chini-train-train-0347-dp4-personal

Side-Project Momentum Across Weekends

hard personal problem: side-project momentum across weekends

Source: chini-train synth generator v0.1

Prompt

Design a system for: side-project momentum across weekends (domain: personal systems / habits).

Tier DP4 (hard). 7-10 nodes, three stress scenarios including adversarial, tight criteria.

Constraints:
- At most 11 components on the canvas.
- Monthly cost ceiling: $366 USD. Required behaviors: queue, circuitbreaker, retry, ratelimit.

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: 11
Required behaviors: queue, circuitbreaker, retry, ratelimit
Monthly budget: $366

Stress scenarios

Baseline traffic

baseline

Steady ambient load with no failures.

Dependency outage

outage

A downstream component is disabled. System must degrade gracefully.

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: 79
Max drop rate: 8.8%
Min delivery rate: 87.5%
Max errors: 6

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-0347-dp4-personal \
  --provider openrouter --model google/gemini-2.0-flash-001 \
  --as alice

Or inspect the prompt first:

chini-bench prompt chini-train-train-0347-dp4-personal

Providers: openai · anthropic · google · openrouter · ollama

Leaderboard

Rank	Submitter	Model	Score	Stability	Delivery	Design	Pass
#1	rl_v07_pilot_a10b	rl_policy custom single-shot	84	66.0	68.0	100.0	✗
#2	rl_v07_pilot_a10b	rl_policy custom single-shot	83	64.0	66.0	100.0	✗
#3	rl_v07_pilot_a10b	rl_policy custom single-shot	76	55.0	42.0	100.0	✗
#4	rl_v07_full_a10	rl_policy custom single-shot	76	55.0	42.0	100.0	✗
#5	rl_v07_full_a10	rl_policy custom single-shot	76	56.0	43.0	100.0	✗
#6	rl_v07_full_a10	rl_policy custom single-shot	76	56.0	43.0	100.0	✗
#7	rl_v07_pilot_a10b	rl_policy custom single-shot	75	54.0	40.0	100.0	✗
#8	rl_v07_full_a10	rl_policy custom single-shot	75	54.0	41.0	100.0	✗
#9	chini-train-03	grok-4.1-fast single-shot	74	41.0	54.0	100.0	✗
#10	chini-train-04	grok-4.1-fast single-shot	74	41.0	54.0	100.0	✗

Per-scenario breakdown of the top run

Scenario	Health	Drop rate	Delivered	Pass
baseline	81.0	1.7%	29	✓
outage-1	71.0	2.8%	0	✗
spike-2	63.0	14.6%	1074	✗
adversarial-3	48.0	88.4%	96	✗

How is this scored? →