Files
turnstone/tests/test_reconstruct_messages.py
T
Patrick Buckley 1295919613 fix: simplify conversation storage — atomic assistant rows with tool_… (#51)
* fix: simplify conversation storage — atomic assistant rows with tool_calls JSON

Replace the denormalized storage model (separate rows for assistant
content, tool_call, tool_result) with atomic assistant rows carrying
tool_calls as a JSON column. Eliminates the 100-line heuristic
reconstruct_messages function and its cross-turn merge bug.

Schema: add tool_calls TEXT column to conversations (migration 013).
Migration backfills existing data — merges tool_call rows into their
parent assistant row as JSON, renames tool_result to tool, deletes
consumed tool_call rows.

Session save path: assistant content + tool_calls saved in one
save_message call before tool execution (crash resilient). Tool
results saved as role="tool".

Extract shared storage utilities to _utils.py: row_to_dict, mutable
field frozensets, reconstruct_messages. Both backends import from
_utils — PostgreSQL no longer depends on _sqlite.py.

Includes denied/blocked tool call badge fix on resume: _build_history
detects denied results and propagates flag to parent assistant entry.
Frontend uses flag for correct badge-denied rendering. Denied tools
visually muted. role="status" on badges for accessibility.

Net -45 lines. 8 new tests for reconstruction, all 1914 tests pass.

* fix: migration 013 uses parameterized deletes and ordered downgrade

- DELETE of consumed tool_call rows now uses parameterized batches
  (chunks of 500) instead of string interpolation
- Downgrade rebuilds via temp table to preserve chronological id
  ordering when re-inserting tool_call rows
2026-03-13 14:26:05 -07:00

230 lines
7.8 KiB
Python

"""Tests for the shared message reconstruction logic."""
import json
from turnstone.core.storage._utils import reconstruct_messages
def _row(
role,
content=None,
tool_name=None,
tool_args=None,
tc_id=None,
pdata=None,
tool_calls=None,
):
"""Build a 7-element conversation row tuple (post-migration 013 format)."""
return (role, content, tool_name, tool_args, tc_id, pdata, tool_calls)
class TestAssistantWithToolCalls:
"""Assistant messages with tool_calls JSON are self-contained."""
def test_assistant_with_tool_calls_and_content(self):
tc = json.dumps(
[
{
"id": "call_1",
"type": "function",
"function": {"name": "read_file", "arguments": '{"path":"/tmp/x"}'},
}
]
)
rows = [
_row("assistant", "Let me check that.", tool_calls=tc),
_row("tool", "file contents", tc_id="call_1"),
]
msgs = reconstruct_messages(rows, "ws1")
assert len(msgs) == 2
assert msgs[0]["role"] == "assistant"
assert msgs[0]["content"] == "Let me check that."
assert len(msgs[0]["tool_calls"]) == 1
assert msgs[0]["tool_calls"][0]["function"]["name"] == "read_file"
assert msgs[1]["role"] == "tool"
assert msgs[1]["tool_call_id"] == "call_1"
def test_assistant_with_multiple_tool_calls(self):
tc = json.dumps(
[
{
"id": "call_1",
"type": "function",
"function": {"name": "bash", "arguments": '{"command":"ls"}'},
},
{
"id": "call_2",
"type": "function",
"function": {"name": "bash", "arguments": '{"command":"pwd"}'},
},
]
)
rows = [
_row("assistant", tool_calls=tc),
_row("tool", "files", tc_id="call_1"),
_row("tool", "/home", tc_id="call_2"),
]
msgs = reconstruct_messages(rows, "ws1")
assert len(msgs) == 3
assert len(msgs[0]["tool_calls"]) == 2
assert msgs[1]["role"] == "tool"
assert msgs[2]["role"] == "tool"
def test_assistant_without_tool_calls(self):
rows = [_row("assistant", "Hello there.")]
msgs = reconstruct_messages(rows, "ws1")
assert len(msgs) == 1
assert msgs[0]["role"] == "assistant"
assert msgs[0]["content"] == "Hello there."
assert "tool_calls" not in msgs[0]
class TestMultipleTurns:
"""Multiple assistant turns with tool calls stay separate."""
def test_two_tool_call_turns(self):
tc1 = json.dumps(
[
{
"id": "call_1",
"type": "function",
"function": {"name": "bash", "arguments": '{"command":"ls"}'},
}
]
)
tc2 = json.dumps(
[
{
"id": "call_2",
"type": "function",
"function": {"name": "bash", "arguments": '{"command":"cat file1"}'},
}
]
)
rows = [
_row("assistant", "I'll run two commands.", tool_calls=tc1),
_row("tool", "file1\nfile2", tc_id="call_1"),
_row("assistant", "Now reading.", tool_calls=tc2),
_row("tool", "contents", tc_id="call_2"),
]
msgs = reconstruct_messages(rows, "ws1")
assert len(msgs) == 4
assert msgs[0]["content"] == "I'll run two commands."
assert len(msgs[0]["tool_calls"]) == 1
assert msgs[2]["content"] == "Now reading."
assert len(msgs[2]["tool_calls"]) == 1
def test_denied_tool_calls_with_commentary(self):
"""Two denied tool batches with assistant commentary in between."""
tc1 = json.dumps(
[
{
"id": "call_1",
"type": "function",
"function": {"name": "bash", "arguments": '{"command":"find /"}'},
}
]
)
tc2 = json.dumps(
[
{
"id": "call_2",
"type": "function",
"function": {"name": "bash", "arguments": '{"command":"curl ..."}'},
}
]
)
rows = [
_row("assistant", tool_calls=tc1),
_row("tool", "Denied by user", tc_id="call_1"),
_row("assistant", "Interesting! Let me try something else."),
_row("assistant", tool_calls=tc2),
_row("tool", "Denied by user", tc_id="call_2"),
]
msgs = reconstruct_messages(rows, "ws1")
assert len(msgs) == 5
assert msgs[0]["role"] == "assistant"
assert msgs[0]["tool_calls"][0]["function"]["name"] == "bash"
assert msgs[1]["role"] == "tool"
assert msgs[2]["role"] == "assistant"
assert msgs[2]["content"] == "Interesting! Let me try something else."
assert "tool_calls" not in msgs[2]
assert msgs[3]["role"] == "assistant"
assert msgs[3]["tool_calls"][0]["function"]["name"] == "bash"
assert msgs[4]["role"] == "tool"
class TestEdgeCases:
"""Edge cases in message reconstruction."""
def test_incomplete_turn_repair(self):
"""Trailing tool_calls without enough tool_results are stripped."""
tc = json.dumps(
[
{
"id": "call_1",
"type": "function",
"function": {"name": "bash", "arguments": '{"command":"ls"}'},
},
{
"id": "call_2",
"type": "function",
"function": {"name": "bash", "arguments": '{"command":"cat x"}'},
},
]
)
rows = [
_row("user", "hello"),
_row("assistant", "Let me check.", tool_calls=tc),
# Only 1 tool result for 2 tool_calls
_row("tool", "file1", tc_id="call_1"),
]
msgs = reconstruct_messages(rows, "ws1")
assert len(msgs) == 1
assert msgs[0]["role"] == "user"
def test_empty_rows(self):
msgs = reconstruct_messages([], "ws1")
assert msgs == []
def test_provider_data_preserved(self):
pdata = json.dumps([{"type": "text", "text": "hello"}])
rows = [_row("assistant", "hello", pdata=pdata)]
msgs = reconstruct_messages(rows, "ws1")
assert msgs[0]["_provider_content"] == [{"type": "text", "text": "hello"}]
def test_user_message(self):
rows = [_row("user", "hello world")]
msgs = reconstruct_messages(rows, "ws1")
assert len(msgs) == 1
assert msgs[0] == {"role": "user", "content": "hello world"}
def test_none_content_becomes_empty_string(self):
rows = [_row("user", None)]
msgs = reconstruct_messages(rows, "ws1")
assert msgs[0]["content"] == ""
def test_tool_without_tc_id_uses_empty_string(self):
rows = [
_row(
"assistant",
tool_calls=json.dumps(
[{"id": "c1", "type": "function", "function": {"name": "x", "arguments": ""}}]
),
),
_row("tool", "output", tc_id=None),
]
msgs = reconstruct_messages(rows, "ws1")
assert msgs[1]["tool_call_id"] == ""
def test_unknown_role_ignored(self):
rows = [
_row("user", "hi"),
_row("system", "you are helpful"),
_row("assistant", "hello"),
]
msgs = reconstruct_messages(rows, "ws1")
assert len(msgs) == 2
assert msgs[0]["role"] == "user"
assert msgs[1]["role"] == "assistant"