Discovery and router delegation
In plain words: Finding docs, scopes and workflows
How an agent finds where to look next: following router documents through scopes to owning docs, playbooks and registered workflows, then packaging what it found into a bounded task handoff.
- 1Routers give task triggers and links; following a workflow link does not start it, and finding a Pattern does not authorize it.
- 2Specialized routing models (e.g. TypeSafe Jev) are an idea to evaluate, not a chosen dependency; confidence is not accuracy.
- 3Discovery can never redirect an admitted Run or splice new steps into its frozen workflow version.
Words on this page, decoded click one for its card
Discovery answers where to look next: which scope holds the relevant owners, which workflow fits the operation, and which exact score can be considered for execution. Within Spellweaver, these routes help a coordinating Agent find the material needed to frame a bounded task.
In the inner instrument, Call gives this opening its address: relevant parts of the work become reachable. Blade judges which material can support the next act. A route can widen the question before a method narrows it.
This is one part of discernment within exploration: finding a source may reveal a better question, while a decisive distinction may redirect the search. Creation Inquiry carries that exchange through bounded probes, independent sufficiency review, and Crucible.
Documentation topology owns scope routing; Workflow owns PatternWorkflow selection and task handoff. This page follows those boundaries in use.
How routers fan out
A router helps a reader choose the next destination by giving task triggers and explicit links. Some links reach an owning document directly. Others open a scope tree whose router maintains its own specialized branches. The parent explains when to enter that tree without duplicating its contents, making the branch and its downstream links a discoverable subgraph of the map.
Each route makes its purpose and destination legible:
| Destination | What the route exposes | Next act |
|---|---|---|
| Scope or another router | Domain boundary, applicable triggers, and further routes | Follow the branch relevant to the task |
| Canonical owner | Architecture, vocabulary, operation, or delivery truth | Establish the governing contract and evidence |
| Workflow playbook | Procedure for the requested operation | Load it after the matching scope |
| Pattern or ScrollWorkflow Version | A named score and its exact revision | Check registration and admission through SpellweaverWorkflow Engine |
The available branches offer choices; the task determines which to read and in what order. Cross into another scope when the task crosses its boundary, leaving unrelated branches unloaded. Following a workflow link does not start the workflow. Finding a PatternWorkflow does not register it or authorize its casting.
Specialized models for routing
Specialized decision models are promising candidates for reducing routing latency and cost when repeated choices require semantic interpretation. For example, TypeSafe's Jev evaluates supplied state and typed questions; its Choice primitive returns a selected option, probabilities, and confidence without generating a prose answer. Such a model could propose a scope, registered PatternWorkflow, or declared graph branch, leaving deeper reasoning for unresolved questions. This is an optimization to evaluate, not a selected LychD dependency or a claim that the fastest router has been established.
Begin with explicit commands and reliable deterministic matches. Where intent remains unresolved, a model can choose among bounded destinations, including an explicit uncertain or unsupported outcome. Give it the relevant conversational context—a short confirmation may refer to substantial earlier work. Even a clear proposal must pass ordinary validation and admission. Ambiguity may call for clarification, a bounded probe, or deeper reasoning; no route proposal can rewrite an admitted ScrollWorkflow Version.
Keep probabilities distinct from confidence. Jev's
Choice confidence rescales the leading probability relative
to an even split across the options; confidence = 0.9 does not itself mean 90% observed routing
accuracy. Check calibration and abstention on representative held-out cases, then set thresholds
according to the consequences of a wrong route. Compare end-to-end latency and cost, including
context preparation, network time, validation, fallbacks, and recovery, against rules and existing
model options at comparable task success.
Placement remains a separate choice. Jev's documented hosted API is a remote disclosure boundary; a local routing model requires its own verified deployment option. Sensitivity flags may inform the Privacy Cut, but a remote router cannot receive private material merely to decide whether that material may leave. Routing scores grant neither capability use nor egress.
Follow a repository route
The repository already provides a concrete example:
- AGENTS.md routes a browser task to the Frontend scope.
- Frontend routes a component or reactivity task onward to the Svelte scope. It also exposes the backend scope when the change crosses the browser projection boundary.
- The selected scope leads to the canonical owner and the smallest source and test slice needed to establish behavior.
- If the task edits source, the root's workflow route exposes the editing playbook. That playbook routes onward to an applicable file-type card; Svelte-specific work continues through its scope's required workflow.
The root keeps Frontend discoverable; Frontend keeps its specialist routes discoverable; the editing index keeps its procedure cards discoverable. Their contents remain with their owners. When adding or moving a branch, maintain its parent link, task trigger, and destination together. A missing prerequisite calls for a targeted probe or bounded request for the missing input.
From discovery to a task handoff
Finding the relevant owners and procedure gives the coordinator enough ground to frame the task. Under the designed scoped context handoff, the chosen routes travel with the task, acceptance target, operator constraints, allowed inputs and effects, exact revisions, dependencies, and unresolved unknowns. The recipient can then continue discovery within that admitted boundary.
Opening another scope in the current conversation retains the material already loaded. A new Agent handoff requires its own ContextBriefing Pack assembly. The parent keeps the wider purpose and assesses the returned candidate and verification evidence; the bounded-task example follows that exchange.
Discovering an executable score
For execution, use Pattern lifecycle to inspect the registered exact revision and its activation policy. Admission pins the selected score; resume uses that stored choice. A discovery link cannot redirect an admitted RunJob Record or splice a newly found branch into its immutable ScrollWorkflow Version.
The current Loom browses the fixed PatternWorkflow registry. Scope routes and playbook links are repository navigation; they do not establish a runtime discovery service or executable subgraph composition. General parallel fan-out and joins retain the Graph design boundary, and scoped Agent handoff is not implemented by those repository routes.