Add Codex Responses support and session debugging

Teach provider config and auth resolution about the Codex Responses
dialect, including user-facing `style = "openai_responses"` with
`dialect = "codex"`. Serialize and parse Responses traffic with
provider-specific reasoning replay, assistant phase metadata, and robust
function-call assembly keyed by `output_index` so streamed tool inputs
survive proxy quirks and empty terminal payloads.

Also persist thinking origins and message metadata across sessions, add
the Anthropic interleaved-thinking header switch, write per-session
debug logs, and improve the TUI and scripts for inspecting tool output
and session costs.

1 files changed, 12 insertions, 0 deletions

diff --git a/libpanto/src/provider.zig b/libpanto/src/provider.zig
index 9c715b7..3c3b52e 100644
--- a/libpanto/src/provider.zig
+++ b/libpanto/src/provider.zig
@@ -326,6 +326,18 @@ pub fn openStream(
             const rr = try req.open(conv, registry);
             return rr.providerStream();
         },
+        .openai_codex_responses => |*c| {
+            var req: provider_openai_responses.OpenAIResponsesRequest = .{
+                .allocator = allocator,
+                .io = io,
+                .config = c,
+                .dialect = .codex,
+                .http_client = client,
+                .diag = diag,
+            };
+            const rr = try req.open(conv, registry);
+            return rr.providerStream();
+        },
     }
 }