auth: openai_responses provider for Codex subscription (Tier 2)

Add the OpenAI Responses API wire dialect (openai_responses APIStyle +
OpenAIResponsesConfig), a request serializer (instructions/input items,
flat function tools, reasoning, store:false, include encrypted reasoning),
and a streaming state machine over the typed response.* SSE events mapping
to the shared block model. Wire dispatch, buildProviderConfig, the C-ABI
free switch, and the reasoning selectors. Ship a commented Codex example in
the default config.

Implemented from the Responses API docs + the open-source Codex client and
covered by fixture tests; live verification against a ChatGPT plan is still
required (documented).

1 files changed, 8 insertions, 0 deletions

diff --git a/libpanto-c/src/lib.zig b/libpanto-c/src/lib.zig
index 78202fb..888c6d6 100644
--- a/libpanto-c/src/lib.zig
+++ b/libpanto-c/src/lib.zig
@@ -368,6 +368,14 @@ fn freeProvider(pv: *panto.ProviderConfig) void {
             allocator.free(c.model);
             if (c.api_version.ptr != "2023-06-01".ptr) allocator.free(c.api_version);
         },
+        // The Responses style is not constructible across the C ABI (no
+        // PantoAPIStyle variant), so `convertProvider` never builds it; this
+        // case exists only to keep the union switch exhaustive.
+        .openai_responses => |c| {
+            allocator.free(c.api_key);
+            allocator.free(c.base_url);
+            allocator.free(c.model);
+        },
     }
 }