feat: extract worker サーキットブレーカーを占有量ベースに統一

crates/manifest/src/config.rs

@@ -252,6 +252,9 @@ impl MemoryConfig {
             extract_worker_max_input_tokens: upper
                 .extract_worker_max_input_tokens
                 .or(self.extract_worker_max_input_tokens),
+            extract_worker_max_turns: upper
+                .extract_worker_max_turns
+                .or(self.extract_worker_max_turns),
             consolidation_model: upper.consolidation_model.or(self.consolidation_model),
             consolidation_threshold_files: upper
                 .consolidation_threshold_files

crates/manifest/src/defaults.rs

@@ -50,7 +50,11 @@ pub const COMPACT_WORKER_MAX_TURNS: Option<u32> = Some(20);
 /// default references.
 pub const COMPACT_DEFAULT_REFERENCE_COUNT: usize = 5;
 
-/// Cumulative input-token cap for the memory Phase 1 (extract) worker's
-/// own LLM calls. Exceeding this aborts the extract run.
-/// See [`crate::MemoryConfig::extract_worker_max_input_tokens`].
+/// Current prompt-occupancy cap for the memory extract worker's own
+/// LLM requests. Exceeding this aborts the extract run (circuit-breaker
+/// path). See [`crate::MemoryConfig::extract_worker_max_input_tokens`].
 pub const MEMORY_EXTRACT_WORKER_MAX_INPUT_TOKENS: u64 = 30_000;
+
+/// Optional maximum extract-worker tool-loop depth. `None` means unlimited.
+/// See [`crate::MemoryConfig::extract_worker_max_turns`].
+pub const MEMORY_EXTRACT_WORKER_MAX_TURNS: Option<u32> = Some(8);

crates/manifest/src/lib.rs

@@ -108,11 +108,17 @@ pub struct MemoryConfig {
     /// the auto-extract trigger is dormant.
     #[serde(default)]
     pub extract_threshold: Option<u64>,
-    /// Cumulative input-token cap for the extract worker's own LLM
-    /// calls. Exceeding this aborts the extract run. `None` ⇒
+    /// Current prompt-occupancy cap for the extract worker's own LLM
+    /// requests. Exceeding this aborts the extract run. `None` ⇒
     /// [`defaults::MEMORY_EXTRACT_WORKER_MAX_INPUT_TOKENS`].
     #[serde(default)]
     pub extract_worker_max_input_tokens: Option<u64>,
+    /// Optional maximum extract-worker tool-loop depth. `None` leaves
+    /// the worker unlimited; the default bounds runaway short-context
+    /// loops. Falls through to
+    /// [`defaults::MEMORY_EXTRACT_WORKER_MAX_TURNS`] when unset.
+    #[serde(default)]
+    pub extract_worker_max_turns: Option<u32>,
     /// Optional model for the Phase 2 (consolidation) worker. When
     /// `None`, the main pod model is cloned via `clone_boxed()`.
     /// Reasoning-class models are recommended.