axstack 0.25.1 → 0.25.2

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "axstack",
-  "version": "0.25.1",
+  "version": "0.25.2",
   "description": "Axstack installer and setup CLI: installs owned chat skills and role data, configures supported harness settings, and checks T3 Code capabilities.",
   "keywords": [
     "claude-code",

package/skills/axstack/references/autopilot.md

@@ -67,6 +67,8 @@ The driver remains the single owner and sole run-record writer.
 Never create a per-PR session or an ownership hand-off.
 Read the [T3 runtime boundary](t3-runtime.md) and use its bound
 `schedule_task` wake (`everyMs:600000`), recording the scheduledTaskId.
+Follow [Native PR links and watches](t3-runtime.md#native-pr-links-and-watches)
+alongside that bound schedule.
 An explicitly adopted PR joins only with its maintenance snapshot.
 The original driver alone routes work; one author writes each
 candidate. Until a PR is merge-ready, wakes feed implement §6 step 4. After

package/skills/axstack/references/candidate-publication.md

@@ -44,6 +44,8 @@ its required checks complete. Review may run in parallel with CI only after the
 remote confirmation. Reviewers inspect a detached immutable checkout of the
 confirmed candidate SHA and pinned base, never only the movable branch name.
 Any author repair creates a new revision and repeats this boundary.
+After verified publication readback, follow
+[Native PR links and watches](t3-runtime.md#native-pr-links-and-watches).
 
 ## Revert line
 

package/skills/axstack/references/routing.md

@@ -85,7 +85,14 @@ step (3) for user routing: no substitution or same-provider review.
 - 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` observation-only
-  mode. Explicit "address", "patch", or "fix" grants authorized maintenance.
+  mode when it does not ask to watch.
+- A user request to watch, babysit, keep watching, maintain, address, patch, or fix
+  own PRs authored by the authenticated `gh api user` login or the user's agents
+  grants authorized maintenance by default.
+  Snapshot the maintenance intent once without extra approval.
+  Observation-only applies only to explicit observe-only requests, status
+  questions without a watch request, or peers' PRs.
+  Explicit observe-only includes "monitor only" or "do not change anything".
 - 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`

package/skills/axstack/references/t3-runtime.md

@@ -9,7 +9,8 @@ delegated tasks, messaging and native schedules.
 The driver must be a T3 thread, save `orchestrator_capabilities` JSON under
 the run record, and follow the advertised tool schema; discovery alone proves
 neither provider readiness nor successful execution. Missing capability holds
-the affected operation, without a substitute runtime.
+the affected operation, without a substitute runtime. Native PR watch absence
+uses the schedule fallback below.
 
 From installed `skills/axstack/roles.json`, the driver must snapshot the selected
 preset and stable role IDs, requested provider/model/class/mode/effort, resolved
@@ -224,6 +225,31 @@ Once nothing remains unsettled the driver must `delete_scheduled_task` for the
 run watch and use `list_scheduled_tasks` to read back its absence; an uncertain
 delete preserves the hold and recorded ID.
 
+## Native PR links and watches
+
+After verified publication readback or adoption of an own PR, the driver calls
+`link_pull_request` with the full PR URL for every layer of a `gh stack`.
+Before finishing PR work, including watch end or Close-out, the driver calls
+`list_thread_pull_requests` and links every missing run PR.
+Never link unrelated PRs.
+
+For every watched own PR in chat-run or standalone adopted maintenance, when
+available the driver calls `watch_pull_request` for T3 wakes on check completion,
+new comments from others, or branch conflicts, then ends the turn.
+Never poll or keep a model active between native PR wake events.
+When T3 reports it stopped watching a PR, the next wake re-checks the PR and
+calls `watch_pull_request` again.
+This includes a stop after T3 could not read the PR for 15 minutes.
+Route native PR wake events through watch §4 and the unchanged §5 readiness predicate.
+
+If `watch_pull_request` is unavailable, fall back to the bound 10-minute schedule
+and `scripts/pr-digest.js` without a hold.
+Keep the schedule cadence unchanged while a native PR watch is active,
+including the existing 7-day quiet relaxation.
+The schedule still reconciles author and review tasks, readiness, and release.
+When a PR merges or closes, or its watch is torn down, call `unwatch_pull_request`
+and keep its link.
+
 ## Evidence, prompts and authority
 
 Put the [Safe-deletion rule](workspace-hygiene.md#safe-deletion) in every worker brief.

package/skills/axstack-watch/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: axstack-watch
-description: When babysitting an existing PR, use axstack-watch to monitor or maintain it within bounded authority.
+description: When babysitting an existing PR, use axstack-watch to maintain own PRs by default within bounded authority.
 ---
 
 # Watch
@@ -37,20 +37,21 @@ live owner and watch; uncertain state holds new registrations until resolved.
 
 For an existing own PR, read the
 [proportional scope identities](../axstack/references/routing.md#proportional-scope-identity),
-verify writable ownership and user maintenance authority, then snapshot the
+apply its default maintenance rule and verify writable ownership, then snapshot the
 accepted maintenance intent once: authorized scope, actual head and base,
 current owner, actual author provenance, and watch state. Check authoring
 session evidence; the orchestrator identity is not author evidence, and never
 assume an author for an imported own PR. It needs no new spec, ticket, or repeated
-approval. Monitoring-only adoption grants no repair or reply authority.
+approval. Explicit observation-only adoption grants no repair or reply authority.
 
 Adoption is settled when the record names one persistent owner, one watch, the
-exact PR revision and base, and the applicable authority snapshot. If write
-authority is unverified, record the hold and continue read-only.
+exact PR revision and base, and the applicable authority snapshot. If writable
+access is unverified, record the hold and continue read-only; pushing stays held.
 
 ## 2. Fix the operating mode
 
-Choose one mode from the user's authority and record it before dispatch:
+Choose one mode under [Shared routing](../axstack/references/routing.md#direct-routes-no-spec-ceremony)
+and record it before dispatch:
 
 - **Chat-run watch:** authorized maintain mode is the default for run-created
   PRs. The initiating chat remains the only driver and record
@@ -63,7 +64,8 @@ Choose one mode from the user's authority and record it before dispatch:
   repair path, including obvious fixes after changed heads or feedback.
 - **Peer:** observe and report a colleague's PR. Peer mode never repairs.
 - **Authorized maintenance:** repair an adopted own PR only within the accepted
-  maintenance snapshot and publication authority.
+  maintenance snapshot and publication authority; own-PR watch requests use this
+  mode by default under Shared routing.
 
 Every later wake must be classifiable from this recorded mode without inferring
 new authority.
@@ -87,7 +89,8 @@ create no recursive teams, and the adoption watcher is never the writer.
 
 A standalone 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. Native
+subject to the [native PR watch fallback](../axstack/references/t3-runtime.md#native-pr-links-and-watches).
+Never 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
@@ -114,11 +117,14 @@ snapshot. Missing, stale, or materially changed identity holds repair routing
 while monitoring continues. Accepted fixes return to the same original author
 session only when the run itself launched that session and evidence allows,
 then receive refreshed review under the authored mode rule before publication.
-For an adopted own PR, the authored-review pairing follows the recorded
-actual provenance of its repair author, not the PR's historical author.
-Unknown, mixed, or unsupported author provenance
-that cannot establish the eligible configured reviewer is an exact gap to
-report to the user, not permission to invent a pairing or model fallback.
+If this run did not launch the original author, or historical provenance is
+unknown or mixed, launch a new configured `axstack-author` attempt under
+[Shared routing](../axstack/references/routing.md).
+For an adopted own PR, pair the authored reviewer from the recorded actual
+provenance of its repair author.
+Hold only when the repair author's own provenance cannot be established or
+an eligible configured reviewer is unavailable; report that exact gap.
+Historical provenance still follows §5's merge-card rule.
 
 A handled wake has an acknowledged event ID, an observation or action bound to
 the current revision, and a recorded hold or next owner where work remains.
@@ -307,6 +313,9 @@ merge result is a run-wide hold on further automated merges until resolved.
 
 ## 6. End and preserve continuity
 
+Reconcile PR links and stop native PR watches under
+[T3 runtime](../axstack/references/t3-runtime.md#native-pr-links-and-watches).
+
 End a chat-run watch only after all members merged or closed, launched work is settled,
 and the run's release step is settled or not applicable, or user cancellation.
 Without an Autopilot or Release record, the release step is not

package/skills/axstack-watch/references/repair-publication.md

@@ -15,10 +15,9 @@ stale, or materially changed boundary holds the repair while read-only
 monitoring continues.
 
 Record the exact defect, allowed files and actions, current revision, feedback
-IDs, and actual author without expanding scope. If actual author information is
-unknown, mixed, or unsupported and cannot establish an eligible configured
-reviewer, report that exact gap and ask the user; do not assume an author from
-the importing owner or orchestrator.
+IDs, and actual author without expanding scope.
+Follow [Feedback routing](../SKILL.md#feedback-routing) to launch an adopted
+repair author and pair its reviewer.
 
 ## 2. Produce a reviewable candidate
 

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

@@ -2,6 +2,9 @@
 
 Read this before starting, resuming, or stopping automated PR observation.
 
+Follow [Native PR links and watches](../../axstack/references/t3-runtime.md#native-pr-links-and-watches)
+for linking, event wakes, re-watching, fallback, and teardown in both watch modes.
+
 For each own PR, the owner must follow [PR previews](../../axstack/references/preview.md)
 when deciding on a preview, restarting it after a head change, or tearing it down.
 
@@ -98,7 +101,8 @@ Quiet ticks never notify.
 
 The driver alone routes repair.
 The driver routes rebases and review feedback to the PR's author for repair.
-For an adopted PR whose author this run did not launch, use a new author attempt under the adoption rules.
+For an adopted PR whose author this run did not launch, use a new author attempt under the
+[adoption rules](../SKILL.md#feedback-routing).
 The watch never writes candidate source.
 Re-read remote head/base and T3 ownership.
 Independent PRs may repair in parallel in separate T3 writer worktrees within