@bastani/atomic 0.9.19-alpha.6 → 0.9.19-alpha.7

package/CHANGELOG.md

@@ -2,6 +2,12 @@
 
 ## [Unreleased]
 
+## [0.9.19-alpha.7] - 2026-09-12
+
+### Fixed
+
+- Reduced CPU work in long `/tasks` live transcripts on Windows by reusing unchanged message rendering during streaming, without dropping history or delaying live updates.
+
 ## [0.9.19-alpha.6] - 2026-09-11
 
 ### Breaking Changes

package/README.md

@@ -79,7 +79,7 @@ atomic
 
 Then just talk to Atomic. By default, Atomic gives the model six coding tools: `read`, `write`, `edit`, `bash`, `find`, and `search`. On native Windows, Atomic also enables `powershell` when `pwsh.exe` or `powershell.exe` is available. The model uses these to fulfill your requests. `read`, `search`, `write`, and successful `edit` calls emit session-scoped hashline anchors (`[path#TAG]` plus `LINE:text`) so the model can make stale-safe line edits; see [docs/tools.md](docs/tools.md). Add capabilities via [skills](#skills), [prompt templates](#prompt-templates), [extensions](#extensions), or [Atomic packages](#atomic-packages).
 
-**Platform notes:** [Windows](docs/windows.md) | [Alpine/musl Linux](docs/index.md#alpine-and-musl-linux-archives) | [Termux (Android)](docs/termux.md) | [tmux](docs/tmux.md) | [Terminal setup](docs/terminal-setup.md) | [Shell aliases](docs/shell-aliases.md)
+**Platform notes:** [Windows](docs/windows.md) | [Alpine/musl Linux](docs/getting-started/installation.md#alpine-and-musl-linux-archives) | [Termux (Android)](docs/termux.md) | [tmux](docs/tmux.md) | [Terminal setup](docs/terminal-setup.md) | [Shell aliases](docs/shell-aliases.md)
 
 ---
 
@@ -138,7 +138,7 @@ For each built-in provider, Atomic maintains a list of tool-capable models, upda
 
 See [docs/providers.md](docs/providers.md) for detailed setup instructions.
 
-Atomic's Pi 0.84.1 model/runtime surface includes Claude Opus 5 on Anthropic and Bedrock, model-capability-aware strict JSON-schema and OpenAI Lark/regex tool sampling, ETag-revalidated cached catalogs, persisted llama.cpp models, arbitrary OpenAI-compatible `samplingParams`, opt-in vLLM thinking-token budgets through `compat.supportsThinkingTokenBudget`, and finishless-stream stop inference through `compat.supportsFinishReason`. A populated `ANTHROPIC_AUTH_TOKEN` makes Anthropic models available/selectable while sending header-only bearer auth—with no synthesized API key or `x-api-key`—across chat and summary/compaction requests. Typed RPC model listings expose constrained-sampling flags through optional `ModelInfo.compat`; capability flags are enforcement claims, so unsupported `require` constraints fail instead of being silently weakened. Custom `models.json` is read from the active Atomic agent directory only; it is not merged across `.pi` and `.atomic` paths. See [models](docs/models.md), [providers](docs/providers.md), [RPC](docs/rpc.md#get_available_models), and [extensions](docs/extensions.md#constrained-sampling).
+Atomic's Pi 0.84.1 model/runtime surface includes Claude Opus 5 on Anthropic and Bedrock, model-capability-aware strict JSON-schema and OpenAI Lark/regex tool sampling, ETag-revalidated cached catalogs, persisted llama.cpp models, arbitrary OpenAI-compatible `samplingParams`, opt-in vLLM thinking-token budgets through `compat.supportsThinkingTokenBudget`, and finishless-stream stop inference through `compat.supportsFinishReason`. A populated `ANTHROPIC_AUTH_TOKEN` makes Anthropic models available/selectable while sending header-only bearer auth—with no synthesized API key or `x-api-key`—across chat and summary/compaction requests. Typed RPC model listings expose constrained-sampling flags through optional `ModelInfo.compat`; capability flags are enforcement claims, so unsupported `require` constraints fail instead of being silently weakened. Custom `models.json` is read from the active Atomic agent directory only; it is not merged across `.pi` and `.atomic` paths. See [models](docs/models.md), [providers](docs/providers.md), [RPC](docs/rpc/protocol.md#get_available_models), and [extensions](docs/extensions/authoring.md#constrained-sampling).
 
 **Custom providers & models:** Add providers via the active agent directory's `models.json` (normally `~/.atomic/agent/models.json`; `ATOMIC_CODING_AGENT_DIR`/`PI_CODING_AGENT_DIR` can select another directory) if they speak a supported API (OpenAI, Anthropic, Google). For custom APIs or OAuth, use extensions. See [docs/models.md](docs/models.md) and [docs/custom-provider.md](docs/custom-provider.md).
 

package/dist/builtin/intercom/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@bastani/intercom",
-  "version": "0.9.19-alpha.6",
+  "version": "0.9.19-alpha.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/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@bastani/mcp",
-  "version": "0.9.19-alpha.6",
+  "version": "0.9.19-alpha.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/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@bastani/subagents",
-  "version": "0.9.19-alpha.6",
+  "version": "0.9.19-alpha.7",
   "private": true,
   "description": "Atomic extension for delegating tasks to subagents with parallel execution. 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]
 
+## [0.9.19-alpha.7] - 2026-09-12
+
+### Fixed
+
+- `fetch_content` now shows each URL's error and recovery steps when an entire batch fails, instead of hiding the causes behind a generic failure count. Retained partial content is shown as incomplete excerpts rather than incorrectly reported as absent.
+
 ## [0.9.19-alpha.6] - 2026-09-11
 
 ### Breaking Changes

package/dist/builtin/web-access/index.bundle.mjs

@@ -91055,19 +91055,38 @@ Showing ${deps.maxInlineContent} of ${fullLength} chars. ` + `Use get_search_con
         if (error) {
           output += `- ${url}: Error - ${error}
 `;
+          if (content.length > 0) {
+            output += `
+Partial content (incomplete):
+${content.slice(0, deps.maxInlineContent)}
+`;
+            if (content.length > deps.maxInlineContent)
+              output += `[Partial content truncated...]
+`;
+            output += `
+`;
+          }
         } else {
           output += `- ${title || url} (${content.length} chars)
 `;
         }
       }
-      output += `
+      const allFailed = successful === 0;
+      if (allFailed) {
+        const contentStatus = totalChars > 0 ? "Partial content was retained; extraction is incomplete." : "No content was retrieved.";
+        output = `All ${urlList.length} URL fetch(es) failed. ${contentStatus}
+
+${output}` + `
+Check each URL and its error above. Retry transient failures individually with ` + 'fetch_content({ urls: ["<failed URL>"] }). If access is blocked or extraction keeps failing, ' + "try an accessible alternate URL or use web_search to find the information. " + (totalChars > 0 ? "get_search_content cannot recover the missing content; use the incomplete excerpts above with caution." : "get_search_content cannot recover content from these failed fetches.");
+      } else {
+        output += `
 ---
 Use get_search_content({ responseId: "${responseId}", urlIndex: 0 }) to retrieve full content.`;
-      const allFailed = successful === 0;
+      }
       return {
         content: [{ type: "text", text: output }],
         details: {
-          ...allFailed ? { outcome: "all_failed", stage: "fetch", error: `All ${urlList.length} URL fetch(es) failed`, failedUrls: urlList.length } : {},
+          ...allFailed ? { outcome: "all_failed", stage: "fetch", error: output, failedUrls: urlList.length } : {},
           urls: urlList,
           urlCount: urlList.length,
           successful,

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

@@ -1,6 +1,6 @@
 {
   "name": "@bastani/web-access",
-  "version": "0.9.19-alpha.6",
+  "version": "0.9.19-alpha.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 +6,15 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/),
 
 ## [Unreleased]
 
+## [0.9.19-alpha.7] - 2026-09-12
+
+### Fixed
+
+- Warm-first verifier and tournament judge groups now advertise conservative possible-stage names in source and bundled workflows without the builtin `warmSteps`/`restSteps` discovery warnings. Call-scoped `possibleStageNames` metadata leaves execution unchanged and retains diagnostics for unsupported dynamic calls ([#3001](https://github.com/bastani-inc/atomic/issues/3001)).
+- Fixed workflow quit hanging while a stage waits on `ask_user_question`. Cancelling the stage's active tool now dismisses its owned question without requiring an answer, including in nested workflows, while preserving paused/resumable state and unrelated questions. Related: [#2897](https://github.com/bastani-inc/atomic/issues/2897).
+- Fixed quit leaving a stage's readiness question answerable after stopping. Readiness questions now dismiss on pause or quit, ignore late answers, and ask again after explicit resume instead of advancing a paused workflow. Related: [#2897](https://github.com/bastani-inc/atomic/issues/2897).
+- Fixed a failed pause or quit leaving a running stage stuck after its readiness answer was accepted. Failed cancellation now releases that stage's temporary hold without releasing a successful pause. Related: [#2897](https://github.com/bastani-inc/atomic/issues/2897).
+
 ## [0.9.19-alpha.6] - 2026-09-11
 
 ### Fixed

package/dist/builtin/workflows/README.md

@@ -103,7 +103,7 @@ The existing `.atomic/workflows/release-docs.ts` keeps its graph in the entry fi
 
 ### Workflow and extension responsibilities
 
-Evaluate Atomic extension hooks when a workflow needs fine-grained, cross-cutting tool or session event control. Workflow TypeScript owns the inspectable DAG, stages, handoffs, durable `ctx.tool` side effects, and gates. Extension hooks own cross-cutting session and model-tool policy such as `tool_call` interception, input mutation, or blocking; `tool_result` transformation; context and provider hooks; lifecycle observation; or reusable custom tools. Use hooks only when cross-stage or cross-workflow event control is materially clearer than embedding the policy in each stage. Do not require a companion extension for ordinary workflow logic. See the authoritative [extension event documentation](../coding-agent/docs/extensions.md#events) for hook contracts and ordering.
+Evaluate Atomic extension hooks when a workflow needs fine-grained, cross-cutting tool or session event control. Workflow TypeScript owns the inspectable DAG, stages, handoffs, durable `ctx.tool` side effects, and gates. Extension hooks own cross-cutting session and model-tool policy such as `tool_call` interception, input mutation, or blocking; `tool_result` transformation; context and provider hooks; lifecycle observation; or reusable custom tools. Use hooks only when cross-stage or cross-workflow event control is materially clearer than embedding the policy in each stage. Do not require a companion extension for ordinary workflow logic. See the authoritative [extension event documentation](../coding-agent/docs/extensions/events.md#events) for hook contracts and ordering.
 
 When a workflow depends on a companion extension, make that dependency explicit and package and document the extension with the workflow. If stages use `tools` allowlists, include any custom tools provided by the extension. Document the hook-driven behavior and keep the graph, stage contracts, artifacts, gates, and stop conditions visible in the workflow entry file so readers can distinguish inspectable workflow orchestration from event policy.
 

package/dist/builtin/workflows/builtin/adversarial-verification.js

@@ -1,7 +1,7 @@
 import {
   adversarial_verification_default
-} from "./chunk-1kx4aggw.js";
-import"./chunk-p8jjwfg6.js";
+} from "./chunk-wf741bv3.js";
+import"./chunk-2377r57g.js";
 import"./chunk-n1910xc4.js";
 import"./chunk-xtxcq5tj.js";
 import"./chunk-a2kdsqn8.js";

package/dist/builtin/workflows/builtin/{chunk-vhmnzdj9.js → chunk-1jth021m.js}

@@ -38,7 +38,7 @@ import {
   reviewerFailureText,
   summarizeReviewConvergence,
   reverify_consolidated_batch
-} from "./chunk-n8zysf1t.js";
+} from "./chunk-ngkqkzej.js";
 import {
   fold_usage
 } from "./chunk-tgt0s5e5.js";

package/dist/builtin/workflows/builtin/{chunk-p8jjwfg6.js → chunk-2377r57g.js}

@@ -95,7 +95,8 @@ async function warm_first_fan_out(ctx, steps, prefixKeyOf, options = {}) {
       const warmResults = await ctx.parallel(warmSteps, {
         ...parallelOptions,
         concurrency: boundedConcurrency(warmSteps.length, warmConcurrency ?? DEFAULT_WARM_CONCURRENCY, inheritedConcurrency),
-        failFast: false
+        failFast: false,
+        possibleStageNames: options.possibleStageNames
       });
       for (const [resultIndex, result] of warmResults.entries()) {
         const originalIndex = warmIndices[resultIndex];
@@ -110,7 +111,8 @@ async function warm_first_fan_out(ctx, steps, prefixKeyOf, options = {}) {
     const restSteps = restIndices.map((index) => steps[index]);
     const restResults = await ctx.parallel(restSteps, {
       ...parallelOptions,
-      concurrency: boundedConcurrency(restSteps.length, undefined, inheritedConcurrency)
+      concurrency: boundedConcurrency(restSteps.length, undefined, inheritedConcurrency),
+      possibleStageNames: options.possibleStageNames
     });
     for (const [resultIndex, result] of restResults.entries()) {
       const originalIndex = restIndices[resultIndex];

package/dist/builtin/workflows/builtin/{chunk-hbnwv56f.js → chunk-31j2gs7h.js}

@@ -13,7 +13,7 @@ import {
   scoring_prompt_reads,
   build_scoring_prompt,
   warm_first_fan_out
-} from "./chunk-p8jjwfg6.js";
+} from "./chunk-2377r57g.js";
 import {
   fold_usage
 } from "./chunk-tgt0s5e5.js";
@@ -369,7 +369,7 @@ async function runTournament(ctx) {
     if (stages.length === 0)
       return { preferences: [], results: [] };
     executed += stages.length;
-    const results = await warm_first_fan_out(ctx, stages.map((stage) => stage.step), (_step, index) => `${stages[index].slot1}:${stages[index].slot2}`, { concurrency: maxConcurrency, failFast: false });
+    const results = await warm_first_fan_out(ctx, stages.map((stage) => stage.step), (_step, index) => `${stages[index].slot1}:${stages[index].slot2}`, { concurrency: maxConcurrency, failFast: false, possibleStageNames: ["judge-*-*-*-r*"] });
     const phaseResults = [...results];
     for (const stage of stages) {
       let report = judgeReport(resultFor(results, stage.name)?.structured);

package/dist/builtin/workflows/builtin/{chunk-n8zysf1t.js → chunk-ngkqkzej.js}

@@ -9,7 +9,7 @@ import {
 import {
   scoring_prompt_reads,
   build_scoring_prompt
-} from "./chunk-p8jjwfg6.js";
+} from "./chunk-2377r57g.js";
 
 // dist/builtin/workflows/src/shared/workflow-artifacts.ts
 import { randomUUID as randomUUID2 } from "node:crypto";

package/dist/builtin/workflows/builtin/{chunk-1nbq96fh.js → chunk-nkrafh9s.js}

@@ -36,7 +36,7 @@ import {
   reviewerFailureText,
   summarizeReviewConvergence,
   reverify_consolidated_batch
-} from "./chunk-n8zysf1t.js";
+} from "./chunk-ngkqkzej.js";
 import {
   VERIFICATION_SCALE
 } from "./chunk-n1910xc4.js";

package/dist/builtin/workflows/builtin/{chunk-1kx4aggw.js → chunk-wf741bv3.js}

@@ -14,7 +14,7 @@ import {
   scoring_prompt_reads,
   build_scoring_prompt,
   warm_first_fan_out
-} from "./chunk-p8jjwfg6.js";
+} from "./chunk-2377r57g.js";
 import {
   fold_usage
 } from "./chunk-tgt0s5e5.js";
@@ -261,7 +261,7 @@ async function runAdversarialVerification(ctx) {
     const runWave = async (pending, reaskWave) => {
       if (pending.length === 0)
         return { valid: [], invalid: [], results: [] };
-      const reports = await warm_first_fan_out(ctx, pending.map((cell) => scoreStep(cell, reaskWave, scoringHead, criteriaPath)), () => scoringHead, { concurrency: Math.min(pending.length, 4), failFast: false });
+      const reports = await warm_first_fan_out(ctx, pending.map((cell) => scoreStep(cell, reaskWave, scoringHead, criteriaPath)), () => scoringHead, { concurrency: Math.min(pending.length, 4), failFast: false, possibleStageNames: ["verifier-*-*-*", "verifier-*-*-*-reask-*"] });
       const byName = new Map;
       for (const report of reports) {
         const name = report.name ?? report.stageName;

package/dist/builtin/workflows/builtin/{chunk-t6x2d78s.js → chunk-z29qbehr.js}

@@ -7,7 +7,7 @@ import {
 import {
   scoring_prompt_reads,
   build_scoring_prompt
-} from "./chunk-p8jjwfg6.js";
+} from "./chunk-2377r57g.js";
 import {
   stableArtifactRoot
 } from "./chunk-rc5ec5xx.js";

package/dist/builtin/workflows/builtin/generate-and-filter.js

@@ -1,7 +1,7 @@
 import {
   generate_and_filter_default
-} from "./chunk-t6x2d78s.js";
-import"./chunk-p8jjwfg6.js";
+} from "./chunk-z29qbehr.js";
+import"./chunk-2377r57g.js";
 import"./chunk-n1910xc4.js";
 import"./chunk-xtxcq5tj.js";
 import"./chunk-a2kdsqn8.js";

package/dist/builtin/workflows/builtin/goal.js

@@ -1,8 +1,8 @@
 import {
   goal_default
-} from "./chunk-1nbq96fh.js";
-import"./chunk-n8zysf1t.js";
-import"./chunk-p8jjwfg6.js";
+} from "./chunk-nkrafh9s.js";
+import"./chunk-ngkqkzej.js";
+import"./chunk-2377r57g.js";
 import"./chunk-z0d03ktm.js";
 import"./chunk-n1910xc4.js";
 import"./chunk-xtxcq5tj.js";

package/dist/builtin/workflows/builtin/index.js

@@ -1,10 +1,10 @@
 import"./chunk-xtxcq5tj.js";
 import"./chunk-a2kdsqn8.js";
 import"./chunk-n1910xc4.js";
-import"./chunk-p8jjwfg6.js";
+import"./chunk-2377r57g.js";
 import {
   adversarial_verification_default
-} from "./chunk-1kx4aggw.js";
+} from "./chunk-wf741bv3.js";
 import {
   classify_and_act_default
 } from "./chunk-g0csgs7w.js";
@@ -13,12 +13,12 @@ import {
 } from "./chunk-fg9esgkj.js";
 import {
   generate_and_filter_default
-} from "./chunk-t6x2d78s.js";
-import"./chunk-n8zysf1t.js";
+} from "./chunk-z29qbehr.js";
+import"./chunk-ngkqkzej.js";
 import"./chunk-z0d03ktm.js";
 import {
   goal_default
-} from "./chunk-1nbq96fh.js";
+} from "./chunk-nkrafh9s.js";
 import {
   open_claude_design_default
 } from "./chunk-yeee2jrc.js";
@@ -27,10 +27,10 @@ import {
 } from "./chunk-6w6cvk6b.js";
 import {
   ralph_default
-} from "./chunk-vhmnzdj9.js";
+} from "./chunk-1jth021m.js";
 import {
   tournament_default
-} from "./chunk-hbnwv56f.js";
+} from "./chunk-31j2gs7h.js";
 export {
   adversarial_verification_default as adversarialVerification,
   classify_and_act_default as classifyAndAct,

package/dist/builtin/workflows/builtin/ralph.js

@@ -1,8 +1,8 @@
 import {
   ralph_default
-} from "./chunk-vhmnzdj9.js";
-import"./chunk-n8zysf1t.js";
-import"./chunk-p8jjwfg6.js";
+} from "./chunk-1jth021m.js";
+import"./chunk-ngkqkzej.js";
+import"./chunk-2377r57g.js";
 import"./chunk-z0d03ktm.js";
 import"./chunk-n1910xc4.js";
 import"./chunk-xtxcq5tj.js";

package/dist/builtin/workflows/builtin/tournament.js

@@ -1,7 +1,7 @@
 import {
   tournament_default
-} from "./chunk-hbnwv56f.js";
-import"./chunk-p8jjwfg6.js";
+} from "./chunk-31j2gs7h.js";
+import"./chunk-2377r57g.js";
 import"./chunk-n1910xc4.js";
 import"./chunk-xtxcq5tj.js";
 import"./chunk-a2kdsqn8.js";

package/dist/builtin/workflows/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@bastani/workflows",
-  "version": "0.9.19-alpha.6",
+  "version": "0.9.19-alpha.7",
   "private": true,
   "description": "Atomic extension for multi-stage workflow authoring and execution.",
   "contributors": [