axstack 0.20.22 → 0.20.23

package/README.md

@@ -99,7 +99,7 @@ upgrades, conflicts, and uninstalling.
   inline or from an explicitly scoped backlog without touching active, manual,
   uncertain, user-owned, dirty, unpushed, or useful unmerged work.
 
-Choose an explicit role preset:
+Choose an explicit role preset (26 stable role IDs in each):
 [mixed](profiles/presets/mixed.json),
 [codex-only](profiles/presets/codex-only.json), or
 [claude-only](profiles/presets/claude-only.json).

package/bin/axstack.js

@@ -335,6 +335,7 @@ async function main() {
       } else {
         if (summary.added.length) console.log(`added: ${summary.added.join(', ')}`);
         if (summary.updated.length) console.log(`updated: ${summary.updated.join(', ')}`);
+        if (summary.addedRoleIds?.length) console.log(`added role IDs: ${summary.addedRoleIds.join(', ')}`);
         if (summary.removed.length) console.log(`removed: ${summary.removed.join(', ')}`);
         if (summary.unchanged.length) console.log(`unchanged: ${summary.unchanged.join(', ')}`);
       }

package/docs/installation.md

@@ -71,7 +71,7 @@ profiles/presets/codex-only.json
 profiles/presets/claude-only.json
 ```
 
-Each has exactly `{ "version": 1, "roles": [...] }` with the same 24 stable
+Each has exactly `{ "version": 1, "roles": [...] }` with the same 26 stable
 role IDs. Installation writes `<skills-dir>/axstack/roles.json` as
 `{ "version": 1, "preset": "<selected preset>", "roles": [...] }` and records
 its ownership hash like every other installed skill asset. There is no second
@@ -140,10 +140,10 @@ The complete bundle is validated before writes:
   the filename's selected identity supplied by the caller, and the same role-ID
   set as its peers;
 - every role has valid preserved fields, while the mixed checker,
-  `axstack-research-web-google`, and `axstack-research-x` launch-by-agent-id
+  `axstack-research-web-google`, `axstack-research-x`, and both arena candidate launch-by-agent-id
   routes explicitly permit `model: null`;
   in each single-provider preset, the unavailable adviser and its matching arena
-  judge seat explicitly permit `model: null`, as do both cross-provider research routes;
+  judge seat explicitly permit `model: null`, as do both cross-provider research routes and both arena candidate seats;
 - obsolete runtime configuration flags fail before mutation with migration
   guidance.
 
@@ -171,7 +171,7 @@ to rewrite them.
 ## Role behavior after installation
 
 The runtime reads `roles.json` from the installed shared root `skills/axstack/`.
-A new run records the selected preset plus all 24 role rows. An active run keeps
+A new run records the selected preset plus all 26 role rows. An active run keeps
 that snapshot after a later preset install unless the user explicitly changes
 it and accepts the resulting evidence invalidation.
 

package/docs/workflows.md

@@ -48,7 +48,7 @@ only affected work.
 
 Installation requires one explicit canonical preset. The three bundle files
 under `profiles/presets/` each contain exactly
-`{ "version": 1, "roles": [...] }` and the same 24 stable IDs.
+`{ "version": 1, "roles": [...] }` and the same 26 stable IDs.
 
 The current chat drives on whatever model runs it; no preset carries a driver
 role.
@@ -122,9 +122,9 @@ session and evidence remain valid.
 - `axstack-align` maps facts and dependencies, asks prioritized questions, and
   consults Astra and Fable independently with the same bounded evidence and
   question. It synthesizes disagreements and reuses unchanged receipts. For a
-  hard-to-reverse design choice it runs one arena round instead: Astra and
-  Fable each author a candidate, `axstack-arena-judge-astra` and
-  `axstack-arena-judge-fable` score both against the driver's rubric, and the
+  hard-to-reverse design choice it runs one arena round instead: Astra,
+  Fable, Grok, and Antigravity each author a candidate, `axstack-arena-judge-astra` and
+  `axstack-arena-judge-fable` score every candidate against the driver's rubric, and the
   driver picks a base, grafts the losers' strong ideas, and presents the
   synthesis as the recommendation; the note lands as `Decisions` rows in the
   run record.

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "axstack",
-  "version": "0.20.22",
+  "version": "0.20.23",
   "description": "Axstack installer and setup CLI: installs owned chat skills and role data, configures supported harness settings, and checks Orca capabilities.",
   "keywords": [
     "claude-code",

package/profiles/presets/claude-only.json

@@ -206,7 +206,7 @@
       "model": null,
       "modeId": "bypassPermissions",
       "thinkingOptionId": "xhigh",
-      "notes": "Required Arena judge (Astra seat). Read-only cross-judge for an arena-grade Align decision: receives the rubric and both candidates by label, scores each criterion, and recommends a base with rationale. Never authors a candidate, never cross-reads the other judge, never mutates. Disagreement between judges is surfaced by the driver, never averaged. Intentionally absent in the claude-only preset; the arena-grade decision holds without substitution."
+      "notes": "Required Arena judge (Astra seat). Read-only cross-judge for an arena-grade Align decision: receives the rubric and every candidate by label, scores each criterion, and recommends a base with rationale. Never authors a candidate, never cross-reads the other judge, never mutates. Disagreement between judges is surfaced by the driver, never averaged. Intentionally absent in the claude-only preset; the arena-grade decision holds without substitution."
     },
     {
       "id": "axstack-arena-judge-fable",
@@ -215,7 +215,25 @@
       "model": "claude-fable-5-1",
       "modeId": "bypassPermissions",
       "thinkingOptionId": "xhigh",
-      "notes": "Arena judge (Fable seat). Read-only cross-judge for an arena-grade Align decision: receives the rubric and both candidates by label, scores each criterion, and recommends a base with rationale. Never authors a candidate, never cross-reads the other judge, never mutates. Disagreement between judges is surfaced by the driver, never averaged."
+      "notes": "Arena judge (Fable seat). Read-only cross-judge for an arena-grade Align decision: receives the rubric and every candidate by label, scores each criterion, and recommends a base with rationale. Never authors a candidate, never cross-reads the other judge, never mutates. Disagreement between judges is surfaced by the driver, never averaged."
+    },
+    {
+      "id": "axstack-arena-candidate-grok",
+      "name": "Axstack arena candidate Grok (unavailable)",
+      "provider": "claude",
+      "model": null,
+      "modeId": "bypassPermissions",
+      "thinkingOptionId": "high",
+      "notes": "Intentional single-provider absence in the claude-only preset; Grok candidate unavailable. Arena holds without substitution."
+    },
+    {
+      "id": "axstack-arena-candidate-antigravity",
+      "name": "Axstack arena candidate Antigravity (unavailable)",
+      "provider": "claude",
+      "model": null,
+      "modeId": "bypassPermissions",
+      "thinkingOptionId": "high",
+      "notes": "Intentional single-provider absence in the claude-only preset; Antigravity candidate unavailable. Arena holds without substitution."
     }
   ]
 }

package/profiles/presets/codex-only.json

@@ -206,7 +206,7 @@
       "model": "gpt-6-astra",
       "modeId": "full-access",
       "thinkingOptionId": "xhigh",
-      "notes": "Arena judge (Astra seat). Read-only cross-judge for an arena-grade Align decision: receives the rubric and both candidates by label, scores each criterion, and recommends a base with rationale. Never authors a candidate, never cross-reads the other judge, never mutates. Disagreement between judges is surfaced by the driver, never averaged."
+      "notes": "Arena judge (Astra seat). Read-only cross-judge for an arena-grade Align decision: receives the rubric and every candidate by label, scores each criterion, and recommends a base with rationale. Never authors a candidate, never cross-reads the other judge, never mutates. Disagreement between judges is surfaced by the driver, never averaged."
     },
     {
       "id": "axstack-arena-judge-fable",
@@ -215,7 +215,25 @@
       "model": null,
       "modeId": "full-access",
       "thinkingOptionId": "xhigh",
-      "notes": "Required Arena judge (Fable seat). Read-only cross-judge for an arena-grade Align decision: receives the rubric and both candidates by label, scores each criterion, and recommends a base with rationale. Never authors a candidate, never cross-reads the other judge, never mutates. Disagreement between judges is surfaced by the driver, never averaged. Intentionally absent in the codex-only preset; the arena-grade decision holds without substitution."
+      "notes": "Required Arena judge (Fable seat). Read-only cross-judge for an arena-grade Align decision: receives the rubric and every candidate by label, scores each criterion, and recommends a base with rationale. Never authors a candidate, never cross-reads the other judge, never mutates. Disagreement between judges is surfaced by the driver, never averaged. Intentionally absent in the codex-only preset; the arena-grade decision holds without substitution."
+    },
+    {
+      "id": "axstack-arena-candidate-grok",
+      "name": "Axstack arena candidate Grok (unavailable)",
+      "provider": "codex",
+      "model": null,
+      "modeId": "full-access",
+      "thinkingOptionId": "high",
+      "notes": "Intentional single-provider absence in the codex-only preset; Grok candidate unavailable. Arena holds without substitution."
+    },
+    {
+      "id": "axstack-arena-candidate-antigravity",
+      "name": "Axstack arena candidate Antigravity (unavailable)",
+      "provider": "codex",
+      "model": null,
+      "modeId": "full-access",
+      "thinkingOptionId": "high",
+      "notes": "Intentional single-provider absence in the codex-only preset; Antigravity candidate unavailable. Arena holds without substitution."
     }
   ]
 }

package/profiles/presets/mixed.json

@@ -206,7 +206,7 @@
       "model": "gpt-6-astra",
       "modeId": "full-access",
       "thinkingOptionId": "xhigh",
-      "notes": "Arena judge (Astra seat). Read-only cross-judge for an arena-grade Align decision: receives the rubric and both candidates by label, scores each criterion, and recommends a base with rationale. Never authors a candidate, never cross-reads the other judge, never mutates. Disagreement between judges is surfaced by the driver, never averaged."
+      "notes": "Arena judge (Astra seat). Read-only cross-judge for an arena-grade Align decision: receives the rubric and every candidate by label, scores each criterion, and recommends a base with rationale. Never authors a candidate, never cross-reads the other judge, never mutates. Disagreement between judges is surfaced by the driver, never averaged."
     },
     {
       "id": "axstack-arena-judge-fable",
@@ -215,7 +215,25 @@
       "model": "claude-fable-5-1",
       "modeId": "bypassPermissions",
       "thinkingOptionId": "xhigh",
-      "notes": "Arena judge (Fable seat). Read-only cross-judge for an arena-grade Align decision: receives the rubric and both candidates by label, scores each criterion, and recommends a base with rationale. Never authors a candidate, never cross-reads the other judge, never mutates. Disagreement between judges is surfaced by the driver, never averaged."
+      "notes": "Arena judge (Fable seat). Read-only cross-judge for an arena-grade Align decision: receives the rubric and every candidate by label, scores each criterion, and recommends a base with rationale. Never authors a candidate, never cross-reads the other judge, never mutates. Disagreement between judges is surfaced by the driver, never averaged."
+    },
+    {
+      "id": "axstack-arena-candidate-grok",
+      "name": "Axstack arena candidate Grok",
+      "provider": "grok",
+      "model": null,
+      "modeId": "full-access",
+      "thinkingOptionId": "high",
+      "notes": "Independent Grok Rung 2 design candidate. Launch by agent id grok; model selected by the TUI default. Receives the same brief without cross-reading; returns design, rationale, and rejected alternatives."
+    },
+    {
+      "id": "axstack-arena-candidate-antigravity",
+      "name": "Axstack arena candidate Antigravity",
+      "provider": "antigravity",
+      "model": null,
+      "modeId": "full-access",
+      "thinkingOptionId": "high",
+      "notes": "Independent Antigravity Rung 2 design candidate. Launch by agent id antigravity; model selected by the TUI default. Receives the same brief without cross-reading; returns design, rationale, and rejected alternatives."
     }
   ]
 }

package/skills/axstack/references/design-lens.md

@@ -15,7 +15,7 @@ sketch through the scope identity.
   not reclassify work: Rung 1 can stay small. An unsettled material design
   question still makes routing reassess size.
 - **Rung 2 — arena.** A Rung 1 design that also meets the existing ADR test:
-  a meaningful, hard-to-reverse, non-obvious trade-off. Use Align's existing
+  a meaningful, hard-to-reverse, non-obvious trade-off. Use Align's all-family
   arena for that question.
 
 There is no numeric threshold, file-count gate, or class-count gate.

package/skills/axstack/references/orca-runtime.md

@@ -38,7 +38,7 @@ Read `roles.json` from the installed shared root `skills/axstack/`. The installe
 shape is `{ "version": 1, "preset": "<name>", "roles": [...] }`. Bundled
 profiles are setup inputs shaped as
 `{ "version": 1, "roles": [...] }`. A new run records the selected preset and
-all 24 role rows once. An active run keeps the exact snapshot until the user
+all 26 role rows once. An active run keeps the exact snapshot until the user
 explicitly changes it.
 
 Select the requested role by stable ID. A missing or null model holds only that role;

package/skills/axstack/references/routing.md

@@ -5,14 +5,14 @@ Driver entry sweep follows [Workspace hygiene](workspace-hygiene.md).
 
 ## Role routing
 
-Presets: `mixed`, `codex-only`, `claude-only`. For a new run, read
+Presets: `mixed`, `codex-only`, `claude-only`. For new runs, use
 `profiles.preset` from `.axstack-manifest.json` at the actually loaded
-skills root, or an explicit user selection recorded in the run record. Proceed
-only with exactly one unambiguous preset; missing or contradictory sources are
+skills root, or an explicit user selection recorded in the run record. Use one
+unambiguous preset; missing or contradictory sources are
 a setup gap: hold. Never infer from live profiles or `list_profiles`, harness,
 tools, credentials, quota, subscription, or default to `mixed`.
 
-At run start, snapshot all 24 role IDs with provider/model/mode/effort; absent
+At run start, snapshot all 26 role IDs with provider/model/mode/effort; absent
 or unconfigured roles are recorded explicitly; invent no provider default.
 Such a role holds only that role's work. A role installed or changed later must not
 silently enter the snapshot; adding it needs an explicit user decision. Live profiles
@@ -25,8 +25,6 @@ revalidation. Unavailable models, unsupported efforts, missing roles, and
 incompatible overrides hold only affected work; no automatic fallback, quota
 routing, subscription inference, or silent provider/model/effort substitution.
 
-Role IDs:
-
 - Chat drives (no role ID); `axstack-owner` owns one PR and
   `axstack-author` its sole writer.
 - `axstack-reviewer-primary` and `axstack-reviewer-secondary` are the ordered
@@ -38,10 +36,11 @@ Role IDs:
   | `mixed` | Claude / Opus (`claude/claude-opus-5-5`) | `axstack-reviewer-primary` (`codex/gpt-6-sol` medium) |
   | `codex-only` | Codex / Sol (`codex/gpt-6-sol`) | `axstack-reviewer-secondary` (`codex/gpt-6-luna` xhigh) |
   | `claude-only` | Claude / Opus (`claude/claude-opus-5-5`) | `axstack-reviewer-secondary` (`claude/claude-sonnet-5` xhigh) |
-- `axstack-advisor-astra` and `axstack-advisor-fable` advise independently
-  and author align arena candidates; `axstack-arena-judge-astra` and
-  `axstack-arena-judge-fable` judge them. `axstack-auditor` audits;
-  `axstack-checker` reports discrepancies.
+- `axstack-advisor-astra`/`axstack-advisor-fable` advise independently and
+  author arena candidates; `axstack-arena-candidate-grok`/
+  `axstack-arena-candidate-antigravity` add families.
+  `axstack-arena-judge-astra`/`axstack-arena-judge-fable` judge them.
+  `axstack-auditor` audits; `axstack-checker` reports discrepancies.
 - `axstack-explainer`/`axstack-explainer-review`: explain/review.
   `axstack-monitor`: standalone watch never sends; chat-run watch: bounded
   internal reports to its Run and original driver.
@@ -51,17 +50,16 @@ Provenance is matched on provider/model ID; effort never maps. Missing table-row
 provenance is unsupported and `INCOMPLETE`; report it and ask the user. Never
 infer from slot, driver, owner, or provider. Author and owner never review.
 
-The `axstack-implement` loop requires `mixed`; single-provider presets hold at
-step (3) for user routing, with no substitution or same-provider review.
+`axstack-implement` requires `mixed`; single-provider presets hold at
+step (3) for user routing: no substitution or same-provider review.
 
 ## Direct routes (no spec ceremony)
 
 - One bounded research question -> `axstack-research`: verify primary sources
-  and code, return a cited note with limitations. Fan out only distinct
-  questions.
+  and code; return a cited note with limitations. Fan out only distinct questions.
 - Understanding a system, change, or implementation gap -> `axstack-explain`:
-  current/intended behavior, evidence dimensions, and bounded gaps from project
-  docs and rendered behavior. "What could this break" follows
+  current/intended behavior, evidence dimensions, bounded gaps from project docs and
+  rendered behavior. "What could this break" follows
   [Blast radius](blast-radius.md). Publication needs separate authority.
 - A bug, failing test, regression, or wrong behavior, red loop wanted ->
   `axstack-debug`: diagnose, escalate via adviser-directed investigators, hand
@@ -69,11 +67,11 @@ step (3) for user routing, with no substitution or same-provider review.
 - Codebase-quality or refactor discovery -> `axstack-improve`: inspect bounded
   scope, rank evidenced candidates, report only; no spec, tickets, or source
   edits.
-- Accepted worker/Task/Run completion or bounded backlog request -> invoke
-  `axstack-cleanup` inline in the driver; never dispatch it.
+- Accepted worker/Task/Run completion or bounded backlog request -> driver invokes
+  `axstack-cleanup` inline; never dispatch it.
 - Preparation completion, watch expiry, resume, or reconciliation -> the
-  [lifecycle](lifecycle.md#native-handoff-and-resume): reconcile the run
-  record, keep its owner, launch no native handoff.
+  [lifecycle](lifecycle.md#native-handoff-and-resume): reconcile run record,
+  keep owner, launch no native handoff.
 - Explicit user-requested ownership transfer -> the same lifecycle section.
   Load the [Orca runtime boundary](orca-runtime.md), follow the runtime-owned
   handoff guide, and require explicit recipient acceptance before ownership
@@ -81,10 +79,10 @@ step (3) for user routing, with no substitution or same-provider review.
 - Colleague PR review -> `axstack-review`, peer mode.
 - Codebase review -> `axstack-review` codebase mode, report only.
 - A status question about an own open PR or stack ("check now", "what's left",
-  "are we done", or "is it approved") -> `axstack-watch` in observation-only
+  "are we done", or "is it approved") -> `axstack-watch` observation-only
   mode. Explicit "address", "patch", or "fix" grants authorized maintenance.
-- Chat-run PR watch -> `axstack-watch`: original driver; verified run PRs
-  and explicit adoptions only.
+- Chat-run PR watch -> `axstack-watch`: original driver; verified run PRs and
+  explicit adoptions only.
 - Other own PR work -> `axstack-review` authored mode or `axstack-watch`
   adoption.
 

package/skills/axstack-align/SKILL.md

@@ -81,29 +81,30 @@ hold Align; safe fact work may continue without substitution.
 
 ## Arena for hard-to-reverse design choices
 
-Critique of one draft anchors every reader to that draft's shape. When a
-question is arena-grade, the same test as for an ADR (a meaningful,
+Critique of one draft anchors every reader to that draft's shape. Rung 2 designs
+alone enter the arena: they meet the same test as for an ADR (a meaningful,
 hard-to-reverse, non-obvious trade-off: architecture, module boundaries, data
-model, migration strategy), replace the critique round for that question with
+model, migration strategy). Replace the critique round for that question with
 one arena round. Small or routine questions never enter the arena.
 
 1. **Frame.** The driver writes the brief (the artifact, its constraints, the
    settled decisions it must respect) and three to six gradeable rubric
    criteria. Candidates receive only the brief; the rubric is for judging.
-2. **Fan out.** `axstack-advisor-astra` and `axstack-advisor-fable` each
-   independently produce one candidate design plus a short rationale naming
-   the alternatives considered and rejected, from the same bounded evidence and
-   question, without cross-reading. The driver authors no candidate.
-3. **Cross-judge.** After both candidates are complete, `axstack-arena-judge-astra`
-   and `axstack-arena-judge-fable` each independently score every candidate
-   per criterion from the rubric and candidates by label, and recommend a base
-   with a reason. Judges never author, never cross-read each other.
+2. **Fan out.** Produce one candidate per configured family independently from the same brief,
+   without cross-reading: `axstack-advisor-astra`, `axstack-advisor-fable`,
+   `axstack-arena-candidate-grok`, and `axstack-arena-candidate-antigravity`.
+   Each gives a design, rationale, and rejected alternatives. The driver authors no candidate.
+3. **Cross-judge.** After every candidate completes, give the judges anonymized,
+   relabeled candidates against the rubric.
+   `axstack-arena-judge-astra` and `axstack-arena-judge-fable` each independently
+   score every candidate against the driver-tailored rubric per criterion and
+   recommend a base with a reason. Judges never author, never cross-read each other.
 4. **Pick.** The driver reads every candidate end to end and scores per
    criterion, not on holistic feel, then compares with both judges. Agreement
    confirms the base. Disagreement between judges or with the driver means one
-   reading is biased or the rubric was ambiguous: re-read both rationales and
+   reading is biased or the rubric was ambiguous: re-read the rationales and
    decide with a stated reason; never average verdicts or fabricate consensus.
-5. **Graft.** Walk the losing candidate once more for the one or two ideas
+5. **Graft.** Walk the losing candidates once more for the one or two ideas
    worth porting and fold them into the base by hand so the result stays
    coherent under one mental model. Convergence on the same shape is a strong
    agreement signal: adopt the consensus shape, no graft. Wide divergence
@@ -117,9 +118,11 @@ Record the synthesis note (base, grafts and their source candidate, rejections,
 dropouts, both judge verdicts) as `Decisions` rows in the
 [run record](../axstack/references/run-record.md). Load
 [Orca runtime](../axstack/references/orca-runtime.md) immediately before the
-first candidate or judge dispatch. If either adviser or judge seat is
-unavailable, hold that question without substitution; unaffected fact work
-and questions continue.
+first candidate or judge dispatch. If any configured candidate or judge seat is
+unavailable at launch or returns a failed receipt, hold that question without
+substitution, record the gap, and ask: the user decides whether to proceed without it.
+For an uncertain dispatch, reconcile natively; it is never treated as absent.
+Unaffected fact work and questions continue.
 
 ## Bound the interview
 

package/src/installer.js

@@ -626,6 +626,16 @@ export async function installBundle({
         if (rel in ownedFiles) installedHashes[rel] = ownedFiles[rel];
       }
     }
+    const previousRoles = desired.find(({ rel }) => rel === 'axstack/roles.json')?.current;
+    if (previousRoles && summary.updated.some((rel) => rel.startsWith('axstack/roles.json'))) {
+      try {
+        const old = JSON.parse(previousRoles.toString());
+        if (Array.isArray(old.roles)) {
+          const oldIds = new Set(old.roles.map((role) => role?.id));
+          summary.addedRoleIds = bundle.bundleRoles.filter((role) => !oldIds.has(role.id)).map((role) => role.id);
+        }
+      } catch { /* No reliable role-ID diff for malformed prior bytes. */ }
+    }
 
     // Stale manifest entries (owned files the bundle no longer ships):
     // the phase-1 plan validated every stale destination read-only

package/src/roles.js

@@ -66,8 +66,10 @@ export function assessRoleReadiness(roles, preset) {
     (preset === 'mixed' && role.id === 'axstack-checker' && role.provider === 'antigravity') ||
     (preset === 'mixed' && role.id === 'axstack-research-web-google' && role.provider === 'antigravity') ||
     (preset === 'mixed' && role.id === 'axstack-research-x' && role.provider === 'grok') ||
-    (preset === 'codex-only' && ['axstack-advisor-fable', 'axstack-arena-judge-fable', 'axstack-research-web-google', 'axstack-research-x'].includes(role.id)) ||
-    (preset === 'claude-only' && ['axstack-advisor-astra', 'axstack-arena-judge-astra', 'axstack-research-web-google', 'axstack-research-x'].includes(role.id))
+    (preset === 'mixed' && role.id === 'axstack-arena-candidate-grok' && role.provider === 'grok') ||
+    (preset === 'mixed' && role.id === 'axstack-arena-candidate-antigravity' && role.provider === 'antigravity') ||
+    (preset === 'codex-only' && ['axstack-advisor-fable', 'axstack-arena-judge-fable', 'axstack-research-web-google', 'axstack-research-x', 'axstack-arena-candidate-grok', 'axstack-arena-candidate-antigravity'].includes(role.id)) ||
+    (preset === 'claude-only' && ['axstack-advisor-astra', 'axstack-arena-judge-astra', 'axstack-research-web-google', 'axstack-research-x', 'axstack-arena-candidate-grok', 'axstack-arena-candidate-antigravity'].includes(role.id))
   );
   for (const role of roles) {
     if (!bounds.has(role.provider)) {