zefiro 0.8.0 → 0.8.1

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 CHANGED
@@ -1,6 +1,6 @@
1
1
  # Zefiro
2
2
 
3
- AI-powered codebase scanner and QA map generator. Scans your project's AST, identifies features and workflows, and generates structured test scenarios all driven by LLM agents.
3
+ AI-powered application explorer. Maps web applications through browser automation, producing structured documentation with screenshots and interactive reports.
4
4
 
5
5
  ## Installation
6
6
 
@@ -13,13 +13,11 @@ bun add -g zefiro
13
13
  ## Quick Start
14
14
 
15
15
  ```bash
16
- # 1. Initialize — copies agents, writes QAI_* env vars to .env
16
+ # 1. Initialize
17
17
  zefiro init
18
18
 
19
- # 2. Scan Analyze → Push
20
- zefiro scan
21
- zefiro analyze
22
- zefiro push
19
+ # 2. Explore a running application
20
+ zefiro scan # static AST scan (optional)
23
21
  ```
24
22
 
25
23
  ---
@@ -33,10 +31,8 @@ zefiro push
33
31
  | `QAI_INPUT_SOURCE` | Issue tracker: `none` \| `jira` \| `linear` |
34
32
  | `QAI_OUTPUT_TARGET` | QA format: `markdown` \| `zephyr` \| `both` |
35
33
  | `QAI_BASE_URL` | QA Intelligence API base URL |
36
- | `QAI_API_URL` | Full push endpoint (overrides base URL) |
37
- | `QAI_API_KEY` | API key for authenticated push |
38
- | `OPENAI_API_KEY` | OpenAI API key (for `analyze` with OpenAI) |
39
- | `ANTHROPIC_API_KEY` | Anthropic API key (for `analyze` with Anthropic) |
34
+ | `OPENAI_API_KEY` | OpenAI API key |
35
+ | `ANTHROPIC_API_KEY` | Anthropic API key |
40
36
 
41
37
  ---
42
38
 
@@ -79,49 +75,6 @@ zefiro scan --no-cache
79
75
 
80
76
  ---
81
77
 
82
- ### `zefiro analyze [input]`
83
-
84
- Two-stage AI analysis that generates a QA map from the AST scan.
85
-
86
- **Stage 1:** Feature analysis — identifies features, workflows, and components (runs in parallel).
87
- **Stage 2:** Scenario planning — generates test scenarios for each workflow (runs in parallel).
88
-
89
- ```bash
90
- zefiro analyze
91
- zefiro analyze custom-scan.json
92
- zefiro analyze --skip-scenarios # features and workflows only
93
- zefiro analyze --output custom-qa-map.json
94
- ```
95
-
96
- | Option | Description |
97
- |--------|-------------|
98
- | `[input]` | AST scan file (default: `.qai/zefiro/ast-scan.json`) |
99
- | `--output <file>` | QA map output (default: `.qai/zefiro/qa-map.json`) |
100
- | `--skip-scenarios` | Skip scenario generation |
101
-
102
- **Incremental:** if the AST is unchanged since the last run, analysis is skipped. If the AST changed, only affected features are re-analyzed.
103
-
104
- ---
105
-
106
- ### `zefiro push [input]`
107
-
108
- Push the generated QA map to QA Intelligence (or a custom endpoint).
109
-
110
- ```bash
111
- zefiro push
112
- zefiro push custom-qa-map.json
113
- zefiro push --commit-sha abc1234
114
- ```
115
-
116
- | Option | Description |
117
- |--------|-------------|
118
- | `[input]` | QA map file (default: `.qai/zefiro/qa-map.json`) |
119
- | `--commit-sha <sha>` | Git commit SHA to associate with this version |
120
-
121
- Authenticates via `zefiro auth login` session first, falls back to `QAI_API_URL` + `QAI_API_KEY`.
122
-
123
- ---
124
-
125
78
  ### `zefiro auth`
126
79
 
127
80
  Manage authentication with QA Intelligence.
@@ -167,11 +120,9 @@ claude mcp add zefiro -s user -- npx -y zefiro-mcp # global
167
120
 
168
121
  | Tool | Description |
169
122
  |------|-------------|
123
+ | `zefiro_explore` | Explore a web application via BFS |
124
+ | `zefiro_read_docs` | Read generated documentation |
170
125
  | `zefiro_scan_codebase` | Scan project test infrastructure |
171
- | `zefiro_scan_ast` | Deep AST scan: routes, components, hooks |
172
- | `zefiro_scan_ast_detail` | Drill into a specific AST category |
173
- | `zefiro_build_qa_map` | Validate and write a QAMapV2Payload |
174
- | `zefiro_read_qa_map` | Read the existing QA map file |
175
126
 
176
127
  ---
177
128
 
@@ -224,11 +175,6 @@ export default defineConfig({
224
175
  integrations: {
225
176
  zephyr: { titlePrefix: 'UI Automation' },
226
177
  },
227
-
228
- push: {
229
- apiUrl: 'https://your-api.com/qa-map',
230
- apiKey: 'your-key',
231
- },
232
178
  });
233
179
  ```
234
180
 
@@ -244,25 +190,12 @@ Zefiro ships with agents copied to `.qai/zefiro/agents/` on `init`. Edit them to
244
190
  |-------|---------|
245
191
  | `1.feature-analyzer-agent` | Identifies features, workflows, and components from AST |
246
192
  | `2.scenario-planner-agent` | Generates test scenarios for each workflow |
247
- | `3.scanner-agent` | Interactive QA map building (used via MCP) |
248
193
  | `input-agent` | Enriches form component input definitions |
249
- | `workflow-agent` | Maps user workflows within features |
250
194
 
251
195
  Add `.qai/zefiro/context.md` to inject project-specific context into every agent call.
252
196
 
253
197
  ---
254
198
 
255
- ## QA Map Output
256
-
257
- The generated `.qai/zefiro/qa-map.json` contains:
258
-
259
- - **Features** — User-facing capabilities grouped by routes
260
- - **Workflows** — User journeys (navigation, CRUD, multi-step, search/filter, configuration)
261
- - **Components** — UI elements (forms, modals, navigation, data display)
262
- - **Scenarios** — Test cases per workflow (happy-path, validation, error, edge-case, permission)
263
-
264
- ---
265
-
266
199
  ## Project Structure
267
200
 
268
201
  ```
@@ -274,7 +207,6 @@ your-project/
274
207
  agents/ # Agent prompts (customizable)
275
208
  workflow.md # Workflow guide
276
209
  ast-scan.json # Latest AST scan output
277
- qa-map.json # Generated QA map
278
210
  scan-cache/ # File-level MD5 cache
279
211
  ```
280
212