hermes-bsd/tests
Teknium ea01bdcebe
refactor(memory): remove flush_memories entirely (#15696)
The AIAgent.flush_memories pre-compression save, the gateway
_flush_memories_for_session, and everything feeding them are
obsolete now that the background memory/skill review handles
persistent memory extraction.

Problems with flush_memories:

- Pre-dates the background review loop.  It was the only memory-save
  path when introduced; the background review now fires every 10 user
  turns on CLI and gateway alike, which is far more frequent than
  compression or session reset ever triggered flush.
- Blocking and synchronous.  Pre-compression flush ran on the live agent
  before compression, blocking the user-visible response.
- Cache-breaking.  Flush built a temporary conversation prefix
  (system prompt + memory-only tool list) that diverged from the live
  conversation's cached prefix, invalidating prompt caching.  The
  gateway variant spawned a fresh AIAgent with its own clean prompt
  for each finalized session — still cache-breaking, just in a
  different process.
- Redundant.  Background review runs in the live conversation's
  session context, gets the same content, writes to the same memory
  store, and doesn't break the cache.  Everything flush_memories
  claimed to preserve is already covered.

What this removes:

- AIAgent.flush_memories() method (~248 LOC in run_agent.py)
- Pre-compression flush call in _compress_context
- flush_memories call sites in cli.py (/new + exit)
- GatewayRunner._flush_memories_for_session + _async_flush_memories
  (and the 3 call sites: session expiry watcher, /new, /resume)
- 'flush_memories' entry from DEFAULT_CONFIG auxiliary tasks,
  hermes tools UI task list, auxiliary_client docstrings
- _memory_flush_min_turns config + init
- #15631's headroom-deduction math in
  _check_compression_model_feasibility (headroom was only needed
  because flush dragged the full main-agent system prompt along;
  the compression summariser sends a single user-role prompt so
  new_threshold = aux_context is safe again)
- The dedicated test files and assertions that exercised
  flush-specific paths

What this renames (with read-time backcompat on sessions.json):

- SessionEntry.memory_flushed -> SessionEntry.expiry_finalized.
  The session-expiry watcher still uses the flag to avoid re-running
  finalize/eviction on the same expired session; the new name
  reflects what it now actually gates.  from_dict() reads
  'expiry_finalized' first, falls back to the legacy 'memory_flushed'
  key so existing sessions.json files upgrade seamlessly.

Supersedes #15631 and #15638.

Tested: 383 targeted tests pass across run_agent/, agent/, cli/,
and gateway/ session-boundary suites.  No behavior regressions —
background memory review continues to handle persistent memory
extraction on both CLI and gateway.
2026-04-25 08:21:14 -07:00
..
acp fix(acp): include MCP toolsets in ACP sessions 2026-04-24 03:04:42 -07:00
agent refactor(memory): remove flush_memories entirely (#15696) 2026-04-25 08:21:14 -07:00
cli refactor(memory): remove flush_memories entirely (#15696) 2026-04-25 08:21:14 -07:00
cron fix(cron): wire context_from through the update action 2026-04-25 04:49:28 -07:00
e2e refactor(commands): drop /provider, /plan handler, and clean up slash registry (#15047) 2026-04-24 03:10:52 -07:00
environments/benchmarks
fakes
gateway refactor(memory): remove flush_memories entirely (#15696) 2026-04-25 08:21:14 -07:00
hermes_cli feat(dashboard): page-scoped plugin slots for built-in pages (#15658) 2026-04-25 06:55:35 -07:00
hermes_state fix(resume): redirect --resume to the descendant that actually holds the messages 2026-04-24 03:04:42 -07:00
honcho_plugin
integration
plugins feat(hindsight): optional bank_id_template for per-agent / per-user banks 2026-04-24 03:38:17 -07:00
run_agent refactor(memory): remove flush_memories entirely (#15696) 2026-04-25 08:21:14 -07:00
skills fix(skills): factor HERMES_HOME resolution into shared _hermes_home helper 2026-04-24 16:45:27 -07:00
tools fix(terminal): three-layer defense against watch_patterns notification spam (#15642) 2026-04-25 06:41:58 -07:00
tui_gateway fix(tui): keep default personality neutral 2026-04-24 16:19:23 -05:00
__init__.py
conftest.py
run_interrupt_test.py
test_account_usage.py
test_base_url_hostname.py
test_batch_runner_checkpoint.py test: regression coverage for checkpoint dedup and inf/nan coercion 2026-04-24 14:32:21 -07:00
test_cli_file_drop.py
test_cli_skin_integration.py
test_ctx_halving_fix.py
test_empty_model_fallback.py
test_evidence_store.py
test_hermes_constants.py
test_hermes_logging.py
test_hermes_state.py
test_honcho_client_config.py
test_ipv4_preference.py
test_mcp_serve.py
test_mini_swe_runner.py
test_minimax_model_validation.py
test_minisweagent_path.py
test_model_picker_scroll.py
test_model_tools.py test: regression coverage for checkpoint dedup and inf/nan coercion 2026-04-24 14:32:21 -07:00
test_model_tools_async_bridge.py
test_ollama_num_ctx.py
test_packaging_metadata.py
test_plugin_skills.py
test_project_metadata.py
test_retry_utils.py
test_sql_injection.py
test_subprocess_home_isolation.py
test_timezone.py
test_toolset_distributions.py
test_toolsets.py feat(discord): split discord_server into discord + discord_admin tools 2026-04-25 04:50:14 -07:00
test_trajectory_compressor.py
test_trajectory_compressor_async.py
test_transform_tool_result_hook.py
test_tui_gateway_server.py feat(tui): per-section visibility for the details accordion 2026-04-24 02:34:32 -05:00
test_utils_truthy_values.py