feat: Shannon 3.0 Agentic SAST (#433)

* feat(worker): add agentic static analysis

Add the ten-stage Agentic SAST pipeline, confined repository tools, model runtime, prompt templates, and SARIF export.

Make retries, repair sessions, reduced coverage, usage accounting, and model-output drift durable across Temporal replay and resume. Keep retry diagnostics in their actionable closed vocabulary. Package the Mantis-derived license material with the prompts that require it.

* feat(worker): deduplicate static and runtime findings before exploitation

Parse Agentic SAST SARIF into typed observations, enrich and route those observations, and reconcile them with pentest findings before exploitation.

Publish deterministic exploitation queues with stable lineage, exact-path Git commits, retry-safe manifests, named drop reasons, and confined task formation. Reject duplicate producer IDs before commit and adopt either legal provenance shape after a lost acknowledgement.

* feat(config)!: replace vuln_classes with agentic_sast

Wire Agentic SAST and reconciliation into the main pipeline, persist their durable state, and add the Miscellaneous finding and exploitation lane.

Make scan completion, cancellation, partial outcomes, resume identity, and report recovery use the integrated final workflow contract. Introduce the atomic finalization, ordering, renumbering, compaction, and output services that workflow calls. Keep completed Miscellaneous work and report drafts idempotent across resume, preserve public main's default-on exploit SARIF behavior, and describe stage-fallback candidates without claiming they were exported.

BREAKING CHANGE: `vuln_classes` has been removed. Configs containing it now fail validation, and all five core pentest classes run on every scan.

Workspaces created by Shannon 2.x cannot be resumed. Finish or discard in-flight scans before upgrading, then start a new workspace name.

* perf: overlap static analysis and the Miscellaneous lane with the pentest

Run Agentic SAST alongside vulnerability analysis and run Miscellaneous exploitation alongside the specialist exploitation lanes.

Keep reconciliation dependent on the completed static-analysis result while preserving parallel work everywhere that has no data dependency.

* feat(cli)!: default the scan target and add a JSON error contract

List local scans, resolve the active or most recent workspace automatically, and make logs, status, and stop use one canonical scan identity.

Add stable machine-readable failures, richer status output, explicit help errors, and seven-day Temporal retention. Treat absent Temporal pending-activity failures as absent whether the decoder represents them as `null` or missing.

BREAKING CHANGE: `status --json` now returns a fixed `failureMessage`. Read `partialReasons`, `agenticSast`, and `workflow.log` for diagnostic detail.

* feat(logging): trace tool calls and write a log per agent

Record complete tool-call arguments in the workflow log and project each agent's events into its own durable log.

Add agent listing and agent-specific log tailing while preserving byte-exact output and draining log handles before
activities return.

* feat(worker): standardize severity and reporting guidance in exploit prompts

Give every exploit agent the same status, confidence, severity-reasoning, report-writing, credential-handling, and
scope contract.

Apply the same task-formation and SAST-enrichment procedure to the Miscellaneous lane.

* feat(worker): disclose scan coverage and make reporting auditable

Build on the retry-safe finalization foundation to preserve correct identities, source locations, scan dates,
partial-coverage limitations, and consistent report JSON, Markdown, SARIF, and PDF output.

Report Agentic SAST, reconciliation wall-clock time, stage usage, retry spend, and background work without duplicate
or hardcoded totals. Keep report findings canonical, drop cross-class restatements, name enrichment losses, and render
the executive-summary narrative in the PDF.

* chore(license): attribute Mantis and Pi and refresh the docs

Add the final Mantis and Pi notices, license copies, acknowledgements, and residual copyright updates.

Update the README, maintained documentation, contributor guidance, and hand-maintained mirrors to describe Agentic
SAST, reconciliation, the Miscellaneous lane, current CLI behavior, and the final release contract. Correct stale
workspace and container guidance and annotate long-standing internals for maintainers.

* fix(logging): treat a slash as a word separator in agent labels

* feat(cli)!: rebuild scan status around model work

- show Capella stages beneath the concurrent Agentic SAST phase
- attach reconciliation time to the class row it feeds
- hide completed bookkeeping and the duplicate miscellaneous wrapper
- carry validated child-workflow progress into durable parent state
- derive the terminal tree and status JSON from the same phase shape

BREAKING CHANGE: `status --json` replaces phase `parallel` with `children` and `meta`, adds phase summaries and notes plus agent attachment fields, and removes the `analysis-engines` and `operational-work` phases.

* fix(report): drop the empty Critical Findings section from the PDF summary

* fix(sast): align Capella export with the submit-time code-path contract

The export gate required every code_paths entry to be file:line, but submit only
requires the primary sink to be file:line and accepts bare trace steps. A single
malformed trace step therefore dropped an otherwise-valid finding at export.

- add isValidPrimaryCodePath as the one shared primary-sink contract
- validate only the primary at export; buildResult already drops unusable steps
- route the submit-time validator through the same helper so the two cannot drift

* feat(sast): tolerate hygiene-only Capella reductions instead of going partial

A reduction only makes a run partial when it loses real coverage or a whole
finding. Malformed model output, salvaged turn-limit work, and rejected duplicate
verdicts are recorded as evidence but no longer flip the run to partial.

- add reductionIsTolerable: partial only when genuine-loss counts are nonzero
- drive runCapella's partial reasons and display coverage off non-tolerable ones
- keep every reduction in agenticSast.reductions so nothing is lost as evidence

* feat(logging): record the provider reason for a failed agent turn

A failed provider turn collapsed to AGENT_EXECUTION_FAILED/unknown with the
underlying reason discarded, so a model-side rejection or safeguard was
indistinguishable from a transport fault in the error log.

- add safeProviderTurnDetails: write bounded, non-sensitive fields (provider,
  model, responseId, stop reason, tool-in-flight, category, retryable) to error.log
- gate a sanitized errorMessage snippet behind SHANNON_DEBUG_PROVIDER_ERRORS, off by default
- forward SHANNON_DEBUG_PROVIDER_ERRORS from the CLI into the worker container

* fix(cli): keep shannon logs tailing through a Temporal blip

- End the interactive tail on the log's own terminal marker or Ctrl-C, so a
  transient Temporal outage no longer aborts the command with exit 1.
- Rebuild the memoized Temporal client after a failed poll: a wedged gRPC
  channel was cached forever, so "retrying…" could never reconnect.
- Keep start --follow (CI) bounded — a genuinely dead Temporal still fails
  the run instead of hanging.

* fix(worker): correct PDF finding reporting

- Render OWASP category, authentication state, and remediation
- Omit the redundant per-finding exploited status
- Preserve canonical category and field ordering across report modes
- Continue Proof of Impact numbering across embedded code blocks
- Wrap long PDF code lines without changing canonical report content

* fix: attribute a reconciliation failure to exploitation only

- Stop marking a class's vulnerability-analysis agent failed when that agent
  succeeded and only reconciliation failed; the status tree now renders the
  analysis row completed and the exploitation row failed
- Consume the worker's failedReconciliations signal in the CLI, which the
  mirrored PipelineState already declared but never read
- Correct the class_reconciliation_failed message, which claimed the class's
  analysis results were still in the report when the class is excluded from it

* fix(pi): give each task sub-session its own resource loader to prevent stale extension ctx

* fix(prompts): scope exploit agents to in-band proof, mark OOB-only findings blocked

* fix(cli): reject a shell credential that shadows a gateway config.toml key

* fix(cli): make scan shutdown verifiable

- preselect and persist workflow identity before worker launch
- cancel first, then verify bounded Temporal termination
- reconcile Docker workers with Temporal open workflows
- fail closed on stale images and unavailable lifecycle state
- mark cancellation only after confirmed shutdown

* feat(cli): prompt for setup on a bare npx invocation with no credentials

* fix(cli): don't blame anthropic when no credentials are configured at all

* chore(release): bump beta base version to 3.0.0

* feat(cli): show a 'start your first scan' box in help on a TTY

* docs: refresh README and platform overview for Shannon 3.0

- lead with the 3.0 launch note and rewrite key capabilities around security
  code analysis, the rebuilt terminal experience, native CI/CD, and PDF/SARIF
- recast the editions table as Shannon Open Source against the Keygraph
  Enterprise Platform, stating open source is not a trial edition
- rewrite the platform overview around exhaustive agentic SAST, canonical
  findings, automated remediation, targeted verification, and governance
- add five product screenshots under assets/keygraph-platform/, referenced
  relative to docs/

* docs: add the Shannon naming section and swap in the 3.0 demo GIF

- explain the Claude Shannon information-theory origin under "What is Shannon?"
- point "Shannon in Action" at the 3.0 recording in assets/Shannon3GIF.gif

Both taken from the README half of #438.

* docs: document CI/CD integrations and the reconciled analysis pipeline

- add a CI/CD Integrations section covering the official GitHub Action and
  GitLab component, pipeline artifacts, and exploit-only severity gates
- redraw the architecture section as a Mermaid flow: agentic code analysis
  and recon feed finding reconciliation, then exploitation and reporting
- describe open-source code analysis as a multi-stage agentic workflow and
  reserve parsed-code CPGs and exhaustive verification for Enterprise
- sharpen the privacy wording: results stay local, but model requests carry
  source context to whichever endpoint you configure
- drop the "not recommended" framing on local models and add a section on
  why Shannon complements rather than replaces human pentesters
- regenerate llms-full.txt from the updated README and docs

* docs: add the Photoview benchmark across three models

- Add a "Shannon in Action" table for Photoview 2.4.0 runs on
  DeepSeek v4 Flash, Grok 4.6, and Claude Opus 5, each linking its
  PDF report and SARIF output
- Store the per-model reports under benchmark/
- Link the (forthcoming) benchmark writeup from the section intro

* docs: add the Shannon vs XBOW/Aikido Photoview benchmark writeup

- Add docs/shannon-xbow-aikido-benchmark.md with methodology, per-model
  cost/coverage tables, and links to each model's report and SARIF
- Link the writeup from the README "Shannon in Action" section

* docs: link the benchmark announcement discussion from the README

* fix(readme): restore theme-aware banner, badge, and buttons

* feat!: trigger the Shannon 3.0 major release

---------

Co-authored-by: ezl-keygraph <ezhil@keygraph.io>

apps/worker/src/temporal/shared.ts

@@ -1,16 +1,97 @@
-import { defineQuery } from '@temporalio/workflow';
+import { defineQuery, defineSignal } from '@temporalio/workflow';
 
 export type { AgentMetrics } from '../types/metrics.js';
 
-import type { DistributedConfig, VulnClass } from '../types/config.js';
+import type {
+  AgenticSastReduction,
+  CapellaFailurePoint,
+  CapellaRecoveredFailure,
+  CapellaStage,
+  SarifRef,
+} from '../ai/sast/types.js';
+import type { VulnClass } from '../types/config.js';
 import type { ErrorCode } from '../types/errors.js';
 import type { AgentMetrics } from '../types/metrics.js';
+import type { ReconciliationClass } from '../types/reconciliation.js';
+import type {
+  MiscellaneousOutcome,
+  PartialReasonView,
+  ReportProgress,
+  ReportSarifDisposition,
+  StoredPdfProvenance,
+} from '../types/run-state.js';
+
+/**
+ * The serializable slice of Capella's configuration passed across the Temporal workflow
+ * boundary into the child workflow input. Everything the workflow needs from the parsed
+ * config or the model spec must be flattened into plain data here; the workflow sandbox
+ * cannot carry functions or class instances across that boundary.
+ */
+export interface AgenticSastInput {
+  readonly codePathAvoids: readonly string[];
+  readonly codePathFocus: readonly string[];
+  readonly modelSpec: string;
+  readonly capellaFormatVersion: string;
+  readonly promptSetVersion: string;
+}
+
+/**
+ * The agentic SAST lifecycle as seen from the pentest workflow: not configured, running as a
+ * child workflow, or one of two terminal outcomes. This is what the live `getProgress` query
+ * and the terminal `PipelineState` both report, so a caller never needs to inspect the Capella
+ * child workflow's own result type directly.
+ */
+export type AgenticSastState =
+  | { readonly status: 'disabled' }
+  | { readonly status: 'running'; readonly startedAt: number }
+  | {
+      readonly status: 'succeeded';
+      readonly findingCount: number;
+      readonly sarifSha256: string;
+      readonly coverage: 'complete' | 'reduced';
+      readonly warnings: readonly string[];
+      readonly durationMs: number;
+      readonly reductions?: readonly AgenticSastReduction[];
+      readonly recoveredFailure?: CapellaRecoveredFailure;
+    }
+  | {
+      readonly status: 'failed';
+      readonly failedStage: CapellaFailurePoint;
+      /** Reader-facing name of `failedStage`, projected once so no surface renders the slug. */
+      readonly failedStageLabel: string;
+      readonly error: string;
+      /** Bounded machine code preserved from the failing Capella activity, when one crossed the child. */
+      readonly errorCode?: string;
+      readonly completedStages: readonly CapellaStage[];
+      readonly warnings: readonly string[];
+      readonly durationMs: number;
+    };
+
+export type OperationalStageStatus = 'pending' | 'running' | 'completed' | 'failed' | 'skipped';
+
+export interface OperationalStageState {
+  readonly key: string;
+  readonly label: string;
+  readonly status: OperationalStageStatus;
+  readonly startedAt?: number;
+  readonly durationMs?: number;
+  readonly error?: string;
+}
+
+export interface OperationalMetrics extends AgentMetrics {
+  readonly usageComplete?: boolean;
+}
+
+/** A degradation the scan recorded and continued past, kept for the terminal summary log rather than for control flow. */
+export interface NonFatalFailure {
+  readonly phase: string;
+  readonly error: string;
+}
 
 export interface PipelineInput {
   webUrl: string;
   repoPath: string;
   configPath?: string;
-  outputPath?: string;
   pipelineTestingMode?: boolean;
   workflowId?: string; // Used for audit correlation
   sessionId?: string; // Workspace directory name (distinct from workflowId for named workspaces)
@@ -19,44 +100,114 @@ export interface PipelineInput {
 
   // Config fields — serializable, flow through to ActivityInput → getOrCreateContainer()
   configYAML?: string; // Raw YAML string (parsed in activity, not workflow — workflow sandbox can't use Node.js)
-  configData?: DistributedConfig; // Pre-parsed config (bypasses file loading)
   deliverablesSubdir?: string; // Override deliverables path (default: '.shannon/deliverables')
   auditDir?: string; // Override audit log directory (default: './workspaces')
   promptDir?: string; // Override prompt template directory
-  sastSarifPath?: string; // Optional path for consumer-supplied findings input
+  agenticSast?: AgenticSastInput;
+  sastSarif?: SarifRef;
+  customerOutputPath?: string; // Stable mounted path for final customer copies only
   checkpointsEnabled?: boolean; // Enable checkpoint activities (default: false)
-  vulnClasses?: VulnClass[]; // omitted = all five
   exploit?: boolean; // false skips the exploitation phase
 }
 
+/** What `loadResumeState` reconstructs from a prior workspace: independently verified, never assumed from session.json alone. */
 export interface ResumeState {
   workspaceName: string;
   originalUrl: string;
   completedAgents: string[];
   checkpointHash: string;
   originalWorkflowId: string;
+  expectedAgents: string[];
+  participatingClasses: ReconciliationClass[];
+  exploit: boolean;
+  reportProgress?: ReportProgress;
+  miscellaneousOutcome?: MiscellaneousOutcome;
+}
+
+/** The narrow view of the durable scan-state record the workflow needs to keep its own queryable state in sync. */
+export interface DurableStateSummary {
+  readonly exploit: boolean;
+  readonly expectedAgents: readonly string[];
+  readonly participatingClasses: readonly ReconciliationClass[];
+  readonly reportStage: ReportProgress['stage'] | 'uninitialized';
+  readonly miscellaneousOutcome?: MiscellaneousOutcome;
+}
+
+/** Common result shape for the deterministic report-processing activities (renumber, compaction). */
+export interface ReconciliationActivityResult {
+  readonly vulnerabilityClass?: ReconciliationClass;
+  readonly skipped: boolean;
+  readonly changedPathCount: number;
+  readonly checkpoint?: string;
+  readonly alreadyCommitted?: boolean;
+}
+
+export interface FinalizeReportActivityResult {
+  readonly checkpoint: string;
+  readonly manifestSha256: string;
+  readonly changedPathCount: number;
+  readonly alreadyCommitted: boolean;
+  /** Adopted-or-produced SARIF disposition from the committed finalization manifest. */
+  readonly sarifDisposition: ReportSarifDisposition;
+  readonly pdfGenerated: boolean;
+  /** Verified provenance for the current PDF bytes, or null when no trustworthy PDF exists. */
+  readonly pdfProvenance: StoredPdfProvenance | null;
+  readonly warningCount: number;
+}
+
+export interface AssembleReportActivityResult {
+  /** Classes whose findings could not be included in the assembled report inputs. */
+  readonly failedClasses: readonly ReconciliationClass[];
+}
+
+export interface SurfaceReportActivityResult {
+  readonly surfaced: readonly string[];
+  readonly removedStale: readonly string[];
+  readonly warningCount: number;
 }
 
 export interface PipelineSummary {
   totalCostUsd: number;
   totalDurationMs: number; // Wall-clock time (end - start)
   totalTurns: number;
+  /** Total resolved agents: those that ran plus those that were skipped. */
   agentCount: number;
+  /** False when operational (Capella/reconciliation) spend is known to be incomplete. */
+  usageAccountingComplete: boolean;
 }
 
+/**
+ * The workflow's whole queryable and terminal state. The CLI cannot import this package, so
+ * `apps/cli/src/scan/pipeline.ts` mirrors this shape (along with AgentMetrics and the
+ * activity-name-to-agent map) by hand; a field added, renamed, or removed here needs the same
+ * change there, or the CLI's status rendering silently falls out of sync with a running scan.
+ */
 export interface PipelineState {
   status: 'running' | 'completed' | 'failed' | 'cancelled' | 'partial';
   currentPhase: string | null;
   currentAgent: string | null;
+  /** Agents that actually ran. Mutually exclusive from `skippedAgents`. */
   completedAgents: string[];
+  /** Expected agents that never ran because their class had nothing to exploit. */
+  skippedAgents: string[];
+  expectedAgents: string[];
+  participatingClasses: ReconciliationClass[];
   // Vuln classes whose pipeline failed while at least one other succeeded. Drives the
   // partial terminal status so a crashed class isn't reported as if it fully passed.
   failedPipelines: { vulnType: VulnClass; error: string }[];
+  failedReconciliations: { vulnerabilityClass: ReconciliationClass; error: string }[];
   failedAgent: string | null;
   error: string | null;
   errorCode?: ErrorCode;
   startTime: number;
   agentMetrics: Record<string, AgentMetrics>;
+  operationalMetrics: Record<string, OperationalMetrics>;
+  operationalStages: Record<string, OperationalStageState>;
+  agenticSast: AgenticSastState;
+  nonFatalFailures: NonFatalFailure[];
+  /** Ordered durable degradation reasons with derived safe messages; empty for a full success. */
+  partialReasons: PartialReasonView[];
+  reportProgress?: ReportProgress;
   summary: PipelineSummary | null;
 }
 
@@ -79,3 +230,20 @@ export interface VulnExploitPipelineResult {
 }
 
 export const getProgress = defineQuery<PipelineProgress>('getProgress');
+
+/**
+ * One Capella stage transition, reported by the SAST child workflow to its parent.
+ *
+ * Capella runs as a child workflow, so its activities never appear in the parent's
+ * pending activities and the CLI cannot observe them. This signal is how per-stage
+ * progress reaches the parent's durable `operationalStages`, which is what both the
+ * live `getProgress` query and the terminal result render from.
+ */
+export interface CapellaStageProgress {
+  readonly stage: CapellaStage;
+  readonly status: 'running' | 'completed' | 'failed';
+  readonly startedAt: number;
+  readonly durationMs?: number;
+}
+
+export const capellaStageProgress = defineSignal<[CapellaStageProgress]>('capellaStageProgress');