@mindrian_os/cli 1.14.0-beta.1 → 1.14.0-beta.3

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
@@ -1,7 +1,27 @@
1
+ ## [1.14.0-beta.3] - 2026-06-19
2
+
3
+ ### Added
4
+ - **Phase 164 -- BONO research/debate engine (`/mos:bono`).** Assembles a de Bono six-hats team across (subdomain x hat) cells, runs an inter-hat debate on your hypothesis, and files structured findings as proposed truth-claim nodes. Mints the `SyntheticExpert` node type so a high-value team member can be saved and re-invoked as a hat in future runs (human-confirmed per Canon Part 9 role 5). Phase gate `tests/run-all-164.sh` 20/20; adversarial verdict 13/13.
5
+ - **Phase 165 -- unknown-unknowns blind-spot engine (backs `/mos:map-unknowns`).** A Horvitz et al. 2019 recast that hunts the claims you are most confident about and confidently wrong: a DSP partitioner + deterministic UCB bandit + Rumsfeld 2x2 router + LOCAL proxy oracle, all zero-Brain-egress, that halts at the F.1 Decision Gate. Proven by instrumentation: `tests/run-all-165.sh` 19/19, adversarial verdict 5/5, Part-8 boundary 8/8.
6
+ - **Phase 163 -- trending-to-the-absurd harness (`/mos:trending-to-absurd`).** The visionary-innovation companion that pushes trends to the absurd to surface future problems. Phase gate 13/13.
7
+ - **Phase 166 -- gated-chain executor (the `runChain` spine).** The shared invoke -> capture -> pass -> loop runtime that auto-runs autonomous-safe steps and halts at material steps via the Decision Gate; the engines (BONO, unknown-unknowns, trending-to-absurd) ride it instead of cloning a per-feature orchestrator. Phase gate `tests/run-all-166.sh` 23/23.
8
+ - **Phase 167 -- harness-as-code completion (`/mos:new-surface`).** A declared 3-MAP manifest + generator that scaffolds a new command/surface onto the connector spine and regenerates the registry transitively, plus posture-scoped fable-mode self-critique on material steps. Phase gate 12/12.
9
+ - **Phase 169 -- graph-derivation harness.** Mints the `NESTED_WITHIN` room-lineage edge so the nested-room fractal joint has a legal, graph-navigable home (child room -> parent room), and ships the self-heal rollup walk. Phase gate `tests/run-all-169.sh` green.
10
+
11
+ ### Changed
12
+ - README rebuilt to reflect v1.14.0: version badge, the new front-door command set (`/mos:ignite`, `/mos:discover`, `/mos:bono`, `/mos:map-unknowns`), and the current surface count (99 commands, 14 skills, 9 agents).
13
+ - mindrian-os.com updated with the new commands and v1.14.0 capability information, version surfaces reconciled, and redeployed.
14
+ - Mindrian Canon advanced to v1.13 (Appendix D entries 21-24): the domain-taxonomy edges (DECOMPOSED_INTO / PART_OF / TAGGED_WITH / RELATED_TO), the Part-4 cascade reconciliation (CONVERGES / INVALIDATES / ENABLES into the navigation chokepoint), the `NESTED_WITHIN` room-lineage edge, and the `SyntheticExpert` node type.
15
+
16
+ ### Fixed
17
+ - **Phase 168 -- Part-4 edge-vocabulary reconciliation.** Brought the Part 9 `writeEdge` chokepoint frozen set into line with Canon Part 4 prose (CONVERGES / INVALIDATES / ENABLES were declared in canon and written by the legacy cascade path but rejected by the chokepoint). Phase gate `tests/run-all-168.sh` green.
18
+ - `tests/run-all-165.sh` no longer trips its own em-dash sweep: the swept-for em-dash is now defined via its U+2014 codepoint escape so the gate file carries no literal em-dash.
19
+ - GSD STATE.md / ROADMAP.md reconciled to the active milestone (`v1.14.0-beta.2`): the stale `v1.13.1` milestone label, the old phase/plan counts, and the stale `## Latest` section were corrected so every progress report reads true.
20
+
1
21
  ## [1.14.0-beta.1] - 2026-06-18
2
22
 
3
23
  ### Added
4
- -
24
+ - Opened the v1.14.0 cycle on top of the shipped v1.13.1 "Larry Reaches" stable release. Detailed v1.14.0 notes are consolidated under the beta.3 entry above (the phases 163-169 executed band landed across beta.1 and beta.2).
5
25
 
6
26
  ## [1.13.1] - 2026-06-17
7
27
 
package/README.md CHANGED
@@ -10,7 +10,7 @@
10
10
  Powered by PWS (Problems Worth Solving), an innovation methodology built and tested through 20 years of teaching by Prof. Lawrence Aronhime.
11
11
  Engineered by Jonathan Sagir.
12
12
 
13
- [![Version](https://img.shields.io/badge/version-1.13.1--beta-1E3A6E)](CHANGELOG.md)
13
+ [![Version](https://img.shields.io/badge/version-1.14.0--beta-1E3A6E)](CHANGELOG.md)
14
14
  [![License](https://img.shields.io/badge/license-BSL_1.1-C8A43C)](LICENSE)
15
15
  [![Works on](https://img.shields.io/badge/CLI_+_Desktop_+_Cowork-2D6B4A)](#three-surfaces)
16
16
 
@@ -114,17 +114,19 @@ Talk. That is the whole interface. You describe what you are trying to do, and L
114
114
  The commands below are internals. You never have to memorize them or type them. Larry reaches for them on your behalf. They are here for the times you already know the shortcut and want it.
115
115
 
116
116
  ```bash
117
- /mos:new-project # tell Larry what you are exploring
117
+ /mos:ignite # the front door: start or excavate a room
118
+ /mos:discover # Larry-led client + product + JTBD discovery
118
119
  /mos:beautiful-question # reframe the problem before solving it
119
120
  /mos:analyze-needs # who has this problem, how badly, what they have tried
120
- /mos:lean-canvas # one-page business model
121
+ /mos:bono # a six-hats research-and-debate team on your question
122
+ /mos:map-unknowns # hunt the claims you are most confident about, and wrong
121
123
  /mos:file-meeting # paste a transcript, Larry files it
122
124
  /mos:opportunities # what grants match this room right now
123
125
  /mos:graph "what is the weakest assumption in my financial model?"
124
126
  /mos:grade # honest assessment against real ventures
125
127
  ```
126
128
 
127
- If you do not know which one to run, that is the normal case. Just talk.
129
+ That is a slice of 99 commands across 14 skills and 9 agents. If you do not know which one to run, that is the normal case. Just talk: Larry reaches for the right one.
128
130
 
129
131
  ---
130
132
 
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@mindrian_os/cli",
3
- "version": "1.14.0-beta.1",
3
+ "version": "1.14.0-beta.3",
4
4
  "description": "Install MindrianOS into Claude Code with one command -- `npx @mindrian_os/cli`. Ships the MindrianOS plugin (Larry + PWS methodology + Data Room) plus a setup/diagnostics CLI (install/doctor/update).",
5
5
  "scripts": {
6
6
  "mcp": "node bin/mindrian-mcp-server.cjs",