@amityco/social-plus-vise 0.14.24 → 0.14.25

package/CHANGELOG.md

@@ -4,6 +4,17 @@ All notable changes to `@amityco/social-plus-vise` are documented in this file.
 
 The format is loosely based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/), and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## 0.14.25 — 2026-06-06
+
+### Added
+- **Engagement Intelligence creative brief:** `vise creative` / MCP `creative_brief` now produces an advisory pre-planning brief from a customer request plus optional requirements document and optional prototype HTML. If requirements are absent or explicitly set to `none`, Vise enters exploratory mode instead of blocking.
+- **Creative sidecars:** `vise creative` writes `sp-vise/creative-brief.json` and `sp-vise/creative-brief.md` with inferred goals, archetypes, candidate variants, feasibility summaries, a blocking `preferred_solution` question, and next `vise plan` / `vise workplan` commands.
+- **Runtime intelligence catalog packaging:** the shipped npm tarball now includes `packages/intelligence` so installed CLIs can load the seeded goals, archetypes, objects, relationships, patterns, UX patterns, and variants catalog.
+
+### Verified
+- Added `test:creative` for requirements-driven mode, exploratory mode, sidecar writes, conflicting flag handling, and MCP smoke coverage.
+- Packed-package E2E now runs `vise creative --no-requirements --no-write` after installing the npm tarball, proving the runtime catalog is present in the package.
+
 ## 0.14.24 — 2026-06-06
 
 ### Changed

package/README.md

@@ -81,6 +81,10 @@ Vise validates on three layers, and the layer is set by the *kind of claim* —
 
 Correctness is gated by deterministic rules or attestations. Baseline completeness is gated by explicit scope decisions: if a baseline capability is legitimately out of scope, record `// vise: scope-omit <id> — <reason>` and it no longer blocks. Optional feed capabilities such as image upload, poll creation, and edit post are offered during planning and become checked only after the user opts in. Conformance remains advisory because "matches the brand" is legitimately subjective. See [docs/ARCHITECTURE.md](docs/ARCHITECTURE.md).
 
+### Engagement Intelligence roadmap
+
+Vise's next architecture track is the social.plus **Engagement Intelligence System**: an outcome-to-experience layer that maps customer goals, archetypes, solution patterns, experience objects, UX patterns, and variants before normal implementation planning. The first advisory runtime slice is `vise creative`: it consumes a request plus optional requirements/prototype inputs, or runs in exploratory mode when requirements are absent, then writes a local creative brief for user variant selection. See [docs/ENGAGEMENT_INTELLIGENCE_SYSTEM.md](docs/ENGAGEMENT_INTELLIGENCE_SYSTEM.md), [docs/MONOREPO_ARCHITECTURE.md](docs/MONOREPO_ARCHITECTURE.md), and [packages/intelligence](packages/intelligence).
+
 ### Relationship to social.plus Block Factory
 
 Vise has two deliberately separate roles:
@@ -161,10 +165,11 @@ Aggregate: **98/99 expected feed capabilities** and **27/27 selected optional ca
 
 ### Current Release Validation
 
-Version 0.14.24 carries current release proof around the full feed-forward, product-expectation, and validation flow:
+Version 0.14.25 carries current release proof around the full feed-forward, product-expectation, creative pre-planning, and validation flow:
 
 | Surface | What was validated |
 |---|---|
+| **Creative pre-planning** | `vise creative` produces requirements-driven or exploratory Engagement Intelligence briefs, writes `sp-vise/creative-brief.json` / `.md`, asks for `preferred_solution`, and survives packed-package installation with the intelligence catalog bundled. |
 | **Product flow** | Local end-to-end smoke covers design extraction, plan feed-forward, blocking intake, answered init, capability check, design conformance, and sensor discovery. |
 | **Multi-surface planning** | Broad social requests are decomposed into a `socialWorkplan` sequence for feed, comments, chat, and profile work instead of forcing a single top-level surface choice. `vise workplan next` tells the host agent which surface to implement next, and `vise workplan complete` records green-check progress in `sp-vise/workplan.json` with per-surface snapshots under `sp-vise/workplan-snapshots/<surface>/`. |
 | **Plan questions** | Plans surface blocking questions such as `design_contract_confirmation`, product-scope questions such as `feed_post_type_scope`, `feed_composer_type_scope`, `comment_tray_scope`, `chat_inbox_scope`, and `profile_identity_scope`, plus optional choices such as `feed_optional_capabilities`. Focused plans still accept `feature_surface` answers when the agent is ready to implement one surface. |
@@ -298,6 +303,7 @@ The flow above is what the skill teaches your AI agent. You — the human — dr
 |---|---|
 | `vise doctor` | Verify install; print version, install path, docs source |
 | `vise inspect [path]` | Detect platform, monorepo surfaces, design signals, available sensors |
+| `vise creative [path] --request "..." [--requirements <path\|none>] [--prototype <html>]` | Produce an advisory Engagement Intelligence brief with 2-3 solution variants before normal implementation planning; writes `sp-vise/creative-brief.json` and `.md` unless `--no-write` is set |
 | `vise plan [path] --request "..."` | Produce a grounded implementation plan with intake questions and docs citations |
 | `vise plan-harness [path] --request "..."` | (Pre-planning step) Build the harness around the request |
 | `vise workplan next [path] --request "..."` | For broad social requests, print the next uncompleted surface plus focused `plan` / `init` / verification commands |
@@ -402,7 +408,7 @@ MCP-capable hosts can call Vise as structured tool calls instead of shell comman
 
 ### Tool names (snake_case per MCP convention)
 
-`inspect_project`, `plan_harness`, `plan_integration`, `init_compliance`, `check_compliance`, `sync_compliance`, `attest_rule`, `explain_rule`, `init_engagement`, `show_engagement`, `resolve_request`, `search_docs`, `get_doc_page`, `debug_issue`, `validate_setup`, `run_sensors`, `suggest_patch`, `design_extract`, `design_check`, `design_preview`, `design_reference`, `design_init_tokens`.
+`inspect_project`, `creative_brief`, `plan_harness`, `plan_integration`, `init_compliance`, `check_compliance`, `sync_compliance`, `attest_rule`, `explain_rule`, `init_engagement`, `show_engagement`, `resolve_request`, `search_docs`, `get_doc_page`, `debug_issue`, `validate_setup`, `run_sensors`, `suggest_patch`, `design_extract`, `design_check`, `design_preview`, `design_reference`, `design_init_tokens`.
 
 These are the same operations as the CLI commands above, exposed as MCP tools.
 
@@ -450,12 +456,14 @@ jobs:
 
 ## Compliance Contract
 
-After a successful `vise init`, your project gets a `sp-vise/` directory. If init returns `needs-clarification`, no compliance sidecar is written; answer the blocking questions and run init again. These files become part of your repo and travel through code review:
+Vise writes local planning, compliance, design, and evidence artifacts under `sp-vise/`. `vise creative` can create advisory creative-brief files before implementation; after a successful `vise init`, the compliance contract files are added. If init returns `needs-clarification`, no compliance sidecar is written; answer the blocking questions and run init again. These files become part of your repo and travel through code review:
 
 | File | Created by | What it contains |
 |---|---|---|
 | `sp-vise/compliance.json` | `vise init` | The rules selected for this integration, the Vise version, the ruleset digest, the target app surface, selected optional capabilities, optional engagement link, and an accepted design-contract digest when confirmed. |
 | `sp-vise/intake.json` | `vise init` | The request, outcome, intake answers, remaining blocking count, design-review status (`absent`, `needs-confirmation`, `accepted`, or `rejected`), and any retrospective `--allow-unresolved-intake` acknowledgement. |
+| `sp-vise/creative-brief.json` | `vise creative` | Advisory Engagement Intelligence brief: mode, objective, inferred goals/archetypes, candidate solution variants, feasibility summary, preferred-solution question, and next plan/workplan commands. |
+| `sp-vise/creative-brief.md` | `vise creative` | Human-readable version of the creative brief for review with the user before selecting a variant. |
 | `sp-vise/attestations/*.json` | `vise sync` (deterministic) or `vise attest` (host-agent / human) | Per-rule evidence: signer, confidence, rationale, cited files (with source fingerprints for drift detection). |
 | `sp-vise/inspection.json` | `vise init` | The platform, monorepo surface, and design-token signals detected at init time. |
 | `sp-vise/workplan.json` | `vise workplan complete` | Local progress for broad social workplans: request, completed surface IDs, outcomes, timestamps, green-check evidence, snapshot paths, and optional host-agent notes. |

package/dist/server.js

@@ -17,11 +17,13 @@ import { runSensorsTool } from "./tools/sensors.js";
 import { getSdkFactsTool } from "./tools/sdkFacts.js";
 import { addBlockInstall, listRegistryBlocks, planBlockInstall, validateBlockInstall } from "./tools/blocks.js";
 import { debugIssueTool, debugIssue } from "./tools/debug.js";
+import { creativeBriefTool } from "./tools/creative.js";
 import { packageName, packageVersion } from "./version.js";
 const tools = new Map([
     searchDocsTool,
     getDocPageTool,
     inspectProjectTool,
+    creativeBriefTool,
     planHarnessTool,
     planIntegrationTool,
     initComplianceTool,
@@ -134,6 +136,21 @@ async function handleCli(args) {
             });
             return "exit";
         }
+        if (command === "creative") {
+            assertOnlyKnownFlags(args, ["request", "requirements", "prototype", "surface", "surface-path", "no-requirements", "no-write"], "creative");
+            if (hasFlag(args, "no-requirements") && flagValue(args, "requirements")) {
+                throw new Error("creative accepts either --requirements <path> or --no-requirements, not both.");
+            }
+            await printToolResult(creativeBriefTool, {
+                repoPath: positionalRepoPath(args.slice(1)),
+                request: requiredFlagValue(args, "request", "creative requires --request."),
+                surfacePath: flagValue(args, "surface") ?? flagValue(args, "surface-path"),
+                requirementsPath: hasFlag(args, "no-requirements") ? "none" : flagValue(args, "requirements"),
+                prototypePath: flagValue(args, "prototype"),
+                write: !hasFlag(args, "no-write"),
+            });
+            return "exit";
+        }
         if (command === "debug") {
             assertOnlyKnownFlags(args, ["error", "error-file", "brief"], "debug");
             let errorMessage = flagValue(args, "error");
@@ -450,6 +467,23 @@ Re-plan with collected answers (repeat --answer for each intake question):
     --answer feed_scope=community \\
     --answer feed_target=existing\\ communityId \\
     --answer target_screen_or_route=app/feed/page.tsx`;
+    }
+    if (command === "creative") {
+        return `${packageName} creative
+
+Create an advisory Engagement Intelligence brief before normal Vise planning.
+
+Usage:
+  vise creative [repoPath] --request "Make this app more social"
+  vise creative [repoPath] --request "Add retention loops" --requirements ./requirements.md
+  vise creative [repoPath] --request "Add engagement" --requirements none
+  vise creative [repoPath] --request "Add engagement" --no-requirements
+  vise creative [repoPath] --request "Add engagement" --prototype ./prototype.html
+  vise creative [repoPath] --request "Add engagement" --no-write
+
+Output:
+  Writes sp-vise/creative-brief.json and sp-vise/creative-brief.md unless --no-write is set.
+  Requirements are optional; absence or explicit none switches creative mode to exploratory.`;
     }
     if (command === "plan-harness") {
         return `${packageName} plan-harness
@@ -697,6 +731,7 @@ Usage:
   vise install-skill --target codex Install bundled skill guidance
   vise print-skill                 Print bundled skill markdown
   vise inspect [repoPath]          Inspect platform and design signals
+  vise creative [repoPath] --request "..." Create an Engagement Intelligence brief
   vise debug [repoPath] --error ... Debug an SDK-specific runtime error and emit a repair brief
   vise plan [repoPath] --request "..." Create an implementation plan
   vise workplan next [repoPath] --request "..." Get the next broad-social surface to implement
@@ -1172,7 +1207,7 @@ function ciCheckResult(result) {
     };
 }
 function positionalRepoPath(args) {
-    const flagsWithValues = new Set(["request", "surface", "surface-path", "platform", "capability", "surface-dir", "format", "include", "timeout-ms", "query", "path", "limit", "answer", "target", "dest", "destination", "rule", "confidence", "signer", "identity", "evidence-file", "rationale", "repo", "reference", "registry", "block", "package-source", "note"]);
+    const flagsWithValues = new Set(["request", "requirements", "prototype", "surface", "surface-path", "platform", "capability", "surface-dir", "format", "include", "timeout-ms", "query", "path", "limit", "answer", "target", "dest", "destination", "rule", "confidence", "signer", "identity", "evidence-file", "rationale", "repo", "reference", "registry", "block", "package-source", "note"]);
     for (let index = 0; index < args.length; index += 1) {
         const arg = args[index];
         if (!arg) {
@@ -1194,7 +1229,7 @@ function positionalRepoPath(args) {
 }
 function requiredPositionalText(args, message) {
     const values = [];
-    const flagsWithValues = new Set(["request", "surface", "surface-path", "platform", "capability", "surface-dir", "format", "include", "timeout-ms", "query", "path", "limit", "answer", "target", "dest", "destination", "rule", "confidence", "signer", "identity", "evidence-file", "rationale", "repo", "reference", "registry", "block", "package-source", "note"]);
+    const flagsWithValues = new Set(["request", "requirements", "prototype", "surface", "surface-path", "platform", "capability", "surface-dir", "format", "include", "timeout-ms", "query", "path", "limit", "answer", "target", "dest", "destination", "rule", "confidence", "signer", "identity", "evidence-file", "rationale", "repo", "reference", "registry", "block", "package-source", "note"]);
     for (let index = 0; index < args.length; index += 1) {
         const arg = args[index];
         if (!arg) {