
|
|
|
|
from nisse_dev.canonical import UserMessage
|
|
from nisse_dev.control import AskHuman, SubmitPlan
|
|
from nisse_dev.llm import LiteLLMClient, RoleMap
|
|
from nisse_dev.oplog import OpLog
|
|
from nisse_dev.planner import LLMPlanningAgent
|
|
from nisse_dev.state import StateStore
|
|
|
|
pytestmark = pytest.mark.integration
|
|
|
|
|
|
def test_live_planning_turn_returns_a_tool_action(
|
|
tmp_path: Path, litellm: LiteLLMClient, live_model: str
|
|
) -> None:
|
|
model = live_model
|
|
roles = RoleMap(executor=model, planner=model, helper=model, expert=model)
|
|
store = StateStore(tmp_path / "state.db", oplog=OpLog("nisse-dev", io.StringIO()))
|
|
store.transcript("t", "operator").append(
|
|
UserMessage(
|
|
text=(
|
|
"Project 'hello-cli': a Python script that prints a greeting. "
|
|
"Draft the architecture plan."
|
|
),
|
|
source="live-test",
|
|
)
|
|
)
|
|
agent = LLMPlanningAgent(litellm, roles)
|
|
|
|
action = agent.plan(store.transcript("t", "planner"), "arch", "hello-cli")
|
|
|
|
assert isinstance(action, SubmitPlan | AskHuman)
|
|
text = action.content if isinstance(action, SubmitPlan) else action.question
|
|
assert text.strip(), "tool call carried empty content"
|
|
# The turn must be durable regardless of what the model said (L8/L7).
|
|
assert len(store.transcript("t", "planner").read()) > 1
|