fix(tests): isolate model-selection env vars so the suite passes on any runner (#6395)

The suite failed 6 tests (test_sprint12 default-model, test_issue1538 Nous
catalog, test_issue1567 picker capacity/symmetry) whenever it ran on a box that
exports HERMES_MODEL (e.g. inside a live Hermes agent session where HERMES_MODEL
is the agent's runtime model). Root cause: get_effective_default_model() in
api/config.py treats HERMES_MODEL / OPENAI_MODEL / LLM_MODEL as the
highest-priority default-model source — above the isolated test config — so a
runner-exported value overrode the sandbox config and polluted the model
picker/catalog (e.g. injecting "opus-4.8" and breaking the @nous: prefix
invariant / default-model readback).

Fix: scrub the three model-selection env vars at conftest module level (before
any product module imports, covering in-process tests) and again in the
out-of-process test_server subprocess env, and add them to the per-test
_scrub_provider_env helpers in the two Nous test modules. The isolated config /
HERMES_WEBUI_DEFAULT_MODEL is now authoritative regardless of the runner env.

Verified: with HERMES_MODEL=opus-4.8 set, the full suite goes from 6 failed to
0 failed (13550 passed); non-vacuity confirmed (disabling the scrub reproduces
the failures).

Co-authored-by: nesquena-hermes <agent@nesquena-hermes>

tests/conftest.py

@@ -181,6 +181,20 @@ os.environ['HERMES_BASE_HOME'] = str(TEST_STATE_DIR)
 # tests that read/write config.yaml stay inside the isolated test home.
 os.environ['HERMES_CONFIG_PATH'] = str(TEST_STATE_DIR / 'config.yaml')
 
+# Model-selection env overrides must NOT leak from the runner into tests.
+# get_effective_default_model() (api/config.py) treats HERMES_MODEL / OPENAI_MODEL
+# / LLM_MODEL as the highest-priority default-model source — above the isolated
+# test config. When the pytest process runs inside a live Hermes agent session,
+# HERMES_MODEL is exported to the agent's runtime model (e.g. "opus-4.8"), which
+# then overrides the sandbox config and pollutes the model picker/catalog. That
+# broke test_sprint12 (default-model readback), test_issue1538 (Nous @nous:
+# prefix invariant) and test_issue1567 (picker capacity/symmetry) whenever the
+# suite ran on a box with HERMES_MODEL set. Strip them at module level so the
+# isolated config is authoritative for the pytest process; the out-of-process
+# test server env is scrubbed identically in the test_server fixture below.
+for _model_env in ('HERMES_MODEL', 'OPENAI_MODEL', 'LLM_MODEL'):
+    os.environ.pop(_model_env, None)
+
 
 @pytest.fixture(autouse=True)
 def _isolate_hermes_config_path():
@@ -987,6 +1001,13 @@ def test_server():
     for _k in list(env):
         if any(_k.startswith(p) for p in _CRED_ENV_PREFIXES):
             del env[_k]
+    # Model-selection overrides must not reach the test server either. They are
+    # already popped from the pytest process env at module level, but strip them
+    # explicitly here so the subprocess default model comes only from the isolated
+    # config / HERMES_WEBUI_DEFAULT_MODEL below — never a runner-exported
+    # HERMES_MODEL (get_effective_default_model gives these env vars top priority).
+    for _model_env in ('HERMES_MODEL', 'OPENAI_MODEL', 'LLM_MODEL'):
+        env.pop(_model_env, None)
     # Belt-and-suspenders: keep IMDS disabled in the spawn env too (we set it
     # at module level above for the pytest process, but make it explicit here
     # so it's never accidentally cleared by an env.update later).

tests/test_issue1538_nous_live_catalog.py

@@ -129,6 +129,12 @@ def _scrub_provider_env(monkeypatch):
         "XIAOMI_API_KEY",
         "OPENCODE_ZEN_API_KEY", "OPENCODE_GO_API_KEY",
         "NOUS_API_KEY", "NVIDIA_API_KEY", "LM_API_KEY", "LMSTUDIO_API_KEY",
+        # Model-selection overrides: get_effective_default_model() treats these
+        # as the highest-priority default-model source, above config. A runner
+        # that exports HERMES_MODEL (e.g. a live agent session set to "opus-4.8")
+        # injects that id into the picker/catalog and breaks the @nous: prefix
+        # invariant below. Scrub so detection sees only the installed stubs.
+        "HERMES_MODEL", "OPENAI_MODEL", "LLM_MODEL",
     ):
         monkeypatch.delenv(var, raising=False)
 

tests/test_issue1567_nous_picker_capacity_and_symmetry.py

@@ -130,6 +130,11 @@ def _scrub_provider_env(monkeypatch):
         "XIAOMI_API_KEY",
         "OPENCODE_ZEN_API_KEY", "OPENCODE_GO_API_KEY",
         "NOUS_API_KEY", "NVIDIA_API_KEY", "LM_API_KEY", "LMSTUDIO_API_KEY",
+        # Model-selection overrides: get_effective_default_model() treats these
+        # as the highest-priority default-model source, above config. A runner
+        # exporting HERMES_MODEL (e.g. a live agent session on "opus-4.8") injects
+        # that id into the picker/catalog and breaks capacity/symmetry assertions.
+        "HERMES_MODEL", "OPENAI_MODEL", "LLM_MODEL",
     ):
         monkeypatch.delenv(var, raising=False)