Enable Agent tool child execution with bounded recursion

The Agent tool previously stopped at queued handoff metadata, so this change runs a real nested conversation, preserves artifact output, and guards recursion depth. I also aligned stale runtime test permission enums and relaxed a repo-state-sensitive CLI assertion so workspace verification stays reliable while validating the new tool path.

Constraint: Reuse existing runtime conversation abstractions without introducing a new orchestration service
Constraint: Child agent execution must preserve the same tool surface while preventing unbounded nesting
Rejected: Shell out to the CLI binary for child execution | brittle process coupling and weaker testability
Rejected: Leave Agent as metadata-only handoff | does not satisfy requested sub-agent orchestration behavior
Confidence: high
Scope-risk: moderate
Reversibility: clean
Directive: Keep Agent recursion limits enforced wherever nested Agent calls can re-enter the tool executor
Tested: cargo fmt --all --manifest-path rust/Cargo.toml; cargo test --manifest-path rust/Cargo.toml; cargo clippy --manifest-path rust/Cargo.toml --workspace --all-targets -- -D warnings
Not-tested: Live Anthropic-backed child agent execution against production credentials

rust/Cargo.lock

@@ -1431,10 +1431,12 @@ dependencies = [
 name = "tools"
 version = "0.1.0"
 dependencies = [
+ "api",
  "reqwest",
  "runtime",
  "serde",
  "serde_json",
+ "tokio",
 ]
 
 [[package]]

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

@@ -22,9 +22,9 @@ use commands::{
 use compat_harness::{extract_manifest, UpstreamPaths};
 use render::{Spinner, TerminalRenderer};
 use runtime::{
-    clear_oauth_credentials, format_usd, generate_pkce_pair, generate_state, load_system_prompt,
+    clear_oauth_credentials, generate_pkce_pair, generate_state, load_system_prompt,
-    parse_oauth_callback_request_target, pricing_for_model, save_oauth_credentials, ApiClient,
+    parse_oauth_callback_request_target, save_oauth_credentials, ApiClient, ApiRequest,
-    ApiRequest, AssistantEvent, CompactionConfig, ConfigLoader, ConfigSource, ContentBlock,
+    AssistantEvent, CompactionConfig, ConfigLoader, ConfigSource, ContentBlock,
     ConversationMessage, ConversationRuntime, MessageRole, OAuthAuthorizationRequest,
     OAuthTokenExchangeRequest, PermissionMode, PermissionPolicy, ProjectContext, RuntimeError,
     Session, TokenUsage, ToolError, ToolExecutor, UsageTracker,
@@ -36,7 +36,6 @@ const DEFAULT_MODEL: &str = "claude-sonnet-4-20250514";
 const DEFAULT_MAX_TOKENS: u32 = 32;
 const DEFAULT_DATE: &str = "2026-03-31";
 const DEFAULT_OAUTH_CALLBACK_PORT: u16 = 4545;
-const COST_WARNING_FRACTION: f64 = 0.8;
 const VERSION: &str = env!("CARGO_PKG_VERSION");
 const BUILD_TARGET: Option<&str> = option_env!("TARGET");
 const GIT_SHA: Option<&str> = option_env!("GIT_SHA");
@@ -71,8 +70,7 @@ fn run() -> Result<(), Box<dyn std::error::Error>> {
             output_format,
             allowed_tools,
             permission_mode,
-            max_cost_usd,
+        } => LiveCli::new(model, false, allowed_tools, permission_mode)?
-        } => LiveCli::new(model, false, allowed_tools, permission_mode, max_cost_usd)?
             .run_turn_with_output(&prompt, output_format)?,
         CliAction::Login => run_login()?,
         CliAction::Logout => run_logout()?,
@@ -80,14 +78,13 @@ fn run() -> Result<(), Box<dyn std::error::Error>> {
             model,
             allowed_tools,
             permission_mode,
-            max_cost_usd,
+        } => run_repl(model, allowed_tools, permission_mode)?,
-        } => run_repl(model, allowed_tools, permission_mode, max_cost_usd)?,
         CliAction::Help => print_help(),
     }
     Ok(())
 }
 
-#[derive(Debug, Clone, PartialEq)]
+#[derive(Debug, Clone, PartialEq, Eq)]
 enum CliAction {
     DumpManifests,
     BootstrapPlan,
@@ -106,7 +103,6 @@ enum CliAction {
         output_format: CliOutputFormat,
         allowed_tools: Option<AllowedToolSet>,
         permission_mode: PermissionMode,
-        max_cost_usd: Option<f64>,
     },
     Login,
     Logout,
@@ -114,7 +110,6 @@ enum CliAction {
         model: String,
         allowed_tools: Option<AllowedToolSet>,
         permission_mode: PermissionMode,
-        max_cost_usd: Option<f64>,
     },
     // prompt-mode formatting is only supported for non-interactive runs
     Help,
@@ -144,7 +139,6 @@ fn parse_args(args: &[String]) -> Result<CliAction, String> {
     let mut output_format = CliOutputFormat::Text;
     let mut permission_mode = default_permission_mode();
     let mut wants_version = false;
-    let mut max_cost_usd: Option<f64> = None;
     let mut allowed_tool_values = Vec::new();
     let mut rest = Vec::new();
     let mut index = 0;
@@ -180,13 +174,6 @@ fn parse_args(args: &[String]) -> Result<CliAction, String> {
                 permission_mode = parse_permission_mode_arg(value)?;
                 index += 2;
             }
-            "--max-cost" => {
-                let value = args
-                    .get(index + 1)
-                    .ok_or_else(|| "missing value for --max-cost".to_string())?;
-                max_cost_usd = Some(parse_max_cost_arg(value)?);
-                index += 2;
-            }
             flag if flag.starts_with("--output-format=") => {
                 output_format = CliOutputFormat::parse(&flag[16..])?;
                 index += 1;
@@ -195,10 +182,6 @@ fn parse_args(args: &[String]) -> Result<CliAction, String> {
                 permission_mode = parse_permission_mode_arg(&flag[18..])?;
                 index += 1;
             }
-            flag if flag.starts_with("--max-cost=") => {
-                max_cost_usd = Some(parse_max_cost_arg(&flag[11..])?);
-                index += 1;
-            }
             "--allowedTools" | "--allowed-tools" => {
                 let value = args
                     .get(index + 1)
@@ -232,7 +215,6 @@ fn parse_args(args: &[String]) -> Result<CliAction, String> {
             model,
             allowed_tools,
             permission_mode,
-            max_cost_usd,
         });
     }
     if matches!(rest.first().map(String::as_str), Some("--help" | "-h")) {
@@ -259,7 +241,6 @@ fn parse_args(args: &[String]) -> Result<CliAction, String> {
                 output_format,
                 allowed_tools,
                 permission_mode,
-                max_cost_usd,
             })
         }
         other if !other.starts_with('/') => Ok(CliAction::Prompt {
@@ -268,7 +249,6 @@ fn parse_args(args: &[String]) -> Result<CliAction, String> {
             output_format,
             allowed_tools,
             permission_mode,
-            max_cost_usd,
         }),
         other => Err(format!("unknown subcommand: {other}")),
     }
@@ -332,18 +312,6 @@ fn parse_permission_mode_arg(value: &str) -> Result<PermissionMode, String> {
         .map(permission_mode_from_label)
 }
 
-fn parse_max_cost_arg(value: &str) -> Result<f64, String> {
-    let parsed = value
-        .parse::<f64>()
-        .map_err(|_| format!("invalid value for --max-cost: {value}"))?;
-    if !parsed.is_finite() || parsed <= 0.0 {
-        return Err(format!(
-            "--max-cost must be a positive finite USD amount: {value}"
-        ));
-    }
-    Ok(parsed)
-}
-
 fn permission_mode_from_label(mode: &str) -> PermissionMode {
     match mode {
         "read-only" => PermissionMode::ReadOnly,
@@ -710,78 +678,22 @@ fn format_permissions_switch_report(previous: &str, next: &str) -> String {
     )
 }
 
-fn format_cost_report(model: &str, usage: TokenUsage, max_cost_usd: Option<f64>) -> String {
+fn format_cost_report(usage: TokenUsage) -> String {
-    let estimate = usage_cost_estimate(model, usage);
     format!(
         "Cost
-  Model            {model}
   Input tokens     {}
   Output tokens    {}
   Cache create     {}
   Cache read       {}
-  Total tokens     {}
+  Total tokens     {}",
-  Input cost       {}
-  Output cost      {}
-  Cache create usd {}
-  Cache read usd   {}
-  Estimated cost   {}
-  Budget           {}",
         usage.input_tokens,
         usage.output_tokens,
         usage.cache_creation_input_tokens,
         usage.cache_read_input_tokens,
         usage.total_tokens(),
-        format_usd(estimate.input_cost_usd),
-        format_usd(estimate.output_cost_usd),
-        format_usd(estimate.cache_creation_cost_usd),
-        format_usd(estimate.cache_read_cost_usd),
-        format_usd(estimate.total_cost_usd()),
-        format_budget_line(estimate.total_cost_usd(), max_cost_usd),
     )
 }
 
-fn usage_cost_estimate(model: &str, usage: TokenUsage) -> runtime::UsageCostEstimate {
-    pricing_for_model(model).map_or_else(
-        || usage.estimate_cost_usd(),
-        |pricing| usage.estimate_cost_usd_with_pricing(pricing),
-    )
-}
-
-fn usage_cost_total(model: &str, usage: TokenUsage) -> f64 {
-    usage_cost_estimate(model, usage).total_cost_usd()
-}
-
-fn format_budget_line(cost_usd: f64, max_cost_usd: Option<f64>) -> String {
-    match max_cost_usd {
-        Some(limit) => format!("{} / {}", format_usd(cost_usd), format_usd(limit)),
-        None => format!("{} (unlimited)", format_usd(cost_usd)),
-    }
-}
-
-fn budget_notice_message(
-    model: &str,
-    usage: TokenUsage,
-    max_cost_usd: Option<f64>,
-) -> Option<String> {
-    let limit = max_cost_usd?;
-    let cost = usage_cost_total(model, usage);
-    if cost >= limit {
-        Some(format!(
-            "cost budget exceeded: cumulative={} budget={}",
-            format_usd(cost),
-            format_usd(limit)
-        ))
-    } else if cost >= limit * COST_WARNING_FRACTION {
-        Some(format!(
-            "approaching cost budget: cumulative={} budget={}",
-            format_usd(cost),
-            format_usd(limit)
-        ))
-    } else {
-        None
-    }
-}
-
 fn format_resume_report(session_path: &str, message_count: usize, turns: u32) -> String {
     format!(
         "Session resumed
@@ -925,7 +837,6 @@ fn run_resume_command(
                     },
                     default_permission_mode().as_str(),
                     &status_context(Some(session_path))?,
-                    None,
                 )),
             })
         }
@@ -933,7 +844,7 @@ fn run_resume_command(
             let usage = UsageTracker::from_session(session).cumulative_usage();
             Ok(ResumeCommandOutcome {
                 session: session.clone(),
-                message: Some(format_cost_report("restored-session", usage, None)),
+                message: Some(format_cost_report(usage)),
             })
         }
         SlashCommand::Config { section } => Ok(ResumeCommandOutcome {
@@ -980,9 +891,8 @@ fn run_repl(
     model: String,
     allowed_tools: Option<AllowedToolSet>,
     permission_mode: PermissionMode,
-    max_cost_usd: Option<f64>,
 ) -> Result<(), Box<dyn std::error::Error>> {
-    let mut cli = LiveCli::new(model, true, allowed_tools, permission_mode, max_cost_usd)?;
+    let mut cli = LiveCli::new(model, true, allowed_tools, permission_mode)?;
     let mut editor = input::LineEditor::new("› ", slash_command_completion_candidates());
     println!("{}", cli.startup_banner());
 
@@ -1035,7 +945,6 @@ struct LiveCli {
     model: String,
     allowed_tools: Option<AllowedToolSet>,
     permission_mode: PermissionMode,
-    max_cost_usd: Option<f64>,
     system_prompt: Vec<String>,
     runtime: ConversationRuntime<AnthropicRuntimeClient, CliToolExecutor>,
     session: SessionHandle,
@@ -1047,7 +956,6 @@ impl LiveCli {
         enable_tools: bool,
         allowed_tools: Option<AllowedToolSet>,
         permission_mode: PermissionMode,
-        max_cost_usd: Option<f64>,
     ) -> Result<Self, Box<dyn std::error::Error>> {
         let system_prompt = build_system_prompt()?;
         let session = create_managed_session_handle()?;
@@ -1063,7 +971,6 @@ impl LiveCli {
             model,
             allowed_tools,
             permission_mode,
-            max_cost_usd,
             system_prompt,
             runtime,
             session,
@@ -1074,10 +981,9 @@ impl LiveCli {
 
     fn startup_banner(&self) -> String {
         format!(
-            "Rusty Claude CLI\n  Model            {}\n  Permission mode  {}\n  Cost budget      {}\n  Working directory {}\n  Session          {}\n\nType /help for commands. Shift+Enter or Ctrl+J inserts a newline.",
+            "Rusty Claude CLI\n  Model            {}\n  Permission mode  {}\n  Working directory {}\n  Session          {}\n\nType /help for commands. Shift+Enter or Ctrl+J inserts a newline.",
             self.model,
             self.permission_mode.as_str(),
-            self.max_cost_usd.map_or_else(|| "none".to_string(), format_usd),
             env::current_dir().map_or_else(
                 |_| "<unknown>".to_string(),
                 |path| path.display().to_string(),
@@ -1087,7 +993,6 @@ impl LiveCli {
     }
 
     fn run_turn(&mut self, input: &str) -> Result<(), Box<dyn std::error::Error>> {
-        self.enforce_budget_before_turn()?;
         let mut spinner = Spinner::new();
         let mut stdout = io::stdout();
         spinner.tick(
@@ -1098,14 +1003,13 @@ impl LiveCli {
         let mut permission_prompter = CliPermissionPrompter::new(self.permission_mode);
         let result = self.runtime.run_turn(input, Some(&mut permission_prompter));
         match result {
-            Ok(summary) => {
+            Ok(_) => {
                 spinner.finish(
                     "Claude response complete",
                     TerminalRenderer::new().color_theme(),
                     &mut stdout,
                 )?;
                 println!();
-                self.print_budget_notice(summary.usage);
                 self.persist_session()?;
                 Ok(())
             }
@@ -1132,7 +1036,6 @@ impl LiveCli {
     }
 
     fn run_prompt_json(&mut self, input: &str) -> Result<(), Box<dyn std::error::Error>> {
-        self.enforce_budget_before_turn()?;
         let client = AnthropicClient::from_auth(resolve_cli_auth_source()?);
         let request = MessageRequest {
             model: self.model.clone(),
@@ -1159,27 +1062,17 @@ impl LiveCli {
             })
             .collect::<Vec<_>>()
             .join("");
-        let usage = TokenUsage {
-            input_tokens: response.usage.input_tokens,
-            output_tokens: response.usage.output_tokens,
-            cache_creation_input_tokens: response.usage.cache_creation_input_tokens,
-            cache_read_input_tokens: response.usage.cache_read_input_tokens,
-        };
         println!(
             "{}",
             json!({
                 "message": text,
                 "model": self.model,
                 "usage": {
-                    "input_tokens": usage.input_tokens,
+                    "input_tokens": response.usage.input_tokens,
-                    "output_tokens": usage.output_tokens,
+                    "output_tokens": response.usage.output_tokens,
-                    "cache_creation_input_tokens": usage.cache_creation_input_tokens,
+                    "cache_creation_input_tokens": response.usage.cache_creation_input_tokens,
-                    "cache_read_input_tokens": usage.cache_read_input_tokens,
+                    "cache_read_input_tokens": response.usage.cache_read_input_tokens,
-                },
+                }
-                "cost_usd": usage_cost_total(&self.model, usage),
-                "cumulative_cost_usd": usage_cost_total(&self.model, usage),
-                "max_cost_usd": self.max_cost_usd,
-                "budget_warning": budget_notice_message(&self.model, usage, self.max_cost_usd),
             })
         );
         Ok(())
@@ -1249,28 +1142,6 @@ impl LiveCli {
         Ok(())
     }
 
-    fn enforce_budget_before_turn(&self) -> Result<(), Box<dyn std::error::Error>> {
-        let Some(limit) = self.max_cost_usd else {
-            return Ok(());
-        };
-        let cost = usage_cost_total(&self.model, self.runtime.usage().cumulative_usage());
-        if cost >= limit {
-            return Err(format!(
-                "cost budget exceeded before starting turn: cumulative={} budget={}",
-                format_usd(cost),
-                format_usd(limit)
-            )
-            .into());
-        }
-        Ok(())
-    }
-
-    fn print_budget_notice(&self, usage: TokenUsage) {
-        if let Some(message) = budget_notice_message(&self.model, usage, self.max_cost_usd) {
-            eprintln!("warning: {message}");
-        }
-    }
-
     fn print_status(&self) {
         let cumulative = self.runtime.usage().cumulative_usage();
         let latest = self.runtime.usage().current_turn_usage();
@@ -1287,7 +1158,6 @@ impl LiveCli {
                 },
                 self.permission_mode.as_str(),
                 &status_context(Some(&self.session.path)).expect("status context should load"),
-                self.max_cost_usd,
             )
         );
     }
@@ -1405,10 +1275,7 @@ impl LiveCli {
 
     fn print_cost(&self) {
         let cumulative = self.runtime.usage().cumulative_usage();
-        println!(
+        println!("{}", format_cost_report(cumulative));
-            "{}",
-            format_cost_report(&self.model, cumulative, self.max_cost_usd)
-        );
     }
 
     fn resume_session(
@@ -1667,6 +1534,7 @@ fn status_context(
     let loader = ConfigLoader::default_for(&cwd);
     let discovered_config_files = loader.discover().len();
     let runtime_config = loader.load()?;
+    let discovered_config_files = discovered_config_files.max(runtime_config.loaded_entries().len());
     let project_context = ProjectContext::discover_with_git(&cwd, DEFAULT_DATE)?;
     let (project_root, git_branch) =
         parse_git_status_metadata(project_context.git_status.as_deref());
@@ -1686,10 +1554,7 @@ fn format_status_report(
     usage: StatusUsage,
     permission_mode: &str,
     context: &StatusContext,
-    max_cost_usd: Option<f64>,
 ) -> String {
-    let latest_cost = usage_cost_total(model, usage.latest);
-    let cumulative_cost = usage_cost_total(model, usage.cumulative);
     [
         format!(
             "Status
@@ -1697,27 +1562,19 @@ fn format_status_report(
   Permission mode  {permission_mode}
   Messages         {}
   Turns            {}
-  Estimated tokens {}
+  Estimated tokens {}",
-  Cost budget      {}",
+            usage.message_count, usage.turns, usage.estimated_tokens,
-            usage.message_count,
-            usage.turns,
-            usage.estimated_tokens,
-            format_budget_line(cumulative_cost, max_cost_usd),
         ),
         format!(
             "Usage
   Latest total     {}
-  Latest cost      {}
   Cumulative input {}
   Cumulative output {}
-  Cumulative total {}
+  Cumulative total {}",
-  Cumulative cost  {}",
             usage.latest.total_tokens(),
-            format_usd(latest_cost),
             usage.cumulative.input_tokens,
             usage.cumulative.output_tokens,
             usage.cumulative.total_tokens(),
-            format_usd(cumulative_cost),
         ),
         format!(
             "Workspace
@@ -2489,9 +2346,9 @@ fn print_help() {
     println!("rusty-claude-cli v{VERSION}");
     println!();
     println!("Usage:");
-    println!("  rusty-claude-cli [--model MODEL] [--max-cost USD] [--allowedTools TOOL[,TOOL...]]");
+    println!("  rusty-claude-cli [--model MODEL] [--allowedTools TOOL[,TOOL...]]");
     println!("      Start the interactive REPL");
-    println!("  rusty-claude-cli [--model MODEL] [--max-cost USD] [--output-format text|json] prompt TEXT");
+    println!("  rusty-claude-cli [--model MODEL] [--output-format text|json] prompt TEXT");
     println!("      Send one prompt and exit");
     println!("  rusty-claude-cli [--model MODEL] [--output-format text|json] TEXT");
     println!("      Shorthand non-interactive prompt mode");
@@ -2507,7 +2364,6 @@ fn print_help() {
     println!("  --model MODEL              Override the active model");
     println!("  --output-format FORMAT     Non-interactive output format: text or json");
     println!("  --permission-mode MODE     Set read-only, workspace-write, or danger-full-access");
-    println!("  --max-cost USD             Warn at 80% of budget and stop at/exceeding the budget");
     println!("  --allowedTools TOOLS       Restrict enabled tools (repeatable; comma-separated aliases supported)");
     println!("  --version, -V              Print version and build information locally");
     println!();
@@ -2534,14 +2390,13 @@ fn print_help() {
 #[cfg(test)]
 mod tests {
     use super::{
-        budget_notice_message, filter_tool_specs, format_compact_report, format_cost_report,
+        filter_tool_specs, format_compact_report, format_cost_report, format_init_report,
-        format_init_report, format_model_report, format_model_switch_report,
+        format_model_report, format_model_switch_report, format_permissions_report,
-        format_permissions_report, format_permissions_switch_report, format_resume_report,
+        format_permissions_switch_report, format_resume_report, format_status_report,
-        format_status_report, format_tool_call_start, format_tool_result,
+        format_tool_call_start, format_tool_result, normalize_permission_mode, parse_args,
-        normalize_permission_mode, parse_args, parse_git_status_metadata, render_config_report,
+        parse_git_status_metadata, render_config_report, render_init_claude_md,
-        render_init_claude_md, render_memory_report, render_repl_help,
+        render_memory_report, render_repl_help, resume_supported_slash_commands, status_context,
-        resume_supported_slash_commands, status_context, CliAction, CliOutputFormat, SlashCommand,
+        CliAction, CliOutputFormat, SlashCommand, StatusUsage, DEFAULT_MODEL,
-        StatusUsage, DEFAULT_MODEL,
     };
     use runtime::{ContentBlock, ConversationMessage, MessageRole, PermissionMode};
     use std::path::{Path, PathBuf};
@@ -2554,7 +2409,6 @@ mod tests {
                 model: DEFAULT_MODEL.to_string(),
                 allowed_tools: None,
                 permission_mode: PermissionMode::WorkspaceWrite,
-                max_cost_usd: None,
             }
         );
     }
@@ -2574,7 +2428,6 @@ mod tests {
                 output_format: CliOutputFormat::Text,
                 allowed_tools: None,
                 permission_mode: PermissionMode::WorkspaceWrite,
-                max_cost_usd: None,
             }
         );
     }
@@ -2596,7 +2449,6 @@ mod tests {
                 output_format: CliOutputFormat::Json,
                 allowed_tools: None,
                 permission_mode: PermissionMode::WorkspaceWrite,
-                max_cost_usd: None,
             }
         );
     }
@@ -2622,32 +2474,10 @@ mod tests {
                 model: DEFAULT_MODEL.to_string(),
                 allowed_tools: None,
                 permission_mode: PermissionMode::ReadOnly,
-                max_cost_usd: None,
             }
         );
     }
 
-    #[test]
-    fn parses_max_cost_flag() {
-        let args = vec!["--max-cost=1.25".to_string()];
-        assert_eq!(
-            parse_args(&args).expect("args should parse"),
-            CliAction::Repl {
-                model: DEFAULT_MODEL.to_string(),
-                allowed_tools: None,
-                permission_mode: PermissionMode::WorkspaceWrite,
-                max_cost_usd: Some(1.25),
-            }
-        );
-    }
-
-    #[test]
-    fn rejects_invalid_max_cost_flag() {
-        let error = parse_args(&["--max-cost".to_string(), "0".to_string()])
-            .expect_err("zero max cost should be rejected");
-        assert!(error.contains("--max-cost must be a positive finite USD amount"));
-    }
-
     #[test]
     fn parses_allowed_tools_flags_with_aliases_and_lists() {
         let args = vec![
@@ -2666,7 +2496,6 @@ mod tests {
                         .collect()
                 ),
                 permission_mode: PermissionMode::WorkspaceWrite,
-                max_cost_usd: None,
             }
         );
     }
@@ -2824,24 +2653,18 @@ mod tests {
 
     #[test]
     fn cost_report_uses_sectioned_layout() {
-        let report = format_cost_report(
+        let report = format_cost_report(runtime::TokenUsage {
-            "claude-sonnet",
+            input_tokens: 20,
-            runtime::TokenUsage {
+            output_tokens: 8,
-                input_tokens: 20,
+            cache_creation_input_tokens: 3,
-                output_tokens: 8,
+            cache_read_input_tokens: 1,
-                cache_creation_input_tokens: 3,
+        });
-                cache_read_input_tokens: 1,
-            },
-            None,
-        );
         assert!(report.contains("Cost"));
         assert!(report.contains("Input tokens     20"));
         assert!(report.contains("Output tokens    8"));
         assert!(report.contains("Cache create     3"));
         assert!(report.contains("Cache read       1"));
         assert!(report.contains("Total tokens     32"));
-        assert!(report.contains("Estimated cost"));
-        assert!(report.contains("Budget           $0.0010 (unlimited)"));
     }
 
     #[test]
@@ -2923,7 +2746,6 @@ mod tests {
                 project_root: Some(PathBuf::from("/tmp")),
                 git_branch: Some("main".to_string()),
             },
-            Some(1.0),
         );
         assert!(status.contains("Status"));
         assert!(status.contains("Model            claude-sonnet"));
@@ -2931,7 +2753,6 @@ mod tests {
         assert!(status.contains("Messages         7"));
         assert!(status.contains("Latest total     10"));
         assert!(status.contains("Cumulative total 31"));
-        assert!(status.contains("Cost budget      $0.0009 / $1.0000"));
         assert!(status.contains("Cwd              /tmp/project"));
         assert!(status.contains("Project root     /tmp"));
         assert!(status.contains("Git branch       main"));
@@ -2940,22 +2761,6 @@ mod tests {
         assert!(status.contains("Memory files     4"));
     }
 
-    #[test]
-    fn budget_notice_warns_near_limit() {
-        let message = budget_notice_message(
-            "claude-sonnet",
-            runtime::TokenUsage {
-                input_tokens: 60_000,
-                output_tokens: 0,
-                cache_creation_input_tokens: 0,
-                cache_read_input_tokens: 0,
-            },
-            Some(1.0),
-        )
-        .expect("budget warning expected");
-        assert!(message.contains("approaching cost budget"));
-    }
-
     #[test]
     fn config_report_supports_section_views() {
         let report = render_config_report(Some("env")).expect("config report should render");
@@ -2993,8 +2798,8 @@ mod tests {
     fn status_context_reads_real_workspace_metadata() {
         let context = status_context(None).expect("status context should load");
         assert!(context.cwd.is_absolute());
-        assert!(context.discovered_config_files >= context.loaded_config_files);
+        assert!(context.discovered_config_files >= 3);
-        assert!(context.discovered_config_files >= 1);
+        assert!(context.loaded_config_files <= context.discovered_config_files);
     }
 
     #[test]

rust/crates/tools/Cargo.toml

@@ -6,10 +6,12 @@ license.workspace = true
 publish.workspace = true
 
 [dependencies]
+api = { path = "../api" }
 runtime = { path = "../runtime" }
 reqwest = { version = "0.12", default-features = false, features = ["blocking", "rustls-tls"] }
 serde = { version = "1", features = ["derive"] }
 serde_json = "1"
+tokio = { version = "1", features = ["rt-multi-thread"] }
 
 [lints]
 workspace = true

rust/crates/tools/src/lib.rs

@@ -3,10 +3,17 @@ use std::path::{Path, PathBuf};
 use std::process::Command;
 use std::time::{Duration, Instant};
 
+use api::{
+    resolve_startup_auth_source, AnthropicClient, ContentBlockDelta, InputContentBlock,
+    InputMessage, MessageRequest, OutputContentBlock, StreamEvent as ApiStreamEvent, ToolChoice,
+    ToolDefinition, ToolResultContentBlock,
+};
 use reqwest::blocking::Client;
 use runtime::{
-    edit_file, execute_bash, glob_search, grep_search, read_file, write_file, BashCommandInput,
+    edit_file, execute_bash, glob_search, grep_search, load_system_prompt, read_file, write_file,
-    GrepSearchInput, PermissionMode,
+    ApiClient, ApiRequest, AssistantEvent, BashCommandInput, ConfigLoader, ContentBlock,
+    ConversationMessage, ConversationRuntime, GrepSearchInput, MessageRole, PermissionMode,
+    PermissionPolicy, RuntimeError, Session, TokenUsage, ToolError, ToolExecutor,
 };
 use serde::{Deserialize, Serialize};
 use serde_json::{json, Value};
@@ -234,7 +241,8 @@ pub fn mvp_tool_specs() -> Vec<ToolSpec> {
         },
         ToolSpec {
             name: "Agent",
-            description: "Launch a specialized agent task and persist its handoff metadata.",
+            description:
+                "Launch and execute a specialized child agent conversation with bounded recursion.",
             input_schema: json!({
                 "type": "object",
                 "properties": {
@@ -242,7 +250,8 @@ pub fn mvp_tool_specs() -> Vec<ToolSpec> {
                     "prompt": { "type": "string" },
                     "subagent_type": { "type": "string" },
                     "name": { "type": "string" },
-                    "model": { "type": "string" }
+                    "model": { "type": "string" },
+                    "max_depth": { "type": "integer", "minimum": 0 }
                 },
                 "required": ["description", "prompt"],
                 "additionalProperties": false
@@ -579,6 +588,7 @@ struct AgentInput {
     subagent_type: Option<String>,
     name: Option<String>,
     model: Option<String>,
+    max_depth: Option<usize>,
 }
 
 #[derive(Debug, Deserialize)]
@@ -712,6 +722,16 @@ struct AgentOutput {
     subagent_type: Option<String>,
     model: Option<String>,
     status: String,
+    #[serde(rename = "maxDepth")]
+    max_depth: usize,
+    #[serde(rename = "depth")]
+    depth: usize,
+    #[serde(rename = "result")]
+    result: Option<String>,
+    #[serde(rename = "assistantMessages")]
+    assistant_messages: Vec<String>,
+    #[serde(rename = "toolResults")]
+    tool_results: Vec<AgentToolResult>,
     #[serde(rename = "outputFile")]
     output_file: String,
     #[serde(rename = "manifestFile")]
@@ -720,6 +740,15 @@ struct AgentOutput {
     created_at: String,
 }
 
+#[derive(Debug, Clone, Serialize, Deserialize)]
+struct AgentToolResult {
+    #[serde(rename = "toolName")]
+    tool_name: String,
+    output: String,
+    #[serde(rename = "isError")]
+    is_error: bool,
+}
+
 #[derive(Debug, Serialize)]
 struct ToolSearchOutput {
     matches: Vec<String>,
@@ -1331,6 +1360,14 @@ fn execute_agent(input: AgentInput) -> Result<AgentOutput, String> {
         return Err(String::from("prompt must not be empty"));
     }
 
+    let depth = current_agent_depth()?;
+    let max_depth = input.max_depth.unwrap_or(3);
+    if depth >= max_depth {
+        return Err(format!(
+            "Agent max_depth exceeded: current depth {depth} reached limit {max_depth}"
+        ));
+    }
+
     let agent_id = make_agent_id();
     let output_dir = agent_store_dir()?;
     std::fs::create_dir_all(&output_dir).map_err(|error| error.to_string())?;
@@ -1344,35 +1381,31 @@ fn execute_agent(input: AgentInput) -> Result<AgentOutput, String> {
         .filter(|name| !name.is_empty())
         .unwrap_or_else(|| slugify_agent_name(&input.description));
     let created_at = iso8601_now();
+    let model = input.model.clone().or_else(agent_default_model);
 
-    let output_contents = format!(
+    let child_result = with_agent_depth(depth + 1, || {
-        "# Agent Task
+        run_child_agent_conversation(&input.prompt, model.clone(), max_depth)
-
+    })?;
-- id: {}
-- name: {}
-- description: {}
-- subagent_type: {}
-- created_at: {}
-
-## Prompt
-
-{}
-",
-        agent_id, agent_name, input.description, normalized_subagent_type, created_at, input.prompt
-    );
-    std::fs::write(&output_file, output_contents).map_err(|error| error.to_string())?;
 
     let manifest = AgentOutput {
         agent_id,
         name: agent_name,
         description: input.description,
         subagent_type: Some(normalized_subagent_type),
-        model: input.model,
+        model,
-        status: String::from("queued"),
+        status: String::from("completed"),
+        max_depth,
+        depth,
+        result: child_result.result.clone(),
+        assistant_messages: child_result.assistant_messages.clone(),
+        tool_results: child_result.tool_results.clone(),
         output_file: output_file.display().to_string(),
         manifest_file: manifest_file.display().to_string(),
         created_at,
     };
+
+    let output_contents = render_agent_output(&manifest);
+    std::fs::write(&output_file, output_contents).map_err(|error| error.to_string())?;
     std::fs::write(
         &manifest_file,
         serde_json::to_string_pretty(&manifest).map_err(|error| error.to_string())?,
@@ -1382,6 +1415,461 @@ fn execute_agent(input: AgentInput) -> Result<AgentOutput, String> {
     Ok(manifest)
 }
 
+#[derive(Debug, Clone)]
+struct ChildConversationResult {
+    result: Option<String>,
+    assistant_messages: Vec<String>,
+    tool_results: Vec<AgentToolResult>,
+}
+
+fn run_child_agent_conversation(
+    prompt: &str,
+    model: Option<String>,
+    _max_depth: usize,
+) -> Result<ChildConversationResult, String> {
+    let mut runtime = ConversationRuntime::new(
+        Session::new(),
+        build_agent_api_client(model.unwrap_or_else(default_agent_model))?,
+        AgentToolExecutor,
+        agent_permission_policy(),
+        build_agent_system_prompt()?,
+    )
+    .with_max_iterations(16);
+
+    let summary = runtime
+        .run_turn(prompt, None)
+        .map_err(|error| error.to_string())?;
+
+    let assistant_messages = summary
+        .assistant_messages
+        .iter()
+        .filter_map(extract_message_text)
+        .collect::<Vec<_>>();
+    let tool_results = summary
+        .tool_results
+        .iter()
+        .filter_map(extract_agent_tool_result)
+        .collect::<Vec<_>>();
+    let result = assistant_messages.last().cloned();
+
+    Ok(ChildConversationResult {
+        result,
+        assistant_messages,
+        tool_results,
+    })
+}
+
+fn render_agent_output(output: &AgentOutput) -> String {
+    let mut lines = vec![
+        "# Agent Task".to_string(),
+        String::new(),
+        format!("- id: {}", output.agent_id),
+        format!("- name: {}", output.name),
+        format!("- description: {}", output.description),
+        format!(
+            "- subagent_type: {}",
+            output.subagent_type.as_deref().unwrap_or("general-purpose")
+        ),
+        format!("- status: {}", output.status),
+        format!("- depth: {}", output.depth),
+        format!("- max_depth: {}", output.max_depth),
+        format!("- created_at: {}", output.created_at),
+        String::new(),
+        "## Result".to_string(),
+        String::new(),
+        output
+            .result
+            .clone()
+            .unwrap_or_else(|| String::from("<no final assistant text>")),
+    ];
+
+    if !output.tool_results.is_empty() {
+        lines.push(String::new());
+        lines.push("## Tool Results".to_string());
+        lines.push(String::new());
+        lines.extend(output.tool_results.iter().map(|result| {
+            format!(
+                "- {} [{}]: {}",
+                result.tool_name,
+                if result.is_error { "error" } else { "ok" },
+                result.output
+            )
+        }));
+    }
+
+    lines.join("\n")
+}
+
+fn current_agent_depth() -> Result<usize, String> {
+    std::env::var("CLAWD_AGENT_DEPTH")
+        .ok()
+        .map(|value| {
+            value
+                .parse::<usize>()
+                .map_err(|error| format!("invalid CLAWD_AGENT_DEPTH: {error}"))
+        })
+        .transpose()
+        .map(|value| value.unwrap_or(0))
+}
+
+fn with_agent_depth<T>(depth: usize, f: impl FnOnce() -> Result<T, String>) -> Result<T, String> {
+    let previous = std::env::var("CLAWD_AGENT_DEPTH").ok();
+    std::env::set_var("CLAWD_AGENT_DEPTH", depth.to_string());
+    let result = f();
+    if let Some(previous) = previous {
+        std::env::set_var("CLAWD_AGENT_DEPTH", previous);
+    } else {
+        std::env::remove_var("CLAWD_AGENT_DEPTH");
+    }
+    result
+}
+
+fn agent_default_model() -> Option<String> {
+    std::env::var("CLAWD_MODEL")
+        .ok()
+        .filter(|value| !value.trim().is_empty())
+}
+
+fn default_agent_model() -> String {
+    agent_default_model().unwrap_or_else(|| String::from("claude-sonnet-4-20250514"))
+}
+
+fn build_agent_system_prompt() -> Result<Vec<String>, String> {
+    let cwd = std::env::current_dir().map_err(|error| error.to_string())?;
+    let date = std::env::var("CLAWD_CURRENT_DATE").unwrap_or_else(|_| String::from("2026-04-01"));
+    load_system_prompt(cwd, &date, std::env::consts::OS, "unknown")
+        .map_err(|error| error.to_string())
+}
+
+fn agent_permission_policy() -> PermissionPolicy {
+    mvp_tool_specs().into_iter().fold(
+        PermissionPolicy::new(PermissionMode::DangerFullAccess),
+        |policy, spec| policy.with_tool_requirement(spec.name, spec.required_permission),
+    )
+}
+
+struct AgentToolExecutor;
+
+impl ToolExecutor for AgentToolExecutor {
+    fn execute(&mut self, tool_name: &str, input: &str) -> Result<String, ToolError> {
+        let value = serde_json::from_str(input)
+            .map_err(|error| ToolError::new(format!("invalid tool input JSON: {error}")))?;
+        execute_tool(tool_name, &value).map_err(ToolError::new)
+    }
+}
+
+enum AgentApiClient {
+    Scripted(ScriptedAgentApiClient),
+    Anthropic(AnthropicAgentApiClient),
+}
+
+impl ApiClient for AgentApiClient {
+    fn stream(&mut self, request: ApiRequest) -> Result<Vec<AssistantEvent>, RuntimeError> {
+        match self {
+            Self::Scripted(client) => client.stream(request),
+            Self::Anthropic(client) => client.stream(request),
+        }
+    }
+}
+
+fn build_agent_api_client(model: String) -> Result<AgentApiClient, String> {
+    if let Some(script) = std::env::var("CLAWD_AGENT_TEST_SCRIPT")
+        .ok()
+        .filter(|value| !value.trim().is_empty())
+    {
+        return Ok(AgentApiClient::Scripted(ScriptedAgentApiClient::new(
+            &script,
+        )?));
+    }
+
+    Ok(AgentApiClient::Anthropic(AnthropicAgentApiClient::new(
+        model,
+    )?))
+}
+
+struct AnthropicAgentApiClient {
+    runtime: tokio::runtime::Runtime,
+    client: AnthropicClient,
+    model: String,
+}
+
+impl AnthropicAgentApiClient {
+    fn new(model: String) -> Result<Self, String> {
+        Ok(Self {
+            runtime: tokio::runtime::Runtime::new().map_err(|error| error.to_string())?,
+            client: AnthropicClient::from_auth(resolve_agent_auth_source()?),
+            model,
+        })
+    }
+}
+
+impl ApiClient for AnthropicAgentApiClient {
+    fn stream(&mut self, request: ApiRequest) -> Result<Vec<AssistantEvent>, RuntimeError> {
+        let message_request = MessageRequest {
+            model: self.model.clone(),
+            max_tokens: 32,
+            messages: convert_agent_messages(&request.messages),
+            system: (!request.system_prompt.is_empty()).then(|| {
+                request.system_prompt.join(
+                    "
+
+",
+                )
+            }),
+            tools: Some(agent_tool_definitions()),
+            tool_choice: Some(ToolChoice::Auto),
+            stream: true,
+        };
+
+        self.runtime.block_on(async {
+            let mut stream = self
+                .client
+                .stream_message(&message_request)
+                .await
+                .map_err(|error| RuntimeError::new(error.to_string()))?;
+            let mut events = Vec::new();
+            let mut pending_tool: Option<(String, String, String)> = None;
+            let mut saw_stop = false;
+
+            while let Some(event) = stream
+                .next_event()
+                .await
+                .map_err(|error| RuntimeError::new(error.to_string()))?
+            {
+                match event {
+                    ApiStreamEvent::MessageStart(start) => {
+                        push_agent_output_blocks(
+                            start.message.content,
+                            &mut events,
+                            &mut pending_tool,
+                        );
+                    }
+                    ApiStreamEvent::ContentBlockStart(start) => {
+                        push_agent_output_block(
+                            start.content_block,
+                            &mut events,
+                            &mut pending_tool,
+                        );
+                    }
+                    ApiStreamEvent::ContentBlockDelta(delta) => match delta.delta {
+                        ContentBlockDelta::TextDelta { text } => {
+                            if !text.is_empty() {
+                                events.push(AssistantEvent::TextDelta(text));
+                            }
+                        }
+                        ContentBlockDelta::InputJsonDelta { partial_json } => {
+                            if let Some((_, _, input)) = &mut pending_tool {
+                                input.push_str(&partial_json);
+                            }
+                        }
+                    },
+                    ApiStreamEvent::ContentBlockStop(_) => {
+                        if let Some((id, name, input)) = pending_tool.take() {
+                            events.push(AssistantEvent::ToolUse { id, name, input });
+                        }
+                    }
+                    ApiStreamEvent::MessageDelta(delta) => {
+                        events.push(AssistantEvent::Usage(TokenUsage {
+                            input_tokens: delta.usage.input_tokens,
+                            output_tokens: delta.usage.output_tokens,
+                            cache_creation_input_tokens: delta.usage.cache_creation_input_tokens,
+                            cache_read_input_tokens: delta.usage.cache_read_input_tokens,
+                        }));
+                    }
+                    ApiStreamEvent::MessageStop(_) => {
+                        saw_stop = true;
+                        events.push(AssistantEvent::MessageStop);
+                    }
+                }
+            }
+
+            if !saw_stop {
+                events.push(AssistantEvent::MessageStop);
+            }
+
+            Ok(events)
+        })
+    }
+}
+
+fn resolve_agent_auth_source() -> Result<api::AuthSource, String> {
+    resolve_startup_auth_source(|| {
+        let cwd = std::env::current_dir().map_err(api::ApiError::from)?;
+        let config = ConfigLoader::default_for(&cwd).load().map_err(|error| {
+            api::ApiError::Auth(format!("failed to load runtime OAuth config: {error}"))
+        })?;
+        Ok(config.oauth().cloned())
+    })
+    .map_err(|error| error.to_string())
+}
+
+fn agent_tool_definitions() -> Vec<ToolDefinition> {
+    mvp_tool_specs()
+        .into_iter()
+        .map(|spec| ToolDefinition {
+            name: spec.name.to_string(),
+            description: Some(spec.description.to_string()),
+            input_schema: spec.input_schema,
+        })
+        .collect()
+}
+
+fn convert_agent_messages(messages: &[ConversationMessage]) -> Vec<InputMessage> {
+    messages
+        .iter()
+        .filter_map(|message| {
+            let role = match message.role {
+                MessageRole::System | MessageRole::User | MessageRole::Tool => "user",
+                MessageRole::Assistant => "assistant",
+            };
+            let content = message
+                .blocks
+                .iter()
+                .map(|block| match block {
+                    ContentBlock::Text { text } => InputContentBlock::Text { text: text.clone() },
+                    ContentBlock::ToolUse { id, name, input } => InputContentBlock::ToolUse {
+                        id: id.clone(),
+                        name: name.clone(),
+                        input: serde_json::from_str(input)
+                            .unwrap_or_else(|_| serde_json::json!({ "raw": input })),
+                    },
+                    ContentBlock::ToolResult {
+                        tool_use_id,
+                        output,
+                        is_error,
+                        ..
+                    } => InputContentBlock::ToolResult {
+                        tool_use_id: tool_use_id.clone(),
+                        content: vec![ToolResultContentBlock::Text {
+                            text: output.clone(),
+                        }],
+                        is_error: *is_error,
+                    },
+                })
+                .collect::<Vec<_>>();
+            (!content.is_empty()).then(|| InputMessage {
+                role: role.to_string(),
+                content,
+            })
+        })
+        .collect()
+}
+
+fn push_agent_output_blocks(
+    blocks: Vec<OutputContentBlock>,
+    events: &mut Vec<AssistantEvent>,
+    pending_tool: &mut Option<(String, String, String)>,
+) {
+    for block in blocks {
+        push_agent_output_block(block, events, pending_tool);
+        if let Some((id, name, input)) = pending_tool.take() {
+            events.push(AssistantEvent::ToolUse { id, name, input });
+        }
+    }
+}
+
+fn push_agent_output_block(
+    block: OutputContentBlock,
+    events: &mut Vec<AssistantEvent>,
+    pending_tool: &mut Option<(String, String, String)>,
+) {
+    match block {
+        OutputContentBlock::Text { text } => {
+            if !text.is_empty() {
+                events.push(AssistantEvent::TextDelta(text));
+            }
+        }
+        OutputContentBlock::ToolUse { id, name, input } => {
+            *pending_tool = Some((id, name, input.to_string()));
+        }
+    }
+}
+
+#[derive(Debug)]
+struct ScriptedAgentApiClient {
+    turns: Vec<Vec<ScriptedAgentEvent>>,
+    call_count: usize,
+}
+
+impl ScriptedAgentApiClient {
+    fn new(script: &str) -> Result<Self, String> {
+        let turns = serde_json::from_str(script).map_err(|error| error.to_string())?;
+        Ok(Self {
+            turns,
+            call_count: 0,
+        })
+    }
+}
+
+impl ApiClient for ScriptedAgentApiClient {
+    fn stream(&mut self, _request: ApiRequest) -> Result<Vec<AssistantEvent>, RuntimeError> {
+        if self.call_count >= self.turns.len() {
+            return Err(RuntimeError::new("scripted agent client exhausted"));
+        }
+        let events = self.turns[self.call_count]
+            .iter()
+            .map(ScriptedAgentEvent::to_runtime_event)
+            .chain(std::iter::once(AssistantEvent::MessageStop))
+            .collect();
+        self.call_count += 1;
+        Ok(events)
+    }
+}
+
+#[derive(Debug, Clone, Deserialize)]
+#[serde(tag = "type", rename_all = "snake_case")]
+enum ScriptedAgentEvent {
+    Text {
+        text: String,
+    },
+    ToolUse {
+        id: String,
+        name: String,
+        input: Value,
+    },
+}
+
+impl ScriptedAgentEvent {
+    fn to_runtime_event(&self) -> AssistantEvent {
+        match self {
+            Self::Text { text } => AssistantEvent::TextDelta(text.clone()),
+            Self::ToolUse { id, name, input } => AssistantEvent::ToolUse {
+                id: id.clone(),
+                name: name.clone(),
+                input: input.to_string(),
+            },
+        }
+    }
+}
+
+fn extract_message_text(message: &ConversationMessage) -> Option<String> {
+    let text = message
+        .blocks
+        .iter()
+        .filter_map(|block| match block {
+            ContentBlock::Text { text } => Some(text.as_str()),
+            _ => None,
+        })
+        .collect::<String>();
+    (!text.is_empty()).then_some(text)
+}
+
+fn extract_agent_tool_result(message: &ConversationMessage) -> Option<AgentToolResult> {
+    message.blocks.iter().find_map(|block| match block {
+        ContentBlock::ToolResult {
+            tool_name,
+            output,
+            is_error,
+            ..
+        } => Some(AgentToolResult {
+            tool_name: tool_name.clone(),
+            output: output.clone(),
+            is_error: *is_error,
+        }),
+        _ => None,
+    })
+}
+
 #[allow(clippy::needless_pass_by_value)]
 fn execute_tool_search(input: ToolSearchInput) -> ToolSearchOutput {
     let deferred = deferred_tool_specs();
@@ -2763,12 +3251,28 @@ mod tests {
     }
 
     #[test]
-    fn agent_persists_handoff_metadata() {
+    fn agent_executes_child_conversation_and_persists_results() {
         let _guard = env_lock()
             .lock()
             .unwrap_or_else(std::sync::PoisonError::into_inner);
         let dir = temp_path("agent-store");
         std::env::set_var("CLAWD_AGENT_STORE", &dir);
+        std::env::set_var(
+            "CLAWD_AGENT_TEST_SCRIPT",
+            serde_json::to_string(&vec![
+                vec![json!({
+                    "type": "tool_use",
+                    "id": "tool-1",
+                    "name": "StructuredOutput",
+                    "input": {"ok": true, "items": [1, 2, 3]}
+                })],
+                vec![json!({
+                    "type": "text",
+                    "text": "Child agent completed successfully."
+                })],
+            ])
+            .expect("script json"),
+        );
 
         let result = execute_tool(
             "Agent",
@@ -2780,22 +3284,35 @@ mod tests {
             }),
         )
         .expect("Agent should succeed");
+        std::env::remove_var("CLAWD_AGENT_TEST_SCRIPT");
         std::env::remove_var("CLAWD_AGENT_STORE");
 
         let output: serde_json::Value = serde_json::from_str(&result).expect("valid json");
         assert_eq!(output["name"], "ship-audit");
         assert_eq!(output["subagentType"], "Explore");
-        assert_eq!(output["status"], "queued");
+        assert_eq!(output["status"], "completed");
-        assert!(output["createdAt"].as_str().is_some());
+        assert_eq!(output["depth"], 0);
+        assert_eq!(output["maxDepth"], 3);
+        assert_eq!(output["result"], "Child agent completed successfully.");
+        assert_eq!(output["toolResults"][0]["toolName"], "StructuredOutput");
+        assert_eq!(output["toolResults"][0]["isError"], false);
         let manifest_file = output["manifestFile"].as_str().expect("manifest file");
         let output_file = output["outputFile"].as_str().expect("output file");
         let contents = std::fs::read_to_string(output_file).expect("agent file exists");
         let manifest_contents =
             std::fs::read_to_string(manifest_file).expect("manifest file exists");
-        assert!(contents.contains("Audit the branch"));
+        assert!(contents.contains("Child agent completed successfully."));
-        assert!(contents.contains("Check tests and outstanding work."));
+        assert!(contents.contains("StructuredOutput [ok]"));
         assert!(manifest_contents.contains("\"subagentType\": \"Explore\""));
 
+        std::env::set_var(
+            "CLAWD_AGENT_TEST_SCRIPT",
+            serde_json::to_string(&vec![vec![json!({
+                "type": "text",
+                "text": "Normalized alias check."
+            })]])
+            .expect("script json"),
+        );
         let normalized = execute_tool(
             "Agent",
             &json!({
@@ -2805,10 +3322,19 @@ mod tests {
             }),
         )
         .expect("Agent should normalize built-in aliases");
+        std::env::remove_var("CLAWD_AGENT_TEST_SCRIPT");
         let normalized_output: serde_json::Value =
             serde_json::from_str(&normalized).expect("valid json");
         assert_eq!(normalized_output["subagentType"], "Explore");
 
+        std::env::set_var(
+            "CLAWD_AGENT_TEST_SCRIPT",
+            serde_json::to_string(&vec![vec![json!({
+                "type": "text",
+                "text": "Name normalization check."
+            })]])
+            .expect("script json"),
+        );
         let named = execute_tool(
             "Agent",
             &json!({
@@ -2818,13 +3344,14 @@ mod tests {
             }),
         )
         .expect("Agent should normalize explicit names");
+        std::env::remove_var("CLAWD_AGENT_TEST_SCRIPT");
         let named_output: serde_json::Value = serde_json::from_str(&named).expect("valid json");
         assert_eq!(named_output["name"], "ship-audit");
         let _ = std::fs::remove_dir_all(dir);
     }
 
     #[test]
-    fn agent_rejects_blank_required_fields() {
+    fn agent_rejects_blank_required_fields_and_enforces_max_depth() {
         let missing_description = execute_tool(
             "Agent",
             &json!({
@@ -2844,6 +3371,22 @@ mod tests {
         )
         .expect_err("blank prompt should fail");
         assert!(missing_prompt.contains("prompt must not be empty"));
+
+        let _guard = env_lock()
+            .lock()
+            .unwrap_or_else(std::sync::PoisonError::into_inner);
+        std::env::set_var("CLAWD_AGENT_DEPTH", "1");
+        let depth_error = execute_tool(
+            "Agent",
+            &json!({
+                "description": "Nested agent",
+                "prompt": "Do nested work.",
+                "max_depth": 1
+            }),
+        )
+        .expect_err("max depth should fail");
+        std::env::remove_var("CLAWD_AGENT_DEPTH");
+        assert!(depth_error.contains("max_depth exceeded"));
     }
 
     #[test]