Files
audita/internal/framework/runner/observability.go

351 lines
11 KiB
Go

package runner
import (
"context"
"sort"
"strings"
"sync"
"time"
"gitea.maximumdirect.net/eric/audita/internal/framework/contracts"
validatormetadata "gitea.maximumdirect.net/eric/audita/internal/validators/metadata"
)
type UtilizationDiagnostics struct {
EffectiveConcurrency EffectiveConcurrencyLimits `json:"effective_concurrency"`
RunTiming RunTimingSummary `json:"run_timing"`
LLMCalls LLMCallSummary `json:"llm_calls"`
Modules []ModuleTimingSummary `json:"modules,omitempty"`
Validators []ValidatorTimingSummary `json:"validators,omitempty"`
}
type EffectiveConcurrencyLimits struct {
TotalLLM int `json:"total_llm"`
ProposalLLM int `json:"proposal_llm"`
ValidationLLM int `json:"validation_llm"`
}
type RunTimingSummary struct {
RunWallTimeMS int64 `json:"run_wall_time_ms"`
SchedulerQueueWaitMS int64 `json:"scheduler_queue_wait_ms"`
LLMExecutionTimeMS int64 `json:"llm_execution_time_ms"`
DeterministicValidationMS int64 `json:"deterministic_validation_time_ms"`
MaxInFlightLLMCalls int `json:"max_in_flight_llm_calls"`
AverageInFlightLLMCalls int `json:"average_in_flight_llm_calls"`
}
type LLMCallSummary struct {
TotalProposalCalls int `json:"total_proposal_calls"`
TotalValidationCalls int `json:"total_validation_calls"`
}
type ModuleTimingSummary struct {
ModuleKey string `json:"module_key"`
ModuleInstance string `json:"module_instance"`
ProposalLLMCalls int `json:"proposal_llm_calls"`
ValidationLLMCalls int `json:"validation_llm_calls"`
SchedulerQueueWaitMS int64 `json:"scheduler_queue_wait_ms"`
LLMExecutionTimeMS int64 `json:"llm_execution_time_ms"`
DeterministicValidationMS int64 `json:"deterministic_validation_time_ms"`
ModuleWallTimeMS int64 `json:"module_wall_time_ms"`
}
type ValidatorTimingSummary struct {
ModuleKey string `json:"module_key"`
ModuleInstance string `json:"module_instance"`
ValidatorKey string `json:"validator_key"`
LLMBacked bool `json:"llm_backed"`
Calls int `json:"calls"`
ElapsedMS int64 `json:"elapsed_ms"`
}
type runInstrumentation struct {
startedAt time.Time
mu sync.Mutex
totalProposalCalls int
totalValidationCalls int
schedulerQueueWait time.Duration
llmExecutionTime time.Duration
deterministicValidation time.Duration
perModuleProposalCalls map[string]int
perModuleValidationCalls map[string]int
perModuleSchedulerQueueWait map[string]time.Duration
perModuleLLMExecutionTime map[string]time.Duration
perModuleDeterministicValidation map[string]time.Duration
validatorSummaries map[string]*ValidatorTimingSummary
inflight int
maxInflight int
inflightArea float64
lastInflightChange time.Time
averageInflightComputed bool
}
func newRunInstrumentation(startedAt time.Time) *runInstrumentation {
return &runInstrumentation{
startedAt: startedAt,
perModuleProposalCalls: make(map[string]int),
perModuleValidationCalls: make(map[string]int),
perModuleSchedulerQueueWait: make(map[string]time.Duration),
perModuleLLMExecutionTime: make(map[string]time.Duration),
perModuleDeterministicValidation: make(map[string]time.Duration),
validatorSummaries: make(map[string]*ValidatorTimingSummary),
lastInflightChange: startedAt,
}
}
func (i *runInstrumentation) wrapProposalClient(client contracts.StructuredLLMClient) contracts.StructuredLLMClient {
if client == nil {
return nil
}
return measuredClient{
inner: client,
collector: i,
isProposal: true,
}
}
func (i *runInstrumentation) wrapValidationClient(client contracts.StructuredLLMClient) contracts.StructuredLLMClient {
if client == nil {
return nil
}
return measuredClient{
inner: client,
collector: i,
isProposal: false,
}
}
func (i *runInstrumentation) wrapScheduler(s contracts.LLMScheduler, isProposal bool) contracts.LLMScheduler {
if s == nil {
return nil
}
return measuredScheduler{
inner: s,
collector: i,
isProposal: isProposal,
}
}
func (i *runInstrumentation) recordValidatorTiming(moduleKey, moduleInstance, validatorKey string, llmBacked bool, elapsed time.Duration) {
i.mu.Lock()
defer i.mu.Unlock()
if !llmBacked {
i.deterministicValidation += elapsed
i.perModuleDeterministicValidation[moduleInstance] += elapsed
}
k := moduleInstance + "::" + validatorKey
summary, ok := i.validatorSummaries[k]
if !ok {
summary = &ValidatorTimingSummary{
ModuleKey: moduleKey,
ModuleInstance: moduleInstance,
ValidatorKey: validatorKey,
LLMBacked: llmBacked,
}
i.validatorSummaries[k] = summary
}
summary.Calls++
summary.ElapsedMS += elapsed.Milliseconds()
}
func (i *runInstrumentation) recordModuleWallTime(moduleInstance string, elapsed time.Duration) {
i.mu.Lock()
defer i.mu.Unlock()
// Derived later from started/completed, but we keep a slot for sanity.
_ = moduleInstance
_ = elapsed
}
func (i *runInstrumentation) beginInFlight() {
now := time.Now().UTC()
i.mu.Lock()
defer i.mu.Unlock()
i.inflightArea += float64(i.inflight) * now.Sub(i.lastInflightChange).Seconds()
i.lastInflightChange = now
i.inflight++
if i.inflight > i.maxInflight {
i.maxInflight = i.inflight
}
}
func (i *runInstrumentation) endInFlight() {
now := time.Now().UTC()
i.mu.Lock()
defer i.mu.Unlock()
i.inflightArea += float64(i.inflight) * now.Sub(i.lastInflightChange).Seconds()
i.lastInflightChange = now
if i.inflight > 0 {
i.inflight--
}
}
func (i *runInstrumentation) finalize(runOutput *RunOutput, completedAt time.Time, limits EffectiveConcurrencyLimits) *UtilizationDiagnostics {
i.mu.Lock()
defer i.mu.Unlock()
if !i.averageInflightComputed {
i.inflightArea += float64(i.inflight) * completedAt.Sub(i.lastInflightChange).Seconds()
i.lastInflightChange = completedAt
i.averageInflightComputed = true
}
runSeconds := completedAt.Sub(i.startedAt).Seconds()
avgInflight := 0
if runSeconds > 0 {
avgInflight = int(i.inflightArea / runSeconds)
}
moduleSummaries := make([]ModuleTimingSummary, 0)
if runOutput != nil {
moduleSummaries = make([]ModuleTimingSummary, 0, len(runOutput.ModuleResults))
for _, moduleResult := range runOutput.ModuleResults {
moduleSummaries = append(moduleSummaries, ModuleTimingSummary{
ModuleKey: moduleResult.ModuleKey,
ModuleInstance: moduleResult.ModuleInstance,
ProposalLLMCalls: i.perModuleProposalCalls[moduleResult.ModuleInstance],
ValidationLLMCalls: i.perModuleValidationCalls[moduleResult.ModuleInstance],
SchedulerQueueWaitMS: i.perModuleSchedulerQueueWait[moduleResult.ModuleInstance].Milliseconds(),
LLMExecutionTimeMS: i.perModuleLLMExecutionTime[moduleResult.ModuleInstance].Milliseconds(),
DeterministicValidationMS: i.perModuleDeterministicValidation[moduleResult.ModuleInstance].Milliseconds(),
ModuleWallTimeMS: moduleResult.CompletedAt.Sub(moduleResult.StartedAt).Milliseconds(),
})
}
}
validatorSummaries := make([]ValidatorTimingSummary, 0, len(i.validatorSummaries))
for _, summary := range i.validatorSummaries {
validatorSummaries = append(validatorSummaries, *summary)
}
sortValidatorSummaries(validatorSummaries)
return &UtilizationDiagnostics{
EffectiveConcurrency: limits,
RunTiming: RunTimingSummary{
RunWallTimeMS: completedAt.Sub(i.startedAt).Milliseconds(),
SchedulerQueueWaitMS: i.schedulerQueueWait.Milliseconds(),
LLMExecutionTimeMS: i.llmExecutionTime.Milliseconds(),
DeterministicValidationMS: i.deterministicValidation.Milliseconds(),
MaxInFlightLLMCalls: i.maxInflight,
AverageInFlightLLMCalls: avgInflight,
},
LLMCalls: LLMCallSummary{
TotalProposalCalls: i.totalProposalCalls,
TotalValidationCalls: i.totalValidationCalls,
},
Modules: moduleSummaries,
Validators: validatorSummaries,
}
}
type measuredClient struct {
inner contracts.StructuredLLMClient
collector *runInstrumentation
isProposal bool
}
func (c measuredClient) CompleteStructured(ctx context.Context, req contracts.StructuredCompletionRequest, out any) (contracts.StructuredCompletionResponse, error) {
if c.collector != nil {
c.collector.beginInFlight()
}
started := time.Now().UTC()
resp, err := c.inner.CompleteStructured(ctx, req, out)
elapsed := time.Since(started)
if c.collector != nil {
c.collector.endInFlight()
c.collector.mu.Lock()
moduleInstance := moduleInstanceFromStage(req.StageName)
c.collector.llmExecutionTime += elapsed
c.collector.perModuleLLMExecutionTime[moduleInstance] += elapsed
if c.isProposal {
c.collector.totalProposalCalls++
c.collector.perModuleProposalCalls[moduleInstance]++
} else {
c.collector.totalValidationCalls++
c.collector.perModuleValidationCalls[moduleInstance]++
}
c.collector.mu.Unlock()
}
return resp, err
}
type measuredScheduler struct {
inner contracts.LLMScheduler
collector *runInstrumentation
isProposal bool
}
func (s measuredScheduler) Run(ctx context.Context, fn func(context.Context) error) error {
started := time.Now().UTC()
var execDuration time.Duration
err := s.inner.Run(ctx, func(runCtx context.Context) error {
execStart := time.Now().UTC()
callErr := fn(runCtx)
execDuration += time.Since(execStart)
return callErr
})
totalDuration := time.Since(started)
waitDuration := totalDuration - execDuration
if waitDuration < 0 {
waitDuration = 0
}
if s.collector != nil {
stageModule := moduleInstanceFromContext(ctx)
s.collector.mu.Lock()
s.collector.schedulerQueueWait += waitDuration
if stageModule != "" {
s.collector.perModuleSchedulerQueueWait[stageModule] += waitDuration
}
s.collector.mu.Unlock()
}
_ = s.isProposal
return err
}
func moduleInstanceFromStage(stage string) string {
stage = strings.TrimSpace(stage)
if stage == "" {
return ""
}
parts := strings.Split(stage, ":")
if len(parts) == 0 {
return stage
}
return strings.TrimSpace(parts[0])
}
func moduleInstanceFromContext(ctx context.Context) string {
if ctx == nil {
return ""
}
if v := ctx.Value(moduleInstanceContextKey{}); v != nil {
if s, ok := v.(string); ok {
return strings.TrimSpace(s)
}
}
return ""
}
type moduleInstanceContextKey struct{}
func withModuleInstanceContext(ctx context.Context, moduleInstance string) context.Context {
if ctx == nil {
ctx = context.Background()
}
return context.WithValue(ctx, moduleInstanceContextKey{}, strings.TrimSpace(moduleInstance))
}
func isLLMBackedValidator(v contracts.Validator) bool {
return validatormetadata.ClassOf(v) == validatormetadata.ExecutionClassLLMBacked
}
func sortValidatorSummaries(in []ValidatorTimingSummary) {
sort.SliceStable(in, func(i, j int) bool {
if in[i].ModuleInstance != in[j].ModuleInstance {
return in[i].ModuleInstance < in[j].ModuleInstance
}
return in[i].ValidatorKey < in[j].ValidatorKey
})
}