axstack 0.16.0 → 0.18.0

package/README.md

@@ -77,7 +77,7 @@ targets are reported without normal-path adoption. Install exits nonzero when
 an instruction conflict is preserved, while clean and idempotent installs exit
 successfully.
 
-The public bundle preserves three canonical 23-role inputs:
+The public bundle preserves three canonical 25-role inputs:
 [mixed](profiles/presets/mixed.json),
 [codex-only](profiles/presets/codex-only.json), and
 [claude-only](profiles/presets/claude-only.json). Each is exactly
@@ -90,9 +90,10 @@ Mixed configures independent Astra and Fable advisers at high. Single-provider
 presets preserve both adviser IDs and mark the unavailable one with `model:
 null` inside that preset's provider bounds; installation remains ready, while
 Align and Spec hold because both receipts are required. The mixed
-`axstack-checker` model is also intentionally `null`; that role stays held
-instead of inheriting a provider default. The single-provider presets configure
-the checker. Preset changes affect new runs only. Stored model, effort, and permission
+`axstack-checker` and `axstack-research-web-google` roles launch Antigravity by
+agent ID with explicit `model: null`; the run records the model reported by the
+TUI. The single-provider presets configure the checker and record the Google
+research branch as intentionally absent. Preset changes affect new runs only. Stored model, effort, and permission
 fields are declared intent until actual Orca launch receipts establish effective
 behavior; installation never proves provider availability or permission parity.
 Subscription availability and quota never select a fallback model.

package/docs/installation.md

@@ -51,7 +51,7 @@ profiles/presets/codex-only.json
 profiles/presets/claude-only.json
 ```
 
-Each has exactly `{ "version": 1, "roles": [...] }` with the same 23 stable
+Each has exactly `{ "version": 1, "roles": [...] }` with the same 25 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
@@ -118,9 +118,11 @@ The complete bundle is validated before writes:
 - each preset is a real JSON file with version 1, a non-empty `roles` array,
   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 and, in each
-  single-provider preset, the unavailable adviser and its matching arena judge
-  seat explicitly permit `model: null`;
+- every role has valid preserved fields, while the mixed checker,
+  `axstack-research-web-google`, and `axstack-research-x` 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;
 - obsolete runtime configuration flags fail before mutation with migration
   guidance.
 
@@ -148,12 +150,16 @@ 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 23 role rows. An active run keeps
+A new run records the selected preset plus all 25 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 checker has `model: null`; checker dispatch is held and never inherits
-a provider default. The single-provider presets configure the checker. Their
+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;
+their notes authorize launch by agent ID, and the run record snapshots the model
+reported by the TUI. The single-provider presets configure the checker and keep
+both cross-provider research routes as intentional absences. Their
 unavailable adviser and its matching arena judge seat remain explicit
 same-provider `model: null` roles, which do not make installation unready;
 Align and Spec still hold until both Astra and Fable can return independent

package/docs/workflows.md

@@ -40,7 +40,7 @@ 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 23 stable IDs.
+`{ "version": 1, "roles": [...] }` and the same 25 stable IDs.
 
 The current chat drives on whatever model runs it; no preset carries a driver
 role.
@@ -63,8 +63,10 @@ selected preset.
 The unavailable adviser in each single-provider preset stays explicitly
 `model: null` within that provider's bounds. Installer readiness accepts that
 intentional absence, but Align and Spec hold because both independent receipts
-are required. The mixed checker also stays explicitly `model: null`; checker work holds instead of
-launching a provider default. Missing or unavailable roles hold only affected
+are required. The mixed checker and Google web-research route use provider
+`antigravity`; the X route uses `grok`. Launch-by-agent-id routes for which Orca
+exposes no model override (today: `grok`, `antigravity`) record `model: null` with an explicit note and are
+launchable; the run record snapshots the model the TUI reports. Missing or unavailable roles hold only affected
 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,

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "axstack",
-  "version": "0.16.0",
+  "version": "0.18.0",
   "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

@@ -91,6 +91,24 @@
       "thinkingOptionId": "low",
       "notes": "Research web reader: gathers primary-source facts efficiently. Validate configured availability at launch; hold affected work without fallback."
     },
+    {
+      "id": "axstack-research-web-google",
+      "name": "Axstack research web (Google unavailable)",
+      "provider": "claude",
+      "model": null,
+      "modeId": "bypassPermissions",
+      "thinkingOptionId": "high",
+      "notes": "Intentional single-provider absence: Google-Search-grounded web research via Gemini/Antigravity is unavailable in claude-only. The explicit null holds this route without provider substitution."
+    },
+    {
+      "id": "axstack-research-x",
+      "name": "Axstack research X (unavailable)",
+      "provider": "claude",
+      "model": null,
+      "modeId": "bypassPermissions",
+      "thinkingOptionId": "high",
+      "notes": "Intentional single-provider absence: X/Twitter research via Grok is unavailable in claude-only. The explicit null holds this route without provider substitution."
+    },
     {
       "id": "axstack-explainer",
       "name": "Axstack explainer",

package/profiles/presets/codex-only.json

@@ -91,6 +91,24 @@
       "thinkingOptionId": "low",
       "notes": "Research web reader: gathers primary-source facts efficiently. Validate configured availability at launch; hold affected work without fallback."
     },
+    {
+      "id": "axstack-research-web-google",
+      "name": "Axstack research web (Google unavailable)",
+      "provider": "codex",
+      "model": null,
+      "modeId": "full-access",
+      "thinkingOptionId": "high",
+      "notes": "Intentional single-provider absence: Google-Search-grounded web research via Gemini/Antigravity is unavailable in codex-only. The explicit null holds this route without provider substitution."
+    },
+    {
+      "id": "axstack-research-x",
+      "name": "Axstack research X (unavailable)",
+      "provider": "codex",
+      "model": null,
+      "modeId": "full-access",
+      "thinkingOptionId": "high",
+      "notes": "Intentional single-provider absence: X/Twitter research via Grok is unavailable in codex-only. The explicit null holds this route without provider substitution."
+    },
     {
       "id": "axstack-explainer",
       "name": "Axstack explainer",

package/profiles/presets/mixed.json

@@ -58,11 +58,11 @@
     {
       "id": "axstack-checker",
       "name": "Axstack Linear checker",
-      "provider": "codex",
+      "provider": "antigravity",
       "model": null,
       "modeId": "full-access",
       "thinkingOptionId": "low",
-      "notes": "Report-only Linear discrepancy checker. Never mutates Linear; 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 Linear discrepancy checker. Never mutates Linear; the driver independently verifies evidence before applying updates. Cheap report-only seat on Gemini Flash; launch by agent id antigravity."
     },
     {
       "id": "axstack-research-requirements",
@@ -91,6 +91,24 @@
       "thinkingOptionId": "low",
       "notes": "Research web reader: gathers primary-source facts efficiently. Validate configured availability at launch; hold affected work without fallback."
     },
+    {
+      "id": "axstack-research-web-google",
+      "name": "Axstack research web (Google)",
+      "provider": "antigravity",
+      "model": null,
+      "modeId": "full-access",
+      "thinkingOptionId": "high",
+      "notes": "Google-Search-grounded web research branch on Gemini via the Antigravity CLI; launch by agent id antigravity; model selected by the TUI default (Gemini 3.8 Flash High observed 2026-09-19; ids from agy models: gemini-3.8-flash-{low,medium,high}, gemini-3.1-pro-{low,high}); cites URL + access date per claim and re-opens sources because the CLI's search citation format is undocumented; report-only."
+    },
+    {
+      "id": "axstack-research-x",
+      "name": "Axstack research X",
+      "provider": "grok",
+      "model": null,
+      "modeId": "full-access",
+      "thinkingOptionId": "high",
+      "notes": "X/Twitter-only research branch: Grok can read X; use for questions where posts, threads, announcements, or sentiment on X are answer-changing evidence. Cites post URLs and dates; never the sole source for a verified claim; report-only, no writes. Launch by agent id grok; model selected by the Grok TUI default."
+    },
     {
       "id": "axstack-explainer",
       "name": "Axstack explainer",

package/skills/axstack/references/lifecycle.md

@@ -128,13 +128,14 @@ nothing without tested independent review.
 
 ## Close-out
 
-After required PRs merge by forge state—not local branch ancestry—close out in
-order: (1) settle every worker terminal through the orchestration guide; (2)
-write a compact record with counts and denominators for
-user interventions, deviations from plan, and repairs; (3) dispatch
-`axstack-auditor` only when any count is non-zero or the user asks—an unavailable
-auditor leaves close-out pending, never skipped silently; (4)
-release merged run worktrees and branches and close Linear tickets
-(driver-owned); (5) mark the [Run record](run-record.md) `Archived`. The driver
-cannot report the run done before steps (1)-(5) have receipts. Small one-step
-lookups keep the run record's exemption.
+PRs merge by forge state—not branch ancestry; close out: (1) settle every worker
+terminal; (2) compact record with counts and denominators—user
+interventions/deviations from plan/repairs; (3) `axstack-auditor`: settle
+non-zero/requested, else `counts zero`; an unavailable auditor leaves close-out
+pending, never skipped silently; (4) release merged run worktrees and branches;
+close Linear tickets; (5) mark the [Run record](run-record.md) `Archived`.
+`Archived`—one each:
+settlement receipt; compact record path; auditor decision plus settlement
+receipt or `counts zero`; release and ticket receipts; archive timestamp.
+`active`/receipt-incomplete record: close-out pending, never done. One-step
+lookups exempt.

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

@@ -26,11 +26,13 @@ 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 23 role rows once. An active run keeps the exact snapshot until the user
+all 25 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;
-never launch a provider default. Validate provider, model, and effort
+never launch a provider default. Launch-by-agent-id routes for which Orca exposes no
+`--model` override (today: `grok`, `antigravity`) record `model: null` with an explicit note and are
+launchable; the run record snapshots the model the TUI reports. Validate provider, model, and effort
 against the guide and actual launch capability. Stored `modeId` and other
 permission fields are conservative intent, not proof of effective permission
 parity or a security boundary. Requested settings, input acceptance, effective

package/skills/axstack/references/routing.md

@@ -11,7 +11,7 @@ only with exactly 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, capture one **routing snapshot**: the complete map of all 23 role
+At run start, capture one **routing snapshot**: the complete map of all 25 role
 IDs with provider/model/mode/effort, absent or unconfigured roles recorded
 explicitly, and no invented provider default. An absent or unconfigured role
 holds only that role's work, not the run. A role installed or changed later

package/skills/axstack-align/SKILL.md

@@ -18,8 +18,15 @@ This preserves the required contracts -> lifecycle -> audit load edge.
 
 1. **Research and map dependencies.** Inspect the available code, docs, and
    tools before asking the user. Separate facts from preferences, name evidence
-   gaps, and map which decisions unlock others. Unresolved research blocks only
-   its dependent branch while safe fact work and independent branches continue.
+   gaps, and map which decisions unlock others. When a fact needed for the
+   frontier is not derivable from the local repo or docs by ordinary reading,
+   dispatch `axstack-research` branches through Orca by source type:
+   requirements, code, web, and, once configured, X. Give one owner per branch,
+   use cross-harness routes where the roles allow, and require a cited note per
+   the research skill's source standards. The driver folds verified claims into
+   the frontier and records the receipts. Ordinary reading stays in-chat; a
+   single factual lookup never dispatches. Unresolved research blocks only its
+   dependent branch while safe fact work and independent branches continue.
 2. **Prioritize the ready frontier.** Rank questions whose prerequisites are
    settled by consequence, uncertainty, and the branches they unlock. Probe
    vague terms, assumptions, success criteria, exclusions, failures, and edge

package/skills/axstack-research/SKILL.md

@@ -24,18 +24,23 @@ is part of research.
    question in one run; separate only genuinely independent questions. Start
    gathering evidence only after the target and stopping boundary are explicit.
 
-2. **Choose the smallest route.** Handle a single factual lookup directly in
-   the current chat. Use a profile only when its specialization or independent
-   work is useful. Before an actual dispatch, read and follow the
-   [Orca runtime boundary](../axstack/references/orca-runtime.md). Give each
-   research branch one owner; keep implementation out of every branch.
-
-   These routes are data presets, not proof of live readiness. Confirm profile
-   availability through the shared launch sequence:
+2. **Fan out research:** A single factual lookup stays in the current chat.
+   Every other research run dispatches every configured research branch through
+   Orca: requirements (Claude), code (Codex), web (Claude), web-google
+   (Gemini/Antigravity, with Google Search built in), and X (Grok).
+   Give each branch one owner, allow no cross-reading, and require a cited note
+   with a URL and access date per claim; re-open sources and never trust a search
+   summary. The driver reconciles agreements/disagreements per claim.
+   An unconfigured or unavailable branch is recorded as absent, never substituted.
+   These routes are data presets, not proof of live readiness; before dispatch,
+   follow the [Orca runtime boundary](../axstack/references/orca-runtime.md),
+   confirm availability, and keep implementation out of every branch:
 
    - `axstack-research-requirements`: requirements and intent.
    - `axstack-research-code`: code behavior.
    - `axstack-research-web`: web and external sources.
+   - `axstack-research-web-google`: Google-Search-grounded web sources via Gemini/Antigravity.
+   - `axstack-research-x`: X (Twitter) posts and threads via Grok; cite post URLs and dates.
    - `axstack-explore-codebase`: broad codebase mapping.
    - `axstack-explore-execution`: execution and runtime traces.
 

package/skills/axstack-review/SKILL.md

@@ -39,7 +39,7 @@ head and current base, and writing authority are recorded.
 
 Independently check the
 [proportional scope identity](../axstack/references/routing.md#proportional-scope-identity)
-before an approval or merge-ready declaration:
+before an approval or [merge-ready declaration](#authored-mode-own-pr):
 
 - Substantial new work: confirm the approved spec identity and matching ticket
   map.
@@ -49,9 +49,12 @@ before an approval or merge-ready declaration:
   author provenance. Never assume an imported own PR's author. That
   snapshot is accepted without repeated approval.
 
-The mode is ready when the applicable identity matches the candidate and no
-material scope change remains unaccepted. Readonly investigation may continue
-while an identity gap holds declarations.
+The mode is ready when the applicable identity matches the candidate, no
+material scope change remains unaccepted, and an independent review receipt
+records `APPROVE` from the required non-author, non-owner reviewer at the exact
+current head. Green CI, passing tests, or an older-head receipt leave readiness
+`UNKNOWN`, never merge-ready. Readonly investigation may continue while an
+identity gap holds declarations.
 
 Resolve actual author provenance from authoring session receipts and candidate
 history. The orchestrator model, provider, profile, or owner name is not author
@@ -244,7 +247,8 @@ Escalate to user: <yes | no> — <criterion> — <reason>
 At any point, promptly raise credible serious security issues, possible
 downtime or data loss, and major design concerns without waiting for every
 mode-required reviewer. Present evidence, likely impact, options, and the user
-decision needed. An urgent hold blocks approval, merge-ready declarations, and
+decision needed. An urgent hold blocks approval,
+[merge-ready declarations](#authored-mode-own-pr), and
 dependent dangerous actions, but does not block safe investigation, unrelated
 work, or reporting validated risk as `REQUEST_CHANGES`. Disagreement and
 silence leave the hold open.
@@ -267,7 +271,7 @@ without waiting; `proceed` never overrides a validated blocking finding.
 ## Publishing rule
 
 Mode-required exact-revision completeness gates external approval,
-merge-ready declarations, and authorized submission. It never gates returning
+[merge-ready declarations](#authored-mode-own-pr), and authorized submission. It never gates returning
 evidence, limitations, validated risk, or an internal `INCOMPLETE` report.
 
 - Peer mode requires both current reviews and no unresolved material finding

package/skills/axstack-watch/SKILL.md

@@ -6,7 +6,8 @@ description: When babysitting an existing PR, use axstack-watch to monitor or ma
 # Watch
 
 Leave each adopted PR with one accountable owner, current readiness evidence,
-and a bounded watch that ends cleanly or preserves enough state to resume.
+and user-facing updates that name its current milestone and next wake or
+condition.
 
 Before acting, load [Standing contracts](../axstack/references/contracts.md).
 Its required edge loads [Shared lifecycle](../axstack/references/lifecycle.md),
@@ -79,14 +80,17 @@ no children or recursive teams, and the adoption watcher is never the writer.
 
 A live watch has verified role and timer receipts, handshakes, watched scope,
 wake ownership, and a common expiry. A missing runtime capability is a setup gap,
-not a reason to invent a call or create a duplicate registration. Wait through
-native wake-ups; no model remains active between events.
+not a reason to invent a call or create a duplicate registration. Native
+wake-ups drive observation; never poll or keep a model active between events.
 
 ## 4. Route each wake
 
 Re-read the remote head and base, then reconcile the event against acknowledged
 IDs and the recorded mode. A changed head, CI result, or review comment is an
 event, not repair authority. Stale or ambiguous observations authorize nothing.
+Every user-facing update is actionable: name the current milestone, the next
+wake or condition, and an ETA when the forge exposes one, such as CI median.
+A healthy unchanged observation produces no user-facing message.
 
 Observation-only and peer wakes produce a read-only report and stop. For an
 authorized maintenance wake that may require a repair or public reply, read and

package/src/roles.js

@@ -1,5 +1,5 @@
 const PROVIDER_BOUNDS = Object.freeze({
-  mixed: new Set(['codex', 'claude']),
+  mixed: new Set(['codex', 'claude', 'grok', 'antigravity']),
   'codex-only': new Set(['codex']),
   'claude-only': new Set(['claude']),
 });
@@ -63,9 +63,11 @@ export function assessRoleReadiness(roles, preset) {
   const byId = new Map(roles.map((role) => [role.id, role]));
   const gaps = [];
   const isIntentionalAbsence = (role) => role.model === null && (
-    (preset === 'mixed' && role.id === 'axstack-checker') ||
-    (preset === 'codex-only' && ['axstack-advisor-fable', 'axstack-arena-judge-fable'].includes(role.id)) ||
-    (preset === 'claude-only' && ['axstack-advisor-astra', 'axstack-arena-judge-astra'].includes(role.id))
+    (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))
   );
   for (const role of roles) {
     if (!bounds.has(role.provider)) {