@humanoiselabs/plus62 0.1.7 → 0.2.0

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 ADDED
@@ -0,0 +1,26 @@
1
+ # Changelog
2
+
3
+ All notable changes to `@humanoiselabs/plus62` (+62 Mode) will be documented in this file.
4
+
5
+ ## [0.2.0] - 2026-11-13
6
+
7
+ ### Added
8
+ - **Expanded Indonesian Cultural Corpus (`culture/id/genz-lexicon.yaml`)**: Scaled from the 7-term KBBI seed to **159 schema-validated entries** incorporating verified Wave 1 & Wave 2 research across Gen Z/Alpha viral slang (`stecu`, `aura-points`, `delulu`, `rizz`, `slay`, `mid`, etc.), local +62 expressions and regional loanwords (`menyala-abangku`, `gak-bisa-yura`, `skena`, `gacor`, `rungkad`, `boncos`, `sat-set`, `gaskeun`, `ra mashok`, `ora urus`, `jancok`), X/Twitter & gaming/tech vocabulary (`jbjb`, `menfess`, `dark-system`, `skill-issue`, `kuli-ketik`, `sepuh`), 11 pragmatic discourse particles (`sih`, `dong`, `deh`, `tuh`, `nih`, `lah`, `kok`, `kan`, `mah`, `loh`, `dah`), and 20 daily chat shorthand groups.
9
+ - **Expanded Situational Memes (`culture/id/memes.yaml`)**: Expanded to **14 meme patterns** while preserving all original developer tropes and flagging awareness-only/dating memes (`sigma`, `skibidi`).
10
+ - **Curated Persona Lexicon (`personas/plus62/lexicon.yaml`)**: Expanded active developer slang whitelist to **15 entries** with strict per-response limits.
11
+ - **E2E Regression Suite (`test/e2e-wave.test.ts` & `TEST_INFRA.md`)**: Added 14 end-to-end verification tests covering full 152-term Wave 1 & 2 coverage, AJV schema validation, awareness-only quota enforcement (`max_per_response: 0`), provenance hygiene, adapter token hard caps, CLI bundle checks, tarball packing, and public infrastructure guardrails.
12
+
13
+ ### Changed
14
+ - **Compact Grouped Runtime Reference Compiler (`src/build.ts`)**: Replaced verbose per-entry multi-line YAML serialization in compiled runtime references with compact behavioral-group formatting so all 159 lexicon entries, 14 memes, and 15 active whitelist rules ship comfortably within strict token budgets (`references: 4889/4950` on Antigravity, `4516/4950` on Claude Code; zero budget warnings).
15
+ - **Provenance Documentation (`culture/id/sources.md`)**: Documented all Wave 1 & Wave 2 primary references cleanly in unmounted source tables.
16
+
17
+ ## [0.1.8] - 2026-11-12
18
+
19
+ ### Changed
20
+ - Polished residual internal naming to **+62 Mode** (`@humanoiselabs/plus62`) across core instructions, persona cards, adapters, installers, and tests.
21
+ - Clarified on-demand skill/rule loading instructions for downstream adapters.
22
+
23
+ ## [0.1.7] - 2026-11-11
24
+
25
+ ### Fixed
26
+ - Applied readiness audit remediations across CLI flags, documentation links, and `HumanoiseLABS` umbrella portal metadata (`https://humanoise.vercel.app`).
package/README.md CHANGED
@@ -156,7 +156,7 @@ node src/cli.ts uninstall --target /path/to/project
156
156
  - Licence: **MIT** (`LICENSE`), chosen 2026-11-07 over Apache-2.0 because this repository is policy text and a small TypeScript compiler with nothing patentable, and MIT adds no `NOTICE` or change-marking step for the harnesses that will bundle it.
157
157
  - Provenance: verified KBBI and NU Online citations for the religious expressions live in `culture/id/sources.md`, which is deliberately not mounted — references cost runtime tokens, citations do not. *MasyaAllah* and *Subhanallah* still have no verified URL, and inventing a `decay_class` for religious vocabulary was rejected as a distortion rather than a fix.
158
158
  - Personas: **+62 Mode** (`profiles/plus62.yaml`, alias: `rusuh-id`) is authored with voice, card, lexicon, examples, and rubric scenarios. **+62 Mode** (`plus62`) is signed off across all three review axes (`linguistic`, `cultural`, `safety`) and passes `build --release`. Installs and uninstalls cleanly across all supported harness adapters.
159
- - Culture KB: small sourced seed. `culture/id/religious-expression.md` and the four expanded `core/*.md` policies are mounted as skill references.
159
+ - Culture KB: expanded v0.2.0 Indonesian lexicon (159 schema-validated entries across KBBI colloquial, Gen Z/Alpha viral slang, X/Twitter/gaming dev terms, regional loanwords, discourse particles, and chat shorthands), 14 situational meme notes, `culture/id/religious-expression.md`, and the four expanded `core/*.md` policies compiled compactly within strict adapter token budgets.
160
160
  - Harnesses: **Claude Code** is the reference target and is verified end-to-end (install, doctor, uninstall, live run, permission posture measured). **opencode** (1.18.31) has its own adapter plus a headless runner (`--harness opencode`): `opencode debug skill` lists the installed skill, a live `opencode run` confirmed the `AGENTS.md` block reaches model context, and a coding fixture graded `solved` with the edit landing in the graded workspace — see `docs/harness-parity.md`. Its study posture is enforced through `OPENCODE_CONFIG` (edit allow, bash/webfetch/external_directory deny) rather than by writing into the target repo. **antigravity** has an adapter that writes `.agents/rules/*.md` with `always_on`/`model_decision` triggers, plus `--scope global` for `~/.gemini/config/rules/`; that layout follows the vendor docs and has **not** been observed loading. **agents-md** emits the vendor-neutral `AGENTS.md` + `.agents/skills/` pair; it is exercised by install/doctor/uninstall round-trips but no Cursor/Codex/Qoder run has read it on this machine. Qoder itself remains unverified — `docs/qoder-assessment.md` still says "Incomplete — no compatibility claim".
161
161
 
162
162
  See `docs/quickstart.md`, `docs/phase-2-integration-findings.md`, `docs/phase-3-content-hardening.md`, `docs/phase-3-live-suite-results.md`, and the Phase 0 documents.
@@ -1,6 +1,6 @@
1
- # HAHahah identity
1
+ # +62 Mode identity
2
2
 
3
- HAHahah is a voice and working-style layer for an existing coding agent. It is not a model, a runtime, or a replacement for the user's instructions.
3
+ +62 Mode is a voice and working-style layer for an existing coding agent. It is not a model, a runtime, or a replacement for the user's instructions.
4
4
 
5
5
  ## Competence contract
6
6
 
@@ -18,7 +18,7 @@ HAHahah is a voice and working-style layer for an existing coding agent. It is n
18
18
  ## Conflict clause
19
19
 
20
20
  1. Host system and harness permissions win.
21
- 2. A project/user instruction wins over HAHahah core when they conflict; surface the conflict instead of hiding it.
21
+ 2. A project/user instruction wins over +62 Mode core when they conflict; surface the conflict instead of hiding it.
22
22
  3. Core safety, decision, and efficiency rules win over persona style.
23
23
  4. If precedence is unclear, take the reversible path or ask one targeted question.
24
24
 
package/core/10-safety.md CHANGED
@@ -1,4 +1,4 @@
1
- # HAHahah safety policy
1
+ # +62 Mode safety policy
2
2
 
3
3
  This policy is always-on in its compact form and cannot be overridden by a persona.
4
4
 
@@ -1,4 +1,4 @@
1
- # HAHahah decision policy
1
+ # +62 Mode decision policy
2
2
 
3
3
  Decide before speaking. Voice is applied after the decision, never before it.
4
4
 
@@ -1,4 +1,4 @@
1
- # HAHahah efficiency policy
1
+ # +62 Mode efficiency policy
2
2
 
3
3
  Efficiency means useful information per token, not minimum characters.
4
4
 
package/core/always-on.md CHANGED
@@ -1,6 +1,6 @@
1
- # HAHahah core
1
+ # +62 Mode core
2
2
 
3
- HAHahah is voice; host policy, permissions, and primary instructions win.
3
+ +62 Mode is voice; host policy, permissions, and primary instructions win.
4
4
 
5
5
  ## Language
6
6
  - Answer in the user's language — incident, diagnosis, and other serious replies included. Keep dev terms English; never translate code, paths, commands, errors.