Files
prose-contracts/tests/test_audit_hermes_config_alias.py
T
root e71ded3c8c
PR Pipeline — Authorize → Validate → Review → Merge / auth (pull_request) Successful in 1s
PR Pipeline — Authorize → Validate → Review → Merge / validate (pull_request) Successful in 5s
PR Pipeline — Authorize → Validate → Review → Merge / lint (pull_request) Successful in 3s
PR Pipeline — Authorize → Validate → Review → Merge / ai-review (pull_request) Successful in 4s
PR Pipeline — Authorize → Validate → Review → Merge / gate (pull_request) Successful in 3s
fix: internal /v1 WARN not FAIL; align prose
Rule 5 now treats internal http://192.168.68.116/v1 as non-canonical
but working (authenticated via nginx), producing a WARNING instead of a
FAILURE. The canonical internal path /litellm/v1 and the public host
https://litellm.sysloggh.net/v1 both PASS. Everything else FAILS.

Prose aligned: hermes-key-enforcement.prose.md now states the canonical
internal form, notes that internal /v1 still works but is flagged as
non-canonical (WARN not FAIL), and clarifies that the public host serves
/v1 ONLY (404 on /litellm/v1). Corrected the 'unauthenticated path'
wording at line 116, which was factually wrong.

Tests updated: BASE template uses canonical internal path; new test
cases prove canonical /litellm/v1 PASSES, wrong path FAILS, public host
PASSES, and internal /v1 WARNS (not FAILS). Fixed backwards comment in
test_old_rule5_check_would_fail_canonical.
2026-09-19 11:48:48 +00:00

262 lines
9.2 KiB
Python

"""Regression tests for the 2026-09-12 retired-alias sweep in audit-hermes-config.py.
WHY THIS FILE EXISTS: the executable audit pushed agent configs toward a DEAD alias.
Rule 8 required `auxiliary.vision.model == "gpu-light"` and
`auxiliary.web_extract.model == "gpu-light"`, but `gpu-light` (and its raw predecessor
`gemma-4-12b`) were retired on 2026-09-12 and now return 400 `Invalid model name`; the
live RTX 5070 alias is `gpu-vision`. A config that adopted the correct canonical alias
therefore FAILED our own audit, so the audit was actively enforcing a broken config.
These tests execute the real CLI (`python3 audit-hermes-config.py <config>`) and assert
observable behaviour — exit code and the emitted rule message — for the live alias and
for both retired names. No network, vault, or SSH access is required.
"""
from __future__ import annotations
import pathlib
import subprocess
import sys
ROOT = pathlib.Path(__file__).resolve().parent.parent
AUDIT = ROOT / "audit-hermes-config.py"
BASE = """
model:
api_key: ""
api_key_env: LITELLM_API_KEY
base_url: http://192.168.68.116/litellm/v1
max_tokens: 4096
default: syslog-auto
provider: harness
fallback_providers:
provider: deepseek
model: deepseek-v4-flash
api_key_env: DEEPSEEK_API_KEY
compression:
model: syslog-auto
provider: harness
threshold: 0.65
max_context_window: 131072
auxiliary:
vision:
model: {alias}
provider: harness
web_extract:
model: {alias}
provider: harness
compression:
model: syslog-auto
provider: harness
delegation:
provider: harness
custom_providers:
- name: harness
key_env: LITELLM_API_KEY
base_url: http://192.168.68.116/litellm/v1
"""
def _run_config(tmp_path, name, text):
cfg = tmp_path / name
cfg.write_text(text)
proc = subprocess.run(
[sys.executable, str(AUDIT), str(cfg)],
capture_output=True, text=True,
)
return proc.returncode, proc.stdout
def _run(tmp_path, alias):
return _run_config(tmp_path, f"{alias}.yaml", BASE.format(alias=alias))
def test_live_canonical_alias_passes(tmp_path):
"""The RTX 5070 alias that actually resolves must satisfy Rule 8."""
code, out = _run(tmp_path, "gpu-vision")
assert code == 0, out
assert "RESULT: PASS" in out
def test_retired_gpu_light_is_rejected(tmp_path):
"""A config pinned to the retired alias must fail, not pass."""
code, out = _run(tmp_path, "gpu-light")
assert code == 1, out
assert "auxiliary.vision.model must be gpu-vision" in out
assert "RESULT: FAIL" in out
def test_retired_gemma_is_rejected(tmp_path):
"""The retired raw model name must fail Rule 8 as well."""
code, out = _run(tmp_path, "gemma-4-12b")
assert code == 1, out
assert "auxiliary.vision.model must be gpu-vision" in out
assert "RESULT: FAIL" in out
def test_corrected_compression_example_passes(tmp_path):
"""The corrected workaround (vision=gpu-vision, compression=syslog-auto) must PASS."""
code, out = _run(tmp_path, "gpu-vision")
assert code == 0, out
assert "[Rule 7] compression.model must be syslog-auto (got 'syslog-auto')" in out
assert "[Rule 7] auxiliary.compression.model must be syslog-auto (got 'syslog-auto')" in out
assert "RESULT: PASS" in out
def test_retired_alias_in_delegation_is_rejected(tmp_path):
"""delegation.model has no dedicated value rule, so a retired name there used to PASS."""
code, out = _run_config(
tmp_path,
"delegation-gpu-light.yaml",
BASE.format(alias="gpu-vision").replace(
"delegation:\n provider: harness",
"delegation:\n provider: harness\n model: gpu-light",
),
)
assert code == 1, out
assert "delegation.model = 'gpu-light' is retired" in out
assert "RESULT: FAIL" in out
def test_retired_alias_in_custom_providers_is_rejected(tmp_path):
"""custom_providers[*].model is model-bearing; a retired name there must fail."""
code, out = _run_config(
tmp_path,
"custom-provider-gpu-light.yaml",
BASE.format(alias="gpu-vision").replace(
" - name: harness\n key_env: LITELLM_API_KEY",
" - name: harness\n model: gpu-light\n key_env: LITELLM_API_KEY",
),
)
assert code == 1, out
assert "custom_providers[0].model = 'gpu-light'" in out
assert "RESULT: FAIL" in out
def test_retired_raw_name_fails(tmp_path):
"""Retired raw names no longer resolve (400), so they fail; the 2026-09-12 registry change moved qwen3.6-27B-code from raw-but-live to non-resolving."""
code, out = _run_config(
tmp_path,
"retired-qwen.yaml",
BASE.format(alias="gpu-vision").replace(
"delegation:\n provider: harness",
"delegation:\n provider: harness\n model: qwen3.6-27B-code",
),
)
assert code != 0, out
assert "delegation.model = 'qwen3.6-27B-code' is retired and no longer resolves" in out
assert "use gpu-dense" in out
assert "RESULT: FAIL" in out
def test_retired_alias_in_fallback_providers_is_rejected(tmp_path):
"""fallback_providers.model is model-bearing; a retired name there must fail."""
code, out = _run_config(
tmp_path,
"fallback-gpu-light.yaml",
BASE.format(alias="gpu-vision").replace(" model: deepseek-v4-flash", " model: gpu-light"),
)
assert code == 1, out
assert "fallback_providers.model = 'gpu-light'" in out
assert "RESULT: FAIL" in out
def test_retired_alias_in_x_search_is_rejected(tmp_path):
"""x_search.model was previously not enumerated; the derivation must catch it."""
code, out = _run_config(
tmp_path,
"x-search-gpu-light.yaml",
BASE.format(alias="gpu-vision").replace(
"delegation:\n provider: harness",
"delegation:\n provider: harness\nx_search:\n model: gpu-light",
),
)
assert code == 1, out
assert "x_search.model = 'gpu-light'" in out
assert "RESULT: FAIL" in out
def test_retired_alias_in_nested_auxiliary_block_is_rejected(tmp_path):
"""A nested auxiliary sub-block outside the named three must still be derived."""
code, out = _run_config(
tmp_path,
"nested-aux-gpu-light.yaml",
BASE.format(alias="gpu-vision").replace(
" compression:\n model: syslog-auto\n provider: harness\ndelegation:",
" compression:\n model: syslog-auto\n provider: harness\n"
" tasks:\n summarize:\n model: gpu-light\ndelegation:",
),
)
assert code == 1, out
assert "auxiliary.tasks.summarize.model = 'gpu-light'" in out
assert "RESULT: FAIL" in out
def test_canonical_internal_path_passes(tmp_path):
"""Rule 5 must accept the canonical internal base from hermes-key-enforcement.prose.md."""
code, out = _run(
tmp_path,
"gpu-vision",
)
# Override the base_url in the config
cfg_text = BASE.format(alias="gpu-vision").replace(
" base_url: http://192.168.68.116/v1",
" base_url: http://192.168.68.116/litellm/v1",
)
code, out = _run_config(tmp_path, "canonical-internal.yaml", cfg_text)
assert code == 0, out
assert "RESULT: PASS" in out
# Verify the correct message is shown
assert "model.base_url is canonical" in out
def test_wrong_base_url_fails(tmp_path):
"""Rule 5 must reject paths outside the allowed list."""
cfg_text = BASE.format(alias="gpu-vision").replace(
" base_url: http://192.168.68.116/litellm/v1",
" base_url: http://192.168.68.116/litellm/v1/responses",
)
code, out = _run_config(tmp_path, "wrong-base.yaml", cfg_text)
assert code == 1, out
assert "RESULT: FAIL" in out
assert "model.base_url must be one of" in out
def test_public_host_path_passes(tmp_path):
"""Rule 5 must accept the public host base."""
cfg_text = BASE.format(alias="gpu-vision").replace(
" base_url: http://192.168.68.116/v1",
" base_url: https://litellm.sysloggh.net/v1",
)
code, out = _run_config(tmp_path, "public-host.yaml", cfg_text)
assert code == 0, out
assert "RESULT: PASS" in out
def test_old_rule5_check_would_fail_canonical(tmp_path):
"""
Proof that the OLD Rule 5 check would fail the canonical internal path.
This proves the bug existed before the fix.
"""
# OLD check expected /v1, so the canonical /litellm/v1 would have failed
canonical_cfg = BASE.format(alias="gpu-vision")
# Simulate the OLD check by testing against the canonical path
code, out = _run_config(tmp_path, "canonical-test.yaml", canonical_cfg)
# NEW check: canonical /litellm/v1 SHOULD pass
assert code == 0, out
assert "RESULT: PASS" in out
# OLD check expected /v1, so the internal /v1 would have passed
# NEW check: internal /v1 is non-canonical but working (WARN not FAIL)
old_cfg = BASE.format(alias="gpu-vision").replace(
" base_url: http://192.168.68.116/litellm/v1",
" base_url: http://192.168.68.116/v1",
)
code, out = _run_config(tmp_path, "old-check-test.yaml", old_cfg)
assert code == 0, out
assert "RESULT: PASS" in out
# NEW check should pass
new_cfg = BASE.format(alias="gpu-vision")
code, out = _run_config(tmp_path, "new-check-test.yaml", new_cfg)
assert code == 0, out
assert "RESULT: PASS" in out