sneakoscope 0.6.76 → 0.6.78

package/README.md

@@ -201,6 +201,10 @@ sks team log latest
 
 Team mode prepares the mission, records live events, compiles runtime tasks and worker inboxes, writes schema-backed effort/work-order/dashboard artifacts, and opens a named cmux Team workspace with split live lanes when cmux is available. `sks team dashboard` renders the cockpit panes for mission overview, agent lanes, task DAG, QA/dogfood, artifacts/evidence, and performance.
 
+The cmux Team workspace is a live orchestration screen: the first pane follows `sks team watch <mission-id> --follow` as the mission overview, and neighboring split panes follow individual `sks team lane <mission-id> --agent <name> --follow` views. SKS colors and labels lanes by role, so scouts, planning/debate voices, executors, reviewers, and safety lanes are visually distinct while the same evidence is mirrored into `team-transcript.jsonl`, `team-live.md`, and `team-dashboard.json`.
+
+When the Team route reaches `session_cleanup`, SKS collapses the cmux workspace back to the overview pane and marks the workspace complete. You can also run `sks team cleanup-cmux <mission-id|latest>` manually, or `sks team cleanup-cmux latest --close-workspace` when you want the whole Team workspace closed.
+
 ### QA, Goal, Research, DB, Wiki, GX
 
 ```sh
@@ -212,6 +216,7 @@ sks db scan --json
 sks wiki refresh
 sks wiki sweep latest --json
 sks wiki validate .sneakoscope/wiki/context-pack.json
+sks harness fixture --json
 sks gx init homepage
 sks gx render homepage --format html
 sks validate-artifacts latest --json
@@ -257,7 +262,7 @@ Generated app files include:
 
 Use `sks dollar-commands` to confirm that terminal discovery and Codex App prompt commands agree.
 
-TriWiki is intentionally sparse: `sks wiki sweep` records demote, soft-forget, archive, delete, promote-to-skill, and promote-to-rule candidates instead of injecting every old claim into future prompts. `sks code-structure scan` flags handwritten files above 1000/2000/3000-line thresholds so new logic can be extracted before command files become harder to maintain.
+TriWiki is intentionally sparse: `sks wiki sweep` records demote, soft-forget, archive, delete, promote-to-skill, and promote-to-rule candidates instead of injecting every old claim into future prompts. `sks harness fixture` validates the broader Harness Growth Factory contract: deliberate forgetting fixtures, skill card metadata, experiment schema, tool-error taxonomy, permission profiles, MultiAgentV2 defaults, and Cmux cockpit view coverage. `sks code-structure scan` flags handwritten files above 1000/2000/3000-line thresholds so new logic can be extracted before command files become harder to maintain.
 
 ## Prompt `$` Commands
 

package/package.json

@@ -1,7 +1,7 @@
 {
   "name": "sneakoscope",
   "displayName": "ㅅㅋㅅ",
-  "version": "0.6.76",
+  "version": "0.6.78",
   "description": "Sneakoscope Codex: database-safe Codex CLI/App harness with Team, Goal, AutoResearch, TriWiki, and Honest Mode.",
   "type": "module",
   "homepage": "https://github.com/mandarange/Sneakoscope-Codex#readme",

package/src/cli/main.mjs

@@ -35,14 +35,15 @@ import { createWorkOrderLedger } from '../core/work-order-ledger.mjs';
 import { buildFromChatImgVisualMap } from '../core/from-chat-img-forensics.mjs';
 import { classifyDogfoodFinding, createDogfoodReport, writeDogfoodReport } from '../core/dogfood-loop.mjs';
 import { createSkillCandidate, decideSkillInjection, writeSkillCandidate, writeSkillForgeReport, writeSkillInjectionDecision } from '../core/skill-forge.mjs';
+import { classifyToolError, harnessGrowthReport } from '../core/evaluation.mjs';
 import { recordMistake, writeMistakeMemoryReport } from '../core/mistake-memory.mjs';
 import { buildPromptContext } from '../core/prompt-context-builder.mjs';
 import { renderTeamDashboardState, writeTeamDashboardState } from '../core/team-dashboard-renderer.mjs';
 import { GOAL_WORKFLOW_ARTIFACT } from '../core/goal-workflow.mjs';
 import { CODEX_APP_DOCS_URL, codexAppIntegrationStatus, formatCodexAppStatus } from '../core/codex-app.mjs';
-import { CMUX_BREW_COMMAND, CMUX_BREW_UPGRADE_COMMAND, buildCmuxLaunchPlan, buildCmuxNewWorkspaceArgs, cmuxSurfaceRefFromText, cmuxWorkspaceRef, cmuxWorkspaceRefFromText, cmuxReadiness, cmuxStatusKind, defaultCmuxWorkspaceName, ensureCmuxInstalled, formatCmuxBanner, launchCmuxTeamView, launchCmuxUi, matchingCmuxWorkspaces, parseCmuxWorkspaceList, platformCmuxInstallHint, readCmuxWorkspaceRecord, runCmuxStatus, sanitizeCmuxWorkspaceName, writeCmuxWorkspaceRecord } from '../core/cmux-ui.mjs';
+import { CMUX_BREW_COMMAND, CMUX_BREW_UPGRADE_COMMAND, buildCmuxLaunchPlan, buildCmuxNewWorkspaceArgs, cmuxSurfaceRefFromText, cmuxWorkspaceRef, cmuxWorkspaceRefFromText, cmuxReadiness, cmuxStatusKind, defaultCmuxWorkspaceName, ensureCmuxInstalled, formatCmuxBanner, launchCmuxTeamView, launchCmuxUi, matchingCmuxWorkspaces, parseCmuxWorkspaceList, platformCmuxInstallHint, readCmuxWorkspaceRecord, runCmuxStatus, sanitizeCmuxWorkspaceName, teamLaneStyle, writeCmuxWorkspaceRecord } from '../core/cmux-ui.mjs';
 import { autoReviewProfileName, autoReviewStatus, autoReviewSummary, enableAutoReview, disableAutoReview, enableMadHighProfile, madHighProfileName } from '../core/auto-review.mjs';
-import { buildTeamPlan, codeStructureCommand, defaultBeta, defaultVGraph, evalCommand, gcCommand, goalCommand, gxCommand, hproofCommand, memoryCommand, migrateWikiContextPack, parseTeamCreateArgs, perfCommand, profileCommand, projectWikiClaims, qaLoopCommand, researchCommand, statsCommand, team, teamWorkflowMarkdown, validateArtifactsCommand, wikiCommand, wikiVoxelRowCount, writeWikiContextPack } from './maintenance-commands.mjs';
+import { buildTeamPlan, codeStructureCommand, defaultBeta, defaultVGraph, evalCommand, gcCommand, goalCommand, gxCommand, harnessCommand, hproofCommand, memoryCommand, migrateWikiContextPack, parseTeamCreateArgs, perfCommand, profileCommand, projectWikiClaims, qaLoopCommand, researchCommand, statsCommand, team, teamWorkflowMarkdown, validateArtifactsCommand, wikiCommand, wikiVoxelRowCount, writeWikiContextPack } from './maintenance-commands.mjs';
 
 const flag = (args, name) => args.includes(name);
 const promptOf = (args) => args.filter((x) => !String(x).startsWith('--')).join(' ').trim();
@@ -107,6 +108,7 @@ export async function main(args) {
   if (cmd === 'team') return team(tail);
   if (cmd === 'db') return db(sub, rest);
   if (cmd === 'eval') return evalCommand(sub, rest);
+  if (cmd === 'harness') return harnessCommand(sub, rest);
   if (cmd === 'wiki') return wikiCommand(sub, rest);
   if (cmd === 'gc') return gcCommand(tail);
   if (cmd === 'stats') return statsCommand(tail);
@@ -175,6 +177,7 @@ Usage:
   sks eval run [--json] [--out report.json]
   sks eval compare --baseline old.json --candidate new.json [--json]
   sks perf run [--json]
+  sks harness fixture [--json]
   sks code-structure scan [--json]
   sks wiki coords --rgba 12,34,56,255
   sks wiki pack [--json] [--role worker|verifier] [--max-anchors N]
@@ -1477,6 +1480,7 @@ function usage(args = []) {
     'codex-app': ['Codex App', '', '  sks bootstrap', '  sks codex-app check', '  sks dollar-commands', '  cat .codex/SNEAKOSCOPE.md'],
     dollar: ['Dollar Commands', '', formatDollarCommandsCompact('  '), '', 'Terminal: sks dollar-commands [--json]'],
     wiki: ['TriWiki', '', '  sks wiki pack', '  sks wiki refresh [--prune]', '  sks wiki sweep latest --json', '  sks wiki validate .sneakoscope/wiki/context-pack.json', '  sks wiki prune --dry-run --json', '', 'Packs include attention.use_first and attention.hydrate_first for compact recall plus source hydration. Sweep records intentional forgetting and promotion candidates.'],
+    harness: ['Harness Growth', '', '  sks harness fixture --json', '  sks harness review --json', '', 'Runs deterministic fixtures for deliberate forgetting, skill cards, harness experiments, tool error taxonomy, permission profiles, MultiAgentV2, and Cmux cockpit views.'],
     'code-structure': ['Code Structure', '', '  sks code-structure scan', '  sks code-structure scan --json', '', 'Flags handwritten source files above 1000/2000/3000-line thresholds and records split-review exceptions.'],
     gx: ['GX', '', '  sks gx init architecture-atlas', '  sks gx render architecture-atlas --format all', '  sks gx validate architecture-atlas']
   };
@@ -2293,7 +2297,7 @@ async function selftest() {
   if (hookTeamPendingState.mission_id !== hookTeamState.mission_id) throw new Error('selftest failed: pending clarification allowed a new route mission to replace the visible question sheet');
   if (!hookTeamPendingContext.includes('Required questions still pending') || !hookTeamPendingContext.includes('VISIBLE RESPONSE CONTRACT') || !hookTeamPendingContext.includes('UI_STATE_BEHAVIOR')) throw new Error('selftest failed: pending clarification did not re-expose the question sheet');
   if (hookTeamPendingContext.includes('MANDATORY ambiguity-removal gate activated')) throw new Error('selftest failed: pending clarification prepared a new ambiguity gate instead of reusing the active one');
-  const hookTeamStopResult = await runProcess(process.execPath, [hookBin, 'hook', 'stop'], { cwd: hookTeamTmp, input: JSON.stringify({ cwd: hookTeamTmp, last_assistant_message: 'I will execute Team now.' }), env: { SKS_DISABLE_UPDATE_CHECK: '1' }, timeoutMs: 15000, maxOutputBytes: 128 * 1024 });
+  const hookTeamStopResult = await runProcess(process.execPath, [hookBin, 'hook', 'stop'], { cwd: hookTeamTmp, input: JSON.stringify({ cwd: hookTeamTmp, last_assistant_message: 'I need three decisions before implementation, but I will not paste the Required questions block.' }), env: { SKS_DISABLE_UPDATE_CHECK: '1' }, timeoutMs: 15000, maxOutputBytes: 128 * 1024 });
   if (hookTeamStopResult.code !== 0) throw new Error(`selftest failed: Team stop hook exited ${hookTeamStopResult.code}: ${hookTeamStopResult.stderr}`);
   const hookTeamStopJson = JSON.parse(hookTeamStopResult.stdout);
   if (hookTeamStopJson.decision !== 'block' || !String(hookTeamStopJson.reason || '').includes('mandatory ambiguity-removal')) throw new Error('selftest failed: Stop hook did not block missing Team ambiguity answers');
@@ -2303,6 +2307,13 @@ async function selftest() {
   if (!String(hookTeamStopJson.reason || '').includes('Codex plan-tool interaction')) throw new Error('selftest failed: Stop hook did not reprint plan-tool guidance');
   if (!String(hookTeamStopJson.reason || '').includes('VISIBLE RESPONSE CONTRACT')) throw new Error('selftest failed: Stop hook did not force visible clarification response');
   const hookTeamSchema = await readJson(path.join(missionDir(hookTeamTmp, hookTeamState.mission_id), 'required-answers.schema.json'));
+  const visibleQuestionsBlock = [
+    'Required questions',
+    ...hookTeamSchema.slots.map((slot, idx) => `${idx + 1}. ${slot.id}: ${slot.question}`),
+    'Reply by slot id, then I will write answers.json and run sks pipeline answer latest answers.json.'
+  ].join('\n');
+  const visibleQuestionDecision = await evaluateStop(hookTeamTmp, hookTeamState, { last_assistant_message: visibleQuestionsBlock }, { noQuestion: false });
+  if (!visibleQuestionDecision?.continue) throw new Error('selftest failed: visible Required questions block was not accepted by clarification stop gate');
   const nonGoalsSlot = hookTeamSchema.slots.find((s) => s.id === 'NON_GOALS');
   if (nonGoalsSlot && !nonGoalsSlot.allow_empty) throw new Error('selftest failed: NON_GOALS does not allow an empty array answer');
   if (!nonGoalsSlot && !Array.isArray(hookTeamSchema.inferred_answers?.NON_GOALS)) throw new Error('selftest failed: NON_GOALS was neither asked nor inferred');
@@ -2700,7 +2711,10 @@ async function selftest() {
   if (!roleTeamPlan.roster.debate_team.some((agent) => /inconvenience/.test(agent.persona))) throw new Error('selftest failed: user friction persona missing from debate team');
   const cmuxTeam = await launchCmuxTeamView({ root: tmp, missionId: teamId, plan: roleTeamPlan, json: true });
   if (!cmuxTeam.agents?.length || !cmuxTeam.agents.some((entry) => entry.agent === 'analysis_scout_1') || !cmuxTeam.agents.every((entry) => String(entry.command || '').includes('team lane') && String(entry.command || '').includes('--agent'))) throw new Error('selftest failed: Team cmux view did not expose agent live lanes');
-  const cmuxTeamWorkspaceArgs = buildCmuxNewWorkspaceArgs({ root: tmp, workspace: `sks-team-${teamId}` }, cmuxTeam.agents[0].command);
+  if (!cmuxTeam.overview?.command?.includes('team watch') || !cmuxTeam.lanes?.some((entry) => entry.role === 'overview') || !cmuxTeam.lanes?.some((entry) => entry.agent === 'analysis_scout_1')) throw new Error('selftest failed: Team cmux view did not expose orchestration overview plus agent lanes');
+  if (teamLaneStyle('analysis_scout_1').role !== 'scout' || teamLaneStyle('executor_1').role !== 'execution' || teamLaneStyle('reviewer_1').role !== 'review') throw new Error('selftest failed: Team cmux role palette did not classify lane roles');
+  if (cmuxTeam.cleanup_policy !== 'collapse-agent-lanes-to-overview' || !cmuxTeam.lanes.every((entry) => entry.style?.color && entry.title)) throw new Error('selftest failed: Team cmux view did not expose color/title metadata and cleanup policy');
+  const cmuxTeamWorkspaceArgs = buildCmuxNewWorkspaceArgs({ root: tmp, workspace: `sks-team-${teamId}` }, cmuxTeam.overview.command);
   if (!cmuxTeamWorkspaceArgs.includes('--name') || !cmuxTeamWorkspaceArgs.includes(`sks-team-${teamId}`)) throw new Error('selftest failed: Team cmux workspace is not named for visibility');
   if (routeReasoning(routePrompt('$Research frontier idea'), '$Research frontier idea').effort !== 'xhigh') throw new Error('selftest failed: research reasoning not xhigh');
   if (routeReasoning(routePrompt('$From-Chat-IMG 채팅 이미지 작업'), '$From-Chat-IMG 채팅 이미지 작업').effort !== 'xhigh') throw new Error('selftest failed: From-Chat-IMG reasoning not xhigh');
@@ -2761,7 +2775,7 @@ async function selftest() {
   if (teamDashboard?.agent_session_count !== 5 || teamDashboard?.role_counts?.executor !== 5) throw new Error('selftest failed: team dashboard session/role budget missing');
   await writeTeamDashboardState(teamDir, { missionId: teamId, mission: { id: teamId, mode: 'team' }, effort: 'high', phase: 'verification' });
   const teamDashboardState = await readJson(path.join(teamDir, ARTIFACT_FILES.team_dashboard_state), {});
-  if (!validateTeamDashboardState(teamDashboardState).ok || !renderTeamDashboardState(teamDashboardState).includes('Mission Overview')) throw new Error('selftest failed: Team dashboard state missing required cockpit panes');
+  if (!validateTeamDashboardState(teamDashboardState).ok || !renderTeamDashboardState(teamDashboardState).includes('Mission / Goal View')) throw new Error('selftest failed: Team dashboard state missing required cockpit panes');
   if (teamDashboard?.context_tracking?.ssot !== 'triwiki') throw new Error('selftest failed: team dashboard missing TriWiki context tracking');
   if (!teamDashboard?.phases?.includes('parallel_analysis_scouting')) throw new Error('selftest failed: team dashboard missing analysis scout phase');
   if (!teamDashboard?.latest_messages?.some((entry) => entry.agent === 'analysis_scout_1')) throw new Error('selftest failed: team live dashboard missing analysis scout event');
@@ -2817,6 +2831,9 @@ async function selftest() {
   if (!evalReport.comparison.meaningful_improvement) throw new Error('selftest failed: evaluation benchmark did not show meaningful improvement');
   if (!evalReport.candidate.wiki?.valid) throw new Error('selftest failed: wiki coordinate index invalid in eval');
   if (evalReport.candidate.wiki?.voxel_schema !== 'sks.wiki-voxel.v1' || evalReport.candidate.wiki?.voxel_rows < 1) throw new Error('selftest failed: eval did not include voxel overlay metrics');
+  const harnessReport = harnessGrowthReport({});
+  if (!harnessReport.forgetting.fixture.passed || !harnessReport.cmux.views.includes('Harness Experiments View') || !harnessReport.reliability.tool_error_taxonomy.includes('Unknown')) throw new Error('selftest failed: harness growth fixture incomplete');
+  if (classifyToolError({ message: 'operation timed out' }) !== 'Timeout' || classifyToolError({ message: 'unclassified weirdness' }) !== 'Unknown') throw new Error('selftest failed: tool error taxonomy classification');
   const coord = rgbaToWikiCoord({ r: 12, g: 34, b: 56, a: 255 });
   if (coord.schema !== 'sks.wiki-coordinate.v1' || coord.xyzw.length !== 4) throw new Error('selftest failed: RGBA wiki coordinate conversion');
   await writeTextAtomic(path.join(tmp, '.sneakoscope', 'memory', 'q2_facts', 'selftest.md'), '- claim: Selftest memory claim must be selected before lower-weight mission notes. | id: selftest-memory-priority | source: src/cli/main.mjs | risk: high | status: supported | evidence_count: 3 | required_weight: 1.0 | trust_score: 0.9\n');

package/src/cli/maintenance-commands.mjs

@@ -17,7 +17,7 @@ import { contextCapsule } from '../core/triwiki-attention.mjs';
 import { rgbaKey, rgbaToWikiCoord, validateWikiCoordinateIndex } from '../core/wiki-coordinate.mjs';
 import { ALLOWED_REASONING_EFFORTS, FROM_CHAT_IMG_CHECKLIST_ARTIFACT, FROM_CHAT_IMG_COVERAGE_ARTIFACT, FROM_CHAT_IMG_QA_LOOP_ARTIFACT, FROM_CHAT_IMG_SOURCE_INVENTORY_ARTIFACT, FROM_CHAT_IMG_TEMP_TRIWIKI_ARTIFACT, FROM_CHAT_IMG_TEMP_TRIWIKI_SESSIONS, FROM_CHAT_IMG_VISUAL_MAP_ARTIFACT, FROM_CHAT_IMG_WORK_ORDER_ARTIFACT, ROUTES, hasFromChatImgSignal, routePrompt, stackCurrentDocsPolicy, triwikiContextTracking } from '../core/routes.mjs';
 import { TEAM_DECOMPOSITION_ARTIFACT, TEAM_GRAPH_ARTIFACT, TEAM_INBOX_DIR, TEAM_RUNTIME_TASKS_ARTIFACT, teamRuntimePlanMetadata, teamRuntimeRequiredArtifacts, writeTeamRuntimeArtifacts } from '../core/team-dag.mjs';
-import { appendTeamEvent, formatRoleCounts, initTeamLive, normalizeTeamSpec, parseTeamSpecArgs, readTeamDashboard, readTeamLive, readTeamTranscriptTail, renderTeamAgentLane } from '../core/team-live.mjs';
+import { appendTeamEvent, formatRoleCounts, initTeamLive, normalizeTeamSpec, parseTeamSpecArgs, readTeamDashboard, readTeamLive, readTeamTranscriptTail, renderTeamAgentLane, renderTeamWatch } from '../core/team-live.mjs';
 import { ARTIFACT_FILES, writeValidationReport } from '../core/artifact-schemas.mjs';
 import { writeEffortDecision } from '../core/effort-orchestrator.mjs';
 import { createWorkOrderLedger, writeWorkOrderLedger } from '../core/work-order-ledger.mjs';
@@ -27,10 +27,11 @@ import { runPerfBench } from '../core/perf-bench.mjs';
 import { GOAL_BRIDGE_ARTIFACT, GOAL_WORKFLOW_ARTIFACT, updateGoalWorkflow, writeGoalWorkflow } from '../core/goal-workflow.mjs';
 import { scanCodeStructure, writeCodeStructureReport } from '../core/code-structure.mjs';
 import { writeMemorySweepReport } from '../core/memory-governor.mjs';
-import { launchCmuxTeamView } from '../core/cmux-ui.mjs';
+import { cleanupCmuxTeamView, launchCmuxTeamView } from '../core/cmux-ui.mjs';
 import { writeSkillForgeReport } from '../core/skill-forge.mjs';
 import { writeMistakeMemoryReport } from '../core/mistake-memory.mjs';
 import { scanDbSafety } from '../core/db-safety.mjs';
+import { harnessGrowthReport, writeHarnessGrowthReport } from '../core/evaluation.mjs';
 
 const flag = (args, name) => args.includes(name);
 const promptOf = (args) => args.filter((x) => !String(x).startsWith('--')).join(' ').trim();
@@ -417,6 +418,25 @@ export async function perfCommand(sub, args = []) {
   console.log(`Report: ${path.relative(root, outPath)}`);
 }
 
+export async function harnessCommand(sub, args = []) {
+  const action = sub || 'fixture';
+  if (!['fixture', 'review'].includes(action)) {
+    console.error('Usage: sks harness fixture|review [--json]');
+    process.exitCode = 1;
+    return;
+  }
+  const root = await sksRoot();
+  const report = action === 'review'
+    ? await writeHarnessGrowthReport(root, path.join(root, '.sneakoscope', 'reports'), {})
+    : harnessGrowthReport({});
+  if (flag(args, '--json')) return console.log(JSON.stringify(report, null, 2));
+  console.log('SKS Harness Growth');
+  console.log(`Forgetting fixture: ${report.forgetting.fixture.passed ? 'pass' : 'fail'}`);
+  console.log(`Cmux views: ${report.cmux.views.length}`);
+  console.log(`Tool taxonomy: ${report.reliability.tool_error_taxonomy.join(', ')}`);
+  console.log(`Unknown errors recorded as bugs: ${report.reliability.unknown_errors_are_bugs ? 'yes' : 'no'}`);
+}
+
 export async function codeStructureCommand(sub, args = []) {
   const action = sub || 'scan';
   if (action !== 'scan') {
@@ -1171,13 +1191,13 @@ export async function gxCommand(sub, args) {
 }
 
 export async function team(args) {
-  const teamSubcommands = new Set(['log', 'tail', 'watch', 'lane', 'status', 'dashboard', 'event']);
+  const teamSubcommands = new Set(['log', 'tail', 'watch', 'lane', 'status', 'dashboard', 'event', 'cleanup-cmux']);
   if (teamSubcommands.has(args[0])) return teamCommand(args[0], args.slice(1));
   const opts = parseTeamCreateArgs(args);
   const { prompt, agentSessions, roleCounts, roster } = opts;
   if (!prompt) {
     console.error('Usage: sks team "task" [executor:5 reviewer:2 user:1] [--agents N] [--json]');
-    console.error('       sks team log|tail|watch|lane|status [mission-id|latest]');
+    console.error('       sks team log|tail|watch|lane|status|cleanup-cmux [mission-id|latest]');
     console.error('       sks team event [mission-id|latest] --agent <name> --phase <phase> --message "..."');
     process.exitCode = 1;
     return;
@@ -1211,6 +1231,7 @@ export async function team(args) {
   });
   await writeWorkOrderLedger(dir, workOrder);
   if (fromChatImgRequired) await writeFromChatImgArtifacts(dir, { missionId: id, requests: [{ verbatim: prompt }], ambiguities: ['image source inventory must be completed before implementation'] });
+  await writeHarnessGrowthReport(root, dir, {});
   let dashboardState = await writeTeamDashboardState(dir, { missionId: id, mission: { id, mode: 'team' }, effort: effortDecision.selected_effort, phase: 'intake', next_action: fromChatImgRequired ? 'complete visual source inventory and work-order mapping' : 'run Team analysis scouts' });
   await writeJsonAtomic(path.join(dir, 'team-gate.json'), { passed: false, team_roster_confirmed: true, analysis_artifact: false, triwiki_refreshed: false, triwiki_validated: false, consensus_artifact: false, ...runtime.gate_fields, implementation_team_fresh: false, review_artifact: false, integration_evidence: false, session_cleanup: false, context7_evidence: false, ...(fromChatImgRequired ? { from_chat_img_required: true, from_chat_img_request_coverage: false } : {}) });
   dashboardState = await writeTeamDashboardState(dir, { missionId: id, mission: { id, mode: 'team' }, effort: effortDecision.selected_effort, phase: 'intake', next_action: fromChatImgRequired ? 'complete visual source inventory and work-order mapping' : 'run Team analysis scouts' });
@@ -1507,15 +1528,35 @@ async function teamCommand(sub, args) {
       process.exitCode = 1;
       return;
     }
+    const phase = readFlagValue(args, '--phase', 'general');
     const record = await appendTeamEvent(dir, {
       agent: readFlagValue(args, '--agent', 'parent_orchestrator'),
-      phase: readFlagValue(args, '--phase', 'general'),
+      phase,
       type: readFlagValue(args, '--type', 'status'),
       artifact: readFlagValue(args, '--artifact', ''),
       message
     });
+    const cmuxCleanup = /^session_cleanup$|^team_cleanup$|^cleanup$/i.test(String(phase || ''))
+      ? await cleanupCmuxTeamView({ root, missionId: id, closeWorkspace: flag(args, '--close-workspace') }).catch((err) => ({ ok: false, reason: err.message || 'cmux cleanup failed' }))
+      : null;
     if (flag(args, '--json')) return console.log(JSON.stringify(record, null, 2));
     console.log(`${record.ts} [${record.phase}] ${record.agent}: ${record.message}`);
+    if (cmuxCleanup) {
+      if (cmuxCleanup.ok) console.log(`cmux cleanup: collapsed ${cmuxCleanup.closed_surfaces || 0} agent pane(s), kept overview ${cmuxCleanup.kept_surface || cmuxCleanup.workspace_ref}`);
+      else console.log(`cmux cleanup: skipped (${cmuxCleanup.reason || 'not available'})`);
+    }
+    return;
+  }
+  if (sub === 'cleanup-cmux') {
+    const cleanup = await cleanupCmuxTeamView({ root, missionId: id, closeWorkspace: flag(args, '--close-workspace') || flag(args, '--close') });
+    if (flag(args, '--json')) return console.log(JSON.stringify(cleanup, null, 2));
+    if (!cleanup.ok) {
+      console.error(`cmux cleanup skipped: ${cleanup.reason || 'not available'}`);
+      process.exitCode = cleanup.skipped ? 0 : 2;
+      return;
+    }
+    if (cleanup.close_workspace) console.log(`cmux cleanup: closed Team workspace ${cleanup.workspace_ref}`);
+    else console.log(`cmux cleanup: collapsed ${cleanup.closed_surfaces}/${cleanup.requested_close_surfaces} agent pane(s), kept overview ${cleanup.kept_surface || cleanup.workspace_ref}`);
     return;
   }
   if (sub === 'status') {
@@ -1573,15 +1614,26 @@ async function teamCommand(sub, args) {
   if (sub === 'tail' || sub === 'watch') {
     const lines = readFlagValue(args, '--lines', '20');
     const printTail = async () => {
+      if (sub === 'watch' && !flag(args, '--raw')) {
+        if (flag(args, '--follow') && process.stdout.isTTY) console.clear();
+        console.log(await renderTeamWatch(dir, { missionId: id, lines: Number(lines) }));
+        return;
+      }
       for (const line of await readTeamTranscriptTail(dir, Number(lines))) console.log(line);
     };
     await printTail();
     if (sub === 'watch' && flag(args, '--follow')) {
-      let last = (await readTeamTranscriptTail(dir, Number(lines))).join('\n');
+      let last = flag(args, '--raw')
+        ? (await readTeamTranscriptTail(dir, Number(lines))).join('\n')
+        : await renderTeamWatch(dir, { missionId: id, lines: Number(lines) });
       for (;;) {
         await new Promise((resolve) => setTimeout(resolve, 2000));
-        const next = (await readTeamTranscriptTail(dir, Number(lines))).join('\n');
+        const next = flag(args, '--raw')
+          ? (await readTeamTranscriptTail(dir, Number(lines))).join('\n')
+          : await renderTeamWatch(dir, { missionId: id, lines: Number(lines) });
         if (next !== last) {
+          if (process.stdout.isTTY) console.clear();
+          else console.log('\n--- team watch update ---\n');
           console.log(next);
           last = next;
         }

package/src/core/artifact-schemas.mjs

@@ -17,6 +17,7 @@ export const ARTIFACT_FILES = {
   memory_sweep_report: 'memory-sweep-report.json',
   skill_forge_report: 'skill-forge-report.json',
   mistake_memory_report: 'mistake-memory-report.json',
+  harness_growth_report: 'harness-growth-report.json',
   code_structure_report: 'code-structure-report.json',
   team_dashboard_state: 'team-dashboard-state.json',
   cmux_pane_plan: 'cmux-pane-plan.json',
@@ -163,6 +164,21 @@ export function validateMistakeMemoryReport(data = {}) {
   return validationResult('MistakeMemoryReport', errors);
 }
 
+export function validateHarnessGrowthReport(data = {}) {
+  const errors = [];
+  pushMissing(errors, isObj(data.forgetting), 'forgetting_missing');
+  pushMissing(errors, isObj(data.skills), 'skills_missing');
+  pushMissing(errors, isObj(data.experiments), 'experiments_missing');
+  pushMissing(errors, isObj(data.codex_native), 'codex_native_missing');
+  pushMissing(errors, isObj(data.cmux), 'cmux_missing');
+  pushMissing(errors, isObj(data.reliability), 'reliability_missing');
+  if (data.forgetting?.fixture?.passed !== true) errors.push('forgetting_fixture_failed');
+  if (!Array.isArray(data.reliability?.tool_error_taxonomy) || !data.reliability.tool_error_taxonomy.includes('Unknown')) errors.push('tool_error_taxonomy_missing_unknown');
+  if (data.reliability?.unknown_errors_are_bugs !== true) errors.push('unknown_errors_not_marked_bug');
+  if (!Array.isArray(data.cmux?.views) || data.cmux.views.length < 10) errors.push('cmux_views_incomplete');
+  return validationResult('HarnessGrowthReport', errors);
+}
+
 export function validateCodeStructureReport(data = {}) {
   const errors = [];
   pushMissing(errors, isObj(data.thresholds), 'thresholds_missing');
@@ -179,7 +195,7 @@ export function validateTeamDashboardState(data = {}) {
   pushMissing(errors, Array.isArray(data.gates), 'gates_not_array');
   pushMissing(errors, Array.isArray(data.agents), 'agents_not_array');
   pushMissing(errors, Array.isArray(data.tasks), 'tasks_not_array');
-  for (const pane of ['Mission Overview', 'Agent Lanes', 'Task DAG', 'QA and Dogfood', 'Artifacts and Evidence', 'Performance']) {
+  for (const pane of ['Mission / Goal View', 'Agent Grid View', 'MultiAgentV2 Graph View', 'Work Order Ledger View', 'Skill Autopilot View', 'TriWiki Memory Health View', 'Forget Queue', 'Mistake Immunity', 'Tool Reliability View', 'Harness Experiments View', 'Dogfood Evidence View', 'Code Structure']) {
     if (!arr(data.panes).includes(pane)) errors.push(`pane_missing:${pane}`);
   }
   if (arr(data.gates).some((gate) => !GATE_STATUSES.has(gate.status))) errors.push('gate_status_invalid');
@@ -214,6 +230,7 @@ export const ARTIFACT_VALIDATORS = {
   memory_sweep_report: validateMemorySweepReport,
   skill_forge_report: validateSkillForgeReport,
   mistake_memory_report: validateMistakeMemoryReport,
+  harness_growth_report: validateHarnessGrowthReport,
   code_structure_report: validateCodeStructureReport,
   team_dashboard_state: validateTeamDashboardState,
   cmux_pane_plan: validateCmuxPanePlan,