mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-05-08 03:01:47 +00:00
9022804d78
Every provider profile is now a self-contained plugin under plugins/model-providers/<name>/, mirroring the plugins/platforms/ pattern established for IRC and Teams. The ProviderProfile ABC stays in providers/; the per-provider profile data moves out. - plugins/model-providers/<name>/__init__.py calls register_provider() - plugins/model-providers/<name>/plugin.yaml declares kind: model-provider - providers/__init__.py._discover_providers() lazily scans bundled plugins then $HERMES_HOME/plugins/model-providers/<name>/ (user override path) - User plugins with the same name override bundled ones (last-writer-wins in register_provider) - Legacy providers/<name>.py layout still supported for back-compat with out-of-tree editable installs - Hermes PluginManager: new kind=model-provider; skipped like memory plugins (providers/ discovery owns them); standalone plugins with register_provider+ProviderProfile in their __init__.py auto-coerce to this kind (same heuristic as memory providers) - skip_names extended to include 'model-providers' so the general PluginManager doesn't double-scan the category - 4 new tests in tests/providers/test_plugin_discovery.py covering bundled discovery, user override, and general-loader isolation - Docs updated: website/docs/developer-guide/adding-providers.md, provider-runtime.md, providers/README.md, plugins/model-providers/README.md No API break: auth.py / config.py / doctor.py / models.py / runtime_provider.py / model_metadata.py / auxiliary_client.py / chat_completions.py / run_agent.py all still consume providers via get_provider_profile() / list_providers() — they just now see plugin-discovered entries instead of pkgutil-iterated ones. Third parties can now drop a single directory into ~/.hermes/plugins/model-providers/<name>/ to add or override an inference provider without touching the repo.
82 lines
2.7 KiB
Python
82 lines
2.7 KiB
Python
"""Qwen Portal provider profile."""
|
|
|
|
import copy
|
|
from typing import Any
|
|
|
|
from providers import register_provider
|
|
from providers.base import ProviderProfile
|
|
|
|
|
|
class QwenProfile(ProviderProfile):
|
|
"""Qwen Portal — message normalization, vl_high_resolution, metadata top-level."""
|
|
|
|
def prepare_messages(self, messages: list[dict[str, Any]]) -> list[dict[str, Any]]:
|
|
"""Normalize content to list-of-dicts format.
|
|
|
|
Inject cache_control on system message.
|
|
|
|
Matches the behavior of run_agent.py:_qwen_prepare_chat_messages().
|
|
"""
|
|
prepared = copy.deepcopy(messages)
|
|
if not prepared:
|
|
return prepared
|
|
|
|
for msg in prepared:
|
|
if not isinstance(msg, dict):
|
|
continue
|
|
content = msg.get("content")
|
|
if isinstance(content, str):
|
|
msg["content"] = [{"type": "text", "text": content}]
|
|
elif isinstance(content, list):
|
|
normalized_parts = []
|
|
for part in content:
|
|
if isinstance(part, str):
|
|
normalized_parts.append({"type": "text", "text": part})
|
|
elif isinstance(part, dict):
|
|
normalized_parts.append(part)
|
|
if normalized_parts:
|
|
msg["content"] = normalized_parts
|
|
|
|
# Inject cache_control on the last part of the system message.
|
|
for msg in prepared:
|
|
if isinstance(msg, dict) and msg.get("role") == "system":
|
|
content = msg.get("content")
|
|
if (
|
|
isinstance(content, list)
|
|
and content
|
|
and isinstance(content[-1], dict)
|
|
):
|
|
content[-1]["cache_control"] = {"type": "ephemeral"}
|
|
break
|
|
|
|
return prepared
|
|
|
|
def build_extra_body(
|
|
self, *, session_id: str | None = None, **context
|
|
) -> dict[str, Any]:
|
|
return {"vl_high_resolution_images": True}
|
|
|
|
def build_api_kwargs_extras(
|
|
self,
|
|
*,
|
|
reasoning_config: dict | None = None,
|
|
qwen_session_metadata: dict | None = None,
|
|
**context,
|
|
) -> tuple[dict[str, Any], dict[str, Any]]:
|
|
"""Qwen metadata goes to top-level api_kwargs, not extra_body."""
|
|
top_level = {}
|
|
if qwen_session_metadata:
|
|
top_level["metadata"] = qwen_session_metadata
|
|
return {}, top_level
|
|
|
|
|
|
qwen = QwenProfile(
|
|
name="qwen-oauth",
|
|
aliases=("qwen", "qwen-portal", "qwen-cli"),
|
|
env_vars=("QWEN_API_KEY",),
|
|
base_url="https://portal.qwen.ai/v1",
|
|
auth_type="oauth_external",
|
|
default_max_tokens=65536,
|
|
)
|
|
|
|
register_provider(qwen)
|