@exellix/ai-tasks 8.5.2 → 8.5.3

package/CHANGELOG.md

@@ -20,21 +20,17 @@ The published **npm version** always matches **`version`** in [`package.json`](p
 
 - `setFuncxExecutionStrategyInvoker`, `setResearchPlanQuestionsFuncxInvoker`, direct `@x12i/funcx` dependency.
 
-## [Unreleased]
+## [8.5.3] - 2026-06-04
 
-### Changed (breaking)
-
-- **`RunTaskRequest.modelConfig` is required** on every `runTask()` call (all three slots). No env-based or hardcoded model defaults (`SYNTHESIS_MODEL`, `AUDIT_MODEL`, `POST_STEP_MODEL`, `"balanced"`, etc.) for model selection.
-
-### Fixed
+### Changed
 
-- **PRE/MAIN model routing:** Root `RunTaskRequest.llmCall` is **MAIN-only** — no longer copied into PRE synthesis compile. When `llmCall.model` duplicates `preActionModel` while `skillModel` differs (graph-engine PRE leakage), MAIN uses `skillModel`. Validation warning `MODEL_CONFIG_LLM_CALL_PRE_MAIN_COLLISION`.
+- Bumped **`@exellix/xynthesis`** to **^4.4.5** and **`@exellix/ai-skills`** to **^6.0.2** for Optimixer **max-token retry** on PRE/POST (xynthesis) and MAIN (ai-skills): one automatic re-invoke when output hits the token limit and Optimixer returns **`retryPrediction`** (no host **`maxTokens`** required).
 
-## [8.4.0] - 2026-06-01
+### Added
 
-### Changed (breaking)
+- Unit test **`runPostStepLlmCall.maxTokenRetry.test.ts`** (mock Optimixer + synthesis invoker; no live LLM).
 
-- **`RunTaskRequest.modelConfig`:** **3-slot triplet only** — `preActionModel`, `skillModel`, `postActionModel`. **`xynthesisModel` removed** (validation rejects with `NON_CANONICAL_MODEL_CONFIG`). PRE uses `preActionModel`; POST uses `postActionModel`.
+## [8.4.0] - 2026-06-01 — `preActionModel`, `skillModel`, `postActionModel`. **`xynthesisModel` removed** (validation rejects with `NON_CANONICAL_MODEL_CONFIG`). PRE uses `preActionModel`; POST uses `postActionModel`.
 - **`@x12i/ai-profiles` ^2.0.0:** Required `catalogLane` on profile resolution; ai-tasks defaults `"text"` ( `"image"` for `vision` ). Registry source defaults to `auto`.
 - **`@exellix/xynthesis` ^4.2.1:** Minimum for ai-profiles v2 alignment.
 

package/README.md

@@ -1071,8 +1071,8 @@ Orchestrators send **model** + **sampling** + **`reasoningEffort`** + (for xynth
 
 | Phase | Package | Caller sends | Package owns |
 |-------|---------|--------------|--------------|
-| **MAIN** | `@exellix/ai-skills` ≥6 | `modelConfig` → `{ model, temperature, topP, reasoningEffort, … }` | Optimixer + Catalox skill catalog (`maxTokens` on `ModelConfig` is rejected) |
-| **PRE / POST / scoping / utility** | `@exellix/xynthesis` ≥4.3 | `outputExpectation` (required on every hop), optional `reasoningEffort`, `temperature`, `topP` | `resolveEffectiveMaxTokens` inside `executeXynthesisAction` |
+| **MAIN** | `@exellix/ai-skills` ≥6 | `modelConfig` → `{ model, temperature, topP, reasoningEffort, … }` | Optimixer + Catalox skill catalog (`maxTokens` on `ModelConfig` is rejected); **one automatic re-invoke** when output hits token limit and Optimixer returns `retryPrediction` |
+| **PRE / POST / scoping / utility** | `@exellix/xynthesis` ≥4.3 | `outputExpectation` (required on every hop), optional `reasoningEffort`, `temperature`, `topP` | `resolveEffectiveMaxTokens` inside `executeXynthesisAction`; **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`).
 

package/documenations/funcx-catalog-hosting-checklist.md

@@ -15,15 +15,19 @@ Use this checklist when **`run(functionId, payload)`** must resolve (custom host
 
 Constants in this repo: [`src/execution-strategies/constants.ts`](../src/execution-strategies/constants.ts) — `FUNCX_EXECUTION_PLAN_FUNCTION_ID`, `FUNCX_EXECUTION_EVALUATE_RESULT_FUNCTION_ID`.
 
-## 2. Optional function ID (web-scope via FuncX)
+## 2. Research / web-scope function ID
 
-| Capability | Canonical `functionId` |
-|------------|----------------------|
-| Research / web-scope questions | `research/plan-questions` |
+| Capability | Canonical `functionId` | Registry key @ 4.4.0 |
+|------------|----------------------|----------------------|
+| Research / web-scope questions | `research/plan-questions` | `research-plan-questions` |
 
-Used only when callers run **`runPlanWebScopeQuestions({ backend: "funcx", … })`** or when another host calls **`run()`** with the payload from **`buildResearchPlanQuestionsPayload`** (see [`genericExecutionFuncxEnvelope.ts`](../src/execution-strategies/genericExecutionFuncxEnvelope.ts)).
+**@exellix/ai-tasks ≥ 8.5** calls **`@exellix/xynthesis`** `plan-web-scope-questions` (not direct `run()`). Use this id for smoke tests, custom hosts, or when xynthesis sets **`XYNTHESIS_FUNCX_SIDEKICK=1`**.
 
-Constant: **`FUNCX_RESEARCH_PLAN_QUESTIONS_FUNCTION_ID`**.
+Payload: **`buildResearchPlanQuestionsPayload`** ([`genericExecutionFuncxEnvelope.ts`](../src/execution-strategies/genericExecutionFuncxEnvelope.ts)). Constant: **`FUNCX_RESEARCH_PLAN_QUESTIONS_FUNCTION_ID`** (re-export from `@x12i/funcx/functions` preferred).
+
+## 2b. Pre/post sidekick ids (not in 4.4.0 registry yet)
+
+See [**funcx-pre-post-sidekick-actions.md**](./upstream-feature-requests/funcx-pre-post-sidekick-actions.md) §1 — `pre/synthesize`, `post/audit`, `post/fix`, `post/audit-checklist`, etc. Catalox seeds already reference these ids from xynthesis `sidekickFuncxCatalogMap.ts`.
 
 ---
 

package/documenations/funcx-scoping-integration-gaps.md

@@ -8,9 +8,9 @@ This package routes **AI scoping** (and any other callers of `runLlmTextCall`) t
 
 **Need:** Every internal call used to carry stable `jobId` and `agentId` (and sometimes skill context) so logs and activity backends can tie completions to a task run.
 
-**Update (@x12i/funcx ≥ 3.6):** `AttributionContext` now includes optional **`jobId`**, **`taskId`**, and **`agentId`** (alongside `functionId`, `projectId`, `traceId`, `tags`). OpenRouter attribution can use `formatOpenRouterUserField(attribution)` where applicable.
+**Update (@x12i/funcx ≥ 3.6 / 4.4.0):** `AttributionContext` includes **`jobId`**, **`taskId`**, **`agentId`**. For **`run()`** with generic envelopes, use **`buildAskAttribution(implFunctionId, envelope)`** from `@x12i/funcx/functions` — it merges `attribution` plus `runId` / `subjectId` / `actorId` and `tags` (see [funcx-generic-xynthesis-hosting.md](./upstream-feature-requests/funcx-generic-xynthesis-hosting.md) §1.3).
 
-**Remaining gap for other call sites:** Not every ai-tasks code path sets these fields on `ask()` yet (e.g. narrow scoping helpers may still omit them). Prefer threading identity from `RunTaskRequest` into `AskOptions.attribution` wherever FuncX is invoked directly.
+**Remaining gap:** ai-tasks **scoping** (`runScopingCall`) may still omit full attribution on `ask()`. xynthesis execution/sidekick paths set attribution via envelope builders when FuncX mode is enabled.
 
 ## 2. High-level “one completion” helper
 

package/documenations/upstream-feature-requests/README.md

@@ -17,10 +17,10 @@ Fix reports filed for sibling packages. Hand these to the package owners; after
 
 | Package | Document | Status |
 |---------|----------|--------|
-| `@x12i/funcx` | [**funcx-generic-xynthesis-hosting.md**](./funcx-generic-xynthesis-hosting.md) | **open** — template `args`, post-step/scoping generics, xynthesis should delegate to `run()` |
-| `@x12i/funcx` | [**funcx-pre-post-sidekick-actions.md**](./funcx-pre-post-sidekick-actions.md) | **open** — built-ins for `pre/synthesize`, `post/audit`, … + Catalox `funcx.functionId` mapping |
-| `@exellix/xynthesis` | `src/catalog/sidekickFuncxCatalogMap.ts` | **shipped (mapping)** — enable with `XYNTHESIS_FUNCX_SIDEKICK=1` after FuncX built-ins land |
-| `@exellix/ai-tasks` | [funcx-scoping-integration-gaps.md](../funcx-scoping-integration-gaps.md) §6 | **partial** — envelope adapters stable; 8.5+ calls xynthesis actions not `run()` |
+| `@x12i/funcx` **4.4.0** | [**funcx-generic-xynthesis-hosting.md**](./funcx-generic-xynthesis-hosting.md) | **partial** — execution/research envelope + built-ins **shipped**; template-vars helper, `runGenericExecution`, sampling on `RunOptions` **open** |
+| `@x12i/funcx` | [**funcx-pre-post-sidekick-actions.md**](./funcx-pre-post-sidekick-actions.md) | **open** — `pre/synthesize`, `post/*` built-ins; execution wire-only (FR-PRE-POST-6) |
+| `@exellix/xynthesis` | `sidekickFuncxCatalogMap.ts`, `sidekickFuncxEnvelope.ts` | **shipped** — Catalox `funcx.functionId` on seeds; `XYNTHESIS_FUNCX_SIDEKICK=1` gates `run()` (not wired in gateway yet) |
+| `@exellix/ai-tasks` | `auditChecklistFuncxEnvelope.ts`, [funcx-scoping-integration-gaps.md](../funcx-scoping-integration-gaps.md) §6 | **partial** — envelopes + adapters; 8.5+ uses xynthesis actions for execution/web-scope |
 
 ## Older / parallel tracks
 

package/documenations/upstream-feature-requests/funcx-generic-xynthesis-hosting.md

@@ -1,294 +1,268 @@
 # `@x12i/funcx` — generic envelope hosting for xynthesis-domain capabilities
 
-**Filed by:** `@exellix/ai-tasks`  
-**Consumers:** `@exellix/xynthesis` (LLM hops), `@exellix/ai-tasks` (envelope builders + adapters)  
-**Out of scope:** `@exellix/ai-skills` MAIN gateway prompts (skill templates, `instructions` / `prompt` on `RunTaskRequest`)
+**Filed by:** `@exellix/ai-tasks` + `@exellix/xynthesis`  
+**Baseline reviewed:** `@x12i/funcx` **4.4.0** (npm; `xynthesis` dependency `^4.4.0`)  
+**Consumers:** `@exellix/xynthesis` 4.4+ (LLM orchestration), `@exellix/ai-tasks` 8.5+ (envelope builders + adapters)  
+**Out of scope:** `@exellix/ai-skills` MAIN gateway prompts
 
 **Related:**
 
-- [`funcx-scoping-integration-gaps.md`](../funcx-scoping-integration-gaps.md) — scoping `ask()` gaps + §6 execution-strategy wire contracts
-- [`funcx-catalog-hosting-checklist.md`](../funcx-catalog-hosting-checklist.md) — deploy checklist for `run()` resolution
-- [`xynthesis-execution-strategies-option-a.md`](./xynthesis-execution-strategies-option-a.md) — **shipped** xynthesis 4.4 sidekick actions (interim: disk templates + `FuncxInvoker.ask`)
-- Envelope builders (stable): [`genericExecutionFuncxEnvelope.ts`](../../src/execution-strategies/genericExecutionFuncxEnvelope.ts)
-- Xynthesis templates today (duplicate host): `xynthesis/templates/execution-plan/`, `execution-evaluate-result/`, `plan-web-scope-questions/`
+- [**funcx-pre-post-sidekick-actions.md**](./funcx-pre-post-sidekick-actions.md) — pre/post sidekick built-ins + `SidekickGenericEnvelope`
+- [`funcx-scoping-integration-gaps.md`](../funcx-scoping-integration-gaps.md) §6 — execution-strategy adapter contracts
+- [`funcx-catalog-hosting-checklist.md`](../funcx-catalog-hosting-checklist.md) — deploy / smoke-test checklist
+- Consumer map: `xynthesis/src/catalog/sidekickFuncxCatalogMap.ts`, `xynthesis/src/sidekickFuncxEnvelope.ts`
+- Envelope builders: [`genericExecutionFuncxEnvelope.ts`](../../src/execution-strategies/genericExecutionFuncxEnvelope.ts), [`auditChecklistFuncxEnvelope.ts`](../../src/post-steps/audit/auditChecklistFuncxEnvelope.ts)
 
 ---
 
 ## 0. Target architecture
 
-For every **xynthesis-domain** LLM capability (not ai-skills MAIN):
+| Layer | Responsibility |
+|-------|----------------|
+| **FuncX** | Host prompts (Catalox `fx/*` content + `content:primitives:sync`), validate I/O, `run(functionId, envelope, runOptions)` |
+| **xynthesis** | Model resolve, Optimixer / `outputExpectation`, JSON parse, Activix, `InvokeAttemptSummary`; gate FuncX prompts with `XYNTHESIS_FUNCX_SIDEKICK=1` |
+| **ai-tasks** | Build envelopes; merge adapted JSON into `RunTaskRequest`; no inline `DEFAULT_SYSTEM` for migrated steps |
 
-1. **Wire:** `GenericExecutionEnvelope` — `goal`, `input`, `context`, optional `result`, `args`, `attribution`.
-2. **Prompt host:** FuncX function (built-in or Catalox content) — templates read envelope fields and **`args`** for per-template customization (guidelines, caps, variant keys).
-3. **Orchestration:** `@exellix/xynthesis` owns model resolution, Optimixer / `outputExpectation`, JSON parse, Activix, `InvokeAttemptSummary` — ideally by calling **`run(functionId, envelope, options)`** instead of re-rendering duplicate templates and calling `Client.ask` directly.
-4. **ai-tasks:** Builds envelopes only; merges adapted JSON into `RunTaskRequest` (planner/optimizer/web-scope). No inline system prompts for these paths.
+**Two envelope families** (do not conflate):
 
-**Today (gap):** FuncX already ships built-ins `execution-plan`, `execution-evaluate-result`, `research-plan-questions` with envelope-shaped I/O, but **xynthesis 4.4 re-hosts prompts** under sidekick templates and uses `executeXynthesisAction` + `FuncxInvoker.ask`. **Post-steps and AI scoping** still use **caller-built** `systemPrompt` / `userPrompt` strings in ai-tasks (partially duplicated vs xynthesis `templates/audit`, `templates/fix`).
+1. **`GenericExecutionEnvelope`** — `@x12i/funcx/functions` type for **execution / research** built-ins (`execution/plan`, `execution/evaluate-result`, `research/plan-questions`, …).
+2. **`SidekickGenericEnvelope`** — defined in **xynthesis** (`sidekickFuncxEnvelope.ts`) for **pre/post sidekick** built-ins (`pre/synthesize`, `post/audit`, …). FuncX should accept the same *shape* at `run()` time; a dedicated exported type is optional (FR-PRE-POST-8).
 
 ---
 
-## 1. Audit — where instructions live
+## 1. FuncX 4.4.0 — shipped structure (source of truth)
 
-| Capability | Prompt / instructions today | Wire today | Generic envelope? | FuncX `run()`? |
-|------------|----------------------------|------------|-------------------|----------------|
-| **execution-plan** | `xynthesis/templates/execution-plan/*` + `buildExecutionStrategyPrompts` | xynthesis `RunExecutionPlanRequest` | Yes (ai-tasks builds payload) | Built-in exists; **not used** by xynthesis 4.4 |
-| **execution-evaluate-result** | Same pattern | xynthesis request + `result` | Yes | Built-in exists; **not used** |
-| **plan-web-scope-questions** | Same pattern | `goal` / `input` / `context` / `args` | Yes | `research-plan-questions` built-in; **not used** |
-| **synthesis (PRE)** | xynthesis `templates/synthesis/*` | `SidekickInput` + rendered skill text | **Sidekick envelope** (FR-PRE-POST) | **`pre/synthesize`** — **missing** |
-| **post-audit** | **ai-tasks** `loadAuditTemplates` + `DEFAULT_SYSTEM` | Pre-built prompts → `executeXynthesisAction` | **Sidekick envelope** | **`post/audit-checklist`** — **missing** |
-| **post-polish** | **ai-tasks** `loadPolishTemplates` + `DEFAULT_SYSTEM` | Pre-built prompts; Optimixer maps stage → `fix` | **Sidekick envelope** | **`post/fix`** — **missing** |
-| **ai-scoping** | **Inline** `SCOPING_SYSTEM` in `runScopingCall.ts` | Pre-built prompts; no `sidekickAction` | **No** | **Missing** |
-| **audit / fix / pick-best / craft-final** (xynthesis-native) | xynthesis `templates/{audit,fix,...}/*` | `runSidekickGatewayCall` when used | Sidekick envelope | **`post/*`** — **missing** (today: rendrix + `ask`) |
+Reviewed from `@x12i/funcx` **4.4.0** (`dist/functions`, README). Use this when implementing or extending FRs.
 
-**Duplication risk:** xynthesis 4.4 execution-strategy templates and FuncX `content-seed` / Catalox prompts for the same three capabilities can drift unless one is canonical.
+### 1.1 Call surface
 
-**ai-tasks still correct for:** envelope construction (`buildPlannerGenericPayload`, `buildOptimizerGenericPayload`, `buildResearchPlanQuestionsPayload`) and response adapters (`adaptExecutionPlanResult`, etc.) — keep even when xynthesis calls FuncX internally.
-
----
-
-## 2. FuncX feature requests (tracker)
-
-| FR id | Topic | Priority |
-|-------|--------|----------|
-| **FR-GEN-1** | Canonical **template context** from `GenericExecutionEnvelope` | P0 |
-| **FR-GEN-2** | **`args` → template customization** contract (document + validate) | P0 |
-| **FR-GEN-3** | **Output JSON schemas** aligned with ai-tasks adapters | P0 |
-| **FR-GEN-4** | **`run()` + `RunOptions`** for model, timeout, `response_format`, attribution | P1 |
-| **FR-GEN-5** | **`runGenericExecution`** helper (envelope → ask → parse → usage) for xynthesis | P1 |
-| **FR-GEN-6** | **Post-step generic** functions (`post/audit`, `post/polish` or `xynthesis/audit`) | P1 |
-| **FR-PRE-POST-*** | **Pre/post sidekick built-ins** + Catalox mapping — see [**funcx-pre-post-sidekick-actions.md**](./funcx-pre-post-sidekick-actions.md) | **P0** |
-| **FR-GEN-7** | **AI scoping** generic function (`scoping/run` or `research/scope-content`) | P2 |
-| **FR-GEN-8** | **`strategyArgs` vs `args`** on wire (or documented merge rule) | P1 |
-| **FR-GEN-9** | **Catalox seed parity** with xynthesis 4.4 templates + CI diff | P1 |
-| **FR-GEN-10** | **Deprecate** legacy `ai-tasks-plan-task` / `ai-tasks-optimizer-evaluate` ids | P2 |
-| **FR-GEN-11** | **Sidekick-shaped** post-steps via envelope (audit checks in `context`) | P2 |
-| **FR-GEN-12** | **Contract tests** package: envelope fixtures → expected adapter output | P1 |
-
-§6 in [`funcx-scoping-integration-gaps.md`](../funcx-scoping-integration-gaps.md) remains the **adapter-level** contract for execution/research ids; this doc adds **hosting + template** requirements.
-
----
-
-### FR-GEN-1 — Canonical template context from envelope
-
-**Need:** Every generic execution/research built-in must render prompts from a **stable, documented** variable map derived from the envelope — not ad hoc TS string building in each consumer.
-
-**Require FuncX built-ins / Catalox templates to expose at minimum:**
-
-| Token / field | Source |
-|---------------|--------|
-| `goal` | `envelope.goal` (string, trimmed) |
-| `input_json` | `JSON.stringify(envelope.input ?? null)` with documented max length + truncation suffix |
-| `context_json` | `JSON.stringify(envelope.context ?? {})` — same truncation rules |
-| `result_json` | Optimizer / evaluate only — `envelope.result` |
-| `args_json` | `JSON.stringify(envelope.args ?? {})` |
-| `iteration_index` | `envelope.args.iterationIndex` when present (stringified) |
-
-**Ask:** Export `buildGenericExecutionTemplateContext(envelope): Record<string, string>` from `@x12i/funcx/functions` (or document it in `docs/migration-generic-execution.md`) so xynthesis can stop duplicating `executionStrategyPromptTemplate.ts` stringification.
+```ts
+import { run, getRunJsonResult, buildAskAttribution } from "@x12i/funcx/functions";
+import type { GenericExecutionEnvelope } from "@x12i/funcx/functions";
+
+const raw = await run("execution/plan", envelope, {
+  client,
+  model: resolvedSlug,
+  timeoutMs: 60_000,
+  responseFormat: { kind: "json_object" },
+  includeUsage: true,
+});
+const json = getRunJsonResult(raw);
+```
 
-**Acceptance:** xynthesis 4.4 templates and FuncX Catalox seeds use the **same** token names; one integration test compares rendered user prompt hashes for a golden fixture.
+| Mechanism | Behavior |
+|-----------|----------|
+| **Id normalization** | Slash ids in constants (`execution/plan`) → hyphen registry keys (`execution-plan`) inside router |
+| **Constants** | `FUNCX_EXECUTION_PLAN_FUNCTION_ID`, `FUNCX_EXECUTION_EVALUATE_RESULT_FUNCTION_ID`, `FUNCX_RESEARCH_PLAN_QUESTIONS_FUNCTION_ID` |
+| **Schema** | `genericExecutionEnvelopeJsonSchema` (draft Ajv object; `goal` required at runtime for built-ins) |
+| **Unwrap** | `getRunJsonResult` / `isHttpRunSuccessBody` — HTTP `{ result, usage }` vs in-process plain object |
 
----
+### 1.2 `GenericExecutionEnvelope` (shipped)
 
-### FR-GEN-2 — `args` → template-level customization
+```ts
+type GenericExecutionEnvelope = {
+  goal?: unknown;       // runtime: non-empty string for execution/research built-ins
+  input?: unknown;
+  context?: unknown;
+  result?: unknown;     // optimizer / evaluate-result
+  args?: Record<string, unknown>;
+  attribution?: Record<string, unknown>;
+  client?: Client;      // in-process only; omit on HTTP
+};
+```
 
-**Need:** Strategy rows and hosts pass opaque knobs in `args` (minus `functionId`) that **templates** read without new function ids — e.g. `customGuidelines`, `maxQuestions`, `allowSkip`, `templateVariant`, `density`.
+**Not on the type today:** `strategyArgs` (xynthesis merges into `args` before `run()` — see §2.3).
 
-**Today (ai-tasks / xynthesis):**
+### 1.3 `buildAskAttribution` (shipped)
 
-- Planner/optimizer: `strategyArgs` forwarded separately in xynthesis; FuncX types only document `args`.
-- Audit: `customAuditGuidelines` merged in ai-tasks `renderAuditSystem`, not in envelope.
-- Web-scope: `args.maxQuestions`, `args.sourceType`, `args.allowSkip`.
+`buildAskAttribution(implFunctionId, req)` merges:
 
-**Ask:**
+- Top-level / `attribution.*`: `projectId`, `traceId`, `jobId`, `taskId`, `agentId`, `runId`, `parentRunId`, `actorId`, `subjectId`
+- `attribution.tags` and top-level `tags`
+- Preserves implementing `functionId`; stores caller `attribution.functionId` in `tags.callerFunctionId`
 
-1. Document **reserved vs extension** keys in `args` per function id (JSON Schema `args` sub-schemas in `fx/*/meta.json`).
-2. Support **nested template overrides** via convention, e.g. `args.promptOverrides.systemSuffix`, `args.customGuidelines`, without breaking generic envelope validation.
-3. Optional: `args._templateProfile: "strict" | "lenient"` to select Catalox template variant.
+**xynthesis / ai-tasks today:** `buildSidekickFuncxAttribution` / `buildExecutionStrategyAttribution` set `runId`←jobId, `subjectId`←taskId, `actorId`←agentId — compatible with FuncX merge rules.
 
-**Acceptance:** Changing only `args.customGuidelines` in a fixture changes the rendered system prompt in tests; no TypeScript change in consumers.
+### 1.4 `RunOptions` (shipped — partial vs orchestrator needs)
 
----
+| Field | Shipped in 4.4.0 |
+|-------|------------------|
+| `client`, `model`, `backend`, `timeoutMs`, `signal` | Yes |
+| `responseFormat` (`json_object` / text) | Yes |
+| `includeUsage`, `validateOutput`, `profile` (race) | Yes |
+| `temperature`, `topP`, `reasoningEffort` | **No** on `RunOptions` (still use `Client.ask` / xynthesis `FuncxInvoker` for sampling) |
 
-### FR-GEN-3 — Output JSON schemas aligned with ai-tasks adapters
+### 1.5 Hosting model (content + router)
 
-**Need:** Built-in outputs must match what [`adaptExecutionPlanResult`](../../src/execution-strategies/genericExecutionFuncxEnvelope.ts), [`adaptEvaluateResultResponse`](../../src/execution-strategies/genericExecutionFuncxEnvelope.ts), and [`adaptResearchPlanQuestionsResult`](../../src/execution-strategies/genericExecutionFuncxEnvelope.ts) expect.
+| Class | Examples | How prompts run |
+|-------|----------|-----------------|
+| **Content-backed** | `execution-plan`, `execution-evaluate-result`, `research-plan-questions`, `research-plan-web-search`, `research-plan-scoped-questions` | Catalox `fx/{id}/` via `executeFuncxFromContent`; instructions rendered with `renderInstructionTemplate(instructions, { input: request, variables })` where **`request` is the full envelope** passed to `run()` |
+| **Code-bound router** | Primitives, runx.*, repair JSON, … | TS handlers; generic execution family delegates to `run("execution-plan", …)` |
+| **Legacy (deprecate)** | `ai-tasks-plan-task`, `ai-tasks-optimizer-evaluate` | Hyphen ids; same envelope family; superseded by `execution-plan` / `execution-evaluate-result` |
 
-**Planner (`execution-plan` / `execution/plan`):**  
-`plan?`, `instructions?`, `steps[]`, `assumptions[]`, `missingInputs[]`, optional `prompt`, `variables`, `templateTokens` (top-level or under `metadata`).
+**Seed bundle:** `content-seed/functions/genericExecutionResearch.seed.json` → `npm run content:primitives:sync` (see FuncX README § Catalox merged primitive seeds).
 
-**Optimizer (`execution-evaluate-result`):**  
-`satisfied` (boolean), `feedback?`, `suggestedChanges[]`, `issues[]`, optional `variables`, `templateTokens`, `metadata`.
+**Executor primitives (all functions):** `executeFuncx` → `callAI` with `buildFuncxUserPrompt(buildPrompt(request))` — user message is JSON (or prefixed JSON body), not xynthesis-style pre-rendered system+user strings.
 
-**Research (`research-plan-questions`):**  
-`questions[]` with `question`, optional `reason`, `confidence`; optional `skipped`, `reasonCodes`.
+### 1.6 Built-in I/O types (shipped — align adapters)
 
-**Ask:** Publish machine-readable schemas next to built-ins; version with semver when fields change. Include **`getRunJsonResult`** normalization examples in docs.
+| Registry id | `run()` alias | Input highlights | Output highlights |
+|-------------|---------------|------------------|-------------------|
+| `execution-plan` | `execution/plan` | `goal`, `input?`, `context?`, `args?`, `attribution?` | `plan?`, `instructions?`, `steps[]`, `assumptions[]`, `missingInputs[]`, `metadata?` |
+| `execution-evaluate-result` | `execution/evaluate-result` | + required `result` | `satisfied`, `feedback?`, `suggestedChanges[]`, `issues[]`, `metadata?` |
+| `research-plan-questions` | `research/plan-questions` | same envelope | `questions[]`, `skipped?`, `reasonCodes?`, `confidence?` |
 
-**Gap vs xynthesis 4.4 parsers:** If FuncX adds fields, xynthesis `parseExecutionStrategyPayload` should defer to FuncX schema or share one JSON Schema file.
+ai-tasks adapters: `adaptExecutionPlanResult`, `adaptEvaluateResultResponse`, `adaptResearchPlanQuestionsResult`.
 
 ---
 
-### FR-GEN-4 — `run()` + `RunOptions` for orchestrator controls
-
-**Need:** `@exellix/xynthesis` must pass **resolved model**, timeout, temperature, `response_format: json_object`, and merged **attribution** without re-implementing `ask()` options.
-
-**Ask:**
-
-- Extend `RunOptions` (or documented overload) with: `model`, `timeoutMs`, `temperature`, `topP`, `reasoningEffort`, `responseFormat`, `maxTokens` / completion cap hint.
-- Built-ins call `buildAskAttribution(implFunctionId, envelope)` internally when `attribution` is present.
-- Return shape includes **`usage`** and fields xynthesis maps to `InvokeAttemptSummary` (or document mapping table).
-
-**Acceptance:** xynthesis `invokeExecutionStrategyAction` can replace `executeXynthesisAction` + manual prompts with `run(FUNCX_EXECUTION_PLAN_FUNCTION_ID, payload, options)` while preserving observability parity.
-
----
+## 2. Consumer prep (shipped in mono-repo)
 
-### FR-GEN-5 — `runGenericExecution` helper for embedders
+| Artifact | Package | Status |
+|----------|---------|--------|
+| `sidekickFuncxCatalogMap.ts` | xynthesis | **Shipped** — actionType ↔ `funcxFunctionId` ↔ Catalox catalog |
+| `sidekickFuncxEnvelope.ts` | xynthesis | **Shipped** — `buildSidekickGenericEnvelope`, `buildExecutionStrategyGenericEnvelope` |
+| `ENV_SIDEKICK_FUNCX` (`XYNTHESIS_FUNCX_SIDEKICK=1`) | xynthesis | **Shipped** — gate; no `run()` wiring in gateway yet |
+| Catalox `XynthesisActionItem.funcx` | xynthesis seed | **Shipped** — `functionId` + `contentVersion: "0.0.0-pending-funcx"` |
+| `auditChecklistFuncxEnvelope.ts` | ai-tasks | **Shipped** — `post/audit-checklist`, `post/audit-merge` envelopes |
+| Execution via xynthesis actions | ai-tasks 8.5+ | **Shipped** — not direct `run()` from ai-tasks |
+| `runExecutionStrategyViaXynthesis` | ai-tasks | **Shipped** — still uses xynthesis disk templates + `FuncxInvoker.ask` |
 
-**Need:** Thin API for packages that already own parse/Activix but should not fork prompt assembly.
+### 2.1 `strategyArgs` merge (consumer — no FuncX FR)
 
-**Proposed export (`@x12i/funcx/functions`):**
+`buildExecutionStrategyGenericEnvelope` folds `req.strategyArgs` into **`args`** (and sets `args.iterationIndex` for optimizer). **Do not** wait for a FuncX type extension; hosts must merge before `run()`.
 
-```ts
-runGenericExecution(opts: {
-  functionId: string;
-  envelope: GenericExecutionEnvelope;
-  client?: Client;
-  runOptions?: RunOptions;
-}): Promise<{ value: unknown; usage?: Usage; model?: string; raw?: unknown }>;
-```
+### 2.2 Template token convention (parity gap)
 
-**Behavior:** Resolve content → render templates from FR-GEN-1 context → `ask` / `askJson` → validate against function output schema → return parsed object.
+| Source | User-prompt tokens |
+|--------|-------------------|
+| **xynthesis disk** (`executionStrategyPromptTemplate.ts`) | `goal`, `input_json`, `context_json`, `result_json`, `args_json`, `strategy_args_json`, `iteration_index` |
+| **FuncX content render** (envelope = `request`) | Typically `{{input.goal}}`, `{{input.context}}`, … via rendrix `input` = full envelope |
 
-**Acceptance:** xynthesis deletes duplicate template render path when this ships; tests use `createAskMock` at FuncX boundary only.
+**FR-GEN-1** (revised): FuncX should export **`envelopeToTemplateVariables(envelope)`** that produces **both** conventions (or document Catalox seeds must use `input.*` paths). Until then, FR-GEN-9 parity diffs must compare normalized renders, not raw file text.
 
 ---
 
-### FR-GEN-6 — Post-step generic functions (audit, polish)
-
-**Need:** Remove ai-tasks **inline** `DEFAULT_SYSTEM` and duplicate template trees; use envelope + FuncX templates.
-
-**Proposed ids:**
-
-| Capability | Suggested `functionId` | Envelope highlights |
-|------------|------------------------|---------------------|
-| Audit evaluator | `post/audit` or `xynthesis/audit` | `goal`: audit objective; `input`: output under test; `context`: checks, synthesis excerpt, pass metadata; `args`: `customGuidelines`, `passNumber` |
-| Polish | `post/polish` or `xynthesis/fix` | `input`: draft output; `context`: checklist, prior pass notes; `args`: `customGuidelines` |
-
-**Output:** Audit — markdown or structured sections; Polish — JSON `{ polishedOutput, changeNotes }` per current ai-tasks parsers.
+## 3. Audit — instructions vs `run()` (current)
 
-**Acceptance:** `runAuditCall` / `runPolishCall` build envelope + `run()`; xynthesis `executeXynthesisAction` only for transport if still needed, or xynthesis wraps FR-GEN-5.
+| Capability | Prompt host today | Envelope | FuncX built-in 4.4.0 |
+|------------|-------------------|----------|----------------------|
+| execution-plan / optimizer / web-scope | xynthesis templates + `ask` | `GenericExecution*` via builders | **Yes** — not called from xynthesis yet |
+| synthesis, audit, fix, pick-best, craft-final | xynthesis disk / Catalox + `ask` | `SidekickGenericEnvelope` when wired | **No** — see [funcx-pre-post-sidekick-actions.md](./funcx-pre-post-sidekick-actions.md) |
+| ai-tasks checklist audit / merge | ai-tasks Handlebars | `auditChecklistFuncxEnvelope` | **No** (`post/audit-checklist`, `post/audit-merge`) |
+| ai-scoping | inline `SCOPING_SYSTEM` | none | **No** |
 
 ---
 
-### FR-GEN-7 — AI scoping generic function
-
-**Need:** Replace `SCOPING_SYSTEM` constant in [`runScopingCall.ts`](../../src/aiScoping/runScopingCall.ts).
-
-**Proposed id:** `scoping/run` or `research/scope-content`
-
-**Envelope:**
-
-- `goal`: scoping directive (from caller `instructions`)
-- `input`: `{ sourceContent: string }` or raw string policy documented
-- `args`: `outputExpectation` hints, `maxOutputLength`
-
-**Output:** Plain text scoped result (no markdown / fences) — document in schema.
-
-**Acceptance:** No inline system string in ai-tasks; FuncX template owns behavior.
+## 4. Feature request tracker (aligned to 4.4.0)
+
+| FR id | Topic | Status @ 4.4.0 |
+|-------|--------|----------------|
+| **FR-GEN-0** | Baseline: envelope, constants, `buildAskAttribution`, `getRunJsonResult`, execution/research built-ins, `genericExecutionResearch` seed | **Shipped** |
+| **FR-GEN-1** | `envelopeToTemplateVariables` (+ document `input.*` vs `*_json` tokens) | **Open** |
+| **FR-GEN-2** | Per-function `args` JSON Schema + template knobs (`customGuidelines`, …) | **Open** (partially by convention) |
+| **FR-GEN-3** | Published output schemas shared with xynthesis parsers | **Open** (TS types exist; no shared JSON Schema artifact) |
+| **FR-GEN-4** | `RunOptions`: `temperature`, `topP`, `reasoningEffort` | **Open** (partial: model, timeout, responseFormat shipped) |
+| **FR-GEN-5** | `runGenericExecution({ functionId, envelope, runOptions })` embedder helper | **Open** |
+| **FR-GEN-6** | Post-step checklist / merge built-ins | **Open** → FR-PRE-POST-2 |
+| **FR-GEN-7** | AI scoping built-in | **Open** |
+| **FR-GEN-8** | `strategyArgs` on wire | **Closed (consumer)** — merge into `args` in xynthesis |
+| **FR-GEN-9** | Catalox seed ↔ xynthesis template parity CI | **Open** |
+| **FR-GEN-10** | Deprecate `ai-tasks-plan-task` / `ai-tasks-optimizer-evaluate` | **Open** |
+| **FR-GEN-11** | Rich audit `context` sub-schema on envelope | **Open** (checklist envelope shipped in ai-tasks) |
+| **FR-GEN-12** | Golden fixtures package | **Open** |
+| **FR-PRE-POST-*** | Pre/post sidekick built-ins | **Open** — [funcx-pre-post-sidekick-actions.md](./funcx-pre-post-sidekick-actions.md) |
 
 ---
 
-### FR-GEN-8 — `strategyArgs` vs `args` on wire
+## 5. Open FR details (only what 4.4.0 does not cover)
 
-**Need:** ai-tasks execution strategies pass catalog row `args` (minus `functionId`) while xynthesis 4.4 also accepts `strategyArgs` on the request object.
+### FR-GEN-1 — Template variables from envelope
 
-**Options (pick one in FuncX):**
-
-1. **Merge rule:** At `run()` entry, `effectiveArgs = { ...envelope.args, ...envelope.strategyArgs }` if `strategyArgs` is added to `GenericExecutionEnvelope`.
-2. **Document:** Consumers must fold `strategyArgs` into `args` before `run()`; export `mergeStrategyArgs(envelope)` helper.
-
-**Ask:** Update `GenericExecutionEnvelope` TypeScript type and `genericExecutionEnvelopeJsonSchema` if `strategyArgs` becomes first-class.
-
----
-
-### FR-GEN-9 — Catalox seed parity with xynthesis 4.4
-
-**Need:** Single canonical prompt source.
+**Need:** One function used by content-backed built-ins and xynthesis so Catalox instructions and `xynthesis/templates/*` stay aligned.
 
 **Ask:**
 
-1. Diff `xynthesis/templates/execution-*` and `plan-web-scope-questions` against `content-seed/functions/genericExecutionResearch.seed.json` (or per-function seeds).
-2. CI job fails on drift unless bumping `contentVersion`.
-3. Document sync procedure: xynthesis exports → FuncX seed import (or FuncX seed → xynthesis pull).
+```ts
+envelopeToTemplateVariables(
+  envelope: GenericExecutionEnvelope | SidekickGenericEnvelope
+): Record<string, string>;
+```
 
-**Acceptance:** Product can disable xynthesis disk templates when Catalox actions enabled (`isCataloxActionsEnabled`) without behavior change.
+Minimum keys: parity with `buildExecutionStrategyUserVars` **and** nested `input.goal` style for `renderInstructionTemplate`.
 
----
+### FR-GEN-2 — `args` contract
 
-### FR-GEN-10 — Deprecate legacy ai-tasks function ids
+Document reserved keys per `functionId` in `fx/*/meta.json`. Execution/research: `maxQuestions`, `allowSkip`, `sourceType`, `iterationIndex`, `customGuidelines`, `templateMode`, …
 
-**Need:** FuncX registry still lists `ai-tasks-plan-task`, `ai-tasks-optimizer-evaluate` alongside `execution-plan`, `execution-evaluate-result`.
+### FR-GEN-3 — Shared output JSON Schema
 
-**Ask:** Mark legacy ids deprecated in meta; route aliases to generic built-ins; remove from seed catalog after one major.
+Export versioned schemas next to built-ins; xynthesis `parseExecutionStrategyPayload` / sidekick parsers consume same files.
 
----
+### FR-GEN-4 — Orchestrator sampling on `run()`
 
-### FR-GEN-11 — Sidekick-shaped post-steps via envelope (optional)
+Add optional `temperature`, `topP`, `reasoningEffort` to `RunOptions` (or document that embedders must use `executeFuncxFromContent` + custom `callAI` until then). xynthesis today passes sampling via **`FuncxInvoker.ask`**, not `run()`.
 
-**Need:** Audit today uses rich `SidekickInput` (checks array, material blocks). Migrating to envelope should not lose structure.
+### FR-GEN-5 — `runGenericExecution`
 
-**Ask:** Define `context.audit` sub-schema (checks, outputText, synthesisSummary, …) in FR-GEN-6 meta so templates stay declarative.
+Thin wrapper: resolve content → render → `askJson` → `getRunJsonResult` → return `{ value, usage, model }`. Sidekick variant accepts `SidekickGenericEnvelope` (FR-PRE-POST-5).
 
----
+### FR-GEN-9 — Seed parity
 
-### FR-GEN-12 — Contract tests for adapters
+Compare `genericExecutionResearch.seed.json` + deployed `fx/execution-plan/*` to `xynthesis/templates/execution-*` using **FR-GEN-1** normalized variables.
 
-**Need:** Prevent drift between FuncX built-in output and ai-tasks adapters.
+### FR-GEN-10 — Legacy ids
 
-**Ask:** Ship `test/fixtures/generic-execution/*.json` in `@x12i/funcx` run in CI; ai-tasks imports fixtures or duplicates with cross-package version pin.
+Alias `ai-tasks-plan-task` → `execution-plan`, `ai-tasks-optimizer-evaluate` → `execution-evaluate-result`; mark deprecated in seed meta.
 
 ---
 
-## 3. Recommended convergence path
+## 6. Convergence path
 
 ```mermaid
 flowchart LR
-  subgraph ai_tasks
-    A[buildPlannerGenericPayload]
+  subgraph consumers
+    AT[ai-tasks envelope builders]
+    XY[xynthesis run* / gateway]
   end
-  subgraph xynthesis
-    B[runExecutionPlan]
-    C{FR-GEN-5 shipped?}
+  subgraph funcx44 [FuncX 4.4 shipped]
+    RUN[run slash id]
+    ATTR[buildAskAttribution]
+    SEED[genericExecutionResearch seed]
   end
-  subgraph funcx
-    D[run execution-plan]
-    E[Catalox templates + args]
+  subgraph funcxNext [FuncX next]
+    PRE[pre/post built-ins]
+    VARS[envelopeToTemplateVariables]
   end
-  A --> B
-  B --> C
-  C -->|yes| D
-  C -->|interim 4.4| F[disk templates + ask]
-  D --> E
-  F --> E
+  AT --> XY
+  XY -->|XYNTHESIS_FUNCX_SIDEKICK=1| RUN
+  RUN --> ATTR
+  RUN --> SEED
+  PRE --> RUN
+  VARS --> SEED
 ```
 
-1. **FuncX:** Implement FR-GEN-1–3, FR-GEN-9 (canonical prompts + schemas).
-2. **FuncX:** FR-GEN-4–5 so xynthesis can call `run()` without duplicate `executionStrategyPromptTemplate.ts`.
-3. **xynthesis:** Follow-up FR (separate doc) — switch `invokeExecutionStrategyAction` to FuncX `run()`; keep parsers/adapters.
-4. **ai-tasks:** FR-GEN-6–7 for audit/polish/scoping; stop shipping `DEFAULT_SYSTEM` strings.
-5. **Docs:** Update [`funcx-catalog-hosting-checklist.md`](../funcx-catalog-hosting-checklist.md) — built-ins are canonical; Catalox overrides via `args`.
+1. **Done:** execution/research envelopes + built-ins + attribution (4.4.0).
+2. **Next FuncX:** FR-GEN-1, FR-PRE-POST-1..4, FR-GEN-9 (before xynthesis deletes duplicate renderers).
+3. **xynthesis:** Wire `invokeExecutionStrategyAction` / gateway to `run(resolveSidekickFuncxFunctionId(...), envelope, opts)` behind `XYNTHESIS_FUNCX_SIDEKICK=1`.
+4. **ai-tasks:** Switch audit/polish/scoping to envelope + `run()` after post built-ins land.
 
 ---
 
-## 4. Non-goals
+## 7. Non-goals
 
-- Changing ai-skills MAIN `instructions` / `prompt` contract.
-- Moving synthesis PRE-step template **cores** (`{{core:analysis}}`) into FuncX — cores stay rendrix/ai-skills; FuncX hosts the **synthesis action** via `pre/synthesize` (see [funcx-pre-post-sidekick-actions.md](./funcx-pre-post-sidekick-actions.md)).
-- Forcing ai-tasks to call `@x12i/funcx` directly again for execution strategies (xynthesis remains the facade after FR-GEN-5).
+- ai-skills MAIN `instructions` / `prompt`.
+- Template **cores** (`{{core:analysis}}`) inside FuncX — stay rendrix/ai-skills; `pre/synthesize` envelope carries **pre-rendered** downstream blocks in `input`.
+- Forcing ai-tasks to call `@x12i/funcx` directly for execution strategies (xynthesis remains facade).
 
 ---
 
-## 5. Version note
+## 8. Version note
+
+| Package | Version | Notes |
+|---------|---------|-------|
+| `@x12i/funcx` | **4.4.0** (npm latest reviewed) | Baseline for §1 |
+| `@exellix/xynthesis` | **4.4.3** | FuncX map + envelopes; execution hop still disk+ask |
+| `@exellix/ai-tasks` | **8.5.2** | xynthesis actions; checklist envelopes ready |
 
-- **@x12i/funcx** ≥ **4.2.0** (ai-tasks dep): `FUNCX_*_FUNCTION_ID`, `genericExecutionEnvelopeJsonSchema`, `buildAskAttribution`, `getRunJsonResult`.
-- Built-in ids in registry: `execution-plan`, `execution-evaluate-result`, `research-plan-questions` (slash aliases normalize per README).
+When FuncX ships pre/post built-ins, bump `contentVersion` on Catalox items from `0.0.0-pending-funcx` and enable `XYNTHESIS_FUNCX_SIDEKICK=1` in CI.

package/documenations/upstream-feature-requests/funcx-pre-post-sidekick-actions.md

@@ -1,301 +1,213 @@
 # `@x12i/funcx` — built-in functions for xynthesis **pre-actions** and **post-actions**
 
 **Filed by:** `@exellix/ai-tasks` + `@exellix/xynthesis`  
-**Blocks:** Catalox-only sidekick path (`runXynthesisAiAction`), ai-tasks audit/polish migration off inline templates  
-**Related:** [funcx-generic-xynthesis-hosting.md](./funcx-generic-xynthesis-hosting.md), [funcx-catalog-hosting-checklist.md](../funcx-catalog-hosting-checklist.md)
+**Baseline:** `@x12i/funcx` **4.4.0** — execution/research generics **shipped**; pre/post ids below are **not** in registry yet  
+**Blocks:** `XYNTHESIS_FUNCX_SIDEKICK=1` production use, ai-tasks audit/polish off Handlebars  
+**Related:** [funcx-generic-xynthesis-hosting.md](./funcx-generic-xynthesis-hosting.md) (4.4.0 baseline + execution FRs)
 
 ---
 
 ## 0. Problem
 
-Today xynthesis **pre-actions** (synthesis) and **post-actions** (audit, fix, pick-best, craft-final) load prompts from:
+**Shipped in FuncX 4.4.0:** `run("execution/plan" | "execution/evaluate-result" | "research/plan-questions", GenericExecutionEnvelope)` with Catalox content under `genericExecutionResearch` seed.
 
-1. On-disk `xynthesis/templates/{actionType}/`, or  
-2. Catalox catalogs `pre-actions` / `post-actions` (same template bodies, seeded from disk).
+**Not shipped:** Sidekick pre/post capabilities (`pre/synthesize`, `post/audit`, …). Today:
 
-The LLM hop uses **`FuncxInvoker.ask(systemPrompt, userPrompt)`** — a **transport-only** use of FuncX. Prompt text is assembled in xynthesis (`sidekickPromptTemplate.ts` + rendrix), **not** resolved from a FuncX **function id** via `run(functionId, envelope)`.
+1. xynthesis loads `xynthesis/templates/{actionType}/` or Catalox `pre-actions` / `post-actions` (same bodies).
+2. LLM hop = **`FuncxInvoker.ask(systemPrompt, userPrompt)`** (transport only).
+3. ai-tasks often builds its **own** audit/polish prompts (`loadAuditTemplates`, `DEFAULT_SYSTEM`).
 
-**ai-tasks** often bypasses even that path: it loads **its own** audit/polish templates and calls `executeXynthesisAction` with pre-built prompts.
-
-**Target:** Each sidekick action has a **first-class FuncX function** (like `execution/plan`). xynthesis calls `run(functionId, envelope, runOptions)`; Catalox `pre-actions` / `post-actions` items **reference** the same `functionId` for content overrides, not duplicate template hosting.
+**Target:** Register pre/post built-ins like execution family → `run(functionId, SidekickGenericEnvelope, runOptions)`; Catalox items keep `funcx.functionId` for overrides only.
 
 ---
 
-## 1. Canonical mapping (FuncX ↔ Catalox ↔ sidekick)
+## 1. Consumer mapping (shipped in xynthesis)
+
+**Source:** `xynthesis/src/catalog/sidekickFuncxCatalogMap.ts`  
+**Envelopes:** `xynthesis/src/sidekickFuncxEnvelope.ts`  
+**Flag:** `XYNTHESIS_FUNCX_SIDEKICK=1` (`isSidekickFuncxEnabled()`)
 
-| Phase | Sidekick `actionType` | Catalox catalog | Catalox item id | Proposed FuncX `functionId` | Hyphen alias |
-|-------|----------------------|-----------------|-----------------|----------------------------|--------------|
-| PRE | `synthesis` | `pre-actions` | `synthesis` | `pre/synthesize` | `pre-synthesize` |
-| PRE | `execution-plan` | `pre-actions` | `execution-plan` | `execution/plan` | `execution-plan` |
-| PRE | `plan-web-scope-questions` | `pre-actions` | `plan-web-scope-questions` | `research/plan-questions` | `research-plan-questions` |
-| POST | `audit` | `post-actions` | `audit` | `post/audit` | `post-audit` |
-| POST | `fix` | `post-actions` | `fix` | `post/fix` | `post-fix` |
-| POST | `pick-best` | `post-actions` | `pick-best` | `post/pick-best` | `post-pick-best` |
-| POST | `craft-final` | `post-actions` | `craft-final` | `post/craft-final` | `post-craft-final` |
-| POST | `execution-evaluate-result` | `post-actions` | `execution-evaluate-result` | `execution/evaluate-result` | `execution-evaluate-result` |
+| Phase | Sidekick `actionType` | Catalox catalog | Item id | FuncX `functionId` | Hyphen alias (router) | In FuncX 4.4 registry? |
+|-------|----------------------|-----------------|---------|-------------------|----------------------|-------------------------|
+| PRE | `synthesis` | `pre-actions` | `synthesis` | `pre/synthesize` | `pre-synthesize` | **No** |
+| PRE | `execution-plan` | `pre-actions` | `execution-plan` | `execution/plan` | `execution-plan` | **Yes** |
+| PRE | `plan-web-scope-questions` | `pre-actions` | `plan-web-scope-questions` | `research/plan-questions` | `research-plan-questions` | **Yes** |
+| POST | `audit` | `post-actions` | `audit` | `post/audit` | `post-audit` | **No** |
+| POST | `fix` | `post-actions` | `fix` | `post/fix` | `post-fix` | **No** |
+| POST | `pick-best` | `post-actions` | `pick-best` | `post/pick-best` | `post-pick-best` | **No** |
+| POST | `craft-final` | `post-actions` | `craft-final` | `post/craft-final` | `post-craft-final` | **No** |
+| POST | `execution-evaluate-result` | `post-actions` | `execution-evaluate-result` | `execution/evaluate-result` | `execution-evaluate-result` | **Yes** |
 
-**ai-tasks pipeline audit (weighted checks, markdown output)** — separate from sidekick JSON audit until unified:
+**ai-tasks-only POST pipeline** (not `SidekickActionType` today):
 
-| Capability | Proposed FuncX id | Catalox (optional) |
-|------------|-------------------|-------------------|
-| Checklist audit evaluator | `post/audit-checklist` | `post-actions` item `audit-checklist` |
-| Audit-cycle synthesis merge | `post/audit-merge` | `post-actions` item `audit-merge` or reuse `pre/synthesize` with `args.profile: "audit-merge"` |
+| Capability | FuncX id | Catalox item | Envelope builder | In registry? |
+|------------|----------|--------------|------------------|--------------|
+| Checklist audit | `post/audit-checklist` | `audit-checklist` | `ai-tasks/.../auditChecklistFuncxEnvelope.ts` | **No** |
+| Audit merge | `post/audit-merge` | `audit-merge` | same module | **No** |
 
-Constants and envelope builders live in xynthesis: `src/catalog/sidekickFuncxCatalogMap.ts`, `src/sidekickFuncxEnvelope.ts`.
+Catalox seed writes `funcx: { functionId, contentVersion: "0.0.0-pending-funcx" }` on every mapped sidekick item (`buildXynthesisSeedPayloads.ts`).
 
 ---
 
-## 2. Wire contract — sidekick generic envelope
+## 2. Wire contract — `SidekickGenericEnvelope`
 
-Extend (or sibling-type) **`GenericExecutionEnvelope`** for sidekick actions:
+**Defined in xynthesis** (not exported from `@x12i/funcx` 4.4.0). FuncX `run()` should accept this object as the **request** body (same as passing `GenericExecutionEnvelope` for execution ids).
 
 ```ts
 type SidekickGenericEnvelope = {
-  /** Directive: question / objective / instruction (maps to SidekickInput.task). */
-  goal: string;
-  /** Action-specific payload (see §3 per function). */
-  input: Record<string, unknown>;
-  /** Shared sidekick context. */
+  goal: string;                    // SidekickInput.task
+  input: Record<string, unknown>; // action-specific (§3)
   context: {
     templateCores: string[];
     taskType?: string;
     metadata?: Record<string, unknown>;
-    /** Optimizer-only / evaluate-only fields when applicable. */
-    result?: unknown;
+    result?: unknown;              // optimizer context when needed
     iterationIndex?: number;
+    identity?: ActivityRunContext;
   };
-  /** Template customization — NOT merged into LLM attribution tags by default. */
-  args?: {
-    templateMode?: "structured" | "markdown";
-    customGuidelines?: string;
-    synthesisPromptOverride?: string;
-    /** Checklist audit: passNumber, cycle, maxCycles, … */
-    [key: string]: unknown;
-  };
-  attribution?: GenericFuncxAttribution;
+  args?: Record<string, unknown>;  // templateMode, customGuidelines, …
+  attribution?: SidekickFuncxAttribution;
 };
 ```
 
-**Template context tokens** (FR-GEN-1 superset) — FuncX must render from envelope, matching xynthesis rendrix vars today:
-
-| Token | Envelope source |
-|-------|-----------------|
-| `task`, `question` | `goal` (both aliases for synthesis compat) |
-| `local_raw` | `input.localRaw` stringified |
-| `supporting_raw` | `input.supportingRaw` stringified |
-| `rendered_downstream_instructions` | `input.renderedInstructions` |
-| `rendered_downstream_prompt` | `input.renderedPrompt` |
-| `ai_output` | `input.aiOutput` |
-| `used_instructions` | `input.usedInstructions` |
-| `used_prompt` | `input.usedPrompt` |
-| `prior_audit_json` | `JSON.stringify(input.priorAudit)` |
-| `candidates_json` | `JSON.stringify(input.candidates)` |
-| `prior_context` | `input.priorContext` |
-| `metadata_json` | `JSON.stringify(context.metadata ?? {})` |
-| `template_cores_json` | `JSON.stringify(context.templateCores)` |
-| `goal`, `input_json`, `context_json`, `args_json` | FR-GEN-1 generic tokens (execution-strategy family) |
-
-**Ask (FuncX):** export `buildSidekickTemplateContext(envelope): Record<string, string>` alongside `buildGenericExecutionTemplateContext`.
-
----
-
-## 3. Per-function specifications
-
-### FR-PRE-1 — `pre/synthesize` (PRE synthesis)
-
-**Canonical content:** `xynthesis/templates/synthesis/system-structured.md` + `user-structured.md` (and markdown variants).
-
-**Envelope `input`:**
+**Builders (shipped):**
 
-| Field | Type | Required |
-|-------|------|----------|
-| `localRaw` | any | no |
-| `supportingRaw` | any | no |
-| `renderedInstructions` | string | no |
-| `renderedPrompt` | string | no |
+- `buildSidekickGenericEnvelope(input, options?)` — synthesis, audit, fix, pick-best, craft-final
+- `buildExecutionStrategyGenericEnvelope(req)` — planner / optimizer / web-scope (merges `strategyArgs` → `args`)
 
-**Output JSON** (matches `parseAndValidateSynthesizedPromptPayload` / `SynthesisPayload`):
+**Attribution:** `buildSidekickFuncxAttribution({ funcxFunctionId, jobId, taskId, agentId })` — align with FuncX `buildAskAttribution(implId, envelope)`.
 
-- `templateCores`, `task`, `synthesized` (`SynthesizedContext`), optional `notes`, `unknowns`, `assumptions`
+### 2.1 Template tokens (for Catalox instructions)
 
-**`args`:** `templateMode`, `customGuidelines`, `synthesisPromptOverride`, `maxItemsPerSide`, `maxItemContentChars`
+FuncX 4.4 renders instructions with `input` = **full envelope**. For parity with xynthesis rendrix disk templates, implement **FR-GEN-1** `envelopeToTemplateVariables` (see generic hosting doc).
 
-**Response format:** `json_object`
+| xynthesis rendrix (disk) | FuncX / rendrix on envelope (`input` = envelope) |
+|--------------------------|--------------------------------------------------|
+| `goal` | `input.goal` |
+| `task`, `question` | `input.goal` (aliases in sidekick templates) |
+| `local_raw`, `supporting_raw` | `input.local_raw`, `input.supporting_raw` (strings; builders stringify) |
+| `rendered_downstream_instructions` | `input.renderedInstructions` |
+| `rendered_downstream_prompt` | `input.renderedPrompt` |
+| `ai_output` | `input.aiOutput` |
+| `used_instructions`, `used_prompt` | `input.usedInstructions`, `input.usedPrompt` |
+| `prior_audit_json` | stringify `input.priorAudit` |
+| `candidates_json` | stringify `input.candidates` |
+| `metadata_json` | stringify `context.metadata` |
+| `template_cores_json` | stringify `context.templateCores` |
+| `goal`, `input_json`, `context_json`, `args_json` | execution family (§3.6) |
 
 ---
 
-### FR-POST-1 — `post/audit` (sidekick JSON audit)
-
-**Canonical content:** `xynthesis/templates/audit/*`
+## 3. Per-function specifications (to implement in FuncX)
 
-**Envelope `input`:**
+Register in router + `content-seed/functions/` (new bundle or extend `genericExecutionResearch` / dedicated `xynthesisSidekick.seed.json`). Follow **4.4.0 patterns**: `meta.json`, IO schemas, `executeFuncxFromContent`, `buildAskAttribution`, `responseFormat: json_object` where noted.
 
-| Field | Type | Required |
-|-------|------|----------|
-| `aiOutput` | string | yes |
-| `usedInstructions` | string | no |
-| `usedPrompt` | string | no |
+### FR-PRE-POST-1 — `pre/synthesize` (P0)
 
-**Output JSON** (matches `parseAuditPayload`):
+**Canonical content:** `xynthesis/templates/synthesis/system-structured.md`, `user-structured.md` (+ markdown pair).
 
-- `verdict`: `"pass" | "fail" | "mixed"`
-- `findings[]`: `{ id, label, content, severity? }`
-- plus sidekick base fields (`notes`, `unknowns`, `assumptions`, …)
+**`input`:** `localRaw`, `supportingRaw`, `renderedInstructions`, `renderedPrompt`, plus string mirrors `local_raw`, `supporting_raw`.
 
----
+**Output:** matches `parseAndValidateSynthesizedPromptPayload` / `SynthesisPayload` (`templateCores`, `task`, `synthesized`, `notes`, `unknowns`, `assumptions`).
 
-### FR-POST-2 — `post/audit-checklist` (ai-tasks weighted audit)
+**`args`:** `templateMode`, `customGuidelines`, `synthesisPromptOverride`, `maxItemsPerSide`, `maxItemContentChars`.
 
-**Canonical content:** migrate from ai-tasks `templates/post-steps/audit/` (Handlebars → FuncX templates with same variables).
+### FR-PRE-POST-2 — `post/audit-checklist` + `post/audit-merge` (P1)
 
-**Envelope `input`:**
+**Checklist** — migrate ai-tasks `templates/post-steps/audit/`:
 
-| Field | Type | Required |
-|-------|------|----------|
-| `candidateOutput` | string | yes |
-| `originalInput` | string | yes |
-| `promptContext` | string | no |
-| `mustChecks` | `{ check, weight }[]` | yes |
-| `shouldChecks` | `{ check, weight }[]` | yes |
-| `previousFeedback` | string | no |
+**`input`:** `candidateOutput`, `originalInput`, `promptContext`, `mustChecks`, `shouldChecks`, `previousFeedback`, `previousCycle` (see `buildAuditChecklistFuncxEnvelope`).
 
-**Output:** structured markdown (`### Checks`, `### Overall feedback`) — parsed by ai-tasks `parseAuditOutputFromMarkdown` until FuncX ships JSON schema variant.
+**Output:** markdown `### Checks` / `### Overall feedback` until JSON schema exists.
 
-**`args`:** `customAuditGuidelines`, `passNumber`, `cycle`, `maxCycles`
+**`args`:** `customAuditGuidelines`, `passNumber`, `cycle`, `maxCycles`.
 
----
+**Merge** — `buildAuditMergeFuncxEnvelope`: `input.candidateA`, `input.candidateB`, `context.task`.
 
-### FR-POST-3 — `post/fix` (polish / fix)
+### FR-PRE-POST-3 — `post/audit` (P0)
 
-**Canonical content:** `xynthesis/templates/fix/*`
+**Content:** `xynthesis/templates/audit/*`. **`input`:** `aiOutput`, `usedInstructions?`, `usedPrompt?`. **Output:** `parseAuditPayload` shape (`verdict`, `findings[]`, …).
 
-**Envelope `input`:** `aiOutput`, `usedInstructions?`, `usedPrompt?`, `priorAudit?` (AuditPayload)
+### FR-PRE-POST-4 — `post/fix` (P0)
 
-**Output JSON:** `fixes[]` with `{ id, label, corrected, rationale? }` per `parseFixPayload`
+**Note:** sidekick action is **`fix`** (polish), not `post/polish`. **Content:** `xynthesis/templates/fix/*`. **Output:** `parseFixPayload` (`fixes[]`).
 
----
+### FR-PRE-POST-5 — `post/pick-best`, `post/craft-final` (P0)
 
-### FR-POST-4 — `post/pick-best`
+Per `parsePickBestPayload` / `parseCraftFinalPayload` and existing disk templates.
 
-**Envelope `input`:** `candidates[]` (`{ id, content }`), `usedInstructions?`
+### FR-PRE-POST-6 — Execution ids (P0 — wire only)
 
-**Output JSON:** `selected`, `rankings[]` per `parsePickBestPayload`
-
----
+**Already in FuncX 4.4.0.** Remaining work:
 
-### FR-POST-5 — `post/craft-final`
+- [ ] xynthesis: stop `buildExecutionStrategyPrompts` + `ask` when `XYNTHESIS_FUNCX_SIDEKICK=1`
+- [ ] Call `run(resolveSidekickFuncxFunctionId(action), buildExecutionStrategyGenericEnvelope(req), runOptions)`
+- [ ] Catalox `contentVersion` ≥ seed version after parity (FR-GEN-9)
 
-**Envelope `input`:** `aiOutput`, `usedInstructions?`, `usedPrompt?`, `priorContext?`
-
-**Output JSON:** per `parseCraftFinalPayload` (`finalOutput`, `rationale?`, …)
+No new FuncX function definitions required if `fx/execution-plan/*` matches xynthesis templates.
 
 ---
 
-### FR-PRE-POST-6 — Execution-strategy ids (already exist — wire only)
-
-**No new FuncX content required** if seeds match xynthesis templates (FR-GEN-9). xynthesis must **stop** re-rendering `executionStrategyPromptTemplate.ts` and call:
-
-- `run("execution/plan", envelope)` 
-- `run("execution/evaluate-result", envelope)` 
-- `run("research/plan-questions", envelope)`
-
-Catalox `pre-actions` / `post-actions` items for these actions gain `funcx.functionId` pointing at built-ins; templates in Catalox become **overrides** only.
+## 4. Catalox catalog shape (consumer — shipped)
 
----
-
-## 4. Catalox catalog shape (consumer-side, after FuncX ships)
-
-Each `XynthesisActionItem` in `pre-actions` / `post-actions` should include:
-
-```json
-{
-  "actionType": "audit",
-  "funcx": {
-    "functionId": "post/audit",
-    "contentVersion": "1.0.0"
-  },
-  "templates": { "structured": { "system": "...", "user": "..." } },
-  "actionOutputDefaults": { ... },
-  "outputIntent": { ... }
-}
+```ts
+// XynthesisActionItem (cataloxXynthesisBootstrap.ts)
+funcx?: {
+  functionId: string;      // slash form from sidekickFuncxCatalogMap
+  contentVersion?: string;   // "0.0.0-pending-funcx" until FuncX seed synced
+};
 ```
 
-**Resolution order (xynthesis):**
+**Resolution order (target):**
 
-1. If `XYNTHESIS_FUNCX_SIDEKICK=1` (new flag): `run(item.funcx.functionId, buildSidekickGenericEnvelope(input), runOptions)`.
-2. Else if `XYNTHESIS_CATALOX_ACTIONS=1`: Catalox templates + rendrix (today).
-3. Else: disk templates (dev/tests).
+1. `XYNTHESIS_FUNCX_SIDEKICK=1` → `run(item.funcx.functionId, envelope, runOptions)` — prompts from FuncX/Catalox only.
+2. `XYNTHESIS_CATALOX_ACTIONS=1` → Catalox templates + rendrix (**today**).
+3. Else → disk templates (dev/tests).
 
-When (1) is active, Catalox `templates` are **ignored for prompt text** unless FuncX catalog points at Catalox-hosted function content (FuncX content-seed parity).
+When (1) is on, Catalox `templates` are **fallback overrides** only if FuncX resolver supports content overrides (same as other `fx/*` functions).
 
 ---
 
-## 5. FuncX package asks (summary tracker)
+## 5. FuncX package tracker (pre/post only)
 
-| FR id | Topic | Priority |
-|-------|--------|----------|
-| **FR-PRE-POST-1** | Register **`pre/synthesize`**, **`post/audit`**, **`post/fix`**, **`post/pick-best`**, **`post/craft-final`** built-ins | **P0** |
-| **FR-PRE-POST-2** | Register **`post/audit-checklist`**, **`post/audit-merge`** for ai-tasks POST pipeline | **P1** |
-| **FR-PRE-POST-3** | **`buildSidekickTemplateContext(envelope)`** export | **P0** |
-| **FR-PRE-POST-4** | Output JSON schemas = xynthesis parser contracts (§3) | **P0** |
-| **FR-PRE-POST-5** | `runSidekickGeneric(opts)` or extend FR-GEN-5 `runGenericExecution` for sidekick envelope | **P1** |
-| **FR-PRE-POST-6** | Content-seed from `xynthesis/templates/{synthesis,audit,fix,...}` + CI drift vs Catalox | **P1** |
-| **FR-PRE-POST-7** | Wire existing **`execution/*`** + **`research/plan-questions`** as canonical for pre/post catalog items (deprecate xynthesis duplicate render path) | **P0** |
+Depends on [funcx-generic-xynthesis-hosting.md](./funcx-generic-xynthesis-hosting.md) **FR-GEN-1, FR-GEN-4, FR-GEN-5** for shared template + `run()` ergonomics.
 
-Depends on [funcx-generic-xynthesis-hosting.md](./funcx-generic-xynthesis-hosting.md) **FR-GEN-1–5** for `RunOptions`, usage return shape, and generic template context.
+| FR id | Topic | Status @ 4.4.0 |
+|-------|--------|----------------|
+| **FR-PRE-POST-1** | `pre/synthesize` built-in + seed | **Open** |
+| **FR-PRE-POST-2** | `post/audit-checklist`, `post/audit-merge` | **Open** (envelope **shipped** in ai-tasks) |
+| **FR-PRE-POST-3** | `post/audit` | **Open** |
+| **FR-PRE-POST-4** | `post/fix` | **Open** |
+| **FR-PRE-POST-5** | `post/pick-best`, `post/craft-final` | **Open** |
+| **FR-PRE-POST-6** | Wire execution/* + research/plan-questions from xynthesis | **Open** (built-ins **shipped**) |
+| **FR-PRE-POST-7** | `buildSidekickTemplateContext` or FR-GEN-1 covering sidekick | **Open** |
+| **FR-PRE-POST-8** | Export `SidekickGenericEnvelope` type from `@x12i/funcx/functions` (optional) | **Open** |
 
 ---
 
-## 6. Acceptance criteria (end-to-end)
+## 6. Acceptance criteria
 
-- [ ] With `XYNTHESIS_FUNCX_SIDEKICK=1`, `runSidekickGatewayCall` never calls `loadSidekickTemplates` for registered actions; prompts come from FuncX `run()`.
-- [ ] Catalox `pre-actions` / `post-actions` items include `funcx.functionId`; validation fails if missing when FuncX mode enabled.
-- [ ] ai-tasks `runAuditPostStep` builds `post/audit-checklist` envelope — no `loadAuditTemplates` / `DEFAULT_SYSTEM`.
-- [ ] ai-tasks PRE structured synthesis uses `pre/synthesize` via xynthesis (not local template load + `executeXynthesisAction`).
-- [ ] Golden fixture: same envelope → FuncX rendered prompts hash-equal to current xynthesis rendrix output (FR-GEN-9 parity).
-- [ ] `sidekickAction` on Activix / `InvokeAttemptSummary` records FuncX `functionId`, not only transport `ask`.
+- [ ] `XYNTHESIS_FUNCX_SIDEKICK=1` → `runSidekickGatewayCall` / `runExecutionPlan` use `run()`, not `loadSidekickTemplates`.
+- [ ] Catalox items keep `funcx.functionId`; validator fails if missing when FuncX mode required.
+- [ ] ai-tasks `runAuditPostStep` uses `post/audit-checklist` envelope (no `loadAuditTemplates` / `DEFAULT_SYSTEM`).
+- [ ] Golden: FR-GEN-1 normalized prompt hash matches current xynthesis rendrix output.
+- [ ] `InvokeAttemptSummary` / Activix record FuncX `functionId`, not only transport `xynthesis/synthesis` on `ask`.
 
 ---
 
-## 7. Convergence (mermaid)
-
-```mermaid
-flowchart TB
-  subgraph ai_tasks
-    AT[buildSidekick envelope data]
-  end
-  subgraph xynthesis
-    XY[runSidekickGatewayCall / runXynthesisAiAction]
-    MAP[sidekickFuncxCatalogMap]
-    ENV[buildSidekickGenericEnvelope]
-  end
-  subgraph funcx
-    RUN["run(functionId, envelope)"]
-    TPL[Catalox / content-seed templates]
-  end
-  subgraph catalox
-    PRE[pre-actions catalog]
-    POST[post-actions catalog]
-  end
-  AT --> XY
-  XY --> MAP
-  MAP --> ENV
-  ENV --> RUN
-  RUN --> TPL
-  PRE -.->|funcx.functionId + optional override| MAP
-  POST -.->|funcx.functionId + optional override| MAP
-```
+## 7. Non-goals
 
----
-
-## 8. Non-goals
-
-- ai-skills MAIN gateway (`instructions` / `prompt` on `RunTaskRequest`).
-- Moving template **cores** (`{{core:analysis}}`) into FuncX — still rendrix/ai-skills concern; synthesis **input** may include pre-rendered downstream blocks only.
+- ai-skills MAIN gateway.
+- FuncX ownership of template **cores** — cores stay rendrix; synthesis `input` may include pre-rendered downstream text only.
 
 ---
 
-## 9. Version note
+## 8. Version note
+
+| Package | Version |
+|---------|---------|
+| `@x12i/funcx` | **4.4.0** — implement FR-PRE-POST-1..5 in **4.5.x** (suggested) |
+| `@exellix/xynthesis` | **4.4.3** — map + envelopes shipped; gateway wiring pending |
+| `@exellix/ai-tasks` | **8.5.2** — checklist envelopes shipped |
 
-- **@x12i/funcx** ≥ **4.4.0** (xynthesis dep): `run`, `getRunJsonResult`, `GenericExecutionEnvelope`, `Client.ask`.
-- New built-ins require FuncX release + content-seed; xynthesis gates behind **`XYNTHESIS_FUNCX_SIDEKICK=1`** until parity tests pass.
+Implement **pre/post content** in FuncX *after* reading §1 of [funcx-generic-xynthesis-hosting.md](./funcx-generic-xynthesis-hosting.md) (do not re-invent envelope / attribution / `getRunJsonResult`).

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@exellix/ai-tasks",
-  "version": "8.5.2",
+  "version": "8.5.3",
   "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": "^6.0.0",
+    "@exellix/ai-skills": "^6.0.2",
     "@exellix/memorix-narrix-adapter": "^2.0.0",
     "@exellix/narrix-adapter-chat": "^2.0.0",
     "@exellix/narrix-adapter-docs": "^2.0.0",
@@ -72,7 +72,7 @@
     "@exellix/narrix-ingest": "^2.0.0",
     "@exellix/narrix-runner": "^2.0.0",
     "@exellix/narrix-web-scoper": "^2.0.0",
-    "@exellix/xynthesis": "^4.4.3",
+    "@exellix/xynthesis": "^4.4.5",
     "@x12i/activix": "^8.5.0",
     "@x12i/ai-profiles": "^2.1.0",
     "@x12i/catalox": "^5.1.3",