docs: document openai responses and anthropic messages wiring

CLAUDE.md

@@ -39,15 +39,18 @@ All protocol models use `msgspec.Struct` — not dataclasses, not Pydantic. Opti
 ```
 lmproto/openai_compatible/     ← Base: model, config, client
 lmproto/openai/                ← OpenAI platform: Responses + chat (extends base)
+lmproto/anthropic/             ← Anthropic Messages: model, config, client
 lmproto/deepseek/openai_compat/ ← Extends base via inheritance + extra fields
 ```
 
 - **`openai_compatible/model.py`** — tagged chat messages (`SystemChatMessage`, `UserChatMessage`, …), tools, request/response, streaming chunks.
-- **`openai_compatible/client.py`** — `BaseOpenAIClient` / `OpenAICompatibleClient` via `niquests` async + SSE; `chat_completions`, `models` only (`OpenAIClient` is a compat alias).
+- **`openai_compatible/client.py`** — `BaseOpenAIClient` / `OpenAICompatibleClient` via `niquests` async + SSE; `chat_completions`, `models` only.
 - **`openai_compatible/config.py`** — `OpenAIConfig` (token + base URL).
 - **`openai/model.py`** — OpenAI Responses API (`ResponsesCreateParam`, `Response`, function_call items, stream events).
-- **`openai/client.py`** — platform `OpenAIClient`: chat completions + `responses` / `get_response` / `delete_response`.
+- **`openai/client.py`** — platform `OpenAIClient` (`kind="responses"`): chat completions + `responses` / `get_response` / `delete_response`.
-- **DeepSeek** — `DeepseekOpenAIClient`; models add `reasoning_content`, `prefix`, `ThinkingOptions`. Config default model ids: `deepseek-v4-flash`, `deepseek-v4-pro`.
+- **`anthropic/model.py`** — Anthropic Messages request/response + SSE event models.
+- **`anthropic/client.py`** — `AnthropicClient` (`kind="messages"`): `POST /messages` + `GET /models`.
+- **DeepSeek** — `DeepseekOpenAIClient` (`kind="chat_completions"`); models add `reasoning_content`, `prefix`, `ThinkingOptions`. Config default model ids: `deepseek-v4-flash`, `deepseek-v4-pro`.
 
 ### Config (`config/`)
 
@@ -55,7 +58,7 @@ TOML load/store (`ConfigStore`): `[providers]` tagged union presets, `[database]
 
 ### Runtime (`runtime/`)
 
-`create_client(provider)` maps config `Provider` → protocol client. `provider_to_openai_config` normalizes `timeout` via `normalize_http_timeout` into `OpenAIConfig.timeout` for `niquests.AsyncSession`. OpenAI → `lmproto.openai.OpenAIClient` (Responses-capable); openai-compatible / deepseek(openai convention) → chat-completions clients; anthropic and deepseek anthropic convention raise `ProviderNotSupportedError`.
+`create_client(provider)` maps config `Provider` → protocol client by effective preset (model-level `preset`/`url` overrides apply). `normalize_http_timeout` feeds OpenAI-compatible configs and Anthropic. Mapping: `openai` → `OpenAIClient` (agent uses Responses), `openai-compatible` / `deepseek` → chat-completions clients, `anthropic` → `AnthropicClient`.
 
 ### Memory (`memory/`)
 
@@ -63,13 +66,14 @@ Async SQLAlchemy + aiosqlite. `MemoryStore`: schema init (+ lightweight SQLite `
 
 ### Agent (`agent/`)
 
-- **`ChatClient`** Protocol for `chat_completions` (agent history stays chat-shaped).
+- **Kind-based dispatch**: clients expose `kind` (`chat_completions` | `responses` | `messages`). Agent history stays chat-completions-shaped; transport adapters return synthetic `ChatCompletionResponse` / stream chunks.
-- **OpenAI Responses integration**: `ResponsesChatClient` adapts platform `OpenAIClient.responses` to `ChatClient`; selected automatically for `OpenAIProvider` in `create_client`. Compat/DeepSeek stay on chat completions.
+- **`responses_bridge` / `responses_dispatch`**: chat ↔ OpenAI Responses; stream text/reasoning deltas; tool calls + usage on `response.completed`.
-- **Provider-side tools**: `OpenAIProvider.provider_tools` (list of dicts; default `[{type="web_search"}]` when omitted; `[]` disables) merged into Responses `tools` alongside local function tools; never executed by `ToolRegistry`.
+- **`messages_bridge` / `messages_dispatch`**: chat ↔ Anthropic Messages; system fold; tool_use/tool_result; stream text + tool argument fragments.
+- **Provider-side tools**: `OpenAIProvider.provider_tools` (list of dicts; default `[{type="web_search"}]` when omitted; `[]` disables) threaded via `ChatAgent`/`run_chat_loop` into Responses only; never executed by `ToolRegistry`.
 - **`@tool` / `ToolRegistry`**: decorator infers JSON Schema from type hints; execute tools by name.
 - **`run_chat_loop`**: multi-round tool loop; default **streaming** text deltas + stream tool-call merge; parallel tools; tool-result char budget; soft context compact on request (**API-calibrated** after first usage when available); cooperative cancel points; optional `on_limit`.
-- **`ChatAgent`**: optional `MemoryStore` (user message persisted immediately; **completed tool batches checkpointed** mid-turn; unfinished assistant suffix rolled back on failure); `stream`; system prompt; `retry()` continues incomplete turns (user-only **or** after committed tools — does not re-run those tools).
+- **`ChatAgent`**: optional `MemoryStore` (user message persisted immediately; **completed tool batches checkpointed** mid-turn; unfinished assistant suffix rolled back on failure); `stream`; system prompt; `provider_tools`; `retry()` continues incomplete turns (user-only **or** after committed tools — does not re-run those tools).
-- **`/compact`**: soft-compact tool dumps → model summary (no tools) → **new** session seeded with summary message. Soft-compact keeps the last **12** tool results full-size by default (`DEFAULT_RECENT_TOOL_RESULTS`); older tool payloads shrink first.
+- **`/compact`**: soft-compact tool dumps → model summary (no tools) via the same kind dispatch → **new** session seeded with summary message. Soft-compact keeps the last **12** tool results full-size by default (`DEFAULT_RECENT_TOOL_RESULTS`); older tool payloads shrink first.
 - Events: text_delta, **reasoning_delta**, assistant_message, tool_call/result, max_rounds, **error** (`retryable`/`source`), **cancelled** (`reason`), **usage** (`TokenUsage`).
 - Usage: API `usage` from completions (stream with `include_usage`); **char≈token fallback** (~4 chars/token) when omitted; **context size** = last request ``prompt_tokens`` (API preferred); `last_turn_usage` / `session_usage` are **billed sums** (tool rounds re-send history); CLI end-of-turn + `/status`.
 - Config ``[agent]``: `system_prompt` (persona; default `DEFAULT_SYSTEM_PROMPT`; `""` omits persona), `tool_directives` (tool playbook; default `DEFAULT_TOOL_DIRECTIVES`; `""` omits playbook; both empty → no system), `max_tool_result_chars`, `parallel_tools`, `confirm_destructive`, `path_denylist`, `max_context_tokens` (default 200k est. tokens).

README.md

@@ -157,7 +157,16 @@ Per-provider **`timeout`** is passed to the HTTP session for chat/completions, R
 
 Third-party **plugins**: install a package that declares `project.entry-points."plyngent.tools"` (and later other groups), then allowlist the entry-point name under **`[plugins].enable`**. Details: [doc/plugins.md](doc/plugins.md).
 
-Supported provider presets today: `openai` (default if `preset` is omitted; default models `gpt-5.4` / `gpt-5.4-mini` / `gpt-5.4-nano` when `models` is omitted), `openai-compatible`, `deepseek` (OpenAI convention; default models `deepseek-v4-flash` and `deepseek-v4-pro` if `models` is omitted). Anthropic presets are modeled in config but not wired in the runtime client yet.
+Supported provider presets today:
+
+| Preset | API used by the agent | Notes |
+|--------|------------------------|--------|
+| `openai` (default if `preset` omitted) | OpenAI **Responses** (`POST /responses`) | Default models `gpt-5.4` / `gpt-5.4-mini` / `gpt-5.4-nano` when `models` is omitted; optional `provider_tools` (default `web_search`) |
+| `openai-compatible` | Chat Completions | Generic hosts (vLLM, LiteLLM, proxies); requires `url` |
+| `deepseek` | Chat Completions (DeepSeek) | Default models `deepseek-v4-flash` / `deepseek-v4-pro` when `models` is omitted |
+| `anthropic` | Anthropic **Messages** (`POST /messages`) | Native tools/streaming; set `access_key_or_token` (API key) |
+
+Model-level `preset` / `url` overrides on a catalog entry can route a single provider name to a different API (e.g. gateway + Anthropic model).
 
 If `[database]` is omitted (or SQLite `url` is unset/empty), chat uses a durable file under the user data dir (e.g. `~/.local/share/plyngent/chat.db` on Linux). Set `url = ":memory:"` for a true in-memory SQLite (CLI warns; no file; useful for tests).
 
@@ -274,8 +283,8 @@ plyngent --log-level INFO chat ...
 
 See [doc/architecture.md](doc/architecture.md) and [CLAUDE.md](CLAUDE.md) for developers.
 
-- **`lmproto/`** — OpenAI-compatible (+ DeepSeek) msgspec models and async SSE clients  
+- **`lmproto/`** — OpenAI-compatible, OpenAI Responses, Anthropic Messages, DeepSeek msgspec models and async SSE clients  
-- **`agent/`** — tool loop, streaming, usage, compact  
+- **`agent/`** — kind-based tool loop (`chat_completions` / `responses` / `messages`), streaming, usage, compact  
 - **`memory/`** — async SQLAlchemy sessions/messages  
 - **`tools/`** — workspace tools  
 - **`cli/`** — Click entry + slash registry (`awaitlet` bridges sync Click to async work)  

doc/architecture.md

@@ -8,13 +8,12 @@
             - config: Configurations for specified providers.
             - client: Clients for accessing existent specified services.
             - server: Servers for accepting other clients.
-        - openai
+        - openai_compatible: Chat Completions base (``kind=chat_completions``).
-        - openai_compatible
+        - openai: Platform Responses + chat (``kind=responses``).
-        - anthropic
+        - anthropic: Messages API (``kind=messages``).
-        - ollama
         - deepseek
             - openai_compat
-            - anthropic
+            - anthropic (convention extras; runtime uses openai_compat today)
     - utils: Common utilities for code architecture.
         - components: Utilities for class composition.
     - memory: Storage controlling for sessions and messages.
@@ -22,7 +21,10 @@
     - config: Plyngent configuration center (TOML), including ``[plugins]`` and
       ``[networking]`` (e.g. fetch SSRF Fake-IP CIDR exemptions). Model entries
       may override provider ``preset`` / ``url`` for mixed API routing.
-    - agent: Tool loop, streaming, usage, compact; `@tool` / tags / registry.
+    - runtime: ``create_client`` maps effective provider preset → protocol client.
+    - agent: Kind-based tool loop, streaming, usage, compact; bridges:
+      ``responses_bridge``/``responses_dispatch``, ``messages_bridge``/``messages_dispatch``;
+      ``@tool`` / tags / registry. History stays chat-completions-shaped.
     - tools: Workspace file/process/VCS/chat/todo/net tools; catalog; plugins;
       instance/session context and views.
     - prompting: Shared ask/choose/form for CLI and tools.

doc/plyngent.example.toml

@@ -89,9 +89,20 @@ access_key_or_token = "sk-replace-me"
 # "gpt-4o-mini" = { text = true }
 # # Model-level preset/url overrides let one provider route models via different APIs.
 # # `preset = "openai"` means /responses; `openai-compatible` means /chat/completions;
-# # `anthropic` means native /messages (support planned).
+# # `anthropic` means native /messages.
 # # "claude-sonnet" = { text = true, preset = "anthropic", url = "https://api.anthropic.com/v1" }
 
+# --- Anthropic (Messages API) ---
+# [providers.anthropic]
+# preset = "anthropic"
+# access_key_or_token = "sk-ant-replace-me"
+# # url defaults to https://api.anthropic.com/v1 when empty
+# timeout = { connect = 10, read = 600 }
+#
+# [providers.anthropic.models]
+# "claude-sonnet-4-20250514" = { text = true }
+# "claude-opus-4-20250514" = { text = true }
+
 # --- DeepSeek (OpenAI-compatible convention) ---
 # Default models if [providers.*.models] is omitted: deepseek-v4-flash, deepseek-v4-pro.
 # [providers.deepseek]