@elevasis/sdk 0.5.12 → 0.5.14

package/dist/templates.js

@@ -31,26 +31,30 @@ ui/dist/
 
 // src/cli/commands/templates/core/claude.ts
 function claudeSettingsTemplate() {
-  return JSON.stringify({
-    autoCompact: false,
-    statusLine: {
-      type: "command",
-      command: "node .claude/scripts/statusline-command.js"
+  return JSON.stringify(
+    {
+      autoCompact: false,
+      statusLine: {
+        type: "command",
+        command: "node .claude/scripts/statusline-command.js"
+      },
+      hooks: {
+        PreToolUse: [
+          {
+            matcher: "Write|Edit|MultiEdit|Bash",
+            hooks: [
+              {
+                type: "command",
+                command: "node .claude/hooks/enforce-sdk-boundary.mjs"
+              }
+            ]
+          }
+        ]
+      }
     },
-    hooks: {
-      PreToolUse: [
-        {
-          matcher: "Write|Edit|MultiEdit|Bash",
-          hooks: [
-            {
-              type: "command",
-              command: "node .claude/hooks/enforce-sdk-boundary.mjs"
-            }
-          ]
-        }
-      ]
-    }
-  }, null, 2) + "\n";
+    null,
+    2
+  ) + "\n";
 }
 function claudeStatuslineScriptTemplate() {
   return `#!/usr/bin/env node
@@ -253,16 +257,16 @@ proactivity -- to their assessed levels.
 
 | Resource | Location | When to Load |
 | --- | --- | --- |
-| Workspace concepts | \`reference/concepts/index.mdx\` | User asks "what is...?" or needs conceptual grounding |
+| Workspace concepts | \`reference/concepts.mdx\` | User asks "what is...?" or needs conceptual grounding |
 | SDK patterns and examples | \`reference/resources/patterns.mdx\` | Building or modifying a workflow |
 | Platform tool catalog | \`reference/platform-tools/index.mdx\` | Connecting to external services |
-| CLI reference | \`reference/cli/index.mdx\` | Running execution/platform operations |
-| Credential model | \`reference/security/credentials.mdx\` | Setting up integrations or tool access |
-| Interaction guidance | \`reference/developer/interaction-guidance.mdx\` | Unsure how to adapt for a skill combination |
+| CLI reference | \`reference/cli.mdx\` | Running execution/platform operations |
+| Credential model | \`reference/platform-tools/index.mdx\` | Setting up integrations or credential security |
+| Interaction guidance | \`reference/framework/interaction-guidance.mdx\` | Unsure how to adapt for a skill combination |
 | Error history | \`.claude/memory/errors/index.md\` | Debugging errors, checking past fixes |
-| Command View model | \`reference/deployment/command-view.mdx\` | Deploying or building resources that invoke other resources |
-| Command Center UI reference | \`reference/deployment/command-center-ui.mdx\` | User asks about post-deployment UI or Command Center navigation |
-| SDK error reference | \`reference/troubleshooting/common-errors.mdx\` | Unknown error not in workspace memory |
+| Command View model | \`reference/deployment/command-center.mdx\` | Deploying or building resources that invoke other resources |
+| Command Center UI reference | \`reference/deployment/command-center.mdx\` | User asks about post-deployment UI or Command Center navigation |
+| SDK error reference | \`reference/troubleshooting.mdx\` | Unknown error not in workspace memory |
 | Project map | \`docs/project-map.mdx\` | Session start, project orientation |
 | Resource inventory | \`docs/resource-map.mdx\` | Finding a specific resource by name or ID |
 | Project priorities | \`docs/priorities.mdx\` | Deciding what to work on next |
@@ -288,7 +292,7 @@ Use \`pnpm exec elevasis-sdk\` for runtime commands (resolves the locally instal
 - \`pnpm exec elevasis-sdk execution <resource-id> <execution-id>\` -- inspect execution detail
 
 Organization is derived from your API key -- no org prefix needed in the resource ID.
-For full CLI reference: \`reference/cli/index.mdx\`
+For full CLI reference: \`reference/cli.mdx\`
 
 ## Rules
 
@@ -303,8 +307,8 @@ SDK patterns (imports, source structure, platform tools) are auto-loaded from
 
 When an error occurs:
 1. Check \`.claude/memory/errors/\` first for past fixes
-2. If new, check \`reference/troubleshooting/common-errors.mdx\`
-3. After resolving, record in \`memory/errors/\` with context and fix
+2. If new, check \`reference/troubleshooting.mdx\`
+3. After resolving, record in \`.claude/memory/errors/\` with context and fix
 4. If an error recurs 3+ times, add a rule to \`.claude/rules/workspace-patterns.md\`${ctx.hasUI ? `
 
 ### UI App (\`ui/\`)
@@ -313,7 +317,8 @@ When an error occurs:
 - Import from \`@elevasis/sdk-ui\`, never from \`@elevasis/sdk\` or \`@repo/ui\`
 - Dev server runs on port 5100: \`cd ui && pnpm dev\`
 - Set \`VITE_WORKOS_CLIENT_ID\` in \`ui/.env\` before running
-- \`ElevasisProvider\` is pre-configured in \`ui/src/App.tsx\` (oauth mode, redirectUri \`http://localhost:5100/auth-redirect\`, apiUrl \`http://localhost:5170\`)
+- \`ElevasisCoreProvider\` (headless, no Mantine dependency) is pre-configured in \`ui/src/App.tsx\` with \`auth={{ mode: 'oauth', clientId, redirectUri }}\`, \`apiUrl="http://localhost:5170"\`, and \`theme={{ colorScheme: 'dark', preset: 'default' }}\`
+- To use pre-built Mantine components from \`@elevasis/sdk-ui\`, switch to \`ElevasisUIProvider\` and install \`@mantine/core\` and \`@mantine/hooks\`
 - OAuth redirect is handled by the \`AuthRedirect\` component at \`/auth-redirect\` -- it uses \`useAuthContext()\` from \`@elevasis/sdk-ui/auth\` and navigates home once \`user\` is set
 - API must be running on port 5170 for the UI to work (\`pnpm --filter api dev\` from the platform monorepo)` : ""}
 
@@ -335,7 +340,7 @@ based on what you find.
 - When growth is observed, note it in the skills.md Growth Log.
 
 For detailed per-dimension adaptation rules, read
-\`reference/developer/interaction-guidance.mdx\`.
+\`reference/framework/interaction-guidance.mdx\`.
 
 ## Commands
 
@@ -344,7 +349,7 @@ For detailed per-dimension adaptation rules, read
 | \`/meta\` | Project lifecycle: init, status, fix, deploy, health |
 | \`/docs\` | Browse, create, and verify permanent documentation |
 | \`/work\` | Task tracking: create, save, resume, complete |
-| \`/tutorial\` | Progressive learning path (7 core lessons + 9 modules) |
+| \`/tutorial\` | Progressive learning path (21 items across 4 sections) |
 
 ## Skills
 
@@ -377,7 +382,7 @@ Do not store in \`.claude/memory/\`:
 
 ### Structure
 
-- \`memory/index.md\` is the root -- maps to topic files and subdirectories
+- \`.claude/memory/index.md\` is the root -- maps to topic files and subdirectories
 - Every subdirectory has its own \`index.md\` mapping to children
 - Start at the root index and drill down
 - When a file outgrows a single document, split into a subdirectory
@@ -401,14 +406,14 @@ Read \`.claude/memory/profile/skills.md\` first. The \`automation\` skill level
 controls which docs you load and which lesson variant you deliver.
 
 **automation: none**
-- Load from \`reference/concepts/index.mdx\`: Glossary, What is a Workflow,
+- Load from \`reference/concepts.mdx\`: Glossary, What is a Workflow,
   Platform Tools Overview only. Skip Zod, Execution Model, Design Decisions.
-- Load \`reference/deployment/command-center-ui.mdx\` for UI-first teaching.
+- Load \`reference/deployment/command-center.mdx\` for UI-first teaching.
 - Do NOT load \`reference/resources/patterns.mdx\` or
   \`reference/platform-tools/adapters.mdx\` during core lessons.
 
 **automation: low-code**
-- Load all sections of \`reference/concepts/index.mdx\`.
+- Load all sections of \`reference/concepts.mdx\`.
 - Load \`reference/resources/patterns.mdx\` with Zapier/Make mapping in mind.
 - Load \`reference/platform-tools/adapters.mdx\` on-demand (when tools are used).
 
@@ -496,7 +501,7 @@ Each lesson follows this flow:
 
 When automation is none:
 Skip the file tour. Start with what Elevasis does for their business -- use analogies
-from \`reference/developer/interaction-guidance.mdx\` (recipe, assembly line, kitchen
+from \`reference/framework/interaction-guidance.mdx\` (recipe, assembly line, kitchen
 appliance). Explain deployment plainly: "You write the recipe here, then deploy it so
 it's live." Deploy the starter echo workflow (\`elevasis-sdk check\` + \`elevasis-sdk deploy\`),
 THEN tour the Command Center so the user sees populated pages, not empty ones. Tour:
@@ -744,14 +749,14 @@ Each module follows this flow:
 ## Modules
 
 **Module: hitl -- Human-in-the-Loop**
-Read: \`reference/deployment/command-center-ui.mdx\` (Command Queue section).
+Read: \`reference/deployment/command-center.mdx\` (Command Queue section).
 Build: Add an approval gate using \`approval.requestApproval()\`. Test full lifecycle:
 trigger, see pending in Command Queue, approve/reject, observe resume.
 Key concepts: approval adapter, pending state, Command Queue UI, resume on decision.
 Verify: Trigger workflow, open Command Queue, approve, confirm completion.
 
 **Module: schedules -- Task Scheduling**
-Read: \`reference/deployment/command-center-ui.mdx\` (Task Scheduler section).
+Read: \`reference/deployment/command-center.mdx\` (Task Scheduler section).
 Build: Create all three schedule types (Recurring cron, Relative delay, Absolute
 datetime). Use \`scheduler\` adapter for in-workflow scheduling.
 Key concepts: schedule types, cron syntax, scheduler adapter, Task Scheduler UI.
@@ -765,7 +770,7 @@ Verify: Run workflow, check notification in Command Center, confirm email receiv
 
 **Module: integrations -- Real-World Integrations**
 Read: \`reference/platform-tools/index.mdx\`, \`reference/platform-tools/adapters.mdx\`,
-\`reference/security/credentials.mdx\`.
+\`reference/platform-tools/index.mdx\`.
 Build: Pick a real integration adapter based on user's goals (read \`identity.md\`).
 Set up credential (OAuth via UI, API key via CLI). Build end-to-end integration workflow.
 Key concepts: adapter pattern, credential scoping, error handling for external calls.
@@ -774,7 +779,7 @@ handling with invalid credential.
 
 **Module: error-handling -- Error Handling Mastery**
 Read: \`reference/resources/patterns.mdx\` (error handling),
-\`reference/troubleshooting/common-errors.mdx\`.
+\`reference/troubleshooting.mdx\`.
 Build: Create a workflow demonstrating all three error types. Add try/catch,
 \`context.logger\`, and error recovery.
 Key concepts: ExecutionError, PlatformToolError, ToolingError, recovery patterns.
@@ -790,7 +795,7 @@ Key concepts: context.store, context.logger, domain organization, schema depth.
 Verify: Run workflow, confirm store values in step output, check logs in Execution Logs.
 
 **Module: composition -- Resource Composition**
-Read: \`reference/deployment/command-view.mdx\`, \`reference/resources/patterns.mdx\`.
+Read: \`reference/deployment/command-center.mdx\`, \`reference/resources/patterns.mdx\`.
 Build: Create two workflows where the first triggers the second using
 \`execution.trigger()\`. Declare the relationship.
 Key concepts: execution.trigger, relationship declarations, Command View graph edges.
@@ -938,7 +943,7 @@ Last Session: {today's date}
 \`\`\`
 
 Update rules:
-- \`Current\`: free-form, e.g. "4: Using Platform Tools" or "M:integrations" or "20: Rules, Memory, and Customization"
+- \`Current\`: free-form, e.g. "7: Using Platform Tools" or "M:integrations" or "20: Rules, Memory, and Customization"
 - \`Last Session\`: update to today's date on each \`/tutorial\` invocation
 - Completed Lessons: add a row when any numbered item (1-10, 20-21) finishes
 - Completed Modules: add a row when any module (items 11-19) finishes
@@ -1034,9 +1039,9 @@ by the \`<!-- initialized: false -->\` flag in CLAUDE.md, or run manually.
    - Create \`.claude/memory/profile/preferences.md\` (verbosity, guidance)
 
 4. **Git check**
-   - If \`.git/\` exists: note git is configured in memory/profile/preferences.md
+   - If \`.git/\` exists: note git is configured in .claude/memory/profile/preferences.md
    - If \`.git/\` does not exist: suggest \`git init\` and optionally GitHub
-   - If git remote exists: note remote URL in memory/profile/preferences.md
+   - If git remote exists: note remote URL in .claude/memory/profile/preferences.md
 
 5. **Verify project**
    Run \`elevasis-sdk check\` to confirm the starter resource is valid.
@@ -1057,9 +1062,9 @@ by the \`<!-- initialized: false -->\` flag in CLAUDE.md, or run manually.
 
 Display a project health summary:
 1. Template version (from elevasis.config.ts) and installed SDK version (from package.json). Suggest \`elevasis-sdk update\` to check for updates
-3. Profile summary (from memory/profile/skills.md)
-4. Quick drift check: count of missing managed files, missing gitignore entries
-5. Last deployment status (from memory/deployment-state.md if it exists)
+2. Profile summary (from .claude/memory/profile/skills.md)
+3. Quick drift check: count of missing managed files, missing gitignore entries
+4. Last deployment status (from .claude/memory/deployment-state.md if it exists)
 
 ### \`/meta fix\` -- Maintenance and Upgrade
 
@@ -1077,9 +1082,9 @@ Detect and repair all drift. Optionally upgrades the SDK first.
 3. **CLAUDE.md sections:** Add missing sections in correct position
 4. **Memory structure:** Create base structure if missing, then verify index consistency.
    If \`.claude/memory/\` does not exist or is empty:
-   - Create \`memory/index.md\` (root index with placeholder entries)
-   - Create \`memory/errors/index.md\` (error category summary, empty tables)
-   - Create \`memory/errors/deploy.md\`, \`memory/errors/runtime.md\`, \`memory/errors/typescript.md\`
+   - Create \`.claude/memory/index.md\` (root index with placeholder entries)
+   - Create \`.claude/memory/errors/index.md\` (error category summary, empty tables)
+   - Create \`.claude/memory/errors/deploy.md\`, \`.claude/memory/errors/runtime.md\`, \`.claude/memory/errors/typescript.md\`
    If memory exists, verify: every file referenced in an index exists; every file
    without an index entry gets one added; broken references are removed.
 5. **Documentation verification:** For each file in docs/:
@@ -1090,7 +1095,7 @@ Detect and repair all drift. Optionally upgrades the SDK first.
    e. Report discrepancies with suggested fixes
    Note: \`/docs verify\` is available for standalone interactive verification outside this pipeline.
 6. **Settings consistency:** Verify expected fields
-7. **Rules health:** Scan \`memory/errors/\` -- flag any entry that has recurred
+7. **Rules health:** Scan \`.claude/memory/errors/\` -- flag any entry that has recurred
    3+ times and is not yet in \`.claude/rules/workspace-patterns.md\`.
    If \`workspace-patterns.md\` has no rules yet and 5+ resources exist in \`src/\`,
    suggest adding patterns. Surface suggestions only -- do not auto-generate.
@@ -1103,7 +1108,7 @@ Each step reports its result. Steps 1-8 run even if step 0 is skipped.
 
 ### \`/meta deploy\` -- Full Deploy Pipeline
 
-0. Read \`reference/deployment/command-view.mdx\` -- understand the Command View
+0. Read \`reference/deployment/command-center.mdx\` -- understand the Command View
    model, relationship declarations, and what deploy-time validation checks.
    This context is essential for diagnosing validation failures in steps 1-2.
 1. Run \`elevasis-sdk check\` (validation)
@@ -1113,18 +1118,18 @@ Each step reports its result. Steps 1-8 run even if step 0 is skipped.
 5. Run \`elevasis-sdk deploy\`
 6. \`docs/project-map.mdx\` is auto-regenerated by deploy (no manual bump needed)
 7. Verify deployment via platform
-8. Update \`memory/deployment-state.md\` with count, timestamp, inventory
+8. Update \`.claude/memory/deployment-state.md\` with count, timestamp, inventory
 9. If git configured and remote exists: optionally push
 
 Each step reports its result. Pipeline stops on failure with suggested fix.
-If validation fails with relationship errors, re-read \`reference/deployment/command-view.mdx\`
+If validation fails with relationship errors, re-read \`reference/deployment/command-center.mdx\`
 for the enforcement model and common fixes.
 
 ### \`/meta health\` -- Execution Debugging
 
 Diagnose runtime failures and environment issues:
 - Show recent executions with status (completed/failed)
-- For failed executions: analyze logs, cross-reference with memory/errors/
+- For failed executions: analyze logs, cross-reference with .claude/memory/errors/
 - Check resource deployment status (deployed, outdated, never deployed)
 - Verify environment: API key valid, credentials accessible, DB connected
 
@@ -1495,7 +1500,6 @@ Your \`ELEVASIS_PLATFORM_KEY\` in \`.env\` determines the organization.
 | --- | --- | --- |
 | \`api-key\` | \`{"apiKey": "sk-..."}\` | Stripe, Resend, Apify, Attio, Instantly |
 | \`webhook-secret\` | \`{"signingSecret": "whsec_..."}\` | Cal.com, Stripe webhooks |
-| \`trello\` | \`{"apiKey": "...", "token": "..."}\` | Trello |
 | \`oauth\` | N/A (browser flow only) | Notion, Google Sheets, Dropbox |
 
 OAuth credentials **cannot** be created via CLI. Redirect the user to the Command Center UI.
@@ -1518,12 +1522,11 @@ elevasis-sdk creds list
 Display the output. Note which are \`oauth\` (not modifiable via CLI).
 
 **\`create\`:** Guided credential creation flow:
-1. Ask credential type (\`api-key\`, \`webhook-secret\`, or \`trello\`). Not \`oauth\`.
+1. Ask credential type (\`api-key\` or \`webhook-secret\`). Not \`oauth\`.
 2. Ask credential name. Validate naming rules before proceeding.
 3. Ask the user to paste the credential value directly in chat.
    - For \`api-key\`: ask for the API key, construct \`{"apiKey": "..."}\`
    - For \`webhook-secret\`: ask for the signing secret, construct \`{"signingSecret": "..."}\`
-   - For \`trello\`: ask for API key AND user token, construct \`{"apiKey": "...", "token": "..."}\`
 4. Pipe to CLI: \`echo '{"apiKey":"..."}' | elevasis-sdk creds create --name {name} --type {type}\`
 5. Confirm success. **NEVER echo the credential value back.**
 

package/dist/types/worker/adapters/index.d.ts

@@ -17,7 +17,6 @@ export { createNotionAdapter } from './notion.js';
 export { createResendAdapter } from './resend.js';
 export { createSignatureApiAdapter } from './signature-api.js';
 export { createStripeAdapter } from './stripe.js';
-export { createTrelloAdapter } from './trello.js';
 export { scheduler } from './scheduler.js';
 export { llm } from './llm.js';
 export { storage } from './storage.js';

package/dist/worker/index.js

@@ -2464,7 +2464,6 @@ You have control over session memory. Use memoryOps to manage critical informati
 **IMPORTANT - System-Managed Memory:**
 Do NOT update these keys via memoryOps (managed automatically by tools/actions):
 - notion-pages-cache (managed by Notion tools)
-- trello-boards-cache (managed by Trello tools)
 - knowledge-map-state (managed by navigate-knowledge)
 
 Attempting to update system-managed keys will be rejected. Use tools to update their caches.
@@ -2877,6 +2876,14 @@ var AgentCancellationError = class extends ExecutionError {
     super(message, context);
   }
 };
+var AgentStalledError = class extends ExecutionError {
+  type = "agent_stalled_error";
+  severity = "critical";
+  category = "agent";
+  constructor(message, context) {
+    super(message, context);
+  }
+};
 var AgentMemoryValidationError = class extends ExecutionError {
   type = "agent_memory_validation_error";
   severity = "info";
@@ -3142,10 +3149,8 @@ var MEMORY_DOMAINS = {
     // Notion tools manage page hierarchy
     "github-repo-cache",
     // GitHub tools manage repository structure
-    "slack-channel-cache",
+    "slack-channel-cache"
     // Slack tools manage channel data
-    "trello-boards-cache"
-    // Trello tools manage boards/lists/cards
   ],
   /**
    * Action-owned keys
@@ -3972,9 +3977,7 @@ async function reloadKnowledgeMapTools(knowledgeMap, memory, context) {
 function initializeKnowledgeMap(knowledgeMap) {
   if (!knowledgeMap) return void 0;
   return {
-    nodes: Object.fromEntries(
-      Object.entries(knowledgeMap.nodes).map(([id, node]) => [id, { ...node }])
-    )
+    nodes: Object.fromEntries(Object.entries(knowledgeMap.nodes).map(([id, node]) => [id, { ...node }]))
   };
 }
 var Agent = class {
@@ -4213,13 +4216,20 @@ var Agent = class {
     while (iteration <= maxIterations) {
       if (context.signal?.aborted) {
         if (context.signal.reason === "timeout") {
-          throw new AgentTimeoutError(
-            `Agent execution exceeded timeout (${this.config.constraints?.timeout}ms)`,
-            { timeout: this.config.constraints?.timeout ?? 0, iteration }
-          );
+          throw new AgentTimeoutError(`Agent execution exceeded timeout (${this.config.constraints?.timeout}ms)`, {
+            timeout: this.config.constraints?.timeout ?? 0,
+            iteration
+          });
+        }
+        if (context.signal.reason === "stalled") {
+          throw new AgentStalledError("Execution stalled: no heartbeat received within threshold", { iteration });
         }
         throw new AgentCancellationError("Execution cancelled by user", { iteration });
       }
+      try {
+        await context.onHeartbeat?.();
+      } catch {
+      }
       const result = await this.runIteration(iteration, context);
       if (result.shouldComplete) {
         return;
@@ -4372,14 +4382,11 @@ var Agent = class {
       const finalOutput = this.contract.outputSchema.parse(retryOutput);
       return { output: finalOutput, attempts: 2 };
     } catch (error) {
-      throw new AgentOutputValidationError(
-        "Agent output validation failed after retry",
-        {
-          agentId: this.config.resourceId,
-          attempts: 2,
-          zodError: error instanceof ZodError ? error.format() : error
-        }
-      );
+      throw new AgentOutputValidationError("Agent output validation failed after retry", {
+        agentId: this.config.resourceId,
+        attempts: 2,
+        zodError: error instanceof ZodError ? error.format() : error
+      });
     }
   }
   /**
@@ -4397,12 +4404,17 @@ var Agent = class {
     try {
       this.logger.action(actionType, `${actionType} started`, 0, generationStartTime, generationStartTime, 0);
       const attempt = actionType === "output-generation" ? 1 : 2;
-      const adapter = this.adapterFactory(this.modelConfig, this.executionContext?.aiUsageCollector, "agent-completion", {
-        type: "agent-completion",
-        attempt,
-        sessionId: this.executionContext?.sessionId,
-        turnNumber: this.executionContext?.sessionTurnNumber
-      });
+      const adapter = this.adapterFactory(
+        this.modelConfig,
+        this.executionContext?.aiUsageCollector,
+        "agent-completion",
+        {
+          type: "agent-completion",
+          attempt,
+          sessionId: this.executionContext?.sessionId,
+          turnNumber: this.executionContext?.sessionTurnNumber
+        }
+      );
       const structuredOutput = await callLLMForAgentCompletion(adapter, {
         systemPrompt,
         memoryContext: this.memoryManager.toContext(this.iterationNumber, this.executionContext?.sessionTurnNumber),
@@ -4885,23 +4897,6 @@ function createStripeAdapter(credential) {
   return createAdapter("stripe", METHODS11, credential);
 }
 
-// src/worker/adapters/trello.ts
-var METHODS12 = [
-  "getBoard",
-  "getLists",
-  "getCards",
-  "createCard",
-  "updateCard",
-  "createList",
-  "createChecklist",
-  "addChecklistItem",
-  "updateChecklistItem",
-  "getCardChecklists"
-];
-function createTrelloAdapter(credential) {
-  return createAdapter("trello", METHODS12, credential);
-}
-
 // src/worker/adapters/scheduler.ts
 var scheduler = createAdapter("scheduler", [
   "createSchedule",
@@ -5150,19 +5145,12 @@ function buildWorkerExecutionContext(params) {
   };
 }
 function startWorker(org) {
-  const workflows = new Map(
-    (org.workflows ?? []).map((w) => [w.config.resourceId, w])
-  );
-  const agents = new Map(
-    (org.agents ?? []).map((a) => [a.config.resourceId, a])
-  );
+  const workflows = new Map((org.workflows ?? []).map((w) => [w.config.resourceId, w]));
+  const agents = new Map((org.agents ?? []).map((a) => [a.config.resourceId, a]));
   let localAbortController = new AbortController();
   console.log(`[SDK-WORKER] Worker started with ${workflows.size} workflow(s), ${agents.size} agent(s)`);
   parentPort.on("message", async (msg) => {
     if (msg.type === "manifest") {
-      const workflowList = (org.workflows ?? []).map((w) => w.config.resourceId);
-      const agentList = (org.agents ?? []).map((a) => a.config.resourceId);
-      console.log(`[SDK-WORKER] Manifest requested: workflows=[${workflowList.join(", ")}], agents=[${agentList.join(", ")}]`);
       parentPort.postMessage({
         type: "manifest",
         workflows: (org.workflows ?? []).map((w) => ({
@@ -5244,7 +5232,13 @@ function startWorker(org) {
         } catch (err) {
           const durationMs = Date.now() - startTime;
           console.error(`[SDK-WORKER] Workflow '${resourceId}' failed (${durationMs}ms): ${String(err)}`);
-          parentPort.postMessage({ type: "result", status: "failed", error: String(err), logs: [], metrics: { durationMs } });
+          parentPort.postMessage({
+            type: "result",
+            status: "failed",
+            error: String(err),
+            logs: [],
+            metrics: { durationMs }
+          });
         }
         return;
       }
@@ -5321,4 +5315,4 @@ function startWorker(org) {
   });
 }
 
-export { PlatformToolError, approval, createAdapter, createApifyAdapter, createAttioAdapter, createDropboxAdapter, createGmailAdapter, createGoogleSheetsAdapter, createInstantlyAdapter, createMailsoAdapter, createNotionAdapter, createResendAdapter, createSignatureApiAdapter, createStripeAdapter, createTrelloAdapter, email, execution, lead, llm, notifications, pdf, platform, scheduler, startWorker, storage };
+export { PlatformToolError, approval, createAdapter, createApifyAdapter, createAttioAdapter, createDropboxAdapter, createGmailAdapter, createGoogleSheetsAdapter, createInstantlyAdapter, createMailsoAdapter, createNotionAdapter, createResendAdapter, createSignatureApiAdapter, createStripeAdapter, email, execution, lead, llm, notifications, pdf, platform, scheduler, startWorker, storage };

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@elevasis/sdk",
-  "version": "0.5.12",
+  "version": "0.5.14",
   "description": "SDK for building Elevasis organization resources",
   "type": "module",
   "bin": {

package/reference/_navigation.md

@@ -1,6 +1,6 @@
 # SDK Reference Navigation
 
-Auto-generated from reference file frontmatter. 32 files indexed.
+Auto-generated from reference file frontmatter. 28 files indexed.
 
 All paths are relative to `node_modules/@elevasis/sdk/reference/`.
 
@@ -8,58 +8,39 @@ All paths are relative to `node_modules/@elevasis/sdk/reference/`.
 
 | Resource | Location | Description | When to Load |
 | --- | --- | --- | --- |
+| CLI Reference | `cli.mdx` | Full reference for every elevasis-sdk CLI command -- scaffold, validate, deploy, execute, and inspect resources | Running CLI operations |
+| Concepts Reference | `concepts.mdx` | Plain-English explanations of Elevasis SDK concepts -- glossary, workflow analogies, Zod schemas, execution model, platform tools, common errors, and design decisions | User asks what is or needs conceptual grounding |
+| Getting Started | `getting-started.mdx` | Install the Elevasis SDK, scaffold a project, and run your first deployment | Setting up a new project or onboarding |
 | Elevasis SDK | `index.mdx` | Build and deploy workflows, agents, and resources with the Elevasis SDK | First session or new to the SDK |
-
-## Cli
-
-| Resource | Location | Description | When to Load |
-| --- | --- | --- | --- |
-| CLI Reference | `cli/index.mdx` | Full reference for every elevasis-sdk CLI command -- scaffold, validate, deploy, execute, and inspect resources | Running CLI operations |
-
-## Concepts
-
-| Resource | Location | Description | When to Load |
-| --- | --- | --- | --- |
-| Concepts Reference | `concepts/index.mdx` | Plain-English explanations of Elevasis SDK concepts -- glossary, workflow analogies, Zod schemas, execution model, platform tools, common errors, and design decisions | User asks what is or needs conceptual grounding |
+| Roadmap | `roadmap.mdx` | Planned SDK features -- error taxonomy, retry semantics, circuit breaker, metrics, alerting, and resource lifecycle extensions | Asking about future features or planned capabilities |
+| Execution Runtime | `runtime.mdx` | How your code runs on the Elevasis platform -- execution lifecycle, concurrency, timeouts, cancellation, error handling, observability, resource limits, and v1 limitations | Debugging execution behavior or understanding the runtime model |
+| Common Errors | `troubleshooting.mdx` | Static SDK-level error catalog -- CLI errors, deployment errors, schema validation, platform tool failures, and runtime errors with diagnostic steps | Debugging an unknown error not found in workspace memory |
 
 ## Deployment
 
 | Resource | Location | Description | When to Load |
 | --- | --- | --- | --- |
 | Execution API | `deployment/api.mdx` | REST endpoints for executing resources, querying execution history, and managing deployments via the Elevasis external API | Calling the API directly or debugging API responses |
-| Command Center UI | `deployment/command-center-ui.mdx` | Reference for the Elevasis Command Center -- what each page does, when to use it post-deployment, and how SDK concepts map to UI actions | User asks about the Command Center UI, post-deployment workflow, or monitoring deployed resources |
-| Command View | `deployment/command-view.mdx` | How the Command View graph works -- node types, relationships, what is enforced vs decorative, and what the platform needs to render your resource graph | Deploying resources or building resources that invoke other resources |
+| Command Center | `deployment/command-center.mdx` | Post-deployment UI reference -- what each page does, the resource graph model, relationships, validation, and how SDK concepts map to Command Center actions | User asks about the Command Center UI, post-deployment workflow, monitoring, or the resource graph |
 | Deploying Resources | `deployment/index.mdx` | How to deploy your Elevasis SDK resources to the platform using elevasis-sdk deploy, including configuration, validation, and environment setup | Preparing to deploy or debugging deploy failures |
 
-## Developer
-
-| Resource | Location | Description | When to Load |
-| --- | --- | --- | --- |
-| Interaction Guidance | `developer/interaction-guidance.mdx` | Full dimensional adaptation rules per skill axis -- platform navigation, API integration, automation concepts, domain expertise -- with growth tracking protocol | Unsure how to adapt for a skill combination |
-
 ## Framework
 
 | Resource | Location | Description | When to Load |
 | --- | --- | --- | --- |
 | Agent System | `framework/agent.mdx` | CLAUDE.md drives all agent behavior -- project instructions, slash commands, memory-based developer profile, and three-tier adaptive guidance | Configuring agent behavior or capabilities |
-| Resource Documentation | `framework/documentation.mdx` | Write and deploy MDX documentation alongside your Elevasis resources | Writing or updating project documentation |
-| Development Framework | `framework/index.mdx` | The SDK scaffolds a complete development environment for Claude Code -- project instructions, slash commands, cross-session memory, and template versioning | Understanding the agent framework structure |
+| Development Framework | `framework/index.mdx` | The SDK scaffolds a complete development environment for Claude Code -- project instructions, slash commands, cross-session memory, template versioning, and resource documentation | Understanding the agent framework structure |
+| Interaction Guidance | `framework/interaction-guidance.mdx` | Full dimensional adaptation rules per skill axis -- platform navigation, API integration, automation concepts, domain expertise -- with growth tracking protocol | Unsure how to adapt for a skill combination |
 | Memory System | `framework/memory.mdx` | Cross-session project knowledge stored in .claude/memory/ -- deployment state, environment, decisions, and error patterns that persist between Claude Code sessions | Working with agent memory or session state |
 | Project Structure | `framework/project-structure.mdx` | Each file scaffolded by elevasis-sdk init and its purpose in the development workflow | Understanding scaffolded files or project layout |
-
-## Getting-started
-
-| Resource | Location | Description | When to Load |
-| --- | --- | --- | --- |
-| Getting Started | `getting-started/index.mdx` | Install the Elevasis SDK, scaffold a project, and run your first deployment | Setting up a new project or onboarding |
+| Tutorial System | `framework/tutorial-system.mdx` | Reference for the SDK tutorial system -- 21-item menu across 4 sections, skill-level adaptation rules, progress tracking format, and per-lesson module contents | (not specified) |
 
 ## Platform-tools
 
 | Resource | Location | Description | When to Load |
 | --- | --- | --- | --- |
-| Typed Adapters | `platform-tools/adapters.mdx` | Type-safe wrappers over platform.call() for all integrations and platform tools -- Attio, Stripe, Notion, Google Sheets, Trello, and more -- with full autocomplete, compile-time checking, and zero boilerplate | Using typed adapters instead of raw platform.call(), or needs to know what adapter methods are available |
-| Integration Examples | `platform-tools/examples.mdx` | Working code examples for email, CRM, PDF, LLM inference, resource triggering, and storage using typed adapters and platform.call() | Implementing a platform tool call in a workflow step |
-| Platform Tools | `platform-tools/index.mdx` | Access 70+ tools across integration adapters and platform services from your SDK workflows -- typed adapters with full autocomplete for all tools, plus platform.call() as a fallback | Connecting to external services |
+| Typed Adapters | `platform-tools/adapters.mdx` | Type-safe wrappers over platform.call() for all integrations and platform tools -- Attio, Stripe, Notion, Google Sheets, and more -- with full autocomplete, compile-time checking, and zero boilerplate | Using typed adapters instead of raw platform.call(), or needs to know what adapter methods are available |
+| Platform Tools | `platform-tools/index.mdx` | Access 70+ tools across integration adapters and platform services from your SDK workflows -- typed adapters, credential security model, and working code examples | Connecting to external services |
 
 ## Resources
 
@@ -69,25 +50,6 @@ All paths are relative to `node_modules/@elevasis/sdk/reference/`.
 | Common Patterns | `resources/patterns.mdx` | Common resource patterns for Elevasis SDK developers -- sequential steps, conditional branching, platform tools, error handling, and resource status management | Building or modifying a workflow |
 | SDK Types | `resources/types.mdx` | Complete type reference for @elevasis/sdk -- package exports, re-exported platform types, ElevasConfig interface, StepHandler context, and runtime values | Looking up type signatures or SDK exports |
 
-## Roadmap
-
-| Resource | Location | Description | When to Load |
-| --- | --- | --- | --- |
-| Roadmap | `roadmap/index.mdx` | Planned SDK features -- error taxonomy, retry semantics, circuit breaker, metrics, alerting, and resource lifecycle extensions | Asking about future features or planned capabilities |
-
-## Runtime
-
-| Resource | Location | Description | When to Load |
-| --- | --- | --- | --- |
-| Execution Runtime | `runtime/index.mdx` | How your code runs on the Elevasis platform -- execution lifecycle, concurrency, timeouts, cancellation, error handling, and observability | Debugging execution behavior or understanding the runtime model |
-| Resource Limits & Quotas | `runtime/limits.mdx` | Memory limits, execution timeouts, scale quotas, networking constraints, and v1 platform limitations for SDK resources | Hitting resource limits or planning for scale |
-
-## Security
-
-| Resource | Location | Description | When to Load |
-| --- | --- | --- | --- |
-| Credential Security | `security/credentials.mdx` | Three-layer credential model: platform tools (server-side injection), http tool (arbitrary APIs), getCredential() (explicit opt-in raw access) -- .env scope and security boundaries | Setting up integrations or configuring tool access |
-
 ## Templates
 
 | Resource | Location | Description | When to Load |
@@ -99,9 +61,3 @@ All paths are relative to `node_modules/@elevasis/sdk/reference/`.
 | Template: Recurring Job | `templates/recurring-job.mdx` | Scheduler-triggered periodic workflow -- run a task on a schedule (daily, weekly, hourly, or custom cron) | Applying the recurring-job workflow template |
 | Template: Text Classifier | `templates/text-classifier.mdx` | Multi-label text classification with structured output -- classify text into predefined categories using an LLM with JSON output | Applying the text-classifier workflow template |
 | Template: Web Scraper | `templates/web-scraper.mdx` | Apify-based web scraper that stores results in Supabase -- fetch structured data from any website via Apify actors | Applying the web-scraper workflow template |
-
-## Troubleshooting
-
-| Resource | Location | Description | When to Load |
-| --- | --- | --- | --- |
-| Common Errors | `troubleshooting/common-errors.mdx` | Static SDK-level error catalog -- CLI errors, deployment errors, schema validation, platform tool failures, and runtime errors with diagnostic steps | Debugging an unknown error not found in workspace memory |