node-autotask 0.83.0 → 0.85.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (41) hide show
  1. package/CHANGELOG.md +17 -0
  2. package/MCP_TOOL_CATALOG.json +323 -11
  3. package/README.md +1 -1
  4. package/capabilities.json +1739 -361
  5. package/dist/capabilities-data.js +2463 -1085
  6. package/dist/capabilities.cjs +4 -4
  7. package/dist/capabilities.js +1 -1
  8. package/dist/{chunk-C2AFRW5M.cjs → chunk-7GNZT7Y7.cjs} +375 -93
  9. package/dist/{chunk-ZKAJVHHZ.js → chunk-EPJG7M5C.js} +42 -7
  10. package/dist/{chunk-DBEAS3IR.js → chunk-GTTAPAGP.js} +3 -3
  11. package/dist/{chunk-HQJLIRXW.js → chunk-HF5YG4TV.js} +5 -2
  12. package/dist/{chunk-QCA5R7QF.cjs → chunk-JCKYM7FD.cjs} +3 -3
  13. package/dist/{chunk-QEMBBAF5.cjs → chunk-JV6MX2U3.cjs} +237 -202
  14. package/dist/{chunk-CV56RIGS.js → chunk-L6YCH2I4.js} +370 -88
  15. package/dist/{chunk-5AHEJCSP.cjs → chunk-PBOH2OHJ.cjs} +33 -30
  16. package/dist/{index-8Hg6dytT.d.cts → index-CCW_EpLg.d.cts} +203 -140
  17. package/dist/{index-8Hg6dytT.d.ts → index-CCW_EpLg.d.ts} +203 -140
  18. package/dist/{index-DxESlIIg.d.cts → index-DkyNXWyt.d.cts} +108 -86
  19. package/dist/{index-nXhYAQOf.d.ts → index-rWcPjRpX.d.ts} +108 -86
  20. package/dist/index.cjs +84 -84
  21. package/dist/index.d.cts +6 -5
  22. package/dist/index.d.ts +6 -5
  23. package/dist/index.js +5 -5
  24. package/dist/operations/index.cjs +51 -51
  25. package/dist/operations/index.d.cts +4 -4
  26. package/dist/operations/index.d.ts +4 -4
  27. package/dist/operations/index.js +2 -2
  28. package/dist/pool.cjs +12 -12
  29. package/dist/pool.d.cts +1 -1
  30. package/dist/pool.d.ts +1 -1
  31. package/dist/pool.js +4 -4
  32. package/dist/resources/index.cjs +27 -27
  33. package/dist/resources/index.d.cts +2 -2
  34. package/dist/resources/index.d.ts +2 -2
  35. package/dist/resources/index.js +3 -3
  36. package/dist/types/index.d.cts +1 -1
  37. package/dist/types/index.d.ts +1 -1
  38. package/docs/API.md +32 -20
  39. package/docs/RELEASING.md +2 -1
  40. package/docs/VENDOR-QUIRKS.md +3 -1
  41. package/package.json +1 -1
package/CHANGELOG.md CHANGED
@@ -7,6 +7,23 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
7
7
 
8
8
  ## [Unreleased]
9
9
 
10
+ ## [0.85.0] - 2026-11-20
11
+
12
+ ### Added
13
+
14
+ - Row and group-key labels name asset references: with labels on, query rows, `operations.aggregate` group keys and `operations.fetchByIds` records gain `productIDName` (the product name), `vendorIDName` (the vendor's company name: the vendor's entity documentation identifies `vendorID` as a Companies reference, so it is read from Companies and follows the company table's id-0 rule; a `vendorID` of 0 is resolved like `companyID` 0 by that table rule, not from a live check of `vendorID` 0) and `configurationItemCategoryIDName` (the category name). The existing semantics hold: opt-in, the shared cold name-read budget, free cache hits, `null` on a miss, capped and wrapped as untrusted content (#495).
15
+ - `configuration_items.profile` returns the item's product record (`product`, `null` with `parts.product: 'absent'` when the item has no product, a `productID` of 0 or the product is not found) and its subscriptions (`subscriptions: { items, capped }`, the Subscriptions query by `configurationItemID`, capped by the new `subscriptionLimit` option, default 50). These two parts degrade on a typed vendor fault, such as an API user without read access: the part is empty, `parts.<part>` is `'unavailable'` and `unavailable.<part>` carries the fault code, while the rest of the profile is served. With `names: true` the CI row also carries `companyIDName`, `productIDName` (taken from the product part, no second read) and `vendorIDName`. The profile stays bounded at up to eight reads; `configuration_items.get` and `configuration_items.query` now list `subscriptions.query` as related (#496).
16
+
17
+ ## [0.84.0] - 2026-11-20
18
+
19
+ ### Added
20
+
21
+ - Deleted task activity, deleted ticket activity and deleted ticket audit reads with global query/count/get and documented metadata. Administrative permissions and record visibility remain vendor-controlled; no deletion, restoration or timesheet lifecycle operation is added (#465).
22
+
23
+ ### Fixed
24
+
25
+ - Preserve the initial method and search across query pages, omit GET query values and vendor echoes from diagnostics, check each GET URL against the vendor limit and reject malformed counts. Audit queries retain exact log IDs across pages and refuse cursors outside the original audit query route. Audit reads validate raw, batch and filter IDs, follow live cursors across empty pages, require an explicit pagination cursor or end marker, and type empty fields as nullable. Aggregate result sanitization fences grouped vendor text, and audit latest queries use the int64 bound (#465).
26
+
10
27
  ## [0.83.0] - 2026-11-19
11
28
 
12
29
  ### Added
@@ -1,7 +1,7 @@
1
1
  {
2
2
  "generatedBy": "scripts/build-tool-catalog.mjs",
3
- "generatedAt": "2026-11-19T12:17:04.297Z",
4
- "planHash": "d758816a699191e3da784f70f8ebe1f37ea9458aaf528241770f7bac94ba6ede",
3
+ "generatedAt": "2026-11-20T05:02:15.646Z",
4
+ "planHash": "9521525945b1306da363ce5fb38649e17c5526f2c0842da64c3bec7993e62735",
5
5
  "metaTools": [
6
6
  {
7
7
  "name": "autotask_catalog",
@@ -51,7 +51,7 @@
51
51
  {
52
52
  "name": "autotask_read",
53
53
  "title": "Read One Registry Operation (read mode)",
54
- "description": "Route an effect=read registry operation by its exact name (never fuzzy, never a tool name): the 423 field/entity/UDF-info reads (getEntityInfo/getFieldInfo/getUdfInfo) have no dedicated tool and ride this one, and any read op is routable. For field discovery use operations.fieldCatalog (compact) instead of per-resource getFieldInfo (full dump). Read-only by construction — every op it can route is effect=read (zero mutating requests), and a write or delete op is refused BEFORE any request (cross-mode refusal; the message names the correct tool). Reads have no dry run (a read with dry_run: true is refused). Harness approval policy: approve every tool with readOnlyHint !== true (exactly 283 today); the 656 readOnlyHint: true tools — including this one — are safe ungated; the 70 destructiveHint: true tools (69 dedicated delete tools + autotask_delete) require confirm === the operation key. Migration: autotask_invoke is REPLACED by autotask_read/autotask_write/autotask_delete — update harness config. For query/count ops args[0] is a params object (filter/limit); call autotask_describe first for the exact arg shape and filter grammar. The argument set is CLOSED at the top level: an unknown argument is refused before any request, with a typed error naming the key and the valid keys.",
54
+ "description": "Route an effect=read registry operation by its exact name (never fuzzy, never a tool name): the 432 field/entity/UDF-info reads (getEntityInfo/getFieldInfo/getUdfInfo) have no dedicated tool and ride this one, and any read op is routable. For field discovery use operations.fieldCatalog (compact) instead of per-resource getFieldInfo (full dump). Read-only by construction — every op it can route is effect=read (zero mutating requests), and a write or delete op is refused BEFORE any request (cross-mode refusal; the message names the correct tool). Reads have no dry run (a read with dry_run: true is refused). Harness approval policy: approve every tool with readOnlyHint !== true (exactly 283 today); the 665 readOnlyHint: true tools — including this one — are safe ungated; the 70 destructiveHint: true tools (69 dedicated delete tools + autotask_delete) require confirm === the operation key. Migration: autotask_invoke is REPLACED by autotask_read/autotask_write/autotask_delete — update harness config. For query/count ops args[0] is a params object (filter/limit); call autotask_describe first for the exact arg shape and filter grammar. The argument set is CLOSED at the top level: an unknown argument is refused before any request, with a typed error naming the key and the valid keys.",
55
55
  "input": {
56
56
  "operation": {
57
57
  "type": "string",
@@ -71,7 +71,7 @@
71
71
  {
72
72
  "name": "autotask_write",
73
73
  "title": "Write One Registry Operation (write mode)",
74
- "description": "Route an effect=write registry operation by its exact name (never fuzzy, never a tool name), dry-run-first: the first call always travels dry_run: true (the pinned DryRunResult envelope, simulated: true — the mutating request is never issued); pass dry_run: false to apply. A read or delete op is refused BEFORE any request (cross-mode refusal; the message names the correct tool). The 2 approval-gated writes (configuration_items.moveConfigurationItem, contacts.moveToCompany) additionally require confirm === the operation key, in BOTH dry-run and apply mode. Harness approval policy: this tool is one of the 283 tools that require approval (readOnlyHint !== true); the 656 readOnlyHint: true tools are safe ungated, and the 70 destructiveHint: true tools (69 dedicated delete tools + autotask_delete) require confirm === the operation key. Migration: autotask_invoke is REPLACED by autotask_read/autotask_write/autotask_delete — update harness config. For query/count ops args[0] is a params object (filter/limit); call autotask_describe first for the exact arg shape and filter grammar. The argument set is CLOSED at the top level: an unknown argument is refused before any request, with a typed error naming the key and the valid keys.",
74
+ "description": "Route an effect=write registry operation by its exact name (never fuzzy, never a tool name), dry-run-first: the first call always travels dry_run: true (the pinned DryRunResult envelope, simulated: true — the mutating request is never issued); pass dry_run: false to apply. A read or delete op is refused BEFORE any request (cross-mode refusal; the message names the correct tool). The 2 approval-gated writes (configuration_items.moveConfigurationItem, contacts.moveToCompany) additionally require confirm === the operation key, in BOTH dry-run and apply mode. Harness approval policy: this tool is one of the 283 tools that require approval (readOnlyHint !== true); the 665 readOnlyHint: true tools are safe ungated, and the 70 destructiveHint: true tools (69 dedicated delete tools + autotask_delete) require confirm === the operation key. Migration: autotask_invoke is REPLACED by autotask_read/autotask_write/autotask_delete — update harness config. For query/count ops args[0] is a params object (filter/limit); call autotask_describe first for the exact arg shape and filter grammar. The argument set is CLOSED at the top level: an unknown argument is refused before any request, with a typed error naming the key and the valid keys.",
75
75
  "input": {
76
76
  "operation": {
77
77
  "type": "string",
@@ -101,7 +101,7 @@
101
101
  {
102
102
  "name": "autotask_delete",
103
103
  "title": "Delete One Registry Operation (delete mode)",
104
- "description": "Route an effect=destructive (delete) registry operation by its exact name (never fuzzy, never a tool name), dry-run-first: the first call always travels dry_run: true (the pinned DryRunResult envelope, simulated: true); pass dry_run: false to apply. confirm === the operation key is REQUIRED for every delete (all 69), in BOTH dry-run and apply mode — the deliberate act is the call, not the delete. A read or write op is refused BEFORE any request (cross-mode refusal; the message names the correct tool). Harness approval policy: this tool is one of the 70 destructiveHint: true tools that require approval + confirm; approve every tool with readOnlyHint !== true (exactly 283 today); the 656 readOnlyHint: true tools are safe ungated. Migration: autotask_invoke is REPLACED by autotask_read/autotask_write/autotask_delete — update harness config. The argument set is CLOSED at the top level: an unknown argument is refused before any request, with a typed error naming the key and the valid keys.",
104
+ "description": "Route an effect=destructive (delete) registry operation by its exact name (never fuzzy, never a tool name), dry-run-first: the first call always travels dry_run: true (the pinned DryRunResult envelope, simulated: true); pass dry_run: false to apply. confirm === the operation key is REQUIRED for every delete (all 69), in BOTH dry-run and apply mode — the deliberate act is the call, not the delete. A read or write op is refused BEFORE any request (cross-mode refusal; the message names the correct tool). Harness approval policy: this tool is one of the 70 destructiveHint: true tools that require approval + confirm; approve every tool with readOnlyHint !== true (exactly 283 today); the 665 readOnlyHint: true tools are safe ungated. Migration: autotask_invoke is REPLACED by autotask_read/autotask_write/autotask_delete — update harness config. The argument set is CLOSED at the top level: an unknown argument is refused before any request, with a typed error naming the key and the valid keys.",
105
105
  "input": {
106
106
  "operation": {
107
107
  "type": "string",
@@ -3247,6 +3247,318 @@
3247
3247
  "reachReason": null,
3248
3248
  "boundedAlternative": null
3249
3249
  },
3250
+ {
3251
+ "operation": "deleted_task_activity_logs.count",
3252
+ "core": false,
3253
+ "tool": "autotask_deletedTaskActivityLog_count",
3254
+ "purpose": "Count DeletedTaskActivityLog audit records matching a JSON filter.",
3255
+ "preferredWhen": null,
3256
+ "backingOperation": "deleted_task_activity_logs.count",
3257
+ "effect": "read",
3258
+ "dryRunFirst": false,
3259
+ "confirm": false,
3260
+ "requiredArgs": [],
3261
+ "tier": "advanced",
3262
+ "reachable": true,
3263
+ "reach": "dedicated tool",
3264
+ "reachReason": null,
3265
+ "boundedAlternative": null
3266
+ },
3267
+ {
3268
+ "operation": "deleted_task_activity_logs.get",
3269
+ "core": false,
3270
+ "tool": "autotask_deletedTaskActivityLog_get",
3271
+ "purpose": "Get one DeletedTaskActivityLog audit record by its log id.",
3272
+ "preferredWhen": "Use the audit log record id, not the task or ticket id; discover log ids with a bounded filtered query.",
3273
+ "backingOperation": "deleted_task_activity_logs.get",
3274
+ "effect": "read",
3275
+ "dryRunFirst": false,
3276
+ "confirm": false,
3277
+ "requiredArgs": [
3278
+ "id"
3279
+ ],
3280
+ "tier": "advanced",
3281
+ "reachable": true,
3282
+ "reach": "dedicated tool",
3283
+ "reachReason": null,
3284
+ "boundedAlternative": null
3285
+ },
3286
+ {
3287
+ "operation": "deleted_task_activity_logs.getEntityInfo",
3288
+ "core": false,
3289
+ "tool": null,
3290
+ "purpose": "Get DeletedTaskActivityLog entity capability metadata.",
3291
+ "preferredWhen": null,
3292
+ "backingOperation": "deleted_task_activity_logs.getEntityInfo",
3293
+ "effect": "read",
3294
+ "dryRunFirst": false,
3295
+ "confirm": false,
3296
+ "requiredArgs": [],
3297
+ "tier": "advanced",
3298
+ "reachable": true,
3299
+ "reach": "autotask_read (exact operation name; effect=read — read-only; zero mutating requests)",
3300
+ "reachReason": "no dedicated tool — the op is still discoverable and invocable by exact name",
3301
+ "boundedAlternative": null
3302
+ },
3303
+ {
3304
+ "operation": "deleted_task_activity_logs.getFieldInfo",
3305
+ "core": false,
3306
+ "tool": null,
3307
+ "purpose": "Get the DeletedTaskActivityLog field catalog (types, picklists, required, maxLength) — the full raw field dump (the largest read of the info trio; compact discovery: operations.fieldCatalog).",
3308
+ "preferredWhen": "Use when the full raw field catalog is needed. Requires Admin-level access to Projects & Tasks or Service Desk. Visibility and module/API-user permissions remain conditional; an empty result does not establish absence. Actor resource IDs do not establish company ownership, and referenced task/ticket records may be unavailable. Read-only audit access does not restore deleted records or unpost time.",
3309
+ "backingOperation": "deleted_task_activity_logs.getFieldInfo",
3310
+ "effect": "read",
3311
+ "dryRunFirst": false,
3312
+ "confirm": false,
3313
+ "requiredArgs": [],
3314
+ "tier": "advanced",
3315
+ "reachable": true,
3316
+ "reach": "autotask_read (exact operation name; effect=read — read-only; zero mutating requests)",
3317
+ "reachReason": "no dedicated tool — the op is still discoverable and invocable by exact name",
3318
+ "boundedAlternative": null
3319
+ },
3320
+ {
3321
+ "operation": "deleted_task_activity_logs.getUdfInfo",
3322
+ "core": false,
3323
+ "tool": null,
3324
+ "purpose": "Get the documented DeletedTaskActivityLog UDF metadata catalog; this entity does not support UDF writes.",
3325
+ "preferredWhen": null,
3326
+ "backingOperation": "deleted_task_activity_logs.getUdfInfo",
3327
+ "effect": "read",
3328
+ "dryRunFirst": false,
3329
+ "confirm": false,
3330
+ "requiredArgs": [],
3331
+ "tier": "advanced",
3332
+ "reachable": true,
3333
+ "reach": "autotask_read (exact operation name; effect=read — read-only; zero mutating requests)",
3334
+ "reachReason": "no dedicated tool — the op is still discoverable and invocable by exact name",
3335
+ "boundedAlternative": null
3336
+ },
3337
+ {
3338
+ "operation": "deleted_task_activity_logs.query",
3339
+ "core": false,
3340
+ "tool": "autotask_deletedTaskActivityLog_query",
3341
+ "purpose": "Query DeletedTaskActivityLog audit records with a JSON filter.",
3342
+ "preferredWhen": "Default for filtered reads (the bounded query op). queryAll is the unbounded raw walk — only when you need the ENTIRE set and accept a large payload; default to the bounded query op. Prefer an includeFields subset over the full model (field names via operations.fieldCatalog). latest: N is the latest-N rows (id-descending) when the newest rows are the goal (the vendor has no sort — count-anchored, docs/API.md §4). Prefer a hand-listed includeFields for common narrow reads (removed the closed fieldsPreset presets — the v1 billing_join field list for billing_items.query, if you need it, is: companyID, ticketID, projectID, timeEntryID, contractServiceID, contractID, billingCodeID, expenseItemID, itemDate, quantity, rate, extendedPrice, totalAmount, nonBillable); noteChars: N caps the untrusted-class free-text fields of the resource (notes/descriptions/UDF prose) to N chars each with the explicit … [+N chars truncated] marker (opt-in; the raw result when absent).",
3343
+ "backingOperation": "deleted_task_activity_logs.query",
3344
+ "effect": "read",
3345
+ "dryRunFirst": false,
3346
+ "confirm": false,
3347
+ "requiredArgs": [],
3348
+ "tier": "advanced",
3349
+ "reachable": true,
3350
+ "reach": "dedicated tool",
3351
+ "reachReason": null,
3352
+ "boundedAlternative": null
3353
+ },
3354
+ {
3355
+ "operation": "deleted_ticket_activity_logs.count",
3356
+ "core": false,
3357
+ "tool": "autotask_deletedTicketActivityLog_count",
3358
+ "purpose": "Count DeletedTicketActivityLog audit records matching a JSON filter.",
3359
+ "preferredWhen": null,
3360
+ "backingOperation": "deleted_ticket_activity_logs.count",
3361
+ "effect": "read",
3362
+ "dryRunFirst": false,
3363
+ "confirm": false,
3364
+ "requiredArgs": [],
3365
+ "tier": "advanced",
3366
+ "reachable": true,
3367
+ "reach": "dedicated tool",
3368
+ "reachReason": null,
3369
+ "boundedAlternative": null
3370
+ },
3371
+ {
3372
+ "operation": "deleted_ticket_activity_logs.get",
3373
+ "core": false,
3374
+ "tool": "autotask_deletedTicketActivityLog_get",
3375
+ "purpose": "Get one DeletedTicketActivityLog audit record by its log id.",
3376
+ "preferredWhen": "Use the audit log record id, not the task or ticket id; discover log ids with a bounded filtered query.",
3377
+ "backingOperation": "deleted_ticket_activity_logs.get",
3378
+ "effect": "read",
3379
+ "dryRunFirst": false,
3380
+ "confirm": false,
3381
+ "requiredArgs": [
3382
+ "id"
3383
+ ],
3384
+ "tier": "advanced",
3385
+ "reachable": true,
3386
+ "reach": "dedicated tool",
3387
+ "reachReason": null,
3388
+ "boundedAlternative": null
3389
+ },
3390
+ {
3391
+ "operation": "deleted_ticket_activity_logs.getEntityInfo",
3392
+ "core": false,
3393
+ "tool": null,
3394
+ "purpose": "Get DeletedTicketActivityLog entity capability metadata.",
3395
+ "preferredWhen": null,
3396
+ "backingOperation": "deleted_ticket_activity_logs.getEntityInfo",
3397
+ "effect": "read",
3398
+ "dryRunFirst": false,
3399
+ "confirm": false,
3400
+ "requiredArgs": [],
3401
+ "tier": "advanced",
3402
+ "reachable": true,
3403
+ "reach": "autotask_read (exact operation name; effect=read — read-only; zero mutating requests)",
3404
+ "reachReason": "no dedicated tool — the op is still discoverable and invocable by exact name",
3405
+ "boundedAlternative": null
3406
+ },
3407
+ {
3408
+ "operation": "deleted_ticket_activity_logs.getFieldInfo",
3409
+ "core": false,
3410
+ "tool": null,
3411
+ "purpose": "Get the DeletedTicketActivityLog field catalog (types, picklists, required, maxLength) — the full raw field dump (the largest read of the info trio; compact discovery: operations.fieldCatalog).",
3412
+ "preferredWhen": "Use when the full raw field catalog is needed. Requires Admin-level access to Projects & Tasks or Service Desk. Visibility and module/API-user permissions remain conditional; an empty result does not establish absence. Actor resource IDs do not establish company ownership, and referenced task/ticket records may be unavailable. Read-only audit access does not restore deleted records or unpost time.",
3413
+ "backingOperation": "deleted_ticket_activity_logs.getFieldInfo",
3414
+ "effect": "read",
3415
+ "dryRunFirst": false,
3416
+ "confirm": false,
3417
+ "requiredArgs": [],
3418
+ "tier": "advanced",
3419
+ "reachable": true,
3420
+ "reach": "autotask_read (exact operation name; effect=read — read-only; zero mutating requests)",
3421
+ "reachReason": "no dedicated tool — the op is still discoverable and invocable by exact name",
3422
+ "boundedAlternative": null
3423
+ },
3424
+ {
3425
+ "operation": "deleted_ticket_activity_logs.getUdfInfo",
3426
+ "core": false,
3427
+ "tool": null,
3428
+ "purpose": "Get the documented DeletedTicketActivityLog UDF metadata catalog; this entity does not support UDF writes.",
3429
+ "preferredWhen": null,
3430
+ "backingOperation": "deleted_ticket_activity_logs.getUdfInfo",
3431
+ "effect": "read",
3432
+ "dryRunFirst": false,
3433
+ "confirm": false,
3434
+ "requiredArgs": [],
3435
+ "tier": "advanced",
3436
+ "reachable": true,
3437
+ "reach": "autotask_read (exact operation name; effect=read — read-only; zero mutating requests)",
3438
+ "reachReason": "no dedicated tool — the op is still discoverable and invocable by exact name",
3439
+ "boundedAlternative": null
3440
+ },
3441
+ {
3442
+ "operation": "deleted_ticket_activity_logs.query",
3443
+ "core": false,
3444
+ "tool": "autotask_deletedTicketActivityLog_query",
3445
+ "purpose": "Query DeletedTicketActivityLog audit records with a JSON filter.",
3446
+ "preferredWhen": "Default for filtered reads (the bounded query op). queryAll is the unbounded raw walk — only when you need the ENTIRE set and accept a large payload; default to the bounded query op. Prefer an includeFields subset over the full model (field names via operations.fieldCatalog). latest: N is the latest-N rows (id-descending) when the newest rows are the goal (the vendor has no sort — count-anchored, docs/API.md §4). Prefer a hand-listed includeFields for common narrow reads (removed the closed fieldsPreset presets — the v1 billing_join field list for billing_items.query, if you need it, is: companyID, ticketID, projectID, timeEntryID, contractServiceID, contractID, billingCodeID, expenseItemID, itemDate, quantity, rate, extendedPrice, totalAmount, nonBillable); noteChars: N caps the untrusted-class free-text fields of the resource (notes/descriptions/UDF prose) to N chars each with the explicit … [+N chars truncated] marker (opt-in; the raw result when absent).",
3447
+ "backingOperation": "deleted_ticket_activity_logs.query",
3448
+ "effect": "read",
3449
+ "dryRunFirst": false,
3450
+ "confirm": false,
3451
+ "requiredArgs": [],
3452
+ "tier": "advanced",
3453
+ "reachable": true,
3454
+ "reach": "dedicated tool",
3455
+ "reachReason": null,
3456
+ "boundedAlternative": null
3457
+ },
3458
+ {
3459
+ "operation": "deleted_ticket_logs.count",
3460
+ "core": false,
3461
+ "tool": "autotask_deletedTicketLog_count",
3462
+ "purpose": "Count DeletedTicketLog audit records matching a JSON filter.",
3463
+ "preferredWhen": null,
3464
+ "backingOperation": "deleted_ticket_logs.count",
3465
+ "effect": "read",
3466
+ "dryRunFirst": false,
3467
+ "confirm": false,
3468
+ "requiredArgs": [],
3469
+ "tier": "advanced",
3470
+ "reachable": true,
3471
+ "reach": "dedicated tool",
3472
+ "reachReason": null,
3473
+ "boundedAlternative": null
3474
+ },
3475
+ {
3476
+ "operation": "deleted_ticket_logs.get",
3477
+ "core": false,
3478
+ "tool": "autotask_deletedTicketLog_get",
3479
+ "purpose": "Get one DeletedTicketLog audit record by its log id.",
3480
+ "preferredWhen": "Use the audit log record id, not the task or ticket id; discover log ids with a bounded filtered query.",
3481
+ "backingOperation": "deleted_ticket_logs.get",
3482
+ "effect": "read",
3483
+ "dryRunFirst": false,
3484
+ "confirm": false,
3485
+ "requiredArgs": [
3486
+ "id"
3487
+ ],
3488
+ "tier": "advanced",
3489
+ "reachable": true,
3490
+ "reach": "dedicated tool",
3491
+ "reachReason": null,
3492
+ "boundedAlternative": null
3493
+ },
3494
+ {
3495
+ "operation": "deleted_ticket_logs.getEntityInfo",
3496
+ "core": false,
3497
+ "tool": null,
3498
+ "purpose": "Get DeletedTicketLog entity capability metadata.",
3499
+ "preferredWhen": null,
3500
+ "backingOperation": "deleted_ticket_logs.getEntityInfo",
3501
+ "effect": "read",
3502
+ "dryRunFirst": false,
3503
+ "confirm": false,
3504
+ "requiredArgs": [],
3505
+ "tier": "advanced",
3506
+ "reachable": true,
3507
+ "reach": "autotask_read (exact operation name; effect=read — read-only; zero mutating requests)",
3508
+ "reachReason": "no dedicated tool — the op is still discoverable and invocable by exact name",
3509
+ "boundedAlternative": null
3510
+ },
3511
+ {
3512
+ "operation": "deleted_ticket_logs.getFieldInfo",
3513
+ "core": false,
3514
+ "tool": null,
3515
+ "purpose": "Get the DeletedTicketLog field catalog (types, picklists, required, maxLength) — the full raw field dump (the largest read of the info trio; compact discovery: operations.fieldCatalog).",
3516
+ "preferredWhen": "Use when the full raw field catalog is needed. Requires Admin-level access to Projects & Tasks or Service Desk. Visibility and module/API-user permissions remain conditional; an empty result does not establish absence. Actor resource IDs do not establish company ownership, and referenced task/ticket records may be unavailable. Read-only audit access does not restore deleted records or unpost time.",
3517
+ "backingOperation": "deleted_ticket_logs.getFieldInfo",
3518
+ "effect": "read",
3519
+ "dryRunFirst": false,
3520
+ "confirm": false,
3521
+ "requiredArgs": [],
3522
+ "tier": "advanced",
3523
+ "reachable": true,
3524
+ "reach": "autotask_read (exact operation name; effect=read — read-only; zero mutating requests)",
3525
+ "reachReason": "no dedicated tool — the op is still discoverable and invocable by exact name",
3526
+ "boundedAlternative": null
3527
+ },
3528
+ {
3529
+ "operation": "deleted_ticket_logs.getUdfInfo",
3530
+ "core": false,
3531
+ "tool": null,
3532
+ "purpose": "Get the documented DeletedTicketLog UDF metadata catalog; this entity does not support UDF writes.",
3533
+ "preferredWhen": null,
3534
+ "backingOperation": "deleted_ticket_logs.getUdfInfo",
3535
+ "effect": "read",
3536
+ "dryRunFirst": false,
3537
+ "confirm": false,
3538
+ "requiredArgs": [],
3539
+ "tier": "advanced",
3540
+ "reachable": true,
3541
+ "reach": "autotask_read (exact operation name; effect=read — read-only; zero mutating requests)",
3542
+ "reachReason": "no dedicated tool — the op is still discoverable and invocable by exact name",
3543
+ "boundedAlternative": null
3544
+ },
3545
+ {
3546
+ "operation": "deleted_ticket_logs.query",
3547
+ "core": false,
3548
+ "tool": "autotask_deletedTicketLog_query",
3549
+ "purpose": "Query DeletedTicketLog audit records with a JSON filter.",
3550
+ "preferredWhen": "Default for filtered reads (the bounded query op). queryAll is the unbounded raw walk — only when you need the ENTIRE set and accept a large payload; default to the bounded query op. Prefer an includeFields subset over the full model (field names via operations.fieldCatalog). latest: N is the latest-N rows (id-descending) when the newest rows are the goal (the vendor has no sort — count-anchored, docs/API.md §4). Prefer a hand-listed includeFields for common narrow reads (removed the closed fieldsPreset presets — the v1 billing_join field list for billing_items.query, if you need it, is: companyID, ticketID, projectID, timeEntryID, contractServiceID, contractID, billingCodeID, expenseItemID, itemDate, quantity, rate, extendedPrice, totalAmount, nonBillable); noteChars: N caps the untrusted-class free-text fields of the resource (notes/descriptions/UDF prose) to N chars each with the explicit … [+N chars truncated] marker (opt-in; the raw result when absent).",
3551
+ "backingOperation": "deleted_ticket_logs.query",
3552
+ "effect": "read",
3553
+ "dryRunFirst": false,
3554
+ "confirm": false,
3555
+ "requiredArgs": [],
3556
+ "tier": "advanced",
3557
+ "reachable": true,
3558
+ "reach": "dedicated tool",
3559
+ "reachReason": null,
3560
+ "boundedAlternative": null
3561
+ },
3250
3562
  {
3251
3563
  "operation": "departments.count",
3252
3564
  "core": false,
@@ -15580,8 +15892,8 @@
15580
15892
  "operation": "configuration_items.profile",
15581
15893
  "core": false,
15582
15894
  "tool": "autotask_configurationItem_profile",
15583
- "purpose": "Get the full profile of one configuration item in a single call: the item, its type and category records, its notes, related items and billing-product associations.",
15584
- "preferredWhen": "The single read for 'what is this configuration item' — replaces 5-6 raw reads + describes with one call.",
15895
+ "purpose": "Get the full profile of one configuration item in a single call: the item, its type, category and product records, its notes, related items, billing-product associations and subscriptions (software/licence terms keyed by configurationItemID).",
15896
+ "preferredWhen": "The single read for 'what is this configuration item' — replaces 7-8 raw reads + describes with one call, including the item's subscription terms (start/end dates, vendor, period price/cost).",
15585
15897
  "backingOperation": "configuration_items.profile",
15586
15898
  "effect": "read",
15587
15899
  "dryRunFirst": false,
@@ -24951,11 +25263,11 @@
24951
25263
  }
24952
25264
  ],
24953
25265
  "counts": {
24954
- "registryOperations": 1357,
25266
+ "registryOperations": 1375,
24955
25267
  "coreOperations": 10,
24956
- "catalogRows": 1357,
24957
- "withTool": 934,
24958
- "readModeOnly": 423,
25268
+ "catalogRows": 1375,
25269
+ "withTool": 943,
25270
+ "readModeOnly": 432,
24959
25271
  "neverExposed": 0,
24960
25272
  "metaTools": 5
24961
25273
  }
package/README.md CHANGED
@@ -389,7 +389,7 @@ The SDK ships the mechanical substrate, not a server (no MCP imports, no zod):
389
389
  governor place: `src/operations/invoke.ts`).
390
390
 
391
391
  <!-- BEGIN GENERATED:approval-policy -->
392
- **Harness approval policy (recommended).** Require approval on every tool whose MCP annotation is `readOnlyHint !== true` — today exactly **283 tools**: the 281 dedicated write/delete tools (212 `effect=write` + 69 `effect=destructive`, every one of them has a dedicated tool) + `autotask_write` + `autotask_delete`. The remaining **656 tools** (the 643 dedicated read tools + the 10 core read tools + `autotask_read` + `autotask_catalog` + `autotask_describe`) all carry `readOnlyHint: true` and are safe ungated: every op they can route is `effect=read` (zero mutating requests). Refined class for the highest-risk ops: the **70 tools with `destructiveHint: true`** (69 dedicated delete tools + `autotask_delete`) additionally require `confirm === <operation key>` even inside `autotask_delete`. The approval-gated writes (`configuration_items.moveConfigurationItem`, `contacts.moveToCompany`) require the same confirm inside `autotask_write`. Migration: `autotask_invoke` is REPLACED by `autotask_read`/`autotask_write`/`autotask_delete` — update harness config and remove any `autotask_invoke` entry. The rule is derivable from the registry `effect` column and the mode tools’ fixed annotations; it never needs a hand-maintained name list.
392
+ **Harness approval policy (recommended).** Require approval on every tool whose MCP annotation is `readOnlyHint !== true` — today exactly **283 tools**: the 281 dedicated write/delete tools (212 `effect=write` + 69 `effect=destructive`, every one of them has a dedicated tool) + `autotask_write` + `autotask_delete`. The remaining **665 tools** (the 652 dedicated read tools + the 10 core read tools + `autotask_read` + `autotask_catalog` + `autotask_describe`) all carry `readOnlyHint: true` and are safe ungated: every op they can route is `effect=read` (zero mutating requests). Refined class for the highest-risk ops: the **70 tools with `destructiveHint: true`** (69 dedicated delete tools + `autotask_delete`) additionally require `confirm === <operation key>` even inside `autotask_delete`. The approval-gated writes (`configuration_items.moveConfigurationItem`, `contacts.moveToCompany`) require the same confirm inside `autotask_write`. Migration: `autotask_invoke` is REPLACED by `autotask_read`/`autotask_write`/`autotask_delete` — update harness config and remove any `autotask_invoke` entry. The rule is derivable from the registry `effect` column and the mode tools’ fixed annotations; it never needs a hand-maintained name list.
393
393
  <!-- END GENERATED:approval-policy -->
394
394
  **Provider tool-search interop.** Hosts with provider-native tool search
395
395
  (OpenAI `type: "tool_search"` / `defer_loading`; Anthropic's tool search