busya/ss-tools
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
610 Commits 3 Branches 0 Tags
73e809e189f7e828240090b8c946e310b913beac
Commit Graph

12 Commits

Author SHA1 Message Date
busya
73e809e189 skills 2026-06-08 15:08:02 +03:00
busya
4cef6af041 fix 2026-06-05 15:01:34 +03:00
busya
4b6c47837f agents skills 2026-05-25 13:25:35 +03:00
busya
c617754cca refactor(semantics): make complexity tiers descriptive, not gatekeeping 
Why: tier rules forbidding @PRE/@POST on C2 cause agents to either
remove useful documentation or generate audit noise. Both outcomes are
worse than having slightly richer metadata.

Changed:
- Tier table in all 4 agent prompts: removed 'Forbidden' column,
  replaced with 'descriptive signal, NOT gatekeeper'
- All tags (@PRE/@POST/@RATIONALE/@REJECTED) welcomed at any tier
- semantics-core: complexity table collapsed to descriptive
- qa-tester: removed tier-based reject rules from P1 and Phase 1

Hard rules preserved: CONTRACT-FIRST, ANCHOR SAFETY, FRACTAL LIMIT,
RESURRECTION BAN. Everything else is descriptive intent.
 2026-05-20 15:15:52 +03:00
busya
07cfaadee1 refactor(agents): inject CONTRACT MANDATE into all coder agent prompts 
Why: agents kept forgetting #region contracts because the rationale
was hidden in loadable skills, not active in their system prompt.

Changed agent prompts (+RATIONALE-first):
- python-coder: +55 lines — 4 failure modes + operational rules
- fullstack-coder: +40 lines — same, with cross-stack emphasis
- svelte-coder: replaced PHYSICS OF ATTENTION with unified mandate
- qa-tester: +15 lines — QA-specific contract mandate

Compressed skills (reference-only):
- semantics-core: 174→110 lines (-37%) — rationale removed, syntax+tables kept
- semantics-contracts: 103→79 lines (-23%) — duplicates removed, methodology kept

Verification: 320 tests pass, 0 parse warnings, 0 semantic audit warnings
 2026-05-20 15:02:29 +03:00
busya
09d12b3b68 semantics 2026-05-20 09:59:03 +03:00
busya
afe6c7e281 agents 2026-05-18 23:58:42 +03:00
busya
8bea44f640 chore: update semantic index, agent configs, and app startup 2026-05-14 21:33:26 +03:00
busya
a9a5eff518 fix(lint): apply QA-found gaps in agent instruction files 
- python-coder.md: ruff check src/ tests/ → ruff check .
- speckit.test.md: add frontend npm run lint
- speckit.plan.md: ruff check . + frontend lint
- speckit.tasks.md: ruff check . + frontend lint
- fullstack-coder.md: move npm run lint to frontend block
 2026-05-14 11:19:22 +03:00
busya
9b8c485562 chore: configure ruff + eslint linters for agentic workflow 
- Replace pylint with ruff (backend/ruff.toml)
  - line-length=300, max-complexity=10, per-file-ignores for tests
  - Exclude D (docstrings replaced by contracts) and ANN
- Add eslint flat config for frontend (eslint-plugin-svelte)
  - Allow console.info/warn/error (belief-state protocol)
- Remove .pylintrc (references non-existent plugin)
- Update agent docs: ruff check . + npm run lint
- Add ruff>=0.11.0 to backend/requirements.txt
- Add eslint + plugins to frontend devDependencies
 2026-05-14 10:28:30 +03:00
busya
9ea177558b agents 2026-05-12 19:37:22 +03:00
busya
fefdee98d0 agents 2026-05-11 22:58:01 +03:00