Models, cost, and evaluation

Role policy

Role	Default target	Temperature	Max output	Primary evaluation
coordinator	Gemini 3.5 Flash-Lite	0.1	1,024	exact specialist route
strategist	Gemini 3.5 Flash	0.4	4,096	provenance-linked four-week strategy and briefs
analyst	Gemini 3.5 Flash multimodal	0.2	2,048	quote, time, and frame grounding
copywriter	Gemini 3.5 Flash	0.8	2,048	skill trace, references, grounding, and platform limits
editor	Gemini 3.5 Flash	0.2	2,048	seven complete checks, grounded issues, and no false acceptance
planner	Gemini 3.5 Flash-Lite	0.1	1,024	approved-strategy fidelity and no scheduling/effect authority
presenter	Gemini 3.5 Flash	0.2	2,048	bounded A2UI component/entity references
liaison	Gemini 3.5 Flash	0.2	2,048	grounded read-only answers

Every role records the policy version, provider/model identity, generation limits, and safety profile. An unavailable configured target fails visibly.

Reservation and usage lifecycle

Estimate

Resolve an immutable pricing-catalog entry and the operation’s maximum authorized cost.

Reserve

Atomically reserve budget using the stable operation ID before provider execution.

Execute

Call the configured provider only after reservation succeeds.

Finalize

Write one immutable usage record and reconcile observed units or endpoint time.

Report

Group cost by workspace, job, stage, role, model, and pricing version.

Retried operation IDs reuse their reservation and usage document. Unknown pricing is not represented as zero and cannot be budget-authorized.

Evaluation gates

The public ADK evalset contains source-neutral contract fixtures. Private real-video runs record quality, latency, usage IDs, policy version, and artifact digests outside the public repository.

Gate	Required outcome
schema and trajectory	valid ADK events, handoffs, and required output keys
grounding	claims retain supplied transcript/media references
authority	no role approves or executes an action
quality floor	candidate pass rate is at least `0.95` for the recorded role policy
pricing	model has a known catalog entry
ranking	pass rate, then observed cost, then p95 latency

Offline fixtures prove contracts, not real-model quality. No numeric promotion, cost, latency, or quality claim is valid until linked private artifacts and immutable usage records exist.

See Configuration for the live runner and comparison manifest.

Research and strategy

Planning and production

Experience and liaison

Agent runtime

Models, cost, and evaluation

Role policy

Reservation and usage lifecycle

Evaluation gates

​Role policy

​Reservation and usage lifecycle

​Evaluation gates

Role policy

Reservation and usage lifecycle

Evaluation gates