@bastani/atomic 0.9.19-alpha.7 → 0.9.19-alpha.9

package/CHANGELOG.md

@@ -2,6 +2,20 @@
 
 ## [Unreleased]
 
+## [0.9.19-alpha.9] - 2026-09-12
+
+### Breaking Changes
+
+- Explicit Intercom `action: "reply"` selectors reject stale, unknown, empty, or sender-mismatched threads instead of falling back. Use `action: "pending"` and `replyTo: "<pending-ask-id>"` for unresolved questions.
+
+### Changed
+
+- Intercom agent lists put exact copyable session IDs and workflow paths first, with useful metadata and meaningful names secondary rather than redundant generated aliases.
+
+### Fixed
+
+- Intercom targeted replies now complete the requested ask when an unrelated message is active, rather than delivering a response with the wrong thread ID or refusing it.
+
 ## [0.9.19-alpha.7] - 2026-09-12
 
 ### Fixed

package/dist/builtin/intercom/CHANGELOG.md

@@ -4,6 +4,20 @@ All notable changes to the `pi-intercom` extension will be documented in this fi
 
 ## [Unreleased]
 
+## [0.9.19-alpha.9] - 2026-09-12
+
+### Breaking Changes
+
+- Explicit `reply` selectors now fail closed: stale, unknown, empty, or sender-mismatched `replyTo` values no longer fall back to another active or pending thread. Use `pending` to select the exact unresolved question.
+
+### Changed
+
+- Agent-visible Intercom lists lead with copyable full session IDs and canonical workflow paths, keeping status, working directory, meaningful names, and future queued counts without redundant generated aliases.
+
+### Fixed
+
+- Targeted replies select the requested sender's pending ask even when an unrelated message triggered the current turn, so a delivered reply no longer leaves that ask waiting on the wrong thread.
+
 ## [0.9.19-alpha.6] - 2026-09-11
 
 ### Fixed

package/dist/builtin/intercom/README.md

@@ -57,7 +57,7 @@ A session becomes intercom-connected when all of these are true:
 
 The session list, ALT+M picker, and group counts include connected agent sessions only. Internal workflow routing/control connections, model-less `ctx.ui` prompts, and `ctx.tool` nodes are hidden and cannot receive ordinary messages, even by a known ID or through a supervisor route. This includes run-level prompts and retained completed synthetic prompt stages. An agent executing a tool, including `tool:workflow`, or awaiting human input remains visible and messageable.
 
-If a session is unnamed, intercom exposes a runtime-only fallback alias like `subagent-chat-1a2b3c4d-1111-4222-8333-123456789abc` so other sessions can still target it. That alias is not persisted as the session title, so resume pickers can keep showing the transcript snippet instead of a generic `session-...` name.
+Unnamed sessions retain a runtime-only alias such as `subagent-chat-1a2b3c4d-1111-4222-8333-123456789abc` for name lookup. Agent lists omit this redundant alias and lead with the copyable full session ID. Meaningful names remain secondary metadata; resume titles are unchanged.
 
 ## Quick Start
 
@@ -76,10 +76,10 @@ The agent can list sessions and send messages using the `intercom` tool. Tool ca
 ```typescript
 // List active sessions
 intercom({ action: "list" })
-// → **Current session:**
-// → • executor (20d43841-1111-4222-8333-123456789abc) — ~/projects/api (claude-sonnet-4) [self, idle]
-// → **Other sessions:**
-// → • research (6332faab-1111-4222-8333-123456789abc) — ~/projects/api (claude-sonnet-4) [same cwd, thinking]
+// → **Current session** (groups: default):
+// → - `20d43841-1111-4222-8333-123456789abc` [self, idle] ~/projects/api (claude-sonnet-4) name: executor
+// → **Other visible sessions and workflow stages:**
+// → - `6332faab-1111-4222-8333-123456789abc` [same cwd, thinking] ~/projects/api (claude-sonnet-4) name: research
 
 // Add a named membership (it is created if no session is there yet)
 intercom({ action: "join", group: "api-review" })
@@ -156,7 +156,7 @@ Verify they see each other from either session:
 
 ```typescript
 intercom({ action: "list" })
-// → • worker — ~/projects/api (claude-sonnet-4) [idle]
+// → - `6332faab-1111-4222-8333-123456789abc` [same cwd, idle] ~/projects/api (claude-sonnet-4) name: worker
 ```
 
 ### The Conversation
@@ -383,7 +383,7 @@ When multiple live agent stages share a name, `ask` refuses the ambiguous target
 
 **`ask`** — Sends a message and waits for a live recipient to reply (10-minute timeout). Invocation control supports a live ask into an owned isolated subgroup, and the exact broker-recorded reply resolves the waiting tool call at the asker without opening reverse or lateral group access. Ask to an uninitialized stage remains refused with `pending_stage_ask_unsupported`; use queued `send` instead, because holding a reply waiter until a stage eventually starts would be unbounded. A recipient disconnect after live delivery fails only that peer's exact wait promptly; the timeout remains the backstop while the recipient stays connected. Up to `maxPendingAsks` blocking asks (default: 6) may run concurrently, including same-target and mixed-target fan-out. Replies resolve by exact sender and message ID, so out-of-order replies cannot cross-settle another call. When capacity is full, new asks receive a structured refusal.
 
-**`reply`** — Replies to the current intercom-triggered message if there is one. Otherwise it falls back to the single unresolved inbound ask. If multiple asks are pending, pass an exact name/full session ID in `to`, or the listed message ID in `replyTo`; use `pending` to inspect them first. `replyTo` also disambiguates multiple asks from the same sender. Under the hood this is still a normal `send` with the exact `replyTo` value.
+**`reply`** without selectors replies to the current intercom-triggered message, or otherwise the single unresolved inbound ask. Explicit `to` selects a pending ask from that exact name/full session ID, even during another sender's turn. If that sender has multiple asks, use `pending` and pass the exact message ID as `replyTo`. Explicit `replyTo` selects only that pending ask or the exact active ordinary message; stale, unknown, or empty IDs fail instead of falling back. When both selectors are supplied, the sender must match the selected thread. A successful reply keeps that sender/thread pair across internal retries.
 
 **`pending`** — Lists unresolved inbound asks with sender, message ID, elapsed time, and a short preview. Useful when replying after the original triggered turn.
 

package/dist/builtin/intercom/broker/client.ts

@@ -38,6 +38,8 @@ export interface SendOptions {
   logicalTarget?: string;
   /** Public reply must use the broker's exact pending reverse question route. */
   requirePendingReply?: true;
+  /** An explicit reply selector must resolve to this frozen recipient, never a namesake. */
+  expectedRecipientId?: string;
   /** Broker-authorized identity for a canonical-path ask, delivered before its recipient can reply. */
   onReplyTarget?: (sessionId: string) => void;
 }
@@ -1004,6 +1006,7 @@ export class IntercomClient extends EventEmitter {
 			transportTarget: to,
 			logicalSignature: buildSendSignature(options.logicalTarget ?? to, options),
 			requirePendingReply: options.requirePendingReply ?? false,
+			...(options.expectedRecipientId === undefined ? {} : { expectedRecipientId: options.expectedRecipientId }),
 		});
 		acquired = this.pendingSends.acquire(messageId, pendingSignature, 10000);
     } catch (error) {
@@ -1028,6 +1031,7 @@ export class IntercomClient extends EventEmitter {
 			to,
 			...(options.logicalTarget === undefined ? {} : { logicalTarget: options.logicalTarget }),
 			...(options.requirePendingReply === undefined ? {} : { requirePendingReply: options.requirePendingReply }),
+			...(options.expectedRecipientId === undefined ? {} : { expectedRecipientId: options.expectedRecipientId }),
       ...(options.onReplyTarget === undefined ? {} : { resolveReplyTarget: true as const }),
 			message,
 			attemptId: acquired.attempt.attemptId,

package/dist/builtin/intercom/broker/send-handler.ts

@@ -143,6 +143,12 @@ export function handleBrokerSend(
     return;
   }
   const requirePendingReply = clientMessage.requirePendingReply === true;
+  const hasExpectedRecipientId = Object.prototype.hasOwnProperty.call(clientMessage, "expectedRecipientId");
+  if (hasExpectedRecipientId && (typeof clientMessage.expectedRecipientId !== "string" || !clientMessage.expectedRecipientId.trim())) {
+    write(socket, { type: "delivery_failed", messageId, attemptId, reason: "Invalid expectedRecipientId format" });
+    return;
+  }
+  const expectedRecipientId = hasExpectedRecipientId ? clientMessage.expectedRecipientId as string : undefined;
   if (Object.prototype.hasOwnProperty.call(clientMessage, "channel")) {
     write(socket, { type: "delivery_failed", messageId: message.id, attemptId, reason: "Invalid channel" });
     return;
@@ -152,6 +158,10 @@ export function handleBrokerSend(
     write(socket, { type: "delivery_failed", messageId, attemptId, reason: "Invalid requirePendingReply message" });
     return;
   }
+  if (expectedRecipientId !== undefined && (supervisorSend || message.replyTo === undefined || message.expectsReply === true)) {
+    write(socket, { type: "delivery_failed", messageId, attemptId, reason: "Invalid expectedRecipientId message" });
+    return;
+  }
 
 
   const fromSession = currentId ? sessions.get(currentId) : undefined;
@@ -161,7 +171,8 @@ export function handleBrokerSend(
   }
 	const senderIdentity = fromSession.registrationReturnAddress ?? fromSession.info.id;
 	const logicalTarget = typeof clientMessage.logicalTarget === "string" ? clientMessage.logicalTarget : clientMessage.to;
-	const baseSignature = buildMessageSendSignature(logicalTarget, message, senderIdentity);
+	const messageSignature = buildMessageSendSignature(logicalTarget, message, senderIdentity);
+	const baseSignature = expectedRecipientId === undefined ? messageSignature : JSON.stringify({ expectedRecipientId, messageSignature });
 	const signature = requirePendingReply
 		? JSON.stringify({
 				requirePendingReply: true,
@@ -221,6 +232,12 @@ export function handleBrokerSend(
   const resolution = exactIdTarget
     ? ({ kind: "resolved", session: exactIdTarget.info } as const)
     : resolveSessionTarget(candidates, trimmedTo);
+  if (expectedRecipientId !== undefined && (resolution.kind !== "resolved" || resolution.session.id !== expectedRecipientId)) {
+    write(socket, { type: "delivery_failed", messageId, attemptId,
+      reason: resolution.kind === "resolved" ? "Reply target does not match the expected recipient" : sessionTargetFailureReason(clientMessage.to, resolution),
+    });
+    return;
+  }
   if (resolution.kind === "resolved") {
     const target = sessions.get(resolution.session.id);
     if (!target) {

package/dist/builtin/intercom/index.bundle.mjs

@@ -1247,7 +1247,8 @@ var init_client = __esm(() => {
         const pendingSignature = JSON.stringify({
           transportTarget: to,
           logicalSignature: buildSendSignature(options.logicalTarget ?? to, options),
-          requirePendingReply: options.requirePendingReply ?? false
+          requirePendingReply: options.requirePendingReply ?? false,
+          ...options.expectedRecipientId === undefined ? {} : { expectedRecipientId: options.expectedRecipientId }
         });
         acquired = this.pendingSends.acquire(messageId, pendingSignature, 1e4);
       } catch (error) {
@@ -1273,6 +1274,7 @@ var init_client = __esm(() => {
           to,
           ...options.logicalTarget === undefined ? {} : { logicalTarget: options.logicalTarget },
           ...options.requirePendingReply === undefined ? {} : { requirePendingReply: options.requirePendingReply },
+          ...options.expectedRecipientId === undefined ? {} : { expectedRecipientId: options.expectedRecipientId },
           ...options.onReplyTarget === undefined ? {} : { resolveReplyTarget: true },
           message,
           attemptId: acquired.attempt.attemptId,
@@ -2008,22 +2010,22 @@ class ReplyTracker {
   }
   resolveReplyTarget(options, now = Date.now()) {
     this.pruneExpired(now);
-    if (options.replyTo) {
-      const exact = this.pendingAsks.get(options.replyTo);
-      if (exact) {
-        if (options.to) {
-          const resolution = resolveSessionTarget([exact.from], options.to);
-          if (resolution.kind !== "resolved")
-            throw new Error(`Pending ask "${options.replyTo}" is not from "${options.to}"`);
-        }
-        return exact;
+    if (options.replyTo !== undefined) {
+      const exact = this.pendingAsks.get(options.replyTo) ?? (this.currentTurnContext?.message.id === options.replyTo && !this.currentTurnContext.message.expectsReply ? this.currentTurnContext : undefined);
+      if (!exact)
+        throw new Error(`No reply context for "${options.replyTo}"`);
+      if (options.to !== undefined) {
+        const resolution = resolveSessionTarget([exact.from], options.to);
+        if (resolution.kind !== "resolved")
+          throw new Error(`Reply context "${options.replyTo}" is not from "${options.to}"`);
       }
+      return exact;
     }
-    if (this.currentTurnContext) {
+    if (options.to === undefined && this.currentTurnContext) {
       return this.currentTurnContext;
     }
     const pending = Array.from(this.pendingAsks.values());
-    if (options.to) {
+    if (options.to !== undefined) {
       const senders = [...new Map(pending.map((context) => [context.from.id, context.from])).values()];
       const resolution = resolveSessionTarget(senders, options.to);
       if (resolution.kind !== "resolved") {
@@ -2446,13 +2448,13 @@ function formatSessionLabel(session, duplicates) {
   return duplicates.has(session.name.toLowerCase()) ? `${session.name} (${session.id})` : session.name;
 }
 function formatSessionListRow(session, currentCwd, isSelf) {
-  const name = session.name || "Unnamed session";
+  const name = session.name && session.name !== session.id && session.name !== resolveIntercomPresenceName(undefined, session.id) ? ` name: ${session.name}` : "";
   const normalizedGroup = normalizeGroup(session.group);
   const groupTag = normalizedGroup !== DEFAULT_GROUP ? `group: ${normalizedGroup}` : undefined;
   const capabilityTag = session.replyCapability === undefined ? undefined : `replyCapability: ${session.replyCapability}`;
   const tags = [isSelf ? "self" : session.cwd === currentCwd ? "same cwd" : undefined, session.status, capabilityTag, groupTag].filter((tag) => Boolean(tag));
   const suffix = tags.length ? ` [${tags.join(", ")}]` : "";
-  return `• ${name} (${session.id}) — ${session.cwd} (${session.model})${suffix}`;
+  return `- \`${session.id}\`${suffix} ${session.cwd} (${session.model})${name}`;
 }
 function previewText(value, maxLength = 72) {
   if (typeof value !== "string") {
@@ -3192,10 +3194,10 @@ async function resolveReplySender(client, logicalTarget, sendTarget) {
   return { kind: "unresolved" };
 }
 function formatWorkflowStageRow(stage) {
-  return `- **${stage.stageName}** — workflow stage [${stage.lifecycle.toUpperCase()}] — target: \`${stage.target}\`${stage.sessionId === undefined ? "" : ` — intercom session: ${stage.sessionId}`}`;
+  return `- \`${stage.target}\` [${stage.lifecycle.toUpperCase()}] workflow stage: ${stage.stageName}${stage.sessionId === undefined ? "" : ` session: \`${stage.sessionId}\``}`;
 }
 function formatWorkflowFutureStageRow(stage) {
-  return `- future workflow stage \`${stage.target}\` — ${stage.queuedCount} queued message${stage.queuedCount === 1 ? "" : "s"}`;
+  return `- \`${stage.target}\` [future] ${stage.queuedCount} queued message${stage.queuedCount === 1 ? "" : "s"}`;
 }
 function registerIntercomTool(pi, deps) {
   const retryIdentities = new RetryIdentityReservations({ maxEntries: deps.retryIdentityMaxEntries });
@@ -3949,12 +3951,13 @@ ${replyText}${replyAttachments}` }],
                 messageId: replyMessageId,
                 logicalTarget: replyLogicalTarget,
                 ...route.expectsReply ? { requirePendingReply: true } : {},
+                ...to === undefined && replyTo === undefined ? {} : { expectedRecipientId: route.senderId },
                 text: message,
                 attachments,
                 replyTo: route.messageId
               });
               let result = await sendReply(replySendTo);
-              if (to === undefined && result.delivered === false && result.reasonCode === "session_not_found" && route.senderName !== undefined) {
+              if (to === undefined && replyTo === undefined && result.delivered === false && result.reasonCode === "session_not_found" && route.senderName !== undefined) {
                 result = await sendReply(route.senderName);
               }
               if (result.queued === true) {

package/dist/builtin/intercom/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@bastani/intercom",
-  "version": "0.9.19-alpha.7",
+  "version": "0.9.19-alpha.9",
   "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/intercom/skills/intercom/SKILL.md

@@ -67,11 +67,11 @@ intercom({
 
 ### Pattern 2: Quick Status Check
 
-Before sending, verify who's connected. The full session ID printed by `list` is directly usable by `send`, `ask`, and targeted `reply`:
+Before sending, verify who's connected. Each list row leads with a copyable full session ID or canonical workflow path. Names are secondary; redundant generated aliases are omitted from the list but remain valid targets.
 
 ```typescript
 intercom({ action: "list" })
-// → • planner (6332faab-1111-4222-8333-123456789abc) — /workspace (model) [idle]
+// → - `6332faab-1111-4222-8333-123456789abc` [idle] /workspace (model) name: planner
 intercom({ action: "ask", to: "6332faab-1111-4222-8333-123456789abc", message: "Which option should I use?" })
 ```
 
@@ -128,7 +128,7 @@ intercom({ action: "pending" })
 intercom({ action: "reply", to: "planner", message: "Use exponential backoff starting at 100ms." })
 ```
 
-`reply` still preserves exact threading under the hood by sending the response with the original `replyTo` value.
+Explicit `to` selects that sender's pending ask even if another message triggered the current turn. Use `pending` and an exact `replyTo` when the sender has several asks. Stale, unknown, empty, or sender-mismatched explicit selectors fail without replying to another thread. Omit both selectors only when you intend to reply to the active message, or otherwise the single pending ask.
 
 ### Pattern 4: Broadcast to Multiple Workers
 

package/dist/builtin/intercom/types.ts

@@ -124,7 +124,7 @@ export type ClientMessage =
 	| { type: "join_group"; requestId: string; group: string }
 	| { type: "leave_group"; requestId: string; group?: string }
   | { type: "authorize_supervisor"; requestId: string; childName: string; capability?: string }
-  | { type: "send" | "supervisor_send"; to: string; logicalTarget?: string; requirePendingReply?: true; resolveReplyTarget?: true; message: Message; attemptId?: string }
+  | { type: "send" | "supervisor_send"; to: string; logicalTarget?: string; requirePendingReply?: true; expectedRecipientId?: string; resolveReplyTarget?: true; message: Message; attemptId?: string }
 	| {
 			type: "send_pending_stage_notification";
 			runId: string;

package/dist/builtin/mcp/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@bastani/mcp",
-  "version": "0.9.19-alpha.7",
+  "version": "0.9.19-alpha.9",
   "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.7",
+  "version": "0.9.19-alpha.9",
   "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.9] - 2026-09-12
+
+### Fixed
+
+- `fetch_content` ignores video frame options for non-video inputs, so webpages and mixed batches no longer fail with video-only errors. Tool and parameter descriptions now distinguish ordinary page fetching, video analysis, and frame extraction.
+
 ## [0.9.19-alpha.7] - 2026-09-12
 
 ### Fixed

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

@@ -74476,13 +74476,15 @@ async function extractContent(url, signal, options) {
   if (signal?.aborted) {
     return { url, title: "", content: "", error: "Aborted" };
   }
-  const frameResult = await extractRequestedFrames(url, options, signal);
-  if (frameResult)
-    return frameResult;
   const localVideo = safeVideoInfo2(url);
   if (localVideo.error) {
     return { url, title: "", content: "", error: localVideo.error };
   }
+  if (localVideo.info || isYouTubeURL(url).isYouTube) {
+    const frameResult = await extractRequestedFrames(url, options, signal);
+    if (frameResult)
+      return frameResult;
+  }
   if (localVideo.info) {
     try {
       const result = await extractVideo(localVideo.info, signal, options);
@@ -90949,29 +90951,29 @@ function registerContentTools(pi, deps) {
   pi.registerTool({
     name: "fetch_content",
     label: "Fetch Content",
-    description: "Fetch URL(s) and extract readable content as markdown. Supports YouTube video transcripts (with thumbnail), GitHub repository contents, and local video files (with frame thumbnail). Video frames can be extracted via timestamp/range or sampled across the entire video with frames alone. Falls back to Gemini for pages that block bots or fail Readability extraction. For YouTube and video files: ALWAYS pass the user's specific question via the prompt parameter — this directs the AI to focus on that aspect of the video, producing much better results than a generic extraction. Content is always stored and can be retrieved with get_search_content.",
-    promptSnippet: "Use to extract readable content from URL(s), YouTube, GitHub repos, or local videos. For video questions, pass the user's exact question in prompt.",
+    description: `Fetch webpages, PDFs, GitHub repositories, YouTube videos, or local video files. For ordinary pages, pass only {"urls":["https://example.com"]}; readable content is returned as markdown. For video analysis, include the user's question in prompt. Optional frames and timestamp extract images only from YouTube or local videos and are ignored for other inputs, including in mixed batches. Content is stored for get_search_content. Blocked or unreadable pages use extraction fallbacks.`,
+    promptSnippet: "Fetch webpages with urls only. For YouTube or local video analysis, include the user's question in prompt; omit frames and timestamp unless images are wanted.",
     parameters: Type2.Object({
       urls: Type2.Array(Type2.String({ minLength: 1 }), {
         minItems: 1,
         description: 'URLs or local video paths to fetch. Always use an array, even for one URL: {"urls":["https://example.com"]}. Multiple URLs are fetched in parallel.'
       }),
       forceClone: Type2.Optional(Type2.Boolean({
-        description: "Force cloning large GitHub repositories that exceed the size threshold"
+        description: "GitHub repositories only: allow cloning above the configured size threshold. Omit for webpages and videos."
       })),
       prompt: Type2.Optional(Type2.String({
-        description: "Question or instruction for video analysis (YouTube and video files). Pass the user's specific question here — e.g. 'describe the book shown at the advice for beginners section'. Without this, a generic transcript extraction is used which may miss what the user is asking about."
+        description: "YouTube/local video analysis only: the user's specific question. Omit for webpages; this is not a webpage search or extraction filter."
       })),
       timestamp: Type2.Optional(Type2.String({
-        description: "Extract video frame(s) at a timestamp or time range. Single: '1:23:45', '23:45', or '85' (seconds). Range: '23:41-25:00' extracts evenly-spaced frames across that span (default 6). Use frames with ranges to control density; single+frames uses a fixed 5s interval. YouTube requires yt-dlp + ffmpeg; local videos require ffmpeg. Use a range when you know the approximate area but not the exact moment — you'll get a contact sheet to visually identify the right frame."
+        description: "YouTube/local video images only: seconds ('85'), time ('1:25'), or range ('1:25-2:00'). Omit for text/transcripts. Ignored for non-video inputs. Ranges default to 6 frames; use frames to adjust."
       })),
       frames: Type2.Optional(Type2.Integer({
         minimum: 1,
         maximum: 12,
-        description: "Number of frames to extract. Use with timestamp range for custom density, with single timestamp to get N frames at 5s intervals, or alone to sample across the entire video. Requires yt-dlp + ffmpeg for YouTube, ffmpeg for local video."
+        description: "YouTube/local video images only: 1-12 frames. Alone, samples the whole video; with a range, samples that span; with a single timestamp, uses 5s intervals. Ignored for non-video inputs. Omit for text/transcripts. Requires ffmpeg, plus yt-dlp for YouTube."
       })),
       model: Type2.Optional(Type2.String({
-        description: "Override the Gemini model for video/YouTube analysis (e.g. 'gemini-2.5-flash', 'gemini-3-flash-preview'). Defaults to config or gemini-3-flash-preview."
+        description: "Gemini model override for YouTube/local video analysis only. Omit to use the configured default; does not select the webpage extraction model."
       }))
     }, { additionalProperties: false }),
     async execute(_toolCallId, params, signal, onUpdate) {
@@ -97598,18 +97600,18 @@ function webAccess(pi) {
   pi.registerTool({
     name: "fetch_content",
     label: "Fetch Content",
-    description: "Fetch URL(s) and extract readable content as markdown. Supports YouTube video transcripts (with thumbnail), GitHub repository contents, and local video files (with frame thumbnail). Video frames can be extracted via timestamp/range or sampled across the entire video with frames alone. Falls back to Gemini for pages that block bots or fail Readability extraction. For YouTube and video files: ALWAYS pass the user's specific question via the prompt parameter — this directs the AI to focus on that aspect of the video, producing much better results than a generic extraction. Content is always stored and can be retrieved with get_search_content.",
-    promptSnippet: "Use to extract readable content from URL(s), YouTube, GitHub repos, or local videos. For video questions, pass the user's exact question in prompt.",
+    description: `Fetch webpages, PDFs, GitHub repositories, YouTube videos, or local video files. For ordinary pages, pass only {"urls":["https://example.com"]}; readable content is returned as markdown. For video analysis, include the user's question in prompt. Optional frames and timestamp extract images only from YouTube or local videos and are ignored for other inputs, including in mixed batches. Content is stored for get_search_content. Blocked or unreadable pages use extraction fallbacks.`,
+    promptSnippet: "Fetch webpages with urls only. For YouTube or local video analysis, include the user's question in prompt; omit frames and timestamp unless images are wanted.",
     parameters: Type4.Object({
       urls: Type4.Array(Type4.String({ minLength: 1 }), {
         minItems: 1,
         description: 'URLs or local video paths to fetch. Always use an array, even for one URL: {"urls":["https://example.com"]}. Multiple URLs are fetched in parallel.'
       }),
-      forceClone: Type4.Optional(Type4.Boolean({ description: "Force cloning large GitHub repositories that exceed the size threshold" })),
-      prompt: Type4.Optional(Type4.String({ description: "Question or instruction for video analysis (YouTube and video files)." })),
-      timestamp: Type4.Optional(Type4.String({ description: "Extract video frame(s) at a timestamp or time range." })),
-      frames: Type4.Optional(Type4.Integer({ minimum: 1, maximum: 12, description: "Number of frames to extract." })),
-      model: Type4.Optional(Type4.String({ description: "Override the Gemini model for video/YouTube analysis." }))
+      forceClone: Type4.Optional(Type4.Boolean({ description: "GitHub repositories only: allow cloning above the configured size threshold. Omit for webpages and videos." })),
+      prompt: Type4.Optional(Type4.String({ description: "YouTube/local video analysis only: the user's specific question. Omit for webpages; this is not a webpage search or extraction filter." })),
+      timestamp: Type4.Optional(Type4.String({ description: "YouTube/local video images only: seconds ('85'), time ('1:25'), or range ('1:25-2:00'). Omit for text/transcripts. Ignored for non-video inputs. Ranges default to 6 frames; use frames to adjust." })),
+      frames: Type4.Optional(Type4.Integer({ minimum: 1, maximum: 12, description: "YouTube/local video images only: 1-12 frames. Alone, samples the whole video; with a range, samples that span; with a single timestamp, uses 5s intervals. Ignored for non-video inputs. Omit for text/transcripts. Requires ffmpeg, plus yt-dlp for YouTube." })),
+      model: Type4.Optional(Type4.String({ description: "Gemini model override for YouTube/local video analysis only. Omit to use the configured default; does not select the webpage extraction model." }))
     }, { additionalProperties: false }),
     execute: (...args) => executeHeavyTool(loadHeavy, "fetch_content", args),
     renderResult: (...args) => renderHeavyToolResult(loadedHeavy?.heavy ?? null, "fetch_content", args)

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

@@ -1,6 +1,6 @@
 {
   "name": "@bastani/web-access",
-  "version": "0.9.19-alpha.7",
+  "version": "0.9.19-alpha.9",
   "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 +6,23 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/),
 
 ## [Unreleased]
 
+## [0.9.19-alpha.9] - 2026-09-12
+
+### Fixed
+
+- Kept the background workflow summary within narrow terminal widths, including 27 columns. The shared workflow widget now stays within ten rows, shrinks on short terminals, and scrolls one row at a time with Alt+PageUp / Alt+PageDown without taking focus from the editor. All workflow rows remain reachable when a multiline draft reduces the visible widget area ([#3015](https://github.com/bastani-inc/atomic/issues/3015)).
+- Kept the workflow being read in view when live runs are inserted or removed above it, including workflows with identical names. Resizing to a collapsed summary and back preserves the reading position; removing the viewed run selects its next surviving neighbour, or the previous one when no later run remains ([#3017](https://github.com/bastani-inc/atomic/pull/3017)).
+
+## [0.9.19-alpha.8] - 2026-09-12
+
+### Fixed
+
+- Workflow status detail now shows started and ended times in the system local timezone instead of UTC, preserving the compact `HH:mm:ss` display and elapsed durations ([#3008](https://github.com/bastani-inc/atomic/issues/3008)).
+
+### Changed
+
+- Removed generated `root`, `dep`, and `deps` labels from workflow graph nodes and left model text blank when no model is set. Cards omit the extra padding row. Queued-message counts appear on a separate `✉ N queued` row, reusing empty space or expanding occupied cards without hiding status or model details. Dependency edges are unchanged.
+
 ## [0.9.19-alpha.7] - 2026-09-12
 
 ### Fixed

package/dist/builtin/workflows/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@bastani/workflows",
-  "version": "0.9.19-alpha.7",
+  "version": "0.9.19-alpha.9",
   "private": true,
   "description": "Atomic extension for multi-stage workflow authoring and execution.",
   "contributors": [