fix(issue-30): review ad3d8206 - a prompt glyph inside a draft is draft text; the R4 regression test tells the defect apart

- input_region: in the prompt-line shape the input box starts only at a
  column-0 prompt (codex indents a draft's continuation lines), and the
  prompt and the (whole-line) placeholder are stripped from the box's first
  non-blank line only, so `› Explain this terminal prompt:\n  ›` is not empty.
- test_r4 runs with S=40 again: the defective code nudged ~30 s after a
  missed transition, which S=10 could not tell from the fixed ~10 s.

Both new checks fail against the defective versions (stall_watch.py at
47e4274 -> 30.24 s < 40; input_region.py at bf0f5c1 -> nudge sent) and pass
now, each with its passing twin.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
GodopuandClaude Opus 5.5 committed 2026-09-25 16:02:39 +00:00
1 parent bf0f5c1014
commit 9ec0569401
2 files changed
+62 -12

No files matched your search

+18 -10
View File
@@ -11,12 +11,13 @@ def extract_input_region(pane_text: str, agent_name: str) -> str:
1. an `input_block_prefix` -> the last contiguous block of lines starting 1. an `input_block_prefix` -> the last contiguous block of lines starting
with it, prefix removed, cut at the first `input_stop_pattern` line; with it, prefix removed, cut at the first `input_stop_pattern` line;
2. two or more `input_rule_pattern` rules -> the lines between the last two; 2. two or more `input_rule_pattern` rules -> the lines between the last two;
3. an `input_prompt` -> from the last line starting with the prompt to 3. an `input_prompt` -> from the last line starting (column 0) with the prompt to
the end of the pane, minus a last non-blank line matching the end of the pane, minus a last non-blank line matching
`input_stop_pattern` (the status footer). Every other line below the `input_stop_pattern` (the status footer). Every other line below the
prompt line is input: a multi-line draft is never cut to its first line. prompt line is input: a multi-line draft is never cut to its first line.
Then `input_frame_chars`, the prompt and the placeholder are stripped. There Then `input_frame_chars` are stripped, and the prompt and the placeholder
(whole-line) are stripped from the box's first non-blank line only. There
is no whole-pane fallback: a pane with none of these shapes has no input is no whole-pane fallback: a pane with none of these shapes has no input
region and yields a non-empty "unknown" result rather than a guess. region and yields a non-empty "unknown" result rather than a guess.
Raises ValueError for agents without input area facts (like hermes' peers). Raises ValueError for agents without input area facts (like hermes' peers).
@@ -52,7 +53,10 @@ def extract_input_region(pane_text: str, agent_name: str) -> str:
region_lines = lines[rule_indices[-2] + 1:rule_indices[-1]] region_lines = lines[rule_indices[-2] + 1:rule_indices[-1]]
if region_lines is None: if region_lines is None:
starts = [i for i, line in enumerate(lines) if line.lstrip().startswith(prompt)] # The composer's prompt sits at column 0; a draft's continuation lines
# are indented, so an indented prompt character is draft text (review
# ad3d8206), never the start of the input box.
starts = [i for i, line in enumerate(lines) if line.startswith(prompt)]
if starts: if starts:
region_lines = [line for line in lines[starts[-1]:]] region_lines = [line for line in lines[starts[-1]:]]
while region_lines and not region_lines[-1].strip(): while region_lines and not region_lines[-1].strip():
@@ -68,11 +72,15 @@ def extract_input_region(pane_text: str, agent_name: str) -> str:
if frame: if frame:
region_lines = [line.strip().strip(frame) for line in region_lines] region_lines = [line.strip().strip(frame) for line in region_lines]
region_text = "\n".join(region_lines) # The prompt and the placeholder belong to the box's first line only: the
region_text = re.sub(r'^\s*' + re.escape(prompt) + r'\s*', '', region_text, flags=re.MULTILINE) # same characters further down are what the user typed.
region_lines = list(region_lines)
first = next((i for i, line in enumerate(region_lines) if line.strip()), None)
if first is not None:
head = re.sub(r'^\s*' + re.escape(prompt) + r'\s*', '', region_lines[first], count=1)
placeholder = adapter.input_placeholder
if placeholder and head.strip() == placeholder:
head = ''
region_lines[first] = head
placeholder = adapter.input_placeholder return "\n".join(region_lines).strip()
if placeholder:
region_text = region_text.replace(placeholder, '')
return region_text.strip()
+44 -2
View File
@@ -676,7 +676,7 @@ def test_r4_a_missed_transition_restarts_the_idle_window(mam_sandbox, mock_herdr
wait mock. process-info retains its measured nested result shape. wait mock. process-info retains its measured nested result shape.
""" """
reg = mam_sandbox / ".mam" / "jobs" reg = mam_sandbox / ".mam" / "jobs"
env = _env(mam_sandbox, MAM_STALL_IDLE_S=10) env = _env(mam_sandbox, MAM_STALL_IDLE_S=40)
jid = _job(env, reg) jid = _job(env, reg)
agent = _proc("exec sleep 300") agent = _proc("exec sleep 300")
observed = mam_sandbox / "observed.json" observed = mam_sandbox / "observed.json"
@@ -729,7 +729,10 @@ def test_r4_a_missed_transition_restarts_the_idle_window(mam_sandbox, mock_herdr
w.terminate() w.terminate()
w.communicate(timeout=10) w.communicate(timeout=10)
idle_time = times['prompted'] - times.get('changed', times['started']) idle_time = times['prompted'] - times.get('changed', times['started'])
assert idle_time >= 10, {'continuous_idle_seconds': idle_time, 'threshold': 10} # S must exceed the 30 s re-judgement interval: with the old code the nudge came
# ~30 s after the missed transition, which only fails the assertion when S > 30
# (review ad3d8206; S=10 passed on the defective code too).
assert idle_time >= 40, {'continuous_idle_seconds': idle_time, 'threshold': 40}
finally: finally:
if w is not None and w.poll() is None: if w is not None and w.poll() is None:
w.terminate() w.terminate()
@@ -745,3 +748,42 @@ def test_r1_the_codex_extractor_keeps_every_line_under_the_prompt():
assert extract_input_region(draft, "codex") == "draft on the second input line" assert extract_input_region(draft, "codex") == "draft on the second input line"
no_footer = "\n".join(idle.splitlines()[:-1]).replace("› Ask Codex to do anything", "›\n a · b · c") no_footer = "\n".join(idle.splitlines()[:-1]).replace("› Ask Codex to do anything", "›\n a · b · c")
assert extract_input_region(no_footer, "codex") != "", "only the last line may be the footer" assert extract_input_region(no_footer, "codex") != "", "only the last line may be the footer"
# Review ad3d8206 (planner-reviewer-codex-01): a prompt glyph inside the draft
# is draft text, not the start of the input box (the reviewer's reproduction).
@pytest.mark.parametrize("draft", [False, True])
def test_r1b_a_draft_containing_the_prompt_glyph_is_not_empty(mam_sandbox, mock_herdr, draft):
reg = mam_sandbox / ".mam" / "jobs"
env = _env(mam_sandbox, MAM_STALL_IDLE_S=1)
jid = _job(env, reg)
agent = _proc("exec sleep 300")
w = None
try:
pane = _pane("codex")
if draft:
pane = pane.replace("› Ask Codex to do anything", "› Explain this terminal prompt:\n ›")
_agent(mock_herdr, "reviewer-codex-t", "codex", agent.pid, "idle", pane)
w = _watch(env, reg, jid, "reviewer-codex-t", "codex")
if draft:
time.sleep(5)
else:
assert _until(lambda: _prompts(mock_herdr))
prompts = _prompts(mock_herdr)
_finish(env, reg, jid, w)
assert len(prompts) == (0 if draft else 1), prompts
finally:
if w is not None and w.poll() is None:
w.terminate()
w.communicate(timeout=10)
_kill(agent)
def test_r1b_the_extractor_strips_the_prompt_from_the_first_line_only():
from lib_py.agents.input_region import extract_input_region
idle = _pane("codex")
for draft in ("› Explain this terminal prompt:\n ›", "›\n ›", "› Ask Codex to do anything\n more"):
assert extract_input_region(idle.replace("› Ask Codex to do anything", draft), "codex") != "", draft
typed = re.sub(r"^❯\s*$", "❯ x\n ❯", _pane("claude"), count=1, flags=re.M)
assert typed != _pane("claude") and extract_input_region(typed, "claude") != ""