axstack 0.20.29 → 0.20.31

package/README.md

@@ -100,15 +100,17 @@ upgrades, conflicts, and uninstalling.
 - Agents keep accepted decisions and evidence for resume. Missing authority,
   unavailable models, and serious risks surface as holds. The human merges by default.
 
-Choose one explicit preset (28 roles each): [mixed](profiles/presets/mixed.json)
+Choose one explicit preset (32 roles each): [mixed](profiles/presets/mixed.json)
 (recommended), [codex-only](profiles/presets/codex-only.json), or
 [claude-only](profiles/presets/claude-only.json). Mixed supports cross-provider
 implementation review; single-provider presets have workflow limits and are
-not automatic fallbacks when a model is unavailable. See
+not automatic cross-class or cross-provider fallbacks when a model is unavailable. See
 [workflow and routing details](docs/workflows.md).
 
-In `mixed` and `claude-only`, requirements research, web research, and the
-optional monitor use Claude Sonnet 5.5 high.
+In `mixed` and `claude-only`, auditing, requirements/code/web research,
+execution exploration, and the optional monitor use the Claude Sonnet class at high effort.
+Auditing, code research, and execution exploration have independent Sol high
+pair seats in `mixed` and `codex-only`; `claude-only` records them as absent.
 
 ## Optional PR automation
 

package/bin/axstack.js

@@ -337,6 +337,7 @@ async function main() {
         if (summary.updated.length) console.log(`updated: ${summary.updated.join(', ')}`);
         if (summary.addedRoleIds?.length) console.log(`added role IDs: ${summary.addedRoleIds.join(', ')}`);
         if (summary.removedRoleIds?.length) console.log(`removed role IDs: ${summary.removedRoleIds.join(', ')}`);
+        if (summary.changedRoleModels?.length) console.log(`changed role models: ${summary.changedRoleModels.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 28 stable
+Each has exactly `{ "version": 1, "roles": [...] }` with the same 32 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
@@ -172,13 +172,19 @@ 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 28 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.
-
-The `mixed` and `claude-only` presets assign `axstack-research-requirements`,
-`axstack-research-web`, and `axstack-monitor` to Claude Sonnet 5.5 high.
+A new run records the selected preset plus all 32 role rows. Class rows resolve
+at run start; each role snapshot records class, exact ID, source, and time.
+An active run and resume reuse that snapshot after a later preset install unless
+the user explicitly changes it and accepts the resulting evidence invalidation.
+
+The `mixed` and `claude-only` presets assign `axstack-auditor`,
+`axstack-research-requirements`, `axstack-research-code`, `axstack-research-web`,
+`axstack-explore-execution`, and `axstack-monitor` to the Claude Sonnet class at high effort.
 The `codex-only` assignments for these roles are unchanged.
+The three `-sol` pair seats for auditor, research-code, and explore-execution
+use Sol high in `mixed` and `codex-only`; `claude-only` records intentional
+absences. The paired seats run independently on one brief and the driver
+reconciles their findings.
 
 The mixed checker and `axstack-research-web-google` have provider
 `antigravity`; mixed `axstack-research-x` has provider `grok`. All three use
@@ -193,8 +199,13 @@ receipts. For an arena-grade Align question, round 1 needs Opus; round 2, if
 invoked, needs escalation Fable and Astra; a required seat that is unavailable holds that
 round. The current chat drives on whatever
 model runs it; no preset carries a driver role. Every other missing, invalid, unsupported, or unavailable role value holds only
-the affected work. There is no model substitution, subscription inference, or
-quota routing.
+the affected work. Codex class resolution reads the explicit catalog path via
+`skills/axstack/scripts/resolve-models.js`; a missing or malformed catalog
+holds. Claude launches an alias once per class, reads the exact ID from the
+first assistant transcript turn, then reuses it. Only explicit model rejection
+before that turn permits a recorded Codex retry within the same class, provider,
+and effort. Claude rejection, timeout, quota, and auth failures hold; no
+subscription inference or quota routing applies.
 
 `modeId` and similar permission fields remain conservative declared intent.
 They do not prove the effective Orca launcher mode, sandboxing, or permission

package/docs/workflows.md

@@ -48,28 +48,39 @@ 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 28 stable IDs.
+`{ "version": 1, "roles": [...] }` and the same 32 stable IDs.
 
 The current chat drives on whatever model runs it; no preset carries a driver
 role.
 
 | Preset | Author | Ordered peer reviewers | Astra / Opus advisers | Auditor |
 | --- | --- | --- | --- | --- |
-| `mixed` | Sol high | Sol high; Opus medium | Astra high / Opus xhigh | Luna xhigh |
-| `codex-only` | Sol high | Sol high; Luna xhigh | Astra high / unavailable | Luna xhigh |
-| `claude-only` | Opus medium | Opus medium; Sonnet high | unavailable / Opus xhigh | Sonnet high |
-
-In `mixed` and `claude-only`, `axstack-research-requirements`,
-`axstack-research-web`, and `axstack-monitor` use Claude Sonnet 5.5 high.
-`codex-only` keeps its Codex assignments for those roles.
+| `mixed` | Sol high | Sol high; Opus medium | Astra high / Opus xhigh | Sonnet high + Sol high |
+| `codex-only` | Sol high | Sol high; Luna xhigh | Astra high / unavailable | Luna xhigh + Sol high |
+| `claude-only` | Opus medium | Opus medium; Sonnet high | unavailable / Opus xhigh | Sonnet high (Sol absent) |
+
+In `mixed` and `claude-only`, `axstack-auditor`, `axstack-research-requirements`,
+`axstack-research-code`, `axstack-research-web`, `axstack-explore-execution`,
+and `axstack-monitor` use the Claude Sonnet class at high effort. `codex-only` keeps its Codex
+assignments for those roles. Mixed web-google and X retain their source-specific
+Antigravity and Grok routes.
+The new `-sol` auditor, research-code, and explore-execution seats use Sol high
+in `mixed` and `codex-only`; `claude-only` records each as intentionally absent.
+Dispatch the base and Sol seats independently on the same brief, then reconcile
+their findings per claim without averaging.
 
 The installed `<skills-dir>/axstack/roles.json` adds the selected preset name:
 `{ "version": 1, "preset": "<name>", "roles": [...] }`. The runtime reads it
 from the installed shared root `skills/axstack/` and records the whole table for
-a new run. Active runs retain their snapshot after later installation changes.
+a new run. Per role it records class, exact ID, source, and time. Codex classes
+resolve from a passed catalog path using `skills/axstack/scripts/resolve-models.js`;
+missing or malformed catalogs hold. Claude's first class launch passes the alias,
+then the first assistant transcript turn supplies the exact ID for later launches.
+Unknown Claude IDs hold provenance-dependent work. Active runs and resume reuse
+their snapshot after later installation changes.
 
 Peer roles keep the stable IDs `axstack-reviewer-primary` and
-`axstack-reviewer-secondary`; their provider/model mappings come only from the
+`axstack-reviewer-secondary`; their provider/class mappings come only from the
 selected preset.
 
 The unavailable adviser in each single-provider preset stays explicitly
@@ -82,7 +93,10 @@ launchable; the run record snapshots the model the TUI reports. Missing or unava
 work. Model, effort, and permission values express requested intent until real
 Orca receipts establish the effective session. Stored `modeId` is not permission
 parity or a sandbox. No route is inferred from subscription, quota, harness,
-provider defaults, or installed tools, and no model is substituted silently.
+provider defaults, or installed tools. Only explicit model rejection before the
+first turn permits a recorded Codex retry with `--retry-of` to the next eligible
+model in the same class, provider, and effort. Claude rejection, timeout, quota,
+and auth failures hold.
 
 ## Orca runtime boundary
 
@@ -195,11 +209,15 @@ keeps the current owner and a resumable record.
 
 Serious security, downtime, data-loss, and major-design risks are raised in a
 prompt immediately and hold dependent dangerous work. This is not a runtime
-gate. An applicable `Notification policy` may use `axstack-relay` for serious
-risk immediately or a genuine blocker needing user intervention after bounded
-safe recovery. Questions, spec approvals, progress, CI pending, merge-ready,
-merged, and completion stay in Orca. The relay normally delivers one-way
-through native `hermes send`: it checks CLI lookup and the configured target,
+gate. An applicable `Notification policy` may use `axstack-relay` only for a
+user-decision hold (including spec or npm approval and a genuine blocker after
+bounded safe recovery), a serious-risk hold immediately, or at most two merge-ready/merged milestones per run.
+Routine questions stay in Orca. Progress, CI pending, and completion always stay
+in Orca.
+Only the bounded categories—user-decision holds (including spec approval),
+serious-risk holds, and at most two merge-ready/merged milestones per run—may
+be relayed under the recorded Notification policy. The relay normally delivers
+one-way through native `hermes send`: it checks CLI lookup and the configured target,
 binds the recipient, deduplicates on the run record, and records the returned
 `message_id`. PR-manager notifications point the user to GitHub or a durable
 user-owned conversation; Telegram delivery, replies, and silence grant no action
@@ -210,9 +228,16 @@ read-only observer for standalone watches and never sends.
 
 ## Chat-run PR watch
 
+For authorized engineering delivery, [Autopilot](../skills/axstack/references/autopilot.md)
+continues from Align through the eligible phase sequence in the same chat.
+The human approves substantial specs, every merge including release PRs, and
+the npm stage. An open hold pauses the run. Implement arms maintain-mode watch
+at its first published PR; release and install run only under recorded per-run
+authority, and Close-out follows their verified receipts.
+
 Use `axstack-watch` chat-run mode to watch every PR raised by this chat's Run, including later verified publications and PRs the driver explicitly adopts. A harness-native monitoring or scheduled wake resumes the driver chat every 10 minutes by default; only when the harness has no such capability does the existing Orca `*/10` observer act as fallback. Record the chosen mechanism in the run record. Each wake runs the own-PR maintenance loop: address feedback, rebase on base movement, rerun required CI, and check the forge-counted human approval. Delegated work still runs through Orca; there is no daemon or polling model between wakes. Independent PRs can repair in parallel with one writer per PR; stack ancestor changes invalidate child evidence. An incomplete scan leaves readiness `UNKNOWN`.
 
-The watch lasts until all member PRs merge or close, you cancel it, or its wake expires. Stop and verify the chosen wake; an Orca fallback also needs automation disable/readback and workspace retirement. Worker settlement and run archive are separate driver steps. Run-created implementation candidates are published and read back before independent authored review. Adopted own-PR maintenance candidates receive independent exact-local-SHA review before driver publication and remote readback. The human merges. Source and installed instructions do not prove scheduled observation, driver wake, or live activation; those require native receipts.
+The watch lasts until all member PRs merge or close and the run's release step is settled or not applicable, you cancel it, or its wake expires. Stop and verify the chosen wake; an Orca fallback also needs automation disable/readback and workspace retirement. Worker settlement and run archive are separate driver steps. Run-created implementation candidates are published and read back before independent authored review. Adopted own-PR maintenance candidates receive independent exact-local-SHA review before driver publication and remote readback. The human merges. Source and installed instructions do not prove scheduled observation, driver wake, or live activation; those require native receipts.
 
 ## Optional native peer-review automation
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "axstack",
-  "version": "0.20.29",
+  "version": "0.20.31",
   "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

@@ -14,82 +14,100 @@
       "id": "axstack-advisor-opus",
       "name": "Axstack Opus adviser",
       "provider": "claude",
-      "model": "claude-opus-5-5",
       "modeId": "bypassPermissions",
       "thinkingOptionId": "xhigh",
-      "notes": "Independent Opus adviser for Align, Spec, and debug L1; authors the Claude arena candidate. Same bounded evidence and question as Astra; reuse only unchanged receipts."
+      "notes": "Independent Opus adviser for Align, Spec, and debug L1; authors the Claude arena candidate. Same bounded evidence and question as Astra; reuse only unchanged receipts. Claude alias resolves at first launch; a Claude rejection holds.",
+      "modelClass": "opus"
     },
     {
       "id": "axstack-owner",
       "name": "Axstack PR owner",
       "provider": "claude",
-      "model": "claude-opus-5-5",
       "modeId": "bypassPermissions",
       "thinkingOptionId": "medium",
-      "notes": "Persistent PR owner: one owner per PR, accountable for candidate, fixes, verification evidence, and monitoring. May delegate coding but never edits a worker-owned candidate concurrently. Launches eligible independent reviewers."
+      "notes": "Persistent PR owner: one owner per PR, accountable for candidate, fixes, verification evidence, and monitoring. May delegate coding but never edits a worker-owned candidate concurrently. Launches eligible independent reviewers. Claude alias resolves at first launch; a Claude rejection holds.",
+      "modelClass": "opus"
     },
     {
       "id": "axstack-author",
       "name": "Axstack author",
       "provider": "claude",
-      "model": "claude-opus-5-5",
       "modeId": "bypassPermissions",
       "thinkingOptionId": "medium",
-      "notes": "Ordinary implementation and repairs. Uses strict red-green-refactor and remains the exclusive writer for a candidate. Validate configured availability at launch; hold affected work without fallback."
+      "notes": "Ordinary implementation and repairs. Uses strict red-green-refactor and remains the exclusive writer for a candidate. Claude alias resolves at first launch; a Claude rejection holds.",
+      "modelClass": "opus"
     },
     {
       "id": "axstack-reviewer-primary",
       "name": "Axstack reviewer (primary)",
       "provider": "claude",
-      "model": "claude-opus-5-5",
       "modeId": "bypassPermissions",
       "thinkingOptionId": "medium",
-      "notes": "Primary reviewer in the ordered claude-only peer pair: Opus medium followed by Sonnet high. Never author or owner; review exact SHA and base across all six angles and acceptance. Peer first pass stays isolated."
+      "notes": "Primary reviewer in the ordered claude-only peer pair: Opus medium followed by Sonnet high. Never author or owner; review exact SHA and base across all six angles and acceptance. Peer first pass stays isolated. Claude alias resolves at first launch; a Claude rejection holds.",
+      "modelClass": "opus"
     },
     {
       "id": "axstack-reviewer-secondary",
       "name": "Axstack reviewer (secondary)",
       "provider": "claude",
-      "model": "claude-sonnet-5-5",
       "modeId": "bypassPermissions",
       "thinkingOptionId": "high",
-      "notes": "Secondary reviewer in the ordered claude-only peer pair: Opus medium followed by Sonnet high. Eligible authored reviewer for an Opus-authored candidate. Never author or owner; review exact SHA and base across all six angles and acceptance. Peer first pass stays isolated."
+      "notes": "Secondary reviewer in the ordered claude-only peer pair: Opus medium followed by Sonnet high. Eligible authored reviewer for an Opus-authored candidate. Never author or owner; review exact SHA and base across all six angles and acceptance. Peer first pass stays isolated. Claude alias resolves at first launch; a Claude rejection holds.",
+      "modelClass": "sonnet"
+    },
+    {
+      "id": "axstack-diligence",
+      "name": "Axstack diligence checker",
+      "provider": "claude",
+      "modeId": "bypassPermissions",
+      "thinkingOptionId": "high",
+      "notes": "Read-only diligence for exact-revision PRs and bounded research, spec, ticket, receipt, and release claims. Returns PASS or FINDINGS with evidence; never authors or edits. Claude alias resolves at first launch; a Claude rejection holds.",
+      "modelClass": "sonnet"
     },
     {
       "id": "axstack-checker",
       "name": "Axstack tracker checker",
       "provider": "claude",
-      "model": "claude-sonnet-5-5",
       "modeId": "bypassPermissions",
       "thinkingOptionId": "high",
-      "notes": "Report-only discrepancy checker for the selected external tracker (Linear or GitHub Issues). Never mutates the tracker; the driver independently verifies evidence before applying updates. A null model means explicit user selection is required before dispatch and must never launch a provider default."
+      "notes": "Report-only discrepancy checker for the selected external tracker (Linear or GitHub Issues). Never mutates the tracker; the driver independently verifies evidence before applying updates. A null model means explicit user selection is required before dispatch and must never launch a provider default. Claude alias resolves at first launch; a Claude rejection holds.",
+      "modelClass": "sonnet"
     },
     {
       "id": "axstack-research-requirements",
       "name": "Axstack research requirements",
       "provider": "claude",
-      "model": "claude-sonnet-5-5",
       "modeId": "bypassPermissions",
       "thinkingOptionId": "high",
-      "notes": "Sonnet high research requirements analyst: scopes bounded questions and acceptance for a research task. Validate configured availability at launch; hold affected work without fallback."
+      "notes": "Sonnet high research requirements analyst: scopes bounded questions and acceptance for a research task. Claude alias resolves at first launch; a Claude rejection holds.",
+      "modelClass": "sonnet"
     },
     {
       "id": "axstack-research-code",
       "name": "Axstack research code",
       "provider": "claude",
-      "model": "claude-opus-5-5",
       "modeId": "bypassPermissions",
-      "thinkingOptionId": "medium",
-      "notes": "Research code investigator: verifies behavior against inspected code and executable evidence. Validate configured availability at launch; hold affected work without fallback."
+      "thinkingOptionId": "high",
+      "notes": "Sonnet high research code investigator: verifies behavior against inspected code and executable evidence. Claude alias resolves at first launch; a Claude rejection holds.",
+      "modelClass": "sonnet"
+    },
+    {
+      "id": "axstack-research-code-sol",
+      "name": "Axstack research code Sol (unavailable)",
+      "provider": "claude",
+      "model": null,
+      "modeId": "bypassPermissions",
+      "thinkingOptionId": "high",
+      "notes": "Intentional single-provider absence: Sol pair seat axstack-research-code-sol is unavailable in claude-only. The explicit null records the absent pair without substitution; the Sonnet seat proceeds alone."
     },
     {
       "id": "axstack-research-web",
       "name": "Axstack research web",
       "provider": "claude",
-      "model": "claude-sonnet-5-5",
       "modeId": "bypassPermissions",
       "thinkingOptionId": "high",
-      "notes": "Sonnet high research web reader: gathers primary-source facts efficiently. Validate configured availability at launch; hold affected work without fallback."
+      "notes": "Sonnet high research web reader: gathers primary-source facts efficiently. Claude alias resolves at first launch; a Claude rejection holds.",
+      "modelClass": "sonnet"
     },
     {
       "id": "axstack-research-web-google",
@@ -113,100 +131,118 @@
       "id": "axstack-explainer",
       "name": "Axstack explainer",
       "provider": "claude",
-      "model": "claude-sonnet-5-5",
       "modeId": "bypassPermissions",
       "thinkingOptionId": "high",
-      "notes": "Complex visual explanation author: traces systems, changes, and implementation gaps in requested artifacts and verifies rendered behavior where applicable. Validate configured availability at launch; hold affected work without fallback."
+      "notes": "Complex visual explanation author: traces systems, changes, and implementation gaps in requested artifacts and verifies rendered behavior where applicable. Claude alias resolves at first launch; a Claude rejection holds.",
+      "modelClass": "sonnet"
     },
     {
       "id": "axstack-explainer-review",
       "name": "Axstack explainer reviewer",
       "provider": "claude",
-      "model": "claude-sonnet-5-5",
       "modeId": "bypassPermissions",
       "thinkingOptionId": "high",
-      "notes": "Independent visual explanation reviewer: checks the exact artifact for text and source fidelity. The rendered pass belongs to axstack-ui-verifier. Any artifact change invalidates its review. Validate configured availability at launch; hold affected work without fallback."
+      "notes": "Independent visual explanation reviewer: checks the exact artifact for text and source fidelity. The rendered pass belongs to axstack-ui-verifier. Any artifact change invalidates its review. Claude alias resolves at first launch; a Claude rejection holds.",
+      "modelClass": "sonnet"
     },
     {
       "id": "axstack-ui-verifier",
       "name": "Axstack UI verifier",
       "provider": "claude",
-      "model": "claude-sonnet-5-5",
       "modeId": "bypassPermissions",
       "thinkingOptionId": "high",
-      "notes": "Read-only UI verifier: runs Playwright or the browser against the given build, URL, or artifact; captures screenshots, interactions, accessibility, desktop/mobile, and reduced-motion evidence in the dispatch evidence folder; returns a verdict with evidence paths. Never edits source. Validate configured availability at launch; hold affected work without fallback."
+      "notes": "Read-only UI verifier: runs Playwright or the browser against the given build, URL, or artifact; captures screenshots, interactions, accessibility, desktop/mobile, and reduced-motion evidence in the dispatch evidence folder; returns a verdict with evidence paths. Never edits source. Claude alias resolves at first launch; a Claude rejection holds.",
+      "modelClass": "sonnet"
     },
     {
       "id": "axstack-explore-codebase",
       "name": "Axstack codebase explorer",
       "provider": "claude",
-      "model": "claude-sonnet-5-5",
       "modeId": "bypassPermissions",
       "thinkingOptionId": "high",
-      "notes": "Codebase mapper: explores repository structure and interfaces for research and handoff context. Validate configured availability at launch; hold affected work without fallback."
+      "notes": "Codebase mapper: explores repository structure and interfaces for research and handoff context. Claude alias resolves at first launch; a Claude rejection holds.",
+      "modelClass": "sonnet"
     },
     {
       "id": "axstack-explore-execution",
       "name": "Axstack execution explorer",
       "provider": "claude",
-      "model": "claude-sonnet-5-5",
       "modeId": "bypassPermissions",
       "thinkingOptionId": "high",
-      "notes": "Execution explorer: runs bounded checks of runtime behavior where authorized. Validate configured availability at launch; hold affected work without fallback."
+      "notes": "Sonnet high execution explorer: runs bounded checks of runtime behavior where authorized. Claude alias resolves at first launch; a Claude rejection holds.",
+      "modelClass": "sonnet"
+    },
+    {
+      "id": "axstack-explore-execution-sol",
+      "name": "Axstack execution explorer Sol (unavailable)",
+      "provider": "claude",
+      "model": null,
+      "modeId": "bypassPermissions",
+      "thinkingOptionId": "high",
+      "notes": "Intentional single-provider absence: Sol pair seat axstack-explore-execution-sol is unavailable in claude-only. The explicit null records the absent pair without substitution; the Sonnet seat proceeds alone."
     },
     {
       "id": "axstack-monitor",
       "name": "Axstack monitor",
       "provider": "claude",
-      "model": "claude-sonnet-5-5",
       "modeId": "bypassPermissions",
       "thinkingOptionId": "high",
-      "notes": "Optional Sonnet high independent read-only observer for a standalone PR watch. Reads GitHub, feedback, and checks, persists event IDs, and wakes the owner only for a new actionable event. Never sends, authors, reviews, replies, or acts as either reusable PR manager. Healthy snapshots stay quiet. Chat-run mode: one same-host native read-only observer per Run; fresh finite passes report precise deltas internally to the original Run/driver and may disable/read back only their own automation at verified stop. No repair, dispatch, public notification, or replacement coordinator. Effective scheduled model/effort and wake require live proof."
+      "notes": "Optional Sonnet high independent read-only observer for a standalone PR watch. Reads GitHub, feedback, and checks, persists event IDs, and wakes the owner only for a new actionable event. Never sends, authors, reviews, replies, or acts as either reusable PR manager. Healthy snapshots stay quiet. Chat-run mode: one same-host native read-only observer per Run; fresh finite passes report precise deltas internally to the original Run/driver and may disable/read back only their own automation at verified stop. No repair, dispatch, public notification, or replacement coordinator. Effective scheduled model/effort and wake require live proof. Claude alias resolves at first launch; a Claude rejection holds.",
+      "modelClass": "sonnet"
     },
     {
       "id": "axstack-auditor",
       "name": "Axstack auditor",
       "provider": "claude",
-      "model": "claude-sonnet-5-5",
       "modeId": "bypassPermissions",
       "thinkingOptionId": "high",
-      "notes": "Read-only end-of-run and checkpoint auditor. Collects scope and outcome evidence with counts and denominators and reports PASS, FAIL, or UNKNOWN without inventing numbers. Never edits, merges, activates, or audits itself."
+      "notes": "Sonnet high read-only end-of-run and checkpoint auditor. Collects scope and outcome evidence with counts and denominators and reports PASS, FAIL, or UNKNOWN without inventing numbers. Never edits, merges, activates, or audits itself. Claude alias resolves at first launch; a Claude rejection holds.",
+      "modelClass": "sonnet"
+    },
+    {
+      "id": "axstack-auditor-sol",
+      "name": "Axstack auditor Sol (unavailable)",
+      "provider": "claude",
+      "model": null,
+      "modeId": "bypassPermissions",
+      "thinkingOptionId": "high",
+      "notes": "Intentional single-provider absence: Sol pair seat axstack-auditor-sol is unavailable in claude-only. The explicit null records the absent pair without substitution; the Sonnet seat proceeds alone."
     },
     {
       "id": "axstack-debug-investigator-1",
       "name": "Axstack debug investigator 1",
       "provider": "claude",
-      "model": "claude-opus-5-5",
       "modeId": "bypassPermissions",
       "thinkingOptionId": "medium",
-      "notes": "Debug investigator seat 1. Dispatched only by axstack-debug at L1 with the shared evidence packet and one distinct brief; never reads another investigator's output. Works in its own disposable worktree at the pinned revision plus the recorded dirty patch; may instrument there for probes; never commits, pushes, publishes, or creates children. Returns one receipt per brief. Independence comes from brief isolation, not model diversity. This preset repeats claude-opus-5-5 at medium effort because it has fewer model families."
+      "notes": "Debug investigator seat 1. Dispatched only by axstack-debug at L1 with the shared evidence packet and one distinct brief; never reads another investigator's output. Works in its own disposable worktree at the pinned revision plus the recorded dirty patch; may instrument there for probes; never commits, pushes, publishes, or creates children. Returns one receipt per brief. Independence comes from brief isolation, not model diversity. This preset repeats the Opus class at medium effort because it has fewer model families. Claude alias resolves at first launch; a Claude rejection holds.",
+      "modelClass": "opus"
     },
     {
       "id": "axstack-debug-investigator-2",
       "name": "Axstack debug investigator 2",
       "provider": "claude",
-      "model": "claude-sonnet-5-5",
       "modeId": "bypassPermissions",
       "thinkingOptionId": "high",
-      "notes": "Debug investigator seat 2. Dispatched only by axstack-debug at L1 with the shared evidence packet and one distinct brief; never reads another investigator's output. Works in its own disposable worktree at the pinned revision plus the recorded dirty patch; may instrument there for probes; never commits, pushes, publishes, or creates children. Returns one receipt per brief. Independence comes from brief isolation, not model diversity. This preset repeats claude-sonnet-5-5 at high effort because it has fewer model families; independence comes from brief isolation."
+      "notes": "Debug investigator seat 2. Dispatched only by axstack-debug at L1 with the shared evidence packet and one distinct brief; never reads another investigator's output. Works in its own disposable worktree at the pinned revision plus the recorded dirty patch; may instrument there for probes; never commits, pushes, publishes, or creates children. Returns one receipt per brief. Independence comes from brief isolation, not model diversity. This preset repeats the Sonnet class at high effort because it has fewer model families; independence comes from brief isolation. Claude alias resolves at first launch; a Claude rejection holds.",
+      "modelClass": "sonnet"
     },
     {
       "id": "axstack-debug-investigator-3",
       "name": "Axstack debug investigator 3",
       "provider": "claude",
-      "model": "claude-opus-5-5",
       "modeId": "bypassPermissions",
       "thinkingOptionId": "medium",
-      "notes": "Debug investigator seat 3. Dispatched only by axstack-debug at L1 with the shared evidence packet and one distinct brief; never reads another investigator's output. Works in its own disposable worktree at the pinned revision plus the recorded dirty patch; may instrument there for probes; never commits, pushes, publishes, or creates children. Returns one receipt per brief. Independence comes from brief isolation, not model diversity. This preset repeats claude-opus-5-5 at medium effort because it has fewer model families."
+      "notes": "Debug investigator seat 3. Dispatched only by axstack-debug at L1 with the shared evidence packet and one distinct brief; never reads another investigator's output. Works in its own disposable worktree at the pinned revision plus the recorded dirty patch; may instrument there for probes; never commits, pushes, publishes, or creates children. Returns one receipt per brief. Independence comes from brief isolation, not model diversity. This preset repeats the Opus class at medium effort because it has fewer model families. Claude alias resolves at first launch; a Claude rejection holds.",
+      "modelClass": "opus"
     },
     {
       "id": "axstack-debug-investigator-4",
       "name": "Axstack debug investigator 4",
       "provider": "claude",
-      "model": "claude-sonnet-5-5",
       "modeId": "bypassPermissions",
       "thinkingOptionId": "high",
-      "notes": "Debug investigator seat 4. Dispatched only by axstack-debug at L1 with the shared evidence packet and one distinct brief; never reads another investigator's output. Works in its own disposable worktree at the pinned revision plus the recorded dirty patch; may instrument there for probes; never commits, pushes, publishes, or creates children. Returns one receipt per brief. Independence comes from brief isolation, not model diversity. This preset repeats claude-sonnet-5-5 at high effort because it has fewer model families; independence comes from brief isolation."
+      "notes": "Debug investigator seat 4. Dispatched only by axstack-debug at L1 with the shared evidence packet and one distinct brief; never reads another investigator's output. Works in its own disposable worktree at the pinned revision plus the recorded dirty patch; may instrument there for probes; never commits, pushes, publishes, or creates children. Returns one receipt per brief. Independence comes from brief isolation, not model diversity. This preset repeats the Sonnet class at high effort because it has fewer model families; independence comes from brief isolation. Claude alias resolves at first launch; a Claude rejection holds.",
+      "modelClass": "sonnet"
     },
     {
       "id": "axstack-arena-judge-astra",
@@ -221,19 +257,19 @@
       "id": "axstack-escalation-fable",
       "name": "Axstack escalation Fable",
       "provider": "claude",
-      "model": "claude-fable-5-1",
       "modeId": "bypassPermissions",
       "thinkingOptionId": "xhigh",
-      "notes": "Fable escalation seat for arena round 2, high-stakes plain AGREE, or the bounded escalation trigger. Fresh session per use; never reuses adviser or candidate context. Read-only round 2 judge: scores every candidate by label; never authors a candidate."
+      "notes": "Fable escalation seat for arena round 2, high-stakes plain AGREE, or the bounded escalation trigger. Fresh session per use; never reuses adviser or candidate context. Read-only round 2 judge: scores every candidate by label; never authors a candidate. Claude alias resolves at first launch; a Claude rejection holds.",
+      "modelClass": "fable"
     },
     {
       "id": "axstack-arena-judge-opus",
       "name": "Axstack arena judge Opus",
       "provider": "claude",
-      "model": "claude-opus-5-5",
       "modeId": "bypassPermissions",
       "thinkingOptionId": "xhigh",
-      "notes": "Read-only round 1 arena judge. Receives the rubric and every candidate by label, scores each criterion, and recommends a base with rationale. Never authors a candidate, never cross-reads another judge, never mutates; the driver compares its verdict without averaging."
+      "notes": "Read-only round 1 arena judge. Receives the rubric and every candidate by label, scores each criterion, and recommends a base with rationale. Never authors a candidate, never cross-reads another judge, never mutates; the driver compares its verdict without averaging. Claude alias resolves at first launch; a Claude rejection holds.",
+      "modelClass": "opus"
     },
     {
       "id": "axstack-arena-candidate-grok",