@exellix/ai-tasks 8.6.8 → 8.7.0

package/CHANGELOG.md

@@ -4,6 +4,14 @@ All notable changes to `@exellix/ai-tasks` are documented here.
 
 The published **npm version** always matches **`version`** in [`package.json`](package.json). If this file skips a semver, treat [`BREAKING-CHANGES.md`](BREAKING-CHANGES.md) and [`RUNTASK_REQUEST.md`](RUNTASK_REQUEST.md) as the source of truth for cross-version upgrades.
 
+## [8.7.0] - 2026-06-05
+
+### Changed
+
+- Bumped **`@exellix/ai-skills`** to **^6.4.0** and **`@exellix/xynthesis`** to **^4.5.0** (gateway **≥ 10.1.0**, **`@x12i/ai-profiles` ^3.0.0**, **`@x12i/activix` ^8.6.0**).
+- Added direct **`@x12i/ai-profiles` ^3.0.0** dependency so orchestrator model resolution aligns with ai-skills / xynthesis (avoids hoisted **2.1.x** from legacy narrix transitive paths).
+- README stack alignment table and gateway 10.x notes updated for the new minimums.
+
 ## [8.6.3] - 2026-06-05
 
 ### Fixed (CR-13)

package/README.md

@@ -10,12 +10,12 @@ Private Git/npm package for executing **tasks** using the Exellix execution stac
 
 | Package | Role in `runTask` | Minimum (this repo) |
 |---------|-------------------|---------------------|
-| `@x12i/ai-profiles` | Profile/choice → wire model (`catalogLane` required on resolve) | **2.1.1** |
-| `@exellix/xynthesis` | PRE synthesis, POST audit/polish, scoping, utilities, execution-strategy sidekick actions (`executeXynthesisAction` via `@x12i/funcx`) | **≥ 4.4.9** |
-| `@exellix/ai-skills` | MAIN `runSkill` (Optimixer caps, `ModelConfig.reasoningEffort`, gateway invoke) | **≥ 6.3.7** |
-| `@x12i/ai-gateway` | LLM wire for MAIN skill (transitive via ai-skills) | **≥ 10.0.6** |
+| `@x12i/ai-profiles` | Profile/choice → wire model (`catalogLane` required on resolve) | **3.0.0** |
+| `@exellix/xynthesis` | PRE synthesis, POST audit/polish, scoping, utilities, execution-strategy sidekick actions (`executeXynthesisAction` via `@x12i/funcx`) | **≥ 4.5.0** |
+| `@exellix/ai-skills` | MAIN `runSkill` (Optimixer caps, `ModelConfig.reasoningEffort`, gateway invoke) | **≥ 6.4.0** |
+| `@x12i/ai-gateway` | LLM wire for MAIN skill (transitive via ai-skills) | **≥ 10.1.0** |
 
-**Gateway 10.x (via `@exellix/ai-skills` ≥ 6.3.7):** The gateway **owns billing** — read **`response.metadata.costUsd`**, **`costStatus`**, and token usage only; do **not** post-price with `@x12i/ai-tools`. Every invoke requires explicit **`model`** and **`maxTokens`** (Optimixer supplies `maxTokens` on MAIN before `gateway.invoke()`). Removed upstream: default model, flex-md token auto-fill, packaged instruction blocks, and the 500 ms between-call rate limit. On Activix rows, prefer root **`cost`** / **`costUsd`** and **`outer.cost`** over **`outer.metadata`** for billing. Failed invokes expose **`error.metadata`** (`GatewayInvokeRejectionMetadata`). Full migration rules: **[UPGRADING_AI_GATEWAY_10.md](../ai-skills/docs/UPGRADING_AI_GATEWAY_10.md)** in `@exellix/ai-skills`.
+**Gateway 10.x (via `@exellix/ai-skills` ≥ 6.4.0):** The gateway **owns billing** — read **`response.metadata.costUsd`**, **`costStatus`**, and token usage only; do **not** post-price with `@x12i/ai-tools`. Every invoke requires explicit **`model`** and **`maxTokens`** (Optimixer supplies `maxTokens` on MAIN before `gateway.invoke()`). Removed upstream: default model, flex-md token auto-fill, packaged instruction blocks, and the 500 ms between-call rate limit. On Activix rows, prefer root **`cost`** / **`costUsd`** and **`outer.cost`** over **`outer.metadata`** for billing. Failed invokes expose **`error.metadata`** (`GatewayInvokeRejectionMetadata`). Full migration rules: **[UPGRADING_AI_GATEWAY_10.md](../ai-skills/docs/UPGRADING_AI_GATEWAY_10.md)** in `@exellix/ai-skills`.
 
 **Stored `modelConfig` slots** must use explicit **ai-profiles** **`profile/choice`** keys (`cheap/default`, `pro/default`, …). Bare profile names (`cheap`, `pro`), `profile@choice`, registry shortcuts, and legacy tier aliases (`weak` / `strong`) are **rejected** at validation — not expanded at invoke.
 
@@ -1060,8 +1060,8 @@ Orchestrators send **model** + **sampling** + **`reasoningEffort`** + (for xynth
 
 | Phase | Package | Caller sends | Package owns |
 |-------|---------|--------------|--------------|
-| **MAIN** | `@exellix/ai-skills` ≥6.3 | `modelConfig` → `{ model, temperature, topP, reasoningEffort, … }` | Optimixer + Catalox skill catalog (`maxTokens` on `ModelConfig` is rejected); gateway **`@x12i/ai-gateway` ≥10.0.6** supplies wire `maxTokens` and authoritative **`costUsd`** / **`costStatus`** on invoke metadata; **one automatic re-invoke** when output hits token limit and Optimixer returns `retryPrediction` |
-| **PRE / POST / scoping / utility** | `@exellix/xynthesis` ≥4.4 | `outputExpectation` (required on every hop), optional `reasoningEffort`, `temperature`, `topP` | `resolveEffectiveMaxTokens` inside `executeXynthesisAction` (default **`@x12i/funcx`** invoker); authoritative billing from funcx/gateway engines — xynthesis is pass-through only; **same one-shot max-token retry** via Optimixer `retryPrediction` |
+| **MAIN** | `@exellix/ai-skills` ≥6.4 | `modelConfig` → `{ model, temperature, topP, reasoningEffort, … }` | Optimixer + Catalox skill catalog (`maxTokens` on `ModelConfig` is rejected); gateway **`@x12i/ai-gateway` ≥10.1** supplies wire `maxTokens` and authoritative **`costUsd`** / **`costStatus`** on invoke metadata; **one automatic re-invoke** when output hits token limit and Optimixer returns `retryPrediction` |
+| **PRE / POST / scoping / utility** | `@exellix/xynthesis` ≥4.5 | `outputExpectation` (required on every hop), optional `reasoningEffort`, `temperature`, `topP` | `resolveEffectiveMaxTokens` inside `executeXynthesisAction` (default **`@x12i/funcx`** invoker); authoritative billing from funcx/gateway engines — xynthesis is pass-through only; **same one-shot max-token retry** via Optimixer `retryPrediction` |
 
 **Xynthesis `outputExpectation`** is sizing/density **intent** for Optimixer — not a literal token count. ai-tasks resolves a per-stage default when the caller omits it (`resolveOutputExpectation` / `resolveLlmOutputExpectationForXynthesis`).
 
@@ -1245,9 +1245,9 @@ type LlmCallObservation =
     };
 ```
 
-**`InvokeAttemptSummary`** (xynthesis ≥ 4.4) carries `{ jobId, taskId, modelRequested, modelResolved, maxTokensFromCaller, maxTokensEffective, modelUsedFromProvider, usage, routing, costUsd, costStatus, traceKind, executionMetadata }`. USD cost is **authoritative from `@x12i/funcx`** — xynthesis does not calculate pricing locally.
+**`InvokeAttemptSummary`** (xynthesis ≥ 4.5) carries `{ jobId, taskId, modelRequested, modelResolved, maxTokensFromCaller, maxTokensEffective, modelUsedFromProvider, usage, routing, costUsd, costStatus, traceKind, executionMetadata }`. USD cost is **authoritative from `@x12i/funcx`** — xynthesis does not calculate pricing locally.
 
-**`RunSkillDiagnostics`** (ai-skills ≥ 6.3) carries `{ trace: { step, timing, routing, usage, costUsd, costStatus, modelUsed, attempts[], rawProviderPayload?, invokeRequest? }, ... }`. USD cost is **authoritative from `@x12i/ai-gateway` ≥10.0.6** — ai-skills normalizes gateway `metadata` only (`mapGatewayInvokeToTrace`, `traceToDiagnostics` re-exported from `@exellix/ai-tasks`). Gateway `costStatus: "priced"` is represented as `costUsd`; `"unpriced"` surfaces as `costStatus: "unpriced"`. For non-trace MAIN failures, read **`(error as Error & { metadata?: GatewayInvokeRejectionMetadata }).metadata`** (re-exported from `@exellix/ai-tasks`) — do not scrape error strings.
+**`RunSkillDiagnostics`** (ai-skills ≥ 6.4) carries `{ trace: { step, timing, routing, usage, costUsd, costStatus, modelUsed, attempts[], rawProviderPayload?, invokeRequest? }, ... }`. USD cost is **authoritative from `@x12i/ai-gateway` ≥10.1** — ai-skills normalizes gateway `metadata` only (`mapGatewayInvokeToTrace`, `traceToDiagnostics` re-exported from `@exellix/ai-tasks`). Gateway `costStatus: "priced"` is represented as `costUsd`; `"unpriced"` surfaces as `costStatus: "unpriced"`. For non-trace MAIN failures, read **`(error as Error & { metadata?: GatewayInvokeRejectionMetadata }).metadata`** (re-exported from `@exellix/ai-tasks`) — do not scrape error strings.
 
 ### Typed errors (instanceof-friendly)
 
@@ -2589,9 +2589,9 @@ ISC
 
 ## Related Packages
 
-- [`@exellix/ai-skills`](https://github.com/exellix/ai-skills) — MAIN skill execution (`runSkill`, Catalox catalog, gateway invoke; **≥ 6.3.7** / gateway **≥ 10.0.6**)
-- [`@exellix/xynthesis`](https://github.com/exellix/xynthesis) — PRE/POST LLM hops (`executeXynthesisAction`, sidekick actions)
-- [`@x12i/ai-gateway`](https://github.com/athenices/ai-gateway) — LLM gateway for MAIN skill (transitive via ai-skills ≥6.3.7, **≥ 10.0.6**)
+- [`@exellix/ai-skills`](https://github.com/exellix/ai-skills) — MAIN skill execution (`runSkill`, Catalox catalog, gateway invoke; **≥ 6.4.0** / gateway **≥ 10.1.0**)
+- [`@exellix/xynthesis`](https://github.com/exellix/xynthesis) — PRE/POST LLM hops (`executeXynthesisAction`, sidekick actions; **≥ 4.5.0**)
+- [`@x12i/ai-gateway`](https://github.com/athenices/ai-gateway) — LLM gateway for MAIN skill (transitive via ai-skills ≥6.4, **≥ 10.1.0**)
 - [`@x12i/execution-memory-manager`](https://github.com/athenices/execution-memory-manager) — Memory management utilities
 
 ## Related Documentation

package/dist/execution-strategies/runExecutionStrategyViaXynthesis.d.ts

@@ -1,5 +1,5 @@
 /**
- * Planner / optimizer via `@exellix/xynthesis` execution-strategy actions (≥ 4.4.0).
+ * Planner / optimizer via `@exellix/xynthesis` execution-strategy actions (≥ 4.5.0).
  */
 import { setExecutionStrategyActionInvoker } from "@exellix/xynthesis";
 import type { RunTaskModelConfig } from "../types/model-config.js";

package/dist/execution-strategies/runExecutionStrategyViaXynthesis.js

@@ -1,5 +1,5 @@
 /**
- * Planner / optimizer via `@exellix/xynthesis` execution-strategy actions (≥ 4.4.0).
+ * Planner / optimizer via `@exellix/xynthesis` execution-strategy actions (≥ 4.5.0).
  */
 import { randomUUID } from "node:crypto";
 import { runExecutionPlan, runExecutionEvaluateResult, setExecutionStrategyActionInvoker, resolveOutputExpectation, } from "@exellix/xynthesis";

package/dist/invocation/defaultAiProfilesResolveOptions.d.ts

@@ -1,5 +1,5 @@
 import type { ProfileCatalogLane, RegistrySourceMode, ResolveAIProfileOptions } from "@x12i/ai-profiles";
-/** Matches `@exellix/xynthesis` `XYNTHESIS_DEFAULT_CATALOG_LANE` (ai-profiles v2 text lane). */
+/** Matches `@exellix/xynthesis` `XYNTHESIS_DEFAULT_CATALOG_LANE` (ai-profiles v3 text lane). */
 export declare const AI_TASKS_DEFAULT_CATALOG_LANE: "text";
 /** Matches `@exellix/xynthesis` `getXynthesisAiProfilesSource()` (honors `XYNTHESIS_AI_PROFILES_SOURCE`). */
 export declare function getAiTasksAiProfilesSource(): RegistrySourceMode;

package/dist/invocation/defaultAiProfilesResolveOptions.js

@@ -1,7 +1,7 @@
 import { normalizeProfileSlotInput } from "../utils/aiProfileModelFormat.js";
 import { resolvePreferOpenRouterPolicy, } from "./preferOpenRouterPolicy.js";
 import { parseProfileSlot } from "./parseProfileSlot.js";
-/** Matches `@exellix/xynthesis` `XYNTHESIS_DEFAULT_CATALOG_LANE` (ai-profiles v2 text lane). */
+/** Matches `@exellix/xynthesis` `XYNTHESIS_DEFAULT_CATALOG_LANE` (ai-profiles v3 text lane). */
 export const AI_TASKS_DEFAULT_CATALOG_LANE = "text";
 /** Matches `@exellix/xynthesis` `getXynthesisAiProfilesSource()` (honors `XYNTHESIS_AI_PROFILES_SOURCE`). */
 export function getAiTasksAiProfilesSource() {

package/dist/planWebScopeQuestions/index.d.ts

@@ -1,6 +1,6 @@
 /**
  * AI-driven planning of explicit web-scope questions (Studio → `narrix.webScopeQuestions`).
- * Default path: xynthesis `plan-web-scope-questions` (≥ `@exellix/xynthesis` 4.4.0).
+ * Default path: xynthesis `plan-web-scope-questions` (≥ `@exellix/xynthesis` 4.5.0).
  */
 import { setPlanWebScopeQuestionsActionInvoker } from "@exellix/xynthesis";
 export { setPlanWebScopeQuestionsActionInvoker };

package/dist/planWebScopeQuestions/index.js

@@ -1,6 +1,6 @@
 /**
  * AI-driven planning of explicit web-scope questions (Studio → `narrix.webScopeQuestions`).
- * Default path: xynthesis `plan-web-scope-questions` (≥ `@exellix/xynthesis` 4.4.0).
+ * Default path: xynthesis `plan-web-scope-questions` (≥ `@exellix/xynthesis` 4.5.0).
  */
 import { randomUUID } from "node:crypto";
 import { runPlanWebScopeQuestionsAction, setPlanWebScopeQuestionsActionInvoker, resolveOutputExpectation, } from "@exellix/xynthesis";

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@exellix/ai-tasks",
-  "version": "8.6.8",
+  "version": "8.7.0",
   "description": "Task orchestration for the Exellix stack: runTask() with local handlers or LLM-backed execution, task-scoped memory/context enrichment, and executor dispatch via @exellix/ai-skills. ERC-compliant.",
   "type": "module",
   "main": "dist/index.js",
@@ -60,7 +60,7 @@
     "node": ">=20"
   },
   "dependencies": {
-    "@exellix/ai-skills": "^6.3.7",
+    "@exellix/ai-skills": "^6.4.0",
     "@exellix/memorix-narrix-adapter": "^2.0.0",
     "@exellix/narrix-adapter-chat": "^2.0.0",
     "@exellix/narrix-adapter-docs": "^2.0.0",
@@ -72,12 +72,14 @@
     "@exellix/narrix-ingest": "^2.0.0",
     "@exellix/narrix-runner": "^2.0.0",
     "@exellix/narrix-web-scoper": "^2.0.0",
-    "@exellix/xynthesis": "^4.4.9",
-    "@x12i/activix": "^8.5.0",
+    "@exellix/xynthesis": "^4.5.0",
+    "@x12i/activix": "^8.6.0",
+    "@x12i/ai-profiles": "^3.0.0",
     "@x12i/catalox": "^5.1.3",
     "@x12i/env": "^4.0.1",
     "@x12i/execution-memory-manager": "^1.2.0",
     "@x12i/logxer": "^4.6.0",
+    "@x12i/optimixer": "^3.4.0",
     "@x12i/rendrix": "^4.3.0",
     "@x12i/search-adapter": "^1.5.1",
     "handlebars": "^4.7.8",