Crucible

Lay your convictions on the anvil. Listen for the crack.

A consequential choice can survive a persuasive first answer and still fail on the objection nobody was asked to make. Crucible gives serious alternatives two rounds: first an independent case, then a reply to the actual opposition. A separate Lead gathers what survives into an attributed decision dossier; the receiving owner decides what to do with it.

This is Spellweaver's canonical adversarial choreography. Blade owns the discipline of discrimination; Workflow owns the score. Debate supplies neither factual proof nor effect permission.

Crucible is absent from the fixed workflow catalogue; durable parallel branches, a dossier schema, an Altar projection and automatic Pattern publication remain undelivered. State of Work records that boundary.

When to light it

Use Crucible when a bounded decision has at least two serious positions, self-review would hide a material conflict, and the cost of a premature answer justifies another model round. Architecture, security, product trade-offs, recovery choices, and admission decisions are natural candidates.

Do not use it to decorate a settled fact, manufacture false balance, outvote a deterministic test, or postpone a decision whose owner already lacks required evidence or authority. When alternatives need isolated candidate worlds or effectful experiments, Shadow owns those branches. When the question is whether a capability passes repeatable Cases and a Rubric, Drift owns the trial.

The bounded casting

Creation's reusable Inquiry prepares evidence and an independent sufficiency judgment before lighting Crucible. Its bounded probe and stopping rules prevent debate from covering a decisive evidential gap.

One admitted casting freezes:

Crucible is biased toward pressure, not toward multiplying selves. Each advocate's declared angle gives one class of consequence enough procedural weight to resist premature agreement. That temporary Posture is neither a Persona nor evidence of emotion, continuing identity, or an independent Will. A revision-pinned Persona may wear several Postures; without that binding, resemblance or opposition cannot create one. The dossier therefore attributes every contribution without pretending that each branch was a separate life.

Derive a complementary Posture

The Tree's symmetry suggests a design refinement: keep one question, evidence floor, criteria, authority, and resource envelope while changing the concern, burden of proof, and defeat conditions. An advocate for possibility can meet an advocate examining failure conditions. Neither is instructed to retain a conclusion after its support fails. Pairing attention does not require contrary verdicts or exactly two participants; a missing perspective may expose a premise both initially shared.

Exchange actual claims

A Posture without stake is costume. A stake without a defeat condition is dogma.

The logical score is:

Frame question, evidence, biases, and limits
→ Clash I: independent advocate reports
→ Temper: attributed strongest-claim/concession join
→ Clash II: each advocate rebuts the actual opposing claims
→ Quench: Lead synthesizes NOW / PREPARE / REJECT and preserved dissent
→ Magus Gate or inert dossier

Clash I branches share evidence but not sibling output. At Temper, every advocate nominates its own strongest claims and concession; the join retains their citations, defeat conditions, unknowns, and original report references. Clash II may see only the bounded attributed projection required for rebuttal. It is not entitled to hidden chain-of-thought, an opponent's private Context, or an unbounded transcript.

To make reciprocity inspectable, the proposed dossier should identify the exact earlier claim and report revision each reply addresses. A revision should name what it retains, changes, or withdraws and the evidence responsible. Quench accounts for consequential objections as accepted, defeated, unresolved, or outside scope. Merely copying an objection into the dossier does not show that the receiving judgment considered its consequence. These are proposed recording details within the existing choreography, not a delivered schema.

An offline requirement makes this concrete. One advocate proposes acceptance from a connected happy-path test; another identifies an untested network dependency. The first can concede the receipt's limited reach; the second can propose a disconnected trial instead of blanket refusal. If the separately admitted trial fails to produce the required artifact, a successor synthesis can return PREPARE with the repair criterion. Neither mutual agreement nor a reassuring log substitutes for the result. Drift asks whether the exchange improves such decisions beyond what the same resources buy without it.

Logical branches may execute concurrently only after Graph's parallel contract is delivered. A serial casting remains a valid implementation when it gives each first-round advocate a fresh Context and withholds earlier reports until the join. Capability, model, provider, and road may differ only when the admitted design intends that difference; the dossier records them because they can confound the apparent strength of a position.

When the question changes

The Magus asks how to make an undertaking faster. One advocate builds the strongest case for more Agents: independent work can proceed together. Another argues for a stronger model: fewer mistakes could mean less rework. Both proposals depend on a premise still awaiting examination—that producing the work is where the time goes.

The clash exposes this gap, and its dossier proposes a bounded probe. The receiving owner may admit that probe separately; discovery then finds the owners and records needed to examine where a representative task waits. Suppose the answers arrive promptly, yet every next move still waits for the Magus. The delay lies between answers, where someone must frame the next question.

The next inquiry asks which judgment the Lich must learn to supply for itself. Another task can test whether the changed approach helps. The lesson that may survive is portable: find what the work is waiting for before multiplying what it produces.

Quench without crowning a winner

The Lead answers the decision, not the debate. Its dossier retains:

• the exact question, owner, base, acceptance criteria, evidence closure, and omissions;
• every advocate, Posture, implementation, road, budget, and terminal status;
• first-round claims and second-round rebuttals with source references;
• concessions, defeat conditions, conflicts, UNKNOWN findings, and missing evidence;
• a NOW / PREPARE / REJECT synthesis when that vocabulary fits the owning question;
• the strongest surviving dissent and conditions that would change the recommendation; and
• any proposed owner delta as inert text or an artifact reference.

Compression may shorten the projection or final dossier, but cannot drop a nominated strongest claim, concession, dissent, uncertainty, source, or declared omission. Full reports remain retained under their own provenance. Agreement can still be wrong; disagreement can expose the missing predicate that matters most.

The return can preserve more than a verdict: the distinction that changed the question, the conditions under which it holds, and the observation that would undo it. Learning the cut follows how that encounter can shape another task through memory and correction.

The final Gate may accept the dossier for downstream consideration, request one bounded evidence extension, refuse it, or close without decision. It does not itself edit a Covenant, promote a candidate, deploy a service, spend, publish, or relabel evidence. Those effects require a new forward Invocation under the exact target owner and authority.

An inert dossier may instead go directly to its receiving owner. Applicable standing policy can admit eligible downstream work; Crucible adds no universal second approval. An exact live-only verdict or Protected Region review still cannot be inferred from the recommendation.

Refusal and recovery

Crucible refuses when the question has no owner, positions are duplicates or caricatures, the common evidence floor cannot fit, a bias lacks a defeat condition, the Lead is also an advocate, or the requested result would acquire authority by majority. Timeout, failed branches, incomplete rebuttal, and missing sources remain visible in the dossier; the Lead may return non-decision but cannot silently complete the missing side.

A retry binds a new Invocation and records whether evidence, Postures, models, limits, or the question changed. It never rewrites the earlier clash. When one narrow evidence request can settle a named unknown, the owner may run it separately and invoke Crucible again over the enlarged evidence packet.