@critiquedotsh/harness 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 +12 -1
- package/dist/cli.js +1358 -270
- package/package.json +4 -3
package/README.md
CHANGED
|
@@ -71,6 +71,12 @@ Then:
|
|
|
71
71
|
critique-code
|
|
72
72
|
```
|
|
73
73
|
|
|
74
|
+
Or skip the TTY and open a local browser UI (still the same Pi author kernel in this process, bound to `127.0.0.1` only):
|
|
75
|
+
|
|
76
|
+
```bash
|
|
77
|
+
critique-code web
|
|
78
|
+
```
|
|
79
|
+
|
|
74
80
|
Describe the change. Slash lines (`/review`, `/ship`, …) are never sent to the model.
|
|
75
81
|
|
|
76
82
|
## What a session does
|
|
@@ -81,7 +87,9 @@ Describe the change. Slash lines (`/review`, `/ship`, …) are never sent to the
|
|
|
81
87
|
4. **`/repair`** runs verified repair on promoted findings. It is not auto-applied chatter.
|
|
82
88
|
5. `none_promoted` means nothing was promoted. It is **not** a correctness proof.
|
|
83
89
|
|
|
84
|
-
The
|
|
90
|
+
The author can fan out **`critique_task`** workers (`explore` is read-only; `general` / `implement` can write through the same CAS path). Independent review is still `/review`, not a worker. `critique_run` still needs your approval. Workers cannot nest `critique_task`.
|
|
91
|
+
|
|
92
|
+
The TTY shows a wordmark, a compact live status (`thinking` / `write path` / `task explore …`), then a one-line `▸` summary before the reply. It does not stream thinking paragraphs.
|
|
85
93
|
|
|
86
94
|
Interactive TTY sessions keep **stdout quiet**. Pass `--json` for the session envelope. `review`, `repair`, and `capabilities` still print JSON on stdout. Live chrome goes to stderr.
|
|
87
95
|
|
|
@@ -90,6 +98,7 @@ Interactive TTY sessions keep **stdout quiet**. Pass `--json` for the session en
|
|
|
90
98
|
```text
|
|
91
99
|
critique-code
|
|
92
100
|
critique-code chat [--intent <text>] [--models provider/model,...] [--cwd <dir>] [--store <dir>] [--voice] [--json]
|
|
101
|
+
critique-code web [--port <n>] [--cwd <dir>] [--store <dir>] [--models ...]
|
|
93
102
|
critique-code login
|
|
94
103
|
critique-code settings | keys | models
|
|
95
104
|
critique-code review [--depth quick|standard|paranoid] [--focus general,security] [--models ...] [--base <ref>] [--intent <text>] [--cwd <dir>] [--store <dir>]
|
|
@@ -103,6 +112,7 @@ critique-code help
|
|
|
103
112
|
| Command | Purpose |
|
|
104
113
|
| --- | --- |
|
|
105
114
|
| `critique-code` / `chat` | Interactive author session |
|
|
115
|
+
| `web` | Local browser UI on `127.0.0.1` (same author kernel; no TTY required) |
|
|
106
116
|
| `login` | Browser device approval; connect Critique Inference |
|
|
107
117
|
| `settings` / `keys` / `models` | TUI for route, stored keys, and model ids |
|
|
108
118
|
| `review` | Evidence harness (JSON on stdout) |
|
|
@@ -124,6 +134,7 @@ critique-code help
|
|
|
124
134
|
| `--base <ref>` | Review against a git base ref (not a checkout) |
|
|
125
135
|
| `--voice` | Start the author session in voice mode |
|
|
126
136
|
| `--json` | Print the session envelope on stdout even on a TTY |
|
|
137
|
+
| `--port <n>` | Loopback port for `critique-code web` (`0` = ephemeral) |
|
|
127
138
|
| `-h` / `help` | Help |
|
|
128
139
|
|
|
129
140
|
`critique-code review` is read-only. Use `critique-code repair <review-run-id>` for explicit repair. `--repair apply` on `review` is rejected.
|