bvandeusenandClaude Opus 5
921565696c
CI & Build / Python lint (push) Successful in 3s
CI & Build / Plugin hooks (push) Successful in 11s
CI & Build / integration (push) Successful in 48s
CI & Build / TypeScript typecheck (push) Successful in 54s
CI & Build / Python tests (push) Successful in 1m24s
CI & Build / Build & push image (push) Successful in 23s
The reporting-back skill ships default shapes; an operator's adjustments to them are preference records. Prompt-time retrieval matches the operator's message, and a shape preference is about the reply, so those preferences were on file and never arrived. Operator's decision (logged on #4013): the server delivers them for a completion report, and the skill asks for every other kind. - Completion reports (option C): closing a task with update_task runs a kind-filtered preference search for the moment "writing the completion report after finishing a task" and returns matches as `reply_preferences` ({id, title, statement, kind}), with a sentence added to `report_back` naming the key. A preference says it is about completion reports through its own when_to_apply; no tag or column. Omitted when nothing matches, and the lookup fails open. - Telemetry: every call logs to retrieval_logs under `report_preference` (empty calls included; a search that never ran writes no row) and hits are recorded surfaced. The source is ranked, so it counts toward pull-through. The bar is the prompt arm's setting until step 6 reads this source's near misses. - Every other reply (option A): reporting-back gains "The operator's own shapes come first". Before a finding, decision, handoff or "where are we", search(content_type="rule") in the words of that moment and follow what comes back. Registered in the ownership guard with reporting-back as owner. - Loading reply shapes at session start (option B) was rejected: it would be a small copy of the preloading milestone 394 retired. Domain-neutral query (pinned); works on an install with no preferences. Plugin version minted. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
59 lines
2.5 KiB
Python
59 lines
2.5 KiB
Python
"""update_task closes a task with a one-line reminder of what the report needs.
|
|
|
|
The in-band half of milestone 409 step 3: the skill and static context only
|
|
exist in the Claude Code plugin, and a tool response reaches every MCP client
|
|
at the moment a piece of work closes. Pinned on the response, not the wording.
|
|
|
|
Step 4 adds the operator's own completion-report preferences beside the cue,
|
|
retrieved at that same moment — and only then, and only when there are any.
|
|
"""
|
|
from unittest.mock import AsyncMock, MagicMock, patch
|
|
|
|
import pytest
|
|
|
|
pytestmark = pytest.mark.usefixtures("_bind_user")
|
|
|
|
_PREF = {"id": 41, "title": "Say how it was checked", "statement": "…", "kind": "preference"}
|
|
|
|
|
|
async def _update(prefs=None, **kwargs):
|
|
from scribe.mcp.tools.tasks import update_task
|
|
|
|
note = MagicMock(id=5, user_id=7, project_id=3)
|
|
note.to_dict.return_value = {"id": 5}
|
|
lookup = AsyncMock(return_value=list(prefs or []))
|
|
with patch("scribe.mcp.tools.tasks.notes_svc.update_note", AsyncMock(return_value=note)), \
|
|
patch("scribe.mcp.tools.tasks.systems_tools.attach_systems", AsyncMock()), \
|
|
patch("scribe.mcp.tools.tasks.placement_svc.attach_placement", AsyncMock()), \
|
|
patch("scribe.mcp.tools.tasks.reply_prefs_svc.completion_preferences", lookup):
|
|
return await update_task(task_id=5, **kwargs), lookup
|
|
|
|
|
|
@pytest.mark.parametrize("status", ["done", "cancelled"])
|
|
async def test_closing_a_task_carries_the_cue(status):
|
|
out, _ = await _update(status=status)
|
|
assert "placement" in out["report_back"] and "needs them" in out["report_back"]
|
|
|
|
|
|
@pytest.mark.parametrize("kwargs", [{"status": "in_progress"}, {"status": "todo"}, {"body": "more notes"}])
|
|
async def test_other_updates_do_not(kwargs):
|
|
out, lookup = await _update(prefs=[_PREF], **kwargs)
|
|
assert "report_back" not in out and "reply_preferences" not in out
|
|
lookup.assert_not_awaited()
|
|
|
|
|
|
async def test_closing_hands_back_the_operators_report_preferences():
|
|
out, lookup = await _update(prefs=[_PREF], status="done")
|
|
assert out["reply_preferences"] == [_PREF]
|
|
# The cue says the key is there, so it never arrives unexplained.
|
|
assert "reply_preferences" in out["report_back"]
|
|
lookup.assert_awaited_once_with(7, project_id=3)
|
|
|
|
|
|
async def test_no_preferences_means_no_key_and_the_plain_cue():
|
|
from scribe.mcp.tools.tasks import REPORT_BACK_CUE
|
|
|
|
out, _ = await _update(prefs=[], status="done")
|
|
assert "reply_preferences" not in out
|
|
assert out["report_back"] == REPORT_BACK_CUE
|