mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-07-30 19:09:28 +00:00
6b81590c55
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).
127 lines
4.1 KiB
Python
127 lines
4.1 KiB
Python
"""MemoryManager strips slash-skill scaffolding for every provider.
|
|
|
|
When a user invokes a /skill or /bundle, Hermes expands the turn into a
|
|
model-facing message that embeds the full skill body. Feeding that verbatim to
|
|
memory providers pollutes their stores/embeddings with prompt scaffolding
|
|
instead of what the user actually asked. The strip lives once in MemoryManager
|
|
so it covers the whole provider fan-out — not per backend.
|
|
|
|
See: agent.skill_commands.extract_user_instruction_from_skill_message and
|
|
MemoryManager._strip_skill_scaffolding.
|
|
"""
|
|
|
|
from agent.memory_manager import MemoryManager
|
|
from agent.memory_provider import MemoryProvider
|
|
from agent.skill_commands import extract_user_instruction_from_skill_message
|
|
|
|
|
|
_SINGLE_SKILL_TURN = (
|
|
'[IMPORTANT: The user has invoked the "skill-creator" skill, indicating they want '
|
|
"you to follow its instructions. The full skill content is loaded below.]\n\n"
|
|
"# Skill Creator\n\n"
|
|
"Large skill body that must not be searched or embedded.\n\n"
|
|
"The user has provided the following instruction alongside the skill invocation: "
|
|
"make a skill for release triage"
|
|
)
|
|
|
|
_BUNDLE_TURN = (
|
|
'[IMPORTANT: The user has invoked the "backend-dev" skill bundle, '
|
|
"loading 2 skills together. Treat every skill below as active guidance for this turn.]\n\n"
|
|
"Bundle: backend-dev\n"
|
|
"Skills loaded: test-driven-development, code-review\n\n"
|
|
"User instruction: fix the failing retrieval test\n\n"
|
|
'[Loaded as part of the "backend-dev" skill bundle.]\n\n'
|
|
"Large bundled skill body that must not be searched or embedded."
|
|
)
|
|
|
|
_BARE_SKILL_TURN = (
|
|
'[IMPORTANT: The user has invoked the "skill-creator" skill, indicating they want '
|
|
"you to follow its instructions. The full skill content is loaded below.]\n\n"
|
|
"# Skill Creator\n\n"
|
|
"Large skill body, no user instruction."
|
|
)
|
|
|
|
|
|
class _RecordingProvider(MemoryProvider):
|
|
"""Captures exactly what user text each fan-out method received."""
|
|
|
|
_name = "recording"
|
|
|
|
def __init__(self):
|
|
self.prefetched = []
|
|
self.queued = []
|
|
self.synced = []
|
|
|
|
@property
|
|
def name(self) -> str:
|
|
return self._name
|
|
|
|
def initialize(self, session_id: str = "", **kwargs) -> None:
|
|
pass
|
|
|
|
def is_available(self) -> bool:
|
|
return True
|
|
|
|
def system_prompt_block(self) -> str:
|
|
return ""
|
|
|
|
def prefetch(self, query, *, session_id: str = "") -> str:
|
|
self.prefetched.append(query)
|
|
return ""
|
|
|
|
def queue_prefetch(self, query, *, session_id: str = "") -> None:
|
|
self.queued.append(query)
|
|
|
|
def sync_turn(self, user_content, assistant_content, *, session_id: str = "", messages=None) -> None:
|
|
self.synced.append(user_content)
|
|
|
|
def get_tool_schemas(self):
|
|
return []
|
|
|
|
|
|
def _manager_with_recorder():
|
|
mgr = MemoryManager()
|
|
provider = _RecordingProvider()
|
|
mgr.add_provider(provider)
|
|
return mgr, provider
|
|
|
|
|
|
class TestExtractUserInstruction:
|
|
def test_non_string_returns_none(self):
|
|
assert extract_user_instruction_from_skill_message(None) is None
|
|
assert extract_user_instruction_from_skill_message(123) is None
|
|
assert extract_user_instruction_from_skill_message([{"text": "hi"}]) is None
|
|
|
|
|
|
|
|
def test_bundle_with_instruction(self):
|
|
assert (
|
|
extract_user_instruction_from_skill_message(_BUNDLE_TURN)
|
|
== "fix the failing retrieval test"
|
|
)
|
|
|
|
|
|
|
|
|
|
class TestMemoryManagerStripsScaffolding:
|
|
|
|
def test_prefetch_all_skips_bare_skill(self):
|
|
mgr, provider = _manager_with_recorder()
|
|
result = mgr.prefetch_all(_BARE_SKILL_TURN)
|
|
assert result == ""
|
|
assert provider.prefetched == []
|
|
|
|
def test_queue_prefetch_all_strips_bundle(self):
|
|
mgr, provider = _manager_with_recorder()
|
|
mgr.queue_prefetch_all(_BUNDLE_TURN)
|
|
mgr.flush_pending(timeout=5.0)
|
|
assert provider.queued == ["fix the failing retrieval test"]
|
|
|
|
|
|
|
|
def test_sync_all_skips_bare_skill(self):
|
|
mgr, provider = _manager_with_recorder()
|
|
mgr.sync_all(_BARE_SKILL_TURN, "Done.")
|
|
mgr.flush_pending(timeout=5.0)
|
|
assert provider.synced == []
|
|
|