Skip to main content
trellis is the repository’s executable Dynamic Delegation v2 workflow: an experimental local workflow, not yet part of the default bunx smthrs init pack. It maps Sol/Fable authors, a Terra validator, and the Terra implementer chain (riding the component’s luna seat) into the <Trellis> component and declares the Smithers Trellis custom UI.
The explicit flag is required even at the default value: Trellis verifies its component cap matches the persisted run cap. To use another value, pass it as both workflow input and run option:

​
Inputs

The optional policy contains allowedCategories, normalized workspace-relative allowedPathPrefixes, and maxChangedLines (1..500): a trusted per-execution admission ceiling. Phase A does not claim measured diff or filesystem-sandbox enforcement. For example:

​
UI

Open the workflow UI to launch and inspect runs:
The launcher submits the selected concurrency as workflow input and run policy. The live surface shows the canonical final outcome, author fuel, accepted/rejected validation generations, the execution tree, node outputs, and durable events, discovering the semantic final node from trusted Trellis metadata rather than parsing hashed physical IDs. Controls default to the next launch, not the selected historical run’s configuration. Each run persists its pinned root concurrency, author-turn cap, generation/depth limits, and per-invocation allocated/remaining author fuel in trusted Trellis task metadata; the selected-run strip reads those fields from the selected run, even ones launched outside the UI. A root-local remaining value is one immutable allocation, not a mutable global counter; older runs missing these fields are labeled not persisted. The capability strip reports Phase A gaps: questions are unavailable, hierarchical token/USD budgets aren’t enforced, tool/filesystem authority depends on the configured agent adapter and sandbox, and prompt restrictions alone are advisory. Rejected IR is visible but never shown as executed. The launcher also omits a critical-execution policy, forcing implementation to Terra/Luna; policy-enabled runs can still launch via workflow input and be inspected in the UI.

​
Agent mapping

  • Sol: synthesis, orchestration, refinement, and exceptional critical work.
  • Fable: alternate root or nested author.
  • Terra: bounded planning, validation, synthesis, and substantial worker goals.
  • Luna: concrete research, POC, execution, review, or preview goals.
Sol/Fable may recursively author subworkflows. Terra/Luna can only complete or block their assigned goal. Every child result passes assignment-aware settlement before it reaches an author continuation.