feat(TASK-043): Responses usage parsing, failure hardening, responses default for stock openai

Parse Responses-API token usage on both wires: non-streaming responses
fill ChatCompletionsOutput.usage and response.completed events feed the
SseHandler accumulator, with cached input mapped from
input_tokens_details.cached_tokens. Harden failure paths: bail with the
payload message on response.failed and error stream events, and surface
incomplete_details.reason when a non-streaming response comes back
incomplete and empty.

Replay hardening: id-only Reasoning blocks (no encrypted_content) are
dropped at replay time since the API 400s on them under store:false,
which would permanently wedge a persisted session; a null summary is
normalized to [] at the same site. Claude's replay guards flip to a
positive Thinking/RedactedThinking allow-list.

Flip the default wire for stock openai (api.openai.com, no custom
api_base) to Responses. The resolver call site now passes a genuine
stock-openai predicate: api-key clients or stock oauth without api_base
qualify, config-oauth gateways never do. Custom api_base and
openai-compatible clients keep defaulting to chat; explicit wire_api
still always wins. Also reject a non-map responses section in
RequestPatch via test.

src/client/common.rs

@@ -1640,6 +1640,15 @@ mod tests {
         assert!(patch.chat_completions.is_some());
     }
 
+    #[test]
+    fn non_map_request_patch_responses_section_is_rejected() {
+        let err = serde_json::from_value::<RequestPatch>(json!({"responses": "bogus"}))
+            .unwrap_err()
+            .to_string();
+
+        assert!(err.contains("expected a map"), "unexpected error: {err}");
+    }
+
     #[test]
     fn chat_client_patch_never_touches_the_responses_wire() {
         let client = patch_probe(