SyslogSolution/prose-contracts
7
0
Fork 0
Code Issues 2 Pull Requests Actions Packages Projects Releases Wiki Activity

fix(audit): reject retired aliases; sweep gpu-light/gemma-4-12b to gpu-vision

Browse Source 
audit-hermes-config.py Rule 8 required auxiliary.vision.model and
auxiliary.web_extract.model to equal the retired 'gpu-light', so a config
adopting the live canonical 'gpu-vision' FAILED our own audit - the audit was
enforcing a dead alias (400 Invalid model name). Rule 8 now requires
gpu-vision; retired names gpu-light/crew-auto join the raw-name rejection set;
the guidance message names the live aliases.

Sweep of the remaining references: gpu-self-heal stops canonicalizing
gpu-light; hermes-config-template, hermes-agent-baseline, hermes-key-enforcement,
inference-optimization, litellm-client-timeouts and gpu-fleet now use the live
gpu-vision alias. Where a file restated model/rpm/weight/fallback state it now
points at CT 116 /opt/inference-harness/litellm_config.yaml instead of
duplicating it. koby's .129 config is report-only and recorded, not edited.

Adds tests/test_audit_hermes_config_alias.py: executes the audit CLI and asserts
gpu-vision passes while gpu-light and gemma-4-12b fail.
This commit is contained in:
abiba
2026-09-12 16:11:46 +00:00
parent 1dc040251d
commit 221f9f79f3
10 changed files with 139 additions and 43 deletions
Download Patch File Download Diff File Expand all files Collapse all files
audit-hermes-config.py
+12 -8
View File
@@ -89,15 +89,16 @@ def audit(path):
)
# --- Rule 8: GPU Workload Distribution ---
# gpu-light (and gemma-4-12b) were retired 2026-09-12; the RTX 5070 stable alias is gpu-vision.
check(
aux.get("vision", {}).get("model") == "gpu-light",
aux.get("vision", {}).get("model") == "gpu-vision",
"Rule 8",
f"auxiliary.vision.model must be gpu-light (got {aux.get('vision', {}).get('model')!r}) — RTX 5070 stable alias",
f"auxiliary.vision.model must be gpu-vision (got {aux.get('vision', {}).get('model')!r}) — RTX 5070 stable alias",
)
check(
aux.get("web_extract", {}).get("model") == "gpu-light",
aux.get("web_extract", {}).get("model") == "gpu-vision",
"Rule 8",
f"auxiliary.web_extract.model must be gpu-light (got {aux.get('web_extract', {}).get('model')!r}) — RTX 5070 stable alias",
f"auxiliary.web_extract.model must be gpu-vision (got {aux.get('web_extract', {}).get('model')!r}) — RTX 5070 stable alias",
)
# --- Rule 9: Compression Threshold ---
@@ -178,8 +179,11 @@ def audit(path):
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"}
# --- No raw or retired model names (Rule 7/8 spirit) ---
# Retired names are rejected by the alias rules above; a config that names them directly is
# flagged here too. gpu-light/gemma-4-12b/crew-auto were retired 2026-09-12.
raw_names = {"gemma-4-12b", "qwen3.6-27B-code", "qwen3.6-35B-udq4", "ornith-1.0-35b",
"gpu-light", "crew-auto"}
for section_path, section_dict in [
("model", model), ("compression", comp),
("auxiliary.vision", aux.get("vision", {})),
@@ -191,8 +195,8 @@ def audit(path):
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)",
f"{section_path}.model = {m!r} — raw or retired model name, use a live stable alias "
f"instead (gpu-vision, gpu-dense, strix-moe, syslog-auto)",
)
# --- Report ---