@brainervirus/workit-opencode 0.8.5 → 0.8.7

package/assets/skills/wk-handoff/SKILL.md

@@ -13,5 +13,6 @@ disable-model-invocation: true
 5. Pass only `message`; the tool itself recognizes an exact `--stay` flag and otherwise selects the new session.
 6. Report the structured success, failure stage, or partial result; never infer success.
 7. After any `workflow_handoff_session` result—success, partial, or failure—end the originating turn immediately after one status message. Never create todos, execute the plan inline, modify files, retry handoff, or call another tool.
+8. A destination run that executes the plan must still end with `workflow_plan_complete` (or the CLI `workit flow complete`) once the SDD ledger is complete and repository verification passes, and never finish the run while the plan is still `active`.
 
 Never emit a continuation prompt, use the clipboard, or ask the user to copy text. If selected, report the session ID only if the current session remains visible. If staying, report the seeded session ID. On failure, report `stage` and `error`; preserve any returned session for the session picker and never recreate it automatically. `todowrite` and `task` are unnecessary here.

package/assets/skills/wk-implement/SKILL.md

@@ -34,8 +34,12 @@ For every plan task whose ID is absent from `completed_task_ids`:
 6. Dispatch separate `general` agents for spec-compliance review and code-quality review. **Blocking findings** (Critical, Important, or spec-compliance) may trigger at most **two** fix+re-review rounds per task. **Advisory** findings (Minor, style, YAGNI, taste) never pause the loop — append them to `<SDD_DIR>/advisories.md` with the task id.
 7. Append the validated ledger line with `workflow_sdd_append_progress` using `confirmed: true`, then mark the task completed with `todowrite`.
 
+Each task lands exactly one contiguous non-empty commit range (`base..head`): fix rounds append commits to that range and never rewrite/amend an active review range; each progress line records the task's real base..head shas.
+
 Never redispatch completed task IDs. Pass task briefs and review diffs to agents; do not make them reparse the plan. Keep commits on the in-place feature/bugfix branch.
 
 ## Final gate
 
 After all remaining tasks, dispatch a final full-branch code review, run `workflow_verify`, and report exact per-check results. Present the full `<SDD_DIR>/advisories.md` roll-up once, then use native `question` so the user can choose which advisory items to fix, discuss, or discard. Only then may advisory fixes run. Use `workflow_git_context` for the final commit preview and the `wk-commit` skill for any approved commit. If a tracked stash reference exists, preview reapplication with `question`, then call `workflow_branch_setup` with `confirmed: true` only after approval.
+
+**Mandatory:** end the run by calling `workflow_plan_complete` (OpenCode/Cursor) or the CLI `workit flow complete` (CLI host) after the final task once the SDD ledger is complete (all task IDs appended) and `workflow_verify` passes — a complete ledger and green verification are the tool's gates. Never finish the run while the plan is still `active`.

package/assets/skills/wk-init/SKILL.md

@@ -7,10 +7,10 @@ disable-model-invocation: true
 # Init
 
 1. Load this skill explicitly through OpenCode's `skill` tool.
-2. Call the read-only `workflow_toolkit_init_status` context tool; its result is ground truth.
+2. Call the read-only `workit_init_status` context tool; its result is ground truth.
 3. Draft an exact preview of each missing scaffold and the active VCS provider.
 4. For each guarded mutation, use native `question` with concise choices and allow a custom answer.
-5. Call `workflow_toolkit_init_apply` only after approval with `confirmed: true` and the chosen action.
+5. Call `workit_init_apply` only after approval with `confirmed: true` and the chosen action.
 6. Report the structured success, failure stage, or partial result; never infer success.
 
 Never ask for or accept tokens in chat. For missing YouTrack configuration, preview `youtrack_scaffold`; for missing VCS configuration, ask GitLab or GitHub, preview `vcs_scaffold`, and pass `vcs_provider`. Both provider token placeholders may be created, but identify which one is active. Show the returned token-create URL and local edit path after apply. Verification remains a separate `wk-status` run. `todowrite` and `task` are unnecessary here.
@@ -24,8 +24,8 @@ When the user wants to personalize the toolkit (locale, timezone, branch policy)
 3. **Branch policy preset** — gitflow / github-flow / trunk-based / custom.
 4. **Custom branch lists** (only when preset = custom): allowed patterns (`feature/*`, `codex/*`, …) and protected names (`main`, …).
 
-Then call `workflow_toolkit_init_apply` with `action: "config"`, `confirmed: true`, and the answered values. Report the written `config.json` path and its contents.
+Then call `workit_init_apply` with `action: "config"`, `confirmed: true`, and the answered values. Report the written `config.json` path and its contents.
 
-After config, call `workflow_toolkit_init_apply` with `action: "gitignore"` and `confirmed: true` to ensure the project `.gitignore` covers `docs/*/sdd/` and common OS/editor entries (creates it if missing, preserves existing entries).
+After config, call `workit_init_apply` with `action: "gitignore"` and `confirmed: true` to ensure the project `.gitignore` covers `docs/*/sdd/` and common OS/editor entries (creates it if missing, preserves existing entries).
 
-After gitignore, call `workflow_toolkit_init_apply` with `action: "hygiene"`, `confirmed: true`, and `include_open_source: true` for open-source repos — creates CHANGELOG.md (Keep a Changelog), README.md, .editorconfig, .gitattributes, and optionally LICENSE + CONTRIBUTING.md. Never overwrites existing files.
+After gitignore, call `workit_init_apply` with `action: "hygiene"`, `confirmed: true`, and `include_open_source: true` for open-source repos — creates CHANGELOG.md (Keep a Changelog), README.md, .editorconfig, .gitattributes, and optionally LICENSE + CONTRIBUTING.md. Never overwrites existing files.

package/assets/skills/wk-status/SKILL.md

@@ -7,10 +7,10 @@ disable-model-invocation: true
 # Status
 
 1. Load this skill explicitly through OpenCode's `skill` tool.
-2. Call the read-only `workflow_toolkit_status` context tool once; its result is ground truth.
+2. Call the read-only `workit_status` context tool once; its result is ground truth.
 3. Draft the health report from structured facts.
 4. This workflow has no guarded mutation and does not need `question`.
 5. Do not call any mutation tool.
 6. Report the structured success, failure stage, or partial result; never infer success.
 
-Show every `items[]` result, the resolved YouTrack settings and verification, the VCS provider and verification, and the exact `ready` verdict. For placeholders, point to the returned token creation and edit paths; never request tokens in chat. Use only `workflow_toolkit_status` and report its structured state. Do not run shell, Git, direct HTTP, isolated token verification, or any mutation. `todowrite` and `task` are unnecessary for this read-only workflow.
+Show every `items[]` result, the resolved YouTrack settings and verification, the VCS provider and verification, and the exact `ready` verdict. For placeholders, point to the returned token creation and edit paths; never request tokens in chat. Use only `workit_status` and report its structured state. Do not run shell, Git, direct HTTP, isolated token verification, or any mutation. `todowrite` and `task` are unnecessary for this read-only workflow.

package/assets/templates/execution-contract.md

@@ -59,6 +59,8 @@ For each top-level task absent from `completed_task_ids`:
 
 Run a separate full-branch code review, then `workflow_verify`. Present the full `<SDD_DIR>/advisories.md` roll-up once, then use native `question` so the user can choose which advisory items to fix, discuss, or discard. Report exact check results and never infer success. Use `workflow_git_context` for a commit preview and load `wk-commit` through `skill` for an approved commit. If working state contains a stash reference, preview reapplication through `question`, then call `workflow_branch_setup` with `confirmed: true` after approval.
 
+**Mandatory:** end the run by calling `workflow_plan_complete` (OpenCode/Cursor) or the CLI `workit flow complete` (CLI host) after the final task once the SDD ledger is complete (all task IDs appended) and `workflow_verify` passes — a complete ledger and green verification are the tool's gates. Never finish the run while the plan is still `active`.
+
 ## Task order
 
 <TASK_LIST>

package/assets/templates/plan-template.md

@@ -9,6 +9,8 @@
 
 ## Global Constraints
 
+- Each task lands exactly one contiguous non-empty commit range (`base..head`): fix rounds append commits to that range and never rewrite/amend an active review range; each progress line records the task's real base..head shas.
+- The final task ends execution with `workflow_plan_complete` (or the CLI `workit flow complete`) once the SDD ledger is complete and repository verification passes — a run never finishes while the plan is still `active`.
 - <project-wide requirements, one line each>
 
 ---

package/assets/vendor/superpowers/skills/subagent-driven-development/SKILL.md

@@ -63,6 +63,7 @@ digraph process {
     "Read plan, note context and global constraints, create todos" [shape=box];
     "More tasks remain?" [shape=diamond];
     "Dispatch final code reviewer subagent (../requesting-code-review/code-reviewer.md)" [shape=box];
+    "Run verification, then workflow_plan_complete once the ledger is complete and verification passes" [shape=box];
     "Use superpowers:finishing-a-development-branch" [shape=box style=filled fillcolor=lightgreen];
 
     "Read plan, note context and global constraints, create todos" -> "Dispatch implementer subagent (./implementer-prompt.md)";
@@ -78,10 +79,13 @@ digraph process {
     "Mark task complete in todo list and progress ledger" -> "More tasks remain?";
     "More tasks remain?" -> "Dispatch implementer subagent (./implementer-prompt.md)" [label="yes"];
     "More tasks remain?" -> "Dispatch final code reviewer subagent (../requesting-code-review/code-reviewer.md)" [label="no"];
-    "Dispatch final code reviewer subagent (../requesting-code-review/code-reviewer.md)" -> "Use superpowers:finishing-a-development-branch";
+    "Dispatch final code reviewer subagent (../requesting-code-review/code-reviewer.md)" -> "Run verification, then workflow_plan_complete once the ledger is complete and verification passes";
+    "Run verification, then workflow_plan_complete once the ledger is complete and verification passes" -> "Use superpowers:finishing-a-development-branch";
 }
 ```
 
+**Mandatory completion:** after the final whole-branch review, run repository verification. Once the SDD ledger is complete and verification passes, end the run by calling `workflow_plan_complete` (or the CLI `workit flow complete`) — a complete ledger and green verification are the tool's gates. Never finish while the plan is still `active`.
+
 ## Pre-Flight Plan Review
 
 Before dispatching Task 1, scan the plan once for conflicts:
@@ -257,6 +261,10 @@ a ledger file, not only in todos.
 - When a task's review comes back clean, append one line to the ledger in
   the same message as your other bookkeeping:
   `Task N: complete (commits <base7>..<head7>, review clean)`.
+- Each task produces exactly one contiguous non-empty commit range: fix
+  rounds append commits to it, never amend or rewrite an active review
+  range, and the ledger progress line records the task's real base..head
+  shas.
 - The ledger is your recovery map: the commits it names exist in git even
   when your context no longer remembers creating them. After compaction,
   trust the ledger and `git log` over your own recollection.

package/dist/plugin.js

@@ -316,9 +316,9 @@ var compiledOpenCodeSections = () => {
 
 // packages/workit-opencode/src/bootstrap.ts
 var root = fileURLToPath(new URL("../assets/", import.meta.url));
-var marker = "<workflow-toolkit-contract>";
+var marker = "<workit-contract>";
 var cached;
-var loadWorkflowBootstrap = (rootDir) => {
+var loadWorkitBootstrap = (rootDir) => {
   const contractPath = path3.join(rootDir, "templates", "superpowers-doc-contract.md");
   try {
     return readFileSync3(contractPath, "utf8");
@@ -326,10 +326,10 @@ var loadWorkflowBootstrap = (rootDir) => {
     return null;
   }
 };
-var getWorkflowBootstrap = () => {
+var getWorkitBootstrap = () => {
   if (cached !== undefined)
     return cached;
-  const contract = loadWorkflowBootstrap(root);
+  const contract = loadWorkitBootstrap(root);
   if (contract === null) {
     cached = null;
     return null;
@@ -364,7 +364,7 @@ On success, use native \`question\` with exactly: Subagent-driven, Inline, Hando
 When the user asks about a library, framework, or API reference, prefer live docs (e.g. Context7 MCP \`resolve-library-id\` + \`query-docs\`) over training-data guesses.
 ${userSections ? `
 ${userSections}
-` : ""}</workflow-toolkit-contract>`;
+` : ""}</workit-contract>`;
   return cached;
 };
 
@@ -1132,10 +1132,22 @@ function isWorkitPlugin(value) {
   const pkgPath = s.includes("/packages/workit-opencode/") || s.includes("/packages/workit-cursor/") || s.includes("/node_modules/@brainervirus/workit-opencode/") || s.includes("/node_modules/@brainervirus/workit-cursor/");
   return named(s, "workflow-toolkit") || named(s, "workflow-toolkit-opencode") || named(s, "local/workflow-toolkit") || named(s, "workit") || named(s, "local/workit") || named(s, "@brainervirus/workit-opencode") || named(s, "@brainervirus/workit-cursor") || url && pkgPath || s.startsWith("git+file://") && s.includes("workflow-toolkit");
 }
-var CURSOR_RUNTIME_PACKAGE = "@brainervirus/workit-cursor@0.8.0";
+var CURSOR_RUNTIME_PACKAGE = "@brainervirus/workit-cursor@latest";
+function cursorMcpServerEntry(_packageDir) {
+  return {
+    command: "npx",
+    args: [
+      "-y",
+      "--prefer-online",
+      `--package=${CURSOR_RUNTIME_PACKAGE}`,
+      "workit-cursor-mcp",
+      "${workspaceFolder}"
+    ]
+  };
+}
 function cursorHooksEntry(_packageDir) {
   return {
-    command: `npx -y --package=${CURSOR_RUNTIME_PACKAGE} workit-cursor-session-start`,
+    command: `npx -y --prefer-online --package=${CURSOR_RUNTIME_PACKAGE} workit-cursor-session-start`,
     args: []
   };
 }
@@ -1505,12 +1517,9 @@ var registeredCursorLauncher = (res) => {
     return "invalid";
   }
   const executable = path10.basename(command).toLowerCase();
+  const canonical = cursorMcpServerEntry("").args;
   if (executable === "npx" || executable === "npx.exe" || executable === "npx.cmd") {
-    if (args[0] !== "-y")
-      return "invalid";
-    if (args[1] !== `--package=${CURSOR_RUNTIME_PACKAGE}`)
-      return "invalid";
-    if (args[2] !== "workit-cursor-mcp")
+    if (args.length !== canonical.length || args.some((a, i) => a !== canonical[i]))
       return "invalid";
     return { kind: "npx" };
   }
@@ -1538,6 +1547,18 @@ var registeredCursorHook = (res) => {
     return "invalid";
   return typeof entry.command === "string" ? entry.command : "invalid";
 };
+var validLocalDistHook = (command, res) => {
+  const m = /^node\s+(.+)$/.exec(command.trim());
+  if (!m)
+    return false;
+  const entry = m[1].trim();
+  if (!path10.isAbsolute(entry))
+    return false;
+  if (path10.resolve(entry) !== path10.resolve(path10.join(res.cursorPluginDir, "dist", "cursor-session-start.js"))) {
+    return false;
+  }
+  return validNodeEntry(entry, "node", res.env);
+};
 var checkLauncher = (res) => {
   const dev = res.dev;
   const hosts = hostsFor(res.host);
@@ -1553,7 +1574,7 @@ var checkLauncher = (res) => {
     const hook = registeredCursorHook(res);
     if (hook === "invalid") {
       missing.push(`cursor: canonical session-start hook in ${path10.join(res.cursorPluginDir, "hooks", "hooks-cursor.json")}`);
-    } else if (hook !== null && hook !== canonicalCursorHook) {
+    } else if (hook !== null && hook !== canonicalCursorHook && !validLocalDistHook(hook, res)) {
       missing.push(`cursor: canonical session-start hook in ${path10.join(res.cursorPluginDir, "hooks", "hooks-cursor.json")} (registered ${hook})`);
     }
   }
@@ -3284,7 +3305,7 @@ function initStatusData(configDirPath = configDir()) {
     ok: fs4.existsSync(ytJson) && youtrackConfig !== null && !("error" in youtrackConfig),
     path: fs4.existsSync(ytJson) ? resolvePath(ytJson) : path16.resolve(ytJson),
     config_edit_path: resolvePath(ytJson),
-    fix: "workflow_toolkit_init_apply action=youtrack_scaffold"
+    fix: "workit_init_apply action=youtrack_scaffold"
   });
   const ytTokenPath = youtrackConfig?.tokenFile ?? path16.join(configDirPath, "youtrack.token");
   const tokenText = fs4.existsSync(ytTokenPath) ? fs4.readFileSync(ytTokenPath, "utf8").trim() : "";
@@ -3347,7 +3368,7 @@ function initStatusData(configDirPath = configDir()) {
     ok: fs4.existsSync(vcsJson) && vcsCfg !== null && !("error" in vcsCfg),
     path: fs4.existsSync(vcsJson) ? resolvePath(vcsJson) : path16.resolve(vcsJson),
     config_edit_path: resolvePath(vcsJson),
-    fix: "workflow_toolkit_init_apply action=vcs_scaffold"
+    fix: "workit_init_apply action=vcs_scaffold"
   });
   const provActive = vcsCfg && !("error" in vcsCfg) ? vcsCfg.provider : null;
   const tokenItem = (tid, label, rawPath, providerKey) => {
@@ -4352,8 +4373,13 @@ function sddReviewPackage({
   const contained = resolveDocsPath({ workspace_root, path: sdd_dir });
   if (!contained.ok)
     return { error: contained.error };
+  if (base_sha === head_sha) {
+    return {
+      error: `empty commit range (base_sha ${base_sha} === head_sha ${head_sha}): nothing to review`,
+      code: "empty_commit_range"
+    };
+  }
   const dir = contained.path;
-  mkdirSync8(dir, { recursive: true });
   const base7 = base_sha.slice(0, 7);
   const head7 = head_sha.slice(0, 7);
   const diffPath = path19.join(dir, `review-${base7}..${head7}.diff`);
@@ -4363,6 +4389,13 @@ function sddReviewPackage({
       encoding: "utf8",
       stdio: ["pipe", "pipe", "pipe"]
     });
+    if (diff.trim() === "") {
+      return {
+        error: `empty commit range (${base_sha}..${head_sha}): diff is empty, nothing to review`,
+        code: "empty_commit_range"
+      };
+    }
+    mkdirSync8(dir, { recursive: true });
     writeFileSync10(diffPath, diff, "utf8");
     const rel = posix2(path19.relative(contained.base, diffPath));
     return { diff_path: rel, base_sha, head_sha, base7, head7 };
@@ -4370,7 +4403,7 @@ function sddReviewPackage({
     return { error: error instanceof Error ? error.message : "git diff failed" };
   }
 }
-var PROGRESS_RE = /^Task\s+\d+:\s+complete\s+\(commits\s+[0-9a-f]{7,40}\.\.[0-9a-f]{7,40},/i;
+var PROGRESS_RE = /^Task\s+\d+:\s+complete\s+\(commits\s+([0-9a-f]{7,40})\.\.([0-9a-f]{7,40}),/i;
 function sddAppendProgress({
   progress_path,
   line,
@@ -4381,7 +4414,8 @@ function sddAppendProgress({
     return { error: contained.error };
   const path_ = contained.path;
   const trimmed = line.trim();
-  if (!PROGRESS_RE.test(trimmed)) {
+  const match = PROGRESS_RE.exec(trimmed);
+  if (!match || match[1].toLowerCase() === match[2].toLowerCase()) {
     return { error: "invalid progress line format" };
   }
   if (existsSync12(path_) && statSync5(path_).isDirectory()) {
@@ -5351,9 +5385,6 @@ var resetForSpecDrift = (state) => ({
 var resetForPlanDrift = (state) => ({
   ...state,
   plan: { ...state.plan, status: "draft", evidence: null, approved_digest: null },
-  menu: { presented: false, chosen: "", evidence: null },
-  execution: { status: "pending", mode: null, evidence: null },
-  handoff_destination: false,
   updated_at: Date.now()
 });
 var driftCodeFor = (root2, relPath, storedDigest) => {
@@ -6117,7 +6148,7 @@ var COORDINATOR_WRITE_TOOLS = [
   "workflow_template_edit",
   "workflow_changelog_apply",
   "workflow_branch_setup",
-  "workflow_toolkit_init_apply",
+  "workit_init_apply",
   "workflow_docs_promote",
   "workflow_docs_layout",
   "workflow_docs_repo_link",
@@ -19470,12 +19501,12 @@ function createRepoTools(runtime = defaultRuntime) {
     return output(scriptResult(await runContext(root2, value), parse5));
   };
   return {
-    workflow_toolkit_init_status: tool({
+    workit_init_status: tool({
       description: "Inspect toolkit initialization",
       args: {},
       execute: async (_input, context2) => output(scriptResult(await runtime.initStatus(context2.directory), json2))
     }),
-    workflow_toolkit_status: tool({
+    workit_status: tool({
       description: "Inspect toolkit and repository state",
       args: {},
       execute: async (_input, context2) => output(scriptResult(await runtime.toolkitStatus(context2.directory), json2))
@@ -19623,7 +19654,7 @@ function createRepoTools(runtime = defaultRuntime) {
         })));
       }
     }),
-    workflow_toolkit_init_apply: tool({
+    workit_init_apply: tool({
       description: "Apply a confirmed toolkit initialization action",
       args: {
         confirmed: tool.schema.boolean(),
@@ -22074,8 +22105,8 @@ var plugin = async ({ client, directory }) => {
           const firstAnchor = firstUser.parts.find((part) => part.type === "text") ?? firstUser.parts[0];
           const firstText = firstUser.parts.filter((part) => part.type === "text").map((part) => part.text ?? "").join(`
 `);
-          const bootstrap = getWorkflowBootstrap();
-          if (bootstrap && !firstText.includes("<workflow-toolkit-contract>")) {
+          const bootstrap = getWorkitBootstrap();
+          if (bootstrap && !firstText.includes("<workit-contract>")) {
             firstUser.parts.unshift({
               id: firstAnchor.id,
               sessionID: firstAnchor.sessionID,

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@brainervirus/workit-opencode",
-  "version": "0.8.5",
+  "version": "0.8.7",
   "private": false,
   "description": "Workit OpenCode plugin (thin wrapper over @brainervirus/workit-core)",
   "keywords": [
@@ -34,7 +34,7 @@
     "typecheck": "tsc --noEmit"
   },
   "dependencies": {
-    "@brainervirus/workit-core": "^0.8.5"
+    "@brainervirus/workit-core": "^0.8.7"
   },
   "devDependencies": {
     "@opencode-ai/plugin": "1.17.7"