Add Rule 14 (provider name must match custom_providers) + audit script
Rule 14: model.provider MUST be 'harness' (custom_providers[0].name), NOT 'custom'. When provider: custom, Hermes falls through to generic resolution path that ignores key_env, producing 'no-key-required' → HTTP 401. audit-hermes-config.py: encodes all 14 contract rules as automated checks. Run before and after any Hermes config change. Root cause: WAL #1471 (2026-07-19 Mumuni 401 incident)
This commit is contained in:
root
@@ -0,0 +1 @@
|
||||
__pycache__/
|
||||
@@ -0,0 +1,230 @@
|
||||
#!/usr/bin/env python3
|
||||
"""
|
||||
Hermes Config Audit — validates a live config.yaml against the prose contract rules.
|
||||
|
||||
Usage:
|
||||
python3 audit-hermes-config.py <config.yaml>
|
||||
python3 audit-hermes-config.py /root/.hermes/config.yaml
|
||||
|
||||
Exit codes:
|
||||
0 = all checks pass
|
||||
1 = one or more contract violations found
|
||||
|
||||
This script encodes every rule from hermes-config-template.prose.md so config
|
||||
changes can be verified before and after application. It is the single automated
|
||||
enforcement layer for the prose contract.
|
||||
|
||||
Contract: /root/prose-contracts/hermes-config-template.prose.md
|
||||
"""
|
||||
|
||||
import sys
|
||||
import yaml
|
||||
|
||||
VIOLATIONS = []
|
||||
WARNINGS = []
|
||||
PASSES = []
|
||||
|
||||
|
||||
def check(condition, rule, message):
|
||||
if condition:
|
||||
PASSES.append(f"[{rule}] {message}")
|
||||
else:
|
||||
VIOLATIONS.append(f"[{rule}] {message}")
|
||||
|
||||
|
||||
def warn(rule, message):
|
||||
WARNINGS.append(f"[{rule}] {message}")
|
||||
|
||||
|
||||
def audit(path):
|
||||
with open(path) as f:
|
||||
cfg = yaml.safe_load(f)
|
||||
|
||||
model = cfg.get("model", {})
|
||||
fb = cfg.get("fallback_providers", {})
|
||||
comp = cfg.get("compression", {})
|
||||
aux = cfg.get("auxiliary", {})
|
||||
deleg = cfg.get("delegation", {})
|
||||
cps = cfg.get("custom_providers", [])
|
||||
cp = cps[0] if cps else {}
|
||||
|
||||
# --- Rule 3: API Keys via Environment ---
|
||||
check(
|
||||
model.get("api_key") in ("", None),
|
||||
"Rule 3",
|
||||
f"model.api_key must be empty (got {model.get('api_key')!r}) — keys via env var, not hardcoded",
|
||||
)
|
||||
check(
|
||||
model.get("api_key_env") == "LITELLM_API_KEY",
|
||||
"Rule 3",
|
||||
f"model.api_key_env must be LITELLM_API_KEY (got {model.get('api_key_env')!r})",
|
||||
)
|
||||
|
||||
# --- Rule 5: Main Config Base URL ---
|
||||
expected_base = "http://192.168.68.116/v1"
|
||||
check(
|
||||
model.get("base_url") == expected_base,
|
||||
"Rule 5",
|
||||
f"model.base_url must be {expected_base} (got {model.get('base_url')!r}) — /v1 not /litellm/v1",
|
||||
)
|
||||
|
||||
# --- Rule 6: max_tokens Is Required ---
|
||||
check(
|
||||
isinstance(model.get("max_tokens"), int) and model.get("max_tokens") <= 8192,
|
||||
"Rule 6",
|
||||
f"model.max_tokens must be set and <= 8192 (got {model.get('max_tokens')!r}) — thermal safety",
|
||||
)
|
||||
|
||||
# --- Rule 7: Auxiliary Model Consistency ---
|
||||
check(
|
||||
comp.get("model") == "strix-moe",
|
||||
"Rule 7",
|
||||
f"compression.model must be strix-moe (got {comp.get('model')!r}) — only valid compression model",
|
||||
)
|
||||
aux_comp = aux.get("compression", {})
|
||||
check(
|
||||
aux_comp.get("model") == "strix-moe",
|
||||
"Rule 7",
|
||||
f"auxiliary.compression.model must be strix-moe (got {aux_comp.get('model')!r}) — must match compression.model",
|
||||
)
|
||||
|
||||
# --- Rule 8: GPU Workload Distribution ---
|
||||
check(
|
||||
aux.get("vision", {}).get("model") == "gpu-light",
|
||||
"Rule 8",
|
||||
f"auxiliary.vision.model must be gpu-light (got {aux.get('vision', {}).get('model')!r}) — RTX 5070 stable alias",
|
||||
)
|
||||
check(
|
||||
aux.get("web_extract", {}).get("model") == "gpu-light",
|
||||
"Rule 8",
|
||||
f"auxiliary.web_extract.model must be gpu-light (got {aux.get('web_extract', {}).get('model')!r}) — RTX 5070 stable alias",
|
||||
)
|
||||
|
||||
# --- Rule 9: Compression Threshold ---
|
||||
check(
|
||||
comp.get("threshold") == 0.65,
|
||||
"Rule 9",
|
||||
f"compression.threshold must be 0.65 for 128K models (got {comp.get('threshold')!r})",
|
||||
)
|
||||
check(
|
||||
comp.get("max_context_window") == 131072,
|
||||
"Rule 9",
|
||||
f"compression.max_context_window must be 131072 (got {comp.get('max_context_window')!r}) — matches 128K GPU capacity",
|
||||
)
|
||||
|
||||
# --- Rule 10: Default Model Must Be syslog-auto ---
|
||||
check(
|
||||
model.get("default") == "syslog-auto",
|
||||
"Rule 10",
|
||||
f"model.default must be syslog-auto (got {model.get('default')!r}) — auto-routing default",
|
||||
)
|
||||
|
||||
# --- Rule 14: Provider Name Must Match custom_providers Name ---
|
||||
check(
|
||||
model.get("provider") == "harness",
|
||||
"Rule 14",
|
||||
f"model.provider must be 'harness' (got {model.get('provider')!r}) — NOT 'custom'. "
|
||||
f"provider: custom causes generic resolution path that ignores key_env → 'no-key-required' → 401",
|
||||
)
|
||||
check(
|
||||
comp.get("provider") == "harness",
|
||||
"Rule 14",
|
||||
f"compression.provider must be 'harness' (got {comp.get('provider')!r})",
|
||||
)
|
||||
for aux_name in ("vision", "web_extract", "compression"):
|
||||
aux_provider = aux.get(aux_name, {}).get("provider")
|
||||
check(
|
||||
aux_provider == "harness",
|
||||
"Rule 14",
|
||||
f"auxiliary.{aux_name}.provider must be 'harness' (got {aux_provider!r})",
|
||||
)
|
||||
check(
|
||||
deleg.get("provider") == "harness",
|
||||
"Rule 14",
|
||||
f"delegation.provider must be 'harness' (got {deleg.get('provider')!r})",
|
||||
)
|
||||
check(
|
||||
fb.get("provider") == "deepseek",
|
||||
"Rule 14",
|
||||
f"fallback_providers.provider must be 'deepseek' (got {fb.get('provider')!r}) — "
|
||||
f"true fallback diversity, not same endpoint as primary",
|
||||
)
|
||||
check(
|
||||
fb.get("model") == "deepseek-v4-flash",
|
||||
"Rule 14",
|
||||
f"fallback_providers.model must be 'deepseek-v4-flash' (got {fb.get('model')!r})",
|
||||
)
|
||||
check(
|
||||
fb.get("api_key_env") == "DEEPSEEK_API_KEY",
|
||||
"Rule 14",
|
||||
f"fallback_providers.api_key_env must be DEEPSEEK_API_KEY (got {fb.get('api_key_env')!r})",
|
||||
)
|
||||
|
||||
# --- custom_providers sanity ---
|
||||
check(
|
||||
cp.get("name") == "harness",
|
||||
"custom_providers",
|
||||
f"custom_providers[0].name must be 'harness' (got {cp.get('name')!r})",
|
||||
)
|
||||
check(
|
||||
cp.get("key_env") == "LITELLM_API_KEY" or cp.get("api_key_env") == "LITELLM_API_KEY",
|
||||
"custom_providers",
|
||||
f"custom_providers[0] must have key_env or api_key_env = LITELLM_API_KEY "
|
||||
f"(got key_env={cp.get('key_env')!r}, api_key_env={cp.get('api_key_env')!r})",
|
||||
)
|
||||
check(
|
||||
cp.get("base_url", "").endswith("/v1"),
|
||||
"custom_providers",
|
||||
f"custom_providers[0].base_url must end with /v1 (got {cp.get('base_url')!r})",
|
||||
)
|
||||
|
||||
# --- No raw model names (Rule 7/8 spirit) ---
|
||||
raw_names = {"gemma-4-12b", "qwen3.6-27B-code", "qwen3.6-35B-udq4", "ornith-1.0-35b"}
|
||||
for section_path, section_dict in [
|
||||
("model", model), ("compression", comp),
|
||||
("auxiliary.vision", aux.get("vision", {})),
|
||||
("auxiliary.web_extract", aux.get("web_extract", {})),
|
||||
("auxiliary.compression", aux.get("compression", {})),
|
||||
("delegation", deleg),
|
||||
]:
|
||||
m = section_dict.get("model", "")
|
||||
if m in raw_names:
|
||||
warn(
|
||||
"Rule 7/8",
|
||||
f"{section_path}.model = {m!r} — raw model name, use stable alias instead "
|
||||
f"(gpu-light, gpu-dense, strix-moe, syslog-auto)",
|
||||
)
|
||||
|
||||
# --- Report ---
|
||||
print(f"{'=' * 60}")
|
||||
print(f"Hermes Config Audit: {path}")
|
||||
print(f"{'=' * 60}")
|
||||
print(f"\n✅ PASSED ({len(PASSES)}):")
|
||||
for p in PASSES:
|
||||
print(f" ✅ {p}")
|
||||
|
||||
if WARNINGS:
|
||||
print(f"\n⚠️ WARNINGS ({len(WARNINGS)}):")
|
||||
for w in WARNINGS:
|
||||
print(f" ⚠️ {w}")
|
||||
|
||||
if VIOLATIONS:
|
||||
print(f"\n❌ VIOLATIONS ({len(VIOLATIONS)}):")
|
||||
for v in VIOLATIONS:
|
||||
print(f" ❌ {v}")
|
||||
print(f"\n{'=' * 60}")
|
||||
print(f"RESULT: FAIL — {len(VIOLATIONS)} violation(s) must be fixed")
|
||||
print(f"{'=' * 60}")
|
||||
return 1
|
||||
else:
|
||||
print(f"\n{'=' * 60}")
|
||||
print(f"RESULT: PASS — all contract rules satisfied")
|
||||
print(f"{'=' * 60}")
|
||||
return 0
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
if len(sys.argv) < 2:
|
||||
print("Usage: python3 audit-hermes-config.py <config.yaml>")
|
||||
sys.exit(2)
|
||||
sys.exit(audit(sys.argv[1]))
|
||||
@@ -371,6 +371,26 @@ curl -s -o /dev/null -w '%{http_code}' -H "Authorization: Bearer $K" http://192.
|
||||
- `/etc/environment` is NO LONGER the canonical key source (stale values there caused 401s).
|
||||
- Do NOT leave a hardcoded stale key in `/etc/environment` — it shadows the drop-in/wrapper.
|
||||
|
||||
### Rule 14: Provider Name Must Match custom_providers Name (ADDED 2026-07-19, WAL #1471)
|
||||
|
||||
- `model.provider` MUST be `harness` (the `custom_providers[0].name`), NOT the literal string `custom`
|
||||
- When `provider: custom`, Hermes' `_get_named_custom_provider("custom")` returns None (no provider is
|
||||
named "custom" — it is named "harness"), causing a fall-through to the generic resolution path
|
||||
(`source: env/config`) at `runtime_provider.py:1156`
|
||||
- The generic path builds `api_key_candidates` from `model.api_key` (empty), host-gated
|
||||
OLLAMA/OPENAI/OPENROUTER keys, and `_host_derived_api_key` (returns "" for IP addresses)
|
||||
- **The generic path does NOT resolve `model.api_key_env` or `custom_providers.key_env`** —
|
||||
`LITELLM_API_KEY` is never read, producing `api_key = "no-key-required"` → HTTP 401
|
||||
- The named custom provider path (`source: custom_provider:harness`) DOES read `key_env` —
|
||||
but only triggers when `provider` matches the `custom_providers[0].name`
|
||||
- All sections MUST use `provider: harness`: `model`, `compression`, `auxiliary.vision`,
|
||||
`auxiliary.web_extract`, `auxiliary.compression`, `delegation`
|
||||
- Only `fallback_providers` uses a different provider (`deepseek`) for true fallback diversity
|
||||
- **Diagnostic**: If you see `source: env/config` in a request dump or log, the provider name
|
||||
is wrong. It should be `source: custom_provider:harness`.
|
||||
- **Audit script**: Run `python3 /root/prose-contracts/audit-hermes-config.py <config.yaml>`
|
||||
before and after any config change to catch this and all other rule violations.
|
||||
|
||||
## Execution
|
||||
|
||||
1. **Check current config** — Read the target agent's config.yaml
|
||||
|
||||
Reference in New Issue
Block a user