Spellweaver

Through motion and silence, the thread remembers its course.

Once work has chosen a score, SpellweaverWorkflow EngineWorkflow Engine keeps it intact through execution, pause, return, and ending. It is LychD's singular logical workflow jurisdiction: it validates immutable ScrollsWorkflow VersionsWorkflow Versions and admits their casting. Code and existing paths retain the short name Weaver.

A PatternWorkflowWorkflow names the score's lineage; a ScrollWorkflow Version fixes one immutable revision. Within it, an Agent call, Gate, tool, effect, wait, or delegation may deserve an independently named SpellStepStep. A Scroll-local station places that SpellStep's exact contract, fixing the relationship before work begins.

Future packages may contribute SpellStep contracts and ScrollWorkflow Version declarations through separate Spellweaver-shaped stores. Executable implementations and adapters remain separate Extension or effect-owner registrations; publication and activation are not implied by contribution. The Core office retains workflow authority. SpellweaverWorkflow Engine never inherits the policy or physical control of the offices it sequences. ADR 28 owns the complete contract.

From Product to performance

A Composition or Suite publishes the score for its work. A ProductPackaged OfferPackaged Offer packages that choice; application records, judgment, and effects remain with their owners.

• Pattern is one named executable-score lineage published by its application owner: normally aan CompositionAppApp, or aan SuiteApp BundleApp Bundle for coordination only; one immutable revision is a ScrollWorkflow VersionWorkflow Version. The two delivered Core PatternsWorkflowsWorkflows are an explicit retained pre-Portfolio exception.
• Spell is one independently named semantic action contract; a station places it in that ScrollWorkflow Version.
• InvocationJob RequestJob Request opens one bounded Circle.
• Casting performs the exact ScrollWorkflow Version inside that InvocationJob Request.
• Run is the durable execution and ledger identity of that InvocationJob Request.

AAn SuiteApp Bundle CastingWorkflow ExecutionWorkflow Execution opens one parent coordination InvocationJob Request/RunJob RecordJob Record from its Suite-owned ScrollWorkflow Version and separate child CompositionApp InvocationsJob Requests/RunsJob Records. The parent owns correlation and aggregate settlement, never a member's records, judgment, consent, credentials, or effects.

Graph is the typed topology that advances ScrollWorkflow Version state among SpellStepStep placements. The Loom is a read-only projection of its declared truth. The current fixed registry has no independent SpellStep catalogue or teaching surface.

The current registry is fixed and source-defined:

bridge_chat@1 (default) / bridge_chat@2 (configured exact capability)
WeaveContext → Converse → AwaitConsent? → ProjectReply → End

bridge_chat@3 (configured public Archive and exact capability)
RecallNotes → AnswerNotes → SettleNoteAnswer → End

bridge_chat@4 (configured Scout and exact local capability)
PreparePageReview → AwaitPageConsent → AcquireAndAnswerPage → SettlePageAnswer → End

bridge_chat@5 (configured semantic generation and exact local capability)
RecallSemanticNotes → AnswerSemanticNotes → SettleSemanticAnswer → End

delegated_rite@1 (default) / delegated_rite@2 (configured exact runtime)
DispatchDelegate ⇢ ProjectDelegatedReply → End

Admission commits the chosen workflow name and exact manifest snapshot with the RunJob Record. That choice lasts: resume looks up the stored score and never routes the IntentRequestRequest again.

The registry is executable substrate, not a general workflow platform. delegated_rite@1 exercises only the deterministic reference adapter. Revision 2 pins an explicit registered runtime and profile for new admissions and retains that selection across resume. Neither revision supplies foreign-runtime containment or an execution plane.

Choose a Bridge capability

In the CodexSettings FolderSettings Folder's lychd.toml, select the registered BridgeChatChat revision and the exact capability key from your declared runtime inventory:

[weaver.bridge]
revision = "2"
capability_key = "my-runtime:chat:my-model"

Replace the example key with your runtime's key. It identifies the AnimatorModel RuntimeModel Runtime, capability family, and model together; a shared model name alone cannot pin a runtime. The selected capability must support chat and tools. Loading Settings validates the selector's shape without contacting an engine; DispatcherTraffic ControllerTraffic Controller checks the actual declaration, readiness, and policy at execution. An unknown, incompatible, or unavailable target refuses the turn rather than choosing another runtime.

After restart, this configuration selects revision 2 for new BridgeChat admissions. Each RunJob RecordJob Record records its choice before queue publication and keeps it through hardware retries and consent pauses. Later configuration changes or removal cannot redirect that RunJob Record or an idempotent retry. Without the section, new turns use revision 1's eligible-pool selection; both revisions remain registered for retained work. The key identifies a capability, not a model artifact or runtime configuration fingerprint. The general Resolution Lock is a separate contract.

Revision 3 adds bounded public-note recall with transient ContextBriefing PackBriefing Pack injection and no tools. Its Archive configuration and authority checks are separate from revision 2's tool-capable conversation.

Revision 4 adds one explicitly declared public page, native consent and transient local-model ContextBriefing Pack. Its Scout configuration selects a qualified static runtime and finite budgets. Neither profile turns a ScrollWorkflow VersionWorkflow Version or source-authored text into tool authority.

Revision 5 adds read-only answers from the independently enabled ArchiveLong-term MemoryLong-term Memory semantic generation, without tools or earlier conversation history. Its semantic generation configuration binds the exact generation, explicit threshold and finite recall bounds to one exact local Chat capability at boot. The selected RunJob Record retains that binding; opening the sources-only recall focus does not change the configured casting.

Prefer a ready route at admission

Revision 2 may instead rank exactly two declared local Chat routes:

[weaver.bridge]
revision = "2"

[weaver.bridge.preference]
schema_version = 1
routes = [
  { capability_key = "local-a:chat:model-a", weight = 9 },
  { capability_key = "local-b:chat:model-b", weight = 1 },
]

Replace both keys with literal identities from the declared inventory. Omit capability_key from [weaver.bridge] when using preference; revision 2 accepts exactly one of them. Both routes, including a disabled one, must declare local SoulstoneLocal ModelLocal Model Chat with tool support. Revisions 3, 4 and 5 retain their exact-key configuration and reject preference.

Weights are integer preferences from 0 through 1,000,000, with a positive total; they are not traffic percentages, measured quality, or additional authority. Zero disables eligibility and omits that route's retained phase and observation time. Admission directly refreshes each AnimatorModel RuntimeModel Runtime hosting an enabled route once, as a complete AnimatorModel Runtime batch, within one cooperative five-second bound. That batch may include a disabled capability sharing the same AnimatorModel Runtime. After the batch, only observed-warm routes with unchanged declarations and an unchanged, open admission generation remain eligible. Highest weight wins; an equal weight uses ascending literal capability key. This observes readiness without activating a model, preparing a grant or entering inference. Malformed or failed probes abort admission; a valid non-warm observation excludes that route. An empty eligible set returns a content-free 503 code before retaining a RunJob RecordJob Record or user turn.

The admission decision becomes part of the RunJob Record: complete policy, digest, dated observations, and one exact selected key. An idempotent replay returns it before any new probe, while changed configuration applies only to new admissions. Execution and restart keep the key under the existing BridgeChatChat tools, consent, and retry rules. The batch reserves no future readiness and provides no execution fallback, so later unavailability may still pause or refuse execution.

The selected RunJob Record's OrbRun InspectorRun Inspector inspector shows these retained observations and exclusions. They describe admission time, not current availability. Follow configured Bridge casting for the qualification boundary and Dispatcher law for the selection and execution distinction.

Follow the Scroll

Choose the route that matches the question:

• Discovery and router delegation follows scope branches, makes nested routes and workflows discoverable, and carries the selected routes into a bounded task handoff.
• Pattern lifecycle covers identity, manifests, admission, contribution, authorship protection, and revision continuity.
• Crucible covers two-round adversarial formation: declared biased Postures, independent first claims, attributed rebuttal, dissent-preserving synthesis, and the MagusYou, the OperatorYou, the Operator Gate.
• Creation applies bounded Inquiry at direction and construction scales, turns support and measure into bounded next steps, and follows local or delegated task handoffs through verification, documentation and authorized VCS effects.
• Ouroboros connects work, evaluation and training through correction, memory, Assimilation, Packaging and Evolution.
• Development bootstrap carries an operator-controlled coding campaign through evidence gates toward bounded native delegation and spare-capacity work. Coding-runtime research compares the dated provider roads behind that procedure.
• Scheduling and service classes covers foreground, deadline-windowed, and spare-capacity admission, schedule time law, overlap, and explicit misses.
• Stasis and return covers Live and Durable StasisPausePause, checkpoints, re-admission, terminal cleanup, and recovery limits.
• Execution roads covers the layered choice among native/local work, Portal-backed cognition, sovereign A2AAgent-to-Agent LineAgent-to-Agent Line tasks, delegated coding runtimes, and operator seats.
• Anonymization, taint, and egress covers the local Privacy CutPrivacy FilterPrivacy Filter, information-flow labels, PortalCloud ModelCloud Model admission, quarantined return, and the boundary that makes subsidized remote reasoning usable.
• Delegated agents covers the typed delegated station, AgentJob boundary, future CLI adapter acceptance, containment, and the present deterministic, no-network, effect-free reference adapter.

Creation and its interpretation

Transmutation in Divination examines the Sephiroth correspondence: the relations that give an idea form, symmetry and reconstruction, and life and the ending of forms. Creation and Ouroboros keep the practical procedures here in SpellweaverWorkflow EngineWorkflow Engine, with handoffs to evaluation and learning.

Progressive craft without a mutable score

A ScrollWorkflow VersionWorkflow Version may admit several explicit finish boundaries. A completed intermediate artifact can begin a new forward InvocationJob RequestJob Request; a terminal RunJob RecordJob Record is never reopened to continue it. Pattern lifecycle distinguishes new input from a changed score.

Model and engine choice stays in the receiver-owned Resolution Lock. A Comfy graph is an implementation preset, and a portable A2AAgent-to-Agent LineAgent-to-Agent Line ScrollWorkflow Version remains inert until admitted. Follow Composition Suites when the work needs live coordination across application owners.

Hand off a bounded task

A scoped context handoff gives another Agent a fresh ContextBriefing PackBriefing Pack for one bounded task while the coordinator keeps the wider purpose. For a repository change, the packet includes the requested result, relevant operator decisions, acceptance checks, allowed paths, source revision, dependencies, and scope routes to the owning documents and code. The recipient reads those owners without inheriting the conversation that produced the task.

If a needed decision is missing, the recipient requests that bounded input. It returns a candidate patch or findings with verification evidence and unresolved questions for the coordinator to assess. Merely loading another scope in the same conversation does not perform this handoff.

The present score

State of Work records local execution and the separate StasisPausePause, delegation, extension, and LoomWorkflow ViewerWorkflow Viewer delivery boundaries. Pattern contribution and durable publication, scheduling, durable parallelism, compatibility and migration, editing, authorship attestation, and protected-region admission remain undelivered.

Repository coding-agent choreography is separate: the tracked workflow playbooks own contributor procedure only, never SpellweaverWorkflow EngineWorkflow Engine or PatternWorkflowWorkflow law.