Hua/nanobot
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

refactor: move generation settings to provider level, eliminate parameter passthrough

Browse Source
This commit is contained in:
Re-bin
2026-03-11 09:47:04 +00:00
parent a180e84536
commit c72c2ce7e2
8 changed files with 120 additions and 223 deletions
Download Patch File Download Diff File Expand all files Collapse all files

15
nanobot/agent/loop.py
View File

@@ -52,9 +52,6 @@ class AgentLoop:
workspace: Path,
model: str | None = None,
max_iterations: int = 40,
temperature: float = 0.1,
max_tokens: int = 4096,
reasoning_effort: str | None = None,
context_window_tokens: int = 65_536,
brave_api_key: str | None = None,
web_proxy: str | None = None,
@@ -72,9 +69,6 @@ class AgentLoop:
self.workspace = workspace
self.model = model or provider.get_default_model()
self.max_iterations = max_iterations
self.temperature = temperature
self.max_tokens = max_tokens
self.reasoning_effort = reasoning_effort
self.context_window_tokens = context_window_tokens
self.brave_api_key = brave_api_key
self.web_proxy = web_proxy
@@ -90,9 +84,6 @@ class AgentLoop:
workspace=workspace,
bus=bus,
model=self.model,
temperature=self.temperature,
max_tokens=self.max_tokens,
reasoning_effort=reasoning_effort,
brave_api_key=brave_api_key,
web_proxy=web_proxy,
exec_config=self.exec_config,
@@ -114,9 +105,6 @@ class AgentLoop:
context_window_tokens=context_window_tokens,
build_messages=self.context.build_messages,
get_tool_definitions=self.tools.get_definitions,
temperature=self.temperature,
max_tokens=self.max_tokens,
reasoning_effort=self.reasoning_effort,
)
self._register_default_tools()
@@ -205,9 +193,6 @@ class AgentLoop:
messages=messages,
tools=tool_defs,
model=self.model,
temperature=self.temperature,
max_tokens=self.max_tokens,
reasoning_effort=self.reasoning_effort,
)
if response.has_tool_calls:

22
nanobot/agent/memory.py
View File

@@ -57,7 +57,6 @@ def _normalize_save_memory_args(args: Any) -> dict[str, Any] | None:
return args[0] if args and isinstance(args[0], dict) else None
return args if isinstance(args, dict) else None
class MemoryStore:
"""Two-layer memory: MEMORY.md (long-term facts) + HISTORY.md (grep-searchable log)."""
@@ -99,9 +98,6 @@ class MemoryStore:
messages: list[dict],
provider: LLMProvider,
model: str,
temperature: float | None = None,
max_tokens: int | None = None,
reasoning_effort: str | None = None,
) -> bool:
"""Consolidate the provided message chunk into MEMORY.md + HISTORY.md."""
if not messages:
@@ -124,9 +120,6 @@ class MemoryStore:
],
tools=_SAVE_MEMORY_TOOL,
model=model,
temperature=temperature,
max_tokens=max_tokens,
reasoning_effort=reasoning_effort,
)
if not response.has_tool_calls:
@@ -166,9 +159,6 @@ class MemoryConsolidator:
context_window_tokens: int,
build_messages: Callable[..., list[dict[str, Any]]],
get_tool_definitions: Callable[[], list[dict[str, Any]]],
temperature: float | None = None,
max_tokens: int | None = None,
reasoning_effort: str | None = None,
):
self.store = MemoryStore(workspace)
self.provider = provider
@@ -177,9 +167,6 @@ class MemoryConsolidator:
self.context_window_tokens = context_window_tokens
self._build_messages = build_messages
self._get_tool_definitions = get_tool_definitions
self._temperature = temperature
self._max_tokens = max_tokens
self._reasoning_effort = reasoning_effort
self._locks: weakref.WeakValueDictionary[str, asyncio.Lock] = weakref.WeakValueDictionary()
def get_lock(self, session_key: str) -> asyncio.Lock:
@@ -188,14 +175,7 @@ class MemoryConsolidator:
async def consolidate_messages(self, messages: list[dict[str, object]]) -> bool:
"""Archive a selected message chunk into persistent memory."""
return await self.store.consolidate(
messages,
self.provider,
self.model,
temperature=self._temperature,
max_tokens=self._max_tokens,
reasoning_effort=self._reasoning_effort,
)
return await self.store.consolidate(messages, self.provider, self.model)
def pick_consolidation_boundary(
self,

9
nanobot/agent/subagent.py
View File

@@ -28,9 +28,6 @@ class SubagentManager:
workspace: Path,
bus: MessageBus,
model: str | None = None,
temperature: float = 0.7,
max_tokens: int = 4096,
reasoning_effort: str | None = None,
brave_api_key: str | None = None,
web_proxy: str | None = None,
exec_config: "ExecToolConfig | None" = None,
@@ -41,9 +38,6 @@ class SubagentManager:
self.workspace = workspace
self.bus = bus
self.model = model or provider.get_default_model()
self.temperature = temperature
self.max_tokens = max_tokens
self.reasoning_effort = reasoning_effort
self.brave_api_key = brave_api_key
self.web_proxy = web_proxy
self.exec_config = exec_config or ExecToolConfig()
@@ -128,9 +122,6 @@ class SubagentManager:
messages=messages,
tools=tools.get_definitions(),
model=self.model,
temperature=self.temperature,
max_tokens=self.max_tokens,
reasoning_effort=self.reasoning_effort,
)
if response.has_tool_calls:

57
nanobot/cli/commands.py
View File

@@ -215,6 +215,7 @@ def onboard():
def _make_provider(config: Config):
"""Create the appropriate LLM provider from config."""
from nanobot.providers.base import GenerationSettings
from nanobot.providers.openai_codex_provider import OpenAICodexProvider
from nanobot.providers.azure_openai_provider import AzureOpenAIProvider
@@ -224,46 +225,50 @@ def _make_provider(config: Config):
# OpenAI Codex (OAuth)
if provider_name == "openai_codex" or model.startswith("openai-codex/"):
return OpenAICodexProvider(default_model=model)
provider = OpenAICodexProvider(default_model=model)
# Custom: direct OpenAI-compatible endpoint, bypasses LiteLLM
from nanobot.providers.custom_provider import CustomProvider
if provider_name == "custom":
return CustomProvider(
elif provider_name == "custom":
from nanobot.providers.custom_provider import CustomProvider
provider = CustomProvider(
api_key=p.api_key if p else "no-key",
api_base=config.get_api_base(model) or "http://localhost:8000/v1",
default_model=model,
)
# Azure OpenAI: direct Azure OpenAI endpoint with deployment name
if provider_name == "azure_openai":
elif provider_name == "azure_openai":
if not p or not p.api_key or not p.api_base:
console.print("[red]Error: Azure OpenAI requires api_key and api_base.[/red]")
console.print("Set them in ~/.nanobot/config.json under providers.azure_openai section")
console.print("Use the model field to specify the deployment name.")
raise typer.Exit(1)
return AzureOpenAIProvider(
provider = AzureOpenAIProvider(
api_key=p.api_key,
api_base=p.api_base,
default_model=model,
)
else:
from nanobot.providers.litellm_provider import LiteLLMProvider
from nanobot.providers.registry import find_by_name
spec = find_by_name(provider_name)
if not model.startswith("bedrock/") and not (p and p.api_key) and not (spec and (spec.is_oauth or spec.is_local)):
console.print("[red]Error: No API key configured.[/red]")
console.print("Set one in ~/.nanobot/config.json under providers section")
raise typer.Exit(1)
provider = LiteLLMProvider(
api_key=p.api_key if p else None,
api_base=config.get_api_base(model),
default_model=model,
extra_headers=p.extra_headers if p else None,
provider_name=provider_name,
)
from nanobot.providers.litellm_provider import LiteLLMProvider
from nanobot.providers.registry import find_by_name
spec = find_by_name(provider_name)
if not model.startswith("bedrock/") and not (p and p.api_key) and not (spec and (spec.is_oauth or spec.is_local)):
console.print("[red]Error: No API key configured.[/red]")
console.print("Set one in ~/.nanobot/config.json under providers section")
raise typer.Exit(1)
return LiteLLMProvider(
api_key=p.api_key if p else None,
api_base=config.get_api_base(model),
default_model=model,
extra_headers=p.extra_headers if p else None,
provider_name=provider_name,
defaults = config.agents.defaults
provider.generation = GenerationSettings(
temperature=defaults.temperature,
max_tokens=defaults.max_tokens,
reasoning_effort=defaults.reasoning_effort,
)
return provider
def _load_runtime_config(config: str | None = None, workspace: str | None = None) -> Config:
@@ -341,10 +346,7 @@ def gateway(
provider=provider,
workspace=config.workspace_path,
model=config.agents.defaults.model,
temperature=config.agents.defaults.temperature,
max_tokens=config.agents.defaults.max_tokens,
max_iterations=config.agents.defaults.max_tool_iterations,
reasoning_effort=config.agents.defaults.reasoning_effort,
context_window_tokens=config.agents.defaults.context_window_tokens,
brave_api_key=config.tools.web.search.api_key or None,
web_proxy=config.tools.web.proxy or None,
@@ -527,10 +529,7 @@ def agent(
provider=provider,
workspace=config.workspace_path,
model=config.agents.defaults.model,
temperature=config.agents.defaults.temperature,
max_tokens=config.agents.defaults.max_tokens,
max_iterations=config.agents.defaults.max_tool_iterations,
reasoning_effort=config.agents.defaults.reasoning_effort,
context_window_tokens=config.agents.defaults.context_window_tokens,
brave_api_key=config.tools.web.search.api_key or None,
web_proxy=config.tools.web.proxy or None,

38
nanobot/providers/base.py
View File

@@ -32,6 +32,21 @@ class LLMResponse:
return len(self.tool_calls) > 0
@dataclass(frozen=True)
class GenerationSettings:
"""Default generation parameters for LLM calls.
Stored on the provider so every call site inherits the same defaults
without having to pass temperature / max_tokens / reasoning_effort
through every layer. Individual call sites can still override by
passing explicit keyword arguments to chat() / chat_with_retry().
"""
temperature: float = 0.7
max_tokens: int = 4096
reasoning_effort: str | None = None
class LLMProvider(ABC):
"""
Abstract base class for LLM providers.
@@ -56,9 +71,12 @@ class LLMProvider(ABC):
"temporarily unavailable",
)
_SENTINEL = object()
def __init__(self, api_key: str | None = None, api_base: str | None = None):
self.api_key = api_key
self.api_base = api_base
self.generation: GenerationSettings = GenerationSettings()
@staticmethod
def _sanitize_empty_content(messages: list[dict[str, Any]]) -> list[dict[str, Any]]:
@@ -155,11 +173,23 @@ class LLMProvider(ABC):
messages: list[dict[str, Any]],
tools: list[dict[str, Any]] | None = None,
model: str | None = None,
max_tokens: int = 4096,
temperature: float = 0.7,
reasoning_effort: str | None = None,
max_tokens: object = _SENTINEL,
temperature: object = _SENTINEL,
reasoning_effort: object = _SENTINEL,
) -> LLMResponse:
"""Call chat() with retry on transient provider failures."""
"""Call chat() with retry on transient provider failures.
Parameters default to ``self.generation`` when not explicitly passed,
so callers no longer need to thread temperature / max_tokens /
reasoning_effort through every layer.
"""
if max_tokens is self._SENTINEL:
max_tokens = self.generation.max_tokens
if temperature is self._SENTINEL:
temperature = self.generation.temperature
if reasoning_effort is self._SENTINEL:
reasoning_effort = self.generation.reasoning_effort
for attempt, delay in enumerate(self._CHAT_RETRY_DELAYS, start=1):
try:
response = await self.chat(