axstack 0.27.1 → 0.27.3

package/docs/host-operations.md

@@ -45,7 +45,7 @@ executor MCP, and live schedule behavior need separate preflights.
 
 Installation creates no production schedule and adds no custom scheduler.
 Every verified own-PR publication arms or joins the driver's chat-run watch.
-Its bound T3 schedule resumes the driver every 5 minutes by default while open PRs stay watched.
+Its bound T3 schedule uses the cadence in [Chat-run watch activation](#chat-run-watch-activation).
 See [Chat-run PR watch](workflows.md#chat-run-pr-watch) for authority, schedule identity and stop conditions.
 Missing schedule capability holds activation.
 The optional review manager uses an unbound 15-minute T3 schedule and requires
@@ -83,7 +83,12 @@ Delivery failure never clears the underlying hold.
 
 ## Chat-run watch activation
 
-A bound T3 schedule resumes the driver thread every 5 minutes by default.
+A bound T3 schedule resumes the driver thread on a 30-minute fallback while
+native PR watches are armed and work and release are settled.
+Unsettled work or release, unavailable or unarmed native watches for any open
+member, or failed re-arming restore five minutes. Human-only waits use 60 minutes
+under [Chat-run watch runtime](../skills/axstack-watch/references/watch-runtime.md#chat-run-watch).
+A T3 "stopped watching" notice triggers a PR re-check and native re-arm in that same turn.
 The run record holds the schedule ID and driver thread.
 Each wake reconciles all unsettled dispatch attempts
 and runs the own-PR maintenance loop: feedback, base movement, required CI,

package/docs/workflows.md

@@ -390,8 +390,8 @@ never sends relay messages.
 Accepted risks: two agents can miss the same defect while CI is green; spec
 approval is the user's main checkpoint. A head guard does not atomically guard
 base freshness; the concurrent-merge race is held by the post-merge push-failure
-rule. A watch waking every 5 minutes (60 when quiet) until PRs land has an accepted
-token cost. Preview code runs under the same VPS user as agents and is not isolated;
+rule. A watch with a 30-minute fallback, 5-minute recovery, and 60-minute human wait
+until PRs land has an accepted token cost. Preview code runs under the same VPS user as agents and is not isolated;
 tests already do, so the added risk is small.
 
 ## Optional native peer-review automation

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "axstack",
-  "version": "0.27.1",
+  "version": "0.27.3",
   "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

@@ -89,6 +89,8 @@ Read the [T3 runtime boundary](t3-runtime.md) and use its bound
 `schedule_task` wake (`everyMs:300000`), recording the scheduledTaskId.
 Follow [Native PR links and watches](t3-runtime.md#native-pr-links-and-watches)
 alongside that bound schedule.
+Apply [Chat-run watch runtime](../../axstack-watch/references/watch-runtime.md#chat-run-watch)
+cadence conditions before ending the turn.
 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/perf-loop.md

@@ -1,9 +1,10 @@
 # Performance loop
 
+The change loop is the ordered steps in this reference, run by `axstack-implement`.
 Keep one writer per candidate.
 The change steps (revert, commit and implement receipt) run only in `axstack-implement`.
 
-Follow this ordered loop:
+Follow these ordered steps:
 
 1. **Freeze and prove sensitivity.**
    Freeze the workload, command and environment before the baseline.

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

@@ -266,18 +266,21 @@ 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.
+A T3 "stopped watching" notice is itself a driver wake: in that same turn,
+re-check the PR and call `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 5-minute schedule
 and `scripts/pr-digest.js` without a hold.
+If re-arming fails, restore the bound 5-minute schedule.
 When the run waits only on a user decision or a human-only step, including a
 user merge, with no unsettled worker and no PR needing watch events, change
 the run watch cadence to 60 minutes at once.
 When work restarts, restore the normal 5-minute cadence.
 Keep native PR watches.
+For chat-run cadence changes, follow [Chat-run watch runtime](../../axstack-watch/references/watch-runtime.md#chat-run-watch)
+for 30-minute fallback eligibility, 5-minute recovery, and schedule update read-back.
 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.

package/skills/axstack-implement/SKILL.md

@@ -87,9 +87,10 @@ Size alone never requires user approval.
 ## 3. Establish test-first evidence
 
 For performance work only, load [Performance loop](../axstack/references/perf-loop.md).
-For performance work, run the change loop.
+For performance work, run the change loop defined in [Performance loop](../axstack/references/perf-loop.md).
 For an accepted optimization scope without new behavior explicitly marked structure-preserving, use the structure-preserving path with the same checks green before and after plus the measured delta.
 For performance work with new behavior, run a failing check first.
+For an optimization not explicitly marked structure-preserving, use the normal behavior path with real red-to-green evidence.
 
 Use the normal behavior path unless the accepted improvement scope is
 explicitly marked **structure-preserving**, or the accepted scope explicitly

package/skills/axstack-watch/SKILL.md

@@ -78,7 +78,8 @@ load. When the watch needs a new owner or automated observation, first read
 [T3 runtime](../axstack/references/t3-runtime.md). Reconcile before creating
 anything. Task-owned observations use their recorded wakes and expiry.
 `axstack-monitor` stays an optional read-only observer for standalone watch
-that never sends. For own open PRs in chat-run mode, wake the driver chat every 5 minutes by default;
+that never sends. For own open PRs in chat-run mode, use the 30-minute fallback when eligible under
+[Chat-run watch runtime](references/watch-runtime.md#chat-run-watch);
 the bound T3 schedule resumes the original driver thread. One read-only PR observation needs
 neither. Start no automation for a read-only check.
 

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

@@ -33,7 +33,7 @@ merge-ready. An own PR published after the watch stops arms a new watch under
 after verified readback, subject to the user's explicit publication boundary.
 
 The initiating T3 thread remains the sole driver and `progress.md` writer.
-Use the bound run watch from [T3 runtime](../../axstack/references/t3-runtime.md):
+Initially use the bound run watch from [T3 runtime](../../axstack/references/t3-runtime.md):
 `schedule_task` with `bindToCurrentThread:true`, `everyMs:300000`, a stable
 `clientRequestId`, and the authorized watch prompt. Record the schedule ID,
 driver thread, chosen mechanism and native schedule lifetime; the watch inherits the driver binding at creation.
@@ -47,8 +47,16 @@ user merge, with no unsettled worker and no PR needing watch events, change
 the run watch cadence to 60 minutes at once.
 When work restarts, restore the normal 5-minute cadence.
 Keep native PR watches.
-On the next event on a watched PR, restore the wake cadence to 5 minutes.
-If launched work becomes unsettled, restore the 5-minute cadence.
+Only while every open watched PR has an armed native `watch_pull_request`, all
+launched work is settled, and the release step is settled or inapplicable, use
+the bound chat-run schedule as a 30-minute fallback (`everyMs:1800000`).
+If native `watch_pull_request` is unavailable or unarmed for any open member,
+or re-arming fails, restore the bound chat-run schedule to 5 minutes (`everyMs:300000`).
+On the next event on a watched PR, re-evaluate the wake cadence against the
+fallback conditions in the same turn.
+If launched work or the release step becomes unsettled, restore the 5-minute cadence (`everyMs:300000`).
+Apply these conditions before ending each driver turn, including after initial
+arming or a work restart; the 60-minute human-only wait rule above still applies.
 Read back each schedule update and record its receipt; an uncertain update holds affected work.
 Each wake reconciles all unsettled runs before running the authorized maintenance loop.
 A failed run holds incomplete work even when its writer sent no receipt.