5eea87882a
* refactor(desktop): split clarify-tool.tsx into a clarify/ folder
Pure moves, no behaviour change. Parsing, the question-card core
(shell, choice rows, question block), the delivery watchdog, and each
pending/settled card get their own file so the core can be reused.
* feat(clarify): one questions[] shape with per-question status and one outcome
The clarify tool now takes only questions=[{question, choices?, multi_select?}].
A wrong shape is a tool error that names the right one, so a model that
sends the old top-level question/choices corrects itself on the next call.
Every result has the same shape on every surface: each response carries
status (answered, skipped, unanswered) with user_response null unless
answered, and the result carries one outcome (submitted, cancelled,
timed_out, undelivered) plus an optional surface-written notice. The
timeout and cancel sentences that used to pose as the user's answer are
gone, and the compressor reads status instead of matching their prefixes.
The callback contract is callback(questions) -> {answers, outcome, notice?}
(None = skipped, missing qid = unanswered). tui_gateway settles a batch the
same way for the last lock, a cancel, an interrupt and the deadline, and
clarify.lock keeps a null answer as a skip. A multi-select answer that is
not a JSON array counts as one typed ("Other") answer. The tool-row preview
reads the first question.
* feat(clarify): every surface asks through the one question card
CLI: the batch panel is the only panel; Enter on an empty field skips a
question, Ctrl+C cancels and keeps the locked answers, the deadline returns
timed_out. -q and -z return undelivered with a no-user notice.
Ink TUI: the single-question prompt is gone; the card supports multi-select
(Space or a digit toggles, Enter locks, typed Other text joins the picks),
an empty submit skips, Esc cancels, and "Batch" names are dropped.
Desktop: the single-question card is deleted and its keyboard handling moved
into the one card (arrows, letters and digits, auto-advance, Enter picks then
confirms). Confirm enables at one answer; blank questions lock null; Skip and
a composer message cancel; the settled card shows No answer for unanswered
questions. The bots room card follows the same contract.
Messaging: one card per question with a "Reply skip to skip" line in every
locale; timeouts and delivery failures map to timed_out and undelivered.
* fix(clarify): cancelled for a released messaging card, labels win over the skip word
A prose reply to a messaging choice card, /new and session end released
the wait with "", which read as timed_out. They now resolve with a
CANCELLED marker and the tool gets outcome cancelled.
A typed reply that matches a choice label ("Skip") now resolves to that
choice; the skip word applies only when no choice matches.
The bots room card sends the picked labels as they are; the tool already
strips the recommendation label. Unused OUTCOMES and a new docstring and
comment are removed.
* fix(tui): re-editing a multi-select answer keeps its picks
The Ink card stored a multi-select answer as display text ("A, B"), so
revisiting the question put the whole string into Other and re-locked it
as one item. The answers map now keeps the raw JSON array, the card
restores the picks on revisit, and only the display lines format it.
Comments that earlier edits reworded are restored to their original
words, minus the phrases the change made wrong. The compute-host clarify
lock accepts None for a skipped question.
* test(clarify): align three checks with the one-answer confirm and the regenerated keys
The desktop Cmd+Enter test now expects a send with one answer (the blank
question locks null), the compressor test expects the single-answer summary
the code gives, and locales/_keys.desktop.json is regenerated for the
removed and added clarify strings.
* test(tui): the one-question card header is singular
56 lines
2.5 KiB
Python
56 lines
2.5 KiB
Python
"""#121548: model-visible elision mints the non-imitable compression marker.
|
|
|
|
The bare bracketed truncation idiom those renderers used to compose was imitated
|
|
from replayed context into new durable writes (see #83435/#83714). All elision now
|
|
routes through ``agent.compression_marker.elide`` / ``elide_middle``; this file pins
|
|
guard parity and that the real renderers emit a guard-visible marker, never the idiom.
|
|
"""
|
|
from __future__ import annotations
|
|
|
|
import json
|
|
import re
|
|
|
|
from agent.compression_marker import (
|
|
_COMPRESSION_MARKER_RE,
|
|
elide,
|
|
elide_middle,
|
|
)
|
|
from agent.context_compressor import (
|
|
ContextCompressor,
|
|
_build_verbatim_user_section,
|
|
_compact_fallback_turn,
|
|
_summarize_tool_result,
|
|
)
|
|
|
|
# Any "...[<words> truncated]" variant, not just the bare one (e.g. "...[fallback summary truncated]").
|
|
IMITABLE_MARKER_RE = re.compile(r"(?:\.\.\.|…)\s?\[[^\]\n]*truncat")
|
|
|
|
|
|
def test_minted_marker_is_caught_by_the_dispatch_boundary_guard():
|
|
"""A copied marker must refuse a durable write regardless of which renderer leaked it."""
|
|
for out in (elide("y" * 4000, 199), elide_middle("y" * 4000, 100, 100)):
|
|
assert _COMPRESSION_MARKER_RE.search(out)
|
|
|
|
|
|
def test_real_renderers_emit_a_guard_visible_marker_never_the_imitable_idiom():
|
|
"""Oversized input through the real renderers yields the guarded marker, not the idiom.
|
|
|
|
The active-task line quotes both apostrophes and double quotes so repr() cannot escape
|
|
the marker's own apostrophe out of the guard's reach.
|
|
"""
|
|
quoted = "a'b\"c " * 400
|
|
clarify = json.dumps({"responses": [{"status": "answered", "user_response": "A" * 5000}]})
|
|
outputs = {
|
|
"clarify": _summarize_tool_result("clarify", "{}", clarify),
|
|
"fallback_turn": _compact_fallback_turn("z " * 5000),
|
|
"verbatim_user": _build_verbatim_user_section([{"role": "user", "content": "q" * 30000}]),
|
|
"record": ContextCompressor._bound_oversized_record("r" * 50000, 4000),
|
|
"active_task": ContextCompressor._latest_user_task_snapshot([{"role": "user", "content": quoted}]),
|
|
}
|
|
for name, out in outputs.items():
|
|
assert out and _COMPRESSION_MARKER_RE.search(out), (name, out[-300:] if out else out)
|
|
assert not IMITABLE_MARKER_RE.search(out), (name, out[-300:])
|
|
# A budget too small for marker + content skips the straddler instead of a marker-only quote.
|
|
fills_budget = [{"role": "user", "content": "u" * 3_998}] * 6 # 23,988 of the 24,000 budget
|
|
assert "chars omitted" not in _build_verbatim_user_section([{"role": "user", "content": "v" * 500}, *fills_budget])
|