@bastani/atomic 0.8.16 → 0.8.17-0

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.
package/CHANGELOG.md CHANGED
@@ -2,6 +2,17 @@
2
2
 
3
3
  ## [Unreleased]
4
4
 
5
+ ## [0.8.17-0] - 2026-05-26
6
+
7
+ ### Breaking Changes
8
+
9
+ - Removed bundled Ralph's configurable `review_quorum` and `blocker_threshold` inputs; `max_turns` remains configurable alongside `objective` and optional `base_branch` ([#1061](https://github.com/flora131/atomic/issues/1061)).
10
+
11
+ ### Changed
12
+
13
+ - Updated bundled Ralph docs and prompts to more closely match Codex `/goal` continuation guidance while retaining deterministic reviewer-gated completion ([#1061](https://github.com/flora131/atomic/issues/1061)).
14
+ - Restored bundled Ralph's stronger historical review gate prompt and `review_decision` schema with findings, oracle satisfaction, receipt assessment, verification remaining, and reviewer-error guard fields.
15
+
5
16
  ## [0.8.16] - 2026-05-26
6
17
 
7
18
  ### Changed
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@bastani/intercom",
3
- "version": "0.8.16",
3
+ "version": "0.8.17-0",
4
4
  "private": true,
5
5
  "description": "Atomic extension providing a private coordination channel between parent and child agent sessions. Fork of: https://github.com/nicobailon/pi-intercom",
6
6
  "contributors": [
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@bastani/mcp",
3
- "version": "0.8.16",
3
+ "version": "0.8.17-0",
4
4
  "private": true,
5
5
  "description": "Atomic extension that adapts MCP (Model Context Protocol) servers into the coding agent. Fork of: https://github.com/nicobailon/pi-mcp-adapter",
6
6
  "contributors": [
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@bastani/subagents",
3
- "version": "0.8.16",
3
+ "version": "0.8.17-0",
4
4
  "private": true,
5
5
  "description": "Atomic extension for delegating tasks to subagents with chains, parallel execution, and TUI clarification. Fork of: https://github.com/nicobailon/pi-subagents",
6
6
  "contributors": [
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@bastani/web-access",
3
- "version": "0.8.16",
3
+ "version": "0.8.17-0",
4
4
  "private": true,
5
5
  "description": "Atomic extension for web search, URL fetching, GitHub repo cloning, PDF/video extraction. Fork of: https://github.com/nicobailon/pi-web-access",
6
6
  "contributors": [
@@ -6,6 +6,17 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/),
6
6
 
7
7
  ## [Unreleased]
8
8
 
9
+ ## [0.8.17-0] - 2026-05-26
10
+
11
+ ### Breaking Changes
12
+
13
+ - Removed Ralph's configurable `review_quorum` and `blocker_threshold` inputs; `max_turns` remains configurable while reviewer quorum and blocker threshold use fixed controller defaults ([#1061](https://github.com/flora131/atomic/issues/1061)).
14
+
15
+ ### Changed
16
+
17
+ - Aligned Ralph's goal-continuation prompt more closely with Codex `/goal` hidden continuation guidance, including current-state evidence, non-shrinking scope, fidelity, completion audit, and strict blocked audit language ([#1061](https://github.com/flora131/atomic/issues/1061)).
18
+ - Restored Ralph's stronger historical review gate prompt and `review_decision` schema with findings, oracle satisfaction, receipt assessment, verification remaining, and reviewer-error guard fields.
19
+
9
20
  ## [0.8.16] - 2026-05-26
10
21
 
11
22
  ### Changed
@@ -306,21 +306,35 @@ Scout + research-history chain → two parallel specialist waves → aggregator.
306
306
 
307
307
  Final Markdown research documents are written to dated `research/` paths relative to the current working directory, with a numeric suffix if needed to avoid overwriting an existing document. Hidden run artifacts are written under `research/.deep-research-<run-id>/`.
308
308
 
309
- ### `ralph`
309
+ ### `goal`
310
310
 
311
311
  Goal Runner workflow: initialize a persisted goal ledger with a per-run goal id and lifecycle events, render goal-continuation context, run bounded worker LM turns, append receipts, run three independent reviewers, and let a TypeScript reducer decide `complete`, `continue`, `blocked`, or `needs_human`. Token budget behavior is intentionally excluded.
312
312
 
313
313
  ```text
314
- /workflow ralph objective="Migrate the database layer to Drizzle ORM" max_turns=5 review_quorum=2
314
+ /workflow goal objective="Migrate the database layer to Drizzle ORM" base_branch=develop
315
+ ```
316
+
317
+ | Input | Type | Required | Default | Description |
318
+ | ------------- | -------- | -------- | ------------- | ------------------------------------------------------------- |
319
+ | `objective` | `text` | ✓ | — | Goal-runner objective. |
320
+ | `max_turns` | `number` | — | `10` | Maximum worker/review turns before human follow-up is needed. |
321
+ | `base_branch` | `string` | — | `origin/main` | Branch reviewers compare the current delta with. |
322
+
323
+ `goal` defaults to 10 worker/review turns. Reviewer quorum is fixed internally at 2 reviewer `complete` votes. The repeated-blocker threshold defaults to 3 consecutive same-blocker turns and is clamped to `max_turns` when you run fewer than 3 turns.
324
+
325
+ ### `ralph`
326
+
327
+ Plan → orchestrate → simplify → discover → review → PR-handoff workflow: write an RFC-style technical design document under `specs/`, delegate implementation through sub-agents, simplify recent changes, discover review infrastructure, run parallel reviewers, iterate until approval or the loop limit, then prepare a pull-request report.
328
+
329
+ ```text
330
+ /workflow ralph prompt="Plan and migrate the database layer to Drizzle ORM" max_loops=3 base_branch=develop
315
331
  ```
316
332
 
317
- | Input | Type | Required | Default | Description |
318
- | ------------------- | -------- | -------- | ------------- | ------------------------------------------------ |
319
- | `objective` | `text` | ✓ | — | Goal-runner objective. |
320
- | `max_turns` | `number` | — | `10` | Maximum worker/review turns. |
321
- | `review_quorum` | `number` | — | `2` | Reviewer `complete` votes required to complete. |
322
- | `blocker_threshold` | `number` | — | `3` | Consecutive same-blocker turns required to block; requires at least two observations and is capped by `max_turns` when possible. |
323
- | `base_branch` | `string` | — | `origin/main` | Branch reviewers compare the current delta with. |
333
+ | Input | Type | Required | Default | Description |
334
+ | ------------- | -------- | -------- | ------------- | ------------------------------------------------------------- |
335
+ | `prompt` | `text` | ✓ | — | Task, feature request, issue summary, or spec path to plan, execute, refine, review, and prepare for PR. |
336
+ | `max_loops` | `number` | — | `10` | Maximum plan/orchestrate/review iterations before PR handoff. |
337
+ | `base_branch` | `string` | — | `origin/main` | Branch reviewers and PR-prep compare the current delta with. |
324
338
 
325
339
  ### `open-claude-design`
326
340