feat: sweep

rust/crates/claw-analog/src/lib.rs

@@ -1111,7 +1111,24 @@ enum BlockKind {
 
 pub(crate) fn format_rag_query_json_for_model(body: &str) -> Result<String, String> {
     let v: Value = serde_json::from_str(body).map_err(|e| format!("invalid JSON: {e}"))?;
-    let phase = v.get("phase").and_then(|x| x.as_str()).unwrap_or("unknown");
+    let phase = v.get("phase").and_then(|x| x.as_str()).ok_or_else(|| {
+        json!({
+            "kind": "unknown_bootstrap_phase",
+            "field": "phase",
+            "received_value": v.get("phase").cloned().unwrap_or(Value::Null),
+            "message": "RAG response is missing a string phase; refusing to silently render phase as unknown"
+        })
+        .to_string()
+    })?;
+    if phase.trim().is_empty() || phase == "unknown" {
+        return Err(json!({
+            "kind": "unknown_bootstrap_phase",
+            "field": "phase",
+            "received_value": phase,
+            "message": "RAG response phase must be a concrete phase name"
+        })
+        .to_string());
+    }
     let hits = v
         .get("hits")
         .and_then(|h| h.as_array())
@@ -2557,6 +2574,20 @@ mod tests {
         assert!(out.contains("score="));
     }
 
+    #[test]
+    fn rag_response_missing_phase_returns_typed_error() {
+        let err = format_rag_query_json_for_model(r#"{"hits":[]}"#).unwrap_err();
+        assert!(err.contains(r#""kind":"unknown_bootstrap_phase""#));
+        assert!(err.contains(r#""field":"phase""#));
+    }
+
+    #[test]
+    fn rag_response_unknown_phase_returns_typed_error() {
+        let err = format_rag_query_json_for_model(r#"{"hits":[],"phase":"unknown"}"#).unwrap_err();
+        assert!(err.contains(r#""kind":"unknown_bootstrap_phase""#));
+        assert!(err.contains(r#""received_value":"unknown""#));
+    }
+
     #[test]
     fn resolve_rag_base_url_toml_beats_env() {
         let _g = mock_env_lock();

rust/crates/runtime/src/trust_resolver.rs

@@ -438,13 +438,24 @@ fn normalize_path(path: &Path) -> PathBuf {
 /// Extract repository name from a path for event context.
 fn extract_repo_name(cwd: &str) -> Option<String> {
     let path = Path::new(cwd);
-    // Try to find a .git directory to identify repo root
-    let mut current = Some(path);
-    while let Some(p) = current {
-        if p.join(".git").is_dir() {
-            return p.file_name().map(|n| n.to_string_lossy().to_string());
+    // Ask git from the cwd itself. Walking ancestors manually can accidentally
+    // classify synthetic/nonexistent paths as an unrelated parent repo (for
+    // example `/tmp/.git`), which makes trust events point at the wrong repo.
+    if path.is_dir() {
+        if let Ok(output) = std::process::Command::new("git")
+            .args(["rev-parse", "--show-toplevel"])
+            .current_dir(path)
+            .output()
+        {
+            if output.status.success() {
+                let root = String::from_utf8_lossy(&output.stdout).trim().to_string();
+                if !root.is_empty() {
+                    return Path::new(&root)
+                        .file_name()
+                        .map(|n| n.to_string_lossy().to_string());
+                }
+            }
         }
-        current = p.parent();
     }
     // Fallback: use the last component of the path
     path.file_name().map(|n| n.to_string_lossy().to_string())

rust/crates/runtime/src/worker_boot.rs

@@ -13,6 +13,7 @@
 
 use std::collections::HashMap;
 use std::path::{Path, PathBuf};
+use std::process::Command;
 use std::sync::{Arc, Mutex};
 use std::time::{SystemTime, UNIX_EPOCH};
 
@@ -73,6 +74,7 @@ pub struct WorkerFailure {
 #[serde(rename_all = "snake_case")]
 pub enum WorkerEventKind {
     Spawning,
+    StartupPreflightWarning,
     TrustRequired,
     ToolPermissionRequired,
     TrustResolved,
@@ -102,6 +104,21 @@ pub enum WorkerPromptTarget {
     Unknown,
 }
 
+#[derive(Debug, Clone, Copy, PartialEq, Eq, Serialize, Deserialize)]
+#[serde(rename_all = "snake_case")]
+pub enum WorkerStartupPreflightWarningKind {
+    FileAbsentOnBranch,
+    GitMetadataNotWritable,
+}
+
+#[derive(Debug, Clone, Serialize, Deserialize, PartialEq, Eq)]
+pub struct WorkerStartupPreflightWarning {
+    pub kind: WorkerStartupPreflightWarningKind,
+    pub message: String,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub path: Option<String>,
+}
+
 /// Classification of startup failure when no evidence is available.
 #[derive(Debug, Clone, Copy, PartialEq, Eq, Serialize, Deserialize)]
 #[serde(rename_all = "snake_case")]
@@ -212,6 +229,12 @@ pub enum WorkerEventPayload {
         evidence: StartupEvidenceBundle,
         classification: StartupFailureClassification,
     },
+    StartupPreflightWarning {
+        kind: WorkerStartupPreflightWarningKind,
+        message: String,
+        #[serde(skip_serializing_if = "Option::is_none")]
+        path: Option<String>,
+    },
 }
 
 #[derive(Debug, Clone, Copy, Serialize, Deserialize, PartialEq, Eq)]
@@ -329,6 +352,34 @@ impl WorkerRegistry {
         inner.workers.get(worker_id).cloned()
     }
 
+    pub fn observe_startup_preflight(
+        &self,
+        worker_id: &str,
+        task_prompt: &str,
+    ) -> Result<Worker, String> {
+        let mut inner = self.inner.lock().expect("worker registry lock poisoned");
+        let worker = inner
+            .workers
+            .get_mut(worker_id)
+            .ok_or_else(|| format!("worker not found: {worker_id}"))?;
+
+        for warning in startup_preflight_warnings(Path::new(&worker.cwd), task_prompt) {
+            push_event(
+                worker,
+                WorkerEventKind::StartupPreflightWarning,
+                worker.status,
+                Some(warning.message.clone()),
+                Some(WorkerEventPayload::StartupPreflightWarning {
+                    kind: warning.kind,
+                    message: warning.message,
+                    path: warning.path,
+                }),
+            );
+        }
+
+        Ok(worker.clone())
+    }
+
     pub fn observe(&self, worker_id: &str, screen_text: &str) -> Result<Worker, String> {
         let mut inner = self.inner.lock().expect("worker registry lock poisoned");
         let worker = inner
@@ -1064,6 +1115,118 @@ fn extract_server_from_qualified_tool(tool: &str) -> Option<String> {
     (!server.is_empty()).then(|| server.to_string())
 }
 
+pub fn startup_preflight_warnings(
+    cwd: &Path,
+    task_prompt: &str,
+) -> Vec<WorkerStartupPreflightWarning> {
+    let mut warnings = Vec::new();
+
+    if let Some(git_path) = git_metadata_path(cwd) {
+        if !path_is_writable(&git_path) {
+            warnings.push(WorkerStartupPreflightWarning {
+                kind: WorkerStartupPreflightWarningKind::GitMetadataNotWritable,
+                message: format!(
+                    "git metadata is not writable; commits or pushes may fail: {}",
+                    git_path.display()
+                ),
+                path: Some(git_path.display().to_string()),
+            });
+        }
+    }
+
+    for path in mentioned_repo_paths(task_prompt) {
+        if !git_tracks_path(cwd, &path) {
+            warnings.push(WorkerStartupPreflightWarning {
+                kind: WorkerStartupPreflightWarningKind::FileAbsentOnBranch,
+                message: format!(
+                    "task mentions {path}, but git does not track it on the current branch"
+                ),
+                path: Some(path),
+            });
+        }
+    }
+
+    warnings
+}
+
+fn mentioned_repo_paths(task_prompt: &str) -> Vec<String> {
+    let mut out = Vec::new();
+    for raw in task_prompt.split_whitespace() {
+        let token = raw.trim_matches(|ch: char| {
+            matches!(
+                ch,
+                '`' | '"' | '\'' | '(' | ')' | '[' | ']' | '{' | '}' | ',' | ';' | ':'
+            )
+        });
+        if !token.contains('/') || token.contains("://") || token.starts_with('/') {
+            continue;
+        }
+        let token = token.trim_start_matches("./");
+        if token.contains("..") {
+            continue;
+        }
+        if token
+            .chars()
+            .all(|ch| ch.is_ascii_alphanumeric() || matches!(ch, '/' | '_' | '-' | '.'))
+            && token
+                .rsplit('/')
+                .next()
+                .is_some_and(|name| name.contains('.'))
+            && !out.iter().any(|seen| seen == token)
+        {
+            out.push(token.to_string());
+        }
+    }
+    out
+}
+
+fn git_tracks_path(cwd: &Path, path: &str) -> bool {
+    Command::new("git")
+        .arg("ls-files")
+        .arg("--error-unmatch")
+        .arg("--")
+        .arg(path)
+        .current_dir(cwd)
+        .output()
+        .is_ok_and(|output| output.status.success())
+}
+
+fn git_metadata_path(cwd: &Path) -> Option<PathBuf> {
+    let output = Command::new("git")
+        .args(["rev-parse", "--git-path", "."])
+        .current_dir(cwd)
+        .output()
+        .ok()?;
+    if !output.status.success() {
+        return None;
+    }
+    let text = String::from_utf8_lossy(&output.stdout).trim().to_string();
+    if text.is_empty() {
+        return None;
+    }
+    let path = PathBuf::from(text);
+    Some(if path.is_absolute() {
+        path
+    } else {
+        cwd.join(path)
+    })
+}
+
+fn path_is_writable(path: &Path) -> bool {
+    let probe_dir = if path.is_dir() {
+        path.to_path_buf()
+    } else {
+        path.parent().unwrap_or(path).to_path_buf()
+    };
+    let probe = probe_dir.join(format!(".claw-write-probe-{}", now_secs()));
+    std::fs::OpenOptions::new()
+        .write(true)
+        .create_new(true)
+        .open(&probe)
+        .and_then(|_| std::fs::remove_file(&probe))
+        .is_ok()
+}
+
 fn detect_trust_prompt(lowered: &str) -> bool {
     [
         "do you trust the files in this folder",
@@ -1285,6 +1448,8 @@ fn cwd_matches_observed_target(expected_cwd: &str, observed_cwd: &str) -> bool {
 #[cfg(test)]
 mod tests {
     use super::*;
+    use std::fs;
+    use std::process::Command;
 
     #[test]
     fn allowlisted_trust_prompt_auto_resolves_then_reaches_ready_state() {
@@ -1431,6 +1596,66 @@ mod tests {
         assert!(!readiness.ready);
     }
 
+    #[test]
+    fn startup_preflight_warns_when_task_file_is_absent_on_branch() {
+        let tmp = tempfile::tempdir().expect("tempdir");
+        Command::new("git")
+            .arg("init")
+            .current_dir(tmp.path())
+            .output()
+            .expect("git init should run");
+        fs::create_dir_all(tmp.path().join("src")).expect("src dir");
+        fs::write(tmp.path().join("src/lib.rs"), "pub fn present() {}\n").expect("write file");
+        Command::new("git")
+            .args(["add", "src/lib.rs"])
+            .current_dir(tmp.path())
+            .output()
+            .expect("git add should run");
+
+        let warnings = startup_preflight_warnings(
+            tmp.path(),
+            "Fix src/lib.rs and rust/crates/runtime/src/trident.rs before testing.",
+        );
+
+        assert!(warnings.iter().any(|warning| {
+            warning.kind == WorkerStartupPreflightWarningKind::FileAbsentOnBranch
+                && warning.path.as_deref() == Some("rust/crates/runtime/src/trident.rs")
+        }));
+        assert!(!warnings.iter().any(|warning| {
+            warning.kind == WorkerStartupPreflightWarningKind::FileAbsentOnBranch
+                && warning.path.as_deref() == Some("src/lib.rs")
+        }));
+    }
+
+    #[test]
+    fn startup_preflight_records_structured_warning_event() {
+        let tmp = tempfile::tempdir().expect("tempdir");
+        Command::new("git")
+            .arg("init")
+            .current_dir(tmp.path())
+            .output()
+            .expect("git init should run");
+        let registry = WorkerRegistry::new();
+        let worker = registry.create(&tmp.path().display().to_string(), &[], true);
+
+        let observed = registry
+            .observe_startup_preflight(&worker.worker_id, "Open missing/file.rs")
+            .expect("preflight should run");
+
+        let event = observed
+            .events
+            .iter()
+            .find(|event| event.kind == WorkerEventKind::StartupPreflightWarning)
+            .expect("preflight warning event");
+        assert!(matches!(
+            event.payload,
+            Some(WorkerEventPayload::StartupPreflightWarning {
+                kind: WorkerStartupPreflightWarningKind::FileAbsentOnBranch,
+                ..
+            })
+        ));
+    }
+
     #[test]
     fn startup_timeout_classifies_tool_permission_prompt() {
         let registry = WorkerRegistry::new();