@poncho-ai/sdk 1.12.0 → 1.14.0

package/.turbo/turbo-build.log

@@ -1,5 +1,5 @@
 
-> @poncho-ai/sdk@1.12.0 build /home/runner/work/poncho-ai/poncho-ai/packages/sdk
+> @poncho-ai/sdk@1.14.0 build /home/runner/work/poncho-ai/poncho-ai/packages/sdk
 > tsup src/index.ts --format esm --dts
 
 CLI Building entry: src/index.ts
@@ -10,5 +10,5 @@
 ESM dist/index.js 17.24 KB
 ESM ⚡️ Build success in 20ms
 DTS Build start
-DTS ⚡️ Build success in 1257ms
-DTS dist/index.d.ts 29.41 KB
+DTS ⚡️ Build success in 1320ms
+DTS dist/index.d.ts 30.03 KB

package/CHANGELOG.md

@@ -1,5 +1,23 @@
 # @poncho-ai/sdk
 
+## 1.14.0
+
+### Minor Changes
+
+- [`d8453b4`](https://github.com/cesr/poncho-ai/commit/d8453b4f2360a1734e448960fe52f6c450cdf842) Thanks [@cesr](https://github.com/cesr)! - harness: propagate `suppressTelemetry` to subagents.
+
+  A telemetry-off run (e.g. incognito) now suppresses telemetry for the subagents it spawns too, not just the parent turn. The parent run's `suppressTelemetry` is exposed on `ToolContext`, captured by `spawn_subagent` into the new `SubagentManager.spawn({ suppressTelemetry })` option, stored on the subagent conversation's `subagentMeta`, and read back by the orchestrator's `runSubagent` / continuation so the child run (and its re-runs) emit no `invoke_agent` / `execute_tool` / AI-SDK spans.
+
+## 1.13.0
+
+### Minor Changes
+
+- [`773f113`](https://github.com/cesr/poncho-ai/commit/773f11309e2410d6c5e17af0fde17425953105f2) Thanks [@cesr](https://github.com/cesr)! - harness: add a per-run `suppressTelemetry` flag so one harness can serve both telemetry-on and telemetry-off runs.
+
+  Telemetry was effectively an instance-level property: whether the OTLP exporter is attached is decided at construction, so a host that wants telemetry-off runs (e.g. incognito) had to build and maintain a _second_ harness instance with no exporter — duplicating all per-harness provisioning (tool registration, subagent manager, etc.) and risking drift between the two.
+
+  `RunInput.suppressTelemetry` lets a single harness — built once, with the exporter attached — emit nothing for a given run: the `invoke_agent` root span, the `execute_tool` spans, and the AI-SDK spans are all gated on `!input.suppressTelemetry`. Hosts can now keep one harness per user and pass `suppressTelemetry: true` per run instead of routing to a parallel exporter-less instance.
+
 ## 1.12.0
 
 ### Minor Changes

package/dist/index.d.ts

@@ -715,6 +715,10 @@ interface ToolContext {
     conversationId?: string;
     /** The tenant ID when running in multi-tenant mode. */
     tenantId?: string;
+    /** Telemetry is suppressed for this run (e.g. an incognito turn). Tools
+     *  that spawn further runs (subagents) propagate this so the child run
+     *  emits no telemetry either. */
+    suppressTelemetry?: boolean;
     /** Virtual filesystem scoped to the current tenant. Available when VFS is enabled. */
     vfs?: VfsAccess;
 }
@@ -756,6 +760,14 @@ interface RunInput {
     disablePromptCache?: boolean;
     /** Scope this run to a specific tenant. */
     tenantId?: string;
+    /**
+     * When true, emit no telemetry for this run — no `invoke_agent` /
+     * `execute_tool` spans and no AI-SDK spans, even on a harness built with an
+     * OTLP exporter attached. Lets a single harness serve both telemetry-on and
+     * telemetry-off (e.g. incognito) runs, instead of needing a separate
+     * exporter-less harness instance per mode.
+     */
+    suppressTelemetry?: boolean;
 }
 interface TokenUsage {
     input: number;

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@poncho-ai/sdk",
-  "version": "1.12.0",
+  "version": "1.14.0",
   "description": "Core types and utilities for building Poncho skills",
   "repository": {
     "type": "git",

package/src/index.ts

@@ -78,6 +78,10 @@ export interface ToolContext {
   conversationId?: string;
   /** The tenant ID when running in multi-tenant mode. */
   tenantId?: string;
+  /** Telemetry is suppressed for this run (e.g. an incognito turn). Tools
+   *  that spawn further runs (subagents) propagate this so the child run
+   *  emits no telemetry either. */
+  suppressTelemetry?: boolean;
   /** Virtual filesystem scoped to the current tenant. Available when VFS is enabled. */
   vfs?: VfsAccess;
 }
@@ -137,6 +141,14 @@ export interface RunInput {
   disablePromptCache?: boolean;
   /** Scope this run to a specific tenant. */
   tenantId?: string;
+  /**
+   * When true, emit no telemetry for this run — no `invoke_agent` /
+   * `execute_tool` spans and no AI-SDK spans, even on a harness built with an
+   * OTLP exporter attached. Lets a single harness serve both telemetry-on and
+   * telemetry-off (e.g. incognito) runs, instead of needing a separate
+   * exporter-less harness instance per mode.
+   */
+  suppressTelemetry?: boolean;
 }
 
 export interface TokenUsage {