@longtable/cli 0.1.64 → 0.1.66

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.
Files changed (2) hide show
  1. package/README.md +28 -5
  2. package/package.json +8 -8
package/README.md CHANGED
@@ -30,16 +30,22 @@ $longtable-start
30
30
  `$longtable-start` creates or resumes the workspace, asks open research-start
31
31
  questions, and stores a Research Specification when there is enough material.
32
32
 
33
- After a Research Specification exists, use:
33
+ Use the unified interview surface for follow-up and critical pressure testing:
34
34
 
35
35
  ```text
36
36
  $longtable-interview
37
37
  ```
38
38
 
39
- `$longtable-interview` is post-start. It uses option-first follow-up choices for
40
- spec revisions, checkpoint resolution, evidence boundaries, coding rules, method
41
- choices, and protected decisions. If no usable Research Specification exists, it
42
- must route to `$longtable-start`.
39
+ Ordinary `$longtable-interview` follow-up is post-start. It uses option-first
40
+ choices for spec revisions, checkpoint resolution, evidence boundaries, coding
41
+ rules, method choices, and protected decisions. If no usable Research
42
+ Specification exists, it must route to `$longtable-start`.
43
+
44
+ Critical, pressure, or grill-me-style requests also run through
45
+ `$longtable-interview`. In that mode LongTable asks one relentless sharpening
46
+ question at a time and stops when remaining questions repeat the same tension
47
+ without producing a new decision. `$critical-interview` remains a compatibility
48
+ alias for this mode, not a separate interview contract.
43
49
 
44
50
  ## Workspace Artifacts
45
51
 
@@ -103,6 +109,23 @@ Team-style requests route through panel. Explicit debate-language requests write
103
109
  panel debate records under `.longtable/panel/`; LongTable team execution is
104
110
  disabled for new work.
105
111
 
112
+ ## Journal Editor Fit Boundary
113
+
114
+ `longtable-editor` and `--role editor` foreground the Journal Editor role; they
115
+ do not invent target-journal knowledge. If a target journal is named, journal
116
+ fit claims require a journal profile: aims/scope, author guidance, recent
117
+ article patterns, and article type expectations. Without that profile,
118
+ LongTable should ask whether to run scholarly/venue search or mark fit as
119
+ provisional.
120
+
121
+ ```bash
122
+ longtable review --role editor --prompt "Evaluate this manuscript positioning."
123
+ longtable panel --role editor,reviewer --prompt "Compare journal fit and reviewer risk."
124
+ longtable search --intent venue --query "<journal or venue context>"
125
+ ```
126
+
127
+ Treat the result as a fit-risk rubric, not an acceptance prediction.
128
+
106
129
  ## Development
107
130
 
108
131
  ```bash
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@longtable/cli",
3
- "version": "0.1.64",
3
+ "version": "0.1.66",
4
4
  "private": false,
5
5
  "description": "Researcher-facing LongTable CLI",
6
6
  "type": "module",
@@ -29,13 +29,13 @@
29
29
  },
30
30
  "dependencies": {
31
31
  "@clack/prompts": "^1.2.0",
32
- "@longtable/checkpoints": "0.1.64",
33
- "@longtable/core": "0.1.64",
34
- "@longtable/memory": "0.1.64",
35
- "@longtable/provider-claude": "0.1.64",
36
- "@longtable/provider-codex": "0.1.64",
37
- "@longtable/scholar-research": "0.1.64",
38
- "@longtable/setup": "0.1.64"
32
+ "@longtable/checkpoints": "0.1.66",
33
+ "@longtable/core": "0.1.66",
34
+ "@longtable/memory": "0.1.66",
35
+ "@longtable/provider-claude": "0.1.66",
36
+ "@longtable/provider-codex": "0.1.66",
37
+ "@longtable/scholar-research": "0.1.66",
38
+ "@longtable/setup": "0.1.66"
39
39
  },
40
40
  "devDependencies": {
41
41
  "@types/node": "^22.10.1",