chini-train-train-0065-dp3-infra

Pub-Sub Broker With Replay

moderate infra problem: pub-sub broker with replay

Source: chini-train synth generator v0.1

Prompt

Design a system for: pub-sub broker with replay (domain: SWE backend / infra).

Tier DP3 (moderate). 6-9 nodes, two stress scenarios (spike + one of cascade/outage), realistic criteria. Sweet spot.

Constraints:
- At most 10 components on the canvas.
- Monthly cost ceiling: $498 USD. Required behaviors: storage, queue, circuitbreaker.

Return a Chinilla CanvasState that handles the listed scenarios. Include trigger components for each entry point and at least one terminal storage / sink so the simulator can score delivery.

Constraints

Max components: 10
Required behaviors: storage, queue, circuitbreaker
Monthly budget: $498

Stress scenarios

Baseline traffic

baseline

Steady ambient load with no failures.

Traffic spike

spike

Traffic suddenly multiplies. The hot path must hold.

Adversarial burst

adversarial

Hostile packets injected on top of clean traffic. Defenses must block them without dropping good requests.

Pass criteria (overall)

Min stability score: 65
Max drop rate: 11.7%
Min delivery rate: 79.8%
Max errors: 8

Submit your run

Submissions go through the chini-bench CLI. It calls your model with your key, scores the result locally, and posts to the leaderboard. Nothing leaves your machine except the canvas it produces.

End-to-end:

pip install git+https://github.com/collapseindex/chini-bench-cli.git
export OPENROUTER_API_KEY=...

chini-bench run chini-train-train-0065-dp3-infra \
  --provider openrouter --model google/gemini-2.0-flash-001 \
  --as alice

Or inspect the prompt first:

chini-bench prompt chini-train-train-0065-dp3-infra

Providers: openai · anthropic · google · openrouter · ollama

Leaderboard

Rank	Submitter	Model	Score	Stability	Delivery	Design	Pass
#1	rl_v07_full_a10	rl_policy custom single-shot	87	70.0	91.0	100.0	✗
#2	rl_v07_full_a10	rl_policy custom single-shot	80	63.0	70.0	100.0	✗
#3	chini-train-03	grok-4.1-fast single-shot	78	48.0	83.0	100.0	✗
#4	rl_v07_full_a10	rl_policy custom single-shot	72	52.0	55.0	100.0	✗
#5	rl_v07_full_a10	rl_policy custom single-shot	67	56.0	61.0	75.0	✗

Per-scenario breakdown of the top run

Scenario	Health	Drop rate	Delivered	Pass
baseline	84.0	1.7%	29	✓
spike-1	67.0	13.1%	860	✗
adversarial-2	59.0	67.1%	93	✗

How is this scored? →