Revert "Merge pull request #3341 from ultraworkers/fix/rebase-on-main"

This reverts commit 734558eb31, reversing
changes made to 942805175a.

rust/crates/api/src/client.rs

@@ -15,13 +15,15 @@ pub enum ProviderClient {
 
 /// Provider selected explicitly by persisted/runtime configuration.
 ///
-/// This is intentionally separate from `ProviderKind`: DashScope speaks the
-/// OpenAI-compatible wire protocol but remains a distinct configured provider.
+/// This is intentionally separate from `ProviderKind`: Custom OpenAI and
+/// DashScope speak the OpenAI-compatible wire protocol but remain distinct
+/// configured providers.
 #[derive(Debug, Clone, Copy, PartialEq, Eq)]
 pub enum ProviderConfigKind {
     Anthropic,
     Xai,
     OpenAi,
+    CustomOpenAi,
     DashScope,
 }
 
@@ -96,9 +98,12 @@ impl ProviderClient {
 
                 Ok(Self::Xai(client))
             }
-            ProviderConfigKind::OpenAi | ProviderConfigKind::DashScope => {
+            ProviderConfigKind::OpenAi
+            | ProviderConfigKind::CustomOpenAi
+            | ProviderConfigKind::DashScope => {
                 let compat = match config.kind {
                     ProviderConfigKind::OpenAi => OpenAiCompatConfig::openai(),
+                    ProviderConfigKind::CustomOpenAi => OpenAiCompatConfig::custom_openai(),
                     ProviderConfigKind::DashScope => OpenAiCompatConfig::dashscope(),
                     _ => unreachable!("non-OpenAI provider reached compatibility path"),
                 };
@@ -403,6 +408,56 @@ mod tests {
         }
     }
 
+    #[test]
+    fn persisted_custom_openai_uses_its_own_environment_namespace() {
+        let _lock = env_lock();
+        let _custom_key = EnvVarGuard::set("CLAWCUSTOMOPENAI_API_KEY", Some("custom-key"));
+        let _custom_url = EnvVarGuard::set(
+            "CLAWCUSTOMOPENAI_BASE_URL",
+            Some("https://custom.example/v1"),
+        );
+        let _openai_key = EnvVarGuard::set("OPENAI_API_KEY", Some("openai-key"));
+        let _openai_url = EnvVarGuard::set("OPENAI_BASE_URL", Some("https://openai.example/v1"));
+        let _ollama = EnvVarGuard::set("OLLAMA_HOST", Some("http://localhost:11434"));
+
+        let config = ProviderConfig {
+            kind: ProviderConfigKind::CustomOpenAi,
+            model: "qwen-plus".to_string(),
+            api_key: None,
+            base_url: None,
+        };
+
+        match ProviderClient::from_config(&config).expect("custom OpenAI config should succeed") {
+            ProviderClient::OpenAi(client) => {
+                assert_eq!(client.base_url(), "https://custom.example/v1");
+            }
+            other => panic!("Expected custom OpenAI provider, got: {other:?}"),
+        }
+    }
+
+    #[test]
+    fn persisted_custom_openai_does_not_reuse_openai_credentials() {
+        let _lock = env_lock();
+        let _custom_key = EnvVarGuard::set("CLAWCUSTOMOPENAI_API_KEY", None);
+        let _custom_url = EnvVarGuard::set(
+            "CLAWCUSTOMOPENAI_BASE_URL",
+            Some("https://custom.example/v1"),
+        );
+        let _openai_key = EnvVarGuard::set("OPENAI_API_KEY", Some("openai-key"));
+        let _ollama = EnvVarGuard::set("OLLAMA_HOST", Some("http://localhost:11434"));
+
+        let config = ProviderConfig {
+            kind: ProviderConfigKind::CustomOpenAi,
+            model: "gpt-5".to_string(),
+            api_key: None,
+            base_url: None,
+        };
+
+        let error = ProviderClient::from_config(&config)
+            .expect_err("custom OpenAI must require its own credentials");
+        assert!(error.to_string().contains("CLAWCUSTOMOPENAI_API_KEY"));
+    }
+
     #[test]
     fn dashscope_model_uses_dashscope_config_not_openai() {
         // Regression: qwen-plus was being routed to OpenAiCompatConfig::openai()

rust/crates/api/src/providers/openai_compat.rs

@@ -42,6 +42,7 @@ pub struct OpenAiCompatConfig {
 
 const XAI_ENV_VARS: &[&str] = &["XAI_API_KEY"];
 const OPENAI_ENV_VARS: &[&str] = &["OPENAI_API_KEY"];
+const CUSTOM_OPENAI_ENV_VARS: &[&str] = &["CLAWCUSTOMOPENAI_API_KEY"];
 const DASHSCOPE_ENV_VARS: &[&str] = &["DASHSCOPE_API_KEY"];
 
 // Provider-specific request body size limits in bytes
@@ -80,6 +81,18 @@ impl OpenAiCompatConfig {
         }
     }
 
+    /// OpenAI-compatible endpoint with its own environment namespace and no default URL.
+    #[must_use]
+    pub const fn custom_openai() -> Self {
+        Self {
+            provider_name: "Custom OpenAI",
+            api_key_env: "CLAWCUSTOMOPENAI_API_KEY",
+            base_url_env: "CLAWCUSTOMOPENAI_BASE_URL",
+            default_base_url: "",
+            max_request_body_bytes: OPENAI_MAX_REQUEST_BODY_BYTES,
+        }
+    }
+
     /// Alibaba `DashScope` compatible-mode endpoint (Qwen family models).
     /// Uses the OpenAI-compatible REST shape at /compatible-mode/v1.
     /// Requested via Discord #clawcode-get-help: native Alibaba API for
@@ -100,6 +113,7 @@ impl OpenAiCompatConfig {
         match self.provider_name {
             "xAI" => XAI_ENV_VARS,
             "OpenAI" => OPENAI_ENV_VARS,
+            "Custom OpenAI" => CUSTOM_OPENAI_ENV_VARS,
             "DashScope" => DASHSCOPE_ENV_VARS,
             _ => &[],
         }

rust/crates/commands/src/lib.rs

@@ -5297,60 +5297,6 @@ fn mcp_server_json(name: &str, server: &ScopedMcpServerConfig) -> Value {
     })
 }
 
-fn render_session_status(session: &Session) -> String {
-    let message_count = session.messages.len();
-    let mut total_input = 0u32;
-    let mut total_output = 0u32;
-    for msg in &session.messages {
-        if let Some(usage) = msg.usage {
-            total_input = total_input.saturating_add(usage.input_tokens);
-            total_output = total_output.saturating_add(usage.output_tokens);
-        }
-    }
-    format!(
-        "Session {}: {} messages, {} input tokens, {} output tokens",
-        &session.session_id[0..8],
-        message_count,
-        total_input,
-        total_output
-    )
-}
-
-fn render_token_cost(session: &Session) -> String {
-    let mut total_input = 0u32;
-    let mut total_output = 0u32;
-    let mut cache_creation = 0u32;
-    let mut cache_read = 0u32;
-    for msg in &session.messages {
-        if let Some(usage) = msg.usage {
-            total_input = total_input.saturating_add(usage.input_tokens);
-            total_output = total_output.saturating_add(usage.output_tokens);
-            cache_creation = cache_creation.saturating_add(usage.cache_creation_input_tokens);
-            cache_read = cache_read.saturating_add(usage.cache_read_input_tokens);
-        }
-    }
-    format!(
-        "Cumulative token usage for this session:
-  Input tokens: {}
-  Output tokens: {}
-  Cache creation tokens: {}
-  Cache read tokens: {}
-  Total input: {}",
-        total_input,
-        total_output,
-        cache_creation,
-        cache_read,
-        total_input
-            .saturating_add(cache_creation)
-            .saturating_add(cache_read)
-    )
-}
-
-fn render_version_info() -> String {
-    let version = env!("CARGO_PKG_VERSION");
-    format!("claw-code version {}", version)
-}
-
 #[must_use]
 pub fn handle_slash_command(
     input: &str,
@@ -5388,19 +5334,8 @@ pub fn handle_slash_command(
             message: render_slash_command_help(),
             session: session.clone(),
         }),
-        SlashCommand::Status => Some(SlashCommandResult {
-            message: render_session_status(session),
-            session: session.clone(),
-        }),
-        SlashCommand::Cost => Some(SlashCommandResult {
-            message: render_token_cost(session),
-            session: session.clone(),
-        }),
-        SlashCommand::Version => Some(SlashCommandResult {
-            message: render_version_info(),
-            session: session.clone(),
-        }),
-        SlashCommand::Bughunter { .. }
+        SlashCommand::Status
+        | SlashCommand::Bughunter { .. }
         | SlashCommand::Commit
         | SlashCommand::Pr { .. }
         | SlashCommand::Issue { .. }
@@ -5411,6 +5346,7 @@ pub fn handle_slash_command(
         | SlashCommand::Model { .. }
         | SlashCommand::Permissions { .. }
         | SlashCommand::Clear { .. }
+        | SlashCommand::Cost
         | SlashCommand::Resume { .. }
         | SlashCommand::Config { .. }
         | SlashCommand::Workspace { .. }
@@ -5418,6 +5354,7 @@ pub fn handle_slash_command(
         | SlashCommand::Memory
         | SlashCommand::Init
         | SlashCommand::Diff
+        | SlashCommand::Version
         | SlashCommand::Export { .. }
         | SlashCommand::Session { .. }
         | SlashCommand::Plugins { .. }
@@ -6256,6 +6193,7 @@ mod tests {
     fn ignores_unknown_or_runtime_bound_slash_commands() {
         let session = Session::new();
         assert!(handle_slash_command("/unknown", &session, CompactionConfig::default()).is_none());
+        assert!(handle_slash_command("/status", &session, CompactionConfig::default()).is_none());
         assert!(handle_slash_command("/sandbox", &session, CompactionConfig::default()).is_none());
         assert!(
             handle_slash_command("/bughunter", &session, CompactionConfig::default()).is_none()
@@ -6287,6 +6225,7 @@ mod tests {
             handle_slash_command("/clear --confirm", &session, CompactionConfig::default())
                 .is_none()
         );
+        assert!(handle_slash_command("/cost", &session, CompactionConfig::default()).is_none());
         assert!(handle_slash_command(
             "/resume session.json",
             &session,
@@ -6305,6 +6244,7 @@ mod tests {
         );
         assert!(handle_slash_command("/mcp list", &session, CompactionConfig::default()).is_none());
         assert!(handle_slash_command("/diff", &session, CompactionConfig::default()).is_none());
+        assert!(handle_slash_command("/version", &session, CompactionConfig::default()).is_none());
         assert!(
             handle_slash_command("/export note.txt", &session, CompactionConfig::default())
                 .is_none()
@@ -7266,79 +7206,4 @@ mod tests {
         let _ = fs::remove_dir_all(config_home);
         let _ = fs::remove_dir_all(bundled_root);
     }
-
-    #[test]
-    fn status_command_shows_session_info() {
-        use runtime::TokenUsage;
-
-        let mut session = Session::new();
-        session.messages.push(ConversationMessage {
-            role: MessageRole::User,
-            blocks: vec![ContentBlock::Text {
-                text: "hello".to_string(),
-            }],
-            usage: Some(TokenUsage {
-                input_tokens: 10,
-                output_tokens: 20,
-                cache_creation_input_tokens: 0,
-                cache_read_input_tokens: 0,
-            }),
-        });
-        session.messages.push(ConversationMessage {
-            role: MessageRole::Assistant,
-            blocks: vec![ContentBlock::Text {
-                text: "response".to_string(),
-            }],
-            usage: Some(TokenUsage {
-                input_tokens: 5,
-                output_tokens: 15,
-                cache_creation_input_tokens: 0,
-                cache_read_input_tokens: 0,
-            }),
-        });
-
-        let result = handle_slash_command("/status", &session, CompactionConfig::default())
-            .expect("/status should be handled");
-        assert!(result.message.contains("2 messages"));
-        assert!(result.message.contains("15 input tokens"));
-        assert!(result.message.contains("35 output tokens"));
-        assert_eq!(result.session, session);
-    }
-
-    #[test]
-    fn cost_command_shows_token_usage() {
-        use runtime::TokenUsage;
-
-        let mut session = Session::new();
-        session.messages.push(ConversationMessage {
-            role: MessageRole::User,
-            blocks: vec![ContentBlock::Text {
-                text: "hello".to_string(),
-            }],
-            usage: Some(TokenUsage {
-                input_tokens: 100,
-                output_tokens: 200,
-                cache_creation_input_tokens: 50,
-                cache_read_input_tokens: 25,
-            }),
-        });
-
-        let result = handle_slash_command("/cost", &session, CompactionConfig::default())
-            .expect("/cost should be handled");
-        assert!(result.message.contains("100"));
-        assert!(result.message.contains("200"));
-        assert!(result.message.contains("50"));
-        assert!(result.message.contains("25"));
-        assert!(result.message.contains("Cumulative token usage"));
-        assert_eq!(result.session, session);
-    }
-
-    #[test]
-    fn version_command_shows_version() {
-        let session = Session::new();
-        let result = handle_slash_command("/version", &session, CompactionConfig::default())
-            .expect("/version should be handled");
-        assert!(result.message.contains("claw-code version"));
-        assert_eq!(result.session, session);
-    }
 }

rust/crates/rusty-claude-cli/src/main.rs

@@ -12910,6 +12910,7 @@ fn provider_config_from_runtime(
         "anthropic" => api::ProviderConfigKind::Anthropic,
         "xai" => api::ProviderConfigKind::Xai,
         "openai" => api::ProviderConfigKind::OpenAi,
+        "custom-openai" => api::ProviderConfigKind::CustomOpenAi,
         "dashscope" => api::ProviderConfigKind::DashScope,
         other => {
             return Err(format!(
@@ -12947,6 +12948,7 @@ fn explicit_provider_kind_for_model(
         Some("anthropic") => Some(api::ProviderConfigKind::Anthropic),
         Some("xai") => Some(api::ProviderConfigKind::Xai),
         Some("openai") | Some("local") => Some(api::ProviderConfigKind::OpenAi),
+        Some("custom-openai") => Some(api::ProviderConfigKind::CustomOpenAi),
         Some("dashscope") | Some("qwen") | Some("kimi") => Some(api::ProviderConfigKind::DashScope),
         _ => {
             let lower = resolved_model.to_ascii_lowercase();
@@ -19664,6 +19666,22 @@ UU conflicted.rs",
             super::explicit_provider_kind_for_model("openai/gpt-5", &config.model),
             Some(api::ProviderConfigKind::OpenAi)
         );
+        assert_eq!(
+            super::explicit_provider_kind_for_model("custom-openai/local-model", &config.model),
+            Some(api::ProviderConfigKind::CustomOpenAi)
+        );
+        assert_eq!(
+            super::explicit_provider_kind_for_model("CUSTOM-OPENAI/local-model", &config.model),
+            Some(api::ProviderConfigKind::CustomOpenAi)
+        );
+        assert_eq!(
+            super::explicit_provider_kind_for_model(
+                "custom-openai/local-model",
+                "custom-openai/local-model"
+            ),
+            None,
+            "matching custom model must keep the persisted provider kind"
+        );
         assert_eq!(
             super::explicit_provider_kind_for_model("qwen-plus", &config.model),
             None,
@@ -19704,6 +19722,44 @@ UU conflicted.rs",
         }
     }
 
+    #[test]
+    fn persisted_custom_openai_configuration_survives_runtime_boundary() {
+        let config_home = temp_dir();
+        let workspace = temp_dir();
+        fs::create_dir_all(&config_home).expect("config home");
+        fs::create_dir_all(&workspace).expect("workspace");
+        fs::write(
+            config_home.join("settings.json"),
+            r#"{
+              "provider": {
+                "kind": "custom-openai",
+                "apiKey": "custom-test-key",
+                "baseUrl": "https://custom.example/v1",
+                "model": "local-model"
+              },
+              "model": "local-model"
+            }"#,
+        )
+        .expect("write provider settings");
+
+        let loader = ConfigLoader::new(&workspace, &config_home);
+        let runtime_config = loader.load().expect("runtime config should load");
+        let provider_config = super::provider_config_from_runtime(runtime_config.provider())
+            .expect("custom provider configuration should adapt")
+            .expect("persisted provider configuration should be present");
+
+        assert_eq!(provider_config.kind, api::ProviderConfigKind::CustomOpenAi);
+        assert_eq!(provider_config.model, "local-model");
+        assert_eq!(provider_config.api_key.as_deref(), Some("custom-test-key"));
+        assert_eq!(
+            provider_config.base_url.as_deref(),
+            Some("https://custom.example/v1")
+        );
+
+        let _ = fs::remove_dir_all(config_home);
+        let _ = fs::remove_dir_all(workspace);
+    }
+
     #[test]
     fn persisted_provider_configuration_controls_runtime_provider_dispatch() {
         let config_home = temp_dir();

rust/crates/rusty-claude-cli/src/render.rs

@@ -249,16 +249,6 @@ impl TerminalRenderer {
 
     #[must_use]
     pub fn render_markdown(&self, markdown: &str) -> String {
-        self.render_markdown_raw(markdown).trim_end().to_string()
-    }
-
-    /// Render markdown to ANSI without trimming trailing whitespace.
-    ///
-    /// Block-level events (paragraphs, headings, lists, code blocks) emit their
-    /// trailing newline separators here. `render_markdown` trims them for
-    /// one-shot output, while streaming keeps them so that successive chunks
-    /// stay on their own lines instead of running together.
-    fn render_markdown_raw(&self, markdown: &str) -> String {
         let normalized = normalize_nested_fences(markdown);
         let mut output = String::new();
         let mut state = RenderState::default();
@@ -277,7 +267,30 @@ impl TerminalRenderer {
             );
         }
 
-        output
+        output.trim_end().to_string()
+    }
+
+    /// Ensures the output ends with at least `required` newlines.
+    /// This is idempotent: calling it multiple times with the same output
+    /// will not add extra newlines beyond what is needed.
+    /// The function is crucial for streaming rendering where chunks may
+    /// split at block boundaries, causing the parser to lose newlines
+    /// that normally separate blocks.
+    fn ensure_newlines(output: &mut String, required: usize) {
+        if output.is_empty() {
+            // Don't start with blank lines
+            return;
+        }
+
+        // Count trailing newlines
+        let trailing_newlines = output.chars().rev().take_while(|&c| c == '\n').count();
+
+        // Add newlines if we don't have enough
+        if trailing_newlines < required {
+            for _ in 0..(required - trailing_newlines) {
+                output.push('\n');
+            }
+        }
     }
 
     #[must_use]
@@ -285,18 +298,6 @@ impl TerminalRenderer {
         self.render_markdown(markdown)
     }
 
-    /// Stream-friendly variant of `markdown_to_ansi` that preserves trailing
-    /// block separators (such as a paragraph's closing newlines).
-    ///
-    /// `MarkdownStreamState::push` writes each rendered chunk directly to the
-    /// terminal with no separator of its own, so the trailing newlines must
-    /// survive here to keep a paragraph from sticking to the block that follows
-    /// it. The final `flush` still uses `markdown_to_ansi` to trim the tail.
-    #[must_use]
-    pub fn markdown_to_ansi_stream(&self, markdown: &str) -> String {
-        self.render_markdown_raw(markdown)
-    }
-
     #[allow(clippy::too_many_lines)]
     fn render_event(
         &self,
@@ -309,10 +310,14 @@ impl TerminalRenderer {
     ) {
         match event {
             Event::Start(Tag::Heading { level, .. }) => {
+                Self::ensure_newlines(output, 1);
                 Self::start_heading(state, level as u8, output);
             }
             Event::End(TagEnd::Paragraph) => output.push_str("\n\n"),
-            Event::Start(Tag::BlockQuote(..)) => self.start_quote(state, output),
+            Event::Start(Tag::BlockQuote(..)) => {
+                Self::ensure_newlines(output, 1);
+                self.start_quote(state, output);
+            }
             Event::End(TagEnd::BlockQuote(..)) => {
                 state.quote = state.quote.saturating_sub(1);
                 output.push('\n');
@@ -325,6 +330,7 @@ impl TerminalRenderer {
                 state.append_raw(output, "\n");
             }
             Event::Start(Tag::List(first_item)) => {
+                Self::ensure_newlines(output, 1);
                 let kind = match first_item {
                     Some(index) => ListKind::Ordered { next_index: index },
                     None => ListKind::Unordered,
@@ -337,6 +343,7 @@ impl TerminalRenderer {
             }
             Event::Start(Tag::Item) => Self::start_item(state, output),
             Event::Start(Tag::CodeBlock(kind)) => {
+                Self::ensure_newlines(output, 2);
                 *in_code_block = true;
                 *code_language = match kind {
                     CodeBlockKind::Indented => String::from("text"),
@@ -360,7 +367,10 @@ impl TerminalRenderer {
                     format!("{}", format!("`{code}`").with(self.color_theme.inline_code));
                 state.append_raw(output, &rendered);
             }
-            Event::Rule => output.push_str("---\n"),
+            Event::Rule => {
+                Self::ensure_newlines(output, 1);
+                output.push_str("---\n");
+            }
             Event::Text(text) => {
                 self.push_text(text.as_ref(), state, output, code_buffer, *in_code_block);
             }
@@ -405,7 +415,10 @@ impl TerminalRenderer {
                 );
                 state.append_raw(output, &rendered);
             }
-            Event::Start(Tag::Table(..)) => state.table = Some(TableState::default()),
+            Event::Start(Tag::Table(..)) => {
+                Self::ensure_newlines(output, 1);
+                state.table = Some(TableState::default());
+            }
             Event::End(TagEnd::Table) => {
                 if let Some(table) = state.table.take() {
                     output.push_str(&self.render_table(&table));
@@ -619,9 +632,21 @@ impl TerminalRenderer {
     }
 }
 
-#[derive(Debug, Default, Clone, PartialEq, Eq)]
+#[derive(Debug, Clone, PartialEq, Eq)]
 pub struct MarkdownStreamState {
     pending: String,
+    /// Track whether the last emitted output ended with a newline.
+    /// Used to ensure proper spacing when resuming from a buffer.
+    last_output_ends_with_newline: bool,
+}
+
+impl Default for MarkdownStreamState {
+    fn default() -> Self {
+        Self {
+            pending: String::new(),
+            last_output_ends_with_newline: false,
+        }
+    }
 }
 
 impl MarkdownStreamState {
@@ -631,7 +656,40 @@ impl MarkdownStreamState {
         let split = find_stream_safe_boundary(&self.pending)?;
         let ready = self.pending[..split].to_string();
         self.pending.drain(..split);
-        Some(renderer.markdown_to_ansi_stream(&ready))
+
+        let mut rendered = renderer.markdown_to_ansi(&ready);
+        let stripped = strip_ansi(&rendered);
+
+        // If the previous output didn't end with a newline and this chunk starts
+        // with a block-level element, ensure proper spacing before it.
+        if !self.last_output_ends_with_newline && !rendered.is_empty() {
+            if stripped.starts_with("\u{256d}\u{2500}")
+                || stripped.starts_with("```")
+                || stripped.starts_with("|")
+                || stripped.starts_with("• ")
+                || stripped.starts_with("1. ")
+                || stripped.starts_with("-")
+            {
+                rendered = format!("\n\n{}", rendered);
+            }
+        }
+
+        // When markdown ends with a code block closing marker or other block-level element,
+        // render_markdown() trims the trailing newlines that finish_code_block() added.
+        // For streaming, we need to restore these newlines so proper spacing is preserved
+        // when chunks are combined. This is critical for idempotence across re-renders.
+        if stripped.ends_with("\u{2570}\u{2500}")
+            || stripped.ends_with("---")
+            || stripped.ends_with("|")
+        {
+            // Block element that should have trailing spacing
+            if !rendered.ends_with('\n') {
+                rendered.push_str("\n\n");
+            }
+        }
+
+        self.last_output_ends_with_newline = rendered.ends_with('\n');
+        Some(rendered)
     }
 
     #[must_use]
@@ -641,7 +699,26 @@ impl MarkdownStreamState {
             None
         } else {
             let pending = std::mem::take(&mut self.pending);
-            Some(renderer.markdown_to_ansi(&pending))
+            let mut rendered = renderer.markdown_to_ansi(&pending);
+
+            // If the previous output didn't end with a newline and this output
+            // starts with a block-level element, ensure proper spacing.
+            if !self.last_output_ends_with_newline && !rendered.is_empty() {
+                // Check if output starts with a block element by looking for common markers
+                let stripped = strip_ansi(&rendered);
+                if stripped.starts_with("\u{256d}\u{2500}")
+                    || stripped.starts_with("```")
+                    || stripped.starts_with("|")
+                    || stripped.starts_with("• ")
+                    || stripped.starts_with("1. ")
+                    || stripped.starts_with("-")
+                {
+                    rendered = format!("\n\n{}", rendered);
+                }
+            }
+
+            self.last_output_ends_with_newline = rendered.ends_with('\n');
+            Some(rendered)
         }
     }
 }
@@ -835,6 +912,11 @@ fn normalize_nested_fences(markdown: &str) -> String {
     out
 }
 
+/// Find a safe boundary for streaming markdown rendering.
+/// Safe boundaries are:
+/// - After a closing fence line (when fence is closed)
+/// - After an empty line
+/// This function returns the position of the last safe boundary found.
 fn find_stream_safe_boundary(markdown: &str) -> Option<usize> {
     let mut open_fence: Option<FenceMarker> = None;
     let mut last_boundary = None;
@@ -1074,34 +1156,6 @@ mod tests {
         assert!(plain_text.contains("fn nested()"));
     }
 
-    #[test]
-    fn stream_rendering_preserves_block_separators() {
-        let renderer = TerminalRenderer::new();
-
-        // The stream variant keeps the paragraph-ending newlines that the
-        // one-shot variant trims, so consecutive streamed chunks do not run
-        // into each other when written back-to-back to the terminal.
-        let streamed = renderer.markdown_to_ansi_stream("Intro paragraph.\n\n");
-        assert!(streamed.ends_with('\n'));
-        assert!(!renderer
-            .markdown_to_ansi("Intro paragraph.\n\n")
-            .ends_with('\n'));
-
-        let mut state = MarkdownStreamState::default();
-        let first = state
-            .push(&renderer, "Intro paragraph.\n\n")
-            .expect("blank line closes the paragraph block");
-        let second = state
-            .push(&renderer, "1. first item\n\n")
-            .expect("blank line closes the list block");
-
-        let combined = strip_ansi(&format!("{first}{second}"));
-        assert!(combined.contains("Intro paragraph."));
-        assert!(combined.contains("1. first item"));
-        // The two blocks stay on separate lines instead of sticking together.
-        assert!(!combined.contains("Intro paragraph.1."));
-    }
-
     #[test]
     fn spinner_advances_frames() {
         let terminal_renderer = TerminalRenderer::new();
@@ -1117,4 +1171,189 @@ mod tests {
         let output = String::from_utf8_lossy(&out);
         assert!(output.contains("Working"));
     }
+
+    #[test]
+    fn streaming_text_before_code_block_preserves_newline_boundary() {
+        let renderer = TerminalRenderer::new();
+        let mut state = MarkdownStreamState::default();
+
+        // Simulate streaming: paragraph text arrives in one chunk
+        assert_eq!(
+            state.push(&renderer, "This is some text."),
+            None,
+            "incomplete paragraph should not flush"
+        );
+
+        // Then code block arrives in the next chunk
+        let rendered = state
+            .push(&renderer, "\n\n```rust\nfn main() {}\n```\n")
+            .expect("fenced block should trigger flush");
+        let plain_text = strip_ansi(&rendered);
+
+        // Verify the paragraph text and code block are present
+        assert!(plain_text.contains("This is some text."));
+        assert!(plain_text.contains("fn main()"));
+
+        // The critical check: there should be a blank line between the paragraph and code block
+        // The paragraph ends, then there should be newlines before the code block marker
+        let lines: Vec<&str> = plain_text.lines().collect();
+        let text_line_idx = lines
+            .iter()
+            .position(|line| line.contains("This is some text."))
+            .expect("find text line");
+        // Skip past the text line and find the code block
+        let code_marker_idx = lines[text_line_idx + 1..]
+            .iter()
+            .position(|line| line.contains("╭─ rust"))
+            .map(|i| i + text_line_idx + 1);
+
+        // There should be at least one empty line between the text and the code block marker
+        if let Some(code_idx) = code_marker_idx {
+            assert!(
+                code_idx > text_line_idx + 1,
+                "there should be spacing between paragraph and code block"
+            );
+        }
+    }
+
+    #[test]
+    fn rendering_paragraph_immediately_before_code_block_has_blank_line() {
+        let renderer = TerminalRenderer::new();
+        let markdown = "This is a paragraph.\n\n```rust\nfn main() {}\n```";
+        let output = renderer.markdown_to_ansi(markdown);
+        let plain_text = strip_ansi(&output);
+        let lines: Vec<&str> = plain_text.lines().collect();
+
+        // Find the paragraph and code block
+        let text_idx = lines
+            .iter()
+            .position(|l| l.contains("This is a paragraph."))
+            .expect("find paragraph");
+        let code_idx = lines[text_idx + 1..]
+            .iter()
+            .position(|l| l.contains("╭─ rust"))
+            .map(|i| i + text_idx + 1)
+            .expect("find code block");
+
+        // There should be at least one blank line between them
+        assert!(
+            code_idx > text_idx + 1,
+            "code block should not immediately follow paragraph"
+        );
+    }
+
+    #[test]
+    fn code_block_ending_with_trailing_text_preserves_spacing() {
+        let renderer = TerminalRenderer::new();
+        let markdown = "```rust\nfn main() {}\n```\n\nText after.";
+        let output = renderer.markdown_to_ansi(markdown);
+        let plain_text = strip_ansi(&output);
+
+        // The code block should end with "╰─" followed by blank lines, then text
+        assert!(
+            plain_text.contains("\u{256d}\u{2500}"),
+            "should contain code block close marker"
+        );
+        assert!(
+            plain_text.contains("\n\nText"),
+            "should have blank line before text"
+        );
+    }
+
+    #[test]
+    fn streaming_code_block_preserves_trailing_newlines() {
+        let renderer = TerminalRenderer::new();
+        let mut state = MarkdownStreamState::default();
+        let markdown = "Text before.\n\n```rust\nfn test() {}\n```\n\nText after.";
+
+        // Debug: let's check what the code block part alone renders to
+        let code_part = "```rust\nfn test() {}\n```\n\nText after.";
+        let code_rendered = strip_ansi(&renderer.markdown_to_ansi(code_part));
+
+        // Simulate the streaming at split position 1
+        let r1 = state.push(&renderer, "T").map(|s| strip_ansi(&s));
+        let r2 = state
+            .push(
+                &renderer,
+                "ext before.\n\n```rust\nfn test() {}\n```\n\nText after.",
+            )
+            .map(|s| strip_ansi(&s));
+
+        // After r2, the pending should contain the code block part
+        let pending_before_r3 = state.pending.clone();
+
+        let r3 = state.flush(&renderer).map(|s| strip_ansi(&s));
+
+        // Combine the results
+        let mut full_streamed = String::new();
+        if let Some(s) = &r1 {
+            full_streamed.push_str(s);
+        }
+        if let Some(s) = &r2 {
+            full_streamed.push_str(s);
+        }
+        if let Some(s) = &r3 {
+            full_streamed.push_str(s);
+        }
+
+        let full_rendered = strip_ansi(&renderer.markdown_to_ansi(markdown));
+
+        assert_eq!(full_streamed, full_rendered,
+            "Streaming mismatch.\n\nCode part alone renders to: {:?}\nPending before r3: {:?}\n\nBreakdown:\n  r1: {:?}\n  r2: {:?}\n  r3: {:?}\n\nExpected:\n{:?}\n\nGot:\n{:?}",
+            code_rendered, pending_before_r3, r1, r2, r3, full_rendered, full_streamed);
+    }
+
+    #[test]
+    fn streaming_with_split_at_every_byte_position_produces_consistent_output() {
+        let renderer = TerminalRenderer::new();
+        let markdown = "Text before.\n\n```rust\nfn test() {}\n```\n\nText after.";
+
+        // First, render the full document
+        let full_output = renderer.markdown_to_ansi(markdown);
+        let full_plain = strip_ansi(&full_output);
+
+        // Now simulate streaming by splitting at different positions
+        for split_pos in 1..markdown.len() {
+            let mut state = MarkdownStreamState::default();
+            let part1 = &markdown[..split_pos];
+            let part2 = &markdown[split_pos..];
+
+            // Try to push both parts
+            let r1 = state.push(&renderer, part1);
+            let r2 = state.push(&renderer, part2);
+            let final_r = state.flush(&renderer);
+
+            // Reconstruct the streamed output
+            let mut streamed_output = String::new();
+            if let Some(out) = r1 {
+                streamed_output.push_str(&out);
+            }
+            if let Some(out) = r2 {
+                streamed_output.push_str(&out);
+            }
+            if let Some(out) = final_r {
+                streamed_output.push_str(&out);
+            }
+
+            let streamed_plain = strip_ansi(&streamed_output);
+
+            if streamed_plain != full_plain {
+                eprintln!("\n=== MISMATCH at split position {} ===", split_pos);
+                eprintln!("Part 1: {:?}", part1);
+                eprintln!("Part 2: {:?}", part2);
+                eprintln!("\nExpected (full):");
+                eprintln!("{:?}", full_plain);
+                eprintln!("\nGot (streamed):");
+                eprintln!("{:?}", streamed_plain);
+                eprintln!("\nStreamed rendered output:");
+                eprintln!("{:?}", streamed_output);
+            }
+
+            assert_eq!(
+                streamed_plain, full_plain,
+                "streaming with split at position {} produces different output",
+                split_pos
+            );
+        }
+    }
 }

rust/crates/rusty-claude-cli/src/setup_wizard.rs

@@ -9,7 +9,7 @@ const PROVIDERS: &[(&str, &str, &str)] = &[
     ("2", "xAI / Grok", "xai"),
     ("3", "OpenAI", "openai"),
     ("4", "DashScope (Qwen/Kimi)", "dashscope"),
-    ("5", "Custom (OpenAI-compat)", "openai"),
+    ("5", "Custom (OpenAI-compat)", "custom-openai"),
 ];
 
 const PROVIDER_MODELS: &[(&str, &[&str])] = &[
@@ -27,6 +27,8 @@ const DEFAULT_BASE_URLS: &[(&str, &str)] = &[
         "dashscope",
         "https://dashscope.aliyuncs.com/compatible-mode/v1",
     ),
+    // Custom OpenAI has no default; user must supply.
+    ("custom-openai", ""),
 ];
 
 const API_KEY_ENV_VARS: &[(&str, &str)] = &[
@@ -34,6 +36,7 @@ const API_KEY_ENV_VARS: &[(&str, &str)] = &[
     ("xai", "XAI_API_KEY"),
     ("openai", "OPENAI_API_KEY"),
     ("dashscope", "DASHSCOPE_API_KEY"),
+    ("custom-openai", "CLAWCUSTOMOPENAI_API_KEY"),
 ];
 
 pub fn run_setup_wizard() -> Result<(), Box<dyn std::error::Error>> {
@@ -177,6 +180,7 @@ fn prompt_base_url(
         "xai" => "XAI_BASE_URL",
         "openai" => "OPENAI_BASE_URL",
         "dashscope" => "DASHSCOPE_BASE_URL",
+        "custom-openai" => "CLAWCUSTOMOPENAI_BASE_URL",
         _ => "BASE_URL",
     };
     let env_set = std::env::var(env_var).ok().is_some_and(|v| !v.is_empty());
@@ -214,7 +218,11 @@ fn prompt_model(
     if !aliases.is_empty() {
         println!("    Common: {}", aliases.join(", "));
     }
-    println!("    Or enter any model name (e.g. openai/gpt-4.1-mini for custom routing)");
+    if kind == "custom-openai" {
+        println!("    Or enter any model name (e.g. custom/gpt-4.1 for custom routing)");
+    } else {
+        println!("    Or enter any model name (e.g. openai/gpt-4.1-mini for custom routing)");
+    }
 
     let input = read_line(&format!("  Model [{current_model}]: "))?;
     if input.trim().is_empty() {