pelikhan · Oct 3, 2026 · Oct 3, 2026 · Oct 3, 2026 · Oct 3, 2026 · Oct 3, 2026
diff --git a/docs/src/content/docs/reference/audit.md b/docs/src/content/docs/reference/audit.md
@@ -84,6 +84,15 @@ The Friction section attributes execution-friction costs by driver and source. I
 
 The Gateway Steering Events section reports `token_steering` and `timeout_steering` warnings emitted when a run approaches its AI Credits or time limit. JSON output includes each event's type, message, and timestamp when available.
 
+The Work Queue section reports the activation-time queue snapshot, the assigned worker's work and claim IDs, the agent's finish intent, and timestamped coordinator operations from workflow job logs. In JSON, `work_queue.snapshot.transactions` contains the queue facts captured at activation, while `work_queue.operations` contains this run's publication and reconciliation diagnostics with their source files. A `finish_intent` is a request, not evidence that completion was verified. The field is omitted when no coordinator evidence is available.
+
+`audit` downloads this evidence by default. For `logs`, which defaults to compact usage downloads, select `work-queue` (activation and agent artifacts plus workflow logs) or `all`. Both commands include `work_queue` in their JSON reports, per run for `logs`, and preserve it in cached summaries:
+
+```bash
+gh aw logs 1234567890 --artifacts work-queue --json
+gh aw audit 1234567890 --artifacts work-queue --json
+```
+
 The Observability Insights section includes `skill_activations` when skill-invocation evidence is found. Each entry reports the skill name, `status` (`invoked`), the detection `source` (`agent_output` or `log_parse`), and provenance fields in JSON output. This makes it possible to distinguish skills that were merely restored or installed from skills that were actually invoked during the run.
 
 The Graders section is present when the run recorded deterministic grader results (`graders` declared in the workflow frontmatter). The `graders` object in JSON output lists each grader (`id`, `name`, `status`, `value`, `unit`, `passed`, and, when declared in the grader manifest, `direction` and `threshold`) plus aggregate counts: `total`, `passed`, `failed`, `error_count`, and `unavailable_count`. Grader results are read from the compact `usage` artifact (mirrored there by the conclusion job), the unified `agent` artifact, or the `agent-output-fallback` artifact, so they are available even when `--artifacts usage` narrows the download. The same `graders` object is included per run in `gh aw logs --json` output.

diff --git a/docs/src/content/docs/setup/cli.md b/docs/src/content/docs/setup/cli.md
@@ -598,7 +598,7 @@ gh aw audit 1234567890 --runtime cloud-hypervisor        # Skip run unless sandb
 
 The `--repo` flag accepts `owner/repo` format and is required when passing a bare numeric run ID without a full URL, allowing the command to locate the correct repository.
 
-The `--artifacts` flag selects which artifact sets to download (default: `all`). Valid sets include `activation`, `agent`, `all`, `detection`, `evals`, `experiment`, `firewall`, `github-api`, `graders`, `info`, `mcp`, and `usage`. Use `all` to download the full artifact set. Unlike `gh aw logs`, which defaults to `usage`, `audit` defaults to `all` for comprehensive analysis. The `--experiment` flag filters to runs that include the named experiment; `--variant` further restricts to a specific variant value and requires `--experiment` to be set. The `--output/-o` flag overrides the output directory.
+The `--artifacts` flag selects which artifact sets to download (default: `all`). Valid sets include `activation`, `agent`, `all`, `detection`, `evals`, `experiment`, `firewall`, `github-api`, `graders`, `info`, `mcp`, `usage`, and `work-queue`. The `work-queue` set downloads queue snapshots, worker finish intents, and workflow logs for coordinator operation reporting. Use `all` to download the full artifact set. Unlike `gh aw logs`, which defaults to `usage`, `audit` defaults to `all` for comprehensive analysis. The `--experiment` flag filters to runs that include the named experiment; `--variant` further restricts to a specific variant value and requires `--experiment` to be set. The `--output/-o` flag overrides the output directory.
 
 Logs are saved to `.github/aw/logs/run-{id}/` with filenames indicating the extraction level. Pre-agent failures (integrity filtering, missing secrets, binary install) surface the actual error in `failure_analysis.error_summary`. Invalid run IDs return a human-readable error.
 

diff --git a/pkg/cli/audit.go b/pkg/cli/audit.go
@@ -79,6 +79,7 @@ type auditAnalysisResults struct {
 	tokenUsageSummary       *TokenUsageSummary
 	workingSet              *WorkingSetMetrics
 	ledger                  *LedgerActivity
+	dispatchCoordinator     *DispatchCoordinatorReport
 	friction                *FrictionCostSummary
 	redactedDomainsAnalysis *RedactedDomainsAnalysis
 	rateLimitUsage          *GitHubRateLimitUsage

diff --git a/pkg/cli/audit_analysis_fanout.go b/pkg/cli/audit_analysis_fanout.go
@@ -207,6 +207,11 @@ func launchFirewallAnalysis(g *errgroup.Group, gctx context.Context, results *au
 
 // launchSupplementalAuditAnalyses exclusively writes redactedDomainsAnalysis, rateLimitUsage, artifacts, and safeItemsCount.
 func launchSupplementalAuditAnalyses(g *errgroup.Group, gctx context.Context, results *auditAnalysisResults, runOutputDir string, verbose bool) {
+	runAuditAnalysis(g, gctx, true, "extractDispatchCoordinatorReport", "Failed to extract dispatch coordinator operations", func(v *DispatchCoordinatorReport) {
+		results.dispatchCoordinator = v
+	}, func() (*DispatchCoordinatorReport, error) {
+		return extractDispatchCoordinatorReport(runOutputDir)
+	})
 	runAuditAnalysis(g, gctx, verbose, "analyzeRedactedDomains", "Failed to analyze redacted domains", func(v *RedactedDomainsAnalysis) {
 		results.redactedDomainsAnalysis = v
 	}, func() (*RedactedDomainsAnalysis, error) {

diff --git a/pkg/cli/audit_cache.go b/pkg/cli/audit_cache.go
@@ -13,7 +13,7 @@ import (
 
 type auditCacheSource string
 
-const auditSchemaVersion = 2
+const auditSchemaVersion = 4
 
 const (
 	auditCacheSourceFull auditCacheSource = "full"
@@ -99,6 +99,9 @@ func writeLogsAuditFile(processedRun ProcessedRun, processedRuns []ProcessedRun,
 		auditData, _ = buildLocalAuditData(processedRun, metrics, processedRun.MCPToolUsage)
 		auditData.CacheSource = auditCacheSourceLogs
 	}
+	if processedRun.DispatchCoordinator != nil {
+		auditData.DispatchCoordinator = processedRun.DispatchCoordinator
+	}
 	hydratedProcessedRuns := hydrateProcessedRunsWithCachedAudit(processedRuns)
 	auditData.Comparison = buildAuditComparisonForProcessedRuns(hydrateProcessedRunWithCachedAudit(processedRun), hydratedProcessedRuns)
 	if err := writeAuditData(runOutputDir, auditData); err != nil {
@@ -141,5 +144,8 @@ func hydrateProcessedRunWithCachedAudit(processedRun ProcessedRun) ProcessedRun
 	if len(processedRun.GatewaySteeringEvents) == 0 {
 		processedRun.GatewaySteeringEvents = audit.GatewaySteeringEvents
 	}
+	if processedRun.DispatchCoordinator == nil {
+		processedRun.DispatchCoordinator = audit.DispatchCoordinator
+	}
 	return processedRun
 }
diff --git a/pkg/cli/audit_render_output.go b/pkg/cli/audit_render_output.go
@@ -42,6 +42,11 @@ func renderAuditReport(ctx context.Context, processedRun ProcessedRun, metrics L
 	if auditData.Ledger == nil {
 		auditData.Ledger = processedRun.Ledger
 	}
+	if mergeDispatchCoordinatorReport(&auditData.DispatchCoordinator, processedRun.DispatchCoordinator) && !opts.NoBaseline {
+		if err := writeAuditData(runOutputDir, auditData); err != nil {
+			return err
+		}
+	}
 	if opts.Group {
 		parseAuditLogsIfRequested(runID, runOutputDir, opts)
 		return nil
@@ -64,6 +69,7 @@ func buildRenderedAuditDataFromCache(ctx context.Context, processedRun Processed
 	if auditData.Ledger == nil {
 		auditData.Ledger = processedRun.Ledger
 	}
+	mergeDispatchCoordinatorReport(&auditData.DispatchCoordinator, processedRun.DispatchCoordinator)
 	createdItems := resolveCreatedItems(runOutputDir, processedRun.SafeOutputs)
 	addAuditOutcomeSummary(ctx, &auditData, createdItems)
 	auditData.Comparison = buildRenderedAuditComparison(ctx, processedRun, createdItems, runOutputDir, opts)

diff --git a/pkg/cli/audit_report.go b/pkg/cli/audit_report.go
@@ -30,47 +30,48 @@ var ghaLogTimestampPrefixPattern = regexp.MustCompile(`^\d{4}-\d{2}-\d{2}T`)
 
 // AuditData represents the complete structured audit data for a workflow run
 type AuditData struct {
-	SchemaVersion           int                      `json:"schema_version"`
-	CacheSource             auditCacheSource         `json:"cache_source,omitempty"`
-	Overview                OverviewData             `json:"overview"`
-	Comparison              *AuditComparisonData     `json:"comparison,omitempty"`
-	TaskDomain              *TaskDomainInfo          `json:"task_domain,omitempty"`
-	BehaviorFingerprint     *BehaviorFingerprint     `json:"behavior_fingerprint,omitempty"`
-	AgenticAssessments      []AgenticAssessment      `json:"agentic_assessments,omitempty"`
-	Metrics                 MetricsData              `json:"metrics"`
-	KeyFindings             []AuditFinding           `json:"key_findings,omitempty"`
-	Recommendations         []Recommendation         `json:"recommendations,omitempty"`
-	ObservabilityInsights   []ObservabilityInsight   `json:"observability_insights,omitempty"`
-	PerformanceMetrics      *PerformanceMetrics      `json:"performance_metrics,omitempty"`
-	EngineConfig            *AuditEngineConfig       `json:"engine_config,omitempty"`
-	PromptAnalysis          *PromptAnalysis          `json:"prompt_analysis,omitempty"`
-	SessionAnalysis         *SessionAnalysis         `json:"session_analysis,omitempty"`
-	SafeOutputSummary       *SafeOutputSummary       `json:"safe_output_summary,omitempty"`
-	MCPServerHealth         *MCPServerHealth         `json:"mcp_server_health,omitempty"`
-	Jobs                    []JobData                `json:"jobs,omitempty"`
-	DownloadedFiles         []FileInfo               `json:"downloaded_files"`
-	MissingTools            []MissingToolReport      `json:"missing_tools,omitempty"`
-	MissingData             []MissingDataReport      `json:"missing_data,omitempty"`
-	Noops                   []NoopReport             `json:"noops,omitempty"`
-	MCPFailures             []MCPFailureReport       `json:"mcp_failures,omitempty"`
-	SkillActivations        []SkillActivation        `json:"skill_activations,omitempty"`
-	GatewaySteeringEvents   []GatewaySteeringEvent   `json:"gateway_steering_events,omitempty"`
-	FirewallTokenUsage      *TokenUsageSummary       `json:"firewall_token_usage,omitempty"`
-	GitHubRateLimitUsage    *GitHubRateLimitUsage    `json:"github_rate_limit_usage,omitempty"`
-	FirewallAnalysis        *FirewallAnalysis        `json:"firewall_analysis,omitempty"`
-	PolicyAnalysis          *PolicyAnalysis          `json:"policy_analysis,omitempty"`
-	RedactedDomainsAnalysis *RedactedDomainsAnalysis `json:"redacted_domains_analysis,omitempty"`
-	Errors                  []ValidationIssue        `json:"errors,omitempty"`
-	Warnings                []ValidationIssue        `json:"warnings,omitempty"`
-	ToolUsage               []ToolUsageInfo          `json:"tool_usage,omitempty"`
-	MCPToolUsage            *MCPToolUsageData        `json:"mcp_tool_usage,omitempty"`
-	CreatedItems            []CreatedItemReport      `json:"created_items,omitempty"`
-	Outcomes                []OutcomeReport          `json:"outcomes,omitempty"`
-	OutcomeSummary          *OutcomeSummary          `json:"outcome_summary,omitempty"`
-	Experiments             *ExperimentData          `json:"experiments,omitempty"`
-	Graders                 *GradersData             `json:"graders,omitempty"`
-	Ledger                  *LedgerActivity          `json:"ledger,omitempty"`
-	Friction                *FrictionCostSummary     `json:"friction,omitempty"`
+	SchemaVersion           int                        `json:"schema_version"`
+	CacheSource             auditCacheSource           `json:"cache_source,omitempty"`
+	Overview                OverviewData               `json:"overview"`
+	Comparison              *AuditComparisonData       `json:"comparison,omitempty"`
+	TaskDomain              *TaskDomainInfo            `json:"task_domain,omitempty"`
+	BehaviorFingerprint     *BehaviorFingerprint       `json:"behavior_fingerprint,omitempty"`
+	AgenticAssessments      []AgenticAssessment        `json:"agentic_assessments,omitempty"`
+	Metrics                 MetricsData                `json:"metrics"`
+	KeyFindings             []AuditFinding             `json:"key_findings,omitempty"`
+	Recommendations         []Recommendation           `json:"recommendations,omitempty"`
+	ObservabilityInsights   []ObservabilityInsight     `json:"observability_insights,omitempty"`
+	PerformanceMetrics      *PerformanceMetrics        `json:"performance_metrics,omitempty"`
+	EngineConfig            *AuditEngineConfig         `json:"engine_config,omitempty"`
+	PromptAnalysis          *PromptAnalysis            `json:"prompt_analysis,omitempty"`
+	SessionAnalysis         *SessionAnalysis           `json:"session_analysis,omitempty"`
+	SafeOutputSummary       *SafeOutputSummary         `json:"safe_output_summary,omitempty"`
+	MCPServerHealth         *MCPServerHealth           `json:"mcp_server_health,omitempty"`
+	Jobs                    []JobData                  `json:"jobs,omitempty"`
+	DownloadedFiles         []FileInfo                 `json:"downloaded_files"`
+	MissingTools            []MissingToolReport        `json:"missing_tools,omitempty"`
+	MissingData             []MissingDataReport        `json:"missing_data,omitempty"`
+	Noops                   []NoopReport               `json:"noops,omitempty"`
+	MCPFailures             []MCPFailureReport         `json:"mcp_failures,omitempty"`
+	SkillActivations        []SkillActivation          `json:"skill_activations,omitempty"`
+	GatewaySteeringEvents   []GatewaySteeringEvent     `json:"gateway_steering_events,omitempty"`
+	FirewallTokenUsage      *TokenUsageSummary         `json:"firewall_token_usage,omitempty"`
+	GitHubRateLimitUsage    *GitHubRateLimitUsage      `json:"github_rate_limit_usage,omitempty"`
+	FirewallAnalysis        *FirewallAnalysis          `json:"firewall_analysis,omitempty"`
+	PolicyAnalysis          *PolicyAnalysis            `json:"policy_analysis,omitempty"`
+	RedactedDomainsAnalysis *RedactedDomainsAnalysis   `json:"redacted_domains_analysis,omitempty"`
+	Errors                  []ValidationIssue          `json:"errors,omitempty"`
+	Warnings                []ValidationIssue          `json:"warnings,omitempty"`
+	ToolUsage               []ToolUsageInfo            `json:"tool_usage,omitempty"`
+	MCPToolUsage            *MCPToolUsageData          `json:"mcp_tool_usage,omitempty"`
+	CreatedItems            []CreatedItemReport        `json:"created_items,omitempty"`
+	Outcomes                []OutcomeReport            `json:"outcomes,omitempty"`
+	OutcomeSummary          *OutcomeSummary            `json:"outcome_summary,omitempty"`
+	Experiments             *ExperimentData            `json:"experiments,omitempty"`
+	Graders                 *GradersData               `json:"graders,omitempty"`
+	Ledger                  *LedgerActivity            `json:"ledger,omitempty"`
+	DispatchCoordinator     *DispatchCoordinatorReport `json:"work_queue,omitempty"`
+	Friction                *FrictionCostSummary       `json:"friction,omitempty"`
 }
 
 // AuditFinding represents a key insight discovered during audit
@@ -560,6 +561,7 @@ func assembleAuditData(inputs auditDataInputs) AuditData {
 		Metrics:                 metricsData,
 		Friction:                inputs.processedRun.Friction,
 		Ledger:                  inputs.processedRun.Ledger,
+		DispatchCoordinator:     inputs.processedRun.DispatchCoordinator,
 		KeyFindings:             inputs.findings,
 		Recommendations:         inputs.recommendations,
 		ObservabilityInsights:   inputs.observabilityInsights,

diff --git a/pkg/cli/audit_report_render.go b/pkg/cli/audit_report_render.go
@@ -328,6 +328,7 @@ func renderConsoleWarnings(warnings []ValidationIssue) {
 }
 
 func renderConsoleOperationalSections(data AuditData) {
+	renderConsoleDispatchCoordinator(data.DispatchCoordinator)
 	renderConsoleSkillActivations(data.SkillActivations)
 	renderConsoleGatewaySteeringEvents(data.GatewaySteeringEvents)
 	renderConsoleMissingTools(data.MissingTools)
@@ -341,6 +342,7 @@ func renderConsoleOperationalSections(data AuditData) {
 	if data.FirewallAnalysis != nil && data.FirewallAnalysis.TotalRequests > 0 {
 		renderCompactFirewall(data.FirewallAnalysis)
 	}
+
 }
 
 // renderConsoleFriction prints the per-driver breakdown and the individual

diff --git a/pkg/cli/audit_run_pipeline.go b/pkg/cli/audit_run_pipeline.go
@@ -176,6 +176,12 @@ func renderCachedAuditIfAvailable(ctx context.Context, cfg auditRunConfig) (done
 	if !ok {
 		return false, false, nil
 	}
+	if dispatchCoordinatorArtifactsRequested(cfg.artifactFilter) && len(findMissingFilterEntries(cfg.artifactFilter, cfg.outputDir)) > 0 {
+		return false, false, nil
+	}
+	if dispatchCoordinatorLogsMissing(cfg.artifactFilter, cfg.outputDir) {
+		return false, false, nil
+	}
 	auditLog.Printf("Using cached run summary for run %d (processed at %s)", cfg.runID, summary.ProcessedAt.Format(time.RFC3339))
 	if cfg.verbose {
 		fmt.Fprintln(os.Stderr, console.FormatInfoMessage(fmt.Sprintf("Using cached run summary for run %d (processed at %s)", cfg.runID, summary.ProcessedAt.Format(time.RFC3339))))
@@ -230,6 +236,7 @@ func auditNeedsDetectionArtifact(cfg auditRunConfig, summary *RunSummary) bool {
 }
 
 func processedRunFromSummary(summary *RunSummary, runOutputDir string) ProcessedRun {
+	backfillDispatchCoordinatorReport(&summary.DispatchCoordinator, runOutputDir)
 	if summary.Ledger == nil {
 		if activity, err := loadUsageActivitySummary(runOutputDir); err == nil && activity != nil {
 			summary.Ledger = activity.Ledger
@@ -261,6 +268,7 @@ func processedRunFromSummary(summary *RunSummary, runOutputDir string) Processed
 		SafeOutputs:             summary.SafeOutputs,
 		WorkingSet:              summary.WorkingSet,
 		Ledger:                  summary.Ledger,
+		DispatchCoordinator:     summary.DispatchCoordinator,
 		Friction:                summary.Friction,
 		GitHubRateLimitUsage:    summary.GitHubRateLimitUsage,
 		JobDetails:              summary.JobDetails,

diff --git a/pkg/cli/audit_summary_build.go b/pkg/cli/audit_summary_build.go
@@ -38,6 +38,7 @@ func buildProcessedAuditRun(run WorkflowRun, results auditAnalysisResults) Proce
 		TokenUsage:              results.tokenUsageSummary,
 		WorkingSet:              results.workingSet,
 		Ledger:                  results.ledger,
+		DispatchCoordinator:     results.dispatchCoordinator,
 		Friction:                results.friction,
 		GitHubRateLimitUsage:    results.rateLimitUsage,
 		JobDetails:              results.jobDetails,
@@ -83,6 +84,7 @@ func buildAuditRunSummary(run WorkflowRun, processedRun ProcessedRun, results au
 			GatewaySteeringEvents:   results.gatewaySteeringEvents,
 			WorkingSet:              results.workingSet,
 			Ledger:                  results.ledger,
+			DispatchCoordinator:     results.dispatchCoordinator,
 			Friction:                results.friction,
 			GitHubRateLimitUsage:    results.rateLimitUsage,
 			JobDetails:              results.jobDetails,