dongarandClaude Opus 5.5
3fba958958
CI / checks (push) Skipped
CI / checks (pull_request) Successful in 1m27s
A model no longer reads another role's turns as its own (#78). The log stays one record per work item; what a role is shown is projected from it by Transcript.view() (views.py), which the planner, executor and helper now build their context from: - own events unchanged; - operator messages labelled with their channel, e.g. [operator, Matrix] or [operator, comment on PR #165]; - orchestrator facts (a new `fact` event) as [orchestrator] statements; - the executor sees a helper's handback as [helper report], not its turns; - a helper sees the approved plan and the executor's milestone work as one-line narration; - the planner sees no other role's work at all. The orchestrator now writes facts at the points the models must know about: work item opened, plan approved or rejected, milestone started, finished or stopped, published (with PR number and URL) or not, review comment answered, next milestone, task completed or abandoned. Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01PPQ14L3LikyefCMFBqEbKE
78 lines
2.8 KiB
Python
78 lines
2.8 KiB
Python
import io
|
|
from pathlib import Path
|
|
|
|
from nisse_dev.canonical import Fact, 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_facts_are_shown_as_the_orchestrators(tmp_path: Path) -> None:
|
|
db = tmp_path / "state.db"
|
|
store_with_a_run(db)
|
|
store = StateStore(db, oplog=OpLog("nisse-dev", io.StringIO()))
|
|
store.transcript("demo-1", "orchestrator").append(Fact(text="PR #3 opened"))
|
|
store.close()
|
|
assert "[demo-1/orchestrator] FACT: PR #3 opened" in render(db)
|
|
|
|
|
|
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
|