@bastani/atomic 0.8.22 → 0.8.23

package/CHANGELOG.md

@@ -2,6 +2,24 @@
 
 ## [Unreleased]
 
+## [0.8.23] - 2026-06-02
+
+### Changed
+
+- Promoted the 0.8.23 prerelease package version to a stable release.
+
+## [0.8.23-0] - 2026-06-02
+
+### Changed
+
+- Documented workflow artifact-path handoffs and `Read the file at <path>...` downstream prompts as the preferred alternative to injecting large `previous` payloads, review histories, or session tails.
+- Updated the Ralph workflow docs to reflect the simplified plan/orchestrate/simplify/review loop without separate `infra-*` discovery stages.
+- Updated the default workflow system-prompt guidance to prefer file/artifact handoffs with explicit downstream read instructions for large stage-to-stage context.
+
+### Fixed
+
+- Fixed severe flickering in the `ask_user_question` dialog on short terminals by suspending the animated working loader while the blocking question UI is open; the inline dialog no longer pushes the ticking loader above the viewport, which had forced a full-screen clear+replay on every spinner frame.
+
 ## [0.8.22] - 2026-06-01
 
 ### Breaking Changes

package/dist/builtin/intercom/CHANGELOG.md

@@ -4,6 +4,18 @@ All notable changes to the `pi-intercom` extension will be documented in this fi
 
 ## [Unreleased]
 
+## [0.8.23] - 2026-06-02
+
+### Changed
+
+- Promoted the 0.8.23 prerelease package version to a stable release.
+
+## [0.8.23-0] - 2026-06-02
+
+### Changed
+
+- Bumped package version for the Atomic 0.8.23 prerelease.
+
 ## [0.8.18] - 2026-05-27
 
 ### Changed

package/dist/builtin/intercom/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@bastani/intercom",
-  "version": "0.8.22",
+  "version": "0.8.23",
   "private": true,
   "description": "Atomic extension providing a private coordination channel between parent and child agent sessions. Fork of: https://github.com/nicobailon/pi-intercom",
   "contributors": [

package/dist/builtin/mcp/CHANGELOG.md

@@ -7,6 +7,18 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
+## [0.8.23] - 2026-06-02
+
+### Changed
+
+- Promoted the 0.8.23 prerelease package version to a stable release.
+
+## [0.8.23-0] - 2026-06-02
+
+### Changed
+
+- Bumped package version for the Atomic 0.8.23 prerelease.
+
 ## [0.8.20] - 2026-05-29
 
 ### Changed

package/dist/builtin/mcp/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@bastani/mcp",
-  "version": "0.8.22",
+  "version": "0.8.23",
   "private": true,
   "description": "Atomic extension that adapts MCP (Model Context Protocol) servers into the coding agent. Fork of: https://github.com/nicobailon/pi-mcp-adapter",
   "contributors": [

package/dist/builtin/subagents/CHANGELOG.md

@@ -2,6 +2,18 @@
 
 ## [Unreleased]
 
+## [0.8.23] - 2026-06-02
+
+### Changed
+
+- Promoted the 0.8.23 prerelease package version to a stable release.
+
+## [0.8.23-0] - 2026-06-02
+
+### Changed
+
+- Bumped package version for the Atomic 0.8.23 prerelease.
+
 ## [0.8.22] - 2026-06-01
 
 ### Fixed

package/dist/builtin/subagents/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@bastani/subagents",
-  "version": "0.8.22",
+  "version": "0.8.23",
   "private": true,
   "description": "Atomic extension for delegating tasks to subagents with chains, parallel execution, and TUI clarification. Fork of: https://github.com/nicobailon/pi-subagents",
   "contributors": [

package/dist/builtin/web-access/CHANGELOG.md

@@ -4,6 +4,18 @@ All notable changes to this project will be documented in this file.
 
 ## [Unreleased]
 
+## [0.8.23] - 2026-06-02
+
+### Changed
+
+- Promoted the 0.8.23 prerelease package version to a stable release.
+
+## [0.8.23-0] - 2026-06-02
+
+### Changed
+
+- Bumped package version for the Atomic 0.8.23 prerelease.
+
 ## [0.8.20] - 2026-05-29
 
 ### Changed

package/dist/builtin/web-access/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@bastani/web-access",
-  "version": "0.8.22",
+  "version": "0.8.23",
   "private": true,
   "description": "Atomic extension for web search, URL fetching, GitHub repo cloning, PDF/video extraction. Fork of: https://github.com/nicobailon/pi-web-access",
   "contributors": [

package/dist/builtin/workflows/CHANGELOG.md

@@ -6,6 +6,29 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/),
 
 ## [Unreleased]
 
+## [0.8.23] - 2026-06-02
+
+### Changed
+
+- Promoted the 0.8.23 prerelease package version to a stable release.
+
+## [0.8.23-0] - 2026-06-02
+
+### Added
+
+- Added a workflow node chat Ctrl+D hint that shares the bottom footer line with model/cwd metadata and appears in the bottom-right corner of stage-local ctx.ui widgets.
+
+### Changed
+
+- Changed bundled Goal and Ralph workflows to save reviewer feedback as JSON artifacts and hand only latest review artifact paths to downstream agents instead of injecting full review histories or session tails.
+- Removed Ralph's separate `infra-locate-*`, `infra-analyze-*`, and `infra-patterns-*` discovery stages; Ralph reviewers now inspect repository infrastructure directly as needed during review.
+- Documented artifact-path handoffs, `outputMode: "file-only"`, `reads`, and explicit `Read the file at <path>...` downstream prompts as the preferred pattern for large workflow context.
+- Updated the workflow tool description to tell agents to hand off large stage context through files/artifacts instead of injected previous text.
+
+### Fixed
+
+- Fixed paused workflow stage chats so Ctrl+D returns to the orchestrator graph instead of closing back to the main chat.
+
 ## [0.8.22] - 2026-06-01
 
 ### Breaking Changes

package/dist/builtin/workflows/README.md

@@ -80,15 +80,27 @@ export default defineWorkflow("parallel-research")
   .run(async (ctx) => {
     const topic = ctx.inputs.topic;
 
-    const reports = await ctx.parallel([
-      { name: "auth-specialist", task: `Research authentication patterns for: ${topic}` },
-      { name: "db-specialist", task: `Research database layer for: ${topic}` },
-      { name: "api-specialist", task: `Research API surface for: ${topic}` },
+    const reportPaths = {
+      auth: ".atomic/workflows/runs/parallel-research/auth.md",
+      db: ".atomic/workflows/runs/parallel-research/db.md",
+      api: ".atomic/workflows/runs/parallel-research/api.md",
+    } as const;
+
+    await ctx.parallel([
+      { name: "auth-specialist", task: `Research authentication patterns for: ${topic}`, output: reportPaths.auth, outputMode: "file-only" },
+      { name: "db-specialist", task: `Research database layer for: ${topic}`, output: reportPaths.db, outputMode: "file-only" },
+      { name: "api-specialist", task: `Research API surface for: ${topic}`, output: reportPaths.api, outputMode: "file-only" },
     ], { concurrency: 2, failFast: false });
 
     const summary = await ctx.task("aggregator", {
-      prompt: "Synthesize these specialist reports:\n\n{previous}",
-      previous: reports,
+      prompt: [
+        "Synthesize the specialist reports.",
+        `Auth report: ${reportPaths.auth}`,
+        `Database report: ${reportPaths.db}`,
+        `API report: ${reportPaths.api}`,
+        "Read the files at the paths above incrementally and only expand sections needed for the synthesis.",
+      ].join("\n"),
+      reads: Object.values(reportPaths),
     });
     return { summary: summary.text };
   })
@@ -106,16 +118,21 @@ export default defineWorkflow("review-and-merge")
   .output("status", Type.Optional(Type.String({ description: "Set to \"cancelled\" when the human rejects the plan." })))
   .output("result", Type.Optional(Type.String({ description: "Implementation result when the plan is approved." })))
   .run(async (ctx) => {
+    const planPath = ".atomic/workflows/runs/review-and-merge/plan.md";
     const plan = await ctx.task("planner", {
       prompt: `Create a concise implementation plan for: ${String(ctx.inputs.task)}`,
+      output: planPath,
     });
 
     const approved = await ctx.ui.confirm(`Proceed with this plan?\n\n${plan.text}`);
     if (!approved) return { status: "cancelled" };
 
     const result = await ctx.task("implementer", {
-      prompt: "Execute this plan exactly:\n\n{previous}",
-      previous: plan,
+      prompt: [
+        `Plan artifact: ${planPath}`,
+        `Read the file at ${planPath} incrementally, then execute it exactly.`,
+      ].join("\n"),
+      reads: [planPath],
     });
     return { result: result.text };
   })
@@ -454,7 +471,7 @@ Prompt answer replay is live-memory only. `StageSnapshot.promptAnswerState` repo
 ```json
 {
   "name": "workflow",
-  "description": "Run named workflows or direct one-off task/tasks/chain workflows; discover with list/get/inputs, inspect status/stages/stage details, send prompt answers or steering, pause/resume/interrupt/kill runs, and reload workflow resources. For transcripts, prefer status/stages/stage to get sessionFile/transcriptPath, quote the exact path without rewriting separators (Windows backslashes are valid), search it with rg/grep, and read small ranges; transcript defaults to at most 5 recent entries and explicit tail/limit overrides that preview.",
+  "description": "Run named workflows or direct one-off task/tasks/chain workflows; discover with list/get/inputs, inspect status/stages/stage details, send prompt answers or steering, pause/resume/interrupt/kill runs, and reload workflow resources. For large stage handoffs, write context to files/artifacts, pass paths via reads, and prompt downstream agents to 'Read the file at <path>...' instead of injecting large previous text. For transcripts, prefer status/stages/stage to get sessionFile/transcriptPath, quote the exact path without rewriting separators (Windows backslashes are valid), search it with rg/grep, and read small ranges; transcript defaults to at most 5 recent entries and explicit tail/limit overrides that preview.",
   "parameters": {
     "workflow": "string (optional) — workflow ID or normalized name",
     "inputs": "object (optional) — key/value map of workflow inputs",
@@ -525,7 +542,7 @@ await runWorkflow({
   concurrency: 2,
   reads: ["research/context.md"],
   output: "research/auth-audit.md",
-  outputMode: "inline",
+  outputMode: "file-only",
   worktree: false,
   maxOutput: { lines: 2000 },
   artifacts: true,
@@ -534,6 +551,8 @@ await runWorkflow({
 
 The programmatic definition object mirrors the workflow tool: named workflow runs, single-task runs, parallel `tasks`, and mixed `chain` runs accept the same direct options (`reads`, `output`, `outputMode`, `worktree`, `gitWorktreeDir`, `baseBranch`, `maxOutput`, `artifacts`, `concurrency`, `failFast`, and stage/session options such as `cwd`, `agentDir`, `model`, `tools`, `context`, and `sessionDir`). `chainDir` is chain-only: it provides the shared artifact directory for chain reads, outputs, and worktree diffs.
 
+For large handoffs, prefer artifact paths over prompt injection: write stage output to `output`, set `outputMode: "file-only"` when the parent only needs the path, pass paths with `reads`, and instruct downstream agents explicitly with wording like `Read the file at <path>...`. Reserve `previous`/`{previous}` for compact summaries; avoid passing full session histories, all prior stage outputs, or every review round directly into the next model prompt. In review loops, save JSON review artifacts and pass only the latest review-round artifact, with a ledger or index file linking older rounds when needed.
+
 Workflow stage sessions follow Atomic SDK directory defaults: `DefaultResourceLoader` is initialized with the project `cwd` and the Atomic default `~/.atomic/agent` directory, while legacy `.pi` paths remain readable where the SDK supports multiple config directories. A stage-supplied `agentDir` is treated as an explicit user override; a stage-supplied `resourceLoader` owns discovery, with `cwd`/`agentDir` left for session naming and tool path resolution.
 
 To inspect a workflow's input schema inside pi, use `/workflow inputs <name>` or `/workflow <name> --help`.
@@ -580,7 +599,7 @@ Child workflow outputs: `result`, `status`, `approved`, `goal_id`, `objective`,
 
 ### `ralph`
 
-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.
+Plan → orchestrate → simplify → review → PR-handoff workflow: write an RFC-style technical design document under `specs/`, delegate implementation through sub-agents, simplify recent changes, run parallel reviewers, iterate until approval or the loop limit, then prepare a pull-request report. Reviewers inspect repository infrastructure directly as needed; Ralph no longer runs separate `infra-*` discovery stages.
 
 ```text
 /workflow ralph prompt="Plan and migrate the database layer to Drizzle ORM" max_loops=3 base_branch=develop
@@ -593,7 +612,7 @@ Plan → orchestrate → simplify → discover → review → PR-handoff workflo
 | `base_branch`      | `string` | —        | `origin/main` | Branch reviewers and PR-prep compare the current delta with; also used to create a missing worktree. |
 | `git_worktree_dir` | `string` | —        | `""`          | Optional reusable Git worktree root. Empty runs in the invoking checkout; non-empty values run Ralph stages in the created/reused worktree. |
 
-Child workflow outputs: `result`, `plan`, `plan_path`, `implementation_notes_path`, `pr_report`, `approved`, `iterations_completed`, and `review_report`.
+Child workflow outputs: `result`, `plan`, `plan_path`, `implementation_notes_path`, `pr_report`, `approved`, `iterations_completed`, `review_report`, and `review_report_path`.
 
 ### `open-claude-design`