@bastani/atomic 0.9.7-alpha.1 → 0.9.7

package/CHANGELOG.md

@@ -2,6 +2,23 @@
 
 ## [Unreleased]
 
+## [0.9.7] - 2026-07-12
+
+### Added
+
+- Added a shared convergence contract to the bundled `goal` and `ralph` workflows: implementation starts from an observable acceptance/contract matrix derived from the literal objective/acceptance criteria (with explicit state/transition/invariant modeling for stateful work), reviewers independently derive adversarial checks from the literal contract before relying on worker receipts or worker-authored tests, reproduced findings require durable regression evidence before they count as resolved, and each review round persists a deduplicated cross-reviewer `consolidated_findings` batch that the next worker turn repairs together instead of one finding per turn. Literal-contract scope controls are preserved throughout, so nothing beyond the user's requirements is forced.
+- Added a "Choosing an Execution Shape" section to `docs/workflows.md`: an agent-facing decision ladder covering inline work, inline subagent delegation, direct one-off `task`/`tasks`/`chain` shapes, named/builtin workflows, custom TypeScript workflows, and composed/nested workflows; a six-dimension scoring rubric (structure, verifiability, iteration, risk, duration, isolation) with hard-signal overrides; a "Task queues and software factories" playbook for fire-and-forget requests like "address all open issues" (enumerate and dependency-classify first, fan out independent items as separate per-item workflow runs in bounded waves with per-item worktrees/PRs, compose dependent items into one parent graph that nests proven children, and mix both for clustered queues); and a "Prompting the choice" guide listing the user prompt levers (naming the shape, acceptance criteria, loop wording, evidence requests, scope boundaries, and queue policy) that steer the agent's execution-shape decision.
+- Added a "Context-Mode-Aware Prompt Text" section to `docs/workflows.md` documenting that stage prompts must not describe their own context mode, fresh stages must not reference invisible context (prior conversation, sibling stages, graph topology), and forked continuation prompts should send only the delta with a pointer back to guidance already established in the forked history.
+
+### Changed
+
+- Accelerated PR/main CI by running platform-independent validation once on Linux while retaining installed-package Node integration and release-archive smoke coverage on Linux and Windows, and by reusing caller-installed dependencies and package builds during binary assembly. Test suites now have one bounded, observable flake-recovery attempt with preserved logs, environment/resource diagnostics, CI annotations, and no retries for deterministic workflow/release/package/publish gates. Release publication no longer reruns the full PR suite: a protected-default-branch integrity gate proves the release commit is generated from a parent already integrated into `main`, contains exactly the expected version and shrinkwrap material, and pins that immutable SHA across release jobs before preserving all release-specific metadata, docs, native, binary, package, and npm provenance checks.
+- Changed bundled `goal` completion to evidence closure rather than reviewer agreement alone: reviewer quorum can only complete the run when no objective-relevant blocking finding from any reviewer in the current round remains unresolved, unresolved findings are recorded in the inspectable reducer decision reason, and the bounded loop still stops at `max_turns` as `needs_human`. Severity labels alone no longer dismiss objective-relevant findings in Goal or Ralph: `required_by_objective` findings block at any priority (P3 included), while `consistent_with_objective` P3 nice-to-haves stay non-blocking.
+
+### Fixed
+
+- Fixed retryable-failure classification across main-chat retry/fallback, workflow stage fallback, and subagent fallback to treat provider usage-limit exhaustion (for example `Codex error: The usage limit has been reached`, plus `usage_limit_reached`/`insufficient_quota`-style codes) as a retryable quota/rate-limit failure, so configured `fallbackModels` advance to the next candidate provider/model instead of dead-ending the turn, stage, or run. Provider messages that flatten the token into free text (for example `usage_limit_reached` or `usage-limit`, matched with space/underscore/hyphen/joined separators) classify the same as the structured codes across all three paths. Nested cause/diagnostic and session-shaped error payloads classify the same way; cancellations, safety refusals, task/tool failures, and unrelated errors remain non-retryable.
+
 ## [0.9.7-alpha.1] - 2026-07-12
 
 ### Added

package/dist/builtin/cursor/CHANGELOG.md

@@ -2,6 +2,12 @@
 
 ## [Unreleased]
 
+## [0.9.7] - 2026-07-12
+
+### Changed
+
+- Published the stable Atomic 0.9.7 release for the Cursor provider package; no functional Cursor provider changes were made after 0.9.6.
+
 ## [0.9.7-alpha.1] - 2026-07-12
 
 ### Changed

package/dist/builtin/cursor/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@bastani/cursor",
-  "version": "0.9.7-alpha.1",
+  "version": "0.9.7",
   "private": true,
   "description": "Experimental first-party Atomic extension for Cursor OAuth, model discovery, and streaming provider registration.",
   "contributors": [
@@ -40,7 +40,7 @@
     }
   },
   "dependencies": {
-    "@bastani/atomic-natives": "0.9.7-alpha.1",
+    "@bastani/atomic-natives": "0.9.7",
     "@bufbuild/protobuf": "^2.12.1",
     "@earendil-works/pi-ai": "^0.80.6"
   }

package/dist/builtin/intercom/CHANGELOG.md

@@ -4,6 +4,16 @@ All notable changes to the `pi-intercom` extension will be documented in this fi
 
 ## [Unreleased]
 
+## [0.9.7] - 2026-07-12
+
+### Fixed
+
+- Made blocking reply waits race-safe under concurrent tool calls. Waiter admission is now an atomic synchronous check-and-reserve shared by `intercom` `ask` and `contact_supervisor`: when several blocking requests race (parallel tool calls in one turn, same-tool or cross-tool), exactly one wins the reservation and every other call returns a normal structured "Already waiting for a reply" tool error. Previously the loser received an already-rejected promise that could sit unhandled while the winner's question was still being sent, crashing the whole agent process with an unhandled `Error: Already waiting for a reply` rejection.
+- Scoped blocking-ask cleanup to the owning call: cancellation, send failures, and delivery errors now settle only that call's own reply waiter instead of rejecting whichever waiter happened to be pending, so a losing or failing concurrent request can no longer tear down another call's in-flight ask. The reply-wait timeout also rejects only its own waiter, threaded replies still resolve the exact winning request, and session shutdown/replacement and broker disconnects continue to reject the currently pending waiter.
+- Made the pending reply-wait promise unhandled-rejection-proof: rejections that fire between the owner's awaits (for example a delivery failure racing dispatch) are pre-handled, so blocking coordination can never terminate the process.
+- Initialized the lazy Intercom runtime from the most recent turn/tool/model lifecycle context when a subagent result or control relay arrives in a session that never emitted `session_start` to extensions (for example non-interactive in-process child sessions). Such sessions now deliver self-addressed subagent result announcements locally instead of failing every relay.
+- Stopped recording misleading `intercom_result_error`/`intercom_control_error` "Intercom shutting down" entries when a relay fires while the runtime is uninitialized and the target is not the local session. The relay now acknowledges the message as undelivered (callers fall back to inline results) without attempting a broker connection that can only fail.
+
 ## [0.9.7-alpha.1] - 2026-07-12
 
 ### Fixed

package/dist/builtin/intercom/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@bastani/intercom",
-  "version": "0.9.7-alpha.1",
+  "version": "0.9.7",
   "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 +7,12 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
+## [0.9.7] - 2026-07-12
+
+### Changed
+
+- Published the stable Atomic 0.9.7 release for the MCP extension; no functional MCP changes were made after 0.9.6.
+
 ## [0.9.7-alpha.1] - 2026-07-12
 
 ### Changed

package/dist/builtin/mcp/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@bastani/mcp",
-  "version": "0.9.7-alpha.1",
+  "version": "0.9.7",
   "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 +2,12 @@
 
 ## [Unreleased]
 
+## [0.9.7] - 2026-07-12
+
+### Fixed
+
+- Fixed subagent model fallback to classify provider usage-limit exhaustion (for example `Codex error: The usage limit has been reached`, plus `usage_limit`/`usage_limit_reached`/`usage_limit_exceeded`/`insufficient_quota` codes) as a retryable quota/rate-limit failure, so configured `fallbackModels` advance to the next candidate provider/model instead of failing the run. The message matcher tolerates the same space/underscore/hyphen/joined separators as the code path, so provider errors that flatten the token into free text (for example `usage_limit_reached` or `usage-limit`) also advance the chain. Nested cause/diagnostic and session-shaped errors classify the same way, while cancellations, safety refusals, task/tool failures, and unrelated errors remain non-retryable; the shared conformance corpus keeps this rule in lockstep with the workflows classifier.
+
 ## [0.9.7-alpha.1] - 2026-07-12
 
 ### Fixed

package/dist/builtin/subagents/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@bastani/subagents",
-  "version": "0.9.7-alpha.1",
+  "version": "0.9.7",
   "private": true,
   "description": "Atomic extension for delegating tasks to subagents with chains, parallel execution, and background runs. Fork of: https://github.com/nicobailon/pi-subagents",
   "contributors": [

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

@@ -4,6 +4,12 @@ All notable changes to this project will be documented in this file.
 
 ## [Unreleased]
 
+## [0.9.7] - 2026-07-12
+
+### Changed
+
+- Published the stable Atomic 0.9.7 release for the web-access extension; no functional web-access changes were made after 0.9.6.
+
 ## [0.9.7-alpha.1] - 2026-07-12
 
 ### Changed

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

@@ -1,6 +1,6 @@
 {
   "name": "@bastani/web-access",
-  "version": "0.9.7-alpha.1",
+  "version": "0.9.7",
   "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 +6,26 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/),
 
 ## [Unreleased]
 
+## [0.9.7] - 2026-07-12
+
+### Added
+
+- Added a shared convergence contract for the builtin `goal` and `ralph` workflows (`builtin/shared-prompts.ts` + deterministic gates in `builtin/review-convergence.ts`): workers/orchestrators must derive an observable acceptance/contract matrix from the literal objective/acceptance criteria before implementing (one row per clause mapped to the concrete check that proves it) and must model states, transitions, and invariants explicitly for stateful work; reviewers must independently derive adversarial checks (boundary/edge/negative and state/transition/invariant probes) from the literal contract before relying on the worker receipt, implementation notes, or worker-authored tests; reproduced findings require durable regression evidence (a persisted test or exact re-runnable check) before they count as resolved; and the evidence-closure policy is stated to both roles so approval semantics are visible in-prompt. All contracts inherit the literal-contract scope controls, so no behavior beyond the objective/acceptance criteria is required.
+- Added deduplicated cross-reviewer `consolidated_findings` batches to the Goal and Ralph `review-round-latest.json` artifacts (`consolidateFindingsBatch` in `builtin/review-convergence.ts`), with blocking entries sorted first and reviewer attribution merged per finding. Goal's next worker turn reads the round artifact first and is instructed to plan and repair the whole batch — grouped by root cause, with regression evidence — instead of fixing one finding per turn; Ralph's research/orchestrator stages receive the same batch through the round artifact.
+
+### Changed
+
+- Changed the built-in `goal` and `ralph` reviewer model defaults for GPT-5.6 Sol from the `:max` reasoning suffix to `:xhigh` across every provider form (`openai-codex`, `github-copilot`, `openai`, `cursor`, and `openrouter/openai`), including Ralph's `reviewer-b` primary model (`openai-codex/gpt-5.6-sol:xhigh`).
+- Aligned all built-in Goal reviewer stages with Ralph's clean, non-forked reviewer context behavior and exact `reviewer-a` model configuration, making Claude Fable 5 the shared primary reviewer while keeping one canonical fallback chain.
+- Changed builtin `goal` completion to evidence closure rather than reviewer agreement alone: the deterministic reducer now completes only when reviewer quorum is met AND no objective-relevant blocking finding from any reviewer in the current round remains unresolved. A quorum-met round with unresolved findings continues with an inspectable decision reason listing the findings, and the bounded loop still stops at `max_turns` as `needs_human` (with the closure gap recorded) so vetoes cannot drift indefinitely.
+- Changed the shared Goal/Ralph review gate so severity labels alone can no longer dismiss objective-relevant findings: `required_by_objective` findings now block at any priority (P3 included) via the shared `findingBlocksClosure` predicate, while `consistent_with_objective` P3 nice-to-haves remain non-blocking (preserving the dummy-finding anti-spin behavior) and `beyond_objective`/`contradicts_objective` findings remain non-blocking scope controls. Goal's `reviewApproved` and Ralph's `isBlockingFinding`/`reviewDecisionApproved` now share this single deterministic predicate.
+- Slimmed the builtin `goal`, `ralph`, and `open-claude-design` stage prompts to remove context-mode bloat: prompts no longer describe the stage's own context window ("previous conversation context", "previous workflow reasoning", or sibling parallel passes that a fresh stage cannot see), and forked continuation prompts now send only the per-iteration delta. Goal's forked worker turns send just the ledger pointer, latest receipts, and latest review artifacts; Ralph's forked orchestrator sends the rewritten research path and notes reminder; and Ralph's forked research-prompt-refinement and research continuations reference the skill, request, and contracts already present in their forked histories instead of re-injecting them (new `renderForkedResearchPromptRefinementPrompt`/`renderForkedResearchPrompt`). Each forked prompt carries a one-line pointer that previously established guidance still applies unchanged.
+
+### Fixed
+
+- Fixed workflow stage model fallback to classify provider usage-limit exhaustion (for example `Codex error: The usage limit has been reached`, plus `usage_limit`/`usage_limit_reached`/`usage_limit_exceeded`/`insufficient_quota` codes) as a retryable quota/rate-limit failure, so configured `fallbackModels` advance to the next candidate provider/model instead of failing the stage. The message matcher tolerates the same space/underscore/hyphen/joined separators as the code path, so provider errors that flatten the token into free text (for example `usage_limit_reached` or `usage-limit`) also advance the chain. Nested cause/diagnostic and session-shaped errors classify the same way, while cancellations, safety refusals, task/tool failures, and unrelated errors remain non-retryable.
+- Fixed model orchestration guidance so every workflow launch from interactive chat stays in the background: named runs remain automatically detached, direct `task`/`tasks`/`chain` launches require top-level `async: true`, inspection and control calls are excluded, and foreground launches require an explicit user request or technical necessity plus advance notice ([#1765](https://github.com/bastani-inc/atomic/issues/1765)).
+
 ## [0.9.7-alpha.1] - 2026-07-12
 
 ### Added

package/dist/builtin/workflows/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@bastani/workflows",
-  "version": "0.9.7-alpha.1",
+  "version": "0.9.7",
   "private": true,
   "description": "Atomic extension for multi-stage workflow authoring and execution.",
   "contributors": [

package/npm-shrinkwrap.json

@@ -1,15 +1,15 @@
 {
 	"name": "@bastani/atomic",
-	"version": "0.9.7-alpha.1",
+	"version": "0.9.7",
 	"lockfileVersion": 3,
 	"requires": true,
 	"packages": {
 		"": {
 			"name": "@bastani/atomic",
-			"version": "0.9.7-alpha.1",
+			"version": "0.9.7",
 			"license": "MIT",
 			"dependencies": {
-				"@bastani/atomic-natives": "0.9.7-alpha.1",
+				"@bastani/atomic-natives": "0.9.7",
 				"@bufbuild/protobuf": "^2.12.1",
 				"@earendil-works/pi-agent-core": "^0.80.6",
 				"@earendil-works/pi-ai": "^0.80.6",
@@ -515,16 +515,16 @@
 			}
 		},
 		"node_modules/@bastani/atomic-natives": {
-			"version": "0.9.7-alpha.1",
-			"resolved": "https://registry.npmjs.org/@bastani/atomic-natives/-/atomic-natives-0.9.7-alpha.1.tgz",
+			"version": "0.9.7",
+			"resolved": "https://registry.npmjs.org/@bastani/atomic-natives/-/atomic-natives-0.9.7.tgz",
 			"license": "MIT",
 			"optionalDependencies": {
-				"@bastani/atomic-natives-darwin-arm64": "0.9.7-alpha.1",
-				"@bastani/atomic-natives-darwin-x64": "0.9.7-alpha.1",
-				"@bastani/atomic-natives-linux-arm64-gnu": "0.9.7-alpha.1",
-				"@bastani/atomic-natives-linux-x64-gnu": "0.9.7-alpha.1",
-				"@bastani/atomic-natives-win32-arm64-msvc": "0.9.7-alpha.1",
-				"@bastani/atomic-natives-win32-x64-msvc": "0.9.7-alpha.1"
+				"@bastani/atomic-natives-darwin-arm64": "0.9.7",
+				"@bastani/atomic-natives-darwin-x64": "0.9.7",
+				"@bastani/atomic-natives-linux-arm64-gnu": "0.9.7",
+				"@bastani/atomic-natives-linux-x64-gnu": "0.9.7",
+				"@bastani/atomic-natives-win32-arm64-msvc": "0.9.7",
+				"@bastani/atomic-natives-win32-x64-msvc": "0.9.7"
 			},
 			"engines": {
 				"bun": ">=1.3.14",
@@ -532,8 +532,8 @@
 			}
 		},
 		"node_modules/@bastani/atomic-natives-darwin-arm64": {
-			"version": "0.9.7-alpha.1",
-			"resolved": "https://registry.npmjs.org/@bastani/atomic-natives-darwin-arm64/-/atomic-natives-darwin-arm64-0.9.7-alpha.1.tgz",
+			"version": "0.9.7",
+			"resolved": "https://registry.npmjs.org/@bastani/atomic-natives-darwin-arm64/-/atomic-natives-darwin-arm64-0.9.7.tgz",
 			"license": "MIT",
 			"os": [
 				"darwin"
@@ -544,8 +544,8 @@
 			"optional": true
 		},
 		"node_modules/@bastani/atomic-natives-darwin-x64": {
-			"version": "0.9.7-alpha.1",
-			"resolved": "https://registry.npmjs.org/@bastani/atomic-natives-darwin-x64/-/atomic-natives-darwin-x64-0.9.7-alpha.1.tgz",
+			"version": "0.9.7",
+			"resolved": "https://registry.npmjs.org/@bastani/atomic-natives-darwin-x64/-/atomic-natives-darwin-x64-0.9.7.tgz",
 			"license": "MIT",
 			"os": [
 				"darwin"
@@ -556,8 +556,8 @@
 			"optional": true
 		},
 		"node_modules/@bastani/atomic-natives-linux-arm64-gnu": {
-			"version": "0.9.7-alpha.1",
-			"resolved": "https://registry.npmjs.org/@bastani/atomic-natives-linux-arm64-gnu/-/atomic-natives-linux-arm64-gnu-0.9.7-alpha.1.tgz",
+			"version": "0.9.7",
+			"resolved": "https://registry.npmjs.org/@bastani/atomic-natives-linux-arm64-gnu/-/atomic-natives-linux-arm64-gnu-0.9.7.tgz",
 			"license": "MIT",
 			"os": [
 				"linux"
@@ -571,8 +571,8 @@
 			"optional": true
 		},
 		"node_modules/@bastani/atomic-natives-linux-x64-gnu": {
-			"version": "0.9.7-alpha.1",
-			"resolved": "https://registry.npmjs.org/@bastani/atomic-natives-linux-x64-gnu/-/atomic-natives-linux-x64-gnu-0.9.7-alpha.1.tgz",
+			"version": "0.9.7",
+			"resolved": "https://registry.npmjs.org/@bastani/atomic-natives-linux-x64-gnu/-/atomic-natives-linux-x64-gnu-0.9.7.tgz",
 			"license": "MIT",
 			"os": [
 				"linux"
@@ -586,8 +586,8 @@
 			"optional": true
 		},
 		"node_modules/@bastani/atomic-natives-win32-arm64-msvc": {
-			"version": "0.9.7-alpha.1",
-			"resolved": "https://registry.npmjs.org/@bastani/atomic-natives-win32-arm64-msvc/-/atomic-natives-win32-arm64-msvc-0.9.7-alpha.1.tgz",
+			"version": "0.9.7",
+			"resolved": "https://registry.npmjs.org/@bastani/atomic-natives-win32-arm64-msvc/-/atomic-natives-win32-arm64-msvc-0.9.7.tgz",
 			"license": "MIT",
 			"os": [
 				"win32"
@@ -598,8 +598,8 @@
 			"optional": true
 		},
 		"node_modules/@bastani/atomic-natives-win32-x64-msvc": {
-			"version": "0.9.7-alpha.1",
-			"resolved": "https://registry.npmjs.org/@bastani/atomic-natives-win32-x64-msvc/-/atomic-natives-win32-x64-msvc-0.9.7-alpha.1.tgz",
+			"version": "0.9.7",
+			"resolved": "https://registry.npmjs.org/@bastani/atomic-natives-win32-x64-msvc/-/atomic-natives-win32-x64-msvc-0.9.7.tgz",
 			"license": "MIT",
 			"os": [
 				"win32"

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@bastani/atomic",
-  "version": "0.9.7-alpha.1",
+  "version": "0.9.7",
   "description": "Atomic coding agent CLI with read, bash, edit, write tools and session management",
   "type": "module",
   "atomicConfig": {
@@ -77,7 +77,7 @@
     "prepublishOnly": "bun run clean && bun run build && bun run shrinkwrap"
   },
   "dependencies": {
-    "@bastani/atomic-natives": "0.9.7-alpha.1",
+    "@bastani/atomic-natives": "0.9.7",
     "@bufbuild/protobuf": "^2.12.1",
     "@earendil-works/pi-agent-core": "^0.80.6",
     "@earendil-works/pi-ai": "^0.80.6",