Merge branch 'main' into rewbs/tool-use-charge-to-subscription

This commit is contained in:
Robin Fernandes
2026-03-31 08:48:54 +09:00
269 changed files with 33678 additions and 2273 deletions

View File

@@ -11,6 +11,7 @@ from agent.auxiliary_client import (
get_text_auxiliary_client,
get_vision_auxiliary_client,
get_available_vision_backends,
resolve_vision_provider_client,
resolve_provider_client,
auxiliary_max_tokens_param,
_read_codex_access_token,
@@ -490,15 +491,17 @@ class TestGetTextAuxiliaryClient:
assert mock_openai.call_args.kwargs["base_url"] == "http://localhost:2345/v1"
assert mock_openai.call_args.kwargs["api_key"] == "task-key"
def test_task_direct_endpoint_without_openai_key_does_not_fall_back(self, monkeypatch):
def test_task_direct_endpoint_without_openai_key_uses_placeholder(self, monkeypatch):
"""Local endpoints without an API key should use 'no-key-required' placeholder."""
monkeypatch.setenv("OPENROUTER_API_KEY", "or-key")
monkeypatch.setenv("AUXILIARY_WEB_EXTRACT_BASE_URL", "http://localhost:2345/v1")
monkeypatch.setenv("AUXILIARY_WEB_EXTRACT_MODEL", "task-model")
with patch("agent.auxiliary_client.OpenAI") as mock_openai:
client, model = get_text_auxiliary_client("web_extract")
assert client is None
assert model is None
mock_openai.assert_not_called()
assert client is not None
assert model == "task-model"
assert mock_openai.call_args.kwargs["api_key"] == "no-key-required"
assert mock_openai.call_args.kwargs["base_url"] == "http://localhost:2345/v1"
def test_custom_endpoint_uses_config_saved_base_url(self, monkeypatch):
config = {
@@ -638,6 +641,30 @@ class TestVisionClientFallback:
assert client.__class__.__name__ == "AnthropicAuxiliaryClient"
assert model == "claude-haiku-4-5-20251001"
def test_selected_codex_provider_short_circuits_vision_auto(self, monkeypatch):
def fake_load_config():
return {"model": {"provider": "openai-codex", "default": "gpt-5.2-codex"}}
codex_client = MagicMock()
with (
patch("hermes_cli.config.load_config", fake_load_config),
patch("agent.auxiliary_client._try_codex", return_value=(codex_client, "gpt-5.2-codex")) as mock_codex,
patch("agent.auxiliary_client._try_openrouter") as mock_openrouter,
patch("agent.auxiliary_client._try_nous") as mock_nous,
patch("agent.auxiliary_client._try_anthropic") as mock_anthropic,
patch("agent.auxiliary_client._try_custom_endpoint") as mock_custom,
):
provider, client, model = resolve_vision_provider_client()
assert provider == "openai-codex"
assert client is codex_client
assert model == "gpt-5.2-codex"
mock_codex.assert_called_once()
mock_openrouter.assert_not_called()
mock_nous.assert_not_called()
mock_anthropic.assert_not_called()
mock_custom.assert_not_called()
def test_vision_auto_includes_codex(self, codex_auth_dir):
"""Codex supports vision (gpt-5.3-codex), so auto mode should use it."""
with patch("agent.auxiliary_client._read_nous_auth", return_value=None), \
@@ -671,15 +698,16 @@ class TestVisionClientFallback:
assert mock_openai.call_args.kwargs["base_url"] == "http://localhost:4567/v1"
assert mock_openai.call_args.kwargs["api_key"] == "vision-key"
def test_vision_direct_endpoint_requires_openai_api_key(self, monkeypatch):
def test_vision_direct_endpoint_without_key_uses_placeholder(self, monkeypatch):
"""Vision endpoint without API key should use 'no-key-required' placeholder."""
monkeypatch.setenv("OPENROUTER_API_KEY", "or-key")
monkeypatch.setenv("AUXILIARY_VISION_BASE_URL", "http://localhost:4567/v1")
monkeypatch.setenv("AUXILIARY_VISION_MODEL", "vision-model")
with patch("agent.auxiliary_client.OpenAI") as mock_openai:
client, model = get_vision_auxiliary_client()
assert client is None
assert model is None
mock_openai.assert_not_called()
assert client is not None
assert model == "vision-model"
assert mock_openai.call_args.kwargs["api_key"] == "no-key-required"
def test_vision_uses_openrouter_when_available(self, monkeypatch):
monkeypatch.setenv("OPENROUTER_API_KEY", "or-key")

View File

@@ -0,0 +1,157 @@
"""Tests for external skill directories (skills.external_dirs config)."""
import json
import os
from pathlib import Path
from unittest.mock import patch
import pytest
@pytest.fixture
def external_skills_dir(tmp_path):
"""Create a temp dir with a sample external skill."""
ext_dir = tmp_path / "external-skills"
skill_dir = ext_dir / "my-external-skill"
skill_dir.mkdir(parents=True)
(skill_dir / "SKILL.md").write_text(
"---\nname: my-external-skill\ndescription: A skill from an external directory\n---\n\n# My External Skill\n\nDo external things.\n"
)
return ext_dir
@pytest.fixture
def hermes_home(tmp_path):
"""Create a minimal HERMES_HOME with config."""
home = tmp_path / ".hermes"
home.mkdir()
(home / "skills").mkdir()
return home
class TestGetExternalSkillsDirs:
def test_empty_config(self, hermes_home):
(hermes_home / "config.yaml").write_text("skills:\n external_dirs: []\n")
with patch.dict(os.environ, {"HERMES_HOME": str(hermes_home)}):
from agent.skill_utils import get_external_skills_dirs
result = get_external_skills_dirs()
assert result == []
def test_nonexistent_dir_skipped(self, hermes_home):
(hermes_home / "config.yaml").write_text(
"skills:\n external_dirs:\n - /nonexistent/path\n"
)
with patch.dict(os.environ, {"HERMES_HOME": str(hermes_home)}):
from agent.skill_utils import get_external_skills_dirs
result = get_external_skills_dirs()
assert result == []
def test_valid_dir_returned(self, hermes_home, external_skills_dir):
(hermes_home / "config.yaml").write_text(
f"skills:\n external_dirs:\n - {external_skills_dir}\n"
)
with patch.dict(os.environ, {"HERMES_HOME": str(hermes_home)}):
from agent.skill_utils import get_external_skills_dirs
result = get_external_skills_dirs()
assert len(result) == 1
assert result[0] == external_skills_dir.resolve()
def test_duplicate_dirs_deduplicated(self, hermes_home, external_skills_dir):
(hermes_home / "config.yaml").write_text(
f"skills:\n external_dirs:\n - {external_skills_dir}\n - {external_skills_dir}\n"
)
with patch.dict(os.environ, {"HERMES_HOME": str(hermes_home)}):
from agent.skill_utils import get_external_skills_dirs
result = get_external_skills_dirs()
assert len(result) == 1
def test_local_skills_dir_excluded(self, hermes_home):
local_skills = hermes_home / "skills"
(hermes_home / "config.yaml").write_text(
f"skills:\n external_dirs:\n - {local_skills}\n"
)
with patch.dict(os.environ, {"HERMES_HOME": str(hermes_home)}):
from agent.skill_utils import get_external_skills_dirs
result = get_external_skills_dirs()
assert result == []
def test_no_config_file(self, hermes_home):
# No config.yaml at all
with patch.dict(os.environ, {"HERMES_HOME": str(hermes_home)}):
from agent.skill_utils import get_external_skills_dirs
result = get_external_skills_dirs()
assert result == []
def test_string_value_converted_to_list(self, hermes_home, external_skills_dir):
(hermes_home / "config.yaml").write_text(
f"skills:\n external_dirs: {external_skills_dir}\n"
)
with patch.dict(os.environ, {"HERMES_HOME": str(hermes_home)}):
from agent.skill_utils import get_external_skills_dirs
result = get_external_skills_dirs()
assert len(result) == 1
class TestGetAllSkillsDirs:
def test_local_always_first(self, hermes_home, external_skills_dir):
(hermes_home / "config.yaml").write_text(
f"skills:\n external_dirs:\n - {external_skills_dir}\n"
)
with patch.dict(os.environ, {"HERMES_HOME": str(hermes_home)}):
from agent.skill_utils import get_all_skills_dirs
result = get_all_skills_dirs()
assert result[0] == hermes_home / "skills"
assert result[1] == external_skills_dir.resolve()
class TestExternalSkillsInFindAll:
def test_external_skills_found(self, hermes_home, external_skills_dir):
(hermes_home / "config.yaml").write_text(
f"skills:\n external_dirs:\n - {external_skills_dir}\n"
)
local_skills = hermes_home / "skills"
with (
patch.dict(os.environ, {"HERMES_HOME": str(hermes_home)}),
patch("tools.skills_tool.SKILLS_DIR", local_skills),
):
from tools.skills_tool import _find_all_skills
skills = _find_all_skills()
names = [s["name"] for s in skills]
assert "my-external-skill" in names
def test_local_takes_precedence(self, hermes_home, external_skills_dir):
"""If the same skill name exists locally and externally, local wins."""
local_skills = hermes_home / "skills"
local_skill = local_skills / "my-external-skill"
local_skill.mkdir(parents=True)
(local_skill / "SKILL.md").write_text(
"---\nname: my-external-skill\ndescription: Local version\n---\n\nLocal.\n"
)
(hermes_home / "config.yaml").write_text(
f"skills:\n external_dirs:\n - {external_skills_dir}\n"
)
with (
patch.dict(os.environ, {"HERMES_HOME": str(hermes_home)}),
patch("tools.skills_tool.SKILLS_DIR", local_skills),
):
from tools.skills_tool import _find_all_skills
skills = _find_all_skills()
matching = [s for s in skills if s["name"] == "my-external-skill"]
assert len(matching) == 1
assert matching[0]["description"] == "Local version"
class TestExternalSkillView:
def test_skill_view_finds_external(self, hermes_home, external_skills_dir):
(hermes_home / "config.yaml").write_text(
f"skills:\n external_dirs:\n - {external_skills_dir}\n"
)
local_skills = hermes_home / "skills"
with (
patch.dict(os.environ, {"HERMES_HOME": str(hermes_home)}),
patch("tools.skills_tool.SKILLS_DIR", local_skills),
):
from tools.skills_tool import skill_view
result = json.loads(skill_view("my-external-skill"))
assert result["success"] is True
assert "external things" in result["content"]

View File

@@ -21,6 +21,8 @@ from agent.prompt_builder import (
build_context_files_prompt,
CONTEXT_FILE_MAX_CHARS,
DEFAULT_AGENT_IDENTITY,
TOOL_USE_ENFORCEMENT_GUIDANCE,
TOOL_USE_ENFORCEMENT_MODELS,
MEMORY_GUIDANCE,
SESSION_SEARCH_GUIDANCE,
PLATFORM_HINTS,
@@ -196,7 +198,7 @@ class TestParseSkillFile:
)
from unittest.mock import patch
with patch("tools.skills_tool.sys") as mock_sys:
with patch("agent.skill_utils.sys") as mock_sys:
mock_sys.platform = "linux"
is_compat, _, _ = _parse_skill_file(skill_file)
assert is_compat is False
@@ -237,6 +239,14 @@ class TestPromptBuilderImports:
class TestBuildSkillsSystemPrompt:
@pytest.fixture(autouse=True)
def _clear_skills_cache(self):
"""Ensure the in-process skills prompt cache doesn't leak between tests."""
from agent.prompt_builder import clear_skills_system_prompt_cache
clear_skills_system_prompt_cache(clear_snapshot=True)
yield
clear_skills_system_prompt_cache(clear_snapshot=True)
def test_empty_when_no_skills_dir(self, monkeypatch, tmp_path):
monkeypatch.setenv("HERMES_HOME", str(tmp_path))
result = build_skills_system_prompt()
@@ -287,7 +297,7 @@ class TestBuildSkillsSystemPrompt:
from unittest.mock import patch
with patch("tools.skills_tool.sys") as mock_sys:
with patch("agent.skill_utils.sys") as mock_sys:
mock_sys.platform = "linux"
result = build_skills_system_prompt()
@@ -306,7 +316,7 @@ class TestBuildSkillsSystemPrompt:
from unittest.mock import patch
with patch("tools.skills_tool.sys") as mock_sys:
with patch("agent.skill_utils.sys") as mock_sys:
mock_sys.platform = "darwin"
result = build_skills_system_prompt()
@@ -334,7 +344,7 @@ class TestBuildSkillsSystemPrompt:
from unittest.mock import patch
with patch(
"tools.skills_tool._get_disabled_skill_names",
"agent.prompt_builder.get_disabled_skill_names",
return_value={"old-tool"},
):
result = build_skills_system_prompt()
@@ -621,6 +631,10 @@ class TestBuildContextFilesPrompt:
result = build_context_files_prompt(cwd=str(tmp_path))
assert "Lowercase claude rules" in result
@pytest.mark.skipif(
sys.platform == "darwin",
reason="APFS default volume is case-insensitive; CLAUDE.md and claude.md alias the same path",
)
def test_claude_md_uppercase_takes_priority(self, tmp_path):
uppercase = tmp_path / "CLAUDE.md"
lowercase = tmp_path / "claude.md"
@@ -868,6 +882,13 @@ class TestSkillShouldShow:
class TestBuildSkillsSystemPromptConditional:
@pytest.fixture(autouse=True)
def _clear_skills_cache(self):
from agent.prompt_builder import clear_skills_system_prompt_cache
clear_skills_system_prompt_cache(clear_snapshot=True)
yield
clear_skills_system_prompt_cache(clear_snapshot=True)
def test_fallback_skill_hidden_when_primary_available(self, monkeypatch, tmp_path):
monkeypatch.setenv("HERMES_HOME", str(tmp_path))
skill_dir = tmp_path / "skills" / "search" / "duckduckgo"
@@ -972,3 +993,98 @@ class TestBuildSkillsSystemPromptConditional:
available_toolsets=set(),
)
assert "nested-null" in result
# =========================================================================
# Tool-use enforcement guidance
# =========================================================================
class TestToolUseEnforcementGuidance:
def test_guidance_mentions_tool_calls(self):
assert "tool call" in TOOL_USE_ENFORCEMENT_GUIDANCE.lower()
def test_guidance_forbids_description_only(self):
assert "describe" in TOOL_USE_ENFORCEMENT_GUIDANCE.lower()
assert "promise" in TOOL_USE_ENFORCEMENT_GUIDANCE.lower()
def test_guidance_requires_action(self):
assert "MUST" in TOOL_USE_ENFORCEMENT_GUIDANCE
def test_enforcement_models_includes_gpt(self):
assert "gpt" in TOOL_USE_ENFORCEMENT_MODELS
def test_enforcement_models_includes_codex(self):
assert "codex" in TOOL_USE_ENFORCEMENT_MODELS
def test_enforcement_models_is_tuple(self):
assert isinstance(TOOL_USE_ENFORCEMENT_MODELS, tuple)
# =========================================================================
# Budget warning history stripping
# =========================================================================
class TestStripBudgetWarningsFromHistory:
def test_strips_json_budget_warning_key(self):
import json
from run_agent import _strip_budget_warnings_from_history
messages = [
{"role": "tool", "tool_call_id": "c1", "content": json.dumps({
"output": "hello",
"exit_code": 0,
"_budget_warning": "[BUDGET: Iteration 55/60. 5 iterations left. Start consolidating your work.]",
})},
]
_strip_budget_warnings_from_history(messages)
parsed = json.loads(messages[0]["content"])
assert "_budget_warning" not in parsed
assert parsed["output"] == "hello"
assert parsed["exit_code"] == 0
def test_strips_text_budget_warning(self):
from run_agent import _strip_budget_warnings_from_history
messages = [
{"role": "tool", "tool_call_id": "c1",
"content": "some result\n\n[BUDGET WARNING: Iteration 58/60. Only 2 iteration(s) left. Provide your final response NOW. No more tool calls unless absolutely critical.]"},
]
_strip_budget_warnings_from_history(messages)
assert messages[0]["content"] == "some result"
def test_leaves_non_tool_messages_unchanged(self):
from run_agent import _strip_budget_warnings_from_history
messages = [
{"role": "assistant", "content": "[BUDGET WARNING: Iteration 58/60. Only 2 iteration(s) left. Provide your final response NOW. No more tool calls unless absolutely critical.]"},
{"role": "user", "content": "hello"},
]
original_contents = [m["content"] for m in messages]
_strip_budget_warnings_from_history(messages)
assert [m["content"] for m in messages] == original_contents
def test_handles_empty_and_missing_content(self):
from run_agent import _strip_budget_warnings_from_history
messages = [
{"role": "tool", "tool_call_id": "c1", "content": ""},
{"role": "tool", "tool_call_id": "c2"},
]
_strip_budget_warnings_from_history(messages)
assert messages[0]["content"] == ""
def test_strips_caution_variant(self):
import json
from run_agent import _strip_budget_warnings_from_history
messages = [
{"role": "tool", "tool_call_id": "c1", "content": json.dumps({
"output": "ok",
"_budget_warning": "[BUDGET: Iteration 42/60. 18 iterations left. Start consolidating your work.]",
})},
]
_strip_budget_warnings_from_history(messages)
parsed = json.loads(messages[0]["content"])
assert "_budget_warning" not in parsed

View File

@@ -54,7 +54,7 @@ class TestScanSkillCommands:
"""macOS-only skills should not register slash commands on Linux."""
with (
patch("tools.skills_tool.SKILLS_DIR", tmp_path),
patch("tools.skills_tool.sys") as mock_sys,
patch("agent.skill_utils.sys") as mock_sys,
):
mock_sys.platform = "linux"
_make_skill(tmp_path, "imessage", frontmatter_extra="platforms: [macos]\n")
@@ -67,7 +67,7 @@ class TestScanSkillCommands:
"""macOS-only skills should register slash commands on macOS."""
with (
patch("tools.skills_tool.SKILLS_DIR", tmp_path),
patch("tools.skills_tool.sys") as mock_sys,
patch("agent.skill_utils.sys") as mock_sys,
):
mock_sys.platform = "darwin"
_make_skill(tmp_path, "imessage", frontmatter_extra="platforms: [macos]\n")
@@ -78,7 +78,7 @@ class TestScanSkillCommands:
"""Skills without platforms field should register on any platform."""
with (
patch("tools.skills_tool.SKILLS_DIR", tmp_path),
patch("tools.skills_tool.sys") as mock_sys,
patch("agent.skill_utils.sys") as mock_sys,
):
mock_sys.platform = "win32"
_make_skill(tmp_path, "generic-tool")
@@ -246,20 +246,10 @@ Generate some audio.
def test_preserves_remaining_remote_setup_warning(self, tmp_path, monkeypatch):
monkeypatch.setenv("TERMINAL_ENV", "ssh")
monkeypatch.delenv("TENOR_API_KEY", raising=False)
def fake_secret_callback(var_name, prompt, metadata=None):
os.environ[var_name] = "stored-in-test"
return {
"success": True,
"stored_as": var_name,
"validated": False,
"skipped": False,
}
monkeypatch.setattr(
skills_tool_module,
"_secret_capture_callback",
fake_secret_callback,
None,
raising=False,
)