mirror of
https://github.com/turnstonelabs/turnstone.git
synced 2026-08-12 23:12:23 -06:00
Patrick Buckley
723cad24bb
* feat: structured memory system — typed/scoped memories with BM25 relevance and metacognitive prompting Replace flat key-value memories table with structured_memories (migration 014). Four memory types (user/project/feedback/reference), three scopes (global/workstream/user). Consolidate remember/recall/forget into two tools: memory (action-based: save/search/delete/list) and recall (conversation history only). BM25 relevance scoring (extracted to turnstone/core/bm25.py) selects top-5 memories for system message injection based on conversation context. Metacognitive prompting injects ephemeral nudges after corrections, tool denials, workstream resume, and completion signals. Scope isolation enforced: system message injection and nudge counts filtered to visible memories only (global + current workstream + authenticated user). User scope requires authentication. Content capped at 32KB. ILIKE/LIKE metacharacters escaped in both backends. 113 new tests (2053 total). * fix: CI failure + copilot review feedback - Fix time.monotonic() cooldown: use None sentinel instead of 0.0 default (monotonic clock starts at boot, not epoch — fresh CI runners have uptime < 300s so cooldown check always triggered) - Catch sa.exc.IntegrityError specifically in upsert instead of broad Exception (copilot review) - Preserve existing description/type on upsert when caller doesn't explicitly set them (copilot review) - Add last_accessed + access_count columns to schema/migration for future LRU/LFU eviction support
129 lines
4.2 KiB
Python
129 lines
4.2 KiB
Python
"""Tests for turnstone.core.tools — JSON auto-loading and schema validation."""
|
|
|
|
from turnstone.core.tools import (
|
|
_META,
|
|
AGENT_AUTO_TOOLS,
|
|
AGENT_TOOLS,
|
|
PRIMARY_KEY_MAP,
|
|
TASK_AGENT_TOOLS,
|
|
TASK_AUTO_TOOLS,
|
|
TOOLS,
|
|
)
|
|
|
|
|
|
class TestToolsSchema:
|
|
def test_all_tools_have_function_type(self):
|
|
for tool in TOOLS:
|
|
assert tool["type"] == "function", f"Tool missing type='function': {tool}"
|
|
|
|
def test_all_tools_have_name(self):
|
|
for tool in TOOLS:
|
|
assert "name" in tool["function"], f"Tool missing name: {tool}"
|
|
assert isinstance(tool["function"]["name"], str)
|
|
|
|
def test_all_tools_have_description(self):
|
|
for tool in TOOLS:
|
|
assert "description" in tool["function"], f"Tool missing description: {tool}"
|
|
assert len(tool["function"]["description"]) > 0
|
|
|
|
def test_all_tools_have_parameters(self):
|
|
for tool in TOOLS:
|
|
params = tool["function"]["parameters"]
|
|
assert params["type"] == "object"
|
|
assert "properties" in params
|
|
|
|
def test_required_fields_exist_in_properties(self):
|
|
for tool in TOOLS:
|
|
func = tool["function"]
|
|
params = func["parameters"]
|
|
required = params.get("required", [])
|
|
properties = params["properties"]
|
|
for field in required:
|
|
assert field in properties, (
|
|
f"Tool '{func['name']}': required field '{field}' not in properties"
|
|
)
|
|
|
|
def test_tool_names_unique(self):
|
|
names = [t["function"]["name"] for t in TOOLS]
|
|
assert len(names) == len(set(names)), f"Duplicate tool names: {names}"
|
|
|
|
def test_agent_tools_subset(self):
|
|
tool_names = {t["function"]["name"] for t in TOOLS}
|
|
agent_names = {t["function"]["name"] for t in AGENT_TOOLS}
|
|
assert agent_names.issubset(tool_names), (
|
|
f"AGENT_TOOLS has names not in TOOLS: {agent_names - tool_names}"
|
|
)
|
|
|
|
def test_task_agent_tools_subset(self):
|
|
tool_names = {t["function"]["name"] for t in TOOLS}
|
|
task_names = {t["function"]["name"] for t in TASK_AGENT_TOOLS}
|
|
assert task_names.issubset(tool_names), (
|
|
f"TASK_AGENT_TOOLS has names not in TOOLS: {task_names - tool_names}"
|
|
)
|
|
|
|
def test_agent_tools_not_empty(self):
|
|
assert len(AGENT_TOOLS) > 0
|
|
|
|
def test_task_agent_tools_not_empty(self):
|
|
assert len(TASK_AGENT_TOOLS) > 0
|
|
|
|
|
|
class TestToolsMetadata:
|
|
"""Validate the metadata extracted from JSON files."""
|
|
|
|
def test_tool_count(self):
|
|
assert len(TOOLS) == 17
|
|
|
|
def test_agent_tools_count(self):
|
|
assert len(AGENT_TOOLS) == 9
|
|
|
|
def test_task_agent_tools_count(self):
|
|
assert len(TASK_AGENT_TOOLS) == 12
|
|
|
|
def test_auto_approve_sets_match(self):
|
|
expected = {
|
|
"read_file",
|
|
"search",
|
|
"math",
|
|
"man",
|
|
"web_fetch",
|
|
"web_search",
|
|
"notify",
|
|
}
|
|
assert expected == AGENT_AUTO_TOOLS
|
|
assert expected == TASK_AUTO_TOOLS
|
|
|
|
def test_primary_key_map(self):
|
|
expected = {
|
|
"bash": "command",
|
|
"math": "code",
|
|
"read_file": "path",
|
|
"search": "query",
|
|
"write_file": "content",
|
|
"edit_file": "old_string",
|
|
"man": "page",
|
|
"web_fetch": "url",
|
|
"web_search": "query",
|
|
"task": "prompt",
|
|
"create_plan": "goal",
|
|
"memory": "name",
|
|
"recall": "query",
|
|
"notify": "message",
|
|
"watch": "command",
|
|
"read_resource": "uri",
|
|
"use_prompt": "name",
|
|
}
|
|
assert expected == PRIMARY_KEY_MAP
|
|
|
|
def test_no_metadata_in_function_dicts(self):
|
|
"""Ensure turnstone metadata keys are stripped from the OpenAI schema."""
|
|
meta_keys = {"agent", "task_agent", "auto_approve", "primary_key"}
|
|
for tool in TOOLS:
|
|
func = tool["function"]
|
|
leaked = meta_keys & set(func)
|
|
assert not leaked, f"Tool '{func['name']}' leaks metadata into function dict: {leaked}"
|
|
|
|
def test_meta_has_all_tools(self):
|
|
tool_names = {t["function"]["name"] for t in TOOLS}
|
|
assert set(_META.keys()) == tool_names
|