Fix compaction loop for small models or large input (#5803)

crates/goose/src/agents/agent.rs

@@ -940,6 +940,7 @@ impl Agent {
             let _ = reply_span.enter();
             let mut turns_taken = 0u32;
             let max_turns = session_config.max_turns.unwrap_or(DEFAULT_MAX_TURNS);
+            let mut compaction_attempts = 0;
 
             loop {
                 if is_token_cancelled(&cancel_token) {
@@ -991,6 +992,8 @@ impl Agent {
 
                     match next {
                         Ok((response, usage)) => {
+                            compaction_attempts = 0;
+
                             // Emit model change event if provider is lead-worker
                             let provider = self.provider().await?;
                             if let Some(lead_worker) = provider.as_lead_worker() {
@@ -1202,6 +1205,19 @@ impl Agent {
                         }
                         Err(ref provider_err @ ProviderError::ContextLengthExceeded(_)) => {
                             crate::posthog::emit_error(provider_err.telemetry_type());
+                            compaction_attempts += 1;
+
+                            if compaction_attempts >= 2 {
+                                error!("Context limit exceeded after compaction - prompt too large");
+                                yield AgentEvent::Message(
+                                    Message::assistant().with_system_notification(
+                                        SystemNotificationType::InlineMessage,
+                                        "Unable to continue: Context limit still exceeded after compaction. Try using a shorter message, a model with a larger context window, or start a new session."
+                                    )
+                                );
+                                break;
+                            }
+
                             yield AgentEvent::Message(
                                 Message::assistant().with_system_notification(
                                     SystemNotificationType::InlineMessage,
@@ -1222,15 +1238,10 @@ impl Agent {
                                     conversation = compacted_conversation;
                                     did_recovery_compact_this_iteration = true;
                                     yield AgentEvent::HistoryReplaced(conversation.clone());
-                                    continue;
+                                    break;
                                 }
                                 Err(e) => {
-                                    error!("Error: {}", e);
-                                    yield AgentEvent::Message(
-                                        Message::assistant().with_text(
-                                            format!("Ran into this error trying to compact: {e}.\n\nPlease retry if you think this is a transient or recoverable error.")
-                                        )
-                                    );
+                                    error!("Compaction failed: {}", e);
                                     break;
                                 }
                             }

crates/goose/src/context_mgmt/mod.rs

@@ -320,8 +320,7 @@ async fn do_compact(
                         continue;
                     } else {
                         return Err(anyhow::anyhow!(
-                            "Failed to compact messages: context length still exceeded after {} attempts with maximum removal",
-                            removal_percentages.len()
+                            "Failed to compact: context limit exceeded even after removing all tool responses"
                         ));
                     }
                 }