@henryqw/pi-prompt-creator 3.1.2 → 3.1.4

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.
Files changed (2) hide show
  1. package/README.md +19 -19
  2. package/package.json +2 -2
package/README.md CHANGED
@@ -1,12 +1,12 @@
1
1
  # `@henryqw/pi-prompt-creator`
2
2
 
3
- Turn repeated requests or corrections in the current conversation into a reviewed global Pi prompt. A tool-free child drafts one candidate, while Main and the user control review and saving.
3
+ Turn repeated requests or corrections in the current conversation into a reviewed global Pi prompt. A tool-free child drafts one Prompt Candidate. Main and the user control Prompt Review and the save.
4
4
 
5
- Automatic analysis only prepares a candidate; the extension never saves it without your approval.
5
+ Automatic analysis only prepares a candidate. The extension never saves it without your approval.
6
6
 
7
7
  ## Install
8
8
 
9
- Requires Pi 1.1.0 or later in the 1.x series. Older Pi releases are no longer supported.
9
+ This package requires Pi 1.1.0 or later in the 1.x series. Older Pi releases are no longer supported.
10
10
 
11
11
  ```bash
12
12
  pi install npm:@henryqw/pi-task-models
@@ -29,25 +29,25 @@ Run `/promptor` in the interactive TUI after a repeated request or correction ap
29
29
  2. Ask Main to refine it and return only the complete Final Prompt Draft.
30
30
  3. Run `/promptor save` to save under the suggested name, or `/promptor save <name>` to rename it.
31
31
 
32
- The prompt is created at `~/.pi/agent/prompts/<name>.md`, then Pi reloads its resources. No selection menu or name prompt is required.
32
+ The prompt is created at `~/.pi/agent/prompts/<name>.md`. Then Pi reloads its resources. No selection menu or name prompt is required.
33
33
 
34
34
  | Surface | Type | Purpose |
35
35
  | --- | --- | --- |
36
36
  | `/promptor [analyze|dismiss|save [name]|automatic <on\|off>]` | command | For users in the interactive TUI: start or show analysis, dismiss a pending candidate, save a reviewed prompt, or control automatic analysis. |
37
- | `pi-prompt-creator/draft` | task | For users configuring `/task-models`: choose the child model and thinking level for drafting. |
38
- | Analysis status widget and candidate message | ui | Show analysis progress, readiness, or failure; a displayed candidate is marked as untrusted. |
37
+ | `pi-prompt-creator/draft` | task | For users who configure `/task-models`: choose the child model and thinking level for the draft. |
38
+ | Analysis status widget and candidate message | ui | Show analysis progress, readiness, or failure. A displayed candidate is marked as untrusted. |
39
39
 
40
40
  ## Flow
41
41
 
42
42
  ![Automatic prompt analysis waits for user display before Main review and approved saving; manual candidates display immediately](./docs/prompt-lifecycle.svg)
43
43
 
44
- The diagram shows the automatic path. Manual analysis displays its candidate immediately, without the WAIT stage. Both paths require Main review and your approval before saving.
44
+ The diagram shows the automatic path. Manual analysis displays its candidate immediately, without the WAIT stage. Both paths require Main review and your approval before the save.
45
45
 
46
46
  ### Automatic analysis
47
47
 
48
48
  Automatic mode waits for the configured number of non-empty user inputs. The default is three.
49
49
 
50
- It starts at the next idle `agent_settled` event that is not aborted. It starts at most once per extension runtime.
50
+ It starts at the next idle `agent_settled` event that is not aborted. It starts at most one time per extension runtime.
51
51
 
52
52
  An aborted run does not start automatic analysis. It keeps the input count and the automatic opportunity, so a later eligible normal settlement can start analysis. `aborted: false` does not prove that the provider completed successfully.
53
53
 
@@ -57,7 +57,7 @@ Branch changes reset the input counter. Automatic analysis and candidate widgets
57
57
 
58
58
  Only one analysis can run at a time. A pending candidate blocks another analysis.
59
59
 
60
- Manual and automatic analysis send Pi's current model-visible session context to the child model configured through `/task-models`. Session context edits that omit or replace messages are honored; original text removed from model context is not sent to the child. Request-local `context` and `context_with_system` transformations are not included.
60
+ Manual and automatic analysis send Pi's current model-visible session context to the child model configured through `/task-models`. Session context edits that omit or replace messages are honored. Original text removed from model context is not sent to the child. Request-local `context` and `context_with_system` transformations are not included.
61
61
 
62
62
  Its payload includes the active compaction or branch summary, user text, successfully completed assistant text, and effective prompt names and descriptions.
63
63
 
@@ -69,17 +69,17 @@ New user input does not stop a running child. Branch navigation discards its old
69
69
 
70
70
  ### Review and save
71
71
 
72
- A manually requested analysis displays its completed candidate immediately. Automatic analysis shows a running widget, then keeps a completed candidate behind the `Prompt ready — /promptor` widget until you run `/promptor` or `/promptor dismiss`, so background work never interrupts the conversation.
72
+ A manually requested analysis displays its completed candidate immediately. Automatic analysis shows a running widget. Then it keeps a completed candidate behind the `Prompt ready — /promptor` widget until you run `/promptor` or `/promptor dismiss`. Thus, background work never interrupts the conversation.
73
73
 
74
74
  Displayed candidates are visible messages marked as untrusted.
75
75
 
76
- Refine the candidate with Main. Ask Main to return only the complete Final Prompt Draft before saving it with `/promptor save [name]`.
76
+ Refine the candidate with Main. Ask Main to return only the complete Final Prompt Draft. Then save it with `/promptor save [name]`.
77
77
 
78
- Saving is allowed only after you show a candidate and Main then completes a valid Markdown review reply. Saving uses that latest retained Main reply as the entire file. Replies before the active compaction or branch summary cannot be saved.
78
+ You can save only after you show a candidate and Main then completes a valid Markdown review reply. The save uses that latest retained Main reply as the entire file. Replies before the active compaction or branch summary cannot be saved.
79
79
 
80
80
  An interrupted, failed, empty, or tool-use reply cannot be saved. The extension never falls back to an older reply.
81
81
 
82
- A successful save ends that review. Show another candidate and complete another Main review reply before saving again.
82
+ A successful save ends that review. Show another candidate and complete another Main review reply before you save again.
83
83
 
84
84
  `/promptor save` uses the suggested candidate name. Pass `/promptor save <name>` to choose another. Names must be lowercase kebab-case, start with a letter, and contain at most 64 ASCII characters. Existing command names and prompt files are rejected.
85
85
 
@@ -100,27 +100,27 @@ Package-owned: `~/.pi/agent/config/pi-prompt-creator/config.json`
100
100
  | `automatic` | Runs automatic analysis after enough user inputs. | Boolean. | `true` |
101
101
  | `inputThreshold` | Sets the number of non-empty user inputs before automatic analysis. | Positive safe integer (`1`–`9007199254740991`). | `3` |
102
102
 
103
- Edit either field, then run `/reload` to apply the change. Omitted fields use their defaults.
103
+ Edit either field. Then run `/reload` to apply the change. Omitted fields use their defaults.
104
104
 
105
105
  A missing file quietly uses both defaults. Startup never creates or rewrites the file.
106
106
 
107
107
  Malformed config or unknown keys disable automatic analysis. Pi warns once and leaves the file unchanged.
108
108
 
109
- Only `/promptor automatic on` or `/promptor automatic off` writes the config. Toggling preserves the configured threshold.
109
+ Only `/promptor automatic on` or `/promptor automatic off` writes the config. A toggle keeps the configured threshold.
110
110
 
111
111
  ## State and storage
112
112
 
113
113
  A pending candidate stays in memory only. Automatic mode persists, but counters and candidates do not.
114
114
 
115
- Saved prompts live at `~/.pi/agent/prompts/<name>.md`. Saving never replaces an existing file.
115
+ Saved prompts are at `~/.pi/agent/prompts/<name>.md`. A save never replaces an existing file.
116
116
 
117
117
  ## Limits and recovery
118
118
 
119
119
  The child payload stays within 30,000 characters, including its JSON envelope and prompt metadata.
120
120
 
121
- It prioritizes the active summary, then the newest complete messages. It omits excess prompt metadata before conversation context.
121
+ It gives priority to the active summary, then to the newest complete messages. It omits excess prompt metadata before conversation context.
122
122
 
123
- Old messages may be omitted. Individual messages are never cut.
123
+ Old messages can be omitted. Individual messages are never cut.
124
124
 
125
125
  Generated candidate names use lowercase kebab-case and stay within 64 ASCII characters.
126
126
 
@@ -128,7 +128,7 @@ Candidate and Final Prompt Draft Markdown must be non-empty and at most 16 KiB.
128
128
 
129
129
  Candidate and saved Markdown reject NUL and other terminal controls. Ordinary tabs and line feeds are allowed.
130
130
 
131
- No candidate clears the running widget without a notice. Invalid output or child failure shows `Prompt analysis failed — /promptor`. Failed analysis is not retried automatically; run `/promptor` or `/promptor analyze` to start again.
131
+ If analysis finds no candidate, the running widget clears without a notice. Invalid output or child failure shows `Prompt analysis failed — /promptor`. Failed analysis is not retried automatically. Run `/promptor` or `/promptor analyze` to start again.
132
132
 
133
133
  The failure widget clears after the next non-empty user input. Analysis has a two-minute idle timeout and five-minute hard timeout.
134
134
 
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@henryqw/pi-prompt-creator",
3
- "version": "3.1.2",
3
+ "version": "3.1.4",
4
4
  "description": "Turn current Pi conversation signals into user-approved prompt templates.",
5
5
  "keywords": [
6
6
  "pi-package",
@@ -46,7 +46,7 @@
46
46
  },
47
47
  "dependencies": {
48
48
  "@henryqw/pi-config-store": "^3.0.0",
49
- "@henryqw/pi-subagent": "^22.0.0 || ^23.0.0 || ^24.0.0 || ^25.0.0 || ^26.0.0",
49
+ "@henryqw/pi-subagent": "^22.0.0 || ^23.0.0 || ^24.0.0 || ^25.0.0 || ^26.0.0 || ^27.0.0",
50
50
  "@henryqw/pi-task-models": "^8.0.0"
51
51
  },
52
52
  "devDependencies": {