Merge pull request #1323 from NousResearch/hermes/hermes-1fc28d17
fix: smart vision setup that respects the user's chosen provider
This commit is contained in:
Teknium
GitHub
commit
14738e0872
2 changed files with 204 additions and 35 deletions
|
|
@ -460,12 +460,41 @@ def _print_setup_summary(config: dict, hermes_home):
|
|||
|
||||
tool_status = []
|
||||
|
||||
# OpenRouter (required for vision, moa)
|
||||
# Vision — works with OpenRouter, Nous OAuth, Codex OAuth, or OpenAI endpoint
|
||||
_has_vision = False
|
||||
if get_env_value("OPENROUTER_API_KEY"):
|
||||
_has_vision = True
|
||||
else:
|
||||
try:
|
||||
_vauth_path = Path(os.environ.get("HERMES_HOME", Path.home() / ".hermes")) / "auth.json"
|
||||
if _vauth_path.is_file():
|
||||
import json as _vjson
|
||||
|
||||
_vauth = _vjson.loads(_vauth_path.read_text())
|
||||
if _vauth.get("active_provider") == "nous":
|
||||
_np = _vauth.get("providers", {}).get("nous", {})
|
||||
if _np.get("agent_key") or _np.get("access_token"):
|
||||
_has_vision = True
|
||||
elif _vauth.get("active_provider") == "openai-codex":
|
||||
_cp = _vauth.get("providers", {}).get("openai-codex", {})
|
||||
if _cp.get("tokens", {}).get("access_token"):
|
||||
_has_vision = True
|
||||
except Exception:
|
||||
pass
|
||||
if not _has_vision:
|
||||
_oai_base = get_env_value("OPENAI_BASE_URL") or ""
|
||||
if get_env_value("OPENAI_API_KEY") and "api.openai.com" in _oai_base.lower():
|
||||
_has_vision = True
|
||||
|
||||
if _has_vision:
|
||||
tool_status.append(("Vision (image analysis)", True, None))
|
||||
else:
|
||||
tool_status.append(("Vision (image analysis)", False, "run 'hermes setup' to configure"))
|
||||
|
||||
# Mixture of Agents — requires OpenRouter specifically (calls multiple models)
|
||||
if get_env_value("OPENROUTER_API_KEY"):
|
||||
tool_status.append(("Mixture of Agents", True, None))
|
||||
else:
|
||||
tool_status.append(("Vision (image analysis)", False, "OPENROUTER_API_KEY"))
|
||||
tool_status.append(("Mixture of Agents", False, "OPENROUTER_API_KEY"))
|
||||
|
||||
# Firecrawl (web tools)
|
||||
|
|
@ -1246,35 +1275,112 @@ def setup_model_provider(config: dict):
|
|||
elif existing_or:
|
||||
selected_provider = "openrouter"
|
||||
|
||||
# ── OpenRouter API Key for tools (if not already set) ──
|
||||
# Tools (vision, web, MoA) use OpenRouter independently of the main provider.
|
||||
# Prompt for OpenRouter key if not set and a non-OpenRouter provider was chosen.
|
||||
if selected_provider in (
|
||||
"nous",
|
||||
"openai-codex",
|
||||
"custom",
|
||||
"zai",
|
||||
"kimi-coding",
|
||||
"minimax",
|
||||
"minimax-cn",
|
||||
"anthropic",
|
||||
) and not get_env_value("OPENROUTER_API_KEY"):
|
||||
print()
|
||||
print_header("OpenRouter API Key (for tools)")
|
||||
print_info("Tools like vision analysis, web search, and MoA use OpenRouter")
|
||||
print_info("independently of your main inference provider.")
|
||||
print_info("Get your API key at: https://openrouter.ai/keys")
|
||||
# ── Vision & Image Analysis Setup ──
|
||||
# Vision requires a multimodal-capable provider. Check whether the user's
|
||||
# chosen provider already covers it — if so, skip the prompt entirely.
|
||||
_vision_needs_setup = True
|
||||
|
||||
api_key = prompt(
|
||||
" OpenRouter API key (optional, press Enter to skip)", password=True
|
||||
)
|
||||
if api_key:
|
||||
save_env_value("OPENROUTER_API_KEY", api_key)
|
||||
print_success("OpenRouter API key saved (for tools)")
|
||||
else:
|
||||
print_info(
|
||||
"Skipped - some tools (vision, web scraping) won't work without this"
|
||||
if selected_provider == "openrouter":
|
||||
# OpenRouter → Gemini for vision, already configured
|
||||
_vision_needs_setup = False
|
||||
elif selected_provider == "nous":
|
||||
# Nous Portal OAuth → Gemini via Nous, already configured
|
||||
_vision_needs_setup = False
|
||||
elif selected_provider == "openai-codex":
|
||||
# Codex OAuth → gpt-5.3-codex supports vision
|
||||
_vision_needs_setup = False
|
||||
elif selected_provider == "custom":
|
||||
_custom_base = (get_env_value("OPENAI_BASE_URL") or "").lower()
|
||||
if "api.openai.com" in _custom_base:
|
||||
# Direct OpenAI endpoint — show vision model picker
|
||||
print()
|
||||
print_header("Vision Model")
|
||||
print_info("Your OpenAI endpoint supports vision. Pick a model for image analysis:")
|
||||
_oai_vision_models = ["gpt-4o", "gpt-4o-mini", "gpt-4.1", "gpt-4.1-mini", "gpt-4.1-nano"]
|
||||
_vm_choices = _oai_vision_models + ["Keep default (gpt-4o-mini)"]
|
||||
_vm_idx = prompt_choice("Select vision model:", _vm_choices, len(_vm_choices) - 1)
|
||||
_selected_vision_model = (
|
||||
_oai_vision_models[_vm_idx]
|
||||
if _vm_idx < len(_oai_vision_models)
|
||||
else "gpt-4o-mini"
|
||||
)
|
||||
save_env_value("AUXILIARY_VISION_MODEL", _selected_vision_model)
|
||||
print_success(f"Vision model set to {_selected_vision_model}")
|
||||
_vision_needs_setup = False
|
||||
|
||||
# Even for providers without native vision, check if existing credentials
|
||||
# from a previous setup already cover it (e.g. user had OpenRouter before
|
||||
# switching to z.ai)
|
||||
if _vision_needs_setup:
|
||||
if get_env_value("OPENROUTER_API_KEY"):
|
||||
_vision_needs_setup = False
|
||||
else:
|
||||
# Check for Nous Portal OAuth in auth.json
|
||||
try:
|
||||
_auth_path = Path(os.environ.get("HERMES_HOME", Path.home() / ".hermes")) / "auth.json"
|
||||
if _auth_path.is_file():
|
||||
import json as _json
|
||||
|
||||
_auth_data = _json.loads(_auth_path.read_text())
|
||||
if _auth_data.get("active_provider") == "nous":
|
||||
_nous_p = _auth_data.get("providers", {}).get("nous", {})
|
||||
if _nous_p.get("agent_key") or _nous_p.get("access_token"):
|
||||
_vision_needs_setup = False
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
if _vision_needs_setup:
|
||||
_prov_names = {
|
||||
"nous-api": "Nous Portal API key",
|
||||
"zai": "Z.AI / GLM",
|
||||
"kimi-coding": "Kimi / Moonshot",
|
||||
"minimax": "MiniMax",
|
||||
"minimax-cn": "MiniMax CN",
|
||||
"anthropic": "Anthropic",
|
||||
"custom": "your custom endpoint",
|
||||
}
|
||||
_prov_display = _prov_names.get(selected_provider, selected_provider or "your provider")
|
||||
|
||||
print()
|
||||
print_header("Vision & Image Analysis (optional)")
|
||||
print_info(f"Vision requires a multimodal-capable provider. {_prov_display}")
|
||||
print_info("doesn't natively support it. Choose how to enable vision,")
|
||||
print_info("or skip to configure later.")
|
||||
print()
|
||||
|
||||
_vision_choices = [
|
||||
"OpenRouter — uses Gemini (free tier at openrouter.ai/keys)",
|
||||
"OpenAI — enter API key & choose a vision model",
|
||||
"Skip for now",
|
||||
]
|
||||
_vision_idx = prompt_choice("Configure vision:", _vision_choices, 2)
|
||||
|
||||
if _vision_idx == 0: # OpenRouter
|
||||
_or_key = prompt(" OpenRouter API key", password=True)
|
||||
if _or_key:
|
||||
save_env_value("OPENROUTER_API_KEY", _or_key)
|
||||
print_success("OpenRouter key saved — vision will use Gemini")
|
||||
else:
|
||||
print_info("Skipped — vision won't be available")
|
||||
elif _vision_idx == 1: # OpenAI
|
||||
_oai_key = prompt(" OpenAI API key", password=True)
|
||||
if _oai_key:
|
||||
save_env_value("OPENAI_API_KEY", _oai_key)
|
||||
save_env_value("OPENAI_BASE_URL", "https://api.openai.com/v1")
|
||||
_oai_vision_models = ["gpt-4o", "gpt-4o-mini", "gpt-4.1", "gpt-4.1-mini", "gpt-4.1-nano"]
|
||||
_vm_choices = _oai_vision_models + ["Use default (gpt-4o-mini)"]
|
||||
_vm_idx = prompt_choice("Select vision model:", _vm_choices, 0)
|
||||
_selected_vision_model = (
|
||||
_oai_vision_models[_vm_idx]
|
||||
if _vm_idx < len(_oai_vision_models)
|
||||
else "gpt-4o-mini"
|
||||
)
|
||||
save_env_value("AUXILIARY_VISION_MODEL", _selected_vision_model)
|
||||
print_success(f"Vision configured with OpenAI ({_selected_vision_model})")
|
||||
else:
|
||||
print_info("Skipped — vision won't be available")
|
||||
else:
|
||||
print_info("Skipped — add later with 'hermes config set OPENROUTER_API_KEY ...'")
|
||||
|
||||
# ── Model Selection (adapts based on provider) ──
|
||||
if selected_provider != "custom": # Custom already prompted for model name
|
||||
|
|
|
|||
|
|
@ -3,7 +3,7 @@
|
|||
from __future__ import annotations
|
||||
|
||||
from hermes_cli.config import load_config, save_config, save_env_value
|
||||
from hermes_cli.setup import setup_model_provider
|
||||
from hermes_cli.setup import _print_setup_summary, setup_model_provider
|
||||
|
||||
|
||||
def _read_env(home):
|
||||
|
|
@ -50,11 +50,15 @@ def test_setup_keep_current_custom_from_config_does_not_fall_through(tmp_path, m
|
|||
|
||||
calls = {"count": 0}
|
||||
|
||||
def fake_prompt_choice(_question, choices, default=0):
|
||||
def fake_prompt_choice(question, choices, default=0):
|
||||
calls["count"] += 1
|
||||
if calls["count"] == 1:
|
||||
assert choices[-1] == "Keep current (Custom: https://example.invalid/v1)"
|
||||
return len(choices) - 1
|
||||
if calls["count"] == 2:
|
||||
assert question == "Configure vision:"
|
||||
assert choices[-1] == "Skip for now"
|
||||
return len(choices) - 1
|
||||
raise AssertionError("Model menu should not appear for keep-current custom")
|
||||
|
||||
monkeypatch.setattr("hermes_cli.setup.prompt_choice", fake_prompt_choice)
|
||||
|
|
@ -70,7 +74,7 @@ def test_setup_keep_current_custom_from_config_does_not_fall_through(tmp_path, m
|
|||
assert reloaded["model"]["provider"] == "custom"
|
||||
assert reloaded["model"]["default"] == "custom/model"
|
||||
assert reloaded["model"]["base_url"] == "https://example.invalid/v1"
|
||||
assert calls["count"] == 1
|
||||
assert calls["count"] == 2
|
||||
|
||||
|
||||
def test_setup_keep_current_config_provider_uses_provider_specific_model_menu(tmp_path, monkeypatch):
|
||||
|
|
@ -88,13 +92,17 @@ def test_setup_keep_current_config_provider_uses_provider_specific_model_menu(tm
|
|||
captured = {"provider_choices": None, "model_choices": None}
|
||||
calls = {"count": 0}
|
||||
|
||||
def fake_prompt_choice(_question, choices, default=0):
|
||||
def fake_prompt_choice(question, choices, default=0):
|
||||
calls["count"] += 1
|
||||
if calls["count"] == 1:
|
||||
captured["provider_choices"] = list(choices)
|
||||
assert choices[-1] == "Keep current (Anthropic)"
|
||||
return len(choices) - 1
|
||||
if calls["count"] == 2:
|
||||
assert question == "Configure vision:"
|
||||
assert choices[-1] == "Skip for now"
|
||||
return len(choices) - 1
|
||||
if calls["count"] == 3:
|
||||
captured["model_choices"] = list(choices)
|
||||
return len(choices) - 1 # keep current model
|
||||
raise AssertionError("Unexpected extra prompt_choice call")
|
||||
|
|
@ -113,7 +121,43 @@ def test_setup_keep_current_config_provider_uses_provider_specific_model_menu(tm
|
|||
assert captured["model_choices"] is not None
|
||||
assert captured["model_choices"][0] == "claude-opus-4-6"
|
||||
assert "anthropic/claude-opus-4.6 (recommended)" not in captured["model_choices"]
|
||||
assert calls["count"] == 2
|
||||
assert calls["count"] == 3
|
||||
|
||||
|
||||
def test_setup_keep_current_anthropic_can_configure_openai_vision_default(tmp_path, monkeypatch):
|
||||
monkeypatch.setenv("HERMES_HOME", str(tmp_path))
|
||||
_clear_provider_env(monkeypatch)
|
||||
|
||||
config = load_config()
|
||||
config["model"] = {
|
||||
"default": "claude-opus-4-6",
|
||||
"provider": "anthropic",
|
||||
}
|
||||
save_config(config)
|
||||
|
||||
picks = iter([
|
||||
9, # keep current provider
|
||||
1, # configure vision with OpenAI
|
||||
5, # use default gpt-4o-mini vision model
|
||||
4, # keep current Anthropic model
|
||||
])
|
||||
|
||||
monkeypatch.setattr("hermes_cli.setup.prompt_choice", lambda *args, **kwargs: next(picks))
|
||||
monkeypatch.setattr(
|
||||
"hermes_cli.setup.prompt",
|
||||
lambda message, *args, **kwargs: "sk-openai" if "OpenAI API key" in message else "",
|
||||
)
|
||||
monkeypatch.setattr("hermes_cli.setup.prompt_yes_no", lambda *args, **kwargs: False)
|
||||
monkeypatch.setattr("hermes_cli.auth.get_active_provider", lambda: None)
|
||||
monkeypatch.setattr("hermes_cli.auth.detect_external_credentials", lambda: [])
|
||||
monkeypatch.setattr("hermes_cli.models.provider_model_ids", lambda provider: [])
|
||||
|
||||
setup_model_provider(config)
|
||||
env = _read_env(tmp_path)
|
||||
|
||||
assert env.get("OPENAI_API_KEY") == "sk-openai"
|
||||
assert env.get("OPENAI_BASE_URL") == "https://api.openai.com/v1"
|
||||
assert env.get("AUXILIARY_VISION_MODEL") == "gpt-4o-mini"
|
||||
|
||||
|
||||
def test_setup_switch_custom_to_codex_clears_custom_endpoint_and_updates_config(tmp_path, monkeypatch):
|
||||
|
|
@ -144,7 +188,7 @@ def test_setup_switch_custom_to_codex_clears_custom_endpoint_and_updates_config(
|
|||
"hermes_cli.auth.resolve_codex_runtime_credentials",
|
||||
lambda *args, **kwargs: {
|
||||
"base_url": "https://chatgpt.com/backend-api/codex",
|
||||
"api_key": "codex-access-token",
|
||||
"api_key": "codex-...oken",
|
||||
},
|
||||
)
|
||||
monkeypatch.setattr(
|
||||
|
|
@ -163,3 +207,22 @@ def test_setup_switch_custom_to_codex_clears_custom_endpoint_and_updates_config(
|
|||
assert reloaded["model"]["provider"] == "openai-codex"
|
||||
assert reloaded["model"]["default"] == "openai/gpt-5.3-codex"
|
||||
assert reloaded["model"]["base_url"] == "https://chatgpt.com/backend-api/codex"
|
||||
|
||||
|
||||
def test_setup_summary_marks_codex_auth_as_vision_available(tmp_path, monkeypatch, capsys):
|
||||
monkeypatch.setenv("HERMES_HOME", str(tmp_path))
|
||||
_clear_provider_env(monkeypatch)
|
||||
|
||||
(tmp_path / "auth.json").write_text(
|
||||
'{"active_provider":"openai-codex","providers":{"openai-codex":{"tokens":{"access_token":"tok"}}}}'
|
||||
)
|
||||
|
||||
monkeypatch.setattr("shutil.which", lambda _name: None)
|
||||
|
||||
_print_setup_summary(load_config(), tmp_path)
|
||||
output = capsys.readouterr().out
|
||||
|
||||
assert "Vision (image analysis)" in output
|
||||
assert "missing run 'hermes setup' to configure" not in output
|
||||
assert "Mixture of Agents" in output
|
||||
assert "missing OPENROUTER_API_KEY" in output
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue