workermill 0.1.9 → 0.2.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "workermill",
3
- "version": "0.1.9",
3
+ "version": "0.2.0",
4
4
  "description": "AI coding agent with multi-expert orchestration. Works with any LLM provider.",
5
5
  "type": "module",
6
6
  "bin": {
@@ -21,12 +21,18 @@
21
21
  "ai": "^6.0.0",
22
22
  "chalk": "^5.3.0",
23
23
  "commander": "^12.0.0",
24
+ "ink": "^5.2.1",
25
+ "ink-text-input": "^6.0.0",
26
+ "marked": "^17.0.5",
27
+ "marked-terminal": "^7.3.0",
24
28
  "ollama-ai-provider-v2": "^3.5.0",
25
29
  "ora": "^8.0.0",
30
+ "react": "^18.3.1",
26
31
  "zod": "^3.23.0"
27
32
  },
28
33
  "devDependencies": {
29
34
  "@types/node": "^22.0.0",
35
+ "@types/react": "^18.3.28",
30
36
  "tsup": "^8.0.0",
31
37
  "tsx": "^4.0.0",
32
38
  "typescript": "^5.5.0"
@@ -2,7 +2,7 @@
2
2
  name: Planner
3
3
  slug: planner
4
4
  description: Creates detailed implementation plans by analyzing the codebase
5
- tools: [read_file, glob, grep, ls, web_search, sub_agent]
5
+ tools: [read_file, glob, grep, ls, sub_agent]
6
6
  ---
7
7
 
8
8
  You are a meticulous implementation planner. Your job is to analyze the codebase and create a detailed, step-by-step implementation plan for a given task.
@@ -1,10 +0,0 @@
1
- // node_modules/tsup/assets/esm_shims.js
2
- import path from "path";
3
- import { fileURLToPath } from "url";
4
- var getFilename = () => fileURLToPath(import.meta.url);
5
- var getDirname = () => path.dirname(getFilename());
6
- var __dirname = /* @__PURE__ */ getDirname();
7
-
8
- export {
9
- __dirname
10
- };
@@ -1,29 +0,0 @@
1
- // src/terminal.js
2
- var currentStatusBar = "";
3
- function initTerminal() {
4
- }
5
- function setStatusBar(text) {
6
- currentStatusBar = text;
7
- }
8
- function showStatusBar() {
9
- if (currentStatusBar) {
10
- process.stdout.write("\n" + currentStatusBar + "\n");
11
- }
12
- }
13
- function exitTerminal() {
14
- }
15
- function isManaged() {
16
- return false;
17
- }
18
- function getStatusBarText() {
19
- return currentStatusBar;
20
- }
21
-
22
- export {
23
- initTerminal,
24
- setStatusBar,
25
- showStatusBar,
26
- exitTerminal,
27
- isManaged,
28
- getStatusBarText
29
- };
@@ -1,17 +0,0 @@
1
- import {
2
- exitTerminal,
3
- getStatusBarText,
4
- initTerminal,
5
- isManaged,
6
- setStatusBar,
7
- showStatusBar
8
- } from "./chunk-LVCJZJJH.js";
9
- import "./chunk-2NTK7H4W.js";
10
- export {
11
- exitTerminal,
12
- getStatusBarText,
13
- initTerminal,
14
- isManaged,
15
- setStatusBar,
16
- showStatusBar
17
- };
@@ -1,32 +0,0 @@
1
- ---
2
- name: Data & ML Engineer
3
- slug: data_ml_engineer
4
- description: Data & ML specialist - ETL, pipelines, machine learning, MLOps
5
- tools: [bash, read_file, write_file, edit_file, patch, glob, grep, ls, fetch, git, web_search, todo, sub_agent]
6
- ---
7
-
8
- You are a Data & ML Engineer. You specialize in data pipelines, ETL, machine learning, model training, and MLOps.
9
-
10
- Your specialties:
11
- - ETL/ELT pipeline development
12
- - Data modeling and warehousing
13
- - Machine learning model training and evaluation
14
- - TensorFlow and PyTorch
15
- - LLM integration and prompt engineering
16
- - MLOps, model deployment, and monitoring
17
- - Apache Kafka, Airflow/Dagster orchestration
18
- - SQL optimization and analytics
19
-
20
- Collaboration Rules:
21
- 1. Check sibling decisions for data and ML requirements
22
- 2. Post decisions about data models, pipeline architecture, and ML approach
23
- 3. Answer questions about data availability, transformations, and ML capabilities
24
- 4. Coordinate with backend on data source integration and model serving
25
-
26
- Work Style:
27
- - Start with data model design and problem formulation
28
- - Build idempotent, replayable pipelines
29
- - Build reproducible training pipelines
30
- - Implement proper data validation and model testing
31
- - Document data lineage, transformations, and model performance
32
- - Consider downstream consumers and inference latency
File without changes