feat: provider extensions and drop claude-code-router mode (#295)

* feat: add ReportOutputProvider for consumer-extended report artifacts

* fix: thread deliverablesSubdir through report assembly

* fix: produce structured report JSON on resume path

* fix: fail loud on structured report output provider errors

* feat: extend checkpoint provider and container DI for consumer-specific backends

* fix: pre-create .shannon overlay mount points on all platforms

* chore: drop claude-code-router mode

* fix: drop 'resets' keyword from spending-cap text patterns

apps/worker/src/temporal/activities.ts

@@ -23,6 +23,7 @@ import type { ResumeAttempt } from '../audit/metrics-tracker.js';
 import type { SessionMetadata } from '../audit/utils.js';
 import type { WorkflowSummary } from '../audit/workflow-logger.js';
 import type { ContainerConfig, ProviderConfig } from '../types/config.js';
+import type { CheckpointContext } from '../interfaces/checkpoint-provider.js';
 import { getContainer, getOrCreateContainer, removeContainer } from '../services/container.js';
 import { classifyErrorForTemporal, PentestError } from '../services/error-handling.js';
 import { ExploitationCheckerService } from '../services/exploitation-checker.js';
@@ -131,6 +132,20 @@ function buildContainerConfig(input: ActivityInput): ContainerConfig {
  */
 async function runAgentActivity(agentName: AgentName, input: ActivityInput): Promise<AgentMetrics> {
   const { repoPath, configPath, pipelineTestingMode = false, workflowId, webUrl } = input;
+
+  // Skip guard: the checkpoint provider decides whether to run the agent.
+  // The default NoOp provider always returns { skip: false }.
+  const skipContainer = getContainer(workflowId) ??
+    getOrCreateContainer(workflowId, buildSessionMetadata(input), buildContainerConfig(input));
+  const decision = await skipContainer.checkpointProvider.shouldSkipAgent(
+    agentName,
+    repoPath,
+    input.deliverablesSubdir ?? DEFAULT_DELIVERABLES_SUBDIR,
+  );
+  if (decision.skip && decision.metrics) {
+    return decision.metrics;
+  }
+
   const startTime = Date.now();
   const attemptNumber = Context.current().info.attempt;
 
@@ -288,7 +303,7 @@ export async function runReportAgent(input: ActivityInput): Promise<AgentMetrics
  * Runs cheap checks before any agent execution:
  * 1. Repository path exists with .git
  * 2. Config file validates (if provided)
- * 3. Credential validation (API key, OAuth, or router mode)
+ * 3. Credential validation (API key, OAuth, Bedrock, or Vertex AI)
  * 4. Target URL reachable from the container
  *
  * NOT using runAgentActivity — preflight doesn't run an agent via the SDK.
@@ -378,11 +393,11 @@ export async function initDeliverableGit(input: ActivityInput): Promise<void> {
  * Assemble the final report by concatenating exploitation evidence files.
  */
 export async function assembleReportActivity(input: ActivityInput): Promise<void> {
-  const { repoPath } = input;
+  const { repoPath, deliverablesSubdir } = input;
   const logger = createActivityLogger();
   logger.info('Assembling deliverables from specialist agents...');
   try {
-    await assembleFinalReport(repoPath, logger);
+    await assembleFinalReport(repoPath, deliverablesSubdir, logger);
   } catch (error) {
     const err = error as Error;
     logger.warn(`Error assembling final report: ${err.message}`);
@@ -393,11 +408,11 @@ export async function assembleReportActivity(input: ActivityInput): Promise<void
  * Inject model metadata into the final report.
  */
 export async function injectReportMetadataActivity(input: ActivityInput): Promise<void> {
-  const { repoPath, sessionId, outputPath } = input;
+  const { repoPath, sessionId, outputPath, deliverablesSubdir } = input;
   const logger = createActivityLogger();
   const effectiveOutputPath = outputPath ? path.join(outputPath, sessionId) : path.join('./workspaces', sessionId);
   try {
-    await injectModelIntoReport(repoPath, effectiveOutputPath, logger);
+    await injectModelIntoReport(repoPath, deliverablesSubdir, effectiveOutputPath, logger);
   } catch (error) {
     const err = error as Error;
     logger.warn(`Error injecting model into report: ${err.message}`);
@@ -585,6 +600,18 @@ export async function restoreGitCheckpoint(
   const logger = createActivityLogger();
   logger.info(`Restoring deliverables to ${checkpointHash}...`);
 
+  // Validate hash exists in this clone before attempting reset
+  try {
+    await executeGitCommandWithRetry(
+      ['git', 'rev-parse', '--verify', checkpointHash],
+      repoPath,
+      'verify checkpoint hash exists'
+    );
+  } catch {
+    logger.info(`Checkpoint hash not found in clone, skipping git reset: ${checkpointHash}`);
+    return;
+  }
+
   await executeGitCommandWithRetry(
     ['git', 'reset', '--hard', checkpointHash],
     deliverablesPath,
@@ -736,5 +763,42 @@ export async function saveCheckpoint(
 ): Promise<void> {
   const container = getContainer(input.workflowId);
   if (!container?.checkpointProvider) return;
-  return container.checkpointProvider.onAgentComplete(agentName, phase, state);
+
+  const context: CheckpointContext = {
+    repoPath: input.repoPath,
+    sessionId: input.sessionId,
+    deliverablesSubdir: input.deliverablesSubdir ?? DEFAULT_DELIVERABLES_SUBDIR,
+    ...(input.outputPath !== undefined && { outputPath: input.outputPath }),
+  };
+
+  return container.checkpointProvider.onAgentComplete(agentName, phase, state, context);
+}
+
+/**
+ * Generate an optional additional output alongside the assembled markdown report.
+ *
+ * Delegates to the ReportOutputProvider registered in the DI container.
+ * Default: no-op. Consumers can override this activity at the worker level
+ * to emit derived outputs from the final report.
+ */
+export async function generateReportOutputActivity(input: ActivityInput): Promise<void> {
+  const container = getContainer(input.workflowId);
+  if (!container?.reportOutputProvider) return;
+
+  const logger = createActivityLogger();
+
+  // Resolve promptDir against the worker root so providers are cwd-independent.
+  const resolvedInput: ActivityInput = {
+    ...input,
+    ...(input.promptDir !== undefined && {
+      promptDir: path.isAbsolute(input.promptDir)
+        ? input.promptDir
+        : path.resolve(process.env.SHANNON_WORKER_ROOT ?? process.cwd(), input.promptDir),
+    }),
+  };
+
+  const result = await container.reportOutputProvider.generate(resolvedInput, logger);
+  if (result.outputPath) {
+    logger.info(`Report output written to ${result.outputPath}`);
+  }
 }

apps/worker/src/temporal/shared.ts

@@ -25,10 +25,10 @@ export interface PipelineInput {
   deliverablesSubdir?: string; // Override deliverables path (default: '.shannon/deliverables')
   auditDir?: string; // Override audit log directory (default: './workspaces')
   promptDir?: string; // Override prompt template directory
-  sastSarifPath?: string; // Path to SARIF file (gates SAST-enhanced mode)
+  sastSarifPath?: string; // Optional path for consumer-supplied findings input
   checkpointsEnabled?: boolean; // Enable checkpoint activities (default: false)
   skipGitCheck?: boolean; // Skip .git directory validation in preflight (e.g. when .git is removed after clone)
-  providerConfig?: ProviderConfig; // LLM provider configuration (Bedrock, Vertex, LiteLLM, etc.)
+  providerConfig?: ProviderConfig; // LLM provider configuration (Bedrock, Vertex, etc.)
 }
 
 export interface ResumeState {

apps/worker/src/temporal/workflows.ts

@@ -322,30 +322,14 @@ export async function pentestPipeline(input: PipelineInput): Promise<PipelineSta
     ];
   }
 
-  // Aggregate results from settled pipeline promises into workflow state
+  // Aggregate errors from settled pipeline promises.
+  // Metrics and completedAgents are updated incrementally inside runVulnExploitPipeline
+  // so that getProgress queries reflect real-time status during execution.
   function aggregatePipelineResults(results: PromiseSettledResult<VulnExploitPipelineResult>[]): void {
     const failedPipelines: string[] = [];
 
     for (const result of results) {
-      if (result.status === 'fulfilled') {
-        const { vulnType, vulnMetrics, exploitMetrics } = result.value;
-
-        const vulnAgentName = `${vulnType}-vuln`;
-        if (vulnMetrics) {
-          state.agentMetrics[vulnAgentName] = vulnMetrics;
-          state.completedAgents.push(vulnAgentName);
-        } else if (shouldSkip(vulnAgentName)) {
-          state.completedAgents.push(vulnAgentName);
-        }
-
-        const exploitAgentName = `${vulnType}-exploit`;
-        if (exploitMetrics) {
-          state.agentMetrics[exploitAgentName] = exploitMetrics;
-          state.completedAgents.push(exploitAgentName);
-        } else if (shouldSkip(exploitAgentName)) {
-          state.completedAgents.push(exploitAgentName);
-        }
-      } else {
+      if (result.status === 'rejected') {
         const errorMsg = result.reason instanceof Error ? result.reason.message : String(result.reason);
         failedPipelines.push(errorMsg);
       }
@@ -432,14 +416,17 @@ export async function pentestPipeline(input: PipelineInput): Promise<PipelineSta
       let vulnMetrics: AgentMetrics | null = null;
       if (!shouldSkip(vulnAgentName)) {
         vulnMetrics = await runVulnAgent();
+        state.agentMetrics[vulnAgentName] = vulnMetrics;
+        state.completedAgents.push(vulnAgentName);
         if (input.checkpointsEnabled) {
           await a.saveCheckpoint(activityInput, vulnAgentName, 'vulnerability-analysis', state);
         }
       } else {
         log.info(`Skipping ${vulnAgentName} (already complete)`);
+        state.completedAgents.push(vulnAgentName);
       }
 
-      // 1.5. Merge external findings (SAST, SCA, etc.) into exploitation queue
+      // 1.5. Merge external findings from consumer provider into exploitation queue
       await a.mergeFindingsIntoQueue(activityInput, vulnType);
 
       // 2. Check exploitation queue for actionable findings
@@ -450,11 +437,14 @@ export async function pentestPipeline(input: PipelineInput): Promise<PipelineSta
       if (decision.shouldExploit) {
         if (!shouldSkip(exploitAgentName)) {
           exploitMetrics = await runExploitAgent();
+          state.agentMetrics[exploitAgentName] = exploitMetrics;
+          state.completedAgents.push(exploitAgentName);
           if (input.checkpointsEnabled) {
             await a.saveCheckpoint(activityInput, exploitAgentName, 'exploitation', state);
           }
         } else {
           log.info(`Skipping ${exploitAgentName} (already complete)`);
+          state.completedAgents.push(exploitAgentName);
         }
       }
 
@@ -516,6 +506,13 @@ export async function pentestPipeline(input: PipelineInput): Promise<PipelineSta
       state.completedAgents.push('report');
     }
 
+    // Runs after the skip gate so consumer providers still execute on resume.
+    await a.generateReportOutputActivity(activityInput);
+
+    if (input.checkpointsEnabled) {
+      await a.saveCheckpoint(activityInput, 'report-output', 'reporting', state);
+    }
+
     state.status = 'completed';
     state.currentPhase = null;
     state.currentAgent = null;