alex/g3
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

rename max_context_length to fallback_default_max_tokens

Browse Source
This commit is contained in:
Jochen
2025-11-06 19:47:02 +11:00
parent af20c93c61
commit 0e1f9dbf9a
5 changed files with 14 additions and 14 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
config.coach-player.example.toml
View File

@@ -19,6 +19,6 @@ max_tokens = 4096
temperature = 0.3 # Slightly higher temperature for more creative implementations
[agent]
max_context_length = 8192
fallback_default_max_tokens = 8192
enable_streaming = true
timeout_seconds = 60

2
config.example.toml
View File

@@ -15,7 +15,7 @@ temperature = 0.1
use_oauth = true
[agent]
max_context_length = 8192
fallback_default_max_tokens = 8192
enable_streaming = true
timeout_seconds = 60

6
crates/g3-config/src/lib.rs
View File

@@ -62,7 +62,7 @@ pub struct EmbeddedConfig {
#[derive(Debug, Clone, Serialize, Deserialize)]
pub struct AgentConfig {
pub max_context_length: usize,
pub fallback_default_max_tokens: usize,
pub enable_streaming: bool,
pub timeout_seconds: u64,
pub auto_compact: bool,
@@ -133,7 +133,7 @@ impl Default for Config {
player: None, // Will use default_provider if not specified
},
agent: AgentConfig {
max_context_length: 8192,
fallback_default_max_tokens: 8192,
enable_streaming: true,
timeout_seconds: 60,
auto_compact: true,
@@ -249,7 +249,7 @@ impl Config {
player: None, // Will use default_provider if not specified
},
agent: AgentConfig {
max_context_length: 8192,
fallback_default_max_tokens: 8192,
enable_streaming: true,
timeout_seconds: 60,
auto_compact: true,

6
crates/g3-config/src/tests.rs
View File

@@ -31,7 +31,7 @@ model_path = "test.gguf"
model_type = "llama"
[agent]
max_context_length = 8192
fallback_default_max_tokens = 8192
enable_streaming = true
timeout_seconds = 60
"#;
@@ -72,7 +72,7 @@ token = "test-token"
model = "test-model"
[agent]
max_context_length = 8192
fallback_default_max_tokens = 8192
enable_streaming = true
timeout_seconds = 60
"#;
@@ -113,7 +113,7 @@ token = "test-token"
model = "test-model"
[agent]
max_context_length = 8192
fallback_default_max_tokens = 8192
enable_streaming = true
timeout_seconds = 60
"#;

12
crates/g3-core/src/lib.rs
View File

@@ -865,7 +865,7 @@ impl<W: UiWriter> Agent<W> {
debug!("Default provider set successfully");
// Determine context window size based on active provider
let context_length = Self::determine_context_length(&config, &providers)?;
let context_length = Self::get_configured_context_length(&config, &providers)?;
let mut context_window = ContextWindow::new(context_length);
// If README content is provided, add it as the first system message
@@ -920,7 +920,7 @@ impl<W: UiWriter> Agent<W> {
})
}
fn determine_context_length(config: &Config, providers: &ProviderRegistry) -> Result<u32> {
fn get_configured_context_length(config: &Config, providers: &ProviderRegistry) -> Result<u32> {
// Get the configured max_tokens for the current provider
fn get_provider_max_tokens(config: &Config, provider_name: &str) -> Option<u32> {
match provider_name {
@@ -959,7 +959,7 @@ impl<W: UiWriter> Agent<W> {
}
})
} else {
config.agent.max_context_length as u32
config.agent.fallback_default_max_tokens as u32
}
}
"openai" => {
@@ -983,7 +983,7 @@ impl<W: UiWriter> Agent<W> {
}
})
}
_ => config.agent.max_context_length as u32,
_ => config.agent.fallback_default_max_tokens as u32,
};
debug!(
@@ -2415,8 +2415,8 @@ Template:
// Check if we need to summarize before starting
if self.context_window.should_summarize() {
// First try thinning if we haven't reached 90% yet
if self.context_window.percentage_used() < 90.0 && self.context_window.should_thin() {
// First try thinning if we are at capacity, don't call the LLM for a summary (might fail)
if self.context_window.percentage_used() > 90.0 && self.context_window.should_thin() {
self.ui_writer.print_context_status(&format!(
"\n🥒 Context window at {}%. Trying thinning first...",
self.context_window.percentage_used() as u32