huskies: merge 531_story_mcp_tool_to_read_agent_session_logs_from_disk_not_just_live_stream

2026-04-10 13:05:04 +00:00
parent 31388da609
commit 1dd675796b
3 changed files with 697 additions and 137 deletions
@@ -78,6 +78,7 @@ fn log_dir(project_root: &Path, story_id: &str) -> PathBuf {
 }

 /// Return the path to a specific log file.
+#[allow(dead_code)]
 pub fn log_file_path(
    project_root: &Path,
    story_id: &str,
@@ -108,6 +109,208 @@ pub fn read_log(path: &Path) -> Result<Vec<LogEntry>, String> {
    Ok(entries)
 }

+/// List all log files for a story, optionally filtered by agent name prefix.
+///
+/// Returns files sorted by modification time (oldest first) so that when all
+/// sessions are concatenated the timeline reads chronologically.
+pub fn list_story_log_files(
+    project_root: &Path,
+    story_id: &str,
+    agent_name_filter: Option<&str>,
+) -> Vec<PathBuf> {
+    let dir = log_dir(project_root, story_id);
+    if !dir.is_dir() {
+        return Vec::new();
+    }
+
+    let prefix = agent_name_filter.map(|n| format!("{n}-"));
+    let mut files: Vec<(PathBuf, std::time::SystemTime)> = Vec::new();
+
+    if let Ok(entries) = fs::read_dir(&dir) {
+        for entry in entries.flatten() {
+            let path = entry.path();
+            let name = match path.file_name().and_then(|n| n.to_str()) {
+                Some(n) => n.to_string(),
+                None => continue,
+            };
+            if !name.ends_with(".log") {
+                continue;
+            }
+            if let Some(ref pfx) = prefix
+                && !name.starts_with(pfx.as_str())
+            {
+                continue;
+            }
+            let modified = entry
+                .metadata()
+                .and_then(|m| m.modified())
+                .unwrap_or(std::time::SystemTime::UNIX_EPOCH);
+            files.push((path, modified));
+        }
+    }
+
+    files.sort_by_key(|(_, t)| *t);
+    files.into_iter().map(|(p, _)| p).collect()
+}
+
+/// Format a single log entry as a human-readable text line.
+///
+/// `timestamp` is an ISO 8601 string; `event` is the flattened `AgentEvent`
+/// value (has `type`, `agent_name`, etc. at the top level).
+///
+/// Returns `None` for entries that should be skipped (raw streaming noise,
+/// trivial status changes, empty output, etc.).
+pub fn format_log_entry_as_text(timestamp: &str, event: &serde_json::Value) -> Option<String> {
+    let agent_name = event
+        .get("agent_name")
+        .and_then(|v| v.as_str())
+        .unwrap_or("?");
+    // Extract HH:MM:SS from ISO 8601 "2026-04-10T12:48:02.123456789+00:00"
+    let ts_short = if timestamp.len() >= 19 {
+        &timestamp[11..19]
+    } else {
+        timestamp
+    };
+    let pfx = format!("[{ts_short}][{agent_name}]");
+
+    match event.get("type").and_then(|v| v.as_str()) {
+        Some("output") => {
+            let text = event
+                .get("text")
+                .and_then(|v| v.as_str())
+                .unwrap_or("")
+                .trim();
+            if text.is_empty() {
+                None
+            } else {
+                Some(format!("{pfx} {text}"))
+            }
+        }
+        Some("error") => {
+            let msg = event
+                .get("message")
+                .and_then(|v| v.as_str())
+                .unwrap_or("(unknown error)");
+            Some(format!("{pfx} ERROR: {msg}"))
+        }
+        Some("done") => Some(format!("{pfx} DONE")),
+        Some("status") => {
+            // Skip trivial running/started noise
+            let status = event
+                .get("status")
+                .and_then(|v| v.as_str())
+                .unwrap_or("?");
+            match status {
+                "running" | "started" => None,
+                _ => Some(format!("{pfx} STATUS: {status}")),
+            }
+        }
+        Some("agent_json") => {
+            let data = event.get("data")?;
+            match data.get("type").and_then(|v| v.as_str()) {
+                Some("assistant") => {
+                    let mut parts: Vec<String> = Vec::new();
+                    if let Some(arr) = data
+                        .pointer("/message/content")
+                        .and_then(|v| v.as_array())
+                    {
+                        for item in arr {
+                            match item.get("type").and_then(|v| v.as_str()) {
+                                Some("text") => {
+                                    let text = item
+                                        .get("text")
+                                        .and_then(|v| v.as_str())
+                                        .unwrap_or("")
+                                        .trim();
+                                    if !text.is_empty() {
+                                        parts.push(format!("{pfx} {text}"));
+                                    }
+                                }
+                                Some("tool_use") => {
+                                    let name = item
+                                        .get("name")
+                                        .and_then(|v| v.as_str())
+                                        .unwrap_or("?");
+                                    let input = item
+                                        .get("input")
+                                        .map(|v| {
+                                            serde_json::to_string(v).unwrap_or_default()
+                                        })
+                                        .unwrap_or_default();
+                                    let display = if input.len() > 200 {
+                                        format!("{}...", &input[..200])
+                                    } else {
+                                        input
+                                    };
+                                    parts.push(format!("{pfx} TOOL: {name}({display})"));
+                                }
+                                _ => {}
+                            }
+                        }
+                    }
+                    if parts.is_empty() {
+                        None
+                    } else {
+                        Some(parts.join("\n"))
+                    }
+                }
+                Some("user") => {
+                    let mut parts: Vec<String> = Vec::new();
+                    if let Some(arr) = data
+                        .pointer("/message/content")
+                        .and_then(|v| v.as_array())
+                    {
+                        for item in arr {
+                            if item.get("type").and_then(|v| v.as_str())
+                                != Some("tool_result")
+                            {
+                                continue;
+                            }
+                            let content_str = match item.get("content") {
+                                Some(serde_json::Value::String(s)) => s.clone(),
+                                Some(v) => v.to_string(),
+                                None => String::new(),
+                            };
+                            let display = if content_str.len() > 500 {
+                                format!(
+                                    "{}... [{} chars total]",
+                                    &content_str[..500],
+                                    content_str.len()
+                                )
+                            } else {
+                                content_str
+                            };
+                            if !display.trim().is_empty() {
+                                parts.push(format!("{pfx} RESULT: {display}"));
+                            }
+                        }
+                    }
+                    if parts.is_empty() {
+                        None
+                    } else {
+                        Some(parts.join("\n"))
+                    }
+                }
+                _ => None, // Skip stream_event, system init, etc.
+            }
+        }
+        _ => None,
+    }
+}
+
+/// Read log entries from a file and convert them to human-readable text lines,
+/// stripping raw streaming noise and JSON internals.
+pub fn read_log_as_readable_lines(path: &Path) -> Result<Vec<String>, String> {
+    let entries = read_log(path)?;
+    let mut result = Vec::new();
+    for entry in &entries {
+        if let Some(line) = format_log_entry_as_text(&entry.timestamp, &entry.event) {
+            result.push(line);
+        }
+    }
+    Ok(result)
+}
+
 /// Find the most recent log file for a given story+agent combination.
 ///
 /// Scans `.huskies/logs/{story_id}/` for files matching `{agent_name}-*.log`
@@ -342,6 +545,235 @@ mod tests {
        );
    }

+    #[test]
+    fn test_list_story_log_files_returns_empty_for_missing_dir() {
+        let tmp = tempdir().unwrap();
+        let files = list_story_log_files(tmp.path(), "nonexistent", None);
+        assert!(files.is_empty());
+    }
+
+    #[test]
+    fn test_list_story_log_files_no_filter_returns_all_logs() {
+        let tmp = tempdir().unwrap();
+        let root = tmp.path();
+
+        let mut w1 = AgentLogWriter::new(root, "42_story_foo", "coder-1", "sess-aaa").unwrap();
+        w1.write_event(&AgentEvent::Output {
+            story_id: "42_story_foo".to_string(),
+            agent_name: "coder-1".to_string(),
+            text: "from coder-1".to_string(),
+        })
+        .unwrap();
+        drop(w1);
+        std::thread::sleep(std::time::Duration::from_millis(10));
+
+        let mut w2 =
+            AgentLogWriter::new(root, "42_story_foo", "mergemaster", "sess-bbb").unwrap();
+        w2.write_event(&AgentEvent::Output {
+            story_id: "42_story_foo".to_string(),
+            agent_name: "mergemaster".to_string(),
+            text: "from mergemaster".to_string(),
+        })
+        .unwrap();
+        drop(w2);
+
+        let files = list_story_log_files(root, "42_story_foo", None);
+        assert_eq!(files.len(), 2, "Should find both log files");
+        // Oldest first
+        assert!(
+            files[0].to_string_lossy().contains("coder-1"),
+            "coder-1 should be first (older)"
+        );
+    }
+
+    #[test]
+    fn test_list_story_log_files_with_agent_filter() {
+        let tmp = tempdir().unwrap();
+        let root = tmp.path();
+
+        let mut w1 = AgentLogWriter::new(root, "42_story_foo", "coder-1", "sess-a").unwrap();
+        w1.write_event(&AgentEvent::Output {
+            story_id: "42_story_foo".to_string(),
+            agent_name: "coder-1".to_string(),
+            text: "from coder-1".to_string(),
+        })
+        .unwrap();
+        drop(w1);
+
+        let mut w2 =
+            AgentLogWriter::new(root, "42_story_foo", "mergemaster", "sess-b").unwrap();
+        w2.write_event(&AgentEvent::Output {
+            story_id: "42_story_foo".to_string(),
+            agent_name: "mergemaster".to_string(),
+            text: "from mergemaster".to_string(),
+        })
+        .unwrap();
+        drop(w2);
+
+        let files = list_story_log_files(root, "42_story_foo", Some("coder-1"));
+        assert_eq!(files.len(), 1, "Should find only coder-1 log");
+        assert!(files[0].to_string_lossy().contains("coder-1"));
+    }
+
+    #[test]
+    fn test_format_log_entry_output_event() {
+        let ts = "2026-04-10T12:48:02.123456789+00:00";
+        let event = serde_json::json!({
+            "type": "output",
+            "story_id": "42_story",
+            "agent_name": "coder-1",
+            "text": "Hello world"
+        });
+        let result = format_log_entry_as_text(ts, &event).unwrap();
+        assert!(result.contains("12:48:02"), "should include timestamp");
+        assert!(result.contains("coder-1"), "should include agent name");
+        assert!(result.contains("Hello world"), "should include text");
+    }
+
+    #[test]
+    fn test_format_log_entry_skips_empty_output() {
+        let ts = "2026-04-10T12:48:02.123456789+00:00";
+        let event = serde_json::json!({
+            "type": "output",
+            "story_id": "42_story",
+            "agent_name": "coder-1",
+            "text": "   "
+        });
+        assert!(format_log_entry_as_text(ts, &event).is_none());
+    }
+
+    #[test]
+    fn test_format_log_entry_error_event() {
+        let ts = "2026-04-10T12:48:02.123+00:00";
+        let event = serde_json::json!({
+            "type": "error",
+            "story_id": "42_story",
+            "agent_name": "coder-1",
+            "message": "Something went wrong"
+        });
+        let result = format_log_entry_as_text(ts, &event).unwrap();
+        assert!(result.contains("ERROR"));
+        assert!(result.contains("Something went wrong"));
+    }
+
+    #[test]
+    fn test_format_log_entry_done_event() {
+        let ts = "2026-04-10T12:48:02.123+00:00";
+        let event = serde_json::json!({
+            "type": "done",
+            "story_id": "42_story",
+            "agent_name": "coder-1",
+            "session_id": null
+        });
+        let result = format_log_entry_as_text(ts, &event).unwrap();
+        assert!(result.contains("DONE"));
+    }
+
+    #[test]
+    fn test_format_log_entry_skips_running_status() {
+        let ts = "2026-04-10T12:48:02.123+00:00";
+        let event = serde_json::json!({
+            "type": "status",
+            "story_id": "42_story",
+            "agent_name": "coder-1",
+            "status": "running"
+        });
+        assert!(format_log_entry_as_text(ts, &event).is_none());
+    }
+
+    #[test]
+    fn test_format_log_entry_agent_json_tool_use() {
+        let ts = "2026-04-10T12:48:03.000+00:00";
+        let event = serde_json::json!({
+            "type": "agent_json",
+            "story_id": "42_story",
+            "agent_name": "coder-1",
+            "data": {
+                "type": "assistant",
+                "message": {
+                    "content": [
+                        {
+                            "type": "tool_use",
+                            "id": "tool-1",
+                            "name": "Read",
+                            "input": {"file_path": "/some/file.rs"}
+                        }
+                    ]
+                }
+            }
+        });
+        let result = format_log_entry_as_text(ts, &event).unwrap();
+        assert!(result.contains("TOOL: Read"), "should show tool call: {result}");
+        assert!(result.contains("file_path"), "should show input: {result}");
+    }
+
+    #[test]
+    fn test_format_log_entry_agent_json_text() {
+        let ts = "2026-04-10T12:48:04.000+00:00";
+        let event = serde_json::json!({
+            "type": "agent_json",
+            "story_id": "42_story",
+            "agent_name": "coder-1",
+            "data": {
+                "type": "assistant",
+                "message": {
+                    "content": [
+                        {
+                            "type": "text",
+                            "text": "Now I will read the file."
+                        }
+                    ]
+                }
+            }
+        });
+        let result = format_log_entry_as_text(ts, &event).unwrap();
+        assert!(result.contains("Now I will read the file."), "should show text: {result}");
+    }
+
+    #[test]
+    fn test_format_log_entry_skips_stream_events() {
+        let ts = "2026-04-10T12:48:04.000+00:00";
+        let event = serde_json::json!({
+            "type": "agent_json",
+            "story_id": "42_story",
+            "agent_name": "coder-1",
+            "data": {
+                "type": "stream_event",
+                "event": {"type": "content_block_delta", "delta": {"type": "text_delta", "text": "chunk"}}
+            }
+        });
+        assert!(format_log_entry_as_text(ts, &event).is_none(), "stream events should be skipped");
+    }
+
+    #[test]
+    fn test_read_log_as_readable_lines_produces_formatted_output() {
+        let tmp = tempdir().unwrap();
+        let root = tmp.path();
+
+        let mut writer =
+            AgentLogWriter::new(root, "42_story_foo", "coder-1", "sess-readable").unwrap();
+        writer
+            .write_event(&AgentEvent::Output {
+                story_id: "42_story_foo".to_string(),
+                agent_name: "coder-1".to_string(),
+                text: "Let me read the file".to_string(),
+            })
+            .unwrap();
+        writer
+            .write_event(&AgentEvent::Done {
+                story_id: "42_story_foo".to_string(),
+                agent_name: "coder-1".to_string(),
+                session_id: Some("sess-readable".to_string()),
+            })
+            .unwrap();
+
+        let path = log_file_path(root, "42_story_foo", "coder-1", "sess-readable");
+        let lines = read_log_as_readable_lines(&path).unwrap();
+        assert_eq!(lines.len(), 2, "Should produce 2 readable lines");
+        assert!(lines[0].contains("Let me read the file"), "first line: {}", lines[0]);
+        assert!(lines[1].contains("DONE"), "second line: {}", lines[1]);
+    }
+
    #[test]
    fn test_find_latest_log_returns_none_for_missing_dir() {
        let tmp = tempdir().unwrap();