@open-agent-toolkit/cli 0.2.19 → 0.2.21

package/assets/skills/subagent-orchestration/references/provider-codex.md

@@ -1,7 +1,7 @@
 ---
-guidance_version: 2026-07-22
-last_verified: 2026-07-22
-review_after: 2026-09-04
+guidance_version: 2026-07-25
+last_verified: 2026-07-25
+review_after: 2026-09-08
 ---
 
 # Codex and OpenAI Model Selection
@@ -33,24 +33,50 @@ name includes `codex`.
 
 ## Dated Task-Class Matrix
 
-| Task class               | Default                 | Economy                                                                                            | Escalation                                           | Floor notes                                                    |
-| ------------------------ | ----------------------- | -------------------------------------------------------------------------------------------------- | ---------------------------------------------------- | -------------------------------------------------------------- |
-| `mechanical-recon`       | `gpt-5.6-luna`, `high`  | Direct API only: `gpt-5.4-mini` medium; `gpt-5.4-nano` medium for strict extraction/classification | `gpt-5.6-terra`, medium or high                      | Do not use Luna none/low for broad repository work.            |
-| `intelligent-recon`      | `gpt-5.6-terra`, `high` | Terra `medium` with tight scope and verification                                                   | Sol `medium`, then `high`                            | A silent miss disqualifies Terra none/low.                     |
-| `default-implementation` | `gpt-5.6-sol`, `medium` | Terra `high` for independently bounded, strongly tested work                                       | Sol `high`                                           | Luna is not the normal implementation lead.                    |
-| `hard-reasoning`         | `gpt-5.6-sol`, `high`   | Sol `medium` only after narrowing the problem                                                      | Sol `xhigh`                                          | Do not automatically escalate Terra to xhigh/max; move to Sol. |
-| `consequential`          | `gpt-5.6-sol`, `xhigh`  | No routine economy route                                                                           | Sol `max`, or a separately evaluated Sol `pro` route | Require independent review and root-owned authorization.       |
+| Task class               | Default                                        | Economy                                                                                            | Escalation                                                                                                       | Floor notes                                                                                     |
+| ------------------------ | ---------------------------------------------- | -------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------- | ----------------------------------------------------------------------------------------------- |
+| `mechanical-recon`       | `gpt-5.6-luna`, `high`                         | Direct API only: `gpt-5.4-mini` medium; `gpt-5.4-nano` medium for strict extraction/classification | `gpt-5.6-terra`, medium or high                                                                                  | Do not use Luna none/low for broad repository work.                                             |
+| `intelligent-recon`      | `gpt-5.6-terra`, `high`                        | Terra `medium` with tight scope and verification                                                   | Sol `medium`, then `high`                                                                                        | A silent miss disqualifies Terra none/low.                                                      |
+| `default-implementation` | `gpt-5.6-sol`, `medium`                        | Terra `high` for independently bounded, strongly tested work                                       | Sol `high`                                                                                                       | Luna is not the normal implementation lead.                                                     |
+| `hard-reasoning`         | `gpt-5.6-sol`, `high`                          | Sol `medium` only after narrowing the problem                                                      | Sol `xhigh`                                                                                                      | Do not automatically escalate Terra to xhigh/max; move to Sol.                                  |
+| `consequential`          | `gpt-5.6-sol`, `high`, plus independent review | No routine economy route                                                                           | Sol `xhigh` when deeper reasoning is required; `max` or a separately evaluated `pro` route only after evaluation | Consequence adds review and root authorization; it does not automatically require xhigh or max. |
 
 `reasoning.mode: "pro"` is a separate quality/latency/cost control on GPT-5.6,
 not a model slug and not an effort label. Record it independently. Evaluate it
 against max or xhigh on representative consequential work before adopting it.
 
+The task-class ladder is work-shape based. Sol is the code-first,
+trajectory-efficient route for implementation and hard reasoning; this does
+not establish a provider-independent ranking against interpretation-heavy
+models in other harnesses. Consequential work requires independent review and
+root-owned authorization. It does not automatically force Sol xhigh or max:
+choose effort from reasoning depth, then add the consequence controls.
+
 ## Long-Context Floor
 
 For very large context, prefer Sol or Terra. Published GPT-5.6 results show a
 large Luna retention drop in the 256K-to-1M range. Large context does not change
 the task class, but it may disqualify Luna, mini, or nano.
 
+For Sol requests above 272K input tokens, the current direct-API price step is
+2× input and 1.5× output. Apply the threshold to the whole request and verify
+the live pricing contract before cost-sensitive dispatch. Crossing this
+threshold can change the economical route even when Sol remains the capability
+choice.
+
+## Trajectory Economics
+
+Token list price and total trajectory cost are separate. A model with a higher
+output-token price can still cost less per completed task when it uses fewer
+output tokens, steps, tool calls, retries, or recoveries. Conversely, a cheap
+attempt is not economical when completion rate is low or operator intervention
+is high.
+
+Evaluate input, cached-input, and output tokens together with the multi-measure
+speed contract from `model-selection-principles.md`. Do not use token price
+alone as a proxy for wall-clock efficiency, and do not infer latency from
+trajectory length without a measured runtime.
+
 ## Tool-Heavy Work
 
 Use Programmatic Tool Calling only for bounded processing such as filtering,

package/assets/skills/subagent-orchestration/references/provider-cursor.md

@@ -1,8 +1,11 @@
 ---
-guidance_version: 2026-07-22
-last_verified: 2026-07-22
+guidance_version: 2026-07-25
+last_verified: 2026-07-25
 review_after: 2026-09-04
-catalog_basis: user-supplied Cursor snapshot plus current Cursor documentation
+catalog_basis:
+  live `cursor-agent models` catalog and CursorBench 3.2, with Opus 5
+  and Opus 4.8 pin selectors probe-verified against Cursor 3.12.30 via
+  subagentStart lifecycle hooks
 ---
 
 # Cursor Model Selection
@@ -23,29 +26,102 @@ conflict.
 The Cursor SDK exposes the Cursor runtime, harness, and models. It is not a
 transparent raw OpenAI or Anthropic API call.
 
+Every exact route below is dated and provisional. Verify the live root or
+nested catalog, resolved identity, reasoning controls, and fallback behavior
+before launch.
+
 ## Service-Tier Rule
 
 Treat every alias ending in `-fast` as a service-tier selection, not a higher
 capability class, unless current Cursor documentation explicitly says
 otherwise. Composer 2.5 fast is documented as the same intelligence at a higher
 price. Use standard aliases for background work and fast aliases only when
-measured wall-clock latency justifies the premium.
+multi-measure latency evidence justifies the premium.
 
 Record the model and the service tier separately even when Cursor encodes both
-in one opaque alias.
+in one opaque alias, and apply the multi-measure speed contract from
+`model-selection-principles.md`. A lower active runtime or higher output rate
+does not by itself prove lower user-observed elapsed time.
 
 ## Dated Task-Class Matrix
 
-Use exact aliases from the live catalog. The examples below were present in the
-user's 2026-07-21 snapshot.
+Use exact aliases from the live catalog. The examples below come from two
+observations, not one. Most were present in a 2026-07-21 catalog snapshot. The
+`claude-opus-5` and `claude-opus-4-8` routes postdate it — Opus 5 released
+2026-07-24 — and were confirmed against the live catalog and probe-verified on
+2026-07-25, as recorded under Verified Opus 5 Cursor Routes below. The
+remainder of the catalog has not been re-snapshotted since 2026-07-21, so treat
+non-Opus entries as the older and weaker observation.
+
+| Task class               | Default                                                                                                                                                      | Economy                                                                              | Escalation                                                                                                             | Floor notes                                                                                                                                                                                                                                                                     |
+| ------------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------ | ---------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| `mechanical-recon`       | `composer-2.5`                                                                                                                                               | `composer-2.5`                                                                       | `gpt-5.6-luna-high`                                                                                                    | Use `composer-2.5-fast` or Luna fast only for latency, not capability.                                                                                                                                                                                                          |
+| `intelligent-recon`      | `cursor-grok-4.5-medium` or `gpt-5.6-sol-medium`                                                                                                             | `gpt-5.6-terra-high`                                                                 | `gpt-5.6-sol-high`                                                                                                     | Grok medium is a primary route; Sol medium is the conservative silent-miss alternative; Terra high is the cost-saving route.                                                                                                                                                    |
+| `default-implementation` | `gpt-5.6-sol-medium`                                                                                                                                         | `composer-2.5` for bounded, testable changes                                         | `claude-opus-5-thinking-medium`                                                                                        | Sol is the code-first incumbent; Opus 5 medium is the substantive route for interpretation-heavy work; `cursor-grok-4.5-medium` remains a primary alternative.                                                                                                                  |
+| `hard-reasoning`         | `claude-opus-5-thinking-high`                                                                                                                                | `cursor-grok-4.5-high` for architecture, ambiguous debugging, and incident diagnosis | `claude-opus-5-thinking-xhigh`, then `gpt-5.6-sol-xhigh` for code-first work                                           | Opus 5 high is the starting point. Escalate to xhigh only for a reasoning-depth bottleneck. Do not infer cross-provider effort equivalence.                                                                                                                                     |
+| `consequential`          | The task's own reasoning-depth route, plus independent cross-family review: typically `gpt-5.6-sol-high` authoring with `claude-opus-5-thinking-high` review | No routine economy route                                                             | Raise the pair to xhigh for a reasoning-depth bottleneck; Sol max plus Opus 5 max only after a workload-specific sweep | Consequence adds independent cross-family review and root authorization, not automatic top effort. Select effort from reasoning depth exactly as the non-consequential row would, then add independence on top. For cyber-sensitive review, do not rely on Fable or Grok alone. |
+
+## Verified Opus 5 Cursor Routes
+
+Opus 5 is a qualified Cursor route. Five effort rungs plus an Opus 4.8 rung were
+probe-verified on 2026-07-25 against Cursor 3.12.30, using `subagentStart`
+lifecycle hooks to read the resolved model that Cursor itself reports:
+
+| Selector                        | Resolves to                      |
+| ------------------------------- | -------------------------------- |
+| `claude-opus-5[effort=low]`     | `claude-opus-5-thinking-low`     |
+| `claude-opus-5[effort=medium]`  | `claude-opus-5-thinking-medium`  |
+| `claude-opus-5[effort=high]`    | `claude-opus-5-thinking-high`    |
+| `claude-opus-5[effort=xhigh]`   | `claude-opus-5-thinking-xhigh`   |
+| `claude-opus-5[effort=max]`     | `claude-opus-5-thinking-max`     |
+| `claude-opus-4-8[effort=xhigh]` | `claude-opus-4-8-thinking-xhigh` |
+
+Every rung resolves to the thinking variant. This is a verified fact, not an
+inference: the catalog carries distinct non-thinking IDs at low, medium, and
+high, and none were selected.
+
+Routing follows the accepted conclusions rather than the effort ladder alone.
+Opus 5 medium is the normal substantive route, high is the hard-reasoning
+starting point, xhigh is selective for a reasoning-depth bottleneck or an
+evaluated long-horizon benefit, and max requires a workload-specific sweep or an
+explicit exception. Sol remains the code-first, trajectory-efficient engineering
+route; Opus is generally stronger for interpretation-heavy work. Exact
+cross-provider substitutions remain provisional.
+
+Opus 4.8 xhigh is catalogued so the cyber-sensitive route is dispatchable, but it
+is deliberately excluded from the bundled recommendation. Select it explicitly
+when the cyber-sensitive refusal profile is required.
+
+### Unresolvable selectors fall back to a default, silently
+
+Probing showed that Cursor does not reject a malformed pin. It substitutes a
+default for whichever component it cannot resolve, with no error or warning:
+
+- An unknown family falls back to the default model. `claude-opus-9[effort=high]`
+  resolved to `cursor-grok-4.5-high-fast`.
+- An unknown effort falls back to the family's default rung.
+  `claude-opus-5[effort=ultra]` resolved to `claude-opus-5-thinking-high`.
+
+The default rung is family-specific, not a fixed value. In the live catalog
+exactly one rung per family carries an unqualified display label, and that marks
+the default: `claude-opus-5-high` shows as `Opus 5 1M` while
+`claude-opus-5-medium` shows as `Opus 5 1M Medium`. The default is not always
+high — `claude-opus-4-7-xhigh` shows as `Opus 4.7 1M` while
+`claude-opus-4-7-high` is explicitly labeled `Opus 4.7 1M High`.
+
+This makes a typo in a pinned selector more dangerous than a plain downgrade.
+The pin silently tracks whatever Cursor currently designates as that family's
+default, so a vendor-side change to the default rung alters capability with no
+corresponding change in the repository.
+
+Two consequences for pinning. A selector must be probe-verified per mapping
+before it ships. And a probe whose requested rung happens to equal the family
+default cannot, on its own, distinguish an honored effort parameter from an
+ignored one; verify at least one non-default rung in the same family.
 
-| Task class               | Default                                                                         | Economy                                                                              | Escalation                                             | Floor notes                                                                                                                                                                           |
-| ------------------------ | ------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------ | ------------------------------------------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| `mechanical-recon`       | `composer-2.5`                                                                  | `composer-2.5`                                                                       | `gpt-5.6-luna-high`                                    | Use `composer-2.5-fast` or Luna fast only for latency, not capability.                                                                                                                |
-| `intelligent-recon`      | `cursor-grok-4.5-medium` or `gpt-5.6-sol-medium`                                | `gpt-5.6-terra-high`                                                                 | `gpt-5.6-sol-high`                                     | Grok medium is a primary route; Sol medium is the conservative silent-miss alternative; Terra high is the cost-saving route.                                                          |
-| `default-implementation` | `gpt-5.6-sol-medium`                                                            | `composer-2.5` for bounded, testable changes                                         | `gpt-5.6-sol-high` or `claude-fable-5-thinking-high`   | Sol is the conservative incumbent; `cursor-grok-4.5-medium` is a primary alternative for general implementation. Choose Fable for open-ended coherence; Sol for code-first execution. |
-| `hard-reasoning`         | `gpt-5.6-sol-high`                                                              | `cursor-grok-4.5-high` for architecture, ambiguous debugging, and incident diagnosis | `gpt-5.6-sol-xhigh` or `claude-fable-5-thinking-xhigh` | Narrow the task before downgrading. Do not infer equivalence between the two escalation efforts.                                                                                      |
-| `consequential`          | Cross-family author/reviewer pair, normally Sol xhigh plus Fable thinking xhigh | No routine economy route                                                             | Sol max plus Fable thinking max                        | For cyber-sensitive review, use `claude-opus-4-8-thinking-xhigh` or max instead of relying on Fable alone. Grok may contribute analysis but is never the sole reviewer.               |
+Neither an agent self-report nor a subagent card label is admissible evidence.
+The card label drops the thinking qualifier and cannot distinguish the thinking
+and non-thinking variants.
 
 ## Broader Cursor Routes
 
@@ -60,7 +136,7 @@ user's 2026-07-21 snapshot.
 - Grok is never the sole final authority for a consequential factual, security,
   incident, or architectural conclusion. Require tool evidence, citations,
   logs, query results, or file references for load-bearing Grok claims, or
-  pair it with an independent Sol, Fable, or Opus reviewer.
+  pair it with an eligible independent cross-family reviewer.
 - CursorBench caveat: Cursor disclosed that Cursor repository data entered
   Grok 4.5's training mixture. Treat its ranking as evidence of
   competitiveness, not proof of superiority over nearby frontier models.

package/dist/providers/cursor/codec/catalog.d.ts

@@ -1,8 +1,26 @@
 export type CursorPinSyntaxFamily = 'gpt-reasoning' | 'claude-effort' | 'composer-fast' | 'grok-effort-fast';
+/**
+ * What a probe submitted and what the harness resolved it to, transcribed from
+ * the probe evidence.
+ *
+ * `submittedSelector` and `resolvedModel` restate the mapping's
+ * `frontmatterModel` and `ladderModelId`. That duplication is the mechanism and
+ * must not be refactored away: these fields are an independent transcription of
+ * an observation, so a mapping edited without re-probing disagrees with its own
+ * record and fails the consistency test. Deriving them from the mapping would
+ * make that test pass by construction and verify nothing.
+ */
+export interface CursorPinProbeRecord {
+    submittedSelector: string;
+    resolvedModel: string;
+    verifiedAt: string;
+    evidencePath: string;
+}
 export interface CursorPinGateEvidence {
     gate: 'g01';
     probeName: string;
     disposition: 'approved';
+    probeRecord?: CursorPinProbeRecord;
 }
 export interface CursorModelPinMapping {
     ladderModelId: string;
@@ -11,7 +29,7 @@ export interface CursorModelPinMapping {
     gateEvidence: CursorPinGateEvidence;
     catalogue: boolean;
 }
-export declare const CURSOR_MODEL_PIN_MAPPINGS: readonly [CursorModelPinMapping, CursorModelPinMapping, CursorModelPinMapping, CursorModelPinMapping, CursorModelPinMapping, CursorModelPinMapping, CursorModelPinMapping, CursorModelPinMapping, CursorModelPinMapping, CursorModelPinMapping, CursorModelPinMapping, CursorModelPinMapping, CursorModelPinMapping, CursorModelPinMapping, CursorModelPinMapping];
+export declare const CURSOR_MODEL_PIN_MAPPINGS: readonly [CursorModelPinMapping, CursorModelPinMapping, CursorModelPinMapping, CursorModelPinMapping, CursorModelPinMapping, CursorModelPinMapping, CursorModelPinMapping, CursorModelPinMapping, CursorModelPinMapping, CursorModelPinMapping, CursorModelPinMapping, CursorModelPinMapping, CursorModelPinMapping, CursorModelPinMapping, CursorModelPinMapping, CursorModelPinMapping, CursorModelPinMapping, CursorModelPinMapping, CursorModelPinMapping, CursorModelPinMapping, CursorModelPinMapping];
 export declare const SUPPORTED_CURSOR_ROLE_TARGETS: CursorModelPinMapping[];
 export declare const SUPPORTED_CURSOR_BASE_ROLES: readonly ['oat-phase-implementer', 'oat-reviewer'];
 export declare function findCursorModelPinMapping(ladderModelId: string): CursorModelPinMapping | undefined;

package/dist/providers/cursor/codec/catalog.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"catalog.d.ts","sourceRoot":"","sources":["../../../../src/providers/cursor/codec/catalog.ts"],"names":[],"mappings":"AAAA,MAAM,MAAM,qBAAqB,GAC7B,eAAe,GACf,eAAe,GACf,eAAe,GACf,kBAAkB,CAAC;AAEvB,MAAM,WAAW,qBAAqB;IACpC,IAAI,EAAE,KAAK,CAAC;IACZ,SAAS,EAAE,MAAM,CAAC;IAClB,WAAW,EAAE,UAAU,CAAC;CACzB;AAED,MAAM,WAAW,qBAAqB;IACpC,aAAa,EAAE,MAAM,CAAC;IACtB,gBAAgB,EAAE,MAAM,CAAC;IACzB,YAAY,EAAE,qBAAqB,CAAC;IACpC,YAAY,EAAE,qBAAqB,CAAC;IACpC,SAAS,EAAE,OAAO,CAAC;CACpB;AA0BD,eAAO,MAAM,yBAAyB,oWA2Ee,CAAC;AAEtD,eAAO,MAAM,6BAA6B,yBAEzC,CAAC;AAEF,eAAO,MAAM,2BAA2B,YACtC,uBAAuB,EACvB,cAAc,CACN,CAAC;AAEX,wBAAgB,yBAAyB,CACvC,aAAa,EAAE,MAAM,GACpB,qBAAqB,GAAG,SAAS,CAInC"}
+{"version":3,"file":"catalog.d.ts","sourceRoot":"","sources":["../../../../src/providers/cursor/codec/catalog.ts"],"names":[],"mappings":"AAAA,MAAM,MAAM,qBAAqB,GAC7B,eAAe,GACf,eAAe,GACf,eAAe,GACf,kBAAkB,CAAC;AAEvB;;;;;;;;;;GAUG;AACH,MAAM,WAAW,oBAAoB;IACnC,iBAAiB,EAAE,MAAM,CAAC;IAC1B,aAAa,EAAE,MAAM,CAAC;IACtB,UAAU,EAAE,MAAM,CAAC;IACnB,YAAY,EAAE,MAAM,CAAC;CACtB;AAED,MAAM,WAAW,qBAAqB;IACpC,IAAI,EAAE,KAAK,CAAC;IACZ,SAAS,EAAE,MAAM,CAAC;IAClB,WAAW,EAAE,UAAU,CAAC;IACxB,WAAW,CAAC,EAAE,oBAAoB,CAAC;CACpC;AAED,MAAM,WAAW,qBAAqB;IACpC,aAAa,EAAE,MAAM,CAAC;IACtB,gBAAgB,EAAE,MAAM,CAAC;IACzB,YAAY,EAAE,qBAAqB,CAAC;IACpC,YAAY,EAAE,qBAAqB,CAAC;IACpC,SAAS,EAAE,OAAO,CAAC;CACpB;AAqCD,eAAO,MAAM,yBAAyB,8eAyJe,CAAC;AAEtD,eAAO,MAAM,6BAA6B,yBAEzC,CAAC;AAEF,eAAO,MAAM,2BAA2B,YACtC,uBAAuB,EACvB,cAAc,CACN,CAAC;AAEX,wBAAgB,yBAAyB,CACvC,aAAa,EAAE,MAAM,GACpB,qBAAqB,GAAG,SAAS,CAInC"}

package/dist/providers/cursor/codec/catalog.js

@@ -1,4 +1,5 @@
 function approvedMapping(ladderModelId, frontmatterModel, syntaxFamily, options = {}) {
+    const { probeRecord } = options;
     return {
         ladderModelId,
         frontmatterModel,
@@ -8,10 +9,15 @@ function approvedMapping(ladderModelId, frontmatterModel, syntaxFamily, options
             probeName: options.probeName ??
                 `oat-pin-probe-${ladderModelId.replaceAll('.', '-')}`,
             disposition: 'approved',
+            ...(probeRecord ? { probeRecord } : {}),
         },
         catalogue: options.catalogue ?? true,
     };
 }
+const G01_PROBE_2026_07_25 = {
+    verifiedAt: '2026-07-25',
+    evidencePath: '.oat/projects/shared/opus-5-model-guidance/references/g01-probe-results.md',
+};
 export const CURSOR_MODEL_PIN_MAPPINGS = [
     approvedMapping('composer-2.5', 'composer-2.5[fast=true]', 'composer-fast'),
     approvedMapping('composer-2.5-fast', 'composer-2.5[fast=true]', 'composer-fast', { catalogue: false }),
@@ -26,6 +32,54 @@ export const CURSOR_MODEL_PIN_MAPPINGS = [
     approvedMapping('claude-fable-5-thinking-high', 'claude-fable-5[effort=high]', 'claude-effort'),
     approvedMapping('claude-fable-5-thinking-xhigh', 'claude-fable-5[effort=xhigh]', 'claude-effort'),
     approvedMapping('claude-fable-5-xhigh', 'claude-fable-5[effort=xhigh]', 'claude-effort', { catalogue: false }),
+    approvedMapping('claude-opus-5-thinking-low', 'claude-opus-5[effort=low]', 'claude-effort', {
+        probeName: 'zz-pin-probe-opus5-low',
+        probeRecord: {
+            submittedSelector: 'claude-opus-5[effort=low]',
+            resolvedModel: 'claude-opus-5-thinking-low',
+            ...G01_PROBE_2026_07_25,
+        },
+    }),
+    approvedMapping('claude-opus-5-thinking-medium', 'claude-opus-5[effort=medium]', 'claude-effort', {
+        probeName: 'zz-pin-probe-opus5-medium',
+        probeRecord: {
+            submittedSelector: 'claude-opus-5[effort=medium]',
+            resolvedModel: 'claude-opus-5-thinking-medium',
+            ...G01_PROBE_2026_07_25,
+        },
+    }),
+    approvedMapping('claude-opus-5-thinking-high', 'claude-opus-5[effort=high]', 'claude-effort', {
+        probeName: 'zz-pin-probe-opus5-high',
+        probeRecord: {
+            submittedSelector: 'claude-opus-5[effort=high]',
+            resolvedModel: 'claude-opus-5-thinking-high',
+            ...G01_PROBE_2026_07_25,
+        },
+    }),
+    approvedMapping('claude-opus-5-thinking-xhigh', 'claude-opus-5[effort=xhigh]', 'claude-effort', {
+        probeName: 'zz-pin-probe-opus5-xhigh',
+        probeRecord: {
+            submittedSelector: 'claude-opus-5[effort=xhigh]',
+            resolvedModel: 'claude-opus-5-thinking-xhigh',
+            ...G01_PROBE_2026_07_25,
+        },
+    }),
+    approvedMapping('claude-opus-5-thinking-max', 'claude-opus-5[effort=max]', 'claude-effort', {
+        probeName: 'zz-pin-probe-opus5-max',
+        probeRecord: {
+            submittedSelector: 'claude-opus-5[effort=max]',
+            resolvedModel: 'claude-opus-5-thinking-max',
+            ...G01_PROBE_2026_07_25,
+        },
+    }),
+    approvedMapping('claude-opus-4-8-thinking-xhigh', 'claude-opus-4-8[effort=xhigh]', 'claude-effort', {
+        probeName: 'zz-pin-probe-opus48-xhigh',
+        probeRecord: {
+            submittedSelector: 'claude-opus-4-8[effort=xhigh]',
+            resolvedModel: 'claude-opus-4-8-thinking-xhigh',
+            ...G01_PROBE_2026_07_25,
+        },
+    }),
     approvedMapping('gpt-5.6-sol-xhigh', 'gpt-5.6-sol[reasoning=xhigh]', 'gpt-reasoning'),
     approvedMapping('gpt-5.6-sol-max', 'gpt-5.6-sol[reasoning=max]', 'gpt-reasoning'),
 ];

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@open-agent-toolkit/cli",
-  "version": "0.2.19",
+  "version": "0.2.21",
   "private": false,
   "description": "Open Agent Toolkit CLI",
   "homepage": "https://github.com/voxmedia/open-agent-toolkit/tree/main/packages/cli",
@@ -34,7 +34,7 @@
     "ora": "^9.0.0",
     "yaml": "2.8.2",
     "zod": "^3.25.76",
-    "@open-agent-toolkit/control-plane": "0.2.19"
+    "@open-agent-toolkit/control-plane": "0.2.21"
   },
   "devDependencies": {
     "@types/node": "^22.10.0",

package/assets/skills/explainer-kit/schemas/author-request.schema.json

@@ -1,85 +0,0 @@
-{
-  "$schema": "https://json-schema.org/draft/2020-12/schema",
-  "$id": "explainer-kit.author-request/v1",
-  "title": "AuthorRequestV1",
-  "type": "object",
-  "additionalProperties": false,
-  "required": [
-    "schemaVersion",
-    "run",
-    "recipe",
-    "artifact",
-    "narrativeOutline",
-    "factBase",
-    "discovery"
-  ],
-  "properties": {
-    "schemaVersion": { "const": "explainer-kit.author-request/v1" },
-    "run": {
-      "type": "object",
-      "additionalProperties": false,
-      "required": ["runId", "slug"],
-      "properties": {
-        "runId": { "type": "string", "minLength": 1 },
-        "slug": {
-          "type": "string",
-          "pattern": "^[a-z0-9]+(?:-[a-z0-9]+)*$"
-        }
-      }
-    },
-    "recipe": {
-      "type": "object",
-      "additionalProperties": false,
-      "required": ["id", "version", "requiredNarrative"],
-      "properties": {
-        "id": { "type": "string", "minLength": 1 },
-        "version": { "type": "string", "minLength": 1 },
-        "requiredNarrative": {
-          "type": "array",
-          "items": { "type": "string", "minLength": 1 },
-          "minItems": 1,
-          "uniqueItems": true
-        }
-      }
-    },
-    "artifact": {
-      "type": "object",
-      "additionalProperties": false,
-      "required": ["id", "type"],
-      "properties": {
-        "id": { "type": "string", "minLength": 1 },
-        "type": { "enum": ["hub", "diagram", "explainer", "deck", "catalog"] }
-      }
-    },
-    "narrativeOutline": {
-      "type": "array",
-      "items": {
-        "type": "object",
-        "additionalProperties": false,
-        "required": ["id", "title"],
-        "properties": {
-          "id": { "type": "string", "minLength": 1 },
-          "title": { "type": "string", "minLength": 1 }
-        }
-      },
-      "minItems": 1,
-      "uniqueItems": true
-    },
-    "factBase": { "$ref": "explainer-kit.fact-base/v1" },
-    "discovery": {
-      "type": "object",
-      "additionalProperties": false,
-      "required": ["rounds", "findings", "reason"],
-      "properties": {
-        "rounds": { "type": "integer", "minimum": 0 },
-        "findings": {
-          "type": "array",
-          "items": { "type": "string", "minLength": 1 }
-        },
-        "reason": {
-          "enum": ["not-requested", "two-empty-rounds", "hard-maximum"]
-        }
-      }
-    }
-  }
-}

package/assets/skills/explainer-kit/schemas/author-result.schema.json

@@ -1,65 +0,0 @@
-{
-  "$schema": "https://json-schema.org/draft/2020-12/schema",
-  "$id": "explainer-kit.author-result/v1",
-  "title": "AuthorResultV1",
-  "type": "object",
-  "additionalProperties": false,
-  "required": ["schemaVersion", "artifactId", "content", "provenance"],
-  "properties": {
-    "schemaVersion": { "const": "explainer-kit.author-result/v1" },
-    "artifactId": { "type": "string", "minLength": 1 },
-    "content": {
-      "type": "object",
-      "additionalProperties": false,
-      "required": ["title", "description", "sections"],
-      "properties": {
-        "title": { "type": "string", "minLength": 1 },
-        "description": { "type": "string", "minLength": 1 },
-        "eyebrow": { "type": "string", "minLength": 1 },
-        "footer": { "type": "string", "minLength": 1 },
-        "sections": {
-          "type": "array",
-          "items": {
-            "type": "object",
-            "additionalProperties": false,
-            "required": ["id", "title", "prose"],
-            "properties": {
-              "id": { "type": "string", "minLength": 1 },
-              "title": { "type": "string", "minLength": 1 },
-              "prose": { "type": "string", "minLength": 1 }
-            }
-          },
-          "minItems": 1,
-          "uniqueItems": true
-        },
-        "artifactLinks": {
-          "type": "array",
-          "items": {
-            "type": "object",
-            "additionalProperties": false,
-            "required": ["id", "type", "label"],
-            "properties": {
-              "id": { "type": "string", "minLength": 1 },
-              "type": {
-                "enum": ["hub", "diagram", "explainer", "deck", "catalog"]
-              },
-              "label": { "type": "string", "minLength": 1 }
-            }
-          },
-          "uniqueItems": true
-        }
-      }
-    },
-    "provenance": {
-      "type": "object",
-      "additionalProperties": false,
-      "required": ["authorId", "generatedAt"],
-      "properties": {
-        "authorId": { "type": "string", "minLength": 1 },
-        "generatedAt": { "type": "string", "format": "date-time" },
-        "method": { "type": "string", "minLength": 1 },
-        "model": { "type": "string", "minLength": 1 }
-      }
-    }
-  }
-}