@ssheleg/agent-stack 0.13.0 → 0.13.1

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/CHANGELOG.md CHANGED
@@ -1,5 +1,27 @@
1
1
  # Changelog
2
2
 
3
+ ## v0.13.1 — a citation into the manifesto is a phrase
4
+
5
+ Five references into the manifesto had rotted, and every rule they named was
6
+ intact — the worst shape a dead citation takes, because it still reads as a
7
+ receipt. `manifesto.md:419-422`, which this pack cited as the home of the four
8
+ priority axes, now holds *"The strongest is mechanical"*; the axes moved twenty
9
+ lines down when the document grew.
10
+
11
+ Converted to phrase anchors, each verified unique in the subject:
12
+ `:156` → *"one input, one job, one output, one owner, and its own completion
13
+ test"*, `:114` → *"you cannot connect it to the evidence graph later without
14
+ inventing the test"*, `:122` → *"The evidence graph says how the result will be
15
+ known"*, `:419-422` → *"How many agents, repositories, services, and owners meet
16
+ at the change"*, `:424` → *"These axes are not a fake numerical score"*.
17
+
18
+ `PRIORITY_AXES_SOURCE` was a constant holding one of the dead addresses; it holds
19
+ the phrase now.
20
+
21
+ Swept from the umbrella's conformance register in the same pass — R-003, run the
22
+ fix against its siblings rather than its instance. `seo-aeo-audit` got the four
23
+ axes this pack already had, in the other direction, on the same day.
24
+
3
25
  ## v0.13.0 — 2026-08-20 — the audit refused a score and computed one
4
26
 
5
27
  `references/audit.md` said *"a prioritized change plan … **not** a score"* at `:20`, argued
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@ssheleg/agent-stack",
3
- "version": "0.13.0",
3
+ "version": "0.13.1",
4
4
  "scripts": {
5
5
  "test": "python3 test/validate.py && python3 test/plant_guard_test.py"
6
6
  },
@@ -1,8 +1,8 @@
1
1
  {
2
2
  "name": "agent-stack",
3
3
  "displayName": "Agent Stack",
4
- "description": "Two skills: agent-orchestrator \u2014 tool-calling loops, multi-stage pipelines with checkpoints, provider routing with fallback, four-layer memory, context engineering, plus the wallet side of reselling LLM access; and agent-evals \u2014 run/trace/thread evals, judges, and fixtures grown from production.",
5
- "version": "0.13.0",
4
+ "description": "Two skills: agent-orchestrator tool-calling loops, multi-stage pipelines with checkpoints, provider routing with fallback, four-layer memory, context engineering, plus the wallet side of reselling LLM access; and agent-evals run/trace/thread evals, judges, and fixtures grown from production.",
5
+ "version": "0.13.1",
6
6
  "author": {
7
7
  "name": "ssheleg",
8
8
  "url": "https://x.com/sshlg93"
@@ -125,8 +125,8 @@ needs.
125
125
  <!-- priority-axes: impact, irreversibility, uncertainty, coordination -->
126
126
 
127
127
  So the inputs are published and the arithmetic is not. The axes are the manifesto's four
128
- (`~/DATA/pod-manifesto/manifesto.md:419-422`, under *these axes are not a fake numerical
129
- score* at `:424`), and two of them were absent here entirely while `effort` — a **cost**,
128
+ (`manifesto` *"How many agents, repositories, services, and owners meet at the
129
+ change"*, under *"These axes are not a fake numerical score"*), and two of them were absent here entirely while `effort` — a **cost**,
130
130
  not a risk axis — had been substituted into their place:
131
131
 
132
132
  | Axis | Question | High · Medium · Low |