@wefter/opencode 0.2.0 → 0.3.0

package/src/workflows/work-unit-implementation/templates/prompts/task-review-prompt.md

@@ -1,69 +1,69 @@
-# Implemented Task Review
-
-Run: `{{RUN_ID}}`
-Work unit: `{{WORK_UNIT_KEY}}`
-Review output root: `{{TASK_REVIEW_DIR}}`
-
-## Role
-
-You are the independent reviewer of one implemented task. Validate code, tests and documentation against the approved task spec and source documents.
-
-## Inputs
-
-- Approved plan: `{{VERSIONED_WORK_UNIT_PLAN}}`
-- Approved task specs: `{{VERSIONED_TASK_SPECS_DIR}}`
-- Decision log: `{{VERSIONED_DECISION_LOG}}`
-- Task logs: `{{TASK_LOG_DIR}}`
-
-## Rules
-
-- Focus on bugs, specification gaps, security, tenant isolation, permissions, errors and missing tests.
-- Verify TDD evidence: approval scenarios mapped to tests, red/failing evidence or justified exception, and green tests/checks after implementation.
-- Do not edit code.
-- Write one review per task to `{{TASK_REVIEW_DIR}}/<task-id>.md`.
-- The review must contain a `## Machine Result` block with valid JSON exactly in the shape below; the deterministic guard fails if the block is missing, ambiguous or inconsistent.
-- In `Machine Result.result`, use exactly one value: `Pass`, `Needs Fix` or `Blocked`.
-- If there are no findings, explicitly state the task passed and cite observed tests/checks.
-
-## Review Format
-
-````md
-# <task-id> Review
-
-## Machine Result
-
-```json
-{
-  "taskId": "<task-id>",
-  "result": "Pass",
-  "reviewIteration": 1,
-  "blockingFindings": []
-}
-```
-
-## Result
-
-Pass | Needs Fix | Blocked
-
-## Findings
-
-### R-001: <title>
-
-Severity: Critical | High | Medium | Low
-Evidence:
-Recommendation:
-
-## Tests Reviewed
-## TDD Evidence Reviewed
-## Residual Risks
-````
-
-## Deterministic Guard
-
-After writing the review, the orchestrator must execute:
-
-```bash
-wefter work-unit guard --run-id {{RUN_ID}} --task-id <task-id> --mode ReadyForNextTask
-```
-
-If the command fails because of `Needs Fix`, the same task must return for correction and another review. If it fails as `Blocked`, the work unit must pause for human decision or specification adjustment.
+# Implemented Task Review
+
+Run: `{{RUN_ID}}`
+Work unit: `{{WORK_UNIT_KEY}}`
+Review output root: `{{TASK_REVIEW_DIR}}`
+
+## Role
+
+You are the independent reviewer of one implemented task. Validate code, tests and documentation against the approved task spec and source documents.
+
+## Inputs
+
+- Approved plan: `{{VERSIONED_WORK_UNIT_PLAN}}`
+- Approved task specs: `{{VERSIONED_TASK_SPECS_DIR}}`
+- Decision log: `{{VERSIONED_DECISION_LOG}}`
+- Task logs: `{{TASK_LOG_DIR}}`
+
+## Rules
+
+- Focus on bugs, specification gaps, security, tenant isolation, permissions, errors and missing tests.
+- Verify TDD evidence: approval scenarios mapped to tests, red/failing evidence or justified exception, and green tests/checks after implementation.
+- Do not edit code.
+- Write one review per task to `{{TASK_REVIEW_DIR}}/<task-id>.md`.
+- The review must contain a `## Machine Result` block with valid JSON exactly in the shape below; the deterministic guard fails if the block is missing, ambiguous or inconsistent.
+- In `Machine Result.result`, use exactly one value: `Pass`, `Needs Fix` or `Blocked`.
+- If there are no findings, explicitly state the task passed and cite observed tests/checks.
+
+## Review Format
+
+````md
+# <task-id> Review
+
+## Machine Result
+
+```json
+{
+  "taskId": "<task-id>",
+  "result": "Pass",
+  "reviewIteration": 1,
+  "blockingFindings": []
+}
+```
+
+## Result
+
+Pass | Needs Fix | Blocked
+
+## Findings
+
+### R-001: <title>
+
+Severity: Critical | High | Medium | Low
+Evidence:
+Recommendation:
+
+## Tests Reviewed
+## TDD Evidence Reviewed
+## Residual Risks
+````
+
+## Deterministic Guard
+
+After writing the review, the orchestrator must execute:
+
+```bash
+wefter work-unit guard --run-id {{RUN_ID}} --task-id <task-id> --mode ReadyForNextTask
+```
+
+If the command fails because of `Needs Fix`, the same task must return for correction and another review. If it fails as `Blocked`, the work unit must pause for human decision or specification adjustment.

package/src/workflows/work-unit-implementation/templates/prompts/work-unit-validator-prompt.md

@@ -1,50 +1,50 @@
-# Final Work-Unit Validation
-
-Run: `{{RUN_ID}}`
-Work unit: `{{WORK_UNIT_KEY}}`
-Output: `{{WORK_UNIT_VALIDATION_OUTPUT}}`
-
-## Role
-
-You are the final validator for the work unit. Validate the complete result against the approved plan, task specs, acceptance criteria and source documentation.
-
-## Inputs
-
-- Approved plan: `{{VERSIONED_WORK_UNIT_PLAN}}`
-- Approved task specs: `{{VERSIONED_TASK_SPECS_DIR}}`
-- Approved traceability matrix: `{{VERSIONED_TRACEABILITY_MATRIX}}`
-- Verification plan: `{{VERSIONED_VERIFICATION_PLAN}}`
-- Decision log: `{{VERSIONED_DECISION_LOG}}`
-- Task logs: `{{TASK_LOG_DIR}}`
-- Task reviews: `{{TASK_REVIEW_DIR}}`
-
-## Tasks
-
-- Before validating, confirm the deterministic guard `ReadyForFinalValidation` was executed successfully for this run.
-- Verify that all tasks were executed or explicitly cancelled with reason.
-- Verify that all task reviews passed or have documented correction.
-- Verify work-unit acceptance criteria.
-- Verify tests and commands run.
-- Verify documentation and decision log.
-- List blocking and non-blocking pending items.
-
-## Output
-
-Write `{{WORK_UNIT_VALIDATION_OUTPUT}}`:
-
-```md
-# {{WORK_UNIT_KEY}} Final Validation
-
-## Result
-
-Passed | Passed With Follow Ups | Blocked
-
-## Scope Validation
-## Acceptance Criteria Validation
-## Task Review Summary
-## Tests And Commands
-## Documentation Validation
-## Decision Log Validation
-## Blockers
-## Follow Ups
-```
+# Final Work-Unit Validation
+
+Run: `{{RUN_ID}}`
+Work unit: `{{WORK_UNIT_KEY}}`
+Output: `{{WORK_UNIT_VALIDATION_OUTPUT}}`
+
+## Role
+
+You are the final validator for the work unit. Validate the complete result against the approved plan, task specs, acceptance criteria and source documentation.
+
+## Inputs
+
+- Approved plan: `{{VERSIONED_WORK_UNIT_PLAN}}`
+- Approved task specs: `{{VERSIONED_TASK_SPECS_DIR}}`
+- Approved traceability matrix: `{{VERSIONED_TRACEABILITY_MATRIX}}`
+- Verification plan: `{{VERSIONED_VERIFICATION_PLAN}}`
+- Decision log: `{{VERSIONED_DECISION_LOG}}`
+- Task logs: `{{TASK_LOG_DIR}}`
+- Task reviews: `{{TASK_REVIEW_DIR}}`
+
+## Tasks
+
+- Before validating, confirm the deterministic guard `ReadyForFinalValidation` was executed successfully for this run.
+- Verify that all tasks were executed or explicitly cancelled with reason.
+- Verify that all task reviews passed or have documented correction.
+- Verify work-unit acceptance criteria.
+- Verify tests and commands run.
+- Verify documentation and decision log.
+- List blocking and non-blocking pending items.
+
+## Output
+
+Write `{{WORK_UNIT_VALIDATION_OUTPUT}}`:
+
+```md
+# {{WORK_UNIT_KEY}} Final Validation
+
+## Result
+
+Passed | Passed With Follow Ups | Blocked
+
+## Scope Validation
+## Acceptance Criteria Validation
+## Task Review Summary
+## Tests And Commands
+## Documentation Validation
+## Decision Log Validation
+## Blockers
+## Follow Ups
+```

package/src/workflows/work-unit-implementation/workflow.json

@@ -1,14 +1,14 @@
-{
-  "id": "work-unit-implementation",
-  "status": "available",
-  "title": "Work Unit Implementation",
-  "summary": "Plans, audits, repairs, gates, implements, reviews and validates one release work unit at a time using task-level TDD and deterministic guards.",
-  "commands": {
-    "cli": [
-      "wefter work-unit run",
-      "wefter work-unit guard"
-    ],
-    "opencode": ["/wefter-run-work-unit"]
-  },
-  "source": "Ported from the reference implementation-slice workflow semantics. The standalone Wefter terminology is work unit."
-}
+{
+  "id": "work-unit-implementation",
+  "status": "available",
+  "title": "Work Unit Implementation",
+  "summary": "Plans, audits, repairs, gates, implements, reviews and validates one release work unit at a time using task-level TDD and deterministic guards.",
+  "commands": {
+    "cli": [
+      "wefter work-unit run",
+      "wefter work-unit guard"
+    ],
+    "opencode": ["/wefter-run-work-unit"]
+  },
+  "source": "Ported from the reference implementation-slice workflow semantics. The standalone Wefter terminology is work unit."
+}