feat(llm): support OpenAI Responses API via per-provider api_type

README.md

@@ -8,6 +8,7 @@ model/provider switching, and local tools.
 
 - TUI-first chat experience with a light theme by default.
 - OpenAI-compatible `/v1/chat/completions` provider support.
+- OpenAI Responses API (`/v1/responses`) provider support.
 - Multiple providers from `~/.agentu/config.yaml`.
 - Session-only provider, model, and thinking-level switching.
 - Read-only project tools enabled by default.
@@ -48,6 +49,7 @@ Use `--config <path>` to load another file.
 ```yaml
 providers:
   loveuer:
+    api_type: chat
     base_url: https://ai.loveuer.com
     api_key: ${AGENTU_API_KEY}
     models:
@@ -64,6 +66,19 @@ Provider names are the keys under `providers`. At startup, agentu selects the
 first provider by name. Use `/model provider <name>` to switch providers for the
 current session.
 
+`api_type` selects which API protocol the provider speaks:
+
+```text
+chat      OpenAI-compatible /v1/chat/completions (default)
+responses OpenAI Responses API /v1/responses
+```
+
+The Responses API client converts the conversation history to Responses input
+items (`user`/`assistant`/`system` messages, `function_call`, and
+`function_call_output`), streams `response.output_text.delta` events, and
+supports function calling through `response.output_item.added`,
+`response.function_call_arguments.delta`, and `response.output_item.done`.
+
 `models` is required. `/model model <name>` is restricted to that list. Each
 entry is an object with:
 
@@ -83,7 +98,10 @@ none, middle, high, xhigh, max
 ```
 
 When configured or changed with `/model thinking ...`, the value is sent as a
-top-level OpenAI-compatible request field named `thinking`.
+top-level request field named `thinking`. For OpenAI reasoning models on the
+Responses API, set `thinking_param: reasoning` so the level is sent as the
+official `reasoning: {"effort": ...}` field; agentu maps its `middle` level to
+the official `medium` value and passes `none`, `high`, `xhigh`, `max` through.
 
 ## CLI Flags
 
@@ -174,5 +192,8 @@ Local config and build outputs are intentionally ignored by git.
 
 - Provider/model/thinking changes are session-only; agentu does not write them
   back to `~/.agentu/config.yaml`.
+- `api_type` is per provider and cannot be changed at runtime; use
+  `/model provider <name>` to switch to a provider configured with a different
+  API type.
 - The config schema is intentionally strict during MVP development. Deprecated
   fields such as `provider` or `active_provider` are rejected.