Expose session cost and budget state in the Rust CLI

The CLI already tracked token usage, but it did not translate that usage into model-aware cost reporting or offer a spend guardrail. This change adds a max-cost flag, integrates estimated USD totals into /status and /cost, emits near-budget warnings, and blocks new turns once the configured budget has been exhausted.

The workspace verification request also surfaced stale runtime test fixtures that still referenced removed permission enum variants, so those test-only call sites were updated to current permission modes to keep full clippy and workspace test coverage green.

Constraint: Reuse existing runtime usage/pricing helpers instead of adding a new billing layer
Constraint: Keep the feature centered in existing CLI/status surfaces with no new dependencies
Rejected: Move budget enforcement into runtime usage/session abstractions | broader refactor than needed for this CLI-scoped feature
Confidence: high
Scope-risk: moderate
Reversibility: clean
Directive: If resumed sessions later need historically accurate per-turn pricing across model switches, persist model metadata before changing the cost math
Tested: cargo fmt --all --check; cargo clippy --workspace --all-targets -- -D warnings; cargo test --workspace
Not-tested: Live network-backed prompt/REPL budget behavior against real Anthropic responses

rust/Cargo.lock

@@ -1431,12 +1431,10 @@ 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, generate_pkce_pair, generate_state, load_system_prompt,
-    parse_oauth_callback_request_target, save_oauth_credentials, ApiClient, ApiRequest,
-    AssistantEvent, CompactionConfig, ConfigLoader, ConfigSource, ContentBlock,
+    clear_oauth_credentials, format_usd, generate_pkce_pair, generate_state, load_system_prompt,
+    parse_oauth_callback_request_target, pricing_for_model, save_oauth_credentials, ApiClient,
+    ApiRequest, AssistantEvent, CompactionConfig, ConfigLoader, ConfigSource, ContentBlock,
     ConversationMessage, ConversationRuntime, MessageRole, OAuthAuthorizationRequest,
     OAuthTokenExchangeRequest, PermissionMode, PermissionPolicy, ProjectContext, RuntimeError,
     Session, TokenUsage, ToolError, ToolExecutor, UsageTracker,
@@ -36,6 +36,7 @@ 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");
@@ -70,7 +71,8 @@ fn run() -> Result<(), Box<dyn std::error::Error>> {
             output_format,
             allowed_tools,
             permission_mode,
-        } => LiveCli::new(model, false, allowed_tools, permission_mode)?
+            max_cost_usd,
+        } => 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()?,
@@ -78,13 +80,14 @@ fn run() -> Result<(), Box<dyn std::error::Error>> {
             model,
             allowed_tools,
             permission_mode,
-        } => run_repl(model, allowed_tools, permission_mode)?,
+            max_cost_usd,
+        } => run_repl(model, allowed_tools, permission_mode, max_cost_usd)?,
         CliAction::Help => print_help(),
     }
     Ok(())
 }
 
-#[derive(Debug, Clone, PartialEq, Eq)]
+#[derive(Debug, Clone, PartialEq)]
 enum CliAction {
     DumpManifests,
     BootstrapPlan,
@@ -103,6 +106,7 @@ enum CliAction {
         output_format: CliOutputFormat,
         allowed_tools: Option<AllowedToolSet>,
         permission_mode: PermissionMode,
+        max_cost_usd: Option<f64>,
     },
     Login,
     Logout,
@@ -110,6 +114,7 @@ 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,
@@ -139,6 +144,7 @@ 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;
@@ -174,6 +180,13 @@ 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;
@@ -182,6 +195,10 @@ 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)
@@ -215,6 +232,7 @@ 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")) {
@@ -241,6 +259,7 @@ 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 {
@@ -249,6 +268,7 @@ fn parse_args(args: &[String]) -> Result<CliAction, String> {
             output_format,
             allowed_tools,
             permission_mode,
+            max_cost_usd,
         }),
         other => Err(format!("unknown subcommand: {other}")),
     }
@@ -312,6 +332,18 @@ 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,
@@ -678,22 +710,78 @@ fn format_permissions_switch_report(previous: &str, next: &str) -> String {
     )
 }
 
-fn format_cost_report(usage: TokenUsage) -> String {
+fn format_cost_report(model: &str, usage: TokenUsage, max_cost_usd: Option<f64>) -> 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
@@ -837,6 +925,7 @@ fn run_resume_command(
                     },
                     default_permission_mode().as_str(),
                     &status_context(Some(session_path))?,
+                    None,
                 )),
             })
         }
@@ -844,7 +933,7 @@ fn run_resume_command(
             let usage = UsageTracker::from_session(session).cumulative_usage();
             Ok(ResumeCommandOutcome {
                 session: session.clone(),
-                message: Some(format_cost_report(usage)),
+                message: Some(format_cost_report("restored-session", usage, None)),
             })
         }
         SlashCommand::Config { section } => Ok(ResumeCommandOutcome {
@@ -891,8 +980,9 @@ 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)?;
+    let mut cli = LiveCli::new(model, true, allowed_tools, permission_mode, max_cost_usd)?;
     let mut editor = input::LineEditor::new("› ", slash_command_completion_candidates());
     println!("{}", cli.startup_banner());
 
@@ -945,6 +1035,7 @@ 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,
@@ -956,6 +1047,7 @@ 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()?;
@@ -971,6 +1063,7 @@ impl LiveCli {
             model,
             allowed_tools,
             permission_mode,
+            max_cost_usd,
             system_prompt,
             runtime,
             session,
@@ -981,9 +1074,10 @@ impl LiveCli {
 
     fn startup_banner(&self) -> String {
         format!(
-            "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.",
+            "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.",
             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(),
@@ -993,6 +1087,7 @@ 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(
@@ -1003,13 +1098,14 @@ 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(_) => {
+            Ok(summary) => {
                 spinner.finish(
                     "Claude response complete",
                     TerminalRenderer::new().color_theme(),
                     &mut stdout,
                 )?;
                 println!();
+                self.print_budget_notice(summary.usage);
                 self.persist_session()?;
                 Ok(())
             }
@@ -1036,6 +1132,7 @@ 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(),
@@ -1062,17 +1159,27 @@ 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": 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,
-                }
+                    "input_tokens": usage.input_tokens,
+                    "output_tokens": usage.output_tokens,
+                    "cache_creation_input_tokens": usage.cache_creation_input_tokens,
+                    "cache_read_input_tokens": 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(())
@@ -1142,6 +1249,28 @@ 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();
@@ -1158,6 +1287,7 @@ impl LiveCli {
                 },
                 self.permission_mode.as_str(),
                 &status_context(Some(&self.session.path)).expect("status context should load"),
+                self.max_cost_usd,
             )
         );
     }
@@ -1275,7 +1405,10 @@ impl LiveCli {
 
     fn print_cost(&self) {
         let cumulative = self.runtime.usage().cumulative_usage();
-        println!("{}", format_cost_report(cumulative));
+        println!(
+            "{}",
+            format_cost_report(&self.model, cumulative, self.max_cost_usd)
+        );
     }
 
     fn resume_session(
@@ -1534,7 +1667,6 @@ 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());
@@ -1554,7 +1686,10 @@ 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
@@ -1562,19 +1697,27 @@ fn format_status_report(
   Permission mode  {permission_mode}
   Messages         {}
   Turns            {}
-  Estimated tokens {}",
-            usage.message_count, usage.turns, usage.estimated_tokens,
+  Estimated tokens {}
+  Cost budget      {}",
+            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
@@ -2346,9 +2489,9 @@ fn print_help() {
     println!("rusty-claude-cli v{VERSION}");
     println!();
     println!("Usage:");
-    println!("  rusty-claude-cli [--model MODEL] [--allowedTools TOOL[,TOOL...]]");
+    println!("  rusty-claude-cli [--model MODEL] [--max-cost USD] [--allowedTools TOOL[,TOOL...]]");
     println!("      Start the interactive REPL");
-    println!("  rusty-claude-cli [--model MODEL] [--output-format text|json] prompt TEXT");
+    println!("  rusty-claude-cli [--model MODEL] [--max-cost USD] [--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");
@@ -2364,6 +2507,7 @@ 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!();
@@ -2390,13 +2534,14 @@ fn print_help() {
 #[cfg(test)]
 mod tests {
     use super::{
-        filter_tool_specs, format_compact_report, format_cost_report, format_init_report,
-        format_model_report, format_model_switch_report, format_permissions_report,
-        format_permissions_switch_report, format_resume_report, format_status_report,
-        format_tool_call_start, format_tool_result, normalize_permission_mode, parse_args,
-        parse_git_status_metadata, render_config_report, render_init_claude_md,
-        render_memory_report, render_repl_help, resume_supported_slash_commands, status_context,
-        CliAction, CliOutputFormat, SlashCommand, StatusUsage, DEFAULT_MODEL,
+        budget_notice_message, filter_tool_specs, format_compact_report, format_cost_report,
+        format_init_report, format_model_report, format_model_switch_report,
+        format_permissions_report, format_permissions_switch_report, format_resume_report,
+        format_status_report, format_tool_call_start, format_tool_result,
+        normalize_permission_mode, parse_args, parse_git_status_metadata, render_config_report,
+        render_init_claude_md, render_memory_report, render_repl_help,
+        resume_supported_slash_commands, status_context, CliAction, CliOutputFormat, SlashCommand,
+        StatusUsage, DEFAULT_MODEL,
     };
     use runtime::{ContentBlock, ConversationMessage, MessageRole, PermissionMode};
     use std::path::{Path, PathBuf};
@@ -2409,6 +2554,7 @@ mod tests {
                 model: DEFAULT_MODEL.to_string(),
                 allowed_tools: None,
                 permission_mode: PermissionMode::WorkspaceWrite,
+                max_cost_usd: None,
             }
         );
     }
@@ -2428,6 +2574,7 @@ mod tests {
                 output_format: CliOutputFormat::Text,
                 allowed_tools: None,
                 permission_mode: PermissionMode::WorkspaceWrite,
+                max_cost_usd: None,
             }
         );
     }
@@ -2449,6 +2596,7 @@ mod tests {
                 output_format: CliOutputFormat::Json,
                 allowed_tools: None,
                 permission_mode: PermissionMode::WorkspaceWrite,
+                max_cost_usd: None,
             }
         );
     }
@@ -2474,10 +2622,32 @@ 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![
@@ -2496,6 +2666,7 @@ mod tests {
                         .collect()
                 ),
                 permission_mode: PermissionMode::WorkspaceWrite,
+                max_cost_usd: None,
             }
         );
     }
@@ -2653,18 +2824,24 @@ mod tests {
 
     #[test]
     fn cost_report_uses_sectioned_layout() {
-        let report = format_cost_report(runtime::TokenUsage {
-            input_tokens: 20,
-            output_tokens: 8,
-            cache_creation_input_tokens: 3,
-            cache_read_input_tokens: 1,
-        });
+        let report = format_cost_report(
+            "claude-sonnet",
+            runtime::TokenUsage {
+                input_tokens: 20,
+                output_tokens: 8,
+                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]
@@ -2746,6 +2923,7 @@ 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"));
@@ -2753,6 +2931,7 @@ 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"));
@@ -2761,6 +2940,22 @@ 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");
@@ -2798,8 +2993,8 @@ 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 >= 3);
-        assert!(context.loaded_config_files <= context.discovered_config_files);
+        assert!(context.discovered_config_files >= context.loaded_config_files);
+        assert!(context.discovered_config_files >= 1);
     }
 
     #[test]

rust/crates/tools/Cargo.toml

@@ -6,12 +6,10 @@ 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

@@ -3,17 +3,10 @@ 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, load_system_prompt, read_file, write_file,
-    ApiClient, ApiRequest, AssistantEvent, BashCommandInput, ConfigLoader, ContentBlock,
-    ConversationMessage, ConversationRuntime, GrepSearchInput, MessageRole, PermissionMode,
-    PermissionPolicy, RuntimeError, Session, TokenUsage, ToolError, ToolExecutor,
+    edit_file, execute_bash, glob_search, grep_search, read_file, write_file, BashCommandInput,
+    GrepSearchInput, PermissionMode,
 };
 use serde::{Deserialize, Serialize};
 use serde_json::{json, Value};
@@ -241,8 +234,7 @@ pub fn mvp_tool_specs() -> Vec<ToolSpec> {
         },
         ToolSpec {
             name: "Agent",
-            description:
-                "Launch and execute a specialized child agent conversation with bounded recursion.",
+            description: "Launch a specialized agent task and persist its handoff metadata.",
             input_schema: json!({
                 "type": "object",
                 "properties": {
@@ -250,8 +242,7 @@ pub fn mvp_tool_specs() -> Vec<ToolSpec> {
                     "prompt": { "type": "string" },
                     "subagent_type": { "type": "string" },
                     "name": { "type": "string" },
-                    "model": { "type": "string" },
-                    "max_depth": { "type": "integer", "minimum": 0 }
+                    "model": { "type": "string" }
                 },
                 "required": ["description", "prompt"],
                 "additionalProperties": false
@@ -588,7 +579,6 @@ struct AgentInput {
     subagent_type: Option<String>,
     name: Option<String>,
     model: Option<String>,
-    max_depth: Option<usize>,
 }
 
 #[derive(Debug, Deserialize)]
@@ -722,16 +712,6 @@ 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")]
@@ -740,15 +720,6 @@ 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>,
@@ -1360,14 +1331,6 @@ 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())?;
@@ -1381,31 +1344,35 @@ 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 child_result = with_agent_depth(depth + 1, || {
-        run_child_agent_conversation(&input.prompt, model.clone(), max_depth)
-    })?;
+    let output_contents = format!(
+        "# Agent Task
+
+- 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,
-        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(),
+        model: input.model,
+        status: String::from("queued"),
         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())?,
@@ -1415,461 +1382,6 @@ 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();
@@ -3251,28 +2763,12 @@ mod tests {
     }
 
     #[test]
-    fn agent_executes_child_conversation_and_persists_results() {
+    fn agent_persists_handoff_metadata() {
         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",
@@ -3284,35 +2780,22 @@ 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"], "completed");
-        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);
+        assert_eq!(output["status"], "queued");
+        assert!(output["createdAt"].as_str().is_some());
         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("Child agent completed successfully."));
-        assert!(contents.contains("StructuredOutput [ok]"));
+        assert!(contents.contains("Audit the branch"));
+        assert!(contents.contains("Check tests and outstanding work."));
         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!({
@@ -3322,19 +2805,10 @@ 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!({
@@ -3344,14 +2818,13 @@ 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_and_enforces_max_depth() {
+    fn agent_rejects_blank_required_fields() {
         let missing_description = execute_tool(
             "Agent",
             &json!({
@@ -3371,22 +2844,6 @@ 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]