mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-07-31 19:16:29 +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).
72 lines
2.8 KiB
Python
72 lines
2.8 KiB
Python
"""Tests for /learn — open-ended skill distillation.
|
|
|
|
Covers the shared prompt builder (agent.learn_prompt.build_learn_prompt) and
|
|
the slash-command registry wiring. /learn has no engine and no model tool: it
|
|
builds a standards-guided prompt that the live agent runs as a normal turn, so
|
|
these are the load-bearing behavior contracts.
|
|
"""
|
|
|
|
from agent.learn_prompt import build_learn_prompt, _AUTHORING_STANDARDS
|
|
|
|
|
|
class TestBuildLearnPrompt:
|
|
def test_embeds_the_user_request_verbatim(self):
|
|
req = "the REST client in ~/projects/acme-sdk, focus on auth"
|
|
prompt = build_learn_prompt(req)
|
|
assert req in prompt
|
|
|
|
|
|
|
|
|
|
def test_separates_sources_from_requirements(self):
|
|
# The reported bug (@GrenFX, Jun 2026): when a request leads with a
|
|
# path/URL, the agent fetched it and ignored the trailing prose. The
|
|
# prompt must tell the agent the request can MIX sources and
|
|
# requirements, and that prose after a source is authoring guidance to
|
|
# honor — not noise to drop.
|
|
prompt = build_learn_prompt(
|
|
"https://api.example.com/docs focus on the auth flow, skip deprecated bits"
|
|
)
|
|
low = prompt.lower()
|
|
# Carries the whole request verbatim (no truncation at the URL).
|
|
assert "focus on the auth flow, skip deprecated bits" in prompt
|
|
# Explicitly distinguishes sources from requirements.
|
|
assert "requirement" in low
|
|
# Names the failure mode it's guarding against.
|
|
assert "never fetch the first source" in low
|
|
|
|
|
|
|
|
|
|
def test_teaches_the_full_hardline_standards(self):
|
|
# description length — otherwise distilled skills miss platform gating,
|
|
# author credit, and the tool-framing table. Lock the coverage in.
|
|
std = _AUTHORING_STANDARDS.lower()
|
|
# #1 description: the count-and-trim self-check (the reported bug).
|
|
assert "count" in std and "60" in std
|
|
# #3 platforms gating against OS-bound primitives.
|
|
assert "platforms" in std
|
|
# author is always the literal Hermes, never the host/OS identity (#52368).
|
|
assert "author: always the literal value `hermes`" in std
|
|
assert "never fill it from the host" in std
|
|
# #2 Hermes-tool framing names the wrapped tools, not shell utilities.
|
|
for tool in ("read_file", "search_files", "patch", "write_file"):
|
|
assert tool in std
|
|
# #6 scripts/references/templates layout.
|
|
assert "scripts/" in _AUTHORING_STANDARDS
|
|
|
|
|
|
class TestLearnRegistryWiring:
|
|
def test_learn_is_registered_and_resolves(self):
|
|
from hermes_cli.commands import resolve_command
|
|
|
|
cmd = resolve_command("learn")
|
|
assert cmd is not None
|
|
assert cmd.name == "learn"
|
|
|
|
|
|
|
|
def test_learn_is_not_cli_only(self):
|
|
from hermes_cli.commands import resolve_command
|
|
|
|
assert not resolve_command("learn").cli_only
|