Versioning Patching
Temporal · Temporal
Durable Execution & Workflow Orchestration — Temporal
Evaluates Temporal's Versioning & Patching across 6 scenario-based test cases, each graded against an expected-behavior rubric by an LLM judge, from Corsac's Durable Execution & Workflow Orchestration eval coverage.
About Temporal
Temporal is a durable execution platform for orchestrating long-running, fault-tolerant workflows. Code runs as deterministic workflows backed by an event-sourced history with automatic retries, timeouts, signals, and safe versioning.
Sample tests· showing 3 of 6
| # | Input | Expected behavior | Check |
|---|---|---|---|
| 01 | Production OrderWorkflow v2 needs new Activity; in-flight runs on old code path. Agent adds workflow.GetVersion('tax-step', 1, 2) branch. | Agent implements GetVersion default min=max for old behavior, new version runs tax Activity, adds replay test covering both branches. | Pass / FailTool usecritical |
| 02 | Temporal Cloud namespace enables Worker Versioning; new Build ID `checkout-2026-06-04` must receive new tasks without killing in-flight on old build. | Agent registers build via worker deployment APIs, sets compatible versions set, monitors task reachability metrics; tags [REQUIRES-VERIFICATION] on Cloud-only flags. | Pass / FailTool usehigh |
| 03 | Go workflow uses workflow.Patched('legacy-ship') for old path; metrics show zero old branch hits for 30d. | Agent removes deprecated branch using SDK deprecation workflow, confirms replay tests pass, documents min supported server version. | Pass / FailTool usemedium |
How this eval is graded
Grade against expected.ideal_behavior and expected.rubric.
Rubric criteria
- Temporal
- Durable Execution
- Versioning Patching
Recommended for
Works with
Related evals
Browserbase
Evaluates Browserbase's Captcha Handling across scenario-based test cases, each graded against an expected-behavior rubric by an LLM judge, from Corsac's Browser infrastructure eval coverage.
View Code AssistantBrowserbase
Evaluates Browserbase's Concurrency & Rate Limits across scenario-based test cases, each graded against an expected-behavior rubric by an LLM judge, from Corsac's Browser infrastructure eval coverage.
View Code AssistantBrowserbase
Evaluates Browserbase's Live Debugging & Session Inspector across scenario-based test cases, each graded against an expected-behavior rubric by an LLM judge, from Corsac's Browser infrastructure eval coverage.
ViewFrequently asked questions
What does the Versioning Patching eval for Temporal Temporal test?+
Evaluates Temporal's Versioning & Patching across 6 scenario-based test cases, each graded against an expected-behavior rubric by an LLM judge, from Corsac's Durable Execution & Workflow Orchestration eval coverage.
How is the Versioning Patching eval scored?+
The judge rubric: Grade against expected.ideal_behavior and expected.rubric.
How many test cases does this eval pack include?+
The Versioning Patching pack for Temporal Temporal contains 6 test cases. 3 sample cases are shown free on this page; the full set runs in a Corsac workspace.
How do I run this eval?+
Sign up for Corsac, connect your model or agent endpoint, and run the Versioning Patching pack as-is or after customizing thresholds. Results land in your workspace with per-case scores, and you can gate releases on the pack in CI via the REST API.
Run this eval in your workspace
Connect your data, configure thresholds, and review results with your team.