@sjawhar/pi-legion 19.16.0 → 19.16.1

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
package/dist/legion.js CHANGED
@@ -28544,7 +28544,7 @@ import { logger as logger3 } from "@oh-my-pi/pi-utils";
28544
28544
  // package.json
28545
28545
  var package_default = {
28546
28546
  name: "@sjawhar/pi-legion",
28547
- version: "19.16.0",
28547
+ version: "19.16.1",
28548
28548
  license: "Apache-2.0",
28549
28549
  type: "module",
28550
28550
  omp: {
@@ -103,18 +103,10 @@ on the pod, so the round does not wait for it. Its retry is the architect's or t
103
103
  for any failed role, and yours once the architect escalates the hold
104
104
  ([An escalated hold](#an-escalated-hold)). A retried claim is asked like any other.
105
105
 
106
- Before it replaces the pod, the daemon checks every workspace on the pod's disk for the issue's
107
- own work the remote lacks, a failed claim's included, and pushes it to the issue's one rescue
108
- branch, `legion/<KEY>-rescue`, which only moves forward. When it found work the issue branch
109
- does not have, it writes the issue a message: a short summary of each branch and its commits,
110
- and a link to an artifact of the issue with the full list, for the issue's roles to merge into
111
- the issue branch. A pod of an older image pushes to branches of its own,
112
- `legion/<KEY>-rescue-<pod>-<n>`, which can hold commits of another session and of another
113
- issue. Its message says so in the same shape, and tells the issue's roles to read each commit
114
- on such a branch and take only the commits they need into the issue branch. That message asks
115
- nothing of you. A pod whose shim is older than the check is replaced unchecked, and the daemon
116
- writes that on the issue. Everything else of the pod's disk goes with the pod: the round's
117
- message tells each role to put any scratch evidence it still needs on Dispatch before it
106
+ Before it replaces the pod, the daemon reads nothing of the pod's disk. A role's own push is
107
+ what keeps its work: work a role did not push before the pod goes, a failed claim's included,
108
+ goes with the pod, and its agent does it again in the new one. The round's message tells each
109
+ role to push its work and to put any scratch evidence it still needs on Dispatch before it
118
110
  answers.
119
111
  One round wakes you once, however many sweeps find it open, so handle it when it arrives.
120
112
  Read `read_state` and the issue first, as for every wake: a round that finished since needs
@@ -125,7 +117,6 @@ Take the wake by what its `reason` names:
125
117
  | `reason` names | What holds the round | What you do |
126
118
  |---|---|---|
127
119
  | an operator's suspension | An operator suspended a role the round asked. The daemon does not replace the pod until the operator resumes each such role, whatever the bound. | Open a finding ask naming the issue and each suspended role, so the operator resumes it. |
128
- | a failed check for unpushed work | The check or a push failed for a workspace, so the daemon did not replace the pod. `reason` names the claim the check ran through, each workspace and its error. | Open a finding ask naming the issue, the round and `reason`, with each workspace and its error, so an operator reads the pod. |
129
120
  | a refused pod replacement | The runtime refused `ReplacePod`. The daemon tries again at each sweep. | Open a finding ask naming the issue, the round and the `ReplacePod` error, so an operator reads the pod. |
130
121
  | no process in the pod | No claim of the issue records a process in the round's pod, or in any pod, so the daemon has nothing to replace the pod through. The round waits for a role of the issue to run again. | Open a finding ask naming the issue, the round and `reason`, so an operator reads the pod. |
131
122
  | two pods | The claims of the issue record two pods, so a replacement is in flight, and the round waits for it. | Open a finding ask naming the issue, the round and `reason`, so an operator reads the pod. |
@@ -408,8 +408,7 @@ records you were sent in it.
408
408
  ## `update-stalled on <KEY>` (`{kind: "update-stalled", reason, update}`)
409
409
 
410
410
  The update round over the issue's pod has passed its bound, and something still holds it: an
411
- operator's suspension, a failed check for unpushed work, a refused pod replacement, no process in
412
- the pod, or two pods. Handle it as
411
+ operator's suspension, a refused pod replacement, no process in the pod, or two pods. Handle it as
413
412
  `skill://legion-controller/references/escalation.md#an-update-round-that-is-not-finishing-update-stalled`
414
413
  says.
415
414
 
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@sjawhar/pi-legion",
3
- "version": "19.16.0",
3
+ "version": "19.16.1",
4
4
  "license": "Apache-2.0",
5
5
  "type": "module",
6
6
  "omp": {