@axiom-lattice/core 2.1.63 → 2.1.64

package/dist/index.mjs

@@ -11883,7 +11883,11 @@ var Agent = class {
             yield chunk;
           }
         } catch (error) {
-          console.error("Resume stream error:", error);
+          if (error?.message === "Thread aborted") {
+            console.debug("Resume stream interrupted: thread aborted");
+          } else {
+            console.error("Resume stream error:", error);
+          }
           throw error;
         }
       }
@@ -18584,15 +18588,76 @@ Use this when the task follows a standard BPO (Business Process Orchestration) p
 
 **Step 4: Design the orchestrator.** Responsibility, system prompt, topology edges, sub-agent list.
 
-**Step 5: Self-review checklist.** Before presenting to the user, verify:
-- Completeness (every stage covered by an edge?)
-- Purposes clear (each edge's business intent?)
-- Order correct (serial chain logical?)
-- Edge cases (invalid input, failure, timeout?)
-
-### Phase 2: Confirm
-
-Present the full design: topology diagram, all sub-agent configs, orchestrator config. **Ask for explicit approval:** "Ready to build? I'll create {N} sub-agents, then the orchestrator. Proceed?" **Do NOT build until the user confirms.**
+ **Step 5: Self-review checklist.** Before presenting to the user, verify:
+ - Completeness (every stage covered by an edge?)
+ - Purposes clear (each edge's business intent?)
+ - Order correct (serial chain logical?)
+ - Edge cases (invalid input, failure, timeout?)
+
+ **Step 6: Write the workflow description (Spec).** After designing the topology and sub-agents, compose a comprehensive **\`description\`** for the orchestrator. This description serves as the workflow's specification \u2014 anyone reading it should understand exactly what this workflow does without needing to inspect individual sub-agent configs.
+
+ The description MUST include ALL of the following:
+
+ | Section | Content |
+ |---------|---------|
+ | **Overview** | One-sentence summary of the workflow's purpose and business value |
+ | **Steps** | Numbered list of each stage in the pipeline. For each step: which sub-agent handles it, what it does, what tools it uses, and what it produces (output) |
+ | **Data Flow** | How data moves between steps. What does each step receive as input? What does it produce and pass to the next step? |
+ | **Logic & Conditions** | Any conditional branching, decision points, retry logic, or exception handling. When does the workflow take path A vs path B? What happens on failure? |
+ | **Tools Used** | Summary table or list of all tools used across sub-agents, grouped by sub-agent |
+ | **Expected Input** | What input does the workflow expect from the user? (format, examples) |
+ | **Expected Output** | What does the workflow produce at the end? (format, examples) |
+
+ **Formatting rules:**
+ - Write in **Chinese** if the user communicates in Chinese; otherwise English
+ - Use **Markdown** for formatting (headings, lists, tables, code blocks)
+ - Be detailed but concise \u2014 each section should be 1-5 lines
+ - Avoid placeholder text like "TODO" or "TBD"
+
+ **Example structure:**
+
+ \`\`\`markdown
+ ## Overview
+ \u672C\u5DE5\u4F5C\u6D41\u81EA\u52A8\u4ECE\u591A\u4E2A\u6570\u636E\u6E90\u91C7\u96C6\u7ADE\u54C1\u4EF7\u683C\uFF0C\u751F\u6210\u5BF9\u6BD4\u5206\u6790\u62A5\u544A\u5E76\u63A8\u9001\u901A\u77E5\u3002
+
+ ## Steps
+ 1. **\u6570\u636E\u91C7\u96C6 (data-collector)** \u2014 \u4F7F\u7528 browser \u5DE5\u5177\u722C\u53D6\u6307\u5B9AURL\u7684\u7ADE\u54C1\u4EF7\u683C\u6570\u636E\uFF0C\u8C03\u7528 metrics API \u62C9\u53D6\u5386\u53F2\u4EF7\u683C\u3002\u8F93\u51FA\u539F\u59CB\u4EF7\u683C\u6570\u636E\u96C6 JSON\u3002
+ 2. **\u6570\u636E\u6E05\u6D17 (data-cleaner)** \u2014 \u4F7F\u7528 code_eval \u6267\u884C Python \u811A\u672C\u6E05\u6D17\u5F02\u5E38\u503C\u548C\u7F3A\u5931\u503C\uFF0C\u7EDF\u4E00\u8D27\u5E01\u5355\u4F4D\u3002\u8F93\u51FA\u6807\u51C6\u5316\u6570\u636E\u96C6\u3002
+ 3. **\u62A5\u544A\u751F\u6210 (report-generator)** \u2014 \u4F7F\u7528 filesystem \u8BFB\u53D6\u6A21\u677F\uFF0Ccode_eval \u8BA1\u7B97\u6DA8\u8DCC\u5E45\u548C\u8D8B\u52BF\uFF0C\u751F\u6210 Markdown \u5BF9\u6BD4\u62A5\u544A\u3002\u8F93\u51FA\u62A5\u544A\u6587\u4EF6\u8DEF\u5F84\u3002
+ 4. **\u901A\u77E5\u63A8\u9001 (notifier)** \u2014 \u8C03\u7528 scheduler \u5B89\u6392\u5B9A\u65F6\u53D1\u9001\uFF0C\u4F7F\u7528 ask_user_to_clarify \u8BF7\u6C42\u53D1\u9001\u786E\u8BA4\u3002\u8F93\u51FA\u53D1\u9001\u7ED3\u679C\u3002
+
+ ## Data Flow
+ \`\u7528\u6237\u8F93\u5165(URL\u5217\u8868 + \u65E5\u671F\u8303\u56F4)\` \u2192 data-collector \u722C\u53D6+\u67E5\u8BE2 \u2192 \u539F\u59CBJSON \u2192 data-cleaner \u6E05\u6D17\u8F6C\u6362 \u2192 \u6807\u51C6\u5316JSON \u2192 report-generator \u5206\u6790\u751F\u6210 \u2192 \u62A5\u544AMarkdown \u2192 notifier \u63A8\u9001
+
+ ## Logic & Conditions
+ - data-collector \u722C\u53D6\u5931\u8D25\u65F6\u91CD\u8BD5\u6700\u591A3\u6B21\uFF0C\u95F4\u969430\u79D2
+ - \u82E5\u67D0\u4E00\u5546\u54C1\u4EF7\u683C\u7F3A\u5931\u8D85\u8FC77\u5929\uFF0C\u6807\u8BB0\u4E3A\u300C\u6570\u636E\u4E0D\u5168\u300D\u5E76\u5728\u62A5\u544A\u4E2D\u9AD8\u4EAE
+ - report-generator \u8BA1\u7B97\u6DA8\u5E45\u8D85\u8FC720%\u65F6\u81EA\u52A8\u6807\u8BB0\u300C\u5F02\u5E38\u6CE2\u52A8\u300D\u8B66\u544A
+ - \u4EFB\u4F55\u6B65\u9AA4\u5931\u8D25\u65F6\uFF0Cworkflow \u505C\u6B62\u5E76\u5C06\u9519\u8BEF\u4FE1\u606F\u8F93\u51FA\u5230\u6700\u7EC8\u62A5\u544A
+
+ ## Tools Used
+ | \u5B50Agent | \u5DE5\u5177 |
+ |---------|------|
+ | data-collector | browser, metrics |
+ | data-cleaner | code_eval, filesystem |
+ | report-generator | code_eval, filesystem |
+ | notifier | scheduler, ask_user_to_clarify |
+
+ ## Expected Input
+ - \u7ADE\u54C1URL\u5217\u8868\uFF08\u6BCF\u884C\u4E00\u4E2A\uFF09
+ - \u65E5\u671F\u8303\u56F4\uFF08\u8D77\u59CB-\u7ED3\u675F\uFF0C\u683C\u5F0F YYYY-MM-DD\uFF09
+ - \u63A8\u9001\u6E20\u9053\u9009\u62E9\uFF08\u90AE\u4EF6/\u9489\u9489/\u4F01\u4E1A\u5FAE\u4FE1\uFF09
+
+ ## Expected Output
+ - Markdown \u683C\u5F0F\u5BF9\u6BD4\u62A5\u544A\uFF0C\u5305\u542B\u4EF7\u683C\u8D8B\u52BF\u56FE\u3001\u6DA8\u8DCC\u5E45\u3001\u5F02\u5E38\u6807\u8BB0
+ - \u62A5\u544A\u6587\u4EF6\u8DEF\u5F84\u53CA\u63A8\u9001\u72B6\u6001\u786E\u8BA4
+ \`\`\`
+
+ **The description field is the single source of truth for the workflow.** When the user clicks the info icon on the workflow in the automation view, they will see this description rendered as a Popover. It must be comprehensive enough to stand alone as a spec document.
+
+ ### Phase 2: Confirm
+
+ Present the full design: topology diagram, all sub-agent configs, orchestrator config, AND the workflow description (spec). **Ask for explicit approval:** "Ready to build? I'll create {N} sub-agents, then the orchestrator. Proceed?" **Do NOT build until the user confirms.**
 
 ### Phase 3: Build
 
@@ -18711,7 +18776,7 @@ Creates a PROCESSING agent with a business-defined workflow topology. Sub-agents
 \`\`\`typescript
 {
   name: string,              // Required. Display name for the orchestrator
-  description?: string,      // Optional. Short description
+  description?: string,      // Required for good UX. Comprehensive workflow spec in Markdown (Chinese if user speaks Chinese). Must cover: Overview, Steps (with tools per step), Data Flow, Logic & Conditions, Tools Used, Expected Input, Expected Output. This is the single source of truth displayed in the automation view info popover.
   prompt: string,            // Required. System prompt \u2014 how to route through the topology
   edges: [{                  // Required. At least 1 edge defining the workflow
     from: string,            // Orchestrator's ID (use placeholder name; tool auto-replaces)
@@ -18733,7 +18798,7 @@ Creates a PROCESSING agent with a business-defined workflow topology. Sub-agents
 \`\`\`typescript
 {
   name: string,              // Required. Display name for the orchestrator
-  description?: string,      // Optional. Short description
+  description?: string,      // Required for good UX. Comprehensive workflow spec in Markdown (Chinese if user speaks Chinese). Must cover: Overview, Steps (with tools per step), Data Flow, Logic & Conditions, Tools Used, Expected Input, Expected Output. This is the single source of truth displayed in the automation view info popover.
   prompt: string,            // Required. System prompt \u2014 how to route through the topology
   edges: [{                  // Required. At least 1 edge defining the serial workflow chain
     from: string,            // Source agent ID. First edge: use orchestrator name as placeholder (tool auto-replaces). Subsequent edges: previous sub-agent ID