opencodekit 0.7.0 → 0.9.0

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

@@ -13,8 +13,8 @@ agent: build
 
 ## Phase 1: Load Bead
 
-```bash
-bd show $ARGUMENTS --json
+```typescript
+bd_show({ id: "$ARGUMENTS" });
 ```
 
 Verify status is `in-progress` or `open`.
@@ -175,31 +175,25 @@ Closes: <bead-id>"
 
 ## Phase 7: Close Bead
 
-**If using Beads Village:** Complete the task and notify other agents:
+Complete the task and release any file reservations:
 
-```
-done(id="$ARGUMENTS", msg="Implemented: [1-liner summary]")
+```typescript
+bd_done({ id: "$ARGUMENTS", msg: "Implemented: [1-liner summary]" });
 ```
 
-This closes the bead, releases any file reservations, and broadcasts completion to the workspace.
-
-**Otherwise:** Close via CLI:
-
-```bash
-bd close $ARGUMENTS --reason "Implemented: [1-liner summary]"
-```
+This closes the bead, releases file locks, and syncs with git.
 
 ## Phase 8: Database Health Check
 
 Check issue count:
 
-```bash
-bd list --status all 2>/dev/null | wc -l
+```typescript
+bd_ls({ status: "all", limit: 1 });
 ```
 
 **If >200 issues:** Warn about performance.
 
-**If >500 issues:** Strongly recommend cleanup.
+**If >500 issues:** Strongly recommend cleanup with `bd_cleanup({ days: 7 })`.
 
 ## Output
 
@@ -224,7 +218,8 @@ Branch: <bead-id>
 
 ```
 ⚠️  Database has [count] issues. Consider running:
-    bd cleanup --older-than 7d && bd sync
+    bd_cleanup({ days: 7 })
+    bd_sync()
 ```
 
 **Session recommendation:**
@@ -238,7 +233,7 @@ Task complete. For best performance:
 Next: Create PR or merge to main
 ```
 
-**If using Beads Village:** After calling `done()`, restart your session for a fresh context. The one-task-per-session pattern keeps agents fast and focused.
+After calling `bd_done()`, restart your session for a fresh context. The one-task-per-session pattern keeps agents fast and focused.
 
 **If work was interrupted or partially complete:**
 

package/dist/template/.opencode/command/fix-ci.md

@@ -15,15 +15,16 @@ For deep tracing: `skill({ name: "root-cause-tracing" })`
 
 CI failures are P0 bugs. Create a bead to track:
 
-```bash
-bd create --title "Fix CI: <failure summary>" --type bug --priority p0 --json
+```typescript
+bd_add({
+  title: "Fix CI: <failure summary>",
+  type: "task",
+  pri: 0,
+  tags: ["bug"],
+});
 ```
 
-Save the bead ID for tracking. Add the CI run reference:
-
-```bash
-bd edit <bead-id> --note "CI Run: $ARGUMENTS"
-```
+Save the bead ID for tracking. Add the CI run reference via `bd_msg` or notes.
 
 ## Workflow
 
@@ -41,8 +42,8 @@ bd edit <bead-id> --note "CI Run: $ARGUMENTS"
 
 Once CI passes:
 
-```bash
-bd close <bead-id> --reason "CI fixed: <summary of fix>"
+```typescript
+bd_done({ id: "<bead-id>", msg: "CI fixed: <summary of fix>" });
 ```
 
 ## Notes

package/dist/template/.opencode/command/fix-types.md

@@ -19,19 +19,12 @@ Run `bun run typecheck` and fix all type errors.
 
 If a bead ID is provided (`$ARGUMENTS`), track the type fixing work:
 
-1. **Before fixing:** Note the initial error count
+1. **Before fixing:** Note the initial error count via `bd_msg` or notes
 
-   ```bash
-   bd edit $ARGUMENTS --note "Type errors found: <count>"
-   ```
-
-2. **After fixing:** Update with resolution
-   ```bash
-   bd edit $ARGUMENTS --note "Type errors resolved: <summary of fixes>"
-   ```
+2. **After fixing:** Update with resolution summary
 
 If type errors reveal deeper issues requiring refactoring, create a follow-up bead:
 
-```bash
-bd create --title "Refactor: <type issue summary>" --type task --related $ARGUMENTS
+```typescript
+bd_add({ title: "Refactor: <type issue summary>", type: "task", pri: 2 });
 ```

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

@@ -10,10 +10,12 @@ agent: build
 
 ## Phase 1: Gather State
 
-```bash
-# Bead info
-bd show $ARGUMENTS --json
+```typescript
+// Bead info
+bd_show({ id: "$ARGUMENTS" });
+```
 
+```bash
 # Git state
 git remote get-url origin 2>/dev/null
 git branch --show-current
@@ -45,12 +47,10 @@ Write `.beads/artifacts/<bead-id>/handoffs/<timestamp>.md`:
 
 ## Provenance
 
-| Key    | Value            |
-| ------ | ---------------- |
-| Repo   | [git remote URL] |
-| Branch | [branch name]    |
-| Commit | [commit hash]    |
-| Clean  | [yes/no]         |
+- **Repo:** [git remote URL]
+- **Branch:** [branch name]
+- **Commit:** [commit hash]
+- **Clean:** [yes/no]
 
 ## Session Context
 
@@ -66,12 +66,10 @@ read_session("last", project="current")
 
 ## Bead State
 
-| Key      | Value      |
-| -------- | ---------- |
-| ID       | <bead-id>  |
-| Title    | [title]    |
-| Status   | [status]   |
-| Priority | [priority] |
+- **ID:** <bead-id>
+- **Title:** [title]
+- **Status:** [status]
+- **Priority:** [priority]
 
 ## Progress
 
@@ -123,9 +121,7 @@ read_session("last", project="current")
 
 ## Phase 4: Update Bead
 
-```bash
-bd edit <bead-id> --note "Handoff created. Resume with /resume <bead-id>"
-```
+Add a note about the handoff via `bd_msg` or update spec with handoff reference.
 
 ## Output
 

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

@@ -12,8 +12,8 @@ For large tasks with 3+ phases, also load: `skill({ name: "subagent-driven-devel
 
 ## Phase 1: Setup Workspace
 
-```bash
-bd show $ARGUMENTS --json
+```typescript
+bd_show({ id: "$ARGUMENTS" });
 ```
 
 Check git state:
@@ -31,12 +31,12 @@ Create branch if not on bead branch:
 git checkout -b <bead-id>
 ```
 
-**Multi-agent coordination (if Beads Village available):**
+**Multi-agent coordination:**
 
 Initialize your agent session and claim the task:
 
-```
-init(team="project", role="<your-role>")
+```typescript
+bd_init({ team: "project", role: "<your-role>" });
 ```
 
 This registers you in the workspace. If another agent is working on the same task, you'll be notified.
@@ -110,12 +110,12 @@ Mode: [Quick/Planned]
 
 ## Phase 4: Implementation
 
-**Reserve files before editing (if Beads Village available):**
+**Reserve files before editing:**
 
 Before making changes, lock the files you'll modify to prevent conflicts with other agents:
 
-```
-reserve(paths=["src/auth.ts", "src/utils/**"])
+```typescript
+bd_reserve({ paths: ["src/auth.ts", "src/utils/**"] });
 ```
 
 This creates an advisory lock. Other agents will see your reservation and avoid those files.
@@ -163,10 +163,10 @@ If "pause" or "stop": Run `/handoff <bead-id>`.
 
 ## Phase 6: Complete
 
-When done, release any file reservations (if Beads Village available):
+When done, release any file reservations:
 
-```
-release()
+```typescript
+bd_release();
 ```
 
 Then report:

package/dist/template/.opencode/command/import-plan.md

@@ -55,8 +55,13 @@ Proceed with import? (yes/modify/cancel)
 
 For each epic (top-level section):
 
-```bash
-bd create "[Epic title]" -t epic -p 2 -d "[description from plan]" --json
+```typescript
+bd_add({
+  title: "[Epic title]",
+  type: "epic",
+  pri: 2,
+  desc: "[description from plan]",
+});
 ```
 
 Store epic IDs for dependency linking.
@@ -65,8 +70,14 @@ Store epic IDs for dependency linking.
 
 For each issue under an epic:
 
-```bash
-bd create "[Issue title]" -t task -p 2 -d "[description]" --epic <epic-id> --json
+```typescript
+bd_add({
+  title: "[Issue title]",
+  type: "task",
+  pri: 2,
+  desc: "[description]",
+  parent: "<epic-id>",
+});
 ```
 
 **Infer type from content:**
@@ -85,10 +96,15 @@ bd create "[Issue title]" -t task -p 2 -d "[description]" --epic <epic-id> --jso
 
 ## Phase 5: Link Dependencies
 
-For issues with dependencies:
+For issues with dependencies, use the `deps` parameter when creating:
 
-```bash
-bd link <issue-id> --blocks <dependent-id>
+```typescript
+bd_add({
+  title: "[title]",
+  type: "task",
+  pri: 2,
+  deps: ["<blocking-issue-id>"],
+});
 ```
 
 Common patterns to detect:
@@ -125,12 +141,7 @@ Apply suggestions? (yes/no/select)
 
 ## Phase 7: Polish (Optional)
 
-If user approves suggestions:
-
-```bash
-bd edit <bead-id> --title "[improved title]"
-bd edit <bead-id> -d "[improved description]"
-```
+If user approves suggestions, update the spec files in `.beads/artifacts/<bead-id>/` directly.
 
 Iterate up to 5 times if user requests more refinement.
 
@@ -152,7 +163,7 @@ Created:
 │   └── <issue-3-id>: [title]
 └── ...
 
-Start work: bd ready
+Start work: `bd_ls({ status: "ready", limit: 10, offset: 0 })`
 First task: /implement <first-unblocked-id>
 ```
 

package/dist/template/.opencode/command/integration-test.md

@@ -14,7 +14,7 @@ agent: build
 
 ## Task Validation
 
-1. **Check bead exists:** `bd show $ARGUMENTS`
+1. **Check bead exists:** `bd_show({ id: "$ARGUMENTS" })`
 2. **Read constraints:** `.beads/artifacts/$ARGUMENTS/spec.md` Testing Notes section
 3. **If missing:** STOP. Create with `/create` first.
 

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

@@ -23,15 +23,11 @@ gh issue view $ARGUMENTS
 
 Create a bead to track this work, linking it to the GitHub issue:
 
-```bash
-bd create --title "<issue title>" --type task --priority <p1|p2|p3> --json
+```typescript
+bd_add({ title: "<issue title>", type: "task", pri: 2 });
 ```
 
-Save the bead ID for subsequent commands. Add the GitHub issue reference:
-
-```bash
-bd edit <bead-id> --note "GitHub issue: #$ARGUMENTS"
-```
+Save the bead ID for subsequent commands. Add the GitHub issue reference via `bd_msg` or in the spec.
 
 ## Create Spec from PRD Template
 
@@ -87,8 +83,13 @@ Save to `.beads/artifacts/<bead-id>/spec.md`:
 
 If analysis reveals additional issues, create child beads:
 
-```bash
-bd create --title "<discovered issue>" --type discovered --parent <parent-bead-id>
+```typescript
+bd_add({
+  title: "<discovered issue>",
+  type: "task",
+  pri: 2,
+  parent: "<parent-bead-id>",
+});
 ```
 
 **Next:** Use `/implement <bead-id>` to start implementation.

package/dist/template/.opencode/command/new-feature.md

@@ -23,8 +23,8 @@ Parse from `$ARGUMENTS`:
 
 ### Step 1: Create Bead
 
-```bash
-bd new [type] "[feature-name]" --priority [priority]
+```typescript
+bd_add({ title: "[feature-name]", type: "[type]", pri: [priority] });
 ```
 
 Capture the bead ID from output.
@@ -112,9 +112,7 @@ Tasks:
 
 ### Step 4: Update Bead
 
-```bash
-bd update [bead-id] --status planning
-```
+Update bead status by adding a note via `bd_msg` or updating the spec.
 
 ## Output
 
@@ -129,7 +127,7 @@ Report:
 
 ```bash
 # View the feature
-bd show [bead-id]
+bd_show({ id: "[bead-id]" })
 
 # Start implementation
 /implement [bead-id]

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

@@ -10,8 +10,8 @@ agent: planner
 
 ## Phase 1: Load Context
 
-```bash
-bd show $ARGUMENTS --json
+```typescript
+bd_show({ id: "$ARGUMENTS" });
 ```
 
 Read artifacts:
@@ -221,9 +221,7 @@ After approval, write `.beads/artifacts/<bead-id>/plan.md`:
 
 ## Phase 7: Update Bead
 
-```bash
-bd edit <bead-id> --note "Plan approved: [option name]. [step count] steps."
-```
+Add a note about plan approval via `bd_msg` or update the spec with the approved approach.
 
 ## Output
 

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

@@ -18,7 +18,7 @@ Create a pull request following these steps:
 2. **Push branch**: `!git push -u origin $(git branch --show-current)`
 
 3. **Check for bead context:**
-   - If `$ARGUMENTS` contains a bead ID, fetch bead details: `bd show $ARGUMENTS --json`
+   - If `$ARGUMENTS` contains a bead ID, fetch bead details: `bd_show({ id: "$ARGUMENTS" })`
    - Use bead title and spec to inform PR content
    - Reference the bead in the PR body for traceability
 
@@ -50,6 +50,4 @@ Closes: bd-XXXXX (if applicable)
 
 If a bead ID was provided, update the bead with PR link:
 
-```bash
-bd edit $ARGUMENTS --note "PR created: <pr-url>"
-```
+Update the bead with a note about the PR using the beads messaging or note system.

package/dist/template/.opencode/command/research-and-implement.md

@@ -12,7 +12,7 @@ Fix directly with clear comments. Commit.
 
 ## Structured work (bead-based)
 
-1. Validate bead exists: `bd show $ARGUMENTS`
+1. Validate bead exists: `bd_show({ id: "$ARGUMENTS" })`
 2. Load constraints from `.beads/artifacts/$ARGUMENTS/spec.md`
 3. Research within scope: `/research $ARGUMENTS`
 4. Plan approach: `/plan $ARGUMENTS`

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

@@ -8,8 +8,8 @@ agent: build
 
 ## Phase 1: Load Bead Context
 
-```bash
-bd show $ARGUMENTS --json
+```typescript
+bd_show({ id: "$ARGUMENTS" });
 ```
 
 **Check for previous research:**
@@ -43,11 +43,11 @@ Extract:
 
 Run these **in parallel** using batch tool calls:
 
-### Internal Codebase (GKG)
+### Internal Codebase
 
-- `gkg_search_codebase_definitions` - Find related functions/classes
-- `gkg_get_references` - See how existing code connects
-- `gkg_repo_map` - Map relevant directories
+- `grep` - Find related functions/classes by pattern
+- `ast-grep` - Semantic code search for patterns
+- `glob` - Map relevant directories
 
 ### External Docs (Context7)
 
@@ -68,12 +68,12 @@ Run these **in parallel** using batch tool calls:
 
 For each finding:
 
-| Check                      | Pass/Fail |
-| -------------------------- | --------- |
-| Within spec scope?         |           |
-| Follows constraints?       |           |
-| Uses allowed libs?         |           |
-| Matches existing patterns? |           |
+**Validation checklist:**
+
+- Within spec scope?
+- Follows constraints?
+- Uses allowed libs?
+- Matches existing patterns?
 
 **Discard anything that fails.**
 
@@ -130,9 +130,7 @@ Existing code that informs implementation:
 
 ## Phase 5: Update Bead
 
-```bash
-bd edit <bead-id> --note "Research complete. Key findings: [1-liner]"
-```
+Add a note about research completion via `bd_msg` or update the spec with key findings.
 
 ## Output
 

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

@@ -30,8 +30,8 @@ Review:
 
 ## Phase 2: Load Bead
 
-```bash
-bd show $ARGUMENTS --json
+```typescript
+bd_show({ id: "$ARGUMENTS" });
 ```
 
 ## Phase 3: Find Latest Handoff

package/dist/template/.opencode/command/revert-feature.md

@@ -24,8 +24,8 @@ Parse from `$ARGUMENTS`:
 
 ### Step 1: Analyze Bead History
 
-```bash
-bd show [bead-id] --history
+```typescript
+bd_show({ id: "[bead-id]" });
 ```
 
 Identify:
@@ -87,9 +87,7 @@ git revert --no-commit [commits...]
 
 ### Step 5: Update Bead
 
-```bash
-bd update [bead-id] --status reverted --note "Reverted [scope]"
-```
+Update bead status by adding a note via `bd_msg` about the revert.
 
 ## Safety Checks
 
@@ -119,10 +117,10 @@ Report:
 
 ```bash
 # View bead history
-bd show [bead-id] --history
+bd_show({ id: "[bead-id]" })
 
 # Check current status
-bd status
+bd_status({ include_agents: false })
 
 # Re-implement after revert
 /implement [bead-id]

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

@@ -8,7 +8,7 @@ agent: explore
 ## Quick Summary
 
 1. **Git:** Current branch, uncommitted changes
-2. **Tasks:** `bd list` - count by status
+2. **Tasks:** `bd_ls()` - count by status
 3. **CI:** Any build issues
 4. **Sessions:** Recent activity
 
@@ -43,8 +43,8 @@ Activity: 2 sessions, 73 messages, 20 files modified
 
 ## Task Compliance
 
-```bash
-bd list --status open
+```typescript
+bd_ls({ status: "open" });
 ```
 
 For each bead, check `.beads/artifacts/<bead-id>/`:
@@ -70,7 +70,7 @@ Compliance: X/Y beads complete
 
 ## Active Tasks
 
-For `bd list --status in-progress`:
+For `bd_ls({ status: "in_progress" })`:
 
 - Bead ID, Title, Priority
 - Goal from spec.md
@@ -79,12 +79,10 @@ For `bd list --status in-progress`:
 
 ## Required Actions
 
-| State           | Action                 |
-| --------------- | ---------------------- |
-| Missing spec    | `/create`              |
-| Has spec        | `/start <bead-id>`     |
-| In Progress     | `/implement <bead-id>` |
-| Ready to finish | `/finish <bead-id>`    |
+- Missing spec → `/create`
+- Has spec → `/start <bead-id>`
+- In Progress → `/implement <bead-id>`
+- Ready to finish → `/finish <bead-id>`
 
 ## Session Insights
 

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

@@ -24,8 +24,18 @@
 				"memory-read",
 				"memory-update",
 				"observation",
-				"use_skill",
-				"skill"
+				"skill",
+				"lsp",
+				"lsp_lsp_rename",
+				"lsp_lsp_code_actions",
+				"lsp_lsp_code_action_apply",
+				"lsp_lsp_organize_imports",
+				"bd_init",
+				"bd_claim",
+				"bd_done",
+				"bd_show",
+				"bd_reserve",
+				"bd_reservations"
 			]
 		},
 		// Removes tool content from context without preservation (for completed tasks or noise)
@@ -51,6 +61,14 @@
 		"supersedeWrites": {
 			"enabled": true
 		},
+		// Prune tool inputs for errored tools after X turns
+		"purgeErrors": {
+			"enabled": true,
+			// Number of turns before errored tool inputs are pruned
+			"turns": 4,
+			// Additional tools to protect from pruning
+			"protectedTools": []
+		},
 		// (Legacy) Run an LLM to analyze what tool calls are no longer relevant on idle
 		"onIdle": {
 			"enabled": false,