opencodekit 0.16.14 → 0.16.17

package/dist/template/.opencode/command/verify.md

@@ -2,20 +2,17 @@
 description: Verify implementation completeness, correctness, and coherence
 argument-hint: "<bead-id> [--quick] [--fix]"
 agent: review
-subtask: true
 ---
 
 # Verify: $ARGUMENTS
 
-Three-dimensional verification before claiming work complete. Inspired by OpenSpec's verify workflow.
+Check implementation against PRD before shipping.
 
 ## Load Skills
 
 ```typescript
 skill({ name: "beads" });
 skill({ name: "verification-before-completion" });
-skill({ name: "systematic-debugging" });
-skill({ name: "memory-system" });
 ```
 
 ## Parse Arguments
@@ -23,285 +20,74 @@ skill({ name: "memory-system" });
 | Argument    | Default  | Description                      |
 | ----------- | -------- | -------------------------------- |
 | `<bead-id>` | required | The bead to verify               |
-| `--quick`   | false    | Skip coherence check, gates only |
-| `--fix`     | false    | Auto-fix issues where possible   |
+| `--quick`   | false    | Gates only, skip coherence check |
+| `--fix`     | false    | Auto-fix lint/format issues      |
 
----
-
-## Phase 1: Check Memory for Context
-
-Search for relevant verification patterns and past issues:
-
-```typescript
-memory_search({ query: "$ARGUMENTS verification issues patterns", limit: 3 });
-```
-
----
-
-## Phase 2: Gather Artifacts
+## Phase 1: Gather Context
 
 ```bash
 br show $ARGUMENTS
 ls .beads/artifacts/$ARGUMENTS/
 ```
 
-Read all artifacts:
+Read the PRD and any other artifacts (plan.md, research.md, design.md).
 
-```bash
-cat .beads/artifacts/$ARGUMENTS/prd.md 2>/dev/null
-cat .beads/artifacts/$ARGUMENTS/plan.md 2>/dev/null
-cat .beads/artifacts/$ARGUMENTS/research.md 2>/dev/null
-cat .beads/artifacts/$ARGUMENTS/design.md 2>/dev/null
-```
+## Phase 2: Completeness
 
----
+Extract all requirements/tasks from the PRD and verify each is implemented:
 
-## Phase 3: Completeness Check
+- For each requirement: find evidence in the codebase (file:line reference)
+- Mark as: complete, partial, or missing
+- Report completeness score (X/Y requirements met)
 
-**Are all required artifacts present?**
+## Phase 3: Correctness
 
-| Artifact      | Required | Status |
-| ------------- | -------- | ------ |
-| `prd.md`      | Yes      | [ ]    |
-| `plan.md`     | Yes      | [ ]    |
-| `research.md` | No       | [ ]    |
-| `design.md`   | No       | [ ]    |
+Detect project type and run the appropriate verification gates:
 
-**Are all tasks in the PRD addressed?**
+| Project Type    | Detect Via                    | Build            | Test            | Lint                          | Typecheck                             |
+| --------------- | ----------------------------- | ---------------- | --------------- | ----------------------------- | ------------------------------------- |
+| Node/TypeScript | `package.json`                | `npm run build`  | `npm test`      | `npm run lint`                | `npm run typecheck` or `tsc --noEmit` |
+| Rust            | `Cargo.toml`                  | `cargo build`    | `cargo test`    | `cargo clippy -- -D warnings` | (included in build)                   |
+| Python          | `pyproject.toml` / `setup.py` | —                | `pytest`        | `ruff check .`                | `mypy .`                              |
+| Go              | `go.mod`                      | `go build ./...` | `go test ./...` | `golangci-lint run`           | (included in build)                   |
 
-Extract tasks/criteria from prd.md and verify each is implemented:
+Check `package.json` scripts, `Makefile`, or `justfile` for project-specific commands first — prefer those over generic defaults.
 
-```markdown
-## Completeness Report
+If `--fix` flag provided, run the project's auto-fix command (e.g., `npm run lint:fix`, `ruff check --fix`, `cargo clippy --fix`).
 
-| Requirement       | Status     | Evidence                |
-| ----------------- | ---------- | ----------------------- |
-| [Req 1 from spec] | ✓ Complete | `src/foo.ts:42`         |
-| [Req 2 from spec] | ✓ Complete | `src/bar.ts:15`         |
-| [Req 3 from spec] | ⚠ Partial  | Missing edge case tests |
-| [Req 4 from spec] | ✗ Missing  | Not implemented         |
-```
-
-**Completeness Score:** X/Y requirements met
-
----
-
-## Phase 4: Correctness Check
-
-**Do the automated gates pass?**
-
-```bash
-# Detect project type and run gates
-ls package.json Cargo.toml pyproject.toml go.mod 2>/dev/null
-```
-
-**Node/TypeScript:**
-
-```bash
-npm run build 2>&1 | tail -10
-npm test 2>&1 | tail -20
-npm run lint 2>&1 | tail -10
-npm run typecheck 2>&1 | tail -10
-```
+Report gate results (pass/warn/fail for each).
 
-**Rust:**
-
-```bash
-cargo build 2>&1 | tail -10
-cargo test 2>&1 | tail -20
-cargo clippy -- -D warnings 2>&1 | tail -10
-```
-
-**Python:**
-
-```bash
-pytest 2>&1 | tail -20
-ruff check . 2>&1 | tail -10
-mypy . 2>&1 | tail -10
-```
-
-**Go:**
-
-```bash
-go build ./... 2>&1 | tail -10
-go test ./... 2>&1 | tail -20
-golangci-lint run 2>&1 | tail -10
-```
-
-```markdown
-## Correctness Report
-
-| Gate      | Status | Details                   |
-| --------- | ------ | ------------------------- |
-| Build     | ✓ Pass |                           |
-| Tests     | ✓ Pass | 42 tests, 0 failures      |
-| Lint      | ⚠ Warn | 2 warnings (non-blocking) |
-| Typecheck | ✓ Pass |                           |
-```
-
-**Correctness Score:** X/Y gates passed
-
----
-
-## Phase 5: Coherence Check (skip with --quick)
-
-**Do artifacts agree with each other?**
+## Phase 4: Coherence (skip with --quick)
 
 Cross-reference artifacts for contradictions:
 
-| Check                        | Status | Issue                               |
-| ---------------------------- | ------ | ----------------------------------- |
-| prd.md ↔ plan.md             | ✓      | Plan addresses all PRD requirements |
-| plan.md ↔ implementation     | ✓      | Code follows plan structure         |
-| research.md ↔ implementation | ⚠      | Didn't use recommended approach     |
-| design.md ↔ implementation   | ✓      | Follows design patterns             |
-
-**Common coherence issues:**
-
-- Plan says X, implementation does Y
-- Research recommended approach A, used approach B (without justification)
-- Spec says must-have, implementation treats as optional
-- Design specifies pattern, implementation uses different pattern
+- PRD vs implementation (does code address all PRD requirements?)
+- Plan vs implementation (did code follow the plan?)
+- Research recommendations vs actual approach (if different, is it justified?)
 
-```markdown
-## Coherence Report
-
-Contradictions found: 1
-
-1. **Research vs Implementation**
-   - Research recommended: Use `zod` for validation
-   - Implementation uses: Manual validation
-   - Impact: Medium - works but less maintainable
-   - Action: Document decision or refactor
-```
+Flag contradictions with specific file references.
 
-**Coherence Score:** X/Y checks passed
-
----
-
-## Phase 6: Verification Summary
-
-```
-Verification: $ARGUMENTS
-━━━━━━━━━━━━━━━━━━━━━━━
-
-Dimension        Score    Status
-───────────────────────────────
-Completeness     4/5      ⚠ PARTIAL
-Correctness      4/4      ✓ PASS
-Coherence        3/4      ⚠ PARTIAL
-
-Overall: ⚠ NEEDS ATTENTION
-
-Issues Found:
-─────────────
-BLOCKING (must fix):
-  • [Req 4] Not implemented
-
-NON-BLOCKING (should fix):
-  • [Req 3] Missing edge case tests
-  • Research recommendation not followed
-
-Recommendations:
-────────────────
-1. Implement [Req 4] before closing
-2. Add tests for edge case X
-3. Document why zod was not used, or refactor to use it
-```
-
----
-
-## Phase 7: Auto-Fix (if --fix)
-
-For fixable issues, attempt automatic resolution:
-
-```typescript
-// If lint issues are fixable
-if (hasLintWarnings && canAutoFix) {
-  bash({ command: "npm run lint -- --fix" });
-}
-
-// If missing tests detected
-if (missingTests) {
-  console.log("Consider adding tests for: [list uncovered code]");
-}
-```
-
----
-
-## Phase 8: Update Bead Notes
-
-Record verification results in bead:
+## Phase 5: Report
 
 ```bash
 br comments add $ARGUMENTS "Verification: [PASS|PARTIAL|FAIL] - [summary]"
 ```
 
----
-
-## Phase 9: Record Findings
-
-If significant issues or patterns discovered:
-
-```typescript
-observation({
-  type: "discovery",
-  title: "Verification findings for $ARGUMENTS",
-  narrative: "[Summary of issues found, patterns discovered, or lessons learned]",
-  concepts: "verification, testing, quality",
-  bead_id: "$ARGUMENTS",
-  confidence: "high",
-});
-```
-
----
-
-## Output
-
-```
-Verification Complete: $ARGUMENTS
-━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
-
-Result: ✓ READY TO SHIP | ⚠ NEEDS WORK | ✗ BLOCKED
-
-Completeness: [score] - [status]
-Correctness:  [score] - [status]
-Coherence:    [score] - [status]
-
-[If READY TO SHIP]
-Next: /ship $ARGUMENTS
-
-[If NEEDS WORK]
-Fix these before shipping:
-• [issue 1]
-• [issue 2]
-
-[If BLOCKED]
-Cannot proceed until:
-• [blocker 1]
-```
-
----
-
-## Examples
-
-```bash
-# Full verification
-/verify br-feature-auth
-
-# Quick check (gates only)
-/verify br-feature-auth --quick
+Output:
 
-# Verify and auto-fix where possible
-/verify br-feature-auth --fix
-```
+1. **Result**: READY TO SHIP / NEEDS WORK / BLOCKED
+2. **Completeness**: score and status
+3. **Correctness**: gate results
+4. **Coherence**: contradictions found (if not --quick)
+5. **Blocking issues** to fix before shipping
+6. **Next step**: `/ship $ARGUMENTS` if ready, or list fixes needed
 
----
+Record significant findings with `observation()`.
 
 ## Related Commands
 
 | Need              | Command            |
 | ----------------- | ------------------ |
-| Ship after verify | `/ship $ARGUMENTS` |
+| Ship after verify | `/ship <id>`       |
 | Review code       | `/review-codebase` |
 | Check status      | `/status`          |

package/dist/template/.opencode/dcp.jsonc

@@ -3,9 +3,9 @@
 	"enabled": true,
 	"debug": false,
 	// "minimal" shows prune activity without noise; "detailed" shows token counts
-	"pruneNotification": "off",
+	"pruneNotification": "detailed",
 	// "chat" (in-conversation) or "toast" (system notification)
-	"pruneNotificationType": "chat",
+	"pruneNotificationType": "toast",
 	// Commands: /dcp context, /dcp stats, /dcp sweep
 	"commands": {
 		"enabled": true,
@@ -30,8 +30,8 @@
 		"settings": {
 			"nudgeEnabled": true,
 			"nudgeFrequency": 10,
-      // v2.0.1: percentage support - 90% of model's 128k context
-      "contextLimit": "90%",
+			// v2.0.1: percentage support - 90% of model's 128k context
+			"contextLimit": "90%",
 			// Protect state-modifying and critical workflow tools
 			// LSP excluded: ephemeral exploration, prune after understanding
 			"protectedTools": [
@@ -55,11 +55,12 @@
 			"permission": "allow",
 			"showDistillation": false
 		},
-    "compress": {
-      // v2.0.1: compress is experimental, deny by default
-      "permission": "deny",
-      "showCompression": false,
-    },
+		"compress": {
+			// v2.0.1: compress is experimental, deny by default
+			"permission": "deny",
+			"showCompression": false
+		}
+	},
 	"strategies": {
 		// Dedup = zero LLM cost, high impact - always enable
 		"deduplication": {

package/dist/template/.opencode/plugin/README.md

@@ -82,12 +82,16 @@ Session 3: read_session("previous") → Tests (90k) → close
 
 ### swarm-enforcer.ts
 
-**Swarm protocol guardrails (Beads-as-board)** - nudges agents to follow the Beads-first workflow.
+**Swarm protocol guardrails (Beads-as-board)** - enforces the `/create` → `/start` → `/ship` workflow.
 
 - Treats `.beads/` as the single source of truth for the swarm task board
-- If user expresses implementation intent and no task is `in_progress`, injects a nudge to use `br ready/show/update`
-- If there are `in_progress` tasks but `.beads/artifacts/<id>/spec.md` is missing, nudges to create it before implementation
-- On `file.edited`, warns if code is being changed without a claimed task or with missing `spec.md`
+- **Workflow stage tracking**: Computes each bead's stage based on artifacts and status:
+  - `⏳needs:/create` — no prd.md exists yet
+  - `⏳needs:/start` — has prd.md but not claimed (in_progress)
+  - `✅ready:/ship` — in_progress with prd.md, ready for implementation
+  - `⚠needs:/create→/start` — in_progress but missing prd.md
+- **System prompt injection** via `experimental.chat.system.transform`: injects workflow stage per bead, enforcement rules ("Do NOT implement until `/start`"), and protocol reminders into every LLM call
+- On `file.edited`, warns if code is being changed without a claimed task or when workflow is incomplete (no prd.md)
 - On `session.idle`, reminds to `br close` + `br sync` when work is done
 
 ### notification.ts