chore: add Pullfrog workflow file

[pullfrog]

This PR adds the .github/workflows/pullfrog.yml workflow file to enable Pullfrog agent runs in this repository.

Once merged, return to the Pullfrog console and click Verify workflow to finish setup.

[github-actions]

Benchmark Comparison

Cross-comparison of workflow performance across World implementations.

workflow with no steps

World	Workflow Time	Wall Time	Overhead	vs Fastest
🥇 💾 Starter (in-memory)	0.015s	1.005s	0.991s	1.00x
🔴 Redis	0.023s	1.011s	0.988s	1.56x
💻 Local	0.029s	1.008s	0.979s	2.00x
🍃 MongoDB	0.067s	1.009s	0.942s	4.58x
🗄️ Turso	0.109s	1.012s	0.902s	7.47x

workflow with 1 step

World	Workflow Time	Wall Time	Overhead	vs Fastest
🥇 💾 Starter (in-memory)	0.044s	1.004s	0.960s	1.00x
🔴 Redis	0.063s	1.009s	0.946s	1.44x
💻 Local	0.089s	1.007s	0.918s	2.03x
🗄️ Turso	0.244s	1.011s	0.767s	5.54x
🍃 MongoDB	0.282s	1.008s	0.727s	6.39x

workflow with 10 sequential steps

World	Workflow Time	Wall Time	Overhead	vs Fastest
🥇 💾 Starter (in-memory)	0.339s	1.003s	0.664s	1.00x
🔴 Redis	0.472s	1.009s	0.536s	1.39x
💻 Local	0.678s	1.007s	0.329s	2.00x
🗄️ Turso	2.114s	3.013s	0.899s	6.24x
🍃 MongoDB	2.117s	3.011s	0.893s	6.25x

workflow with 10 parallel steps

World	Workflow Time	Wall Time	Overhead	vs Fastest
🥇 💾 Starter (in-memory)	0.136s	1.003s	0.867s	1.00x
🔴 Redis	0.188s	1.008s	0.820s	1.38x
💻 Local	0.297s	1.006s	0.710s	2.18x
🗄️ Turso	1.570s	2.011s	0.441s	11.54x
🍃 MongoDB	1.572s	2.008s	0.435s	11.56x

---

Stream Benchmarks

Stream benchmarks include Time to First Byte (TTFB) metrics.

workflow with stream

World	Workflow Time	TTFB	Wall Time	Overhead	vs Fastest
🥇 💾 Starter (in-memory)	0.073s	1.002s	1.004s	0.931s	1.00x
🔴 Redis	0.103s	1.003s	1.008s	0.905s	1.41x
💻 Local	0.144s	0.992s	1.010s	0.866s	1.98x
🍃 MongoDB	0.463s	0.966s	1.008s	0.545s	6.36x
🗄️ Turso	0.473s	0.955s	1.011s	0.538s	6.50x

---

Summary: Average Performance by World

World	Avg Workflow Time	Benchmarks
💾 Starter (in-memory)	0.121s	5
🔴 Redis	0.170s	5
💻 Local	0.247s	5
🍃 MongoDB	0.900s	5
🗄️ Turso	0.902s	5

Column Definitions

• Workflow Time: Runtime reported by workflow (completedAt - createdAt) - primary metric
• TTFB: Time to First Byte - time from workflow start until first stream byte received (stream benchmarks only)
• Wall Time: Total testbench time (trigger workflow + poll for result)
• Overhead: Testbench overhead (Wall Time - Workflow Time)
• vs Fastest: How much slower compared to the fastest World for this benchmark

Worlds:

• 💻 Local: Built-in workflow world
• 🐘 Postgres: PostgreSQL database world
• ▲ Vercel: Vercel production world
• 💾 Starter: In-memory reference implementation
• 🍃 MongoDB: MongoDB database world
• 🔴 Redis: Redis/BullMQ backend

[github-actions]

E2E Test Results

E2E jobs failed before producing test results. View workflow run