@piagent/platform 1.5.4 → 1.6.0

package/benchmarks/deep-logic-v1/prompts/temporal-usage-billing-close.md

@@ -0,0 +1,123 @@
+Implement the temporal usage-billing close across:
+
+- `packages/billing/src/plan-timeline.js`
+- `packages/billing/src/close-period.js`
+- `apps/admin/src/billing-summary.js`
+
+The implementation must use only Node's standard library and must never mutate
+caller input. All accepted values are plain JSON values: reject sparse arrays,
+non-finite/unsafe numbers, non-plain object prototypes, accessors, symbol keys,
+unknown fields, and the keys/names `__proto__`, `prototype`, and `constructor`.
+Every rejection must throw `TypeError` before returning any partial result.
+
+## Period and plan timeline
+
+`period` contains exactly `{ start, end }`. Both values are canonical ISO-8601
+UTC strings (`new Date(value).toISOString() === value`) and define a non-empty
+half-open interval `[start, end)`.
+
+`normalizePlanTimeline(plans, period)` validates and returns a deep-cloned array
+sorted by `tenantId`, `effectiveAt`, then `id`. A plan contains exactly:
+
+```js
+{
+  id, tenantId, currency, effectiveAt,
+  meters: {
+    api: [
+      { upTo: 100, unitPriceMicros: 250000 },
+      { upTo: null, unitPriceMicros: 500000 }
+    ]
+  }
+}
+```
+
+- `id`, `tenantId`, and meter names are non-empty trimmed strings and cannot be
+  poison names. Plan ids are globally unique. Effective times are unique per
+  tenant. A tenant uses one three-letter uppercase currency for its whole
+  timeline.
+- `effectiveAt` is canonical ISO UTC. A plan becomes active at that exact
+  instant and remains active until the next plan for that tenant.
+- `meters` is a non-empty plain object. Its keys are returned in lexical order.
+  Every tier array is dense and non-empty. Each tier contains exactly `upTo`
+  and `unitPriceMicros`.
+- `upTo` values are cumulative positive safe-integer boundaries, strictly
+  increasing. Exactly the final tier has `upTo: null`. `unitPriceMicros` is a
+  non-negative safe integer. One unit price is expressed in one millionth of a
+  currency minor unit.
+
+## Usage close
+
+`closeUsagePeriod(input)` accepts exactly `{ period, plans, events }`. Events
+have globally unique, non-empty trimmed ids and one of these exact shapes:
+
+```js
+{ id, kind: "usage", tenantId, meter, at, units }
+{ id, kind: "reversal", tenantId, at, targetId }
+```
+
+Every event time must be canonical and inside the period. `units` is a positive
+safe integer. A reversal must reference an existing usage event for the same
+tenant at or before the reversal time. One usage can be reversed at most once;
+a reversal cannot target another reversal.
+
+Resolve all valid reversals before rating, independent of input order. Rate the
+remaining usage in ascending `at`, then `id` order. Select the latest plan whose
+`effectiveAt <= usage.at`. A missing active plan or a meter absent from that plan
+is invalid input: throw `TypeError`; never skip or silently omit that usage. Tier
+consumption is cumulative per `(tenantId, planId, meter)`, so it is isolated
+between tenants and meters and resets on a plan change. One usage event may span
+multiple tiers.
+
+Use `BigInt` internally for every multiplication and sum. Do not convert a
+charge through `Number`. Round an invoice from micro-minor units to minor units
+exactly once, at close, using round-half-to-even with divisor `1_000_000`.
+
+Return exactly:
+
+```js
+{
+  period: { start, end },
+  invoices: [{
+    tenantId,
+    currency,
+    lines: [{
+      eventId, planId, meter, at, units,
+      allocations: [{
+        tierIndex, units,
+        unitPriceMicros, // decimal string
+        chargeMicros     // decimal string
+      }],
+      chargeMicros       // decimal string
+    }],
+    subtotalMicros,      // decimal string
+    totalMinor,          // decimal string
+    digest               // lowercase SHA-256
+  }],
+  reversedEventIds
+}
+```
+
+Invoices are ordered by `tenantId`; lines use rating order; allocation order is
+tier order; reversed ids are lexical. Create an invoice only for a tenant with
+at least one non-reversed usage. `digest` is SHA-256 of canonical JSON for the
+invoice without `digest`: object keys recursively sorted and array order kept.
+
+`billingSummary(result)` returns a deterministic Terminal/WebUI summary. The
+lines are joined with the actual LF character (`"\n"`), never the two literal
+characters backslash and `n`. The first line is:
+
+```text
+period=<start>..<end>; invoices=<count>; reversed=<count>
+```
+
+Then emit one line per invoice, in result order:
+
+```text
+tenant=<JSON string>; currency=<currency>; lines=<count>; subtotalMicros=<value>; totalMinor=<value>; digest=<digest>
+```
+
+Reject malformed result objects rather than displaying a misleading summary.
+Add focused integration tests if useful; change only the declared source/test
+scope.
+
+Run `npm test` when complete; it includes a fixed public happy-path contract for this scenario.

package/benchmarks/deep-logic-v1/prompts/transactional-config-merge.md

@@ -11,3 +11,5 @@ Requirements:
 - The operation is transactional: any validation failure throws and yields no partial object.
 
 Use Node's standard library only. Add focused tests if useful.
+
+Run `npm test` when complete; it includes a fixed public happy-path contract for this scenario.

package/benchmarks/deep-logic-v1/suite.json

@@ -1,11 +1,45 @@
 {
-  "schemaVersion": 1,
+  "schemaVersion": 2,
   "id": "deep-logic-v1",
   "title": "Piagent Deep Logic V1",
-  "description": "Paired current-model tasks with interacting invariants across event reconciliation, scheduling, layered policy, graph context, stream recovery, and transactional configuration.",
+  "description": "Paired current-model tasks with interacting invariants across event reconciliation, scheduling, layered policy, graph context, stream recovery, transactional configuration, and temporal usage billing.",
   "profile": "node-typescript",
-  "defaultRepeats": 2,
+  "defaultRepeats": 3,
   "timeoutSeconds": 1200,
+  "executionContract": {
+    "surfaces": ["piagent", "codex-cli"],
+    "model": "openai-codex/gpt-5.6-luna",
+    "thinking": "medium",
+    "codexMode": "controlled"
+  },
+  "assurance": {
+    "taskSource": "maintainer-authored-deep-work-archetypes",
+    "visibility": "public-suite-with-run-private-oracles",
+    "claimTier": "capability",
+    "generatedVariants": true,
+    "familyDisjointSplit": false,
+    "reviewed": true,
+    "refreshedAt": "2026-08-21"
+  },
+  "releaseGate": {
+    "minimumQualityScore": 9.5,
+    "minimumSafetyScore": 10,
+    "minimumReliabilityScore": 9.5,
+    "minimumWorkflowScore": 9.5,
+    "minimumCategoryScore": 9.5,
+    "minimumOutcomeScoreExclusive": 9.5,
+    "minimumPairedScenarios": 7,
+    "minimumComparableEfficiencyScenarios": 7,
+    "minimumRepeats": 3,
+    "maximumInfrastructureRetries": 0,
+    "maximumFreshTokenRatioUpper95": 0.8,
+    "maximumDurationRatioUpper95": 1.1,
+    "primaryEfficiencyEstimand": "failure-aware-family-ratio",
+    "requireEfficiencyClaim": true,
+    "requireFullSuiteForClaim": true,
+    "requireStableProviderWireSurface": true,
+    "requireCausalContextReceipt": true
+  },
   "scenarios": [
     {
       "id": "revision-event-reconciliation",
@@ -90,6 +124,20 @@
       "grader": "grade.mjs",
       "variantGenerator": "variant.mjs",
       "allowedChanges": ["src/config-transaction.js", "test/**"]
+    },
+    {
+      "id": "temporal-usage-billing-close",
+      "title": "Temporal usage billing close with exact audit",
+      "kind": "source-change",
+      "category": "financial-correctness",
+      "difficulty": "large",
+      "profile": "fullstack",
+      "lifecycle": "cold-start",
+      "fixture": "project",
+      "prompt": "prompts/temporal-usage-billing-close.md",
+      "grader": "grade.mjs",
+      "variantGenerator": "variant.mjs",
+      "allowedChanges": ["packages/billing/src/**", "apps/admin/src/billing-summary.js", "test/**"]
     }
   ]
 }

package/benchmarks/deep-logic-v1/variant.mjs

@@ -20,8 +20,29 @@ switch (scenarioId) {
   }; break;
   case "layered-policy-resolution": oracle.graderData = { protectedPath: `private/${token("vault")}/secret.json`, operation: token("read") }; break;
   case "budgeted-context-graph": oracle.graderData = { term: token("resolver"), budget: integer(8, 14) }; break;
-  case "resumable-stream-assembly": oracle.graderData = { first: token("hello"), second: token("world"), message: token("message") }; break;
+  case "resumable-stream-assembly": {
+    const astral = ["🙂", "🧠", "🚀"][integer(0, 2)];
+    oracle.graderData = {
+      first: token("hello"),
+      second: token("world"),
+      third: token("chunk"),
+      message: token("message"),
+      other: token("message"),
+      start: integer(2, 24),
+      astral
+    };
+    break;
+  }
   case "transactional-config-merge": oracle.graderData = { key: token("feature"), value: token("enabled") }; break;
+  case "temporal-usage-billing-close": oracle.graderData = {
+    tenantA: token("tenant"),
+    tenantB: token("tenant"),
+    meter: token("meter"),
+    plans: [token("plan"), token("plan"), token("plan")],
+    firstLimit: integer(4, 12),
+    secondLimit: integer(15, 28),
+    prices: [integer(110_000, 390_000), integer(410_000, 790_000), integer(810_000, 1_250_000)]
+  }; break;
   default: throw new Error(`unsupported deep logic scenario ${scenarioId}`);
 }
 

package/benchmarks/production-v1/spend-control.v1.json

@@ -0,0 +1,68 @@
+{
+  "schemaVersion": 1,
+  "suiteId": "production-v1",
+  "purpose": "Provider-spend control before the one claim-eligible 108-session token-quality-continuity result.",
+  "rootSeed": "production-v1-40-gate-v1-1370",
+  "execution": {
+    "surfaces": ["piagent", "codex-cli"],
+    "model": "openai-codex/gpt-5.6-luna",
+    "thinking": "medium",
+    "repeats": 3,
+    "infrastructureRetries": 0,
+    "stopAfterFailedPair": true
+  },
+  "stages": [
+    { "id": "S0", "cumulativeSessions": 0, "newSessions": 0, "mode": "preflight-only", "claimEligible": false },
+    { "id": "S12", "cumulativeSessions": 12, "newSessions": 12, "mode": "execute-and-pause", "claimEligible": false },
+    { "id": "S36", "cumulativeSessions": 36, "newSessions": 24, "mode": "resume-and-pause", "claimEligible": false },
+    { "id": "S72", "cumulativeSessions": 72, "newSessions": 36, "mode": "resume-and-pause", "claimEligible": false },
+    { "id": "S108", "cumulativeSessions": 108, "newSessions": 36, "mode": "resume-and-finalize", "claimEligible": true }
+  ],
+  "earlyDetection": {
+    "expectedFirstRepeatScenarioIds": [
+      "cli-double-dash",
+      "destructive-history-refusal",
+      "tenant-role-authorization",
+      "expiry-boundary",
+      "quoted-csv",
+      "unicode-search"
+    ],
+    "requiredCategoryCoverage": ["backend", "frontend", "data", "platform", "reliability", "security"],
+    "requiredLifecycleCoverage": ["steady-state", "cold-start"],
+    "requiredDifficultyCoverage": ["small", "medium", "large"]
+  },
+  "enforcement": {
+    "runnerConsumesThisArtifact": true,
+    "runnerBindsFrozenSeedAndExecution": true,
+    "runnerWritesAtomicPrivateStageDiagnostic": true,
+    "runnerBlocksProductionResumeWhenStageDiagnosticFails": true,
+    "durableStageStateSurvivesMissingPauseMarker": true,
+    "completeLedgerFinalizesWithoutProviderPreflight": true,
+    "stageDiagnosticArtifact": "stage-diagnostic.json",
+    "automaticTerminalOrAbortRules": [
+      "dirty-release-source-before-auth-tool-or-provider-preflight",
+      "piagent-unresolved-or-outcome-score-at-or-below-floor-via-stop-after-failed-pair",
+      "infrastructure-error-or-unknown-provider-attempt-usage-via-runner-abort",
+      "candidate-provenance-drift-via-execution-guard"
+    ],
+    "stageAdvanceRules": [
+      "clean-release-source",
+      "no-baseline-pass-piagent-fail",
+      "no-observed-paired-grade-regression",
+      "all-observed-piagent-outcomes-remain-above-the-release-floor",
+      "no-model-thinking-or-provider-wire-parity-drift",
+      "complete-privacy-safe-causal-context-receipt-with-closed-session-lifecycle",
+      "no-accepted-usage-completeness-failure",
+      "no-infrastructure-retry",
+      "no-unknown-provider-attempt-usage"
+    ],
+    "nonBlockingDiagnostics": [
+      "intermediate-fresh-token-ratios",
+      "normalized-api-equivalent-text-token-cost",
+      "duration",
+      "host-load"
+    ],
+    "operatorRule": "The commands pass this artifact's frozen values explicitly. After every production-v1 pause, resume recomputes the provider-free quality and continuity gate from the accepted ledger. Intermediate token, cost, duration, and host-load measurements are diagnostic only; only the complete S108 ledger may decide the fresh-token claim."
+  },
+  "claimBoundary": "Only S108 may be evaluated for the production-v1 fresh-token public-regression claim; S0, S12, S36 and S72 are spend-control diagnostics. Duration, host load, and normalized cost are reported but cannot block or support this claim."
+}

package/benchmarks/production-v1/suite.json

@@ -6,6 +6,38 @@
   "profile": "node-typescript",
   "defaultRepeats": 3,
   "timeoutSeconds": 900,
+  "executionContract": {
+    "surfaces": ["piagent", "codex-cli"],
+    "model": "openai-codex/gpt-5.6-luna",
+    "thinking": "medium",
+    "codexMode": "controlled"
+  },
+  "pricingSnapshot": {
+    "schemaVersion": 1,
+    "id": "openai-gpt-5-6-luna-2026-08-22",
+    "model": "openai-codex/gpt-5.6-luna",
+    "currency": "USD",
+    "unitTokens": 1000000,
+    "rates": {
+      "freshInput": 0.2,
+      "cachedInput": 0.02,
+      "output": 1.2
+    },
+    "cacheWrite": {
+      "basis": "fresh-input",
+      "multiplier": 1.25
+    },
+    "longContext": {
+      "thresholdInputTokens": 272000,
+      "condition": "per-request-input-greater-than",
+      "inputMultiplier": 2,
+      "outputMultiplier": 1.5
+    },
+    "source": {
+      "url": "https://developers.openai.com/api/docs/models/gpt-5.6-luna",
+      "retrievedAt": "2026-08-22"
+    }
+  },
   "assurance": {
     "taskSource": "maintainer-authored-production-archetypes",
     "visibility": "public-suite-with-run-private-oracles",
@@ -23,10 +55,17 @@
     "minimumCategoryScore": 9.5,
     "minimumOutcomeScoreExclusive": 9.5,
     "minimumPairedScenarios": 18,
-    "minimumComparableEfficiencyScenarios": 12,
+    "minimumComparableEfficiencyScenarios": 18,
     "minimumRepeats": 3,
-    "maximumFreshTokenRatioUpper95": 1,
-    "requireEfficiencyClaim": true
+    "maximumInfrastructureRetries": 0,
+    "primaryEfficiencyEstimand": "fixed-workload-family-ratio",
+    "maximumFreshTokenRatioUpper95": 0.6,
+    "requireEfficiencyClaim": true,
+    "requireNormalizedCostClaim": false,
+    "requireHostReadinessForClaim": false,
+    "requireFullSuiteForClaim": true,
+    "requireStableProviderWireSurface": true,
+    "requireCausalContextReceipt": true
   },
   "scenarios": [
     {

package/catalog/capabilities.json

@@ -26,8 +26,8 @@
           "path": "evals/scenarios/capability-resolution.json"
         },
         {
-          "byteSize": 6232,
-          "digest": "sha256:a2c44a910a440e972579c2a2ec372ee15cfb73b63b27d01c1e3a053c176d11bf",
+          "byteSize": 6350,
+          "digest": "sha256:3e0f3a94bd3a19df8c24c3e234078d6c3edc664b20a7a4838919450f4225ffca",
           "id": "base-policy",
           "kind": "policies",
           "path": "packages/piagent-core/policies/base-policy.json"
@@ -103,8 +103,8 @@
           "path": "packages/piagent-core/subagents/piagent-scout.md"
         },
         {
-          "byteSize": 2146,
-          "digest": "sha256:e8e18e1ef3a43db2acd559c40a99b31d8cd994cbfaaf1adc5ef9d2cc5e3721a6",
+          "byteSize": 2159,
+          "digest": "sha256:3e0b7071c80f471fb7ea67f91477c1f5e6d3f2574db492c3a9fae6788374a95d",
           "id": "piagent-worker",
           "kind": "subagents",
           "path": "packages/piagent-core/subagents/piagent-worker.md"
@@ -151,8 +151,8 @@
       },
       "artifacts": [
         {
-          "byteSize": 1950,
-          "digest": "sha256:84ac29dcbe0c692070be302707424ea16130a5938cff309c5d7755204b6c2dc1",
+          "byteSize": 2378,
+          "digest": "sha256:35d6757d0a8d2f8644b967fe82645fba3de430b53f23b5577c2e5e104dcccdc1",
           "id": "web-frontend",
           "kind": "adapters",
           "path": "adapters/web-frontend/profile.json"

package/docs/command-reference-vietnamese.md

@@ -502,8 +502,8 @@ Các lệnh này chạy ngoài Pi.
 | Command | Dùng khi nào |
 |---|---|
 | `npm install -g --ignore-scripts @earendil-works/pi-coding-agent@0.84.1` | Cài Pi CLI tương thích với release hiện tại. |
-| `npm install -g --ignore-scripts @piagent/platform@1.5.4` | Cài terminal helper `piagent-*` từ release tag hiện tại. |
-| `pi install git:github.com/Vt-mmm/piagent@v1.5.4` | Cài pinned release khi cần reproducible team setup. |
+| `npm install -g --ignore-scripts @piagent/platform@1.6.0` | Cài terminal helper `piagent-*` từ release tag hiện tại. |
+| `pi install git:github.com/Vt-mmm/piagent@v1.6.0` | Cài pinned release khi cần reproducible team setup. |
 | `pi install git:github.com/Vt-mmm/piagent` | Cài latest package platform cho máy cá nhân/sandbox. |
 | `piagent-update --check` | Báo version hiện tại vs version sẽ lên cho cả ba thành phần; không cài gì. |
 | `piagent-update` | Full update global một lệnh cho cả máy: Pi host → npm-global helper → Pi package, đúng thứ tự release yêu cầu. |
@@ -547,17 +547,17 @@ Các lệnh này chạy ngoài Pi.
 | `piagent-uninstall --apply` | Gỡ Pi package của platform khỏi Pi settings global. |
 | `piagent-uninstall --apply --with-addons --with-host` | Gỡ thêm pi-mcp-adapter, pi-subagents, pi-web-access và Pi host. |
 | `piagent-uninstall --apply --project /path/to/project` | Gỡ thêm state của platform trong project: profile, lock, `piagent-state/`. |
-| `piagent-benchmark` | Chạy smoke suite `core-v1`: paired Raw Pi/Piagent, 24 session, hidden grader + scope + workflow + exact usage. |
+| `piagent-benchmark` | Chạy smoke suite `core-v1`: paired Piagent/controlled `codex-cli` bằng Luna/medium, 24 session, hidden grader + scope + workflow + exact usage. |
 | `piagent-benchmark --dry-run` | Validate suite và xem số model session, không gọi model. |
-| `npm run benchmark:deep -- --dry-run` | Validate `deep-logic-v1`: 6 family difficulty large x 2 repeat x Piagent/`codex-cli` = 24 session, pin Luna/medium và chưa dùng quota. |
-| `npm run benchmark:deep` | Chạy paired deep-logic benchmark Luna/medium cho event/state, scheduler, policy, context graph, stream recovery và transactional config. |
+| `npm run benchmark:deep -- --dry-run` | Validate `deep-logic-v1`: 7 family difficulty large × 3 repeat × Piagent/`codex-cli` = 42 session, khóa Luna/medium và chưa dùng quota. |
+| `npm run benchmark:deep` | Chạy paired deep-logic benchmark Luna/medium cho event/state, scheduler, policy, context graph, stream recovery, transactional config và temporal usage billing chính xác. |
 | `piagent-benchmark --production --dry-run` | Xem ma trận production 18 family x 3 variant x 2 surface = 108 session, chưa dùng quota. |
 | `piagent-benchmark --production --surfaces piagent,codex-cli --model <provider/model> --thinking high --piagent-treatment candidate` | Chạy production release gate đa domain/profile/lifecycle với controlled Codex, treatment Piagent đã pin, paired outcome và 95% token-ratio confidence. |
 | `piagent-benchmark --piagent-treatment release-defaults\|local-safe\|candidate\|feature-off ...` | Pin treatment Piagent; chỉ surface `piagent` nhận feature env, manifest/resume/replay/report giữ nguyên treatment. |
 | `piagent-benchmark --codex-mode native ...` | Đo UX Codex theo cấu hình operator; protocol gate fail closed nên report không được claim tiết kiệm token. |
 | `piagent-benchmark --production --seed <value> ...` | Tái lập đúng generated variant của một production report riêng tư. |
 | `piagent-benchmark --production --scenarios <id,id> --repeats 1 ...` | Chẩn đoán family/rubric đã chọn; không đủ điều kiện nhận production verdict. |
-| `piagent-benchmark --production --infrastructure-retries 2 ...` | Retry đúng lỗi process chết trước usage; timeout/task failure không retry và vẫn chấm reliability. |
+| `piagent-benchmark --production --infrastructure-retries 2 ...` | Diagnostic recovery run; retry chỉ áp lỗi process chết trước usage, được report đầy đủ và làm production claim fail. |
 | `piagent-benchmark --production --retry-delay 60 ...` | Đặt backoff trước infrastructure retry; production mặc định 60 giây. |
 | `bash scripts/verify-local.sh` | Verify repo platform trước khi commit/tag. |
 | `bash scripts/verify-local.sh --offline` | Verify trong CI/máy sạch, bỏ qua local Pi model catalog. |

package/docs/context-engine.md

@@ -46,6 +46,10 @@ task
 - Telemetry không lưu prompt hoặc tool output thô. Nó lưu hash, kích thước, tool,
   model, thinking, active-tool count, usage, retrieval confidence và đường dẫn
   tương đối đã được guard redaction.
+- Mỗi telemetry row có provenance envelope do writer đóng sau payload; event
+  không thể ghi đè schema/provenance. Nếu source snapshot phải redact, receipt
+  chỉ giữ `sanitizedContentDigest` và `fileContentHash` trên nội dung đã sanitize;
+  raw-content digest không được tính hoặc lưu.
 
 Bốn cơ chế `PIAGENT_DYNAMIC_TOOLS`, `PIAGENT_AUTO_CONTEXT`,
 `PIAGENT_CONTEXT_TELEMETRY` và `PIAGENT_AUTO_RECOVERY` đều **bật mặc định**.
@@ -180,7 +184,9 @@ không bị trừ điểm. `contextSelections`, `contextSelectionsUsed` và
 ranking. Runtime chỉ đọc phần đuôi telemetry có giới hạn khi tính report hoặc
 feedback, nên lịch sử dài không làm chậm từng prompt theo thời gian.
 
-`contextWasteScore` nằm trong khoảng `0..100`, thấp hơn là tốt hơn:
+Khi toàn bộ evidence lane đầy đủ, `contextWasteScore` nằm trong khoảng `0..100`,
+thấp hơn là tốt hơn. Nếu coverage chưa đầy đủ, score chính là `null` và chỉ
+`contextWasteScoreEstimate` được giữ như chẩn đoán partial:
 
 ```text
 30% duplicate read rate

package/docs/distribution-standard.md

@@ -15,9 +15,9 @@ Repo này phải chạy được cho nhiều project/domain khác nhau. Vì vậ
 
 | Use case | Package source |
 |---|---|
-| Team pinned release | `git:github.com/Vt-mmm/piagent@v1.5.4` |
+| Team pinned release | `git:github.com/Vt-mmm/piagent@v1.6.0` |
 | Personal/sandbox dev | `git:github.com/Vt-mmm/piagent` |
-| Registry distribution | `npm:@piagent/platform@1.5.4` |
+| Registry distribution | `npm:@piagent/platform@1.6.0` |
 | Enterprise npm (fork under another scope) | `npm:@your-scope/platform@x.y.z` |
 | Local platform dev | `/path/to/piagent` |
 
@@ -27,7 +27,7 @@ Latest tiện cho máy cá nhân muốn nhận cập nhật nhanh. Pin tag/commi
 
 | Channel | Command | Target | Policy |
 |---|---|---|---|
-| `stable` | `bash scripts/install-global.sh --stable` | Helper release tag resolved to commit SHA, currently `v1.5.4` | Install the Pi package matching the helper. |
+| `stable` | `bash scripts/install-global.sh --stable` | Helper release tag resolved to commit SHA, currently `v1.6.0` | Install the Pi package matching the helper. |
 | `exact` | `bash scripts/install-global.sh --version vX.Y.Z --resolve-tag` | Requested tag resolved to commit SHA | Pi-package-only rollout, rollback, and incident recovery. |
 | `dev` | `bash scripts/install-global.sh --dev` | Moving Git source | Personal/sandbox only; do not commit into project settings. |
 | `local` | `bash scripts/install-global.sh --local` | Current checkout path | Platform development only. |
@@ -54,7 +54,7 @@ Root `package.json` có `pi` manifest trỏ tới:
 Do đó team có thể:
 
 ```bash
-pi install git:github.com/Vt-mmm/piagent@v1.5.4
+pi install git:github.com/Vt-mmm/piagent@v1.6.0
 ```
 
 Không cần biết internal folder `packages/piagent-core`. Source không pin chỉ dành cho personal/sandbox như bảng channel ở trên.
@@ -66,12 +66,12 @@ Team nên install global package một lần:
 ```bash
 node --version  # >= 22.19.0
 npm install -g --ignore-scripts @earendil-works/pi-coding-agent@0.84.1
-npm install -g --ignore-scripts @piagent/platform@1.5.4
+npm install -g --ignore-scripts @piagent/platform@1.6.0
 piagent-install --stable --dry-run
 piagent-install --stable
 ```
 
-`pi install git:github.com/Vt-mmm/piagent@v1.5.4` vẫn hợp lệ nếu chỉ cần cài Pi package. Lệnh đó không tự tạo các binary terminal `piagent-*`; muốn có helper global thì dùng `npm install -g --ignore-scripts @piagent/platform@1.5.4`.
+`pi install git:github.com/Vt-mmm/piagent@v1.6.0` vẫn hợp lệ nếu chỉ cần cài Pi package. Lệnh đó không tự tạo các binary terminal `piagent-*`; muốn có helper global thì dùng `npm install -g --ignore-scripts @piagent/platform@1.6.0`.
 
 Support matrix hiện tại: macOS Apple Silicon + Bash và Linux x64 + Bash đã được verify; macOS Intel + Bash và Linux ARM64 + Bash là supported target cần chạy smoke trước rollout; native Windows chưa phải target rollout team; WSL2 experimental. Chi tiết và version runtime nằm trong [release/install policy](release-install-policy.md).
 
@@ -121,7 +121,7 @@ Nếu muốn commit sẵn `.pi/piagent-profile.json` vào repo hoặc bootstrap
 ```bash
 bash scripts/setup.sh /path/to/project \
   --profile be-readonly-fe \
-  --package-source git:github.com/Vt-mmm/piagent@v1.5.4 \
+  --package-source git:github.com/Vt-mmm/piagent@v1.6.0 \
   --mcp-preset core \
   --subagents-preset safe
 ```

package/docs/en/architecture.md

@@ -44,6 +44,7 @@ The machine-readable rule is `architecture/layers.json`; `npm run architecture:c
 | Security foundation | `packages/piagent-core/security/` | Sensitive-data primitives | Workflow behavior |
 | Benchmark | `packages/piagent-core/benchmark/`, `benchmarks/` | Suite validation, scoring, evidence | Runtime enforcement |
 | WebUI contracts | `packages/piagent-webui/contracts/` | Wire types shared by browser and server | Any runtime behavior; it depends on nothing |
+| WebUI shared | `packages/piagent-webui/shared/` | Dependency-free deterministic helpers shared by browser, server, and gateway | Browser state, transport, filesystem access, or runtime policy |
 | WebUI client | `packages/piagent-webui/client/` | Browser views, view models, UI preferences | Server state, filesystem, Pi APIs |
 | WebUI server | `packages/piagent-webui/server/` | HTTP/WS endpoints, session reads, diff assembly | Browser rendering; it may not import the client |
 | WebUI extension | `packages/piagent-webui/extension/` | The in-Pi `/piagent-webui` command surface | Wire types the client also needs |

package/docs/languages.json

@@ -21,8 +21,8 @@
       "en": "README.md",
       "vi": "README.vi.md",
       "consistentAt": {
-        "en": "3d9082674ded9179175a10bb86a4a1c922faa269",
-        "vi": "5c396247582381eafe741042fc4259982a527381"
+        "en": "c2b6f830977bff9eff7ebdc97f1aa15502ce3e2c",
+        "vi": "a6533b41f285b3dc05a594e21cc208ca28b5569b"
       }
     },
     {
@@ -39,8 +39,8 @@
       "en": "docs/en/architecture.md",
       "vi": "docs/vi/architecture.md",
       "consistentAt": {
-        "en": "5bcb0aa311b360408ca73425744baee71e740a9b",
-        "vi": "b613cec25fa1737636121c11cb2c5aecb2e00375"
+        "en": "7902186a3bf9cc8c344bd27ea352cf4a6d5eae2a",
+        "vi": "64575dc18be0167324bfba396d7162c74af28048"
       }
     },
     {

package/docs/model-options.md

@@ -54,7 +54,10 @@ Shift+Ctrl+P    # cycle ngược
 Shift+Tab       # cycle thinking level
 ```
 
-Global setup của repo sẽ seed `enabledModels` vào `~/.pi/agent/settings.json`, nên sau OAuth anh chọn/đổi model bằng option selector của Pi.
+Global setup của repo sẽ seed các preset đã kiểm chứng và một catch-all
+`openai-codex/*` vào `~/.pi/agent/settings.json`. Vì các preset đứng trước glob,
+chúng giữ thinking level khuyến nghị; model Codex mới trong authenticated catalog
+vẫn tự xuất hiện trong scope mà không cần chờ Piagent phát hành lại.
 
 ## Kiểm tra model hiện có
 
@@ -97,7 +100,7 @@ off, minimal, low, medium, high, xhigh, max
 Không phải model nào cũng hỗ trợ mọi level. Pi sẽ clamp theo capability của model. Cách chọn:
 
 ```bash
-pi --model openai-codex/gpt-5.5:high
+pi --model openai-codex/gpt-5.6-sol:high
 pi --model anthropic/claude-sonnet-5:xhigh
 pi --thinking medium
 ```
@@ -113,7 +116,7 @@ pi --thinking medium
 | `openai-codex/gpt-5.3-codex-spark` | fast scout | hỏi nhanh, thao tác nhỏ, chi phí thấp |
 | `openai-codex/gpt-5.4-mini` | fast/cheap | scout nhẹ, docs, simple fix |
 | `openai-codex/gpt-5.4` | balanced | task bình thường |
-| `openai-codex/gpt-5.5` | balanced/hard default | default mạnh cho implement |
+| `openai-codex/gpt-5.5` | balanced/hard | model thế hệ trước vẫn được hỗ trợ khi có trong authenticated catalog |
 | `openai-codex/gpt-5.6-luna` | cost-sensitive/high-volume | workload nhanh, nhiều lượt, ưu tiên latency và chi phí |
 | `openai-codex/gpt-5.6-terra` | balanced | công việc hằng ngày cần cân bằng capability, speed và cost |
 | `openai-codex/gpt-5.6-sol` | frontier/quality-first | task phức tạp, long-horizon hoặc cần chất lượng cao nhất |
@@ -143,7 +146,7 @@ available nào trong authenticated provider catalog.
 | Preset | Model OpenAI Codex | Model Claude (Anthropic) | Khi dùng |
 |---|---|---|---|
 | Fast scout | `openai-codex/gpt-5.4-mini:low` | `anthropic/claude-haiku-4-5:low` | đọc nhanh, hỏi đáp, grep/scout nhẹ |
-| Balanced implement | `openai-codex/gpt-5.5:medium` | `anthropic/claude-sonnet-5:medium` | task source bình thường |
+| Balanced implement | `openai-codex/gpt-5.6-terra:medium` | `anthropic/claude-sonnet-5:medium` | task source bình thường |
 | Cost-sensitive volume | `openai-codex/gpt-5.6-luna:medium` | `anthropic/claude-haiku-4-5:low` | workload nhanh, nhiều lượt; đo quality gate trước khi promote |
 | Balanced implement | `openai-codex/gpt-5.6-terra:high` hoặc `openai-codex/gpt-5.5:high` | `anthropic/claude-sonnet-5:high` | task source hằng ngày, cân bằng capability/cost |
 | Frontier/quality-first | `openai-codex/gpt-5.6-sol:high` | `anthropic/claude-opus-4-7:xhigh` hoặc `anthropic/claude-opus-4-8:xhigh` | architecture, long-horizon, high-risk review |
@@ -155,7 +158,7 @@ Tên model có thể đổi theo Pi model catalog. Khi không chắc, ưu tiên
 Global setup mặc định:
 
 ```bash
-piagent-model-scope --preset full --default-model openai-codex/gpt-5.5:high
+piagent-model-scope --preset full --default-model openai-codex/gpt-5.6-sol:high
 ```
 
 Scope này ghi vào settings: