style: apply rustfmt to reasoning tests

src/agent/agentic_loop.rs

@@ -10,7 +10,9 @@ use std::borrow::Cow;
 
 use crate::agent::session::PendingApproval;
 use crate::error::Error;
-use crate::llm::{ChatMessage, FinishReason, Reasoning, ReasoningContext, RespondResult};
+use crate::llm::{
+    ChatMessage, FinishReason, Reasoning, ReasoningContext, RespondResult, ResponseMetadata,
+};
 
 /// Signal from the delegate indicating how the loop should proceed.
 pub enum LoopSignal {
@@ -38,6 +40,8 @@ pub enum LoopOutcome {
     Stopped,
     /// Max iterations exceeded.
     MaxIterations,
+    /// Loop terminated early with a clear failure reason.
+    Failure(String),
     /// A tool requires user approval before continuing (chat delegate only).
     NeedApproval(Box<PendingApproval>),
 }
@@ -103,6 +107,7 @@ pub trait LoopDelegate: Send + Sync {
     async fn handle_text_response(
         &self,
         text: &str,
+        metadata: ResponseMetadata,
         reason_ctx: &mut ReasoningContext,
     ) -> TextAction;
 
@@ -209,7 +214,10 @@ pub async fn run_agentic_loop(
                     consecutive_tool_intent_nudges = 0;
                 }
 
-                match delegate.handle_text_response(&text, reason_ctx).await {
+                match delegate
+                    .handle_text_response(&text, output.metadata, reason_ctx)
+                    .await
+                {
                     TextAction::Return(outcome) => return Ok(outcome),
                     TextAction::Continue => {}
                 }
@@ -279,7 +287,7 @@ pub fn truncate_for_preview(s: &str, max: usize) -> Cow<'_, str> {
 #[cfg(test)]
 mod tests {
     use super::*;
-    use crate::llm::{RespondOutput, TokenUsage, ToolCall};
+    use crate::llm::{RespondOutput, ResponseAnomaly, ResponseMetadata, TokenUsage, ToolCall};
     use crate::testing::StubLlm;
     use std::sync::Arc;
     use std::sync::atomic::{AtomicUsize, Ordering};
@@ -303,6 +311,7 @@ mod tests {
             result: RespondResult::Text(text.to_string()),
             usage: zero_usage(),
             finish_reason: FinishReason::Stop,
+            metadata: ResponseMetadata::default(),
         }
     }
 
@@ -314,6 +323,7 @@ mod tests {
             },
             usage: zero_usage(),
             finish_reason: FinishReason::ToolUse,
+            metadata: ResponseMetadata::default(),
         }
     }
 
@@ -391,6 +401,7 @@ mod tests {
         async fn handle_text_response(
             &self,
             text: &str,
+            _metadata: ResponseMetadata,
             _reason_ctx: &mut ReasoningContext,
         ) -> TextAction {
             TextAction::Return(LoopOutcome::Response(text.to_string()))
@@ -508,6 +519,79 @@ mod tests {
         );
     }
 
+    #[tokio::test]
+    async fn test_text_response_metadata_can_fail_fast() {
+        struct FailOnMalformedResponse;
+
+        #[async_trait]
+        impl LoopDelegate for FailOnMalformedResponse {
+            async fn check_signals(&self) -> LoopSignal {
+                LoopSignal::Continue
+            }
+
+            async fn before_llm_call(
+                &self,
+                _: &mut ReasoningContext,
+                _: usize,
+            ) -> Option<LoopOutcome> {
+                None
+            }
+
+            async fn call_llm(
+                &self,
+                _: &Reasoning,
+                _: &mut ReasoningContext,
+                _: usize,
+            ) -> Result<crate::llm::RespondOutput, crate::error::Error> {
+                Ok(RespondOutput {
+                    result: RespondResult::Text("fallback".to_string()),
+                    usage: zero_usage(),
+                    finish_reason: FinishReason::Stop,
+                    metadata: ResponseMetadata {
+                        anomaly: Some(ResponseAnomaly::EmptyToolCompletion),
+                    },
+                })
+            }
+
+            async fn handle_text_response(
+                &self,
+                _: &str,
+                metadata: ResponseMetadata,
+                _: &mut ReasoningContext,
+            ) -> TextAction {
+                assert_eq!(metadata.anomaly, Some(ResponseAnomaly::EmptyToolCompletion));
+                TextAction::Return(LoopOutcome::Failure(
+                    "malformed tool completion".to_string(),
+                ))
+            }
+
+            async fn execute_tool_calls(
+                &self,
+                _: Vec<ToolCall>,
+                _: Option<String>,
+                _: &mut ReasoningContext,
+            ) -> Result<Option<LoopOutcome>, crate::error::Error> {
+                Ok(None)
+            }
+        }
+
+        let delegate = FailOnMalformedResponse;
+        let reasoning = stub_reasoning();
+        let mut ctx = ReasoningContext::new();
+        let outcome = run_agentic_loop(
+            &delegate,
+            &reasoning,
+            &mut ctx,
+            &AgenticLoopConfig::default(),
+        )
+        .await
+        .unwrap();
+
+        assert!(
+            matches!(outcome, LoopOutcome::Failure(ref reason) if reason == "malformed tool completion")
+        );
+    }
+
     #[tokio::test]
     async fn test_max_iterations_reached() {
         struct ContinueDelegate;
@@ -535,6 +619,7 @@ mod tests {
             async fn handle_text_response(
                 &self,
                 _: &str,
+                _: ResponseMetadata,
                 ctx: &mut ReasoningContext,
             ) -> TextAction {
                 ctx.messages.push(ChatMessage::assistant("still working"));
@@ -671,6 +756,7 @@ mod tests {
             },
             usage: zero_usage(),
             finish_reason: FinishReason::Length, // response was truncated
+            metadata: ResponseMetadata::default(),
         };
         let delegate = MockDelegate::new(vec![truncated_output, text_output("Summarized it.")]);
         let reasoning = stub_reasoning();
@@ -719,6 +805,7 @@ mod tests {
             },
             usage: zero_usage(),
             finish_reason: FinishReason::Length,
+            metadata: ResponseMetadata::default(),
         };
         // Three truncated responses, then a text response
         let delegate = MockDelegate::new(vec![

src/agent/dispatcher.rs

@@ -219,6 +219,11 @@ impl Agent {
                 reason: format!("Exceeded maximum tool iterations ({max_tool_iterations})"),
             }
             .into()),
+            LoopOutcome::Failure(reason) => Err(crate::error::LlmError::InvalidResponse {
+                provider: "agent".to_string(),
+                reason,
+            }
+            .into()),
             LoopOutcome::NeedApproval(pending) => Ok(AgenticLoopResult::NeedApproval { pending }),
         }
     }
@@ -439,6 +444,7 @@ impl<'a> LoopDelegate for ChatDelegate<'a> {
     async fn handle_text_response(
         &self,
         text: &str,
+        _metadata: crate::llm::ResponseMetadata,
         _reason_ctx: &mut ReasoningContext,
     ) -> TextAction {
         // Strip internal "[Called tool ...]" text that can leak when

src/llm/mod.rs

@@ -62,9 +62,9 @@ pub use provider::{
     ToolDefinition, ToolResult, generate_tool_call_id,
 };
 pub use reasoning::{
-    ActionPlan, Reasoning, ReasoningContext, RespondOutput, RespondResult, SILENT_REPLY_TOKEN,
-    TOOL_INTENT_NUDGE, TRUNCATED_TOOL_CALL_NOTICE, TokenUsage, ToolSelection, is_silent_reply,
-    llm_signals_tool_intent,
+    ActionPlan, Reasoning, ReasoningContext, RespondOutput, RespondResult, ResponseAnomaly,
+    ResponseMetadata, SILENT_REPLY_TOKEN, TOOL_INTENT_NUDGE, TRUNCATED_TOOL_CALL_NOTICE,
+    TokenUsage, ToolSelection, is_silent_reply, llm_signals_tool_intent,
 };
 pub use recording::RecordingLlm;
 pub use registry::{ProviderDefinition, ProviderProtocol, ProviderRegistry};

src/llm/reasoning.rs

@@ -337,6 +337,23 @@ impl TokenUsage {
     }
 }
 
+/// Structured anomaly classification for LLM responses.
+#[derive(Debug, Clone, Copy, PartialEq, Eq)]
+pub enum ResponseAnomaly {
+    /// Tool mode was requested, but the provider returned no usable tool calls
+    /// and no recoverable text content.
+    EmptyToolCompletion,
+    /// Text mode returned no usable content after cleaning/truncation.
+    EmptyTextResponse,
+}
+
+/// Metadata attached to `RespondOutput` so callers can react to malformed
+/// provider behavior without inferring it from fallback strings.
+#[derive(Debug, Clone, Copy, Default, PartialEq, Eq)]
+pub struct ResponseMetadata {
+    pub anomaly: Option<ResponseAnomaly>,
+}
+
 /// Result of a response with potential tool calls.
 ///
 /// Used by the agent loop to handle tool execution before returning a final response.
@@ -359,6 +376,7 @@ pub struct RespondOutput {
     pub result: RespondResult,
     pub usage: TokenUsage,
     pub finish_reason: FinishReason,
+    pub metadata: ResponseMetadata,
 }
 
 /// Reasoning engine for the agent.
@@ -744,12 +762,11 @@ Respond in JSON format:
                     },
                     usage,
                     finish_reason: response.finish_reason,
+                    metadata: ResponseMetadata::default(),
                 });
             }
 
-            let content = response
-                .content
-                .unwrap_or_else(|| "I'm not sure how to respond to that.".to_string());
+            let content = response.content.unwrap_or_default();
 
             // Some models (e.g. GLM-4.7) emit tool calls as XML tags in content
             // instead of using the structured tool_calls field. Try to recover
@@ -772,6 +789,7 @@ Respond in JSON format:
                     },
                     usage,
                     finish_reason: response.finish_reason,
+                    metadata: ResponseMetadata::default(),
                 });
             }
 
@@ -785,11 +803,18 @@ Respond in JSON format:
             // Pre-truncate at tool tags to preserve text before the tag.
             let pre_truncated = truncate_at_tool_tags(&content);
             let cleaned = clean_response(&pre_truncated);
-            let final_text = if cleaned.trim().is_empty() {
+            let metadata = if cleaned.trim().is_empty() {
                 tracing::warn!(
                     "LLM response was empty after cleaning (original len={}), using fallback",
                     content.len()
                 );
+                ResponseMetadata {
+                    anomaly: Some(ResponseAnomaly::EmptyToolCompletion),
+                }
+            } else {
+                ResponseMetadata::default()
+            };
+            let final_text = if metadata.anomaly.is_some() {
                 "I'm not sure how to respond to that.".to_string()
             } else {
                 cleaned
@@ -798,6 +823,7 @@ Respond in JSON format:
                 result: RespondResult::Text(final_text),
                 usage,
                 finish_reason: response.finish_reason,
+                metadata,
             })
         } else {
             // No tools, use simple completion
@@ -812,11 +838,18 @@ Respond in JSON format:
             let response = self.llm.complete(request).await?;
             let pre_truncated = truncate_at_tool_tags(&response.content);
             let cleaned = clean_response(&pre_truncated);
-            let final_text = if cleaned.trim().is_empty() {
+            let metadata = if cleaned.trim().is_empty() {
                 tracing::warn!(
                     "LLM response was empty after cleaning (original len={}), using fallback",
                     response.content.len()
                 );
+                ResponseMetadata {
+                    anomaly: Some(ResponseAnomaly::EmptyTextResponse),
+                }
+            } else {
+                ResponseMetadata::default()
+            };
+            let final_text = if metadata.anomaly.is_some() {
                 "I'm not sure how to respond to that.".to_string()
             } else {
                 cleaned
@@ -830,6 +863,7 @@ Respond in JSON format:
                     cache_creation_input_tokens: response.cache_creation_input_tokens,
                 },
                 finish_reason: response.finish_reason,
+                metadata,
             })
         }
     }
@@ -3101,9 +3135,104 @@ That's my plan."#;
         context.force_text = true;
 
         let output = reasoning.respond_with_tools(&context).await.unwrap();
+        let metadata = output.metadata;
         match output.result {
             RespondResult::Text(text) => {
                 assert_eq!(text, "I'm not sure how to respond to that.");
+                assert_eq!(metadata.anomaly, Some(ResponseAnomaly::EmptyTextResponse));
+            }
+            RespondResult::ToolCalls { .. } => {
+                panic!("Expected fallback text, not tool calls");
+            }
+        }
+    }
+
+    #[tokio::test]
+    async fn test_respond_with_tools_flags_empty_tool_completion() {
+        use crate::testing::StubLlm;
+        let llm = Arc::new(StubLlm::new(""));
+        let reasoning = Reasoning::new(llm);
+
+        let context = ReasoningContext::new()
+            .with_message(ChatMessage::user("list tools"))
+            .with_tools(vec![ToolDefinition {
+                name: "tool_list".to_string(),
+                description: "Lists tools".to_string(),
+                parameters: serde_json::json!({}),
+            }]);
+
+        let output = reasoning.respond_with_tools(&context).await.unwrap();
+        let metadata = output.metadata;
+        match output.result {
+            RespondResult::Text(text) => {
+                assert_eq!(text, "I'm not sure how to respond to that.");
+                assert_eq!(metadata.anomaly, Some(ResponseAnomaly::EmptyToolCompletion));
+            }
+            RespondResult::ToolCalls { .. } => {
+                panic!("Expected fallback text, not tool calls");
+            }
+        }
+    }
+
+    #[tokio::test]
+    async fn test_respond_with_tools_flags_empty_tool_completion_when_content_is_none() {
+        use crate::llm::{
+            FinishReason, LlmProvider, ToolCompletionRequest, ToolCompletionResponse,
+        };
+        use async_trait::async_trait;
+        use rust_decimal::Decimal;
+
+        struct NoneContentToolLlm;
+
+        #[async_trait]
+        impl LlmProvider for NoneContentToolLlm {
+            fn model_name(&self) -> &str {
+                "none-content-tool-llm"
+            }
+
+            fn cost_per_token(&self) -> (Decimal, Decimal) {
+                (Decimal::ZERO, Decimal::ZERO)
+            }
+
+            async fn complete(
+                &self,
+                _request: crate::llm::CompletionRequest,
+            ) -> Result<crate::llm::CompletionResponse, crate::llm::LlmError> {
+                unreachable!("tool-mode test should not call complete()")
+            }
+
+            async fn complete_with_tools(
+                &self,
+                _request: ToolCompletionRequest,
+            ) -> Result<ToolCompletionResponse, crate::llm::LlmError> {
+                Ok(ToolCompletionResponse {
+                    content: None,
+                    tool_calls: Vec::new(),
+                    input_tokens: 0,
+                    output_tokens: 0,
+                    finish_reason: FinishReason::Stop,
+                    cache_read_input_tokens: 0,
+                    cache_creation_input_tokens: 0,
+                })
+            }
+        }
+
+        let reasoning = Reasoning::new(Arc::new(NoneContentToolLlm));
+
+        let context = ReasoningContext::new()
+            .with_message(ChatMessage::user("list tools"))
+            .with_tools(vec![ToolDefinition {
+                name: "tool_list".to_string(),
+                description: "Lists tools".to_string(),
+                parameters: serde_json::json!({}),
+            }]);
+
+        let output = reasoning.respond_with_tools(&context).await.unwrap();
+        let metadata = output.metadata;
+        match output.result {
+            RespondResult::Text(text) => {
+                assert_eq!(text, "I'm not sure how to respond to that.");
+                assert_eq!(metadata.anomaly, Some(ResponseAnomaly::EmptyToolCompletion));
             }
             RespondResult::ToolCalls { .. } => {
                 panic!("Expected fallback text, not tool calls");

src/tools/builtin/file.rs

@@ -117,13 +117,6 @@ impl Tool for ReadFileTool {
 
         let path = validate_path(path_str, self.base_dir.as_deref())?;
 
-        if super::path_utils::is_sensitive_path(&path) {
-            return Err(ToolError::NotAuthorized(format!(
-                "Access denied: '{}' is a sensitive path. Use the appropriate secrets management tool instead.",
-                path_str
-            )));
-        }
-
         // Check file size
         let metadata = fs::metadata(&path)
             .await
@@ -263,13 +256,6 @@ impl Tool for WriteFileTool {
 
         let path = validate_path(path_str, self.base_dir.as_deref())?;
 
-        if super::path_utils::is_sensitive_path(&path) {
-            return Err(ToolError::NotAuthorized(format!(
-                "Access denied: '{}' is a sensitive path",
-                path_str
-            )));
-        }
-
         // Create parent directories
         if let Some(parent) = path.parent() {
             fs::create_dir_all(parent).await.map_err(|e| {
@@ -378,13 +364,6 @@ impl Tool for ListDirTool {
 
         let path = validate_path(path_str, self.base_dir.as_deref())?;
 
-        if super::path_utils::is_sensitive_path(&path) {
-            return Err(ToolError::NotAuthorized(format!(
-                "Access denied: '{}' is a sensitive directory",
-                path_str
-            )));
-        }
-
         let mut entries = Vec::new();
         list_dir_inner(&path, &path, recursive, max_depth, 0, &mut entries).await?;
 
@@ -468,10 +447,6 @@ async fn list_dir_inner(
         entries.push(display);
 
         if recursive && is_dir && current_depth < max_depth {
-            // Skip sensitive directories during recursive traversal
-            if super::path_utils::is_sensitive_path(&entry_path) {
-                continue;
-            }
             // Skip common non-essential directories
             let name = entry.file_name();
             let name_str = name.to_string_lossy();
@@ -586,13 +561,6 @@ impl Tool for ApplyPatchTool {
 
         let path = validate_path(path_str, self.base_dir.as_deref())?;
 
-        if super::path_utils::is_sensitive_path(&path) {
-            return Err(ToolError::NotAuthorized(format!(
-                "Access denied: '{}' is a sensitive path",
-                path_str
-            )));
-        }
-
         // Read current content
         let content = fs::read_to_string(&path)
             .await

src/tools/builtin/path_utils.rs

@@ -4,119 +4,9 @@
 //! attacks and ensure paths stay within allowed sandboxes.
 
 use std::path::{Path, PathBuf};
-use std::sync::LazyLock;
 
 use crate::tools::tool::ToolError;
 
-/// Paths that contain credentials, secrets, or private keys.
-/// Used by both file tools (exact path check) and shell tool (substring scan).
-/// Keep sorted by category for readability.
-static SENSITIVE_PATH_PATTERNS: LazyLock<Vec<&'static str>> = LazyLock::new(|| {
-    vec![
-        // SSH
-        "/.ssh/",
-        "/id_rsa",
-        "/id_ed25519",
-        "/id_ecdsa",
-        "/id_dsa",
-        "/authorized_keys",
-        "/known_hosts",
-        // GPG
-        "/.gnupg/",
-        // AWS
-        "/.aws/credentials",
-        "/.aws/config",
-        // Kubernetes
-        "/.kube/config",
-        // Cloud providers
-        "/.azure/",
-        "/.gcloud/",
-        "/.config/gcloud/",
-        // Terraform
-        "/.terraform.d/credentials.tfrc.json",
-        // GitHub CLI
-        "/.config/gh/hosts.yml",
-        // Docker
-        "/.docker/config.json",
-        // Vault
-        "/.vault-token",
-        // Shell history
-        "/.bash_history",
-        "/.zsh_history",
-        "/.histfile",
-        // Env files (may contain secrets)
-        "/.env",
-        // Git credentials
-        "/.git-credentials",
-        "/.netrc",
-        "/.pgpass",
-        // IronClaw's own secrets
-        "/.ironclaw/secrets/",
-        // System
-        "/etc/shadow",
-        "/etc/gshadow",
-    ]
-});
-
-/// File extensions that are always sensitive regardless of location.
-static SENSITIVE_EXTENSIONS: LazyLock<Vec<&'static str>> =
-    LazyLock::new(|| vec![".pem", ".key", ".p12", ".pfx", ".jks", ".keystore"]);
-
-/// Suffixes that indicate a file is safe despite matching a sensitive pattern
-/// (e.g., `.env.example`, `.env.sample`).
-static SAFE_SUFFIXES: LazyLock<Vec<&'static str>> =
-    LazyLock::new(|| vec![".example", ".sample", ".template", ".dist", ".bak.example"]);
-
-/// Check if a resolved file path points to a sensitive location.
-/// Used by file tools (read, write, list_dir, apply_patch).
-pub fn is_sensitive_path(path: &Path) -> bool {
-    let path_str = match path.canonicalize() {
-        Ok(p) => p.to_string_lossy().to_string(),
-        Err(_) => path.to_string_lossy().to_string(),
-    };
-
-    // Safe suffixes override sensitive patterns
-    let lower = path_str.to_lowercase();
-    if SAFE_SUFFIXES.iter().any(|s| lower.ends_with(s)) {
-        return false;
-    }
-
-    // Check sensitive path patterns
-    if SENSITIVE_PATH_PATTERNS.iter().any(|p| path_str.contains(p)) {
-        return true;
-    }
-
-    // Check sensitive file extensions
-    if let Some(ext) = path.extension().and_then(|e| e.to_str()) {
-        let dot_ext = format!(".{}", ext.to_lowercase());
-        if SENSITIVE_EXTENSIONS.iter().any(|e| *e == dot_ext) {
-            return true;
-        }
-    }
-
-    false
-}
-
-/// Scan a shell command string for references to sensitive paths.
-/// Returns the first matched pattern, or None if the command is clean.
-/// Used by the shell tool to block `cat ~/.ssh/id_rsa` etc.
-pub fn command_references_sensitive_path(command: &str) -> Option<&'static str> {
-    let normalized = command.to_lowercase();
-
-    for pattern in SENSITIVE_PATH_PATTERNS.iter() {
-        // For path patterns, check case-insensitively
-        if normalized.contains(&pattern.to_lowercase()) {
-            return Some(pattern);
-        }
-    }
-
-    // Check for sensitive extensions in file arguments
-    SENSITIVE_EXTENSIONS
-        .iter()
-        .find(|ext| normalized.contains(*ext))
-        .copied()
-}
-
 /// Normalize a path by resolving `.` and `..` components lexically (no filesystem access).
 ///
 /// This is critical for security: `std::fs::canonicalize` only works on paths that exist,
@@ -346,95 +236,4 @@ mod tests {
         let result = validate_path("a/b/../c.txt", Some(dir.path()));
         assert!(result.is_ok());
     }
-
-    // ── sensitive path tests ──
-
-    #[test]
-    fn test_is_sensitive_path_blocks_ssh() {
-        assert!(is_sensitive_path(Path::new("/home/user/.ssh/id_rsa")));
-        assert!(is_sensitive_path(Path::new(
-            "/home/user/.ssh/authorized_keys"
-        )));
-        assert!(is_sensitive_path(Path::new("/root/.ssh/config")));
-    }
-
-    #[test]
-    fn test_is_sensitive_path_blocks_cloud_credentials() {
-        assert!(is_sensitive_path(Path::new("/home/user/.aws/credentials")));
-        assert!(is_sensitive_path(Path::new("/home/user/.kube/config")));
-        assert!(is_sensitive_path(Path::new("/home/user/.azure/some_token")));
-        assert!(is_sensitive_path(Path::new(
-            "/home/user/.config/gh/hosts.yml"
-        )));
-    }
-
-    #[test]
-    fn test_is_sensitive_path_blocks_system_secrets() {
-        assert!(is_sensitive_path(Path::new("/etc/shadow")));
-        assert!(is_sensitive_path(Path::new("/etc/gshadow")));
-    }
-
-    #[test]
-    fn test_is_sensitive_path_blocks_key_files_by_extension() {
-        assert!(is_sensitive_path(Path::new("/tmp/server.pem")));
-        assert!(is_sensitive_path(Path::new("/app/certs/private.key")));
-        assert!(is_sensitive_path(Path::new("/home/user/keystore.p12")));
-    }
-
-    #[test]
-    fn test_is_sensitive_path_allows_safe_suffixes() {
-        assert!(!is_sensitive_path(Path::new("/app/.env.example")));
-        assert!(!is_sensitive_path(Path::new("/app/.env.sample")));
-        assert!(!is_sensitive_path(Path::new("/app/.env.template")));
-    }
-
-    #[test]
-    fn test_is_sensitive_path_allows_normal_files() {
-        assert!(!is_sensitive_path(Path::new("/app/src/main.rs")));
-        assert!(!is_sensitive_path(Path::new("/home/user/README.md")));
-        assert!(!is_sensitive_path(Path::new("/tmp/output.json")));
-    }
-
-    #[test]
-    fn test_is_sensitive_path_blocks_env_files() {
-        assert!(is_sensitive_path(Path::new("/app/.env")));
-        assert!(is_sensitive_path(Path::new("/app/.env.local")));
-        assert!(is_sensitive_path(Path::new("/app/.env.production")));
-    }
-
-    // ── command scanning tests ──
-
-    #[test]
-    fn test_command_references_sensitive_path_catches_cat_ssh() {
-        assert!(command_references_sensitive_path("cat ~/.ssh/id_rsa").is_some());
-        assert!(
-            command_references_sensitive_path("head -n 5 /home/user/.ssh/authorized_keys")
-                .is_some()
-        );
-    }
-
-    #[test]
-    fn test_command_references_sensitive_path_catches_aws() {
-        assert!(command_references_sensitive_path("cat ~/.aws/credentials").is_some());
-        assert!(command_references_sensitive_path("grep key ~/.aws/config").is_some());
-    }
-
-    #[test]
-    fn test_command_references_sensitive_path_catches_etc_shadow() {
-        assert!(command_references_sensitive_path("cat /etc/shadow").is_some());
-    }
-
-    #[test]
-    fn test_command_references_sensitive_path_catches_key_extensions() {
-        assert!(command_references_sensitive_path("cp server.pem /tmp/").is_some());
-        assert!(command_references_sensitive_path("cat private.key").is_some());
-    }
-
-    #[test]
-    fn test_command_references_sensitive_path_allows_safe_commands() {
-        assert!(command_references_sensitive_path("ls -la").is_none());
-        assert!(command_references_sensitive_path("cargo build").is_none());
-        assert!(command_references_sensitive_path("git status").is_none());
-        assert!(command_references_sensitive_path("cat README.md").is_none());
-    }
 }

src/tools/builtin/shell.rs

@@ -83,12 +83,21 @@ static BLOCKED_COMMANDS: LazyLock<HashSet<&'static str>> = LazyLock::new(|| {
 });
 
 /// Patterns that indicate potentially dangerous commands.
-/// Note: sensitive file paths (/.ssh/, /etc/shadow, etc.) are now handled by
-/// `command_references_sensitive_path` in path_utils.rs for consistency with
-/// file tool protections. This list covers command-level dangers only.
 static DANGEROUS_PATTERNS: LazyLock<Vec<&'static str>> = LazyLock::new(|| {
     vec![
-        "sudo ", "doas ", " | sh", " | bash", " | zsh", "eval ", "$(curl", "$(wget",
+        "sudo ",
+        "doas ",
+        " | sh",
+        " | bash",
+        " | zsh",
+        "eval ",
+        "$(curl",
+        "$(wget",
+        "/etc/passwd",
+        "/etc/shadow",
+        "~/.ssh",
+        ".bash_history",
+        "id_rsa",
     ]
 });
 
@@ -613,11 +622,6 @@ impl ShellTool {
             }
         }
 
-        // Block commands that reference sensitive file paths (shared with file tools)
-        if super::path_utils::command_references_sensitive_path(cmd).is_some() {
-            return Some("Command references sensitive file path");
-        }
-
         None
     }
 

src/worker/autonomous_recovery.rs

@@ -0,0 +1,150 @@
+use crate::llm::{ResponseAnomaly, ResponseMetadata};
+
+pub(crate) const EMPTY_TOOL_COMPLETION_NUDGE: &str = "\
+Your previous tool-enabled response was empty or malformed.\n\
+If you need to use a tool, call it now with valid arguments.\n\
+Otherwise, provide a real status update about work already completed.";
+
+pub(crate) const FORCE_TEXT_RECOVERY_PROMPT: &str = "\
+Your previous tool-enabled responses were empty or malformed.\n\
+Do not call any more tools in the next reply.\n\
+Instead, provide a concise final status based only on work already completed.\n\
+If the job is complete, say so explicitly. If not, explain what blocked you.";
+
+pub(crate) const EMPTY_TOOL_COMPLETION_FAILURE: &str = "the selected model repeatedly returned empty or malformed tool-completion responses and is not reliable for autonomous tool use.";
+
+#[derive(Debug, Default, Clone, Copy)]
+pub(crate) struct AutonomousRecoveryState {
+    consecutive_empty_tool_completions: usize,
+    force_text_recovery_pending: bool,
+    force_text_recovery_active: bool,
+}
+
+#[derive(Debug, Clone, Copy, PartialEq, Eq)]
+pub(crate) enum AutonomousRecoveryAction {
+    Continue,
+    ToolModeNudge,
+    ForceTextRecovery,
+    Fail,
+}
+
+impl AutonomousRecoveryState {
+    pub(crate) fn begin_iteration(&mut self) -> bool {
+        if self.force_text_recovery_pending {
+            self.force_text_recovery_pending = false;
+            self.force_text_recovery_active = true;
+            true
+        } else {
+            self.force_text_recovery_active
+        }
+    }
+
+    pub(crate) fn on_text_response(
+        &mut self,
+        metadata: ResponseMetadata,
+        text: &str,
+    ) -> AutonomousRecoveryAction {
+        match metadata.anomaly {
+            Some(ResponseAnomaly::EmptyToolCompletion) => {
+                self.consecutive_empty_tool_completions =
+                    self.consecutive_empty_tool_completions.saturating_add(1);
+                self.force_text_recovery_active = false;
+                match self.consecutive_empty_tool_completions {
+                    1 => AutonomousRecoveryAction::ToolModeNudge,
+                    2 => {
+                        self.force_text_recovery_pending = true;
+                        AutonomousRecoveryAction::ForceTextRecovery
+                    }
+                    _ => AutonomousRecoveryAction::Fail,
+                }
+            }
+            Some(ResponseAnomaly::EmptyTextResponse) if self.force_text_recovery_active => {
+                self.force_text_recovery_active = false;
+                AutonomousRecoveryAction::Fail
+            }
+            _ if !text.trim().is_empty() => {
+                self.reset();
+                AutonomousRecoveryAction::Continue
+            }
+            _ => AutonomousRecoveryAction::Continue,
+        }
+    }
+
+    pub(crate) fn on_valid_tool_call(&mut self) {
+        self.reset();
+    }
+
+    fn reset(&mut self) {
+        self.consecutive_empty_tool_completions = 0;
+        self.force_text_recovery_pending = false;
+        self.force_text_recovery_active = false;
+    }
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+
+    fn metadata(anomaly: ResponseAnomaly) -> ResponseMetadata {
+        ResponseMetadata {
+            anomaly: Some(anomaly),
+        }
+    }
+
+    #[test]
+    fn first_empty_tool_completion_issues_nudge() {
+        let mut state = AutonomousRecoveryState::default();
+        let action = state.on_text_response(
+            metadata(ResponseAnomaly::EmptyToolCompletion),
+            "I'm not sure how to respond to that.",
+        );
+        assert_eq!(action, AutonomousRecoveryAction::ToolModeNudge);
+        assert!(!state.begin_iteration());
+    }
+
+    #[test]
+    fn second_empty_tool_completion_schedules_text_recovery() {
+        let mut state = AutonomousRecoveryState::default();
+        let _ = state.on_text_response(metadata(ResponseAnomaly::EmptyToolCompletion), "fallback");
+        let action =
+            state.on_text_response(metadata(ResponseAnomaly::EmptyToolCompletion), "fallback");
+        assert_eq!(action, AutonomousRecoveryAction::ForceTextRecovery);
+        assert!(state.begin_iteration());
+    }
+
+    #[test]
+    fn forced_text_recovery_fallback_fails() {
+        let mut state = AutonomousRecoveryState::default();
+        let _ = state.on_text_response(metadata(ResponseAnomaly::EmptyToolCompletion), "fallback");
+        let _ = state.on_text_response(metadata(ResponseAnomaly::EmptyToolCompletion), "fallback");
+        assert!(state.begin_iteration());
+        let action =
+            state.on_text_response(metadata(ResponseAnomaly::EmptyTextResponse), "fallback");
+        assert_eq!(action, AutonomousRecoveryAction::Fail);
+    }
+
+    #[test]
+    fn valid_tool_call_resets_counter() {
+        let mut state = AutonomousRecoveryState::default();
+        let _ = state.on_text_response(metadata(ResponseAnomaly::EmptyToolCompletion), "fallback");
+        state.on_valid_tool_call();
+        let action =
+            state.on_text_response(metadata(ResponseAnomaly::EmptyToolCompletion), "fallback");
+        assert_eq!(action, AutonomousRecoveryAction::ToolModeNudge);
+    }
+
+    #[test]
+    fn meaningful_text_after_text_recovery_resets_state() {
+        let mut state = AutonomousRecoveryState::default();
+        let _ = state.on_text_response(metadata(ResponseAnomaly::EmptyToolCompletion), "fallback");
+        let _ = state.on_text_response(metadata(ResponseAnomaly::EmptyToolCompletion), "fallback");
+        assert!(state.begin_iteration());
+
+        let action = state.on_text_response(ResponseMetadata::default(), "Still working on step 2");
+        assert_eq!(action, AutonomousRecoveryAction::Continue);
+
+        let next =
+            state.on_text_response(metadata(ResponseAnomaly::EmptyToolCompletion), "fallback");
+        assert_eq!(next, AutonomousRecoveryAction::ToolModeNudge);
+    }
+}

src/worker/container.rs

@@ -21,11 +21,15 @@ use crate::agent::agentic_loop::{
 use crate::config::SafetyConfig;
 use crate::context::JobContext;
 use crate::error::WorkerError;
-use crate::llm::{ChatMessage, LlmProvider, Reasoning, ReasoningContext};
+use crate::llm::{ChatMessage, LlmProvider, Reasoning, ReasoningContext, ResponseMetadata};
 use crate::safety::SafetyLayer;
 use crate::tools::ToolRegistry;
 use crate::tools::execute::{execute_tool_simple, process_tool_result};
 use crate::worker::api::{CompletionReport, JobEventPayload, StatusUpdate, WorkerHttpClient};
+use crate::worker::autonomous_recovery::{
+    AutonomousRecoveryAction, AutonomousRecoveryState, EMPTY_TOOL_COMPLETION_FAILURE,
+    EMPTY_TOOL_COMPLETION_NUDGE, FORCE_TEXT_RECOVERY_PROMPT,
+};
 use crate::worker::proxy_llm::ProxyLlmProvider;
 
 /// Configuration for the worker runtime.
@@ -170,6 +174,7 @@ Work independently to complete this job. When finished, your final message MUST
                 extra_env: self.extra_env.clone(),
                 last_output: Mutex::new(String::new()),
                 iteration_tracker: iteration_tracker.clone(),
+                recovery_state: Mutex::new(AutonomousRecoveryState::default()),
             };
 
             let config = AgenticLoopConfig {
@@ -228,6 +233,24 @@ Work independently to complete this job. When finished, your final message MUST
                     })
                     .await?;
             }
+            Ok(Ok(LoopOutcome::Failure(reason))) => {
+                tracing::warn!("Worker failed for job {}: {}", self.config.job_id, reason);
+                self.post_event(
+                    "result",
+                    serde_json::json!({
+                        "success": false,
+                        "message": reason,
+                    }),
+                )
+                .await;
+                self.client
+                    .report_complete(&CompletionReport {
+                        success: false,
+                        message: Some(reason),
+                        iterations,
+                    })
+                    .await?;
+            }
             Ok(Ok(LoopOutcome::Stopped | LoopOutcome::NeedApproval(_))) => {
                 tracing::info!("Worker for job {} stopped", self.config.job_id);
                 self.client
@@ -304,6 +327,7 @@ struct ContainerDelegate {
     /// Tracks the current iteration — shared with the outer `run` method so
     /// `CompletionReport` can include accurate iteration counts.
     iteration_tracker: Arc<Mutex<u32>>,
+    recovery_state: Mutex<AutonomousRecoveryState>,
 }
 
 impl ContainerDelegate {
@@ -377,8 +401,17 @@ impl LoopDelegate for ContainerDelegate {
         // conversation. Ensure the last message is user-role before calling the LLM.
         crate::util::ensure_ends_with_user_message(&mut reason_ctx.messages);
 
-        // Refresh tools (in case WASM tools were built)
-        reason_ctx.available_tools = self.tools.tool_definitions().await;
+        let force_text_recovery = {
+            let mut recovery = self.recovery_state.lock().await;
+            recovery.begin_iteration()
+        };
+        if force_text_recovery {
+            tracing::warn!("Switching to text-only recovery after malformed tool completions");
+            reason_ctx.available_tools.clear();
+        } else {
+            // Refresh tools (in case WASM tools were built)
+            reason_ctx.available_tools = self.tools.tool_definitions().await;
+        }
 
         None
     }
@@ -399,8 +432,53 @@ impl LoopDelegate for ContainerDelegate {
     async fn handle_text_response(
         &self,
         text: &str,
+        metadata: ResponseMetadata,
         reason_ctx: &mut ReasoningContext,
     ) -> TextAction {
+        let action = {
+            let mut recovery = self.recovery_state.lock().await;
+            recovery.on_text_response(metadata, text)
+        };
+        match action {
+            AutonomousRecoveryAction::ToolModeNudge => {
+                tracing::warn!("Malformed empty tool completion detected; retrying in tool mode");
+                self.post_event(
+                    "status",
+                    serde_json::json!({
+                        "message": "Model returned an empty tool-completion response; retrying with a stronger tool-use nudge.",
+                    }),
+                )
+                .await;
+                reason_ctx
+                    .messages
+                    .push(ChatMessage::user(EMPTY_TOOL_COMPLETION_NUDGE));
+                return TextAction::Continue;
+            }
+            AutonomousRecoveryAction::ForceTextRecovery => {
+                tracing::warn!(
+                    "Repeated malformed tool completions detected; switching to text-only recovery"
+                );
+                self.post_event(
+                    "status",
+                    serde_json::json!({
+                        "message": "Model returned repeated empty tool-completion responses; requesting a final status update without tools.",
+                    }),
+                )
+                .await;
+                reason_ctx
+                    .messages
+                    .push(ChatMessage::user(FORCE_TEXT_RECOVERY_PROMPT));
+                return TextAction::Continue;
+            }
+            AutonomousRecoveryAction::Fail => {
+                tracing::warn!("Failing fast after repeated malformed autonomous responses");
+                return TextAction::Return(LoopOutcome::Failure(
+                    EMPTY_TOOL_COMPLETION_FAILURE.to_string(),
+                ));
+            }
+            AutonomousRecoveryAction::Continue => {}
+        }
+
         self.post_event(
             "message",
             serde_json::json!({
@@ -431,6 +509,11 @@ impl LoopDelegate for ContainerDelegate {
         content: Option<String>,
         reason_ctx: &mut ReasoningContext,
     ) -> Result<Option<LoopOutcome>, crate::error::Error> {
+        {
+            let mut recovery = self.recovery_state.lock().await;
+            recovery.on_valid_tool_call();
+        }
+
         if let Some(ref text) = content {
             self.post_event(
                 "message",

src/worker/job.rs

@@ -23,8 +23,8 @@ use crate::context::{ContextManager, JobState};
 use crate::error::Error;
 use crate::hooks::HookRegistry;
 use crate::llm::{
-    ActionPlan, ChatMessage, LlmProvider, Reasoning, ReasoningContext, RespondResult, ToolCall,
-    ToolSelection,
+    ActionPlan, ChatMessage, LlmProvider, Reasoning, ReasoningContext, RespondResult,
+    ResponseMetadata, ToolCall, ToolSelection,
 };
 use crate::safety::SafetyLayer;
 use crate::tenant::AdminScope;
@@ -33,6 +33,10 @@ use crate::tools::rate_limiter::RateLimitResult;
 use crate::tools::{
     ApprovalContext, ToolRegistry, autonomous_unavailable_error, prepare_tool_params, redact_params,
 };
+use crate::worker::autonomous_recovery::{
+    AutonomousRecoveryAction, AutonomousRecoveryState, EMPTY_TOOL_COMPLETION_FAILURE,
+    EMPTY_TOOL_COMPLETION_NUDGE, FORCE_TEXT_RECOVERY_PROMPT,
+};
 use ironclaw_common::AppEvent;
 
 /// Shared dependencies for worker execution.
@@ -391,6 +395,7 @@ Report when the job is complete or if you encounter issues you cannot resolve."#
             worker: self,
             rx: tokio::sync::Mutex::new(rx),
             consecutive_rate_limits: std::sync::atomic::AtomicUsize::new(0),
+            recovery_state: tokio::sync::Mutex::new(AutonomousRecoveryState::default()),
         };
 
         let config = AgenticLoopConfig {
@@ -409,6 +414,9 @@ Report when the job is complete or if you encounter issues you cannot resolve."#
                 self.mark_failed("Maximum iterations exceeded: job hit the iteration cap")
                     .await?;
             }
+            LoopOutcome::Failure(reason) => {
+                self.mark_failed(&reason).await?;
+            }
             LoopOutcome::Stopped => {
                 // Stop signal handled — nothing more to do
             }
@@ -1109,6 +1117,7 @@ struct JobDelegate<'a> {
     rx: tokio::sync::Mutex<&'a mut mpsc::Receiver<WorkerMessage>>,
     /// Tracks consecutive rate-limit errors to fail fast instead of burning iterations.
     consecutive_rate_limits: std::sync::atomic::AtomicUsize,
+    recovery_state: tokio::sync::Mutex<AutonomousRecoveryState>,
 }
 
 impl<'a> JobDelegate<'a> {
@@ -1159,6 +1168,7 @@ impl<'a> JobDelegate<'a> {
             result: RespondResult::Text(String::new()),
             usage: crate::llm::TokenUsage::default(),
             finish_reason: crate::llm::FinishReason::Stop,
+            metadata: ResponseMetadata::default(),
         })
     }
 }
@@ -1250,8 +1260,21 @@ impl<'a> LoopDelegate for JobDelegate<'a> {
         reason_ctx: &mut ReasoningContext,
         _iteration: usize,
     ) -> Option<LoopOutcome> {
-        // Refresh tool definitions so newly built tools become visible
-        reason_ctx.available_tools = self.worker.tools().tool_definitions().await;
+        let force_text_recovery = {
+            let mut recovery = self.recovery_state.lock().await;
+            recovery.begin_iteration()
+        };
+
+        if force_text_recovery {
+            tracing::warn!(
+                job_id = %self.worker.job_id,
+                "Switching to text-only recovery after malformed tool completions"
+            );
+            reason_ctx.available_tools.clear();
+        } else {
+            // Refresh tool definitions so newly built tools become visible
+            reason_ctx.available_tools = self.worker.tools().tool_definitions().await;
+        }
 
         // Claude 4.6 rejects assistant prefill; NEAR AI rejects any non-user-ending
         // conversation. Ensure the last message is user-role before calling the LLM.
@@ -1285,6 +1308,7 @@ impl<'a> LoopDelegate for JobDelegate<'a> {
                     },
                     usage: crate::llm::TokenUsage::default(),
                     finish_reason: crate::llm::FinishReason::ToolUse,
+                    metadata: ResponseMetadata::default(),
                 });
             }
             Ok(_) => {} // empty selections, fall through
@@ -1328,8 +1352,59 @@ impl<'a> LoopDelegate for JobDelegate<'a> {
     async fn handle_text_response(
         &self,
         text: &str,
+        metadata: ResponseMetadata,
         reason_ctx: &mut ReasoningContext,
     ) -> TextAction {
+        let action = {
+            let mut recovery = self.recovery_state.lock().await;
+            recovery.on_text_response(metadata, text)
+        };
+
+        match action {
+            AutonomousRecoveryAction::ToolModeNudge => {
+                tracing::warn!(
+                    job_id = %self.worker.job_id,
+                    "Malformed empty tool completion detected; retrying in tool mode"
+                );
+                self.worker.log_event(
+                    "status",
+                    serde_json::json!({
+                        "message": "Model returned an empty tool-completion response; retrying with a stronger tool-use nudge.",
+                    }),
+                );
+                reason_ctx
+                    .messages
+                    .push(ChatMessage::user(EMPTY_TOOL_COMPLETION_NUDGE));
+                return TextAction::Continue;
+            }
+            AutonomousRecoveryAction::ForceTextRecovery => {
+                tracing::warn!(
+                    job_id = %self.worker.job_id,
+                    "Repeated malformed tool completions detected; switching to text-only recovery"
+                );
+                self.worker.log_event(
+                    "status",
+                    serde_json::json!({
+                        "message": "Model returned repeated empty tool-completion responses; requesting a final status update without tools.",
+                    }),
+                );
+                reason_ctx
+                    .messages
+                    .push(ChatMessage::user(FORCE_TEXT_RECOVERY_PROMPT));
+                return TextAction::Continue;
+            }
+            AutonomousRecoveryAction::Fail => {
+                tracing::warn!(
+                    job_id = %self.worker.job_id,
+                    "Failing fast after repeated malformed autonomous responses"
+                );
+                return TextAction::Return(LoopOutcome::Failure(
+                    EMPTY_TOOL_COMPLETION_FAILURE.to_string(),
+                ));
+            }
+            AutonomousRecoveryAction::Continue => {}
+        }
+
         // Empty text from rate-limit backoff retry — skip processing and let the
         // loop proceed to the next iteration which will re-call the LLM.
         if text.is_empty() {
@@ -1368,6 +1443,11 @@ impl<'a> LoopDelegate for JobDelegate<'a> {
         content: Option<String>,
         reason_ctx: &mut ReasoningContext,
     ) -> Result<Option<LoopOutcome>, crate::error::Error> {
+        {
+            let mut recovery = self.recovery_state.lock().await;
+            recovery.on_valid_tool_call();
+        }
+
         if let Some(ref text) = content {
             self.worker.log_event(
                 "message",

src/worker/mod.rs

@@ -25,6 +25,7 @@
 //! ```
 
 pub mod api;
+mod autonomous_recovery;
 pub mod claude_bridge;
 pub mod container;
 pub mod job;

tests/e2e_builtin_tool_coverage.rs

@@ -11,9 +11,76 @@ mod tests {
     use std::time::Duration;
 
     use ironclaw::agent::routine::{RoutineAction, Trigger};
+    use ironclaw::context::{JobContext, JobState};
+    use uuid::Uuid;
 
-    use crate::support::test_rig::TestRigBuilder;
-    use crate::support::trace_llm::LlmTrace;
+    use crate::support::test_rig::{TestRig, TestRigBuilder};
+    use crate::support::trace_llm::{LlmTrace, RequestHint, TraceResponse, TraceStep};
+
+    fn text_step(content: &str) -> TraceStep {
+        TraceStep {
+            request_hint: None,
+            response: TraceResponse::Text {
+                content: content.to_string(),
+                input_tokens: 10,
+                output_tokens: 5,
+            },
+            expected_tool_results: Vec::new(),
+        }
+    }
+
+    fn hinted_text_step(content: &str, last_user_message_contains: &str) -> TraceStep {
+        TraceStep {
+            request_hint: Some(RequestHint {
+                last_user_message_contains: Some(last_user_message_contains.to_string()),
+                min_message_count: None,
+            }),
+            response: TraceResponse::Text {
+                content: content.to_string(),
+                input_tokens: 10,
+                output_tokens: 5,
+            },
+            expected_tool_results: Vec::new(),
+        }
+    }
+
+    fn extract_job_id(response: &str) -> Uuid {
+        let id = response
+            .lines()
+            .find_map(|line| line.strip_prefix("ID: "))
+            .expect("job creation response should include an ID line");
+        Uuid::parse_str(id).expect("job ID should be a UUID")
+    }
+
+    async fn wait_for_job_state(rig: &TestRig, job_id: Uuid, expected: JobState) -> JobContext {
+        let deadline = tokio::time::Instant::now() + Duration::from_secs(10);
+
+        loop {
+            if let Some(job) = rig
+                .database()
+                .get_job(job_id)
+                .await
+                .expect("get_job should succeed")
+                && job.state == expected
+            {
+                return job;
+            }
+
+            assert!(
+                tokio::time::Instant::now() < deadline,
+                "job {job_id} did not reach state {expected:?} before timeout"
+            );
+
+            tokio::time::sleep(Duration::from_millis(50)).await;
+        }
+    }
+
+    fn requests_contain(requests: &[Vec<ironclaw::llm::ChatMessage>], needle: &str) -> bool {
+        requests
+            .iter()
+            .flatten()
+            .any(|message| message.content.contains(needle))
+    }
 
     // -----------------------------------------------------------------------
     // Test 1: time_parse_and_diff
@@ -685,6 +752,149 @@ mod tests {
         rig.shutdown();
     }
 
+    // -----------------------------------------------------------------------
+    // Test 8a: command_job_fails_fast_on_repeated_empty_tool_completions
+    // -----------------------------------------------------------------------
+
+    #[tokio::test]
+    async fn command_job_fails_fast_on_repeated_empty_tool_completions() {
+        let trace = LlmTrace::single_turn(
+            "test-empty-tool-recovery-fail",
+            "(worker only)",
+            vec![
+                text_step(""),
+                text_step(""),
+                hinted_text_step("", "valid arguments"),
+                text_step(""),
+                hinted_text_step("", "Do not call any more tools in the next reply."),
+            ],
+        );
+
+        let rig = TestRigBuilder::new()
+            .with_trace(trace)
+            .with_auto_approve_tools(true)
+            .build()
+            .await;
+
+        rig.send_message("/job reproduce empty tool completion loop")
+            .await;
+        let create_responses = rig.wait_for_responses(1, Duration::from_secs(15)).await;
+        let job_id = extract_job_id(&create_responses[0].content);
+
+        let job = wait_for_job_state(&rig, job_id, JobState::Failed).await;
+        assert_eq!(job.title, "reproduce empty tool completion loop");
+
+        let failure_reason = rig
+            .database()
+            .get_agent_job_failure_reason(job_id)
+            .await
+            .expect("get_agent_job_failure_reason should succeed")
+            .expect("failed job should persist a failure reason");
+        assert!(
+            failure_reason
+                .contains("repeatedly returned empty or malformed tool-completion responses"),
+            "unexpected failure reason: {failure_reason}"
+        );
+        assert!(
+            !failure_reason.contains("max iterations"),
+            "failure should not surface as iteration exhaustion: {failure_reason}"
+        );
+
+        assert_eq!(
+            rig.llm_call_count(),
+            5,
+            "worker should stop after the bounded recovery flow"
+        );
+        assert!(
+            !rig.collect_metrics().await.hit_iteration_limit,
+            "bounded recovery should stop before iteration-limit reporting"
+        );
+
+        let requests = rig.captured_llm_requests();
+        assert!(
+            requests_contain(&requests, "call it now with valid arguments"),
+            "expected targeted tool-mode recovery nudge in worker requests"
+        );
+        assert!(
+            requests_contain(&requests, "Do not call any more tools in the next reply."),
+            "expected forced text-only recovery prompt in worker requests"
+        );
+
+        rig.clear().await;
+        rig.send_message(&format!("/status {}", job_id)).await;
+        let status_responses = rig.wait_for_responses(1, Duration::from_secs(5)).await;
+        assert!(
+            status_responses[0].content.contains("Status: Failed"),
+            "unexpected status response: {:?}",
+            status_responses[0].content
+        );
+
+        rig.shutdown();
+    }
+
+    // -----------------------------------------------------------------------
+    // Test 8b: command_job_text_recovery_can_complete
+    // -----------------------------------------------------------------------
+
+    #[tokio::test]
+    async fn command_job_text_recovery_can_complete() {
+        let trace = LlmTrace::single_turn(
+            "test-empty-tool-recovery-success",
+            "(worker only)",
+            vec![
+                text_step(""),
+                text_step(""),
+                hinted_text_step("", "valid arguments"),
+                text_step(""),
+                hinted_text_step(
+                    "The job is complete. I finished the requested work and there is nothing left to do.",
+                    "Do not call any more tools in the next reply.",
+                ),
+            ],
+        );
+
+        let rig = TestRigBuilder::new()
+            .with_trace(trace)
+            .with_auto_approve_tools(true)
+            .build()
+            .await;
+
+        rig.send_message("/job recover after malformed tool completions")
+            .await;
+        let create_responses = rig.wait_for_responses(1, Duration::from_secs(15)).await;
+        let job_id = extract_job_id(&create_responses[0].content);
+
+        let job = wait_for_job_state(&rig, job_id, JobState::Completed).await;
+        assert_eq!(job.title, "recover after malformed tool completions");
+
+        assert_eq!(
+            rig.llm_call_count(),
+            5,
+            "worker should complete within the bounded recovery flow"
+        );
+
+        let requests = rig.captured_llm_requests();
+        assert!(
+            requests_contain(&requests, "call it now with valid arguments"),
+            "expected targeted tool-mode recovery nudge in worker requests"
+        );
+        assert!(
+            requests_contain(&requests, "Do not call any more tools in the next reply."),
+            "expected forced text-only recovery prompt in worker requests"
+        );
+
+        rig.clear().await;
+        rig.send_message(&format!("/status {}", job_id)).await;
+        let status_responses = rig.wait_for_responses(1, Duration::from_secs(5)).await;
+        assert!(
+            status_responses[0].content.contains("Status: Completed"),
+            "unexpected status response: {:?}",
+            status_responses[0].content
+        );
+
+        rig.shutdown();
+    }
+
     // -----------------------------------------------------------------------
     // Test 9: job_list_cancel
     // -----------------------------------------------------------------------