feat(agent): subagent tool paralel + auto-load AGENTS.md + verify cek setelah edit

Lanjutan audit alur AI agent (round 2), mengisi celah yang tersisa dari
perpbaikan paralel tool di loop utama (74b1ad4) agar lebih mirip Claude Code.

- feat(subagent): eksekusi batch tool read-only paralel di subagent engine
  (engine.rs). Tool::run sinkron, jadi pakai scoped OS thread (bounded
  window 8); hasil dipertahankan dalam urutan panggilan asli. Batch dengan
  tool mutating jatuh balik ke jalur sequential aman.
- feat(agent): auto-load AGENTS.md/CLAUDE.md/.cursorrules ke system prompt
  tiap turn (seperti Claude Code load AGENTS.md saat startup). Fungsi
  main_agent_prompt_with_project_context menempel blok PROJECT CONTEXT;
  dibaca dari workspace root pertama & dibatasi 12k char.
- feat(prompt): arahan VERIFY AFTER EDIT — setelah edit/write, agent wajib
  jalankan cargo check/clippy/test (atau lint/test sesuai stack) via bash
  sebelum mengakhiri turn; perbaiki error yang terlihat, jangan klaim
  'compiles/works' tanpa hasil nyata.
- feat(infra): build_rich_context kini membaca AGENTS.md & CLAUDE.md juga
  (untuk explore_codebase/scout).
- test: +3 subagent engine (order paralel, kecepatan konkuren, fallback
  mutating), +2 domain prompt (konteks proyek & fallback kosong).

Cargo.lock

@@ -4862,7 +4862,7 @@ dependencies = [
 
 [[package]]
 name = "zesdex-api"
-version = "1.19.4"
+version = "1.19.5"
 dependencies = [
  "anyhow",
  "argon2",
@@ -4885,7 +4885,7 @@ dependencies = [
 
 [[package]]
 name = "zesdex-application"
-version = "1.19.4"
+version = "1.19.5"
 dependencies = [
  "anyhow",
  "base64",
@@ -4903,7 +4903,7 @@ dependencies = [
 
 [[package]]
 name = "zesdex-bootstrap"
-version = "1.19.4"
+version = "1.19.5"
 dependencies = [
  "anyhow",
  "chrono",
@@ -4920,7 +4920,7 @@ dependencies = [
 
 [[package]]
 name = "zesdex-daemon"
-version = "1.19.4"
+version = "1.19.5"
 dependencies = [
  "anyhow",
  "base64",
@@ -4944,7 +4944,7 @@ dependencies = [
 
 [[package]]
 name = "zesdex-domain"
-version = "1.19.4"
+version = "1.19.5"
 dependencies = [
  "anyhow",
  "base64",
@@ -4960,7 +4960,7 @@ dependencies = [
 
 [[package]]
 name = "zesdex-gateway"
-version = "1.19.4"
+version = "1.19.5"
 dependencies = [
  "anyhow",
  "axum",
@@ -4987,7 +4987,7 @@ dependencies = [
 
 [[package]]
 name = "zesdex-grpc"
-version = "1.19.4"
+version = "1.19.5"
 dependencies = [
  "anyhow",
  "axum",
@@ -5004,7 +5004,7 @@ dependencies = [
 
 [[package]]
 name = "zesdex-infrastructure"
-version = "1.19.4"
+version = "1.19.5"
 dependencies = [
  "anyhow",
  "argon2",
@@ -5052,7 +5052,7 @@ dependencies = [
 
 [[package]]
 name = "zesdex-tui"
-version = "1.19.4"
+version = "1.19.5"
 dependencies = [
  "anyhow",
  "base64",
@@ -5078,7 +5078,7 @@ dependencies = [
 
 [[package]]
 name = "zesdex-web"
-version = "1.19.4"
+version = "1.19.5"
 dependencies = [
  "anyhow",
  "axum",
@@ -5098,7 +5098,7 @@ dependencies = [
 
 [[package]]
 name = "zesdex-ws"
-version = "1.19.4"
+version = "1.19.5"
 dependencies = [
  "anyhow",
  "axum",

apps/application/src/agent/turn_service.rs

@@ -5,7 +5,7 @@ use tracing::{debug, info, warn};
 
 use zesdex_domain::agent::{AgentTurnParams, TurnEvent};
 use zesdex_domain::core::{ChatMessage, StreamEvent, ToolDef};
-use zesdex_domain::main_agent_prompt;
+use zesdex_domain::main_agent_prompt_with_project_context;
 
 use super::ToolExecutor;
 use crate::ports::ProviderService;
@@ -111,6 +111,46 @@ fn conversation_chars(messages: &[ChatMessage]) -> usize {
         .sum()
 }
 
+/// The maximum combined size (characters) of project-rule files injected into
+/// the system prompt, so a huge AGENTS.md cannot blow the context window.
+const PROJECT_CONTEXT_MAX_CHARS: usize = 12_000;
+
+/// Case-insensitive rule filenames auto-loaded from the workspace root into
+/// the system prompt, matching the Claude-Code/AGENTS.md convention.
+const RULE_FILENAMES: [&str; 6] = [
+    "AGENTS.md",
+    "agent.md",
+    "CLAUDE.md",
+    "claude.md",
+    ".cursorrules",
+    ".zesdexrules",
+];
+
+/// Build a compact "project context" block from the repo's convention files
+/// (AGENTS.md, CLAUDE.md, .cursorrules, …) found at the workspace root.
+///
+/// Follows the Claude-Code convention of loading AGENTS.md at startup so the
+/// model starts each turn with the repo's rules. Reads are best-effort and
+/// capped at [`PROJECT_CONTEXT_MAX_CHARS`] total; missing files are skipped.
+fn build_project_context(root: &std::path::Path) -> String {
+    let mut ctx = String::new();
+    for file in RULE_FILENAMES {
+        let full = root.join(file);
+        if let Ok(content) = std::fs::read_to_string(&full) {
+            ctx.push_str(&format!("\n### {file}\n```\n{}\n```", content.trim()));
+        }
+    }
+    let context = ctx.trim().to_string();
+    if context.len() <= PROJECT_CONTEXT_MAX_CHARS {
+        return context;
+    }
+    context
+        .chars()
+        .take(PROJECT_CONTEXT_MAX_CHARS)
+        .collect::<String>()
+        + "\n...[project context truncated]"
+}
+
 /// Track repeated tool-call errors so the loop can recover instead of
 /// burning iterations retrying the same failing tool.
 #[derive(Default)]
@@ -341,9 +381,17 @@ impl<P: ProviderService, T: ToolExecutor> super::AgentTurnService for AgentTurnS
 
         // Insert system prompt at position 0 once and keep it there for the
         // entire turn, avoiding per-iteration clones of the full message list.
+        // Auto-load repo conventions (AGENTS.md / CLAUDE.md / .cursorrules)
+        // from the first workspace root, like Claude Code does at startup.
+        let project_context = params
+            .workspace_roots
+            .first()
+            .map(|root| build_project_context(root))
+            .unwrap_or_default();
+        let system_prompt = main_agent_prompt_with_project_context(&project_context);
         params
             .messages
-            .insert(0, ChatMessage::system(main_agent_prompt()));
+            .insert(0, ChatMessage::system(system_prompt));
         let original_count = params.messages.len();
 
         // Estimate request complexity from the last user message.

apps/domain/src/agent/prompt.rs

@@ -41,10 +41,43 @@ architectural plans and `todowrite` to maintain granular task checklists.
 4. TOOL EXECUTION: Execute individual tools (file edits, terminal commands) \
 within or guided by your workflows. If an error occurs, analyse and fix it.
 
+VERIFY AFTER EDIT (CLAUDE-CODE STYLE):
+- After modifying code (edit/write), run the repo's check command via `bash` \
+before ending the turn: `cargo check` / `cargo clippy` / `cargo test` for Rust, \
+or the equivalent lint/test (`bun run lint && bun run test`, `npm test`, etc.) \
+for other stacks. Pick the project's actual verify command (see PROJECT \
+CONTEXT / AGENTS.md when present).
+- If the check fails, fix the errors you can see and re-run; only end the turn \
+after the check passes or you cannot resolve a failure yourself (then report it \
+explicitly).
+- Do NOT claim code compiles or works without running a real check.
+
 Respond conversationally, concisely, and helpfully."
         .to_string()
 }
 
+/// Build the main-agent system prompt including an injected block of project
+/// context (AGENTS.md / CLAUDE.md / project rules).
+///
+/// Like Claude Code, which loads AGENTS.md at startup so the model starts with
+/// the repo's conventions, this wraps [`main_agent_prompt`] and appends a
+/// clearly-delimited `## PROJECT CONTEXT` section carrying the rules the user
+/// keeps next to their code. When `project_context` is empty the returned
+/// prompt is identical to [`main_agent_prompt`], so callers can fall back
+/// safely.
+pub fn main_agent_prompt_with_project_context(project_context: &str) -> String {
+    let base = main_agent_prompt();
+    let context = project_context.trim();
+    if context.is_empty() {
+        return base;
+    }
+    format!(
+        "{base}\n\n\
+## PROJECT CONTEXT (repo rules — follow these conventions)\n\
+{context}"
+    )
+}
+
 /// Build a subagent directive prompt.
 ///
 /// The directive is embedded in a system message that also communicates the
@@ -119,6 +152,25 @@ mod tests {
         assert!(prompt.contains("WORKFLOW FIRST"));
     }
 
+    #[test]
+    fn project_context_prompt_appends_context_and_keeps_base() {
+        let base = main_agent_prompt();
+        let with_ctx = main_agent_prompt_with_project_context("## AGENTS.md\nUse cargo clippy.");
+        assert!(with_ctx.contains("Zesdex"), "base prompt must be preserved");
+        assert!(with_ctx.contains("PROJECT CONTEXT"));
+        assert!(with_ctx.contains("Use cargo clippy."));
+        assert!(with_ctx.contains(&base));
+        // The base section should appear before the context section.
+        assert!(with_ctx.find("PROJECT CONTEXT").unwrap() > with_ctx.find("Zesdex").unwrap());
+    }
+
+    #[test]
+    fn empty_project_context_returns_base_prompt() {
+        let base = main_agent_prompt();
+        assert_eq!(main_agent_prompt_with_project_context(""), base);
+        assert_eq!(main_agent_prompt_with_project_context("   "), base);
+    }
+
     #[test]
     fn subagent_directive_includes_directive_text() {
         let prompt = subagent_directive("test directive", "/home", "/home/project");

apps/domain/src/lib.rs

@@ -58,6 +58,9 @@ pub use agent::*;
 // Sub-module items need explicit re-exports
 pub use agent::defaults::*;
 pub use agent::progress::AgentProgress;
-pub use agent::prompt::{compaction_prompt, main_agent_prompt, subagent_directive};
+pub use agent::prompt::{
+    compaction_prompt, main_agent_prompt, main_agent_prompt_with_project_context,
+    subagent_directive,
+};
 pub use subagent::*;
 pub use workflow::*;

apps/infrastructure/src/subagent/engine.rs

@@ -14,7 +14,8 @@ use tracing::{debug, info, instrument};
 use crate::llm::provider::LlmClient;
 use crate::subagent::context::SubagentContext;
 use crate::subagent::division::{tools_for, AccessTier};
-use crate::tools::{tool_defs, ToolCtx};
+use crate::tools::{tool_defs, Tool, ToolCtx};
+use serde_json::Value;
 use zesdex_domain::agent::progress::AgentProgress;
 use zesdex_domain::core::tool_call::sanitize_tool_arguments;
 use zesdex_domain::core::ChatMessage;
@@ -31,6 +32,95 @@ const TOOL_OUTPUT_MAX_CHARS: usize = 12_000;
 /// recovery note steering the model to a different approach.
 const MAX_CONSECUTIVE_TOOL_ERRORS: usize = 3;
 
+/// Maximum number of read-only tool calls executed concurrently in a single
+/// subagent batch. Read-only tools (read/grep/glob/…) block on disk I/O, so
+/// running them on parallel OS threads removes the serial round-trip latency
+/// for a batch of independent lookups, mirroring the main turn loop.
+const MAX_PARALLEL_TOOLS: usize = 8;
+
+/// Execute a batch of tool calls, running read-only tools concurrently when
+/// the whole batch is parallel-safe.
+///
+/// Returns one `(tool_call_id, tool_name, result)` per call **in the original
+/// call order** (OpenAI/Anthropic tool-result ordering contract). `Tool::run`
+/// is synchronous, so real parallelism comes from scoped OS threads; `Tool`
+/// and `ToolCtx` are `Send + Sync`, so the borrowed references can be shared
+/// across the short-lived scoped threads.
+///
+/// If any single tool in the batch mutates state (edit/write/bash/git/…), the
+/// whole batch falls back to the safe sequential path so writes never race.
+fn execute_tool_batch(
+    tools: &[Box<dyn Tool>],
+    tool_ctx: &ToolCtx,
+    tool_calls: &[zesdex_domain::core::ToolCall],
+) -> Vec<(String, String, String)> {
+    let parallel = tool_calls.len() > 1
+        && tool_calls
+            .iter()
+            .all(|tc| crate::tools::tool_is_parallel_safe(&tc.function.name));
+
+    if !parallel {
+        // Sequential fallback (kept identical to the historical behavior).
+        return tool_calls
+            .iter()
+            .map(|tc| {
+                let tool_name = tc.function.name.clone();
+                let args = sanitize_tool_arguments(&tc.function.arguments);
+                let result = run_one_tool(tools, tool_ctx, &tool_name, &args);
+                (tc.id.clone(), tool_name, result)
+            })
+            .collect();
+    }
+
+    // Bounded parallel path: process the batch in windows of
+    // `MAX_PARALLEL_TOOLS` so concurrency stays bounded, joining each window
+    // before the next so results stay in original order.
+    let mut ordered = Vec::with_capacity(tool_calls.len());
+    for window in tool_calls.chunks(MAX_PARALLEL_TOOLS) {
+        let window_results = std::thread::scope(|s| {
+            let handles: Vec<_> = window
+                .iter()
+                .map(|tc| {
+                    let tool_name = tc.function.name.clone();
+                    let args = sanitize_tool_arguments(&tc.function.arguments);
+                    s.spawn(move || {
+                        debug!("Subagent executing tool: {tool_name}");
+                        run_one_tool(tools, tool_ctx, &tool_name, &args)
+                    })
+                })
+                .collect();
+            handles
+                .into_iter()
+                .map(|h| {
+                    h.join()
+                        .unwrap_or_else(|_| "Error: tool panicked".to_string())
+                })
+                .collect::<Vec<_>>()
+        });
+        for (tc, result) in window.iter().zip(window_results) {
+            ordered.push((tc.id.clone(), tc.function.name.clone(), result));
+        }
+    }
+    ordered
+}
+
+/// Run a single synchronous tool call and capture its result string.
+fn run_one_tool(
+    tools: &[Box<dyn Tool>],
+    tool_ctx: &ToolCtx,
+    tool_name: &str,
+    args: &Value,
+) -> String {
+    if let Some(tool) = tools.iter().find(|t| t.name() == tool_name) {
+        match tool.run(tool_ctx, args) {
+            Ok(output) => output,
+            Err(e) => format!("Error: {e}"),
+        }
+    } else {
+        format!("Unknown tool: {tool_name}")
+    }
+}
+
 /// Pick a `max_tokens` budget proportional to the directive's length.
 fn adaptive_max_tokens(directive_len: usize) -> u32 {
     if directive_len <= 80 {
@@ -139,12 +229,12 @@ pub async fn run_agent(
             return Ok(content);
         }
 
-        // Execute tool calls
+        // Execute tool calls — read-only batches run concurrently (bounded,
-        for tc in &tool_calls {
+        // order preserved); any mutating tool forces the safe sequential path.
-            let tool_name = &tc.function.name;
+        let results = execute_tool_batch(&tools, &tool_ctx, &tool_calls);
-            let args = sanitize_tool_arguments(&tc.function.arguments);
 
-            debug!("Subagent executing tool: {tool_name}");
+        for (id, tool_name, result) in results {
+            debug!("Subagent tool {tool_name} finished");
 
             report_progress(
                 &tool_ctx,
@@ -155,15 +245,6 @@ pub async fn run_agent(
                 ),
             );
 
-            let result = if let Some(tool) = tools.iter().find(|t| t.name() == tool_name) {
-                match tool.run(&tool_ctx, &args) {
-                    Ok(output) => output,
-                    Err(e) => format!("Error: {e}"),
-                }
-            } else {
-                format!("Unknown tool: {tool_name}")
-            };
-
             // Error-recovery: if the same tool keeps failing, inject a
             // system note steering the model to a different approach.
             if result.starts_with("Error:") {
@@ -171,11 +252,11 @@ pub async fn run_agent(
                     consecutive_errors += 1;
                 } else {
                     consecutive_errors = 1;
-                    last_tool = tool_name.to_string();
+                    last_tool = tool_name.clone();
                 }
                 if consecutive_errors >= MAX_CONSECUTIVE_TOOL_ERRORS {
                     messages.push(ChatMessage::system(
-                        zesdex_domain::agent::prompt::error_recovery_note(tool_name, &result),
+                        zesdex_domain::agent::prompt::error_recovery_note(&tool_name, &result),
                     ));
                     consecutive_errors = 0;
                 }
@@ -183,10 +264,7 @@ pub async fn run_agent(
                 consecutive_errors = 0;
             }
 
-            messages.push(ChatMessage::tool(
+            messages.push(ChatMessage::tool(id, truncate_tool_output(result)));
-                tc.id.clone(),
-                truncate_tool_output(result),
-            ));
         }
 
         // Add assistant response if there was text content
@@ -208,3 +286,111 @@ pub async fn run_agent(
         "Subagent reached iteration limit ({MAX_ITERATIONS})"
     ))
 }
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+    use crate::tools::ToolCtxBuilder;
+    use serde_json::json;
+
+    /// A deterministic mock tool whose `run` returns its own name (opting into
+    /// an optional sleep to make parallel-vs-sequential observable).
+    struct MockTool {
+        name: &'static str,
+        sleep_ms: u64,
+    }
+
+    impl MockTool {
+        fn new(name: &'static str, sleep_ms: u64) -> Self {
+            Self { name, sleep_ms }
+        }
+    }
+
+    impl Tool for MockTool {
+        fn name(&self) -> &'static str {
+            self.name
+        }
+        fn description(&self) -> &'static str {
+            "mock tool for tests"
+        }
+        fn parameters(&self) -> Value {
+            json!({"type":"object","properties":{}})
+        }
+        fn run(&self, _ctx: &ToolCtx, _args: &Value) -> Result<String> {
+            if self.sleep_ms > 0 {
+                std::thread::sleep(std::time::Duration::from_millis(self.sleep_ms));
+            }
+            Ok(self.name.to_string())
+        }
+    }
+
+    fn tc(name: &str, id: usize) -> zesdex_domain::core::ToolCall {
+        zesdex_domain::core::ToolCall {
+            id: format!("call_{id}"),
+            type_: "function".to_string(),
+            function: zesdex_domain::core::ToolFunction {
+                name: name.to_string(),
+                arguments: serde_json::Value::String(String::new()),
+            },
+        }
+    }
+
+    fn ctx() -> ToolCtx {
+        ToolCtxBuilder::default().build()
+    }
+
+    #[test]
+    fn parallel_batch_preserves_original_order() {
+        let tools: Vec<Box<dyn Tool>> = vec![
+            Box::new(MockTool::new("read", 0)),
+            Box::new(MockTool::new("grep", 0)),
+        ];
+        let calls = vec![tc("read", 1), tc("grep", 2), tc("read", 3)];
+
+        let results = execute_tool_batch(&tools, &ctx(), &calls);
+
+        // Results keep the assistant's original call order.
+        let names: Vec<&str> = results.iter().map(|(_, n, _)| n.as_str()).collect();
+        assert_eq!(names, vec!["read", "grep", "read"]);
+        // IDs follow the same original order (ordering contract).
+        let ids: Vec<&str> = results.iter().map(|(id, _, _)| id.as_str()).collect();
+        assert_eq!(ids, vec!["call_1", "call_2", "call_3"]);
+    }
+
+    #[test]
+    fn parallel_read_batch_is_faster_than_sequential() {
+        // Both reads sleep 30ms each. Parallel should finish ~30ms (both run
+        // at once), sequential would take ~60ms.
+        let tools: Vec<Box<dyn Tool>> = vec![Box::new(MockTool::new("read", 30))];
+        let calls = vec![tc("read", 1), tc("read", 2)];
+
+        let started = std::time::Instant::now();
+        let results = execute_tool_batch(&tools, &ctx(), &calls);
+        let elapsed = started.elapsed();
+
+        assert_eq!(results.len(), 2);
+        assert!(
+            elapsed < std::time::Duration::from_millis(55),
+            "parallel read batch took {elapsed:?}, expected concurrent execution"
+        );
+        assert!(elapsed >= std::time::Duration::from_millis(25));
+    }
+
+    #[test]
+    fn mutating_tool_forces_sequential_batch() {
+        // A batch containing a mutating tool ("write") must NOT run in
+        // parallel — the single 30ms read runs alone, then the write runs.
+        let tools: Vec<Box<dyn Tool>> = vec![
+            Box::new(MockTool::new("read", 30)),
+            Box::new(MockTool::new("write", 0)),
+        ];
+        let calls = vec![tc("read", 1), tc("write", 2)];
+
+        let results = execute_tool_batch(&tools, &ctx(), &calls);
+
+        let names: Vec<&str> = results.iter().map(|(_, n, _)| n.as_str()).collect();
+        assert_eq!(names, vec!["read", "write"]);
+        let ids: Vec<&str> = results.iter().map(|(id, _, _)| id.as_str()).collect();
+        assert_eq!(ids, vec!["call_1", "call_2"]);
+    }
+}

apps/infrastructure/src/utils.rs

@@ -221,7 +221,14 @@ pub fn build_rich_context(root: &Path) -> String {
     ));
 
     // 2. Custom Rules
-    let rule_files = [".cursorrules", ".zesdexrules", "claude.md", "agent.md"];
+    let rule_files = [
+        "AGENTS.md",
+        "CLAUDE.md",
+        ".cursorrules",
+        ".zesdexrules",
+        "claude.md",
+        "agent.md",
+    ];
     for file in rule_files {
         let p = root.join(file);
         if let Ok(content) = std::fs::read_to_string(&p) {