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
69 lines
2.4 KiB
Python
69 lines
2.4 KiB
Python
import io
|
|
from pathlib import Path
|
|
|
|
from nisse_dev.canonical import PlanSubmitted, ToolCall, ToolResult, UserMessage
|
|
from nisse_dev.dump import main, render
|
|
from nisse_dev.oplog import OpLog
|
|
from nisse_dev.state import StateStore
|
|
|
|
|
|
def store_with_a_run(path: Path) -> None:
|
|
store = StateStore(path, oplog=OpLog("nisse-dev", io.StringIO()))
|
|
store.transcript(None, "operator").append(
|
|
UserMessage(text="hello before use", source="matrix")
|
|
)
|
|
store.transition(
|
|
"AWAIT_ARCH_SIGNOFF",
|
|
cause="test",
|
|
project="demo",
|
|
data={"task_id": "demo-1", "gate": {"name": "arch", "rev": 1}},
|
|
)
|
|
log = store.transcript("demo-1", "operator")
|
|
log.append(UserMessage(text="Add a truncate helper", source="matrix"))
|
|
log.as_actor("planner").append(PlanSubmitted(plan="x" * 500, model="opus"))
|
|
executor = log.as_actor("executor")
|
|
executor.append(
|
|
ToolCall(call_id="c1", tool="run_command", arguments={"command": "ls"})
|
|
)
|
|
executor.append(ToolResult(call_id="c1", result="README.md", success=False))
|
|
log.begin_intent("open_pr", {"branch": "b"}, cause="test")
|
|
store.close()
|
|
|
|
|
|
def test_the_dump_shows_items_intents_and_each_event_with_its_actor(
|
|
tmp_path: Path,
|
|
) -> None:
|
|
db = tmp_path / "state.db"
|
|
store_with_a_run(db)
|
|
text = render(db)
|
|
assert "active work item: demo-1" in text
|
|
assert (
|
|
"demo-1 open position: AWAIT_ARCH_SIGNOFF scope: demo gate: arch rev-1"
|
|
in (text)
|
|
)
|
|
assert "pending intent #1 open_pr [demo-1]" in text
|
|
assert "[agent/operator] USER [matrix]: hello before use" in text
|
|
assert "[demo-1/operator] USER [matrix]: Add a truncate helper" in text
|
|
assert "[demo-1/planner] PLAN (opus, 500 chars): " in text and "[340 more]" in text
|
|
assert '[demo-1/executor] CALL run_command {"command": "ls"}' in text
|
|
assert "result (FAILED): README.md" in text
|
|
|
|
|
|
def test_full_shows_long_texts_whole(tmp_path: Path) -> None:
|
|
db = tmp_path / "state.db"
|
|
store_with_a_run(db)
|
|
assert "x" * 500 in render(db, full=True)
|
|
|
|
|
|
def test_the_dump_never_writes_to_the_store(tmp_path: Path) -> None:
|
|
db = tmp_path / "state.db"
|
|
store_with_a_run(db)
|
|
before = db.read_bytes()
|
|
render(db)
|
|
assert db.read_bytes() == before
|
|
|
|
|
|
def test_a_missing_store_is_reported(tmp_path: Path, capsys) -> None:
|
|
assert main([str(tmp_path / "nope.db")]) == 1
|
|
assert "no state store" in capsys.readouterr().err
|