ccqa 0.6.0 → 0.7.0
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/README.md +6 -4
- package/dist/bin/ccqa.mjs +1499 -335
- package/dist/package.json +1 -1
- package/package.json +1 -1
package/README.md
CHANGED
|
@@ -63,10 +63,10 @@ ccqa generate tasks/create-and-complete
|
|
|
63
63
|
ccqa run tasks/create-and-complete
|
|
64
64
|
```
|
|
65
65
|
|
|
66
|
-
In CI you can opt in to
|
|
66
|
+
In CI you can opt in to an HTML run report by passing `--drift-report` — every failing spec gets a drift audit plus a root-cause call (TEST_DRIFT / SPEC_CHANGE / PRODUCT_BUG) using the PR diff as context, and the report lets a human grade those calls to measure their accuracy. Requires `ANTHROPIC_API_KEY` or a local Claude login for the analysis part. See [Run report](./docs/report.md).
|
|
67
67
|
|
|
68
68
|
```bash
|
|
69
|
-
ccqa run tasks/create-and-complete --drift --
|
|
69
|
+
ccqa run tasks/create-and-complete --drift-report --drift-base origin/main
|
|
70
70
|
```
|
|
71
71
|
|
|
72
72
|
## Features
|
|
@@ -78,7 +78,9 @@ ccqa run tasks/create-and-complete --drift --format github
|
|
|
78
78
|
| Assertion helper functions | [Assertions](./docs/assertions.md) |
|
|
79
79
|
| Auto-fix failing tests | [Auto-fix](./docs/auto-fix.md) |
|
|
80
80
|
| Detect spec/code drift in CI | [Drift](./docs/drift.md) |
|
|
81
|
+
| HTML run report with failure root-cause calls | [Run report](./docs/report.md) |
|
|
81
82
|
| Inventory existing test coverage | [Perspectives](./docs/perspectives.md) |
|
|
83
|
+
| Architecture decision records (why it is built this way) | [ADR](./docs/adr/README.md) |
|
|
82
84
|
|
|
83
85
|
## Commands
|
|
84
86
|
|
|
@@ -86,12 +88,12 @@ ccqa run tasks/create-and-complete --drift --format github
|
|
|
86
88
|
ccqa draft [feature/spec] Co-author a test spec with Claude
|
|
87
89
|
ccqa trace <feature/spec> Record browser actions for a spec (inlines any included blocks)
|
|
88
90
|
ccqa generate <feature/spec> Generate test script from recorded actions
|
|
89
|
-
ccqa run [feature/spec] Execute generated test scripts (add --drift
|
|
91
|
+
ccqa run [feature/spec] Execute generated test scripts (add --drift-report for an HTML report with failure analysis)
|
|
90
92
|
ccqa drift [feature/spec] Standalone spec ↔ codebase drift audit (for scheduled jobs)
|
|
91
93
|
ccqa perspectives Inventory existing test coverage into .ccqa/perspectives.yaml
|
|
92
94
|
```
|
|
93
95
|
|
|
94
|
-
All Claude-driven commands accept `-m, --model <name>` (alias `sonnet` | `opus` | `haiku`, or a full model ID). The flag overrides `CCQA_MODEL`; when both are unset, the Claude Code CLI default is used. They also accept `--language <bcp47>` (e.g. `ja`, `en`) to set the language of human-readable output; the default `auto` follows the language of the spec/codebase. Interactive commands authenticate via your local Claude Code login; commands that talk to Claude in CI (`ccqa run --drift`, `ccqa drift`) additionally honor `ANTHROPIC_API_KEY`.
|
|
96
|
+
All Claude-driven commands accept `-m, --model <name>` (alias `sonnet` | `opus` | `haiku`, or a full model ID). The flag overrides `CCQA_MODEL`; when both are unset, the Claude Code CLI default is used. They also accept `--language <bcp47>` (e.g. `ja`, `en`) to set the language of human-readable output; the default `auto` follows the language of the spec/codebase. Interactive commands authenticate via your local Claude Code login; commands that talk to Claude in CI (`ccqa run --drift-report`, `ccqa drift`) additionally honor `ANTHROPIC_API_KEY`.
|
|
95
97
|
|
|
96
98
|
`<feature/spec>` is a 2-segment alias for the on-disk path `.ccqa/features/<feature>/test-cases/<spec>/`.
|
|
97
99
|
|