scene-capability-engine 3.4.6 → 3.5.0

package/CHANGELOG.md

@@ -7,6 +7,26 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
+## [3.5.0] - 2026-03-02
+
+### Added
+- Studio automatic intake + spec governance baseline:
+  - new policy: `.sce/config/studio-intake-policy.json` (template/adopt/takeover managed)
+  - `studio plan` now auto-detects goal intent and resolves spec by bind/create strategy
+  - new commands:
+    - `sce studio intake`
+    - `sce studio portfolio`
+  - plan stage now auto-writes scene portfolio governance artifacts:
+    - `.sce/spec-governance/scene-portfolio.latest.json`
+    - `.sce/spec-governance/scene-index.json`
+- New intake/governance module:
+  - `lib/studio/spec-intake-governor.js`
+  - scene-level duplicate/overflow/stale spec governance summary for portfolio management
+
+### Changed
+- Takeover/adoption managed config baseline now includes `config/studio-intake-policy.json` by default.
+- README/README.zh/command reference updated for auto intake and scene-organized spec governance workflow.
+
 ## [3.4.6] - 2026-03-02
 
 ### Added

package/README.md

@@ -26,6 +26,7 @@ SCE is designed for teams that want AI agents to deliver software end-to-end wit
 | Capability | What SCE Provides | Outcome |
 | --- | --- | --- |
 | Scene + Spec model | Scene-governed sessions and Spec lifecycle (`requirements/design/tasks`) | Stable context across long AI runs |
+| Auto intake + Spec governance | Goal intent detection, auto spec bind/create, scene portfolio governance | Automatic scene-to-spec tracking with bounded spec growth |
 | Studio workflow | `studio plan -> generate -> apply -> verify -> release` | Structured chat-to-release execution |
 | Autonomous delivery | `auto close-loop`, `close-loop-program`, `close-loop-controller` | Unattended bounded convergence |
 | Multi-agent orchestration | DAG scheduling, retries, 429 adaptive parallel control | Reliable parallel execution at scale |
@@ -106,6 +107,7 @@ SCE now enforces a domain-closed diagnosis and repair route by default:
 Hard rule defaults:
 - After two failed rounds on the same problem fingerprint, debug evidence is required in subsequent attempts.
 - `studio verify/release` run `problem-closure-gate` by default when a spec is bound.
+- `studio plan` auto-runs goal intake (`bind existing spec` or `create spec`) and writes scene portfolio governance snapshots by default.
 
 ---
 
@@ -128,6 +130,7 @@ SCE is tool-agnostic and works with Codex, Claude Code, Cursor, Windsurf, VS Cod
 
 ## Important Version Changes
 
+- `3.5.0`: Added Studio automatic goal intake + scene spec portfolio governance (`sce studio intake`, `sce studio portfolio`), including default intake policy baseline and governance artifacts for bounded scene spec growth.
 - `3.4.6`: Added default `problem-closure-gate` + `problem-contract` baseline and strengthened mandatory problem evaluation dimensions (`problem_contract`/`ontology_alignment`/`convergence`) for verify/release convergence control.
 - `3.4.5`: `git-managed-gate` now treats worktree checks as advisory in default relaxed CI mode (`CI/GITHUB_ACTIONS`, non-strict), preventing false release blocking.
 - `3.4.4`: Added `SCE_GIT_MANAGEMENT_ALLOW_UNTRACKED=1` / `--allow-untracked`; release workflow uses it for npm publish after generating release evidence artifacts.
@@ -174,5 +177,5 @@ MIT. See [LICENSE](LICENSE).
 
 ---
 
-**Version**: 3.4.6  
+**Version**: 3.5.0  
 **Last Updated**: 2026-03-02

package/README.zh.md

@@ -26,6 +26,7 @@ SCE 面向希望让 AI Agent 端到端推进交付、同时保持治理可控的
 | 能力 | SCE 提供什么 | 结果 |
 | --- | --- | --- |
 | Scene + Spec 模型 | 场景主会话治理 + Spec 生命周期（需求/设计/任务） | 长周期 AI 上下文稳定 |
+| 自动 intake + Spec 治理 | 目标意图识别、自动绑定/创建 spec、按 scene 组合治理 | 场景需求自动纳管，spec 增长可控 |
 | Studio 工作流 | `studio plan -> generate -> apply -> verify -> release` | 对话到发布路径结构化 |
 | 自动闭环交付 | `auto close-loop`、`close-loop-program`、`close-loop-controller` | 无人值守有界收敛 |
 | 多 Agent 编排 | DAG 调度、重试、429 自适应并行 | 并行执行稳定可控 |
@@ -106,6 +107,7 @@ SCE 默认按“问题域闭环”推进诊断与修复：
 默认硬规则：
 - 同一问题指纹失败两轮后，后续尝试必须补充 debug 证据。
 - 当 spec 绑定时，`studio verify/release` 默认执行 `problem-closure-gate`。
+- `studio plan` 默认执行目标 intake（自动绑定已有 spec 或新建 spec），并自动写入 scene 维度的 spec 治理快照。
 
 ---
 
@@ -128,6 +130,7 @@ SCE 对工具无锁定，可接入 Codex、Claude Code、Cursor、Windsurf、VS
 
 ## 重要版本变更
 
+- `3.5.0`：新增 Studio 目标自动 intake + 场景 spec 组合治理（`sce studio intake`、`sce studio portfolio`），并默认启用 intake 策略基线与治理快照产物，控制场景内 spec 无序增长。
 - `3.4.6`：新增默认 `problem-closure-gate` + `problem-contract` 基线，并强化问题评估强制维度（`problem_contract`/`ontology_alignment`/`convergence`），提升 verify/release 收敛控制。
 - `3.4.5`：`git-managed-gate` 在默认 CI 放宽模式下（`CI/GITHUB_ACTIONS` 且非 strict）对工作区变更改为告警，不再误阻断发布。
 - `3.4.4`：新增 `SCE_GIT_MANAGEMENT_ALLOW_UNTRACKED=1` / `--allow-untracked`；发布工作流在 npm publish 前生成证据资产时可放行未跟踪文件。
@@ -174,5 +177,5 @@ MIT，见 [LICENSE](LICENSE)。
 
 ---
 
-**版本**：3.4.6  
+**版本**：3.5.0  
 **最后更新**：2026-03-02

package/docs/command-reference.md

@@ -2,7 +2,7 @@
 
 > Quick reference for all `sce` commands
 
-**Version**: 3.4.6
+**Version**: 3.5.0
 **Last Updated**: 2026-03-02
 
 ---
@@ -523,6 +523,13 @@ Curated quality policy (`宁缺毋滥，优胜略汰`) defaults:
 sce studio plan --scene scene.customer-order-inventory --from-chat session-20260226 --goal "customer+order+inventory demo" --json
 # Recommended: bind spec explicitly so Studio can ingest problem-domain-chain deterministically
 sce studio plan --scene scene.customer-order-inventory --spec 01-00-customer-order-inventory --from-chat session-20260226 --goal "customer+order+inventory demo" --json
+# Disable auto intake for emergency/manual mode
+sce studio plan --scene scene.customer-order-inventory --from-chat session-20260226 --goal "customer+order+inventory demo" --manual-spec --json
+
+# Analyze intake decision only (no write by default)
+sce studio intake --scene scene.customer-order-inventory --from-chat session-20260226 --goal "optimize checkout retry flow" --json
+# Apply intake and create spec when decision is create_spec
+sce studio intake --scene scene.customer-order-inventory --from-chat session-20260226 --goal "optimize checkout retry flow" --apply --json
 
 # Generate patch bundle metadata (scene is inherited from plan)
 sce studio generate --target 331 --json
@@ -549,15 +556,26 @@ sce studio events --job <job-id> --limit 50 --json
 # Rollback a job after apply/release
 sce studio rollback --job <job-id> --reason "manual-check-failed" --json
 
+# Build scene-organized spec governance portfolio
+sce studio portfolio --json
+sce studio portfolio --scene scene.customer-order-inventory --strict --json
+
 # Enforce authorization for a protected action
 SCE_STUDIO_REQUIRE_AUTH=1 SCE_STUDIO_AUTH_PASSWORD=top-secret sce studio apply --job <job-id> --auth-password top-secret --json
 ```
 
 Stage guardrails are enforced by default:
 - `plan` requires `--scene`; SCE binds one active primary session per scene
+- `plan` runs auto intake by default (`.sce/config/studio-intake-policy.json`):
+  - detect goal intent (`change_request` vs `analysis_only`)
+  - resolve spec via explicit binding / scene latest / related specs / auto-create
+  - auto-create spec artifacts when no suitable spec is found and policy requires tracking
 - `plan --spec <id>` (recommended) ingests `.sce/specs/<spec>/custom/problem-domain-chain.json` into studio job context
 - when `--spec` is omitted, `plan` auto-resolves the latest matching spec chain by `scene_id` when available
 - `plan` auto-searches related historical specs by `scene + goal` and writes top candidates into job metadata (`source.related_specs`)
+- `plan` auto-runs scene spec governance snapshot and writes:
+  - `.sce/spec-governance/scene-portfolio.latest.json`
+  - `.sce/spec-governance/scene-index.json`
 - successful `release` auto-archives current scene session and auto-opens the next scene cycle session
 - `generate` requires `plan`
 - `generate` consumes the plan-stage domain-chain context and writes chain-aware metadata/report (`.sce/reports/studio/generate-<job-id>.json`)
@@ -632,6 +650,24 @@ Default policy file (recommended to commit): `.sce/config/studio-security.json`
 }
 ```
 
+Studio intake policy file (default, recommended to commit): `.sce/config/studio-intake-policy.json`
+
+```json
+{
+  "enabled": true,
+  "auto_create_spec": true,
+  "force_spec_for_studio_plan": true,
+  "prefer_existing_scene_spec": true,
+  "related_spec_min_score": 45,
+  "governance": {
+    "auto_run_on_plan": true,
+    "max_active_specs_per_scene": 3,
+    "stale_days": 14,
+    "duplicate_similarity_threshold": 0.66
+  }
+}
+```
+
 ### Capability Matrix Utilities
 
 ```bash

package/lib/adoption/adoption-strategy.js

@@ -120,6 +120,7 @@ class AdoptionStrategy {
       'config/spec-domain-policy.json',
       'config/problem-eval-policy.json',
       'config/problem-closure-policy.json',
+      'config/studio-intake-policy.json',
       'specs/SPEC_WORKFLOW_GUIDE.md',
       'hooks/sync-tasks-on-edit.sce.hook',
       'hooks/check-spec-on-create.sce.hook',

package/lib/adoption/detection-engine.js

@@ -169,6 +169,7 @@ class DetectionEngine {
         'config/spec-domain-policy.json',
         'config/problem-eval-policy.json',
         'config/problem-closure-policy.json',
+        'config/studio-intake-policy.json',
         'README.md',
         'ultrawork-application-guide.md',
         'ultrawork-integration-summary.md',

package/lib/adoption/file-classifier.js

@@ -70,7 +70,8 @@ class FileClassifier {
       'config/session-governance.json',
       'config/spec-domain-policy.json',
       'config/problem-eval-policy.json',
-      'config/problem-closure-policy.json'
+      'config/problem-closure-policy.json',
+      'config/studio-intake-policy.json'
     ];
 
     // Generated directory patterns

package/lib/adoption/smart-orchestrator.js

@@ -290,6 +290,7 @@ class SmartOrchestrator {
       'config/spec-domain-policy.json',
       'config/problem-eval-policy.json',
       'config/problem-closure-policy.json',
+      'config/studio-intake-policy.json',
       'README.md'
     ];
 

package/lib/commands/studio.js

@@ -11,6 +11,10 @@ const {
 const { findRelatedSpecs } = require('../spec/related-specs');
 const { captureTimelineCheckpoint } = require('../runtime/project-timeline');
 const { runProblemEvaluation } = require('../problem/problem-evaluator');
+const {
+  runStudioAutoIntake,
+  runStudioSpecGovernance
+} = require('../studio/spec-intake-governor');
 
 const STUDIO_JOB_API_VERSION = 'sce.studio.job/v0.1';
 const STAGE_ORDER = ['plan', 'generate', 'apply', 'verify', 'release'];
@@ -1343,6 +1347,9 @@ async function runStudioPlanCommand(options = {}, dependencies = {}) {
   const fromChat = normalizeString(options.fromChat);
   const sceneId = normalizeString(options.scene);
   const specId = normalizeString(options.spec);
+  const goal = normalizeString(options.goal);
+  const manualSpecMode = options.manualSpec === true;
+  const skipSpecGovernance = options.specGovernance === false;
 
   if (!fromChat) {
     throw new Error('--from-chat is required');
@@ -1350,16 +1357,18 @@ async function runStudioPlanCommand(options = {}, dependencies = {}) {
   if (!sceneId) {
     throw new Error('--scene is required');
   }
-  const domainChainBinding = await resolveDomainChainBinding({
+
+  let domainChainBinding = await resolveDomainChainBinding({
     sceneId,
     specId,
-    goal: normalizeString(options.goal)
+    goal
   }, {
     projectPath,
     fileSystem
   });
-  const relatedSpecLookup = await findRelatedSpecs({
-    query: normalizeString(options.goal),
+
+  let relatedSpecLookup = await findRelatedSpecs({
+    query: goal,
     sceneId,
     limit: 8,
     excludeSpecId: domainChainBinding.spec_id || specId || null
@@ -1367,6 +1376,45 @@ async function runStudioPlanCommand(options = {}, dependencies = {}) {
     projectPath,
     fileSystem
   });
+
+  const intake = await runStudioAutoIntake({
+    scene_id: sceneId,
+    from_chat: fromChat,
+    goal,
+    explicit_spec_id: specId,
+    domain_chain_binding: domainChainBinding,
+    related_specs: relatedSpecLookup,
+    apply: !manualSpecMode,
+    skip: manualSpecMode
+  }, {
+    projectPath,
+    fileSystem
+  });
+
+  const intakeSpecId = normalizeString(intake && intake.selected_spec_id);
+  const effectiveSpecId = intakeSpecId || normalizeString(domainChainBinding.spec_id) || specId || null;
+
+  if (effectiveSpecId && effectiveSpecId !== normalizeString(domainChainBinding.spec_id)) {
+    domainChainBinding = await resolveDomainChainBinding({
+      sceneId,
+      specId: effectiveSpecId,
+      goal
+    }, {
+      projectPath,
+      fileSystem
+    });
+  }
+
+  relatedSpecLookup = await findRelatedSpecs({
+    query: goal,
+    sceneId,
+    limit: 8,
+    excludeSpecId: effectiveSpecId || null
+  }, {
+    projectPath,
+    fileSystem
+  });
+
   const relatedSpecItems = Array.isArray(relatedSpecLookup.related_specs)
     ? relatedSpecLookup.related_specs.map((item) => ({
       spec_id: item.spec_id,
@@ -1387,7 +1435,7 @@ async function runStudioPlanCommand(options = {}, dependencies = {}) {
     domainChainBinding.problem_contract || {},
     {
       scene_id: sceneId,
-      goal: normalizeString(options.goal),
+      goal,
       problem_statement: normalizeString(domainChainBinding?.summary?.problem_statement),
       verification_plan: normalizeString(domainChainBinding?.summary?.verification_plan)
     }
@@ -1396,11 +1444,11 @@ async function runStudioPlanCommand(options = {}, dependencies = {}) {
     job_id: jobId,
     scene: {
       id: sceneId,
-      spec_id: domainChainBinding.spec_id || specId || null
+      spec_id: effectiveSpecId
     },
     source: {
-      goal: normalizeString(options.goal) || null,
-      spec_id: domainChainBinding.spec_id || specId || null,
+      goal: goal || null,
+      spec_id: effectiveSpecId,
       problem_contract: problemContract,
       problem_contract_path: domainChainBinding.problem_contract_path || null,
       domain_chain: {
@@ -1415,8 +1463,8 @@ async function runStudioPlanCommand(options = {}, dependencies = {}) {
   };
   const planProblemEvaluation = await enforceProblemEvaluationForStage(planShadowJob, 'plan', {
     scene_id: sceneId,
-    spec_id: domainChainBinding.spec_id || specId || null,
-    goal: normalizeString(options.goal) || null,
+    spec_id: effectiveSpecId,
+    goal: goal || null,
     problem_contract: problemContract,
     domain_chain: {
       resolved: domainChainBinding.resolved === true,
@@ -1444,16 +1492,35 @@ async function runStudioPlanCommand(options = {}, dependencies = {}) {
   const sessionStore = dependencies.sessionStore || new SessionStore(projectPath);
   const sceneSessionBinding = await sessionStore.beginSceneSession({
     sceneId,
-    objective: normalizeString(options.goal) || `Studio scene cycle for ${sceneId}`,
+    objective: goal || `Studio scene cycle for ${sceneId}`,
     tool: normalizeString(options.tool) || 'generic'
   });
+
+  let governanceSnapshot = null;
+  let governanceWarning = '';
+  const autoRunGovernance = !(skipSpecGovernance)
+    && (!intake || !intake.policy || !intake.policy.governance || intake.policy.governance.auto_run_on_plan !== false);
+  if (autoRunGovernance) {
+    try {
+      governanceSnapshot = await runStudioSpecGovernance({
+        apply: true,
+        scene: sceneId
+      }, {
+        projectPath,
+        fileSystem
+      });
+    } catch (error) {
+      governanceWarning = normalizeString(error && error.message);
+    }
+  }
+
   stages.plan = {
     status: 'completed',
     completed_at: now,
     metadata: {
       from_chat: fromChat,
       scene_id: sceneId,
-      spec_id: domainChainBinding.spec_id || specId || null,
+      spec_id: effectiveSpecId,
       scene_session_id: sceneSessionBinding.session.session_id,
       scene_cycle: sceneSessionBinding.scene_cycle,
       domain_chain_resolved: domainChainBinding.resolved === true,
@@ -1463,7 +1530,18 @@ async function runStudioPlanCommand(options = {}, dependencies = {}) {
       domain_chain_summary: domainChainBinding.summary || null,
       domain_chain_reason: domainChainBinding.reason || null,
       problem_contract: problemContract,
+      intake: intake ? {
+        enabled: intake.enabled === true,
+        intent_type: intake.intent ? intake.intent.intent_type : null,
+        decision_action: intake.decision ? intake.decision.action : null,
+        decision_reason: intake.decision ? intake.decision.reason : null,
+        selected_spec_id: intake.selected_spec_id || effectiveSpecId || null,
+        created_spec_id: intake.created_spec && intake.created_spec.created ? intake.created_spec.spec_id : null,
+        policy_path: intake.policy_path || null
+      } : null,
       problem_evaluation: summarizeProblemEvaluation(planProblemEvaluation),
+      spec_governance: governanceSnapshot ? governanceSnapshot.summary : null,
+      spec_governance_warning: governanceWarning || null,
       related_specs_total: Number(relatedSpecLookup.total_candidates || 0),
       related_specs_top: relatedSpecItems
     }
@@ -1477,15 +1555,24 @@ async function runStudioPlanCommand(options = {}, dependencies = {}) {
     status: 'planned',
     source: {
       from_chat: fromChat,
-      goal: normalizeString(options.goal) || null,
-      spec_id: domainChainBinding.spec_id || specId || null,
+      goal: goal || null,
+      spec_id: effectiveSpecId,
       problem_contract: problemContract,
       problem_contract_path: domainChainBinding.problem_contract_path || null,
+      intake: intake ? {
+        enabled: intake.enabled === true,
+        policy_path: intake.policy_path || null,
+        policy_loaded_from: intake.policy_loaded_from || null,
+        intent: intake.intent || null,
+        decision: intake.decision || null,
+        selected_spec_id: intake.selected_spec_id || effectiveSpecId || null,
+        created_spec: intake.created_spec || null
+      } : null,
       domain_chain: {
         resolved: domainChainBinding.resolved === true,
         source: domainChainBinding.source || 'none',
         reason: domainChainBinding.reason || null,
-        spec_id: domainChainBinding.spec_id || null,
+        spec_id: effectiveSpecId || domainChainBinding.spec_id || null,
         chain_path: domainChainBinding.chain_path || null,
         candidate_count: Number.isFinite(Number(domainChainBinding.candidate_count))
           ? Number(domainChainBinding.candidate_count)
@@ -1500,11 +1587,20 @@ async function runStudioPlanCommand(options = {}, dependencies = {}) {
         scene_id: relatedSpecLookup.scene_id || null,
         total_candidates: Number(relatedSpecLookup.total_candidates || 0),
         items: relatedSpecItems
-      }
+      },
+      spec_governance: governanceSnapshot
+        ? {
+          status: governanceSnapshot.summary ? governanceSnapshot.summary.status : null,
+          alert_count: governanceSnapshot.summary ? Number(governanceSnapshot.summary.alert_count || 0) : 0,
+          report_file: governanceSnapshot.report_file || null,
+          scene_index_file: governanceSnapshot.scene_index_file || null
+        }
+        : null,
+      spec_governance_warning: governanceWarning || null
     },
     scene: {
       id: sceneId,
-      spec_id: domainChainBinding.spec_id || specId || null,
+      spec_id: effectiveSpecId,
       related_spec_ids: relatedSpecItems.map((item) => item.spec_id)
     },
     session: {
@@ -1520,6 +1616,12 @@ async function runStudioPlanCommand(options = {}, dependencies = {}) {
       patch_bundle_id: null,
       verify_report: null,
       release_ref: null,
+      spec_portfolio_report: governanceSnapshot && governanceSnapshot.report_file
+        ? governanceSnapshot.report_file
+        : null,
+      spec_scene_index: governanceSnapshot && governanceSnapshot.scene_index_file
+        ? governanceSnapshot.scene_index_file
+        : null,
       problem_eval_reports: {
         plan: normalizeString(planProblemEvaluation.report_file) || null
       }
@@ -1530,7 +1632,7 @@ async function runStudioPlanCommand(options = {}, dependencies = {}) {
   await appendStudioEvent(paths, job, 'stage.plan.completed', {
     from_chat: fromChat,
     scene_id: sceneId,
-    spec_id: domainChainBinding.spec_id || specId || null,
+    spec_id: effectiveSpecId,
     scene_session_id: sceneSessionBinding.session.session_id,
     scene_cycle: sceneSessionBinding.scene_cycle,
     target: job.target,
@@ -1539,13 +1641,27 @@ async function runStudioPlanCommand(options = {}, dependencies = {}) {
     domain_chain_spec_id: domainChainBinding.spec_id || null,
     domain_chain_path: domainChainBinding.chain_path || null,
     problem_contract: problemContract,
+    intake_action: intake && intake.decision ? intake.decision.action : null,
+    intake_reason: intake && intake.decision ? intake.decision.reason : null,
+    intake_selected_spec_id: intake ? intake.selected_spec_id || effectiveSpecId || null : effectiveSpecId,
+    intake_created_spec_id: intake && intake.created_spec && intake.created_spec.created
+      ? intake.created_spec.spec_id
+      : null,
     problem_evaluation: summarizeProblemEvaluation(planProblemEvaluation),
+    spec_governance: governanceSnapshot ? governanceSnapshot.summary : null,
+    spec_governance_warning: governanceWarning || null,
     related_specs_total: Number(relatedSpecLookup.total_candidates || 0),
     related_spec_ids: relatedSpecItems.map((item) => item.spec_id)
   }, fileSystem);
   await writeLatestJob(paths, jobId, fileSystem);
 
   const payload = buildCommandPayload('studio-plan', job);
+  payload.scene = {
+    id: sceneId,
+    spec_id: effectiveSpecId
+  };
+  payload.intake = job.source && job.source.intake ? job.source.intake : null;
+  payload.spec_governance = governanceSnapshot ? governanceSnapshot.summary : null;
   printStudioPayload(payload, options);
   return payload;
 }
@@ -2178,6 +2294,116 @@ async function runStudioEventsCommand(options = {}, dependencies = {}) {
   return payload;
 }
 
+function printStudioIntakePayload(payload, options = {}) {
+  if (options.json) {
+    console.log(JSON.stringify(payload, null, 2));
+    return;
+  }
+
+  console.log(chalk.blue('Studio intake'));
+  console.log(`  Scene: ${payload.scene_id || 'n/a'}`);
+  console.log(`  Goal: ${payload.goal || '(empty)'}`);
+  console.log(`  Intent: ${payload.intent && payload.intent.intent_type ? payload.intent.intent_type : 'unknown'}`);
+  console.log(`  Decision: ${payload.decision && payload.decision.action ? payload.decision.action : 'none'}`);
+  console.log(`  Spec: ${payload.selected_spec_id || 'n/a'}`);
+}
+
+async function runStudioIntakeCommand(options = {}, dependencies = {}) {
+  const projectPath = dependencies.projectPath || process.cwd();
+  const fileSystem = dependencies.fileSystem || fs;
+  const sceneId = normalizeString(options.scene);
+  const fromChat = normalizeString(options.fromChat);
+  const goal = normalizeString(options.goal);
+  const specId = normalizeString(options.spec);
+
+  if (!sceneId) {
+    throw new Error('--scene is required');
+  }
+  if (!fromChat) {
+    throw new Error('--from-chat is required');
+  }
+
+  const domainChainBinding = await resolveDomainChainBinding({
+    sceneId,
+    specId,
+    goal
+  }, {
+    projectPath,
+    fileSystem
+  });
+
+  const relatedSpecLookup = await findRelatedSpecs({
+    query: goal,
+    sceneId,
+    limit: 8,
+    excludeSpecId: domainChainBinding.spec_id || specId || null
+  }, {
+    projectPath,
+    fileSystem
+  });
+
+  const intake = await runStudioAutoIntake({
+    scene_id: sceneId,
+    from_chat: fromChat,
+    goal,
+    explicit_spec_id: specId,
+    domain_chain_binding: domainChainBinding,
+    related_specs: relatedSpecLookup,
+    apply: options.apply === true,
+    skip: options.manualSpec === true
+  }, {
+    projectPath,
+    fileSystem
+  });
+
+  const payload = {
+    ...intake,
+    domain_chain_source: domainChainBinding.source || 'none',
+    domain_chain_spec_id: domainChainBinding.spec_id || null,
+    related_specs_total: Number(relatedSpecLookup.total_candidates || 0)
+  };
+  printStudioIntakePayload(payload, options);
+  return payload;
+}
+
+function printStudioPortfolioPayload(payload, options = {}) {
+  if (options.json) {
+    console.log(JSON.stringify(payload, null, 2));
+    return;
+  }
+  const summary = payload.summary || {};
+  console.log(chalk.blue('Studio portfolio governance'));
+  console.log(`  Status: ${summary.status || 'unknown'}`);
+  console.log(`  Scenes: ${summary.scene_count || 0}`);
+  console.log(`  Specs: ${summary.total_specs || 0}`);
+  console.log(`  Active: ${summary.active_specs || 0}`);
+  console.log(`  Completed: ${summary.completed_specs || 0}`);
+  console.log(`  Stale: ${summary.stale_specs || 0}`);
+  console.log(`  Duplicate pairs: ${summary.duplicate_pairs || 0}`);
+  console.log(`  Overflow scenes: ${summary.overflow_scenes || 0}`);
+}
+
+async function runStudioPortfolioCommand(options = {}, dependencies = {}) {
+  const projectPath = dependencies.projectPath || process.cwd();
+  const fileSystem = dependencies.fileSystem || fs;
+  const payload = await runStudioSpecGovernance({
+    scene: normalizeString(options.scene),
+    apply: options.apply !== false
+  }, {
+    projectPath,
+    fileSystem
+  });
+
+  if (options.strict && payload.summary && Number(payload.summary.alert_count || 0) > 0) {
+    throw new Error(
+      `studio portfolio governance has alerts: ${payload.summary.alert_count} (duplicate/stale/overflow)`
+    );
+  }
+
+  printStudioPortfolioPayload(payload, options);
+  return payload;
+}
+
 async function runStudioCommand(handler, options, stageName = '') {
   try {
     const stage = normalizeString(stageName) || 'unknown';
@@ -2221,11 +2447,34 @@ function registerStudioCommands(program) {
     .requiredOption('--from-chat <session>', 'Chat session identifier or transcript reference')
     .option('--spec <spec-id>', 'Optional spec binding for domain-chain context ingestion')
     .option('--goal <goal>', 'Optional goal summary')
+    .option('--manual-spec', 'Disable auto intake and only use explicit --spec or existing scene binding')
     .option('--target <target>', 'Target integration profile', 'default')
+    .option('--no-spec-governance', 'Skip auto portfolio governance snapshot on plan stage')
     .option('--job <job-id>', 'Reuse an explicit studio job id')
     .option('--json', 'Print machine-readable JSON output')
     .action(async (options) => runStudioCommand(runStudioPlanCommand, options, 'plan'));
 
+  studio
+    .command('intake')
+    .description('Analyze chat goal and auto-resolve spec binding/create decision')
+    .requiredOption('--scene <scene-id>', 'Scene identifier')
+    .requiredOption('--from-chat <session>', 'Chat session identifier or transcript reference')
+    .option('--spec <spec-id>', 'Optional explicit spec id')
+    .option('--goal <goal>', 'Goal text used for intent classification')
+    .option('--apply', 'Create spec when decision is create_spec')
+    .option('--manual-spec', 'Disable auto intake and keep explicit/manual binding only')
+    .option('--json', 'Print machine-readable JSON output')
+    .action(async (options) => runStudioCommand(runStudioIntakeCommand, options, 'intake'));
+
+  studio
+    .command('portfolio')
+    .description('Build scene-organized spec governance portfolio')
+    .option('--scene <scene-id>', 'Optional scene filter')
+    .option('--no-apply', 'Do not write portfolio/index artifacts to .sce/spec-governance/')
+    .option('--strict', 'Fail when governance alerts are detected')
+    .option('--json', 'Print machine-readable JSON output')
+    .action(async (options) => runStudioCommand(runStudioPortfolioCommand, options, 'portfolio'));
+
   studio
     .command('generate')
     .description('Generate patch bundle metadata for a planned studio job (scene inherited from plan)')
@@ -2310,12 +2559,14 @@ module.exports = {
   resolveNextAction,
   buildProgress,
   runStudioPlanCommand,
+  runStudioIntakeCommand,
   runStudioGenerateCommand,
   runStudioApplyCommand,
   runStudioVerifyCommand,
   runStudioReleaseCommand,
   runStudioRollbackCommand,
   runStudioEventsCommand,
+  runStudioPortfolioCommand,
   runStudioResumeCommand,
   registerStudioCommands
 };