Provider-neutral context management

src/agent/provider/anthropic/controller.rs

@@ -15,7 +15,7 @@ use crate::agent::provider::{
 };
 use crate::conversation::llm::{
     Author as LLMAuthor, Conversation as LLMConversation, Message as LLMMessage,
-    MessageContent as LLMMessageContent, shorten_messages_list_to_context_size,
+    MessageContent as LLMMessageContent, TokenEstimate, shorten_messages_list_to_context_size,
 };
 use crate::strings;
 
@@ -130,7 +130,7 @@ impl ControllerTrait for Controller {
             tracing::trace!("Shortening messages list to context size");
 
             conversation_messages = shorten_messages_list_to_context_size(
-                &text_generation_config.model_id,
+                TokenEstimate::Approximate,
                 &prompt_message,
                 conversation_messages,
                 Some(text_generation_config.max_response_tokens),

src/agent/provider/openai/controller.rs

@@ -24,7 +24,7 @@ use crate::{
     },
     conversation::llm::{
         Author as LLMAuthor, Conversation as LLMConversation, Message as LLMMessage,
-        MessageContent as LLMMessageContent, shorten_messages_list_to_context_size,
+        MessageContent as LLMMessageContent, TokenEstimate, shorten_messages_list_to_context_size,
     },
     utils::base64::base64_decode,
 };
@@ -117,7 +117,7 @@ impl ControllerTrait for Controller {
             tracing::trace!("Shortening messages list to context size");
 
             conversation_messages = shorten_messages_list_to_context_size(
-                &text_generation_config.model_id,
+                TokenEstimate::Tiktoken(&text_generation_config.model_id),
                 &prompt_message,
                 conversation_messages,
                 text_generation_config.max_response_tokens,

src/agent/provider/openai_compat/controller.rs

@@ -15,7 +15,7 @@ use crate::{
     },
     conversation::llm::{
         Author as LLMAuthor, Conversation as LLMConversation, Message as LLMMessage,
-        MessageContent as LLMMessageContent, shorten_messages_list_to_context_size,
+        MessageContent as LLMMessageContent, TokenEstimate, shorten_messages_list_to_context_size,
     },
 };
 use crate::{
@@ -114,7 +114,7 @@ impl ControllerTrait for Controller {
             tracing::trace!("Shortening messages list to context size");
 
             conversation_messages = shorten_messages_list_to_context_size(
-                &text_generation_config.model_id,
+                TokenEstimate::Approximate,
                 &prompt_message,
                 conversation_messages,
                 text_generation_config.max_response_tokens,

src/agent/provider/venice/chat.rs

@@ -8,7 +8,7 @@ use crate::agent::AgentPurpose;
 use crate::agent::provider::entity::{TextGenerationParams, TextGenerationResult};
 use crate::conversation::llm::{
     Author as LLMAuthor, Conversation as LLMConversation, Message as LLMMessage,
-    MessageContent as LLMMessageContent, shorten_messages_list_to_context_size,
+    MessageContent as LLMMessageContent, TokenEstimate, shorten_messages_list_to_context_size,
 };
 use crate::strings;
 
@@ -64,7 +64,7 @@ pub async fn generate_text(
 
     if params.context_management_enabled {
         conversation_messages = shorten_messages_list_to_context_size(
-            &text_generation_config.model_id,
+            TokenEstimate::Approximate,
             &prompt_message,
             conversation_messages,
             text_generation_config.max_response_tokens,