What's Changed

• docs：chvm is the recommended way to install crewhaus by @StudioMaxIO in https://github.com/crewhaus/factory/pull/419 • chvm is at crewhaus/chvm, and covers Windows by @crewhaus in https://github.com/crewhaus/factory/pull/420 • chvm installs in one command now by @crewhaus in https://github.com/crewhaus/factory/pull/421 • fix(crew-orchestrator)：forward per-role model_pool/model_tiers/model_fallbacks to the role loop by @crewhaus in https://github.com/crewhaus/factory/pull/422 • feat(runtime-core)：budget substrate — gate every model call, pool-aware degrade, toolsInPlay union, streaming model latency by @crewhaus in https://github.com/crewhaus/factory/pull/423 • feat(trace)：role/stage/profile attribution on model events, model_stage + model_directive kinds, durable routing event-log kinds by @crewhaus in https://github.com/crewhaus/factory/pull/424 • feat(model-plan)：new @crewhaus/model-plan package, strongest sentinel, requiresModelFeatures, adapter effectiveParams by @crewhaus in https://github.com/crewhaus/factory/pull/425 • feat(eval-judge)：judge and compaction spend on the run bus, budget.judge_share, run-spanning workflow meter by @crewhaus in https://github.com/crewhaus/factory/pull/426 • feat(observability)：OTel model attributes and metrics, escalation/judge/floor alerts and SLO, session pin/models fields, sessions tail and export by @crewhaus in https://github.com/crewhaus/factory/pull/427 • feat(spec)：models: profile registry, $profile references, hybrid pool blocks, escalate, judge panels, per-node/sub-agent routing by @crewhaus in https://github.com/crewhaus/factory/pull/428 • feat(ir,compiler)：IrModelProfile, $profile resolution at every slot, modelPlanIntegrity pass, capability/sunset validation by @crewhaus in https://github.com/crewhaus/factory/pull/429 • feat(crew)：per-candidate profile enrichment on roles and crew.routing.model for the llm router by @crewhaus in https://github.com/crewhaus/factory/pull/431 • refactor(model-service)：wireModels composition root wrapping today's emitter routing fragments byte-identically by @crewhaus in https://github.com/crewhaus/factory/pull/430 • feat(tool-consult)：Consult + Escalate tools, TrustOrigin consult, narrowRuleSet, interpreter parity by @crewhaus in https://github.com/crewhaus/factory/pull/432 • feat(migration)：MIGRATION_1_TO_2 via SpecEdits, irreversible guard, comment-preserving upgrade and migrate-all, --hoist-models, per-release upgrade notes, pricing-feed sunsets by @crewhaus in https://github.com/crewhaus/factory/pull/433 • feat(runtime-core)：per-candidate plan table — request params, subset tool advertisement, dispatch gate, per-candidate permissions/rate-limits/tool_config, volatile overlay by @crewhaus in https://github.com/crewhaus/factory/pull/434 • feat(runtime-core)：preRoute decision phase — directives with session pin, rules, capability eligibility, classifier hook, budget hints, pre-model mutate by @crewhaus in https://github.com/crewhaus/factory/pull/435 • feat(model-service)：guide, shadow, and committee side-call closures with nested single-turn isolation by @crewhaus in https://github.com/crewhaus/factory/pull/437 • feat(sub-agents)：per-sub-agent routing, projectParentHandle, Task profile allowlist, inherit_routing, child spend re-published by @crewhaus in https://github.com/crewhaus/factory/pull/438 • feat(runtime-core)：cascade and draft-verify — runOneTurn force, evaluation.on_fail escalate, clean-prompt snapshot, deferred quality fold by @crewhaus in https://github.com/crewhaus/factory/pull/436 • feat(spec-patch)：wildcard segment, model_pool structural rule, the 0.6.0 OPTIMIZABLE_PATHS delta with fixtures, Hangar spec-edit tiers, lint/doctor checks by @crewhaus in https://github.com/crewhaus/factory/pull/439 • feat(model-router,routing-store)：RouteSignals + hint input, policy union, scoped arms with backoff, per-candidate chains, v2 lines, priors, floor, route freeze by @crewhaus in https://github.com/crewhaus/factory/pull/440 • feat(eval)：routed evals with pinned seed and ephemeral scoreboard, served-model attribution, per-arm baselines, eval leaderboard by @crewhaus in https://github.com/crewhaus/factory/pull/442 • feat(emitters)：compiled bundles wire model-service runtime closures — Consult/Escalate, classifier, guide/shadow/committee — when the IR declares them by @crewhaus in https://github.com/crewhaus/factory/pull/441 • feat(emitters)：hybrid closure wiring on pipeline, research, batch and browser — closing the §11.3 shortfall by @crewhaus in https://github.com/crewhaus/factory/pull/444 • feat(eval-grader)：graders.yaml per_model, judge usage by (judge, arm), calibration by pair, judge calibrate --by-model by @crewhaus in https://github.com/crewhaus/factory/pull/443 • feat(routing)：reward.quality_source, route promote --gate, routing_promotion audit, feed-routing per stage by @crewhaus in https://github.com/crewhaus/factory/pull/445 • feat(hangar)：models tab and routes, per-role/profile cost aggregation, gutter kinds, advisor items and jobs, SECURITY_SURFACES by @crewhaus in https://github.com/crewhaus/factory/pull/446 • feat(cli)：models list|explain|audit|propose, route explain --json/status --by/propose, enumerateModelSlots, advise rules, routed from-advice, routing-aware canary, flywheel template, init --hybrid by @crewhaus in https://github.com/crewhaus/factory/pull/447 • feat(eval-judge)：wire the in-loop judge panel — judges/repeats/temperature/target at every judge site, and profile params on aux model slots by @crewhaus in https://github.com/crewhaus/factory/pull/448 • fix(compiler)：a profile's narrowing fields on a single-model slot are by design, not a pending row by @crewhaus in https://github.com/crewhaus/factory/pull/449 • chore(release)：crewhaus 0.6.0 by @crewhaus in https://github.com/crewhaus/factory/pull/450 • docs(agents)：AGENTS.md's routing pointer matched the shipped hybrid wiring by @crewhaus in https://github.com/crewhaus/factory/pull/451

Full Changelog：https://github.com/crewhaus/factory/compare/v0.5.8...v0.6.0