hermes-agent/tests/run_agent/test_860_dedup.py
Teknium 6b81590c55
test: prune low-value tests suite-wide (wave 1) — 46,820 → 28,106 test functions
Systematic prune per AGENTS.md test policy, one pass over every major
test tree (gateway, hermes_cli, tools, agent, run_agent, plugins, cli,
cron, tui_gateway, honcho/openviking, root-level):

- DELETE: source-reading tests (read_text/getsource on prod files),
  change-detector tests (exact catalog counts, model-name snapshots,
  config version literals), mock-echo tests (assert a mock returns what
  it was told), assertion-free/trivial tests, near-duplicate
  parametrizations (boundaries + one representative kept), async/sync
  twin duplicates, cosmetic within-file variations.
- KEEP (mandatory): security/redaction/approval guards, message-role
  alternation invariants, prompt-caching/deterministic-call-id
  invariants, issue-number regression tests (deduped), E2E tests.
- 6 test files deleted outright (script-style/no-assert or fully
  redundant); conftest.py, fakes/, fixtures/ untouched.
- tests/acp/conftest.py added: autouse fixture stubs the live
  models.dev/GitHub/Copilot/Anthropic inventory fetches that ACP server
  tests performed on every session create — test_server.py 147s → 3.4s,
  and the tests are now genuinely hermetic.
- Sleep-based slowness shrunk where safe (codex_ttfb_watchdog,
  compression_concurrent_fork, etc.); no wall-clock assertion tightened.

Verification: full hermetic suite via scripts/run_tests.sh —
2439 files, 31,130 tests passed, 0 failed, 0 flaky retries, 315s wall
(baseline: 583s wall, 13,564s subprocess CPU).
2026-07-29 13:10:23 -07:00

171 lines
6.5 KiB
Python

"""Tests for issue #860 — SQLite session transcript deduplication.
Verifies that:
1. _flush_messages_to_session_db uses _last_flushed_db_idx to avoid re-writing
2. Multiple _persist_session calls don't duplicate messages
3. append_to_transcript(skip_db=True) skips SQLite but writes JSONL
4. The gateway doesn't double-write messages the agent already persisted
"""
import os
import tempfile
from pathlib import Path
from unittest.mock import patch
# ---------------------------------------------------------------------------
# Test: _flush_messages_to_session_db only writes new messages
# ---------------------------------------------------------------------------
class TestFlushDeduplication:
"""Verify _flush_messages_to_session_db tracks what it already wrote."""
def _make_agent(self, session_db):
"""Create a minimal AIAgent with a real session DB."""
with patch.dict(os.environ, {"OPENROUTER_API_KEY": "test-key"}):
from run_agent import AIAgent
agent = AIAgent(
api_key="test-key",
base_url="https://openrouter.ai/api/v1",
model="test/model",
quiet_mode=True,
session_db=session_db,
session_id="test-session-860",
skip_context_files=True,
skip_memory=True,
)
# Simulate lazy session creation (normally done by run_conversation)
agent._ensure_db_session()
return agent
def test_flush_writes_only_new_messages(self):
"""First flush writes all new messages, second flush writes none."""
from hermes_state import SessionDB
with tempfile.TemporaryDirectory() as tmpdir:
db_path = Path(tmpdir) / "test.db"
db = SessionDB(db_path=db_path)
try:
agent = self._make_agent(db)
conversation_history = [
{"role": "user", "content": "old message"},
]
messages = list(conversation_history) + [
{"role": "user", "content": "new question"},
{"role": "assistant", "content": "new answer"},
]
# First flush — should write 2 new messages
agent._flush_messages_to_session_db(messages, conversation_history)
rows = db.get_messages(agent.session_id)
assert len(rows) == 2, f"Expected 2 messages, got {len(rows)}"
# Second flush with SAME messages — should write 0 new messages
agent._flush_messages_to_session_db(messages, conversation_history)
rows = db.get_messages(agent.session_id)
assert len(rows) == 2, f"Expected still 2 messages after second flush, got {len(rows)}"
finally:
db.close()
def test_flush_reset_after_compression(self):
"""After compression creates a new session, flush index resets."""
from hermes_state import SessionDB
with tempfile.TemporaryDirectory() as tmpdir:
db_path = Path(tmpdir) / "test.db"
db = SessionDB(db_path=db_path)
try:
agent = self._make_agent(db)
# Write some messages
messages = [
{"role": "user", "content": "msg1"},
{"role": "assistant", "content": "reply1"},
]
agent._flush_messages_to_session_db(messages, [])
old_session = agent.session_id
assert agent._last_flushed_db_idx == 2
# Simulate what _compress_context does: new session, reset idx
agent.session_id = "compressed-session-new"
db.create_session(session_id=agent.session_id, source="test")
agent._last_flushed_db_idx = 0
# Now flush compressed messages to new session
compressed_messages = [
{"role": "user", "content": "summary of conversation"},
]
agent._flush_messages_to_session_db(compressed_messages, [])
new_rows = db.get_messages(agent.session_id)
assert len(new_rows) == 1
# Old session should still have its 2 messages
old_rows = db.get_messages(old_session)
assert len(old_rows) == 2
finally:
db.close()
# ---------------------------------------------------------------------------
# Test: append_to_transcript skip_db parameter
# ---------------------------------------------------------------------------
class TestAppendToTranscriptSkipDb:
"""Verify skip_db=True skips the SQLite write."""
def test_skip_db_prevents_sqlite_write(self, tmp_path):
"""With skip_db=True and a real DB, message does NOT appear in SQLite."""
from gateway.config import GatewayConfig
from gateway.session import SessionStore
from hermes_state import SessionDB
db_path = tmp_path / "test_skip.db"
db = SessionDB(db_path=db_path)
config = GatewayConfig()
with patch("gateway.session.SessionStore._ensure_loaded"):
store = SessionStore(sessions_dir=tmp_path, config=config)
store._db = db
store._loaded = True
session_id = "test-skip-db-real"
db.create_session(session_id=session_id, source="test")
msg = {"role": "assistant", "content": "hello world"}
store.append_to_transcript(session_id, msg, skip_db=True)
# SQLite should NOT have the message
rows = db.get_messages(session_id)
assert len(rows) == 0, f"Expected 0 DB rows with skip_db=True, got {len(rows)}"
# ---------------------------------------------------------------------------
# Test: _last_flushed_db_idx initialization
# ---------------------------------------------------------------------------
class TestFlushIdxInit:
"""Verify _last_flushed_db_idx is properly initialized."""
def test_init_zero(self):
"""Agent starts with _last_flushed_db_idx = 0."""
with patch.dict(os.environ, {"OPENROUTER_API_KEY": "test-key"}):
from run_agent import AIAgent
agent = AIAgent(
api_key="test-key",
base_url="https://openrouter.ai/api/v1",
model="test/model",
quiet_mode=True,
skip_context_files=True,
skip_memory=True,
)
assert agent._last_flushed_db_idx == 0