@polderlabs/bizar 5.5.5 → 5.5.6

package/cli/plow-through.test.mjs

@@ -0,0 +1,55 @@
+/**
+ * cli/plow-through.test.mjs
+ *
+ * Tests for the /plow-through slash command file.
+ */
+import { test, describe } from 'node:test';
+import assert from 'node:assert/strict';
+import { readFileSync, existsSync } from 'node:fs';
+import { join, dirname } from 'node:path';
+import { fileURLToPath } from 'node:url';
+
+const __dirname = dirname(fileURLToPath(import.meta.url));
+const PROJECT_ROOT = join(__dirname, '..');
+const CMD_PATH = join(PROJECT_ROOT, 'config', 'commands', 'plow-through.md');
+
+describe('/plow-through command file', () => {
+  test('file exists at config/commands/plow-through.md', () => {
+    assert.equal(existsSync(CMD_PATH), true, 'plow-through.md must exist');
+  });
+
+  test('YAML frontmatter has description field', () => {
+    const content = readFileSync(CMD_PATH, 'utf8');
+    assert.match(content, /^---\ndescription:/m, 'frontmatter must have description');
+  });
+
+  test('YAML frontmatter has agent field set to odin', () => {
+    const content = readFileSync(CMD_PATH, 'utf8');
+    assert.match(content, /^---\n.*\nagent: odin$/ms, 'frontmatter agent must be odin');
+  });
+
+  test('body has content (more than 5 lines)', () => {
+    const content = readFileSync(CMD_PATH, 'utf8');
+    // Strip frontmatter
+    const body = content.replace(/^---[\s\S]*?---\n/, '');
+    const lines = body.trim().split('\n').filter(l => l.trim().length > 0);
+    assert.ok(lines.length > 5, `body should have content, got ${lines.length} non-empty lines`);
+  });
+
+  test('body contains autonomous-mode contract keywords', () => {
+    const content = readFileSync(CMD_PATH, 'utf8');
+    const body = content.replace(/^---[\s\S]*?---\n/, '');
+    const lower = body.toLowerCase();
+    assert.ok(lower.includes('no clarifying questions') || lower.includes('no clarifying'), 'body must state no clarifying questions');
+    assert.ok(lower.includes('parallel') || lower.includes('dispatch'), 'body must mention parallel dispatch');
+    assert.ok(lower.includes('work to completion') || lower.includes('complete'), 'body must state work-to-completion');
+  });
+
+  test('body contains when NOT to use section', () => {
+    const content = readFileSync(CMD_PATH, 'utf8');
+    const lower = content.toLowerCase();
+    assert.ok(lower.includes('when not to use'), 'body must have a when NOT to use section');
+  });
+});
+
+console.log('  plow-through.test.mjs loaded — run with: node --test cli/plow-through.test.mjs');

package/config/commands/plow-through.md

@@ -0,0 +1,47 @@
+---
+description: Autonomous mode — work fully independently, make all decisions, complete the task end-to-end without asking the user anything.
+agent: odin
+---
+
+# Plow Through — Autonomous Mode
+
+You are in `/plow-through` mode. The user has invoked this command to tell you: **work autonomously, don't ask, decide things yourself, complete the task end-to-end.**
+
+## Contract
+
+- **No clarifying questions.** If the request is ambiguous, use the most reasonable interpretation based on project context. If you genuinely cannot proceed without user input (e.g., a destructive action requiring explicit authorization), log the blocker in your final report and continue with everything else.
+- **Decide things yourself.** Use your judgment. Read `.bizar/PROJECT.md`, `FINAL_GOAL.md`, `ROADMAP.md`, and search the memory vault (`bizar memory search "<topic>"`) for prior context before deciding.
+- **Split into parallel work streams.** Always dispatch 2+ subagents in parallel when the work is decomposable. Each stream must have a disjoint file scope.
+- **Work to completion.** Don't stop at "I did X, should I continue?". The task is complete when: the deliverable exists, tests pass, changes are committed and pushed (where applicable).
+- **Report at the end.** Summarize what was done, what tests ran, any blockers encountered.
+
+## Background agents for long-running work
+
+Use `bizar_spawn_background` (or the dashboard UI) to spawn background agents for tasks that span more than a few minutes. Check on them later via `bizar_status` or the Background Agents panel.
+
+## When to use
+
+- Multi-file refactors that don't require user approval
+- Bug-fix sweeps across a known surface area
+- Implementing a clearly-spec'd feature from the roadmap
+- Migration tasks (e.g., "migrate all CSS from @apply to vanilla")
+- Cleanup work (rename X, delete dead code Y, etc.)
+
+## When NOT to use
+
+- Anything that touches auth, billing, or destructive operations on user data
+- Architectural decisions with multiple valid approaches (use `/plan` first)
+- Tasks where you genuinely need user input on a key decision
+- Anything where being wrong has high consequences (merges to main, security patches)
+
+## Execution pattern
+
+1. Read project context (`.bizar/PROJECT.md`, `FINAL_GOAL.md`, `ROADMAP.md`)
+2. Search memory for prior context (`bizar memory search "<topic>"`)
+3. Decompose into independent work streams
+4. Dispatch streams via `task` to @thor and @tyr in parallel
+5. After streams return: run test gate
+6. Fix any test failures
+7. Update self-improvement log (`.bizar/AGENTS_SELF_IMPROVEMENT.md`)
+8. Commit + push (delegated to @hermod)
+9. Report final outcome

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@polderlabs/bizar",
-  "version": "5.5.5",
+  "version": "5.5.6",
   "description": "Norse-pantheon multi-agent system for opencode — 13 agents across 4 cost tiers with cost-aware routing, plans, and a configurable agent harness. v4 ships as a single npm package bundling the dashboard server, opencode plugin, and typed SDK.",
   "type": "module",
   "bin": {