fix(session): preserve complete transcripts

This commit is contained in:
chengyongru
2026-08-19 18:40:20 +08:00
committed by chengyongru
parent 3c41d5e7f3
commit 9ef1e292ea
15 changed files with 160 additions and 770 deletions
-124
View File
@@ -1,5 +1,3 @@
import pytest
from nanobot.providers.base import ProviderConversationState
from nanobot.runtime_context import (
RUNTIME_CONTEXT_HISTORY_META,
@@ -832,9 +830,6 @@ def test_get_history_extend_to_user_keeps_newer_user_inside_window():
_assert_no_orphans(history)
# --- enforce_file_cap archive correctness (issue #4128) ---
def test_retain_recent_legal_suffix_returns_dropped_messages():
"""retain_recent_legal_suffix returns the actually-dropped messages."""
session = Session(
@@ -894,125 +889,6 @@ def test_retain_recent_legal_suffix_returns_all_on_zero():
assert session.messages == []
def test_enforce_file_cap_no_duplicate_archive_in_else_branch():
"""When the tail is assistant-only, enforce_file_cap must not archive
messages that are also retained (the bug from issue #4128)."""
from unittest.mock import MagicMock
session = Session(key="test:else-archive")
# Build: 15 user messages, then 10 assistant messages (no user in tail)
for i in range(15):
session.messages.append({"role": "user", "content": f"u{i}"})
for i in range(10):
session.messages.append({"role": "assistant", "content": f"a{i}"})
archive_fn = MagicMock()
session.enforce_file_cap(on_archive=archive_fn, limit=6)
assert len(session.messages) <= 6
# Verify archived messages have NO overlap with retained
if archive_fn.called:
archived = archive_fn.call_args.args[0]
archived_ids = set(id(m) for m in archived)
retained_ids = set(id(m) for m in session.messages)
assert not archived_ids & retained_ids, (
f"Duplicate messages in archive and retained: "
f"overlap contents = {[m['content'] for m in archived if id(m) in retained_ids]}"
)
def test_enforce_file_cap_no_message_loss_in_else_branch():
"""In the else branch, no messages should silently disappear — every
message must be either retained or archived."""
from unittest.mock import MagicMock
session = Session(key="test:else-no-loss")
all_messages = []
for i in range(15):
msg = {"role": "user", "content": f"u{i}"}
session.messages.append(msg)
all_messages.append(msg)
for i in range(10):
msg = {"role": "assistant", "content": f"a{i}"}
session.messages.append(msg)
all_messages.append(msg)
archive_fn = MagicMock()
session.enforce_file_cap(on_archive=archive_fn, limit=6)
# Collect all messages accounted for (retained + archived)
accounted = set(id(m) for m in session.messages)
if archive_fn.called:
for m in archive_fn.call_args.args[0]:
accounted.add(id(m))
all_ids = set(id(m) for m in all_messages)
missing = all_ids - accounted
assert not missing, (
f"Lost {len(missing)} message(s) — neither retained nor archived"
)
def test_enforce_file_cap_correct_archive_with_last_consolidated_in_else_branch():
"""When last_consolidated > 0 and the else branch fires, only the
unconsolidated dropped messages should be raw-archived. Messages in the
consolidated prefix that are dropped do NOT need raw archiving."""
from unittest.mock import MagicMock
session = Session(key="test:else-lc-archive")
# 20 messages total: u0..u9 (user), a0..a9 (assistant)
for i in range(10):
session.messages.append({"role": "user", "content": f"u{i}"})
for i in range(10):
session.messages.append({"role": "assistant", "content": f"a{i}"})
# First 8 messages already consolidated
session.last_consolidated = 8
archive_fn = MagicMock()
session.enforce_file_cap(on_archive=archive_fn, limit=4)
if archive_fn.called:
archived = archive_fn.call_args.args[0]
# Archived messages should NOT include any from the consolidated prefix
# (u0..u7). They should only be unconsolidated dropped messages.
archived_contents = [m["content"] for m in archived]
for c in archived_contents:
assert c not in [f"u{i}" for i in range(8)], (
f"Consolidated message {c!r} should not be raw-archived"
)
def test_enforce_file_cap_restores_session_when_archive_fails():
state = ProviderConversationState(
kind="openai_responses",
provider="openai:test",
model="test-model",
version=1,
payload={"items": []},
)
session = Session(key="test:archive-failure", provider_state=state)
for i in range(8):
session.messages.append({"role": "user", "content": f"msg{i}"})
original_messages = session.messages
original_updated_at = session.updated_at
session.last_consolidated = 2
def fail_archive(_messages):
raise RuntimeError("history unavailable")
with pytest.raises(RuntimeError, match="history unavailable"):
session.enforce_file_cap(on_archive=fail_archive, limit=4)
assert session.messages is original_messages
assert [message["content"] for message in session.messages] == [
f"msg{i}" for i in range(8)
]
assert session.last_consolidated == 2
assert session.provider_state is state
assert session.updated_at == original_updated_at
def test_retain_recent_legal_suffix_last_consolidated_correct_in_else_branch():
"""last_consolidated after retain_recent_legal_suffix should reflect how
many retained messages were inside the old consolidated prefix."""