@bastani/atomic 0.9.11-alpha.1 → 0.9.11-alpha.11

package/dist/builtin/web-access/github-extract.ts

@@ -3,6 +3,7 @@ import { execFile } from "node:child_process";
 import { extname, join, resolve as resolvePath, sep as pathSep } from "node:path";
 import { activityMonitor } from "./activity.js";
 import type { ExtractedContent } from "./extract.js";
+import { flattenTruncatedString } from "./flat-string.js";
 import { checkGhAvailable, checkRepoSize, fetchViaApi, showGhHint } from "./github-api.js";
 import { BINARY_EXTENSIONS, MAX_INLINE_FILE_CHARS, MAX_TREE_ENTRIES, NOISE_DIRS, loadGitHubConfig, parseGitHubUrl, resetGitHubConfig, type GitHubCloneConfig, type GitHubUrlInfo } from "./github-config.js";
 export { parseGitHubUrl, type GitHubUrlInfo } from "./github-config.js";
@@ -225,14 +226,14 @@ function buildDirListing(rootPath: string, subPath: string): string {
 	return lines.join("\n");
 }
 
-function readReadme(localPath: string): string | null {
+export function readReadme(localPath: string): string | null {
 	const candidates = ["README.md", "readme.md", "README", "README.txt", "README.rst"];
 	for (const name of candidates) {
 		const readmePath = join(localPath, name);
 		if (existsSync(readmePath)) {
 			try {
 				const content = readFileSync(readmePath, "utf-8");
-				return content.length > 8192 ? content.slice(0, 8192) + "\n\n[README truncated at 8K chars]" : content;
+				return content.length > 8192 ? flattenTruncatedString(content.slice(0, 8192) + "\n\n[README truncated at 8K chars]") : content;
 			} catch {
 				continue;
 			}

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

@@ -1,6 +1,6 @@
 {
   "name": "@bastani/web-access",
-  "version": "0.9.11-alpha.1",
+  "version": "0.9.11-alpha.11",
   "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": [
@@ -31,7 +31,7 @@
   },
   "peerDependencies": {
     "@bastani/atomic": "*",
-    "@earendil-works/pi-tui": "^0.80.10"
+    "@earendil-works/pi-tui": "^0.83.0"
   },
   "peerDependenciesMeta": {
     "@bastani/atomic": {

package/dist/builtin/workflows/CHANGELOG.md

@@ -6,6 +6,125 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/),
 
 ## [Unreleased]
 
+## [0.9.11-alpha.11] - 2026-08-03
+
+### Fixed
+
+- Fixed workflow graph rendering for large, wide fan-outs by clipping cards, edges, and composed rows to the visible viewport, retaining cached topology and layout across status-only updates, and making idle animation eligibility constant-time ([#2100](https://github.com/bastani-inc/atomic/issues/2100)).
+- Fixed every interactive store mutation cloning the full run payload before the graph could repaint. A status or question update used to build a complete `JSON.stringify`/`JSON.parse` snapshot, traversing workflow inputs, authored stage result bodies, child output values, and tool input/output bodies, so mutation cost scaled with payload size rather than with the graph. Store observation now offers a synchronous invalidation-only channel plus one immutable memoized graph projection per store version, and the graph, overlay, attach pane, stage chat, widget, lifecycle and HIL notifications, resume picker, and send admission all read that projection. In the default configuration (`statusFile: false`), mutations no longer build the legacy full snapshot; enabling `statusFile` retains that snapshot and status-file serialization cost. Topology, status, timing, prompts, attachment state, notices, bounded returned-status fields, durable tool summaries, and child output counts are preserved; the existing `Store.snapshot()` / `Store.subscribe(snapshot)` contract is unchanged for external consumers ([#2100](https://github.com/bastani-inc/atomic/issues/2100)).
+- Fixed the memoized graph projection keeping whole run results in memory. Truncating a result field with `slice()` leaves a V8 SlicedString that points at its untruncated parent, so a 1 KiB projected field kept a multi-megabyte run result alive — inside the store's cached projection, and inside every long-lived holder of one — long after the run itself was removed. Truncated fields are now copied into fresh flat strings, so a session with large workflow results no longer grows heap ([#2100](https://github.com/bastani-inc/atomic/issues/2100)).
+- Fixed durable tool-result summaries retaining the payloads they summarize. `summarizeToolResult` and `summarizeCompletedToolResult` bounded a serialized value with `` `${serialized.slice(0, 237)}...` ``, which leaves a V8 SlicedString behind a ConsString, both pointing at the untruncated parent — so a 240-character summary written into a durable checkpoint or held in a completed-run catalog row kept the entire `JSON.stringify` output alive (measured at 8.4 MiB for one large tool result). Both summaries now copy into fresh flat strings via a shared `flattenTruncatedString` helper, which the memoized graph projection also uses ([#2100](https://github.com/bastani-inc/atomic/issues/2100)).
+- Fixed Escape in an attached workflow-stage chat restoring queued steering and follow-up messages into the editor instead of leaving them stuck in the pending-message queue.
+
+## [0.9.11-alpha.9] - 2026-08-01
+
+### Added
+
+- Added per-node cancellation to `ctx.tool`. Every callback now receives a `WorkflowToolContext` (`{ signal }`) derived from a per-invocation `AbortController` combined with the run signal, so a run abort still cascades to every node while one node can be aborted alone. All retries of a call share that one signal, and existing zero-argument callbacks keep compiling and running unchanged. `WorkflowToolContext` is exported from the authoring surface ([#2078](https://github.com/bastani-inc/atomic/issues/2078)).
+- Added tool nodes as addressable abort targets for `workflow({ action: "quit"|"interrupt", runId, stageId })`. A node resolves by expanded id, local `tool:<argsHash>` id, or tool name with the same exact-then-unique precedence and ambiguity diagnostics stages get. Aborting one node marks it `cancelled` and leaves sibling stages and tool nodes running; tool nodes stay non-attachable, so this adds abort, not chat. The result reports the node outcome and the run separately — `status: "cancelled"` with the observed `workflowStatus` — instead of claiming the run was paused. `pause` on a tool node is now rejected explicitly instead of resolving to nothing ([#2078](https://github.com/bastani-inc/atomic/issues/2078)).
+
+### Changed
+
+- Declared `handlesCtrlC` on every workflow surface mounted through `ctx.ui.custom()` — the graph pane (which hosts stage chat, prompt cards, and the inline form) and the inputs picker. In isolated interactive sessions the terminal host now closes an undeclared remote component on the first Ctrl+C, so the declaration is what keeps `ctrl+c Skip`, `ctrl+c Close`, and picker cancel working.
+- Documented deterministic delivery timing for workflow stage messages. `steer` (and `auto` against a streaming stage) is consumed after the current assistant response finishes its whole tool batch and before the next model request — never between two tool calls of the same response; `followUp` is consumed only when the agent would otherwise stop. Each queue is FIFO in admission order, and steering keeps priority over an earlier-submitted follow-up, so there is no global FIFO across the two queues ([#2074](https://github.com/bastani-inc/atomic/issues/2074)).
+
+### Fixed
+
+- Fixed `open-claude-design` converting a failed `user-feedback-*` stage into design approval (the [#1499](https://github.com/bastani-inc/atomic/issues/1499) catch-then-approve path). A rejected feedback stage — provider errors, model-fallback exhaustion, broken session forks — now propagates and fails the run instead of silently setting `approved_for_export` and exporting an unreviewed design. Resolved results are unchanged: a stage that runs and reports no meaningful notes, including degraded manual/headless display paths, still legitimately reads as approval, and browser/tooling trouble continues to resolve gracefully rather than reject (playwright-cli auto-install, the early browser exit, and the stage's degradation contract are unaffected) ([#2123](https://github.com/bastani-inc/atomic/issues/2123)).
+- Fixed `open-claude-design` embedding unbounded research context inline in single stage prompts, the same single-message overflow class as the [#1499](https://github.com/bastani-inc/atomic/issues/1499) `413 request_too_large`. The composed project design context now persists to `<artifact_dir>/design-context.md` and the curated references brief always persists to `<artifact_dir>/references.md` (with the no-references fallback when discovery is skipped); `reference-discovery` reads the design context, and the generate and exporter stages read both files via `reads` with explicit read-the-file instructions instead of inline `design_system`/`reference_inspiration` embeds. The joined research results are no longer injected as `previous` payloads into `generate-1` or `reference-discovery`. Because the files are required stage inputs, a failed write no longer passes silently: the run exits `blocked` through `ctx.exit` with the artifact paths surfaced (or propagates the error when `ctx.exit` is unavailable) instead of dispatching stages against nonexistent context. Deliberately small inline payloads are unchanged: verbatim-threaded user annotations (the #1464 guardrail) and the word-capped prior design summary ([#2121](https://github.com/bastani-inc/atomic/issues/2121)).
+- Fixed `open-claude-design` blocking on browser live review while reporting `running`, leaving the user with no input affordance. Each refinement round now raises a deterministic run-level `ctx.ui` prompt before its `user-feedback-*` stage starts, so the needs-attention badge fires and the prompt names the preview path and `file://` URL; choosing the skip option accepts the current design and proceeds to export. Only the executor's unavailable-UI rejection (headless mode or a missing UI adapter) degrades to running the review directly; any other gate failure — interruption, a failed durable checkpoint — propagates and stops the run. The feedback-stage prompt additionally instructs the agent to print the live `http://` review URL before starting any long-poll wait, so the URL is visible at the top of the stage output when attaching mid-run ([#2060](https://github.com/bastani-inc/atomic/issues/2060)).
+- Hardened the bundled `impeccable` live-mode scripts against four CodeQL security findings, preserving behavior for all valid inputs: live-edit session ids now fall back to `crypto.getRandomValues` instead of `Math.random` outside secure contexts (`js/insecure-randomness`); the live server clamps the client-supplied poll timeout to the 10-minute default ceiling (`js/resource-exhaustion`); `live-accept` escapes the `--variant` value before splicing it into a `RegExp` (`js/regex-injection`); and manual-edit evidence decodes `&amp;` last so crafted input cannot be double-unescaped (`js/double-escaping`).
+- Fixed worktree setup hooks being reported as failed when they never read their stdin. The hook's JSON input is written to its stdin, but nothing requires a hook to consume it; a hook that exited before that write flushed made `spawnSync` report `EPIPE` and the whole worktree creation was torn down, even though the hook had run to completion and its stdout was captured in full. The child's exit status and output are now authoritative, so only a spawn that never produced a status is treated as a hook failure. Timeouts and every other spawn error stay fatal as before. This race was lost far more often on loaded machines, making it look intermittent.
+- Fixed graceful quit ignoring in-flight `ctx.tool` calls. A run whose only in-flight work was a durable tool node reported `No controllable stages on run <id>; the run remains active` and left the callback running with no way to stop it. Quit now counts running tool nodes as controllable work; after stage pauses acknowledge it closes the root-shared tool-admission boundary, so a call admitted during that wait is still included and none can start afterwards — not even while the durable write is in flight. It then aborts the complete root/nested set, waits a bounded interval for settlement, and only then records the durable paused/resumable transition, so quit is again an exact durability boundary rather than a pause declared while a callback is still mutating the world. A call attempted after the close is refused with the graceful-quit signal and never runs. A callback that ignores its signal is abandoned instead of pinning quit, and the result reports cancelled and abandoned calls by owning `{runId, nodeId}` identity, so two nested children sharing one local node id stay distinguishable ([#2078](https://github.com/bastani-inc/atomic/issues/2078)).
+- Fixed resume after quitting an unfinished `ctx.tool` call. A cancelled call now writes no replayable checkpoint and no `return_failure` outcome, so a cancellation can never replay as data; under `failureMode: "return"` it keeps exactly one inspection-only `tool-failure:` record, which stays out of the replay cache. Resume recomputes the same ordinal and `argsHash` and re-executes exactly that callback at the same `tool:<argsHash>` node, while completed sibling tools still replay from cache. A late value returned by an abandoned callback is discarded before persistence ([#2078](https://github.com/bastani-inc/atomic/issues/2078)).
+- Fixed a quit-time hole where workflow code that caught the tool cancellation could still publish a completed run over quit's paused record: the executor now suspends whenever its own tool work was aborted or refused by a whole-run quit, whichever path the author's code takes afterwards. A catch may clean up, but it is not an opt-out; targeted node abort remains the way to abort one call and keep a run going ([#2078](https://github.com/bastani-inc/atomic/issues/2078)).
+- Fixed resume adopting the stale executor after a callback was abandoned. Quit now detaches that background job, so resume relaunches a fresh executor under the same workflow id and actually re-runs the unfinished call instead of flipping the run to running with nothing driving it. Job and cancellation cleanup are identity-conditional and tool-node store writes are generation-owned, so a late zombie callback can neither evict the replacement's registrations nor mutate its graph node, and registering a second job for one live run id is now a loud error instead of silent double dispatch ([#2078](https://github.com/bastani-inc/atomic/issues/2078)).
+- Fixed a quit whose durable paused transition failed or was refused leaving the run reported as running with nothing running it. Aborting an in-flight `ctx.tool` call commits its executor to suspending, so quit now records the local pause whatever the durable write does; only the resumable promise follows the durable outcome, and the reported error names the durable failure and what it left behind instead of just failing. The run stays controllable, so a retried `/workflow quit` re-attempts the transition and upgrades the pause to resumable — previously the tool handles were already gone, so the retry answered `No controllable stages on run <id>` and the run could never be quit, resumed, or ended ([#2078](https://github.com/bastani-inc/atomic/issues/2078)).
+- Fixed a typed message in an attached workflow stage chat being demoted to a follow-up. When the chat read the stage as idle while workflow message admission still owned the retiring turn, Enter fell through to the unspecified-delivery default and landed at the end of the turn instead of at the next steering boundary, so mid-run correction did not work. Typed Enter now names steering explicitly, matching normal session steering. The choice is scoped to one submission — it travels with the submitting key through the chat host — so a slow in-flight Ctrl+F cannot make a later Enter a follow-up. Ctrl+F still queues a follow-up, a genuinely idle stage still starts a fresh turn, and the authored `stage.sendUserMessage()` default is unchanged ([#2074](https://github.com/bastani-inc/atomic/issues/2074)).
+- Fixed queued steering and follow-up rows disappearing when you left a stage. The queue lives on the stage session, but its display lived in the chat pane that detach destroys, so reattaching showed nothing even though the messages were still queued. The stage handle now keeps its own projection of the session's `queue_update` snapshots for its whole lifetime, and reattaching rehydrates the pending rows from it. Because the projection is fed by the events rather than by a concrete Atomic `AgentSession`, a stage backed by a custom `AgentSessionAdapter` keeps its rows too ([#2074](https://github.com/bastani-inc/atomic/issues/2074)).
+- Fixed a queued stage message being invisible from the workflow graph. A stage node with pending queued messages now shows a `✉ N queued` badge read from that same handle projection, so a message queued before detaching stays visible without reattaching. The badge claims the node's dim metadata row, or the redundant `waiting for response` row on an awaiting-input node so its `↵ enter to respond` hint survives. Nested child stages resolve to their real run and stage identity, tool nodes are never asked, card geometry is unchanged, and no queue state enters a store snapshot ([#2074](https://github.com/bastani-inc/atomic/issues/2074)).
+- Fixed a stage session that arrives already holding queued messages showing an empty queue. A session announces its queue by event, so a queue that exists before this stage's listeners are bound to that session was announced to nobody: a retiring stage session hands its pending messages to the session replacing it, and a retained session reopened for post-mortem chat is restored with whatever it was holding. Both published that queue while the handle's projection was attached to nothing, so the badge read zero and a reattached chat redrew no rows even though the messages were still pending. Attaching a session now replays the one snapshot its listeners missed, read from the session itself; every later change still arrives as an ordinary `queue_update`, and a runtime that does not expose its queues is unaffected ([#2074](https://github.com/bastani-inc/atomic/issues/2074)).
+- Fixed Ctrl+F losing its follow-up intent on a stage handle that predates the delivery-aware send. The compatibility path submitted the message as an ordinary prompt, so a follow-up typed while the stage streamed a retiring turn was admitted with prompt delivery instead of waiting in the follow-up queue. Ctrl+F now reaches the follow-up queue exactly while the stage streams, and still starts a turn on a genuinely idle stage — matching what the delivery-aware path does, rather than parking text no turn would consume ([#2074](https://github.com/bastani-inc/atomic/issues/2074)).
+
+## [0.9.11-alpha.6] - 2026-07-28
+
+### Added
+
+- Added opt-in `ctx.tool(..., { failureMode: "return" })` outcomes for checks that may fail during repair flows. Exhausted callback failures now preserve bounded, best-effort redacted `exitCode`, `stdout`, and `stderr` as typed durable data; replay returns the same outcome without rerunning the callback; failed tool nodes remain truthful while explicit downstream repair and bounded reruns continue; and default failures, cancellation, admission errors, and storage faults still throw ([#1993](https://github.com/bastani-inc/atomic/issues/1993)).
+- Re-added the built-in Goal and Ralph workflows, including their typed composition exports, command metadata, focused tests, and user-facing docs.
+- Added a run-contract discipline to every builtin workflow. Only the user may change a run's contract: mid-run steering, follow-ups, and resume text are authoritative amendments, while agents may never widen the contract themselves. A new steering propagation contract requires each stage to restate the amendments it received under a `Contract amendments received` heading in its handoff, keep them separate from its own observations, treat inherited amendments as contract clauses rather than out-of-scope work, and resolve ambiguity through `intercom` before implementing. Every bundled workflow wraps its run context once through `withSteeringPropagationContext` (exported from `@bastani/workflows/builtin/steering-context`), so `ctx.task`, `ctx.chain`, and `ctx.parallel` prompts carry the contract automatically and a stage added later inherits it. Without propagation an implementer builds to an amended contract while reviewers still score the launch contract and mark the added work as unrequested scope.
+- Added a scope discipline contract to builtin implementation stages: freeze the acceptance criteria before writing code, stop when they pass, trace every addition to a criterion, keep a deferred list instead of a growing diff, prefer the smallest diff that satisfies the contract, and report the contract, per-criterion evidence, and deferred items at the end.
+- Added a draft handoff for `ralph` runs that exhaust their review budget. When `create_pr` is enabled and the loop ends without unanimous approval, the run now opens a provider-native draft pull request that reproduces every unresolved blocking finding with priority, objective alignment, and cited `file:line`, states the iteration count, and requests no reviewers. Previously the branch was left unpushed with no handoff. Runs without `create_pr` still never touch a pull request, approved or not.
+- Added workflow-authoring guidance so, after creating and reloading a custom workflow, Atomic reports `Custom workflow created. You can inspect its code at: <workflow-folder-path>` only for newly created custom workflows, explicitly excluding builtin and pre-existing workflows ([#1978](https://github.com/bastani-inc/atomic/issues/1978)).
+
+### Removed
+
+- Removed the parenthesized context-window authoring token from workflow model strings. `(1m)`, `(1.1m)`, `(936k)`, and the generic `(long)` marker are no longer parsed from `model` / `fallbackModels` entries, and the `contextWindow` / `contextWindowStrict` stage options are gone. Builtin workflow model policies now use plain ids such as `github-copilot/claude-opus-4.8:high`, and every stage session uses its model's catalog context window.
+
+### Changed
+
+- Cleaned up workflow overlay status chrome. The orchestrator pane no longer echoes the host `MCP: <n>/<n> servers` count in its statusline, and attaching to a stage no longer adds a `pi-workflows/<workflow>/<stage>` tag next to the footer statuses in stage chat. Other extension statuses, such as async subagent progress, still render in the orchestrator statusline.
+- Changed workflow stage chat to render Atomic's exact one-cell `∀` with a pronounced, theme-aware dark → accent → bright/bold → accent → dark luminance ramp at 88ms and the ordinary one-row working geometry, while preserving `NO_COLOR` weight activity, reduced-motion static accent styling, blocked/prompt chrome suppression, composer space, and factual-state precedence.
+- Workflow invocations now assign a stable, non-`default` Intercom group from the persistent top-level run identity and apply it to every Intercom-capable stage by default. Nested workflows, model fallback, pause/resume, durable replay, and subagent inheritance retain the group; separate runs remain isolated; explicit stage/task/parallel groups (including `"default"`) still override it; and stages without Intercom access remain ungrouped. Workflow authors no longer need to mint and thread group names manually ([#1999](https://github.com/bastani-inc/atomic/issues/1999)).
+- Strengthened workflow-authoring prompts and docs to require every dynamically materialized execution topology to remain a DAG, reject self-edges and ancestor back-edges before launch, unroll bounded loops into distinct tracked work, distinguish discovery diagnostics from runtime/replay/DBOS topology validation, and require topology sketches for branches, loops, and nested workflow boundaries ([#2012](https://github.com/bastani-inc/atomic/issues/2012)).
+- Changed model-visible workflow routing to triage multi-item implementation queues before launch, run independent items as bounded concurrent top-level workflows with separate worktrees and root failure boundaries, preserve ordered composition for real dependencies and clusters, and report per-item run/worktree/branch/results ([#2010](https://github.com/bastani-inc/atomic/issues/2010)).
+- Adopted Claude Opus 5 as the primary model for the Ralph prompt-engineer, orchestrator, and reviewer-A stages, the Goal orchestrator and reviewer stages, and the Open Claude Design chain, with `github-copilot/claude-opus-5` and `openrouter/anthropic/claude-opus-5` mirrors added to every affected chain. Ralph's research and reviewer-B chains keep their GPT-5.6 primaries and gain Opus 5 fallbacks. Anthropic candidates now list the direct `anthropic/...` entry ahead of its `github-copilot/...` mirror, and `claude-fable-5` gains its missing Copilot mirror. Goal's orchestrator remains an exact local copy of Ralph's.
+- Reworked the shipped Goal, Ralph, Open Claude Design, and six pattern-workflow stage prompts for GPT-5.6, Claude Opus 5, and Claude Fable 5. Prompts now put artifacts before the final query, use explicit output and stop contracts, ground status claims in current tool evidence, damp unnecessary delegation, and request commands, observed results, and file:line evidence instead of internal reasoning; shared reviewer, acceptance, E2E/QA-video, and `stop_review_loop` derivation rules now have canonical definitions. This reduces repetition and avoids Claude Fable 5 `reasoning_extraction` refusals that could force model fallback while preserving schemas, convergence semantics, and exports.
+- Rewrote the bundled `prompt-engineer` skill and its three progressive-disclosure references for current GPT-5.6, Claude Opus 5, and Claude Fable 5 behavior, reducing them from 864 to 396 lines. Removed response-prefilling guidance that errors on Claude 4.6+, visible chain-of-thought as a primary technique, and generic self-check loops; added a delete-first optimization workflow, model-family guidance, agentic prompt structure, tool routing, adaptive-thinking effort and response-length controls, query-last long-context ordering, delegation damping, grounded reporting, and the Fable 5 `reasoning_extraction` hazard.
+
+### Fixed
+
+- Fixed the Ralph research stage destroying its own research artifact. The stage prompt told the agent to write the run's research file while the stage also declared that same path as its runner-owned `output`, so the runner overwrote the authored report with the stage's final chat message once the stage ended. Because `reads` passes a path rather than file content, the orchestrator and both reviewers then read a short pointer stub instead of the findings, and each loop re-derived context the research stage had already paid for. Research stages now return the full report as their final message and are explicitly told not to write the artifact path themselves; skill-owned notes under `research/docs/` and `research/web/` are unaffected.
+- Fixed the Classify-and-act, Fan-out-and-synthesize, Generate-and-filter, Loop-until-done, and Tournament workflows returning a whole terminal artifact into the calling session's context window. The first three set `outputMode: "file-only"` to keep the parent result compact and then read the saved file back with `readFile` before returning it, cancelling the saving; the last two declared `output` without `outputMode: "file-only"`, so the runner returned the full report text alongside the saved-file reference. Each `result` output is now the compact artifact reference, and the existing `action_path`, `synthesis_path`, `final_path`, and `result_path` outputs carry the full report for callers that want it. Passing file references rather than content is now the documented default for stage handoffs and workflow outputs alike.
+- Fixed admitted durable `ctx.tool(...)` callback and command failures being misclassified as killed/cancelled when no run cancellation won, including cancellation-shaped errors and wrappers with nested process evidence. First-event arbitration now preserves the first observed failure error and node even for concurrent same-value errors. Once the workflow body settles, an ordinary failure winner closes tool admission and cancels non-cooperative sibling nodes without needing an external kill; cancellation-first races still end killed. Failed resumable roots remain on the execution-resume path and win direct same-ID collisions with completed read-only history. Awaited and unawaited failures, concise nested command errors, root metadata, and selected tool links survive session and fresh DBOS inspection without becoming replay cache hits. Named interactive launches emit one failed lifecycle card and hidden reconciliation turn; prompt-start retries and restores reuse the card's atomic recovery marker, while status inspection and repeated startup binding do not duplicate it. Failed physical session appends now roll back partial single-entry and initial-batch writes to the exact prior file state, preventing malformed JSONL tails, duplicate IDs, phantom parents, and lost retry entries after reopen ([#2021](https://github.com/bastani-inc/atomic/issues/2021)).
+- Fixed durable nested `ctx.workflow(...)` resume and completed hydration across fresh processes. Atomic now persists an awaited, input-bound boundary-start identity before child dispatch, reuses stable boundary/child ids across reversed parallel ordering, keeps identical calls distinct by ordinal, scopes child checkpoint reads symmetrically at every nesting depth, and preserves source stage ids/order/parents/status and exact owner targets. Active and completed topology, boundary lifecycle transitions, and child results are validated atomically before cache/control/child dispatch; stale, aliased, cyclic, poisoned, or nonreciprocal records fail closed without repair execution. Completed child work and `ctx.tool(...)` effects remain exactly once, completed graphs remain root-catalog-only/read-only, retained child chat stays detached from execution, and ambiguous local stage ids or names no longer route to the first match.
+- Fixed workflow-supplied working-indicator palettes to quantize through Atomic's detected terminal color mode, preserving the intended phase progression in 256-color and conhost-like environments instead of forcing truecolor output.
+- Fixed controlled workflow pauses allowing queued or late-arriving work and continuation to run after a stage was visibly paused. Atomic's native session now establishes a synchronous raw queue hold before one serialized abort boundary; repeated pause and early resume share that boundary, abort failure rollback is explicitly observed and retried, and the existing resume action releases preserved steering, follow-up, duplicate, custom, async, and user-message entries exactly once. Clearing the final item never opens the gate. Existing custom adapters remain compatible without the optional native queue-pause methods and retain fallback abort/suspension behavior, including deferring runner-admitted public deliveries until resume. Fallback replacement installs an acyclic retirement forwarding fence before atomically moving raw/display/protected ownership source-first within each queue kind, serializes source and replacement interrupts through the live owner, clears the source, and leaves the target paused. Completed post-mortem stage chat resumes only its retained conversation queue on the next ordinary submission and never changes terminal workflow state ([#1983](https://github.com/bastani-inc/atomic/issues/1983)).
+- Fixed `ctx.tool()` calls durably completing side effects before a late empty-stage rejection. Tools now create ordered, inspectable, non-chat graph nodes with live, failed, completed, cancelled, and cached states; root completion waits for every admitted tool and promotes the first observed admitted failure left by a fulfilled body, while ordinary body rejections keep their exact error and link the selected matching failed tool when available; tool-only workflows complete normally; durable replay reconstructs and migrates topology without repeating callbacks; and completed tool-only runs open read-only without appearing stale or treating inspection as a new lifecycle transition. Terminal publication now atomically closes tool admission after admitted settlement continuations drain, so retained post-terminal calls reject before callbacks, retries, nodes, or checkpoints; rejected legacy child-topology annotation writes remain best-effort cache hits, do not poison DBOS flush, and retry on later replay; top-level status/session projections include nested tools with rewritten graph identity and explicit ownership; and completed retained-session stages remain chat-openable while tool nodes stay non-chat ([#1991](https://github.com/bastani-inc/atomic/issues/1991)).
+- Fixed live and restored nested `ctx.workflow()` graphs flattening valid child stages without preserving the authored composition topology. Hidden import boundaries now connect every boundary parent to every child root and every child terminal to downstream parent stages regardless of snapshot order; recursive one-level and deeper composition preserves sibling, sequential, parallel, and repeated child workflows; and boundaries with invalid, missing, empty, stale, mismatched, or recursively unusable child graphs, plus failed or skipped boundaries, retain the boundary summary rather than flattening an unrelated run. Duplicate child-local stage IDs and names keep distinct virtual IDs and exact owning `{runId, stageId}` targets across attach, messaging, pause, interrupt, resume, inspection, selection, and post-mortem chat, while nested runs remain excluded from top-level listings and ordinary workflow graph behavior is unchanged.
+- Fixed retained terminal stage chats dropping the Working indicator after Enter and before the follow-up agent turn started; the indicator now remains visible and animated throughout prompt attachment and processing without reviving stale terminal activity ([#1982](https://github.com/bastani-inc/atomic/issues/1982)).
+- Fixed programmatic `workflow send` reopening retained stage conversations after the authoritative root workflow had terminated. Completed, failed, skipped, cancelled, killed, and terminal-blocked roots now return a structured `WORKFLOW_TERMINAL` failure before stage or nested-owner resolution, prompt inspection, session probing/revival, handle lookup, admission, or delivery. Atomic rechecks the shared terminal authority at final synchronous SDK admission, including after awaited retained-session creation and paused or isolated-session resume setup; unsafe legacy handle delivery has no fallback. Terminal publication promptly unregisters and disposes an unclaimed provisional handle without waiting for hung session creation, late-created sessions are disposed, and handle replacement revokes stale admission while settling every provisional lease against one disposal. Prompt, model, tool, file, transcript, and workflow-snapshot side effects remain blocked. Live idle/streaming sends, pending-input answers, and explicit paused/interrupted resume remain available, while `/workflow attach` and Intercom can claim the retained handle and keep their explicit post-mortem chat paths ([#2009](https://github.com/bastani-inc/atomic/issues/2009)).
+
+### Removed
+
+- Removed Cursor model fallbacks and Cursor-branded Impeccable harness compatibility from shipped workflows and skills ([#1994](https://github.com/bastani-inc/atomic/issues/1994)).
+- Removed the built-in `deep-research-codebase` workflow.
+
+## [0.9.11-alpha.5] - 2026-07-23
+
+### Changed
+
+- Strengthened the existing Goal and Ralph reviewer prompts with a conditional contract-probe playbook for exact external-consumer APIs, build/feature matrices, schema optionality, state transitions, configuration precedence, low-level feature-flag independence, and permissive inputs. Reviewers now record independent probe outcomes in existing evidence fields and withhold approval when a material literal clause remains unverified, without changing reviewer counts, schemas, or convergence semantics. ([#1973](https://github.com/bastani-inc/atomic/issues/1973))
+- Strengthened model-visible workflow routing guidance with a pre-launch requirement/risk/evidence coverage pass, a one-launch composition commitment, concrete graph-selection signals, and bounded skeptical-reviewer loops whose model-selected probes are executed authoritatively through durable `ctx.tool(...)` verifier gates rather than model self-report ([#1974](https://github.com/bastani-inc/atomic/issues/1974)).
+- Changed the builtin Goal execution stage from a direct worker into a Ralph-style sub-agent orchestrator. Goal now runs `orchestrator-N` stages that track and delegate implementation, validation, documentation, and follow-up repairs through the `subagent` tool; writes `orchestrator-receipt.md`; forks later turns from the prior orchestrator session; and uses a locally contained copy of Ralph's exact xhigh orchestrator model and fallback chain while retaining Goal's ledger, reviewer, reducer, and optional final PR flow.
+- Reordered Goal's reviewer fallbacks so GPT-5.6 is tried before Kimi K3 within both the leading direct-provider group and the OpenRouter group, while retaining Claude Fable 5 as primary and preserving each group's position in the full chain.
+
+## [0.9.11-alpha.4] - 2026-07-23
+
+### Added
+
+- Added the opt-in `autoAttach` workflow-definition field, which opens the graph overlay when an interactive top-level named workflow is launched through `/workflow <name>` or the registered `workflow` tool without changing headless launches, nested workflow composition, or the existing input-form launch path.
+- `WorkflowRunContext` now optionally exposes the host session's model catalog as `ctx.models` (including `currentModel`, the user-selected session model, and `listModels()`). Custom workflow definitions can use it to select stage models from the live catalog; the field is absent when the host provides no catalog, and builtin workflow model chains are unchanged.
+
+### Changed
+
+- Workflow prompt guidance now instructs agents to give each workflow invocation its own intercom group by default — unless the user requests otherwise — by minting one invocation-scoped literal group name inside the workflow's `run` function (e.g. `"myflow-" + randomUUID()`) and passing it via the `group` option on each stage, task, or parallel step that should share it; `group: true`/`"auto"` mints one shared UUID group per `ctx.parallel(...)` set but a fresh UUID per non-parallel stage. This keeps stage and subagent intercom chatter isolated from the parent chat and other concurrent runs, since ungrouped sessions all share the `"default"` group; subagent inheritance, capability gating, and cross-group `contact_supervisor` escalation are unchanged.
+- Attached workflow stage chats now match the main interactive footer by showing the home-shortened current folder with its cached, live-updating Git branch and by mirroring current extension status lines such as MCP connectivity, using the workflow chat theme without replacing the existing hierarchy and copy-mode hints.
+- The builtin `goal` and `ralph` workflow descriptions and their `objective`/`prompt`/`create_pr` input descriptions now instruct launching agents that when a delegated task includes submitting a pull request (or MR/review), that final action must be stripped from the objective/prompt text and requested via `create_pr=true` instead when preparing the workflow inputs. This keeps PR creation an explicitly authorized final-stage action rather than embedded task text that intermediate stages are told to ignore.
+- Goal worker and Ralph orchestrator prompts now carry an explicit worktree-discipline contract: all work happens in the invoking checkout (or the run's explicitly configured worktree), stages never create additional git worktrees, clones, or repository copies unless the user's task explicitly requests them, and work discovered stranded outside the invoking checkout must be brought back in before continuing. The `git_worktree_dir` input descriptions state the same rule for launching agents.
+- Goal and Ralph reviewer prompts now include a code-delta presence and integrity contract: before trusting receipts or stage summaries, reviewers must prove the code delta actually exists in the review checkout using the repository's version-control tooling (for git: `git worktree list`, `git status`, and a baseline diff), treat claimed-but-absent work as a blocking finding instead of approving over an empty or unrelated delta, treat uncommitted work at claimed readiness as remaining work unless the objective forbids committing, and flag any modification, rename, or deletion of pre-existing test files or test functions as a finding requiring explicit justification.
+- Goal worker prompts now require committing work in the current checkout with a descriptive message before claiming readiness for review — verifying a clean working tree with the repository's version-control status command and reporting the commit identifier in the receipt — unless the objective or acceptance criteria explicitly forbid committing. Delivery verification stays with reviewers and prompts (version-control-agnostic) rather than a hardcoded git gate in the runner.
+
+### Fixed
+
+- Fixed host-session replacement (`/new`, `/resume`, `/fork`, `/reload`) leaving the process-global DBOS executor stopped so every subsequent workflow run in the same Atomic process failed at its first durable checkpoint with `` `DBOS.launch()` must be called before running workflows ``. The DBOS executor lifetime is now process-scoped: process-preserving session boundaries flush pending durable writes but keep the executor launched, and SDK shutdown is reserved for actual process exit (`quit`/`beforeExit`), which still flushes and shuts down exactly once. Defense in depth: the durable-backend factory revalidates its memoized backend against the current DBOS lifecycle generation and never hands out a stopped backend (post-shutdown initialization fails loudly instead of silently degrading to a non-durable backend), the extension runtime no longer caches a permanently resolved readiness promise across lifecycle generations, and root workflow registration is durably flushed before startup admission so a stopped or unhealthy backend fails before workflow code executes any side effects. ([#1957](https://github.com/bastani-inc/atomic/issues/1957))
+
+## [0.9.11-alpha.2] - 2026-07-21
+
+### Fixed
+
+- Fixed fresh-process workflow resume and completed-run inspection losing nested child-workflow and parallel stage hierarchy. DBOS stage checkpoints now retain owning-run and boundary topology, replay restores source parentage and child runs, graceful quit persists exact sub-30-second stage timing, completed runs persist and display accumulated run duration, and project-local workflows reloaded during a chat are rediscovered from their original invocation directory. The `/workflow resume` and `/workflows` picker rows also no longer display the redundant `N prompts` segment.
+
 ## [0.9.11-alpha.1] - 2026-07-20
 
 ### Added
@@ -23,6 +142,7 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/),
 - Fixed `workflow({ action: "resume", runId })` returning `Run not found` for eligible durably paused workflows after session-local run state was cleared. Explicit tool resume now resolves exact IDs and unique or ambiguous prefixes through the authoritative DBOS catalog before refusing the target, preserves original workflow IDs and checkpoint replay, and surfaces resource or durable lookup failures without making ordinary status listing hydrate durable history. ([#1924](https://github.com/bastani-inc/atomic/issues/1924))
 - Fixed session teardown crashing the process (exit code 1) after DBOS durability provisioning had failed: `shutdownDbos` re-awaited the memoized rejected configuration promise and rethrew the original provisioning error out of session dispose and the `beforeExit` hook, turning otherwise-successful `--print` runs into nonzero exits (surfacing as `NonZeroAgentExitCodeError` in eval harnesses). Shutdown is now a no-op for a backend that never reached readiness, and genuine teardown failures are logged instead of thrown.
 
+
 ## [0.9.10] - 2026-07-20
 
 ### Breaking Changes