fix(doctor): detect + repair stale HERMES_MAX_ITERATIONS .env ghost shadowing config.yaml (#38222)

* fix(doctor): detect + repair stale HERMES_MAX_ITERATIONS .env ghost shadowing config.yaml

hermes doctor now flags when ~/.hermes/.env carries a HERMES_MAX_ITERATIONS
value that disagrees with agent.max_turns in config.yaml, and 'hermes doctor
--fix' removes the stale .env line so config.yaml is authoritative. 'hermes
config show' surfaces the same drift inline under Max turns.

The setup wizard stopped dual-writing this value, but users who edited only
config.yaml from a pre-fix install keep a .env ghost. The gateway bridge
normally overrides it at startup, but if the bridge bails on any earlier
config-parse error the ghost silently wins — config says 400 while the
gateway activity line reads N/90.

The detector reads the .env FILE directly (load_env), not get_env_value/
os.environ, since the startup bridge may already have overwritten os.environ
with the config value.

Closes #17534.

* fix(config): stop offering HERMES_MAX_ITERATIONS as an editable env var

Removes HERMES_MAX_ITERATIONS from OPTIONAL_ENV_VARS so the dashboard env
editor (PUT /api/env) and any env-var prompt no longer let a user write it
to .env — which would recreate the stale ghost that shadows config.yaml's
agent.max_turns (issue #17534). The iteration budget is configured only via
config.yaml; the env var stays a read-only backward-compat fallback in the
gateway/CLI, never a promoted write target.

Regression test asserts it is absent from OPTIONAL_ENV_VARS.
This commit is contained in:
Teknium
2026-06-03 06:38:40 -07:00
committed by GitHub
parent de26b17854
commit 6ee046a72f
4 changed files with 168 additions and 8 deletions
+15 -8
View File
@@ -3346,13 +3346,6 @@ OPTIONAL_ENV_VARS = {
"password": True,
"category": "setting",
},
"HERMES_MAX_ITERATIONS": {
"description": "Maximum tool-calling iterations per conversation (default: 90)",
"prompt": "Max iterations",
"url": None,
"password": False,
"category": "setting",
},
# HERMES_TOOL_PROGRESS and HERMES_TOOL_PROGRESS_MODE are deprecated —
# now configured via display.tool_progress in config.yaml (off|new|all|verbose).
# Gateway falls back to these env vars for backward compatibility.
@@ -5593,7 +5586,21 @@ def show_config():
print()
print(color("◆ Model", Colors.CYAN, Colors.BOLD))
print(f" Model: {config.get('model', 'not set')}")
print(f" Max turns: {config.get('agent', {}).get('max_turns', DEFAULT_CONFIG['agent']['max_turns'])}")
_cfg_max_turns = config.get('agent', {}).get('max_turns', DEFAULT_CONFIG['agent']['max_turns'])
print(f" Max turns: {_cfg_max_turns}")
# Warn on stale HERMES_MAX_ITERATIONS ghost in .env that disagrees with
# config.yaml (issue #17534). Read the .env FILE directly so we catch the
# ghost even when the gateway bridge already overrode os.environ.
try:
_env_ghost = load_env().get("HERMES_MAX_ITERATIONS")
if _env_ghost is not None and str(_env_ghost).strip() != str(_cfg_max_turns).strip():
print(color(
f" ⚠ .env has stale HERMES_MAX_ITERATIONS={_env_ghost} "
f"(run 'hermes doctor --fix' to remove)",
Colors.YELLOW,
))
except Exception:
pass
# Display
print()