jaz-clio 5.2.6 → 5.3.0

package/README.md

@@ -54,7 +54,7 @@ clio practice create-engagement acme-pte-ltd --type monthly-close --period 2026-
 
 ## MCP Server
 
-272 CLI tools, available to any AI agent that speaks MCP. Runs locally — no cloud, no ports. Includes the v5.2.0 `practice_*` tools (init, onboard_client, list_clients, load_client, create_engagement, load_engagement) so an agent in Claude Desktop or Claude Code can scaffold and load client workspaces conversationally.
+273 CLI tools, available to any AI agent that speaks MCP. Runs locally — no cloud, no ports. Includes the v5.2.0 `practice_*` tools (init, onboard_client, list_clients, load_client, create_engagement, load_engagement) so an agent in Claude Desktop or Claude Code can scaffold and load client workspaces conversationally.
 
 **Claude Code:**
 ```bash

package/assets/skills/api/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: jaz-api
-version: 5.2.6
+version: 5.3.0
 description: >-
   Use this skill whenever you call, debug, or review code that touches the Jaz
   REST API. Covers field names, response shapes, 117 production gotchas, error
@@ -437,6 +437,10 @@ Bills, invoices, and credit notes share identical mandatory field specs. Adding
 
 136. **Sync bulk-upsert response carries per-row failures** — `bulk_upsert_currency_rates` and `bulk_upsert_chart_of_accounts` return `{ resourceIds: string[], failedRows: ImportedRowError[], failedCount: number }` synchronously (no jobId polling needed). Each `failedRows` entry: `{ rowIndex, columnName, columnValue, errorCode, errorMessage }`. Empty `failedRows: []` + `failedCount: 0` on full success. For `bulk_upsert_currency_rates` specifically: omitting `rateApplicableTo` defaults it to `rateApplicableFrom - 0.999ms` (prevents temporal gaps in rate lookups). Contrast with async bulk-upserts (contacts, invoices, journals, etc.) which return `{ jobId }` and need `search_background_jobs` polling — there, per-row failures live in the job's `errorDetails` field instead.
 
+137. **`bulk_upsert_contacts` request-level validation** — fails the WHOLE batch with HTTP 422 (no per-row partial success at this layer). Five rules to satisfy before submitting: (a) every contact must have `customer: true` OR `supplier: true` after defaults+backfill — for updates, the API backfills omitted flags from the existing contact; for creates, you must explicitly set at least one. (b) `emailList[]` entries within a contact must be case-insensitively unique. (c) `customerPaymentTerms.value` and `supplierPaymentTerms.value` must be positive integers when `name` != "CUSTOM". (d) `name` must be unique within the batch (after whitespace+case normalize). (e) When `billingAddress` or `shippingAddress` is provided, its `addressLine1` is required. Pre-validate client-side before calling; one bad row rejects the entire batch and the agent loses any successful work-in-progress.
+
+138. **`get_contact_signals` — read-only contact-history pattern lookup** — `GET /api/v1/contacts/{resourceId}/signals?btType=…` returns the contact's modal patterns (currency, payment-terms, tax-inclusion/presence, top-COA, top-item), cadence (median interval days, days-since-last, interval ratio), and outstanding-balance snapshot for one (contact × business-transaction-type) pair. `btType` is required: `SALE` | `PURCHASE` | `SALE_CREDIT_NOTE` | `PURCHASE_CREDIT_NOTE`. Returns null `data` when sampleSize < 5 or the freshness layer is unavailable. Cache key is per-(contactId, btType) pair, so repeated calls for the same pair are cheap. **Three slices are always empty/null on this endpoint** — `severitySummary`, `outlierFlags`, `revealedDivergences` — because they require a draft to compare against; those populate only on the per-result `contactInsight` object inside `validate_drafts` responses. Use this tool for "what does this contact normally look like?" questions before drafting; use `validate_drafts` for "how does this draft compare to the contact's history?" questions after drafting.
+
 ## Supporting Files
 
 For detailed reference, read these files in this skill directory:

package/assets/skills/cli/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: jaz-cli
-version: 5.2.6
+version: 5.3.0
 description: >-
   Use this skill when running Clio CLI commands, building shell scripts with
   Clio, debugging auth issues, understanding --json output, paginating results,

package/assets/skills/conversion/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: jaz-conversion
-version: 5.2.6
+version: 5.3.0
 description: >-
   Use this skill when migrating accounting data into Jaz — importing from Xero,
   QuickBooks, Sage, MYOB, or Excel exports. Covers the full conversion pipeline:

package/assets/skills/jobs/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: jaz-jobs
-version: 5.2.6
+version: 5.3.0
 description: >-
   Use this skill for recurring accounting workflows — month/quarter/year-end
   close, bank reconciliation, GST/VAT filing, payment runs, credit control,

package/assets/skills/practice/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: jaz-practice
-version: 5.2.6
+version: 5.3.0
 description: >-
   Use this skill whenever an accounting practitioner is doing client work in
   Jaz — closing the books, filing GST, year-end statutory, onboarding a new

package/assets/skills/transaction-recipes/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: jaz-recipes
-version: 5.2.6
+version: 5.3.0
 description: >-
   Use this skill when modeling complex multi-step accounting transactions —
   anything that spans multiple periods, involves changing amounts, or requires