ptbk 0.114.0-48 → 0.114.0-49
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 +44 -25
- package/package.json +3 -3
package/README.md
CHANGED
|
@@ -383,7 +383,7 @@ Promptbook Coder is **not another standalone coding model**. It is an orchestrat
|
|
|
383
383
|
|
|
384
384
|
- prompt files with explicit statuses like `[ ]`, `[^]`, `[x]`, and `[-]`
|
|
385
385
|
- automatic selection of the next runnable task, including priority support
|
|
386
|
-
-
|
|
386
|
+
- shared project context loaded from `AGENTS.md` by default
|
|
387
387
|
- automatic `git add`, commit, and push after each successful prompt
|
|
388
388
|
- dedicated coding-agent Git identity and optional GPG signing
|
|
389
389
|
- verification and repair flow for work that is done, partial, or broken
|
|
@@ -405,7 +405,7 @@ Prompts marked with `[-]` are not ready yet, prompts containing `@@@` are treate
|
|
|
405
405
|
#### Features
|
|
406
406
|
|
|
407
407
|
- **Multi-runner execution:** `openai-codex`, `github-copilot`, `cline`, `claude-code`, `opencode`, `gemini`, `qwen-code`
|
|
408
|
-
- **
|
|
408
|
+
- **Project defaults:** Developer, invocation cwd, and project `AGENTS.md`; `--agent`, `--path`, and `--context` independently override them
|
|
409
409
|
- **Reasoning control:** `--thinking-level low|medium|high|xhigh` for supported runners
|
|
410
410
|
- **Unattended or interactive runs:** default auto mode, or `--no-auto` to wait for user confirmation before each prompt
|
|
411
411
|
- **Git safety:** clean working tree check by default, or `--git-changes ignore` to keep the changes and `--git-changes continue` to resume an interrupted prompt
|
|
@@ -425,11 +425,11 @@ npx ts-node ./src/cli/test/ptbk.ts coder generate-boilerplates --template prompt
|
|
|
425
425
|
|
|
426
426
|
npx ts-node ./src/cli/test/ptbk.ts coder generate-boilerplates --template prompts/templates/agents-server.md
|
|
427
427
|
|
|
428
|
-
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
|
|
428
|
+
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
|
|
429
429
|
|
|
430
|
-
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 --
|
|
430
|
+
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 --auto-push
|
|
431
431
|
|
|
432
|
-
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 --
|
|
432
|
+
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 --git-changes ignore
|
|
433
433
|
|
|
434
434
|
npx ts-node ./src/cli/test/ptbk.ts coder find-refactor-candidates
|
|
435
435
|
|
|
@@ -451,11 +451,11 @@ ptbk coder generate-boilerplates
|
|
|
451
451
|
|
|
452
452
|
ptbk coder generate-boilerplates --template prompts/templates/common.md
|
|
453
453
|
|
|
454
|
-
ptbk coder run --harness github-copilot --model gpt-5.4 --thinking-level xhigh --agent agents/coding/developer.book --
|
|
454
|
+
ptbk coder run --harness github-copilot --model gpt-5.4 --thinking-level xhigh --agent agents/coding/developer.book --check "npm run check"
|
|
455
455
|
|
|
456
|
-
ptbk coder run --harness github-copilot --model gpt-5.4 --thinking-level xhigh --agent agents/coding/developer.book --
|
|
456
|
+
ptbk coder run --harness github-copilot --model gpt-5.4 --thinking-level xhigh --agent agents/coding/developer.book --auto-push
|
|
457
457
|
|
|
458
|
-
ptbk coder run --harness github-copilot --model gpt-5.4 --thinking-level xhigh --agent agents/coding/developer.book --
|
|
458
|
+
ptbk coder run --harness github-copilot --model gpt-5.4 --thinking-level xhigh --agent agents/coding/developer.book --check "npm run check" --git-changes ignore
|
|
459
459
|
|
|
460
460
|
ptbk coder find-refactor-candidates
|
|
461
461
|
|
|
@@ -472,33 +472,52 @@ ptbk coder verify
|
|
|
472
472
|
| ------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | --- | ------ | ---- | ----- | ------------------------------------------------------------------------ |
|
|
473
473
|
| `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/`. |
|
|
474
474
|
| `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. |
|
|
475
|
-
| `ptbk coder run` | Picks the next ready prompt, can run
|
|
475
|
+
| `ptbk coder run` | Picks the next ready prompt, can run project checks before coding to stop or repair pre-existing failures, appends optional context, runs it through the selected coding agent, can optionally check each attempt with the project command and feed failing output back for retries, then marks success or failure, commits the result, and pushes only when `--auto-push` is enabled. |
|
|
476
476
|
| `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. |
|
|
477
477
|
| `ptbk coder verify` | Walks through completed prompts, archives truly finished work, and adds follow-up repair prompts for unfinished results. |
|
|
478
478
|
|
|
479
479
|
#### Most useful `ptbk coder run` flags
|
|
480
480
|
|
|
481
|
-
|
|
482
|
-
|
|
483
|
-
|
|
484
|
-
|
|
485
|
-
|
|
486
|
-
|
|
487
|
-
|
|
488
|
-
|
|
489
|
-
|
|
490
|
-
|
|
491
|
-
|
|
492
|
-
|
|
493
|
-
|
|
494
|
-
|
|
495
|
-
|
|
481
|
+
A **check** is the project's aggregate validation: tests, linting, typechecking, builds, generated-code consistency,
|
|
482
|
+
and other quality checks. `ptbk init` and `ptbk coder init` preserve an existing `scripts.check`, or compose available
|
|
483
|
+
validation scripts and report their scope. Configure the failing setup placeholder if the project has none.
|
|
484
|
+
|
|
485
|
+
```bash
|
|
486
|
+
ptbk coder run --harness openai-codex --check "npm run check" --check-before yes-and-fix
|
|
487
|
+
ptbk coder run --harness openai-codex --check "npm run lint && npm run build && npm test"
|
|
488
|
+
```
|
|
489
|
+
|
|
490
|
+
The default preflight mode remains `no`. Enabled preflight uses `npm run check` when no command is supplied;
|
|
491
|
+
post-prompt verification remains opt-in. Initial checks and repairs use the same command and actual process result.
|
|
492
|
+
Replace retired `--test` and `--test-before` with `--check` and `--check-before`. Init migrates recognized generated
|
|
493
|
+
scripts while preserving custom validation. For conflicts or custom callers, it reports the exact entries/files to
|
|
494
|
+
review: preserve the required validation in `check`, update references, then remove the unused legacy entry.
|
|
495
|
+
Automation that invokes `npm run test-for-ptbk-coder` must switch to `npm run check`. Restart an already-running
|
|
496
|
+
Coder invocation with the new flags to release its captured legacy command; initialization creates no compatibility alias.
|
|
497
|
+
|
|
498
|
+
| Flag | Purpose |
|
|
499
|
+
| -------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
|
|
500
|
+
| `--harness <name>` | Selects the coding harness. |
|
|
501
|
+
| `--agent <book>` | Selects the primary Book; defaults to the selected project's `agents/developer.book`. |
|
|
502
|
+
| `--path <directory>` | Selects the project; defaults to invocation cwd. Relative paths start there, not at the CLI installation or enclosing Git root. |
|
|
503
|
+
| `--model <model>` | Chooses the runner model; required for `openai-codex`, `gemini` and `qwen-code`, optional for `github-copilot`. |
|
|
504
|
+
| `--context <text-or-file>` | Replaces the default project `AGENTS.md` with inline instructions or a project-relative file; an empty value disables context. |
|
|
505
|
+
| `--check <command>` | Runs a verification command after each prompt attempt and feeds failing output back for retries. |
|
|
506
|
+
| `--check-before <mode>` | Runs project checks before coding: `no` (default), `yes-and-fail` (stop with results), or `yes-and-fix` (create one repair prompt first); defaults to `npm run check` when enabled without `--check`. |
|
|
507
|
+
| `--thinking-level <level>` | Sets reasoning effort for supported runners. |
|
|
508
|
+
| `--no-auto` | Waits for user confirmation before each prompt instead of running automatically through the queue. |
|
|
509
|
+
| `--git-changes <mode>` | Decides what happens with a dirty working tree: `fail` (default), `ignore` to keep the changes, or `continue` to resume the single interrupted `[^]` prompt with them. |
|
|
510
|
+
| `--priority <n>` | Runs only prompts at or above the given priority. |
|
|
511
|
+
| `--dry-run` | Prints which prompts are ready instead of executing them. |
|
|
512
|
+
| `--allow-credits` | Lets OpenAI Codex spend credits when required. |
|
|
513
|
+
| `--auto-push` | Pushes each successful coding-agent commit to the configured remote. |
|
|
514
|
+
| `--auto-migrate` | Runs testing-server database migrations after each successful prompt. |
|
|
496
515
|
|
|
497
516
|
#### Typical usage pattern
|
|
498
517
|
|
|
499
518
|
1. Initialize once with `ptbk coder init`.
|
|
500
519
|
2. Customize `prompts/templates/*.md` if needed, then create or write prompt files in `prompts/`.
|
|
501
|
-
3. Customize
|
|
520
|
+
3. Customize `agents/developer.book` and `AGENTS.md`; the runner selects both automatically. Use `--path` for another project or `--agent` and `--context` for explicit overrides.
|
|
502
521
|
4. Run unattended batches by default, or pass `--no-auto` to confirm each prompt interactively.
|
|
503
522
|
5. Finish with `ptbk coder verify` so resolved prompts are archived and broken ones get explicit repair follow-ups.
|
|
504
523
|
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "ptbk",
|
|
3
|
-
"version": "0.114.0-
|
|
3
|
+
"version": "0.114.0-49",
|
|
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,
|
|
@@ -88,10 +88,10 @@
|
|
|
88
88
|
"npm": ">=8.0.0"
|
|
89
89
|
},
|
|
90
90
|
"peerDependencies": {
|
|
91
|
-
"@promptbook/core": "0.114.0-
|
|
91
|
+
"@promptbook/core": "0.114.0-49"
|
|
92
92
|
},
|
|
93
93
|
"dependencies": {
|
|
94
|
-
"promptbook": "0.114.0-
|
|
94
|
+
"promptbook": "0.114.0-49"
|
|
95
95
|
},
|
|
96
96
|
"bin": {
|
|
97
97
|
"ptbk": "bin/promptbook-cli-proxy.js"
|