feat(plugin): a reply's sections are chosen, not filled (#4153)
CI & Build / Python lint (push) Successful in 4s
CI & Build / Plugin hooks (push) Successful in 13s
CI & Build / TypeScript typecheck (push) Successful in 53s
CI & Build / integration (push) Successful in 49s
CI & Build / Python tests (push) Successful in 1m30s
CI & Build / Build & push image (push) Successful in 16s
CI & Build / Python lint (push) Successful in 4s
CI & Build / Plugin hooks (push) Successful in 13s
CI & Build / TypeScript typecheck (push) Successful in 53s
CI & Build / integration (push) Successful in 49s
CI & Build / Python tests (push) Successful in 1m30s
CI & Build / Build & push image (push) Successful in 16s
Milestone 409 step 6 measured the scaffold on live sessions and found its
two halves disagreeing: adherence passed and the read test failed.
Completion replies carried every section the table asks for and were
still hard to read.
The cause was in the skill, not in compliance with it. It said to pick a
kind of reply "then fill its sections... keep them even when one is
short", which is an instruction to complete a form, and nothing anywhere
set a ceiling. A faithful reply and an unreadable one were the same
reply.
Four changes to the discipline around the scaffold. The categories and
their sections are untouched.
- Sections are what to consider including, not a form to complete. A
section answering a standing question ("does anything need me?") is
always answered, even with "nothing"; a section that explains earns its
place only when it changes what the operator does. Otherwise it belongs
in the record's log, where it is available and not in the way.
- Write the shortest reply that carries the answer, with named exceptions
so this cannot be read as "always be terse".
- "Needs you" takes BOTH tests: theirs to decide, AND work is waiting on
it. A question answerable by reading something or taking an available
measurement is work not yet done, not a request — settle it, say which
way you went, and leave them free to overrule.
- A decision already made gets acted on. Re-arguing a settled question
reads as contradicting yourself rather than as being careful, and costs
the operator the decision twice.
"Before sending" gains a second pass for what can go, since the existing
check asks what is MISSING, which a bloated reply passes.
Guards in tests/test_reply_discipline.py, three topics registered for
ownership. Every guard was falsified against the pre-change text before
committing (rule 167): all five fail on it and pass on the fix, and the
sixth deliberately passes both since it guards the scaffold against
collateral damage. No absence checks — the skill legitimately discusses
filling in order to warn against it, so asserting "fill" is absent would
false-alarm on the corrected text (snippet #3352).
Instance-agnostic per rule 115: the added text carries no record ids, no
software-specific terms and no verbatim quotes.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01821k5B3Ysecp9fNYs92Kuy
This commit is contained in:
@@ -0,0 +1,137 @@
|
||||
"""A reply's sections are chosen, not filled (#4153, milestone 409 step 7).
|
||||
|
||||
WHY THIS EXISTS
|
||||
|
||||
Step 6 measured the scaffold on live sessions and found the two halves
|
||||
disagreeing: **adherence passed and the read test failed.** Completion replies
|
||||
carried every section the table asks for — placement, what changed, what needs
|
||||
the operator, what comes next — and the operator still could not read them.
|
||||
|
||||
The cause was in the skill rather than in compliance with it. It said to pick a
|
||||
kind of reply "then fill its sections… keep them even when one is short", which
|
||||
is an instruction to complete a form. Nothing anywhere set a ceiling, and a
|
||||
section with a heading and nothing to say gets filled rather than dropped. So a
|
||||
faithful reply and an unreadable one were the same reply.
|
||||
|
||||
WHAT IS PINNED
|
||||
|
||||
The discipline, not the scaffold. The fifteen categories and their sections are
|
||||
unchanged and are not this file's subject:
|
||||
|
||||
1. Sections are chosen — a standing question is always answered, an
|
||||
explanation earns its place.
|
||||
2. The reply is as short as the answer allows, and gets a second pass for
|
||||
what can go.
|
||||
3. "Needs you" takes BOTH tests: theirs to decide, and blocking.
|
||||
4. A decision already made is acted on rather than re-argued.
|
||||
|
||||
RULE 167, AND WHY THERE IS NO ABSENCE CHECK HERE
|
||||
|
||||
The obvious guard — assert the skill no longer tells anyone to "fill" a
|
||||
section — is the trap snippet #3352 names. This skill legitimately discusses
|
||||
filling in order to warn against it ("not a form to complete", "a section
|
||||
filled because it was in the table"), so an absence check would fail on the
|
||||
corrected text: a false alarm about the very thing it protects.
|
||||
|
||||
So every assertion here is a PRESENCE check, and one is POSITIONAL —
|
||||
`test_the_needs_you_test_sits_with_the_needs_you_section` pins where the test
|
||||
lives, not merely that the words occur somewhere in the file. All four were
|
||||
falsified against the pre-#4153 text before being committed.
|
||||
"""
|
||||
from __future__ import annotations
|
||||
|
||||
import pathlib
|
||||
|
||||
ROOT = pathlib.Path(__file__).resolve().parents[1]
|
||||
SKILL = ROOT / "plugin/skills/reporting-back/SKILL.md"
|
||||
|
||||
|
||||
def _flat() -> str:
|
||||
"""Whitespace-flattened: the file is hard-wrapped, so phrases straddle lines."""
|
||||
return " ".join(SKILL.read_text().split()).lower()
|
||||
|
||||
|
||||
def test_sections_are_chosen_rather_than_completed():
|
||||
"""The framing the operator reacted to was "fill its sections"."""
|
||||
text = _flat()
|
||||
assert "not a form to complete" in text
|
||||
# Both halves of the distinction, or "choose" collapses back into "fill":
|
||||
# a standing question is answered even when the answer is nothing, an
|
||||
# explanation is dropped when it changes nothing.
|
||||
assert "always answered, even when the answer is nothing" in text
|
||||
assert "changes what the operator does or decides" in text
|
||||
|
||||
|
||||
def test_the_reply_carries_a_length_discipline():
|
||||
"""Without a ceiling, every section is an invitation to keep writing."""
|
||||
text = _flat()
|
||||
assert "write the shortest reply that carries the answer" in text
|
||||
# And the ceiling has named exceptions, so this cannot be read as
|
||||
# "always be terse" — a measurement the operator asked for still earns room.
|
||||
assert "extra length has to be earned" in text
|
||||
|
||||
|
||||
def test_the_reply_gets_a_second_pass_for_what_can_go():
|
||||
"""Cutting is a separate act from writing, and needs saying separately.
|
||||
|
||||
The pre-existing check asked whether anything was MISSING, which a bloated
|
||||
reply passes.
|
||||
"""
|
||||
text = _flat()
|
||||
assert "what can go" in text
|
||||
# Cutting must not read as withholding, or it will not be done.
|
||||
assert "cutting is not hiding" in text
|
||||
|
||||
|
||||
def test_the_needs_you_test_sits_with_the_needs_you_section():
|
||||
"""POSITIONAL. The test has to be where the section is defined.
|
||||
|
||||
A reader reaches this while writing that section; stated anywhere else it
|
||||
is a paragraph nobody is reading at the moment it applies. Asserted by
|
||||
offset rather than by presence, so moving it away fails here.
|
||||
"""
|
||||
raw = " ".join(SKILL.read_text().split())
|
||||
lowered = raw.lower()
|
||||
|
||||
needs_you = lowered.index("- **needs you** — an action")
|
||||
the_test = lowered.index("is this theirs to decide")
|
||||
next_bullet = lowered.index("- **next** —", needs_you)
|
||||
|
||||
assert needs_you < the_test < next_bullet, (
|
||||
"the needs-you test has moved out of the Needs you bullet; a reader "
|
||||
"writing that section will not meet it"
|
||||
)
|
||||
# Both halves are load-bearing: "theirs" alone still admits a question the
|
||||
# session could have answered, "blocking" alone admits one that is not
|
||||
# theirs to make.
|
||||
assert "work waiting on it" in lowered
|
||||
assert "not for what you are unsure about" in lowered
|
||||
|
||||
|
||||
def test_a_settled_decision_is_acted_on_rather_than_re_argued():
|
||||
"""Re-opening a decision reads as self-contradiction, not as diligence.
|
||||
|
||||
Phrased as a practice rather than a prohibition (rule 165): the instruction
|
||||
is what to DO with a decision, with the failure named after it.
|
||||
"""
|
||||
text = _flat()
|
||||
assert "a decision already made gets acted on" in text
|
||||
assert "reads as contradicting yourself rather than as being careful" in text
|
||||
# The escape hatch stays open, or this becomes a rule against ever
|
||||
# correcting anything — which is the opposite of what is wanted.
|
||||
assert "genuinely overturns the choice" in text
|
||||
|
||||
|
||||
def test_the_scaffold_itself_is_untouched():
|
||||
"""This step changed the discipline AROUND the sections, not the sections.
|
||||
|
||||
If a future edit deletes a category while tightening the prose, that is a
|
||||
change to #4009's subject and should not ride along silently here.
|
||||
"""
|
||||
text = _flat()
|
||||
for section in ("where this sits", "what now works", "how / why",
|
||||
"needs you", "next"):
|
||||
assert section in text, f"completion-report section {section!r} is gone"
|
||||
for kind in ("completion", "finding", "blocked / failed", "progress",
|
||||
"decision", "clarification", "handoff", "approval", "conflict"):
|
||||
assert kind in text, f"reply kind {kind!r} is gone"
|
||||
Reference in New Issue
Block a user