valknar/llmx
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Auto compact at ~90% (#5292)

Browse Source 
Users now hit a window exceeded limit and they usually don't know what
to do. This starts auto compact at ~90% of the window.
This commit is contained in:
Ahmed Ibrahim
2025-10-20 11:29:49 -07:00
committed by GitHub
parent cda6db6ccf
commit 049a61bcfc
21 changed files with 236 additions and 110 deletions
Download Patch File Download Diff File Expand all files Collapse all files

16
codex-rs/core/src/config.rs
View File

@@ -85,10 +85,10 @@ pub struct Config {
pub model_family: ModelFamily,
/// Size of the context window for the model, in tokens.
pub model_context_window: Option<u64>,
pub model_context_window: Option<i64>,
/// Maximum number of output tokens.
pub model_max_output_tokens: Option<u64>,
pub model_max_output_tokens: Option<i64>,
/// Token usage threshold triggering auto-compaction of conversation history.
pub model_auto_compact_token_limit: Option<i64>,
@@ -824,10 +824,10 @@ pub struct ConfigToml {
pub model_provider: Option<String>,
/// Size of the context window for the model, in tokens.
pub model_context_window: Option<u64>,
pub model_context_window: Option<i64>,
/// Maximum number of output tokens.
pub model_max_output_tokens: Option<u64>,
pub model_max_output_tokens: Option<i64>,
/// Token usage threshold triggering auto-compaction of conversation history.
pub model_auto_compact_token_limit: Option<i64>,
@@ -2805,7 +2805,7 @@ model_verbosity = "high"
model_family: find_family_for_model("o3").expect("known model slug"),
model_context_window: Some(200_000),
model_max_output_tokens: Some(100_000),
model_auto_compact_token_limit: None,
model_auto_compact_token_limit: Some(180_000),
model_provider_id: "openai".to_string(),
model_provider: fixture.openai_provider.clone(),
approval_policy: AskForApproval::Never,
@@ -2874,7 +2874,7 @@ model_verbosity = "high"
model_family: find_family_for_model("gpt-3.5-turbo").expect("known model slug"),
model_context_window: Some(16_385),
model_max_output_tokens: Some(4_096),
model_auto_compact_token_limit: None,
model_auto_compact_token_limit: Some(14_746),
model_provider_id: "openai-chat-completions".to_string(),
model_provider: fixture.openai_chat_completions_provider.clone(),
approval_policy: AskForApproval::UnlessTrusted,
@@ -2958,7 +2958,7 @@ model_verbosity = "high"
model_family: find_family_for_model("o3").expect("known model slug"),
model_context_window: Some(200_000),
model_max_output_tokens: Some(100_000),
model_auto_compact_token_limit: None,
model_auto_compact_token_limit: Some(180_000),
model_provider_id: "openai".to_string(),
model_provider: fixture.openai_provider.clone(),
approval_policy: AskForApproval::OnFailure,
@@ -3028,7 +3028,7 @@ model_verbosity = "high"
model_family: find_family_for_model("gpt-5").expect("known model slug"),
model_context_window: Some(272_000),
model_max_output_tokens: Some(128_000),
model_auto_compact_token_limit: None,
model_auto_compact_token_limit: Some(244_800),
model_provider_id: "openai".to_string(),
model_provider: fixture.openai_provider.clone(),
approval_policy: AskForApproval::OnFailure,