@hue-run/sdk 0.15.0 → 0.15.2

package/CLI.md

@@ -42,7 +42,7 @@ project manifest are refused because managers can update ancestor locks; Python
 The generated `hue.setup.mjs` or `hue_setup.py` always selects `captureContent: false` /
 `capture_content=False`. For a supported application, setup installs the dependency and adds the
 managed import and middleware registration to the existing entrypoint; an unreferenced helper is
-not a completed integration. TypeScript uses `@hue-run/sdk@0.15.0`, `@opentelemetry/api@1.9.1` and
+not a completed integration. TypeScript uses `@hue-run/sdk@0.15.2`, `@opentelemetry/api@1.9.1` and
 `@opentelemetry/context-async-hooks@2.11.0`; Python setup uses its separately tested package pin.
 Content capture requires an ordinary account-managed key and a later explicit application decision.
 
@@ -469,7 +469,7 @@ node packages/sdk-typescript/scripts/verify-package.mjs --artifacts-dir .artifac
 # Set project to an existing supported fixture; use the same directory on resume.
 project=/absolute/path/to/supported-fixture
 node packages/sdk-typescript/scripts/verify-setup-live.mjs \
-  --archive .artifacts/typescript/hue-run-sdk-0.15.0.tgz \
+  --archive .artifacts/typescript/hue-run-sdk-0.15.2.tgz \
   --origin https://STAGING_ORIGIN \
   --project "$project" --command setup \
   --evidence .context/setup-staging-before-claim.json
@@ -480,7 +480,7 @@ the private local handoff and finish the real browser claim, then reconcile the
 
 ```sh
 node packages/sdk-typescript/scripts/verify-setup-live.mjs \
-  --archive .artifacts/typescript/hue-run-sdk-0.15.0.tgz \
+  --archive .artifacts/typescript/hue-run-sdk-0.15.2.tgz \
   --origin https://STAGING_ORIGIN \
   --project "$project" --command claim \
   --evidence .context/setup-staging-after-claim.json
@@ -523,10 +523,10 @@ production agent lacks. Pin the SDK and bring its `zod` peer along, so the agent
 gains no dependency:
 
 ```sh
-npx --yes --package @hue-run/sdk@0.15.0 --package "zod@^4.6.5" hue eval --case "Refund an eligible charge" --command "node agent.js" --env-file .env.hue
-npx --yes --package @hue-run/sdk@0.15.0 --package "zod@^4.6.5" hue eval --case https://app.hue.run/projects/demo/scenarios/<id> --command "python agent.py" --timeout 120 --baseline <experiment id>
-npx --yes --package @hue-run/sdk@0.15.0 --package "zod@^4.6.5" hue eval --set "Billing regressions" --scorer-version <id> --command "node agent.js" --save-version
-npx --yes --package @hue-run/sdk@0.15.0 --package "zod@^4.6.5" hue eval --worker --command "node agent.js" --agent-key support-agent --revision <new-agent-revision> --env-file .env.hue
+npx --yes --package @hue-run/sdk@0.15.2 --package "zod@^4.6.5" hue eval --case "Refund an eligible charge" --command "node agent.js" --env-file .env.hue
+npx --yes --package @hue-run/sdk@0.15.2 --package "zod@^4.6.5" hue eval --case https://app.hue.run/projects/demo/scenarios/<id> --command "python agent.py" --timeout 120 --baseline <experiment id>
+npx --yes --package @hue-run/sdk@0.15.2 --package "zod@^4.6.5" hue eval --set "Billing regressions" --scorer-version <id> --command "node agent.js" --save-version
+npx --yes --package @hue-run/sdk@0.15.2 --package "zod@^4.6.5" hue eval --worker --command "node agent.js" --agent-key support-agent --revision <new-agent-revision> --env-file .env.hue
 ```
 
 Without the second `--package`, `hue eval` exits with `hue eval needs zod`, even for `--help`;
@@ -562,7 +562,7 @@ export default function runMyAgent(inputs: JsonValue, context: SimulationTargetC
 ```
 
 ```sh
-npx --yes --package @hue-run/sdk@0.15.0 --package "zod@^4.6.5" hue eval --case "Refund an eligible charge" ./hue-agent.ts --content --env-file .env.hue
+npx --yes --package @hue-run/sdk@0.15.2 --package "zod@^4.6.5" hue eval --case "Refund an eligible charge" ./hue-agent.ts --content --env-file .env.hue
 ```
 
 `--scenario` remains an alias for `--case` for existing scripts. Pass one selection flag.

package/EVALUATIONS.md

@@ -164,7 +164,7 @@ A callback receives `{inputs,hasOutput,output?,hasExpected,expected?,metadata,ex
 - `{state:"error",error:{type,message?}}`.
 - `{state:"skipped",explanation:"reason"}`.
 
-All declared metrics must appear exactly once and satisfy pinned types, bounds and categories. Each metric may include an optional `description` (1–500 characters) shown with its check in Hue's run view. The binding must match language, entrypoint, SHA-256 source digest and metric definitions. The digest is an authenticated caller declaration; it does not attest closures, dependency versions or actual execution. Callback source is never downloaded or evaluated. Callbacks are trusted local code; they have **no execution timeout or side-effect cancellation**. Concurrency limits active cases to 1–16 (default 1), with scorers evaluated sequentially within each case.
+All declared metrics must appear exactly once and satisfy pinned types, bounds and categories. Each metric may include an optional `description` (1–500 characters) shown with its check in Hue's run view. The binding must match language, entrypoint, SHA-256 source digest and metric definitions. The digest is an authenticated caller declaration; it does not attest closures, dependency versions or actual execution. Callback source is never downloaded or evaluated. Callbacks are trusted local code; they have **no execution timeout or side-effect cancellation**. Concurrency limits active cases to 1–100 (default 1), with scorers evaluated sequentially within each case.
 
 `files` is present only when the runner handled files for that execution: every pinned input file
 (all roles, including the evaluator-only `org_template`) and every generated output, each with its

package/README.md

@@ -491,8 +491,8 @@ const hue = createHue({
 
 ## Delivery behavior
 
-Exports retry temporary HTTP/network failures (429, 502, 503, 504 and connection errors,
-honoring `Retry-After`) within the export timeout, by OpenTelemetry's OTLP/HTTP exporter rules. A
+Exports retry temporary HTTP/network failures (429, 500, 502, 503, 504 and connection errors,
+honoring `Retry-After`) within the export timeout. A
 429 whose `Retry-After` outlasts the export timeout keeps its records queued, within the queue's
 bounds, and sends them again once the wait has passed; an export holds its records this way for at
 most 60 seconds in all, and a longer wait loses them, reported as a `failed` issue with status 429.

package/dist/cli/eval.js

@@ -85,7 +85,7 @@ Output and limits:
                                   --content the case span still carries the output
   --save-version                  Freeze an unsaved eval-set version before running
   --checkpoint-dir <path>         Private checkpoint directory (default: .hue/eval/<agent-key>)
-  --concurrency <n>               Cases in flight, 1-64 (default: 1)
+  --concurrency <n>               Cases in flight, 1-100 (default: 1)
   --trace-not-accepted <policy>   A case whose telemetry Hue did not accept in time: fail_case
                                   (default) completes it as failed with the evidence omitted;
                                   pending completes it in its true state with the trace still to
@@ -1093,7 +1093,7 @@ function parseBaseline(value) {
 }
 async function runOnce(values, connection, agents, agent, hue, output, signal) {
     const client = new EvaluationClient(connection);
-    const concurrency = integer("concurrency", values.concurrency, 1, 1, 64);
+    const concurrency = integer("concurrency", values.concurrency, 1, 1, 100);
     const baselineId = parseBaseline(values.baseline);
     const mode = parseMode(values.mode);
     const pins = await resolveSelection(client, values);
@@ -1296,7 +1296,7 @@ async function runWorker(values, connection, agents, agent, hue, output, signal)
     const client = new ObservedClient(connection);
     const environmentClient = createEnvironmentClient(connection);
     const wait = integer("wait", values.wait, 300, 0, 86_400);
-    const concurrency = integer("concurrency", values.concurrency, 1, 1, 64);
+    const concurrency = integer("concurrency", values.concurrency, 1, 1, 100);
     const maxRuns = values["max-runs"] === undefined
         ? undefined
         : integer("max-runs", values["max-runs"], 1, 1, 1_000_000);

package/dist/evals/local-worker.d.ts

@@ -100,7 +100,7 @@ export interface RunLocalAgentOptions {
     agent: LocalAgentRegistration;
     /** Local scorer bindings matching the published source digests. */
     scorers?: LocalScorer[];
-    /** Cases in flight, between 1 and 16; defaults to 1. */
+    /** Cases in flight, between 1 and 100; defaults to 1. */
     concurrency?: number;
     /** What a case does when its telemetry is not accepted; see
      * `traceNotAccepted` of {@link runExperiment}. Defaults to `"stop"`. */

package/dist/evals/runner.d.ts

@@ -74,7 +74,7 @@ interface RunnerOptions {
      * (for example a Hue-operated grading worker that owns the evaluator source) instead of
      * refusing the run. Their IDs are reported in `deferredScorerVersionIds`. */
     deferUnboundLocalScorers?: boolean;
-    /** Cases in flight at once, 1–64. Default 1. */
+    /** Cases in flight at once, 1–100. Default 1. */
     concurrency?: number;
     /** Deadline for JSON Schema scoring in its worker, 100–60000 ms. Default 2000. */
     schemaTimeoutMillis?: number;

package/dist/evals/runner.js

@@ -183,8 +183,8 @@ function settings(options) {
     if (typeof options.persistResultContent !== "boolean")
         throw new TypeError("Choose persistResultContent explicitly: true or false");
     const concurrency = options.concurrency ?? 1;
-    if (!Number.isInteger(concurrency) || concurrency < 1 || concurrency > 64)
-        throw new RangeError("concurrency must be 1–64");
+    if (!Number.isInteger(concurrency) || concurrency < 1 || concurrency > 100)
+        throw new RangeError("concurrency must be 1–100");
     const timeout = options.schemaTimeoutMillis ?? 2000;
     if (!Number.isInteger(timeout) || timeout < 100 || timeout > 60_000)
         throw new RangeError("schemaTimeoutMillis must be 100–60000");

package/dist/evals/simulation.d.ts

@@ -166,7 +166,7 @@ export interface RunSimulationOptions {
     onTelemetryNotAccepted?(entry: TelemetryNotAccepted): void | Promise<void>;
     /** Local scorer callbacks bound by their declared source digests. */
     localScorers?: LocalScorer[];
-    /** Cases in flight, 1–64; defaults to 1. */
+    /** Cases in flight, 1–100; defaults to 1. */
     concurrency?: number;
     /** JSON Schema worker deadline in milliseconds. */
     schemaTimeoutMillis?: number;

package/dist/transport.js

@@ -1326,7 +1326,8 @@ const MAX_BACKOFF_MILLIS = 5000;
 const BACKOFF_MULTIPLIER = 1.5;
 const JITTER = 0.2;
 const MAX_RESPONSE_BYTES = 4 * 1024 * 1024;
-const RETRYABLE_STATUS = new Set([429, 502, 503, 504]);
+// Hue also retries transient collector HTTP 500 responses within the same attempt/deadline budget.
+const RETRYABLE_STATUS = new Set([429, 500, 502, 503, 504]);
 const RETRYABLE_NETWORK_ERRORS = new Set([
     "ECONNRESET",
     "ECONNREFUSED",

package/dist/version.d.ts

@@ -1,2 +1,2 @@
 /** Package version shared by the instrumentation scope and the export User-Agent. */
-export declare const sdkVersion = "0.15.0";
+export declare const sdkVersion = "0.15.2";

package/dist/version.js

@@ -1,3 +1,3 @@
 // Generated by scripts/write-version.mjs from package.json; do not edit by hand.
 /** Package version shared by the instrumentation scope and the export User-Agent. */
-export const sdkVersion = "0.15.0";
+export const sdkVersion = "0.15.2";

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@hue-run/sdk",
-  "version": "0.15.0",
+  "version": "0.15.2",
   "private": false,
   "license": "MIT",
   "publishConfig": {