feat: dir ignore support in ovcli.conf (#1393)

sentisso · web-flow · commit 7388e4d598e1 · 2026-04-13T11:14:10.000+08:00
diff --git a/crates/ov_cli/src/client.rs b/crates/ov_cli/src/client.rs
@@ -787,7 +787,11 @@ impl HttpClient {
         // Determine target path
         let to_path = Path::new(to);
         let final_path = if to_path.is_dir() {
-            let base_name = uri.trim_end_matches('/').split('/').last().unwrap_or("export");
+            let base_name = uri
+                .trim_end_matches('/')
+                .split('/')
+                .last()
+                .unwrap_or("export");
             to_path.join(format!("{}.ovpack", base_name))
         } else if !to.ends_with(".ovpack") {
             Path::new(&format!("{}.ovpack", to)).to_path_buf()
@@ -822,10 +826,7 @@ impl HttpClient {
             )));
         }
         if !file_path_obj.is_file() {
-            return Err(Error::Client(format!(
-                "Path is not a file: {}",
-                file_path
-            )));
+            return Err(Error::Client(format!("Path is not a file: {}", file_path)));
         }
 
         let temp_file_id = self.upload_temp_file(file_path_obj).await?;
diff --git a/crates/ov_cli/src/commands/search.rs b/crates/ov_cli/src/commands/search.rs
@@ -53,7 +53,14 @@ pub async fn grep(
     compact: bool,
 ) -> Result<()> {
     let result = client
-        .grep(uri, exclude_uri, pattern, ignore_case, node_limit, level_limit)
+        .grep(
+            uri,
+            exclude_uri,
+            pattern,
+            ignore_case,
+            node_limit,
+            level_limit,
+        )
         .await?;
     output_success(&result, output_format, compact);
     Ok(())
diff --git a/crates/ov_cli/src/config.rs b/crates/ov_cli/src/config.rs
@@ -5,6 +5,23 @@ use crate::error::{Error, Result};
 
 const OPENVIKING_CLI_CONFIG_ENV: &str = "OPENVIKING_CLI_CONFIG_FILE";
 
+#[derive(Debug, Clone, Serialize, Deserialize)]
+pub struct UploadConfig {
+    pub ignore_dirs: Option<String>,
+    pub include: Option<String>,
+    pub exclude: Option<String>,
+}
+
+impl Default for UploadConfig {
+    fn default() -> Self {
+        Self {
+            ignore_dirs: None,
+            include: None,
+            exclude: None,
+        }
+    }
+}
+
 #[derive(Debug, Clone, Serialize, Deserialize)]
 pub struct Config {
     #[serde(default = "default_url")]
@@ -19,6 +36,8 @@ pub struct Config {
     pub output: String,
     #[serde(default = "default_echo_command")]
     pub echo_command: bool,
+    #[serde(default)]
+    pub upload: UploadConfig,
 }
 
 fn default_url() -> String {
@@ -48,10 +67,35 @@ impl Default for Config {
             timeout: 60.0,
             output: "table".to_string(),
             echo_command: true,
+            upload: UploadConfig::default(),
         }
     }
 }
 
+fn normalize_csv_option(value: Option<String>) -> Vec<String> {
+    value
+        .unwrap_or_default()
+        .split(',')
+        .map(str::trim)
+        .filter(|token| !token.is_empty())
+        .map(ToString::to_string)
+        .collect()
+}
+
+pub fn merge_csv_options(
+    config_value: Option<String>,
+    cli_value: Option<String>,
+) -> Option<String> {
+    let mut merged = normalize_csv_option(config_value);
+    merged.extend(normalize_csv_option(cli_value));
+
+    if merged.is_empty() {
+        None
+    } else {
+        Some(merged.join(","))
+    }
+}
+
 impl Config {
     /// Load config from default location or create default
     pub fn load() -> Result<Self> {
@@ -115,7 +159,7 @@ pub fn get_or_create_machine_id() -> Result<String> {
 
 #[cfg(test)]
 mod tests {
-    use super::Config;
+    use super::{Config, merge_csv_options};
 
     #[test]
     fn config_deserializes_account_and_user_fields() {
@@ -133,5 +177,77 @@ mod tests {
         assert_eq!(config.account.as_deref(), Some("acme"));
         assert_eq!(config.user.as_deref(), Some("alice"));
         assert_eq!(config.agent_id.as_deref(), Some("assistant-1"));
+        assert!(config.upload.ignore_dirs.is_none());
+        assert!(config.upload.include.is_none());
+        assert!(config.upload.exclude.is_none());
+    }
+
+    #[test]
+    fn config_deserializes_upload_fields() {
+        let config: Config = serde_json::from_str(
+            r#"{
+                "url": "http://localhost:1933",
+                "upload": {
+                    "ignore_dirs": "node_modules,dist",
+                    "include": "*.md,*.pdf",
+                    "exclude": "*.tmp,*.log"
+                }
+            }"#,
+        )
+        .expect("config should deserialize");
+
+        assert_eq!(
+            config.upload.ignore_dirs.as_deref(),
+            Some("node_modules,dist")
+        );
+        assert_eq!(config.upload.include.as_deref(), Some("*.md,*.pdf"));
+        assert_eq!(config.upload.exclude.as_deref(), Some("*.tmp,*.log"));
+    }
+
+    #[test]
+    fn merge_csv_options_config_only() {
+        assert_eq!(
+            merge_csv_options(Some("node_modules,dist".to_string()), None),
+            Some("node_modules,dist".to_string())
+        );
+    }
+
+    #[test]
+    fn merge_csv_options_cli_only() {
+        assert_eq!(
+            merge_csv_options(None, Some("*.md,*.pdf".to_string())),
+            Some("*.md,*.pdf".to_string())
+        );
+    }
+
+    #[test]
+    fn merge_csv_options_additive_merge() {
+        assert_eq!(
+            merge_csv_options(
+                Some("node_modules,dist".to_string()),
+                Some("build,out".to_string())
+            ),
+            Some("node_modules,dist,build,out".to_string())
+        );
+    }
+
+    #[test]
+    fn merge_csv_options_trims_and_drops_empty_tokens() {
+        assert_eq!(
+            merge_csv_options(
+                Some(" node_modules , , dist ,".to_string()),
+                Some(" ,*.tmp,  *.log  ,".to_string())
+            ),
+            Some("node_modules,dist,*.tmp,*.log".to_string())
+        );
+    }
+
+    #[test]
+    fn merge_csv_options_returns_none_when_empty() {
+        assert_eq!(
+            merge_csv_options(Some("  ,  , ".to_string()), Some("".to_string())),
+            None
+        );
+        assert_eq!(merge_csv_options(None, None), None);
     }
 }
diff --git a/crates/ov_cli/src/main.rs b/crates/ov_cli/src/main.rs
@@ -7,7 +7,7 @@ mod tui;
 mod utils;
 
 use clap::{ArgAction, Parser, Subcommand};
-use config::Config;
+use config::{Config, merge_csv_options};
 use error::{Error, Result};
 use output::OutputFormat;
 
@@ -784,8 +784,7 @@ async fn main() {
             append,
             wait,
             timeout,
-        } => handle_write(uri, content, from_file, append, wait, timeout, ctx)
-            .await,
+        } => handle_write(uri, content, from_file, append, wait, timeout, ctx).await,
         Commands::Reindex {
             uri,
             regenerate,
@@ -812,7 +811,18 @@ async fn main() {
             ignore_case,
             node_limit,
             level_limit,
-        } => handle_grep(uri, exclude_uri, pattern, ignore_case, node_limit, level_limit, ctx).await,
+        } => {
+            handle_grep(
+                uri,
+                exclude_uri,
+                pattern,
+                ignore_case,
+                node_limit,
+                level_limit,
+                ctx,
+            )
+            .await
+        }
 
         Commands::Glob {
             pattern,
@@ -886,6 +896,11 @@ async fn handle_add_resource(
     let strict = strict_mode;
     let directly_upload_media = !no_directly_upload_media;
 
+    let effective_ignore_dirs =
+        merge_csv_options(ctx.config.upload.ignore_dirs.clone(), ignore_dirs);
+    let effective_include = merge_csv_options(ctx.config.upload.include.clone(), include);
+    let effective_exclude = merge_csv_options(ctx.config.upload.exclude.clone(), exclude);
+
     let effective_timeout = if wait {
         timeout.unwrap_or(60.0).max(ctx.config.timeout)
     } else {
@@ -909,9 +924,9 @@ async fn handle_add_resource(
         wait,
         timeout,
         strict,
-        ignore_dirs,
-        include,
-        exclude,
+        effective_ignore_dirs,
+        effective_include,
+        effective_exclude,
         directly_upload_media,
         watch_interval,
         ctx.output_format,
@@ -1237,7 +1252,11 @@ async fn handle_write(
         (Some(value), None) => value,
         (None, Some(path)) => std::fs::read_to_string(path)
             .map_err(|e| Error::Client(format!("Failed to read --from-file: {}", e)))?,
-        _ => return Err(Error::Client("Specify exactly one of --content or --from-file".into())),
+        _ => {
+            return Err(Error::Client(
+                "Specify exactly one of --content or --from-file".into(),
+            ));
+        }
     };
     commands::content::write(
         &client,
@@ -1454,7 +1473,11 @@ async fn handle_grep(
         std::process::exit(1);
     }
 
-    let mut params = vec![format!("--uri={}", uri), format!("-n {}", node_limit), format!("-L {}", level_limit)];
+    let mut params = vec![
+        format!("--uri={}", uri),
+        format!("-n {}", node_limit),
+        format!("-L {}", level_limit),
+    ];
     if let Some(excluded) = &exclude_uri {
         params.push(format!("-x {}", excluded));
     }
@@ -1548,6 +1571,7 @@ mod tests {
             timeout: 60.0,
             output: "table".to_string(),
             echo_command: true,
+            upload: Default::default(),
         };
 
         let ctx = CliContext::from_config(
diff --git a/crates/ov_cli/src/output.rs b/crates/ov_cli/src/output.rs
@@ -392,19 +392,22 @@ fn render_session_context(
         ));
         lines.push(format!(
             "total_archives         {}",
-            stats.get("totalArchives")
+            stats
+                .get("totalArchives")
                 .map(format_value)
                 .unwrap_or_else(|| "0".to_string())
         ));
         lines.push(format!(
             "included_archives      {}",
-            stats.get("includedArchives")
+            stats
+                .get("includedArchives")
                 .map(format_value)
                 .unwrap_or_else(|| "0".to_string())
         ));
         lines.push(format!(
             "dropped_archives       {}",
-            stats.get("droppedArchives")
+            stats
+                .get("droppedArchives")
                 .map(format_value)
                 .unwrap_or_else(|| "0".to_string())
         ));
@@ -457,7 +460,9 @@ fn render_session_archive(
     obj: &serde_json::Map<String, serde_json::Value>,
     compact: bool,
 ) -> Option<String> {
-    if !(obj.contains_key("archive_id") && obj.contains_key("overview") && obj.contains_key("messages"))
+    if !(obj.contains_key("archive_id")
+        && obj.contains_key("overview")
+        && obj.contains_key("messages"))
     {
         return None;
     }
@@ -571,8 +576,14 @@ fn summarize_message_content(parts: Option<&Vec<serde_json::Value>>) -> String {
                 });
             }
             "tool" => {
-                let name = obj.get("tool_name").and_then(|v| v.as_str()).unwrap_or("tool");
-                let status = obj.get("tool_status").and_then(|v| v.as_str()).unwrap_or("");
+                let name = obj
+                    .get("tool_name")
+                    .and_then(|v| v.as_str())
+                    .unwrap_or("tool");
+                let status = obj
+                    .get("tool_status")
+                    .and_then(|v| v.as_str())
+                    .unwrap_or("");
                 chunks.push(if status.is_empty() {
                     format!("[tool:{}]", name)
                 } else {
diff --git a/docs/en/guides/01-configuration.md b/docs/en/guides/01-configuration.md
@@ -794,7 +794,12 @@ Config file for the HTTP client (`SyncHTTPClient` / `AsyncHTTPClient`) and CLI t
   "account": "acme",
   "user": "alice",
   "agent_id": "my-agent",
-  "output": "table"
+  "output": "table",
+  "upload": {
+    "ignore_dirs": "node_modules,.cache,.nx",
+    "include": "*.md,*.pdf",
+    "exclude": "*.tmp,*.log"
+  }
 }
 ```
 
@@ -806,13 +811,24 @@ Config file for the HTTP client (`SyncHTTPClient` / `AsyncHTTPClient`) and CLI t
 | `user` | Default user sent as `X-OpenViking-User` | `null` |
 | `agent_id` | Agent identifier for agent space isolation | `null` |
 | `output` | Default output format: `"table"` or `"json"` | `"table"` |
+| `upload.ignore_dirs` | Default directory ignore list for `add-resource` (CSV) | `null` |
+| `upload.include` | Default include patterns for `add-resource` (CSV) | `null` |
+| `upload.exclude` | Default exclude patterns for `add-resource` (CSV) | `null` |
 
 CLI flags can override these identity fields per command:
 
 ```bash
 openviking --account acme --user alice --agent-id assistant-2 ls viking://
 ```
 
+For `add-resource`, upload filter flags are merged additively with `ovcli.conf` defaults:
+
+```bash
+# ovcli.conf: upload.exclude="*.log"
+openviking add-resource ./docs --exclude "*.tmp"
+# effective exclude sent to server: "*.log,*.tmp"
+```
+
 See [Deployment](./03-deployment.md) for details.
 
 ## server Section
diff --git a/docs/zh/guides/01-configuration.md b/docs/zh/guides/01-configuration.md
diff --git a/openviking_cli/utils/config/ovcli_config.py b/openviking_cli/utils/config/ovcli_config.py
diff --git a/tests/client/test_http_client_config.py b/tests/client/test_http_client_config.py
