axstack 0.20.28 → 0.20.29

package/README.md

@@ -100,13 +100,16 @@ 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 (27 roles each): [mixed](profiles/presets/mixed.json)
+Choose one explicit preset (28 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
 [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.
+
 ## Optional PR automation
 
 Manual review works without a schedule. Own open PRs in chat-run mode use a

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 27 stable
+Each has exactly `{ "version": 1, "roles": [...] }` with the same 28 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
@@ -172,10 +172,14 @@ 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 27 role rows. An active run keeps
+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.
+The `codex-only` assignments for these roles are unchanged.
+
 The mixed checker and `axstack-research-web-google` have provider
 `antigravity`; mixed `axstack-research-x` has provider `grok`. All three use
 `model: null` because Orca exposes no model override for those agent-ID routes;

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 27 stable IDs.
+`{ "version": 1, "roles": [...] }` and the same 28 stable IDs.
 
 The current chat drives on whatever model runs it; no preset carries a driver
 role.
@@ -59,6 +59,10 @@ role.
 | `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.
+
 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

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "axstack",
-  "version": "0.20.28",
+  "version": "0.20.29",
   "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

@@ -68,10 +68,10 @@
       "id": "axstack-research-requirements",
       "name": "Axstack research requirements",
       "provider": "claude",
-      "model": "claude-opus-5-5",
+      "model": "claude-sonnet-5-5",
       "modeId": "bypassPermissions",
-      "thinkingOptionId": "medium",
-      "notes": "Research requirements analyst: scopes bounded questions and acceptance for a research task. Validate configured availability at launch; hold affected work without fallback."
+      "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."
     },
     {
       "id": "axstack-research-code",
@@ -89,7 +89,7 @@
       "model": "claude-sonnet-5-5",
       "modeId": "bypassPermissions",
       "thinkingOptionId": "high",
-      "notes": "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. Validate configured availability at launch; hold affected work without fallback."
     },
     {
       "id": "axstack-research-web-google",
@@ -125,7 +125,16 @@
       "model": "claude-sonnet-5-5",
       "modeId": "bypassPermissions",
       "thinkingOptionId": "high",
-      "notes": "Independent visual explanation reviewer: checks the exact artifact for source fidelity and rendered behavior where warranted. 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. Validate configured availability at launch; hold affected work without fallback."
+    },
+    {
+      "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."
     },
     {
       "id": "axstack-explore-codebase",
@@ -152,7 +161,7 @@
       "model": "claude-sonnet-5-5",
       "modeId": "bypassPermissions",
       "thinkingOptionId": "high",
-      "notes": "Optional 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."
     },
     {
       "id": "axstack-auditor",

package/profiles/presets/codex-only.json

@@ -125,7 +125,16 @@
       "model": "gpt-6-luna",
       "modeId": "full-access",
       "thinkingOptionId": "xhigh",
-      "notes": "Independent visual explanation reviewer: checks the exact artifact for source fidelity and rendered behavior where warranted. 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. Validate configured availability at launch; hold affected work without fallback."
+    },
+    {
+      "id": "axstack-ui-verifier",
+      "name": "Axstack UI verifier",
+      "provider": "codex",
+      "model": "gpt-6-sol",
+      "modeId": "full-access",
+      "thinkingOptionId": "medium",
+      "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."
     },
     {
       "id": "axstack-explore-codebase",

package/profiles/presets/mixed.json

@@ -68,10 +68,10 @@
       "id": "axstack-research-requirements",
       "name": "Axstack research requirements",
       "provider": "claude",
-      "model": "claude-opus-5-5",
+      "model": "claude-sonnet-5-5",
       "modeId": "bypassPermissions",
-      "thinkingOptionId": "medium",
-      "notes": "Research requirements analyst: scopes bounded questions and acceptance for a research task. Validate configured availability at launch; hold affected work without fallback."
+      "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."
     },
     {
       "id": "axstack-research-code",
@@ -86,10 +86,10 @@
       "id": "axstack-research-web",
       "name": "Axstack research web",
       "provider": "claude",
-      "model": "claude-opus-5-5",
+      "model": "claude-sonnet-5-5",
       "modeId": "bypassPermissions",
-      "thinkingOptionId": "low",
-      "notes": "Research web reader: gathers primary-source facts efficiently. Validate configured availability at launch; hold affected work without fallback."
+      "thinkingOptionId": "high",
+      "notes": "Sonnet high research web reader: gathers primary-source facts efficiently. Validate configured availability at launch; hold affected work without fallback."
     },
     {
       "id": "axstack-research-web-google",
@@ -125,7 +125,16 @@
       "model": "gpt-6-luna",
       "modeId": "full-access",
       "thinkingOptionId": "xhigh",
-      "notes": "Independent visual explanation reviewer: checks the exact artifact for source fidelity and rendered behavior where warranted. 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. Validate configured availability at launch; hold affected work without fallback."
+    },
+    {
+      "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."
     },
     {
       "id": "axstack-explore-codebase",
@@ -149,10 +158,10 @@
       "id": "axstack-monitor",
       "name": "Axstack monitor",
       "provider": "claude",
-      "model": "claude-opus-5-5",
+      "model": "claude-sonnet-5-5",
       "modeId": "bypassPermissions",
-      "thinkingOptionId": "medium",
-      "notes": "Optional 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."
+      "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."
     },
     {
       "id": "axstack-auditor",

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 27 role rows once. An active run keeps the exact snapshot until the user
+all 28 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

@@ -11,10 +11,10 @@ skills root, or an explicit user selection in the run record. Missing or contrad
 a setup gap: hold. Never infer from live profiles or `list_profiles`, harness,
 tools, credentials, quota, subscription, or default to `mixed`.
 
-At start, snapshot all 27 role IDs with provider/model/mode/effort; absent
+At start, snapshot all 28 role IDs with provider/model/mode/effort; absent
 or unconfigured roles are recorded explicitly; never 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
+Such a role holds only its work. Later installed or changed roles need an
+explicit user decision to enter the snapshot. Live profiles
 are authoritative at snapshot time and for availability; bundled presets are setup
 inputs, not runtime proof.
 
@@ -42,6 +42,9 @@ provider/model/effort substitution.
   High-stakes/trigger: fresh [contract](contracts.md) session.
   `axstack-auditor` audits; `axstack-checker` reports discrepancies.
 - `axstack-explainer`/`axstack-explainer-review`: explain/review.
+- `axstack-ui-verifier`: [UI checks](ui-verification.md).
+- `axstack-research-requirements`/`axstack-research-web`/`axstack-monitor`:
+  Sonnet 5.5 high in mixed/claude-only.
   `axstack-monitor`: standalone watch never sends; chat-run watch: bounded
   internal reports to its Run and original driver.
 - `axstack-debug-investigator-1..4` probe L1 briefs.
@@ -55,18 +58,17 @@ 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.
-- Understanding a system, change, or implementation gap -> `axstack-explain`:
-  current/intended behavior, evidence dimensions, bounded gaps from project docs and
-  rendered behavior. "What could this break" follows
+- Bounded research -> `axstack-research`: verify primary sources and code,
+  cite limits, and fan out distinct questions.
+- Understand a system or gap -> `axstack-explain`:
+  current/intended behavior and bounded gaps from docs and renders.
+  "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
   off a classified repair (explain: how; debug: what's wrong).
-- Codebase-quality or refactor discovery -> `axstack-improve`: inspect bounded
-  scope, rank evidenced candidates, report only; no spec, tickets, or source
-  edits.
+- Code quality/refactor discovery -> `axstack-improve`: rank bounded
+  candidates with evidence; report only, no source edits.
 - 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

package/skills/axstack/references/ui-verification.md

@@ -0,0 +1,13 @@
+# UI verification
+
+Every Playwright, browser, or rendered-UI check, including a "confirm it in the
+browser" step, goes through an Orca Dispatch to `axstack-ui-verifier` from the
+run's role snapshot. Give it the exact build, URL, or artifact and the private
+dispatch's evidence folder. The verifier is read-only: it never edits source.
+The PR writer remains the sole writer.
+
+Ask for screenshots and observed interactions, accessibility, desktop and
+mobile layouts, and reduced-motion behavior where relevant. The verifier
+returns a verdict with evidence paths and names checks it could not run.
+Keep the verdict tied to the exact artifact or revision; changed bytes need a
+fresh rendered pass.

package/skills/axstack-debug/SKILL.md

@@ -39,6 +39,8 @@ recorded reason.
    loop cannot be built, stop, list what was tried, and ask the user for an
    environment, a redacted artifact, or instrumentation permission. Done when
    the command has run once and its red output is recorded.
+   Delegate any L0 or L1 headless-browser reproduction through
+   [UI verification](../axstack/references/ui-verification.md).
 2. **Reproduce and minimise.** Confirm the loop reproduces the user's failure
    and not a neighbour. Remove inputs, callers, config, data, and steps one at
    a time within a stated budget until the repro is the smallest practical;

package/skills/axstack-explain/references/visual-qa.md

@@ -5,11 +5,14 @@ rendering matters.
 
 1. Identify the final artifact bytes and theme. The explicit user theme wins;
    otherwise use the dark default.
-2. Render the final artifact at desktop and mobile widths. Record actual
-   observations for both, or name the missing layout check.
-3. Exercise relevant interactions, keyboard and screen-reader accessibility,
-   and reduced-motion behavior. Report each unavailable check honestly.
-4. Keep source correctness, tests, rendered behavior, independent review, and
-   publication evidence separate.
+2. Delegate the rendered pass through [UI verification](../../axstack/references/ui-verification.md).
+   Record actual desktop and mobile observations, or name the missing layout
+   check.
+3. Have the verifier exercise relevant interactions, keyboard and screen-reader
+   accessibility, and reduced-motion behavior. Report each unavailable check
+   honestly.
+4. The explainer reviewer checks text and source fidelity. Keep source
+   correctness, tests, rendered behavior, independent review, and publication
+   evidence separate.
 5. Bind review to the exact artifact identity. Any byte change invalidates the
    affected approval and requires fresh QA and review.

package/skills/axstack-implement/SKILL.md

@@ -148,8 +148,9 @@ including evidence and retained complexity.
 
 Run the acceptance checks and affected integration boundaries. Record commands,
 observed outputs, and verified states. UI work includes rendered interaction
-evidence when relevant. Name every unavailable OS, harness, credential, or
-other boundary instead of implying coverage.
+evidence through [UI verification](../axstack/references/ui-verification.md)
+when relevant. Name every unavailable OS, harness, credential, or other
+boundary instead of implying coverage.
 
 After the last change, pin the exact candidate revision and return this compact
 implementation receipt to the driver:

package/skills/axstack-review/SKILL.md

@@ -279,7 +279,8 @@ This section applies to peer and authored PR modes.
 
    Verify the applicable spec, ticket, or intent acceptance, executable
    evidence, exact candidate SHA, current base, and affected integration
-   boundary, plus rendered interaction evidence for relevant UI work. A
+   boundary, plus rendered interaction evidence for relevant UI work through
+   [UI verification](../axstack/references/ui-verification.md). A
    passing test is insufficient when it checks the wrong behavior. Call out
    seeded regressions, inadequate checks, and every unverified boundary. Every
    mode-required receipt records concrete evidence and consequences, coverage,