opencode-orchestrator 0.1.53 → 0.1.55
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/README.md +71 -141
- package/bin/orchestrator-linux-arm64 +0 -0
- package/bin/orchestrator-linux-x64 +0 -0
- package/dist/index.js +1 -1
- package/package.json +1 -1
package/README.md
CHANGED
|
@@ -2,78 +2,23 @@
|
|
|
2
2
|
<img src="assets/logo.png" alt="Logo" width="200" />
|
|
3
3
|
</div>
|
|
4
4
|
|
|
5
|
-
# OpenCode Orchestrator
|
|
5
|
+
# OpenCode Orchestrator
|
|
6
6
|
|
|
7
7
|
> **Multi-Agent Plugin for [OpenCode](https://opencode.ai)**
|
|
8
8
|
|
|
9
9
|
[](LICENSE)
|
|
10
10
|
[](https://www.npmjs.com/package/opencode-orchestrator)
|
|
11
|
-
[](https://www.npmjs.com/package/opencode-orchestrator)
|
|
12
|
-
[](https://opencode.ai)
|
|
13
|
-
|
|
14
|
-
**OpenCode Orchestrator** is a collaborative framework that enables **low-benchmark models to deliver senior-level engineering results**.
|
|
15
|
-
|
|
16
|
-
By maximizing the **method of agent collaboration**, we overcome the inherent limitations of individual AI models. We don't just "chat" with AI; we use a structured engineering layer to ensure complex missions are executed with 100% reliability and relentlessly pushed to completion, regardless of the model's price point.
|
|
17
|
-
|
|
18
|
-
**Core Philosophy: Excellence through Collaboration**
|
|
19
|
-
|
|
20
|
-
We believe that **a perfect collaboration method is superior to individual intelligence**.
|
|
21
|
-
|
|
22
|
-
* **Systems Engineering Fusion**: We integrate Operating System principles (Scheduling), Distributed Systems (Actor Model), and Algorithm Theory (Divide & Conquer) to transform unpredictable LLMs into a **controlled computing resource**.
|
|
23
|
-
* **Relentless PDCA Loop**: Every change follows a strict **Plan-Do-Check-Act** cycle. This systematic approach ensures that high-level professional tasks are completed without the quality decay or hallucinations typical of raw LLM outputs.
|
|
24
|
-
* **Architecture over Benchmarks**: By decomposing missions into atomic, verifiable tasks, we extract **high-fidelity outcomes** from cost-effective models, proving that superior architecture can outperform raw scale.
|
|
25
11
|
|
|
26
12
|
---
|
|
27
13
|
|
|
28
|
-
##
|
|
14
|
+
## What is this?
|
|
29
15
|
|
|
30
|
-
|
|
31
|
-
|-------------|-------------------|
|
|
32
|
-
| Expensive "Smart" Model required | **Affordable Model + Smart Process** |
|
|
33
|
-
| High Token Costs (Huge Context) | **Token Efficient** (Filtered Context) |
|
|
34
|
-
| Linear, Slow Execution | **Parallel, Fast Execution** |
|
|
35
|
-
| Errors compound silently | **Self-Correcting Verification Loops** |
|
|
36
|
-
| "Hope it works" | **Strategic Micro-Tasking** |
|
|
16
|
+
A 6-agent collaborative system that turns **affordable LLMs into reliable engineering teams**.
|
|
37
17
|
|
|
38
|
-
|
|
39
|
-
|
|
40
|
-
-
|
|
41
|
-
-
|
|
42
|
-
- **⚡ Parallel DAG** — Concurrent execution for speed and efficiency
|
|
43
|
-
- **🔍 Micro-Tasking** — Atomic decomposition to prevent hallucinations
|
|
44
|
-
- **🛡️ Style Guardian** — Strict AST-based linting and consistency checks
|
|
45
|
-
- **🔄 Self-Healing** — Autonomous pivot strategies for complex errors
|
|
46
|
-
- **🏗️ Rust Core** — Native performance for heavy lifting
|
|
47
|
-
|
|
48
|
-
---
|
|
49
|
-
|
|
50
|
-
## How It Works (Parallel DAG)
|
|
51
|
-
|
|
52
|
-
Instead of a linear sequence, we use a **Directed Acyclic Graph (DAG)** to model your mission.
|
|
53
|
-
|
|
54
|
-
```
|
|
55
|
-
Mission Start (/task)
|
|
56
|
-
│
|
|
57
|
-
▼
|
|
58
|
-
┌───────────────┐
|
|
59
|
-
│ PLANNER │ (Architect)
|
|
60
|
-
└───────┬───────┘
|
|
61
|
-
│
|
|
62
|
-
┌───────┴───────┐
|
|
63
|
-
│ │ (Parallel Streams)
|
|
64
|
-
▼ ▼
|
|
65
|
-
┌───────────┐ ┌───────────┐
|
|
66
|
-
│ Tasks (A) │ │ Tasks (B) │
|
|
67
|
-
└─────┬─────┘ └─────┬─────┘
|
|
68
|
-
│ │
|
|
69
|
-
└───────┬───────┘
|
|
70
|
-
▼
|
|
71
|
-
┌───────────────┐
|
|
72
|
-
│ REVIEWER │ (Style Guardian)
|
|
73
|
-
└───────┬───────┘
|
|
74
|
-
▼
|
|
75
|
-
✅ MISSION COMPLETE
|
|
76
|
-
```
|
|
18
|
+
- **Atomic Decomposition** — Tasks broken into verifiable micro-units
|
|
19
|
+
- **PDCA Loop** — Plan → Do → Check → Act (self-correcting)
|
|
20
|
+
- **Parallel DAG** — Independent tasks run concurrently
|
|
21
|
+
- **Style Guardian** — Reviewer catches all errors before merge
|
|
77
22
|
|
|
78
23
|
---
|
|
79
24
|
|
|
@@ -83,31 +28,22 @@ Instead of a linear sequence, we use a **Directed Acyclic Graph (DAG)** to model
|
|
|
83
28
|
npm install -g opencode-orchestrator
|
|
84
29
|
```
|
|
85
30
|
|
|
86
|
-
|
|
87
|
-
> The plugin will automatically register itself in `~/.config/opencode/opencode.json` with its absolute path.
|
|
88
|
-
|
|
89
|
-
### Troubleshooting
|
|
90
|
-
If the command `/task` does not appear:
|
|
91
|
-
1. Uninstall: `npm uninstall -g opencode-orchestrator`
|
|
92
|
-
2. Clear config: `rm -rf ~/.config/opencode` (Warning: resets all plugins)
|
|
93
|
-
3. Reinstall: `npm install -g opencode-orchestrator`
|
|
94
|
-
|
|
31
|
+
Restart OpenCode after installation.
|
|
95
32
|
|
|
96
33
|
---
|
|
97
34
|
|
|
98
|
-
|
|
35
|
+
## Usage
|
|
99
36
|
|
|
100
37
|
```bash
|
|
101
38
|
/task "Implement user authentication with JWT"
|
|
102
39
|
```
|
|
103
40
|
|
|
104
41
|
The Orchestrator will:
|
|
105
|
-
1. **
|
|
106
|
-
2. **
|
|
107
|
-
3. **
|
|
108
|
-
4. **
|
|
109
|
-
5. **
|
|
110
|
-
6. **Self-Heal** if errors occur
|
|
42
|
+
1. **Plan** — Decompose into atomic tasks
|
|
43
|
+
2. **Search** — Find patterns and context
|
|
44
|
+
3. **Code** — Implement with precision
|
|
45
|
+
4. **Review** — Verify via quality gate
|
|
46
|
+
5. **Fix** — Self-heal if errors occur
|
|
111
47
|
|
|
112
48
|
---
|
|
113
49
|
|
|
@@ -115,85 +51,79 @@ The Orchestrator will:
|
|
|
115
51
|
|
|
116
52
|
| Agent | Role |
|
|
117
53
|
|-------|------|
|
|
118
|
-
|
|
|
119
|
-
|
|
|
120
|
-
|
|
|
121
|
-
|
|
|
122
|
-
|
|
|
123
|
-
|
|
|
54
|
+
| Orchestrator | Team leader — coordinates the mission |
|
|
55
|
+
| Planner | Decomposes work into atomic tasks |
|
|
56
|
+
| Coder | Implements one task at a time |
|
|
57
|
+
| Reviewer | Quality gate — catches all errors |
|
|
58
|
+
| Fixer | Targeted error resolution |
|
|
59
|
+
| Searcher | Finds context before coding |
|
|
124
60
|
|
|
125
61
|
---
|
|
126
62
|
|
|
127
|
-
|
|
128
|
-
- **[Configuration](docs/CONFIGURATION.md)**: `opencode.toml` setup guide.
|
|
129
|
-
|
|
130
|
-
---
|
|
131
|
-
|
|
132
|
-
## Open Source
|
|
133
|
-
|
|
134
|
-
MIT License. No telemetry. No backdoors.
|
|
135
|
-
|
|
136
|
-
[github.com/agnusdei1207/opencode-orchestrator](https://github.com/agnusdei1207/opencode-orchestrator)
|
|
63
|
+
## How It Works
|
|
137
64
|
|
|
138
|
-
|
|
139
|
-
|
|
140
|
-
|
|
141
|
-
|
|
142
|
-
|
|
143
|
-
|
|
144
|
-
|
|
65
|
+
```
|
|
66
|
+
/task "mission"
|
|
67
|
+
│
|
|
68
|
+
▼
|
|
69
|
+
┌─────────────┐
|
|
70
|
+
│ PLANNER │
|
|
71
|
+
└──────┬──────┘
|
|
72
|
+
│
|
|
73
|
+
┌──────┴──────┐
|
|
74
|
+
▼ ▼
|
|
75
|
+
[Task A] [Task B] (parallel)
|
|
76
|
+
│ │
|
|
77
|
+
└──────┬──────┘
|
|
78
|
+
▼
|
|
79
|
+
┌─────────────┐
|
|
80
|
+
│ REVIEWER │
|
|
81
|
+
└──────┬──────┘
|
|
82
|
+
▼
|
|
83
|
+
✅ DONE
|
|
84
|
+
```
|
|
145
85
|
|
|
146
86
|
---
|
|
147
87
|
|
|
148
|
-
##
|
|
149
|
-
|
|
150
|
-
We have moved beyond simple "chatbots". **OpenCode Orchestrator** implements a **Deterministic Engineering Layer** built on top of the stochastic nature of LLMs,
|
|
151
|
-
- **Strict PDCA Loop**: Guarantees quality via Plan-Do-Check-Act cycle.
|
|
152
|
-
- **🔍 Micro-tasking**: Atomic decomposition to prevent hallucinations.
|
|
153
|
-
- **🛡️ Style Guardian**: Strict AST-based linting and consistency checks by the Reviewer.
|
|
154
|
-
- **🔄 Self-healing**: Autonomous pivoting strategies for complex errors.
|
|
155
|
-
- **Distributed Cognitive System**: Intelligence layer acting like an OS Kernel.
|
|
156
|
-
- **File-Based State**: Uses physical filesystem as RAM, ignoring context limits.
|
|
157
|
-
We treat agents as **Semantic Compute Units**. By applying rigorous Computer Science principles, we achieve a level of reliability that no single model can match.
|
|
158
|
-
|
|
159
|
-
### 🧬 The "Grand Fusion" of Methodologies
|
|
160
|
-
We explicitly fused three massive domains into one seamless workflow:
|
|
161
|
-
|
|
162
|
-
1. **PDCA Methodology (Quality Assurance)**:
|
|
163
|
-
* **Plan (Planner)**: Recursively decomposes mission into atomic tasks ($O(log n)$).
|
|
164
|
-
* **Do (Coder)**: Executes the atomic tasks in parallel (Distributed Actions).
|
|
165
|
-
* **Check (Reviewer)**: Acts as a **Byzantine Fault Tolerance** node, strictly validating code against requirements.
|
|
166
|
-
* **Act (Orchestrator)**: Merges successful states or **Pivots** (Dynamic Programming) if failures occur.
|
|
88
|
+
## PDCA Control Loop
|
|
167
89
|
|
|
168
|
-
|
|
169
|
-
|
|
170
|
-
|
|
171
|
-
|
|
172
|
-
|
|
173
|
-
|
|
174
|
-
|
|
175
|
-
|
|
176
|
-
|
|
90
|
+
```
|
|
91
|
+
┌─────────────────────────────────────────────────────┐
|
|
92
|
+
│ PDCA LOOP │
|
|
93
|
+
│ │
|
|
94
|
+
│ PLAN ──→ DO ──→ CHECK ──→ ACT │
|
|
95
|
+
│ │ │ │ │ │
|
|
96
|
+
│ Planner Coder Reviewer Orchestrator │
|
|
97
|
+
│ ↓ ↓ ↓ ↓ │
|
|
98
|
+
│ DAG Code Pass/Fail Merge/Pivot │
|
|
99
|
+
│ │ │
|
|
100
|
+
│ ┌───────┴───────┐ │
|
|
101
|
+
│ ↓ ↓ │
|
|
102
|
+
│ ✅ Pass ❌ Fail → Fixer │
|
|
103
|
+
└─────────────────────────────────────────────────────┘
|
|
104
|
+
```
|
|
177
105
|
|
|
178
|
-
|
|
106
|
+
## Troubleshooting
|
|
179
107
|
|
|
108
|
+
If `/task` doesn't appear:
|
|
180
109
|
```bash
|
|
181
|
-
|
|
110
|
+
npm uninstall -g opencode-orchestrator
|
|
111
|
+
npm install -g opencode-orchestrator
|
|
182
112
|
```
|
|
183
113
|
|
|
184
|
-
|
|
114
|
+
---
|
|
185
115
|
|
|
186
|
-
|
|
116
|
+
## Docs
|
|
187
117
|
|
|
188
|
-
|
|
189
|
-
|
|
190
|
-
3. **🚀 Phase 3: Parallel Execution**: The **Orchestrator** identifies independent tasks and runs them concurrently.
|
|
191
|
-
4. **🛡️ Phase 4: Sync & Verify**: The **Reviewer** acts as the gatekeeper. It checks syntax, logic, and *cross-file consistency*.
|
|
192
|
-
5. **💰 Phase 5: Cost-Effective Completion**: We achieve "Senior Developer" results at "Junior Intern" prices.
|
|
118
|
+
- [Architecture](docs/ARCHITECTURE.md)
|
|
119
|
+
- [Plugin Troubleshooting](docs/PLUGIN_TROUBLESHOOTING.md)
|
|
193
120
|
|
|
194
121
|
---
|
|
195
122
|
|
|
196
|
-
##
|
|
123
|
+
## License
|
|
124
|
+
|
|
125
|
+
MIT License. [LICENSE](LICENSE)
|
|
126
|
+
|
|
127
|
+
---
|
|
197
128
|
|
|
198
|
-
|
|
199
|
-
Updates are frequent. Keep your version fresh.
|
|
129
|
+
**Fast-Paced Development** — Updates are frequent. Keep your version fresh.
|
|
Binary file
|
|
Binary file
|
package/dist/index.js
CHANGED
|
@@ -684,7 +684,7 @@ var OrchestratorPlugin = async (input) => {
|
|
|
684
684
|
};
|
|
685
685
|
}
|
|
686
686
|
const orchestratorAgents = {
|
|
687
|
-
|
|
687
|
+
Orchestrator: {
|
|
688
688
|
name: "Orchestrator",
|
|
689
689
|
description: "Mission Commander - 6-agent collaborative AI for complex tasks",
|
|
690
690
|
systemPrompt: AGENTS.orchestrator.systemPrompt
|
package/package.json
CHANGED
|
@@ -2,7 +2,7 @@
|
|
|
2
2
|
"name": "opencode-orchestrator",
|
|
3
3
|
"displayName": "OpenCode Orchestrator",
|
|
4
4
|
"description": "Distributed Cognitive Architecture for OpenCode. Turns simple prompts into specialized multi-agent workflows (Planner, Coder, Reviewer).",
|
|
5
|
-
"version": "0.1.
|
|
5
|
+
"version": "0.1.55",
|
|
6
6
|
"author": "agnusdei1207",
|
|
7
7
|
"license": "MIT",
|
|
8
8
|
"repository": {
|