feat(llm): task-level cumulative budget engine (issue #569)

CONFIGURATION.md

@@ -70,6 +70,7 @@ aish run --config ~/work/ai-shell-config.yaml
 | `context_token_budget` | integer/null | `null` | 可选的上下文 token 预算限制 | 如：4000，为 null 则仅使用消息数量限制 |
 | `enable_token_estimation` | boolean | `true` | 启用基于 tiktoken 的 token 估算 | true/false |
 | `context_auto_compact` | object | 见下方 | 自动上下文压缩配置，面向 shell/tool 输出控量 | 可选 |
+| `task_budget` | object | 见下方 | 任务级累计预算（issue #569），任一维度达到上限即停止循环并提示（继续不会重置；调整预算需显式确认并写入审计） | 各维度 integer/null |
 
 ### 工具输出配置
 
@@ -203,6 +204,14 @@ max_llm_messages: 50
 max_shell_messages: 20
 context_token_budget: null
 enable_token_estimation: true
+
+# 任务级累计预算（可选；缺省不限，仅计数）
+task_budget:
+  max_rounds: null        # 累计工具循环轮次
+  max_tool_calls: null    # 累计工具调用次数
+  max_tokens: null        # 累计 token（输入+输出，不含缓存命中）
+  max_duration_secs: null # 累计活跃时长（秒）
+
 context_auto_compact:
   enabled: true
   full_compact_enabled: true

crates/aish-config/src/lib.rs

@@ -19,5 +19,5 @@ pub mod model;
 pub use loader::ConfigLoader;
 pub use model::{
     compile_remote_danger_patterns, ApiAccountConfig, ConfigModel, InlineCompletionConfig,
-    MemoryConfig, OutputOffloadConfig, RegistrySource, SkillsConfig, ToolArgPreviewConfig,
+    MemoryConfig, OutputOffloadConfig, RegistrySource, SkillsConfig, TaskBudgetConfig,
 };

crates/aish-config/src/model.rs

@@ -194,6 +194,37 @@ impl Default for ContextAutoCompactConfig {
     }
 }
 
+// ---------------------------------------------------------------------------
+// Task budget sub-config (issue #569)
+// ---------------------------------------------------------------------------
+
+/// Task-level cumulative budget bounds. All dimensions are optional and
+/// default to unlimited; the runtime still accrues counters for display.
+/// A tripped budget stops the loop with `BudgetExhausted`; raising a limit
+/// is an explicit, audit-logged action — never implied by "continue".
+#[derive(Debug, Clone, Serialize, Deserialize, Default, PartialEq)]
+#[serde(default)]
+pub struct TaskBudgetConfig {
+    /// Cumulative tool-loop rounds for the whole task.
+    pub max_rounds: Option<u64>,
+    /// Cumulative tool executions (parallel calls each count).
+    pub max_tool_calls: Option<u64>,
+    /// Cumulative fresh tokens (input + output; cached reads excluded).
+    pub max_tokens: Option<u64>,
+    /// Cumulative active wall-clock seconds (turn time only, no idle).
+    pub max_duration_secs: Option<u64>,
+}
+
+impl TaskBudgetConfig {
+    /// True when any dimension is bounded.
+    pub fn is_bounded(&self) -> bool {
+        self.max_rounds.is_some()
+            || self.max_tool_calls.is_some()
+            || self.max_tokens.is_some()
+            || self.max_duration_secs.is_some()
+    }
+}
+
 // ---------------------------------------------------------------------------
 // Inline AI completion sub-config
 // ---------------------------------------------------------------------------
@@ -483,6 +514,11 @@ pub struct ConfigModel {
     #[serde(default)]
     pub context_token_budget: Option<usize>,
 
+    /// Task-level cumulative budget (issue #569). Every dimension is
+    /// optional; absent = unlimited (counters still accrue for /token).
+    #[serde(default)]
+    pub task_budget: TaskBudgetConfig,
+
     /// Enable tiktoken-based token estimation for context trimming
     #[serde(default = "default_true")]
     pub enable_token_estimation: bool,
@@ -582,6 +618,7 @@ impl Default for ConfigModel {
             context_token_budget: None,
             enable_token_estimation: default_true(),
             context_auto_compact: ContextAutoCompactConfig::default(),
+            task_budget: TaskBudgetConfig::default(),
             enable_scripts: default_true(),
             history_size: default_history_size(),
             terminal_resize_mode: default_terminal_resize_mode(),
@@ -1018,4 +1055,27 @@ inline_completion:
         assert_eq!(m.inline_completion.debounce_ms, 400);
         assert_eq!(m.inline_completion.max_tokens, 512);
     }
+
+    #[test]
+    fn task_budget_config_parses_from_yaml() {
+        let yaml = r#"
+max_llm_messages: 30
+task_budget:
+  max_rounds: 200
+  max_tokens: 2000000
+"#;
+        let config: ConfigModel = serde_yaml::from_str(yaml).unwrap();
+        assert!(config.task_budget.is_bounded());
+        assert_eq!(config.task_budget.max_rounds, Some(200));
+        assert_eq!(config.task_budget.max_tokens, Some(2_000_000));
+        assert_eq!(config.task_budget.max_tool_calls, None);
+        assert_eq!(config.task_budget.max_duration_secs, None);
+    }
+
+    #[test]
+    fn task_budget_config_defaults_to_unbounded() {
+        let config = ConfigModel::default();
+        assert!(!config.task_budget.is_bounded());
+        assert_eq!(config.task_budget.max_rounds, None);
+    }
 }

crates/aish-core/src/error.rs

@@ -45,6 +45,11 @@ pub enum AishError {
     #[error("tool loop stopped at the iteration limit")]
     IterationLimit,
 
+    /// Task-level cumulative budget exhausted (issue #569). The field names
+    /// the dimension that tripped (rounds / tool_calls / tokens / duration).
+    #[error("task budget exhausted: {0}")]
+    BudgetExhausted(String),
+
     #[error("operation timed out")]
     Timeout,
 }
@@ -74,6 +79,7 @@ impl AishError {
             AishError::Shell(_) => "shell",
             AishError::Cancelled => "cancelled",
             AishError::IterationLimit => "iteration_limit",
+            AishError::BudgetExhausted(_) => "budget_exhausted",
             AishError::Parse(_) => "parse",
             AishError::Timeout => "timeout",
         }

crates/aish-i18n/locales/de-DE.yaml

@@ -332,6 +332,15 @@ shell:
     no_evidence: "(nicht angegeben)"
   nl_detection:
     confirm_ask_ai: "Das sieht nach einer natürlichen Sprachfrage aus. KI fragen? (Y/n)"
+  budget:
+    exhausted_title: "⛔ Aufgabenbudget erschoepft"
+    exhausted_detail: "Dimension: {dimension} · Genutzt: {used} · Limit: {limit}"
+    exhausted_options: "Budget anpassen und fortfahren? Anpassungen werden auditiert (y=anpassen / n=stoppen)"
+    stopped_by_user: "Durch Budget gestoppt. Abgeschlossene Werkzeugschritte sind gespeichert; fortsetzen vom gespeicherten Punkt."
+    new_limit_prompt: "Neues Limit fuer diese Dimension eingeben:"
+    raised: "Budget angepasst: {dimension} -> {value}. Aufgabe erneut ausgeben, um fortzufahren."
+    invalid_limit: "Ungueltiger Wert (muss ueber der Nutzung liegen); Budget unveraendert."
+
   error:
     load_script_failed: "Skript '{script}' konnte nicht geladen werden: {error}"
     pty_error: "PTY-Fehler: {error}"
@@ -343,6 +352,7 @@ shell:
     llm_error_message: "Fehler: {error}"
     partial_turn_saved: "Die abgeschlossenen Werkzeugschritte dieses Durchgangs wurden gespeichert ({steps} Schritte). Die Arbeit vor dem Fehler geht nicht verloren; geben Sie eine neue Aufgabe ein oder ;retry, um ab dem gespeicherten Punkt fortzufahren."
     partial_turn_saved_limit: "Die abgeschlossenen Werkzeugschritte dieses Durchgangs wurden vor dem Stopp am Iterationslimit gespeichert ({steps} Schritte). Die Arbeit bleibt erhalten; geben Sie eine neue Aufgabe ein oder ;retry, um ab dem gespeicherten Punkt fortzufahren."
+    partial_turn_saved_budget: "Die abgeschlossenen Werkzeugschritte dieses Durchgangs wurden vor dem Stopp am Aufgabenbudgetlimit gespeichert ({steps} Schritte). Die Arbeit bleibt erhalten; geben Sie eine neue Aufgabe ein oder ;retry, um vom gespeicherten Punkt fortzufahren."
     llm_error_details_title: "Debug-Details"
     tool_args_json_invalid_hint: "❌ Anfrage fehlgeschlagen, bitte erneut versuchen."
   prompt:
@@ -446,6 +456,13 @@ shell:
     output_tokens: "Ausgabe-Tokens"
     total: "Gesamt"
     api_calls: "API-Aufrufe"
+    budget_title: "Aufgabenbudget"
+    budget_rounds: "Runden (genutzt/Limit):"
+    budget_tool_calls: "Werkzeugaufrufe (genutzt/Limit):"
+    budget_tokens: "Token (genutzt/Limit):"
+    budget_duration: "Aktive Sekunden (genutzt/Limit):"
+    budget_cost: "Kosten:"
+    budget_cost_unavailable: "nicht verfuegbar (Anbieter melden keine Preise)"
   setup:
     no_config_manager: "Neukonfiguration nicht möglich: Konfigurationsmanager nicht verfügbar"
     cancelled: "Einrichtung abgebrochen; aktuelle Einstellungen werden beibehalten"
@@ -559,6 +576,9 @@ shell:
       inline_enforce_json:
         label: "Inline Enforce JSON"
         desc: "Inline-Completion zwingen, striktes JSON zurückzugeben"
+      task_budget_max_rounds:
+        label: "Aufgabenbudget-Rundenlimit"
+        desc: "Kumulierte Werkzeugschleifen-Runden pro Aufgabe; leer = unbegrenzt (Weitermachen setzt nicht zurueck)"
       max_llm_messages:
         label: "Max LLM-Messages"
         desc: "Maximale Konversations-Turns im LLM-Verlauf"

crates/aish-i18n/locales/en-US.yaml

@@ -768,6 +768,15 @@ shell:
   nl_detection:
     confirm_ask_ai: "This looks like a natural language question. Ask AI? (Y/n)"
 
+  budget:
+    exhausted_title: "⛔ Task budget exhausted"
+    exhausted_detail: "Dimension: {dimension} · Used: {used} · Limit: {limit}"
+    exhausted_options: "Adjust the budget and continue? Adjustments are audit-logged (y=adjust / n=stop)"
+    stopped_by_user: "Stopped by budget. Completed tool evidence is saved; resume from the saved point later."
+    new_limit_prompt: "Enter the new limit for this dimension:"
+    raised: "Budget adjusted: {dimension} -> {value}. Re-issue the task to continue from the saved point."
+    invalid_limit: "Invalid value (must exceed usage); budget unchanged."
+
   error:
     execution_error: "❌ Error during execution: {error}"
     pty_decode_error: "Caught PTY output decode error: {error}"
@@ -779,6 +788,7 @@ shell:
     llm_error_message: "Error: {error}"
     partial_turn_saved: "Saved the completed tool steps of this turn ({steps} steps). Work done before the failure is not lost; enter a new task or ;retry to continue from the saved point."
     partial_turn_saved_limit: "Saved the completed tool steps of this turn ({steps} steps) before stopping at the iteration limit. The work is kept; enter a new task or ;retry to continue from the saved point."
+    partial_turn_saved_budget: "Saved the completed tool steps of this turn ({steps} steps) before stopping at the task budget limit. The work is kept; enter a new task or ;retry to continue from the saved point."
     llm_error_details_title: "Debug Details"
     tool_args_json_invalid_hint: "❌ Request failed, please retry."
 
@@ -888,6 +898,13 @@ shell:
     output_tokens: "Output tokens"
     total: "Total"
     api_calls: "API calls"
+    budget_title: "Task budget"
+    budget_rounds: "Rounds (used/limit):"
+    budget_tool_calls: "Tool calls (used/limit):"
+    budget_tokens: "Tokens (used/limit):"
+    budget_duration: "Active seconds (used/limit):"
+    budget_cost: "Cost:"
+    budget_cost_unavailable: "unavailable (providers do not report pricing)"
 
   setup:
     no_config_manager: "Cannot reconfigure: configuration manager unavailable"
@@ -983,6 +1000,9 @@ shell:
       inline_completion:
         label: "Inline AI Completion"
         desc: "Gray ghost-text AI suggestions while typing an AI prompt"
+      task_budget_max_rounds:
+        label: "Task Budget Round Limit"
+        desc: "Cumulative tool-loop rounds per task; blank = unlimited (continues never reset it)"
       max_llm_messages:
         label: "Max AI Messages"
         desc: "How many AI conversation turns to keep in context"

crates/aish-i18n/locales/es-ES.yaml

@@ -332,6 +332,15 @@ shell:
     no_evidence: "(no proporcionada)"
   nl_detection:
     confirm_ask_ai: "Esto parece una pregunta en lenguaje natural. ¿Preguntar a IA? (Y/n)"
+  budget:
+    exhausted_title: "⛔ Presupuesto de tarea agotado"
+    exhausted_detail: "Dimensión: {dimension} · Usado: {used} · Límite: {limit}"
+    exhausted_options: "¿Ajustar el presupuesto y continuar? Los ajustes se registran en la auditoría (y=ajustar / n=detener)"
+    stopped_by_user: "Detenido por presupuesto. La evidencia de herramientas completadas está guardada; reanude desde el punto guardado."
+    new_limit_prompt: "Introduzca el nuevo límite para esta dimensión:"
+    raised: "Presupuesto ajustado: {dimension} -> {value}. Emita la tarea de nuevo para continuar."
+    invalid_limit: "Valor inválido (debe superar el uso); presupuesto sin cambios."
+
   error:
     load_script_failed: "No se pudo cargar el script '{script}': {error}"
     pty_error: "Error de PTY: {error}"
@@ -343,6 +352,7 @@ shell:
     llm_error_message: "Error: {error}"
     partial_turn_saved: "Se guardaron los pasos de herramienta completados de este turno ({steps} pasos). El trabajo previo al error no se pierde; escriba una nueva tarea o ;retry para continuar desde el punto guardado."
     partial_turn_saved_limit: "Se guardaron los pasos de herramienta completados de este turno ({steps} pasos) antes de detenerse en el límite de iteraciones. El trabajo se conserva; escriba una nueva tarea o ;retry para continuar desde el punto guardado."
+    partial_turn_saved_budget: "Se guardaron los pasos de herramientas completados de este turno ({steps} pasos) antes de detenerse en el límite de presupuesto de la tarea. El trabajo se conserva; escriba una nueva tarea o ;retry para continuar desde el punto guardado."
     llm_error_details_title: "Detalles de depuración"
     tool_args_json_invalid_hint: "❌ La solicitud falló; inténtalo de nuevo."
   prompt:
@@ -446,6 +456,13 @@ shell:
     output_tokens: "Tokens de salida"
     total: "Total"
     api_calls: "Llamadas API"
+    budget_title: "Presupuesto de tarea"
+    budget_rounds: "Rondas (usado/límite):"
+    budget_tool_calls: "Llamadas de herramientas (usado/límite):"
+    budget_tokens: "Tokens (usado/límite):"
+    budget_duration: "Segundos activos (usado/límite):"
+    budget_cost: "Costo:"
+    budget_cost_unavailable: "no disponible (los proveedores no informan precios)"
   setup:
     no_config_manager: "No se puede reconfigurar: el gestor de configuración no está disponible"
     cancelled: "Configuración cancelada; se conservan los ajustes actuales"
@@ -559,6 +576,9 @@ shell:
       inline_enforce_json:
         label: "Forzar JSON en línea"
         desc: "Forzar que el completado en línea devuelva JSON estricto"
+      task_budget_max_rounds:
+        label: "Límite de rondas del presupuesto"
+        desc: "Rondas acumuladas del bucle de herramientas por tarea; vacío = ilimitado (continuar nunca lo restablece)"
       max_llm_messages:
         label: "Mensajes LLM máx."
         desc: "Máximo de turnos de conversación conservados en el historial del LLM"

crates/aish-i18n/locales/fr-FR.yaml

@@ -332,6 +332,15 @@ shell:
     no_evidence: "(non fournie)"
   nl_detection:
     confirm_ask_ai: "Cela ressemble à une question en langage naturel. Demander à l'IA ? (Y/n)"
+  budget:
+    exhausted_title: "⛔ Budget de tache epuise"
+    exhausted_detail: "Dimension : {dimension} · Utilise : {used} · Limite : {limit}"
+    exhausted_options: "Ajuster le budget et continuer ? Les ajustements sont journalises (y=ajuster / n=arreter)"
+    stopped_by_user: "Arrete par budget. Les preuves d'outils completes sont sauvegardees ; reprenez depuis le point sauvegarde."
+    new_limit_prompt: "Saisissez la nouvelle limite pour cette dimension :"
+    raised: "Budget ajuste : {dimension} -> {value}. Relancez la tache pour continuer."
+    invalid_limit: "Valeur invalide (doit depasser l'utilisation) ; budget inchange."
+
   error:
     load_script_failed: "Échec du chargement du script '{script}' : {error}"
     pty_error: "Erreur PTY : {error}"
@@ -343,6 +352,7 @@ shell:
     llm_error_message: "Erreur : {error}"
     partial_turn_saved: "Les etapes d'outils completees de ce tour ont ete sauvegardees ({steps} etapes). Le travail precedent l'erreur n'est pas perdu ; saisissez une nouvelle tache ou ;retry pour reprendre depuis le point sauvegarde."
     partial_turn_saved_limit: "Les etapes d'outils completees de ce tour ont ete sauvegardees ({steps} etapes) avant l'arret a la limite d'iterations. Le travail est conserve ; saisissez une nouvelle tache ou ;retry pour reprendre depuis le point sauvegarde."
+    partial_turn_saved_budget: "Les etapes d'outils completees de ce tour ont ete sauvegardees ({steps} etapes) avant l'arret a la limite de budget de la tache. Le travail est conserve ; saisissez une nouvelle tache ou ;retry pour continuer depuis le point sauvegarde."
     llm_error_details_title: "Details de debogage"
     tool_args_json_invalid_hint: "❌ La requete a echoue, veuillez reessayer."
   prompt:
@@ -446,6 +456,13 @@ shell:
     output_tokens: "Tokens de sortie"
     total: "Total"
     api_calls: "Appels API"
+    budget_title: "Budget de tache"
+    budget_rounds: "Tours (utilise/limite):"
+    budget_tool_calls: "Appels d'outils (utilise/limite):"
+    budget_tokens: "Tokens (utilise/limite):"
+    budget_duration: "Secondes actives (utilise/limite):"
+    budget_cost: "Cout:"
+    budget_cost_unavailable: "indisponible (les fournisseurs ne rapportent pas de prix)"
   setup:
     no_config_manager: "Reconfiguration impossible : gestionnaire de configuration indisponible"
     cancelled: "Configuration annulee, les parametres actuels sont conserves"
@@ -559,6 +576,9 @@ shell:
       inline_enforce_json:
         label: "Forcer JSON en ligne"
         desc: "Forcer la complétion en ligne à renvoyer du JSON strict"
+      task_budget_max_rounds:
+        label: "Limite de tours du budget"
+        desc: "Tours cumules de la boucle d'outils par tache ; vide = illimite (continuer ne reinitialise jamais)"
       max_llm_messages:
         label: "Messages LLM max"
         desc: "Tours de conversation maximum conservés dans l'historique LLM"