eric/audita
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases 2 Wiki Activity

Add explicit LLM concurrency controls

Browse Source
This commit is contained in:
Eric Rakestraw
2026-05-12 21:17:35 +00:00
parent a48f6da1f4
commit 509436cc4a
19 changed files with 875 additions and 99 deletions
Download Patch File Download Diff File Expand all files Collapse all files

33
internal/cli/run.go
View File

@@ -196,8 +196,7 @@ var processRunner = func(inv processInvocation, stdout io.Writer) (*normalizatio
}
globalScheduler := proposalScheduler
if globalScheduler == nil {
primaryCfg := llm.ResolvePrimaryConfig(inv.Config)
s, sErr := llm.NewScheduler(primaryCfg.Concurrency)
s, sErr := llm.NewScheduler(inv.Config.TotalLLMConcurrency)
if sErr != nil {
return fail("runner_setup", sErr, nil)
}
@@ -205,12 +204,18 @@ var processRunner = func(inv processInvocation, stdout io.Writer) (*normalizatio
}
if proposalScheduler == nil {
proposalScheduler = globalScheduler
if inv.Config.EffectiveProposalLLMConcurrency() < inv.Config.TotalLLMConcurrency {
s, sErr := llm.NewScheduler(inv.Config.EffectiveProposalLLMConcurrency())
if sErr != nil {
return fail("runner_setup", sErr, nil)
}
proposalScheduler = composeSchedulers(globalScheduler, s)
}
}
if validationScheduler == nil {
validationScheduler = globalScheduler
if inv.Config.ValidationLLM.Concurrency != nil && inv.Config.PrimaryLLM.Concurrency > inv.Config.EffectiveValidationLLMConfig().Concurrency {
validationCfg := llm.ResolveValidationConfig(inv.Config)
s, sErr := llm.NewScheduler(validationCfg.Concurrency)
if inv.Config.ValidationLLMConcurrency != nil && inv.Config.EffectiveValidationLLMConcurrency() < inv.Config.TotalLLMConcurrency {
s, sErr := llm.NewScheduler(inv.Config.EffectiveValidationLLMConcurrency())
if sErr != nil {
return fail("runner_setup", sErr, nil)
}
@@ -392,6 +397,10 @@ func runProcess(args []string, stdout, stderr io.Writer) int {
overrides.ValidationBaseURL = pFlags.validationBaseURL
case "llm-timeout-seconds":
overrides.PrimaryLLMTimeoutSeconds = pFlags.llmTimeoutSeconds
case "total-llm-concurrency":
overrides.TotalLLMConcurrency = pFlags.totalLLMConcurrency
case "proposal-llm-concurrency":
overrides.ProposalLLMConcurrency = pFlags.proposalLLMConcurrency
case "llm-concurrency":
overrides.PrimaryLLMConcurrency = pFlags.llmConcurrency
case "validation-llm-timeout-seconds":
@@ -682,6 +691,8 @@ type processFlags struct {
baseURL *string
validationBaseURL *string
llmTimeoutSeconds *int
totalLLMConcurrency *int
proposalLLMConcurrency *int
llmConcurrency *int
validationLLMTimeoutSeconds *int
validationMaxPromptTokens *int
@@ -717,9 +728,9 @@ func newProcessFlagSet(cfg config.Config, stderr io.Writer) (*flag.FlagSet, proc
validationMaxRetriesDefault = *cfg.ValidationLLM.MaxRetries
}
validationLLMConcurrencyDefault := cfg.PrimaryLLM.Concurrency
if cfg.ValidationLLM.Concurrency != nil {
validationLLMConcurrencyDefault = *cfg.ValidationLLM.Concurrency
validationLLMConcurrencyDefault := cfg.TotalLLMConcurrency
if cfg.ValidationLLMConcurrency != nil {
validationLLMConcurrencyDefault = *cfg.ValidationLLMConcurrency
}
targetSectionsDefault := 0
@@ -739,13 +750,15 @@ func newProcessFlagSet(cfg config.Config, stderr io.Writer) (*flag.FlagSet, proc
baseURL: fs.String("base-url", cfg.PrimaryLLM.BaseURL, "Primary OpenAI-compatible base URL"),
validationBaseURL: fs.String("validation-base-url", cfg.ValidationLLM.BaseURL, "Validation OpenAI-compatible base URL"),
llmTimeoutSeconds: fs.Int("llm-timeout-seconds", cfg.PrimaryLLM.TimeoutSeconds, "Primary LLM timeout in seconds"),
llmConcurrency: fs.Int("llm-concurrency", cfg.PrimaryLLM.Concurrency, "Primary LLM concurrency"),
totalLLMConcurrency: fs.Int("total-llm-concurrency", cfg.TotalLLMConcurrency, "Total concurrent LLM calls across proposal and validation"),
proposalLLMConcurrency: fs.Int("proposal-llm-concurrency", cfg.EffectiveProposalLLMConcurrency(), "Concurrent proposal-generation LLM calls"),
llmConcurrency: fs.Int("llm-concurrency", cfg.TotalLLMConcurrency, "Alias for --total-llm-concurrency"),
validationLLMTimeoutSeconds: fs.Int("validation-llm-timeout-seconds", validationTimeoutSecondsDefault, "Validation LLM timeout in seconds"),
validationMaxPromptTokens: fs.Int("validation-max-prompt-tokens", cfg.ValidationMaxPromptTokens, "Validation max prompt tokens"),
targetSections: fs.Int("target-sections", targetSectionsDefault, "Target number of transcript sections"),
maxRetries: fs.Int("max-retries", cfg.PrimaryLLM.MaxRetries, "Maximum structured-output retries"),
validationMaxRetries: fs.Int("validation-max-retries", validationMaxRetriesDefault, "Validation structured-output retries"),
validationLLMConcurrency: fs.Int("validation-llm-concurrency", validationLLMConcurrencyDefault, "Validation LLM concurrency"),
validationLLMConcurrency: fs.Int("validation-llm-concurrency", validationLLMConcurrencyDefault, "Concurrent validation LLM calls (inherits total when unset)"),
maxSectionTokens: fs.Int("max-section-tokens", cfg.MaxSectionTokens, "Maximum section tokens"),
minSectionTokens: fs.Int("min-section-tokens", cfg.MinSectionTokens, "Minimum section tokens"),
glossaryConfidenceThreshold: fs.Float64("glossary-confidence-threshold", cfg.Thresholds.Glossary, "Glossary confidence threshold"),