#!/usr/bin/env python3
"""Static + logic tests for the task event-log page's client JS.
The app binary cannot be built in every container (statum-mkpstm /
libstatum are build-time dependencies), so this suite verifies
src/pages/task_log.html two ways:
1. Statically - the ", 1)
assert head, "no content before the script block"
return body
# ---------------------------------------------------------------------------
# Static checks
# ---------------------------------------------------------------------------
class ScriptSourceTests(unittest.TestCase):
"""What the served bytes must look like after compilation."""
def setUp(self):
self.body = script_body()
def test_script_is_ascii_only(self):
"""Non-ASCII in a script body comes back as literal entity
text ("·") because the compiler escapes script bodies
and the browser decodes exactly once. ASCII (with \\uXXXX
escapes for the characters we want) is immune."""
offenders = [(index, hex(ord(char)))
for index, char in enumerate(self.body) if ord(char) > 127]
self.assertEqual(offenders, [])
def test_unicode_escapes_used_for_separators(self):
"""The separator characters must still render - as escapes,
not as raw bytes and not as HTML entities."""
for escape in ("\\u00b7", "\\u2026", "\\u2014"):
self.assertIn(escape, self.body)
self.assertNotIn("·", self.body)
self.assertNotIn("—", self.body)
def test_stream_wired_through_onmessage(self):
self.assertRegex(self.body, r"stream\.onmessage\s*=")
self.assertNotIn("addEventListener('append'", self.body)
self.assertNotIn('addEventListener("append"', self.body)
def test_heartbeat_ping_is_skipped(self):
self.assertRegex(self.body, r"message\.data\s*===\s*'ping'")
def test_load_more_pages_before_oldest(self):
self.assertRegex(self.body, r"/events\?before='\s*\+\s*\(state\.oldest")
def test_page_is_reversed_before_ingest(self):
self.assertIn("slice().reverse().forEach(ingest)", self.body)
def test_exhausted_set_when_no_more(self):
self.assertIn("state.exhausted = true", self.body)
def test_more_button_sits_above_the_feed(self):
# Search the page markup only - the script's comments also
# mention [data-log-feed], before the elements do.
with open(PAGE, encoding="utf-8") as handle:
markup = handle.read().split("", 1)[1]
more = markup.index("data-log-more")
feed = markup.index("data-log-feed")
self.assertLess(more, feed,
"the load-older control must precede the feed markup")
def test_delimiters_balance(self):
"""A cheap structural stand-in for a JS parser (none is
installed here): after stripping comments and string literals
every bracket must close."""
body = self.body
out = []
i = 0
mode = None # None | 'line' | 'block' | "'" | '"'
while i < len(body):
char = body[i]
nxt = body[i + 1] if i + 1 < len(body) else ""
if mode is None:
if char == "/" and nxt == "/":
mode = "line"
i += 2
continue
if char == "/" and nxt == "*":
mode = "block"
i += 2
continue
if char in "'\"":
mode = char
i += 1
continue
out.append(char)
elif mode == "line":
if char == "\n":
mode = None
out.append("\n")
elif mode == "block":
if char == "*" and nxt == "/":
mode = None
i += 2
continue
else: # inside a string literal
if char == "\\":
i += 2
continue
if char == mode:
mode = None
i += 1
self.assertEqual(mode, None, "unterminated comment or string literal")
pairs = {")": "(", "]": "[", "}": "{"}
stack = []
for char in out:
if char in "([{":
stack.append(char)
elif char in pairs:
self.assertTrue(stack and stack[-1] == pairs[char],
"unbalanced %r at depth %s" % (char, stack))
stack.pop()
self.assertEqual(stack, [], "unclosed delimiters %s" % stack)
# ---------------------------------------------------------------------------
# Port of the client logic (keep in step with task_log.html)
# ---------------------------------------------------------------------------
STICK_THRESHOLD = 48 # px that still counts as "reading the tail"
PAGE_SIZE = 30
class Feed(object):
"""Scroll-state stand-in for [data-log-feed]."""
def __init__(self, scroll_height=0, client_height=600, scroll_top=0):
self.scroll_height = scroll_height
self.client_height = client_height
self.scroll_top = scroll_top
def at_bottom(feed):
"""PORT: a feed shorter than its viewport counts as at-bottom."""
return feed.scroll_height - feed.scroll_top - feed.client_height \
<= STICK_THRESHOLD
class State(object):
"""PORT: the module-level `state` object."""
def __init__(self):
self.events = []
self.oldest = 0
self.exhausted = False
self.loading = False
self.seeded = False
def ingest(state, evt):
"""PORT: keep state.events oldest-first (ascending id); skip ids
already held (SSE replay after a reconnect resends a frame)."""
i = 0
while i < len(state.events) and state.events[i]["id"] < evt["id"]:
i += 1
if i < len(state.events) and state.events[i]["id"] == evt["id"]:
return
state.events.insert(i, evt)
if evt["id"] < state.oldest or state.oldest == 0:
state.oldest = evt["id"]
def render(state, feed, mode=None, height_after=None):
"""PORT of render(mode): decide the post-render scroll position.
height_after stands in for the DOM rebuild's new scrollHeight."""
was_at_bottom = at_bottom(feed)
height_before = feed.scroll_height
scroll_top_before = feed.scroll_top
if height_after is not None:
feed.scroll_height = height_after
if not state.seeded and len(state.events) > 0:
state.seeded = True
feed.scroll_top = feed.scroll_height # scrollToBottom()
elif mode == "prepend":
if was_at_bottom:
feed.scroll_top = feed.scroll_height
else:
feed.scroll_top = scroll_top_before + (feed.scroll_height
- height_before)
elif was_at_bottom:
feed.scroll_top = feed.scroll_height
else:
feed.scroll_top = scroll_top_before
return feed.scroll_top
def server_page(newest, oldest, more):
"""The endpoint's wire shape: newest-first within the page."""
return {"events": [{"id": i} for i in range(newest, oldest - 1, -1)],
"more": more}
def load_more(state, feed, page, height_after):
"""PORT of loadMore's success path: reverse the newest-first page
into chronological order, ingest it, set exhausted, render."""
rows = page["events"]
for evt in reversed(rows):
ingest(state, evt)
if not page["more"] or len(rows) == 0:
state.exhausted = True
return render(state, feed, mode="prepend", height_after=height_after)
def on_stream_message(state, feed, data, height_after):
"""PORT of onStreamMessage: skip heartbeats, ingest one row."""
if data == "ping":
return feed.scroll_top
ingest(state, {"id": int(data)})
return render(state, feed, mode="append", height_after=height_after)
# ---------------------------------------------------------------------------
# Behaviour tests
# ---------------------------------------------------------------------------
def ids(state):
return [evt["id"] for evt in state.events]
class ChronologyTests(unittest.TestCase):
def test_initial_window_renders_oldest_first(self):
"""The SSE replay / first JSON page arrives newest-first
([30..1]); the feed must render [1..30] - oldest at the top."""
state = State()
for evt in server_page(30, 1, True)["events"]:
ingest(state, evt)
self.assertEqual(ids(state), list(range(1, 31)))
self.assertEqual(state.oldest, 1)
def test_live_appends_land_in_order(self):
state = State()
for i in range(30, 0, -1):
ingest(state, {"id": i})
ingest(state, {"id": 31})
ingest(state, {"id": 33})
ingest(state, {"id": 32}) # out of order arrival
self.assertEqual(ids(state)[-3:], [31, 32, 33])
def test_duplicate_ids_are_dropped(self):
state = State()
ingest(state, {"id": 5})
ingest(state, {"id": 5}) # EventSource reconnect replay
self.assertEqual(ids(state), [5])
class ScrollStickTests(unittest.TestCase):
def test_first_render_with_rows_seeds_at_the_bottom(self):
state = State()
feed = Feed(scroll_height=0, client_height=600)
for evt in server_page(30, 1, True)["events"]:
ingest(state, evt)
render(state, feed, height_after=3000)
self.assertTrue(state.seeded)
self.assertEqual(feed.scroll_top, 3000)
def test_append_sticks_when_reading_the_tail(self):
state = State()
feed = Feed(scroll_height=3000, client_height=600)
state.seeded = True
feed.scroll_top = 2400 # exactly at the bottom
self.assertTrue(at_bottom(feed))
ingest(state, {"id": 31})
render(state, feed, mode="append", height_after=3100)
self.assertEqual(feed.scroll_top, 3100)
def test_append_within_threshold_still_sticks(self):
feed = Feed(scroll_height=3000, client_height=600, scroll_top=2360)
self.assertTrue(at_bottom(feed)) # 40px shy: close enough
def test_just_past_threshold_is_not_the_tail(self):
feed = Feed(scroll_height=3000, client_height=600, scroll_top=2351)
self.assertFalse(at_bottom(feed)) # 49px shy: reading history
def test_scrolled_up_reader_is_never_yanked(self):
state = State()
feed = Feed(scroll_height=3000, client_height=600, scroll_top=500)
state.seeded = True
self.assertFalse(at_bottom(feed))
ingest(state, {"id": 31})
render(state, feed, mode="append", height_after=3100)
self.assertEqual(feed.scroll_top, 500)
def test_short_feed_counts_as_at_bottom(self):
"""A feed shorter than its viewport cannot be scrolled away
from the newest row."""
feed = Feed(scroll_height=100, client_height=600, scroll_top=0)
self.assertTrue(at_bottom(feed))
def test_heartbeat_does_not_touch_anything(self):
state = State()
feed = Feed(scroll_height=3000, client_height=600, scroll_top=2400)
state.seeded = True
before = (list(ids(state)), feed.scroll_top)
on_stream_message(state, feed, "ping", height_after=3100)
self.assertEqual((list(ids(state)), feed.scroll_top), before)
class LoadMoreTests(unittest.TestCase):
def test_older_page_is_reversed_and_prepended(self):
"""before==1 returns [60..31] newest-first on the
wire; the display must gain [31..60] above [1..30]."""
state = State()
feed = Feed(scroll_height=3000, client_height=600, scroll_top=500)
for evt in server_page(30, 1, True)["events"]:
ingest(state, evt)
state.seeded = True
render(state, feed, height_after=3000)
feed.scroll_top = 500 # the reader scrolled up into history
load_more(state, feed, server_page(60, 31, True), height_after=6000)
self.assertEqual(ids(state), list(range(1, 61)))
self.assertEqual(state.oldest, 1)
self.assertFalse(state.exhausted)
def test_prepend_keeps_the_viewport_anchored(self):
"""Content added above must not move the rows under the
reader's cursor: scrollTop grows by the added height."""
state = State()
feed = Feed(scroll_height=3000, client_height=600, scroll_top=500)
state.seeded = True
self.assertFalse(at_bottom(feed))
delta = 3000
load_more(state, feed, server_page(60, 31, True),
height_after=3000 + delta)
self.assertEqual(feed.scroll_top, 500 + delta)
def test_prepend_while_at_bottom_stays_at_bottom(self):
state = State()
feed = Feed(scroll_height=3000, client_height=600, scroll_top=2400)
state.seeded = True
self.assertTrue(at_bottom(feed))
load_more(state, feed, server_page(60, 31, True), height_after=6000)
self.assertEqual(feed.scroll_top, 6000)
def test_exhausted_when_more_is_false(self):
state = State()
feed = Feed(scroll_height=3000, client_height=600, scroll_top=2400)
state.seeded = True
load_more(state, feed, server_page(60, 31, False), height_after=6000)
self.assertTrue(state.exhausted)
def test_empty_page_exhausts_too(self):
"""A defensive guard: a page with no rows means no older
history, whatever the flag says."""
state = State()
feed = Feed(scroll_height=3000, client_height=600, scroll_top=2400)
state.seeded = True
ingest(state, {"id": 1})
load_more(state, feed, {"events": [], "more": True}, height_after=3000)
self.assertTrue(state.exhausted)
class EndToEndSequenceTests(unittest.TestCase):
"""The whole first-minute story: replay, live tail, history."""
def test_replay_then_append_then_history(self):
state = State()
feed = Feed(scroll_height=0, client_height=600)
# 1. SSE replay: most-recent-30 oldest-first on the wire.
for evt in server_page(30, 1, True)["events"]:
ingest(state, evt)
render(state, feed, height_after=3000)
self.assertEqual(ids(state), list(range(1, 31)))
self.assertEqual(feed.scroll_top, 3000) # seeded at the tail
# 2. Two live rows arrive; the reader is at the bottom.
on_stream_message(state, feed, "31", height_after=3100)
on_stream_message(state, feed, "32", height_after=3200)
self.assertEqual(ids(state)[-2:], [31, 32])
self.assertEqual(feed.scroll_top, 3200)
# 3. A heartbeat is ignored, then the reader scrolls up.
on_stream_message(state, feed, "ping", height_after=3200)
feed.scroll_top = 100
on_stream_message(state, feed, "33", height_after=3300)
self.assertEqual(feed.scroll_top, 100) # never yanked
# 4. Load older: before=1 -> [60..31] newest-first wire page.
self.assertEqual(state.oldest, 1)
load_more(state, feed, server_page(60, 31, False), height_after=6300)
self.assertEqual(ids(state), list(range(1, 61)))
self.assertTrue(state.exhausted)
self.assertEqual(feed.scroll_top, 100 + 3000) # anchored
# ---------------------------------------------------------------------------
# Payload contract: the daemon JSON-encodes args/result into STRINGS
# ---------------------------------------------------------------------------
def parse_maybe_json(value):
"""PORT of parseMaybeJson: strings decode, objects pass through,
a non-JSON string answers None so the caller can fall back to
rendering the raw text."""
if not isinstance(value, str):
return value
try:
return json.loads(value)
except ValueError:
return None
def is_plain_object(value):
"""PORT of isPlainObject."""
return isinstance(value, dict)
def fmt_bytes(n):
"""PORT of fmtBytes."""
if n < 1024:
return "%d B" % n
if n < 1024 * 1024:
return "%.1f KiB" % (n / 1024)
return "%.1f MiB" % (n / (1024 * 1024))
def str_text(value):
"""PORT of strText."""
return value if isinstance(value, str) else ""
def filter_of(kind):
"""PORT of filterOf: which filter bucket owns a kind. The yeehaw
celebration lands in the comments bucket (goal 9 task 4b)."""
if kind == "tool_call":
return "commands"
if kind in ("tool_result", "command_output"):
return "results"
if kind in ("comment", "answer", "verdict", "yeehaw"):
return "comments"
if kind == "usage":
return "usage"
return "transitions"
def yeehaw_render(evt):
"""PORT of eventNode's yeehaw branch -> (span_class, message)."""
payload = evt.get("payload") or {}
return "yeehaw-message", str_text(payload.get("message"))
def fmt_duration(ms):
"""PORT of fmtDuration."""
if ms < 1000:
return "%d ms" % ms
return "%.1f s" % (ms / 1000)
def str_bytes(value):
"""PORT of strBytes."""
return len(value) if isinstance(value, str) else 0
def result_envelope(evt):
"""PORT of resultEnvelope: the parsed result string when it
decodes to an object, else the object-shaped payload itself."""
payload = evt.get("payload") or {}
parsed = parse_maybe_json(payload.get("result"))
if is_plain_object(parsed):
return parsed
if is_plain_object(payload):
return payload
return {}
RESULT_PLUMBING = ("ok", "exit_code", "stdout", "stderr", "bytes_out",
"bytes_err", "truncated", "duration_ms", "turn", "tool")
def result_extras(envelope):
"""PORT of resultExtras: the envelope minus command plumbing
and minus the note members (rendered separately)."""
return dict((key, value) for key, value in envelope.items()
if key not in RESULT_PLUMBING
and key not in ("error", "note", "timeout"))
def result_summary(evt):
"""PORT of resultSummary -> the summary line's text."""
envelope = result_envelope(evt)
payload = evt.get("payload") or {}
bits = []
if envelope.get("exit_code") is not None:
bits.append("exit %s" % envelope["exit_code"])
elif envelope.get("ok") is False:
bits.append("failed")
if isinstance(envelope.get("bytes_out"), int) \
and isinstance(envelope.get("bytes_err"), int):
bytes_count = envelope["bytes_out"] + envelope["bytes_err"]
else:
bytes_count = str_bytes(envelope.get("stdout")) \
+ str_bytes(envelope.get("stderr"))
if bytes_count > 0:
bits.append(fmt_bytes(bytes_count))
if envelope.get("truncated"):
bits.append("truncated")
if isinstance(envelope.get("duration_ms"), int):
bits.append(fmt_duration(envelope["duration_ms"]))
if payload.get("turn") is not None:
bits.append("turn %s" % payload["turn"])
# PORT: a non-JSON result string carries no envelope; its own
# size is the only metric we have.
if not bits and isinstance(payload.get("result"), str) \
and not is_plain_object(parse_maybe_json(payload["result"])):
bits.append(fmt_bytes(len(payload["result"])))
return "result" + (" (" + ", ".join(bits) + ")" if bits else "")
def result_output(evt):
"""PORT of resultBody's text decisions -> (stdout_text,
stderr_text, note_text, extras_text, no_output_flag)."""
envelope = result_envelope(evt)
payload = evt.get("payload") or {}
parsed = parse_maybe_json(payload.get("result"))
out = err = ""
if is_plain_object(parsed):
out = str_text(envelope.get("stdout"))
err = str_text(envelope.get("stderr"))
elif isinstance(parsed, str):
out = parsed # a JSON string literal
elif isinstance(payload.get("result"), str):
out = payload["result"]
else:
out = str_text(envelope.get("stdout"))
err = str_text(envelope.get("stderr"))
note = ""
extras = ""
if not out and not err:
note = str_text(envelope.get("error")) or str_text(envelope.get("note")) \
or ("timed out" if envelope.get("timeout") else "")
if not note:
remainder = result_extras(envelope)
if remainder:
compact = json.dumps(remainder)
extras = compact if len(compact) <= 120 \
else json.dumps(remainder, indent=2)
return out, err, note, extras, (not out and not err and not note and not extras)
def args_without(args, skip):
"""PORT of argsWithout: every member except `skip`, pretty-
printed; '' when nothing is left."""
rest = dict((key, value) for key, value in args.items() if key != skip)
return json.dumps(rest, indent=2) if rest else ""
def tool_call_render(evt):
"""PORT of toolCallBody -> the rendered blocks as (kind, text)
pairs: ('head', line) for a command-styled head, ('pre', text)
for plain pre lines, ('para', text) for prose, ('fold', label)
for collapsed payloads, ('diff', '- old') / ('diff', '+ new')
for the replace_in_file diff. Bespoke bodies come from
tailored_blocks; None falls back to the generic view."""
payload = evt.get("payload") or {}
tool = str_text(payload.get("tool")) or "tool"
parsed = parse_maybe_json(payload.get("args"))
args = parsed if is_plain_object(parsed) else None
if args is not None:
blocks = tailored_blocks(tool, args)
if blocks is not None:
return blocks
blocks = [("head", tool)]
if args is not None:
rest = args_without(args, "command")
if rest:
blocks.append(("pre", rest))
elif str_text(payload.get("args")):
blocks.append(("pre", payload["args"]))
elif payload.get("args") is not None and not isinstance(payload.get("args"), str):
blocks.append(("pre", json.dumps(payload["args"], indent=2)))
return blocks
def fmt_int(n):
"""PORT of fmtInt: thousands separators without locale."""
digits = str(abs(int(round(n))))
out = ""
for i, char in enumerate(digits):
if i > 0 and (len(digits) - i) % 3 == 0:
out += ","
out += char
return ("-" if n < 0 else "") + out
def usage_line(payload):
"""PORT of eventNode's usage branch -> the one-line text. The
daemon may report either token count alone."""
bits = []
if str_text(payload.get("model")):
bits.append(payload["model"])
in_tok = "%s in" % fmt_int(payload["prompt_tokens"]) \
if isinstance(payload.get("prompt_tokens"), int) else ""
out_tok = "%s out" % fmt_int(payload["completion_tokens"]) \
if isinstance(payload.get("completion_tokens"), int) else ""
if in_tok or out_tok:
bits.append(in_tok + (" / " if in_tok and out_tok else "") + out_tok + " tok")
if isinstance(payload.get("cached_tokens"), int):
bits.append("%s cached" % fmt_int(payload["cached_tokens"]))
if isinstance(payload.get("elapsed_ms"), int):
bits.append(fmt_duration(payload["elapsed_ms"]))
return " \u00b7 ".join(bits) if bits else "unreported"
def state_change_line(payload):
"""PORT of eventNode's state_change branch."""
from_status = str_text(payload.get("from"))
to_status = str_text(payload.get("to"))
if from_status and to_status:
return from_status + " \u2192 " + to_status
return str_text(payload.get("text")) or json.dumps(payload)
DIFF_CONTEXT = 2
DIFF_MAX_LINES = 400
def _push_side(rows, lines, begin, end, marker):
"""PORT of pushSide."""
count = end - begin
half = DIFF_MAX_LINES // 2
if count <= DIFF_MAX_LINES:
for i in range(begin, end):
rows.append([marker, lines[i]])
return
for j in range(begin, begin + half):
rows.append([marker, lines[j]])
rows.append([marker, "... %d more lines ..." % (count - half * 2)])
for k in range(end - half, end):
rows.append([marker, lines[k]])
def diff_rows(old_text, new_text):
"""PORT of diffRows: common head/tail become clamped context,
the differing middle renders as -old/+new."""
old_lines = old_text.split("\n")
new_lines = new_text.split("\n")
start = 0
while start < len(old_lines) and start < len(new_lines) \
and old_lines[start] == new_lines[start]:
start += 1
end_old, end_new = len(old_lines), len(new_lines)
while end_old > start and end_new > start \
and old_lines[end_old - 1] == new_lines[end_new - 1]:
end_old -= 1
end_new -= 1
rows = []
has_middle = end_old > start or end_new > start
if has_middle:
for i in range(max(0, start - DIFF_CONTEXT), start):
rows.append([" ", old_lines[i]])
_push_side(rows, old_lines, start, end_old, "-")
_push_side(rows, new_lines, start, end_new, "+")
for i in range(end_old, min(len(old_lines), end_old + DIFF_CONTEXT)):
rows.append([" ", old_lines[i]])
return rows
def tailored_blocks(tool, args):
"""PORT of tailoredCallBody -> the bespoke blocks, or None to
fall back to the generic JSON view (fields missing - e.g. a
truncated args string that clamped mid-JSON)."""
path = str_text(args.get("path"))
command = str_text(args.get("command"))
question = str_text(args.get("question"))
bits = []
def head(text, more=None):
block = ("head", text)
if more:
block = ("head", text + " \u00b7 " + " \u00b7 ".join(more))
return block
if tool == "run_command":
if not command:
return None
if isinstance(args.get("timeout_ms"), int):
bits.append("timeout %ds" % round(args["timeout_ms"] / 1000))
return [head("$ " + command, bits)]
if tool == "read_file":
if not path:
return None
if isinstance(args.get("offset"), int) and args["offset"] > 1:
bits.append("from line %d" % args["offset"])
if isinstance(args.get("limit"), int):
bits.append("%d lines" % args["limit"])
return [head("read_file " + path, bits)]
if tool in ("write_file", "overwrite_file"):
content = str_text(args.get("content"))
if not path or not content:
return None
return [head(tool + " " + path, [fmt_bytes(len(content))]),
("fold", "content \u00b7 " + fmt_bytes(len(content)))]
if tool == "replace_in_file":
old = str_text(args.get("old"))
if not path or not old:
return None
if isinstance(args.get("expected_count"), int):
bits.append("expect %d" % args["expected_count"])
blocks = [head("replace_in_file " + path, bits)]
rows = diff_rows(old, str_text(args.get("new")))
if rows:
blocks.extend(("diff", marker + " " + text) for marker, text in rows)
return blocks
if tool in ("enqueue_task", "delete_task", "get_task"):
if not isinstance(args.get("task_id"), int):
return None
return [head(tool + " #" + str(args["task_id"]))]
if tool in ("update_progress", "add_comment", "save_note"):
text = str_text(args.get("text")) or str_text(args.get("body"))
if not text:
return None
if tool == "save_note" and str_text(args.get("project")):
bits.append(str_text(args.get("project")))
return [head(tool, bits), ("para", text)]
if tool == "ask_question":
if not question:
return None
blocks = [head("ask_question"), ("para", "Q: " + question)]
if isinstance(args.get("options"), list) and args["options"]:
blocks.append(("options", [str(o) for o in args["options"]]))
return blocks
return None
def command_output_render(evt):
"""PORT of eventNode's command_output branch ->
(command_prefix, output_text)."""
payload = evt.get("payload") or {}
command = str_text(payload.get("command"))
text = payload.get("text") or payload.get("chunk") or ""
return ("$ " + command if command else ""), text
# --- Fixtures: copied from the live ledger (web-db.sqlite, events
# table) and the test fake's object-shaped pushes - the real wire
# shapes, inner JSON spelled out as the daemon serialises it. ---
# The daemon's inner JSON, built with json.dumps so the escaping
# is exactly what the wire carries (a JSON string holding JSON).
inner_call = json.dumps({"command": "cd /workspace && ls"})
inner_progress = json.dumps(
{"text": "Root-caused the SSE listener; next: the payload parse"})
inner_enqueue = json.dumps({"task_id": 3})
inner_result = json.dumps(
{"ok": True, "exit_code": 0,
"stdout": "find /workspace/task-1 -maxdepth 2",
"stderr": "", "duration_ms": 11,
"bytes_out": 6042, "bytes_err": 0, "truncated": True})
inner_error = json.dumps(
{"ok": False,
"error": "suspend refused: 3 draft task(s) were never enqueued"})
inner_empty = json.dumps({"ok": True, "exit_code": 0,
"stdout": "", "stderr": ""})
FIXTURE_RUN_COMMAND_CALL = json.loads(
'{"turn": 52, "tool": "run_command", "args": ' + json.dumps(inner_call) + '}')
FIXTURE_UPDATE_PROGRESS_CALL = json.loads(
'{"turn": 6, "tool": "update_progress", "args": '
+ json.dumps(inner_progress) + '}')
FIXTURE_ENQUEUE_CALL = json.loads(
'{"turn": 5, "tool": "enqueue_task", "args": '
+ json.dumps(inner_enqueue) + '}')
FIXTURE_RUN_COMMAND_RESULT = json.loads(
'{"tool": "run_command", "result": ' + json.dumps(inner_result)
+ ', "turn": 52}')
FIXTURE_ERROR_RESULT = json.loads(
'{"tool": "suspend", "result": ' + json.dumps(inner_error) + '}')
FIXTURE_EMPTY_RESULT = json.loads(
'{"tool": "run_command", "result": ' + json.dumps(inner_empty) + '}')
# Not valid JSON: the live daemon emitted result strings that are
# truncated raw output (72 rows in the production ledger).
FIXTURE_NOT_JSON_RESULT = {
"tool": "run_command",
"result": '{"ok":true,"exit_code":0,"stdout":"=== Spry ===\n'
'MANIFEST.usm README.md meson.build',
}
# command_output: the harness fake's shape; `command` is a member.
FIXTURE_COMMAND_OUTPUT = {"command": "meson test -C builddir",
"text": "nobody:/task-1$ done\r\n"}
# The harness fake's legacy object-shaped payloads (plan 17's own
# tests push these): args/result as real objects.
FIXTURE_OBJECT_CALL = {"turn": 1, "tool": "run_command",
"args": {"command": "echo hello"}}
FIXTURE_OBJECT_RESULT = {"turn": 1, "tool": "run_command",
"stdout": "hello\n", "exit_code": 0}
# Tailored-rendering fixtures (plan 18): the file tools' arg shapes
# straight off the daemon's tool schemas.
FIXTURE_REPLACE_CALL = {"turn": 40, "tool": "replace_in_file", "args": {
"path": "src/pages/app.css",
"old": ".event-turn {\n border-left: 3px solid #ddf4ff;\n}",
"new": ".event-turn {\n border-left: 3px solid #ddf4ff;\n color: var(--ink-muted);\n}",
"expected_count": 1}}
FIXTURE_WRITE_CALL = {"turn": 41, "tool": "write_file", "args": {
"path": "notes.md", "content": "# Notes\n- first\n- second"}}
# Args clamped mid-JSON by the daemon's display clamp: parsing
# fails, so the bespoke renderer must step aside and the generic
# view shows the raw text.
FIXTURE_TRUNCATED_ARGS = {"turn": 42, "tool": "write_file", "args":
'{"path":"big.bin","content":"AAA'}
class PayloadParserTests(unittest.TestCase):
def test_string_args_decode_to_an_object(self):
parsed = parse_maybe_json(FIXTURE_RUN_COMMAND_CALL["args"])
self.assertEqual(parsed, {"command": "cd /workspace && ls"})
def test_non_json_string_answers_none(self):
self.assertIsNone(parse_maybe_json(
FIXTURE_NOT_JSON_RESULT["result"]))
def test_objects_pass_through(self):
self.assertEqual(parse_maybe_json({"command": "ls"}), {"command": "ls"})
self.assertEqual(parse_maybe_json(None), None)
class ToolCallRenderTests(unittest.TestCase):
"""The command the agent ran must surface in EVERY render path,
and each known tool renders through its tailored body."""
def evt(self, payload):
return {"kind": "tool_call", "payload": payload}
def test_run_command_call_heads_with_the_dollar(self):
blocks = tool_call_render(self.evt(FIXTURE_RUN_COMMAND_CALL))
self.assertEqual(blocks[0], ("head", "$ cd /workspace && ls"))
def test_run_command_timeout_rides_the_head(self):
blocks = tool_call_render(self.evt({"tool": "run_command", "args":
{"command": "make", "timeout_ms": 900000}}))
self.assertEqual(blocks[0],
("head", "$ make \u00b7 timeout 900s"))
def test_update_progress_call_renders_prose_not_json(self):
"""The old renderer dumped {"text": ...} as JSON; the
tailored body renders the text itself."""
blocks = tool_call_render(self.evt(FIXTURE_UPDATE_PROGRESS_CALL))
self.assertEqual(blocks[0], ("head", "update_progress"))
self.assertEqual(blocks[1],
("para", "Root-caused the SSE listener; next: the payload parse"))
self.assertNotIn('"text"', json.dumps(blocks))
def test_enqueue_call_renders_the_id(self):
blocks = tool_call_render(self.evt(FIXTURE_ENQUEUE_CALL))
self.assertEqual(blocks, [("head", "enqueue_task #3")])
def test_replace_in_file_renders_a_diff(self):
blocks = tool_call_render(self.evt(FIXTURE_REPLACE_CALL))
self.assertEqual(blocks[0],
("head", "replace_in_file src/pages/app.css \u00b7 expect 1"))
diff_texts = [text for kind, text in blocks if kind == "diff"]
joined = " ".join(diff_texts)
self.assertIn(" .event-turn {", joined)
# The untouched border line is context; only the added color
# line is an addition - no phantom removals.
self.assertIn(" border-left: 3px solid #ddf4ff;", joined)
self.assertIn("+ color: var(--ink-muted);", joined)
self.assertIn(" }", joined)
self.assertFalse([t for t in diff_texts if t.startswith("- ")],
"an unchanged line must never render as a removal")
def test_write_file_folds_its_content(self):
blocks = tool_call_render(self.evt(FIXTURE_WRITE_CALL))
self.assertEqual(blocks[0], ("head", "write_file notes.md \u00b7 24 B"))
self.assertEqual(blocks[1], ("fold", "content \u00b7 24 B"))
def test_truncated_args_fall_back_to_the_raw_view(self):
blocks = tool_call_render(self.evt(FIXTURE_TRUNCATED_ARGS))
self.assertEqual(blocks[0], ("head", "write_file"))
self.assertEqual(blocks[1][0], "pre")
self.assertIn('"path":"big.bin"', blocks[1][1])
def test_unknown_tool_falls_back_to_json_args(self):
blocks = tool_call_render(self.evt(
{"tool": "brand_new_tool", "args": {"deep": {"a": 1}}}))
self.assertEqual(blocks[0], ("head", "brand_new_tool"))
self.assertIn('"deep"', blocks[1][1])
def test_object_shaped_call_still_works(self):
blocks = tool_call_render(self.evt(FIXTURE_OBJECT_CALL))
self.assertEqual(blocks, [("head", "$ echo hello")])
def test_non_json_args_render_raw(self):
blocks = tool_call_render(self.evt(
{"tool": "run_command", "args": "not json at all"}))
self.assertEqual(blocks,
[("head", "run_command"), ("pre", "not json at all")])
def test_no_args_at_all_renders_the_tool_name(self):
blocks = tool_call_render(self.evt({"tool": "list_tasks"}))
self.assertEqual(blocks, [("head", "list_tasks")])
def test_bespoke_missing_fields_step_aside(self):
"""A replace_in_file without its old string (clamped args
that still parse) falls back rather than lying."""
blocks = tool_call_render(self.evt(
{"tool": "replace_in_file", "args": {"path": "x.c"}}))
self.assertEqual(blocks[0], ("head", "replace_in_file"))
self.assertEqual(blocks[1][0], "pre")
class DiffRowTests(unittest.TestCase):
"""The replace_in_file diff: context clamping and honest
replacement semantics."""
def test_single_line_swap(self):
rows = diff_rows("alpha\nbeta\ngamma", "alpha\nBETA\ngamma")
self.assertEqual(rows, [[" ", "alpha"], ["-", "beta"],
["+", "BETA"], [" ", "gamma"]])
def test_context_is_clamped_to_two_lines_per_side(self):
old = "\n".join(["ctx"] * 10 + ["old-line"] + ["ctx"] * 10)
new = "\n".join(["ctx"] * 10 + ["new-line"] + ["ctx"] * 10)
rows = diff_rows(old, new)
context = [text for marker, text in rows if marker == " "]
self.assertEqual(context, ["ctx"] * 4)
def test_whole_file_rewrite_shows_no_context(self):
rows = diff_rows("a\nb\nc", "x\ny\nz")
self.assertEqual([m for m, _ in rows], ["-", "-", "-", "+", "+", "+"])
def test_deletion_only_keeps_its_context(self):
rows = diff_rows("keep\ndrop\nkeep", "keep\nkeep")
self.assertEqual(rows, [[" ", "keep"], ["-", "drop"], [" ", "keep"]])
def test_empty_new_text(self):
rows = diff_rows("line", "")
self.assertEqual(rows, [["-", "line"], ["+", ""]])
def test_oversized_side_keeps_head_and_tail(self):
old = "\n".join("line-%04d" % i for i in range(1000))
rows = diff_rows(old, "changed")
dels = [text for marker, text in rows if marker == "-"]
self.assertEqual(len(dels), 401)
self.assertIn("more lines", dels[200])
self.assertEqual(dels[0], "line-0000")
self.assertEqual(dels[-1], "line-0999")
def test_identical_text_renders_nothing(self):
self.assertEqual(diff_rows("same\nsame", "same\nsame"), [])
class UsageLineTests(unittest.TestCase):
def test_full_payload_is_one_line(self):
line = usage_line({"model": "glm-4.7", "prompt_tokens": 45200000,
"completion_tokens": 1100000, "cached_tokens": 4500,
"elapsed_ms": 3200})
self.assertEqual(line,
"glm-4.7 \u00b7 45,200,000 in / 1,100,000 out tok "
"\u00b7 4,500 cached \u00b7 3.2 s")
def test_unreported_when_no_numbers(self):
self.assertEqual(usage_line({}), "unreported")
def test_partial_payload_skips_missing_members(self):
line = usage_line({"completion_tokens": 5, "elapsed_ms": 40})
self.assertEqual(line, "5 out tok \u00b7 40 ms")
class StateChangeLineTests(unittest.TestCase):
def test_from_to_arrow(self):
self.assertEqual(
state_change_line({"from": "working", "to": "blocked",
"text": "Status \u2192 blocked"}),
"working \u2192 blocked")
def test_text_fallback(self):
self.assertEqual(
state_change_line({"text": "Goal created (branch x)"}),
"Goal created (branch x)")
def test_json_fallback(self):
self.assertEqual(state_change_line({}), "{}")
class ToolResultRenderTests(unittest.TestCase):
def evt(self, payload):
return {"kind": "tool_result", "payload": payload}
def test_summary_comes_from_the_envelope(self):
line = result_summary(self.evt(FIXTURE_RUN_COMMAND_RESULT))
self.assertEqual(line,
"result (exit 0, 5.9 KiB, truncated, 11 ms, turn 52)")
def test_summary_marks_failed_envelopes(self):
line = result_summary(self.evt(
{"tool": "run_command", "result": '{"ok":false,"error":"x"}'}))
self.assertEqual(line, "result (failed)")
def test_body_shows_the_envelopes_stdout(self):
out, err, note, extras, no_output = result_output(
self.evt(FIXTURE_RUN_COMMAND_RESULT))
self.assertEqual(out, "find /workspace/task-1 -maxdepth 2")
self.assertEqual(err, "")
self.assertFalse(no_output)
def test_non_json_result_renders_as_output_text(self):
out, err, note, extras, no_output = result_output(
self.evt(FIXTURE_NOT_JSON_RESULT))
self.assertIn("=== Spry ===", out)
self.assertFalse(no_output,
"raw output must never be called (no output)")
def test_error_envelope_is_not_no_output(self):
out, err, note, extras, no_output = result_output(
self.evt(FIXTURE_ERROR_RESULT))
self.assertEqual((out, err), ("", ""))
self.assertIn("suspend refused", note)
self.assertFalse(no_output,
"an error member means the result said something")
def test_genuinely_empty_result_says_no_output(self):
out, err, note, extras, no_output = result_output(self.evt(FIXTURE_EMPTY_RESULT))
self.assertEqual((out, err, note, extras), ("", "", "", ""))
self.assertTrue(no_output)
def test_object_shaped_result_still_works(self):
line = result_summary(self.evt(FIXTURE_OBJECT_RESULT))
self.assertEqual(line, "result (exit 0, 6 B, turn 1)")
out, err, note, extras, no_output = result_output(self.evt(FIXTURE_OBJECT_RESULT))
self.assertEqual(out, "hello\n")
def test_tool_answer_envelope_is_rendered_not_swallowed(self):
"""The live ledger's update_progress/create_task/finish
results carry {"recorded":true} / {"ok":true,"task_id":4}
/ {"accepted":true} with empty streams: that IS the tool's
answer and must render, not "(no output)"."""
for inner in ('{"recorded":true}',
'{"ok":true,"task_id":4,"status":"draft"}',
'{"accepted":true}',
'{"suspended":true}',
'{"ok":true,"status":"pending"}'):
out, err, note, extras, no_output = result_output(self.evt(
{"tool": "update_progress", "result": inner}))
self.assertFalse(no_output, inner)
self.assertEqual((out, err, note), ("", "", ""))
self.assertTrue(extras, inner)
def test_list_tasks_answer_renders_as_json(self):
inner = json.dumps({"ok": True, "tasks": [
{"id": 6, "title": "UX notes", "status": "queued"},
{"id": 5, "title": "Event log parse", "status": "working"}]})
out, err, note, extras, no_output = result_output(self.evt(
{"tool": "list_tasks", "result": inner}))
self.assertFalse(no_output)
self.assertIn('"tasks"', extras)
self.assertIn("UX notes", extras)
def test_run_command_with_empty_streams_is_still_no_output(self):
"""Only command plumbing present: the run genuinely said
nothing - keep the honest "(no output)"."""
out, err, note, extras, no_output = result_output(self.evt(
{"tool": "run_command",
"result": '{"ok":true,"exit_code":0,"stdout":"",'
'"stderr":"","duration_ms":5,"bytes_out":0,'
'"bytes_err":0,"truncated":false}'}))
self.assertTrue(no_output)
self.assertEqual(extras, "")
class CommandOutputRenderTests(unittest.TestCase):
def test_command_is_prefixed_as_a_shell_line(self):
command, text = command_output_render(
{"kind": "command_output", "payload": FIXTURE_COMMAND_OUTPUT})
self.assertEqual(command, "$ meson test -C builddir")
self.assertEqual(text, "nobody:/task-1$ done\r\n")
def test_text_only_chunk_keeps_the_old_render(self):
command, text = command_output_render(
{"kind": "command_output", "payload": {"text": "hello\r\n"}})
self.assertEqual(command, "")
self.assertEqual(text, "hello\r\n")
class SearchHaystackTests(unittest.TestCase):
"""A search for text inside the STRING-encoded args/result must
still find the event: the haystack appends the raw strings."""
def test_search_matches_through_the_string_encoding(self):
payload = FIXTURE_RUN_COMMAND_CALL
haystack = "tool_call daemon " + json.dumps(payload) + " " \
+ str_text(payload.get("args")) + " " \
+ str_text(payload.get("result"))
self.assertIn("cd /workspace && ls", haystack)
class YeehawFilterTests(unittest.TestCase):
"""The celebration must ride the comments filter (goal 9 task 4b):
a human scanning the conversation sees the yeehaw, and the
comments toggle hides it like any other chatter."""
def test_yeehaw_maps_to_comments(self):
self.assertEqual(filter_of("yeehaw"), "comments")
def test_comment_kinds_unchanged(self):
for kind in ("comment", "answer", "verdict"):
self.assertEqual(filter_of(kind), "comments")
def test_other_kinds_unchanged(self):
self.assertEqual(filter_of("tool_call"), "commands")
self.assertEqual(filter_of("tool_result"), "results")
self.assertEqual(filter_of("command_output"), "results")
self.assertEqual(filter_of("usage"), "usage")
self.assertEqual(filter_of("lifecycle"), "transitions")
class YeehawRenderTests(unittest.TestCase):
"""The yeehaw branch: the message in the bold .yeehaw-message span
(the festive palette), never a JSON payload dump."""
def test_message_renders_in_the_span(self):
span, message = yeehaw_render(
{"kind": "yeehaw", "payload": {"message": "Loved every line"}})
self.assertEqual(span, "yeehaw-message")
self.assertEqual(message, "Loved every line")
def test_missing_message_is_blank_not_garbage(self):
span, message = yeehaw_render({"kind": "yeehaw", "payload": {}})
self.assertEqual(message, "")
def test_non_string_message_is_blank(self):
span, message = yeehaw_render(
{"kind": "yeehaw", "payload": {"message": 42}})
self.assertEqual(message, "")
class RendererSourceTests(unittest.TestCase):
"""The shipped script itself (no JS engine in this container, so
the render decisions are pinned by the ports above plus these
shape checks on the served source)."""
def setUp(self):
self.body = script_body()
def test_parse_maybe_json_is_defined_and_used(self):
self.assertIn("function parseMaybeJson(value) {", self.body)
self.assertGreaterEqual(self.body.count("parseMaybeJson("), 4)
def test_no_innerhtml_anywhere(self):
self.assertNotIn(".innerHTML", self.body)
def test_command_output_prefixes_the_dollar(self):
self.assertIn("'$ ' + p.command", self.body)
def test_tool_call_line_uses_parsed_args(self):
self.assertIn("args.command", self.body)
self.assertIn("toolCallBody", self.body)
def test_result_reads_parsed_envelope(self):
self.assertIn("resultEnvelope", self.body)
self.assertIn("bytes_out", self.body)
self.assertIn("duration_ms", self.body)
def test_yeehaw_lands_in_the_comments_bucket(self):
self.assertRegex(
self.body,
r"kind === 'comment' \|\| kind === 'answer' \|\| kind === 'verdict'[\s\S]*?"
r"kind === 'yeehaw'\) return 'comments'")
def test_yeehaw_renders_the_message_span(self):
self.assertIn("evt.kind === 'yeehaw'", self.body)
self.assertIn("'yeehaw-message'", self.body)
self.assertIn("strText(p.message)", self.body)
def test_tailored_renderers_present(self):
self.assertIn("function tailoredCallBody(tool, args) {", self.body)
self.assertIn("function diffRows(oldText, newText) {", self.body)
self.assertIn("'event-diff'", self.body)
self.assertIn("tailoredCallBody(tool, args)", self.body)
if __name__ == "__main__":
unittest.main(verbosity=2)