Skip to content

fix(runtime): honour HERMES_LLM_BASE_URL in pool-based and explicit runtime resolution #34044

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
OmarB97 wants to merge 2 commits into from
Closed

fix(runtime): honour HERMES_LLM_BASE_URL in pool-based and explicit runtime resolution #34044

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
87e6acb
fix: honour HERMES_LLM_BASE_URL in runtime_provider.py api_key path
May 28, 2026
2654245
fix: honour HERMES_LLM_BASE_URL in pool-based runtime provider resolu…
May 28, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
15 changes: 15 additions & 0 deletions hermes_cli/runtime_provider.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -304,6 +304,15 @@ def _resolve_runtime_from_pool_entry(
# config.default was still a Claude model.
effective_model = (target_model or model_cfg.get("default") or "")
base_url = (getattr(entry, "runtime_base_url", None) or getattr(entry, "base_url", None) or "").rstrip("/")
# MeshBoard stream-tap launcher sets HERMES_LLM_BASE_URL to a local
# loopback proxy URL when the stream-tap is active. This env var
# must override the pool's default base_url so inference traffic
# is routed through the proxy and captured as JSONL for the
# dashboard. Without this, Hermes bypasses the tap entirely and
# the dashboard shows "model silent" during active dispatches.
_tap_url = os.getenv("HERMES_LLM_BASE_URL", "").strip().rstrip("/")
if _tap_url:
base_url = _tap_url
api_key = getattr(entry, "runtime_api_key", None) or getattr(entry, "access_token", "")
api_mode = "chat_completions"
if provider == "openai-codex":
Expand Down Expand Up @@ -1153,6 +1162,12 @@ def _resolve_explicit_runtime(
env_url = ""
if pconfig.base_url_env_var:
env_url = os.getenv(pconfig.base_url_env_var, "").strip().rstrip("/")
# MeshBoard stream-tap launcher sets HERMES_LLM_BASE_URL to a local
# proxy URL. Honour it when the provider-specific env var is absent
# so the tap proxy actually receives inference traffic instead of
# being silently bypassed in favour of the default upstream URL.
if not env_url:
env_url = os.getenv("HERMES_LLM_BASE_URL", "").strip().rstrip("/")

base_url = explicit_base_url
if not base_url:
Expand Down