fix: provider/model resolution — salvage 4 PRs + MiniMax aux URL fix (#5983)

Salvaged fixes from community PRs:

- fix(model_switch): _read_auth_store → _load_auth_store + fix auth store
  key lookup (was checking top-level dict instead of store['providers']).
  OAuth providers now correctly detected in /model picker.
  Cherry-picked from PR #5911 by Xule Lin (linxule).

- fix(ollama): pass num_ctx to override 2048 default context window.
  Ollama defaults to 2048 context regardless of model capabilities. Now
  auto-detects from /api/show metadata and injects num_ctx into every
  request. Config override via model.ollama_num_ctx. Fixes #2708.
  Cherry-picked from PR #5929 by kshitij (kshitijk4poor).

- fix(aux): normalize provider aliases for vision/auxiliary routing.
  Adds _normalize_aux_provider() with 17 aliases (google→gemini,
  claude→anthropic, glm→zai, etc). Fixes vision routing failure when
  provider is set to 'google' instead of 'gemini'.
  Cherry-picked from PR #5793 by e11i (Elizabeth1979).

- fix(aux): rewrite MiniMax /anthropic base URLs to /v1 for OpenAI SDK.
  MiniMax's inference_base_url ends in /anthropic (Anthropic Messages API),
  but auxiliary client uses OpenAI SDK which appends /chat/completions →
  404 at /anthropic/chat/completions. Generic _to_openai_base_url() helper
  rewrites terminal /anthropic to /v1 for OpenAI-compatible endpoint.
  Inspired by PR #5786 by Lempkey.

Added debug logging to silent exception blocks across all fixes.

Co-authored-by: Hermes Agent <hermes@nousresearch.com>
This commit is contained in:
Teknium 2026-04-07 22:23:28 -07:00 committed by GitHub
parent 8d7a98d2ff
commit 5c03f2e7cc
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
7 changed files with 378 additions and 31 deletions

View file

@ -471,6 +471,23 @@ class TestExplicitProviderRouting:
client, model = resolve_provider_client("zai")
assert client is not None
def test_explicit_google_alias_uses_gemini_credentials(self):
"""provider='google' should route through the gemini API-key provider."""
with (
patch("hermes_cli.auth.resolve_api_key_provider_credentials", return_value={
"api_key": "gemini-key",
"base_url": "https://generativelanguage.googleapis.com/v1beta/openai",
}),
patch("agent.auxiliary_client.OpenAI") as mock_openai,
):
mock_openai.return_value = MagicMock()
client, model = resolve_provider_client("google", model="gemini-3.1-pro-preview")
assert client is not None
assert model == "gemini-3.1-pro-preview"
assert mock_openai.call_args.kwargs["api_key"] == "gemini-key"
assert mock_openai.call_args.kwargs["base_url"] == "https://generativelanguage.googleapis.com/v1beta/openai"
def test_explicit_unknown_returns_none(self, monkeypatch):
"""Unknown provider should return None."""
client, model = resolve_provider_client("nonexistent-provider")
@ -822,6 +839,31 @@ class TestAuxiliaryPoolAwareness:
assert model == "google/gemini-3-flash-preview"
assert client is not None
def test_vision_config_google_provider_uses_gemini_credentials(self, monkeypatch):
config = {
"auxiliary": {
"vision": {
"provider": "google",
"model": "gemini-3.1-pro-preview",
}
}
}
monkeypatch.setattr("hermes_cli.config.load_config", lambda: config)
with (
patch("hermes_cli.auth.resolve_api_key_provider_credentials", return_value={
"api_key": "gemini-key",
"base_url": "https://generativelanguage.googleapis.com/v1beta/openai",
}),
patch("agent.auxiliary_client.OpenAI") as mock_openai,
):
resolved_provider, client, model = resolve_vision_provider_client()
assert resolved_provider == "gemini"
assert client is not None
assert model == "gemini-3.1-pro-preview"
assert mock_openai.call_args.kwargs["api_key"] == "gemini-key"
assert mock_openai.call_args.kwargs["base_url"] == "https://generativelanguage.googleapis.com/v1beta/openai"
def test_vision_forced_main_uses_custom_endpoint(self, monkeypatch):
"""When explicitly forced to 'main', vision CAN use custom endpoint."""
config = {