@compozy/cli 0.1.2 → 0.1.4
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 +141 -127
- package/package.json +21 -21
package/README.md
CHANGED
|
@@ -28,10 +28,10 @@ One CLI to replace scattered prompts, manual task tracking, and copy-paste revie
|
|
|
28
28
|
|
|
29
29
|
## ✨ Highlights
|
|
30
30
|
|
|
31
|
-
- **One command, 40+ agents.** Install bundled skills into Claude Code, Codex, Cursor, Droid, OpenCode, Pi, and 40+ other agents and editors with `compozy setup
|
|
32
|
-
- **Idea to code in
|
|
31
|
+
- **One command, 40+ agents.** Install bundled skills into Claude Code, Codex, Cursor, Droid, OpenCode, Pi, Gemini, and 40+ other agents and editors with `compozy setup`.
|
|
32
|
+
- **Idea to code in a structured pipeline.** Optional Issue → PRD → TechSpec → Tasks → Execution → Review. Each phase produces plain markdown artifacts that feed into the next. Start from an issue for full research and debate, or jump straight to PRD if you already have a clear scope.
|
|
33
33
|
- **Codebase-aware enrichment.** Tasks aren't generic prompts. Compozy spawns parallel agents to explore your codebase, discover patterns, and ground every task in real project context.
|
|
34
|
-
- **Multi-agent execution.** Run tasks through Claude Code, Codex, Cursor, Droid, OpenCode, or
|
|
34
|
+
- **Multi-agent execution.** Run tasks through ACP-capable runtimes like Claude Code, Codex, Cursor, Droid, OpenCode, Pi, or Gemini — just change `--ide`. Concurrent batch processing with configurable timeouts, retries, and exponential backoff, all with a live terminal UI.
|
|
35
35
|
- **Workflow memory between runs.** Agents inherit context from every previous task — decisions, learnings, errors, and handoffs. Two-tier markdown memory with automatic compaction keeps context fresh without manual bookkeeping.
|
|
36
36
|
- **Provider-agnostic reviews.** Fetch review comments from CodeRabbit, GitHub, or run AI-powered reviews internally. All normalize to the same format. Provider threads resolve automatically after fixes.
|
|
37
37
|
- **Markdown everywhere.** PRDs, specs, tasks, reviews, and ADRs are human-readable markdown files. Version-controlled, diffable, editable between steps. No vendor lock-in.
|
|
@@ -74,40 +74,29 @@ compozy setup # interactive — pick agents and skills
|
|
|
74
74
|
compozy setup --all # install everything to every detected agent
|
|
75
75
|
```
|
|
76
76
|
|
|
77
|
+
Execution runtimes are separate from skill installation. To run `compozy start` or `compozy fix-reviews`, install an ACP-capable runtime or adapter on `PATH` for the `--ide` you choose:
|
|
78
|
+
|
|
79
|
+
| Runtime | `--ide` flag | Expected ACP command |
|
|
80
|
+
| ------------ | -------------- | -------------------------------- |
|
|
81
|
+
| Claude Agent | `claude` | `claude-agent-acp` |
|
|
82
|
+
| Codex CLI | `codex` | `codex-acp` |
|
|
83
|
+
| Cursor | `cursor-agent` | `cursor-agent acp` |
|
|
84
|
+
| Droid | `droid` | `droid exec --output-format acp` |
|
|
85
|
+
| OpenCode | `opencode` | `opencode acp` |
|
|
86
|
+
| pi ACP | `pi` | `pi-acp` |
|
|
87
|
+
| Gemini CLI | `gemini` | `gemini --acp` |
|
|
88
|
+
|
|
89
|
+
When the direct ACP command is not installed, Compozy can also fall back to supported launchers such as `npx @zed-industries/codex-acp` when the launcher is available locally.
|
|
90
|
+
|
|
77
91
|
## 🔄 How It Works
|
|
78
92
|
|
|
79
|
-
|
|
80
|
-
|
|
81
|
-
|
|
82
|
-
▼
|
|
83
|
-
/cy-create-prd user-auth .compozy/tasks/user-auth/_prd.md
|
|
84
|
-
│ + Architecture Decision Records
|
|
85
|
-
▼
|
|
86
|
-
/cy-create-techspec user-auth .compozy/tasks/user-auth/_techspec.md
|
|
87
|
-
│
|
|
88
|
-
▼
|
|
89
|
-
/cy-create-tasks user-auth .compozy/tasks/user-auth/task_01.md … task_N.md
|
|
90
|
-
│
|
|
91
|
-
▼
|
|
92
|
-
compozy sync --name user-auth Refresh task workflow _meta.md
|
|
93
|
-
│
|
|
94
|
-
▼
|
|
95
|
-
compozy start --name user-auth AI agents execute each task
|
|
96
|
-
│ ↕ .compozy/tasks/user-auth/memory/
|
|
97
|
-
│
|
|
98
|
-
▼
|
|
99
|
-
compozy fetch-reviews / /cy-review-round .compozy/tasks/user-auth/reviews-001/
|
|
100
|
-
│
|
|
101
|
-
▼
|
|
102
|
-
compozy fix-reviews --name user-auth Issues triaged, fixed, resolved
|
|
103
|
-
│
|
|
104
|
-
▼
|
|
105
|
-
Repeat until clean → Ship
|
|
106
|
-
```
|
|
93
|
+
<div align="center">
|
|
94
|
+
<img src="imgs/how-it-works-flow.png" alt="Compozy workflow from setup to ship with markdown artifacts at each step" width="100%">
|
|
95
|
+
</div>
|
|
107
96
|
|
|
108
97
|
Every artifact is a plain markdown file in `.compozy/tasks/<name>/`. You can read, edit, or version-control any of them between steps.
|
|
109
98
|
|
|
110
|
-
Task and review issue files use YAML frontmatter for parseable metadata such as `status`, `domain`, `severity`, and `provider_ref`. Task workflow `_meta.md` files can be refreshed explicitly with `compozy sync`. If you have an older project with XML-tagged artifacts, run `compozy migrate` once before using `start` or `fix-reviews`.
|
|
99
|
+
Task and review issue files use YAML frontmatter for parseable metadata such as `status`, `domain`, `severity`, and `provider_ref`. Task workflow `_meta.md` files can be refreshed explicitly with `compozy sync`. Fully completed workflows can be moved out of the active task root with `compozy archive`. If you have an older project with XML-tagged artifacts, run `compozy migrate` once before using `start` or `fix-reviews`.
|
|
111
100
|
|
|
112
101
|
## 🚀 Quick Start
|
|
113
102
|
|
|
@@ -116,22 +105,30 @@ This walkthrough builds a feature called **user-auth** from idea to shipped code
|
|
|
116
105
|
### 1. Install skills
|
|
117
106
|
|
|
118
107
|
```bash
|
|
119
|
-
compozy setup
|
|
108
|
+
compozy setup
|
|
120
109
|
```
|
|
121
110
|
|
|
122
111
|
Auto-detects installed agents and copies (or symlinks) skills into their configuration directories.
|
|
123
112
|
|
|
124
|
-
### 2. Create
|
|
113
|
+
### 2. (Optional) Create an Issue
|
|
125
114
|
|
|
126
115
|
Inside your AI agent (Claude Code, Codex, Cursor, OpenCode, Pi, etc.):
|
|
127
116
|
|
|
117
|
+
```
|
|
118
|
+
/cy-idea-factory user-auth
|
|
119
|
+
```
|
|
120
|
+
|
|
121
|
+
Transforms a raw idea into a structured issue spec — asks targeted questions, researches market and codebase in parallel, runs business analysis and council debate, suggests high-leverage alternatives, and produces a research-backed issue. Skip this step if you already have a clear feature scope.
|
|
122
|
+
|
|
123
|
+
### 3. Create a PRD
|
|
124
|
+
|
|
128
125
|
```
|
|
129
126
|
/cy-create-prd user-auth
|
|
130
127
|
```
|
|
131
128
|
|
|
132
|
-
Interactive brainstorming session — asks clarifying questions, spawns parallel agents to research your codebase and the web, produces a business-focused PRD with ADRs.
|
|
129
|
+
Interactive brainstorming session — reads the issue if one exists, asks clarifying questions, spawns parallel agents to research your codebase and the web, produces a business-focused PRD with ADRs.
|
|
133
130
|
|
|
134
|
-
###
|
|
131
|
+
### 4. Create a TechSpec
|
|
135
132
|
|
|
136
133
|
```
|
|
137
134
|
/cy-create-techspec user-auth
|
|
@@ -139,7 +136,7 @@ Interactive brainstorming session — asks clarifying questions, spawns parallel
|
|
|
139
136
|
|
|
140
137
|
Reads your PRD, explores the codebase architecture, asks technical clarification questions. Produces architecture specs, API designs, and data models.
|
|
141
138
|
|
|
142
|
-
###
|
|
139
|
+
### 5. Break down into tasks
|
|
143
140
|
|
|
144
141
|
```
|
|
145
142
|
/cy-create-tasks user-auth
|
|
@@ -147,7 +144,7 @@ Reads your PRD, explores the codebase architecture, asks technical clarification
|
|
|
147
144
|
|
|
148
145
|
Analyzes both documents, explores your codebase for relevant files and patterns, produces individually executable task files with status tracking, context, and acceptance criteria.
|
|
149
146
|
|
|
150
|
-
###
|
|
147
|
+
### 6. Execute tasks
|
|
151
148
|
|
|
152
149
|
```bash
|
|
153
150
|
compozy start --name user-auth --ide claude
|
|
@@ -155,7 +152,7 @@ compozy start --name user-auth --ide claude
|
|
|
155
152
|
|
|
156
153
|
Each pending task is processed sequentially — the agent reads the spec, implements the code, validates it, and updates the task status. Use `--dry-run` to preview prompts without executing.
|
|
157
154
|
|
|
158
|
-
###
|
|
155
|
+
### 7. Review
|
|
159
156
|
|
|
160
157
|
**Option A** — AI-powered review inside your agent:
|
|
161
158
|
|
|
@@ -171,7 +168,7 @@ compozy fetch-reviews --provider coderabbit --pr 42 --name user-auth
|
|
|
171
168
|
|
|
172
169
|
Both produce the same output: `.compozy/tasks/user-auth/reviews-001/issue_*.md`
|
|
173
170
|
|
|
174
|
-
###
|
|
171
|
+
### 8. Fix review issues
|
|
175
172
|
|
|
176
173
|
```bash
|
|
177
174
|
compozy fix-reviews --name user-auth --ide claude --concurrent 2 --batch-size 3
|
|
@@ -179,24 +176,25 @@ compozy fix-reviews --name user-auth --ide claude --concurrent 2 --batch-size 3
|
|
|
179
176
|
|
|
180
177
|
Agents triage each issue as valid or invalid, implement fixes for valid issues, and update statuses. Provider threads are resolved automatically.
|
|
181
178
|
|
|
182
|
-
###
|
|
179
|
+
### 9. Iterate and ship
|
|
183
180
|
|
|
184
|
-
Repeat steps
|
|
181
|
+
Repeat steps 7–8. Each cycle creates a new review round (`reviews-002/`, `reviews-003/`), preserving full history. When clean — merge and ship.
|
|
185
182
|
|
|
186
183
|
## 🧩 Skills
|
|
187
184
|
|
|
188
|
-
Compozy bundles
|
|
185
|
+
Compozy bundles 9 skills that its workflows depend on. They run inside your AI agent — no context switching to external tools.
|
|
189
186
|
|
|
190
|
-
| Skill
|
|
191
|
-
|
|
|
192
|
-
| `cy-
|
|
193
|
-
| `cy-create-
|
|
194
|
-
| `cy-create-
|
|
195
|
-
| `cy-
|
|
187
|
+
| Skill | Purpose |
|
|
188
|
+
| -------------------- | -------------------------------------------------------------------------- |
|
|
189
|
+
| `cy-idea-factory` | Raw idea → structured issue spec with market research, business analysis, and council debate |
|
|
190
|
+
| `cy-create-prd` | Issue/idea → Product Requirements Document with ADRs |
|
|
191
|
+
| `cy-create-techspec` | PRD → Technical Specification with architecture exploration |
|
|
192
|
+
| `cy-create-tasks` | PRD + TechSpec → Independently implementable task files |
|
|
193
|
+
| `cy-execute-task` | Executes one task end-to-end: implement, validate, track, commit |
|
|
196
194
|
| `cy-workflow-memory` | Maintains cross-task context so agents pick up where the last one left off |
|
|
197
|
-
| `cy-review-round`
|
|
198
|
-
| `cy-fix-reviews`
|
|
199
|
-
| `cy-final-verify`
|
|
195
|
+
| `cy-review-round` | Comprehensive code review → structured issue files |
|
|
196
|
+
| `cy-fix-reviews` | Triage, fix, verify, and resolve review issues |
|
|
197
|
+
| `cy-final-verify` | Enforces verification evidence before any completion claim |
|
|
200
198
|
|
|
201
199
|
### 🧠 Workflow Memory
|
|
202
200
|
|
|
@@ -204,10 +202,10 @@ When agents execute tasks, context gets lost between runs — decisions made, er
|
|
|
204
202
|
|
|
205
203
|
Every task execution automatically bootstraps two markdown files inside `.compozy/tasks/<name>/memory/`:
|
|
206
204
|
|
|
207
|
-
| File
|
|
208
|
-
|
|
|
209
|
-
| `MEMORY.md`
|
|
210
|
-
| `task_01.md` | Single task
|
|
205
|
+
| File | Scope | What goes here |
|
|
206
|
+
| ------------ | ------------------ | ------------------------------------------------------------------------------- |
|
|
207
|
+
| `MEMORY.md` | Cross-task, shared | Architecture decisions, discovered patterns, open risks, handoffs between tasks |
|
|
208
|
+
| `task_01.md` | Single task | Objective snapshot, files touched, errors hit, what's ready for the next run |
|
|
211
209
|
|
|
212
210
|
**How it works:**
|
|
213
211
|
|
|
@@ -219,28 +217,29 @@ Every task execution automatically bootstraps two markdown files inside `.compoz
|
|
|
219
217
|
|
|
220
218
|
**Automatic compaction.** Memory files have soft limits (150 lines / 12 KB for shared, 200 lines / 16 KB per task). When a file exceeds its threshold, Compozy flags it for compaction — the agent trims noise and repetition while preserving active risks, decisions, and handoffs.
|
|
221
219
|
|
|
222
|
-
**No duplication.** Memory files don't copy what's already in the repo, git history, PRD, or task specs. They capture only what would otherwise be lost between runs: the
|
|
220
|
+
**No duplication.** Memory files don't copy what's already in the repo, git history, PRD, or task specs. They capture only what would otherwise be lost between runs: the _why_ behind decisions, surprising findings, and context that makes the next agent immediately productive.
|
|
223
221
|
|
|
224
222
|
The `cy-workflow-memory` skill handles all of this automatically when referenced in task prompts. No manual setup required — just run `compozy start` and agents inherit context from every previous run.
|
|
225
223
|
|
|
226
224
|
### 🤖 Supported Agents
|
|
227
225
|
|
|
228
|
-
**Execution** (`compozy start`, `compozy fix-reviews`) —
|
|
226
|
+
**Execution** (`compozy start`, `compozy fix-reviews`) — ACP-capable runtimes that can run tasks:
|
|
229
227
|
|
|
230
|
-
| Agent
|
|
231
|
-
|
|
|
232
|
-
| Claude Code | `claude`
|
|
233
|
-
| Codex
|
|
234
|
-
| Cursor
|
|
235
|
-
| Droid
|
|
236
|
-
| OpenCode
|
|
237
|
-
| Pi
|
|
228
|
+
| Agent | `--ide` flag |
|
|
229
|
+
| ----------- | -------------- |
|
|
230
|
+
| Claude Code | `claude` |
|
|
231
|
+
| Codex | `codex` |
|
|
232
|
+
| Cursor | `cursor-agent` |
|
|
233
|
+
| Droid | `droid` |
|
|
234
|
+
| OpenCode | `opencode` |
|
|
235
|
+
| Pi | `pi` |
|
|
236
|
+
| Gemini | `gemini` |
|
|
238
237
|
|
|
239
238
|
**Skill installation** (`compozy setup`) — 40+ agents and editors, including Claude Code, Codex, Cursor, Droid, OpenCode, Pi, Gemini CLI, GitHub Copilot, Windsurf, Amp, Continue, Goose, Roo Code, Augment, Kiro CLI, Cline, and many more. Run `compozy setup` to see all detected agents on your system.
|
|
240
239
|
|
|
241
240
|
When installing to multiple agents, Compozy offers two modes:
|
|
242
241
|
|
|
243
|
-
- **Symlink**
|
|
242
|
+
- **Symlink** _(default)_ — One canonical copy with symlinks from each agent directory. All agents stay in sync.
|
|
244
243
|
- **Copy** — Independent copies per agent. Use `--copy` when symlinks are not supported.
|
|
245
244
|
|
|
246
245
|
## 📖 CLI Reference
|
|
@@ -252,15 +251,15 @@ When installing to multiple agents, Compozy offers two modes:
|
|
|
252
251
|
compozy setup [flags]
|
|
253
252
|
```
|
|
254
253
|
|
|
255
|
-
| Flag
|
|
256
|
-
|
|
|
257
|
-
| `--agent`, `-a`
|
|
258
|
-
| `--skill`, `-s`
|
|
254
|
+
| Flag | Default | Description |
|
|
255
|
+
| ---------------- | ------- | -------------------------------------------- |
|
|
256
|
+
| `--agent`, `-a` | | Target agent name (repeatable) |
|
|
257
|
+
| `--skill`, `-s` | | Skill name to install (repeatable) |
|
|
259
258
|
| `--global`, `-g` | `false` | Install to user directory instead of project |
|
|
260
|
-
| `--copy`
|
|
261
|
-
| `--list`, `-l`
|
|
262
|
-
| `--yes`, `-y`
|
|
263
|
-
| `--all`
|
|
259
|
+
| `--copy` | `false` | Copy files instead of symlinking |
|
|
260
|
+
| `--list`, `-l` | `false` | List bundled skills without installing |
|
|
261
|
+
| `--yes`, `-y` | `false` | Skip confirmation prompts |
|
|
262
|
+
| `--all` | `false` | Install all skills to all agents |
|
|
264
263
|
|
|
265
264
|
</details>
|
|
266
265
|
|
|
@@ -271,13 +270,13 @@ compozy setup [flags]
|
|
|
271
270
|
compozy migrate [flags]
|
|
272
271
|
```
|
|
273
272
|
|
|
274
|
-
| Flag
|
|
275
|
-
|
|
|
276
|
-
| `--root-dir`
|
|
277
|
-
| `--name`
|
|
278
|
-
| `--tasks-dir`
|
|
279
|
-
| `--reviews-dir` |
|
|
280
|
-
| `--dry-run`
|
|
273
|
+
| Flag | Default | Description |
|
|
274
|
+
| --------------- | ---------------- | ------------------------------------------------- |
|
|
275
|
+
| `--root-dir` | `.compozy/tasks` | Workflow root to scan recursively |
|
|
276
|
+
| `--name` | | Restrict migration to one workflow name |
|
|
277
|
+
| `--tasks-dir` | | Restrict migration to one task workflow directory |
|
|
278
|
+
| `--reviews-dir` | | Restrict migration to one review round directory |
|
|
279
|
+
| `--dry-run` | `false` | Preview migrations without writing files |
|
|
281
280
|
|
|
282
281
|
</details>
|
|
283
282
|
|
|
@@ -288,11 +287,26 @@ compozy migrate [flags]
|
|
|
288
287
|
compozy sync [flags]
|
|
289
288
|
```
|
|
290
289
|
|
|
291
|
-
| Flag
|
|
292
|
-
|
|
|
293
|
-
| `--root-dir`
|
|
294
|
-
| `--name`
|
|
295
|
-
| `--tasks-dir` |
|
|
290
|
+
| Flag | Default | Description |
|
|
291
|
+
| ------------- | ---------------- | -------------------------------------------- |
|
|
292
|
+
| `--root-dir` | `.compozy/tasks` | Workflow root to scan |
|
|
293
|
+
| `--name` | | Restrict sync to one workflow name |
|
|
294
|
+
| `--tasks-dir` | | Restrict sync to one task workflow directory |
|
|
295
|
+
|
|
296
|
+
</details>
|
|
297
|
+
|
|
298
|
+
<details>
|
|
299
|
+
<summary><code>compozy archive</code> — Move fully completed workflows into the archive root</summary>
|
|
300
|
+
|
|
301
|
+
```bash
|
|
302
|
+
compozy archive [flags]
|
|
303
|
+
```
|
|
304
|
+
|
|
305
|
+
| Flag | Default | Description |
|
|
306
|
+
| ------------- | ---------------- | ------------------------------------------------- |
|
|
307
|
+
| `--root-dir` | `.compozy/tasks` | Workflow root to scan |
|
|
308
|
+
| `--name` | | Restrict archiving to one workflow name |
|
|
309
|
+
| `--tasks-dir` | | Restrict archiving to one task workflow directory |
|
|
296
310
|
|
|
297
311
|
</details>
|
|
298
312
|
|
|
@@ -305,21 +319,21 @@ compozy start [flags]
|
|
|
305
319
|
|
|
306
320
|
Running `compozy start` with no flags opens the interactive form automatically.
|
|
307
321
|
|
|
308
|
-
| Flag
|
|
309
|
-
|
|
|
310
|
-
| `--name`
|
|
311
|
-
| `--tasks-dir`
|
|
312
|
-
| `--ide`
|
|
313
|
-
| `--model`
|
|
314
|
-
| `--reasoning-effort`
|
|
315
|
-
| `--timeout`
|
|
316
|
-
| `--max-retries`
|
|
317
|
-
| `--retry-backoff-multiplier` | `1.5`
|
|
318
|
-
| `--tail-lines`
|
|
319
|
-
| `--add-dir`
|
|
320
|
-
| `--auto-commit`
|
|
321
|
-
| `--include-completed`
|
|
322
|
-
| `--dry-run`
|
|
322
|
+
| Flag | Default | Description |
|
|
323
|
+
| ---------------------------- | ----------- | ------------------------------------------------------------- |
|
|
324
|
+
| `--name` | | Workflow name (`.compozy/tasks/<name>`) |
|
|
325
|
+
| `--tasks-dir` | | Path to tasks directory |
|
|
326
|
+
| `--ide` | `codex` | Agent: `claude`, `codex`, `cursor`, `droid`, `opencode`, `pi` |
|
|
327
|
+
| `--model` | _(per IDE)_ | Model override |
|
|
328
|
+
| `--reasoning-effort` | `medium` | `low`, `medium`, `high`, `xhigh` |
|
|
329
|
+
| `--timeout` | `10m` | Activity timeout per job |
|
|
330
|
+
| `--max-retries` | `0` | Retry failed jobs N times |
|
|
331
|
+
| `--retry-backoff-multiplier` | `1.5` | Timeout multiplier per retry |
|
|
332
|
+
| `--tail-lines` | `30` | Log lines shown per job in UI |
|
|
333
|
+
| `--add-dir` | | Additional directories to allow (repeatable) |
|
|
334
|
+
| `--auto-commit` | `false` | Auto-commit after each task |
|
|
335
|
+
| `--include-completed` | `false` | Re-run completed tasks |
|
|
336
|
+
| `--dry-run` | `false` | Preview prompts without executing |
|
|
323
337
|
|
|
324
338
|
</details>
|
|
325
339
|
|
|
@@ -332,12 +346,12 @@ compozy fetch-reviews [flags]
|
|
|
332
346
|
|
|
333
347
|
Running `compozy fetch-reviews` with no flags opens the interactive form automatically.
|
|
334
348
|
|
|
335
|
-
| Flag
|
|
336
|
-
|
|
|
337
|
-
| `--provider` |
|
|
338
|
-
| `--pr`
|
|
339
|
-
| `--name`
|
|
340
|
-
| `--round`
|
|
349
|
+
| Flag | Default | Description |
|
|
350
|
+
| ------------ | ------- | ----------------------------------------- |
|
|
351
|
+
| `--provider` | | Review provider (`coderabbit`, etc.) |
|
|
352
|
+
| `--pr` | | Pull request number |
|
|
353
|
+
| `--name` | | Workflow name |
|
|
354
|
+
| `--round` | `0` | Round number (auto-increments if omitted) |
|
|
341
355
|
|
|
342
356
|
</details>
|
|
343
357
|
|
|
@@ -350,25 +364,25 @@ compozy fix-reviews [flags]
|
|
|
350
364
|
|
|
351
365
|
Running `compozy fix-reviews` with no flags opens the interactive form automatically.
|
|
352
366
|
|
|
353
|
-
| Flag
|
|
354
|
-
|
|
|
355
|
-
| `--name`
|
|
356
|
-
| `--round`
|
|
357
|
-
| `--reviews-dir`
|
|
358
|
-
| `--ide`
|
|
359
|
-
| `--model`
|
|
360
|
-
| `--batch-size`
|
|
361
|
-
| `--concurrent`
|
|
362
|
-
| `--grouped`
|
|
363
|
-
| `--include-resolved`
|
|
364
|
-
| `--reasoning-effort`
|
|
365
|
-
| `--timeout`
|
|
366
|
-
| `--max-retries`
|
|
367
|
-
| `--retry-backoff-multiplier` | `1.5`
|
|
368
|
-
| `--tail-lines`
|
|
369
|
-
| `--add-dir`
|
|
370
|
-
| `--auto-commit`
|
|
371
|
-
| `--dry-run`
|
|
367
|
+
| Flag | Default | Description |
|
|
368
|
+
| ---------------------------- | ----------- | ------------------------------------------------------------- |
|
|
369
|
+
| `--name` | | Workflow name |
|
|
370
|
+
| `--round` | `0` | Round number (latest if omitted) |
|
|
371
|
+
| `--reviews-dir` | | Override review directory path |
|
|
372
|
+
| `--ide` | `codex` | Agent: `claude`, `codex`, `cursor`, `droid`, `opencode`, `pi` |
|
|
373
|
+
| `--model` | _(per IDE)_ | Model override |
|
|
374
|
+
| `--batch-size` | `1` | Issues per batch |
|
|
375
|
+
| `--concurrent` | `1` | Parallel batches |
|
|
376
|
+
| `--grouped` | `false` | Generate grouped issue summaries |
|
|
377
|
+
| `--include-resolved` | `false` | Re-process resolved issues |
|
|
378
|
+
| `--reasoning-effort` | `medium` | `low`, `medium`, `high`, `xhigh` |
|
|
379
|
+
| `--timeout` | `10m` | Activity timeout per job |
|
|
380
|
+
| `--max-retries` | `0` | Retry failed jobs N times |
|
|
381
|
+
| `--retry-backoff-multiplier` | `1.5` | Timeout multiplier per retry |
|
|
382
|
+
| `--tail-lines` | `30` | Log lines shown per job in UI |
|
|
383
|
+
| `--add-dir` | | Additional directories to allow (repeatable) |
|
|
384
|
+
| `--auto-commit` | `false` | Auto-commit after each batch |
|
|
385
|
+
| `--dry-run` | `false` | Preview prompts without executing |
|
|
372
386
|
|
|
373
387
|
</details>
|
|
374
388
|
|
package/package.json
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "@compozy/cli",
|
|
3
3
|
"type": "module",
|
|
4
|
-
"version": "0.1.
|
|
4
|
+
"version": "0.1.4",
|
|
5
5
|
"description": "Compozy CLI",
|
|
6
6
|
"scripts": {
|
|
7
7
|
"postinstall": "node install.js",
|
|
@@ -27,69 +27,69 @@
|
|
|
27
27
|
},
|
|
28
28
|
"archives": {
|
|
29
29
|
"darwin-arm64": {
|
|
30
|
-
"name": "compozy_0.1.
|
|
31
|
-
"url": "https://github.com/compozy/compozy/releases/download/v0.1.
|
|
30
|
+
"name": "compozy_0.1.4_darwin_arm64.tar.gz",
|
|
31
|
+
"url": "https://github.com/compozy/compozy/releases/download/v0.1.4/compozy_0.1.4_darwin_arm64.tar.gz",
|
|
32
32
|
"bins": [
|
|
33
33
|
"compozy"
|
|
34
34
|
],
|
|
35
35
|
"format": "tar.gz",
|
|
36
36
|
"checksum": {
|
|
37
37
|
"algorithm": "sha256",
|
|
38
|
-
"digest": "
|
|
38
|
+
"digest": "5e384a0463fbc65514a5990aa3b335ad6532e4691d38834d73cd7237f92d9b22"
|
|
39
39
|
},
|
|
40
|
-
"wrappedIn": "compozy_0.1.
|
|
40
|
+
"wrappedIn": "compozy_0.1.4_darwin_arm64"
|
|
41
41
|
},
|
|
42
42
|
"darwin-x64": {
|
|
43
|
-
"name": "compozy_0.1.
|
|
44
|
-
"url": "https://github.com/compozy/compozy/releases/download/v0.1.
|
|
43
|
+
"name": "compozy_0.1.4_darwin_x86_64.tar.gz",
|
|
44
|
+
"url": "https://github.com/compozy/compozy/releases/download/v0.1.4/compozy_0.1.4_darwin_x86_64.tar.gz",
|
|
45
45
|
"bins": [
|
|
46
46
|
"compozy"
|
|
47
47
|
],
|
|
48
48
|
"format": "tar.gz",
|
|
49
49
|
"checksum": {
|
|
50
50
|
"algorithm": "sha256",
|
|
51
|
-
"digest": "
|
|
51
|
+
"digest": "7d372733a379d47fb21bed556bce8cb73f45163d0133f0ff25af4c8bef4a1f5e"
|
|
52
52
|
},
|
|
53
|
-
"wrappedIn": "compozy_0.1.
|
|
53
|
+
"wrappedIn": "compozy_0.1.4_darwin_x86_64"
|
|
54
54
|
},
|
|
55
55
|
"linux-arm64": {
|
|
56
|
-
"name": "compozy_0.1.
|
|
57
|
-
"url": "https://github.com/compozy/compozy/releases/download/v0.1.
|
|
56
|
+
"name": "compozy_0.1.4_linux_arm64.tar.gz",
|
|
57
|
+
"url": "https://github.com/compozy/compozy/releases/download/v0.1.4/compozy_0.1.4_linux_arm64.tar.gz",
|
|
58
58
|
"bins": [
|
|
59
59
|
"compozy"
|
|
60
60
|
],
|
|
61
61
|
"format": "tar.gz",
|
|
62
62
|
"checksum": {
|
|
63
63
|
"algorithm": "sha256",
|
|
64
|
-
"digest": "
|
|
64
|
+
"digest": "9dded2212070d39ee62817589712e95da628f498bd4cb87aa9639af646ca6fbe"
|
|
65
65
|
},
|
|
66
|
-
"wrappedIn": "compozy_0.1.
|
|
66
|
+
"wrappedIn": "compozy_0.1.4_linux_arm64"
|
|
67
67
|
},
|
|
68
68
|
"linux-x64": {
|
|
69
|
-
"name": "compozy_0.1.
|
|
70
|
-
"url": "https://github.com/compozy/compozy/releases/download/v0.1.
|
|
69
|
+
"name": "compozy_0.1.4_linux_x86_64.tar.gz",
|
|
70
|
+
"url": "https://github.com/compozy/compozy/releases/download/v0.1.4/compozy_0.1.4_linux_x86_64.tar.gz",
|
|
71
71
|
"bins": [
|
|
72
72
|
"compozy"
|
|
73
73
|
],
|
|
74
74
|
"format": "tar.gz",
|
|
75
75
|
"checksum": {
|
|
76
76
|
"algorithm": "sha256",
|
|
77
|
-
"digest": "
|
|
77
|
+
"digest": "c7043253f9ecd58e771ee0610f04190906115c092565a57ee2965e4365455937"
|
|
78
78
|
},
|
|
79
|
-
"wrappedIn": "compozy_0.1.
|
|
79
|
+
"wrappedIn": "compozy_0.1.4_linux_x86_64"
|
|
80
80
|
},
|
|
81
81
|
"win32-x64": {
|
|
82
|
-
"name": "compozy_0.1.
|
|
83
|
-
"url": "https://github.com/compozy/compozy/releases/download/v0.1.
|
|
82
|
+
"name": "compozy_0.1.4_windows_x86_64.zip",
|
|
83
|
+
"url": "https://github.com/compozy/compozy/releases/download/v0.1.4/compozy_0.1.4_windows_x86_64.zip",
|
|
84
84
|
"bins": [
|
|
85
85
|
"compozy.exe"
|
|
86
86
|
],
|
|
87
87
|
"format": "zip",
|
|
88
88
|
"checksum": {
|
|
89
89
|
"algorithm": "sha256",
|
|
90
|
-
"digest": "
|
|
90
|
+
"digest": "1d8caf3070b63b4f3dfe36428bd5b53992e78fb5a5e83785b2c9fd54a38c5bea"
|
|
91
91
|
},
|
|
92
|
-
"wrappedIn": "compozy_0.1.
|
|
92
|
+
"wrappedIn": "compozy_0.1.4_windows_x86_64"
|
|
93
93
|
}
|
|
94
94
|
}
|
|
95
95
|
}
|