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
92 lines
3.2 KiB
Python
92 lines
3.2 KiB
Python
"""A real delegation over the Anthropic passthrough: scoped sub-task in,
|
|
working code and a structured handback out."""
|
|
|
|
import io
|
|
from pathlib import Path
|
|
|
|
import pytest
|
|
|
|
from nisse_dev.delegation import Caps, Delegation
|
|
from nisse_dev.git import GitRepo
|
|
from nisse_dev.llm import AnthropicPassthroughClient
|
|
from nisse_dev.oplog import OpLog
|
|
from nisse_dev.state import StateStore
|
|
from nisse_dev.tools import Workspace
|
|
|
|
pytestmark = pytest.mark.integration
|
|
|
|
BRIEF = """Create `slugify.py` in the workspace root containing a function
|
|
`slugify(text)` that lowercases the text and replaces every run of
|
|
non-alphanumeric characters with a single hyphen, with no leading or trailing
|
|
hyphen. Then create `test_slugify.py` with at least two assertions covering
|
|
it, and run `python -m pytest test_slugify.py -q` until it passes."""
|
|
|
|
|
|
def build(
|
|
tmp_path: Path, caps: Caps, client: AnthropicPassthroughClient, model: str
|
|
) -> tuple[Delegation, GitRepo, StateStore]:
|
|
repo = GitRepo(tmp_path / "work")
|
|
repo.init()
|
|
repo.configure_identity("nisse-dev-testing", "n@t.test")
|
|
(repo.root / "README.md").write_text("sandbox\n")
|
|
repo.commit_all("seed")
|
|
store = StateStore(tmp_path / "state.db", oplog=OpLog("nisse-dev", io.StringIO()))
|
|
delegation = Delegation(
|
|
client,
|
|
store,
|
|
Workspace(repo.root, timeout_s=60),
|
|
repo,
|
|
model=model,
|
|
caps=caps,
|
|
)
|
|
return delegation, repo, store
|
|
|
|
|
|
def test_delegate_completes_a_scoped_subtask(
|
|
tmp_path: Path, passthrough: AnthropicPassthroughClient, live_model: str
|
|
) -> None:
|
|
delegation, repo, store = build(
|
|
tmp_path, Caps(turns=12, wall_clock_s=300.0), passthrough, live_model
|
|
)
|
|
|
|
result = delegation.run(
|
|
store.transcript("t", "helper"), brief=BRIEF, branch="live/delegation-1"
|
|
)
|
|
|
|
assert result.usable, f"delegation did not hand back: {result.status} {result.note}"
|
|
assert (repo.root / "slugify.py").exists()
|
|
|
|
# The handback is the entire interface back, so it must actually say
|
|
# something in each part rather than be structurally present but empty.
|
|
handback = result.handback
|
|
assert handback is not None
|
|
assert len(handback.changed) > 10
|
|
assert len(handback.now_true) > 10
|
|
assert len(handback.next) > 5
|
|
|
|
# The delegate's own work is on its branch, and it really runs.
|
|
assert repo.current_branch() == "live/delegation-1"
|
|
check = Workspace(repo.root, timeout_s=60).run_command(
|
|
"python -m pytest test_slugify.py -q"
|
|
)
|
|
assert check.success, f"delegate's own tests do not pass: {check.result[:400]}"
|
|
|
|
|
|
def test_a_cap_breach_discards_the_work(
|
|
tmp_path: Path, passthrough: AnthropicPassthroughClient, live_model: str
|
|
) -> None:
|
|
# One turn cannot finish the brief, so this exercises the abort path
|
|
# against a real model rather than a scripted one.
|
|
delegation, repo, store = build(
|
|
tmp_path, Caps(turns=1, wall_clock_s=120.0), passthrough, live_model
|
|
)
|
|
|
|
result = delegation.run(
|
|
store.transcript("t", "helper"), brief=BRIEF, branch="live/delegation-2"
|
|
)
|
|
|
|
assert not result.usable
|
|
assert result.status == "capped"
|
|
assert repo.current_branch() == "main"
|
|
assert not (repo.root / "slugify.py").exists()
|