@topy-ai/maggie 0.7.45 → 0.7.47

package/README-zh-TW.md

@@ -29,7 +29,20 @@ npx @topy-ai/maggie init --scope project --agent all
 npx @topy-ai/maggie doctor --scope project --project .
 ```
 
-目前 release 是 `0.7.45`。新增 Codex/Claude Code 的一次性 user-scope 安裝、bundled
+目前 release 是 `0.7.47`。本版處理 2026-09-26 五條新 feedback：project-scope
+`maggie init` 會建立本地 memory store；context 預設只讀取本 project scope；memory hook
+在 local Python adapter 不存在時 fallback 到已安裝 CLI；重複 init 保留既有檔案與時間戳；
+`maggie feedback list` 的 `--project` 可放在子命令前或後。Generated VPS runner 現在記錄
+Maggie 版本與 template fingerprint；preflight 會警示過期/無標記 runner，其他路徑可用
+`maggie deployment --check-runner PATH` 檢查。
+
+0.7.46 feedback batch 仍包含 release profile capability gate、deployment readiness bounded
+retry、Google account/property target verification、GA/GTM external-write idempotency/readback、
+browser adapter capability preflight、privacy-safe feedback evidence references/relationships，
+以及 root-level unittest import 支援。`browser-audit
+--check-browser` 會在導覽前拒絕 missing/incompatible adapter，包括解析成
+`xdg-open` 的系統 `browse`；feedback graph 不保存 raw payload、logs、credentials
+或本機路徑。另包含 0.7.45 的 Codex/Claude Code 一次性 user-scope 安裝、bundled
 workflow runner 與 user-scope maintenance commands；並完成 2026-09-24 booking feedback batch：MaggieDash
 Calendar availability grid/free-slot entry，以及 ORA modal focus restoration
 的驗證證據。另新增 secret-free Starter marketplace provisioning
@@ -100,7 +113,7 @@ structure drift 或重複 treatment product 時 fail closed。
 deployment、memory、feedback 和 MaggieDash。內容先 draft/review，外部寫入、
 publish 與 production deployment 需要明確確認。
 
-目前 source tree 的正式 release 是 `0.7.45`。本版完成 2026-09-24 booking feedback batch：Calendar grid/free-slot entry 與 host modal focus-restoration evidence。本版新增 Starter marketplace provisioning plan；本版完成 feedback batches 22、23：加入 declarative browser interaction evidence、design markup/style/content-key gate、compiler source anchoring、entity double-escape protection、`update --help` read-only、noindex hypothetical indexability、可過期 baseline acknowledgement、DOM-only link extraction regression，以及 MaggieDash 0.2.10 的 content override、短期 browser session、CDN-safe public-session cache contracts。authentication 和 isolated dev server 仍由 host 負責。`maggie-booking` workflow、傳統 email/password、Stripe、Resend、public booking flow 及既有安全邊界維持不變；provider-bound video generation 與 transactional delivery 仍記錄在 issue #39，前一批延後功能仍在 issue #38，不會直接成為 active memory。0.7.33 記錄並審查一筆更正回饋；確認 0.7.32 已正確處理 batch index，沒有修改已驗證的 shared behavior。0.7.32 加入 feedback 一基索引支援、MaggieDash panel 的 source/freshness/error evidence、Consent Mode 與實際 write/no-op reconciliation、SEO baseline recapture、sitemap origin rebasing、content-diff scope、migration ledger reconciliation、deployment credential preflight、release provenance/runtime preflight、icon release gate、opt-in blog auto-publish gate，以及 least-privilege VPS deployer。也修復 top-level `maggie feedback` dispatcher parity。0.7.31 加入 update 差異摘要、atomic installer copy、subset install manifest merge，以及 inventory drift 時 doctor non-zero。0.7.30 補上 feedback tracking issue closeout gate 與 batch 14/15 audit ledger。0.7.29 修正 npm package landing page 使用英文 README；0.7.28 加入 versioned Gemini model policy、明確 fallback 與 provenance、bundled-first CLI
+目前 source tree 的正式 release 是 `0.7.47`。本版完成 2026-09-24 booking feedback batch：Calendar grid/free-slot entry 與 host modal focus-restoration evidence。本版新增 Starter marketplace provisioning plan；本版完成 feedback batches 22、23：加入 declarative browser interaction evidence、design markup/style/content-key gate、compiler source anchoring、entity double-escape protection、`update --help` read-only、noindex hypothetical indexability、可過期 baseline acknowledgement、DOM-only link extraction regression，以及 MaggieDash 0.2.10 的 content override、短期 browser session、CDN-safe public-session cache contracts。authentication 和 isolated dev server 仍由 host 負責。`maggie-booking` workflow、傳統 email/password、Stripe、Resend、public booking flow 及既有安全邊界維持不變；provider-bound video generation 與 transactional delivery 仍記錄在 issue #39，前一批延後功能仍在 issue #38，不會直接成為 active memory。0.7.33 記錄並審查一筆更正回饋；確認 0.7.32 已正確處理 batch index，沒有修改已驗證的 shared behavior。0.7.32 加入 feedback 一基索引支援、MaggieDash panel 的 source/freshness/error evidence、Consent Mode 與實際 write/no-op reconciliation、SEO baseline recapture、sitemap origin rebasing、content-diff scope、migration ledger reconciliation、deployment credential preflight、release provenance/runtime preflight、icon release gate、opt-in blog auto-publish gate，以及 least-privilege VPS deployer。也修復 top-level `maggie feedback` dispatcher parity。0.7.31 加入 update 差異摘要、atomic installer copy、subset install manifest merge，以及 inventory drift 時 doctor non-zero。0.7.30 補上 feedback tracking issue closeout gate 與 batch 14/15 audit ledger。0.7.29 修正 npm package landing page 使用英文 README；0.7.28 加入 versioned Gemini model policy、明確 fallback 與 provenance、bundled-first CLI
 dispatch、`maggie --version`、feedback batch review 聚合與重複偵測、marketplace enrichment evidence、booking
 worker/resolver evidence，以及 read-only migration preflight。它也包含 host-owned mobile app surface contract、signed-in
 camera-state QA、直接 Astro route resolution、correlated feedback batch，以及

package/README.md

@@ -89,7 +89,22 @@ Maggie keeps the existing project foundation and asks for decisions before
 shared routes, analytics, or publishing boundaries change. The current
 package ships 20 installable skills and a local-first MaggieDash foundation.
 
-The current release is `0.7.45`. It adds one-time user-scope installation for
+The current release is `0.7.47`. Project initialization creates a local Maggie
+Memory store, memory contexts default to project scope, and the shared hook
+falls back to the installed CLI if project Python tools are absent. Repeated
+memory initialization preserves existing files and timestamps. Feedback list
+accepts `--project` before or after its subcommand. Generated VPS runners record
+their Maggie version and template fingerprint; deployment preflight warns on
+stale or unmarked runners, with `maggie deployment --check-runner PATH` for
+other locations.
+
+The 0.7.46 feedback batch remains included: capability-aware release profiles,
+bounded deployment-readiness retries, verified Google account/target evidence,
+idempotent external-write readback, browser-adapter capability preflight,
+privacy-safe feedback evidence and relationships, and root-level unittest
+import support. `browser-audit --check-browser` rejects missing or incompatible
+adapters before navigation, including a system `browse`/`xdg-open` opener.
+It also includes the 0.7.45 one-time user-scope installation for
 Codex and Claude Code, a bundled workflow runner, and scoped maintenance
 commands. It also closes the 2026-09-24 booking feedback
 batch with the canonical MaggieDash Calendar availability grid/free-slot
@@ -490,6 +505,23 @@ maggie blog auto-publish-gate \
 
 ### Design and deployment release gates
 
+`maggie release` requires an explicit `.maggie/release-profile.json` capability
+manifest. This prevents a public Astro site from being evaluated against
+unrelated MaggieDash, Booking, migration, service-catalogue, or analytics
+artifacts. A minimal profile is:
+
+```json
+{
+  "schemaVersion": "maggie-release-profile.v1",
+  "profile": "public-astro",
+  "projectType": "astro",
+  "capabilities": ["deployment"]
+}
+```
+
+Declare optional capabilities only when the project owns their evidence. The
+release report records undeclared optional gates as `skipped`.
+
 Check source-to-runtime icon coverage before shipping a design:
 
 ```bash
@@ -588,6 +620,10 @@ maggie deployment readiness --project . \
   --output .maggie/deployment-readiness.json
 ```
 
+Individual suites can also be invoked from the repository root with
+`python3 -m unittest tools.tests.test_maggie_feedback_batch`. Use the
+regression runner for the complete discovered suite.
+
 The readiness report follows `maggie-deployment-readiness.v1`. It reports unit
 regression, package smoke, host browser evidence, rendered canary, and
 deployment preflight separately. Missing host adapter evidence is
@@ -631,8 +667,8 @@ artifact schemas.
 Recommended upgrade sequence for the current release:
 
 ```bash
-npx @topy-ai/maggie@0.7.45 update --scope project --project . --force
-npx @topy-ai/maggie@0.7.45 cleanup --scope project --project .
+npx @topy-ai/maggie@0.7.47 update --scope project --project . --force
+npx @topy-ai/maggie@0.7.47 cleanup --scope project --project .
 ```
 
 Maintainers should pass npm credentials through the repository helper, never
@@ -930,6 +966,16 @@ The `maggie-feedback-batch-review.v1` report retains bounded observations,
 missing-index and duplicate checks, and privacy flags. It never contains raw
 responses, local paths, or secrets.
 
+Add safe relationships when a report must point to a test or related run:
+
+```bash
+maggie feedback collect --project . --summary "Adapter unavailable" \
+  --evidence-ref test:browser-capability:passed \
+  --relationship same-run=clone-001
+```
+
+Batch review also emits bounded `evidenceGraph` and remediation suggestions.
+
 The same evidence-first pattern is available for the other maintainer checks:
 
 ```bash
@@ -1179,6 +1225,12 @@ maggie browser-audit https://example.com \
 It captures scroll/geometry samples and screenshots, then fails on hidden
 required elements, horizontal overflow or invalid sticky positioning.
 
+Before navigation, the command writes a redacted
+`maggie-browser-capability.v1` report and rejects missing or incompatible
+adapters, including a system `browse`/`xdg-open` desktop opener. Add
+`--check-browser` to run only this preflight and receive bounded
+installation/fallback guidance.
+
 List every installed skill and command:
 
 ```bash

package/bin/maggie.js

@@ -19,6 +19,23 @@ const TEMPLATES_ROOT = join(PACKAGE_ROOT, "bundled-templates");
 const STATE_DIR = ".maggie";
 const USER_SCOPE = "user";
 const PROJECT_SCOPE = "project";
+const PROJECT_MEMORY_FILES = {
+  preferences: "preferences.json",
+  conventions: "project-conventions.json",
+  lessons: "lessons.json",
+  errors: "error-patterns.json",
+};
+
+function initializeProjectMemory(root) {
+  const memoryRoot = join(root, STATE_DIR, "memory");
+  mkdirSync(memoryRoot, { recursive: true });
+  for (const [kind, filename] of Object.entries(PROJECT_MEMORY_FILES)) {
+    const path = join(memoryRoot, filename);
+    if (!existsSync(path)) {
+      writeFileSync(path, `${JSON.stringify({ schemaVersion: 1, kind, updatedAt: new Date().toISOString(), items: [] }, null, 2)}\n`, { flag: "wx" });
+    }
+  }
+}
 function loadSkillNames() {
   try {
     return JSON.parse(readFileSync(join(SKILLS_ROOT, "catalog.json"), "utf8")).skills.map((skill) => skill.name);
@@ -153,7 +170,7 @@ Usage:
   maggie brand-kit --manifest FILE | --project PATH --design DESIGN.md [--write --confirm]
   maggie npm11 --project PATH [--smoke --confirm]
   maggie booking-delivery [--policy FILE]
-  maggie release PATH --environment staging --target vps-with-cloudflare-dns
+  maggie release PATH --profile .maggie/release-profile.json --environment staging --target vps-with-cloudflare-dns
   maggie api lifecycle --project PATH [--execute --allow-quota]
   maggie memory <init|list|search|context|add|record-error|transition|export> --project PATH
   maggie localization <extract|plan|generate|preview|validate|review|publish|stale|glossary> [options]
@@ -163,7 +180,7 @@ Usage:
   maggie site-audit URL [--crawl] [--access-log FILE] [--require-sitemap-request] [--languages en-GB,es-MX,ja-JP] [--check-hreflang] [--check-internal-links]
   maggie site-audit URL --crawl --save-baseline FILE --reviewer NAME
   maggie site-audit URL --crawl --baseline FILE [--reason-all REASON]
-  maggie browser-audit URL --browse PATH --output DIR --required SELECTOR [--sticky SELECTOR] [--interactions FILE]
+  maggie browser-audit URL --browse PATH --output DIR [--required SELECTOR] [--sticky SELECTOR] [--interactions FILE] [--check-browser]
   maggie verification coverage --contract FILE --evidence FILE
   maggie ops audit|preflight|verify|lockfiles|seed-manifest|google-capabilities|favicon-check --project PATH
   maggie ops google-capabilities --project PATH --report FILE [--output FILE]
@@ -488,6 +505,7 @@ function install(args) {
     if (existsSync(MARKETPLACE_ROOT)) copyIfMissing(MARKETPLACE_ROOT, join(root, "marketplace"));
     if (existsSync(CONTRACTS_ROOT)) copyIfMissing(CONTRACTS_ROOT, join(root, "contracts"));
     if (existsSync(join(TEMPLATES_ROOT, "maggiedash"))) copyIfMissing(join(TEMPLATES_ROOT, "maggiedash"), join(root, "templates", "maggiedash"));
+    initializeProjectMemory(root);
   }
   const manifestRoots = scope === USER_SCOPE ? allUserAgentRoots() : roots;
   const installedUserSkills = scope === USER_SCOPE ? mergedUserSkillNames(manifestRoots) : [];
@@ -496,7 +514,7 @@ function install(args) {
     : { scope, version: PACKAGE_VERSION, agents: roots.map((item) => item.slice(root.length + 1)), skills: mergedSkillNames(root, skills), managedFiles: managedFileDigests(root, roots, skills), installed_at: new Date().toISOString() };
   writeInstallManifest(root, manifest, scope);
   console.log(scope === USER_SCOPE ? `Maggie installed for this user in ${userStateRoot()}` : `Maggie installed in ${root}`);
-  console.log(scope === USER_SCOPE ? "Project state remains local; run `maggie doctor --scope user` to verify the user install." : "Run `maggie doctor --project .` before using mutating workflows.");
+  console.log(scope === USER_SCOPE ? "Project state remains local; run `maggie doctor --scope user` to verify the user install." : "Project-scoped Maggie Memory is initialized locally; run `maggie doctor --project .` before using mutating workflows.");
 }
 
 function update(args) {
@@ -591,7 +609,7 @@ function workflowCli(name, args) {
   const root = projectRoot(args);
   const script = toolScript(name, root);
   if (!existsSync(script)) throw new Error(`${name} is missing: ${script}`);
-  const env = name === "maggie_feedback.py" ? { ...process.env, MAGGIE_VERSION: PACKAGE_VERSION } : process.env;
+  const env = { ...process.env, MAGGIE_VERSION: PACKAGE_VERSION };
   const result = spawnSync("python3", [script, ...args], { stdio: "inherit", cwd: root, env });
   if (result.error) throw result.error;
   process.exitCode = result.status ?? 1;

package/bundled-contracts/google-integrations/capability-report-v2.schema.json

@@ -0,0 +1,76 @@
+{
+  "$schema": "https://json-schema.org/draft/2020-12/schema",
+  "$id": "https://maggie.noblox.app/contracts/google-integrations/capability-report-v2.json",
+  "title": "Maggie Google integrations capability report v2",
+  "type": "object",
+  "additionalProperties": false,
+  "required": ["schemaVersion", "generatedAt", "providerResults", "passed", "mutationsAllowed"],
+  "properties": {
+    "schemaVersion": {"const": "maggie-google-capability-report.v2"},
+    "generatedAt": {"type": "string", "minLength": 1},
+    "providerResults": {"type": "array", "minItems": 1, "items": {"$ref": "#/$defs/providerResult"}},
+    "passed": {"type": "boolean"},
+    "mutationsAllowed": {"const": false}
+  },
+  "$defs": {
+    "providerResult": {
+      "type": "object",
+      "additionalProperties": false,
+      "required": ["provider", "resource", "activeAccount", "target", "authMode", "scopes", "productRole", "evidence", "capabilities", "nextAction"],
+      "properties": {
+        "provider": {"enum": ["gsc", "ga4", "gtm", "google-ads", "firebase"]},
+        "resource": {"type": "string", "minLength": 1, "maxLength": 200},
+        "activeAccount": {"$ref": "#/$defs/verifiedRef"},
+        "target": {
+          "type": "object",
+          "additionalProperties": false,
+          "required": ["id", "kind", "verified"],
+          "properties": {
+            "id": {"type": "string", "minLength": 1, "maxLength": 200},
+            "kind": {"enum": ["property", "container", "customer", "project", "site", "account"]},
+            "verified": {"const": true}
+          }
+        },
+        "authMode": {"enum": ["desktop-oauth", "service-account-impersonation", "none"]},
+        "scopes": {"type": "array", "items": {"type": "string", "minLength": 1}, "uniqueItems": true},
+        "productRole": {"type": "string", "minLength": 1, "maxLength": 200},
+        "evidence": {"$ref": "#/$defs/evidence"},
+        "capabilities": {"$ref": "#/$defs/capabilities"},
+        "nextAction": {"type": "string", "minLength": 1, "maxLength": 500}
+      }
+    },
+    "verifiedRef": {
+      "type": "object",
+      "additionalProperties": false,
+      "required": ["id", "verified"],
+      "properties": {
+        "id": {"type": "string", "pattern": "^[^@\\s]{1,200}$"},
+        "verified": {"const": true}
+      }
+    },
+    "evidence": {
+      "type": "object",
+      "additionalProperties": false,
+      "required": ["verified", "endpoint", "statusCode", "readOnly"],
+      "properties": {
+        "verified": {"type": "boolean"},
+        "endpoint": {"type": "string", "minLength": 1, "maxLength": 500},
+        "statusCode": {"type": "integer", "minimum": 100, "maximum": 599},
+        "readOnly": {"type": "boolean"},
+        "writeTest": {"type": "object"},
+        "adsPrerequisites": {"type": "object"}
+      }
+    },
+    "capabilities": {
+      "type": "object",
+      "additionalProperties": false,
+      "required": ["read", "report", "edit", "publish"],
+      "properties": {
+        "read": {"enum": ["verified", "not_tested", "not_available", "blocked"]},
+        "report": {"enum": ["verified", "not_tested", "not_available", "blocked"]},
+        "edit": {"enum": ["verified", "not_tested", "not_available", "blocked"]},
+        "publish": {"enum": ["verified", "not_tested", "not_available", "blocked"]}
+      }
+    }
+  }
+}

package/bundled-contracts/google-integrations/external-write-readback-v1.schema.json

@@ -0,0 +1,36 @@
+{
+  "$schema": "https://json-schema.org/draft/2020-12/schema",
+  "$id": "https://maggie.noblox.app/contracts/google-integrations/external-write-readback-v1.json",
+  "title": "Maggie external provider write readback evidence v1",
+  "type": "object",
+  "additionalProperties": false,
+  "required": ["schemaVersion", "generatedAt", "provider", "resource", "operation", "idempotencyKey", "retry", "mutation", "readback", "duplicates", "orphaned", "cleanup", "mutationExecuted"],
+  "properties": {
+    "schemaVersion": {"const": "maggie-external-write-readback.v1"},
+    "generatedAt": {"type": "string", "minLength": 1},
+    "provider": {"enum": ["ga4", "gtm", "gsc", "google-ads", "firebase"]},
+    "resource": {"type": "string", "minLength": 1, "maxLength": 200},
+    "operation": {"type": "string", "pattern": "^[a-z][a-z0-9_.-]{1,63}$"},
+    "idempotencyKey": {"type": "string", "pattern": "^[A-Za-z0-9][A-Za-z0-9_.:-]{2,127}$"},
+    "retry": {
+      "type": "object", "additionalProperties": false, "required": ["attempt", "maxAttempts", "sameKeyOnRetry"],
+      "properties": {"attempt": {"type": "integer", "minimum": 1, "maximum": 3}, "maxAttempts": {"type": "integer", "minimum": 1, "maximum": 3}, "sameKeyOnRetry": {"const": true}}
+    },
+    "mutation": {
+      "type": "object", "additionalProperties": false, "required": ["status", "statusCode", "explicitConfirmation"],
+      "properties": {"status": {"enum": ["created", "updated", "no-op"]}, "statusCode": {"type": "integer", "minimum": 200, "maximum": 299}, "explicitConfirmation": {"const": true}}
+    },
+    "readback": {
+      "type": "object", "additionalProperties": false, "required": ["passed", "endpoint", "checks"],
+      "properties": {
+        "passed": {"const": true},
+        "endpoint": {"type": "string", "pattern": "^https://[^\\s?#]+$"},
+        "checks": {"type": "array", "minItems": 1, "items": {"type": "object"}}
+      }
+    },
+    "duplicates": {"type": "array", "maxItems": 0},
+    "orphaned": {"type": "array", "maxItems": 0},
+    "cleanup": {"type": "object", "additionalProperties": false, "required": ["status", "checked"], "properties": {"status": {"enum": ["not-needed", "passed"]}, "checked": {"const": true}}},
+    "mutationExecuted": {"const": true}
+  }
+}

package/bundled-contracts/maggie-deployment/deployer-delegation-v1.schema.json

@@ -0,0 +1,20 @@
+{
+  "$schema": "https://json-schema.org/draft/2020-12/schema",
+  "$id": "https://maggiedash.noblox.app/contracts/deployer-delegation-v1.schema.json",
+  "title": "Maggie deployment deployer delegation evidence v1",
+  "type": "object",
+  "additionalProperties": false,
+  "required": ["schemaVersion", "host", "user", "releaseRoot", "service", "state", "passed", "checks", "mutation"],
+  "properties": {
+    "schemaVersion": {"const": "maggie-deployment-delegation.v1"},
+    "host": {"type": "string", "minLength": 1},
+    "user": {"type": "string", "pattern": "^[a-z_][a-z0-9_-]{0,31}\\$?$"},
+    "releaseRoot": {"type": "string", "pattern": "^/[^\\r\\n]*$"},
+    "service": {"type": "string", "pattern": "^[A-Za-z0-9_.@-]+$"},
+    "state": {"enum": ["passed", "failed", "transient", "inconclusive"]},
+    "passed": {"type": "boolean"},
+    "checks": {"type": "object"},
+    "errors": {"type": "array", "items": {"type": "string"}},
+    "mutation": {"const": "not executed"}
+  }
+}

package/bundled-contracts/maggie-deployment/release-profile-v1.schema.json

@@ -0,0 +1,34 @@
+{
+  "$schema": "https://json-schema.org/draft/2020-12/schema",
+  "$id": "https://maggiedash.noblox.app/contracts/release-profile-v1.schema.json",
+  "title": "Maggie release profile v1",
+  "type": "object",
+  "additionalProperties": false,
+  "required": ["schemaVersion", "profile", "capabilities"],
+  "properties": {
+    "schemaVersion": {"const": "maggie-release-profile.v1"},
+    "profile": {"type": "string", "pattern": "^[a-z][a-z0-9-]{1,63}$"},
+    "projectType": {"type": "string", "enum": ["astro", "nextjs", "sveltekit", "nuxt", "vite-react", "vite-vue", "other"]},
+    "capabilities": {
+      "type": "array",
+      "minItems": 1,
+      "uniqueItems": true,
+      "items": {
+        "enum": [
+          "deployment",
+          "scenario-qa",
+          "social-card-audit",
+          "migration",
+          "maggiedash-health",
+          "schedule",
+          "analytics-contract",
+          "analytics-release-gate",
+          "service-facts",
+          "maggiedash-schema",
+          "editorial-review",
+          "durable-site-evidence"
+        ]
+      }
+    }
+  }
+}

package/bundled-contracts/maggie-design/browser-capability-v1.schema.json

@@ -0,0 +1,33 @@
+{
+  "$schema": "https://json-schema.org/draft/2020-12/schema",
+  "$id": "https://maggie.noblox.app/contracts/browser-capability-v1.schema.json",
+  "title": "Maggie browser adapter capability report v1",
+  "type": "object",
+  "required": ["schemaVersion", "adapter", "status", "checks", "requiredCommands", "fallback"],
+  "properties": {
+    "schemaVersion": {"const": "maggie-browser-capability.v1"},
+    "adapter": {
+      "type": "object",
+      "required": ["requested"],
+      "properties": {
+        "requested": {"type": "string", "minLength": 1, "maxLength": 160},
+        "name": {"type": "string", "maxLength": 160},
+        "requestedPathFingerprint": {"type": ["string", "null"], "pattern": "^(sha256:[a-f0-9]{64})?$"},
+        "resolvedPathFingerprint": {"type": ["string", "null"], "pattern": "^(sha256:[a-f0-9]{64})?$"}
+      },
+      "additionalProperties": false
+    },
+    "status": {"enum": ["ready", "missing", "incompatible"]},
+    "errorCode": {"type": "string", "maxLength": 80},
+    "message": {"type": "string", "maxLength": 240},
+    "checks": {
+      "type": "object",
+      "required": ["resolved", "regularFile", "executable", "help", "requiredCommands", "interactionCommands"],
+      "additionalProperties": {"type": "boolean"}
+    },
+    "requiredCommands": {"type": "array", "items": {"type": "string"}, "minItems": 1, "maxItems": 20},
+    "missingCommands": {"type": "array", "items": {"type": "string"}, "maxItems": 20},
+    "fallback": {"type": "array", "items": {"type": "string", "maxLength": 240}, "maxItems": 8}
+  },
+  "additionalProperties": false
+}

package/bundled-contracts/maggie-feedback/evidence-bundle-v1.schema.json

@@ -0,0 +1,38 @@
+{
+  "$schema": "https://json-schema.org/draft/2020-12/schema",
+  "$id": "https://maggie.noblox.app/contracts/feedback-evidence-bundle-v1.schema.json",
+  "title": "Maggie privacy-safe feedback evidence bundle v1",
+  "type": "object",
+  "required": ["evidence", "relationships"],
+  "properties": {
+    "evidence": {
+      "type": "array",
+      "maxItems": 20,
+      "items": {
+        "type": "object",
+        "required": ["kind", "ref", "status"],
+        "properties": {
+          "kind": {"enum": ["test", "report", "screenshot", "command", "deployment", "issue", "commit", "artifact"]},
+          "ref": {"type": "string", "pattern": "^[A-Za-z0-9][A-Za-z0-9._:/=-]{0,159}$"},
+          "status": {"enum": ["passed", "failed", "observed", "not-run", "unknown"]}
+        },
+        "additionalProperties": false
+      }
+    },
+    "relationships": {
+      "type": "array",
+      "maxItems": 20,
+      "items": {
+        "type": "object",
+        "required": ["kind", "target", "confidence"],
+        "properties": {
+          "kind": {"enum": ["related", "same-run", "same-fingerprint", "duplicates", "validates", "remediates", "caused-by"]},
+          "target": {"type": "string", "pattern": "^[A-Za-z0-9][A-Za-z0-9._:/=-]{0,159}$"},
+          "confidence": {"enum": ["low", "medium", "high"]}
+        },
+        "additionalProperties": false
+      }
+    }
+  },
+  "additionalProperties": false
+}

package/bundled-references/browser-inspection.md

@@ -14,6 +14,23 @@ The browser capability must support:
 - slow scrolling, click, hover, keyboard focus, and back/forward navigation;
 - reading computed CSS, media sources, links, and visible accessibility labels.
 
+Before navigation, Maggie runs a capability preflight against the configured
+adapter. The report is `maggie-browser-capability.v1` and classifies the
+adapter as `ready`, `missing`, or `incompatible`. This prevents a system
+`browse`/`xdg-open` desktop opener from being mistaken for a browser adapter:
+
+```bash
+maggie browser-audit https://example.com \
+  --browse "$HOME/.codex/skills/gstack/browse/dist/browse" \
+  --output .maggie/browser-audit --required body --check-browser
+```
+
+The report contains only the adapter name, path fingerprints, capability
+checks, and bounded installation/fallback guidance. If it is `missing` or
+`incompatible`, install or enable an authorized Chrome/Playwright/gstack
+adapter and pass its executable path. Maggie does not silently install a
+browser runtime or use a desktop opener as a fallback.
+
 The minimum extraction result for a target is:
 
 ```text

package/bundled-references/google-integrations-runbook.md

@@ -111,8 +111,13 @@ maggie ops google-capabilities \
 ```
 
 The report contract is
-[`capability-report-v1.json`](../bundled-contracts/google-integrations/capability-report-v1.json).
+[`capability-report-v2.schema.json`](../bundled-contracts/google-integrations/capability-report-v2.schema.json).
 The CLI writes a normalized result and never copies arbitrary input fields.
+Every provider row must also identify the redacted active account and selected
+target resource, both with `verified: true`; the target ID must equal the
+selected `resource`. A report that only proves account discovery, or comes from
+the wrong browser account/property, is rejected before a write workflow can use
+it.
 
 ## Capability matrix
 
@@ -121,6 +126,8 @@ Every provider/resource row must expose this shape:
 | Field | Meaning |
 |---|---|
 | `provider` / `resource` | The Google product and scoped resource being checked |
+| `activeAccount` | Redacted account/principal reference confirmed by the current auth session |
+| `target` | Resource ID and kind confirmed in the current account; must match `resource` |
 | `authMode` | `desktop-oauth`, `service-account-impersonation`, or `none` |
 | `scopes` | Exact allowlisted OAuth scopes, never token values |
 | `productRole` | Role granted in the product, distinct from Cloud IAM |

package/bundled-references/memory-hook.md

@@ -1,23 +1,36 @@
 # Maggie Memory Hook
 
-Every Maggie skill invocation has an automatic memory lifecycle when the host
-project contains `tools/clis/maggie_memory.py`.
+Every Maggie skill invocation uses the current project's Maggie Memory by
+default. Project initialization creates `.maggie/memory/` for that repository.
 
 ## Before work
 
-Run:
+Use the project-local adapter when it is present:
 
 ```bash
 python3 tools/clis/maggie_memory.py context --project . --skill <current-skill>
 ```
 
+If that adapter is absent, use the installed CLI:
+
+```bash
+maggie memory context --project . --skill <current-skill>
+```
+
 Load the returned active preferences, conventions, lessons, and matching error
 history into the current decision context. Surface material rules and verify
 them against current project evidence. Memory never replaces inspection,
 approval, bootstrap, or production gates.
 
-If the command is unavailable, report that memory is unavailable and continue
-with the normal workflow. Do not invent or silently reconstruct memory.
+The context response reports `status: "uninitialized"` when Maggie Memory is
+available but the project has not initialized its store. In that case, explain
+that `maggie init --scope project` initializes it; do not call memory
+unavailable. Report unavailable only when neither the project adapter nor the
+installed `maggie` CLI can run. Do not invent or silently reconstruct memory.
+
+Context includes only active project-scope items for the current repository.
+Include user/workspace entries only after a separate explicit opt-in with
+`--include-shared`.
 
 ## After work
 

package/bundled-skills/maggie-clone/SKILL.md

@@ -104,6 +104,13 @@ for the inspection contract and [`references/operational-model.md`](references/o
 for run artifacts and phase gates. If no browser tool is available, stop before
 editing and report the missing capability.
 
+When using the CLI adapter, run its capability preflight first. A command such
+as `/usr/bin/browse` that resolves to `xdg-open` is a desktop opener, not a
+browser adapter, and must be reported as incompatible. Use the report and its
+bounded fallback guidance to install or select an authorized adapter; do not
+silently substitute a desktop opener or install a browser runtime without the
+user's approval.
+
 ## Phase 0: Preflight and plan
 
 1. Parse and normalize all target URLs. Reject invalid, inaccessible, or