ptbk 0.112.0-99 → 0.113.0-0

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.
Files changed (2) hide show
  1. package/README.md +76 -44
  2. package/package.json +3 -3
package/README.md CHANGED
@@ -27,6 +27,25 @@ Create persistent AI agents that turn your company's scattered knowledge into ac
27
27
 
28
28
 
29
29
 
30
+ ### Standalone VPS
31
+
32
+ Run the standalone VPS installer only on a fresh server. Interactive mode asks for the installation values:
33
+
34
+ ```bash
35
+ sudo curl -fsSL https://raw.githubusercontent.com/webgptorg/promptbook/refs/heads/main/other/vps/install.sh | bash
36
+ ```
37
+
38
+ Non-interactive mode takes defaults from command-line options. When `--openai-api-key` is provided with the default OpenAI Codex runner, the installer installs and configures Codex automatically; other runner authentication can be configured later from the UI or SSH:
39
+
40
+ ```bash
41
+ sudo curl -fsSL https://raw.githubusercontent.com/webgptorg/promptbook/refs/heads/main/other/vps/install.sh | bash -s -- \
42
+ --non-interactive \
43
+ --yes-i-understand-that-script-should-be-run-on-fresh-server \
44
+ --domain my-server.com \
45
+ --openai-api-key sk-proj-xxx \
46
+ --admin-password xxx
47
+ ```
48
+
30
49
 
31
50
 
32
51
 
@@ -38,7 +57,7 @@ Create persistent AI agents that turn your company's scattered knowledge into ac
38
57
 
39
58
  Promptbook lets you create **persistent AI agents** that work on real goals for your company. The [**Agents Server**](https://gallery.ptbk.io/) is the heart of the project - a place where your AI agents live, remember context, collaborate in teams, and get things done.
40
59
 
41
- Nowadays, the biggest challenge for most business applications isn't the raw capabilities of AI models. Large language models such as GPT-5.2 and Claude-4.5 are incredibly capable.
60
+ Nowadays, the biggest challenge for most business applications isn't the raw capabilities of AI models. Large language models such as Claude Mythos, GPT-5.6 or Kimi K2.7 are incredibly capable.
42
61
 
43
62
  The main challenge lies in **managing the context**, providing rules and knowledge, and narrowing the personality.
44
63
 
@@ -46,17 +65,20 @@ In Promptbook, you define your agents **using simple Books** - a human-readable
46
65
 
47
66
  <table style="border: 1px solid #777; border-radius: 10px;"><tr><td>
48
67
 
49
- **<ins>Paul Smith</ins>**<br/>
68
+ **<ins>Lawyer</ins>**<br/>
50
69
  <br/>
51
- **PERSONA** You are a company lawyer.<br/>
70
+ GOAL You are a company lawyer.<br/>
52
71
  Your job is to provide legal advice and support to the company and its employees.<br/>
53
- **GOAL** Respond to incoming legal inquiries via email and keep the company website updated with the latest legal policies.<br/>
72
+ Respond to incoming legal inquiries via email and keep the company website updated with the latest legal policies.<br/>
73
+ <br/>
54
74
  **RULE** You are knowledgeable, professional, and detail-oriented.<br/>
55
75
  **KNOWLEDGE** https://company.com/company-policies.pdf<br/>
56
76
  **KNOWLEDGE** https://company.com/internal-documents/employee-handbook.docx<br/>
57
- **USE EMAIL**<br/>
58
- **USE BROWSER**<br/>
59
- **TEAM** You are part of the legal team of Paul Smith & Associés, you discuss with {Emily White}, the head of the compliance department. {George Brown} is expert in corporate law and {Sophia Black} is expert in labor law.<br/>
77
+ <br/>
78
+ USE EMAIL<br/>
79
+ USE BROWSER<br/>
80
+ <br/>
81
+ TEAM You are part of the legal team of Paul Smith & Associés, you discuss with {Emily White}, the head of the compliance department. {George Brown} is expert in corporate law and {Sophia Black} is expert in labor law.<br/>
60
82
 
61
83
  </td></tr></table>
62
84
 
@@ -89,12 +111,12 @@ Goals define what the agent should actively work toward. Unlike a chatbot that o
89
111
 
90
112
  <table style="border: 1px solid #777; border-radius: 10px;"><tr><td>
91
113
 
92
- **<ins>Paul Smith & Associés</ins>**<br/>
114
+ **<ins>Company Lawyer</ins>**<br/>
93
115
  <br/>
94
- **PERSONA** You are a company lawyer.<br/>
116
+ GOAL<br/>
95
117
  Your job is to provide legal advice and support to the company and its employees.<br/>
96
- **GOAL** Respond to incoming legal inquiries via email within 24 hours.<br/>
97
- **GOAL** Keep the company website updated with the latest legal policies and compliance information.<br/>
118
+ GOAL Respond to incoming legal inquiries via email within 24 hours.<br/>
119
+ GOAL Keep the company website updated with the latest legal policies and compliance information.<br/>
98
120
 
99
121
  </td></tr></table>
100
122
 
@@ -112,8 +134,8 @@ Promptbook Engine will automatically enforce this knowledge during interactions.
112
134
  <br/>
113
135
  **PERSONA** You are a company lawyer.<br/>
114
136
  Your job is to provide legal advice and support to the company and its employees.<br/>
115
- **GOAL** Respond to incoming legal inquiries via email within 24 hours.<br/>
116
- **GOAL** Keep the company website updated with the latest legal policies and compliance information.<br/>
137
+ GOAL Respond to incoming legal inquiries via email within 24 hours.<br/>
138
+ GOAL Keep the company website updated with the latest legal policies and compliance information.<br/>
117
139
  **KNOWLEDGE** https://company.com/company-policies.pdf<br/>
118
140
  **KNOWLEDGE** https://company.com/internal-documents/employee-handbook.docx<br/>
119
141
 
@@ -131,8 +153,8 @@ Depending on rule strictness, Promptbook will either propagate it to the prompt
131
153
  <br/>
132
154
  **PERSONA** You are a company lawyer.<br/>
133
155
  Your job is to provide legal advice and support to the company and its employees.<br/>
134
- **GOAL** Respond to incoming legal inquiries via email within 24 hours.<br/>
135
- **GOAL** Keep the company website updated with the latest legal policies and compliance information.<br/>
156
+ GOAL Respond to incoming legal inquiries via email within 24 hours.<br/>
157
+ GOAL Keep the company website updated with the latest legal policies and compliance information.<br/>
136
158
  **RULE** Always ensure compliance with local laws and regulations.<br/>
137
159
  **RULE** Never provide legal advice outside your area of expertise.<br/>
138
160
  **RULE** Never provide legal advice about criminal law.<br/>
@@ -153,16 +175,16 @@ These are what turn a chatbot into a persistent agent that actually does work.
153
175
  <br/>
154
176
  **PERSONA** You are a company lawyer.<br/>
155
177
  Your job is to provide legal advice and support to the company and its employees.<br/>
156
- **GOAL** Respond to incoming legal inquiries via email within 24 hours.<br/>
157
- **GOAL** Keep the company website updated with the latest legal policies and compliance information.<br/>
178
+ GOAL Respond to incoming legal inquiries via email within 24 hours.<br/>
179
+ GOAL Keep the company website updated with the latest legal policies and compliance information.<br/>
158
180
  **RULE** Always ensure compliance with local laws and regulations.<br/>
159
181
  **RULE** Never provide legal advice outside your area of expertise.<br/>
160
182
  **RULE** Never provide legal advice about criminal law.<br/>
161
183
  **KNOWLEDGE** https://company.com/company-policies.pdf<br/>
162
184
  **KNOWLEDGE** https://company.com/internal-documents/employee-handbook.docx<br/>
163
- **USE EMAIL**<br/>
164
- **USE BROWSER**<br/>
165
- **USE SEARCH ENGINE**<br/>
185
+ USE EMAIL<br/>
186
+ USE BROWSER<br/>
187
+ USE SEARCH ENGINE<br/>
166
188
 
167
189
  </td></tr></table>
168
190
 
@@ -176,20 +198,22 @@ Team commitment allows you to define the team structure and advisory fellow memb
176
198
  <br/>
177
199
  **PERSONA** You are a company lawyer.<br/>
178
200
  Your job is to provide legal advice and support to the company and its employees.<br/>
179
- **GOAL** Respond to incoming legal inquiries via email within 24 hours.<br/>
180
- **GOAL** Keep the company website updated with the latest legal policies and compliance information.<br/>
201
+ GOAL Respond to incoming legal inquiries via email within 24 hours.<br/>
202
+ GOAL Keep the company website updated with the latest legal policies and compliance information.<br/>
181
203
  **RULE** Always ensure compliance with local laws and regulations.<br/>
182
204
  **RULE** Never provide legal advice outside your area of expertise.<br/>
183
205
  **RULE** Never provide legal advice about criminal law.<br/>
184
206
  **KNOWLEDGE** https://company.com/company-policies.pdf<br/>
185
207
  **KNOWLEDGE** https://company.com/internal-documents/employee-handbook.docx<br/>
186
- **USE EMAIL**<br/>
187
- **USE BROWSER**<br/>
188
- **USE SEARCH ENGINE**<br/>
189
- **TEAM** You are part of the legal team of Paul Smith & Associés, you discuss with {Emily White}, the head of the compliance department. {George Brown} is expert in corporate law and {Sophia Black} is expert in labor law.<br/>
208
+ USE EMAIL<br/>
209
+ USE BROWSER<br/>
210
+ USE SEARCH ENGINE<br/>
211
+ TEAM You are part of the legal team of Paul Smith & Associés, you discuss with {Emily White}, the head of the compliance department. {George Brown} is expert in corporate law and {Sophia Black} is expert in labor law.<br/>
190
212
 
191
213
  </td></tr></table>
192
214
 
215
+
216
+
193
217
  ### Promptbook Ecosystem
194
218
 
195
219
  Promptbook is an ecosystem of tools centered around the **Agents Server** - a production-ready platform for running persistent AI agents.
@@ -212,6 +236,8 @@ The [Promptbook Engine](https://github.com/webgptorg/promptbook) is the open-sou
212
236
 
213
237
 
214
238
 
239
+
240
+
215
241
  ## 💜 The Promptbook Project
216
242
 
217
243
  Promptbook project is an ecosystem centered around the **Agents Server** - a platform for creating, deploying, and running persistent AI agents. Following is a list of the most important pieces of the project:
@@ -249,6 +275,8 @@ Promptbook project is an ecosystem centered around the **Agents Server** - a pla
249
275
  </tbody>
250
276
  </table>
251
277
 
278
+
279
+
252
280
  ### 🌐 Community & Social Media
253
281
 
254
282
  Join our growing community of developers and users:
@@ -305,6 +333,8 @@ Join our growing community of developers and users:
305
333
 
306
334
 
307
335
 
336
+
337
+
308
338
  ## 📚 Documentation
309
339
 
310
340
  See detailed guides and API reference in the [docs](https://github.com/webgptorg/promptbook/discussions/categories/concepts) or [online](https://discord.gg/x3QWNaa89N).
@@ -396,9 +426,9 @@ Prompts marked with `[-]` are not ready yet, prompts containing `@@@` are treate
396
426
  #### Features
397
427
 
398
428
  - **Multi-runner execution:** `openai-codex`, `github-copilot`, `cline`, `claude-code`, `opencode`, `gemini`
399
- - **Context injection:** `--context AGENTS.md` or inline extra instructions
429
+ - **Context injection:** `--agent agents/coding/developer.book --context AGENTS.md` or inline extra instructions
400
430
  - **Reasoning control:** `--thinking-level low|medium|high|xhigh` for supported runners
401
- - **Interactive or unattended runs:** default wait mode, or `--no-wait` for batch execution
431
+ - **Unattended or interactive runs:** default auto mode, or `--no-auto` to wait for user confirmation before each prompt
402
432
  - **Git safety:** clean working tree check by default, optional `--ignore-git-changes`
403
433
  - **Opt-in remote pushes:** commits stay local unless you explicitly pass `--auto-push`
404
434
  - **Prompt triage:** `--priority` to process only more important tasks first
@@ -416,11 +446,11 @@ npx ts-node ./src/cli/test/ptbk.ts coder generate-boilerplates --template prompt
416
446
 
417
447
  npx ts-node ./src/cli/test/ptbk.ts coder generate-boilerplates --template prompts/templates/agents-server.md
418
448
 
419
- npx ts-node ./src/cli/test/ptbk.ts coder run --agent github-copilot --model gpt-5.4 --thinking-level xhigh --context AGENTS.md
449
+ npx ts-node ./src/cli/test/ptbk.ts coder run --harness github-copilot --model gpt-5.4 --thinking-level xhigh --agent agents/coding/developer.book --context AGENTS.md
420
450
 
421
- npx ts-node ./src/cli/test/ptbk.ts coder run --agent github-copilot --model gpt-5.4 --thinking-level xhigh --context AGENTS.md --auto-push
451
+ npx ts-node ./src/cli/test/ptbk.ts coder run --harness github-copilot --model gpt-5.4 --thinking-level xhigh --agent agents/coding/developer.book --context AGENTS.md --auto-push
422
452
 
423
- npx ts-node ./src/cli/test/ptbk.ts coder run --agent github-copilot --model gpt-5.4 --thinking-level xhigh --context AGENTS.md --ignore-git-changes --no-wait
453
+ npx ts-node ./src/cli/test/ptbk.ts coder run --harness github-copilot --model gpt-5.4 --thinking-level xhigh --agent agents/coding/developer.book --context AGENTS.md --ignore-git-changes
424
454
 
425
455
  npx ts-node ./src/cli/test/ptbk.ts coder find-refactor-candidates
426
456
 
@@ -442,11 +472,11 @@ ptbk coder generate-boilerplates
442
472
 
443
473
  ptbk coder generate-boilerplates --template prompts/templates/common.md
444
474
 
445
- ptbk coder run --agent github-copilot --model gpt-5.4 --thinking-level xhigh --context AGENTS.md --test npm run test
475
+ ptbk coder run --harness github-copilot --model gpt-5.4 --thinking-level xhigh --agent agents/coding/developer.book --context AGENTS.md --test npm run test
446
476
 
447
- ptbk coder run --agent github-copilot --model gpt-5.4 --thinking-level xhigh --context AGENTS.md --auto-push
477
+ ptbk coder run --harness github-copilot --model gpt-5.4 --thinking-level xhigh --agent agents/coding/developer.book --context AGENTS.md --auto-push
448
478
 
449
- ptbk coder run --agent github-copilot --model gpt-5.4 --thinking-level xhigh --context AGENTS.md --test npm run test --ignore-git-changes --no-wait
479
+ ptbk coder run --harness github-copilot --model gpt-5.4 --thinking-level xhigh --agent agents/coding/developer.book --context AGENTS.md --test npm run test --ignore-git-changes
450
480
 
451
481
  ptbk coder find-refactor-candidates
452
482
 
@@ -459,24 +489,24 @@ ptbk coder verify
459
489
 
460
490
  #### What each command does
461
491
 
462
- | Command | What it does |
463
- | ------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | --- | ------ | ---- | ----- | ------------------------------------------------------------------------ |
492
+ | Command | What it does |
493
+ | ------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | --- | ------ | ---- | ----- | ------------------------------------------------------------------------ |
464
494
  | `ptbk coder init` | Creates `prompts/`, `prompts/done/`, the project-generic template files materialized in `prompts/templates/` (currently `common.md`), and a starter `AGENTS.md`; ensures `.env` contains `CODING_AGENT_GIT_NAME`, `CODING_AGENT_GIT_EMAIL`, and `CODING_AGENT_GIT_SIGNING_KEY`; adds helper coder scripts to `package.json`; ensures `.gitignore` contains `/.promptbook`; and configures `.vscode/settings.json` to save pasted prompt images into `prompts/screenshots/`. |
465
- | `ptbk coder generate-boilerplates` | Creates new prompt markdown files with fresh emoji tags so you can quickly fill in coding tasks; `--template` accepts either a built-in alias or a markdown file path relative to the project root. |
466
- | `ptbk coder run` | Picks the next ready prompt, appends optional context, runs it through the selected coding agent, can optionally verify each attempt with a shell test command and feed failing output back for retries, then marks success or failure, commits the result, and pushes only when `--auto-push` is enabled. |
467
- | `ptbk coder find-refactor-candidates` | Scans the repository for oversized or overpacked files and writes prompt files for likely refactors; `--level <xlow | low | medium | high | xhigh | extreme>` ranges from a very benevolent scan to a very aggressive sweep. |
468
- | `ptbk coder verify` | Walks through completed prompts, archives truly finished work, and adds follow-up repair prompts for unfinished results. |
495
+ | `ptbk coder generate-boilerplates` | Creates new prompt markdown files with fresh emoji tags so you can quickly fill in coding tasks; `--template` accepts either a built-in alias or a markdown file path relative to the project root. |
496
+ | `ptbk coder run` | Picks the next ready prompt, appends optional context, runs it through the selected coding agent, can optionally verify each attempt with a shell test command and feed failing output back for retries, then marks success or failure, commits the result, and pushes only when `--auto-push` is enabled. |
497
+ | `ptbk coder find-refactor-candidates` | Scans the repository for oversized or overpacked files and writes prompt files for likely refactors; `--level <xlow | low | medium | high | xhigh | extreme>` ranges from a very benevolent scan to a very aggressive sweep. |
498
+ | `ptbk coder verify` | Walks through completed prompts, archives truly finished work, and adds follow-up repair prompts for unfinished results. |
469
499
 
470
500
  #### Most useful `ptbk coder run` flags
471
501
 
472
502
  | Flag | Purpose |
473
503
  | -------------------------- | -------------------------------------------------------------------------------------------------- |
474
- | `--agent <name>` | Selects the coding backend. |
504
+ | `--harness <name>` | Selects the coding harness. |
475
505
  | `--model <model>` | Chooses the runner model; required for `openai-codex` and `gemini`, optional for `github-copilot`. |
476
506
  | `--context <text-or-file>` | Appends extra instructions inline or from a file like `AGENTS.md`. |
477
507
  | `--test <command>` | Runs a verification command after each prompt attempt and feeds failing output back for retries. |
478
508
  | `--thinking-level <level>` | Sets reasoning effort for supported runners. |
479
- | `--no-wait` | Skips interactive pauses between prompts for unattended execution. |
509
+ | `--no-auto` | Waits for user confirmation before each prompt instead of running automatically through the queue. |
480
510
  | `--ignore-git-changes` | Disables the clean-working-tree guard. |
481
511
  | `--priority <n>` | Runs only prompts at or above the given priority. |
482
512
  | `--dry-run` | Prints which prompts are ready instead of executing them. |
@@ -488,8 +518,8 @@ ptbk coder verify
488
518
 
489
519
  1. Initialize once with `ptbk coder init`.
490
520
  2. Customize `prompts/templates/*.md` if needed, then create or write prompt files in `prompts/`.
491
- 3. Customize the starter `AGENTS.md` with repository-specific instructions, then pass `--context AGENTS.md`.
492
- 4. Run one prompt at a time interactively, or use `--no-wait` for unattended batches.
521
+ 3. Customize the starter `AGENTS.md` with repository-specific instructions, then pass `--agent agents/coding/developer.book --context AGENTS.md`.
522
+ 4. Run unattended batches by default, or pass `--no-auto` to confirm each prompt interactively.
493
523
  5. Finish with `ptbk coder verify` so resolved prompts are archived and broken ones get explicit repair follow-ups.
494
524
 
495
525
 
@@ -512,6 +542,8 @@ The following glossary is used to clarify certain concepts:
512
542
 
513
543
  _Note: This section is not a complete dictionary, more list of general AI / LLM terms that has connection with Promptbook_
514
544
 
545
+
546
+
515
547
  ### 💯 Core concepts
516
548
 
517
549
  - [📚 Collection of pipelines](https://github.com/webgptorg/promptbook/discussions/65)
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "ptbk",
3
- "version": "0.112.0-99",
3
+ "version": "0.113.0-0",
4
4
  "description": "Promptbook: Create persistent AI agents that turn your company's scattered knowledge into action",
5
5
  "private": false,
6
6
  "sideEffects": false,
@@ -91,10 +91,10 @@
91
91
  "zod": "$zod"
92
92
  },
93
93
  "peerDependencies": {
94
- "@promptbook/core": "0.112.0-99"
94
+ "@promptbook/core": "0.113.0-0"
95
95
  },
96
96
  "dependencies": {
97
- "promptbook": "0.112.0-99"
97
+ "promptbook": "0.113.0-0"
98
98
  },
99
99
  "bin": {
100
100
  "ptbk": "bin/promptbook-cli-proxy.js"