perf(agent): rombak alur AI agent — adaptif, hemat token, self-healing

Ganti explore phase MANDATORY (3 subagent tiap turn, boros) dengan
tool explore_codebase yang DIPUTUSKAN agent sendiri (lazy, token-aware):
- hapus ExploreService trait + with_explore + Phase 0 dari turn loop
- ExploreServiceImpl kini jadi tool 'explore_codebase' (1 context-scout
  subagent, read-only, cap output 4k chars)
- system prompt: instruksi TOKEN BUDGET (jawab langsung utk query simple,
  panggil explore_codebase sekali utk task kompleks)

Loop utama kini adaptif & self-healing:
- max_tokens adaptif (800/1600/4096 by request length) — bukan selalu 4096
- temperature 0.2 saat tool-calling, 0.7 utk final answer
- ErrorTracker: deteksi tool error berulang → inject recovery note,
  stop setelah 8 error total (bukan 50 iterasi sia-sia)
- auto-compact history > 60k chars sebelum LLM call
- tool output di-truncate ke 12k chars sebelum masuk konteks

Tambah 8 unit test (truncation, adaptive tokens, error tracker).

apps/application/src/agent/explore.rs

@@ -1,57 +0,0 @@
-//! Mandatory explore phase — spawns parallel subagents to discover context
-//! before the main agent begins its turn.
-//!
-//! # Flow
-//!
-//! Before the main agent's LLM loop, [`ExploreService::explore`] dispatches
-//! at least 3 subagents in parallel (code-structure scan, symbol-index query,
-//! semantic-context search). Their findings are consolidated into a single
-//! system message that is prepended to the conversation.
-//!
-//! # Why mandatory
-//!
-//! Without structured exploration the main agent works from an empty context
-//! window. The explore phase guarantees that every turn starts with a compact
-//! snapshot of what the codebase contains and where relevant code lives.
-
-use anyhow::Result;
-use std::collections::VecDeque;
-use std::future::Future;
-use std::pin::Pin;
-use std::sync::{Arc, Mutex};
-use zesdex_domain::agent::TurnEvent;
-
-/// The consolidated output of an explore phase — a set of system-level
-/// context messages injected before the main agent prompt.
-#[derive(Debug, Clone)]
-pub struct ExploreOutput {
-    /// One or more system messages summarising what the explore subagents
-    /// discovered. Prepended to the conversation by the turn service.
-    pub context_messages: Vec<String>,
-    /// Short human-readable summary of what was explored.
-    pub summary: String,
-}
-
-/// Service trait for the mandatory pre-turn exploration phase.
-///
-/// Implementors spawn ≥3 parallel subagents, each analysing a different
-/// aspect of the workspace, and return a consolidated summary.
-///
-/// # Object safety
-///
-/// This trait is `dyn`-safe — it returns `Pin<Box<dyn Future>>` so it can
-/// be stored as `Arc<dyn ExploreService>`.
-pub trait ExploreService: Send + Sync {
-    /// Run the explore phase.
-    ///
-    /// `query` — the user's current input phrase.
-    /// `workspace_root` — absolute path to the workspace root.
-    /// `turn_events` — shared event queue for TUI updates.
-    /// Returns structured context messages and a summary blob.
-    fn explore<'a>(
-        &'a self,
-        query: &'a str,
-        workspace_root: &'a str,
-        turn_events: &'a Arc<Mutex<VecDeque<TurnEvent>>>,
-    ) -> Pin<Box<dyn Future<Output = Result<ExploreOutput>> + Send + 'a>>;
-}

apps/application/src/agent/mod.rs

@@ -19,8 +19,6 @@ pub trait AgentTurnService: Send + Sync {
     fn run_turn(&self, params: AgentTurnParams) -> impl Future<Output = Result<()>> + Send;
 }
 
-pub mod explore;
 pub mod turn_service;
 
-pub use explore::{ExploreOutput, ExploreService};
 pub use turn_service::{compact_messages_with_ai, AgentTurnServiceImpl};

apps/application/src/agent/turn_service.rs

@@ -7,12 +7,29 @@ use zesdex_domain::agent::{AgentTurnParams, TurnEvent};
 use zesdex_domain::core::{ChatMessage, StreamEvent, ToolDef};
 use zesdex_domain::main_agent_prompt;
 
-use super::{ExploreService, ToolExecutor};
+use super::ToolExecutor;
 use crate::ports::ProviderService;
 
 /// Maximum tool-call iterations per agent turn before forcing termination.
 const MAX_TURN_ITERATIONS: u32 = 50;
 
+/// Maximum number of consecutive identical tool errors before the loop
+/// injects a recovery note and forces a different approach.
+const MAX_CONSECUTIVE_TOOL_ERRORS: usize = 3;
+
+/// Total tool-call errors tolerated per turn before the loop is stopped.
+const MAX_TOTAL_TOOL_ERRORS: usize = 8;
+
+/// Ceiling for a single tool-result message inserted into context.
+///
+/// Tool outputs can be huge (read / semantic_search). Truncating keeps the
+/// context window from exploding while preserving the important head.
+const TOOL_OUTPUT_MAX_CHARS: usize = 12_000;
+
+/// Total conversation characters that trigger auto-compaction before the
+/// next LLM call.
+const AUTO_COMPACT_CHARS: usize = 60_000;
+
 // ---------------------------------------------------------------------------
 // Helper: push a TurnEvent onto the shared queue.
 // ---------------------------------------------------------------------------
@@ -51,6 +68,89 @@ fn make_stream_callback(
     })
 }
 
+// ---------------------------------------------------------------------------
+// Helper: truncate a long tool output before it enters the conversation
+// context. Preserves the head and appends a clear truncation marker.
+// ---------------------------------------------------------------------------
+
+fn truncate_tool_output(output: String) -> String {
+    if output.len() <= TOOL_OUTPUT_MAX_CHARS {
+        return output;
+    }
+    let mut result: String = output.chars().take(TOOL_OUTPUT_MAX_CHARS).collect();
+    result.push_str(&format!(
+        "\n...[truncated {} chars]",
+        output.len() - TOOL_OUTPUT_MAX_CHARS
+    ));
+    result
+}
+
+// ---------------------------------------------------------------------------
+// Helper: adaptive generation parameters.
+// ---------------------------------------------------------------------------
+
+/// Pick a `max_tokens` budget for the turn's next LLM call based on the
+/// length of the user's request. Short requests need far fewer tokens than
+/// the current hardcoded 4096 — big savings on small tasks.
+fn adaptive_max_tokens(request_len: usize) -> u32 {
+    if request_len <= 80 {
+        800
+    } else if request_len <= 400 {
+        1600
+    } else {
+        4096
+    }
+}
+
+/// Sum the character length of the conversation (user + assistant +
+/// tool content) as a cheap proxy for context size.
+fn conversation_chars(messages: &[ChatMessage]) -> usize {
+    messages
+        .iter()
+        .map(|m| m.content.as_deref().map(str::len).unwrap_or(0))
+        .sum()
+}
+
+/// Track repeated tool-call errors so the loop can recover instead of
+/// burning iterations retrying the same failing tool.
+#[derive(Default)]
+struct ErrorTracker {
+    consecutive: usize,
+    total: usize,
+    last_tool: String,
+    last_error: String,
+}
+
+impl ErrorTracker {
+    fn record(&mut self, tool_name: &str, error: &str, messages: &mut Vec<ChatMessage>) {
+        if self.last_tool == tool_name {
+            self.consecutive += 1;
+        } else {
+            self.consecutive = 1;
+        }
+        self.last_tool = tool_name.to_string();
+        self.last_error = error.to_string();
+        self.total += 1;
+
+        // Inject a recovery note once the same tool keeps failing.
+        if self.consecutive >= MAX_CONSECUTIVE_TOOL_ERRORS
+            && !messages.iter().any(|m| {
+                m.content
+                    .as_deref()
+                    .is_some_and(|c| c.contains("[System note]"))
+            })
+        {
+            messages.push(ChatMessage::system(
+                zesdex_domain::agent::prompt::error_recovery_note(tool_name, error),
+            ));
+        }
+    }
+
+    fn should_stop(&self) -> bool {
+        self.consecutive >= MAX_CONSECUTIVE_TOOL_ERRORS * 2 || self.total >= MAX_TOTAL_TOOL_ERRORS
+    }
+}
+
 // ---------------------------------------------------------------------------
 // Helper: execute a single tool call, push events, return the result string.
 // ---------------------------------------------------------------------------
@@ -71,6 +171,7 @@ async fn execute_tool_call<T: ToolExecutor>(
     };
 
     let is_error = output.starts_with("Error:");
+    let output = truncate_tool_output(output);
 
     push_event(
         turn_events,
@@ -108,19 +209,19 @@ fn emit_usage(turn_events: &Arc<Mutex<VecDeque<TurnEvent>>>, usage: Option<(u64,
 
 /// Service implementation for executing an agent turn asynchronously.
 ///
-/// # Explore phase
-///
-/// Before the main LLM loop begins, [`AgentTurnServiceImpl`] runs a mandatory
-/// explore phase that spawns ≥3 parallel subagents (code structure, symbol
-/// index, semantic context) and injects their consolidated findings as a
-/// system message. See [`ExploreService`] for the trait contract.
+/// The turn loop is adaptive and token-aware:
+/// - No mandatory explore phase — the *agent* decides when to call the
+///   `explore_codebase` tool (see the main prompt), so simple queries skip
+///   exploration entirely.
+/// - `max_tokens` / `temperature` adapt to the request length and phase.
+/// - Repeated tool errors trigger a system recovery note and eventually
+///   stop the loop instead of burning iterations.
+/// - Tool outputs are truncated before entering context.
+/// - Oversized histories are auto-compacted before the next LLM call.
 pub struct AgentTurnServiceImpl<P: ProviderService, T: ToolExecutor> {
     provider: Arc<P>,
     tool_executor: Arc<T>,
     tool_defs: Vec<ToolDef>,
-    /// Optional explore-phase service. When `Some`, the explore phase runs
-    /// before every turn; when `None` it is skipped (tests, daemon mode).
-    explore_service: Option<Arc<dyn ExploreService>>,
 }
 
 impl<P: ProviderService, T: ToolExecutor> AgentTurnServiceImpl<P, T> {
@@ -129,19 +230,9 @@ impl<P: ProviderService, T: ToolExecutor> AgentTurnServiceImpl<P, T> {
             provider,
             tool_executor,
             tool_defs,
-            explore_service: None,
         }
     }
 
-    /// Attach an optional explore-phase service.
-    ///
-    /// When set, every call to `run_turn` will first run the explore phase
-    /// and inject the consolidated context as a system message.
-    pub fn with_explore(mut self, service: Arc<dyn ExploreService>) -> Self {
-        self.explore_service = Some(service);
-        self
-    }
-
     /// Execute a single LLM call with the current message list, handling
     /// streaming events and error reporting.
     async fn call_llm(
@@ -149,6 +240,8 @@ impl<P: ProviderService, T: ToolExecutor> AgentTurnServiceImpl<P, T> {
         messages: &[ChatMessage],
         abort: &Arc<AtomicBool>,
         turn_events: &Arc<Mutex<VecDeque<TurnEvent>>>,
+        max_tokens: u32,
+        temperature: f32,
     ) -> Result<(ChatMessage, Option<(u64, u64)>), String> {
         let on_event = make_stream_callback(abort, turn_events);
 
@@ -156,13 +249,39 @@ impl<P: ProviderService, T: ToolExecutor> AgentTurnServiceImpl<P, T> {
             .chat_stream(
                 messages,
                 Some(self.tool_defs.clone()),
-                Some(4096),
-                Some(0.7),
+                Some(max_tokens),
+                Some(temperature),
                 on_event,
             )
             .await
             .map_err(|e| format!("LLM error: {e}"))
     }
+
+    /// Auto-compact the history in place if it exceeds the threshold.
+    ///
+    /// Runs at most once per turn. Skips the synthetic system prompt that
+    /// this service inserts at index 0.
+    async fn auto_compact_if_needed(&self, messages: &mut Vec<ChatMessage>) {
+        if conversation_chars(messages) <= AUTO_COMPACT_CHARS {
+            return;
+        }
+        // Keep the system prompt (index 0) out of compaction.
+        let sys = messages[0].clone();
+        let mut rest: Vec<ChatMessage> = messages.drain(1..).collect();
+        let before = rest.len();
+        if let Err(e) = super::compact_messages_with_ai(&mut rest, self.provider.as_ref()).await {
+            warn!("auto-compact failed (non-fatal): {e}");
+        }
+        info!(
+            "auto-compacted history: {} messages -> {}",
+            before,
+            rest.len()
+        );
+        let mut rebuilt = Vec::with_capacity(rest.len() + 1);
+        rebuilt.push(sys);
+        rebuilt.extend(rest);
+        *messages = rebuilt;
+    }
 }
 
 impl<P: ProviderService, T: ToolExecutor> super::AgentTurnService for AgentTurnServiceImpl<P, T> {
@@ -173,73 +292,26 @@ impl<P: ProviderService, T: ToolExecutor> super::AgentTurnService for AgentTurnS
             params.model
         );
 
-        // ── Phase 0: Mandatory explore ──────────────────────────────────
-        // Spawn ≥3 parallel subagents to discover code structure, symbols,
-        // and semantic context. The consolidated summary is injected as a
-        // system message before the main agent prompt.
-        if let Some(ref explorer) = self.explore_service {
-            // Determine workspace root from the first message's context or
-            // the first workspace root in params.
-            let user_query = params
-                .messages
-                .last()
-                .map(|m| m.content.clone().unwrap_or_default())
-                .unwrap_or_default();
-            let workspace_root = params
-                .workspace_roots
-                .first()
-                .map(|p| p.to_string_lossy().to_string())
-                .unwrap_or_else(|| ".".to_string());
-
-            push_event(
-                &params.turn_events,
-                TurnEvent::SystemNote {
-                    kind: "info".into(),
-                    message: "🔍 Exploring codebase structure...".into(),
-                },
-            );
-
-            match explorer
-                .explore(&user_query, &workspace_root, &params.turn_events)
-                .await
-            {
-                Ok(output) => {
-                    // Insert each context message as a system message.
-                    // They go at index 0 and are removed after the turn
-                    // like the main agent prompt.
-                    for ctx_msg in &output.context_messages {
-                        params
-                            .messages
-                            .insert(0, ChatMessage::system(ctx_msg.clone()));
-                    }
-                    info!(
-                        "Explore phase complete: {} context messages, {}",
-                        output.context_messages.len(),
-                        output.summary
-                    );
-                }
-                Err(e) => {
-                    warn!("Explore phase failed (non-fatal): {e}");
-                    push_event(
-                        &params.turn_events,
-                        TurnEvent::SystemNote {
-                            kind: "warn".into(),
-                            message: format!("Explore phase failed: {e}"),
-                        },
-                    );
-                }
-            }
-        }
-
         // Insert system prompt at position 0 once and keep it there for the
         // entire turn, avoiding per-iteration clones of the full message list.
-        // It is removed before emitting the Compacted event so persistence
-        // does not store the prompt redundantly.
         params
             .messages
             .insert(0, ChatMessage::system(main_agent_prompt()));
         let original_count = params.messages.len();
 
+        // Estimate request complexity from the last user message.
+        let request_len = params
+            .messages
+            .last()
+            .and_then(|m| m.content.as_deref())
+            .map(str::len)
+            .unwrap_or(0);
+
+        let mut errors = ErrorTracker::default();
+        // Track whether the previous call produced tool calls — used to
+        // lower temperature once the agent starts producing a final answer.
+        let mut saw_tool_calls = false;
+
         for iteration in 0..MAX_TURN_ITERATIONS {
             // ── Check abort flag ────────────────────────────────────────
             if params.abort.load(Ordering::SeqCst) {
@@ -254,15 +326,40 @@ impl<P: ProviderService, T: ToolExecutor> super::AgentTurnService for AgentTurnS
                 break;
             }
 
+            if errors.should_stop() {
+                push_event(
+                    &params.turn_events,
+                    TurnEvent::SystemNote {
+                        kind: "warn".into(),
+                        message: "Stopping: repeated tool errors without progress".into(),
+                    },
+                );
+                break;
+            }
+
             debug!("agent turn iteration {iteration}");
 
+            // ── Auto-compact oversized history before the LLM call ─────
+            self.auto_compact_if_needed(&mut params.messages).await;
+
+            // ── Adaptive generation parameters ─────────────────────────
+            let max_tokens = adaptive_max_tokens(request_len);
+            // Lower temperature while the agent is still choosing tools to
+            // keep tool selection deterministic; raise it for the final
+            // free-form answer.
+            let temperature = if saw_tool_calls { 0.2 } else { 0.7 };
+
             // ── Stream start + call LLM ─────────────────────────────────
             push_event(&params.turn_events, TurnEvent::StreamStart);
 
-            // Uses params.messages directly (sys_msg[0] already in place
-            // from the insert above) — no per-iteration clone needed.
             let result = self
-                .call_llm(&params.messages, &params.abort, &params.turn_events)
+                .call_llm(
+                    &params.messages,
+                    &params.abort,
+                    &params.turn_events,
+                    max_tokens,
+                    temperature,
+                )
                 .await;
 
             match result {
@@ -283,6 +380,7 @@ impl<P: ProviderService, T: ToolExecutor> super::AgentTurnService for AgentTurnS
                         break;
                     }
 
+                    saw_tool_calls = true;
                     params.messages.push(assistant_msg);
 
                     // ── Execute each tool call ──────────────────────────
@@ -290,6 +388,9 @@ impl<P: ProviderService, T: ToolExecutor> super::AgentTurnService for AgentTurnS
                         let output =
                             execute_tool_call(self.tool_executor.as_ref(), &params.turn_events, tc)
                                 .await;
+                        if output.starts_with("Error:") {
+                            errors.record(&tc.function.name, &output, &mut params.messages);
+                        }
                         params
                             .messages
                             .push(ChatMessage::tool(tc.id.clone(), output));
@@ -370,3 +471,69 @@ pub async fn compact_messages_with_ai<P: ProviderService>(
         }
     }
 }
+
+// ---------------------------------------------------------------------------
+// Tests
+// ---------------------------------------------------------------------------
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+
+    #[test]
+    fn truncate_short_output_is_unchanged() {
+        let out = "short".to_string();
+        assert_eq!(truncate_tool_output(out.clone()), out);
+    }
+
+    #[test]
+    fn truncate_long_output_preserves_head_and_marks_cut() {
+        let long = "x".repeat(TOOL_OUTPUT_MAX_CHARS + 500);
+        let truncated = truncate_tool_output(long.clone());
+        assert!(truncated.len() < long.len());
+        assert!(truncated.contains("...[truncated"));
+        assert!(truncated.starts_with("xxx"));
+    }
+
+    #[test]
+    fn adaptive_max_tokens_scales_with_request_len() {
+        assert_eq!(adaptive_max_tokens(10), 800);
+        assert_eq!(adaptive_max_tokens(200), 1600);
+        assert_eq!(adaptive_max_tokens(5000), 4096);
+    }
+
+    #[test]
+    fn error_tracker_injects_recovery_note_after_repeats() {
+        let mut tracker = ErrorTracker::default();
+        let mut messages: Vec<ChatMessage> = Vec::new();
+        tracker.record("read", "Error: File not found", &mut messages);
+        tracker.record("read", "Error: File not found", &mut messages);
+        assert!(!tracker.should_stop());
+        // Third consecutive failure → recovery note injected.
+        tracker.record("read", "Error: File not found", &mut messages);
+        assert!(messages.iter().any(|m| m
+            .content
+            .as_deref()
+            .is_some_and(|c| c.contains("[System note]"))));
+    }
+
+    #[test]
+    fn error_tracker_stops_after_too_many_errors() {
+        let mut tracker = ErrorTracker::default();
+        let mut messages: Vec<ChatMessage> = Vec::new();
+        for i in 0..MAX_TOTAL_TOOL_ERRORS {
+            tracker.record("bash", &format!("Error: boom {i}"), &mut messages);
+        }
+        assert!(tracker.should_stop());
+    }
+
+    #[test]
+    fn conversation_chars_sums_content_only() {
+        let messages = vec![
+            ChatMessage::system("sys".to_string()),
+            ChatMessage::user("hello world".to_string()),
+            ChatMessage::tool("id".to_string(), "output".to_string()),
+        ];
+        assert_eq!(conversation_chars(&messages), 3 + 11 + 6);
+    }
+}

apps/application/src/lib.rs

@@ -52,5 +52,5 @@ pub use cms::{
 
 pub use agent::{
     turn_service::{compact_messages_with_ai, AgentTurnServiceImpl},
-    AgentTurnService, ExploreOutput, ExploreService, ToolExecutor,
+    AgentTurnService, ToolExecutor,
 };