scene-capability-engine 3.4.6 → 3.5.1

package/CHANGELOG.md

@@ -7,6 +7,41 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
+## [3.5.1] - 2026-03-03
+
+### Added
+- Studio historical scene backfill command:
+  - `sce studio backfill-spec-scenes`
+  - supports active-only/default batch backfill and writes `.sce/spec-governance/spec-scene-overrides.json`
+  - optionally refreshes governance artifacts after apply
+
+### Changed
+- Studio intake/governance policy is now stricter by default:
+  - `allow_manual_spec_override=false` blocks `--manual-spec` bypass unless explicitly enabled
+  - `governance.require_auto_on_plan=true` blocks `--no-spec-governance` bypass unless explicitly enabled
+- Spec governance and related-spec lookup now read scene override mappings from `.sce/spec-governance/spec-scene-overrides.json`.
+- Takeover/adoption baseline now provisions the stricter intake policy and backfill defaults.
+
+## [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 +107,9 @@ 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.
+- `studio plan --manual-spec` and `--no-spec-governance` are blocked by default policy; use policy overrides only when absolutely necessary.
+- Historical specs can be scene-governed incrementally via `sce studio backfill-spec-scenes --apply` (writes `.sce/spec-governance/spec-scene-overrides.json`).
 
 ---
 
@@ -128,6 +132,8 @@ SCE is tool-agnostic and works with Codex, Claude Code, Cursor, Windsurf, VS Cod
 
 ## Important Version Changes
 
+- `3.5.1`: Enforced stricter Studio intake defaults (`--manual-spec` and `--no-spec-governance` blocked unless policy override), added historical spec scene backfill command (`sce studio backfill-spec-scenes`) and persisted override mapping (`.sce/spec-governance/spec-scene-overrides.json`) for portfolio/related-spec alignment.
+- `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 +180,5 @@ MIT. See [LICENSE](LICENSE).
 
 ---
 
-**Version**: 3.4.6  
-**Last Updated**: 2026-03-02
+**Version**: 3.5.1  
+**Last Updated**: 2026-03-03

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 +107,9 @@ 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。
+- 默认策略会阻断 `studio plan --manual-spec` 与 `--no-spec-governance`（仅在确有必要且策略显式放开时可绕过）。
+- 历史 spec 可通过 `sce studio backfill-spec-scenes --apply` 分批回填到 scene 治理映射（写入 `.sce/spec-governance/spec-scene-overrides.json`）。
 
 ---
 
@@ -128,6 +132,8 @@ SCE 对工具无锁定，可接入 Codex、Claude Code、Cursor、Windsurf、VS
 
 ## 重要版本变更
 
+- `3.5.1`：默认强化 Studio intake 治理（`--manual-spec`、`--no-spec-governance` 在未显式放开策略时会被阻断），新增历史 spec 场景回填命令 `sce studio backfill-spec-scenes`，并写入 `.sce/spec-governance/spec-scene-overrides.json` 以统一 portfolio 与 related-spec 的场景映射。
+- `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 +180,5 @@ MIT，见 [LICENSE](LICENSE)。
 
 ---
 
-**版本**：3.4.6  
-**最后更新**：2026-03-02
+**版本**：3.5.1  
+**最后更新**：2026-03-03

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
 
 ---
@@ -524,6 +524,11 @@ sce studio plan --scene scene.customer-order-inventory --from-chat session-20260
 # 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
 
+# 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
 # Optional explicit scene check (must match planned scene)
@@ -549,15 +554,36 @@ 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
+
+# Backfill historical spec scene bindings into override map (active-only by default)
+sce studio backfill-spec-scenes --apply --json
+# Backfill a bounded batch from unassigned scene and refresh governance snapshot
+sce studio backfill-spec-scenes --scene scene.unassigned --limit 20 --apply --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 --manual-spec` is blocked by default (`allow_manual_spec_override=false`)
+- `plan --no-spec-governance` is blocked by default (`governance.require_auto_on_plan=true`)
 - `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`
+- historical spec scene backfill can be managed via:
+  - `sce studio backfill-spec-scenes --apply`
+  - writes `.sce/spec-governance/spec-scene-overrides.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 +658,32 @@ 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,
+  "allow_manual_spec_override": false,
+  "prefer_existing_scene_spec": true,
+  "related_spec_min_score": 45,
+  "governance": {
+    "auto_run_on_plan": true,
+    "require_auto_on_plan": true,
+    "max_active_specs_per_scene": 3,
+    "stale_days": 14,
+    "duplicate_similarity_threshold": 0.66
+  },
+  "backfill": {
+    "enabled": true,
+    "active_only_default": true,
+    "default_scene_id": "scene.sce-core",
+    "override_file": ".sce/spec-governance/spec-scene-overrides.json"
+  }
+}
+```
+
 ### 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'
     ];