mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-05-18 04:41:56 +00:00
486b692ddd
Some checks failed
Deploy Site / deploy-vercel (push) Waiting to run
Deploy Site / deploy-docs (push) Waiting to run
Docker Build and Publish / build-amd64 (push) Waiting to run
Docker Build and Publish / build-arm64 (push) Waiting to run
Docker Build and Publish / merge (push) Blocked by required conditions
Docker Build and Publish / move-latest (push) Blocked by required conditions
Lint (ruff + ty) / ruff + ty diff (push) Waiting to run
Lint (ruff + ty) / ruff enforcement (blocking) (push) Waiting to run
Lint (ruff + ty) / Windows footguns (blocking) (push) Waiting to run
Nix / nix (macos-latest) (push) Waiting to run
Nix / nix (ubuntu-latest) (push) Waiting to run
Tests / test (push) Waiting to run
Tests / e2e (push) Waiting to run
OSV-Scanner / Scan lockfiles (push) Has been cancelled
uv.lock check / uv lock --check (push) Has been cancelled
* feat(nous): unified client=hermes-client-v<version> tag on every Portal request Every Hermes request to Nous Portal now carries the same client=hermes-client-v<__version__> tag (e.g. client=hermes-client-v0.13.0 on this release), sourced live from hermes_cli.__version__. The release script's regex bump auto-aligns it on every release. Centralized in agent/portal_tags.py and wired into all four call sites: - NousProfile.build_extra_body (main agent loop, every chat completion) - auxiliary_client.NOUS_EXTRA_BODY + _build_call_kwargs (aux client) - run_agent.py compression-summary fallback path - tools/web_tools.py web_extract fallback Replaces the client=aux marker added in #24194 with the unified version tag. Tests assert against the helper output (invariant) rather than the literal string, so they don't need updating on every release. * feat(nous): cover /goal judge and kanban specify aux paths Two aux-using surfaces bypassed call_llm by invoking client.chat.completions.create() directly without extra_body, so they were missing the unified Portal client tag: - hermes_cli/goals.py — /goal standing-goal judge - hermes_cli/kanban_specify.py — kanban triage specifier Both now pass extra_body=get_auxiliary_extra_body() or None so they inherit the version tag when the aux client points at Nous Portal, and emit nothing otherwise (no tag leak to OpenRouter/Anthropic auxes).
259 lines
9.2 KiB
Python
259 lines
9.2 KiB
Python
"""Parity tests: pin the exact current transport behavior per provider.
|
|
|
|
These tests document the flag-based contract between run_agent.py and
|
|
ChatCompletionsTransport.build_kwargs(). When the next PR wires profiles
|
|
to replace flags, every assertion here must still pass — any failure is
|
|
a behavioral regression.
|
|
"""
|
|
|
|
import pytest
|
|
from agent.transports.chat_completions import ChatCompletionsTransport
|
|
from providers import get_provider_profile
|
|
|
|
|
|
@pytest.fixture
|
|
def transport():
|
|
return ChatCompletionsTransport()
|
|
|
|
|
|
def _simple_messages():
|
|
return [{"role": "user", "content": "hello"}]
|
|
|
|
|
|
def _max_tokens_fn(n):
|
|
return {"max_completion_tokens": n}
|
|
|
|
|
|
class TestNvidiaParity:
|
|
"""NVIDIA NIM: default max_tokens=16384."""
|
|
|
|
def test_default_max_tokens(self, transport):
|
|
"""NVIDIA default max_tokens=16384 comes from profile, not legacy is_nvidia_nim flag."""
|
|
from providers import get_provider_profile
|
|
|
|
profile = get_provider_profile("nvidia")
|
|
kw = transport.build_kwargs(
|
|
model="nvidia/llama-3.1-nemotron-70b-instruct",
|
|
messages=_simple_messages(),
|
|
tools=None,
|
|
max_tokens_param_fn=_max_tokens_fn,
|
|
provider_profile=profile,
|
|
)
|
|
assert kw["max_completion_tokens"] == 16384
|
|
|
|
def test_user_max_tokens_overrides(self, transport):
|
|
from providers import get_provider_profile
|
|
|
|
profile = get_provider_profile("nvidia")
|
|
kw = transport.build_kwargs(
|
|
model="nvidia/llama-3.1-nemotron-70b-instruct",
|
|
messages=_simple_messages(),
|
|
tools=None,
|
|
max_tokens=4096,
|
|
max_tokens_param_fn=_max_tokens_fn,
|
|
provider_profile=profile,
|
|
)
|
|
assert kw["max_completion_tokens"] == 4096 # user overrides default
|
|
|
|
|
|
class TestKimiParity:
|
|
"""Kimi: OMIT temperature, max_tokens=32000, thinking + reasoning_effort."""
|
|
|
|
def test_temperature_omitted(self, transport):
|
|
kw = transport.build_kwargs(
|
|
model="kimi-k2",
|
|
messages=_simple_messages(),
|
|
tools=None,
|
|
provider_profile=get_provider_profile("kimi-coding"),
|
|
omit_temperature=True,
|
|
)
|
|
assert "temperature" not in kw
|
|
|
|
def test_default_max_tokens(self, transport):
|
|
kw = transport.build_kwargs(
|
|
model="kimi-k2",
|
|
messages=_simple_messages(),
|
|
tools=None,
|
|
provider_profile=get_provider_profile("kimi-coding"),
|
|
max_tokens_param_fn=_max_tokens_fn,
|
|
)
|
|
assert kw["max_completion_tokens"] == 32000
|
|
|
|
def test_thinking_enabled(self, transport):
|
|
kw = transport.build_kwargs(
|
|
model="kimi-k2",
|
|
messages=_simple_messages(),
|
|
tools=None,
|
|
provider_profile=get_provider_profile("kimi-coding"),
|
|
reasoning_config={"enabled": True, "effort": "high"},
|
|
)
|
|
assert kw["extra_body"]["thinking"] == {"type": "enabled"}
|
|
|
|
def test_thinking_disabled(self, transport):
|
|
kw = transport.build_kwargs(
|
|
model="kimi-k2",
|
|
messages=_simple_messages(),
|
|
tools=None,
|
|
provider_profile=get_provider_profile("kimi-coding"),
|
|
reasoning_config={"enabled": False},
|
|
)
|
|
assert kw["extra_body"]["thinking"] == {"type": "disabled"}
|
|
|
|
def test_reasoning_effort_top_level(self, transport):
|
|
"""Kimi reasoning_effort is a TOP-LEVEL api_kwargs key, NOT in extra_body."""
|
|
kw = transport.build_kwargs(
|
|
model="kimi-k2",
|
|
messages=_simple_messages(),
|
|
tools=None,
|
|
provider_profile=get_provider_profile("kimi-coding"),
|
|
reasoning_config={"enabled": True, "effort": "high"},
|
|
)
|
|
assert kw.get("reasoning_effort") == "high"
|
|
assert "reasoning_effort" not in kw.get("extra_body", {})
|
|
|
|
def test_reasoning_effort_default_medium(self, transport):
|
|
kw = transport.build_kwargs(
|
|
model="kimi-k2",
|
|
messages=_simple_messages(),
|
|
tools=None,
|
|
provider_profile=get_provider_profile("kimi-coding"),
|
|
reasoning_config={"enabled": True},
|
|
)
|
|
assert kw.get("reasoning_effort") == "medium"
|
|
|
|
|
|
class TestOpenRouterParity:
|
|
"""OpenRouter: provider preferences, reasoning in extra_body."""
|
|
|
|
def test_provider_preferences(self, transport):
|
|
prefs = {"allow": ["anthropic"], "sort": "price"}
|
|
kw = transport.build_kwargs(
|
|
model="anthropic/claude-sonnet-4.6",
|
|
messages=_simple_messages(),
|
|
tools=None,
|
|
provider_profile=get_provider_profile("openrouter"),
|
|
provider_preferences=prefs,
|
|
)
|
|
assert kw["extra_body"]["provider"] == prefs
|
|
|
|
def test_reasoning_passes_full_config(self, transport):
|
|
"""OpenRouter passes the FULL reasoning_config dict, not just effort."""
|
|
rc = {"enabled": True, "effort": "high"}
|
|
kw = transport.build_kwargs(
|
|
model="anthropic/claude-sonnet-4.6",
|
|
messages=_simple_messages(),
|
|
tools=None,
|
|
provider_profile=get_provider_profile("openrouter"),
|
|
supports_reasoning=True,
|
|
reasoning_config=rc,
|
|
)
|
|
assert kw["extra_body"]["reasoning"] == rc
|
|
|
|
def test_default_reasoning_when_no_config(self, transport):
|
|
"""When supports_reasoning=True but no config, adds default."""
|
|
kw = transport.build_kwargs(
|
|
model="anthropic/claude-sonnet-4.6",
|
|
messages=_simple_messages(),
|
|
tools=None,
|
|
provider_profile=get_provider_profile("openrouter"),
|
|
supports_reasoning=True,
|
|
)
|
|
assert kw["extra_body"]["reasoning"] == {"enabled": True, "effort": "medium"}
|
|
|
|
|
|
class TestNousParity:
|
|
"""Nous: product tags, reasoning, omit when disabled."""
|
|
|
|
def test_tags(self, transport):
|
|
from agent.portal_tags import nous_portal_tags
|
|
kw = transport.build_kwargs(
|
|
model="hermes-3-llama-3.1-405b",
|
|
messages=_simple_messages(),
|
|
tools=None,
|
|
provider_profile=get_provider_profile("nous"),
|
|
)
|
|
assert kw["extra_body"]["tags"] == nous_portal_tags()
|
|
|
|
def test_reasoning_omitted_when_disabled(self, transport):
|
|
"""Nous special case: reasoning omitted entirely when disabled."""
|
|
kw = transport.build_kwargs(
|
|
model="hermes-3-llama-3.1-405b",
|
|
messages=_simple_messages(),
|
|
tools=None,
|
|
provider_profile=get_provider_profile("nous"),
|
|
supports_reasoning=True,
|
|
reasoning_config={"enabled": False},
|
|
)
|
|
assert "reasoning" not in kw.get("extra_body", {})
|
|
|
|
def test_reasoning_enabled(self, transport):
|
|
rc = {"enabled": True, "effort": "high"}
|
|
kw = transport.build_kwargs(
|
|
model="hermes-3-llama-3.1-405b",
|
|
messages=_simple_messages(),
|
|
tools=None,
|
|
provider_profile=get_provider_profile("nous"),
|
|
supports_reasoning=True,
|
|
reasoning_config=rc,
|
|
)
|
|
assert kw["extra_body"]["reasoning"] == rc
|
|
|
|
|
|
class TestQwenParity:
|
|
"""Qwen: max_tokens=65536, vl_high_resolution, metadata top-level."""
|
|
|
|
def test_default_max_tokens(self, transport):
|
|
kw = transport.build_kwargs(
|
|
model="qwen3.5-plus",
|
|
messages=_simple_messages(),
|
|
tools=None,
|
|
provider_profile=get_provider_profile("qwen-oauth"),
|
|
max_tokens_param_fn=_max_tokens_fn,
|
|
)
|
|
assert kw["max_completion_tokens"] == 65536
|
|
|
|
def test_vl_high_resolution(self, transport):
|
|
kw = transport.build_kwargs(
|
|
model="qwen3.5-plus",
|
|
messages=_simple_messages(),
|
|
tools=None,
|
|
provider_profile=get_provider_profile("qwen-oauth"),
|
|
)
|
|
assert kw["extra_body"]["vl_high_resolution_images"] is True
|
|
|
|
def test_metadata_top_level(self, transport):
|
|
"""Qwen metadata goes to top-level api_kwargs, NOT extra_body."""
|
|
meta = {"sessionId": "s123", "promptId": "p456"}
|
|
kw = transport.build_kwargs(
|
|
model="qwen3.5-plus",
|
|
messages=_simple_messages(),
|
|
tools=None,
|
|
provider_profile=get_provider_profile("qwen-oauth"),
|
|
qwen_session_metadata=meta,
|
|
)
|
|
assert kw["metadata"] == meta
|
|
assert "metadata" not in kw.get("extra_body", {})
|
|
|
|
|
|
class TestCustomOllamaParity:
|
|
"""Custom/Ollama: num_ctx, think=false — now tested via profile."""
|
|
|
|
def test_ollama_num_ctx(self, transport):
|
|
kw = transport.build_kwargs(
|
|
model="llama3.1",
|
|
messages=_simple_messages(),
|
|
tools=None,
|
|
provider_profile=get_provider_profile("custom"),
|
|
ollama_num_ctx=131072,
|
|
)
|
|
assert kw["extra_body"]["options"]["num_ctx"] == 131072
|
|
|
|
def test_think_false_when_disabled(self, transport):
|
|
kw = transport.build_kwargs(
|
|
model="qwen3:72b",
|
|
messages=_simple_messages(),
|
|
tools=None,
|
|
provider_profile=get_provider_profile("custom"),
|
|
reasoning_config={"enabled": False, "effort": "none"},
|
|
)
|
|
assert kw["extra_body"]["think"] is False
|