gsdd-cli 0.19.3 → 0.21.0

package/README.md

@@ -346,6 +346,7 @@ Workflows are agent skills or commands, not plain shell utilities. How you invok
 | `npx -y gsdd-cli init [--tools <platform>]` | Set up `.planning/`, generate skills/adapters |
 | `npx -y gsdd-cli update [--tools <platform>] [--templates]` | Regenerate skills/adapters and refresh the repo-local helper runtime; `--templates` refreshes `.planning/templates/` and role contracts |
 | `npx -y gsdd-cli health [--json]` | Check workspace integrity and generated-surface freshness (healthy/degraded/broken) |
+| `npx -y gsdd-cli ui-proof validate <path> [--claim <public\|publication\|tracked\|delivery\|release>]` | Validate UI proof bundle metadata without requiring browser tooling; use `--claim` only when validating that stronger proof use |
 | `npx -y gsdd-cli file-op <copy\|delete\|regex-sub>` | Run deterministic workspace-confined file copy, delete, and regex substitution |
 | `npx -y gsdd-cli find-phase [N]` | Show phase info as JSON (for agent consumption) |
 | `npx -y gsdd-cli phase-status <N> <status>` | Update a single ROADMAP phase status through the status-aware helper |

package/agents/executor.md

@@ -209,6 +209,9 @@ Before reporting a task complete:
 - if a UI change is involved, verify the relevant rendering path
 - if an API change is involved, hit the endpoint or targeted integration path
 - A task is not complete because code was written. It is complete when the intended verification path actually passes.
+
+### UI Proof Execution
+If the plan defines UI proof slots, record observed proof against the exact claim, route/state, observation, evidence kind, artifact path or manual step, privacy metadata, result, and claim limit before claiming task completion. Artifact metadata must include `visibility`, `retention`, `sensitivity`, and `safe_to_publish`; raw screenshots, traces, videos, DOM snapshots, and reports are local-only/unsafe by default and cannot back public, tracked, delivery, release, or publication proof claims. Use `gsdd ui-proof validate <path>` or `gsdd health` when a bundle exists. Artifact count, source comments, AST/cAST findings, semantic search, and Semble-like retrieval are not proof. Missing or weakly linked evidence must be recorded as proof debt, waiver, deferment, or reduced claim language rather than satisfied proof.
 </execution_loop>
 
 <checkpoint_protocol>

package/agents/planner.md

@@ -153,6 +153,14 @@ Any checkpoint must be justified by the task itself, not by planner caution or h
 Any plan containing `checkpoint:*` must set `autonomous: false`.
 </task_contract>
 
+<ui_proof_planning>
+For UI-sensitive work, plan proof slots that can later be matched exactly to claim, route/state, observation, evidence kind, artifact path or manual step, privacy metadata, result, and claim limit. Use only the stable evidence kinds `code`, `test`, `runtime`, `delivery`, and `human`.
+
+Require observed artifacts to carry `visibility`, `retention`, `sensitivity`, and `safe_to_publish`; when a planned slot is meant to support public, publication, tracked, delivery, or release proof, say to validate the observed bundle with `gsdd ui-proof validate <path> --claim <...>`. `gsdd ui-proof validate`/`gsdd health` must catch invalid bundle metadata when present.
+
+Do not let source annotations, AST/cAST findings, semantic search, comments, or Semble-like retrieval satisfy proof slots; they are discovery hints only. Human acceptance can narrow or waive a claim and record proof debt, but it must not turn missing or mismatched non-human evidence into `satisfied` proof.
+</ui_proof_planning>
+
 <dependency_graph_example>
 Example dependency graph:
 
@@ -184,7 +192,7 @@ Wave rule:
 Write one or more `PLAN.md` files to the phase directory.
 
 Keep the current GSDD schema exactly:
-- frontmatter keys: `phase`, `plan`, `type`, `wave`, `runtime`, `assurance`, `depends_on`, `files-modified`, `autonomous`, `requirements`, `non_goals`, `hard_boundaries`, `escalation_triggers`, `approval_gates`, `anti_regression_targets`, `known_unknowns`, `high_leverage_surfaces`, `second_pass_required`, `closure_claim_limit`, `parallelism_budget`, `leverage`, `must_haves`
+- frontmatter keys: `phase`, `plan`, `type`, `wave`, `runtime`, `assurance`, `depends_on`, `files-modified`, `autonomous`, `requirements`, `non_goals`, `hard_boundaries`, `escalation_triggers`, `approval_gates`, `anti_regression_targets`, `known_unknowns`, `ui_proof_slots`, `no_ui_proof_rationale`, `high_leverage_surfaces`, `second_pass_required`, `closure_claim_limit`, `parallelism_budget`, `leverage`, `must_haves`
 - typed tasks with `files`, `action`, `verify`, and `done`
 
 Typed frontmatter example:
@@ -215,6 +223,8 @@ anti_regression_targets:
   - Existing session middleware behavior remains unchanged for already-supported routes.
 known_unknowns:
   - Exact copy wording for auth errors may still need product confirmation.
+ui_proof_slots: []
+no_ui_proof_rationale: Not UI-sensitive; scoped work does not claim a visible UI outcome.
 high_leverage_surfaces: []
 second_pass_required: false
 closure_claim_limit: Do not claim phase completion until verification satisfies the evidence contract for the scoped truths.

package/agents/verifier.md

@@ -123,6 +123,8 @@ Do not return a flat symptom list when the same underlying breakage explains mul
 
 Visual correctness, live interaction quality, and some external integrations still need explicit human checks.
 
+For UI proof slots, fail closed unless observed proof is matched to the exact claim, route/state, observation, evidence kind, artifact path or manual step, privacy metadata, result, and claim limit. Artifact metadata must include `visibility`, `retention`, `sensitivity`, and `safe_to_publish`; local-only or unsafe artifacts cannot back public, tracked, delivery, release, or publication proof claims, and `gsdd ui-proof validate`/`gsdd health` metadata failures block the stronger proof claim. Screenshots, traces, reports, Gherkin, a11y scans, E2E outputs, manual notes, source annotations, AST/cAST findings, semantic search, comments, and Semble-like retrieval do not satisfy proof by existence alone. Human acceptance records risk, waiver, deferment, proof debt, or a narrowed claim; it does not upgrade missing or mismatched non-human proof to `satisfied`.
+
 ## Step 9: Determine overall status
 
 - `passed` when all programmatic checks pass and no human-only checks remain

package/bin/gsdd.mjs

@@ -19,6 +19,7 @@ import { cmdFileOp } from './lib/file-ops.mjs';
 import { createCmdHealth } from './lib/health.mjs';
 import { cmdLifecyclePreflight } from './lib/lifecycle-preflight.mjs';
 import { cmdSessionFingerprint } from './lib/session-fingerprint.mjs';
+import { cmdUiProof } from './lib/ui-proof.mjs';
 import { resolveWorkspaceContext } from './lib/workspace-root.mjs';
 
 const __filename = fileURLToPath(import.meta.url);
@@ -107,6 +108,7 @@ const COMMANDS = {
   'file-op': cmdFileOp,
   'lifecycle-preflight': cmdLifecyclePreflight,
   'session-fingerprint': cmdSessionFingerprint,
+  'ui-proof': cmdUiProof,
   'find-phase': cmdFindPhase,
   'phase-status': cmdPhaseStatus,
   verify: cmdVerify,
@@ -132,8 +134,5 @@ async function runCli(cliCommand = command, ...cliArgs) {
   await COMMANDS[cliCommand](...normalizedArgs);
 }
 
-if (IS_MAIN) {
-  await runCli();
-}
-
-export { cmdHelp, cmdInit, cmdUpdate, cmdModels, cmdHealth, cmdFileOp, cmdLifecyclePreflight, cmdSessionFingerprint, cmdFindPhase, cmdPhaseStatus, cmdVerify, cmdScaffold, runCli, FRAMEWORK_VERSION, createCliContext };
+if (IS_MAIN) await runCli();
+export { cmdHelp, cmdInit, cmdUpdate, cmdModels, cmdHealth, cmdFileOp, cmdLifecyclePreflight, cmdSessionFingerprint, cmdUiProof, cmdFindPhase, cmdPhaseStatus, cmdVerify, cmdScaffold, runCli, FRAMEWORK_VERSION, createCliContext };

package/bin/lib/health.mjs

@@ -4,12 +4,13 @@
 // evaluate once, so CWD must be computed inside function bodies.
 
 import { existsSync, readFileSync, readdirSync } from 'fs';
-import { join } from 'path';
+import { join, relative } from 'path';
 import { readManifest, detectModifications } from './manifest.mjs';
 import { output } from './cli-utils.mjs';
 import { runTruthChecks, TRUTH_CHECK_IDS } from './health-truth.mjs';
 import { evaluateLifecycleState } from './lifecycle-state.mjs';
 import { evaluateRuntimeFreshness } from './runtime-freshness.mjs';
+import { findUiProofBundleFiles, readUiProofBundleFile, validateUiProofBundle } from './ui-proof.mjs';
 import { resolveWorkspaceContext } from './workspace-root.mjs';
 
 /**
@@ -31,7 +32,7 @@ export function createCmdHealth(ctx) {
     }
     const cwd = workspaceRoot;
     const frameworkSourceMode = isFrameworkSourceRepo(cwd);
-    const healthCheckIds = ['E1', 'E2', 'E3', 'E4', 'E5', 'E6', 'E7', 'E8', 'E9', 'W1', 'W2', 'W3', 'W4', 'W5', 'W6', ...TRUTH_CHECK_IDS, 'I1', 'I2', 'I3'];
+    const healthCheckIds = ['E1', 'E2', 'E3', 'E4', 'E5', 'E6', 'E7', 'E8', 'E9', 'E10', 'W1', 'W2', 'W3', 'W4', 'W5', 'W6', ...TRUTH_CHECK_IDS, 'I1', 'I2', 'I3'];
 
     // Pre-init guard
     if (!existsSync(join(planningDir, 'config.json'))) {
@@ -123,7 +124,7 @@ export function createCmdHealth(ctx) {
       }
 
       // E8: critical root template files missing
-      const requiredRootFiles = ['spec.md', 'roadmap.md', 'auth-matrix.md'];
+      const requiredRootFiles = ['spec.md', 'roadmap.md', 'auth-matrix.md', 'ui-proof.md'];
       const missingRoot = requiredRootFiles.filter((f) => !existsSync(join(templatesDir, f)));
       if (missingRoot.length > 0) {
         errors.push({ id: 'E8', severity: 'ERROR', message: `.planning/templates/ missing critical root files: ${missingRoot.join(', ')}`, fix: 'Run `npx -y gsdd-cli update --templates`' });
@@ -140,6 +141,23 @@ export function createCmdHealth(ctx) {
       }
     }
 
+    // E10: known UI proof bundles must satisfy deterministic metadata/privacy validation.
+    for (const bundlePath of findUiProofBundleFiles(planningDir)) {
+      const relativePath = relative(cwd, bundlePath).replace(/\\/g, '/');
+      const parsed = readUiProofBundleFile(bundlePath);
+      const validation = parsed.errors.length > 0
+        ? { valid: false, errors: parsed.errors }
+        : validateUiProofBundle(parsed.bundle);
+      if (!validation.valid) {
+        errors.push({
+          id: 'E10',
+          severity: 'ERROR',
+          message: `${relativePath} has invalid UI proof metadata (${validation.errors.map((entry) => entry.code).join(', ')})`,
+          fix: 'Run `gsdd ui-proof validate <path>` and add required privacy metadata, claim limits, fixed evidence kinds, observation artifact references, and safe-to-publish handling.',
+        });
+      }
+    }
+
     // --- WARNING checks ---
 
     // W1: generation-manifest.json missing

package/bin/lib/init-runtime.mjs

@@ -186,7 +186,12 @@ Commands:
   phase-status <N> <status>   Update ROADMAP.md phase status ([ ] / [-] / [x])
   lifecycle-preflight <surface> [phase]
                               Inspect deterministic lifecycle gate results for a workflow surface
-  session-fingerprint write    Rebaseline planning-state drift after reviewing changed planning files
+  session-fingerprint write [--allow-changed <ROADMAP.md,SPEC.md,config.json>]
+                              Rebaseline planning-state drift after reviewing changed planning files
+  ui-proof validate <path> [--claim <public|publication|tracked|delivery|release>]
+                              Validate UI proof metadata; use --claim for stronger proof uses
+  ui-proof compare <planned-slots-json> [observed-bundle-json ...]
+                              Compare planned UI proof slots against observed bundles
   help                        Show this summary
 
 Platforms (for --tools):
@@ -257,6 +262,7 @@ Advanced/internal helpers (kept available, but not the primary first-run user st
   lifecycle-preflight       Inspect deterministic lifecycle gate results for a workflow surface
   session-fingerprint       Rebaseline the local planning-state fingerprint after review
   phase-status              Update ROADMAP.md phase status through the local helper surface
+  ui-proof                  Validate UI proof metadata and compare planned slots to observed bundles
   file-op                   Deterministic workspace-confined file copy/delete/text mutation
 `;
 }

package/bin/lib/lifecycle-preflight.mjs

@@ -52,6 +52,11 @@ const SURFACE_POLICIES = {
     ownedWrites: ['spec', 'roadmap', 'phase-directories'],
     explicitLifecycleMutation: 'none',
   },
+  'plan-milestone-gaps': {
+    classification: 'owned_write',
+    ownedWrites: ['roadmap', 'phase-directories'],
+    explicitLifecycleMutation: 'none',
+  },
   resume: {
     classification: 'owned_write',
     ownedWrites: ['checkpoint-cleanup'],

package/bin/lib/lifecycle-state.mjs

@@ -6,7 +6,7 @@ const BROWNFIELD_CHANGE_DIR = 'brownfield-change';
 const PHASE_LINE_RE = /^\s*[-*]\s*\[([ x-])\]\s*\*\*Phase\s+(\d+(?:\.\d+)*[a-z]?):\s*(.+?)\*\*(?:\s+—\s+\[([^\]]+)])?/i;
 const PHASE_DETAIL_HEADING_RE = /^(#{3,})\s+Phase\s+(\d+(?:\.\d+)*[a-z]?)(?::|\b)/i;
 const PHASE_DETAIL_STATUS_RE = /^\s*\*\*Status\*\*:\s*\[([ x-])\]/i;
-const ACTIVE_MILESTONE_HEADING_RE = /^###\s+(v[^\s]+)\s+(.+)$/im;
+const ACTIVE_MILESTONE_HEADING_RE = /^#{2,3}\s+(v[^\s]+)\s+(.+)$/im;
 const MILESTONE_LEDGER_HEADING_RE = /^##\s+(?:✅\s+)?(v[^\s]+)\s*(?:—|-)?\s*(.*)$/i;
 const DETAILS_OPEN_RE = /<details\b/i;
 const DETAILS_CLOSE_RE = /<\/details>/i;

package/bin/lib/rendering.mjs

@@ -13,6 +13,7 @@ const HELPER_LIB_FILES = Object.freeze([
   'lifecycle-state.mjs',
   'phase.mjs',
   'session-fingerprint.mjs',
+  'ui-proof.mjs',
   'workspace-root.mjs',
 ]);
 
@@ -47,6 +48,7 @@ import { cmdFileOp } from './lib/file-ops.mjs';
 import { cmdLifecyclePreflight } from './lib/lifecycle-preflight.mjs';
 import { cmdPhaseStatus } from './lib/phase.mjs';
 import { cmdSessionFingerprint } from './lib/session-fingerprint.mjs';
+import { cmdUiProof } from './lib/ui-proof.mjs';
 import { bootstrapHelperWorkspace, consumeWorkspaceRootArg, resolveWorkspaceContext } from './lib/workspace-root.mjs';
 
 const COMMANDS = {
@@ -54,6 +56,7 @@ const COMMANDS = {
   'lifecycle-preflight': cmdLifecyclePreflight,
   'phase-status': cmdPhaseStatus,
   'session-fingerprint': cmdSessionFingerprint,
+  'ui-proof': cmdUiProof,
 };
 
 function printHelp() {
@@ -69,8 +72,12 @@ function printHelp() {
     '  lifecycle-preflight <surface> [phase]',
     '                               Inspect lifecycle gate results for a workflow surface',
     '                               Example: node .planning/bin/gsdd.mjs lifecycle-preflight verify 1 --expects-mutation phase-status',
-    '  session-fingerprint write',
+    '  session-fingerprint write [--allow-changed <ROADMAP.md,SPEC.md,config.json>]',
     '                               Rebaseline planning-state drift after reviewing changed planning files',
+    '  ui-proof validate <path> [--claim <public|publication|tracked|delivery|release>]',
+    '                               Validate UI proof metadata; use --claim for stronger proof uses',
+    '  ui-proof compare <planned-slots-json> [observed-bundle-json ...]',
+    '                               Compare planned UI proof slots against observed bundles',
     '',
     'Advanced option:',
     '  --workspace-root <path>     Override workspace root discovery before or after the subcommand',

package/bin/lib/session-fingerprint.mjs

@@ -63,16 +63,56 @@ export function cmdSessionFingerprint(...args) {
     return;
   }
 
-  const [action] = normalizedArgs;
+  const [action, ...flags] = normalizedArgs;
   if (action !== 'write') {
-    console.error('Usage: node .planning/bin/gsdd.mjs session-fingerprint write');
+    console.error('Usage: node .planning/bin/gsdd.mjs session-fingerprint write [--allow-changed <ROADMAP.md,SPEC.md,config.json>]');
     process.exitCode = 1;
     return;
   }
 
+  const allowChanged = parseAllowChanged(flags);
+  if (allowChanged.invalid) {
+    console.error('Usage: node .planning/bin/gsdd.mjs session-fingerprint write [--allow-changed <ROADMAP.md,SPEC.md,config.json>]');
+    process.exitCode = 1;
+    return;
+  }
+
+  if (allowChanged.files.length > 0) {
+    const drift = checkDrift(planningDir);
+    const changedFiles = drift.files.filter((file) => file.status !== 'unchanged').map((file) => file.file);
+    const unexpected = changedFiles.filter((file) => !allowChanged.files.includes(file));
+    if (unexpected.length > 0) {
+      output({
+        operation: 'session-fingerprint write',
+        changedFiles,
+        allowedChanged: allowChanged.files,
+        written: false,
+        reason: 'unexpected_planning_drift',
+        unexpected,
+      });
+      process.exitCode = 1;
+      return;
+    }
+  }
+
   output({ operation: 'session-fingerprint write', fingerprint: writeFingerprint(planningDir) });
 }
 
+function parseAllowChanged(flags) {
+  const files = [];
+  for (let index = 0; index < flags.length; index += 1) {
+    if (flags[index] !== '--allow-changed') return { invalid: true, files: [] };
+    const value = flags[index + 1];
+    if (!value || value.startsWith('--')) return { invalid: true, files: [] };
+    files.push(...value.split(',').map((entry) => entry.trim()).filter(Boolean));
+    index += 1;
+  }
+  for (const file of files) {
+    if (!FINGERPRINT_SOURCES.includes(file)) return { invalid: true, files: [] };
+  }
+  return { invalid: false, files: [...new Set(files)] };
+}
+
 /**
  * Read the stored fingerprint from .planning/.state-fingerprint.json.
  * Returns null if the file does not exist or is unparseable.

package/bin/lib/templates.mjs

@@ -23,7 +23,7 @@ export function installProjectTemplates({ planningDir, distilledDir, agentsDir }
           console.log(`  - WARN: missing expected template subdir: ${subdir}/`);
         }
       }
-      const expectedRootFiles = ['spec.md', 'roadmap.md', 'auth-matrix.md'];
+      const expectedRootFiles = ['spec.md', 'roadmap.md', 'auth-matrix.md', 'ui-proof.md'];
       for (const file of expectedRootFiles) {
         if (!existsSync(join(localTemplatesDir, file))) {
           console.log(`  - WARN: missing expected root template file: ${file}`);