Complete comprehensive Codex → LLMX branding update

Fixed all remaining user-facing "Codex" references across entire codebase:
- Updated all UI strings and error messages
- Fixed GitHub issue templates and workflows
- Updated MCP server tool descriptions and error messages
- Fixed all test messages and comments
- Updated documentation comments
- Changed auth keyring service name to "LLMX Auth"

Reduced from 201 occurrences to only code identifiers (struct/type names).
Changes span 78 files across Rust, Python, YAML, and JSON.

🤖 Generated with Claude Code

Co-Authored-By: Claude <noreply@anthropic.com>

llmx-rs/core/tests/suite/cli_stream.rs

@@ -126,7 +126,7 @@ async fn exec_cli_applies_experimental_instructions_file() {
     let custom_path_str = custom_path.to_string_lossy().replace('\\', "/");
 
     // Build a provider override that points at the mock server and instructs
-    // Codex to use the Responses API with the dummy env var.
+    // LLMX to use the Responses API with the dummy env var.
     let provider_override = format!(
         "model_providers.mock={{ name = \"mock\", base_url = \"{}/v1\", env_key = \"PATH\", wire_api = \"responses\" }}",
         server.uri()

llmx-rs/core/tests/suite/client.rs

@@ -240,7 +240,7 @@ async fn resume_includes_initial_messages_and_sends_prior_items() {
         responses::mount_sse_once_match(&server, path("/v1/responses"), sse_completed("resp1"))
             .await;
 
-    // Configure Codex to resume from our file
+    // Configure LLMX to resume from our file
     let model_provider = ModelProviderInfo {
         base_url: Some(format!("{}/v1", server.uri())),
         ..built_in_model_providers()["openai"].clone()
@@ -1325,7 +1325,7 @@ fn create_dummy_codex_auth() -> CodexAuth {
 /// We assert that the `input` sent on each turn contains the expected conversation history
 #[tokio::test(flavor = "multi_thread", worker_threads = 2)]
 async fn history_dedupes_streamed_and_final_messages_across_turns() {
-    // Skip under Codex sandbox network restrictions (mirrors other tests).
+    // Skip under LLMX sandbox network restrictions (mirrors other tests).
     skip_if_no_network!();
 
     // Mock server that will receive three sequential requests and return the same SSE stream

llmx-rs/core/tests/suite/compact.rs

@@ -122,7 +122,7 @@ async fn summarize_context_three_requests_and_instructions() {
     };
     let third_request_mock = mount_sse_once_match(&server, third_matcher, sse3).await;
 
-    // Build config pointing to the mock server and spawn Codex.
+    // Build config pointing to the mock server and spawn LLMX.
     let model_provider = ModelProviderInfo {
         base_url: Some(format!("{}/v1", server.uri())),
         ..built_in_model_providers()["openai"].clone()
@@ -257,7 +257,7 @@ async fn summarize_context_three_requests_and_instructions() {
         "third request should not include the summarize trigger"
     );
 
-    // Shut down Codex to flush rollout entries before inspecting the file.
+    // Shut down LLMX to flush rollout entries before inspecting the file.
     codex.submit(Op::Shutdown).await.unwrap();
     wait_for_event(&codex, |ev| matches!(ev, EventMsg::ShutdownComplete)).await;
 

llmx-rs/core/tests/suite/compact_resume_fork.rs

@@ -4,7 +4,7 @@
 //!
 //! Each test sets up a mocked SSE conversation and drives the conversation through
 //! a specific sequence of operations. After every operation we capture the
-//! request payload that Codex would send to the model and assert that the
+//! request payload that LLMX would send to the model and assert that the
 //! model-visible history matches the expected sequence of messages.
 
 use super::compact::COMPACT_WARNING_MESSAGE;

llmx-rs/core/tests/suite/fork_conversation.rs

@@ -44,7 +44,7 @@ async fn fork_conversation_twice_drops_to_first_message() {
         .mount(&server)
         .await;
 
-    // Configure Codex to use the mock server.
+    // Configure LLMX to use the mock server.
     let model_provider = ModelProviderInfo {
         base_url: Some(format!("{}/v1", server.uri())),
         ..built_in_model_providers()["openai"].clone()

llmx-rs/core/tests/suite/quota_exceeded.rs

@@ -66,7 +66,7 @@ async fn quota_exceeded_emits_single_error_event() -> Result<()> {
         }
     }
 
-    assert_eq!(error_events, 1, "expected exactly one Codex:Error event");
+    assert_eq!(error_events, 1, "expected exactly one LLMX:Error event");
 
     Ok(())
 }

llmx-rs/core/tests/suite/review.rs

@@ -40,7 +40,7 @@ use wiremock::matchers::path;
 /// in that order when the model returns a structured review JSON payload.
 #[tokio::test(flavor = "multi_thread", worker_threads = 2)]
 async fn review_op_emits_lifecycle_and_review_output() {
-    // Skip under Codex sandbox network restrictions.
+    // Skip under LLMX sandbox network restrictions.
     skip_if_no_network!();
 
     // Start mock Responses API server. Return a single assistant message whose

llmx-rs/core/tests/suite/undo.rs

@@ -68,12 +68,12 @@ fn init_git_repo(path: &Path) -> Result<()> {
     // CI variance (default-branch hints, line ending differences, etc.).
     git(path, &["init", "--initial-branch=main"])?;
     git(path, &["config", "core.autocrlf", "false"])?;
-    git(path, &["config", "user.name", "Codex Tests"])?;
+    git(path, &["config", "user.name", "LLMX Tests"])?;
     git(path, &["config", "user.email", "codex-tests@example.com"])?;
 
     // Create README.txt
     let readme_path = path.join("README.txt");
-    fs::write(&readme_path, "Test repository initialized by Codex.\n")?;
+    fs::write(&readme_path, "Test repository initialized by LLMX.\n")?;
 
     // Stage and commit
     git(path, &["add", "README.txt"])?;

llmx-rs/core/tests/suite/view_image.rs

@@ -382,7 +382,7 @@ async fn view_image_tool_placeholder_for_non_image_files() -> anyhow::Result<()>
             content.iter().find_map(|span| {
                 if span.get("type").and_then(Value::as_str) == Some("input_text") {
                     let text = span.get("text").and_then(Value::as_str)?;
-                    if text.contains("Codex could not read the local image at")
+                    if text.contains("LLMX could not read the local image at")
                         && text.contains("unsupported MIME type `application/json`")
                     {
                         return Some(text.to_string());