steve/llama-swap
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Changes and fixes before the release (docs/small tweaks) (#750)

Browse Source 
- update README.md with new docker instructions
- update docs/configuration.md
- update .github/workflows to have pinned action versions
- gofmt events package
- fix small bugs in CI scripts
- reduce config options for internal/perf/monitor and config. A ring buffer is used to keep 1hr of entries at max 5s granularity. For long term stats use prometheus monitoring on /metrics

Fixes #744
This commit is contained in:
Benson Wong
2026-05-13 21:18:19 -07:00
committed by GitHub
parent 3e3646f9f9
commit a4b91e08cf
23 changed files with 499 additions and 569 deletions
Download Patch File Download Diff File Expand all files Collapse all files
proxy/config/config.go
+2 -5
View File
@@ -223,11 +223,8 @@ func LoadConfigFromReader(r io.Reader) (Config, error) {
}
// Apply defaults for performance config when section is missing
if !config.Performance.Enable && config.Performance.Every == 0 && config.Performance.MaxAge == 0 && config.Performance.GC == 0 {
config.Performance.Enable = true
config.Performance.Every = 15 * time.Second
config.Performance.MaxAge = 1 * time.Hour
config.Performance.GC = 5 * time.Minute
if config.Performance.Every == 0 {
config.Performance.Every = 5 * time.Second
}
if err = config.Performance.Validate(); err != nil {
return Config{}, fmt.Errorf("performance: %w", err)
proxy/config/config_posix_test.go
+1 -4
View File
@@ -231,10 +231,7 @@ groups:
MetricsMaxInMemory: 1000,
CaptureBuffer: 5,
Performance: PerformanceConfig{
Enable: true,
Every: 15 * time.Second,
MaxAge: 1 * time.Hour,
GC: 5 * time.Minute,
Every: 5 * time.Second,
},
Profiles: map[string][]string{
"test": {"model1", "model2"},
proxy/config/config_windows_test.go
+1 -4
View File
@@ -220,10 +220,7 @@ groups:
MetricsMaxInMemory: 1000,
CaptureBuffer: 5,
Performance: PerformanceConfig{
Enable: true,
Every: 15 * time.Second,
MaxAge: 1 * time.Hour,
GC: 5 * time.Minute,
Every: 5 * time.Second,
},
Profiles: map[string][]string{
"test": {"model1", "model2"},
proxy/config/performance.go
+5 -16
View File
@@ -7,19 +7,14 @@ import (
// PerformanceConfig holds configuration for system performance monitoring
type PerformanceConfig struct {
Enable bool `yaml:"enable"`
Every time.Duration `yaml:"every"`
MaxAge time.Duration `yaml:"maxAge"`
GC time.Duration `yaml:"gc"`
Disabled bool `yaml:"disabled"`
Every time.Duration `yaml:"every"`
}
func (p *PerformanceConfig) UnmarshalYAML(unmarshal func(interface{}) error) error {
type rawPerformanceConfig PerformanceConfig
defaults := rawPerformanceConfig{
Enable: true,
Every: 15 * time.Second,
MaxAge: 1 * time.Hour,
GC: 5 * time.Minute,
Every: 5 * time.Second,
}
if err := unmarshal(&defaults); err != nil {
@@ -32,14 +27,8 @@ func (p *PerformanceConfig) UnmarshalYAML(unmarshal func(interface{}) error) err
// Validate checks the PerformanceConfig values and returns an error if invalid
func (p *PerformanceConfig) Validate() error {
if p.Every < time.Second {
return fmt.Errorf("every must be at least 1s, got %v", p.Every)
}
if p.MaxAge <= 0 {
return fmt.Errorf("maxAge must be greater than 0, got %v", p.MaxAge)
}
if p.GC <= 0 {
return fmt.Errorf("gc must be greater than 0, got %v", p.GC)
if p.Every < 5*time.Second {
return fmt.Errorf("every must be at least 5s, got %v", p.Every)
}
return nil
}
proxy/config/performance_test.go
+9 -51
View File
@@ -18,10 +18,8 @@ models:
assert.NoError(t, err)
// When performance section is missing, defaults should be applied
assert.True(t, config.Performance.Enable)
assert.Equal(t, 15*time.Second, config.Performance.Every)
assert.Equal(t, 1*time.Hour, config.Performance.MaxAge)
assert.Equal(t, 5*time.Minute, config.Performance.GC)
assert.False(t, config.Performance.Disabled)
assert.Equal(t, 5*time.Second, config.Performance.Every)
}
func TestPerformanceConfig_CustomValues(t *testing.T) {
@@ -29,8 +27,6 @@ func TestPerformanceConfig_CustomValues(t *testing.T) {
performance:
enable: true
every: 30s
maxAge: 12h
gc: 10m
models:
model1:
cmd: path/to/cmd --port ${PORT}
@@ -38,16 +34,14 @@ models:
config, err := LoadConfigFromReader(strings.NewReader(content))
assert.NoError(t, err)
assert.True(t, config.Performance.Enable)
assert.False(t, config.Performance.Disabled)
assert.Equal(t, 30*time.Second, config.Performance.Every)
assert.Equal(t, 12*time.Hour, config.Performance.MaxAge)
assert.Equal(t, 10*time.Minute, config.Performance.GC)
}
func TestPerformanceConfig_Disabled(t *testing.T) {
content := `
performance:
enable: false
disabled: true
models:
model1:
cmd: path/to/cmd --port ${PORT}
@@ -55,18 +49,15 @@ models:
config, err := LoadConfigFromReader(strings.NewReader(content))
assert.NoError(t, err)
assert.False(t, config.Performance.Enable)
assert.True(t, config.Performance.Disabled)
// Duration defaults should still apply
assert.Equal(t, 15*time.Second, config.Performance.Every)
assert.Equal(t, 1*time.Hour, config.Performance.MaxAge)
assert.Equal(t, 5*time.Minute, config.Performance.GC)
assert.Equal(t, 5*time.Second, config.Performance.Every)
}
func TestPerformanceConfig_PartialValues(t *testing.T) {
content := `
performance:
every: 10s
maxAge: 6h
models:
model1:
cmd: path/to/cmd --port ${PORT}
@@ -75,58 +66,27 @@ models:
assert.NoError(t, err)
// enable should default to true
assert.True(t, config.Performance.Enable)
assert.False(t, config.Performance.Disabled)
assert.Equal(t, 10*time.Second, config.Performance.Every)
assert.Equal(t, 6*time.Hour, config.Performance.MaxAge)
// gc should use default
assert.Equal(t, 5*time.Minute, config.Performance.GC)
}
func TestPerformanceConfig_InvalidEvery(t *testing.T) {
content := `
performance:
every: 500ms
every: 4s
models:
model1:
cmd: path/to/cmd --port ${PORT}
`
_, err := LoadConfigFromReader(strings.NewReader(content))
assert.Error(t, err)
assert.Contains(t, err.Error(), "every must be at least 1s")
}
func TestPerformanceConfig_InvalidMaxAge(t *testing.T) {
content := `
performance:
maxAge: 0s
models:
model1:
cmd: path/to/cmd --port ${PORT}
`
_, err := LoadConfigFromReader(strings.NewReader(content))
assert.Error(t, err)
assert.Contains(t, err.Error(), "maxAge must be greater than 0")
}
func TestPerformanceConfig_InvalidGC(t *testing.T) {
content := `
performance:
gc: 0s
models:
model1:
cmd: path/to/cmd --port ${PORT}
`
_, err := LoadConfigFromReader(strings.NewReader(content))
assert.Error(t, err)
assert.Contains(t, err.Error(), "gc must be greater than 0")
assert.Contains(t, err.Error(), "every must be at least 5s")
}
func TestPerformanceConfig_ComplexDurations(t *testing.T) {
content := `
performance:
every: 1m30s
maxAge: 2h10m
gc: 1m
models:
model1:
cmd: path/to/cmd --port ${PORT}
@@ -135,6 +95,4 @@ models:
assert.NoError(t, err)
assert.Equal(t, 90*time.Second, config.Performance.Every)
assert.Equal(t, (2*time.Hour)+(10*time.Minute), config.Performance.MaxAge)
assert.Equal(t, 1*time.Minute, config.Performance.GC)
}