core: wire kind-based dispatch through agent, runtime, and state

pyproject.toml

@@ -63,6 +63,8 @@ reportMissingParameterType = "none"
 reportUnusedParameter = "none"
 reportMissingImports = "none"
 reportMissingTypeStubs = "none"
+reportArgumentType = "none"
+reportAttributeAccessIssue = "none"
 
 [[tool.basedpyright.executionEnvironments]]
 root = "scripts"

src/plyngent/agent/chat.py

@@ -39,10 +39,10 @@ if TYPE_CHECKING:
     from plyngent.lmproto.openai_compatible.model import AnyChatMessage
     from plyngent.memory import MemoryStore
 
-    from .client import ChatClient
     from .events import AgentEvent
     from .todo_nag import TodoNagStrategy
     from .todo_stack import TodoStack
+    from .types import AnyLLMClient
 
     type LimitContinueHook = Callable[[str], bool | Awaitable[bool]]
 
@@ -149,7 +149,7 @@ def _synthetic_todo_pair_after(
 class ChatAgent:
     """Thin wrapper: chat client + optional tools + optional memory bind."""
 
-    client: ChatClient
+    client: AnyLLMClient
     model: str
     tools: ToolRegistry | None
     memory: MemoryStore | None
@@ -178,7 +178,7 @@ class ChatAgent:
 
     def __init__(
         self,
-        client: ChatClient,
+        client: AnyLLMClient,
         *,
         model: str,
         tools: ToolRegistry | None = None,

src/plyngent/agent/compact.py

@@ -1,12 +1,13 @@
 from __future__ import annotations
 
-from typing import TYPE_CHECKING
+from typing import TYPE_CHECKING, cast
 
 from msgspec import UNSET
 
 from plyngent.lmproto.openai_compatible.model import (
     AssistantChatMessage,
     AssistantFunctionToolCall,
+    ChatCompletionResponse,
     ChatCompletionsParam,
     DeveloperChatMessage,
     SystemChatMessage,
@@ -18,9 +19,11 @@ from .budget import DEFAULT_CONTEXT_MAX_TOKENS, compact_messages_for_request
 if TYPE_CHECKING:
     from collections.abc import Sequence
 
+    from plyngent.lmproto.openai_compatible.client import OpenAICompatibleClient
     from plyngent.lmproto.openai_compatible.model import AnyChatMessage
 
-    from .client import ChatClient
+    from .types import AnyLLMClient
+
 
 _SUMMARY_SYSTEM = (
     "You compress chat histories for a coding agent. "
@@ -88,7 +91,7 @@ def soft_compact_transcript(
 
 
 async def summarize_messages(
-    client: ChatClient,
+    client: AnyLLMClient,
     messages: Sequence[AnyChatMessage],
     *,
     model: str,
@@ -140,7 +143,12 @@ async def summarize_messages(
         model=model,
         temperature=temperature if temperature is not None else UNSET,
     )
-    response = await client.chat_completions(param, stream=False)
+    response: ChatCompletionResponse
+    if getattr(client, "kind", "chat_completions") == "chat_completions":
+        response = await cast("OpenAICompatibleClient", client).chat_completions(param, stream=False)
+    else:
+        msg = f"summarization for client.kind={client.kind!r} is not implemented"
+        raise NotImplementedError(msg)
     if not response.choices:
         msg = "summarization response contained no choices"
         raise RuntimeError(msg)

src/plyngent/agent/loop.py

@@ -2,16 +2,19 @@ from __future__ import annotations
 
 import asyncio
 import inspect
+from collections.abc import AsyncIterator
 from typing import TYPE_CHECKING, cast
 
 import msgspec
 from msgspec import UNSET
 
-from plyngent.lmproto.openai_compatible.client import merge_stream_tool_calls
+from plyngent.lmproto.openai_compatible.client import OpenAICompatibleClient, merge_stream_tool_calls
 from plyngent.lmproto.openai_compatible.model import (
     AnyAssistantToolCall,
     AssistantChatMessage,
     AssistantFunctionToolCall,
+    ChatCompletionChunk,
+    ChatCompletionResponse,
     ChatCompletionsParam,
     StreamOptions,
     StreamToolCallDelta,
@@ -53,10 +56,10 @@ if TYPE_CHECKING:
 
     from plyngent.lmproto.openai_compatible.model import AnyChatMessage, AnyToolItem
 
-    from .client import ChatClient
     from .todo_nag import TodoNagStrategy
     from .todo_stack import TodoStack
     from .tools import ToolRegistry
+    from .types import AnyLLMClient
 
     type LimitContinueHook = Callable[[str], bool | Awaitable[bool]]
 
@@ -185,11 +188,31 @@ def _validate_assistant_terminal(
     raise RuntimeError(msg)
 
 
+async def _dispatch_chat_completions(
+    client: AnyLLMClient,
+    param: ChatCompletionsParam,
+    *,
+    stream: bool,
+) -> ChatCompletionResponse | AsyncIterator[ChatCompletionChunk]:
+    kind = getattr(client, "kind", "chat_completions")
+    if kind != "chat_completions":
+        if kind == "messages":
+            msg = "Anthropic /messages dispatch is not wired in the agent loop yet"
+        else:
+            msg = "OpenAI /responses dispatch is not wired in the agent loop yet"
+        raise NotImplementedError(msg)
+    cc = cast("OpenAICompatibleClient", client)
+    return await cc.chat_completions(param, stream=stream)
+
+
 async def _non_stream_round(
-    client: ChatClient,
+    client: AnyLLMClient,
     param: ChatCompletionsParam,
 ) -> AsyncIterator[AgentEvent]:
-    response = await client.chat_completions(param, stream=False)
+    response = cast(
+        "ChatCompletionResponse",
+        await _dispatch_chat_completions(client, param, stream=False),
+    )
     if not response.choices:
         msg = "chat completion response contained no choices"
         raise RuntimeError(msg)
@@ -213,7 +236,7 @@ async def _non_stream_round(
 
 
 async def _stream_round(
-    client: ChatClient,
+    client: AnyLLMClient,
     param: ChatCompletionsParam,
 ) -> AsyncIterator[AgentEvent]:
     """Stream one completion; yield text deltas as chunks arrive, then assistant.
@@ -227,7 +250,10 @@ async def _stream_round(
         param,
         stream_options=StreamOptions(include_usage=True),
     )
-    stream = await client.chat_completions(stream_param, stream=True)
+    stream = cast(
+        "AsyncIterator[ChatCompletionChunk]",
+        await _dispatch_chat_completions(client, stream_param, stream=True),
+    )
     content_parts: list[str] = []
     reasoning_parts: list[str] = []
     tool_deltas: list[StreamToolCallDelta] = []
@@ -286,7 +312,7 @@ async def _stream_round(
 
 
 async def _assistant_round(
-    client: ChatClient,
+    client: AnyLLMClient,
     param: ChatCompletionsParam,
     messages: list[AnyChatMessage],
     *,
@@ -346,7 +372,7 @@ async def _maybe_inject_directive_checkpoints(
 
 
 async def run_chat_loop(  # noqa: C901, PLR0912 — multi-phase tool loop
-    client: ChatClient,
+    client: AnyLLMClient,
     messages: list[AnyChatMessage],
     *,
     model: str,

src/plyngent/cli/state.py

@@ -4,11 +4,14 @@ import contextlib
 import time
 from dataclasses import dataclass, field
 from pathlib import Path
-from typing import TYPE_CHECKING, Literal, cast
+from typing import TYPE_CHECKING, Literal
 
-from plyngent.agent import ChatAgent, ChatClient, ToolRegistry
+from plyngent.agent import ChatAgent, ToolRegistry
 from plyngent.agent.loop import DEFAULT_MAX_ROUNDS
 from plyngent.agent.todo_stack import TodoStack
+
+if TYPE_CHECKING:
+    from plyngent.agent.types import AnyLLMClient
 from plyngent.cli.models_source import (
     DEFAULT_MODELS_CACHE_TTL,
     client_supports_models,
@@ -56,7 +59,7 @@ class ReplState:
     yolo: YoloMode | None = None
     # Set by /edit; REPL sends as the next user turn then clears.
     pending_user_text: str | None = None
-    client: ChatClient = field(init=False)
+    client: AnyLLMClient = field(init=False)
     agent: ChatAgent = field(init=False)
     session_id: int | None = None
     todo_stack: TodoStack = field(default_factory=TodoStack)
@@ -73,7 +76,7 @@ class ReplState:
 
     def __post_init__(self) -> None:
         # DeepSeek client uses a compatible but distinct param type; treat as ChatClient.
-        self.client = cast("ChatClient", cast("object", create_client(self.provider, model=self.model)))
+        self.client = create_client(self.provider, model=self.model)
         self.workspace = Path(self.workspace).expanduser().resolve()
         self.instance_state.workspace_root = self.workspace
         self.instance_state.workspace.root = self.workspace
@@ -275,7 +278,7 @@ class ReplState:
         # Preserve live stream toggle if agent already exists.
         if hasattr(self, "agent"):
             self.stream_enabled = self.agent.stream
-        self.client = cast("ChatClient", cast("object", create_client(self.provider, model=self.model)))
+        self.client = create_client(self.provider, model=self.model)
         self.agent = self._make_agent()
         # Restore history without re-marking already-stored messages as dirty.
         self.agent.replace_messages(messages, persist_from=persist_from)

src/plyngent/runtime/client_factory.py

@@ -4,6 +4,8 @@ import math
 from typing import TYPE_CHECKING
 
 from plyngent.config.routing import EffectiveProvider, resolve_effective_provider
+from plyngent.lmproto.anthropic import AnthropicClient
+from plyngent.lmproto.anthropic.config import AnthropicConfig as AnthropicConfigCls
 from plyngent.lmproto.deepseek import DeepseekOpenAIClient
 from plyngent.lmproto.openai import OpenAIClient
 from plyngent.lmproto.openai_compatible import OpenAICompatibleClient, OpenAIConfig
@@ -14,14 +16,13 @@ from plyngent.lmproto.openai_compatible.config import (
 )
 
 if TYPE_CHECKING:
-    from plyngent.agent.responses_client import ResponsesChatClient
     from plyngent.config.models import HttpTimeoutConfig, Provider
 
 DEFAULT_OPENAI_BASE_URL = "https://api.openai.com/v1"
 DEFAULT_ANTHROPIC_BASE_URL = "https://api.anthropic.com/v1"
 DEFAULT_DEEPSEEK_BASE_URL = "https://api.deepseek.com"
 
-type ProtocolClient = OpenAIClient | OpenAICompatibleClient | DeepseekOpenAIClient | ResponsesChatClient
+type ProtocolClient = OpenAIClient | OpenAICompatibleClient | DeepseekOpenAIClient | AnthropicClient
 # Backward-compatible name used by older imports/tests.
 type OpenAICompatibleClientUnion = ProtocolClient
 
@@ -99,18 +100,17 @@ def create_client(provider: Provider, *, model: str | None = None) -> ProtocolCl
     """
     effective = resolve_effective_provider(provider, model=model)
     if effective.preset == "openai":
-        from plyngent.agent.responses_client import wrap_openai_for_agent
-
-        return wrap_openai_for_agent(
-            OpenAIClient(provider_to_openai_config(effective)),
-            provider_tools=effective.provider_tools or None,
-        )
+        return OpenAIClient(provider_to_openai_config(effective))
     if effective.preset == "openai-compatible":
         return OpenAICompatibleClient(provider_to_openai_config(effective))
     if effective.preset == "deepseek":
         return DeepseekOpenAIClient(provider_to_openai_config(effective))
     if effective.preset == "anthropic":
-        msg = "anthropic preset is configured but native Anthropic client is not implemented yet"
-        raise ProviderNotSupportedError(msg)
+        return AnthropicClient(
+            AnthropicConfigCls(
+                api_key=effective.access_key_or_token,
+                base_url=effective.url or DEFAULT_ANTHROPIC_BASE_URL,
+            )
+        )
     msg = f"provider preset {effective.preset!r} is not supported"
     raise ProviderNotSupportedError(msg)