busya/ss-tools
1
0
Fork 0
Code Issues Pull Requests 1 Actions Packages Projects Releases Wiki Activity

speckit update

Browse Source
This commit is contained in:
busya
2026-03-16 23:55:42 +03:00
parent c957207bce
commit e916cb1f17
2 changed files with 59 additions and 11 deletions
Download Patch File Download Diff File Expand all files Collapse all files

39
.kilocode/workflows/speckit.implement.md
View File

@@ -122,11 +122,20 @@ You **MUST** consider the user input before proceeding (if not empty).
7. Implementation execution rules:
- **Strict Adherence**: Apply `.ai/standards/semantics.md` rules:
- Every file MUST start with a `[DEF:id:Type]` header and end with a closing `[/DEF:id:Type]` anchor.
- Include `@TIER` and define contracts (`@PRE`, `@POST`).
- For Svelte components, use `@UX_STATE`, `@UX_FEEDBACK`, `@UX_RECOVERY`, and explicitly declare reactivity with `@UX_REATIVITY: State: $state, Derived: $derived`.
- **Molecular Topology Logging**: Use prefixes `[EXPLORE]`, `[REASON]`, `[REFLECT]` in logs to trace logic.
- Every file MUST start with a `[DEF:id:Type]` header and end with a matching closing `[/DEF:id:Type]` anchor.
- Use `@COMPLEXITY` / `@C:` as the primary control tag; treat `@TIER` only as legacy compatibility metadata.
- Contract density MUST match effective complexity from [`.ai/standards/semantics.md`](.ai/standards/semantics.md):
- Complexity 1: anchors only.
- Complexity 2: require `@PURPOSE`.
- Complexity 3: require `@PURPOSE` and `@RELATION`.
- Complexity 4: require `@PURPOSE`, `@RELATION`, `@PRE`, `@POST`, `@SIDE_EFFECT`.
- Complexity 5: require full level-4 contract plus `@DATA_CONTRACT` and `@INVARIANT`.
- For Python Complexity 4+ modules, implementation MUST include a meaningful semantic logging path using `logger.reason()` and `logger.reflect()`.
- For Python Complexity 5 modules, `belief_scope(...)` is mandatory and the critical path must be irrigated with `logger.reason()` / `logger.reflect()` according to the contract.
- For Svelte components, require `@UX_STATE`, `@UX_FEEDBACK`, `@UX_RECOVERY`, and `@UX_REACTIVITY`; runes-only reactivity is allowed (`$state`, `$derived`, `$effect`, `$props`).
- Reject pseudo-semantic markup: docstrings containing loose `@PURPOSE` / `@PRE` text do **NOT** satisfy the protocol unless represented in canonical anchored metadata blocks.
- **Self-Audit**: The Coder MUST use `axiom-core` tools (like `audit_contracts_tool`) to verify semantic compliance before completion.
- **Semantic Rejection Gate**: If self-audit reveals broken anchors, missing closing tags, missing required metadata for the effective complexity, orphaned critical classes/functions, or Complexity 4/5 Python code without required belief-state logging, the task is NOT complete and cannot be handed off as accepted work.
- **CRITICAL Contracts**: If a task description contains a contract summary (e.g., `CRITICAL: PRE: ..., POST: ...`), these constraints are **MANDATORY** and must be strictly implemented in the code using guards/assertions (if applicable per protocol).
- **Setup first**: Initialize project structure, dependencies, configuration
- **Tests before code**: If you need to write tests for contracts, entities, and integration scenarios
@@ -144,23 +153,41 @@ You **MUST** consider the user input before proceeding (if not empty).
9. **Handoff to Tester (Audit Loop)**:
- Once a task or phase is complete, the Coder hands off to the Tester.
- Handoff includes: File paths, expected contracts (@PRE/@POST), and logic overview.
- Handoff includes: file paths, declared complexity, expected contracts (`@PRE`, `@POST`, `@SIDE_EFFECT`, `@DATA_CONTRACT`, `@INVARIANT` when applicable), and a short logic overview.
- Handoff MUST explicitly disclose any contract exceptions or known semantic debt. Hidden semantic debt is forbidden.
- The handoff payload MUST instruct the Tester to execute the dedicated testing workflow [`.kilocode/workflows/speckit.test.md`](.kilocode/workflows/speckit.test.md), not just perform an informal review.
10. **Tester Verification & Orchestrator Gate**:
- Tester MUST:
- Explicitly run the [`.kilocode/workflows/speckit.test.md`](.kilocode/workflows/speckit.test.md) workflow as the verification procedure for the delivered implementation batch.
- Perform mandatory semantic audit (using `audit_contracts_tool`).
- Reject code that only imitates the protocol superficially, such as free-form docstrings with `@PURPOSE` text but without canonical `[DEF]...[/DEF]` anchors and header metadata.
- Verify that effective complexity and required metadata match [`.ai/standards/semantics.md`](.ai/standards/semantics.md).
- Verify that Python Complexity 4/5 implementations include required belief-state instrumentation (`belief_scope`, `logger.reason()`, `logger.reflect()`).
- Emulate algorithms "in mind" step-by-step to ensure logic consistency.
- Verify unit tests match the declared contracts.
- If Tester finds issues:
- Emit `[AUDIT_FAIL: reason]` and notify the Orchestrator.
- Emit `[AUDIT_FAIL: semantic_noncompliance | contract_mismatch | logic_mismatch | test_mismatch | speckit_test_not_run]`.
- Provide concrete file-path-based reasons, for example: missing anchors, module/class contract mismatch, missing `@DATA_CONTRACT`, missing `logger.reason()`, illegal docstring-only annotations, or missing execution of [`.kilocode/workflows/speckit.test.md`](.kilocode/workflows/speckit.test.md).
- Notify the Orchestrator.
- Orchestrator redirects the feedback to the Coder for remediation.
- Orchestrator green-status rule:
- The Orchestrator MUST NOT assign green/accepted status unless the Tester confirms that [`.kilocode/workflows/speckit.test.md`](.kilocode/workflows/speckit.test.md) was executed.
- Missing execution evidence for [`.kilocode/workflows/speckit.test.md`](.kilocode/workflows/speckit.test.md) is an automatic gate failure even if the Tester verbally reports that the code "looks fine".
- Acceptance (Final mark [X]):
- Only after the Tester is satisfied with semantics, emulation, and tests.
- Any semantic audit warning relevant to touched files blocks acceptance until remediated or explicitly waived by the user.
- No final green status is allowed without explicit confirmation that [`.kilocode/workflows/speckit.test.md`](.kilocode/workflows/speckit.test.md) was run.
11. Completion validation:
- Verify all required tasks are completed and accepted by the Tester.
- Check that implemented features match the original specification.
- Confirm the implementation follows the technical plan and GRACE standards.
- Confirm touched files do not contain protocol-invalid patterns such as:
- class/function-level docstring contracts standing in for canonical anchors,
- missing closing anchors,
- missing required metadata for declared complexity,
- Complexity 5 repository/service code using only `belief_scope(...)` without explicit `logger.reason()` / `logger.reflect()` checkpoints.
- Report final status with summary of completed and audited work.
Note: This command assumes a complete task breakdown exists in tasks.md. If tasks are incomplete or missing, suggest running `/speckit.tasks` first to regenerate the task list.

31
.kilocode/workflows/speckit.test.md
View File

@@ -60,11 +60,18 @@ Create coverage matrix:
Before writing tests, the Tester MUST:
1. **Run `axiom-core.audit_contracts_tool`**: Identify semantic violations.
2. **Emulate Algorithm**: Step through the code implementation in mind.
2. **Run a protocol-shape review on touched files**:
- Reject non-canonical semantic markup, including docstring-only annotations such as `@PURPOSE`, `@PRE`, or `@INVARIANT` written inside class/function docstrings without canonical `[DEF]...[/DEF]` anchors and header metadata.
- Reject files whose effective complexity contract is under-specified relative to [`.ai/standards/semantics.md`](.ai/standards/semantics.md).
- Reject Python Complexity 4+ modules that omit meaningful `logger.reason()` / `logger.reflect()` checkpoints.
- Reject Python Complexity 5 modules that omit `belief_scope(...)`, `@DATA_CONTRACT`, or `@INVARIANT`.
- Treat broken or missing closing anchors as blocking violations.
3. **Emulate Algorithm**: Step through the code implementation in mind.
- Verify it adheres to the `@PURPOSE` and `@INVARIANT`.
- Verify `@PRE` and `@POST` conditions are correctly handled.
3. **Validation Verdict**:
- If audit fails: Emit `[AUDIT_FAIL: reason]` and notify Orchestrator.
4. **Validation Verdict**:
- If audit fails: Emit `[AUDIT_FAIL: semantic_noncompliance]` with concrete file-path reasons and notify Orchestrator.
- Example blocking case: [`backend/src/services/dataset_review/repositories/session_repository.py`](backend/src/services/dataset_review/repositories/session_repository.py) contains a module anchor, but its nested repository class/method semantics are expressed as loose docstrings instead of canonical anchored contracts; this MUST be rejected until remediated or explicitly waived.
- If audit passes: Proceed to writing/verifying tests.
### 5. Write Tests (TDD Approach)
@@ -73,10 +80,13 @@ For each module requiring tests:
1. **Check existing tests**: Scan `__tests__/` for duplicates.
2. **Read TEST_FIXTURE**: If CRITICAL tier, read @TEST_FIXTURE from semantics header.
3. **Write test**: Follow co-location strategy.
3. **Do not normalize broken semantics through tests**:
- The Tester must not write tests that silently accept malformed semantic protocol usage.
- If implementation is semantically invalid, stop and reject instead of adapting tests around the invalid structure.
4. **Write test**: Follow co-location strategy.
- Python: `src/module/__tests__/test_module.py`
- Svelte: `src/lib/components/__tests__/test_component.test.js`
4. **Use mocks**: Use `unittest.mock.MagicMock` for external dependencies
5. **Use mocks**: Use `unittest.mock.MagicMock` for external dependencies
### 4a. UX Contract Testing (Frontend Components)
@@ -173,6 +183,16 @@ Generate test execution report:
- Failed: [X]
- Skipped: [X]
## Semantic Audit Verdict
- Verdict: PASS | FAIL
- Blocking Violations:
- [file path] -> [reason]
- Notes:
- Reject docstring-only semantic pseudo-markup
- Reject complexity/contract mismatches
- Reject missing belief-state instrumentation for Python Complexity 4/5
## Issues Found
| Test | Error | Resolution |
@@ -182,6 +202,7 @@ Generate test execution report:
## Next Steps
- [ ] Fix failed tests
- [ ] Fix blocking semantic violations before acceptance
- [ ] Add more coverage for [module]
- [ ] Review TEST_FIXTURE fixtures
```